maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/lldb/source/Core/Debugger.cpp

2381 lines
94 KiB
C++
Raw Normal View History

Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
//===-- Debugger.cpp --------------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
Committing type format code for Enrico Granata. This commit adds a new top level command named "type". Currently this command implements three commands: type format add <format> <typename1> [<typename2> ...] type format delete <typename1> [<typename2> ...] type format list [<typename1> [<typename2>] ...] This allows you to specify the default format that will be used to display types when you use "frame variable" or "expression", or the SBValue classes. Examples: // Format uint*_t as hex type format add x uint16_t uint32_t uint64_t // Format intptr_t as a pointer type format add p intptr_t The format characters are the same as "printf" for the most part with many additions. These format character specifiers are also used in many other commands ("frame variable" for one). The current list of format characters include: a - char buffer b - binary B - boolean c - char C - printable char d - signed decimal e - float f - float g - float i - signed decimal I - complex integer o - octal O - OSType p - pointer s - c-string u - unsigned decimal x - hex X - complex float y - bytes Y - bytes with ASCII llvm-svn: 133728
2011-06-24 01:59:56 +08:00
#include "lldb/Core/Debugger.h"
#include <map>
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
#include "clang/AST/DeclCXX.h"
#include "clang/AST/Type.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/lldb-private.h"
#include "lldb/Core/ConnectionFileDescriptor.h"
Committing type format code for Enrico Granata. This commit adds a new top level command named "type". Currently this command implements three commands: type format add <format> <typename1> [<typename2> ...] type format delete <typename1> [<typename2> ...] type format list [<typename1> [<typename2>] ...] This allows you to specify the default format that will be used to display types when you use "frame variable" or "expression", or the SBValue classes. Examples: // Format uint*_t as hex type format add x uint16_t uint32_t uint64_t // Format intptr_t as a pointer type format add p intptr_t The format characters are the same as "printf" for the most part with many additions. These format character specifiers are also used in many other commands ("frame variable" for one). The current list of format characters include: a - char buffer b - binary B - boolean c - char C - printable char d - signed decimal e - float f - float g - float i - signed decimal I - complex integer o - octal O - OSType p - pointer s - c-string u - unsigned decimal x - hex X - complex float y - bytes Y - bytes with ASCII llvm-svn: 133728
2011-06-24 01:59:56 +08:00
#include "lldb/Core/FormatManager.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Core/InputReader.h"
While implementing unwind information using UnwindAssemblyInstEmulation I ran into some cleanup I have been wanting to do when reading/writing registers. Previously all RegisterContext subclasses would need to implement: virtual bool ReadRegisterBytes (uint32_t reg, DataExtractor &data); virtual bool WriteRegisterBytes (uint32_t reg, DataExtractor &data, uint32_t data_offset = 0); There is now a new class specifically designed to hold register values: lldb_private::RegisterValue The new register context calls that subclasses must implement are: virtual bool ReadRegister (const RegisterInfo *reg_info, RegisterValue &reg_value) = 0; virtual bool WriteRegister (const RegisterInfo *reg_info, const RegisterValue &reg_value) = 0; The RegisterValue class must be big enough to handle any register value. The class contains an enumeration for the value type, and then a union for the data value. Any integer/float values are stored directly in an appropriate host integer/float. Anything bigger is stored in a byte buffer that has a length and byte order. The RegisterValue class also knows how to copy register value bytes into in a buffer with a specified byte order which can be used to write the register value down into memory, and this does the right thing when not all bytes from the register values are needed (getting a uint8 from a uint32 register value..). All RegiterContext and other sources have been switched over to using the new regiter value class. llvm-svn: 131096
2011-05-10 04:18:18 +08:00
#include "lldb/Core/RegisterValue.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Core/State.h"
Added Debugger::GetAsync{Output/Error}Stream, and use it to print parse errors when we go to run a breakpoint condition. llvm-svn: 132517
2011-06-03 07:58:26 +08:00
#include "lldb/Core/StreamAsynchronousIO.h"
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
#include "lldb/Core/StreamString.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Core/Timer.h"
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
#include "lldb/Core/ValueObject.h"
Abtract terminal stuff into a new lldb_private::Terminal class where the implementation is hidden in the host layer. This avoids a slew of "#if LLDB_CONFIG_TERMIOS_SUPPORTED" statements in the code and keeps things cleaner. llvm-svn: 125057
2011-02-08 07:24:47 +08:00
#include "lldb/Host/Terminal.h"
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
#include "lldb/Interpreter/CommandInterpreter.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Target/TargetList.h"
#include "lldb/Target/Process.h"
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
#include "lldb/Target/RegisterContext.h"
#include "lldb/Target/StopInfo.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Target/Thread.h"
using namespace lldb;
using namespace lldb_private;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
static uint32_t g_shared_debugger_refcount = 0;
Add a unique ID to each debugger instance. Add functions to look up debugger by id Add global variable to lldb python module, to hold debugger id Modify embedded Python interpreter to update the global variable with the id of its current debugger. Modify the char ** typemap definition in lldb.swig to accept 'None' (for NULL) as a valid value. The point of all this is so that, when you drop into the embedded interpreter from the command interpreter (or when doing Python-based breakpoint commands), there is a way for the Python side to find/get the correct debugger instance ( by checking debugger_unique_id, then calling SBDebugger::FindDebuggerWithID on it). llvm-svn: 107287
2010-07-01 00:22:25 +08:00
static lldb::user_id_t g_unique_id = 1;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
#pragma mark Static Functions
static Mutex &
GetDebuggerListMutex ()
{
static Mutex g_mutex(Mutex::eMutexTypeRecursive);
return g_mutex;
}
typedef std::vector<DebuggerSP> DebuggerList;
static DebuggerList &
GetDebuggerList()
{
// hide the static debugger list inside a singleton accessor to avoid
// global init contructors
static DebuggerList g_list;
return g_list;
}
#pragma mark Debugger
Cleaned up code that wasn't using the Initialize and Terminate paradigm by changing it to use it. There was an extra parameter added to the static accessor global user settings controllers that wasn't needed. A bool was being used as a parameter to the accessor just so it could be used to clean up the global user settings controller which is now fixed by splitting up the initialization into the "static void Class::Initialize()", access into the "static UserSettingsControllerSP & Class::GetSettingsController()", and cleanup into "static void Class::Terminate()". Also added initialize and terminate calls to the logging code to avoid issues when LLDB is shutting down. There were cases after the logging was switched over to use shared pointers where we could crash if the global destructor chain was being run and it causes the log to be destroyed and any any logging occurred. llvm-svn: 119757
2010-11-19 07:32:35 +08:00
UserSettingsControllerSP &
Debugger::GetSettingsController ()
{
static UserSettingsControllerSP g_settings_controller;
return g_settings_controller;
}
Split up the Python script interpreter code to allow multiple script interpreter objects to exist within the same process (one script interpreter object per debugger object). The python script interpreter objects are all using the same global Python script interpreter; they use separate dictionaries to keep their data separate, and mutex's to prevent any object attempting to use the global Python interpreter when another object is already using it. llvm-svn: 123415
2011-01-14 08:29:16 +08:00
int
Debugger::TestDebuggerRefCount ()
{
return g_shared_debugger_refcount;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
void
Debugger::Initialize ()
{
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
if (g_shared_debugger_refcount == 0)
Cleaned up code that wasn't using the Initialize and Terminate paradigm by changing it to use it. There was an extra parameter added to the static accessor global user settings controllers that wasn't needed. A bool was being used as a parameter to the accessor just so it could be used to clean up the global user settings controller which is now fixed by splitting up the initialization into the "static void Class::Initialize()", access into the "static UserSettingsControllerSP & Class::GetSettingsController()", and cleanup into "static void Class::Terminate()". Also added initialize and terminate calls to the logging code to avoid issues when LLDB is shutting down. There were cases after the logging was switched over to use shared pointers where we could crash if the global destructor chain was being run and it causes the log to be destroyed and any any logging occurred. llvm-svn: 119757
2010-11-19 07:32:35 +08:00
{
Fixed an issue where the UserSettingsControllers were being created out of order and this was causing the target, process and thread trees to not be available. llvm-svn: 119784
2010-11-19 11:46:01 +08:00
lldb_private::Initialize();
Cleaned up code that wasn't using the Initialize and Terminate paradigm by changing it to use it. There was an extra parameter added to the static accessor global user settings controllers that wasn't needed. A bool was being used as a parameter to the accessor just so it could be used to clean up the global user settings controller which is now fixed by splitting up the initialization into the "static void Class::Initialize()", access into the "static UserSettingsControllerSP & Class::GetSettingsController()", and cleanup into "static void Class::Terminate()". Also added initialize and terminate calls to the logging code to avoid issues when LLDB is shutting down. There were cases after the logging was switched over to use shared pointers where we could crash if the global destructor chain was being run and it causes the log to be destroyed and any any logging occurred. llvm-svn: 119757
2010-11-19 07:32:35 +08:00
}
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
g_shared_debugger_refcount++;
Cleaned up code that wasn't using the Initialize and Terminate paradigm by changing it to use it. There was an extra parameter added to the static accessor global user settings controllers that wasn't needed. A bool was being used as a parameter to the accessor just so it could be used to clean up the global user settings controller which is now fixed by splitting up the initialization into the "static void Class::Initialize()", access into the "static UserSettingsControllerSP & Class::GetSettingsController()", and cleanup into "static void Class::Terminate()". Also added initialize and terminate calls to the logging code to avoid issues when LLDB is shutting down. There were cases after the logging was switched over to use shared pointers where we could crash if the global destructor chain was being run and it causes the log to be destroyed and any any logging occurred. llvm-svn: 119757
2010-11-19 07:32:35 +08:00
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
Debugger::Terminate ()
{
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
if (g_shared_debugger_refcount > 0)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
g_shared_debugger_refcount--;
if (g_shared_debugger_refcount == 0)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Fixed an issue where the UserSettingsControllers were being created out of order and this was causing the target, process and thread trees to not be available. llvm-svn: 119784
2010-11-19 11:46:01 +08:00
lldb_private::WillTerminate();
lldb_private::Terminate();
Replace Mutex guarding python interpreter access with Predicate, allowing timeouts & informing the user when the lock is unavailable. Fixed problem where Debugger::Terminate was clearing the debugger list even when the global ref count was greater than zero. llvm-svn: 123674
2011-01-18 05:55:19 +08:00
// Clear our master list of debugger objects
Mutex::Locker locker (GetDebuggerListMutex ());
GetDebuggerList().clear();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
}
}
The UserSettings controllers must be initialized & terminated in the correct order. Previously this was tacitly implemented but not enforced, so it was possible to accidentally do things in the wrong order and cause problems. This fixes that problem. llvm-svn: 127430
2011-03-11 06:14:10 +08:00
void
Debugger::SettingsInitialize ()
{
static bool g_initialized = false;
if (!g_initialized)
{
g_initialized = true;
UserSettingsControllerSP &usc = GetSettingsController();
usc.reset (new SettingsController);
UserSettingsController::InitializeSettingsController (usc,
SettingsController::global_settings_table,
SettingsController::instance_settings_table);
// Now call SettingsInitialize for each settings 'child' of Debugger
Target::SettingsInitialize ();
}
}
void
Debugger::SettingsTerminate ()
{
// Must call SettingsTerminate() for each settings 'child' of Debugger, before terminating the Debugger's
// Settings.
Target::SettingsTerminate ();
// Now terminate the Debugger Settings.
UserSettingsControllerSP &usc = GetSettingsController();
UserSettingsController::FinalizeSettingsController (usc);
usc.reset();
}
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
DebuggerSP
Debugger::CreateInstance ()
{
DebuggerSP debugger_sp (new Debugger);
// Scope for locker
{
Mutex::Locker locker (GetDebuggerListMutex ());
GetDebuggerList().push_back(debugger_sp);
}
return debugger_sp;
}
Add API and implementation for SBDebugger::Destroy and Debugger::Destroy. llvm-svn: 124011
2011-01-22 09:02:07 +08:00
void
Debugger::Destroy (lldb::DebuggerSP &debugger_sp)
{
if (debugger_sp.get() == NULL)
return;
Mutex::Locker locker (GetDebuggerListMutex ());
DebuggerList &debugger_list = GetDebuggerList ();
DebuggerList::iterator pos, end = debugger_list.end();
for (pos = debugger_list.begin (); pos != end; ++pos)
{
if ((*pos).get() == debugger_sp.get())
{
debugger_list.erase (pos);
return;
}
}
}
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
lldb::DebuggerSP
Debugger::GetSP ()
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
lldb::DebuggerSP debugger_sp;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
Mutex::Locker locker (GetDebuggerListMutex ());
DebuggerList &debugger_list = GetDebuggerList();
DebuggerList::iterator pos, end = debugger_list.end();
for (pos = debugger_list.begin(); pos != end; ++pos)
{
if ((*pos).get() == this)
{
debugger_sp = *pos;
break;
}
}
return debugger_sp;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
lldb::DebuggerSP
Debugger::FindDebuggerWithInstanceName (const ConstString &instance_name)
{
lldb::DebuggerSP debugger_sp;
Mutex::Locker locker (GetDebuggerListMutex ());
DebuggerList &debugger_list = GetDebuggerList();
DebuggerList::iterator pos, end = debugger_list.end();
for (pos = debugger_list.begin(); pos != end; ++pos)
{
if ((*pos).get()->m_instance_name == instance_name)
{
debugger_sp = *pos;
break;
}
}
return debugger_sp;
}
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
TargetSP
Debugger::FindTargetWithProcessID (lldb::pid_t pid)
{
lldb::TargetSP target_sp;
Mutex::Locker locker (GetDebuggerListMutex ());
DebuggerList &debugger_list = GetDebuggerList();
DebuggerList::iterator pos, end = debugger_list.end();
for (pos = debugger_list.begin(); pos != end; ++pos)
{
target_sp = (*pos)->GetTargetList().FindTargetWithProcessID (pid);
if (target_sp)
break;
}
return target_sp;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Debugger::Debugger () :
Add a unique ID to each debugger instance. Add functions to look up debugger by id Add global variable to lldb python module, to hold debugger id Modify embedded Python interpreter to update the global variable with the id of its current debugger. Modify the char ** typemap definition in lldb.swig to accept 'None' (for NULL) as a valid value. The point of all this is so that, when you drop into the embedded interpreter from the command interpreter (or when doing Python-based breakpoint commands), there is a way for the Python side to find/get the correct debugger instance ( by checking debugger_unique_id, then calling SBDebugger::FindDebuggerWithID on it). llvm-svn: 107287
2010-07-01 00:22:25 +08:00
UserID (g_unique_id++),
Fixed an issue where the UserSettingsControllers were being created out of order and this was causing the target, process and thread trees to not be available. llvm-svn: 119784
2010-11-19 11:46:01 +08:00
DebuggerInstanceSettings (*GetSettingsController()),
More reverting of the EOF stuff as the API was changed which we don't want to do. Closing on EOF is an option that can be set on the lldb_private::Communication or the lldb::SBCommunication objects after they are created. Of course the EOF support isn't hooked up, so they don't do anything at the moment, but they are left in so when the code is fixed, it will be easy to get working again. llvm-svn: 120885
2010-12-04 10:39:47 +08:00
m_input_comm("debugger.input"),
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
m_input_file (),
m_output_file (),
m_error_file (),
m_target_list (),
Added more platform support. There are now some new commands: platform status -- gets status information for the selected platform platform create <platform-name> -- creates a new instance of a remote platform platform list -- list all available platforms platform select -- select a platform instance as the current platform (not working yet) When using "platform create" it will create a remote platform and make it the selected platform. For instances for iPhone OS debugging on Mac OS X one can do: (lldb) platform create remote-ios --sdk-version=4.0 Remote platform: iOS platform SDK version: 4.0 SDK path: "/Developer/Platforms/iPhoneOS.platform/DeviceSupport/4.0" Not connected to a remote device. (lldb) file ~/Documents/a.out Current executable set to '~/Documents/a.out' (armv6). (lldb) image list [ 0] /Volumes/work/gclayton/Documents/devb/attach/a.out [ 1] /Developer/Platforms/iPhoneOS.platform/DeviceSupport/4.0/Symbols/usr/lib/dyld [ 2] /Developer/Platforms/iPhoneOS.platform/DeviceSupport/4.0/Symbols/usr/lib/libSystem.B.dylib Note that this is all happening prior to running _or_ connecting to a remote platform. Once connected to a remote platform the OS version might change which means we will need to update our dependecies. Also once we run, we will need to match up the actualy binaries with the actualy UUID's to files in the SDK, or download and cache them locally. This is just the start of the remote platforms, but this modification is the first iteration in getting the platforms really doing something. llvm-svn: 127934
2011-03-19 09:12:21 +08:00
m_platform_list (),
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
m_listener ("lldb.Debugger"),
m_source_manager (),
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
m_command_interpreter_ap (new CommandInterpreter (*this, eScriptLanguageDefault, false)),
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
m_input_reader_stack (),
Cleaned up a unused member variable in Debugger. Added the start of Host specific launch services, though it currently isn't hookup up to anything. We want to be able to launch a process and use the native launch services to launch an app like it would be launched by the user double clicking on the app. We also eventually want to be able to run a command line app in a newly spawned terminal to avoid terminal sharing. Fixed an issue with the new DWARF forward type declaration stuff. A crasher was found that was happening when trying to properly expand the forward declarations. llvm-svn: 115213
2010-10-01 05:49:03 +08:00
m_input_reader_data ()
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
m_command_interpreter_ap->Initialize ();
Added more platform support. There are now some new commands: platform status -- gets status information for the selected platform platform create <platform-name> -- creates a new instance of a remote platform platform list -- list all available platforms platform select -- select a platform instance as the current platform (not working yet) When using "platform create" it will create a remote platform and make it the selected platform. For instances for iPhone OS debugging on Mac OS X one can do: (lldb) platform create remote-ios --sdk-version=4.0 Remote platform: iOS platform SDK version: 4.0 SDK path: "/Developer/Platforms/iPhoneOS.platform/DeviceSupport/4.0" Not connected to a remote device. (lldb) file ~/Documents/a.out Current executable set to '~/Documents/a.out' (armv6). (lldb) image list [ 0] /Volumes/work/gclayton/Documents/devb/attach/a.out [ 1] /Developer/Platforms/iPhoneOS.platform/DeviceSupport/4.0/Symbols/usr/lib/dyld [ 2] /Developer/Platforms/iPhoneOS.platform/DeviceSupport/4.0/Symbols/usr/lib/libSystem.B.dylib Note that this is all happening prior to running _or_ connecting to a remote platform. Once connected to a remote platform the OS version might change which means we will need to update our dependecies. Also once we run, we will need to match up the actualy binaries with the actualy UUID's to files in the SDK, or download and cache them locally. This is just the start of the remote platforms, but this modification is the first iteration in getting the platforms really doing something. llvm-svn: 127934
2011-03-19 09:12:21 +08:00
// Always add our default platform to the platform list
PlatformSP default_platform_sp (Platform::GetDefaultPlatform());
assert (default_platform_sp.get());
m_platform_list.Append (default_platform_sp, true);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Debugger::~Debugger ()
{
Add code to make sure InputReaders finish and are cleaned up when a Debugger object is destroyed or re-set. (Thus making sure that, for example, the Python interpreter finishes and exits cleanly rather than being left in an undefined state.) llvm-svn: 122255
2010-12-21 02:35:50 +08:00
CleanUpInputReaders();
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
int num_targets = m_target_list.GetNumTargets();
for (int i = 0; i < num_targets; i++)
{
ProcessSP process_sp (m_target_list.GetTargetAtIndex (i)->GetProcessSP());
if (process_sp)
process_sp->Destroy();
}
DisconnectInput();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Don't have the debugger default to ignoring EOF. This is only what the driver (or anything running in a terminal) wants. Not what a UI (Xcode) would want where it creates a debugger per debug window. The current code had an infinite loop after a debug session ended. llvm-svn: 132280
2011-05-29 12:06:55 +08:00
bool
Debugger::GetCloseInputOnEOF () const
{
return m_input_comm.GetCloseOnEOF();
}
void
Debugger::SetCloseInputOnEOF (bool b)
{
m_input_comm.SetCloseOnEOF(b);
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
bool
Debugger::GetAsyncExecution ()
{
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
return !m_command_interpreter_ap->GetSynchronous();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
Debugger::SetAsyncExecution (bool async_execution)
{
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
m_command_interpreter_ap->SetSynchronous (!async_execution);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
Debugger::SetInputFileHandle (FILE *fh, bool tranfer_ownership)
{
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
File &in_file = GetInputFile();
in_file.SetStream (fh, tranfer_ownership);
if (in_file.IsValid() == false)
in_file.SetStream (stdin, true);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
// Disconnect from any old connection if we had one
m_input_comm.Disconnect ();
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
m_input_comm.SetConnection (new ConnectionFileDescriptor (in_file.GetDescriptor(), true));
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
m_input_comm.SetReadThreadBytesReceivedCallback (Debugger::DispatchInputCallback, this);
Error error;
if (m_input_comm.StartReadThread (&error) == false)
{
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
File &err_file = GetErrorFile();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
err_file.Printf ("error: failed to main input read thread: %s", error.AsCString() ? error.AsCString() : "unkown error");
exit(1);
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
Debugger::SetOutputFileHandle (FILE *fh, bool tranfer_ownership)
{
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
File &out_file = GetOutputFile();
out_file.SetStream (fh, tranfer_ownership);
if (out_file.IsValid() == false)
out_file.SetStream (stdout, false);
Split up the Python script interpreter code to allow multiple script interpreter objects to exist within the same process (one script interpreter object per debugger object). The python script interpreter objects are all using the same global Python script interpreter; they use separate dictionaries to keep their data separate, and mutex's to prevent any object attempting to use the global Python interpreter when another object is already using it. llvm-svn: 123415
2011-01-14 08:29:16 +08:00
GetCommandInterpreter().GetScriptInterpreter()->ResetOutputFileHandle (fh);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
Debugger::SetErrorFileHandle (FILE *fh, bool tranfer_ownership)
{
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
File &err_file = GetErrorFile();
err_file.SetStream (fh, tranfer_ownership);
if (err_file.IsValid() == false)
err_file.SetStream (stderr, false);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
ExecutionContext
Change "Current" as in GetCurrentThread, GetCurrentStackFrame, etc, to "Selected" i.e. GetSelectedThread. Selected makes more sense, since these are set by some user action (a selection). I didn't change "CurrentProcess" since this is always controlled by the target, and a given target can only have one process, so it really can't be selected. llvm-svn: 112221
2010-08-27 05:32:51 +08:00
Debugger::GetSelectedExecutionContext ()
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
ExecutionContext exe_ctx;
exe_ctx.Clear();
Change "Current" as in GetCurrentThread, GetCurrentStackFrame, etc, to "Selected" i.e. GetSelectedThread. Selected makes more sense, since these are set by some user action (a selection). I didn't change "CurrentProcess" since this is always controlled by the target, and a given target can only have one process, so it really can't be selected. llvm-svn: 112221
2010-08-27 05:32:51 +08:00
lldb::TargetSP target_sp = GetSelectedTarget();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
exe_ctx.target = target_sp.get();
if (target_sp)
{
exe_ctx.process = target_sp->GetProcessSP().get();
if (exe_ctx.process && exe_ctx.process->IsRunning() == false)
{
Change "Current" as in GetCurrentThread, GetCurrentStackFrame, etc, to "Selected" i.e. GetSelectedThread. Selected makes more sense, since these are set by some user action (a selection). I didn't change "CurrentProcess" since this is always controlled by the target, and a given target can only have one process, so it really can't be selected. llvm-svn: 112221
2010-08-27 05:32:51 +08:00
exe_ctx.thread = exe_ctx.process->GetThreadList().GetSelectedThread().get();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (exe_ctx.thread == NULL)
exe_ctx.thread = exe_ctx.process->GetThreadList().GetThreadAtIndex(0).get();
if (exe_ctx.thread)
{
Change "Current" as in GetCurrentThread, GetCurrentStackFrame, etc, to "Selected" i.e. GetSelectedThread. Selected makes more sense, since these are set by some user action (a selection). I didn't change "CurrentProcess" since this is always controlled by the target, and a given target can only have one process, so it really can't be selected. llvm-svn: 112221
2010-08-27 05:32:51 +08:00
exe_ctx.frame = exe_ctx.thread->GetSelectedFrame().get();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (exe_ctx.frame == NULL)
exe_ctx.frame = exe_ctx.thread->GetStackFrameAtIndex (0).get();
}
}
}
return exe_ctx;
}
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
InputReaderSP
Debugger::GetCurrentInputReader ()
{
InputReaderSP reader_sp;
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
if (!m_input_reader_stack.IsEmpty())
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
{
// Clear any finished readers from the stack
while (CheckIfTopInputReaderIsDone()) ;
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
if (!m_input_reader_stack.IsEmpty())
reader_sp = m_input_reader_stack.Top();
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
}
return reader_sp;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
void
Debugger::DispatchInputCallback (void *baton, const void *bytes, size_t bytes_len)
{
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
if (bytes_len > 0)
((Debugger *)baton)->DispatchInput ((char *)bytes, bytes_len);
else
((Debugger *)baton)->DispatchInputEndOfFile ();
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
void
Debugger::DispatchInput (const char *bytes, size_t bytes_len)
{
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
if (bytes == NULL || bytes_len == 0)
return;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
WriteToDefaultReader (bytes, bytes_len);
}
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
void
Debugger::DispatchInputInterrupt ()
{
m_input_reader_data.clear();
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
InputReaderSP reader_sp (GetCurrentInputReader ());
if (reader_sp)
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
{
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
reader_sp->Notify (eInputReaderInterrupt);
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
// If notifying the reader of the interrupt finished the reader, we should pop it off the stack.
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
while (CheckIfTopInputReaderIsDone ()) ;
}
}
void
Debugger::DispatchInputEndOfFile ()
{
m_input_reader_data.clear();
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
InputReaderSP reader_sp (GetCurrentInputReader ());
if (reader_sp)
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
{
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
reader_sp->Notify (eInputReaderEndOfFile);
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
// If notifying the reader of the end-of-file finished the reader, we should pop it off the stack.
Add the ability to catch and do the right thing with Interrupts (often control-c) and end-of-file (often control-d). llvm-svn: 119837
2010-11-20 04:47:54 +08:00
while (CheckIfTopInputReaderIsDone ()) ;
}
}
Add code to make sure InputReaders finish and are cleaned up when a Debugger object is destroyed or re-set. (Thus making sure that, for example, the Python interpreter finishes and exits cleanly rather than being left in an undefined state.) llvm-svn: 122255
2010-12-21 02:35:50 +08:00
void
Debugger::CleanUpInputReaders ()
{
m_input_reader_data.clear();
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
// The bottom input reader should be the main debugger input reader. We do not want to close that one here.
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
while (m_input_reader_stack.GetSize() > 1)
Add code to make sure InputReaders finish and are cleaned up when a Debugger object is destroyed or re-set. (Thus making sure that, for example, the Python interpreter finishes and exits cleanly rather than being left in an undefined state.) llvm-svn: 122255
2010-12-21 02:35:50 +08:00
{
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
InputReaderSP reader_sp (GetCurrentInputReader ());
Add code to make sure InputReaders finish and are cleaned up when a Debugger object is destroyed or re-set. (Thus making sure that, for example, the Python interpreter finishes and exits cleanly rather than being left in an undefined state.) llvm-svn: 122255
2010-12-21 02:35:50 +08:00
if (reader_sp)
{
reader_sp->Notify (eInputReaderEndOfFile);
reader_sp->SetIsDone (true);
}
}
}
This patch captures and serializes all output being written by the command line driver, including the lldb prompt being output by editline, the asynchronous process output & error messages, and asynchronous messages written by target stop-hooks. As part of this it introduces a new Stream class, StreamAsynchronousIO. A StreamAsynchronousIO object is created with a broadcaster, who will eventually broadcast the stream's data for a listener to handle, and an event type indicating what type of event the broadcaster will broadcast. When the Write method is called on a StreamAsynchronousIO object, the data is appended to an internal string. When the Flush method is called on a StreamAsynchronousIO object, it broadcasts it's data string and clears the string. Anything in lldb-core that needs to generate asynchronous output for the end-user should use the StreamAsynchronousIO objects. I have also added a new notification type for InputReaders, to let them know that a asynchronous output has been written. This is to allow the input readers to, for example, refresh their prompts and lines, if desired. I added the case statements to all the input readers to catch this notification, but I haven't added any code for handling them yet (except to the IOChannel input reader). llvm-svn: 130721
2011-05-03 04:41:46 +08:00
void
Debugger::NotifyTopInputReader (InputReaderAction notification)
{
InputReaderSP reader_sp (GetCurrentInputReader());
if (reader_sp)
{
reader_sp->Notify (notification);
// Flush out any input readers that are done.
while (CheckIfTopInputReaderIsDone ())
/* Do nothing. */;
}
}
Make sure writing asynchronous output only backs up & overwrites prompt if the IOChannel input reader is the top input reader. llvm-svn: 131110
2011-05-10 07:06:58 +08:00
bool
Debugger::InputReaderIsTopReader (const lldb::InputReaderSP& reader_sp)
{
Add 'batch_mode' to CommandInterpreter. Modify InputReaders to not write output (prompts, instructions,etc.) if the CommandInterpreter is in batch_mode. Also, finish updating InputReaders to write to the asynchronous stream, rather than using the Debugger's output file directly. llvm-svn: 133162
2011-06-17 00:27:19 +08:00
InputReaderSP top_reader_sp (GetCurrentInputReader());
Make sure writing asynchronous output only backs up & overwrites prompt if the IOChannel input reader is the top input reader. llvm-svn: 131110
2011-05-10 07:06:58 +08:00
Add 'batch_mode' to CommandInterpreter. Modify InputReaders to not write output (prompts, instructions,etc.) if the CommandInterpreter is in batch_mode. Also, finish updating InputReaders to write to the asynchronous stream, rather than using the Debugger's output file directly. llvm-svn: 133162
2011-06-17 00:27:19 +08:00
return (reader_sp.get() == top_reader_sp.get());
Make sure writing asynchronous output only backs up & overwrites prompt if the IOChannel input reader is the top input reader. llvm-svn: 131110
2011-05-10 07:06:58 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
void
Debugger::WriteToDefaultReader (const char *bytes, size_t bytes_len)
{
if (bytes && bytes_len)
m_input_reader_data.append (bytes, bytes_len);
if (m_input_reader_data.empty())
return;
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
while (!m_input_reader_stack.IsEmpty() && !m_input_reader_data.empty())
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
// Get the input reader from the top of the stack
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
InputReaderSP reader_sp (GetCurrentInputReader ());
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (!reader_sp)
break;
Remove use of STL collection class use of the "data()" method since it isn't part of C++'98. Most of these were "std::vector<T>::data()" and "std::string::data()". llvm-svn: 108957
2010-07-21 06:52:08 +08:00
size_t bytes_handled = reader_sp->HandleRawBytes (m_input_reader_data.c_str(),
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
m_input_reader_data.size());
if (bytes_handled)
{
m_input_reader_data.erase (0, bytes_handled);
}
else
{
// No bytes were handled, we might not have reached our
// granularity, just return and wait for more data
break;
}
}
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
// Flush out any input readers that are done.
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
while (CheckIfTopInputReaderIsDone ())
/* Do nothing. */;
}
void
Debugger::PushInputReader (const InputReaderSP& reader_sp)
{
if (!reader_sp)
return;
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
// Deactivate the old top reader
InputReaderSP top_reader_sp (GetCurrentInputReader ());
if (top_reader_sp)
top_reader_sp->Notify (eInputReaderDeactivate);
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
m_input_reader_stack.Push (reader_sp);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
reader_sp->Notify (eInputReaderActivate);
ActivateInputReader (reader_sp);
}
bool
Debugger::PopInputReader (const lldb::InputReaderSP& pop_reader_sp)
{
bool result = false;
// The reader on the stop of the stack is done, so let the next
// read on the stack referesh its prompt and if there is one...
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
if (!m_input_reader_stack.IsEmpty())
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
// Cannot call GetCurrentInputReader here, as that would cause an infinite loop.
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
InputReaderSP reader_sp(m_input_reader_stack.Top());
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (!pop_reader_sp || pop_reader_sp.get() == reader_sp.get())
{
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
m_input_reader_stack.Pop ();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
reader_sp->Notify (eInputReaderDeactivate);
reader_sp->Notify (eInputReaderDone);
result = true;
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
if (!m_input_reader_stack.IsEmpty())
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
reader_sp = m_input_reader_stack.Top();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (reader_sp)
{
ActivateInputReader (reader_sp);
reader_sp->Notify (eInputReaderReactivate);
}
}
}
}
return result;
}
bool
Debugger::CheckIfTopInputReaderIsDone ()
{
bool result = false;
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
if (!m_input_reader_stack.IsEmpty())
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Add a new function to Debugger for finding the top/current input reader. Always make sure the input reader stack is not empty before trying to get the top element from the stack. llvm-svn: 125255
2011-02-10 09:15:13 +08:00
// Cannot call GetCurrentInputReader here, as that would cause an infinite loop.
Create new class, InputReaderStack, to better handle mutexes around input readers and prevent deadlocking; modify Debugger to use the new class. llvm-svn: 132475
2011-06-03 03:18:55 +08:00
InputReaderSP reader_sp(m_input_reader_stack.Top());
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (reader_sp && reader_sp->IsDone())
{
result = true;
PopInputReader (reader_sp);
}
}
return result;
}
void
Debugger::ActivateInputReader (const InputReaderSP &reader_sp)
{
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
int input_fd = m_input_file.GetFile().GetDescriptor();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
if (input_fd >= 0)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Use Host::File in lldb_private::StreamFile and other places to cleanup host layer a bit more. llvm-svn: 125149
2011-02-09 09:08:52 +08:00
Terminal tty(input_fd);
Abtract terminal stuff into a new lldb_private::Terminal class where the implementation is hidden in the host layer. This avoids a slew of "#if LLDB_CONFIG_TERMIOS_SUPPORTED" statements in the code and keeps things cleaner. llvm-svn: 125057
2011-02-08 07:24:47 +08:00
tty.SetEcho(reader_sp->GetEcho());
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Abtract terminal stuff into a new lldb_private::Terminal class where the implementation is hidden in the host layer. This avoids a slew of "#if LLDB_CONFIG_TERMIOS_SUPPORTED" statements in the code and keeps things cleaner. llvm-svn: 125057
2011-02-08 07:24:47 +08:00
switch (reader_sp->GetGranularity())
{
case eInputReaderGranularityByte:
case eInputReaderGranularityWord:
tty.SetCanonical (false);
break;
case eInputReaderGranularityLine:
case eInputReaderGranularityAll:
tty.SetCanonical (true);
break;
default:
break;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
}
}
Very large changes that were needed in order to allow multiple connections to the debugger from GUI windows. Previously there was one global debugger instance that could be accessed that had its own command interpreter and current state (current target/process/thread/frame). When a GUI debugger was attached, if it opened more than one window that each had a console window, there were issues where the last one to setup the global debugger object won and got control of the debugger. To avoid this we now create instances of the lldb_private::Debugger that each has its own state: - target list for targets the debugger instance owns - current process/thread/frame - its own command interpreter - its own input, output and error file handles to avoid conflicts - its own input reader stack So now clients should call: SBDebugger::Initialize(); // (static function) SBDebugger debugger (SBDebugger::Create()); // Use which ever file handles you wish debugger.SetErrorFileHandle (stderr, false); debugger.SetOutputFileHandle (stdout, false); debugger.SetInputFileHandle (stdin, true); // main loop SBDebugger::Terminate(); // (static function) SBDebugger::Initialize() and SBDebugger::Terminate() are ref counted to ensure nothing gets destroyed too early when multiple clients might be attached. Cleaned up the command interpreter and the CommandObject and all subclasses to take more appropriate arguments. llvm-svn: 106615
2010-06-23 09:19:29 +08:00
Added Debugger::GetAsync{Output/Error}Stream, and use it to print parse errors when we go to run a breakpoint condition. llvm-svn: 132517
2011-06-03 07:58:26 +08:00
StreamSP
Debugger::GetAsyncOutputStream ()
{
return StreamSP (new StreamAsynchronousIO (GetCommandInterpreter(),
CommandInterpreter::eBroadcastBitAsynchronousOutputData));
}
StreamSP
Debugger::GetAsyncErrorStream ()
{
return StreamSP (new StreamAsynchronousIO (GetCommandInterpreter(),
CommandInterpreter::eBroadcastBitAsynchronousErrorData));
}
Add a unique ID to each debugger instance. Add functions to look up debugger by id Add global variable to lldb python module, to hold debugger id Modify embedded Python interpreter to update the global variable with the id of its current debugger. Modify the char ** typemap definition in lldb.swig to accept 'None' (for NULL) as a valid value. The point of all this is so that, when you drop into the embedded interpreter from the command interpreter (or when doing Python-based breakpoint commands), there is a way for the Python side to find/get the correct debugger instance ( by checking debugger_unique_id, then calling SBDebugger::FindDebuggerWithID on it). llvm-svn: 107287
2010-07-01 00:22:25 +08:00
DebuggerSP
Debugger::FindDebuggerWithID (lldb::user_id_t id)
{
lldb::DebuggerSP debugger_sp;
Mutex::Locker locker (GetDebuggerListMutex ());
DebuggerList &debugger_list = GetDebuggerList();
DebuggerList::iterator pos, end = debugger_list.end();
for (pos = debugger_list.begin(); pos != end; ++pos)
{
if ((*pos).get()->GetID() == id)
{
debugger_sp = *pos;
break;
}
}
return debugger_sp;
}
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
static void
TestPromptFormats (StackFrame *frame)
{
if (frame == NULL)
return;
StreamString s;
const char *prompt_format =
"{addr = '${addr}'\n}"
"{process.id = '${process.id}'\n}"
"{process.name = '${process.name}'\n}"
"{process.file.basename = '${process.file.basename}'\n}"
"{process.file.fullpath = '${process.file.fullpath}'\n}"
"{thread.id = '${thread.id}'\n}"
"{thread.index = '${thread.index}'\n}"
"{thread.name = '${thread.name}'\n}"
"{thread.queue = '${thread.queue}'\n}"
"{thread.stop-reason = '${thread.stop-reason}'\n}"
"{target.arch = '${target.arch}'\n}"
"{module.file.basename = '${module.file.basename}'\n}"
"{module.file.fullpath = '${module.file.fullpath}'\n}"
"{file.basename = '${file.basename}'\n}"
"{file.fullpath = '${file.fullpath}'\n}"
"{frame.index = '${frame.index}'\n}"
"{frame.pc = '${frame.pc}'\n}"
"{frame.sp = '${frame.sp}'\n}"
"{frame.fp = '${frame.fp}'\n}"
"{frame.flags = '${frame.flags}'\n}"
"{frame.reg.rdi = '${frame.reg.rdi}'\n}"
"{frame.reg.rip = '${frame.reg.rip}'\n}"
"{frame.reg.rsp = '${frame.reg.rsp}'\n}"
"{frame.reg.rbp = '${frame.reg.rbp}'\n}"
"{frame.reg.rflags = '${frame.reg.rflags}'\n}"
"{frame.reg.xmm0 = '${frame.reg.xmm0}'\n}"
"{frame.reg.carp = '${frame.reg.carp}'\n}"
"{function.id = '${function.id}'\n}"
"{function.name = '${function.name}'\n}"
"{function.addr-offset = '${function.addr-offset}'\n}"
"{function.line-offset = '${function.line-offset}'\n}"
"{function.pc-offset = '${function.pc-offset}'\n}"
"{line.file.basename = '${line.file.basename}'\n}"
"{line.file.fullpath = '${line.file.fullpath}'\n}"
"{line.number = '${line.number}'\n}"
"{line.start-addr = '${line.start-addr}'\n}"
"{line.end-addr = '${line.end-addr}'\n}"
;
SymbolContext sc (frame->GetSymbolContext(eSymbolContextEverything));
ExecutionContext exe_ctx;
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
frame->CalculateExecutionContext(exe_ctx);
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
const char *end = NULL;
if (Debugger::FormatPrompt (prompt_format, &sc, &exe_ctx, &sc.line_entry.range.GetBaseAddress(), s, &end))
{
printf("%s\n", s.GetData());
}
else
{
printf ("error: at '%s'\n", end);
printf ("what we got: %s\n", s.GetData());
}
}
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
#define IFERROR_PRINT_IT if (error.Fail()) \
{ \
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log) \
log->Printf("ERROR: %s\n", error.AsCString("unknown")); \
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
break; \
}
static bool
ScanFormatDescriptor(const char* var_name_begin,
const char* var_name_end,
const char** var_name_final,
const char** percent_position,
lldb::Format* custom_format,
ValueObject::ValueObjectRepresentationStyle* val_obj_display)
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
LogSP log(lldb_private::GetLogIfAllCategoriesSet (LIBLLDB_LOG_TYPES));
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
*percent_position = ::strchr(var_name_begin,'%');
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (!*percent_position || *percent_position > var_name_end)
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
{
if (log)
log->Printf("no format descriptor in string, skipping");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
*var_name_final = var_name_end;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
}
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
else
{
*var_name_final = *percent_position;
char* format_name = new char[var_name_end-*var_name_final]; format_name[var_name_end-*var_name_final-1] = '\0';
memcpy(format_name, *var_name_final+1, var_name_end-*var_name_final-1);
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("parsing %s as a format descriptor", format_name);
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
if ( !FormatManager::GetFormatFromCString(format_name,
true,
*custom_format) )
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("%s is an unknown format", format_name);
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
// if this is an @ sign, print ObjC description
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (*format_name == '@')
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
*val_obj_display = ValueObject::eDisplayLanguageSpecific;
// if this is a V, print the value using the default format
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
else if (*format_name == 'V')
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
*val_obj_display = ValueObject::eDisplayValue;
when typing a summary string you can use the %S symbol to explicitly indicate that you want the summary to be used to print the target object (e.g. ${var%S}). this might already be the default if your variable is of an aggregate type new feature: synthetic filters. you can restrict the number of children for your variables to only a meaningful subset - the restricted list of children obeys the typical rules (e.g. summaries prevail over children) - one-line summaries show only the filtered (synthetic) children, if you type an expanded summary string, or you use Python scripts, all the real children are accessible - to provide a synthetic children list use the "type synth add" command, as in: type synth add foo_type --child varA --child varB[0] --child varC->packet->flags[1-4] (you can use ., ->, single-item array operator [N] and bitfield operator [N-M]; array slice access is not supported, giving simplified names to expression paths is not supported) - a new -S option to frame variable and target variable lets you override synthetic children and instead show real ones llvm-svn: 135731
2011-07-22 08:16:08 +08:00
// if this is an L, print the location of the value
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
else if (*format_name == 'L')
Python summary strings: - you can use a Python script to write a summary string for data-types, in one of three ways: -P option and typing the script a line at a time -s option and passing a one-line Python script -F option and passing the name of a Python function these options all work for the "type summary add" command your Python code (if provided through -P or -s) is wrapped in a function that accepts two parameters: valobj (a ValueObject) and dict (an LLDB internal dictionary object). if you use -F and give a function name, you're expected to define the function on your own and with the right prototype. your function, however defined, must return a Python string - test case for the Python summary feature - a few quirks: Python summaries cannot have names, and cannot use regex as type names both issues will be fixed ASAP major redesign of type summary code: - type summary working with strings and type summary working with Python code are two classes, with a common base class SummaryFormat - SummaryFormat classes now are able to actively format objects rather than just aggregating data - cleaner code to print descriptions for summaries the public API now exports a method to easily navigate a ValueObject hierarchy New InputReaderEZ and PriorityPointerPair classes Several minor fixes and improvements llvm-svn: 135238
2011-07-15 10:26:42 +08:00
*val_obj_display = ValueObject::eDisplayLocation;
when typing a summary string you can use the %S symbol to explicitly indicate that you want the summary to be used to print the target object (e.g. ${var%S}). this might already be the default if your variable is of an aggregate type new feature: synthetic filters. you can restrict the number of children for your variables to only a meaningful subset - the restricted list of children obeys the typical rules (e.g. summaries prevail over children) - one-line summaries show only the filtered (synthetic) children, if you type an expanded summary string, or you use Python scripts, all the real children are accessible - to provide a synthetic children list use the "type synth add" command, as in: type synth add foo_type --child varA --child varB[0] --child varC->packet->flags[1-4] (you can use ., ->, single-item array operator [N] and bitfield operator [N-M]; array slice access is not supported, giving simplified names to expression paths is not supported) - a new -S option to frame variable and target variable lets you override synthetic children and instead show real ones llvm-svn: 135731
2011-07-22 08:16:08 +08:00
// if this is an S, print the summary after all
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
else if (*format_name == 'S')
when typing a summary string you can use the %S symbol to explicitly indicate that you want the summary to be used to print the target object (e.g. ${var%S}). this might already be the default if your variable is of an aggregate type new feature: synthetic filters. you can restrict the number of children for your variables to only a meaningful subset - the restricted list of children obeys the typical rules (e.g. summaries prevail over children) - one-line summaries show only the filtered (synthetic) children, if you type an expanded summary string, or you use Python scripts, all the real children are accessible - to provide a synthetic children list use the "type synth add" command, as in: type synth add foo_type --child varA --child varB[0] --child varC->packet->flags[1-4] (you can use ., ->, single-item array operator [N] and bitfield operator [N-M]; array slice access is not supported, giving simplified names to expression paths is not supported) - a new -S option to frame variable and target variable lets you override synthetic children and instead show real ones llvm-svn: 135731
2011-07-22 08:16:08 +08:00
*val_obj_display = ValueObject::eDisplaySummary;
New formatting symbol %# can be used in summary strings to get the "count of children" of a variable - accordingly, the test cases for the synthetic providers for the std:: containers have been edited to use ${svar%#} instead of ${svar.len} to print out the count of elements ; the .len synthetic child has been removed from the synthetic providers The synthetic children providers for the std:: containers now return None when asked for children indexes >= num_children() Basic code to support filter names based on regular expressions (WIP) llvm-svn: 136862
2011-08-04 10:34:29 +08:00
else if (*format_name == '#')
*val_obj_display = ValueObject::eDisplayChildrenCount;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
else if (log)
log->Printf("%s is an error, leaving the previous value alone", format_name);
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
}
// a good custom format tells us to print the value using it
else
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
{
if (log)
log->Printf("will display value for this VO");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
*val_obj_display = ValueObject::eDisplayValue;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
}
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
delete format_name;
}
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("final format description outcome: custom_format = %d, val_obj_display = %d",
*custom_format,
*val_obj_display);
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
return true;
}
static bool
ScanBracketedRange(const char* var_name_begin,
const char* var_name_end,
const char* var_name_final,
const char** open_bracket_position,
const char** separator_position,
const char** close_bracket_position,
const char** var_name_final_if_array_range,
int64_t* index_lower,
int64_t* index_higher)
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
LogSP log(lldb_private::GetLogIfAllCategoriesSet (LIBLLDB_LOG_TYPES));
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
*open_bracket_position = ::strchr(var_name_begin,'[');
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (*open_bracket_position && *open_bracket_position < var_name_final)
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
{
*separator_position = ::strchr(*open_bracket_position,'-'); // might be NULL if this is a simple var[N] bitfield
*close_bracket_position = ::strchr(*open_bracket_position,']');
// as usual, we assume that [] will come before %
//printf("trying to expand a []\n");
*var_name_final_if_array_range = *open_bracket_position;
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (*close_bracket_position - *open_bracket_position == 1)
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("[] detected.. going from 0 to end of data");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
*index_lower = 0;
}
else if (*separator_position == NULL || *separator_position > var_name_end)
{
char *end = NULL;
*index_lower = ::strtoul (*open_bracket_position+1, &end, 0);
*index_higher = *index_lower;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("[%d] detected, high index is same",index_lower);
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
}
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
else if (*close_bracket_position && *close_bracket_position < var_name_end)
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
{
char *end = NULL;
*index_lower = ::strtoul (*open_bracket_position+1, &end, 0);
*index_higher = ::strtoul (*separator_position+1, &end, 0);
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("[%d-%d] detected",index_lower,index_higher);
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
}
else
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
{
if (log)
log->Printf("expression is erroneous, cannot extract indices out of it");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
return false;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
}
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
if (*index_lower > *index_higher && *index_higher > 0)
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("swapping indices");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
int temp = *index_lower;
*index_lower = *index_higher;
*index_higher = temp;
}
}
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
else if (log)
log->Printf("no bracketed range, skipping entirely");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
return true;
}
static ValueObjectSP
ExpandExpressionPath(ValueObject* vobj,
StackFrame* frame,
bool* do_deref_pointer,
const char* var_name_begin,
const char* var_name_final,
Error& error)
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
LogSP log(lldb_private::GetLogIfAllCategoriesSet (LIBLLDB_LOG_TYPES));
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
StreamString sstring;
VariableSP var_sp;
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (*do_deref_pointer)
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
{
if (log)
log->Printf("been told to deref_pointer by caller");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
sstring.PutChar('*');
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
}
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
else if (vobj->IsDereferenceOfParent() && ClangASTContext::IsPointerType(vobj->GetParent()->GetClangType()) && !vobj->IsArrayItemForPointer())
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("decided to deref_pointer myself");
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
sstring.PutChar('*');
*do_deref_pointer = true;
}
vobj->GetExpressionPath(sstring, true, ValueObject::eHonorPointers);
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("expression path to expand in phase 0: %s",sstring.GetData());
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
sstring.PutRawBytes(var_name_begin+3, var_name_final-var_name_begin-3);
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("expression path to expand in phase 1: %s",sstring.GetData());
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
std::string name = std::string(sstring.GetData());
ValueObjectSP target = frame->GetValueForVariableExpressionPath (name.c_str(),
eNoDynamicValues,
0,
var_sp,
error);
return target;
}
static ValueObjectSP
ExpandIndexedExpression(ValueObject* vobj,
uint32_t index,
StackFrame* frame,
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
bool deref_pointer)
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
LogSP log(lldb_private::GetLogIfAllCategoriesSet (LIBLLDB_LOG_TYPES));
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
const char* ptr_deref_format = "[%d]";
std::auto_ptr<char> ptr_deref_buffer(new char[10]);
::sprintf(ptr_deref_buffer.get(), ptr_deref_format, index);
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("name to deref: %s",ptr_deref_buffer.get());
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
const char* first_unparsed;
ValueObject::GetValueForExpressionPathOptions options;
ValueObject::ExpressionPathEndResultType final_value_type;
ValueObject::ExpressionPathScanEndReason reason_to_stop;
ValueObject::ExpressionPathAftermath what_next = (deref_pointer ? ValueObject::eDereference : ValueObject::eNothing);
ValueObjectSP item = vobj->GetValueForExpressionPath (ptr_deref_buffer.get(),
&first_unparsed,
&reason_to_stop,
&final_value_type,
options,
&what_next);
if (!item)
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("ERROR: unparsed portion = %s, why stopping = %d,"
" final_value_type %d",
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
first_unparsed, reason_to_stop, final_value_type);
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
}
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
else
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("ALL RIGHT: unparsed portion = %s, why stopping = %d,"
" final_value_type %d",
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
first_unparsed, reason_to_stop, final_value_type);
}
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
return item;
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
bool
Debugger::FormatPrompt
(
const char *format,
const SymbolContext *sc,
const ExecutionContext *exe_ctx,
const Address *addr,
Stream &s,
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
const char **end,
ValueObject* vobj
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
)
{
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
ValueObject* realvobj = NULL; // makes it super-easy to parse pointers
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
bool success = true;
const char *p;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
LogSP log(lldb_private::GetLogIfAllCategoriesSet (LIBLLDB_LOG_TYPES));
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
for (p = format; *p != '\0'; ++p)
{
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (realvobj)
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
vobj = realvobj;
realvobj = NULL;
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
size_t non_special_chars = ::strcspn (p, "${}\\");
if (non_special_chars > 0)
{
if (success)
s.Write (p, non_special_chars);
p += non_special_chars;
}
if (*p == '\0')
{
break;
}
else if (*p == '{')
{
// Start a new scope that must have everything it needs if it is to
// to make it into the final output stream "s". If you want to make
// a format that only prints out the function or symbol name if there
// is one in the symbol context you can use:
// "{function =${function.name}}"
// The first '{' starts a new scope that end with the matching '}' at
// the end of the string. The contents "function =${function.name}"
// will then be evaluated and only be output if there is a function
// or symbol with a valid name.
StreamString sub_strm;
++p; // Skip the '{'
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
if (FormatPrompt (p, sc, exe_ctx, addr, sub_strm, &p, vobj))
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
// The stream had all it needed
s.Write(sub_strm.GetData(), sub_strm.GetSize());
}
if (*p != '}')
{
success = false;
break;
}
}
else if (*p == '}')
{
// End of a enclosing scope
break;
}
else if (*p == '$')
{
// We have a prompt variable to print
++p;
if (*p == '{')
{
++p;
const char *var_name_begin = p;
const char *var_name_end = ::strchr (p, '}');
if (var_name_end && var_name_begin < var_name_end)
{
// if we have already failed to parse, skip this variable
if (success)
{
const char *cstr = NULL;
Address format_addr;
bool calculate_format_addr_function_offset = false;
// Set reg_kind and reg_num to invalid values
RegisterKind reg_kind = kNumRegisterKinds;
uint32_t reg_num = LLDB_INVALID_REGNUM;
FileSpec format_file_spec;
Fixed the LLDB build so that we can have private types, private enums and public types and public enums. This was done to keep the SWIG stuff from parsing all sorts of enums and types that weren't needed, and allows us to abstract our API better. llvm-svn: 128239
2011-03-25 05:19:54 +08:00
const RegisterInfo *reg_info = NULL;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
RegisterContext *reg_ctx = NULL;
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
bool do_deref_pointer = false;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
ValueObject::ExpressionPathScanEndReason reason_to_stop = ValueObject::eEndOfString;
ValueObject::ExpressionPathEndResultType final_value_type = ValueObject::ePlain;
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
// Each variable must set success to true below...
bool var_success = false;
switch (var_name_begin[0])
{
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
case '*':
case 'v':
Public API changes: - Completely new implementation of SBType - Various enhancements in several other classes Python synthetic children providers for std::vector<T>, std::list<T> and std::map<K,V>: - these return the actual elements into the container as the children of the container - basic template name parsing that works (hopefully) on both Clang and GCC - find them in examples/synthetic and in the test suite in functionalities/data-formatter/data-formatter-python-synth New summary string token ${svar : - the syntax is just the same as in ${var but this new token lets you read the values coming from the synthetic children provider instead of the actual children - Python providers above provide a synthetic child len that returns the number of elements into the container Full bug fix for the issue in which getting byte size for a non-complete type would crash LLDB Several other fixes, including: - inverted the order of arguments in the ClangASTType constructor - EvaluationPoint now only returns SharedPointer's to Target and Process - the help text for several type subcommands now correctly indicates argument-less options as such llvm-svn: 136504
2011-07-30 03:53:35 +08:00
case 's':
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
Public API changes: - Completely new implementation of SBType - Various enhancements in several other classes Python synthetic children providers for std::vector<T>, std::list<T> and std::map<K,V>: - these return the actual elements into the container as the children of the container - basic template name parsing that works (hopefully) on both Clang and GCC - find them in examples/synthetic and in the test suite in functionalities/data-formatter/data-formatter-python-synth New summary string token ${svar : - the syntax is just the same as in ${var but this new token lets you read the values coming from the synthetic children provider instead of the actual children - Python providers above provide a synthetic child len that returns the number of elements into the container Full bug fix for the issue in which getting byte size for a non-complete type would crash LLDB Several other fixes, including: - inverted the order of arguments in the ClangASTType constructor - EvaluationPoint now only returns SharedPointer's to Target and Process - the help text for several type subcommands now correctly indicates argument-less options as such llvm-svn: 136504
2011-07-30 03:53:35 +08:00
if (!vobj)
break;
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
if (log)
log->Printf("initial string: %s",var_name_begin);
Public API changes: - Completely new implementation of SBType - Various enhancements in several other classes Python synthetic children providers for std::vector<T>, std::list<T> and std::map<K,V>: - these return the actual elements into the container as the children of the container - basic template name parsing that works (hopefully) on both Clang and GCC - find them in examples/synthetic and in the test suite in functionalities/data-formatter/data-formatter-python-synth New summary string token ${svar : - the syntax is just the same as in ${var but this new token lets you read the values coming from the synthetic children provider instead of the actual children - Python providers above provide a synthetic child len that returns the number of elements into the container Full bug fix for the issue in which getting byte size for a non-complete type would crash LLDB Several other fixes, including: - inverted the order of arguments in the ClangASTType constructor - EvaluationPoint now only returns SharedPointer's to Target and Process - the help text for several type subcommands now correctly indicates argument-less options as such llvm-svn: 136504
2011-07-30 03:53:35 +08:00
// check for *var and *svar
if (*var_name_begin == '*')
{
do_deref_pointer = true;
var_name_begin++;
}
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
if (log)
log->Printf("initial string: %s",var_name_begin);
Public API changes: - Completely new implementation of SBType - Various enhancements in several other classes Python synthetic children providers for std::vector<T>, std::list<T> and std::map<K,V>: - these return the actual elements into the container as the children of the container - basic template name parsing that works (hopefully) on both Clang and GCC - find them in examples/synthetic and in the test suite in functionalities/data-formatter/data-formatter-python-synth New summary string token ${svar : - the syntax is just the same as in ${var but this new token lets you read the values coming from the synthetic children provider instead of the actual children - Python providers above provide a synthetic child len that returns the number of elements into the container Full bug fix for the issue in which getting byte size for a non-complete type would crash LLDB Several other fixes, including: - inverted the order of arguments in the ClangASTType constructor - EvaluationPoint now only returns SharedPointer's to Target and Process - the help text for several type subcommands now correctly indicates argument-less options as such llvm-svn: 136504
2011-07-30 03:53:35 +08:00
if (*var_name_begin == 's')
{
vobj = vobj->GetSyntheticValue(lldb::eUseSyntheticFilter).get();
var_name_begin++;
}
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
if (log)
log->Printf("initial string: %s",var_name_begin);
Public API changes: - Completely new implementation of SBType - Various enhancements in several other classes Python synthetic children providers for std::vector<T>, std::list<T> and std::map<K,V>: - these return the actual elements into the container as the children of the container - basic template name parsing that works (hopefully) on both Clang and GCC - find them in examples/synthetic and in the test suite in functionalities/data-formatter/data-formatter-python-synth New summary string token ${svar : - the syntax is just the same as in ${var but this new token lets you read the values coming from the synthetic children provider instead of the actual children - Python providers above provide a synthetic child len that returns the number of elements into the container Full bug fix for the issue in which getting byte size for a non-complete type would crash LLDB Several other fixes, including: - inverted the order of arguments in the ClangASTType constructor - EvaluationPoint now only returns SharedPointer's to Target and Process - the help text for several type subcommands now correctly indicates argument-less options as such llvm-svn: 136504
2011-07-30 03:53:35 +08:00
// should be a 'v' by now
if (*var_name_begin != 'v')
break;
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
if (log)
log->Printf("initial string: %s",var_name_begin);
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
ValueObject::ExpressionPathAftermath what_next = (do_deref_pointer ?
ValueObject::eDereference : ValueObject::eNothing);
ValueObject::GetValueForExpressionPathOptions options;
options.DontCheckDotVsArrowSyntax().DoAllowBitfieldSyntax().DoAllowFragileIVar();
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
ValueObject::ValueObjectRepresentationStyle val_obj_display = ValueObject::eDisplaySummary;
ValueObject* target = NULL;
lldb::Format custom_format = eFormatInvalid;
const char* var_name_final = NULL;
const char* var_name_final_if_array_range = NULL;
const char* close_bracket_position = NULL;
int64_t index_lower = -1;
int64_t index_higher = -1;
bool is_array_range = false;
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
const char* first_unparsed;
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (!vobj) break;
// simplest case ${var}, just print vobj's value
if (::strncmp (var_name_begin, "var}", strlen("var}")) == 0)
{
target = vobj;
val_obj_display = ValueObject::eDisplayValue;
}
else if (::strncmp(var_name_begin,"var%",strlen("var%")) == 0)
{
// this is a variable with some custom format applied to it
const char* percent_position;
target = vobj;
val_obj_display = ValueObject::eDisplayValue;
ScanFormatDescriptor (var_name_begin,
var_name_end,
&var_name_final,
&percent_position,
&custom_format,
&val_obj_display);
}
// this is ${var.something} or multiple .something nested
else if (::strncmp (var_name_begin, "var", strlen("var")) == 0)
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
const char* percent_position;
ScanFormatDescriptor (var_name_begin,
var_name_end,
&var_name_final,
&percent_position,
&custom_format,
&val_obj_display);
const char* open_bracket_position;
const char* separator_position;
ScanBracketedRange (var_name_begin,
var_name_end,
var_name_final,
&open_bracket_position,
&separator_position,
&close_bracket_position,
&var_name_final_if_array_range,
&index_lower,
&index_higher);
Error error;
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
std::auto_ptr<char> expr_path(new char[var_name_final-var_name_begin-1]);
::memset(expr_path.get(), 0, var_name_final-var_name_begin-1);
memcpy(expr_path.get(), var_name_begin+3,var_name_final-var_name_begin-3);
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("symbol to expand: %s",expr_path.get());
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
target = vobj->GetValueForExpressionPath(expr_path.get(),
&first_unparsed,
&reason_to_stop,
&final_value_type,
options,
&what_next).get();
if (!target)
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("ERROR: unparsed portion = %s, why stopping = %d,"
" final_value_type %d",
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
first_unparsed, reason_to_stop, final_value_type);
break;
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
}
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
else
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("ALL RIGHT: unparsed portion = %s, why stopping = %d,"
" final_value_type %d",
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
first_unparsed, reason_to_stop, final_value_type);
}
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
}
else
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
break;
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
is_array_range = (final_value_type == ValueObject::eBoundedRange ||
final_value_type == ValueObject::eUnboundedRange);
do_deref_pointer = (what_next == ValueObject::eDereference);
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
bug fix in summary strings: - ${*var[].something} was not working as expected options -p and -r now also work for type format add llvm-svn: 134523
2011-07-07 03:27:11 +08:00
if (do_deref_pointer && !is_array_range)
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
{
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
// I have not deref-ed yet, let's do it
// this happens when we are not going through GetValueForVariableExpressionPath
// to get to the target ValueObject
Error error;
target = target->Dereference(error).get();
IFERROR_PRINT_IT
do_deref_pointer = false;
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
}
smarter summary strings: - formats %s %char[] %c and %a now work to print 0-terminated c-strings if they are applied to a char* or char[] even without the [] operator (e.g. ${var%s}) - array formats (char[], intN[], ..) now work when applied to an array of a scalar type even without the [] operator (e.g. ${var%int32_t[]}) LLDB will not crash because of endless loop when trying to obtain a summary for an object that has no value and references itself in its summary string In many cases, a wrong summary string will now display an "<error>" message instead of giving out an empty string llvm-svn: 135007
2011-07-13 06:56:10 +08:00
bool is_array = ClangASTContext::IsArrayType(target->GetClangType());
bool is_pointer = ClangASTContext::IsPointerType(target->GetClangType());
if ((is_array || is_pointer) && (!is_array_range) && val_obj_display == ValueObject::eDisplayValue) // this should be wrong, but there are some exceptions
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("I am into array || pointer && !range");
smarter summary strings: - formats %s %char[] %c and %a now work to print 0-terminated c-strings if they are applied to a char* or char[] even without the [] operator (e.g. ${var%s}) - array formats (char[], intN[], ..) now work when applied to an array of a scalar type even without the [] operator (e.g. ${var%int32_t[]}) LLDB will not crash because of endless loop when trying to obtain a summary for an object that has no value and references itself in its summary string In many cases, a wrong summary string will now display an "<error>" message instead of giving out an empty string llvm-svn: 135007
2011-07-13 06:56:10 +08:00
// try to use the special cases
var_success = target->DumpPrintableRepresentation(s,val_obj_display, custom_format);
if (!var_success)
s << "<invalid, please use [] operator>";
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("special cases did%s match", var_success ? "" : "n't");
smarter summary strings: - formats %s %char[] %c and %a now work to print 0-terminated c-strings if they are applied to a char* or char[] even without the [] operator (e.g. ${var%s}) - array formats (char[], intN[], ..) now work when applied to an array of a scalar type even without the [] operator (e.g. ${var%int32_t[]}) LLDB will not crash because of endless loop when trying to obtain a summary for an object that has no value and references itself in its summary string In many cases, a wrong summary string will now display an "<error>" message instead of giving out an empty string llvm-svn: 135007
2011-07-13 06:56:10 +08:00
break;
}
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (!is_array_range)
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
{
if (log)
log->Printf("dumping ordinary printable output");
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
var_success = target->DumpPrintableRepresentation(s,val_obj_display, custom_format);
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
}
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
else
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
{
if (log)
log->Printf("checking if I can handle as array");
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (!is_array && !is_pointer)
break;
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("handle as array");
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
const char* special_directions = NULL;
StreamString special_directions_writer;
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (close_bracket_position && (var_name_end-close_bracket_position > 1))
{
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
ConstString additional_data;
additional_data.SetCStringWithLength(close_bracket_position+1, var_name_end-close_bracket_position-1);
special_directions_writer.Printf("${%svar%s}",
do_deref_pointer ? "*" : "",
additional_data.GetCString());
special_directions = special_directions_writer.GetData();
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
}
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
// let us display items index_lower thru index_higher of this array
s.PutChar('[');
var_success = true;
if (index_higher < 0)
index_higher = vobj->GetNumChildren() - 1;
for (;index_lower<=index_higher;index_lower++)
{
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
ValueObject* item = ExpandIndexedExpression(target,
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
index_lower,
exe_ctx->frame,
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
false).get();
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
if (!item)
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("ERROR in getting child item at index %d", index_lower);
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
}
else
{
some editing of data visualization error messages to make them more meaningful debugging printfs() for data visualization turned into a meaningful log: - introduced a new log category `types' in channel `lldb' llvm-svn: 135773
2011-07-23 01:03:19 +08:00
if (log)
log->Printf("special_directions for child item: %s",special_directions);
final fix for the global constructors issue new GetValueForExpressionPath() method in ValueObject to navigate expression paths in a more bitfield vs slices aware way changes to the varformats.html document (WIP) llvm-svn: 134679
2011-07-08 10:51:01 +08:00
}
Fixed some issues with ARM backtraces by not processing any push/pop instructions if they are conditional. Also fixed issues where the PC wasn't getting bit zero stripped for ARM targets when a stack frame was thumb. We now properly call through the GetOpcodeLoadAddress() functions to make sure the addresses are properly stripped for any targets that may decorate up their addresses. We now don't pass the SIGSTOP signals along. We can revisit this soon, but currently this was interfering with debugging some older ARM targets that don't have vCont support in the GDB server. llvm-svn: 134461
2011-07-06 12:07:21 +08:00
if (!special_directions)
var_success &= item->DumpPrintableRepresentation(s,val_obj_display, custom_format);
else
var_success &= FormatPrompt(special_directions, sc, exe_ctx, addr, s, NULL, item);
if (index_lower < index_higher)
s.PutChar(',');
}
s.PutChar(']');
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
}
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
}
new syntax for summary strings: - ${*expr} now simply means to dereference expr before actually using it - bitfields, array ranges and pointer ranges now work in a (hopefully) more natural and language-compliant way a new class TypeHierarchyNavigator replicates the behavior of the FormatManager in going through type hierarchies when one-lining summary strings, children's summaries can be used as well as values llvm-svn: 134458
2011-07-06 10:13:41 +08:00
break;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
case 'a':
if (::strncmp (var_name_begin, "addr}", strlen("addr}")) == 0)
{
if (addr && addr->IsValid())
{
var_success = true;
format_addr = *addr;
}
}
break;
case 'p':
if (::strncmp (var_name_begin, "process.", strlen("process.")) == 0)
{
if (exe_ctx && exe_ctx->process != NULL)
{
var_name_begin += ::strlen ("process.");
if (::strncmp (var_name_begin, "id}", strlen("id}")) == 0)
{
s.Printf("%i", exe_ctx->process->GetID());
var_success = true;
}
else if ((::strncmp (var_name_begin, "name}", strlen("name}")) == 0) ||
(::strncmp (var_name_begin, "file.basename}", strlen("file.basename}")) == 0) ||
(::strncmp (var_name_begin, "file.fullpath}", strlen("file.fullpath}")) == 0))
{
ModuleSP exe_module_sp (exe_ctx->process->GetTarget().GetExecutableModule());
if (exe_module_sp)
{
if (var_name_begin[0] == 'n' || var_name_begin[5] == 'f')
{
format_file_spec.GetFilename() = exe_module_sp->GetFileSpec().GetFilename();
var_success = format_file_spec;
}
else
{
format_file_spec = exe_module_sp->GetFileSpec();
var_success = format_file_spec;
}
}
}
}
}
break;
case 't':
if (::strncmp (var_name_begin, "thread.", strlen("thread.")) == 0)
{
if (exe_ctx && exe_ctx->thread)
{
var_name_begin += ::strlen ("thread.");
if (::strncmp (var_name_begin, "id}", strlen("id}")) == 0)
{
s.Printf("0x%4.4x", exe_ctx->thread->GetID());
var_success = true;
}
else if (::strncmp (var_name_begin, "index}", strlen("index}")) == 0)
{
s.Printf("%u", exe_ctx->thread->GetIndexID());
var_success = true;
}
else if (::strncmp (var_name_begin, "name}", strlen("name}")) == 0)
{
cstr = exe_ctx->thread->GetName();
var_success = cstr && cstr[0];
if (var_success)
s.PutCString(cstr);
}
else if (::strncmp (var_name_begin, "queue}", strlen("queue}")) == 0)
{
cstr = exe_ctx->thread->GetQueueName();
var_success = cstr && cstr[0];
if (var_success)
s.PutCString(cstr);
}
else if (::strncmp (var_name_begin, "stop-reason}", strlen("stop-reason}")) == 0)
{
Don't cache the public stop reason, since it can change as plan completion gets processed. That means GetStopReason needs to return a shared pointer, not a pointer to the thread's cached version. Also allow the thread plans to get and set the thread private stop reason - that is usually more appropriate for the logic the thread plans need to do. llvm-svn: 116892
2010-10-20 08:39:53 +08:00
StopInfoSP stop_info_sp = exe_ctx->thread->GetStopInfo ();
if (stop_info_sp)
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
Don't cache the public stop reason, since it can change as plan completion gets processed. That means GetStopReason needs to return a shared pointer, not a pointer to the thread's cached version. Also allow the thread plans to get and set the thread private stop reason - that is usually more appropriate for the logic the thread plans need to do. llvm-svn: 116892
2010-10-20 08:39:53 +08:00
cstr = stop_info_sp->GetDescription();
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
if (cstr && cstr[0])
{
s.PutCString(cstr);
var_success = true;
}
}
}
}
}
else if (::strncmp (var_name_begin, "target.", strlen("target.")) == 0)
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
Target *target = Target::GetTargetFromContexts (exe_ctx, sc);
if (target)
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
var_name_begin += ::strlen ("target.");
if (::strncmp (var_name_begin, "arch}", strlen("arch}")) == 0)
{
ArchSpec arch (target->GetArchitecture ());
if (arch.IsValid())
{
Abtracted all mach-o and ELF out of ArchSpec. This patch is a modified form of Stephen Wilson's idea (thanks for the input Stephen!). What I ended up doing was: - Got rid of ArchSpec::CPU (which was a generic CPU enumeration that mimics the contents of llvm::Triple::ArchType). We now rely upon the llvm::Triple to give us the machine type from llvm::Triple::ArchType. - There is a new ArchSpec::Core definition which further qualifies the CPU core we are dealing with into a single enumeration. If you need support for a new Core and want to debug it in LLDB, it must be added to this list. In the future we can allow for dynamic core registration, but for now it is hard coded. - The ArchSpec can now be initialized with a llvm::Triple or with a C string that represents the triple (it can just be an arch still like "i386"). - The ArchSpec can still initialize itself with a architecture type -- mach-o with cpu type and subtype, or ELF with e_machine + e_flags -- and this will then get translated into the internal llvm::Triple::ArchSpec + ArchSpec::Core. The mach-o cpu type and subtype can be accessed using the getter functions: uint32_t ArchSpec::GetMachOCPUType () const; uint32_t ArchSpec::GetMachOCPUSubType () const; But these functions are just converting out internal llvm::Triple::ArchSpec + ArchSpec::Core back into mach-o. Same goes for ELF. All code has been updated to deal with the changes. This should abstract us until later when the llvm::TargetSpec stuff gets finalized and we can then adopt it. llvm-svn: 126278
2011-02-23 08:35:02 +08:00
s.PutCString (arch.GetArchitectureName());
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
var_success = true;
}
}
}
}
break;
case 'm':
if (::strncmp (var_name_begin, "module.", strlen("module.")) == 0)
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
if (sc && sc->module_sp.get())
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
Module *module = sc->module_sp.get();
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
var_name_begin += ::strlen ("module.");
if (::strncmp (var_name_begin, "file.", strlen("file.")) == 0)
{
if (module->GetFileSpec())
{
var_name_begin += ::strlen ("file.");
if (::strncmp (var_name_begin, "basename}", strlen("basename}")) == 0)
{
format_file_spec.GetFilename() = module->GetFileSpec().GetFilename();
var_success = format_file_spec;
}
else if (::strncmp (var_name_begin, "fullpath}", strlen("fullpath}")) == 0)
{
format_file_spec = module->GetFileSpec();
var_success = format_file_spec;
}
}
}
}
}
break;
case 'f':
if (::strncmp (var_name_begin, "file.", strlen("file.")) == 0)
{
if (sc && sc->comp_unit != NULL)
{
var_name_begin += ::strlen ("file.");
if (::strncmp (var_name_begin, "basename}", strlen("basename}")) == 0)
{
format_file_spec.GetFilename() = sc->comp_unit->GetFilename();
var_success = format_file_spec;
}
else if (::strncmp (var_name_begin, "fullpath}", strlen("fullpath}")) == 0)
{
format_file_spec = *sc->comp_unit;
var_success = format_file_spec;
}
}
}
else if (::strncmp (var_name_begin, "frame.", strlen("frame.")) == 0)
{
if (exe_ctx && exe_ctx->frame)
{
var_name_begin += ::strlen ("frame.");
if (::strncmp (var_name_begin, "index}", strlen("index}")) == 0)
{
s.Printf("%u", exe_ctx->frame->GetFrameIndex());
var_success = true;
}
else if (::strncmp (var_name_begin, "pc}", strlen("pc}")) == 0)
{
reg_kind = eRegisterKindGeneric;
reg_num = LLDB_REGNUM_GENERIC_PC;
var_success = true;
}
else if (::strncmp (var_name_begin, "sp}", strlen("sp}")) == 0)
{
reg_kind = eRegisterKindGeneric;
reg_num = LLDB_REGNUM_GENERIC_SP;
var_success = true;
}
else if (::strncmp (var_name_begin, "fp}", strlen("fp}")) == 0)
{
reg_kind = eRegisterKindGeneric;
reg_num = LLDB_REGNUM_GENERIC_FP;
var_success = true;
}
else if (::strncmp (var_name_begin, "flags}", strlen("flags}")) == 0)
{
reg_kind = eRegisterKindGeneric;
reg_num = LLDB_REGNUM_GENERIC_FLAGS;
var_success = true;
}
else if (::strncmp (var_name_begin, "reg.", strlen ("reg.")) == 0)
{
Fixed issues with RegisterContext classes and the subclasses. There was an issue with the way the UnwindLLDB was handing out RegisterContexts: it was making shared pointers to register contexts and then handing out just the pointers (which would get put into shared pointers in the thread and stack frame classes) and cause double free issues. MallocScribble helped to find these issues after I did some other cleanup. To help avoid any RegisterContext issue in the future, all code that deals with them now returns shared pointers to the register contexts so we don't end up with multiple deletions. Also now that the RegisterContext class doesn't require a stack frame, we patched a memory leak where a StackFrame object was being created and leaked. Made the RegisterContext class not have a pointer to a StackFrame object as one register context class can be used for N inlined stack frames so there is not a 1 - 1 mapping. Updates the ExecutionContextScope part of the RegisterContext class to never return a stack frame to indicate this when it is asked to recreate the execution context. Now register contexts point to the concrete frame using a concrete frame index. Concrete frames are all of the frames that are actually formed on the stack of a thread. These concrete frames can be turned into one or more user visible frames due to inlining. Each inlined stack frame has the exact same register context (shared via shared pointers) as any parent inlined stack frames all the way up to the concrete frame itself. So now the stack frames and the register contexts should behave much better. llvm-svn: 122976
2011-01-07 06:15:06 +08:00
reg_ctx = exe_ctx->frame->GetRegisterContext().get();
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
if (reg_ctx)
{
var_name_begin += ::strlen ("reg.");
if (var_name_begin < var_name_end)
{
std::string reg_name (var_name_begin, var_name_end);
reg_info = reg_ctx->GetRegisterInfoByName (reg_name.c_str());
if (reg_info)
var_success = true;
}
}
}
}
}
else if (::strncmp (var_name_begin, "function.", strlen("function.")) == 0)
{
if (sc && (sc->function != NULL || sc->symbol != NULL))
{
var_name_begin += ::strlen ("function.");
if (::strncmp (var_name_begin, "id}", strlen("id}")) == 0)
{
if (sc->function)
s.Printf("function{0x%8.8x}", sc->function->GetID());
else
s.Printf("symbol[%u]", sc->symbol->GetID());
var_success = true;
}
else if (::strncmp (var_name_begin, "name}", strlen("name}")) == 0)
{
if (sc->function)
cstr = sc->function->GetName().AsCString (NULL);
else if (sc->symbol)
cstr = sc->symbol->GetName().AsCString (NULL);
if (cstr)
{
s.PutCString(cstr);
Fixed and issue where we weren't seeing inlined functions anymore. We also now show the correct pc-offset within the inlined function. llvm-svn: 115522
2010-10-05 01:26:49 +08:00
if (sc->block)
{
Block *inline_block = sc->block->GetContainingInlinedBlock ();
if (inline_block)
{
const InlineFunctionInfo *inline_info = sc->block->GetInlinedFunctionInfo();
if (inline_info)
{
s.PutCString(" [inlined] ");
inline_info->GetName().Dump(&s);
}
}
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
var_success = true;
}
}
else if (::strncmp (var_name_begin, "addr-offset}", strlen("addr-offset}")) == 0)
{
var_success = addr != NULL;
if (var_success)
{
format_addr = *addr;
calculate_format_addr_function_offset = true;
}
}
else if (::strncmp (var_name_begin, "line-offset}", strlen("line-offset}")) == 0)
{
var_success = sc->line_entry.range.GetBaseAddress().IsValid();
if (var_success)
{
format_addr = sc->line_entry.range.GetBaseAddress();
calculate_format_addr_function_offset = true;
}
}
else if (::strncmp (var_name_begin, "pc-offset}", strlen("pc-offset}")) == 0)
{
var_success = exe_ctx->frame;
if (var_success)
{
format_addr = exe_ctx->frame->GetFrameCodeAddress();
calculate_format_addr_function_offset = true;
}
}
}
}
break;
case 'l':
if (::strncmp (var_name_begin, "line.", strlen("line.")) == 0)
{
if (sc && sc->line_entry.IsValid())
{
var_name_begin += ::strlen ("line.");
if (::strncmp (var_name_begin, "file.", strlen("file.")) == 0)
{
var_name_begin += ::strlen ("file.");
if (::strncmp (var_name_begin, "basename}", strlen("basename}")) == 0)
{
format_file_spec.GetFilename() = sc->line_entry.file.GetFilename();
var_success = format_file_spec;
}
else if (::strncmp (var_name_begin, "fullpath}", strlen("fullpath}")) == 0)
{
format_file_spec = sc->line_entry.file;
var_success = format_file_spec;
}
}
else if (::strncmp (var_name_begin, "number}", strlen("number}")) == 0)
{
var_success = true;
s.Printf("%u", sc->line_entry.line);
}
else if ((::strncmp (var_name_begin, "start-addr}", strlen("start-addr}")) == 0) ||
(::strncmp (var_name_begin, "end-addr}", strlen("end-addr}")) == 0))
{
var_success = sc && sc->line_entry.range.GetBaseAddress().IsValid();
if (var_success)
{
format_addr = sc->line_entry.range.GetBaseAddress();
if (var_name_begin[0] == 'e')
format_addr.Slide (sc->line_entry.range.GetByteSize());
}
}
}
}
break;
}
if (var_success)
{
// If format addr is valid, then we need to print an address
if (reg_num != LLDB_INVALID_REGNUM)
{
// We have a register value to display...
if (reg_num == LLDB_REGNUM_GENERIC_PC && reg_kind == eRegisterKindGeneric)
{
format_addr = exe_ctx->frame->GetFrameCodeAddress();
}
else
{
if (reg_ctx == NULL)
Fixed issues with RegisterContext classes and the subclasses. There was an issue with the way the UnwindLLDB was handing out RegisterContexts: it was making shared pointers to register contexts and then handing out just the pointers (which would get put into shared pointers in the thread and stack frame classes) and cause double free issues. MallocScribble helped to find these issues after I did some other cleanup. To help avoid any RegisterContext issue in the future, all code that deals with them now returns shared pointers to the register contexts so we don't end up with multiple deletions. Also now that the RegisterContext class doesn't require a stack frame, we patched a memory leak where a StackFrame object was being created and leaked. Made the RegisterContext class not have a pointer to a StackFrame object as one register context class can be used for N inlined stack frames so there is not a 1 - 1 mapping. Updates the ExecutionContextScope part of the RegisterContext class to never return a stack frame to indicate this when it is asked to recreate the execution context. Now register contexts point to the concrete frame using a concrete frame index. Concrete frames are all of the frames that are actually formed on the stack of a thread. These concrete frames can be turned into one or more user visible frames due to inlining. Each inlined stack frame has the exact same register context (shared via shared pointers) as any parent inlined stack frames all the way up to the concrete frame itself. So now the stack frames and the register contexts should behave much better. llvm-svn: 122976
2011-01-07 06:15:06 +08:00
reg_ctx = exe_ctx->frame->GetRegisterContext().get();
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
if (reg_ctx)
{
if (reg_kind != kNumRegisterKinds)
reg_num = reg_ctx->ConvertRegisterKindToRegisterNumber(reg_kind, reg_num);
reg_info = reg_ctx->GetRegisterInfoAtIndex (reg_num);
var_success = reg_info != NULL;
}
}
}
if (reg_info != NULL)
{
While implementing unwind information using UnwindAssemblyInstEmulation I ran into some cleanup I have been wanting to do when reading/writing registers. Previously all RegisterContext subclasses would need to implement: virtual bool ReadRegisterBytes (uint32_t reg, DataExtractor &data); virtual bool WriteRegisterBytes (uint32_t reg, DataExtractor &data, uint32_t data_offset = 0); There is now a new class specifically designed to hold register values: lldb_private::RegisterValue The new register context calls that subclasses must implement are: virtual bool ReadRegister (const RegisterInfo *reg_info, RegisterValue &reg_value) = 0; virtual bool WriteRegister (const RegisterInfo *reg_info, const RegisterValue &reg_value) = 0; The RegisterValue class must be big enough to handle any register value. The class contains an enumeration for the value type, and then a union for the data value. Any integer/float values are stored directly in an appropriate host integer/float. Anything bigger is stored in a byte buffer that has a length and byte order. The RegisterValue class also knows how to copy register value bytes into in a buffer with a specified byte order which can be used to write the register value down into memory, and this does the right thing when not all bytes from the register values are needed (getting a uint8 from a uint32 register value..). All RegiterContext and other sources have been switched over to using the new regiter value class. llvm-svn: 131096
2011-05-10 04:18:18 +08:00
RegisterValue reg_value;
var_success = reg_ctx->ReadRegister (reg_info, reg_value);
if (var_success)
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
Added generic register numbers for simple ABI argument registers and defined the appropriate registers for arm and x86_64. The register names for the arguments that are the size of a pointer or less are all named "arg1", "arg2", etc. This allows you to read these registers by name: (lldb) register read arg1 arg2 arg3 ... You can also now specify you want to see alternate register names when executing the read register command: (lldb) register read --alternate (lldb) register read -A llvm-svn: 131376
2011-05-15 12:12:07 +08:00
reg_value.Dump(&s, reg_info, false, false, eFormatDefault);
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
}
}
if (format_file_spec)
{
s << format_file_spec;
}
// If format addr is valid, then we need to print an address
if (format_addr.IsValid())
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
var_success = false;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
if (calculate_format_addr_function_offset)
{
Address func_addr;
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
if (sc)
{
if (sc->function)
Fixed and issue where we weren't seeing inlined functions anymore. We also now show the correct pc-offset within the inlined function. llvm-svn: 115522
2010-10-05 01:26:49 +08:00
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
func_addr = sc->function->GetAddressRange().GetBaseAddress();
Fixed and issue where we weren't seeing inlined functions anymore. We also now show the correct pc-offset within the inlined function. llvm-svn: 115522
2010-10-05 01:26:49 +08:00
if (sc->block)
{
// Check to make sure we aren't in an inline
// function. If we are, use the inline block
// range that contains "format_addr" since
// blocks can be discontiguous.
Block *inline_block = sc->block->GetContainingInlinedBlock ();
AddressRange inline_range;
if (inline_block && inline_block->GetRangeContainingAddress (format_addr, inline_range))
func_addr = inline_range.GetBaseAddress();
}
}
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
else if (sc->symbol && sc->symbol->GetAddressRangePtr())
func_addr = sc->symbol->GetAddressRangePtr()->GetBaseAddress();
}
if (func_addr.IsValid())
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
if (func_addr.GetSection() == format_addr.GetSection())
{
addr_t func_file_addr = func_addr.GetFileAddress();
addr_t addr_file_addr = format_addr.GetFileAddress();
if (addr_file_addr > func_file_addr)
s.Printf(" + %llu", addr_file_addr - func_file_addr);
else if (addr_file_addr < func_file_addr)
s.Printf(" - %llu", func_file_addr - addr_file_addr);
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
var_success = true;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
}
else
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
{
Target *target = Target::GetTargetFromContexts (exe_ctx, sc);
if (target)
{
addr_t func_load_addr = func_addr.GetLoadAddress (target);
addr_t addr_load_addr = format_addr.GetLoadAddress (target);
if (addr_load_addr > func_load_addr)
s.Printf(" + %llu", addr_load_addr - func_load_addr);
else if (addr_load_addr < func_load_addr)
s.Printf(" - %llu", func_load_addr - addr_load_addr);
var_success = true;
}
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
}
}
else
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
Target *target = Target::GetTargetFromContexts (exe_ctx, sc);
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
addr_t vaddr = LLDB_INVALID_ADDRESS;
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
if (exe_ctx && !target->GetSectionLoadList().IsEmpty())
vaddr = format_addr.GetLoadAddress (target);
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
if (vaddr == LLDB_INVALID_ADDRESS)
vaddr = format_addr.GetFileAddress ();
if (vaddr != LLDB_INVALID_ADDRESS)
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
{
Made lldb_private::ArchSpec contain much more than just an architecture. It now, in addition to cpu type/subtype and architecture flavor, contains: - byte order (big endian, little endian) - address size in bytes - llvm::Triple for true target triple support and for more powerful plug-in selection. llvm-svn: 125602
2011-02-16 05:59:32 +08:00
int addr_width = target->GetArchitecture().GetAddressByteSize() * 2;
Print out addresses with the correct width for 32 bit programs. llvm-svn: 119786
2010-11-19 12:16:11 +08:00
if (addr_width == 0)
addr_width = 16;
s.Printf("0x%*.*llx", addr_width, addr_width, vaddr);
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
var_success = true;
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
}
}
}
if (var_success == false)
success = false;
}
p = var_name_end;
}
else
break;
}
else
{
// We got a dollar sign with no '{' after it, it must just be a dollar sign
s.PutChar(*p);
}
}
else if (*p == '\\')
{
++p; // skip the slash
switch (*p)
{
case 'a': s.PutChar ('\a'); break;
case 'b': s.PutChar ('\b'); break;
case 'f': s.PutChar ('\f'); break;
case 'n': s.PutChar ('\n'); break;
case 'r': s.PutChar ('\r'); break;
case 't': s.PutChar ('\t'); break;
case 'v': s.PutChar ('\v'); break;
case '\'': s.PutChar ('\''); break;
case '\\': s.PutChar ('\\'); break;
case '0':
// 1 to 3 octal chars
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
// Make a string that can hold onto the initial zero char,
// up to 3 octal digits, and a terminating NULL.
char oct_str[5] = { 0, 0, 0, 0, 0 };
int i;
for (i=0; (p[i] >= '0' && p[i] <= '7') && i<4; ++i)
oct_str[i] = p[i];
// We don't want to consume the last octal character since
// the main for loop will do this for us, so we advance p by
// one less than i (even if i is zero)
p += i - 1;
unsigned long octal_value = ::strtoul (oct_str, NULL, 8);
if (octal_value <= UINT8_MAX)
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
char octal_char = octal_value;
s.Write (&octal_char, 1);
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
}
}
break;
case 'x':
// hex number in the format
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
if (isxdigit(p[1]))
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
++p; // Skip the 'x'
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
// Make a string that can hold onto two hex chars plus a
// NULL terminator
char hex_str[3] = { 0,0,0 };
hex_str[0] = *p;
if (isxdigit(p[1]))
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
++p; // Skip the first of the two hex chars
hex_str[1] = *p;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
}
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
unsigned long hex_value = strtoul (hex_str, NULL, 16);
if (hex_value <= UINT8_MAX)
s.PutChar (hex_value);
}
else
{
s.PutChar('x');
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
}
break;
default:
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
// Just desensitize any other character by just printing what
// came after the '\'
s << *p;
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
break;
}
}
}
if (end)
*end = p;
return success;
}
Committing type format code for Enrico Granata. This commit adds a new top level command named "type". Currently this command implements three commands: type format add <format> <typename1> [<typename2> ...] type format delete <typename1> [<typename2> ...] type format list [<typename1> [<typename2>] ...] This allows you to specify the default format that will be used to display types when you use "frame variable" or "expression", or the SBValue classes. Examples: // Format uint*_t as hex type format add x uint16_t uint32_t uint64_t // Format intptr_t as a pointer type format add p intptr_t The format characters are the same as "printf" for the most part with many additions. These format character specifiers are also used in many other commands ("frame variable" for one). The current list of format characters include: a - char buffer b - binary B - boolean c - char C - printable char d - signed decimal e - float f - float g - float i - signed decimal I - complex integer o - octal O - OSType p - pointer s - c-string u - unsigned decimal x - hex X - complex float y - bytes Y - bytes with ASCII llvm-svn: 133728
2011-06-24 01:59:56 +08:00
static FormatManager&
GetFormatManager() {
static FormatManager g_format_manager;
return g_format_manager;
}
Python synthetic children: - you can now define a Python class as a synthetic children producer for a type the class must adhere to this "interface": def __init__(self, valobj, dict): def get_child_at_index(self, index): def get_child_index(self, name): then using type synth add -l className typeName (e.g. type synth add -l fooSynthProvider foo) (This is still WIP with lots to be added) A small test case is available also as reference llvm-svn: 135865
2011-07-24 08:14:56 +08:00
void
Debugger::Formatting::ForceUpdate()
{
GetFormatManager().Changed();
}
Committing type format code for Enrico Granata. This commit adds a new top level command named "type". Currently this command implements three commands: type format add <format> <typename1> [<typename2> ...] type format delete <typename1> [<typename2> ...] type format list [<typename1> [<typename2>] ...] This allows you to specify the default format that will be used to display types when you use "frame variable" or "expression", or the SBValue classes. Examples: // Format uint*_t as hex type format add x uint16_t uint32_t uint64_t // Format intptr_t as a pointer type format add p intptr_t The format characters are the same as "printf" for the most part with many additions. These format character specifiers are also used in many other commands ("frame variable" for one). The current list of format characters include: a - char buffer b - binary B - boolean c - char C - printable char d - signed decimal e - float f - float g - float i - signed decimal I - complex integer o - octal O - OSType p - pointer s - c-string u - unsigned decimal x - hex X - complex float y - bytes Y - bytes with ASCII llvm-svn: 133728
2011-06-24 01:59:56 +08:00
bool
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
Debugger::Formatting::ValueFormats::Get(ValueObject& vobj, lldb::DynamicValueType use_dynamic, ValueFormat::SharedPointer &entry)
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
return GetFormatManager().Value().Get(vobj,entry, use_dynamic);
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::ValueFormats::Add(const ConstString &type, const ValueFormat::SharedPointer &entry)
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
GetFormatManager().Value().Add(type.AsCString(),entry);
}
bool
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::ValueFormats::Delete(const ConstString &type)
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
return GetFormatManager().Value().Delete(type.AsCString());
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::ValueFormats::Clear()
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
GetFormatManager().Value().Clear();
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::ValueFormats::LoopThrough(ValueFormat::ValueCallback callback, void* callback_baton)
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
GetFormatManager().Value().LoopThrough(callback, callback_baton);
}
uint32_t
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::ValueFormats::GetCurrentRevision()
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
{
return GetFormatManager().GetCurrentRevision();
}
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
uint32_t
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::ValueFormats::GetCount()
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
{
return GetFormatManager().Value().GetCount();
}
This commit adds a new top subcommand "summary" to command type named "type". Currently this command implements three commands: type summary add <format> <typename1> [<typename2> ...] type summary delete <typename1> [<typename2> ...] type summary list [<typename1> [<typename2>] ...] type summary clear This allows you to specify the default format that will be used to display summaries for variables, shown when you use "frame variable" or "expression", or the SBValue classes. Examples: type summary add "x = ${var.x}" Point type summary list type summary add --one-liner SimpleType llvm-svn: 134108
2011-06-30 06:27:15 +08:00
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
bool
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::GetSummaryFormat(ValueObject& vobj,
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
lldb::DynamicValueType use_dynamic,
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
lldb::SummaryFormatSP& entry)
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
{
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
return GetFormatManager().Get(vobj, entry, use_dynamic);
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
}
when typing a summary string you can use the %S symbol to explicitly indicate that you want the summary to be used to print the target object (e.g. ${var%S}). this might already be the default if your variable is of an aggregate type new feature: synthetic filters. you can restrict the number of children for your variables to only a meaningful subset - the restricted list of children obeys the typical rules (e.g. summaries prevail over children) - one-line summaries show only the filtered (synthetic) children, if you type an expanded summary string, or you use Python scripts, all the real children are accessible - to provide a synthetic children list use the "type synth add" command, as in: type synth add foo_type --child varA --child varB[0] --child varC->packet->flags[1-4] (you can use ., ->, single-item array operator [N] and bitfield operator [N-M]; array slice access is not supported, giving simplified names to expression paths is not supported) - a new -S option to frame variable and target variable lets you override synthetic children and instead show real ones llvm-svn: 135731
2011-07-22 08:16:08 +08:00
bool
Debugger::Formatting::GetSyntheticFilter(ValueObject& vobj,
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
lldb::DynamicValueType use_dynamic,
Python synthetic children: - you can now define a Python class as a synthetic children producer for a type the class must adhere to this "interface": def __init__(self, valobj, dict): def get_child_at_index(self, index): def get_child_index(self, name): then using type synth add -l className typeName (e.g. type synth add -l fooSynthProvider foo) (This is still WIP with lots to be added) A small test case is available also as reference llvm-svn: 135865
2011-07-24 08:14:56 +08:00
lldb::SyntheticChildrenSP& entry)
when typing a summary string you can use the %S symbol to explicitly indicate that you want the summary to be used to print the target object (e.g. ${var%S}). this might already be the default if your variable is of an aggregate type new feature: synthetic filters. you can restrict the number of children for your variables to only a meaningful subset - the restricted list of children obeys the typical rules (e.g. summaries prevail over children) - one-line summaries show only the filtered (synthetic) children, if you type an expanded summary string, or you use Python scripts, all the real children are accessible - to provide a synthetic children list use the "type synth add" command, as in: type synth add foo_type --child varA --child varB[0] --child varC->packet->flags[1-4] (you can use ., ->, single-item array operator [N] and bitfield operator [N-M]; array slice access is not supported, giving simplified names to expression paths is not supported) - a new -S option to frame variable and target variable lets you override synthetic children and instead show real ones llvm-svn: 135731
2011-07-22 08:16:08 +08:00
{
Fixed a bug where a variable could not be formatted in a summary if its datatype already had a custom format Fixed a bug where Objective-C variables coming out of the expression parser could crash the Python synthetic providers: - expression parser output has a "frozen data" component, which is a byte-exact copy of the value (in host memory), if trying to read into memory based on the host address, LLDB would crash. we are now passing the correct (target) pointer to the Python code Objective-C "id" variables are now formatted according to their dynamic type, if the -d option to frame variable is used: - Code based on the Objective-C 2.0 runtime is used to obtain this information without running code on the target llvm-svn: 136695
2011-08-03 01:27:39 +08:00
return GetFormatManager().Get(vobj, entry, use_dynamic);
when typing a summary string you can use the %S symbol to explicitly indicate that you want the summary to be used to print the target object (e.g. ${var%S}). this might already be the default if your variable is of an aggregate type new feature: synthetic filters. you can restrict the number of children for your variables to only a meaningful subset - the restricted list of children obeys the typical rules (e.g. summaries prevail over children) - one-line summaries show only the filtered (synthetic) children, if you type an expanded summary string, or you use Python scripts, all the real children are accessible - to provide a synthetic children list use the "type synth add" command, as in: type synth add foo_type --child varA --child varB[0] --child varC->packet->flags[1-4] (you can use ., ->, single-item array operator [N] and bitfield operator [N-M]; array slice access is not supported, giving simplified names to expression paths is not supported) - a new -S option to frame variable and target variable lets you override synthetic children and instead show real ones llvm-svn: 135731
2011-07-22 08:16:08 +08:00
}
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
bool
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::Get(const ConstString &category, lldb::FormatCategorySP &entry)
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
entry = GetFormatManager().Category(category.GetCString());
return true;
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::Add(const ConstString &category)
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
GetFormatManager().Category(category.GetCString());
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
}
bool
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::Delete(const ConstString &category)
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
GetFormatManager().DisableCategory(category.GetCString());
return GetFormatManager().Categories().Delete(category.GetCString());
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::Clear()
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
GetFormatManager().Categories().Clear();
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::Clear(ConstString &category)
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
{
when typing a summary string you can use the %S symbol to explicitly indicate that you want the summary to be used to print the target object (e.g. ${var%S}). this might already be the default if your variable is of an aggregate type new feature: synthetic filters. you can restrict the number of children for your variables to only a meaningful subset - the restricted list of children obeys the typical rules (e.g. summaries prevail over children) - one-line summaries show only the filtered (synthetic) children, if you type an expanded summary string, or you use Python scripts, all the real children are accessible - to provide a synthetic children list use the "type synth add" command, as in: type synth add foo_type --child varA --child varB[0] --child varC->packet->flags[1-4] (you can use ., ->, single-item array operator [N] and bitfield operator [N-M]; array slice access is not supported, giving simplified names to expression paths is not supported) - a new -S option to frame variable and target variable lets you override synthetic children and instead show real ones llvm-svn: 135731
2011-07-22 08:16:08 +08:00
GetFormatManager().Category(category.GetCString())->ClearSummaries();
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::Enable(ConstString& category)
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
if (GetFormatManager().Category(category.GetCString())->IsEnabled() == false)
GetFormatManager().EnableCategory(category.GetCString());
else
{
GetFormatManager().DisableCategory(category.GetCString());
GetFormatManager().EnableCategory(category.GetCString());
}
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::Disable(ConstString& category)
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
if (GetFormatManager().Category(category.GetCString())->IsEnabled() == true)
GetFormatManager().DisableCategory(category.GetCString());
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::LoopThrough(FormatManager::CategoryCallback callback, void* callback_baton)
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
GetFormatManager().LoopThroughCategories(callback, callback_baton);
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
}
uint32_t
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::GetCurrentRevision()
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
{
return GetFormatManager().GetCurrentRevision();
}
uint32_t
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::Categories::GetCount()
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
{
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
return GetFormatManager().Categories().GetCount();
System-wide summaries: - Summaries for char*, const char* and char[] are loaded at startup as system-wide summaries. This means you cannot delete them unless you use the -a option to type summary delete/clear - You can add your own system-wide summaries by using the -w option to type summary add Several code improvements for the Python summaries feature llvm-svn: 135326
2011-07-16 07:30:15 +08:00
}
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
bool
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::NamedSummaryFormats::Get(const ConstString &type, SummaryFormat::SharedPointer &entry)
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
{
return GetFormatManager().NamedSummary().Get(type.AsCString(),entry);
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::NamedSummaryFormats::Add(const ConstString &type, const SummaryFormat::SharedPointer &entry)
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
{
GetFormatManager().NamedSummary().Add(type.AsCString(),entry);
}
bool
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::NamedSummaryFormats::Delete(const ConstString &type)
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
{
return GetFormatManager().NamedSummary().Delete(type.AsCString());
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::NamedSummaryFormats::Clear()
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
{
GetFormatManager().NamedSummary().Clear();
}
void
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::NamedSummaryFormats::LoopThrough(SummaryFormat::SummaryCallback callback, void* callback_baton)
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
{
GetFormatManager().NamedSummary().LoopThrough(callback, callback_baton);
}
uint32_t
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::NamedSummaryFormats::GetCurrentRevision()
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
{
return GetFormatManager().GetCurrentRevision();
}
uint32_t
Fixed a bug where deleting a regex summary would not immediately reflect in the variables display The "systemwide summaries" feature has been removed and replaced with a more general and powerful mechanism. Categories: - summaries can now be grouped into buckets, called "categories" (it is expected that categories correspond to libraries and/or runtime environments) - to add a summary to a category, you can use the -w option to type summary add and give a category name (e.g. type summary add -f "foo" foo_t -w foo_category) - categories are by default disabled, which means LLDB will not look into them for summaries, to enable a category use "type category enable". once a category is enabled, LLDB will look into that category for summaries. the rules are quite trivial: every enabled category is searched for an exact match. if an exact match is nowhere to be found, any match is searched for in every enabled category (whether it involves cascading, going to base classes, ...). categories are searched into the order in which they were enabled (the most recently enabled category first, then the second most and so on..) - by default, most commands that deal with summaries, use a category named "default" if no explicit -w parameter is given (the observable behavior of LLDB should not change when categories are not explicitly used) - the systemwide summaries are now part of a "system" category llvm-svn: 135463
2011-07-19 10:34:21 +08:00
Debugger::Formatting::NamedSummaryFormats::GetCount()
named summaries: - a new --name option for "type summary add" lets you give a name to a summary - a new --summary option for "frame variable" lets you bind a named summary to one or more variables ${var%s} now works for printing the value of 0-terminated CStrings type format test case now tests for cascading - this is disabled on GCC because GCC may end up stripping typedef chains, basically breaking cascading new design for the FormatNavigator class new template class CleanUp2 meant to support cleanup routines with 1 additional parameter beyond resource handle llvm-svn: 134943
2011-07-12 08:18:11 +08:00
{
return GetFormatManager().NamedSummary().GetCount();
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
#pragma mark Debugger::SettingsController
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
//--------------------------------------------------
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
// class Debugger::SettingsController
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
//--------------------------------------------------
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
Debugger::SettingsController::SettingsController () :
Make all debugger-level user settable variables into instance variables. Make get/set variable at the debugger level always set the particular debugger's instance variables rather than the default variables. llvm-svn: 113474
2010-09-09 14:25:08 +08:00
UserSettingsController ("", lldb::UserSettingsControllerSP())
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
Make sure creating a pending instance doesn't also trigger creating a live instance; also make sure creating a pending instance uses the specified instance name rather than creating a new one; add brackets to instance names when searching for and removing pending instances. llvm-svn: 113370
2010-09-09 01:48:55 +08:00
m_default_settings.reset (new DebuggerInstanceSettings (*this, false,
InstanceSettings::GetDefaultName().AsCString()));
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
Debugger::SettingsController::~SettingsController ()
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
}
lldb::InstanceSettingsSP
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
Debugger::SettingsController::CreateInstanceSettings (const char *instance_name)
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
Fixed an issue where the UserSettingsControllers were being created out of order and this was causing the target, process and thread trees to not be available. llvm-svn: 119784
2010-11-19 11:46:01 +08:00
DebuggerInstanceSettings *new_settings = new DebuggerInstanceSettings (*GetSettingsController(),
Make sure creating a pending instance doesn't also trigger creating a live instance; also make sure creating a pending instance uses the specified instance name rather than creating a new one; add brackets to instance names when searching for and removing pending instances. llvm-svn: 113370
2010-09-09 01:48:55 +08:00
false, instance_name);
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
lldb::InstanceSettingsSP new_settings_sp (new_settings);
return new_settings_sp;
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
#pragma mark DebuggerInstanceSettings
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
//--------------------------------------------------
// class DebuggerInstanceSettings
//--------------------------------------------------
Fixed the way set/show variables were being accessed to being natively accessed by the objects that own the settings. The previous approach wasn't very usable and made for a lot of unnecessary code just to access variables that were already owned by the objects. While I fixed those things, I saw that CommandObject objects should really have a reference to their command interpreter so they can access the terminal with if they want to output usaage. Fixed up all CommandObjects to take an interpreter and cleaned up the API to not need the interpreter to be passed in. Fixed the disassemble command to output the usage if no options are passed down and arguments are passed (all disassebmle variants take options, there are no "args only"). llvm-svn: 114252
2010-09-18 09:14:36 +08:00
DebuggerInstanceSettings::DebuggerInstanceSettings
(
UserSettingsController &owner,
bool live_instance,
const char *name
) :
Added the ability for a process to inherit the current host environment. This was done as an settings variable in the process for now. We will eventually move all environment stuff over to the target, but we will leave it with the process for now. The default setting is for a process to inherit the host environment. This can be disabled by setting the "inherit-env" setting to false in the process. llvm-svn: 120862
2010-12-04 08:10:17 +08:00
InstanceSettings (owner, name ? name : InstanceSettings::InvalidName().AsCString(), live_instance),
Fixed the way set/show variables were being accessed to being natively accessed by the objects that own the settings. The previous approach wasn't very usable and made for a lot of unnecessary code just to access variables that were already owned by the objects. While I fixed those things, I saw that CommandObject objects should really have a reference to their command interpreter so they can access the terminal with if they want to output usaage. Fixed up all CommandObjects to take an interpreter and cleaned up the API to not need the interpreter to be passed in. Fixed the disassemble command to output the usage if no options are passed down and arguments are passed (all disassebmle variants take options, there are no "args only"). llvm-svn: 114252
2010-09-18 09:14:36 +08:00
m_term_width (80),
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
m_prompt (),
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
m_frame_format (),
m_thread_format (),
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
m_script_lang (),
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
m_use_external_editor (false),
m_auto_confirm_on (false)
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
Add comments to InstanceSettings constructors explaining why they have to be set up the way they are. Comment out code that removes pending settings for live instances (after the settings are copied over). llvm-svn: 113519
2010-09-10 02:26:37 +08:00
// CopyInstanceSettings is a pure virtual function in InstanceSettings; it therefore cannot be called
// until the vtables for DebuggerInstanceSettings are properly set up, i.e. AFTER all the initializers.
// For this reason it has to be called here, rather than in the initializer or in the parent constructor.
Fix issues with CreateInstanceName, a virtual function, being called in an initializer. llvm-svn: 114107
2010-09-17 03:05:55 +08:00
// The same is true of CreateInstanceName().
if (GetInstanceName() == InstanceSettings::InvalidName())
{
ChangeInstanceName (std::string (CreateInstanceName().AsCString()));
m_owner.RegisterInstanceSettings (this);
}
Add comments to InstanceSettings constructors explaining why they have to be set up the way they are. Comment out code that removes pending settings for live instances (after the settings are copied over). llvm-svn: 113519
2010-09-10 02:26:37 +08:00
if (live_instance)
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
const lldb::InstanceSettingsSP &pending_settings = m_owner.FindPendingSettings (m_instance_name);
CopyInstanceSettings (pending_settings, false);
}
}
DebuggerInstanceSettings::DebuggerInstanceSettings (const DebuggerInstanceSettings &rhs) :
Cleaned up code that wasn't using the Initialize and Terminate paradigm by changing it to use it. There was an extra parameter added to the static accessor global user settings controllers that wasn't needed. A bool was being used as a parameter to the accessor just so it could be used to clean up the global user settings controller which is now fixed by splitting up the initialization into the "static void Class::Initialize()", access into the "static UserSettingsControllerSP & Class::GetSettingsController()", and cleanup into "static void Class::Terminate()". Also added initialize and terminate calls to the logging code to avoid issues when LLDB is shutting down. There were cases after the logging was switched over to use shared pointers where we could crash if the global destructor chain was being run and it causes the log to be destroyed and any any logging occurred. llvm-svn: 119757
2010-11-19 07:32:35 +08:00
InstanceSettings (*Debugger::GetSettingsController(), CreateInstanceName ().AsCString()),
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
m_prompt (rhs.m_prompt),
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
m_frame_format (rhs.m_frame_format),
m_thread_format (rhs.m_thread_format),
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
m_script_lang (rhs.m_script_lang),
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
m_use_external_editor (rhs.m_use_external_editor),
m_auto_confirm_on(rhs.m_auto_confirm_on)
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
const lldb::InstanceSettingsSP &pending_settings = m_owner.FindPendingSettings (m_instance_name);
CopyInstanceSettings (pending_settings, false);
m_owner.RemovePendingSettings (m_instance_name);
}
DebuggerInstanceSettings::~DebuggerInstanceSettings ()
{
}
DebuggerInstanceSettings&
DebuggerInstanceSettings::operator= (const DebuggerInstanceSettings &rhs)
{
if (this != &rhs)
{
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
m_term_width = rhs.m_term_width;
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
m_prompt = rhs.m_prompt;
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
m_frame_format = rhs.m_frame_format;
m_thread_format = rhs.m_thread_format;
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
m_script_lang = rhs.m_script_lang;
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
m_use_external_editor = rhs.m_use_external_editor;
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
m_auto_confirm_on = rhs.m_auto_confirm_on;
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
}
return *this;
}
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
bool
DebuggerInstanceSettings::ValidTermWidthValue (const char *value, Error err)
{
bool valid = false;
// Verify we have a value string.
if (value == NULL || value[0] == '\0')
{
err.SetErrorString ("Missing value. Can't set terminal width without a value.\n");
}
else
{
char *end = NULL;
const uint32_t width = ::strtoul (value, &end, 0);
Fixed lldb 'settings set term-widt 70' command not working. rdar://problem/8449849 llvm-svn: 114328
2010-09-21 00:36:43 +08:00
if (end && end[0] == '\0')
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
{
Fixed wrong logic in validating term-width value; should be && instead of ||. llvm-svn: 114330
2010-09-21 01:04:41 +08:00
if (width >= 10 && width <= 1024)
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
valid = true;
else
err.SetErrorString ("Invalid term-width value; value must be between 10 and 1024.\n");
}
else
err.SetErrorStringWithFormat ("'%s' is not a valid unsigned integer string.\n", value);
}
return valid;
}
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
void
DebuggerInstanceSettings::UpdateInstanceSettingsVariable (const ConstString &var_name,
const char *index_value,
const char *value,
const ConstString &instance_name,
const SettingEntry &entry,
Fixed the LLDB build so that we can have private types, private enums and public types and public enums. This was done to keep the SWIG stuff from parsing all sorts of enums and types that weren't needed, and allows us to abstract our API better. llvm-svn: 128239
2011-03-25 05:19:54 +08:00
VarSetOperationType op,
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
Error &err,
bool pending)
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
if (var_name == TermWidthVarName())
{
if (ValidTermWidthValue (value, err))
{
m_term_width = ::strtoul (value, NULL, 0);
}
}
else if (var_name == PromptVarName())
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
Make all debugger-level user settable variables into instance variables. Make get/set variable at the debugger level always set the particular debugger's instance variables rather than the default variables. llvm-svn: 113474
2010-09-09 14:25:08 +08:00
UserSettingsController::UpdateStringVariable (op, m_prompt, value, err);
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
if (!pending)
{
Fix various minor bugs in the Settings stuff. llvm-svn: 113245
2010-09-08 02:35:40 +08:00
// 'instance_name' is actually (probably) in the form '[<instance_name>]'; if so, we need to
// strip off the brackets before passing it to BroadcastPromptChange.
std::string tmp_instance_name (instance_name.AsCString());
if ((tmp_instance_name[0] == '[')
&& (tmp_instance_name[instance_name.GetLength() - 1] == ']'))
tmp_instance_name = tmp_instance_name.substr (1, instance_name.GetLength() - 2);
ConstString new_name (tmp_instance_name.c_str());
BroadcastPromptChange (new_name, m_prompt.c_str());
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
}
}
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
else if (var_name == GetFrameFormatName())
{
UserSettingsController::UpdateStringVariable (op, m_frame_format, value, err);
}
else if (var_name == GetThreadFormatName())
{
UserSettingsController::UpdateStringVariable (op, m_thread_format, value, err);
}
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
else if (var_name == ScriptLangVarName())
{
bool success;
m_script_lang = Args::StringToScriptLanguage (value, eScriptLanguageDefault,
&success);
}
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
else if (var_name == UseExternalEditorVarName ())
{
Did some work on the "register read" command to only show the first register set by default when dumping registers. If you want to see all of the register sets you can use the "--all" option: (lldb) register read --all If you want to just see some register sets, you can currently specify them by index: (lldb) register read --set 0 --set 2 We need to get shorter register set names soon so we can specify the register sets by name without having to type too much. I will make this change soon. You can also have any integer encoded registers resolve the address values back to any code or data from the object files using the "--lookup" option. Below is sample output when stopped in the libc function "puts" with some const strings in registers: Process 8973 stopped * thread #1: tid = 0x2c03, 0x00007fff828fa30f libSystem.B.dylib`puts + 1, stop reason = instruction step into frame #0: 0x00007fff828fa30f libSystem.B.dylib`puts + 1 (lldb) register read --lookup General Purpose Registers: rax = 0x0000000100000e98 "----------------------------------------------------------------------" rbx = 0x0000000000000000 rcx = 0x0000000000000001 rdx = 0x0000000000000000 rdi = 0x0000000100000e98 "----------------------------------------------------------------------" rsi = 0x0000000100800000 rbp = 0x00007fff5fbff710 rsp = 0x00007fff5fbff280 r8 = 0x0000000000000040 r9 = 0x0000000000000000 r10 = 0x0000000000000000 r11 = 0x0000000000000246 r12 = 0x0000000000000000 r13 = 0x0000000000000000 r14 = 0x0000000000000000 r15 = 0x0000000000000000 rip = 0x00007fff828fa30f libSystem.B.dylib`puts + 1 rflags = 0x0000000000000246 cs = 0x0000000000000027 fs = 0x0000000000000000 gs = 0x0000000000000000 As we can see, we see two constant strings and the PC (register "rip") is showing the code it resolves to. I fixed the register "--format" option to work as expected. Added a setting to disable skipping the function prologue when setting breakpoints as a target settings variable: (lldb) settings set target.skip-prologue false Updated the user settings controller boolean value handler funciton to be able to take the default value so it can correctly respond to the eVarSetOperationClear operation. Did some usability work on the OptionValue classes. Fixed the "image lookup" command to correctly respond to the "--verbose" option and display the detailed symbol context information when looking up line table entries and functions by name. This previously was only working for address lookups. llvm-svn: 129977
2011-04-22 11:55:06 +08:00
UserSettingsController::UpdateBooleanVariable (op, m_use_external_editor, value, false, err);
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
}
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
else if (var_name == AutoConfirmName ())
{
Did some work on the "register read" command to only show the first register set by default when dumping registers. If you want to see all of the register sets you can use the "--all" option: (lldb) register read --all If you want to just see some register sets, you can currently specify them by index: (lldb) register read --set 0 --set 2 We need to get shorter register set names soon so we can specify the register sets by name without having to type too much. I will make this change soon. You can also have any integer encoded registers resolve the address values back to any code or data from the object files using the "--lookup" option. Below is sample output when stopped in the libc function "puts" with some const strings in registers: Process 8973 stopped * thread #1: tid = 0x2c03, 0x00007fff828fa30f libSystem.B.dylib`puts + 1, stop reason = instruction step into frame #0: 0x00007fff828fa30f libSystem.B.dylib`puts + 1 (lldb) register read --lookup General Purpose Registers: rax = 0x0000000100000e98 "----------------------------------------------------------------------" rbx = 0x0000000000000000 rcx = 0x0000000000000001 rdx = 0x0000000000000000 rdi = 0x0000000100000e98 "----------------------------------------------------------------------" rsi = 0x0000000100800000 rbp = 0x00007fff5fbff710 rsp = 0x00007fff5fbff280 r8 = 0x0000000000000040 r9 = 0x0000000000000000 r10 = 0x0000000000000000 r11 = 0x0000000000000246 r12 = 0x0000000000000000 r13 = 0x0000000000000000 r14 = 0x0000000000000000 r15 = 0x0000000000000000 rip = 0x00007fff828fa30f libSystem.B.dylib`puts + 1 rflags = 0x0000000000000246 cs = 0x0000000000000027 fs = 0x0000000000000000 gs = 0x0000000000000000 As we can see, we see two constant strings and the PC (register "rip") is showing the code it resolves to. I fixed the register "--format" option to work as expected. Added a setting to disable skipping the function prologue when setting breakpoints as a target settings variable: (lldb) settings set target.skip-prologue false Updated the user settings controller boolean value handler funciton to be able to take the default value so it can correctly respond to the eVarSetOperationClear operation. Did some usability work on the OptionValue classes. Fixed the "image lookup" command to correctly respond to the "--verbose" option and display the detailed symbol context information when looking up line table entries and functions by name. This previously was only working for address lookups. llvm-svn: 129977
2011-04-22 11:55:06 +08:00
UserSettingsController::UpdateBooleanVariable (op, m_auto_confirm_on, value, false, err);
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
}
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
}
Make GetInstanceSettingsValue methods take an Error * rather than an Error &, and have them return a bool to indicate success or not. llvm-svn: 114361
2010-09-21 05:37:42 +08:00
bool
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
DebuggerInstanceSettings::GetInstanceSettingsValue (const SettingEntry &entry,
const ConstString &var_name,
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
StringList &value,
Make GetInstanceSettingsValue methods take an Error * rather than an Error &, and have them return a bool to indicate success or not. llvm-svn: 114361
2010-09-21 05:37:42 +08:00
Error *err)
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
if (var_name == PromptVarName())
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
value.AppendString (m_prompt.c_str(), m_prompt.size());
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
}
else if (var_name == ScriptLangVarName())
{
value.AppendString (ScriptInterpreter::LanguageToString (m_script_lang).c_str());
}
Make all debugger-level user settable variables into instance variables. Make get/set variable at the debugger level always set the particular debugger's instance variables rather than the default variables. llvm-svn: 113474
2010-09-09 14:25:08 +08:00
else if (var_name == TermWidthVarName())
{
StreamString width_str;
width_str.Printf ("%d", m_term_width);
value.AppendString (width_str.GetData());
}
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
else if (var_name == GetFrameFormatName ())
{
value.AppendString(m_frame_format.c_str(), m_frame_format.size());
}
else if (var_name == GetThreadFormatName ())
{
value.AppendString(m_thread_format.c_str(), m_thread_format.size());
}
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
else if (var_name == UseExternalEditorVarName())
{
if (m_use_external_editor)
value.AppendString ("true");
else
value.AppendString ("false");
}
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
else if (var_name == AutoConfirmName())
{
if (m_auto_confirm_on)
value.AppendString ("true");
else
value.AppendString ("false");
}
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
else
Make GetInstanceSettingsValue methods take an Error * rather than an Error &, and have them return a bool to indicate success or not. llvm-svn: 114361
2010-09-21 05:37:42 +08:00
{
if (err)
err->SetErrorStringWithFormat ("unrecognized variable name '%s'", var_name.AsCString());
return false;
}
return true;
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
}
void
DebuggerInstanceSettings::CopyInstanceSettings (const lldb::InstanceSettingsSP &new_settings,
bool pending)
{
if (new_settings.get() == NULL)
return;
DebuggerInstanceSettings *new_debugger_settings = (DebuggerInstanceSettings *) new_settings.get();
m_prompt = new_debugger_settings->m_prompt;
if (!pending)
Fix various minor bugs in the Settings stuff. llvm-svn: 113245
2010-09-08 02:35:40 +08:00
{
// 'instance_name' is actually (probably) in the form '[<instance_name>]'; if so, we need to
// strip off the brackets before passing it to BroadcastPromptChange.
std::string tmp_instance_name (m_instance_name.AsCString());
if ((tmp_instance_name[0] == '[')
&& (tmp_instance_name[m_instance_name.GetLength() - 1] == ']'))
tmp_instance_name = tmp_instance_name.substr (1, m_instance_name.GetLength() - 2);
ConstString new_name (tmp_instance_name.c_str());
BroadcastPromptChange (new_name, m_prompt.c_str());
}
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
m_frame_format = new_debugger_settings->m_frame_format;
m_thread_format = new_debugger_settings->m_thread_format;
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
m_term_width = new_debugger_settings->m_term_width;
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
m_script_lang = new_debugger_settings->m_script_lang;
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
m_use_external_editor = new_debugger_settings->m_use_external_editor;
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
m_auto_confirm_on = new_debugger_settings->m_auto_confirm_on;
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
}
bool
DebuggerInstanceSettings::BroadcastPromptChange (const ConstString &instance_name, const char *new_prompt)
{
std::string tmp_prompt;
if (new_prompt != NULL)
{
tmp_prompt = new_prompt ;
int len = tmp_prompt.size();
if (len > 1
&& (tmp_prompt[0] == '\'' || tmp_prompt[0] == '"')
&& (tmp_prompt[len-1] == tmp_prompt[0]))
{
tmp_prompt = tmp_prompt.substr(1,len-2);
}
len = tmp_prompt.size();
if (tmp_prompt[len-1] != ' ')
tmp_prompt.append(" ");
}
EventSP new_event_sp;
new_event_sp.reset (new Event(CommandInterpreter::eBroadcastBitResetPrompt,
new EventDataBytes (tmp_prompt.c_str())));
if (instance_name.GetLength() != 0)
{
// Set prompt for a particular instance.
Debugger *dbg = Debugger::FindDebuggerWithInstanceName (instance_name).get();
if (dbg != NULL)
{
dbg->GetCommandInterpreter().BroadcastEvent (new_event_sp);
}
}
return true;
}
const ConstString
DebuggerInstanceSettings::CreateInstanceName ()
{
static int instance_count = 1;
StreamString sstr;
sstr.Printf ("debugger_%d", instance_count);
++instance_count;
const ConstString ret_val (sstr.GetData());
return ret_val;
}
const ConstString &
DebuggerInstanceSettings::PromptVarName ()
{
static ConstString prompt_var_name ("prompt");
return prompt_var_name;
}
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
const ConstString &
DebuggerInstanceSettings::GetFrameFormatName ()
{
static ConstString prompt_var_name ("frame-format");
return prompt_var_name;
}
const ConstString &
DebuggerInstanceSettings::GetThreadFormatName ()
{
static ConstString prompt_var_name ("thread-format");
return prompt_var_name;
}
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
const ConstString &
DebuggerInstanceSettings::ScriptLangVarName ()
{
static ConstString script_lang_var_name ("script-lang");
return script_lang_var_name;
}
Make all debugger-level user settable variables into instance variables. Make get/set variable at the debugger level always set the particular debugger's instance variables rather than the default variables. llvm-svn: 113474
2010-09-09 14:25:08 +08:00
const ConstString &
DebuggerInstanceSettings::TermWidthVarName ()
{
static ConstString term_width_var_name ("term-width");
return term_width_var_name;
}
Add UserSettings to Target class, making Target settings the parent of Process settings; add 'default-arch' as a class-wide setting for Target. Replace lldb::GetDefaultArchitecture with Target::GetDefaultArchitecture & Target::SetDefaultArchitecture. Add 'use-external-editor' as user setting to Debugger class & update code appropriately. Add Error parameter to methods that get user settings, for easier reporting of bad requests. Fix various other minor related bugs. Fix test cases to work with new changes. llvm-svn: 114352
2010-09-21 04:44:43 +08:00
const ConstString &
DebuggerInstanceSettings::UseExternalEditorVarName ()
{
static ConstString use_external_editor_var_name ("use-external-editor");
return use_external_editor_var_name;
}
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
const ConstString &
DebuggerInstanceSettings::AutoConfirmName ()
{
static ConstString use_external_editor_var_name ("auto-confirm");
return use_external_editor_var_name;
}
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
//--------------------------------------------------
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
// SettingsController Variable Tables
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
//--------------------------------------------------
SettingEntry
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
Debugger::SettingsController::global_settings_table[] =
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
//{ "var-name", var-type, "default", enum-table, init'd, hidden, "help-text"},
Make all debugger-level user settable variables into instance variables. Make get/set variable at the debugger level always set the particular debugger's instance variables rather than the default variables. llvm-svn: 113474
2010-09-09 14:25:08 +08:00
// The Debugger level global table should always be empty; all Debugger settable variables should be instance
// variables.
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{ NULL, eSetVarTypeNone, NULL, NULL, 0, 0, NULL }
};
Fixed an issue with the default frame format settings string where if a frame was stopped in a module, yet had no valid function for the PC, no module would be displayed. llvm-svn: 115490
2010-10-04 10:44:26 +08:00
#define MODULE_WITH_FUNC "{ ${module.file.basename}{`${function.name}${function.pc-offset}}}"
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
#define FILE_AND_LINE "{ at ${line.file.basename}:${line.number}}"
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
#define DEFAULT_THREAD_FORMAT "thread #${thread.index}: tid = ${thread.id}"\
"{, ${frame.pc}}"\
MODULE_WITH_FUNC\
Added file and line back to the default thread format. llvm-svn: 115519
2010-10-05 01:04:23 +08:00
FILE_AND_LINE\
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
"{, stop reason = ${thread.stop-reason}}"\
"\\n"
Fixed our overly verbose stop reasons which by default included the thread name and thread queue. Users can modify the thread-format strings to add these back if needed. llvm-svn: 118000
2010-11-02 09:53:21 +08:00
//#define DEFAULT_THREAD_FORMAT "thread #${thread.index}: tid = ${thread.id}"\
// "{, ${frame.pc}}"\
// MODULE_WITH_FUNC\
// FILE_AND_LINE\
// "{, stop reason = ${thread.stop-reason}}"\
// "{, name = ${thread.name}}"\
// "{, queue = ${thread.queue}}"\
// "\\n"
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
#define DEFAULT_FRAME_FORMAT "frame #${frame.index}: ${frame.pc}"\
MODULE_WITH_FUNC\
FILE_AND_LINE\
"\\n"
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
SettingEntry
Added code that will allow completely customizable prompts for use in replacing the "(lldb)" prompt, the "frame #1..." displays when doing stack backtracing and the "thread #1....". This will allow you to see exactly the information that you want to see where you want to see it. This currently isn't hookup up to the prompts yet, but it will be soon. So what is the format of the prompts? Prompts can contain variables that have access to the current program state. Variables are text that appears in between a prefix of "${" and ends with a "}". Some of the interesting variables include: // The frame index (0, 1, 2, 3...) ${frame.index} // common frame registers with generic names ${frame.pc} ${frame.sp} ${frame.fp} ${frame.ra} ${frame.flags} // Access to any frame registers by name where REGNAME is any register name: ${frame.reg.REGNAME} // The current compile unit file where the frame is located ${file.basename} ${file.fullpath} // Function information ${function.name} ${function.pc-offset} // Process info ${process.file.basename} ${process.file.fullpath} ${process.id} ${process.name} // Thread info ${thread.id} ${thread.index} ${thread.name} ${thread.queue} ${thread.stop-reason} // Target information ${target.arch} // The current module for the current frame (the shared library or executable // that contains the current frame PC value): ${module.file.basename} ${module.file.fullpath} // Access to the line entry for where the current frame is when your thread // is stopped: ${line.file.basename} ${line.file.fullpath} ${line.number} ${line.start-addr} ${line.end-addr} Many times the information that you might have in your prompt might not be available and you won't want it to print out if it isn't valid. To take care of this you can enclose everything that must resolve into a scope. A scope is starts with '{' and ends with '}'. For example in order to only display the current file and line number when the information is available the format would be: "{ at {$line.file.basename}:${line.number}}" Broken down this is: start the scope: "{" format whose content will only be displayed if all information is available: "at {$line.file.basename}:${line.number}" end the scope: "}" We currently can represent the infomration we see when stopped at a frame: frame #0: 0x0000000100000e85 a.out`main + 4 at test.c:19 with the following format: "frame #${frame.index}: ${frame.pc} {${module.file.basename}`}{${function.name}{${function.pc-offset}}{ at ${line.file.basename}:${line.number}}\n" This breaks down to always print: "frame #${frame.index}: ${frame.pc} " only print the module followed by a tick if we have a valid module: "{${module.file.basename}`}" print the function name with optional offset: "{${function.name}{${function.pc-offset}}" print the line info if it is available: "{ at ${line.file.basename}:${line.number}}" then finish off with a newline: "\n" Notice you can also put newlines ("\n") and tabs and everything else you are used to putting in a format string when desensitized with the \ character. Cleaned up some of the user settings controller subclasses. All of them do not have any global settings variables and were all implementing stubs for the get/set global settings variable. Now there is a default version in UserSettingsController that will do nothing. llvm-svn: 114306
2010-09-19 10:33:57 +08:00
Debugger::SettingsController::instance_settings_table[] =
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
{
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
// NAME Setting variable type Default Enum Init'd Hidden Help
// ======================= ======================= ====================== ==== ====== ====== ======================
{ "frame-format", eSetVarTypeString, DEFAULT_FRAME_FORMAT, NULL, false, false, "The default frame format string to use when displaying thread information." },
Fix the default prompt to have a space. llvm-svn: 117150
2010-10-23 05:15:00 +08:00
{ "prompt", eSetVarTypeString, "(lldb) ", NULL, false, false, "The debugger command line prompt displayed for the user." },
Add an "auto-confirm" setting to the debugger so you can turn off the confirmations if you want to. llvm-svn: 115572
2010-10-05 06:44:14 +08:00
{ "script-lang", eSetVarTypeString, "python", NULL, false, false, "The script language to be used for evaluating user-written scripts." },
{ "term-width", eSetVarTypeInt, "80" , NULL, false, false, "The maximum number of columns to use for displaying text." },
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
{ "thread-format", eSetVarTypeString, DEFAULT_THREAD_FORMAT, NULL, false, false, "The default thread format string to use when displaying thread information." },
Add ThreadPlanTracer class to allow instruction step tracing of execution. Also changed eSetVarTypeBool to eSetVarTypeBoolean to make it consistent with eArgTypeBoolean. llvm-svn: 118824
2010-11-12 03:26:09 +08:00
{ "use-external-editor", eSetVarTypeBoolean, "false", NULL, false, false, "Whether to use an external editor or not." },
{ "auto-confirm", eSetVarTypeBoolean, "false", NULL, false, false, "If true all confirmation prompts will receive their default reply." },
There are now to new "settings set" variables that live in each debugger instance: settings set frame-format <string> settings set thread-format <string> This allows users to control the information that is seen when dumping threads and frames. The default values are set such that they do what they used to do prior to changing over the the user defined formats. This allows users with terminals that can display color to make different items different colors using the escape control codes. A few alias examples that will colorize your thread and frame prompts are: settings set frame-format 'frame #${frame.index}: \033[0;33m${frame.pc}\033[0m{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{ \033[0;35mat \033[1;35m${line.file.basename}:${line.number}}\033[0m\n' settings set thread-format 'thread #${thread.index}: \033[1;33mtid\033[0;33m = ${thread.id}\033[0m{, \033[0;33m${frame.pc}\033[0m}{ \033[1;4;36m${module.file.basename}\033[0;36m ${function.name}{${function.pc-offset}}\033[0m}{, \033[1;35mstop reason\033[0;35m = ${thread.stop-reason}\033[0m}{, \033[1;36mname = \033[0;36m${thread.name}\033[0m}{, \033[1;32mqueue = \033[0;32m${thread.queue}}\033[0m\n' A quick web search for "colorize terminal output" should allow you to see what you can do to make your output look like you want it. The "settings set" commands above can of course be added to your ~/.lldbinit file for permanent use. Changed the pure virtual void ExecutionContextScope::Calculate (ExecutionContext&); To: void ExecutionContextScope::CalculateExecutionContext (ExecutionContext&); I did this because this is a class that anything in the execution context heirarchy inherits from and "target->Calculate (exe_ctx)" didn't always tell you what it was really trying to do unless you look at the parameter. llvm-svn: 115485
2010-10-04 09:05:56 +08:00
{ NULL, eSetVarTypeNone, NULL, NULL, false, false, NULL }
This is a very large commit that completely re-does the way lldb handles user settable internal variables (the equivalent of set/show variables in gdb). In addition to the basic infrastructure (most of which is defined in UserSettingsController.{h,cpp}, there are examples of two classes that have been set up to contain user settable variables (the Debugger and Process classes). The 'settings' command has been modified to be a command-subcommand structure, and the 'set', 'show' and 'append' commands have been moved into this sub-commabnd structure. The old StateVariable class has been completely replaced by this, and the state variable dictionary has been removed from the Command Interpreter. Places that formerly accessed the state variable mechanism have been modified to access the variables in this new structure instead (checking the term-width; getting/checking the prompt; etc.) Variables are attached to classes; there are two basic "flavors" of variables that can be set: "global" variables (static/class-wide), and "instance" variables (one per instance of the class). The whole thing has been set up so that any global or instance variable can be set at any time (e.g. on start up, in your .lldbinit file), whether or not any instances actually exist (there's a whole pending and default values mechanism to help deal with that). llvm-svn: 113041
2010-09-04 08:03:46 +08:00
};