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

2448 lines
88 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
//===-- CommandInterpreter.cpp ----------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include <string>
Fix some memory leaks. Add call to lldb.SBDebugger.Initialize() to lldb.py, so it automatically gets called when the lldb Python module gets loaded. llvm-svn: 116345
2010-10-13 05:57:09 +08:00
#include <vector>
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include <getopt.h>
#include <stdlib.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 "CommandObjectScript.h"
Fix header paths llvm-svn: 133755
2011-06-24 04:37:26 +08:00
#include "lldb/Interpreter/CommandObjectRegexCommand.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
Fix include paths; please check that this works on Mac. llvm-svn: 105906
2010-06-13 10:17:17 +08:00
#include "../Commands/CommandObjectApropos.h"
#include "../Commands/CommandObjectArgs.h"
#include "../Commands/CommandObjectBreakpoint.h"
#include "../Commands/CommandObjectDisassemble.h"
#include "../Commands/CommandObjectExpression.h"
#include "../Commands/CommandObjectFrame.h"
#include "../Commands/CommandObjectHelp.h"
#include "../Commands/CommandObjectLog.h"
#include "../Commands/CommandObjectMemory.h"
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
#include "../Commands/CommandObjectPlatform.h"
Fix include paths; please check that this works on Mac. llvm-svn: 105906
2010-06-13 10:17:17 +08:00
#include "../Commands/CommandObjectProcess.h"
#include "../Commands/CommandObjectQuit.h"
#include "../Commands/CommandObjectRegister.h"
#include "../Commands/CommandObjectSettings.h"
#include "../Commands/CommandObjectSource.h"
Fix GetRepeatCommand so it works with multi-word commands. Move the "source", "alias", and "unalias" commands to "commands *". Move "source-file" to "source list". Added a "source info" command but it isn't implemented yet. llvm-svn: 107751
2010-07-07 11:36:20 +08:00
#include "../Commands/CommandObjectCommands.h"
Fix include paths; please check that this works on Mac. llvm-svn: 105906
2010-06-13 10:17:17 +08:00
#include "../Commands/CommandObjectSyntax.h"
#include "../Commands/CommandObjectTarget.h"
#include "../Commands/CommandObjectThread.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 "../Commands/CommandObjectType.h"
Add a simple command: 'version' to the command interpreter, and an accompanying test case test_help_version(). llvm-svn: 122515
2010-12-24 04:21:44 +08:00
#include "../Commands/CommandObjectVersion.h"
Add initial implementation of watchpoint commands for list, enable, disable, and delete. Test cases to be added later. llvm-svn: 140322
2011-09-23 02:04:58 +08:00
#include "../Commands/CommandObjectWatchpoint.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Move Args.{cpp,h} and Options.{cpp,h} to Interpreter where they really belong. llvm-svn: 106034
2010-06-16 03:49:27 +08:00
#include "lldb/Interpreter/Args.h"
Replace calls to HandleCommand in lldb core with more appropriate direct function calls. As part of this, collect code that processes arguments & options for aliases into a single function. llvm-svn: 131020
2011-05-07 05:37:15 +08:00
#include "lldb/Interpreter/Options.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Core/Debugger.h"
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
#include "lldb/Core/InputReader.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Core/Stream.h"
#include "lldb/Core/Timer.h"
Endian patch from Kirk Beitz that allows better cross platform building. llvm-svn: 124643
2011-02-01 09:31:41 +08:00
#include "lldb/Host/Host.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Target/Process.h"
#include "lldb/Target/Thread.h"
#include "lldb/Target/TargetList.h"
Modified lldb_private::SymboleFile to be able to override where its TypeList comes from by using a virtual function to provide it from the Module's SymbolVendor by default. This allows the DWARF parser, when being used to parse DWARF in .o files with a parent DWARF + debug map parser, to get its type list from the DWARF + debug map parser so when we go and find full definitions for types (that might come from other .o files), we can use the type list from the debug map parser. Otherwise we ended up mixing clang types from one .o file (say a const pointer to a forward declaration "class A") with the a full type from another .o file. This causes expression parsing, when copying the clang types from those parsed by the DWARF parser into the expression AST, to fail -- for good reason. Now all types are created in the same list. Also added host support for crash description strings that can be set before doing a piece of work. On MacOSX, this ties in with CrashReporter support that allows a string to be dispalyed when the app crashes and allows LLDB.framework to print a description string in the crash log. Right now this is hookup up the the CommandInterpreter::HandleCommand() where each command notes that it is about to be executed, so if we crash while trying to do this command, we should be able to see the command that caused LLDB to exit. For all other platforms, this is a nop. llvm-svn: 118672
2010-11-10 12:57:04 +08:00
#include "lldb/Utility/CleanUp.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Interpreter/CommandReturnObject.h"
#include "lldb/Interpreter/CommandInterpreter.h"
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
#include "lldb/Interpreter/ScriptInterpreterNone.h"
#include "lldb/Interpreter/ScriptInterpreterPython.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
using namespace lldb;
using namespace lldb_private;
CommandInterpreter::CommandInterpreter
(
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
Debugger &debugger,
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
ScriptLanguage script_language,
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
bool synchronous_execution
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
) :
Cleaned up the API logging a lot more to reduce redundant information and keep the file size a bit smaller. Exposed SBValue::GetExpressionPath() so SBValue users can get an expression path for their values. llvm-svn: 117851
2010-10-31 11:01:06 +08:00
Broadcaster ("lldb.command-interpreter"),
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_debugger (debugger),
Added a "--no-lldbinit" option (-n for short (which magically matches what gdb uses)) so we can tell our "lldb" driver program to not automatically parse any .lldbinit files. llvm-svn: 116179
2010-10-11 09:05:37 +08:00
m_synchronous_execution (synchronous_execution),
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
m_skip_lldbinit_files (false),
Make ValueObject::SetValueFromCString work correctly. Also change the SourceInitFile to look for .lldb-<APPNAME> and source that preferentially if it exists. Also made the breakpoint site report its address as well as its breakpoint number when it gets hit and can't find any the associated locations (usually because the breakpoint got disabled or deleted programmatically between the time it was hit and reported.) Changed ThreadPlanCallFunction to initialize the ivar m_func in the initializers of the constructor, rather than waiting to initialize till later on in the function. Fixed a bug where if you make an SBError and the ask it Success, it returns false. Fixed ValueObject::ResolveValue so that it resolves a temporary value, rather than overwriting the one in the value object. llvm-svn: 137536
2011-08-13 07:34:31 +08:00
m_skip_app_init_files (false),
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
m_script_interpreter_ap (),
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
m_comment_char ('#'),
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
m_repeat_char ('!'),
One-line fix for a possible spurious truncation warning llvm-svn: 137640
2011-08-16 03:24:02 +08:00
m_batch_command_mode (false),
m_truncation_warning(eNoTruncation)
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
const char *dbg_name = debugger.GetInstanceName().AsCString();
std::string lang_name = ScriptInterpreter::LanguageToString (script_language);
StreamString var_name;
var_name.Printf ("[%s].script-lang", dbg_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
debugger.GetSettingsController()->SetVariable (var_name.GetData(), lang_name.c_str(),
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
eVarSetOperationAssign, false,
Cleaned up the API logging a lot more to reduce redundant information and keep the file size a bit smaller. Exposed SBValue::GetExpressionPath() so SBValue users can get an expression path for their values. llvm-svn: 117851
2010-10-31 11:01:06 +08:00
m_debugger.GetInstanceName().AsCString());
SetEventName (eBroadcastBitThreadShouldExit, "thread-should-exit");
SetEventName (eBroadcastBitResetPrompt, "reset-prompt");
SetEventName (eBroadcastBitQuitCommandReceived, "quit");
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
CommandInterpreter::Initialize ()
{
Timer scoped_timer (__PRETTY_FUNCTION__, __PRETTY_FUNCTION__);
CommandReturnObject result;
LoadCommandDictionary ();
// Set up some initial aliases.
Replace calls to HandleCommand in lldb core with more appropriate direct function calls. As part of this, collect code that processes arguments & options for aliases into a single function. llvm-svn: 131020
2011-05-07 05:37:15 +08:00
CommandObjectSP cmd_obj_sp = GetCommandSPExact ("quit", false);
if (cmd_obj_sp)
{
AddAlias ("q", cmd_obj_sp);
AddAlias ("exit", cmd_obj_sp);
}
cmd_obj_sp = GetCommandSPExact ("process continue", false);
if (cmd_obj_sp)
{
AddAlias ("c", cmd_obj_sp);
AddAlias ("continue", cmd_obj_sp);
}
cmd_obj_sp = GetCommandSPExact ("_regexp-break",false);
if (cmd_obj_sp)
AddAlias ("b", cmd_obj_sp);
cmd_obj_sp = GetCommandSPExact ("thread backtrace", false);
if (cmd_obj_sp)
AddAlias ("bt", cmd_obj_sp);
cmd_obj_sp = GetCommandSPExact ("thread step-inst", false);
if (cmd_obj_sp)
AddAlias ("si", cmd_obj_sp);
cmd_obj_sp = GetCommandSPExact ("thread step-in", false);
if (cmd_obj_sp)
{
AddAlias ("s", cmd_obj_sp);
AddAlias ("step", cmd_obj_sp);
}
cmd_obj_sp = GetCommandSPExact ("thread step-over", false);
if (cmd_obj_sp)
{
AddAlias ("n", cmd_obj_sp);
AddAlias ("next", cmd_obj_sp);
}
cmd_obj_sp = GetCommandSPExact ("thread step-out", false);
if (cmd_obj_sp)
{
AddAlias ("f", cmd_obj_sp);
AddAlias ("finish", cmd_obj_sp);
}
cmd_obj_sp = GetCommandSPExact ("source list", false);
if (cmd_obj_sp)
{
AddAlias ("l", cmd_obj_sp);
AddAlias ("list", cmd_obj_sp);
}
cmd_obj_sp = GetCommandSPExact ("memory read", false);
if (cmd_obj_sp)
AddAlias ("x", cmd_obj_sp);
cmd_obj_sp = GetCommandSPExact ("_regexp-up", false);
if (cmd_obj_sp)
AddAlias ("up", cmd_obj_sp);
cmd_obj_sp = GetCommandSPExact ("_regexp-down", false);
if (cmd_obj_sp)
AddAlias ("down", cmd_obj_sp);
cmd_obj_sp = GetCommandSPExact ("target create", false);
if (cmd_obj_sp)
AddAlias ("file", cmd_obj_sp);
cmd_obj_sp = GetCommandSPExact ("target modules", false);
if (cmd_obj_sp)
AddAlias ("image", cmd_obj_sp);
OptionArgVectorSP alias_arguments_vector_sp (new OptionArgVector);
Add "up" and "down" aliases. llvm-svn: 128066
2011-03-22 10:29:32 +08:00
Replace calls to HandleCommand in lldb core with more appropriate direct function calls. As part of this, collect code that processes arguments & options for aliases into a single function. llvm-svn: 131020
2011-05-07 05:37:15 +08:00
cmd_obj_sp = GetCommandSPExact ("expression", false);
if (cmd_obj_sp)
{
AddAlias ("expr", cmd_obj_sp);
ProcessAliasOptionsArgs (cmd_obj_sp, "--", alias_arguments_vector_sp);
AddAlias ("p", cmd_obj_sp);
AddAlias ("print", cmd_obj_sp);
AddOrReplaceAliasOptions ("p", alias_arguments_vector_sp);
AddOrReplaceAliasOptions ("print", alias_arguments_vector_sp);
alias_arguments_vector_sp.reset (new OptionArgVector);
ProcessAliasOptionsArgs (cmd_obj_sp, "-o --", alias_arguments_vector_sp);
AddAlias ("po", cmd_obj_sp);
AddOrReplaceAliasOptions ("po", alias_arguments_vector_sp);
}
cmd_obj_sp = GetCommandSPExact ("process launch", false);
if (cmd_obj_sp)
{
alias_arguments_vector_sp.reset (new OptionArgVector);
ProcessAliasOptionsArgs (cmd_obj_sp, "--", alias_arguments_vector_sp);
AddAlias ("r", cmd_obj_sp);
AddAlias ("run", cmd_obj_sp);
AddOrReplaceAliasOptions ("r", alias_arguments_vector_sp);
AddOrReplaceAliasOptions ("run", alias_arguments_vector_sp);
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
const char *
CommandInterpreter::ProcessEmbeddedScriptCommands (const char *arg)
{
// This function has not yet been implemented.
// Look for any embedded script command
// If found,
// get interpreter object from the command dictionary,
// call execute_one_command on it,
// get the results as a string,
// substitute that string for current stuff.
return arg;
}
void
CommandInterpreter::LoadCommandDictionary ()
{
Timer scoped_timer (__PRETTY_FUNCTION__, __PRETTY_FUNCTION__);
// **** IMPORTANT **** IMPORTANT *** IMPORTANT *** **** IMPORTANT **** IMPORTANT *** IMPORTANT ***
//
// Command objects that are used as cross reference objects (i.e. they inherit from CommandObjectCrossref)
// *MUST* be created and put into the command dictionary *BEFORE* any multi-word commands (which may use
// the cross-referencing stuff) are created!!!
//
// **** IMPORTANT **** IMPORTANT *** IMPORTANT *** **** IMPORTANT **** IMPORTANT *** IMPORTANT ***
// Command objects that inherit from CommandObjectCrossref must be created before other command objects
// are created. This is so that when another command is created that needs to go into a crossref object,
// the crossref object exists and is ready to take the cross reference. Put the cross referencing command
// objects into the CommandDictionary now, so they are ready for use when the other commands get created.
// Non-CommandObjectCrossref commands can now be created.
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
lldb::ScriptLanguage script_language = m_debugger.GetScriptLanguage();
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 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_command_dict["apropos"] = CommandObjectSP (new CommandObjectApropos (*this));
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_dict["breakpoint"]= CommandObjectSP (new CommandObjectMultiwordBreakpoint (*this));
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_command_dict["call"] = CommandObjectSP (new CommandObjectCall (*this));
Fixed some more 'commands' to 'command' change. llvm-svn: 129897
2011-04-21 08:39:18 +08:00
m_command_dict["command"] = CommandObjectSP (new CommandObjectMultiwordCommands (*this));
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_command_dict["disassemble"] = CommandObjectSP (new CommandObjectDisassemble (*this));
m_command_dict["expression"]= CommandObjectSP (new CommandObjectExpression (*this));
Centralized a lot of the status information for processes, threads, and stack frame down in the lldb_private::Process, lldb_private::Thread, lldb_private::StackFrameList and the lldb_private::StackFrame classes. We had some command line commands that had duplicate versions of the process status output ("thread list" and "process status" for example). Removed the "file" command and placed it where it should have been: "target create". Made an alias for "file" to "target create" so we stay compatible with GDB commands. We can now have multple usable targets in lldb at the same time. This is nice for comparing two runs of a program or debugging more than one binary at the same time. The new command is "target select <target-idx>" and also to see a list of the current targets you can use the new "target list" command. The flow in a debug session can be: (lldb) target create /path/to/exe/a.out (lldb) breakpoint set --name main (lldb) run ... hit breakpoint (lldb) target create /bin/ls (lldb) run /tmp Process 36001 exited with status = 0 (0x00000000) (lldb) target list Current targets: target #0: /tmp/args/a.out ( arch=x86_64-apple-darwin, platform=localhost, pid=35999, state=stopped ) * target #1: /bin/ls ( arch=x86_64-apple-darwin, platform=localhost, pid=36001, state=exited ) (lldb) target select 0 Current targets: * target #0: /tmp/args/a.out ( arch=x86_64-apple-darwin, platform=localhost, pid=35999, state=stopped ) target #1: /bin/ls ( arch=x86_64-apple-darwin, platform=localhost, pid=36001, state=exited ) (lldb) bt * thread #1: tid = 0x2d03, 0x0000000100000b9a a.out`main + 42 at main.c:16, stop reason = breakpoint 1.1 frame #0: 0x0000000100000b9a a.out`main + 42 at main.c:16 frame #1: 0x0000000100000b64 a.out`start + 52 Above we created a target for "a.out" and ran and hit a breakpoint at "main". Then we created a new target for /bin/ls and ran it. Then we listed the targest and selected our original "a.out" program, so we showed two concurent debug sessions going on at the same time. llvm-svn: 129695
2011-04-18 16:33:37 +08:00
// m_command_dict["file"] = CommandObjectSP (new CommandObjectFile (*this));
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_dict["frame"] = CommandObjectSP (new CommandObjectMultiwordFrame (*this));
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_command_dict["help"] = CommandObjectSP (new CommandObjectHelp (*this));
Added new OptionGroup classes for UInt64, UUID, File and Boolean values. Removed the "image" command and moved it to "target modules". Added an alias for "image" to "target modules". Added some new target commands to be able to add and load modules to a target: (lldb) target modules add <path> (lldb) target modules load [--file <path>] [--slide <offset>] [<sect-name> <sect-load-addr> ...] So you can load individual sections without running a target: (lldb) target modules load --file /usr/lib/libSystem.B.dylib __TEXT 0x7fccc80000 __DATA 0x1234000000 Or you can rigidly slide an entire shared library: (lldb) target modules load --file /usr/lib/libSystem.B.dylib --slid 0x7fccc80000 This should improve bare board debugging when symbol files need to be slid around manually. llvm-svn: 130796
2011-05-04 06:09:39 +08:00
/// m_command_dict["image"] = CommandObjectSP (new CommandObjectImage (*this));
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_dict["log"] = CommandObjectSP (new CommandObjectLog (*this));
m_command_dict["memory"] = CommandObjectSP (new CommandObjectMemory (*this));
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_command_dict["platform"] = CommandObjectSP (new CommandObjectPlatform (*this));
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_dict["process"] = CommandObjectSP (new CommandObjectMultiwordProcess (*this));
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_command_dict["quit"] = CommandObjectSP (new CommandObjectQuit (*this));
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_dict["register"] = CommandObjectSP (new CommandObjectRegister (*this));
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_command_dict["script"] = CommandObjectSP (new CommandObjectScript (*this, script_language));
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_command_dict["settings"] = CommandObjectSP (new CommandObjectMultiwordSettings (*this));
Fix GetRepeatCommand so it works with multi-word commands. Move the "source", "alias", and "unalias" commands to "commands *". Move "source-file" to "source list". Added a "source info" command but it isn't implemented yet. llvm-svn: 107751
2010-07-07 11:36:20 +08:00
m_command_dict["source"] = CommandObjectSP (new CommandObjectMultiwordSource (*this));
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_dict["target"] = CommandObjectSP (new CommandObjectMultiwordTarget (*this));
m_command_dict["thread"] = CommandObjectSP (new CommandObjectMultiwordThread (*this));
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
m_command_dict["type"] = CommandObjectSP (new CommandObjectType (*this));
Add a simple command: 'version' to the command interpreter, and an accompanying test case test_help_version(). llvm-svn: 122515
2010-12-24 04:21:44 +08:00
m_command_dict["version"] = CommandObjectSP (new CommandObjectVersion (*this));
Add initial implementation of watchpoint commands for list, enable, disable, and delete. Test cases to be added later. llvm-svn: 140322
2011-09-23 02:04:58 +08:00
m_command_dict["watchpoint"]= CommandObjectSP (new CommandObjectMultiwordWatchpoint (*this));
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
std::auto_ptr<CommandObjectRegexCommand>
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
break_regex_cmd_ap(new CommandObjectRegexCommand (*this,
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
"_regexp-break",
Small help text fixes, to make it more consistent and accurate. Temporarily remove -l option from 'expr' command (at Sean's request). llvm-svn: 113298
2010-09-08 06:38:08 +08:00
"Set a breakpoint using a regular expression to specify the location.",
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
"_regexp-break [<filename>:<linenum>]\n_regexp-break [<address>]\n_regexp-break <...>", 2));
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (break_regex_cmd_ap.get())
{
if (break_regex_cmd_ap->AddRegexCommand("^(.*[^[:space:]])[[:space:]]*:[[:space:]]*([[:digit:]]+)[[:space:]]*$", "breakpoint set --file '%1' --line %2") &&
break_regex_cmd_ap->AddRegexCommand("^(0x[[:xdigit:]]+)[[:space:]]*$", "breakpoint set --address %1") &&
break_regex_cmd_ap->AddRegexCommand("^[\"']?([-+]\\[.*\\])[\"']?[[:space:]]*$", "breakpoint set --name '%1'") &&
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
break_regex_cmd_ap->AddRegexCommand("^$", "breakpoint list --full") &&
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
break_regex_cmd_ap->AddRegexCommand("^(-.*)$", "breakpoint set %1") &&
A few of the issue I have been trying to track down and fix have been due to the way LLDB lazily gets complete definitions for types within the debug info. When we run across a class/struct/union definition in the DWARF, we will only parse the full definition if we need to. This works fine for top level types that are assigned directly to variables and arguments, but when we have a variable with a class, lets say "A" for this example, that has a member: "B *m_b". Initially we don't need to hunt down a definition for this class unless we are ever asked to do something with it ("expr m_b->getDecl()" for example). With my previous approach to lazy type completion, we would be able to take a "A *a" and get a complete type for it, but we wouldn't be able to then do an "a->m_b->getDecl()" unless we always expanded all types within a class prior to handing out the type. Expanding everything is very costly and it would be great if there were a better way. A few months ago I worked with the llvm/clang folks to have the ExternalASTSource class be able to complete classes if there weren't completed yet: class ExternalASTSource { .... virtual void CompleteType (clang::TagDecl *Tag); virtual void CompleteType (clang::ObjCInterfaceDecl *Class); }; This was great, because we can now have the class that is producing the AST (SymbolFileDWARF and SymbolFileDWARFDebugMap) sign up as external AST sources and the object that creates the forward declaration types can now also complete them anywhere within the clang type system. This patch makes a few major changes: - lldb_private::Module classes now own the AST context. Previously the TypeList objects did. - The DWARF parsers now sign up as an external AST sources so they can complete types. - All of the pure clang type system wrapper code we have in LLDB (ClangASTContext, ClangASTType, and more) can now be iterating through children of any type, and if a class/union/struct type (clang::RecordType or ObjC interface) is found that is incomplete, we can ask the AST to get the definition. - The SymbolFileDWARFDebugMap class now will create and use a single AST that all child SymbolFileDWARF classes will share (much like what happens when we have a complete linked DWARF for an executable). We will need to modify some of the ClangUserExpression code to take more advantage of this completion ability in the near future. Meanwhile we should be better off now that we can be accessing any children of variables through pointers and always be able to resolve the clang type if needed. llvm-svn: 123613
2011-01-17 11:46:26 +08:00
break_regex_cmd_ap->AddRegexCommand("^(.*[^[:space:]])`(.*[^[:space:]])[[:space:]]*$", "breakpoint set --name '%2' --shlib '%1'") &&
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
break_regex_cmd_ap->AddRegexCommand("^(.*[^[:space:]])[[:space:]]*$", "breakpoint set --name '%1'"))
{
CommandObjectSP break_regex_cmd_sp(break_regex_cmd_ap.release());
m_command_dict[break_regex_cmd_sp->GetCommandName ()] = break_regex_cmd_sp;
}
}
Add "up" and "down" aliases. llvm-svn: 128066
2011-03-22 10:29:32 +08:00
std::auto_ptr<CommandObjectRegexCommand>
down_regex_cmd_ap(new CommandObjectRegexCommand (*this,
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
"_regexp-down",
"Go down \"n\" frames in the stack (1 frame by default).",
"_regexp-down [n]", 2));
Add "up" and "down" aliases. llvm-svn: 128066
2011-03-22 10:29:32 +08:00
if (down_regex_cmd_ap.get())
{
if (down_regex_cmd_ap->AddRegexCommand("^$", "frame select -r -1") &&
down_regex_cmd_ap->AddRegexCommand("^([0-9]+)$", "frame select -r -%1"))
{
CommandObjectSP down_regex_cmd_sp(down_regex_cmd_ap.release());
m_command_dict[down_regex_cmd_sp->GetCommandName ()] = down_regex_cmd_sp;
}
}
std::auto_ptr<CommandObjectRegexCommand>
up_regex_cmd_ap(new CommandObjectRegexCommand (*this,
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
"_regexp-up",
"Go up \"n\" frames in the stack (1 frame by default).",
"_regexp-up [n]", 2));
Add "up" and "down" aliases. llvm-svn: 128066
2011-03-22 10:29:32 +08:00
if (up_regex_cmd_ap.get())
{
if (up_regex_cmd_ap->AddRegexCommand("^$", "frame select -r 1") &&
up_regex_cmd_ap->AddRegexCommand("^([0-9]+)$", "frame select -r %1"))
{
CommandObjectSP up_regex_cmd_sp(up_regex_cmd_ap.release());
m_command_dict[up_regex_cmd_sp->GetCommandName ()] = up_regex_cmd_sp;
}
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
int
CommandInterpreter::GetCommandNamesMatchingPartialString (const char *cmd_str, bool include_aliases,
StringList &matches)
{
CommandObject::AddNamesMatchingPartialString (m_command_dict, cmd_str, matches);
if (include_aliases)
{
CommandObject::AddNamesMatchingPartialString (m_alias_dict, cmd_str, matches);
}
return matches.GetSize();
}
CommandObjectSP
CommandInterpreter::GetCommandSP (const char *cmd_cstr, bool include_aliases, bool exact, StringList *matches)
{
CommandObject::CommandMap::iterator pos;
CommandObjectSP ret_val;
std::string cmd(cmd_cstr);
if (HasCommands())
{
pos = m_command_dict.find(cmd);
if (pos != m_command_dict.end())
ret_val = pos->second;
}
if (include_aliases && HasAliases())
{
pos = m_alias_dict.find(cmd);
if (pos != m_alias_dict.end())
ret_val = pos->second;
}
if (HasUserCommands())
{
pos = m_user_dict.find(cmd);
if (pos != m_user_dict.end())
ret_val = pos->second;
}
if (!exact && ret_val == NULL)
{
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
// We will only get into here if we didn't find any exact matches.
CommandObjectSP user_match_sp, alias_match_sp, real_match_sp;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
StringList local_matches;
if (matches == NULL)
matches = &local_matches;
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
unsigned int num_cmd_matches = 0;
unsigned int num_alias_matches = 0;
unsigned int num_user_matches = 0;
// Look through the command dictionaries one by one, and if we get only one match from any of
// them in toto, then return that, otherwise return an empty CommandObjectSP and the list of matches.
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (HasCommands())
{
num_cmd_matches = CommandObject::AddNamesMatchingPartialString (m_command_dict, cmd_cstr, *matches);
}
if (num_cmd_matches == 1)
{
cmd.assign(matches->GetStringAtIndex(0));
pos = m_command_dict.find(cmd);
if (pos != m_command_dict.end())
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
real_match_sp = pos->second;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Fix a bug in handling command resolution for non-exact matches. Now we will correctly give help options when there are both aliases & real commands matching the current input string. llvm-svn: 106782
2010-06-25 04:28:42 +08:00
if (include_aliases && HasAliases())
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
num_alias_matches = CommandObject::AddNamesMatchingPartialString (m_alias_dict, cmd_cstr, *matches);
}
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
if (num_alias_matches == 1)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
cmd.assign(matches->GetStringAtIndex (num_cmd_matches));
pos = m_alias_dict.find(cmd);
if (pos != m_alias_dict.end())
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
alias_match_sp = pos->second;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Fix a bug in handling command resolution for non-exact matches. Now we will correctly give help options when there are both aliases & real commands matching the current input string. llvm-svn: 106782
2010-06-25 04:28:42 +08:00
if (HasUserCommands())
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
num_user_matches = CommandObject::AddNamesMatchingPartialString (m_user_dict, cmd_cstr, *matches);
}
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
if (num_user_matches == 1)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
cmd.assign (matches->GetStringAtIndex (num_cmd_matches + num_alias_matches));
pos = m_user_dict.find (cmd);
if (pos != m_user_dict.end())
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
user_match_sp = pos->second;
}
// If we got exactly one match, return that, otherwise return the match list.
if (num_user_matches + num_cmd_matches + num_alias_matches == 1)
{
if (num_cmd_matches)
return real_match_sp;
else if (num_alias_matches)
return alias_match_sp;
else
return user_match_sp;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
}
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
else if (matches && ret_val != NULL)
{
matches->AppendString (cmd_cstr);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
return ret_val;
}
Added the ability for users to create new regex commands. To do this currently, it must be done in multi-line mode: (lldb) commands regex --help "Help text for command" --syntax "syntax for command" <cmd-name> Any example that would use "f" for "finish" when there are no arguments, and "f <num>" to do a "frame select <num>" would be: (lldb) commands regex f Enter multiple regular expressions in the form s/find/replace/ then terminate with an empty line: s/^$/finish/ s/([0-9]+)/frame select %1/ (lldb) f 11 frame select 12 ... (lldb) f finish ... Also added the string version of the OptionValue as OptionValueString. llvm-svn: 129855
2011-04-21 00:37:46 +08:00
bool
CommandInterpreter::AddCommand (const char *name, const lldb::CommandObjectSP &cmd_sp, bool can_replace)
{
if (name && name[0])
{
std::string name_sstr(name);
if (!can_replace)
{
if (m_command_dict.find (name_sstr) != m_command_dict.end())
return false;
}
m_command_dict[name_sstr] = cmd_sp;
return true;
}
return false;
}
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
bool
CommandInterpreter::AddUserCommand (const char *name,
const lldb::CommandObjectSP &cmd_sp,
bool can_replace)
{
if (name && name[0])
{
std::string name_sstr(name);
if (!can_replace)
{
if (m_user_dict.find (name_sstr) != m_user_dict.end())
return false;
}
m_user_dict[name_sstr] = cmd_sp;
return true;
}
return false;
}
Added the ability for users to create new regex commands. To do this currently, it must be done in multi-line mode: (lldb) commands regex --help "Help text for command" --syntax "syntax for command" <cmd-name> Any example that would use "f" for "finish" when there are no arguments, and "f <num>" to do a "frame select <num>" would be: (lldb) commands regex f Enter multiple regular expressions in the form s/find/replace/ then terminate with an empty line: s/^$/finish/ s/([0-9]+)/frame select %1/ (lldb) f 11 frame select 12 ... (lldb) f finish ... Also added the string version of the OptionValue as OptionValueString. llvm-svn: 129855
2011-04-21 00:37:46 +08:00
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
CommandObjectSP
CommandInterpreter::GetCommandSPExact (const char *cmd_cstr, bool include_aliases)
{
Fix small bugs: - Make sure cmd_obj & cmd_obj_sp contain a valid objects before attempting to dereference, in CommandObjectCommandsAlias::Execute and CommandInterpreter::HandleCommand. - Modify CommandInterpreter::GetCommandSPExact to properly handle multi-word command inputs. llvm-svn: 121779
2010-12-15 02:51:39 +08:00
Args cmd_words (cmd_cstr); // Break up the command string into words, in case it's a multi-word command.
CommandObjectSP ret_val; // Possibly empty return value.
if (cmd_cstr == NULL)
return ret_val;
if (cmd_words.GetArgumentCount() == 1)
return GetCommandSP(cmd_cstr, include_aliases, true, NULL);
else
{
// We have a multi-word command (seemingly), so we need to do more work.
// First, get the cmd_obj_sp for the first word in the command.
CommandObjectSP cmd_obj_sp = GetCommandSP (cmd_words.GetArgumentAtIndex (0), include_aliases, true, NULL);
if (cmd_obj_sp.get() != NULL)
{
// Loop through the rest of the words in the command (everything passed in was supposed to be part of a
// command name), and find the appropriate sub-command SP for each command word....
size_t end = cmd_words.GetArgumentCount();
for (size_t j= 1; j < end; ++j)
{
if (cmd_obj_sp->IsMultiwordObject())
{
cmd_obj_sp = ((CommandObjectMultiword *) cmd_obj_sp.get())->GetSubcommandSP
(cmd_words.GetArgumentAtIndex (j));
if (cmd_obj_sp.get() == NULL)
// The sub-command name was invalid. Fail and return the empty 'ret_val'.
return ret_val;
}
else
// We have more words in the command name, but we don't have a multiword object. Fail and return
// empty 'ret_val'.
return ret_val;
}
// We successfully looped through all the command words and got valid command objects for them. Assign the
// last object retrieved to 'ret_val'.
ret_val = cmd_obj_sp;
}
}
return ret_val;
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
CommandObject *
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
CommandInterpreter::GetCommandObjectExact (const char *cmd_cstr, bool include_aliases)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
return GetCommandSPExact (cmd_cstr, include_aliases).get();
}
CommandObject *
CommandInterpreter::GetCommandObject (const char *cmd_cstr, StringList *matches)
{
CommandObject *command_obj = GetCommandSP (cmd_cstr, false, true, matches).get();
// If we didn't find an exact match to the command string in the commands, look in
// the aliases.
if (command_obj == NULL)
{
command_obj = GetCommandSP (cmd_cstr, true, true, matches).get();
}
// Finally, if there wasn't an exact match among the aliases, look for an inexact match
// in both the commands and the aliases.
if (command_obj == NULL)
command_obj = GetCommandSP(cmd_cstr, true, false, matches).get();
return command_obj;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
bool
CommandInterpreter::CommandExists (const char *cmd)
{
return m_command_dict.find(cmd) != m_command_dict.end();
}
Replace calls to HandleCommand in lldb core with more appropriate direct function calls. As part of this, collect code that processes arguments & options for aliases into a single function. llvm-svn: 131020
2011-05-07 05:37:15 +08:00
bool
CommandInterpreter::ProcessAliasOptionsArgs (lldb::CommandObjectSP &cmd_obj_sp,
const char *options_args,
OptionArgVectorSP &option_arg_vector_sp)
{
bool success = true;
OptionArgVector *option_arg_vector = option_arg_vector_sp.get();
if (!options_args || (strlen (options_args) < 1))
return true;
std::string options_string (options_args);
Args args (options_args);
CommandReturnObject result;
// Check to see if the command being aliased can take any command options.
Options *options = cmd_obj_sp->GetOptions ();
if (options)
{
// See if any options were specified as part of the alias; if so, handle them appropriately.
options->NotifyOptionParsingStarting ();
args.Unshift ("dummy_arg");
args.ParseAliasOptions (*options, result, option_arg_vector, options_string);
args.Shift ();
if (result.Succeeded())
options->VerifyPartialOptions (result);
if (!result.Succeeded() && result.GetStatus() != lldb::eReturnStatusStarted)
{
result.AppendError ("Unable to create requested alias.\n");
return false;
}
}
if (options_string.size() > 0)
{
if (cmd_obj_sp->WantsRawCommandString ())
option_arg_vector->push_back (OptionArgPair ("<argument>",
OptionArgValue (-1,
options_string)));
else
{
int argc = args.GetArgumentCount();
for (size_t i = 0; i < argc; ++i)
if (strcmp (args.GetArgumentAtIndex (i), "") != 0)
option_arg_vector->push_back
(OptionArgPair ("<argument>",
OptionArgValue (-1,
std::string (args.GetArgumentAtIndex (i)))));
}
}
return success;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
bool
CommandInterpreter::AliasExists (const char *cmd)
{
return m_alias_dict.find(cmd) != m_alias_dict.end();
}
bool
CommandInterpreter::UserCommandExists (const char *cmd)
{
return m_user_dict.find(cmd) != m_user_dict.end();
}
void
CommandInterpreter::AddAlias (const char *alias_name, CommandObjectSP& command_obj_sp)
{
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
command_obj_sp->SetIsAlias (true);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
m_alias_dict[alias_name] = command_obj_sp;
}
bool
CommandInterpreter::RemoveAlias (const char *alias_name)
{
CommandObject::CommandMap::iterator pos = m_alias_dict.find(alias_name);
if (pos != m_alias_dict.end())
{
m_alias_dict.erase(pos);
return true;
}
return false;
}
bool
CommandInterpreter::RemoveUser (const char *alias_name)
{
CommandObject::CommandMap::iterator pos = m_user_dict.find(alias_name);
if (pos != m_user_dict.end())
{
m_user_dict.erase(pos);
return true;
}
return false;
}
void
CommandInterpreter::GetAliasHelp (const char *alias_name, const char *command_name, StreamString &help_string)
{
help_string.Printf ("'%s", command_name);
OptionArgVectorSP option_arg_vector_sp = GetAliasOptions (alias_name);
if (option_arg_vector_sp != NULL)
{
OptionArgVector *options = option_arg_vector_sp.get();
for (int i = 0; i < options->size(); ++i)
{
OptionArgPair cur_option = (*options)[i];
std::string opt = cur_option.first;
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
OptionArgValue value_pair = cur_option.second;
std::string value = value_pair.second;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (opt.compare("<argument>") == 0)
{
help_string.Printf (" %s", value.c_str());
}
else
{
help_string.Printf (" %s", opt.c_str());
if ((value.compare ("<no-argument>") != 0)
&& (value.compare ("<need-argument") != 0))
{
help_string.Printf (" %s", value.c_str());
}
}
}
}
help_string.Printf ("'");
}
Changed the StackID to store its start PC address as a load address instead of a section offset address. Fixed up some very inefficient STL code. llvm-svn: 112230
2010-08-27 06:05:43 +08:00
size_t
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
CommandInterpreter::FindLongestCommandWord (CommandObject::CommandMap &dict)
{
CommandObject::CommandMap::const_iterator pos;
Changed the StackID to store its start PC address as a load address instead of a section offset address. Fixed up some very inefficient STL code. llvm-svn: 112230
2010-08-27 06:05:43 +08:00
CommandObject::CommandMap::const_iterator end = dict.end();
size_t max_len = 0;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Changed the StackID to store its start PC address as a load address instead of a section offset address. Fixed up some very inefficient STL code. llvm-svn: 112230
2010-08-27 06:05:43 +08:00
for (pos = dict.begin(); pos != end; ++pos)
{
size_t len = pos->first.size();
if (max_len < len)
max_len = len;
}
return max_len;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
CommandInterpreter::GetHelp (CommandReturnObject &result,
Adding two new options to the 'help' command: --show-aliases (-a) shows aliases for commands, as well as built-in commands --hide-user-defined (-u) hides user defined commands by default 'help' without arguments does not show aliases anymore. to see them, add --show-aliases to have only built-in commands appear, use 'help --hide-user-defined' ; there is currently no way to hide built-in commands from the help output 'help command' is not changed by this commit, and help is shown even if command is an alias and -a is not specified llvm-svn: 139377
2011-09-10 01:49:36 +08:00
uint32_t cmd_types)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
CommandObject::CommandMap::const_iterator pos;
Changed the StackID to store its start PC address as a load address instead of a section offset address. Fixed up some very inefficient STL code. llvm-svn: 112230
2010-08-27 06:05:43 +08:00
uint32_t max_len = FindLongestCommandWord (m_command_dict);
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
if ( (cmd_types & eCommandTypesBuiltin) == eCommandTypesBuiltin )
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
result.AppendMessage("The following is a list of built-in, permanent debugger commands:");
result.AppendMessage("");
for (pos = m_command_dict.begin(); pos != m_command_dict.end(); ++pos)
{
OutputFormattedHelpText (result.GetOutputStream(), pos->first.c_str(), "--", pos->second->GetHelp(),
max_len);
}
result.AppendMessage("");
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
if (m_alias_dict.size() > 0 && ( (cmd_types & eCommandTypesAliases) == eCommandTypesAliases ))
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Changed "run" to alias "process launch --". Added "po" alias for "expression -o --" llvm-svn: 117125
2010-10-23 02:47:16 +08:00
result.AppendMessage("The following is a list of your current command abbreviations "
Fixed some more 'commands' to 'command' change. llvm-svn: 129897
2011-04-21 08:39:18 +08:00
"(see 'help command alias' for more info):");
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
result.AppendMessage("");
Changed the StackID to store its start PC address as a load address instead of a section offset address. Fixed up some very inefficient STL code. llvm-svn: 112230
2010-08-27 06:05:43 +08:00
max_len = FindLongestCommandWord (m_alias_dict);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
for (pos = m_alias_dict.begin(); pos != m_alias_dict.end(); ++pos)
{
StreamString sstr;
StreamString translation_and_help;
std::string entry_name = pos->first;
std::string second_entry = pos->second.get()->GetCommandName();
GetAliasHelp (pos->first.c_str(), pos->second->GetCommandName(), sstr);
translation_and_help.Printf ("(%s) %s", sstr.GetData(), pos->second->GetHelp());
OutputFormattedHelpText (result.GetOutputStream(), pos->first.c_str(), "--",
translation_and_help.GetData(), max_len);
}
result.AppendMessage("");
}
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
if (m_user_dict.size() > 0 && ( (cmd_types & eCommandTypesUserDef) == eCommandTypesUserDef ))
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
result.AppendMessage ("The following is a list of your current user-defined commands:");
result.AppendMessage("");
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
max_len = FindLongestCommandWord (m_user_dict);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
for (pos = m_user_dict.begin(); pos != m_user_dict.end(); ++pos)
{
Changes to Python commands: - They now have an SBCommandReturnObject instead of an SBStream as third argument - The class CommandObjectPythonFunction has been merged into CommandObjectCommands.cpp - The command to manage them is now: command script with subcommands add, list, delete, clear command alias is returned to its previous functionality - Python commands are now part of an user dictionary, instead of being seen as aliases llvm-svn: 137785
2011-08-17 07:24:13 +08:00
OutputFormattedHelpText (result.GetOutputStream(), pos->first.c_str(), "--", pos->second->GetHelp(),
max_len);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
result.AppendMessage("");
}
result.AppendMessage("For more information on any particular command, try 'help <command-name>'.");
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
CommandObject *
CommandInterpreter::GetCommandObjectForCommand (std::string &command_string)
{
// This function finds the final, lowest-level, alias-resolved command object whose 'Execute' function will
// eventually be invoked by the given command line.
CommandObject *cmd_obj = NULL;
std::string white_space (" \t\v");
size_t start = command_string.find_first_not_of (white_space);
size_t end = 0;
bool done = false;
while (!done)
{
if (start != std::string::npos)
{
// Get the next word from command_string.
end = command_string.find_first_of (white_space, start);
if (end == std::string::npos)
end = command_string.size();
std::string cmd_word = command_string.substr (start, end - start);
if (cmd_obj == NULL)
// Since cmd_obj is NULL we are on our first time through this loop. Check to see if cmd_word is a valid
// command or alias.
cmd_obj = GetCommandObject (cmd_word.c_str());
else if (cmd_obj->IsMultiwordObject ())
{
// Our current object is a multi-word object; see if the cmd_word is a valid sub-command for our object.
CommandObject *sub_cmd_obj =
((CommandObjectMultiword *) cmd_obj)->GetSubcommandObject (cmd_word.c_str());
if (sub_cmd_obj)
cmd_obj = sub_cmd_obj;
else // cmd_word was not a valid sub-command word, so we are donee
done = true;
}
else
// We have a cmd_obj and it is not a multi-word object, so we are done.
done = true;
// If we didn't find a valid command object, or our command object is not a multi-word object, or
// we are at the end of the command_string, then we are done. Otherwise, find the start of the
// next word.
if (!cmd_obj || !cmd_obj->IsMultiwordObject() || end >= command_string.size())
done = true;
else
start = command_string.find_first_not_of (white_space, end);
}
else
// Unable to find any more words.
done = true;
}
if (end == command_string.size())
command_string.clear();
else
command_string = command_string.substr(end);
return cmd_obj;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
bool
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
CommandInterpreter::StripFirstWord (std::string &command_string, std::string &word, bool &was_quoted, char &quote_char)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
std::string white_space (" \t\v");
size_t start;
size_t end;
start = command_string.find_first_not_of (white_space);
if (start != std::string::npos)
{
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
size_t len = command_string.size() - start;
if (len >= 2
&& ((command_string[start] == '\'') || (command_string[start] == '"')))
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
{
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
was_quoted = true;
quote_char = command_string[start];
std::string quote_string = command_string.substr (start, 1);
start = start + 1;
end = command_string.find (quote_string, start);
if (end != std::string::npos)
{
word = command_string.substr (start, end - start);
if (end + 1 < len)
command_string = command_string.substr (end+1);
else
command_string.erase ();
size_t pos = command_string.find_first_not_of (white_space);
if ((pos != 0) && (pos != std::string::npos))
command_string = command_string.substr (pos);
}
else
{
word = command_string.substr (start - 1);
command_string.erase ();
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
}
else
{
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
end = command_string.find_first_of (white_space, start);
if (end != std::string::npos)
{
word = command_string.substr (start, end - start);
command_string = command_string.substr (end);
size_t pos = command_string.find_first_not_of (white_space);
if ((pos != 0) && (pos != std::string::npos))
command_string = command_string.substr (pos);
}
else
{
word = command_string.substr (start);
command_string.erase();
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
}
}
return true;
}
void
CommandInterpreter::BuildAliasResult (const char *alias_name, std::string &raw_input_string, std::string &alias_result,
CommandObject *&alias_cmd_obj, CommandReturnObject &result)
{
Args cmd_args (raw_input_string.c_str());
alias_cmd_obj = GetCommandObject (alias_name);
StreamString result_str;
if (alias_cmd_obj)
{
std::string alias_name_str = alias_name;
if ((cmd_args.GetArgumentCount() == 0)
|| (alias_name_str.compare (cmd_args.GetArgumentAtIndex(0)) != 0))
cmd_args.Unshift (alias_name);
result_str.Printf ("%s", alias_cmd_obj->GetCommandName ());
OptionArgVectorSP option_arg_vector_sp = GetAliasOptions (alias_name);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
if (option_arg_vector_sp.get())
{
OptionArgVector *option_arg_vector = option_arg_vector_sp.get();
for (int i = 0; i < option_arg_vector->size(); ++i)
{
OptionArgPair option_pair = (*option_arg_vector)[i];
OptionArgValue value_pair = option_pair.second;
int value_type = value_pair.first;
std::string option = option_pair.first;
std::string value = value_pair.second;
if (option.compare ("<argument>") == 0)
result_str.Printf (" %s", value.c_str());
else
{
result_str.Printf (" %s", option.c_str());
if (value_type != optional_argument)
result_str.Printf (" ");
if (value.compare ("<no_argument>") != 0)
{
int index = GetOptionArgumentPosition (value.c_str());
if (index == 0)
result_str.Printf ("%s", value.c_str());
else if (index >= cmd_args.GetArgumentCount())
{
result.AppendErrorWithFormat
("Not enough arguments provided; you need at least %d arguments to use this alias.\n",
index);
result.SetStatus (eReturnStatusFailed);
return;
}
else
{
size_t strpos = raw_input_string.find (cmd_args.GetArgumentAtIndex (index));
if (strpos != std::string::npos)
raw_input_string = raw_input_string.erase (strpos,
strlen (cmd_args.GetArgumentAtIndex (index)));
result_str.Printf ("%s", cmd_args.GetArgumentAtIndex (index));
}
}
}
}
}
alias_result = result_str.GetData();
}
}
Added the ability to run expressions in any command. Expressions can be inserted in commands by using backticks: (lldb) memory read `$rsp-16` `$rsp+16` (lldb) memory read -c `(int)strlen(argv[0])` `argv[0]` The result of the expression will be inserted into the command as a sort of preprocess stage where this gets done first. We might need to tweak where this preprocess stage goes, but it is very functional already. Added ansi color support to the Debugger::FormatPrompt() so you can use things like "${ansi.fg.blue}" and "${ansi.bold}" many more. This helps in adding colors to your prompts without needing to know the ANSI color code strings. llvm-svn: 141948
2011-10-14 15:41:33 +08:00
Error
CommandInterpreter::PreprocessCommand (std::string &command)
{
// The command preprocessor needs to do things to the command
// line before any parsing of arguments or anything else is done.
// The only current stuff that gets proprocessed is anyting enclosed
// in backtick ('`') characters is evaluated as an expression and
// the result of the expression must be a scalar that can be substituted
// into the command. An example would be:
// (lldb) memory read `$rsp + 20`
Error error; // Error for any expressions that might not evaluate
size_t start_backtick;
size_t pos = 0;
while ((start_backtick = command.find ('`', pos)) != std::string::npos)
{
if (start_backtick > 0 && command[start_backtick-1] == '\\')
{
// The backtick was preceeded by a '\' character, remove the slash
// and don't treat the backtick as the start of an expression
command.erase(start_backtick-1, 1);
// No need to add one to start_backtick since we just deleted a char
pos = start_backtick;
}
else
{
const size_t expr_content_start = start_backtick + 1;
const size_t end_backtick = command.find ('`', expr_content_start);
if (end_backtick == std::string::npos)
return error;
else if (end_backtick == expr_content_start)
{
// Empty expression (two backticks in a row)
command.erase (start_backtick, 2);
}
else
{
std::string expr_str (command, expr_content_start, end_backtick - expr_content_start);
Target *target = m_exe_ctx.GetTargetPtr();
if (target)
{
const bool unwind_on_error = true;
const bool keep_in_memory = false;
ValueObjectSP expr_result_valobj_sp;
ExecutionResults expr_result = target->EvaluateExpression (expr_str.c_str(),
m_exe_ctx.GetFramePtr(),
eExecutionPolicyOnlyWhenNeeded,
unwind_on_error, keep_in_memory,
eNoDynamicValues,
expr_result_valobj_sp);
if (expr_result == eExecutionCompleted)
{
Scalar scalar;
if (expr_result_valobj_sp->ResolveValue (scalar))
{
command.erase (start_backtick, end_backtick - start_backtick + 1);
StreamString value_strm;
const bool show_type = false;
scalar.GetValue (&value_strm, show_type);
size_t value_string_size = value_strm.GetSize();
if (value_string_size)
{
command.insert (start_backtick, value_strm.GetData(), value_string_size);
pos = start_backtick + value_string_size;
continue;
}
else
{
error.SetErrorStringWithFormat("expression value didn't result in a scalar value for the expression '%s'", expr_str.c_str());
}
}
else
{
error.SetErrorStringWithFormat("expression value didn't result in a scalar value for the expression '%s'", expr_str.c_str());
}
}
else
{
if (expr_result_valobj_sp)
error = expr_result_valobj_sp->GetError();
if (error.Success())
{
switch (expr_result)
{
case eExecutionSetupError:
error.SetErrorStringWithFormat("expression setup error for the expression '%s'", expr_str.c_str());
break;
case eExecutionCompleted:
break;
case eExecutionDiscarded:
error.SetErrorStringWithFormat("expression discarded for the expression '%s'", expr_str.c_str());
break;
case eExecutionInterrupted:
error.SetErrorStringWithFormat("expression interrupted for the expression '%s'", expr_str.c_str());
break;
case eExecutionTimedOut:
error.SetErrorStringWithFormat("expression timed out for the expression '%s'", expr_str.c_str());
break;
}
}
}
}
}
if (error.Fail())
break;
}
}
return error;
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
bool
CommandInterpreter::HandleCommand (const char *command_line,
bool add_to_history,
CommandReturnObject &result,
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
ExecutionContext *override_context,
Fix a problem where the stop-hook command 'frame variable g_val' produces nothing when newly created threads were subsequently stopped due to breakpoint hit. The stop-hook mechanism delegates to CommandInterpreter::HandleCommands() to execuet the commands. Make sure the execution context is switched only once at the beginning of HandleCommands() only and don't update the context while looping on each individual command to be executed. rdar://problem/10228156 llvm-svn: 141144
2011-10-05 08:42:59 +08:00
bool repeat_on_empty_command,
bool no_context_switching)
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
{
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
bool done = false;
CommandObject *cmd_obj = NULL;
std::string next_word;
bool wants_raw_input = false;
std::string command_string (command_line);
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
std::string original_command_string (command_line);
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
LogSP log (lldb_private::GetLogIfAllCategoriesSet (LIBLLDB_LOG_COMMANDS));
Modified lldb_private::SymboleFile to be able to override where its TypeList comes from by using a virtual function to provide it from the Module's SymbolVendor by default. This allows the DWARF parser, when being used to parse DWARF in .o files with a parent DWARF + debug map parser, to get its type list from the DWARF + debug map parser so when we go and find full definitions for types (that might come from other .o files), we can use the type list from the debug map parser. Otherwise we ended up mixing clang types from one .o file (say a const pointer to a forward declaration "class A") with the a full type from another .o file. This causes expression parsing, when copying the clang types from those parsed by the DWARF parser into the expression AST, to fail -- for good reason. Now all types are created in the same list. Also added host support for crash description strings that can be set before doing a piece of work. On MacOSX, this ties in with CrashReporter support that allows a string to be dispalyed when the app crashes and allows LLDB.framework to print a description string in the crash log. Right now this is hookup up the the CommandInterpreter::HandleCommand() where each command notes that it is about to be executed, so if we crash while trying to do this command, we should be able to see the command that caused LLDB to exit. For all other platforms, this is a nop. llvm-svn: 118672
2010-11-10 12:57:04 +08:00
Host::SetCrashDescriptionWithFormat ("HandleCommand(command = \"%s\")", command_line);
// Make a scoped cleanup object that will clear the crash description string
// on exit of this function.
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
lldb_utility::CleanUp <const char *> crash_description_cleanup(NULL, Host::SetCrashDescription);
Modified lldb_private::SymboleFile to be able to override where its TypeList comes from by using a virtual function to provide it from the Module's SymbolVendor by default. This allows the DWARF parser, when being used to parse DWARF in .o files with a parent DWARF + debug map parser, to get its type list from the DWARF + debug map parser so when we go and find full definitions for types (that might come from other .o files), we can use the type list from the debug map parser. Otherwise we ended up mixing clang types from one .o file (say a const pointer to a forward declaration "class A") with the a full type from another .o file. This causes expression parsing, when copying the clang types from those parsed by the DWARF parser into the expression AST, to fail -- for good reason. Now all types are created in the same list. Also added host support for crash description strings that can be set before doing a piece of work. On MacOSX, this ties in with CrashReporter support that allows a string to be dispalyed when the app crashes and allows LLDB.framework to print a description string in the crash log. Right now this is hookup up the the CommandInterpreter::HandleCommand() where each command notes that it is about to be executed, so if we crash while trying to do this command, we should be able to see the command that caused LLDB to exit. For all other platforms, this is a nop. llvm-svn: 118672
2010-11-10 12:57:04 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
if (log)
log->Printf ("Processing command: %s", command_line);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Added a top level Timer to the interpreter execute command. Also added an option to pass the depth to "log timer enable". That allows you to time just command execution with: log timer enable 1 <command> log timer dump llvm-svn: 118267
2010-11-05 07:08:45 +08:00
Timer scoped_timer (__PRETTY_FUNCTION__, "Handling command: %s.", command_line);
Fix a problem where the stop-hook command 'frame variable g_val' produces nothing when newly created threads were subsequently stopped due to breakpoint hit. The stop-hook mechanism delegates to CommandInterpreter::HandleCommands() to execuet the commands. Make sure the execution context is switched only once at the beginning of HandleCommands() only and don't update the context while looping on each individual command to be executed. rdar://problem/10228156 llvm-svn: 141144
2011-10-05 08:42:59 +08:00
if (!no_context_switching)
UpdateExecutionContext (override_context);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
bool empty_command = false;
bool comment_command = false;
if (command_string.empty())
empty_command = true;
else
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
const char *k_space_characters = "\t\n\v\f\r ";
size_t non_space = command_string.find_first_not_of (k_space_characters);
// Check for empty line or comment line (lines whose first
// non-space character is the comment character for this interpreter)
if (non_space == std::string::npos)
empty_command = true;
else if (command_string[non_space] == m_comment_char)
comment_command = true;
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
else if (command_string[non_space] == m_repeat_char)
{
const char *history_string = FindHistoryString (command_string.c_str() + non_space);
if (history_string == NULL)
{
result.AppendErrorWithFormat ("Could not find entry: %s in history", command_string.c_str());
result.SetStatus(eReturnStatusFailed);
return false;
}
add_to_history = false;
command_string = history_string;
original_command_string = history_string;
}
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
}
if (empty_command)
{
if (repeat_on_empty_command)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
if (m_command_history.empty())
Added a "GetRepeatCommand" to the command object. The Interpreter uses this instead of the last history item to provide a command for the "empty" command. Use this in the source-file command to make <RETURN> continue the listing rather than relist the first listing... llvm-svn: 107736
2010-07-07 07:48:33 +08:00
{
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
result.AppendError ("empty command");
result.SetStatus(eReturnStatusFailed);
Added a "GetRepeatCommand" to the command object. The Interpreter uses this instead of the last history item to provide a command for the "empty" command. Use this in the source-file command to make <RETURN> continue the listing rather than relist the first listing... llvm-svn: 107736
2010-07-07 07:48:33 +08:00
return false;
}
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
else
{
command_line = m_repeat_command.c_str();
command_string = command_line;
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
original_command_string = command_line;
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
if (m_repeat_command.empty())
{
result.AppendErrorWithFormat("No auto repeat.\n");
result.SetStatus (eReturnStatusFailed);
return false;
}
}
add_to_history = false;
}
else
{
result.SetStatus (eReturnStatusSuccessFinishNoResult);
return true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
}
else if (comment_command)
{
result.SetStatus (eReturnStatusSuccessFinishNoResult);
return true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
Added the ability to run expressions in any command. Expressions can be inserted in commands by using backticks: (lldb) memory read `$rsp-16` `$rsp+16` (lldb) memory read -c `(int)strlen(argv[0])` `argv[0]` The result of the expression will be inserted into the command as a sort of preprocess stage where this gets done first. We might need to tweak where this preprocess stage goes, but it is very functional already. Added ansi color support to the Debugger::FormatPrompt() so you can use things like "${ansi.fg.blue}" and "${ansi.bold}" many more. This helps in adding colors to your prompts without needing to know the ANSI color code strings. llvm-svn: 141948
2011-10-14 15:41:33 +08:00
Error error (PreprocessCommand (command_string));
if (error.Fail())
{
result.AppendError (error.AsCString());
result.SetStatus(eReturnStatusFailed);
return false;
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
// Phase 1.
// Before we do ANY kind of argument processing, etc. we need to figure out what the real/final command object
// is for the specified command, and whether or not it wants raw input. This gets complicated by the fact that
// the user could have specified an alias, and in translating the alias there may also be command options and/or
// even data (including raw text strings) that need to be found and inserted into the command line as part of
// the translation. So this first step is plain look-up & replacement, resulting in three things: 1). the command
Spelling changes applied from lldb_spelling.diffs from Bruce Mitchener. Thanks Bruce! llvm-svn: 123083
2011-01-09 04:28:42 +08:00
// object whose Execute method will actually be called; 2). a revised command string, with all substitutions &
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
// replacements taken care of; 3). whether or not the Execute function wants raw input or not.
StreamString revised_command_line;
Fix bug where using incomplete strings for command names causes lldb to crash (because of attempt to look for full names when full names were not used). llvm-svn: 121607
2010-12-11 16:16:56 +08:00
size_t actual_cmd_name_len = 0;
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
while (!done)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
bool was_quoted = false;
char quote_char = '\0';
StripFirstWord (command_string, next_word, was_quoted, quote_char);
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
if (!cmd_obj && AliasExists (next_word.c_str()))
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
std::string alias_result;
BuildAliasResult (next_word.c_str(), command_string, alias_result, cmd_obj, result);
revised_command_line.Printf ("%s", alias_result.c_str());
if (cmd_obj)
Fix small bugs: - Make sure cmd_obj & cmd_obj_sp contain a valid objects before attempting to dereference, in CommandObjectCommandsAlias::Execute and CommandInterpreter::HandleCommand. - Modify CommandInterpreter::GetCommandSPExact to properly handle multi-word command inputs. llvm-svn: 121779
2010-12-15 02:51:39 +08:00
{
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
wants_raw_input = cmd_obj->WantsRawCommandString ();
Fix small bugs: - Make sure cmd_obj & cmd_obj_sp contain a valid objects before attempting to dereference, in CommandObjectCommandsAlias::Execute and CommandInterpreter::HandleCommand. - Modify CommandInterpreter::GetCommandSPExact to properly handle multi-word command inputs. llvm-svn: 121779
2010-12-15 02:51:39 +08:00
actual_cmd_name_len = strlen (cmd_obj->GetCommandName());
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
}
else if (!cmd_obj)
{
cmd_obj = GetCommandObject (next_word.c_str());
if (cmd_obj)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
Fix bug where using incomplete strings for command names causes lldb to crash (because of attempt to look for full names when full names were not used). llvm-svn: 121607
2010-12-11 16:16:56 +08:00
actual_cmd_name_len += next_word.length();
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
revised_command_line.Printf ("%s", next_word.c_str());
wants_raw_input = cmd_obj->WantsRawCommandString ();
}
else
{
revised_command_line.Printf ("%s", next_word.c_str());
}
}
else if (cmd_obj->IsMultiwordObject ())
{
CommandObject *sub_cmd_obj = ((CommandObjectMultiword *) cmd_obj)->GetSubcommandObject (next_word.c_str());
if (sub_cmd_obj)
{
Fix bug where using incomplete strings for command names causes lldb to crash (because of attempt to look for full names when full names were not used). llvm-svn: 121607
2010-12-11 16:16:56 +08:00
actual_cmd_name_len += next_word.length() + 1;
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
revised_command_line.Printf (" %s", next_word.c_str());
cmd_obj = sub_cmd_obj;
wants_raw_input = cmd_obj->WantsRawCommandString ();
}
else
{
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
if (was_quoted)
{
if (quote_char == '"')
revised_command_line.Printf (" \"%s\"", next_word.c_str());
else
revised_command_line.Printf (" '%s'", next_word.c_str());
}
else
revised_command_line.Printf (" %s", next_word.c_str());
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
done = true;
}
}
else
{
Add ability to recognize/handle quotes around commands (e.g. '"target" create' works as well as 'target create'). llvm-svn: 131185
2011-05-12 00:07:06 +08:00
if (was_quoted)
{
if (quote_char == '"')
revised_command_line.Printf (" \"%s\"", next_word.c_str());
else
revised_command_line.Printf (" '%s'", next_word.c_str());
}
else
revised_command_line.Printf (" %s", next_word.c_str());
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
done = true;
}
if (cmd_obj == NULL)
{
result.AppendErrorWithFormat ("'%s' is not a valid command.\n", next_word.c_str());
result.SetStatus (eReturnStatusFailed);
return false;
}
next_word.erase ();
if (command_string.length() == 0)
done = true;
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
if (command_string.size() > 0)
revised_command_line.Printf (" %s", command_string.c_str());
Added a "GetRepeatCommand" to the command object. The Interpreter uses this instead of the last history item to provide a command for the "empty" command. Use this in the source-file command to make <RETURN> continue the listing rather than relist the first listing... llvm-svn: 107736
2010-07-07 07:48:33 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
// End of Phase 1.
// At this point cmd_obj should contain the CommandObject whose Execute method will be called, if the command
// specified was valid; revised_command_line contains the complete command line (including command name(s)),
// fully translated with all substitutions & translations taken care of (still in raw text format); and
// wants_raw_input specifies whether the Execute method expects raw input or not.
Added a "GetRepeatCommand" to the command object. The Interpreter uses this instead of the last history item to provide a command for the "empty" command. Use this in the source-file command to make <RETURN> continue the listing rather than relist the first listing... llvm-svn: 107736
2010-07-07 07:48:33 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
if (log)
{
log->Printf ("HandleCommand, cmd_obj : '%s'", cmd_obj ? cmd_obj->GetCommandName() : "<not found>");
log->Printf ("HandleCommand, revised_command_line: '%s'", revised_command_line.GetData());
log->Printf ("HandleCommand, wants_raw_input:'%s'", wants_raw_input ? "True" : "False");
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
// Phase 2.
// Take care of things like setting up the history command & calling the appropriate Execute method on the
// CommandObject, with the appropriate arguments.
if (cmd_obj != NULL)
{
if (add_to_history)
{
Args command_args (revised_command_line.GetData());
const char *repeat_command = cmd_obj->GetRepeatCommand(command_args, 0);
if (repeat_command != NULL)
m_repeat_command.assign(repeat_command);
else
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
m_repeat_command.assign(original_command_string.c_str());
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
// Don't keep pushing the same command onto the history...
if (m_command_history.size() == 0 || m_command_history.back() != original_command_string)
m_command_history.push_back (original_command_string);
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
}
command_string = revised_command_line.GetData();
std::string command_name (cmd_obj->GetCommandName());
Fix bug where using incomplete strings for command names causes lldb to crash (because of attempt to look for full names when full names were not used). llvm-svn: 121607
2010-12-11 16:16:56 +08:00
std::string remainder;
if (actual_cmd_name_len < command_string.length())
remainder = command_string.substr (actual_cmd_name_len); // Note: 'actual_cmd_name_len' may be considerably shorter
// than cmd_obj->GetCommandName(), because name completion
// allows users to enter short versions of the names,
// e.g. 'br s' for 'breakpoint set'.
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
// Remove any initial spaces
std::string white_space (" \t\v");
size_t pos = remainder.find_first_not_of (white_space);
if (pos != 0 && pos != std::string::npos)
Erase from a string instead of using substr when you don't really need to. llvm-svn: 130013
2011-04-23 04:58:45 +08:00
remainder.erase(0, pos);
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
if (log)
Include lldb/commands as a valid logging type in the 'log list' output. Remove an extraneous \n from one of the lldb/commands log line. Add an lldb/commands log indicating whether the command was successful or not. llvm-svn: 138530
2011-08-25 08:20:04 +08:00
log->Printf ("HandleCommand, command line after removing command name(s): '%s'", remainder.c_str());
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
if (wants_raw_input)
cmd_obj->ExecuteRawCommandString (remainder.c_str(), result);
else
{
Args cmd_args (remainder.c_str());
cmd_obj->ExecuteWithOptions (cmd_args, result);
}
}
else
{
// We didn't find the first command object, so complete the first argument.
Args command_args (revised_command_line.GetData());
StringList matches;
int num_matches;
int cursor_index = 0;
int cursor_char_position = strlen (command_args.GetArgumentAtIndex(0));
bool word_complete;
num_matches = HandleCompletionMatches (command_args,
cursor_index,
cursor_char_position,
0,
-1,
word_complete,
matches);
if (num_matches > 0)
{
std::string error_msg;
error_msg.assign ("ambiguous command '");
error_msg.append(command_args.GetArgumentAtIndex(0));
error_msg.append ("'.");
error_msg.append (" Possible completions:");
for (int i = 0; i < num_matches; i++)
{
error_msg.append ("\n\t");
error_msg.append (matches.GetStringAtIndex (i));
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
error_msg.append ("\n");
result.AppendRawError (error_msg.c_str(), error_msg.size());
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
else
result.AppendErrorWithFormat ("Unrecognized command '%s'.\n", command_args.GetArgumentAtIndex (0));
result.SetStatus (eReturnStatusFailed);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Modify HandleCommand to not do any argument processing until it has determined whether or not the command should take raw input, then handle & dispatch the arguments appropriately. Also change the 'alias' command to be a command that takes raw input. This is necessary to allow aliases to be created for other commands that take raw input and might want to include raw input in the alias itself. Fix a bug in the aliasing mechanism when creating aliases for commands with 3-or-more words. Raw input should now be properly handled by all the command and alias mechanisms. llvm-svn: 121423
2010-12-10 06:52:49 +08:00
Include lldb/commands as a valid logging type in the 'log list' output. Remove an extraneous \n from one of the lldb/commands log line. Add an lldb/commands log indicating whether the command was successful or not. llvm-svn: 138530
2011-08-25 08:20:04 +08:00
if (log)
log->Printf ("HandleCommand, command %s", (result.Succeeded() ? "succeeded" : "did not succeed"));
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
return result.Succeeded();
}
int
CommandInterpreter::HandleCompletionMatches (Args &parsed_line,
int &cursor_index,
int &cursor_char_position,
int match_start_point,
int max_return_elements,
Add a source file completer to the CommandCompleters. Add a way for the completers to say whether the completed argument should have a space inserted after is or not. Added the file name completer to the "file" command. llvm-svn: 107247
2010-06-30 13:02:46 +08:00
bool &word_complete,
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
StringList &matches)
{
int num_command_matches = 0;
bool look_for_subcommand = false;
Add a source file completer to the CommandCompleters. Add a way for the completers to say whether the completed argument should have a space inserted after is or not. Added the file name completer to the "file" command. llvm-svn: 107247
2010-06-30 13:02:46 +08:00
// For any of the command completions a unique match will be a complete word.
word_complete = true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (cursor_index == -1)
{
// We got nothing on the command line, so return the list of commands
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
bool include_aliases = true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
num_command_matches = GetCommandNamesMatchingPartialString ("", include_aliases, matches);
}
else if (cursor_index == 0)
{
// The cursor is in the first argument, so just do a lookup in the dictionary.
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
CommandObject *cmd_obj = GetCommandObject (parsed_line.GetArgumentAtIndex(0), &matches);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
num_command_matches = matches.GetSize();
if (num_command_matches == 1
&& cmd_obj && cmd_obj->IsMultiwordObject()
&& matches.GetStringAtIndex(0) != NULL
&& strcmp (parsed_line.GetArgumentAtIndex(0), matches.GetStringAtIndex(0)) == 0)
{
look_for_subcommand = true;
num_command_matches = 0;
matches.DeleteStringAtIndex(0);
parsed_line.AppendArgument ("");
cursor_index++;
cursor_char_position = 0;
}
}
if (cursor_index > 0 || look_for_subcommand)
{
// We are completing further on into a commands arguments, so find the command and tell it
// to complete the command.
// First see if there is a matching initial command:
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
CommandObject *command_object = GetCommandObject (parsed_line.GetArgumentAtIndex(0));
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (command_object == NULL)
{
return 0;
}
else
{
parsed_line.Shift();
cursor_index--;
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
num_command_matches = command_object->HandleCompletion (parsed_line,
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
cursor_index,
cursor_char_position,
match_start_point,
Add a source file completer to the CommandCompleters. Add a way for the completers to say whether the completed argument should have a space inserted after is or not. Added the file name completer to the "file" command. llvm-svn: 107247
2010-06-30 13:02:46 +08:00
max_return_elements,
word_complete,
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
matches);
}
}
return num_command_matches;
}
int
CommandInterpreter::HandleCompletion (const char *current_line,
const char *cursor,
const char *last_char,
int match_start_point,
int max_return_elements,
StringList &matches)
{
// We parse the argument up to the cursor, so the last argument in parsed_line is
// the one containing the cursor, and the cursor is after the last character.
Args parsed_line(current_line, last_char - current_line);
Args partial_parsed_line(current_line, cursor - current_line);
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
// Don't complete comments, and if the line we are completing is just the history repeat character,
// substitute the appropriate history line.
const char *first_arg = parsed_line.GetArgumentAtIndex(0);
if (first_arg)
{
if (first_arg[0] == m_comment_char)
return 0;
else if (first_arg[0] == m_repeat_char)
{
const char *history_string = FindHistoryString (first_arg);
if (history_string != NULL)
{
matches.Clear();
matches.InsertStringAtIndex(0, history_string);
return -2;
}
else
return 0;
}
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
int num_args = partial_parsed_line.GetArgumentCount();
int cursor_index = partial_parsed_line.GetArgumentCount() - 1;
int cursor_char_position;
if (cursor_index == -1)
cursor_char_position = 0;
else
cursor_char_position = strlen (partial_parsed_line.GetArgumentAtIndex(cursor_index));
Fix the completion of "fr " and the like. llvm-svn: 121785
2010-12-15 03:56:01 +08:00
if (cursor > current_line && cursor[-1] == ' ')
{
// We are just after a space. If we are in an argument, then we will continue
// parsing, but if we are between arguments, then we have to complete whatever the next
// element would be.
// We can distinguish the two cases because if we are in an argument (e.g. because the space is
// protected by a quote) then the space will also be in the parsed argument...
const char *current_elem = partial_parsed_line.GetArgumentAtIndex(cursor_index);
if (cursor_char_position == 0 || current_elem[cursor_char_position - 1] != ' ')
{
parsed_line.InsertArgumentAtIndex(cursor_index + 1, "", '"');
cursor_index++;
cursor_char_position = 0;
}
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
int num_command_matches;
matches.Clear();
// Only max_return_elements == -1 is supported at present:
assert (max_return_elements == -1);
Add a source file completer to the CommandCompleters. Add a way for the completers to say whether the completed argument should have a space inserted after is or not. Added the file name completer to the "file" command. llvm-svn: 107247
2010-06-30 13:02:46 +08:00
bool word_complete;
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
num_command_matches = HandleCompletionMatches (parsed_line,
cursor_index,
cursor_char_position,
match_start_point,
Add a source file completer to the CommandCompleters. Add a way for the completers to say whether the completed argument should have a space inserted after is or not. Added the file name completer to the "file" command. llvm-svn: 107247
2010-06-30 13:02:46 +08:00
max_return_elements,
word_complete,
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
matches);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (num_command_matches <= 0)
return num_command_matches;
if (num_args == 0)
{
// If we got an empty string, insert nothing.
matches.InsertStringAtIndex(0, "");
}
else
{
// Now figure out if there is a common substring, and if so put that in element 0, otherwise
// put an empty string in element 0.
std::string command_partial_str;
if (cursor_index >= 0)
Changed "run" to alias "process launch --". Added "po" alias for "expression -o --" llvm-svn: 117125
2010-10-23 02:47:16 +08:00
command_partial_str.assign(parsed_line.GetArgumentAtIndex(cursor_index),
parsed_line.GetArgumentAtIndex(cursor_index) + cursor_char_position);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
std::string common_prefix;
matches.LongestCommonPrefix (common_prefix);
int partial_name_len = command_partial_str.size();
// If we matched a unique single command, add a space...
Add a source file completer to the CommandCompleters. Add a way for the completers to say whether the completed argument should have a space inserted after is or not. Added the file name completer to the "file" command. llvm-svn: 107247
2010-06-30 13:02:46 +08:00
// Only do this if the completer told us this was a complete word, however...
if (num_command_matches == 1 && word_complete)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
char quote_char = parsed_line.GetArgumentQuoteCharAtIndex(cursor_index);
if (quote_char != '\0')
common_prefix.push_back(quote_char);
common_prefix.push_back(' ');
}
common_prefix.erase (0, partial_name_len);
matches.InsertStringAtIndex(0, common_prefix.c_str());
}
return num_command_matches;
}
CommandInterpreter::~CommandInterpreter ()
{
}
const char *
CommandInterpreter::GetPrompt ()
{
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
return m_debugger.GetPrompt();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
CommandInterpreter::SetPrompt (const char *new_prompt)
{
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_debugger.SetPrompt (new_prompt);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
size_t
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
CommandInterpreter::GetConfirmationInputReaderCallback
(
void *baton,
InputReader &reader,
lldb::InputReaderAction action,
const char *bytes,
size_t bytes_len
)
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +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
File &out_file = reader.GetDebugger().GetOutputFile();
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
bool *response_ptr = (bool *) baton;
switch (action)
{
case eInputReaderActivate:
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 (out_file.IsValid())
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
{
if (reader.GetPrompt())
Make sure the confirmation input reader calls fflush after writing its output. (<rdar://problem/8946573>) llvm-svn: 124711
2011-02-02 09:17:56 +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
out_file.Printf ("%s", reader.GetPrompt());
out_file.Flush ();
Make sure the confirmation input reader calls fflush after writing its output. (<rdar://problem/8946573>) llvm-svn: 124711
2011-02-02 09:17:56 +08:00
}
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
}
break;
case eInputReaderDeactivate:
break;
case eInputReaderReactivate:
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 (out_file.IsValid() && reader.GetPrompt())
Make sure the confirmation input reader calls fflush after writing its output. (<rdar://problem/8946573>) llvm-svn: 124711
2011-02-02 09:17:56 +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
out_file.Printf ("%s", reader.GetPrompt());
out_file.Flush ();
Make sure the confirmation input reader calls fflush after writing its output. (<rdar://problem/8946573>) llvm-svn: 124711
2011-02-02 09:17:56 +08:00
}
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
break;
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
case eInputReaderAsynchronousOutputWritten:
break;
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
case eInputReaderGotToken:
if (bytes_len == 0)
{
reader.SetIsDone(true);
}
else if (bytes[0] == 'y')
{
*response_ptr = true;
reader.SetIsDone(true);
}
else if (bytes[0] == 'n')
{
*response_ptr = false;
reader.SetIsDone(true);
}
else
{
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 (out_file.IsValid() && !reader.IsDone() && reader.GetPrompt())
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +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
out_file.Printf ("Please answer \"y\" or \"n\"\n%s", reader.GetPrompt());
out_file.Flush ();
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
}
}
break;
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
case eInputReaderInterrupt:
case eInputReaderEndOfFile:
*response_ptr = false; // Assume ^C or ^D means cancel the proposed action
reader.SetIsDone (true);
break;
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
case eInputReaderDone:
break;
}
return bytes_len;
}
bool
CommandInterpreter::Confirm (const char *message, bool default_answer)
{
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
// Check AutoConfirm first:
if (m_debugger.GetAutoConfirm())
return default_answer;
Add a "Confirm" function to the CommandInterpreter so you can confirm potentially dangerous operations in a generic way. llvm-svn: 115546
2010-10-05 03:49:29 +08:00
InputReaderSP reader_sp (new InputReader(GetDebugger()));
bool response = default_answer;
if (reader_sp)
{
std::string prompt(message);
prompt.append(": [");
if (default_answer)
prompt.append ("Y/n] ");
else
prompt.append ("y/N] ");
Error err (reader_sp->Initialize (CommandInterpreter::GetConfirmationInputReaderCallback,
&response, // baton
eInputReaderGranularityLine, // token size, to pass to callback function
NULL, // end token
prompt.c_str(), // prompt
true)); // echo input
if (err.Success())
{
GetDebugger().PushInputReader (reader_sp);
}
reader_sp->WaitOnReaderIsDone();
}
return response;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
void
CommandInterpreter::CrossRegisterCommand (const char * dest_cmd, const char * object_type)
{
Hide the logic for command resolution for commands, aliases & user commands behind a single interface so everybody does it the same way. Add an "exact" lookup for internal uses. Fix up a few little cases where we weren't reporting command lookup errors correctly. Added "b" as an alias for "breakpoint" so it doesn't collide with "bt". llvm-svn: 107718
2010-07-07 06:46:59 +08:00
CommandObjectSP cmd_obj_sp = GetCommandSPExact (dest_cmd, true);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (cmd_obj_sp != NULL)
{
CommandObject *cmd_obj = cmd_obj_sp.get();
if (cmd_obj->IsCrossRefObject ())
cmd_obj->AddObject (object_type);
}
}
OptionArgVectorSP
CommandInterpreter::GetAliasOptions (const char *alias_name)
{
OptionArgMap::iterator pos;
OptionArgVectorSP ret_val;
std::string alias (alias_name);
if (HasAliasOptions())
{
pos = m_alias_options.find (alias);
if (pos != m_alias_options.end())
ret_val = pos->second;
}
return ret_val;
}
void
CommandInterpreter::RemoveAliasOptions (const char *alias_name)
{
OptionArgMap::iterator pos = m_alias_options.find(alias_name);
if (pos != m_alias_options.end())
{
m_alias_options.erase (pos);
}
}
void
CommandInterpreter::AddOrReplaceAliasOptions (const char *alias_name, OptionArgVectorSP &option_arg_vector_sp)
{
m_alias_options[alias_name] = option_arg_vector_sp;
}
bool
CommandInterpreter::HasCommands ()
{
return (!m_command_dict.empty());
}
bool
CommandInterpreter::HasAliases ()
{
return (!m_alias_dict.empty());
}
bool
CommandInterpreter::HasUserCommands ()
{
return (!m_user_dict.empty());
}
bool
CommandInterpreter::HasAliasOptions ()
{
return (!m_alias_options.empty());
}
void
Fix some memory leaks. Add call to lldb.SBDebugger.Initialize() to lldb.py, so it automatically gets called when the lldb Python module gets loaded. llvm-svn: 116345
2010-10-13 05:57:09 +08:00
CommandInterpreter::BuildAliasCommandArgs (CommandObject *alias_cmd_obj,
const char *alias_name,
Args &cmd_args,
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
std::string &raw_input_string,
Fix some memory leaks. Add call to lldb.SBDebugger.Initialize() to lldb.py, so it automatically gets called when the lldb Python module gets loaded. llvm-svn: 116345
2010-10-13 05:57:09 +08:00
CommandReturnObject &result)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
OptionArgVectorSP option_arg_vector_sp = GetAliasOptions (alias_name);
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
bool wants_raw_input = alias_cmd_obj->WantsRawCommandString();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
// Make sure that the alias name is the 0th element in cmd_args
std::string alias_name_str = alias_name;
if (alias_name_str.compare (cmd_args.GetArgumentAtIndex(0)) != 0)
cmd_args.Unshift (alias_name);
Args new_args (alias_cmd_obj->GetCommandName());
if (new_args.GetArgumentCount() == 2)
new_args.Shift();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (option_arg_vector_sp.get())
{
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
if (wants_raw_input)
{
// We have a command that both has command options and takes raw input. Make *sure* it has a
// " -- " in the right place in the raw_input_string.
size_t pos = raw_input_string.find(" -- ");
if (pos == std::string::npos)
{
// None found; assume it goes at the beginning of the raw input string
raw_input_string.insert (0, " -- ");
}
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
OptionArgVector *option_arg_vector = option_arg_vector_sp.get();
int old_size = cmd_args.GetArgumentCount();
Fix some memory leaks. Add call to lldb.SBDebugger.Initialize() to lldb.py, so it automatically gets called when the lldb Python module gets loaded. llvm-svn: 116345
2010-10-13 05:57:09 +08:00
std::vector<bool> used (old_size + 1, false);
used[0] = true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
for (int i = 0; i < option_arg_vector->size(); ++i)
{
OptionArgPair option_pair = (*option_arg_vector)[i];
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
OptionArgValue value_pair = option_pair.second;
int value_type = value_pair.first;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
std::string option = option_pair.first;
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
std::string value = value_pair.second;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (option.compare ("<argument>") == 0)
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
{
if (!wants_raw_input
|| (value.compare("--") != 0)) // Since we inserted this above, make sure we don't insert it twice
new_args.AppendArgument (value.c_str());
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
else
{
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
if (value_type != optional_argument)
new_args.AppendArgument (option.c_str());
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (value.compare ("<no-argument>") != 0)
{
int index = GetOptionArgumentPosition (value.c_str());
if (index == 0)
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
{
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
// value was NOT a positional argument; must be a real value
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
if (value_type != optional_argument)
new_args.AppendArgument (value.c_str());
else
{
char buffer[255];
::snprintf (buffer, sizeof (buffer), "%s%s", option.c_str(), value.c_str());
new_args.AppendArgument (buffer);
}
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
else if (index >= cmd_args.GetArgumentCount())
{
result.AppendErrorWithFormat
("Not enough arguments provided; you need at least %d arguments to use this alias.\n",
index);
result.SetStatus (eReturnStatusFailed);
return;
}
else
{
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
// Find and remove cmd_args.GetArgumentAtIndex(i) from raw_input_string
size_t strpos = raw_input_string.find (cmd_args.GetArgumentAtIndex (index));
if (strpos != std::string::npos)
{
raw_input_string = raw_input_string.erase (strpos, strlen (cmd_args.GetArgumentAtIndex (index)));
}
if (value_type != optional_argument)
new_args.AppendArgument (cmd_args.GetArgumentAtIndex (index));
else
{
char buffer[255];
::snprintf (buffer, sizeof(buffer), "%s%s", option.c_str(),
cmd_args.GetArgumentAtIndex (index));
new_args.AppendArgument (buffer);
}
Fix some memory leaks. Add call to lldb.SBDebugger.Initialize() to lldb.py, so it automatically gets called when the lldb Python module gets loaded. llvm-svn: 116345
2010-10-13 05:57:09 +08:00
used[index] = true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
}
}
}
for (int j = 0; j < cmd_args.GetArgumentCount(); ++j)
{
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
if (!used[j] && !wants_raw_input)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
new_args.AppendArgument (cmd_args.GetArgumentAtIndex (j));
}
cmd_args.Clear();
cmd_args.SetArguments (new_args.GetArgumentCount(), (const char **) new_args.GetArgumentVector());
}
else
{
result.SetStatus (eReturnStatusSuccessFinishNoResult);
- Fix alias-building & resolving to properly handle optional arguments for command options. - Add logging for command resolution ('log enable lldb commands') - Fix alias resolution to properly handle commands that take raw input (resolve the alias, but don't muck up the raw arguments). Net result: Among other things, 'expr' command can now take strings with escaped characters and not have the command handling & alias resolution code muck up the escaped characters. E.g. 'expr printf ("\n\n\tHello there!")' should now work properly. Not working yet: Creating aliases with raw input for commands that take raw input. Working on that. e.g. 'command alias print_hi expr printf ("\n\tHi!")' does not work yet. llvm-svn: 121171
2010-12-08 03:58:26 +08:00
// This alias was not created with any options; nothing further needs to be done, unless it is a command that
// wants raw input, in which case we need to clear the rest of the data from cmd_args, since its in the raw
// input string.
if (wants_raw_input)
{
cmd_args.Clear();
cmd_args.SetArguments (new_args.GetArgumentCount(), (const char **) new_args.GetArgumentVector());
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
return;
}
result.SetStatus (eReturnStatusSuccessFinishNoResult);
return;
}
int
CommandInterpreter::GetOptionArgumentPosition (const char *in_string)
{
int position = 0; // Any string that isn't an argument position, i.e. '%' followed by an integer, gets a position
// of zero.
char *cptr = (char *) in_string;
// Does it start with '%'
if (cptr[0] == '%')
{
++cptr;
// Is the rest of it entirely digits?
if (isdigit (cptr[0]))
{
const char *start = cptr;
while (isdigit (cptr[0]))
++cptr;
// We've gotten to the end of the digits; are we at the end of the string?
if (cptr[0] == '\0')
position = atoi (start);
}
}
return position;
}
void
CommandInterpreter::SourceInitFile (bool in_cwd, CommandReturnObject &result)
{
Make ValueObject::SetValueFromCString work correctly. Also change the SourceInitFile to look for .lldb-<APPNAME> and source that preferentially if it exists. Also made the breakpoint site report its address as well as its breakpoint number when it gets hit and can't find any the associated locations (usually because the breakpoint got disabled or deleted programmatically between the time it was hit and reported.) Changed ThreadPlanCallFunction to initialize the ivar m_func in the initializers of the constructor, rather than waiting to initialize till later on in the function. Fixed a bug where if you make an SBError and the ask it Success, it returns false. Fixed ValueObject::ResolveValue so that it resolves a temporary value, rather than overwriting the one in the value object. llvm-svn: 137536
2011-08-13 07:34:31 +08:00
FileSpec init_file;
Don't skip the application specific ~/.lldbinit file when the program name is "lldb". So currently when you startup any application and you have not specified that you would like to skip loading init files through the API or from "lldb" options, then LLDB will try and load: "~/.lldbinit-%s" where %s the basename of your program "~/.lldbinit" Then LLDB will load any program specified on the command line and then source the "./.llbinit" file for any temporary debug session specific commands. I want this feature because I have thread and frame formats that do ANSI color codes that I only want to load when running in a terminal which is when I am running the "lldb" command line program. llvm-svn: 139476
2011-09-11 08:01:44 +08:00
if (in_cwd)
Make ValueObject::SetValueFromCString work correctly. Also change the SourceInitFile to look for .lldb-<APPNAME> and source that preferentially if it exists. Also made the breakpoint site report its address as well as its breakpoint number when it gets hit and can't find any the associated locations (usually because the breakpoint got disabled or deleted programmatically between the time it was hit and reported.) Changed ThreadPlanCallFunction to initialize the ivar m_func in the initializers of the constructor, rather than waiting to initialize till later on in the function. Fixed a bug where if you make an SBError and the ask it Success, it returns false. Fixed ValueObject::ResolveValue so that it resolves a temporary value, rather than overwriting the one in the value object. llvm-svn: 137536
2011-08-13 07:34:31 +08:00
{
Don't skip the application specific ~/.lldbinit file when the program name is "lldb". So currently when you startup any application and you have not specified that you would like to skip loading init files through the API or from "lldb" options, then LLDB will try and load: "~/.lldbinit-%s" where %s the basename of your program "~/.lldbinit" Then LLDB will load any program specified on the command line and then source the "./.llbinit" file for any temporary debug session specific commands. I want this feature because I have thread and frame formats that do ANSI color codes that I only want to load when running in a terminal which is when I am running the "lldb" command line program. llvm-svn: 139476
2011-09-11 08:01:44 +08:00
// In the current working directory we don't load any program specific
// .lldbinit files, we only look for a "./.lldbinit" file.
if (m_skip_lldbinit_files)
return;
init_file.SetFile ("./.lldbinit", true);
Make ValueObject::SetValueFromCString work correctly. Also change the SourceInitFile to look for .lldb-<APPNAME> and source that preferentially if it exists. Also made the breakpoint site report its address as well as its breakpoint number when it gets hit and can't find any the associated locations (usually because the breakpoint got disabled or deleted programmatically between the time it was hit and reported.) Changed ThreadPlanCallFunction to initialize the ivar m_func in the initializers of the constructor, rather than waiting to initialize till later on in the function. Fixed a bug where if you make an SBError and the ask it Success, it returns false. Fixed ValueObject::ResolveValue so that it resolves a temporary value, rather than overwriting the one in the value object. llvm-svn: 137536
2011-08-13 07:34:31 +08:00
}
Don't skip the application specific ~/.lldbinit file when the program name is "lldb". So currently when you startup any application and you have not specified that you would like to skip loading init files through the API or from "lldb" options, then LLDB will try and load: "~/.lldbinit-%s" where %s the basename of your program "~/.lldbinit" Then LLDB will load any program specified on the command line and then source the "./.llbinit" file for any temporary debug session specific commands. I want this feature because I have thread and frame formats that do ANSI color codes that I only want to load when running in a terminal which is when I am running the "lldb" command line program. llvm-svn: 139476
2011-09-11 08:01:44 +08:00
else
Make ValueObject::SetValueFromCString work correctly. Also change the SourceInitFile to look for .lldb-<APPNAME> and source that preferentially if it exists. Also made the breakpoint site report its address as well as its breakpoint number when it gets hit and can't find any the associated locations (usually because the breakpoint got disabled or deleted programmatically between the time it was hit and reported.) Changed ThreadPlanCallFunction to initialize the ivar m_func in the initializers of the constructor, rather than waiting to initialize till later on in the function. Fixed a bug where if you make an SBError and the ask it Success, it returns false. Fixed ValueObject::ResolveValue so that it resolves a temporary value, rather than overwriting the one in the value object. llvm-svn: 137536
2011-08-13 07:34:31 +08:00
{
Don't skip the application specific ~/.lldbinit file when the program name is "lldb". So currently when you startup any application and you have not specified that you would like to skip loading init files through the API or from "lldb" options, then LLDB will try and load: "~/.lldbinit-%s" where %s the basename of your program "~/.lldbinit" Then LLDB will load any program specified on the command line and then source the "./.llbinit" file for any temporary debug session specific commands. I want this feature because I have thread and frame formats that do ANSI color codes that I only want to load when running in a terminal which is when I am running the "lldb" command line program. llvm-svn: 139476
2011-09-11 08:01:44 +08:00
// If we aren't looking in the current working directory we are looking
// in the home directory. We will first see if there is an application
// specific ".lldbinit" file whose name is "~/.lldbinit" followed by a
// "-" and the name of the program. If this file doesn't exist, we fall
// back to just the "~/.lldbinit" file. We also obey any requests to not
// load the init files.
const char *init_file_path = "~/.lldbinit";
if (m_skip_app_init_files == false)
{
FileSpec program_file_spec (Host::GetProgramFileSpec());
const char *program_name = program_file_spec.GetFilename().AsCString();
Make ValueObject::SetValueFromCString work correctly. Also change the SourceInitFile to look for .lldb-<APPNAME> and source that preferentially if it exists. Also made the breakpoint site report its address as well as its breakpoint number when it gets hit and can't find any the associated locations (usually because the breakpoint got disabled or deleted programmatically between the time it was hit and reported.) Changed ThreadPlanCallFunction to initialize the ivar m_func in the initializers of the constructor, rather than waiting to initialize till later on in the function. Fixed a bug where if you make an SBError and the ask it Success, it returns false. Fixed ValueObject::ResolveValue so that it resolves a temporary value, rather than overwriting the one in the value object. llvm-svn: 137536
2011-08-13 07:34:31 +08:00
Don't skip the application specific ~/.lldbinit file when the program name is "lldb". So currently when you startup any application and you have not specified that you would like to skip loading init files through the API or from "lldb" options, then LLDB will try and load: "~/.lldbinit-%s" where %s the basename of your program "~/.lldbinit" Then LLDB will load any program specified on the command line and then source the "./.llbinit" file for any temporary debug session specific commands. I want this feature because I have thread and frame formats that do ANSI color codes that I only want to load when running in a terminal which is when I am running the "lldb" command line program. llvm-svn: 139476
2011-09-11 08:01:44 +08:00
if (program_name)
{
char program_init_file_name[PATH_MAX];
::snprintf (program_init_file_name, sizeof(program_init_file_name), "%s-%s", init_file_path, program_name);
init_file.SetFile (program_init_file_name, true);
if (!init_file.Exists())
init_file.Clear();
}
}
if (!init_file && !m_skip_lldbinit_files)
init_file.SetFile (init_file_path, true);
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
// If the file exists, tell HandleCommand to 'source' it; this will do the actual broadcasting
// of the commands back to any appropriate listener (see CommandObjectSource::Execute for more details).
if (init_file.Exists())
{
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
ExecutionContext *exe_ctx = NULL; // We don't have any context yet.
bool stop_on_continue = true;
bool stop_on_error = false;
bool echo_commands = false;
bool print_results = false;
HandleCommandsFromFile (init_file, exe_ctx, stop_on_continue, stop_on_error, echo_commands, print_results, result);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
else
{
// nothing to be done if the file doesn't exist
result.SetStatus(eReturnStatusSuccessFinishNoResult);
}
}
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
PlatformSP
CommandInterpreter::GetPlatform (bool prefer_target_platform)
{
PlatformSP platform_sp;
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
if (prefer_target_platform)
{
Target *target = m_exe_ctx.GetTargetPtr();
if (target)
platform_sp = target->GetPlatform();
}
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
if (!platform_sp)
platform_sp = m_debugger.GetPlatformList().GetSelectedPlatform();
return platform_sp;
}
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
void
CommandInterpreter::HandleCommands should take its commands as a "const StringList &" since it doesn't modify it... Also, don't turn on the immediate output in the temporary result, or you'll get doubled output. llvm-svn: 127452
2011-03-11 09:51:49 +08:00
CommandInterpreter::HandleCommands (const StringList &commands,
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
ExecutionContext *override_context,
bool stop_on_continue,
bool stop_on_error,
bool echo_commands,
bool print_results,
CommandReturnObject &result)
{
size_t num_lines = commands.GetSize();
// If we are going to continue past a "continue" then we need to run the commands synchronously.
// Make sure you reset this value anywhere you return from the function.
bool old_async_execution = m_debugger.GetAsyncExecution();
// If we've been given an execution context, set it at the start, but don't keep resetting it or we will
// cause series of commands that change the context, then do an operation that relies on that context to fail.
if (override_context != NULL)
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
UpdateExecutionContext (override_context);
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
if (!stop_on_continue)
{
m_debugger.SetAsyncExecution (false);
}
for (int idx = 0; idx < num_lines; idx++)
{
const char *cmd = commands.GetStringAtIndex(idx);
if (cmd[0] == '\0')
continue;
if (echo_commands)
{
result.AppendMessageWithFormat ("%s %s\n",
GetPrompt(),
cmd);
}
Don't limit StreamTee to just two streams. It now can contain N streams by making the stream a vector of stream shared pointers that is protected by a mutex. Streams can be get/set by index which allows indexes to be defined as stream indentifiers. If a stream is set at index 3 and there are now streams in the collection, then empty stream objects are inserted to ensure that stream at index 3 has a valid stream. There is also an append method that allows a stream to be pushed onto the stack. This will allow our streams to be very flexible in where the output goes. Modified the CommandReturnObject to use the new StreamTee functionality. This class now defines two StreamTee indexes: 0 for the stream string stream, and 1 for the immediate stream. This is used both on the output and error streams. Added the ability to get argument types as strings or as descriptions. This is exported through the SBCommandInterpreter API to allow external access. Modified the Driver class to use the newly exported argument names from SBCommandInterpreter::GetArgumentTypeAsCString(). llvm-svn: 126067
2011-02-20 10:15:07 +08:00
CommandReturnObject tmp_result;
Fix a problem where the stop-hook command 'frame variable g_val' produces nothing when newly created threads were subsequently stopped due to breakpoint hit. The stop-hook mechanism delegates to CommandInterpreter::HandleCommands() to execuet the commands. Make sure the execution context is switched only once at the beginning of HandleCommands() only and don't update the context while looping on each individual command to be executed. rdar://problem/10228156 llvm-svn: 141144
2011-10-05 08:42:59 +08:00
// If override_context is not NULL, pass no_context_switching = true for
// HandleCommand() since we updated our context already.
bool success = HandleCommand(cmd, false, tmp_result,
NULL, /* override_context */
true, /* repeat_on_empty_command */
override_context != NULL /* no_context_switching */);
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
if (print_results)
{
if (tmp_result.Succeeded())
- Changed all the places where CommandObjectReturn was exporting a StreamString to just exporting a Stream, and then added GetOutputData & GetErrorData to get the accumulated data. - Added a StreamTee that will tee output to two provided lldb::StreamSP's. - Made the CommandObjectReturn use this so you can Tee the results immediately to the debuggers output file, as well as saving up the results to return when the command is done executing. - HandleCommands now uses this so that if you have a set of commands that continue the target you will see the commands come out as they are processed. - The Driver now uses this to output the command results as you go, which makes the interface more reactive seeming. llvm-svn: 126015
2011-02-19 10:53:09 +08:00
result.AppendMessageWithFormat("%s", tmp_result.GetOutputData());
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
}
if (!success || !tmp_result.Succeeded())
{
if (stop_on_error)
{
result.AppendErrorWithFormat("Aborting reading of commands after command #%d: '%s' failed.\n",
idx, cmd);
result.SetStatus (eReturnStatusFailed);
m_debugger.SetAsyncExecution (old_async_execution);
return;
}
else if (print_results)
{
result.AppendMessageWithFormat ("Command #%d '%s' failed with error: %s.\n",
idx + 1,
cmd,
- Changed all the places where CommandObjectReturn was exporting a StreamString to just exporting a Stream, and then added GetOutputData & GetErrorData to get the accumulated data. - Added a StreamTee that will tee output to two provided lldb::StreamSP's. - Made the CommandObjectReturn use this so you can Tee the results immediately to the debuggers output file, as well as saving up the results to return when the command is done executing. - HandleCommands now uses this so that if you have a set of commands that continue the target you will see the commands come out as they are processed. - The Driver now uses this to output the command results as you go, which makes the interface more reactive seeming. llvm-svn: 126015
2011-02-19 10:53:09 +08:00
tmp_result.GetErrorData());
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
}
}
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
if (result.GetImmediateOutputStream())
result.GetImmediateOutputStream()->Flush();
if (result.GetImmediateErrorStream())
result.GetImmediateErrorStream()->Flush();
Factor all the code that does "Execute a list of lldb command interpreter commands" into a single function in the Interpreter, and then use that in all the places that used to do this by hand. llvm-svn: 125807
2011-02-18 08:54:25 +08:00
// N.B. Can't depend on DidChangeProcessState, because the state coming into the command execution
// could be running (for instance in Breakpoint Commands.
// So we check the return value to see if it is has running in it.
if ((tmp_result.GetStatus() == eReturnStatusSuccessContinuingNoResult)
|| (tmp_result.GetStatus() == eReturnStatusSuccessContinuingResult))
{
if (stop_on_continue)
{
// If we caused the target to proceed, and we're going to stop in that case, set the
// status in our real result before returning. This is an error if the continue was not the
// last command in the set of commands to be run.
if (idx != num_lines - 1)
result.AppendErrorWithFormat("Aborting reading of commands after command #%d: '%s' continued the target.\n",
idx + 1, cmd);
else
result.AppendMessageWithFormat ("Command #%d '%s' continued the target.\n", idx + 1, cmd);
result.SetStatus(tmp_result.GetStatus());
m_debugger.SetAsyncExecution (old_async_execution);
return;
}
}
}
result.SetStatus (eReturnStatusSuccessFinishResult);
m_debugger.SetAsyncExecution (old_async_execution);
return;
}
void
CommandInterpreter::HandleCommandsFromFile (FileSpec &cmd_file,
ExecutionContext *context,
bool stop_on_continue,
bool stop_on_error,
bool echo_command,
bool print_result,
CommandReturnObject &result)
{
if (cmd_file.Exists())
{
bool success;
StringList commands;
success = commands.ReadFileLines(cmd_file);
if (!success)
{
result.AppendErrorWithFormat ("Error reading commands from file: %s.\n", cmd_file.GetFilename().AsCString());
result.SetStatus (eReturnStatusFailed);
return;
}
HandleCommands (commands, context, stop_on_continue, stop_on_error, echo_command, print_result, result);
}
else
{
result.AppendErrorWithFormat ("Error reading commands from file %s - file not found.\n",
cmd_file.GetFilename().AsCString());
result.SetStatus (eReturnStatusFailed);
return;
}
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
ScriptInterpreter *
CommandInterpreter::GetScriptInterpreter ()
{
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
if (m_script_interpreter_ap.get() != NULL)
return m_script_interpreter_ap.get();
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
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
lldb::ScriptLanguage script_lang = GetDebugger().GetScriptLanguage();
switch (script_lang)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
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
case eScriptLanguageNone:
m_script_interpreter_ap.reset (new ScriptInterpreterNone (*this));
break;
case eScriptLanguagePython:
m_script_interpreter_ap.reset (new ScriptInterpreterPython (*this));
break;
default:
break;
};
return m_script_interpreter_ap.get();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
bool
CommandInterpreter::GetSynchronous ()
{
return m_synchronous_execution;
}
void
CommandInterpreter::SetSynchronous (bool value)
{
Add an initial version of test that exercise the lldb commands: 'process signal' and 'process handle'. The test suite would like to control the asynch/sync execution of the interpreter during the middle of the test method, so the CommandInterpreter::SetSynchronous(bool value) is modified to allow the mode to be changed more than once. In practice, it would be advisable to control the process and to set the async/sync mode from a single thread, too. llvm-svn: 116467
2010-10-14 09:22:03 +08:00
m_synchronous_execution = value;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
void
CommandInterpreter::OutputFormattedHelpText (Stream &strm,
const char *word_text,
const char *separator,
const char *help_text,
uint32_t max_word_len)
{
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
const uint32_t max_columns = m_debugger.GetTerminalWidth();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
int indent_size = max_word_len + strlen (separator) + 2;
strm.IndentMore (indent_size);
Added new target instance settings for execution settings: Targets can now specify some additional parameters for when we debug executables that can help with plug-in selection: target.execution-level = auto | user | kernel target.execution-mode = auto | dynamic | static target.execution-os-type = auto | none | halted | live On some systems, the binaries that are created are the same wether you use them to debug a kernel, or a user space program. Many times inspecting an object file can reveal what an executable should be. For these cases we can now be a little more complete by specifying wether to detect all of these things automatically (inspect the main executable file and select a plug-in accordingly), or manually to force the selection of certain plug-ins. To do this we now allow the specficifation of wether one is debugging a user space program (target.execution-level = user) or a kernel program (target.execution-level = kernel). We can also specify if we want to debug a program where shared libraries are dynamically loaded using a DynamicLoader plug-in (target.execution-mode = dynamic), or wether we will treat all symbol files as already linked at the correct address (target.execution-mode = static). We can also specify if the inferior we are debugging is being debugged on a bare board (target.execution-os-type = none), or debugging an OS where we have a JTAG or other direct connection to the inferior stops the entire OS (target.execution-os-type = halted), or if we are debugging a program on something that has live debug services (target.execution-os-type = live). For the "target.execution-os-type = halted" mode, we will need to create ProcessHelper plug-ins that allow us to extract the process/thread and other OS information by reading/writing memory. This should allow LLDB to be used for a wide variety of debugging tasks and handle them all correctly. llvm-svn: 125815
2011-02-18 09:44:25 +08:00
StreamString text_strm;
text_strm.Printf ("%-*s %s %s", max_word_len, word_text, separator, help_text);
size_t len = text_strm.GetSize();
const char *text = text_strm.GetData();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (text[len - 1] == '\n')
Added new target instance settings for execution settings: Targets can now specify some additional parameters for when we debug executables that can help with plug-in selection: target.execution-level = auto | user | kernel target.execution-mode = auto | dynamic | static target.execution-os-type = auto | none | halted | live On some systems, the binaries that are created are the same wether you use them to debug a kernel, or a user space program. Many times inspecting an object file can reveal what an executable should be. For these cases we can now be a little more complete by specifying wether to detect all of these things automatically (inspect the main executable file and select a plug-in accordingly), or manually to force the selection of certain plug-ins. To do this we now allow the specficifation of wether one is debugging a user space program (target.execution-level = user) or a kernel program (target.execution-level = kernel). We can also specify if we want to debug a program where shared libraries are dynamically loaded using a DynamicLoader plug-in (target.execution-mode = dynamic), or wether we will treat all symbol files as already linked at the correct address (target.execution-mode = static). We can also specify if the inferior we are debugging is being debugged on a bare board (target.execution-os-type = none), or debugging an OS where we have a JTAG or other direct connection to the inferior stops the entire OS (target.execution-os-type = halted), or if we are debugging a program on something that has live debug services (target.execution-os-type = live). For the "target.execution-os-type = halted" mode, we will need to create ProcessHelper plug-ins that allow us to extract the process/thread and other OS information by reading/writing memory. This should allow LLDB to be used for a wide variety of debugging tasks and handle them all correctly. llvm-svn: 125815
2011-02-18 09:44:25 +08:00
{
text_strm.EOL();
len = text_strm.GetSize();
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
if (len < max_columns)
{
// Output it as a single line.
strm.Printf ("%s", text);
}
else
{
// We need to break it up into multiple lines.
bool first_line = true;
int text_width;
int start = 0;
int end = start;
int final_end = strlen (text);
int sub_len;
while (end < final_end)
{
if (first_line)
text_width = max_columns - 1;
else
text_width = max_columns - indent_size - 1;
// Don't start the 'text' on a space, since we're already outputting the indentation.
if (!first_line)
{
while ((start < final_end) && (text[start] == ' '))
start++;
}
end = start + text_width;
if (end > final_end)
end = final_end;
else
{
// If we're not at the end of the text, make sure we break the line on white space.
while (end > start
&& text[end] != ' ' && text[end] != '\t' && text[end] != '\n')
end--;
}
sub_len = end - start;
if (start != 0)
strm.EOL();
if (!first_line)
strm.Indent();
else
first_line = false;
assert (start <= final_end);
assert (start + sub_len <= final_end);
if (sub_len > 0)
strm.Write (text + start, sub_len);
start = end + 1;
}
}
strm.EOL();
strm.IndentLess(indent_size);
}
new detailed descriptions for type summary add and type format add some changes to the help system code for better display of long help text -p and -r flags now also work for type format add llvm-svn: 134574
2011-07-07 08:38:40 +08:00
void
CommandInterpreter::OutputHelpText (Stream &strm,
const char *word_text,
const char *separator,
const char *help_text,
uint32_t max_word_len)
{
int indent_size = max_word_len + strlen (separator) + 2;
strm.IndentMore (indent_size);
StreamString text_strm;
text_strm.Printf ("%-*s %s %s", max_word_len, word_text, separator, help_text);
const uint32_t max_columns = m_debugger.GetTerminalWidth();
bool first_line = true;
size_t len = text_strm.GetSize();
const char *text = text_strm.GetData();
uint32_t chars_left = max_columns;
for (uint32_t i = 0; i < len; i++)
{
if ((text[i] == ' ' && ::strchr((text+i+1), ' ') && chars_left < ::strchr((text+i+1), ' ')-(text+i)) || text[i] == '\n')
{
first_line = false;
chars_left = max_columns - indent_size;
strm.EOL();
strm.Indent();
}
else
{
strm.PutChar(text[i]);
chars_left--;
}
}
strm.EOL();
strm.IndentLess(indent_size);
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
void
CommandInterpreter::AproposAllSubCommands (CommandObject *cmd_obj, const char *prefix, const char *search_word,
StringList &commands_found, StringList &commands_help)
{
CommandObject::CommandMap::const_iterator pos;
CommandObject::CommandMap sub_cmd_dict = ((CommandObjectMultiword *) cmd_obj)->m_subcommand_dict;
CommandObject *sub_cmd_obj;
for (pos = sub_cmd_dict.begin(); pos != sub_cmd_dict.end(); ++pos)
{
const char * command_name = pos->first.c_str();
sub_cmd_obj = pos->second.get();
StreamString complete_command_name;
complete_command_name.Printf ("%s %s", prefix, command_name);
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
if (sub_cmd_obj->HelpTextContainsWord (search_word))
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
commands_found.AppendString (complete_command_name.GetData());
commands_help.AppendString (sub_cmd_obj->GetHelp());
}
if (sub_cmd_obj->IsMultiwordObject())
AproposAllSubCommands (sub_cmd_obj, complete_command_name.GetData(), search_word, commands_found,
commands_help);
}
}
void
CommandInterpreter::FindCommandsForApropos (const char *search_word, StringList &commands_found,
StringList &commands_help)
{
CommandObject::CommandMap::const_iterator pos;
for (pos = m_command_dict.begin(); pos != m_command_dict.end(); ++pos)
{
const char *command_name = pos->first.c_str();
CommandObject *cmd_obj = pos->second.get();
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
if (cmd_obj->HelpTextContainsWord (search_word))
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
commands_found.AppendString (command_name);
commands_help.AppendString (cmd_obj->GetHelp());
}
if (cmd_obj->IsMultiwordObject())
AproposAllSubCommands (cmd_obj, command_name, search_word, commands_found, commands_help);
}
}
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
void
CommandInterpreter::UpdateExecutionContext (ExecutionContext *override_context)
{
m_exe_ctx.Clear();
if (override_context != NULL)
{
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
m_exe_ctx = *override_context;
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
}
else
{
TargetSP target_sp (m_debugger.GetSelectedTarget());
if (target_sp)
{
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
m_exe_ctx.SetTargetSP (target_sp);
ProcessSP process_sp (target_sp->GetProcessSP());
m_exe_ctx.SetProcessSP (process_sp);
if (process_sp && process_sp->IsAlive() && !process_sp->IsRunning())
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
{
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
ThreadSP thread_sp (process_sp->GetThreadList().GetSelectedThread().get());
if (thread_sp)
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
{
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
m_exe_ctx.SetThreadSP (thread_sp);
StackFrameSP frame_sp (thread_sp->GetSelectedFrame());
if (!frame_sp)
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
{
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
frame_sp = thread_sp->GetStackFrameAtIndex (0);
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
// If we didn't have a selected frame select one here.
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
if (frame_sp)
thread_sp->SetSelectedFrame(frame_sp.get());
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
}
Converted the lldb_private::Process over to use the intrusive shared pointers. Changed the ExecutionContext over to use shared pointers for the target, process, thread and frame since these objects can easily go away at any time and any object that was holding onto an ExecutionContext was running the risk of using a bad object. Now that the shared pointers for target, process, thread and frame are just a single pointer (they all use the instrusive shared pointers) the execution context is much safer and still the same size. Made the shared pointers in the the ExecutionContext class protected and made accessors for all of the various ways to get at the pointers, references, and shared pointers. llvm-svn: 140298
2011-09-22 12:58:26 +08:00
if (frame_sp)
m_exe_ctx.SetFrameSP (frame_sp);
Moved the execution context that was in the Debugger into the CommandInterpreter where it was always being used. Make sure that Modules can track their object file offsets correctly to allow opening of sub object files (like the "__commpage" on darwin). Modified the Platforms to be able to launch processes. The first part of this move is the platform soon will become the entity that launches your program and when it does, it uses a new ProcessLaunchInfo class which encapsulates all process launching settings. This simplifies the internal APIs needed for launching. I want to slowly phase out process launching from the process classes, so for now we can still launch just as we used to, but eventually the platform is the object that should do the launching. Modified the Host::LaunchProcess in the MacOSX Host.mm to correctly be able to launch processes with all of the new eLaunchFlag settings. Modified any code that was manually launching processes to use the Host::LaunchProcess functions. Fixed an issue where lldb_private::Args had implicitly defined copy constructors that could do the wrong thing. This has now been fixed by adding an appropriate copy constructor and assignment operator. Make sure we don't add empty ModuleSP entries to a module list. Fixed the commpage module creation on MacOSX, but we still need to train the MacOSX dynamic loader to not get rid of it when it doesn't have an entry in the all image infos. Abstracted many more calls from in ProcessGDBRemote down into the GDBRemoteCommunicationClient subclass to make the classes cleaner and more efficient. Fixed the default iOS ARM register context to be correct and also added support for targets that don't support the qThreadStopInfo packet by selecting the current thread (only if needed) and then sending a stop reply packet. Debugserver can now start up with a --unix-socket (-u for short) and can then bind to port zero and send the port it bound to to a listening process on the other end. This allows the GDB remote platform to spawn new GDB server instances (debugserver) to allow platform debugging. llvm-svn: 129351
2011-04-12 13:54:46 +08:00
}
}
}
}
}
Added "command history" command to dump the command history. Also made: (lldb) !<NUM> (lldb) !-<NUM> (lldb) !! work with the history. For added benefit: (lldb) !<NUM><TAB> will insert the command at position <NUM> in the history into the command line to be edited. This is only partial, I still need to sync up editline's history list with the one kept by the interpreter. llvm-svn: 134955
2011-07-12 11:12:18 +08:00
void
CommandInterpreter::DumpHistory (Stream &stream, uint32_t count) const
{
DumpHistory (stream, 0, count - 1);
}
void
CommandInterpreter::DumpHistory (Stream &stream, uint32_t start, uint32_t end) const
{
size_t num_history_elements = m_command_history.size();
if (start > num_history_elements)
return;
for (uint32_t i = start; i < num_history_elements && i <= end; i++)
{
if (!m_command_history[i].empty())
{
stream.Indent();
stream.Printf ("%4d: %s\n", i, m_command_history[i].c_str());
}
}
}
const char *
CommandInterpreter::FindHistoryString (const char *input_str) const
{
if (input_str[0] != m_repeat_char)
return NULL;
if (input_str[1] == '-')
{
bool success;
uint32_t idx = Args::StringToUInt32 (input_str+2, 0, 0, &success);
if (!success)
return NULL;
if (idx > m_command_history.size())
return NULL;
idx = m_command_history.size() - idx;
return m_command_history[idx].c_str();
}
else if (input_str[1] == m_repeat_char)
{
if (m_command_history.empty())
return NULL;
else
return m_command_history.back().c_str();
}
else
{
bool success;
uint32_t idx = Args::StringToUInt32 (input_str+1, 0, 0, &success);
if (!success)
return NULL;
if (idx >= m_command_history.size())
return NULL;
return m_command_history[idx].c_str();
}
}