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

617 lines
23 KiB
C++
Raw Normal View History

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
//===-- FormatManager.cpp -------------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "lldb/Core/FormatManager.h"
// C Includes
// C++ Includes
// Other libraries and framework includes
// Project includes
Python summary strings: - you can use a Python script to write a summary string for data-types, in one of three ways: -P option and typing the script a line at a time -s option and passing a one-line Python script -F option and passing the name of a Python function these options all work for the "type summary add" command your Python code (if provided through -P or -s) is wrapped in a function that accepts two parameters: valobj (a ValueObject) and dict (an LLDB internal dictionary object). if you use -F and give a function name, you're expected to define the function on your own and with the right prototype. your function, however defined, must return a Python string - test case for the Python summary feature - a few quirks: Python summaries cannot have names, and cannot use regex as type names both issues will be fixed ASAP major redesign of type summary code: - type summary working with strings and type summary working with Python code are two classes, with a common base class SummaryFormat - SummaryFormat classes now are able to actively format objects rather than just aggregating data - cleaner code to print descriptions for summaries the public API now exports a method to easily navigate a ValueObject hierarchy New InputReaderEZ and PriorityPointerPair classes Several minor fixes and improvements llvm-svn: 135238
2011-07-15 10:26:42 +08:00
#include "lldb/Core/Debugger.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
using namespace lldb;
using namespace lldb_private;
Centralized all of the format to c-string and to format character code inside the FormatManager class. Modified the format arguments in any commands to be able to use a single character format, or a full format name, or a partial format name if no full format names match. Modified any code that was displaying formats to use the new FormatManager calls so that our help text and errors never get out of date. Modified the display of the "type format list" command to be a bit more human readable by showing the format as a format string rather than the single character format char. llvm-svn: 133765
2011-06-24 05:22:24 +08:00
struct FormatInfo
{
Format format;
const char format_char; // One or more format characters that can be used for this format.
const char *format_name; // Long format name that can be used to specify the current format
};
static FormatInfo
g_format_infos[] =
{
{ eFormatDefault , '\0' , "default" },
{ eFormatBoolean , 'B' , "boolean" },
{ eFormatBinary , 'b' , "binary" },
{ eFormatBytes , 'y' , "bytes" },
{ eFormatBytesWithASCII , 'Y' , "bytes with ASCII" },
{ eFormatChar , 'c' , "character" },
{ eFormatCharPrintable , 'C' , "printable character" },
{ eFormatComplexFloat , 'F' , "complex float" },
{ eFormatCString , 's' , "c-string" },
Improved the user-friendliness of errors shown by the summary feature in certain areas Renamed format "signed decimal" to be "decimal". "unsigned decimal" remains unchanged: - the name "signed decimal" was interfering with symbol %S (use summary) in summary strings. because of the way summary strings are implemented, this did not really lead to a bug, but simply to performing more steps than necessary to display a summary. this is fixed. Documentation improvements (more on synthetic children, some information on filters). This is still a WIP. llvm-svn: 138384
2011-08-24 05:26:09 +08:00
{ eFormatDecimal , 'i' , "decimal" },
Centralized all of the format to c-string and to format character code inside the FormatManager class. Modified the format arguments in any commands to be able to use a single character format, or a full format name, or a partial format name if no full format names match. Modified any code that was displaying formats to use the new FormatManager calls so that our help text and errors never get out of date. Modified the display of the "type format list" command to be a bit more human readable by showing the format as a format string rather than the single character format char. llvm-svn: 133765
2011-06-24 05:22:24 +08:00
{ eFormatEnum , 'E' , "enumeration" },
{ eFormatHex , 'x' , "hex" },
{ eFormatFloat , 'f' , "float" },
{ eFormatOctal , 'o' , "octal" },
{ eFormatOSType , 'O' , "OSType" },
{ eFormatUnicode16 , 'U' , "unicode16" },
{ eFormatUnicode32 , '\0' , "unicode32" },
{ eFormatUnsigned , 'u' , "unsigned decimal" },
{ eFormatPointer , 'p' , "pointer" },
{ eFormatVectorOfChar , '\0' , "char[]" },
{ eFormatVectorOfSInt8 , '\0' , "int8_t[]" },
{ eFormatVectorOfUInt8 , '\0' , "uint8_t[]" },
{ eFormatVectorOfSInt16 , '\0' , "int16_t[]" },
{ eFormatVectorOfUInt16 , '\0' , "uint16_t[]" },
Fixed some format names llvm-svn: 134492
2011-07-06 23:56:06 +08:00
{ eFormatVectorOfSInt32 , '\0' , "int32_t[]" },
{ eFormatVectorOfUInt32 , '\0' , "uint32_t[]" },
{ eFormatVectorOfSInt64 , '\0' , "int64_t[]" },
{ eFormatVectorOfUInt64 , '\0' , "uint64_t[]" },
Centralized all of the format to c-string and to format character code inside the FormatManager class. Modified the format arguments in any commands to be able to use a single character format, or a full format name, or a partial format name if no full format names match. Modified any code that was displaying formats to use the new FormatManager calls so that our help text and errors never get out of date. Modified the display of the "type format list" command to be a bit more human readable by showing the format as a format string rather than the single character format char. llvm-svn: 133765
2011-06-24 05:22:24 +08:00
{ eFormatVectorOfFloat32, '\0' , "float32[]" },
{ eFormatVectorOfFloat64, '\0' , "float64[]" },
{ eFormatVectorOfUInt128, '\0' , "uint128_t[]" },
{ eFormatComplexInteger , 'I' , "complex integer" },
{ eFormatCharArray , 'a' , "character array" }
};
static uint32_t
g_num_format_infos = sizeof(g_format_infos)/sizeof(FormatInfo);
static bool
GetFormatFromFormatChar (char format_char, Format &format)
{
for (uint32_t i=0; i<g_num_format_infos; ++i)
{
if (g_format_infos[i].format_char == format_char)
{
format = g_format_infos[i].format;
return true;
}
}
format = eFormatInvalid;
return false;
}
static bool
GetFormatFromFormatName (const char *format_name, bool partial_match_ok, Format &format)
{
uint32_t i;
for (i=0; i<g_num_format_infos; ++i)
{
if (strcasecmp (g_format_infos[i].format_name, format_name) == 0)
{
format = g_format_infos[i].format;
return true;
}
}
if (partial_match_ok)
{
for (i=0; i<g_num_format_infos; ++i)
{
if (strcasestr (g_format_infos[i].format_name, format_name) == g_format_infos[i].format_name)
{
format = g_format_infos[i].format;
return true;
}
}
}
format = eFormatInvalid;
return false;
}
bool
FormatManager::GetFormatFromCString (const char *format_cstr,
bool partial_match_ok,
lldb::Format &format)
{
bool success = false;
if (format_cstr && format_cstr[0])
{
if (format_cstr[1] == '\0')
{
success = GetFormatFromFormatChar (format_cstr[0], format);
if (success)
return true;
}
success = GetFormatFromFormatName (format_cstr, partial_match_ok, format);
}
if (!success)
format = eFormatInvalid;
return success;
}
char
FormatManager::GetFormatAsFormatChar (lldb::Format format)
{
for (uint32_t i=0; i<g_num_format_infos; ++i)
{
if (g_format_infos[i].format == format)
return g_format_infos[i].format_char;
}
return '\0';
}
const char *
FormatManager::GetFormatAsCString (Format format)
{
if (format >= eFormatDefault && format < kNumFormats)
return g_format_infos[format].format_name;
return NULL;
}
several improvements to "type summary": - type names can now be regular expressions (exact matching is done first, and is faster) - integral (and floating) types can be printed as bitfields, i.e. ${var[low-high]} will extract bits low thru high of the value and print them - array subscripts are supported, both for arrays and for pointers. the syntax is ${*var[low-high]}, or ${*var[]} to print the whole array (the latter only works for statically sized arrays) - summary is now printed by default when a summary string references a variable. if that variable's type has no summary, value is printed instead. to force value, you can use %V as a format specifier - basic support for ObjectiveC: - ObjectiveC inheritance chains are now walked through - %@ can be specified as a summary format, to print the ObjectiveC runtime description for an object - some bug fixes llvm-svn: 134293
2011-07-02 08:25:22 +08:00
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
FormatCategory::FormatCategory(IFormatChangeListener* clist,
std::string name) :
m_summary_nav(new SummaryNavigator("summary",clist)),
m_regex_summary_nav(new RegexSummaryNavigator("regex-summary",clist)),
m_filter_nav(new FilterNavigator("filter",clist)),
m_regex_filter_nav(new RegexFilterNavigator("regex-filter",clist)),
m_synth_nav(new SynthNavigator("synth",clist)),
m_regex_synth_nav(new RegexSynthNavigator("regex-synth",clist)),
m_enabled(false),
m_change_listener(clist),
m_mutex(Mutex::eMutexTypeRecursive),
m_name(name)
{}
Additional code cleanups ; Short option name for --python-script in type summary add moved from -s to -o (this is a preliminary step in moving the short option for --summary-string from -f to -s) ; Accordingly updated the test suite llvm-svn: 138315
2011-08-23 08:32:52 +08:00
bool
FormatCategory::Get (ValueObject& valobj,
lldb::SummaryFormatSP& entry,
lldb::DynamicValueType use_dynamic,
uint32_t* reason)
{
if (!IsEnabled())
return false;
if (GetSummaryNavigator()->Get(valobj, entry, use_dynamic, reason))
return true;
bool regex = GetRegexSummaryNavigator()->Get(valobj, entry, use_dynamic, reason);
if (regex && reason)
*reason |= lldb::eFormatterChoiceCriterionRegularExpressionSummary;
return regex;
}
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
bool
FormatCategory::Get(ValueObject& valobj,
lldb::SyntheticChildrenSP& entry,
lldb::DynamicValueType use_dynamic,
uint32_t* reason)
{
if (!IsEnabled())
return false;
SyntheticFilter::SharedPointer filter;
SyntheticScriptProvider::SharedPointer synth;
bool regex_filter, regex_synth;
uint32_t reason_filter;
uint32_t reason_synth;
bool pick_synth = false;
// first find both Filter and Synth, and then check which is most recent
if (!GetFilterNavigator()->Get(valobj, filter, use_dynamic, &reason_filter))
regex_filter = GetRegexFilterNavigator()->Get(valobj, filter, use_dynamic, &reason_filter);
if (!GetSyntheticNavigator()->Get(valobj, synth, use_dynamic, &reason_synth))
regex_synth = GetRegexSyntheticNavigator()->Get(valobj, synth, use_dynamic, &reason_synth);
if (!filter.get() && !synth.get())
return false;
else if (!filter.get() && synth.get())
pick_synth = true;
else if (filter.get() && !synth.get())
pick_synth = false;
else /*if (filter.get() && synth.get())*/
{
if (filter->m_my_revision > synth->m_my_revision)
pick_synth = false;
else
pick_synth = true;
}
if (pick_synth)
{
if (regex_synth && reason)
*reason |= lldb::eFormatterChoiceCriterionRegularExpressionFilter;
entry = synth;
return true;
}
else
{
if (regex_filter && reason)
*reason |= lldb::eFormatterChoiceCriterionRegularExpressionFilter;
entry = filter;
return true;
}
}
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
void
FormatCategory::Clear (FormatCategoryItems items)
{
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSummary) == eFormatCategoryItemSummary )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
m_summary_nav->Clear();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSummary) == eFormatCategoryItemRegexSummary )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
m_regex_summary_nav->Clear();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemFilter) == eFormatCategoryItemFilter )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
m_filter_nav->Clear();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexFilter) == eFormatCategoryItemRegexFilter )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
m_regex_filter_nav->Clear();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSynth) == eFormatCategoryItemSynth )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
m_synth_nav->Clear();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSynth) == eFormatCategoryItemRegexSynth )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
m_regex_synth_nav->Clear();
}
bool
FormatCategory::Delete (ConstString name,
FormatCategoryItems items)
{
bool success = false;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSummary) == eFormatCategoryItemSummary )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
success = m_summary_nav->Delete(name) || success;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSummary) == eFormatCategoryItemRegexSummary )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
success = m_regex_summary_nav->Delete(name) || success;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemFilter) == eFormatCategoryItemFilter )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
success = m_filter_nav->Delete(name) || success;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexFilter) == eFormatCategoryItemRegexFilter )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
success = m_regex_filter_nav->Delete(name) || success;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSynth) == eFormatCategoryItemSynth )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
success = m_synth_nav->Delete(name) || success;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSynth) == eFormatCategoryItemRegexSynth )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
success = m_regex_synth_nav->Delete(name) || success;
return success;
}
uint32_t
FormatCategory::GetCount (FormatCategoryItems items)
{
uint32_t count = 0;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSummary) == eFormatCategoryItemSummary )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
count += m_summary_nav->GetCount();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSummary) == eFormatCategoryItemRegexSummary )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
count += m_regex_summary_nav->GetCount();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemFilter) == eFormatCategoryItemFilter )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
count += m_filter_nav->GetCount();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexFilter) == eFormatCategoryItemRegexFilter )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
count += m_regex_filter_nav->GetCount();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSynth) == eFormatCategoryItemSynth )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
count += m_synth_nav->GetCount();
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSynth) == eFormatCategoryItemRegexSynth )
More cleanups ; Separated implementation of FormatManager from class DataVisualization as a front-end by using separate .h/.cpp files - Final aim is to break up FormatManager.h/cpp into several separate files llvm-svn: 138279
2011-08-23 06:03:47 +08:00
count += m_regex_synth_nav->GetCount();
return count;
}
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
bool
FormatCategory::AnyMatches(ConstString type_name,
FormatCategoryItems items,
bool only_enabled,
const char** matching_category,
FormatCategoryItems* matching_type)
{
if (!IsEnabled() && only_enabled)
return false;
lldb::SummaryFormatSP summary;
SyntheticFilter::SharedPointer filter;
SyntheticScriptProvider::SharedPointer synth;
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSummary) == eFormatCategoryItemSummary )
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
{
if (m_summary_nav->Get(type_name, summary))
{
if (matching_category)
*matching_category = m_name.c_str();
if (matching_type)
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
*matching_type = eFormatCategoryItemSummary;
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
return true;
}
}
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSummary) == eFormatCategoryItemRegexSummary )
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
{
if (m_regex_summary_nav->Get(type_name, summary))
{
if (matching_category)
*matching_category = m_name.c_str();
if (matching_type)
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
*matching_type = eFormatCategoryItemRegexSummary;
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
return true;
}
}
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemFilter) == eFormatCategoryItemFilter )
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
{
if (m_filter_nav->Get(type_name, filter))
{
if (matching_category)
*matching_category = m_name.c_str();
if (matching_type)
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
*matching_type = eFormatCategoryItemFilter;
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
return true;
}
}
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexFilter) == eFormatCategoryItemRegexFilter )
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
{
if (m_regex_filter_nav->Get(type_name, filter))
{
if (matching_category)
*matching_category = m_name.c_str();
if (matching_type)
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
*matching_type = eFormatCategoryItemRegexFilter;
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
return true;
}
}
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemSynth) == eFormatCategoryItemSynth )
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
{
if (m_synth_nav->Get(type_name, synth))
{
if (matching_category)
*matching_category = m_name.c_str();
if (matching_type)
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
*matching_type = eFormatCategoryItemSynth;
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
return true;
}
}
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
if ( (items & eFormatCategoryItemRegexSynth) == eFormatCategoryItemRegexSynth )
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
{
if (m_regex_synth_nav->Get(type_name, synth))
{
if (matching_category)
*matching_category = m_name.c_str();
if (matching_type)
Separated FormatNavigator and FormatManager in two different files ; moved FormatCategoryItem enum out of FormatManager.h as a debugger-wide lldb_private enum ; minor style cleanups llvm-svn: 138307
2011-08-23 07:45:15 +08:00
*matching_type = eFormatCategoryItemRegexSynth;
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
return true;
}
}
return false;
}
Additional code cleanups ; Short option name for --python-script in type summary add moved from -s to -o (this is a preliminary step in moving the short option for --summary-string from -f to -s) ; Accordingly updated the test suite llvm-svn: 138315
2011-08-23 08:32:52 +08:00
bool
CategoryMap::AnyMatches (ConstString type_name,
FormatCategory::FormatCategoryItems items,
bool only_enabled,
const char** matching_category,
FormatCategory::FormatCategoryItems* matching_type)
{
Mutex::Locker(m_map_mutex);
MapIterator pos, end = m_map.end();
for (pos = m_map.begin(); pos != end; pos++)
{
if (pos->second->AnyMatches(type_name,
items,
only_enabled,
matching_category,
matching_type))
return true;
}
return false;
}
bool
CategoryMap::Get (ValueObject& valobj,
lldb::SummaryFormatSP& entry,
lldb::DynamicValueType use_dynamic)
{
Mutex::Locker(m_map_mutex);
uint32_t reason_why;
ActiveCategoriesIterator begin, end = m_active_categories.end();
for (begin = m_active_categories.begin(); begin != end; begin++)
{
lldb::FormatCategorySP category = *begin;
lldb::SummaryFormatSP current_format;
if (!category->Get(valobj, current_format, use_dynamic, &reason_why))
continue;
entry = current_format;
return true;
}
return false;
}
bool
CategoryMap::Get (ValueObject& valobj,
lldb::SyntheticChildrenSP& entry,
lldb::DynamicValueType use_dynamic)
{
Mutex::Locker(m_map_mutex);
uint32_t reason_why;
ActiveCategoriesIterator begin, end = m_active_categories.end();
for (begin = m_active_categories.begin(); begin != end; begin++)
{
lldb::FormatCategorySP category = *begin;
lldb::SyntheticChildrenSP current_format;
if (!category->Get(valobj, current_format, use_dynamic, &reason_why))
continue;
entry = current_format;
return true;
}
return false;
}
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
void
CategoryMap::LoopThrough(CallbackType callback, void* param)
{
if (callback)
{
Mutex::Locker(m_map_mutex);
// loop through enabled categories in respective order
{
ActiveCategoriesIterator begin, end = m_active_categories.end();
for (begin = m_active_categories.begin(); begin != end; begin++)
{
lldb::FormatCategorySP category = *begin;
Code cleanup and refactoring (round 4): - FormatCategories now are directly mapped by ConstString objects instead of going through const char* -> ConstString -> const char* - FormatCategory callback does not pass category name anymore. This is not necessary because FormatCategory objects themselves hold their name as a member variable llvm-svn: 138254
2011-08-23 02:36:52 +08:00
ConstString type = ConstString(category->GetName().c_str());
if (!callback(param, category))
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
break;
}
}
// loop through disabled categories in just any order
{
MapIterator pos, end = m_map.end();
for (pos = m_map.begin(); pos != end; pos++)
{
if (pos->second->IsEnabled())
continue;
KeyType type = pos->first;
Code cleanup and refactoring (round 4): - FormatCategories now are directly mapped by ConstString objects instead of going through const char* -> ConstString -> const char* - FormatCategory callback does not pass category name anymore. This is not necessary because FormatCategory objects themselves hold their name as a member variable llvm-svn: 138254
2011-08-23 02:36:52 +08:00
if (!callback(param, pos->second))
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
break;
}
}
}
}
Additional code cleanups ; Short option name for --python-script in type summary add moved from -s to -o (this is a preliminary step in moving the short option for --summary-string from -f to -s) ; Accordingly updated the test suite llvm-svn: 138315
2011-08-23 08:32:52 +08:00
lldb::FormatCategorySP
FormatManager::Category (const ConstString& category_name,
bool can_create)
{
if (!category_name)
return Category(m_default_category_name);
lldb::FormatCategorySP category;
if (m_categories_map.Get(category_name, category))
return category;
if (!can_create)
return lldb::FormatCategorySP();
m_categories_map.Add(category_name,lldb::FormatCategorySP(new FormatCategory(this, category_name.AsCString())));
return Category(category_name);
}
smarter summary strings: - formats %s %char[] %c and %a now work to print 0-terminated c-strings if they are applied to a char* or char[] even without the [] operator (e.g. ${var%s}) - array formats (char[], intN[], ..) now work when applied to an array of a scalar type even without the [] operator (e.g. ${var%int32_t[]}) LLDB will not crash because of endless loop when trying to obtain a summary for an object that has no value and references itself in its summary string In many cases, a wrong summary string will now display an "<error>" message instead of giving out an empty string llvm-svn: 135007
2011-07-13 06:56:10 +08:00
lldb::Format
FormatManager::GetSingleItemFormat(lldb::Format vector_format)
{
switch(vector_format)
{
case eFormatVectorOfChar:
return eFormatCharArray;
case eFormatVectorOfSInt8:
case eFormatVectorOfSInt16:
case eFormatVectorOfSInt32:
case eFormatVectorOfSInt64:
return eFormatDecimal;
case eFormatVectorOfUInt8:
case eFormatVectorOfUInt16:
case eFormatVectorOfUInt32:
case eFormatVectorOfUInt64:
case eFormatVectorOfUInt128:
return eFormatHex;
case eFormatVectorOfFloat32:
case eFormatVectorOfFloat64:
return eFormatFloat;
default:
return lldb::eFormatInvalid;
}
While tracking down memory consumption issue a few things were needed: the ability to dump more information about modules in "target modules list". We can now dump the shared pointer reference count for modules, the pointer to the module itself (in case performance tools can help track down who has references to said pointer), and the modification time. Added "target delete [target-idx ...]" to be able to delete targets when they are no longer needed. This will help track down memory usage issues and help to resolve when module ref counts keep getting incremented. If the command gets no arguments, the currently selected target will be deleted. If any arguments are given, they must all be valid target indexes (use the "target list" command to get the current target indexes). Took care of a bunch of "no newline at end of file" warnings. TimeValue objects can now dump their time to a lldb_private::Stream object. Modified the "target modules list --global" command to not error out if there are no targets since it doesn't require a target. Fixed an issue in the MacOSX DYLD dynamic loader plug-in where if a shared library was updated on disk, we would keep using the older one, even if it was updated. Don't allow the ModuleList::GetSharedModule(...) to return an empty module. Previously we could specify a valid path on disc to a module, and specify an architecture that wasn't contained in that module and get a shared pointer to a module that wouldn't be able to return an object file or a symbol file. We now make sure an object file can be extracted prior to adding the shared pointer to the module to get added to the shared list. llvm-svn: 137196
2011-08-10 10:10:13 +08:00
}
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
Third round of code cleanups: - reorganizing the PTS (Partial Template Specializations) in FormatManager.h - applied a patch by Filipe Cabecinhas to make LLDB compile with GCC Functional changes: - fixed an issue where command type summary add for type "struct Foo" would not match any types. currently, "struct" will be stripped off and type "Foo" will be matched. similar behavior occurs for class, enum and union specifiers. llvm-svn: 138020
2011-08-19 09:14:49 +08:00
ConstString
FormatManager::GetValidTypeName (const ConstString& type)
{
return ::GetValidTypeName_Impl(type);
}
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
FormatManager::FormatManager() :
m_value_nav("format",this),
m_named_summaries_map(this),
m_last_revision(0),
m_categories_map(this),
Code cleanup and refactoring (round 4): - FormatCategories now are directly mapped by ConstString objects instead of going through const char* -> ConstString -> const char* - FormatCategory callback does not pass category name anymore. This is not necessary because FormatCategory objects themselves hold their name as a member variable llvm-svn: 138254
2011-08-23 02:36:52 +08:00
m_default_category_name(ConstString("default")),
m_system_category_name(ConstString("system")),
m_gnu_cpp_category_name(ConstString("gnu-libstdc++"))
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
{
// add some default stuff
// most formats, summaries, ... actually belong to the users' lldbinit file rather than here
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
lldb::SummaryFormatSP string_format(new StringSummaryFormat(false,
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
true,
false,
true,
false,
false,
"${var%s}"));
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
lldb::SummaryFormatSP string_array_format(new StringSummaryFormat(false,
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
true,
false,
false,
false,
false,
"${var%s}"));
lldb::RegularExpressionSP any_size_char_arr(new RegularExpression("char \\[[0-9]+\\]"));
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
Category(m_system_category_name)->GetSummaryNavigator()->Add(ConstString("char *"), string_format);
Category(m_system_category_name)->GetSummaryNavigator()->Add(ConstString("const char *"), string_format);
Category(m_system_category_name)->GetRegexSummaryNavigator()->Add(any_size_char_arr, string_array_format);
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
Category(m_default_category_name); // this call is there to force LLDB into creating an empty "default" category
// WARNING: temporary code!!
// The platform should be responsible for initializing its own formatters
// (e.g. to handle versioning, different runtime libraries, ...)
// Currently, basic formatters for std:: objects as implemented by
// the GNU libstdc++ are defined regardless, and enabled by default
// This is going to be moved to some platform-dependent location
// (in the meanwhile, these formatters should work for Mac OS X & Linux)
lldb::SummaryFormatSP std_string_summary_sp(new StringSummaryFormat(true,
false,
false,
true,
true,
false,
"${var._M_dataplus._M_p}"));
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
Category(m_gnu_cpp_category_name)->GetSummaryNavigator()->Add(ConstString("std::string"),
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
std_string_summary_sp);
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
Category(m_gnu_cpp_category_name)->GetSummaryNavigator()->Add(ConstString("std::basic_string<char>"),
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
std_string_summary_sp);
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
Category(m_gnu_cpp_category_name)->GetSummaryNavigator()->Add(ConstString("std::basic_string<char,std::char_traits<char>,std::allocator<char> >"),
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
std_string_summary_sp);
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
Category(m_gnu_cpp_category_name)->GetRegexSyntheticNavigator()->Add(RegularExpressionSP(new RegularExpression("std::vector<")),
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
SyntheticChildrenSP(new SyntheticScriptProvider(true,
false,
false,
- Support for Python namespaces: If you have a Python module foo, in order to use its contained objects in LLDB you do not need to use 'from foo import *'. You can use 'import foo', and then refer to items in foo as 'foo.bar', and LLDB will know how to resolve bar as a member of foo. Accordingly, GNU libstdc++ formatters have been moved from the global namespace to gnu_libstdcpp and a few test cases are also updated to reflect the new convention. Python docs suggest using a plain 'import' en lieu of 'from-import'. llvm-svn: 138244
2011-08-23 01:34:47 +08:00
"gnu_libstdcpp.StdVectorSynthProvider")));
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
Category(m_gnu_cpp_category_name)->GetRegexSyntheticNavigator()->Add(RegularExpressionSP(new RegularExpression("std::map<")),
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
SyntheticChildrenSP(new SyntheticScriptProvider(true,
false,
false,
- Support for Python namespaces: If you have a Python module foo, in order to use its contained objects in LLDB you do not need to use 'from foo import *'. You can use 'import foo', and then refer to items in foo as 'foo.bar', and LLDB will know how to resolve bar as a member of foo. Accordingly, GNU libstdc++ formatters have been moved from the global namespace to gnu_libstdcpp and a few test cases are also updated to reflect the new convention. Python docs suggest using a plain 'import' en lieu of 'from-import'. llvm-svn: 138244
2011-08-23 01:34:47 +08:00
"gnu_libstdcpp.StdMapSynthProvider")));
Second round of code cleanups: - reorganizing classes layout to have public part first Typedefs that we want to keep private, but must be defined for some public code to work correctly are an exception - avoiding methods in the form T foo() { code; } all on one-line - moving method implementations from .h to .cpp whenever feasible Templatized code is an exception and so are very small methods - generally, adhering to coding conventions followed project-wide Functional changes: - fixed an issue where using ${var} in a summary for an aggregate, and then displaying a pointer-to-aggregate would lead to no summary being displayed The issue was not a major one because all ${var} was meant to do in that context was display an error for invalid use of pointer Accordingly fixed test cases and added a new test case llvm-svn: 137944
2011-08-19 00:38:26 +08:00
Category(m_gnu_cpp_category_name)->GetRegexSyntheticNavigator()->Add(RegularExpressionSP(new RegularExpression("std::list<")),
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
SyntheticChildrenSP(new SyntheticScriptProvider(true,
false,
false,
- Support for Python namespaces: If you have a Python module foo, in order to use its contained objects in LLDB you do not need to use 'from foo import *'. You can use 'import foo', and then refer to items in foo as 'foo.bar', and LLDB will know how to resolve bar as a member of foo. Accordingly, GNU libstdc++ formatters have been moved from the global namespace to gnu_libstdcpp and a few test cases are also updated to reflect the new convention. Python docs suggest using a plain 'import' en lieu of 'from-import'. llvm-svn: 138244
2011-08-23 01:34:47 +08:00
"gnu_libstdcpp.StdListSynthProvider")));
First round of code cleanups: - all instances of "vobj" have been renamed to "valobj" - class Debugger::Formatting has been renamed to DataVisualization (defined in FormatManager.h/cpp) The interface to this class has not changed - FormatCategory now uses ConstString's as keys to the navigators instead of repeatedly casting from ConstString to const char* and back all the time Next step is making the same happen for categories themselves - category gnu-libstdc++ is defined in the constructor for a FormatManager The source code for it is defined in gnu_libstdcpp.py, drawn from examples/synthetic at compile time All references to previous 'osxcpp' name have been removed from both code and file names Functional changes: - the name of the option to use a summary string for 'type summary add' has changed from the previous --format-string to the new --summary-string. It is expected that the short option will change from -f to -s, and -s for --python-script will become -o llvm-svn: 137886
2011-08-18 06:13:59 +08:00
// DO NOT change the order of these calls, unless you WANT a change in the priority of these categories
EnableCategory(m_system_category_name);
EnableCategory(m_gnu_cpp_category_name);
EnableCategory(m_default_category_name);
}