Commit Graph

98 Commits

Author SHA1 Message Date
Enrico Granata 4cc21772f3 <rdar://problem/12632394>
Add a format for FourCharCode

This is now safe to do thanks to the "formats in categories" feature

llvm-svn: 192233
2013-10-08 20:59:02 +00:00
Enrico Granata 852cc954db <rdar://problem/11778815>
Formats (as in "type format") are now included in categories
The only bit missing is caching formats along with synthetic children and summaries, which might be now desirable

llvm-svn: 192217
2013-10-08 19:03:22 +00:00
Enrico Granata 41b1653350 --raw was not always doing the right thing w.r.t. one-lining children. This checkin fixes that
llvm-svn: 192116
2013-10-07 17:59:03 +00:00
Enrico Granata 938d1d67e8 Cleaner way to work around the lack of delegating constructors on some versions of GCC
llvm-svn: 192013
2013-10-05 00:20:27 +00:00
Enrico Granata 1c127dfbbe <rdar://problem/15154623>
Several CF* data formatters were in the AppKit category
This puts them back where they belong, i.e. in category CoreFoundation

llvm-svn: 192008
2013-10-05 00:03:07 +00:00
Enrico Granata a29cb0bada <rdar://problem/12042982>
This radar extends the notion of one-liner summaries to automagically apply in a few interesting cases

More specifically, this checkin changes the printout of ValueObjects to print on one-line (as if type summary add -c had been applied) iff:
this ValueObject does not have a summary
its children have no synthetic children
its children are not a non-empty base class without a summary
its children do not have a summary that asks for children to show up
the aggregate length of all the names of all the children is <= 50 characters
you did not ask to see the types during a printout
your pointer depth is 0

This is meant to simplify the way LLDB shows data on screen for small structs and similarly compact data types (e.g. std::pair<int,int> anyone?)

Feedback is especially welcome on how the feature feels and corner cases where we should apply this printout and don't (or viceversa, we are applying it when we shouldn't be)

llvm-svn: 191996
2013-10-04 23:14:13 +00:00
Enrico Granata 245b3caa57 A more thorough fix for the newlines issue
llvm-svn: 191919
2013-10-03 18:11:24 +00:00
Enrico Granata 39938938cf <rdar://problem/15118409>
Fix an issue with the new ValueObjectPrinter where in some cases spurious \n would be printed

llvm-svn: 191869
2013-10-03 02:06:02 +00:00
Daniel Malea 73435afda7 Fix build with GCC 4.6.2 (non-c++11 compilant compiler)
- delegating c'tors not supported

llvm-svn: 191709
2013-09-30 23:12:05 +00:00
Daniel Malea dfc637b9de Fix CMake build by including ValueObjectPrinter.cpp in list of sources
llvm-svn: 191703
2013-09-30 21:30:44 +00:00
Enrico Granata 4d93b8cdf3 <rdar://problem/14393032>
DumpValueObject() 2.0

This checkin restores pre-Xcode5 functionality to the "po" (expr -O) command:
- expr now has a new --description-verbosity (-v) argument, which takes either compact or full as a value (-v is the same as -vfull)
 When the full mode is on, "po" will show the extended output with type name, persistent variable name and value, as in
(lldb) expr -O -v -- foo
(id) $0 = 0x000000010010baf0 {
    1 = 2;
    2 = 3;
}

 When -v is omitted, or -vcompact is passed, the Xcode5-style output will be shown, as in
(lldb) expr -O -- foo
{
    1 = 2;
    2 = 3;
}

- for a non-ObjectiveC object, LLDB will still try to retrieve a summary and/or value to display
(lldb) po 5
5
-v also works in this mode
(lldb) expr -O -vfull -- 5
(int) $4 = 5 

On top of that, this is a major refactoring of the ValueObject printing code. The functionality is now factored into a ValueObjectPrinter class for easier maintenance in the future
DumpValueObject() was turned into an instance method ValueObject::Dump() which simply calls through to the printer code, Dump_Impl has been removed

Test case to follow

llvm-svn: 191694
2013-09-30 19:11:51 +00:00
Joerg Sonnenberger 340a17595e Convert to UNIX line endings.
llvm-svn: 191367
2013-09-25 10:37:32 +00:00
Richard Mitton 83f0f88954 Updated CMakeLists to match XCode project
llvm-svn: 190573
2013-09-12 02:20:39 +00:00
Enrico Granata e2e220a805 <rdar://problem/14071463>
SVN r189964 provided a sample Python script to inspect unordered(multi){set|map} with synthetic children, contribued by Jared Grubb
This checkin converts that sample script to a C++ provider built into LLDB
A test case is also provided

llvm-svn: 190564
2013-09-12 00:48:47 +00:00
Virgile Bello f02a3c599b Use standard boolean operators.
llvm-svn: 189367
2013-08-27 16:24:58 +00:00
Virgile Bello b2f1fb2943 MingW compilation (windows). Includes various refactoring to improve portability.
llvm-svn: 189107
2013-08-23 12:44:05 +00:00
Michael Sartain 89c862f298 clean up about 22 warnings messages
llvm-svn: 187900
2013-08-07 19:05:15 +00:00
Enrico Granata ea9f9e8e06 Disabling the introspecting summary for __NSCFSet (essentially, for CF*SetRef)
llvm-svn: 186362
2013-07-15 23:17:32 +00:00
Greg Clayton 57ee306789 Huge change to clean up types.
A long time ago we start with clang types that were created by the symbol files and there were many functions in lldb_private::ClangASTContext that helped. Later we create ClangASTType which contains a clang::ASTContext and an opauque QualType, but we didn't switch over to fully using it. There were a lot of places where we would pass around a raw clang_type_t and also pass along a clang::ASTContext separately. This left room for error.

This checkin change all type code over to use ClangASTType everywhere and I cleaned up the interfaces quite a bit. Any code that was in ClangASTContext that was type related, was moved over into ClangASTType. All code that used these types was switched over to use all of the new goodness.

llvm-svn: 186130
2013-07-11 22:46:58 +00:00
Enrico Granata e602fe1e7f Adding a summary for ObjC blocks
llvm-svn: 186023
2013-07-10 18:25:45 +00:00
Enrico Granata c2a96407c5 Remove the #define USE_CACHE since the formatters cache has been operational for a while now and has not caused issues that warrant disabling it
Also, print the cache hits statistics if the log is in debugging mode vs. LLDB being a debug build - this should make it easier to gather useful metrics on cache success rate for real users

llvm-svn: 184900
2013-06-26 01:03:38 +00:00
Enrico Granata c71f349a9e <rdar://problem/14005652>
Fixing a bug with the NSString data formatter where some strings would be truncated

llvm-svn: 184336
2013-06-19 19:15:29 +00:00
Andy Gibbs a297a97e09 Sort out a number of mismatched integer types in order to cut down the number of compiler warnings.
llvm-svn: 184333
2013-06-19 19:04:53 +00:00
Enrico Granata 68ae4117d9 <rdar://problem/12717717>
Modifying our data formatters matching algorithm to ensure that "const X*" is treated as equivalent to "X*"
Also, a couple improvements to the "lldb types" logging

llvm-svn: 184215
2013-06-18 18:23:07 +00:00
Enrico Granata 6f63001879 Removing a redundant write
llvm-svn: 183814
2013-06-12 00:32:31 +00:00
Greg Clayton 3fb543b06d Remove eFormatHalfFloat as it isn't needed. eFormatFloat should be used and the byte size will tell us how to display it.
llvm-svn: 183755
2013-06-11 17:32:06 +00:00
Enrico Granata 97fe23e00a <rdar://problem/12783351>
Add support for half-floats, as specified by IEEE-754-2008
With this checkin, you can now say:
(lldb) x/7hf foo

to read 7 half-floats at address foo

llvm-svn: 183716
2013-06-11 00:18:18 +00:00
Enrico Granata 4c648b1884 <rdar://problem/14101771>
Hardening the CFBitVector data formatter against failed reads

llvm-svn: 183706
2013-06-10 22:26:15 +00:00
Enrico Granata b26fdada54 <rdar://problem/13125225>
Adding data formatters for std::set, std::multiset and std::multimap for libc++
The underlying data structure is the same as std::map, so this change is very minimal and mostly consists of test cases

llvm-svn: 183323
2013-06-05 17:47:23 +00:00
Enrico Granata 983920d1a9 <rdar://problem/14003462>
Formatters for unsigned char* and const variant

llvm-svn: 183254
2013-06-04 21:53:55 +00:00
Matt Kopec ef14371d3f Fix various build warnings.
llvm-svn: 183140
2013-06-03 18:00:07 +00:00
Enrico Granata 1c333d071f An NSData with 0 bytes in it would report a summary of “0 byte”
Making sure that I get my English right by saying “0 bytes” instead

llvm-svn: 182978
2013-05-31 01:14:22 +00:00
Michael Sartain c3ce7f2740 Add ${ansi.XX} parsing to lldb prompt, use-color setting, and -no-use-colors command line options.
settings set use-color [false|true]
settings set prompt "${ansi.bold}${ansi.fg.green}(lldb)${ansi.normal} "
also "--no-use-colors" on the command prompt

llvm-svn: 182609
2013-05-23 20:47:45 +00:00
Enrico Granata 5a9c4fe272 <rdar://problem/13928053>
Fix the fact that an empty NSString (e.g. one obtained from @"" would show no summary)

llvm-svn: 182173
2013-05-17 23:28:13 +00:00
Jim Ingham 5c42d8a87c Fixed a few obvious errors pointed out by the static analyzer.
llvm-svn: 181911
2013-05-15 18:27:08 +00:00
Enrico Granata a3962a77cd <rdar://problem/13821289>
Changes to the libc++ std::string data formatter

llvm-svn: 181855
2013-05-15 00:47:46 +00:00
Enrico Granata 14b74fd153 <rdar://problem/11669154>
Make a summary format for libc++ STL containers that shows the number of items as before, but also shows the pointer value for pointer-to-container

llvm-svn: 181236
2013-05-06 18:55:52 +00:00
Enrico Granata 4ffff2791f Harden against potential empty nodes in the map
llvm-svn: 181045
2013-05-03 19:07:20 +00:00
Enrico Granata d03a273b96 <rdar://problem/13749871>
Improvements to the std::map data formatter to recognize when invalid memory is being explored and bail out instead of looping for a potentially very long time

llvm-svn: 181044
2013-05-03 19:04:35 +00:00
Enrico Granata cd67f97cb7 <rdar://problem/12529989>
Synthetic children provider for NSOrderedSet

llvm-svn: 180655
2013-04-27 00:27:20 +00:00
Enrico Granata c76b97bcce Make a synthetic children provider for the ObjC Class type
llvm-svn: 180588
2013-04-26 00:59:02 +00:00
Enrico Granata 3f8e40ce7a See: http://stackoverflow.com/questions/16166897/c-how-to-obtain-address-of-stdvector-object-in-lldb-xcode
The user was trying to obtain the address-of an std::vector and the experience was more painful than necessary because data formatters were kicking in for vector* objects
We got this right for libc++ - we should get it right for libstdc++ too

llvm-svn: 180219
2013-04-24 21:52:24 +00:00
Enrico Granata b636be79c0 Changes to the ObjC runtime
llvm-svn: 180199
2013-04-24 17:49:08 +00:00
Enrico Granata 66e0abb3bc Closing parentheses is good - doing it while respecting printf format specifiers is even better
llvm-svn: 180156
2013-04-23 22:38:25 +00:00
Enrico Granata c03c586d14 char32_t should use an uppercase U as its prefix
llvm-svn: 180148
2013-04-23 21:37:33 +00:00
Enrico Granata 906f2cbc65 Closing parentheses once they are open is a good idea
llvm-svn: 180142
2013-04-23 20:09:10 +00:00
Enrico Granata 5676839246 The new ReadStringFromMemory() API does not work correctly with NSStrings that have an explicit length and no NULL terminator
This checkin reverts NSString to the old behavior when appropriate, and cleans up the syntax to call the UTF Reader&Dumper function
Incidentally, add a "-d" command-line flag to redo.py with the same semantics as "-d" in dotest.py

llvm-svn: 180141
2013-04-23 20:05:05 +00:00
Enrico Granata 723e129aa2 <rdar://problem/13437949>
Making sure that CF*{Array|Dictionary}Ref provide synthetic children correctly.

llvm-svn: 180074
2013-04-23 01:13:50 +00:00
Enrico Granata dea46d7c38 Much better way to get at the size of an std::list
llvm-svn: 180071
2013-04-22 23:36:35 +00:00
Greg Clayton 03da4cc294 Fixed some linux buildbot warnings.
llvm-svn: 179892
2013-04-19 21:31:16 +00:00