[cfe-dev] segfault in lexing

[harsh gupta]

I am using the lexer to get a stream of tokens for a file. However if there is a nested block comment,
 for eg /* some comment /*This is a nested comment*/ some more comment */ 
Then the lexer gives a segmentation fault. Is there any way to avoid this segmentation fault?

The code that i am using is:    clang::DiagnosticOptions diagnosticOptions;    clang::TextDiagnosticPrinter *pTextDiagnosticPrinter = new clang::TextDiagnosticPrinter( llvm::outs(), diagnosticOptions);    llvm::IntrusiveRefCntPtr<clang::DiagnosticIDs> pDiagIDs;    clang::Diagnostic diagnostic(pDiagIDs,pTextDiagnosticPrinter);
    clang::LangOptions languageOptions;    clang::FileSystemOptions fileSystemOptions;    clang::FileManager fileManager(fileSystemOptions);

    clang::SourceManager sourceManager( diagnostic, fileManager);    clang::HeaderSearch headerSearch(fileManager);
    clang::TargetOptions targetOptions;    targetOptions.Triple = llvm::sys::getHostTriple();
    clang::TargetInfo *pTargetInfo =     clang::TargetInfo::CreateTargetInfo( diagnostic, targetOptions);
    clang::Preprocessor preprocessor( diagnostic, languageOptions, *pTargetInfo, sourceManager, headerSearch);
    const clang::FileEntry *pFile = fileManager.getFile( _outFilename);    sourceManager.createMainFileID(pFile);    preprocessor.EnterMainSourceFile();
    std::vector<GeneralCommand> cmdvect;    GeneralCommand cmd;    clang::Token token;    do {            preprocessor.Lex(token);            if( diagnostic.hasErrorOccurred())            {                break;            }
   } while(token.isNot(clang::tok::eof));


And the backtrace is:
Program received signal SIGSEGV, Segmentation fault.0x00000000004708fc in clang::LangOptions::LangOptions (this=0x7fffffffbc38) at /home/harsh/Desktop/llvm/tools/clang/lib/Sema/../../include/clang/Basic/LangOptions.h:2424	class LangOptions {(gdb) bt#0  0x00000000004708fc in clang::LangOptions::LangOptions (this=0x7fffffffbc38) at /home/harsh/Desktop/llvm/tools/clang/lib/Sema/../../include/clang/Basic/LangOptions.h:24#1  0x00000000007502c2 in clang::Lexer::Lexer (this=0x7fffffffbbb0, fileloc=..., features=...,     BufStart=0x12a32cc8 "\n//#include <sys/wait.h>\n\n\n//#include <stdio.h>\n//#include <stdlib.h>\n//#include <errno.h>\n//#include <string.h>\n//#include <fcntl.h>\n//#include <sys/types.h>\n//#include <sys/stat.h>\n//#include <unist"...,     BufPtr=0x12a338c4 "/*printf(\"God mode wasted \\n\")*/;\n/*\n\tswitch (gbuf[0]) \n\t\t{\n\t\t\tcase('h') :\n\t\t\t\tread(0,gbuf,6);\n\t\t\t\twrite(harpipe[1],gbuf,6);\n\t\t\tcase('t') :\n\t\t\t\tread(0,gbuf,6);\n\t\t\t\twrite(turpipe[1],gbuf,6);\n\t\t\tdefault"..., BufEnd=0x12a3411a "") at Lexer.cpp:117#2  0x0000000000750ae8 in clang::Lexer::MeasureTokenLength (Loc=..., SM=..., LangOpts=...) at Lexer.cpp:349#3  0x0000000000744116 in clang::TextDiagnosticPrinter::EmitCaretDiagnostic (this=0x12a0ab30, Loc=..., Ranges=0x7fffffffc010, NumRanges=0, SM=..., Hints=0x0, NumHints=0, Columns=0, OnMacroInst=0,     MacroSkipStart=0, MacroSkipEnd=0) at TextDiagnosticPrinter.cpp:382#4  0x0000000000746a4d in clang::TextDiagnosticPrinter::HandleDiagnostic (this=0x12a0ab30, Level=clang::Diagnostic::Warning, Info=...) at TextDiagnosticPrinter.cpp:1041#5  0x0000000000921c04 in clang::DiagnosticIDs::ProcessDiag (this=0x0, Diag=...) at DiagnosticIDs.cpp:582#6  0x000000000091cc03 in clang::Diagnostic::ProcessDiag (this=0x7fffffffd410) at /home/harsh/Desktop/llvm/tools/clang/lib/Basic/../../include/clang/Basic/Diagnostic.h:608#7  0x000000000091b4a2 in clang::DiagnosticBuilder::Emit (this=0x7fffffffc460) at Diagnostic.cpp:225#8  0x0000000000421ee2 in clang::DiagnosticBuilder::~DiagnosticBuilder (this=0x7fffffffc460, __in_chrg=<value optimized out>)    at /home/harsh/Desktop/llvm/tools/clang/lib/Sema/../../include/clang/Basic/Diagnostic.h:696#9  0x000000000075369d in clang::Lexer::SkipBlockComment (this=0x129db190, Result=...,     CurPtr=0x12a338c5 "*printf(\"God mode wasted \\n\")*/;\n/*\n\tswitch (gbuf[0]) \n\t\t{\n\t\t\tcase('h') :\n\t\t\t\tread(0,gbuf,6);\n\t\t\t\twrite(harpipe[1],gbuf,6);\n\t\t\tcase('t') :\n\t\t\t\tread(0,gbuf,6);\n\t\t\t\twrite(turpipe[1],gbuf,6);\n\t\t\tdefault "...) at Lexer.cpp:1629#10 0x0000000000754fd8 in clang::Lexer::LexTokenInternal (this=0x129db190, Result=...) at Lexer.cpp:2248#11 0x00000000007101e8 in clang::Lexer::Lex (this=0x129db190, Result=...) at /home/harsh/Desktop/llvm/tools/clang/lib/Frontend/../../include/clang/Lex/Lexer.h:131#12 0x00000000007102d5 in clang::Preprocessor::Lex (this=0x7fffffffc650, Result=...) at /home/harsh/Desktop/llvm/tools/clang/lib/Frontend/../../include/clang/Lex/Preprocessor.h:507#13 0x00000000007c2c84 in MyRewriter::getLexerTokens (this=0x7fffffffd750) at MyRewriter.cpp:304#14 0x00000000007c2847 in MyRewriter::getParseTrees (this=0x7fffffffd750) at MyRewriter.cpp:263#15 0x00000000007bdf26 in GeneralCandidate::parse (this=0xff09160) at GeneralCandidate.cpp:15#16 0x00000000007e3a10 in main () at CPPMain.cpp:1111
Harsh Gupta


 		 	   		  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/cfe-dev/attachments/20110704/68126f3f/attachment.html>