diff options
author | Daniel Dunbar <daniel@zuster.org> | 2009-08-14 18:19:52 +0000 |
---|---|---|
committer | Daniel Dunbar <daniel@zuster.org> | 2009-08-14 18:19:52 +0000 |
commit | 2f91e8630d3a5de82e56c643072bb220c76b0c65 (patch) | |
tree | 432a54c2dcebf6c297ef06b65e212f4e27a49675 /tools/llvm-mc | |
parent | 5e9f7e858be074a667a3cf0d8c4ebccdb124d56f (diff) | |
download | external_llvm-2f91e8630d3a5de82e56c643072bb220c76b0c65.zip external_llvm-2f91e8630d3a5de82e56c643072bb220c76b0c65.tar.gz external_llvm-2f91e8630d3a5de82e56c643072bb220c76b0c65.tar.bz2 |
llvm-mc: Support escaped characters in string literals (for .ascii and .asciz)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79010 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'tools/llvm-mc')
-rw-r--r-- | tools/llvm-mc/AsmParser.cpp | 68 | ||||
-rw-r--r-- | tools/llvm-mc/AsmParser.h | 4 |
2 files changed, 67 insertions, 5 deletions
diff --git a/tools/llvm-mc/AsmParser.cpp b/tools/llvm-mc/AsmParser.cpp index eec4cc8..c37abfd 100644 --- a/tools/llvm-mc/AsmParser.cpp +++ b/tools/llvm-mc/AsmParser.cpp @@ -765,6 +765,64 @@ bool AsmParser::ParseDirectiveSectionSwitch(const char *Segment, return false; } +bool AsmParser::ParseEscapedString(std::string &Data) { + assert(Lexer.is(AsmToken::String) && "Unexpected current token!"); + + Data = ""; + StringRef Str = Lexer.getTok().getStringContents(); + for (unsigned i = 0, e = Str.size(); i != e; ++i) { + if (Str[i] != '\\') { + Data += Str[i]; + continue; + } + + // Recognize escaped characters. Note that this escape semantics currently + // loosely follows Darwin 'as'. Notably, it doesn't support hex escapes. + ++i; + if (i == e) + return TokError("unexpected backslash at end of string"); + + // Recognize octal sequences. + if ((unsigned) (Str[i] - '0') <= 7) { + // Consume up to three octal characters. + unsigned Value = Str[i] - '0'; + + if (i + 1 != e && ((unsigned) (Str[i + 1] - '0')) <= 7) { + ++i; + Value = Value * 8 + (Str[i] - '0'); + + if (i + 1 != e && ((unsigned) (Str[i + 1] - '0')) <= 7) { + ++i; + Value = Value * 8 + (Str[i] - '0'); + } + } + + if (Value > 255) + return TokError("invalid octal escape sequence (out of range)"); + + Data += (unsigned char) Value; + continue; + } + + // Otherwise recognize individual escapes. + switch (Str[i]) { + default: + // Just reject invalid escape sequences for now. + return TokError("invalid escape sequence (unrecognized character)"); + + case 'b': Data += '\b'; break; + case 'f': Data += '\f'; break; + case 'n': Data += '\n'; break; + case 'r': Data += '\r'; break; + case 't': Data += '\t'; break; + case '"': Data += '"'; break; + case '\\': Data += '\\'; break; + } + } + + return false; +} + /// ParseDirectiveAscii: /// ::= ( .ascii | .asciz ) [ "string" ( , "string" )* ] bool AsmParser::ParseDirectiveAscii(bool ZeroTerminated) { @@ -773,11 +831,11 @@ bool AsmParser::ParseDirectiveAscii(bool ZeroTerminated) { if (Lexer.isNot(AsmToken::String)) return TokError("expected string in '.ascii' or '.asciz' directive"); - // FIXME: This shouldn't use a const char* + strlen, the string could have - // embedded nulls. - // FIXME: Should have accessor for getting string contents. - StringRef Str = Lexer.getTok().getString(); - Out.EmitBytes(Str.substr(1, Str.size() - 2)); + std::string Data; + if (ParseEscapedString(Data)) + return true; + + Out.EmitBytes(Data); if (ZeroTerminated) Out.EmitBytes(StringRef("\0", 1)); diff --git a/tools/llvm-mc/AsmParser.h b/tools/llvm-mc/AsmParser.h index 55efa84..a19f35f 100644 --- a/tools/llvm-mc/AsmParser.h +++ b/tools/llvm-mc/AsmParser.h @@ -135,6 +135,10 @@ private: bool ParseDirectiveFile(SMLoc DirectiveLoc); // ".file" bool ParseDirectiveLine(SMLoc DirectiveLoc); // ".line" bool ParseDirectiveLoc(SMLoc DirectiveLoc); // ".loc" + + /// ParseEscapedString - Parse the current token as a string which may include + /// escaped characters and return the string contents. + bool ParseEscapedString(std::string &Data); }; } // end namespace llvm |