idlecode updated this revision to Diff 102110.
idlecode added a comment.
Added tests for `isNewLineEscaped` - this fixed some corner cases
https://reviews.llvm.org/D30748
Files:
lib/Lex/Lexer.cpp
unittests/Lex/LexerTest.cpp
Index: unittests/Lex/LexerTest.cpp
===================================================================
--- unittests/Lex/LexerTest.cpp
+++ unittests/Lex/LexerTest.cpp
@@ -25,6 +25,8 @@
using namespace clang;
+bool isNewLineEscaped(const char *BufferStart, const char *Str);
+
namespace {
// The test fixture.
@@ -365,4 +367,53 @@
EXPECT_EQ(SourceMgr.getFileIDSize(SourceMgr.getFileID(helper1ArgLoc)), 8U);
}
+TEST_F(LexerTest, IsNewLineEscapedValid) {
+ std::vector<std::pair<bool, std::string>> TestLines = {
+ {true, "\\\r"}, {true, "\\\n"}, {true, "\\\r\n"},
+ {true, "\\\n\r"}, {true, "\\ \t\v\f\r"}, {true, "\\ \t\v\f\r\n"},
+ {false, "\\\r\r"}, {false, "\\\r\r\n"}, {false, "\\\n\n"},
+ {false, "\r"}, {false, "\n"}, {false, "\r\n"},
+ {false, "\n\r"}, {false, "\r\r"}, {false, "\n\n"}};
+
+ int i = 1;
+ for (const std::pair<bool, std::string> &Pattern : TestLines) {
+ bool IsEscaped = Pattern.first;
+ const std::string &Line = Pattern.second;
+ EXPECT_EQ(IsEscaped,
+ isNewLineEscaped(Line.c_str(), Line.c_str() + Line.length() - 1))
+ << "Pattern #" << i << " not recognized as escaped new line\n";
+ ++i;
+ }
+}
+
+TEST_F(LexerTest, GetBeginningOfTokenWithEscapedNewLine) {
+ // Each line should have the same length for
+ // further offset calculation to be more straightforward.
+ const unsigned IdentifierLength = 8;
+ std::string TextToLex = "rabarbar\n"
+ "foo\\\nbar\n"
+ "foo\\\rbar\n"
+ "fo\\\r\nbar\n"
+ "foo\\\n\rba\n";
+ std::vector<tok::TokenKind> ExpectedTokens{5, tok::identifier};
+ std::vector<Token> LexedTokens = CheckLex(TextToLex, ExpectedTokens);
+
+ for (const Token &Tok : LexedTokens) {
+ std::pair<FileID, unsigned> OriginalLocation =
+ SourceMgr.getDecomposedLoc(Tok.getLocation());
+ for (unsigned Offset = 0; Offset < IdentifierLength; ++Offset) {
+ SourceLocation LookupLocation =
+ Tok.getLocation().getLocWithOffset(Offset);
+
+ std::pair<FileID, unsigned> FoundLocation =
+ SourceMgr.getDecomposedExpansionLoc(
+ Lexer::GetBeginningOfToken(LookupLocation, SourceMgr, LangOpts));
+
+ // Check that location returned by the GetBeginningOfToken
+ // is the same as original token location reported by Lexer.
+ EXPECT_EQ(FoundLocation.second, OriginalLocation.second);
+ }
+ }
+}
+
} // anonymous namespace
Index: lib/Lex/Lexer.cpp
===================================================================
--- lib/Lex/Lexer.cpp
+++ lib/Lex/Lexer.cpp
@@ -456,25 +456,45 @@
return false;
}
+/// \brief Check if new line pointed by Str is escaped.
+bool isNewLineEscaped(const char *BufferStart, const char *Str) {
+ assert(isVerticalWhitespace(Str[0]));
+ if (Str - 1 < BufferStart)
+ return false;
+
+ if ((Str[0] == '\n' && Str[-1] == '\r') ||
+ (Str[0] == '\r' && Str[-1] == '\n')) {
+ if (Str - 2 < BufferStart)
+ return false;
+ --Str;
+ }
+ --Str;
+
+ // Rewind to first non-space character:
+ while (isHorizontalWhitespace(*Str) && Str > BufferStart)
+ --Str;
+
+ return *Str == '\\';
+}
+
/// Returns the pointer that points to the beginning of line that contains
/// the given offset, or null if the offset if invalid.
static const char *findBeginningOfLine(StringRef Buffer, unsigned Offset) {
const char *BufStart = Buffer.data();
if (Offset >= Buffer.size())
return nullptr;
- const char *StrData = BufStart + Offset;
- if (StrData[0] == '\n' || StrData[0] == '\r')
- return StrData;
+ const char *LexStart = BufStart + Offset;
+ for (; LexStart != BufStart; --LexStart) {
+ if (!isVerticalWhitespace(LexStart[0]))
+ continue;
- const char *LexStart = StrData;
- while (LexStart != BufStart) {
- if (LexStart[0] == '\n' || LexStart[0] == '\r') {
- ++LexStart;
- break;
- }
+ if (isNewLineEscaped(BufStart, LexStart))
+ continue;
- --LexStart;
+ // LexStart should point at first character of logical line.
+ ++LexStart;
+ break;
}
return LexStart;
}
@@ -486,7 +506,7 @@
std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(Loc);
if (LocInfo.first.isInvalid())
return Loc;
-
+
bool Invalid = false;
StringRef Buffer = SM.getBufferData(LocInfo.first, &Invalid);
if (Invalid)
@@ -498,52 +518,52 @@
const char *LexStart = findBeginningOfLine(Buffer, LocInfo.second);
if (!LexStart || LexStart == StrData)
return Loc;
-
+
// Create a lexer starting at the beginning of this token.
SourceLocation LexerStartLoc = Loc.getLocWithOffset(-LocInfo.second);
Lexer TheLexer(LexerStartLoc, LangOpts, Buffer.data(), LexStart,
Buffer.end());
TheLexer.SetCommentRetentionState(true);
-
+
// Lex tokens until we find the token that contains the source location.
Token TheTok;
do {
TheLexer.LexFromRawLexer(TheTok);
-
+
if (TheLexer.getBufferLocation() > StrData) {
// Lexing this token has taken the lexer past the source location we're
// looking for. If the current token encompasses our source location,
// return the beginning of that token.
if (TheLexer.getBufferLocation() - TheTok.getLength() <= StrData)
return TheTok.getLocation();
-
+
// We ended up skipping over the source location entirely, which means
// that it points into whitespace. We're done here.
break;
}
} while (TheTok.getKind() != tok::eof);
-
+
// We've passed our source location; just return the original source location.
return Loc;
}
SourceLocation Lexer::GetBeginningOfToken(SourceLocation Loc,
const SourceManager &SM,
const LangOptions &LangOpts) {
- if (Loc.isFileID())
- return getBeginningOfFileToken(Loc, SM, LangOpts);
-
- if (!SM.isMacroArgExpansion(Loc))
- return Loc;
-
- SourceLocation FileLoc = SM.getSpellingLoc(Loc);
- SourceLocation BeginFileLoc = getBeginningOfFileToken(FileLoc, SM, LangOpts);
- std::pair<FileID, unsigned> FileLocInfo = SM.getDecomposedLoc(FileLoc);
- std::pair<FileID, unsigned> BeginFileLocInfo
- = SM.getDecomposedLoc(BeginFileLoc);
- assert(FileLocInfo.first == BeginFileLocInfo.first &&
- FileLocInfo.second >= BeginFileLocInfo.second);
- return Loc.getLocWithOffset(BeginFileLocInfo.second - FileLocInfo.second);
+ if (Loc.isFileID())
+ return getBeginningOfFileToken(Loc, SM, LangOpts);
+
+ if (!SM.isMacroArgExpansion(Loc))
+ return Loc;
+
+ SourceLocation FileLoc = SM.getSpellingLoc(Loc);
+ SourceLocation BeginFileLoc = getBeginningOfFileToken(FileLoc, SM, LangOpts);
+ std::pair<FileID, unsigned> FileLocInfo = SM.getDecomposedLoc(FileLoc);
+ std::pair<FileID, unsigned> BeginFileLocInfo
+ = SM.getDecomposedLoc(BeginFileLoc);
+ assert(FileLocInfo.first == BeginFileLocInfo.first &&
+ FileLocInfo.second >= BeginFileLocInfo.second);
+ return Loc.getLocWithOffset(BeginFileLocInfo.second - FileLocInfo.second);
}
namespace {
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
