summaryrefslogtreecommitdiff
path: root/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/llvm/tools/clang/lib/Lex/Lexer.cpp')
-rw-r--r--contrib/llvm/tools/clang/lib/Lex/Lexer.cpp75
1 files changed, 40 insertions, 35 deletions
diff --git a/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp b/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
index 5212dd86e7a1..a5ba7dbe0a93 100644
--- a/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
+++ b/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
@@ -513,10 +513,13 @@ Lexer::ComputePreamble(const llvm::MemoryBuffer *Buffer,
// "fake" file source location at offset 1 so that the lexer will track our
// position within the file.
const unsigned StartOffset = 1;
- SourceLocation StartLoc = SourceLocation::getFromRawEncoding(StartOffset);
- Lexer TheLexer(StartLoc, LangOpts, Buffer->getBufferStart(),
+ SourceLocation FileLoc = SourceLocation::getFromRawEncoding(StartOffset);
+ Lexer TheLexer(FileLoc, LangOpts, Buffer->getBufferStart(),
Buffer->getBufferStart(), Buffer->getBufferEnd());
-
+
+ // StartLoc will differ from FileLoc if there is a BOM that was skipped.
+ SourceLocation StartLoc = TheLexer.getSourceLocation();
+
bool InPreprocessorDirective = false;
Token TheTok;
Token IfStartTok;
@@ -1534,7 +1537,7 @@ FinishIdentifier:
/// isHexaLiteral - Return true if Start points to a hex constant.
/// in microsoft mode (where this is supposed to be several different tokens).
-static bool isHexaLiteral(const char *Start, const LangOptions &LangOpts) {
+bool Lexer::isHexaLiteral(const char *Start, const LangOptions &LangOpts) {
unsigned Size;
char C1 = Lexer::getCharAndSizeNoWarn(Start, Size, LangOpts);
if (C1 != '0')
@@ -1813,17 +1816,18 @@ void Lexer::LexCharConstant(Token &Result, const char *CurPtr,
while (C != '\'') {
// Skip escaped characters.
- if (C == '\\') {
- // Skip the escaped character.
- // FIXME: UCN's
- getAndAdvanceChar(CurPtr, Result);
- } else if (C == '\n' || C == '\r' || // Newline.
- (C == 0 && CurPtr-1 == BufferEnd)) { // End of file.
+ if (C == '\\')
+ C = getAndAdvanceChar(CurPtr, Result);
+
+ if (C == '\n' || C == '\r' || // Newline.
+ (C == 0 && CurPtr-1 == BufferEnd)) { // End of file.
if (!isLexingRawMode() && !LangOpts.AsmPreprocessor)
Diag(BufferPtr, diag::ext_unterminated_char);
FormTokenWithChars(Result, CurPtr-1, tok::unknown);
return;
- } else if (C == 0) {
+ }
+
+ if (C == 0) {
if (isCodeCompletionPoint(CurPtr-1)) {
PP->CodeCompleteNaturalLanguage();
FormTokenWithChars(Result, CurPtr-1, tok::unknown);
@@ -1895,21 +1899,21 @@ bool Lexer::SkipWhitespace(Token &Result, const char *CurPtr) {
return false;
}
-// SkipBCPLComment - We have just read the // characters from input. Skip until
-// we find the newline character thats terminate the comment. Then update
-/// BufferPtr and return.
+/// We have just read the // characters from input. Skip until we find the
+/// newline character thats terminate the comment. Then update BufferPtr and
+/// return.
///
/// If we're in KeepCommentMode or any CommentHandler has inserted
/// some tokens, this will store the first token and return true.
-bool Lexer::SkipBCPLComment(Token &Result, const char *CurPtr) {
- // If BCPL comments aren't explicitly enabled for this language, emit an
+bool Lexer::SkipLineComment(Token &Result, const char *CurPtr) {
+ // If Line comments aren't explicitly enabled for this language, emit an
// extension warning.
- if (!LangOpts.BCPLComment && !isLexingRawMode()) {
- Diag(BufferPtr, diag::ext_bcpl_comment);
+ if (!LangOpts.LineComment && !isLexingRawMode()) {
+ Diag(BufferPtr, diag::ext_line_comment);
// Mark them enabled so we only emit one warning for this translation
// unit.
- LangOpts.BCPLComment = true;
+ LangOpts.LineComment = true;
}
// Scan over the body of the comment. The common case, when scanning, is that
@@ -1973,7 +1977,7 @@ bool Lexer::SkipBCPLComment(Token &Result, const char *CurPtr) {
}
if (!isLexingRawMode())
- Diag(OldPtr-1, diag::ext_multi_line_bcpl_comment);
+ Diag(OldPtr-1, diag::ext_multi_line_line_comment);
break;
}
}
@@ -2002,7 +2006,7 @@ bool Lexer::SkipBCPLComment(Token &Result, const char *CurPtr) {
// If we are returning comments as tokens, return this comment as a token.
if (inKeepCommentMode())
- return SaveBCPLComment(Result, CurPtr);
+ return SaveLineComment(Result, CurPtr);
// If we are inside a preprocessor directive and we see the end of line,
// return immediately, so that the lexer can return this as an EOD token.
@@ -2026,9 +2030,9 @@ bool Lexer::SkipBCPLComment(Token &Result, const char *CurPtr) {
return false;
}
-/// SaveBCPLComment - If in save-comment mode, package up this BCPL comment in
-/// an appropriate way and return it.
-bool Lexer::SaveBCPLComment(Token &Result, const char *CurPtr) {
+/// If in save-comment mode, package up this Line comment in an appropriate
+/// way and return it.
+bool Lexer::SaveLineComment(Token &Result, const char *CurPtr) {
// If we're not in a preprocessor directive, just return the // comment
// directly.
FormTokenWithChars(Result, CurPtr, tok::comment);
@@ -2036,19 +2040,19 @@ bool Lexer::SaveBCPLComment(Token &Result, const char *CurPtr) {
if (!ParsingPreprocessorDirective || LexingRawMode)
return true;
- // If this BCPL-style comment is in a macro definition, transmogrify it into
+ // If this Line-style comment is in a macro definition, transmogrify it into
// a C-style block comment.
bool Invalid = false;
std::string Spelling = PP->getSpelling(Result, &Invalid);
if (Invalid)
return true;
- assert(Spelling[0] == '/' && Spelling[1] == '/' && "Not bcpl comment?");
+ assert(Spelling[0] == '/' && Spelling[1] == '/' && "Not line comment?");
Spelling[1] = '*'; // Change prefix to "/*".
Spelling += "*/"; // add suffix.
Result.setKind(tok::comment);
- PP->CreateString(&Spelling[0], Spelling.size(), Result,
+ PP->CreateString(Spelling, Result,
Result.getLocation(), Result.getLocation());
return true;
}
@@ -2179,7 +2183,8 @@ bool Lexer::SkipBlockComment(Token &Result, const char *CurPtr) {
#ifdef __SSE2__
__m128i Slashes = _mm_set1_epi8('/');
while (CurPtr+16 <= BufferEnd) {
- int cmp = _mm_movemask_epi8(_mm_cmpeq_epi8(*(__m128i*)CurPtr, Slashes));
+ int cmp = _mm_movemask_epi8(_mm_cmpeq_epi8(*(const __m128i*)CurPtr,
+ Slashes));
if (cmp != 0) {
// Adjust the pointer to point directly after the first slash. It's
// not necessary to set C here, it will be overwritten at the end of
@@ -2669,8 +2674,8 @@ LexNextToken:
// If the next token is obviously a // or /* */ comment, skip it efficiently
// too (without going through the big switch stmt).
if (CurPtr[0] == '/' && CurPtr[1] == '/' && !inKeepCommentMode() &&
- LangOpts.BCPLComment && !LangOpts.TraditionalCPP) {
- if (SkipBCPLComment(Result, CurPtr+2))
+ LangOpts.LineComment && !LangOpts.TraditionalCPP) {
+ if (SkipLineComment(Result, CurPtr+2))
return; // There is a token to return.
goto SkipIgnoredUnits;
} else if (CurPtr[0] == '/' && CurPtr[1] == '*' && !inKeepCommentMode()) {
@@ -2955,19 +2960,19 @@ LexNextToken:
case '/':
// 6.4.9: Comments
Char = getCharAndSize(CurPtr, SizeTmp);
- if (Char == '/') { // BCPL comment.
- // Even if BCPL comments are disabled (e.g. in C89 mode), we generally
+ if (Char == '/') { // Line comment.
+ // Even if Line comments are disabled (e.g. in C89 mode), we generally
// want to lex this as a comment. There is one problem with this though,
// that in one particular corner case, this can change the behavior of the
// resultant program. For example, In "foo //**/ bar", C89 would lex
- // this as "foo / bar" and langauges with BCPL comments would lex it as
+ // this as "foo / bar" and langauges with Line comments would lex it as
// "foo". Check to see if the character after the second slash is a '*'.
// If so, we will lex that as a "/" instead of the start of a comment.
// However, we never do this in -traditional-cpp mode.
- if ((LangOpts.BCPLComment ||
+ if ((LangOpts.LineComment ||
getCharAndSize(CurPtr+SizeTmp, SizeTmp2) != '*') &&
!LangOpts.TraditionalCPP) {
- if (SkipBCPLComment(Result, ConsumeChar(CurPtr, SizeTmp, Result)))
+ if (SkipLineComment(Result, ConsumeChar(CurPtr, SizeTmp, Result)))
return; // There is a token to return.
// It is common for the tokens immediately after a // comment to be
generated by cgit v1.2.3 (git 2.25.1) at 2025-11-04 14:50:29 +0000