/// LookUpIdentifierInfo - Given a tok::raw_identifier token, look up the
/// identifier information for the token and install it into the token,
/// updating the token kind accordingly.
IdentifierInfo *Preprocessor::LookUpIdentifierInfo(Token &Identifier) const {
assert(!Identifier.getRawIdentifier().empty() && "No raw identifier data!");
// Look up this token, see if it is a macro, or if it is a language keyword.
IdentifierInfo *II;
if (!Identifier.needsCleaning() && !Identifier.hasUCN()) {
// No cleaning needed, just use the characters from the lexed buffer.
II = getIdentifierInfo(Identifier.getRawIdentifier());
} else {
// Cleaning needed, alloca a buffer, clean into it, then use the buffer.
SmallString<64> IdentifierBuffer;
StringRef CleanedStr = getSpelling(Identifier, IdentifierBuffer);
if (Identifier.hasUCN()) {
SmallString<64> UCNIdentifierBuffer;
expandUCNs(UCNIdentifierBuffer, CleanedStr);
II = getIdentifierInfo(UCNIdentifierBuffer);
} else {
II = getIdentifierInfo(CleanedStr);
}
}
// Update the token info (identifier info and appropriate token kind).
Identifier.setIdentifierInfo(II);
Identifier.setKind(II->getTokenID());
return II;
}
void Parser::ClassifyToken(Token &T) {
if (T.isNot(tok::identifier))
return;
// Set the identifier info for this token.
llvm::SmallVector<llvm::StringRef, 2> Spelling;
TheLexer.getSpelling(T, Spelling);
std::string NameStr = Tok.CleanLiteral(Spelling);
// We assume that the "common case" is that if an identifier is also a
// keyword, it will most likely be used as a keyword. I.e., most programs are
// sane, and won't use keywords for variable names. We mark it as a keyword
// for ease in parsing. But it's weak and can change into an identifier or
// builtin depending upon the context.
if (IdentifierInfo *KW = Identifiers.lookupKeyword(NameStr)) {
T.setIdentifierInfo(KW);
T.setKind(KW->getTokenID());
} else if (IdentifierInfo *BI = Identifiers.lookupBuiltin(NameStr)) {
T.setIdentifierInfo(BI);
T.setKind(BI->getTokenID());
} else {
IdentifierInfo *II = getIdentifierInfo(NameStr);
T.setIdentifierInfo(II);
T.setKind(II->getTokenID());
}
}
/// LookUpIdentifierInfo - Given a tok::raw_identifier token, look up the
/// identifier information for the token and install it into the token,
/// updating the token kind accordingly.
IdentifierInfo *Preprocessor::LookUpIdentifierInfo(Token &Identifier) const {
assert(!Identifier.getRawIdentifier().empty() && "No raw identifier data!");
// Look up this token, see if it is a macro, or if it is a language keyword.
IdentifierInfo *II;
if (!Identifier.needsCleaning() && !Identifier.hasUCN()) {
// No cleaning needed, just use the characters from the lexed buffer.
II = getIdentifierInfo(Identifier.getRawIdentifier());
} else {
// Cleaning needed, alloca a buffer, clean into it, then use the buffer.
SmallString<64> IdentifierBuffer;
StringRef CleanedStr = getSpelling(Identifier, IdentifierBuffer);
if (Identifier.hasUCN()) {
SmallString<64> UCNIdentifierBuffer;
expandUCNs(UCNIdentifierBuffer, CleanedStr);
II = getIdentifierInfo(UCNIdentifierBuffer);
} else {
II = getIdentifierInfo(CleanedStr);
}
}
// Update the token info (identifier info and appropriate token kind).
Identifier.setIdentifierInfo(II);
if (getLangOpts().MSVCCompat && II->isCPlusPlusOperatorKeyword() &&
getSourceManager().isInSystemHeader(Identifier.getLocation()))
Identifier.setKind(clang::tok::identifier);
else
Identifier.setKind(II->getTokenID());
return II;
}
/// Lex - Lex and return a token from this macro stream.
///
void TokenLexer::Lex(Token &Tok) {
// Lexing off the end of the macro, pop this macro off the expansion stack.
if (isAtEnd()) {
// If this is a macro (not a token stream), mark the macro enabled now
// that it is no longer being expanded.
if (Macro) Macro->EnableMacro();
// Pop this context off the preprocessors lexer stack and get the next
// token. This will delete "this" so remember the PP instance var.
Preprocessor &PPCache = PP;
if (PP.HandleEndOfTokenLexer(Tok))
return;
// HandleEndOfTokenLexer may not return a token. If it doesn't, lex
// whatever is next.
return PPCache.Lex(Tok);
}
SourceManager &SM = PP.getSourceManager();
// If this is the first token of the expanded result, we inherit spacing
// properties later.
bool isFirstToken = CurToken == 0;
// Get the next token to return.
Tok = Tokens[CurToken++];
bool TokenIsFromPaste = false;
// If this token is followed by a token paste (##) operator, paste the tokens!
// Note that ## is a normal token when not expanding a macro.
if (!isAtEnd() && Tokens[CurToken].is(tok::hashhash) && Macro) {
// When handling the microsoft /##/ extension, the final token is
// returned by PasteTokens, not the pasted token.
if (PasteTokens(Tok))
return;
TokenIsFromPaste = true;
}
// The token's current location indicate where the token was lexed from. We
// need this information to compute the spelling of the token, but any
// diagnostics for the expanded token should appear as if they came from
// ExpansionLoc. Pull this information together into a new SourceLocation
// that captures all of this.
if (ExpandLocStart.isValid() && // Don't do this for token streams.
// Check that the token's location was not already set properly.
SM.isBeforeInSLocAddrSpace(Tok.getLocation(), MacroStartSLocOffset)) {
SourceLocation instLoc;
if (Tok.is(tok::comment)) {
instLoc = SM.createExpansionLoc(Tok.getLocation(),
ExpandLocStart,
ExpandLocEnd,
Tok.getLength());
} else {
instLoc = getExpansionLocForMacroDefLoc(Tok.getLocation());
}
Tok.setLocation(instLoc);
}
// If this is the first token, set the lexical properties of the token to
// match the lexical properties of the macro identifier.
if (isFirstToken) {
Tok.setFlagValue(Token::StartOfLine , AtStartOfLine);
Tok.setFlagValue(Token::LeadingSpace, HasLeadingSpace);
}
// Handle recursive expansion!
if (!Tok.isAnnotation() && Tok.getIdentifierInfo() != 0) {
// Change the kind of this identifier to the appropriate token kind, e.g.
// turning "for" into a keyword.
IdentifierInfo *II = Tok.getIdentifierInfo();
Tok.setKind(II->getTokenID());
// If this identifier was poisoned and from a paste, emit an error. This
// won't be handled by Preprocessor::HandleIdentifier because this is coming
// from a macro expansion.
if (II->isPoisoned() && TokenIsFromPaste) {
PP.HandlePoisonedIdentifier(Tok);
}
if (!DisableMacroExpansion && II->isHandleIdentifierCase())
PP.HandleIdentifier(Tok);
}
// Otherwise, return a normal token.
}
/// Lex - Lex and return a token from this macro stream.
///
bool TokenLexer::Lex(Token &Tok) {
// Lexing off the end of the macro, pop this macro off the expansion stack.
if (isAtEnd()) {
// If this is a macro (not a token stream), mark the macro enabled now
// that it is no longer being expanded.
if (Macro) Macro->EnableMacro();
Tok.startToken();
Tok.setFlagValue(Token::StartOfLine , AtStartOfLine);
Tok.setFlagValue(Token::LeadingSpace, HasLeadingSpace || NextTokGetsSpace);
if (CurToken == 0)
Tok.setFlag(Token::LeadingEmptyMacro);
return PP.HandleEndOfTokenLexer(Tok);
}
SourceManager &SM = PP.getSourceManager();
// If this is the first token of the expanded result, we inherit spacing
// properties later.
bool isFirstToken = CurToken == 0;
// Get the next token to return.
Tok = Tokens[CurToken++];
bool TokenIsFromPaste = false;
// If this token is followed by a token paste (##) operator, paste the tokens!
// Note that ## is a normal token when not expanding a macro.
if (!isAtEnd() && Macro &&
(Tokens[CurToken].is(tok::hashhash) ||
// Special processing of L#x macros in -fms-compatibility mode.
// Microsoft compiler is able to form a wide string literal from
// 'L#macro_arg' construct in a function-like macro.
(PP.getLangOpts().MSVCCompat &&
isWideStringLiteralFromMacro(Tok, Tokens[CurToken])))) {
// When handling the microsoft /##/ extension, the final token is
// returned by PasteTokens, not the pasted token.
if (PasteTokens(Tok))
return true;
TokenIsFromPaste = true;
}
// The token's current location indicate where the token was lexed from. We
// need this information to compute the spelling of the token, but any
// diagnostics for the expanded token should appear as if they came from
// ExpansionLoc. Pull this information together into a new SourceLocation
// that captures all of this.
if (ExpandLocStart.isValid() && // Don't do this for token streams.
// Check that the token's location was not already set properly.
SM.isBeforeInSLocAddrSpace(Tok.getLocation(), MacroStartSLocOffset)) {
SourceLocation instLoc;
if (Tok.is(tok::comment)) {
instLoc = SM.createExpansionLoc(Tok.getLocation(),
ExpandLocStart,
ExpandLocEnd,
Tok.getLength());
} else {
instLoc = getExpansionLocForMacroDefLoc(Tok.getLocation());
}
Tok.setLocation(instLoc);
}
// If this is the first token, set the lexical properties of the token to
// match the lexical properties of the macro identifier.
if (isFirstToken) {
Tok.setFlagValue(Token::StartOfLine , AtStartOfLine);
Tok.setFlagValue(Token::LeadingSpace, HasLeadingSpace);
} else {
// If this is not the first token, we may still need to pass through
// leading whitespace if we've expanded a macro.
if (AtStartOfLine) Tok.setFlag(Token::StartOfLine);
if (HasLeadingSpace) Tok.setFlag(Token::LeadingSpace);
}
AtStartOfLine = false;
HasLeadingSpace = false;
// Handle recursive expansion!
if (!Tok.isAnnotation() && Tok.getIdentifierInfo() != nullptr) {
// Change the kind of this identifier to the appropriate token kind, e.g.
// turning "for" into a keyword.
IdentifierInfo *II = Tok.getIdentifierInfo();
Tok.setKind(II->getTokenID());
// If this identifier was poisoned and from a paste, emit an error. This
// won't be handled by Preprocessor::HandleIdentifier because this is coming
// from a macro expansion.
if (II->isPoisoned() && TokenIsFromPaste) {
PP.HandlePoisonedIdentifier(Tok);
}
if (!DisableMacroExpansion && II->isHandleIdentifierCase())
return PP.HandleIdentifier(Tok);
}
// Otherwise, return a normal token.
return true;
}
/// SyntaxHighlight - Relex the specified FileID and annotate the HTML with
/// information about keywords, macro expansions etc. This uses the macro
/// table state from the end of the file, so it won't be perfectly perfect,
/// but it will be reasonably close.
void html::SyntaxHighlight(Rewriter &R, FileID FID, Preprocessor &PP) {
RewriteBuffer &RB = R.getEditBuffer(FID);
const SourceManager &SM = PP.getSourceManager();
Lexer L(FID, SM, PP.getLangOptions());
const char *BufferStart = L.getBufferStart();
// Inform the preprocessor that we want to retain comments as tokens, so we
// can highlight them.
L.SetCommentRetentionState(true);
// Lex all the tokens in raw mode, to avoid entering #includes or expanding
// macros.
Token Tok;
L.LexFromRawLexer(Tok);
while (Tok.isNot(tok::eof)) {
// Since we are lexing unexpanded tokens, all tokens are from the main
// FileID.
unsigned TokOffs = SM.getFileOffset(Tok.getLocation());
unsigned TokLen = Tok.getLength();
switch (Tok.getKind()) {
default: break;
case tok::identifier: {
// Fill in Result.IdentifierInfo, looking up the identifier in the
// identifier table.
IdentifierInfo *II = PP.LookUpIdentifierInfo(Tok, BufferStart+TokOffs);
// If this is a pp-identifier, for a keyword, highlight it as such.
if (II->getTokenID() != tok::identifier)
HighlightRange(RB, TokOffs, TokOffs+TokLen, BufferStart,
"<span class='keyword'>", "</span>");
break;
}
case tok::comment:
HighlightRange(RB, TokOffs, TokOffs+TokLen, BufferStart,
"<span class='comment'>", "</span>");
break;
case tok::wide_string_literal:
// Chop off the L prefix
++TokOffs;
--TokLen;
// FALL THROUGH.
case tok::string_literal:
HighlightRange(RB, TokOffs, TokOffs+TokLen, BufferStart,
"<span class='string_literal'>", "</span>");
break;
case tok::hash: {
// If this is a preprocessor directive, all tokens to end of line are too.
if (!Tok.isAtStartOfLine())
break;
// Eat all of the tokens until we get to the next one at the start of
// line.
unsigned TokEnd = TokOffs+TokLen;
L.LexFromRawLexer(Tok);
while (!Tok.isAtStartOfLine() && Tok.isNot(tok::eof)) {
TokEnd = SM.getFileOffset(Tok.getLocation())+Tok.getLength();
L.LexFromRawLexer(Tok);
}
// Find end of line. This is a hack.
HighlightRange(RB, TokOffs, TokEnd, BufferStart,
"<span class='directive'>", "</span>");
// Don't skip the next token.
continue;
}
}
L.LexFromRawLexer(Tok);
}
}
