Lexer - This provides a simple interface that turns a text buffer into a stream of tokens. More...

#include "clang/Lex/Lexer.h"

Inheritance diagram for clang::Lexer:

Classes
struct	SizedChar
	Represents a char and the number of bytes parsed to produce it. More...

Public Member Functions
	Lexer (FileID FID, const llvm::MemoryBufferRef &InputFile, Preprocessor &PP, bool IsFirstIncludeOfFile=true)
	Lexer constructor - Create a new lexer object for the specified buffer with the specified preprocessor managing the lexing process.

	Lexer (SourceLocation FileLoc, const LangOptions &LangOpts, const char BufStart, const char BufPtr, const char *BufEnd, bool IsFirstIncludeOfFile=true)
	Lexer constructor - Create a new raw lexer object.

	Lexer (FileID FID, const llvm::MemoryBufferRef &FromFile, const SourceManager &SM, const LangOptions &LangOpts, bool IsFirstIncludeOfFile=true)
	Lexer constructor - Create a new raw lexer object.

	Lexer (const Lexer &)=delete

Lexer &	operator= (const Lexer &)=delete

SourceLocation	getFileLoc () const
	getFileLoc - Return the File Location for the file we are lexing out of.

bool	Lex (Token &Result)
	Lex - Return the next token in the file.

bool	isPragmaLexer () const
	isPragmaLexer - Returns true if this Lexer is being used to lex a pragma.

bool	LexFromRawLexer (Token &Result)
	LexFromRawLexer - Lex a token from a designated raw lexer (one with no associated preprocessor object.

bool	isKeepWhitespaceMode () const
	isKeepWhitespaceMode - Return true if the lexer should return tokens for every character in the file, including whitespace and comments.

void	SetKeepWhitespaceMode (bool Val)
	SetKeepWhitespaceMode - This method lets clients enable or disable whitespace retention mode.

bool	inKeepCommentMode () const
	inKeepCommentMode - Return true if the lexer should return comments as tokens.

void	SetCommentRetentionState (bool Mode)
	SetCommentRetentionMode - Change the comment retention mode of the lexer to the specified mode.

void	resetExtendedTokenMode ()
	Sets the extended token mode back to its initial value, according to the language options and preprocessor.

StringRef	getBuffer () const
	Gets source code buffer.

void	ReadToEndOfLine (SmallVectorImpl< char > *Result=nullptr)
	ReadToEndOfLine - Read the rest of the current preprocessor line as an uninterpreted string.

DiagnosticBuilder	Diag (const char *Loc, unsigned DiagID) const
	Diag - Forwarding function for diagnostics.

SourceLocation	getSourceLocation (const char *Loc, unsigned TokLen=1) const
	getSourceLocation - Return a source location identifier for the specified offset in the current file.

SourceLocation	getSourceLocation () override
	getSourceLocation - Return a source location for the next character in the current file.

const char *	getBufferLocation () const
	Return the current location in the buffer.

unsigned	getCurrentBufferOffset ()
	Returns the current lexing offset.

void	seek (unsigned Offset, bool IsAtStartOfLine)
	Set the lexer's buffer pointer to `Offset`.

bool	isFirstTimeLexingFile () const
	Check if this is the first time we're lexing the input file.

Public Member Functions inherited from clang::PreprocessorLexer
	PreprocessorLexer (const PreprocessorLexer &)=delete

PreprocessorLexer &	operator= (const PreprocessorLexer &)=delete

void	LexIncludeFilename (Token &FilenameTok)
	Lex a token, producing a header-name token if possible.

void	setParsingPreprocessorDirective (bool f)
	Inform the lexer whether or not we are currently lexing a preprocessor directive.

bool	isLexingRawMode () const
	Return true if this lexer is in raw mode or not.

Preprocessor *	getPP () const
	Return the preprocessor object for this lexer.

FileID	getFileID () const

unsigned	getInitialNumSLocEntries () const
	Number of SLocEntries before lexing the file.

OptionalFileEntryRef	getFileEntry () const
	getFileEntry - Return the FileEntry corresponding to this FileID.

conditional_iterator	conditional_begin () const

conditional_iterator	conditional_end () const

void	setConditionalLevels (ArrayRef< PPConditionalInfo > CL)

Static Public Member Functions
static Lexer *	Create_PragmaLexer (SourceLocation SpellingLoc, SourceLocation ExpansionLocStart, SourceLocation ExpansionLocEnd, unsigned TokLen, Preprocessor &PP)
	Create_PragmaLexer: Lexer constructor - Create a new lexer object for _Pragma expansion.

static std::string	Stringify (StringRef Str, bool Charify=false)
	Stringify - Convert the specified string into a C string by i) escaping '\' and " characters and ii) replacing newline character(s) with "\n".

static void	Stringify (SmallVectorImpl< char > &Str)
	Stringify - Convert the specified string into a C string by i) escaping '\' and " characters and ii) replacing newline character(s) with "\n".

static unsigned	getSpelling (const Token &Tok, const char &Buffer, const SourceManager &SourceMgr, const LangOptions &LangOpts, bool Invalid=nullptr)
	getSpelling - This method is used to get the spelling of a token into a preallocated buffer, instead of as an std::string.

static std::string	getSpelling (const Token &Tok, const SourceManager &SourceMgr, const LangOptions &LangOpts, bool *Invalid=nullptr)
	getSpelling() - Return the 'spelling' of the Tok token.

static StringRef	getSpelling (SourceLocation loc, SmallVectorImpl< char > &buffer, const SourceManager &SM, const LangOptions &options, bool *invalid=nullptr)
	getSpelling - This method is used to get the spelling of the token at the given source location.

static unsigned	MeasureTokenLength (SourceLocation Loc, const SourceManager &SM, const LangOptions &LangOpts)
	MeasureTokenLength - Relex the token at the specified location and return its length in bytes in the input file.

static bool	getRawToken (SourceLocation Loc, Token &Result, const SourceManager &SM, const LangOptions &LangOpts, bool IgnoreWhiteSpace=false)
	Relex the token at the specified location.

static SourceLocation	GetBeginningOfToken (SourceLocation Loc, const SourceManager &SM, const LangOptions &LangOpts)
	Given a location any where in a source buffer, find the location that corresponds to the beginning of the token in which the original source location lands.

static unsigned	getTokenPrefixLength (SourceLocation TokStart, unsigned CharNo, const SourceManager &SM, const LangOptions &LangOpts)
	Get the physical length (including trigraphs and escaped newlines) of the first `Characters` characters of the token starting at TokStart.

static SourceLocation	AdvanceToTokenCharacter (SourceLocation TokStart, unsigned Characters, const SourceManager &SM, const LangOptions &LangOpts)
	AdvanceToTokenCharacter - If the current SourceLocation specifies a location at the start of a token, return a new location that specifies a character within the token.

static SourceLocation	getLocForEndOfToken (SourceLocation Loc, unsigned Offset, const SourceManager &SM, const LangOptions &LangOpts)
	Computes the source location just past the end of the token at this source location.

static CharSourceRange	getAsCharRange (SourceRange Range, const SourceManager &SM, const LangOptions &LangOpts)
	Given a token range, produce a corresponding CharSourceRange that is not a token range.

static CharSourceRange	getAsCharRange (CharSourceRange Range, const SourceManager &SM, const LangOptions &LangOpts)

static bool	isAtStartOfMacroExpansion (SourceLocation loc, const SourceManager &SM, const LangOptions &LangOpts, SourceLocation *MacroBegin=nullptr)
	Returns true if the given MacroID location points at the first token of the macro expansion.

static bool	isAtEndOfMacroExpansion (SourceLocation loc, const SourceManager &SM, const LangOptions &LangOpts, SourceLocation *MacroEnd=nullptr)
	Returns true if the given MacroID location points at the last token of the macro expansion.

static CharSourceRange	makeFileCharRange (CharSourceRange Range, const SourceManager &SM, const LangOptions &LangOpts)
	Accepts a range and returns a character range with file locations.

static StringRef	getSourceText (CharSourceRange Range, const SourceManager &SM, const LangOptions &LangOpts, bool *Invalid=nullptr)
	Returns a string for the source that the range encompasses.

static StringRef	getImmediateMacroName (SourceLocation Loc, const SourceManager &SM, const LangOptions &LangOpts)
	Retrieve the name of the immediate macro expansion.

static StringRef	getImmediateMacroNameForDiagnostics (SourceLocation Loc, const SourceManager &SM, const LangOptions &LangOpts)
	Retrieve the name of the immediate macro expansion.

static PreambleBounds	ComputePreamble (StringRef Buffer, const LangOptions &LangOpts, unsigned MaxLines=0)
	Compute the preamble of the given file.

static std::optional< Token >	findNextToken (SourceLocation Loc, const SourceManager &SM, const LangOptions &LangOpts)
	Finds the token that comes right after the given location.

static SourceLocation	findLocationAfterToken (SourceLocation loc, tok::TokenKind TKind, const SourceManager &SM, const LangOptions &LangOpts, bool SkipTrailingWhitespaceAndNewLine)
	Checks that the given token is the first token that occurs after the given location (this excludes comments and whitespace).

static bool	isAsciiIdentifierContinueChar (char c, const LangOptions &LangOpts)
	Returns true if the given character could appear in an identifier.

static bool	isNewLineEscaped (const char BufferStart, const char Str)
	Checks whether new line pointed by Str is preceded by escape sequence.

static SizedChar	getCharAndSizeNoWarn (const char *Ptr, const LangOptions &LangOpts)
	getCharAndSizeNoWarn - Like the getCharAndSize method, but does not ever emit a warning.

static StringRef	getIndentationForLine (SourceLocation Loc, const SourceManager &SM)
	Returns the leading whitespace for line that corresponds to the given location `Loc`.

Friends
class	Preprocessor

Additional Inherited Members
Public Types inherited from clang::PreprocessorLexer
using	conditional_iterator = SmallVectorImpl< PPConditionalInfo >::const_iterator
	Iterator that traverses the current stack of preprocessor conditional directives (#if/#ifdef/#ifndef).

Protected Member Functions inherited from clang::PreprocessorLexer
	PreprocessorLexer ()

	PreprocessorLexer (Preprocessor *pp, FileID fid)

virtual	~PreprocessorLexer ()=default

virtual void	IndirectLex (Token &Result)=0

virtual SourceLocation	getSourceLocation ()=0
	Return the source location for the next observable location.

void	pushConditionalLevel (SourceLocation DirectiveStart, bool WasSkipping, bool FoundNonSkip, bool FoundElse)
	pushConditionalLevel - When we enter a #if directive, this keeps track of what we are currently in for diagnostic emission (e.g.

void	pushConditionalLevel (const PPConditionalInfo &CI)

bool	popConditionalLevel (PPConditionalInfo &CI)
	popConditionalLevel - Remove an entry off the top of the conditional stack, returning information about it.

PPConditionalInfo &	peekConditionalLevel ()
	Return the top of the conditional stack.

unsigned	getConditionalStackDepth () const

Protected Attributes inherited from clang::PreprocessorLexer
Preprocessor *	PP = nullptr

const FileID	FID
	The SourceManager FileID corresponding to the file being lexed.

unsigned	InitialNumSLocEntries = 0
	Number of SLocEntries before lexing the file.

bool	ParsingPreprocessorDirective = false
	True when parsing #XXX; turns '\n' into a tok::eod token.

bool	ParsingFilename = false
	True after #include; turns <xx> or "xxx" into a tok::header_name token.

bool	LexingRawMode = false
	True if in raw mode.

MultipleIncludeOpt	MIOpt
	A state machine that detects the #ifndef-wrapping a file idiom for the multiple-include optimization.

SmallVector< PPConditionalInfo, 4 >	ConditionalStack
	Information about the set of #if/#ifdef/#ifndef blocks we are currently in.

Detailed Description

Lexer - This provides a simple interface that turns a text buffer into a stream of tokens.

This provides no support for file reading or buffering, or buffering/seeking of tokens, only forward lexing is supported. It relies on the specified Preprocessor object to handle preprocessor directives, etc.

Definition at line 78 of file Lexer.h.

Constructor & Destructor Documentation

◆ Lexer() [1/4]

Lexer::Lexer	(	FileID	FID,
		const llvm::MemoryBufferRef &	InputFile,
		Preprocessor &	PP,
		bool	IsFirstIncludeOfFile = `true`
	)

Lexer constructor - Create a new lexer object for the specified buffer with the specified preprocessor managing the lexing process.

This lexer assumes that the associated file buffer and Preprocessor objects will outlive it, so it doesn't take ownership of either of them.

Definition at line 184 of file Lexer.cpp.

References resetExtendedTokenMode().

◆ Lexer() [2/4]

Lexer::Lexer	(	SourceLocation	fileloc,
		const LangOptions &	langOpts,
		const char *	BufStart,
		const char *	BufPtr,
		const char *	BufEnd,
		bool	IsFirstIncludeOfFile = `true`
	)

Lexer constructor - Create a new raw lexer object.

This object is only suitable for calls to 'LexFromRawLexer'. This lexer assumes that the text range will outlive it, so it doesn't take ownership of it.

Definition at line 199 of file Lexer.cpp.

References clang::PreprocessorLexer::LexingRawMode.

◆ Lexer() [3/4]

Lexer::Lexer	(	FileID	FID,
		const llvm::MemoryBufferRef &	FromFile,
		const SourceManager &	SM,
		const LangOptions &	langOpts,
		bool	IsFirstIncludeOfFile = `true`
	)

Lexer constructor - Create a new raw lexer object.

This object is only suitable for calls to 'LexFromRawLexer'. This lexer assumes that the text range will outlive it, so it doesn't take ownership of it.

Definition at line 213 of file Lexer.cpp.

◆ Lexer() [4/4]

clang::Lexer::Lexer ( const Lexer & )

delete

Member Function Documentation

◆ AdvanceToTokenCharacter()

static SourceLocation clang::Lexer::AdvanceToTokenCharacter	(	SourceLocation	TokStart,
		unsigned	Characters,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

inlinestatic

AdvanceToTokenCharacter - If the current SourceLocation specifies a location at the start of a token, return a new location that specifies a character within the token.

This handles trigraphs and escaped newlines.

Definition at line 399 of file Lexer.h.

References clang::SourceLocation::getLocWithOffset(), getTokenPrefixLength(), and SM.

Referenced by clang::Sema::ActOnStringLiteral(), clang::Preprocessor::AdvanceToTokenCharacter(), Diag(), clang::StringLiteral::getLocationOfByte(), getUDSuffixLoc(), MakeCharSourceRange(), and clang::NumericLiteralParser::NumericLiteralParser().

◆ ComputePreamble()

PreambleBounds Lexer::ComputePreamble	(	StringRef	Buffer,
		const LangOptions &	LangOpts,
		unsigned	MaxLines = `0`
	)

static

Compute the preamble of the given file.

The preamble of a file contains the initial comments, include directives, and other preprocessor directives that occur before the code in this particular file actually begins. The preamble of the main source file is a potential prefix header.

Parameters

Buffer	The memory buffer containing the file's contents.
MaxLines	If non-zero, restrict the length of the preamble to fewer than this number of lines.

Returns: The offset into the file where the preamble ends and the rest of the file begins along with a boolean value indicating whether the preamble ends at the beginning of a new line.

Definition at line 637 of file Lexer.cpp.

References clang::SourceLocation::getFromRawEncoding(), clang::Token::getKind(), clang::Token::getLocation(), clang::SourceLocation::getRawEncoding(), clang::Token::getRawIdentifier(), clang::Token::isAtStartOfLine(), clang::SourceLocation::isInvalid(), clang::SourceLocation::isValid(), LexFromRawLexer(), clang::Token::needsCleaning(), and SetCommentRetentionState().

Referenced by clang::ComputePreambleBounds(), and clang::PrintPreambleAction::ExecuteAction().

◆ Create_PragmaLexer()

Lexer * Lexer::Create_PragmaLexer	(	SourceLocation	SpellingLoc,
		SourceLocation	ExpansionLocStart,
		SourceLocation	ExpansionLocEnd,
		unsigned	TokLen,
		Preprocessor &	PP
	)

static

Create_PragmaLexer: Lexer constructor - Create a new lexer object for _Pragma expansion.

This has a variety of magic semantics that this method sets up. It returns a new'd Lexer that must be delete'd when done.

On entrance to this routine, TokStartLoc is a macro location which has a spelling loc that indicates the bytes to be lexed for the token and an expansion location that indicates where all lexed tokens should be "expanded from".

TODO: It would really be nice to make _Pragma just be a wrapper around a normal lexer that remaps tokens as they fly by. This would require making Preprocessor::Lex virtual. Given that, we could just dump in a magic lexer interface that could handle this stuff. This would pull GetMappedTokenLoc out of the critical path of the lexer!

Definition at line 243 of file Lexer.cpp.

References clang::Preprocessor::getSourceManager(), clang::PreprocessorLexer::ParsingPreprocessorDirective, clang::PreprocessorLexer::PP, and SM.

◆ Diag()

DiagnosticBuilder Lexer::Diag	(	const char *	Loc,
		unsigned	DiagID
	)		const

Diag - Forwarding function for diagnostics.

This translate a source position in the current buffer into a SourceLocation object for rendering.

Definition at line 1232 of file Lexer.cpp.

References clang::Preprocessor::Diag(), getSourceLocation(), and clang::PreprocessorLexer::PP.

Referenced by DecodeTrigraphChar(), and isEndOfBlockCommentWithEscapedNewLine().

◆ findLocationAfterToken()

SourceLocation Lexer::findLocationAfterToken	(	SourceLocation	Loc,
		tok::TokenKind	TKind,
		const SourceManager &	SM,
		const LangOptions &	LangOpts,
		bool	SkipTrailingWhitespaceAndNewLine
	)

static

Checks that the given token is the first token that occurs after the given location (this excludes comments and whitespace).

Returns the location immediately after the specified token. If the token is not found or the location is inside a macro, the returned source location will be invalid.

Definition at line 1358 of file Lexer.cpp.

References clang::C, findNextToken(), clang::SourceLocation::getLocWithOffset(), clang::isHorizontalWhitespace(), and SM.

Referenced by DiagnoseMismatchedNewDelete(), clang::Sema::DiagnoseUnterminatedPragmaAlignPack(), and GenerateFixForUnusedDecl().

◆ findNextToken()

std::optional< Token > Lexer::findNextToken	(	SourceLocation	Loc,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

Finds the token that comes right after the given location.

Returns the next token, or std::nullopt if the location is inside a macro.

Definition at line 1325 of file Lexer.cpp.

References clang::File, getLocForEndOfToken(), isAtEndOfMacroExpansion(), clang::SourceLocation::isMacroID(), LexFromRawLexer(), and SM.

Referenced by clang::tooling::ExtractionSemicolonPolicy::compute(), findLocationAfterToken(), and fixVarDeclWithArray().

◆ getAsCharRange() [1/2]

static CharSourceRange clang::Lexer::getAsCharRange	(	CharSourceRange	Range,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

inlinestatic

Definition at line 438 of file Lexer.h.

References getAsCharRange(), and SM.

◆ getAsCharRange() [2/2]

static CharSourceRange clang::Lexer::getAsCharRange	(	SourceRange	Range,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

inlinestatic

Given a token range, produce a corresponding CharSourceRange that is not a token range.

This allows the source range to be used by components that don't have access to the lexer and thus can't find the end of the range for themselves.

Definition at line 430 of file Lexer.h.

References clang::CharSourceRange::getCharRange(), getLocForEndOfToken(), and SM.

Referenced by getAsCharRange(), clang::tooling::maybeExtendRange(), clang::ento::ConditionBRVisitor::patternMatch(), and clang::arcmt::writeARCDiagsToPlist().

◆ GetBeginningOfToken()

SourceLocation Lexer::GetBeginningOfToken	(	SourceLocation	Loc,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

Given a location any where in a source buffer, find the location that corresponds to the beginning of the token in which the original source location lands.

Definition at line 609 of file Lexer.cpp.

References getBeginningOfFileToken(), clang::SourceLocation::getLocWithOffset(), clang::SourceLocation::isFileID(), and SM.

Referenced by adjustRemoval(), and findPreviousTokenStart().

◆ getBuffer()

StringRef clang::Lexer::getBuffer ( ) const

inline

Gets source code buffer.

Definition at line 284 of file Lexer.h.

◆ getBufferLocation()

const char * clang::Lexer::getBufferLocation ( ) const

inline

Return the current location in the buffer.

Definition at line 308 of file Lexer.h.

Referenced by getBeginningOfFileToken().

◆ getCharAndSizeNoWarn()

static SizedChar clang::Lexer::getCharAndSizeNoWarn	(	const char *	Ptr,
		const LangOptions &	LangOpts
	)

inlinestatic

getCharAndSizeNoWarn - Like the getCharAndSize method, but does not ever emit a warning.

Definition at line 586 of file Lexer.h.

Referenced by getSpellingSlow(), and getTokenPrefixLength().

◆ getCurrentBufferOffset()

unsigned clang::Lexer::getCurrentBufferOffset ( )

inline

Returns the current lexing offset.

Definition at line 311 of file Lexer.h.

Referenced by clang::syntax::tokenize().

◆ getFileLoc()

SourceLocation clang::Lexer::getFileLoc ( ) const

inline

getFileLoc - Return the File Location for the file we are lexing out of.

The physical location encodes the location where the characters come from, the virtual location encodes where we should claim the characters came from. Currently this is only used by _Pragma handling.

Definition at line 199 of file Lexer.h.

◆ getImmediateMacroName()

StringRef Lexer::getImmediateMacroName	(	SourceLocation	Loc,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

Retrieve the name of the immediate macro expansion.

This routine starts from a source location, and finds the name of the macro responsible for its immediate expansion. It looks through any intervening macro argument expansions to compute this. It returns a StringRef which refers to the SourceManager-owned buffer of the source where that macro name is spelled. Thus, the result shouldn't out-live that SourceManager.

Definition at line 1060 of file Lexer.cpp.

References clang::PreprocessorLexer::FID, clang::SrcMgr::SLocEntry::getExpansion(), clang::SrcMgr::ExpansionInfo::getExpansionLocStart(), clang::SrcMgr::ExpansionInfo::getSpellingLoc(), clang::SourceLocation::isFileID(), clang::SrcMgr::ExpansionInfo::isMacroArgExpansion(), clang::SourceLocation::isMacroID(), MeasureTokenLength(), and SM.

Referenced by BuiltinOverflow(), CheckMemaccessSize(), clang::Preprocessor::getImmediateMacroName(), getMacroName(), clang::ento::CheckerContext::getMacroNameOrSpelling(), IsEnumConstOrFromMacro(), clang::data_collection::printMacroName(), and clang::Sema::ProcessAPINotes().

◆ getImmediateMacroNameForDiagnostics()

StringRef Lexer::getImmediateMacroNameForDiagnostics	(	SourceLocation	Loc,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

Retrieve the name of the immediate macro expansion.

This routine starts from a source location, and finds the name of the macro responsible for its immediate expansion. It looks through any intervening macro argument expansions to compute this. It returns a StringRef which refers to the SourceManager-owned buffer of the source where that macro name is spelled. Thus, the result shouldn't out-live that SourceManager.

This differs from Lexer::getImmediateMacroName in that any macro argument location will result in the topmost function macro that accepted it. e.g.

MAC1( MAC2(foo) )

for location of 'foo' token, this function will return "MAC1" while Lexer::getImmediateMacroName will return "MAC2".

Definition at line 1107 of file Lexer.cpp.

References clang::SourceLocation::isFileID(), clang::SourceLocation::isMacroID(), MeasureTokenLength(), and SM.

Referenced by DiagnoseNullConversion().

◆ getIndentationForLine()

StringRef Lexer::getIndentationForLine	(	SourceLocation	Loc,
		const SourceManager &	SM
	)

static

Returns the leading whitespace for line that corresponds to the given location Loc.

Definition at line 1158 of file Lexer.cpp.

References findBeginningOfLine(), clang::Invalid, clang::SourceLocation::isInvalid(), clang::SourceLocation::isMacroID(), clang::Line, and SM.

◆ getLocForEndOfToken()

SourceLocation Lexer::getLocForEndOfToken	(	SourceLocation	Loc,
		unsigned	Offset,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

Computes the source location just past the end of the token at this source location.

This routine can be used to produce a source location that points just past the end of the token referenced by Loc, and is generally used when a diagnostic needs to point just after a token where it expected something different that it received. If the returned source location would not be meaningful (e.g., if it points into a macro), this routine returns an invalid source location.

Parameters

Offset an offset from the end of the token, where the source location should refer to. The default offset (0) produces a source location pointing just past the end of the token; an offset of 1 produces a source location pointing to the last character in the token, etc.

Definition at line 850 of file Lexer.cpp.

References clang::SourceLocation::getLocWithOffset(), isAtEndOfMacroExpansion(), clang::SourceLocation::isInvalid(), clang::SourceLocation::isMacroID(), MeasureTokenLength(), and SM.

Referenced by AnalyzeImplicitConversions(), convertTokenRangeToCharRange(), createAttributeInsertion(), findNextToken(), clang::arcmt::trans::findSemiAfterLocation(), getAsCharRange(), getFunNameText(), clang::Preprocessor::getLocForEndOfToken(), clang::Sema::getLocForEndOfToken(), getPastLoc(), getPointeeTypeText(), getRange(), clang::diff::SyntaxTree::getSourceRangeOffsets(), getSourceRangeToTokenEnd(), getVarDeclIdentifierText(), makeRangeFromFileLocs(), clang::tooling::RecursiveSymbolVisitor< T >::VisitCXXConstructorDecl(), clang::tooling::RecursiveSymbolVisitor< T >::VisitTypedefTypeLoc(), and clang::tooling::RecursiveSymbolVisitor< T >::VisitTypeLoc().

◆ getRawToken()

bool Lexer::getRawToken	(	SourceLocation	Loc,
		Token &	Result,
		const SourceManager &	SM,
		const LangOptions &	LangOpts,
		bool	IgnoreWhiteSpace = `false`
	)

static

Relex the token at the specified location.

Returns: true if there was a failure, false on success.

Definition at line 510 of file Lexer.cpp.

References clang::Invalid, clang::isWhitespace(), LexFromRawLexer(), clang::Result, SetCommentRetentionState(), and SM.

Referenced by atOrBeforeSeparation(), findPreviousTokenKind(), clang::Preprocessor::getRawToken(), clang::tooling::maybeExtendRange(), and MeasureTokenLength().

◆ getSourceLocation() [1/2]

SourceLocation clang::Lexer::getSourceLocation ( )

inlineoverridevirtual

getSourceLocation - Return a source location for the next character in the current file.

Implements clang::PreprocessorLexer.

Definition at line 303 of file Lexer.h.

References getSourceLocation().

Referenced by Diag(), and getSourceLocation().

◆ getSourceLocation() [2/2]

SourceLocation Lexer::getSourceLocation	(	const char *	Loc,
		unsigned	TokLen = `1`
	)		const

getSourceLocation - Return a source location identifier for the specified offset in the current file.

Definition at line 1213 of file Lexer.cpp.

References clang::SourceLocation::getLocWithOffset(), GetMappedTokenLoc(), clang::SourceLocation::isFileID(), and clang::PreprocessorLexer::PP.

Referenced by makeCharRange(), and clang::ModuleMap::parseModuleMapFile().

◆ getSourceText()

StringRef Lexer::getSourceText	(	CharSourceRange	Range,
		const SourceManager &	SM,
		const LangOptions &	LangOpts,
		bool *	Invalid = `nullptr`
	)

static

Returns a string for the source that the range encompasses.

Definition at line 1024 of file Lexer.cpp.

References clang::Invalid, makeFileCharRange(), and SM.

Referenced by AnalyzeImplicitConversions(), constructDebugPieceForTrackedCondition(), clang::tooling::createRenameAtomicChanges(), DiagnoseBaseOrMemInitializerOrder(), diagnoseXorMisusedAsPow(), GCRewriteFinalize(), clang::diff::SyntaxTree::Impl::getDeclValue(), GetDefaultValueString(), getExprText(), getLiteralInfo(), clang::MacroExpansionContext::getOriginalText(), getRangeText(), clang::tooling::getText(), clang::tooling::fixit::internal::getText(), clang::ento::ConditionBRVisitor::patternMatch(), printExprAsWritten(), clang::tooling::replaceStmtWithStmt(), and clang::tooling::ReplaceNodeWithTemplate::run().

◆ getSpelling() [1/3]

unsigned Lexer::getSpelling	(	const Token &	Tok,
		const char *&	Buffer,
		const SourceManager &	SourceMgr,
		const LangOptions &	LangOpts,
		bool *	Invalid = `nullptr`
	)

static

getSpelling - This method is used to get the spelling of a token into a preallocated buffer, instead of as an std::string.

The caller is required to allocate enough space for the token, which is guaranteed to be at least Tok.getLength() bytes long. The length of the actual result is returned.

Note that this method may do two possible things: it may either fill in the buffer specified with characters, or it may change the input pointer to point to a constant buffer with the data already in it (avoiding a copy). The caller is not allowed to modify the returned buffer pointer if an internal buffer is returned.

The caller is required to allocate enough space for the token, which is guaranteed to be at least Tok.getLength() bytes long. The actual length of the token is returned.

Note that this method may do two possible things: it may either fill in the buffer specified with characters, or it may change the input pointer to point to a constant buffer with the data already in it (avoiding a copy). The caller is not allowed to modify the returned buffer pointer if an internal buffer is returned.

Definition at line 452 of file Lexer.cpp.

References clang::SourceManager::getCharacterData(), clang::Token::getIdentifierInfo(), clang::Token::getLength(), clang::Token::getLiteralData(), clang::Token::getLocation(), clang::Token::getRawIdentifier(), getSpellingSlow(), clang::Token::hasUCN(), clang::Invalid, clang::Token::is(), clang::Token::isLiteral(), and clang::Token::needsCleaning().

Referenced by findDirectives(), clang::ento::CheckerContext::getMacroNameOrSpelling(), clang::StringLiteralParser::getOffsetOfStringByte(), clang::Preprocessor::getSpelling(), highlightLines(), clang::ast_matchers::internal::isTokenAtLoc(), and ReadOriginalFileName().

◆ getSpelling() [2/3]

std::string Lexer::getSpelling	(	const Token &	Tok,
		const SourceManager &	SourceMgr,
		const LangOptions &	LangOpts,
		bool *	Invalid = `nullptr`
	)

static

getSpelling() - Return the 'spelling' of the Tok token.

getSpelling() - Return the 'spelling' of this token.

The spelling of a token is the characters used to represent the token in the source file after trigraph expansion and escaped-newline folding. In particular, this wants to get the true, uncanonicalized, spelling of things like digraphs UCNs, etc.

The spelling of a token are the characters used to represent the token in the source file after trigraph expansion and escaped-newline folding. In particular, this wants to get the true, uncanonicalized, spelling of things like digraphs UCNs, etc.

Definition at line 420 of file Lexer.cpp.

References clang::SourceManager::getCharacterData(), clang::Token::getLength(), clang::Token::getLocation(), getSpellingSlow(), clang::Invalid, clang::Token::needsCleaning(), and clang::Result.

◆ getSpelling() [3/3]

StringRef Lexer::getSpelling	(	SourceLocation	loc,
		SmallVectorImpl< char > &	buffer,
		const SourceManager &	SM,
		const LangOptions &	options,
		bool *	invalid = `nullptr`
	)

static

getSpelling - This method is used to get the spelling of the token at the given source location.

getSpelling() - Return the 'spelling' of this token.

If, as is usually true, it is not necessary to copy any data, then the returned string may not point into the provided buffer.

This method lexes at the expansion depth of the given location and does not jump to the expansion or spelling location.

The spelling of a token are the characters used to represent the token in the source file after trigraph expansion and escaped-newline folding. In particular, this wants to get the true, uncanonicalized, spelling of things like digraphs UCNs, etc.

Definition at line 379 of file Lexer.cpp.

References clang::Token::getLength(), getSpellingSlow(), length(), LexFromRawLexer(), clang::Token::needsCleaning(), and SM.

◆ getTokenPrefixLength()

unsigned Lexer::getTokenPrefixLength	(	SourceLocation	TokStart,
		unsigned	CharNo,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

Get the physical length (including trigraphs and escaped newlines) of the first Characters characters of the token starting at TokStart.

Definition at line 791 of file Lexer.cpp.

References getCharAndSizeNoWarn(), clang::Invalid, and SM.

Referenced by AdvanceToTokenCharacter().

◆ inKeepCommentMode()

bool clang::Lexer::inKeepCommentMode ( ) const

inline

inKeepCommentMode - Return true if the lexer should return comments as tokens.

Definition at line 262 of file Lexer.h.

◆ isAsciiIdentifierContinueChar()

bool Lexer::isAsciiIdentifierContinueChar	(	char	c,
		const LangOptions &	LangOpts
	)

static

Returns true if the given character could appear in an identifier.

Definition at line 1134 of file Lexer.cpp.

References c, and clang::isAsciiIdentifierContinue().

Referenced by addFixitForObjCARCConversion(), and canBeJoined().

◆ isAtEndOfMacroExpansion()

bool Lexer::isAtEndOfMacroExpansion	(	SourceLocation	loc,
		const SourceManager &	SM,
		const LangOptions &	LangOpts,
		SourceLocation *	MacroEnd = `nullptr`
	)

static

Returns true if the given MacroID location points at the last token of the macro expansion.

Parameters

MacroEnd If non-null and function returns true, it is set to end location of the macro.

Definition at line 894 of file Lexer.cpp.

References clang::SourceLocation::getLocWithOffset(), isAtEndOfMacroExpansion(), clang::SourceLocation::isFileID(), clang::SourceLocation::isMacroID(), clang::SourceLocation::isValid(), MeasureTokenLength(), and SM.

Referenced by FindLocsWithCommonFileID(), findNextToken(), clang::arcmt::trans::findSemiAfterLocation(), getLocForEndOfToken(), getVarDeclIdentifierText(), isAtEndOfMacroExpansion(), clang::Preprocessor::isAtEndOfMacroExpansion(), makeFileCharRange(), and clang::ento::ConditionBRVisitor::patternMatch().

◆ isAtStartOfMacroExpansion()

bool Lexer::isAtStartOfMacroExpansion	(	SourceLocation	loc,
		const SourceManager &	SM,
		const LangOptions &	LangOpts,
		SourceLocation *	MacroBegin = `nullptr`
	)

static

Returns true if the given MacroID location points at the first token of the macro expansion.

Parameters

MacroBegin If non-null and function returns true, it is set to begin location of the macro.

Definition at line 872 of file Lexer.cpp.

References isAtStartOfMacroExpansion(), clang::SourceLocation::isFileID(), clang::SourceLocation::isMacroID(), clang::SourceLocation::isValid(), and SM.

Referenced by FindLocsWithCommonFileID(), isAtStartOfMacroExpansion(), clang::Preprocessor::isAtStartOfMacroExpansion(), makeFileCharRange(), and clang::ento::ConditionBRVisitor::patternMatch().

◆ isFirstTimeLexingFile()

bool clang::Lexer::isFirstTimeLexingFile ( ) const

inline

Check if this is the first time we're lexing the input file.

Definition at line 603 of file Lexer.h.

◆ isKeepWhitespaceMode()

bool clang::Lexer::isKeepWhitespaceMode ( ) const

inline

isKeepWhitespaceMode - Return true if the lexer should return tokens for every character in the file, including whitespace and comments.

This should only be used in raw mode, as the preprocessor is not prepared to deal with the excess tokens.

Definition at line 248 of file Lexer.h.

Referenced by SetCommentRetentionState().

◆ isNewLineEscaped()

bool Lexer::isNewLineEscaped	(	const char *	BufferStart,
		const char *	Str
	)

static

Checks whether new line pointed by Str is preceded by escape sequence.

Definition at line 1138 of file Lexer.cpp.

References clang::isHorizontalWhitespace(), and clang::isVerticalWhitespace().

Referenced by findBeginningOfLine().

◆ isPragmaLexer()

bool clang::Lexer::isPragmaLexer ( ) const

inline

isPragmaLexer - Returns true if this Lexer is being used to lex a pragma.

Definition at line 225 of file Lexer.h.

◆ Lex()

bool Lexer::Lex ( Token & Result )

Lex - Return the next token in the file.

If this is the end of file, it return the tok::eof token. This implicitly involves the preprocessor.

Definition at line 3669 of file Lexer.cpp.

References clang::PreprocessorLexer::isLexingRawMode(), clang::Token::LeadingEmptyMacro, clang::Token::LeadingSpace, clang::Result, and clang::Token::StartOfLine.

Referenced by LexFromRawLexer(), and ReadToEndOfLine().

◆ LexFromRawLexer()

bool clang::Lexer::LexFromRawLexer ( Token & Result )

inline

LexFromRawLexer - Lex a token from a designated raw lexer (one with no associated preprocessor object.

Return true if the 'next character to read' pointer points at the end of the lexer buffer, false otherwise.

Definition at line 236 of file Lexer.h.

References Lex(), clang::PreprocessorLexer::LexingRawMode, and clang::Result.

Referenced by clang::arcmt::trans::MigrationContext::addPropertyAttribute(), ComputePreamble(), EmitAlphaCounter(), clang::DumpRawTokensAction::ExecuteAction(), findDirectives(), findNextToken(), clang::arcmt::trans::findSemiAfterLocation(), getBeginningOfFileToken(), getEntityEndLoc(), clang::StringLiteral::getLocationOfByte(), getRawToken(), getSpelling(), LexRawTokensFromMainFile(), LocPropertyAttribute(), NormalizeLine(), clang::format::IntegerLiteralSeparatorFixer::process(), clang::arcmt::trans::MigrationContext::rewritePropertyAttribute(), clang::syntax::tokenize(), and clang::TokenRewriter::TokenRewriter().

◆ makeFileCharRange()

CharSourceRange Lexer::makeFileCharRange	(	CharSourceRange	Range,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

Accepts a range and returns a character range with file locations.

Returns a null range if a part of the range resides inside a macro expansion or the range does not reside on the same FileID.

This function is trying to deal with macros and return a range based on file locations. The cases where it can successfully handle macros are:

-begin or end range lies at the start or end of a macro expansion, in which case the location will be set to the expansion point, e.g: #define M 1 2 a M If you have a range [a, 2] (where 2 came from the macro), the function will return a range for "a M" if you have range [a, 1], the function will fail because the range overlaps with only a part of the macro

-The macro is a function macro and the range can be mapped to the macro arguments, e.g: #define M 1 2 #define FM(x) x FM(a b M) if you have range [b, 2], the function will return the file range "b M" inside the macro arguments. if you have range [a, 2], the function will return the file range "FM(a b M)" since the range includes all of the macro expansion.

Definition at line 955 of file Lexer.cpp.

References Begin, clang::SrcMgr::SLocEntry::getExpansion(), clang::SrcMgr::ExpansionInfo::getExpansionLocStart(), clang::Invalid, isAtEndOfMacroExpansion(), isAtStartOfMacroExpansion(), clang::SourceLocation::isFileID(), isInExpansionTokenRange(), clang::SourceLocation::isInvalid(), clang::SrcMgr::ExpansionInfo::isMacroArgExpansion(), clang::SourceLocation::isMacroID(), makeFileCharRange(), makeRangeFromFileLocs(), and SM.

Referenced by clang::transformer::after(), clang::tooling::getAssociatedRange(), getRange(), getSourceText(), makeFileCharRange(), and makeStandaloneRange().

◆ MeasureTokenLength()

unsigned Lexer::MeasureTokenLength	(	SourceLocation	Loc,
		const SourceManager &	SM,
		const LangOptions &	LangOpts
	)

static

MeasureTokenLength - Relex the token at the specified location and return its length in bytes in the input file.

If the token needs cleaning (e.g. includes a trigraph or an escaped newline) then this count includes bytes that are part of that.

Definition at line 499 of file Lexer.cpp.

References clang::Token::getLength(), getRawToken(), and SM.

Referenced by clang::TextDiagnostic::emitDiagnosticLoc(), getEndCharLoc(), getImmediateMacroName(), getImmediateMacroNameForDiagnostics(), getLocForEndOfToken(), clang::Rewriter::getRangeSize(), getRangeSize(), clang::Rewriter::getRewrittenText(), clang::html::HighlightRange(), isAtEndOfMacroExpansion(), prepareAndFilterRanges(), and clang::PrintingCodeCompleteConsumer::ProcessCodeCompleteResults().

◆ operator=()

Lexer & clang::Lexer::operator= ( const Lexer & )

delete

◆ ReadToEndOfLine()

void Lexer::ReadToEndOfLine ( SmallVectorImpl< char > * Result = nullptr )

ReadToEndOfLine - Read the rest of the current preprocessor line as an uninterpreted string.

This switches the lexer out of directive mode.

Definition at line 3056 of file Lexer.cpp.

References clang::Preprocessor::CodeCompleteNaturalLanguage(), clang::Token::is(), Lex(), clang::PreprocessorLexer::ParsingFilename, clang::PreprocessorLexer::ParsingPreprocessorDirective, clang::PreprocessorLexer::PP, clang::Result, and clang::Token::startToken().

◆ resetExtendedTokenMode()

void Lexer::resetExtendedTokenMode ( )

Sets the extended token mode back to its initial value, according to the language options and preprocessor.

This controls whether the lexer produces comment and whitespace tokens.

This requires the lexer to have an associated preprocessor. A standalone lexer has nothing to reset to.

Definition at line 220 of file Lexer.cpp.

References clang::Preprocessor::getCommentRetentionState(), clang::PreprocessorLexer::PP, SetCommentRetentionState(), and SetKeepWhitespaceMode().

Referenced by Lexer().

◆ seek()

void Lexer::seek	(	unsigned	Offset,
		bool	IsAtStartOfLine
	)

Set the lexer's buffer pointer to Offset.

Definition at line 278 of file Lexer.cpp.

◆ SetCommentRetentionState()

void clang::Lexer::SetCommentRetentionState ( bool Mode )

inline

SetCommentRetentionMode - Change the comment retention mode of the lexer to the specified mode.

This is really only useful when lexing in raw mode, because otherwise the lexer needs to manage this.

Definition at line 269 of file Lexer.h.

References isKeepWhitespaceMode().

Referenced by ComputePreamble(), findDirectives(), getBeginningOfFileToken(), getRawToken(), LexRawTokensFromMainFile(), clang::format::IntegerLiteralSeparatorFixer::process(), and resetExtendedTokenMode().

◆ SetKeepWhitespaceMode()

void clang::Lexer::SetKeepWhitespaceMode ( bool Val )

inline

SetKeepWhitespaceMode - This method lets clients enable or disable whitespace retention mode.

Definition at line 254 of file Lexer.h.

References clang::PreprocessorLexer::LexingRawMode.

Referenced by clang::DumpRawTokensAction::ExecuteAction(), getEntityEndLoc(), resetExtendedTokenMode(), and clang::TokenRewriter::TokenRewriter().

◆ Stringify() [1/2]

void Lexer::Stringify ( SmallVectorImpl< char > & Str )

static

Stringify - Convert the specified string into a C string by i) escaping '\' and " characters and ii) replacing newline character(s) with "\n".

Definition at line 317 of file Lexer.cpp.

References StringifyImpl().

◆ Stringify() [2/2]

std::string Lexer::Stringify	(	StringRef	Str,
		bool	Charify = `false`
	)

static

Stringify - Convert the specified string into a C string by i) escaping '\' and " characters and ii) replacing newline character(s) with "\n".

If Charify is true, this escapes the ' character instead of ".

Definition at line 310 of file Lexer.cpp.

References clang::Result, and StringifyImpl().

Referenced by clang::Sema::ExpandFunctionLocalPredefinedMacros(), PrintHeaderInfo(), and clang::MacroArgs::StringifyArgument().

Friends And Related Function Documentation

◆ Preprocessor

friend class Preprocessor

friend

Definition at line 79 of file Lexer.h.

The documentation for this class was generated from the following files:

include/clang/Lex/Lexer.h
lib/Lex/Lexer.cpp

Classes

Public Member Functions

Static Public Member Functions

Friends

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ Lexer() [1/4]

◆ Lexer() [2/4]

◆ Lexer() [3/4]

◆ Lexer() [4/4]

Member Function Documentation

◆ AdvanceToTokenCharacter()

◆ ComputePreamble()

◆ Create_PragmaLexer()

◆ Diag()

◆ findLocationAfterToken()

◆ findNextToken()

◆ getAsCharRange() [1/2]

◆ getAsCharRange() [2/2]

◆ GetBeginningOfToken()

◆ getBuffer()

◆ getBufferLocation()

◆ getCharAndSizeNoWarn()

◆ getCurrentBufferOffset()

◆ getFileLoc()

◆ getImmediateMacroName()

◆ getImmediateMacroNameForDiagnostics()

◆ getIndentationForLine()

◆ getLocForEndOfToken()

◆ getRawToken()

◆ getSourceLocation() [1/2]

◆ getSourceLocation() [2/2]

◆ getSourceText()

◆ getSpelling() [1/3]

◆ getSpelling() [2/3]

◆ getSpelling() [3/3]

◆ getTokenPrefixLength()

◆ inKeepCommentMode()

◆ isAsciiIdentifierContinueChar()

◆ isAtEndOfMacroExpansion()

◆ isAtStartOfMacroExpansion()

◆ isFirstTimeLexingFile()

◆ isKeepWhitespaceMode()

◆ isNewLineEscaped()

◆ isPragmaLexer()

◆ Lex()

◆ LexFromRawLexer()

◆ makeFileCharRange()

◆ MeasureTokenLength()

◆ operator=()

◆ ReadToEndOfLine()

◆ resetExtendedTokenMode()

◆ seek()

◆ SetCommentRetentionState()

◆ SetKeepWhitespaceMode()

◆ Stringify() [1/2]

◆ Stringify() [2/2]

Friends And Related Function Documentation

◆ Preprocessor