summaryrefslogtreecommitdiffstats
path: root/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
diff options
context:
space:
mode:
authordim <dim@FreeBSD.org>2017-09-26 19:56:36 +0000
committerdim <dim@FreeBSD.org>2017-09-26 19:56:36 +0000
commit12cd91cf4c6b96a24427c0de5374916f2808d263 (patch)
tree6d243b0ccba6738dbbd30767188e2963f90ef18f /contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
parentb60520398f206195e21774c315afb59a0f6d7146 (diff)
downloadFreeBSD-src-12cd91cf4c6b96a24427c0de5374916f2808d263.zip
FreeBSD-src-12cd91cf4c6b96a24427c0de5374916f2808d263.tar.gz
Merge clang, llvm, lld, lldb, compiler-rt and libc++ 5.0.0 release.
MFC r309126 (by emaste): Correct lld llvm-tblgen dependency file name MFC r309169: Get rid of separate Subversion mergeinfo properties for llvm-dwarfdump and llvm-lto. The mergeinfo confuses Subversion enormously, and these directories will just use the mergeinfo for llvm itself. MFC r312765: Pull in r276136 from upstream llvm trunk (by Wei Mi): Use ValueOffsetPair to enhance value reuse during SCEV expansion. In D12090, the ExprValueMap was added to reuse existing value during SCEV expansion. However, const folding and sext/zext distribution can make the reuse still difficult. A simplified case is: suppose we know S1 expands to V1 in ExprValueMap, and S1 = S2 + C_a S3 = S2 + C_b where C_a and C_b are different SCEVConstants. Then we'd like to expand S3 as V1 - C_a + C_b instead of expanding S2 literally. It is helpful when S2 is a complex SCEV expr and S2 has no entry in ExprValueMap, which is usually caused by the fact that S3 is generated from S1 after const folding. In order to do that, we represent ExprValueMap as a mapping from SCEV to ValueOffsetPair. We will save both S1->{V1, 0} and S2->{V1, C_a} into the ExprValueMap when we create SCEV for V1. When S3 is expanded, it will first expand S2 to V1 - C_a because of S2->{V1, C_a} in the map, then expand S3 to V1 - C_a + C_b. Differential Revision: https://reviews.llvm.org/D21313 This should fix assertion failures when building OpenCV >= 3.1. PR: 215649 MFC r312831: Revert r312765 for now, since it causes assertions when building lang/spidermonkey24. Reported by: antoine PR: 215649 MFC r316511 (by jhb): Add an implementation of __ffssi2() derived from __ffsdi2(). Newer versions of GCC include an __ffssi2() symbol in libgcc and the compiler can emit calls to it in generated code. This is true for at least GCC 6.2 when compiling world for mips and mips64. Reviewed by: jmallett, dim Sponsored by: DARPA / AFRL Differential Revision: https://reviews.freebsd.org/D10086 MFC r318601 (by adrian): [libcompiler-rt] add bswapdi2/bswapsi2 This is required for mips gcc 6.3 userland to build/run. Reviewed by: emaste, dim Approved by: emaste Differential Revision: https://reviews.freebsd.org/D10838 MFC r318884 (by emaste): lldb: map TRAP_CAP to a trace trap In the absense of a more specific handler for TRAP_CAP (generated by ENOTCAPABLE or ECAPMODE while in capability mode) treat it as a trace trap. Example usage (testing the bug in PR219173): % proccontrol -m trapcap lldb usr.bin/hexdump/obj/hexdump -- -Cv -s 1 /bin/ls ... (lldb) run Process 12980 launching Process 12980 launched: '.../usr.bin/hexdump/obj/hexdump' (x86_64) Process 12980 stopped * thread #1, stop reason = trace frame #0: 0x0000004b80c65f1a libc.so.7`__sys_lseek + 10 ... In the future we should have LLDB control the trapcap procctl itself (as it does with ASLR), as well as report a specific stop reason. This change eliminates an assertion failure from LLDB for now. MFC r319796: Remove a few unneeded files from libllvm, libclang and liblldb. MFC r319885 (by emaste): lld: ELF: Fix ICF crash on absolute symbol relocations. If two sections contained relocations to absolute symbols with the same value we would crash when trying to access their sections. Add a check that both symbols point to sections before accessing their sections, and treat absolute symbols as equal if their values are equal. Obtained from: LLD commit r292578 MFC r319918: Revert r319796 for now, it can cause undefined references when linking in some circumstances. Reported by: Shawn Webb <shawn.webb@hardenedbsd.org> MFC r319957 (by emaste): lld: Add armelf emulation mode Obtained from: LLD r305375 MFC r321369: Upgrade our copies of clang, llvm, lld, lldb, compiler-rt and libc++ to 5.0.0 (trunk r308421). Upstream has branched for the 5.0.0 release, which should be in about a month. Please report bugs and regressions, so we can get them into the release. Please note that from 3.5.0 onwards, clang, llvm and lldb require C++11 support to build; see UPDATING for more information. MFC r321420: Add a few more object files to liblldb, which should solve errors when linking the lldb executable in some cases. In particular, when the -ffunction-sections -fdata-sections options are turned off, or ineffective. Reported by: Shawn Webb, Mark Millard MFC r321433: Cleanup stale Options.inc files from the previous libllvm build for clang 4.0.0. Otherwise, these can get included before the two newly generated ones (which are different) for clang 5.0.0. Reported by: Mark Millard MFC r321439 (by bdrewery): Move llvm Options.inc hack from r321433 for NO_CLEAN to lib/clang/libllvm. The files are only ever generated to .OBJDIR, not to WORLDTMP (as a sysroot) and are only ever included from a compilation. So using a beforebuild target here removes the file before the compilation tries to include it. MFC r321664: Pull in r308891 from upstream llvm trunk (by Benjamin Kramer): [CodeGenPrepare] Cut off FindAllMemoryUses if there are too many uses. This avoids excessive compile time. The case I'm looking at is Function.cpp from an old version of LLVM that still had the giant memcmp string matcher in it. Before r308322 this compiled in about 2 minutes, after it, clang takes infinite* time to compile it. With this patch we're at 5 min, which is still bad but this is a pathological case. The cut off at 20 uses was chosen by looking at other cut-offs in LLVM for user scanning. It's probably too high, but does the job and is very unlikely to regress anything. Fixes PR33900. * I'm impatient and aborted after 15 minutes, on the bug report it was killed after 2h. Pull in r308986 from upstream llvm trunk (by Simon Pilgrim): [X86][CGP] Reduce memcmp() expansion to 2 load pairs (PR33914) D35067/rL308322 attempted to support up to 4 load pairs for memcmp inlining which resulted in regressions for some optimized libc memcmp implementations (PR33914). Until we can match these more optimal cases, this patch reduces the memcmp expansion to a maximum of 2 load pairs (which matches what we do for -Os). This patch should be considered for the 5.0.0 release branch as well Differential Revision: https://reviews.llvm.org/D35830 These fix a hang (or extremely long compile time) when building older LLVM ports. Reported by: antoine PR: 219139 MFC r321719: Pull in r309503 from upstream clang trunk (by Richard Smith): PR33902: Invalidate line number cache when adding more text to existing buffer. This led to crashes as the line number cache would report a bogus line number for a line of code, and we'd try to find a nonexistent column within the line when printing diagnostics. This fixes an assertion when building the graphics/champlain port. Reported by: antoine, kwm PR: 219139 MFC r321723: Upgrade our copies of clang, llvm, lld and lldb to r309439 from the upstream release_50 branch. This is just after upstream's 5.0.0-rc1. MFC r322320: Upgrade our copies of clang, llvm and libc++ to r310316 from the upstream release_50 branch. MFC r322326 (by emaste): lldb: Make i386-*-freebsd expression work on JIT path * Enable i386 ABI creation for freebsd * Added an extra argument in ABISysV_i386::PrepareTrivialCall for mmap syscall * Unlike linux, the last argument of mmap is actually 64-bit(off_t). This requires us to push an additional word for the higher order bits. * Prior to this change, ktrace dump will show mmap failures due to invalid argument coming from the 6th mmap argument. Submitted by: Karnajit Wangkhem Differential Revision: https://reviews.llvm.org/D34776 MFC r322360 (by emaste): lldb: Report inferior signals as signals, not exceptions, on FreeBSD This is the FreeBSD equivalent of LLVM r238549. This serves 2 purposes: * LLDB should handle inferior process signals SIGSEGV/SIGILL/SIGBUS/ SIGFPE the way it is suppose to be handled. Prior to this fix these signals will neither create a coredump, nor exit from the debugger or work for signal handling scenario. * eInvalidCrashReason need not report "unknown crash reason" if we have a valid si_signo llvm.org/pr23699 Patch by Karnajit Wangkhem Differential Revision: https://reviews.llvm.org/D35223 Submitted by: Karnajit Wangkhem Obtained from: LLVM r310591 MFC r322474 (by emaste): lld: Add `-z muldefs` option. Obtained from: LLVM r310757 MFC r322740: Upgrade our copies of clang, llvm, lld and libc++ to r311219 from the upstream release_50 branch. MFC r322855: Upgrade our copies of clang, llvm, lldb and compiler-rt to r311606 from the upstream release_50 branch. As of this version, lib/msun's trig test should also work correctly again (see bug 220989 for more information). PR: 220989 MFC r323112: Upgrade our copies of clang, llvm, lldb and compiler-rt to r312293 from the upstream release_50 branch. This corresponds to 5.0.0 rc4. As of this version, the cad/stepcode port should now compile in a more reasonable time on i386 (see bug 221836 for more information). PR: 221836 MFC r323245: Upgrade our copies of clang, llvm, lld, lldb, compiler-rt and libc++ to 5.0.0 release (upstream r312559). Release notes for llvm, clang and lld will be available here soon: <http://releases.llvm.org/5.0.0/docs/ReleaseNotes.html> <http://releases.llvm.org/5.0.0/tools/clang/docs/ReleaseNotes.html> <http://releases.llvm.org/5.0.0/tools/lld/docs/ReleaseNotes.html> Relnotes: yes
Diffstat (limited to 'contrib/llvm/tools/clang/lib/Lex/Lexer.cpp')
-rw-r--r--contrib/llvm/tools/clang/lib/Lex/Lexer.cpp199
1 files changed, 125 insertions, 74 deletions
diff --git a/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp b/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
index 6025a66..61bcef8 100644
--- a/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
+++ b/contrib/llvm/tools/clang/lib/Lex/Lexer.cpp
@@ -19,6 +19,7 @@
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Lex/LiteralSupport.h"
#include "clang/Lex/Preprocessor.h"
+#include "clang/Lex/PreprocessorOptions.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/Compiler.h"
@@ -43,6 +44,8 @@ using namespace clang;
/// isObjCAtKeyword - Return true if we have an ObjC keyword identifier.
bool Token::isObjCAtKeyword(tok::ObjCKeywordKind objcKey) const {
+ if (isAnnotation())
+ return false;
if (IdentifierInfo *II = getIdentifierInfo())
return II->getObjCKeywordID() == objcKey;
return false;
@@ -50,6 +53,8 @@ bool Token::isObjCAtKeyword(tok::ObjCKeywordKind objcKey) const {
/// getObjCKeywordID - Return the ObjC keyword kind.
tok::ObjCKeywordKind Token::getObjCKeywordID() const {
+ if (isAnnotation())
+ return tok::objc_not_keyword;
IdentifierInfo *specId = getIdentifierInfo();
return specId ? specId->getObjCKeywordID() : tok::objc_not_keyword;
}
@@ -452,6 +457,29 @@ bool Lexer::getRawToken(SourceLocation Loc, Token &Result,
return false;
}
+/// 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 = StrData;
+ while (LexStart != BufStart) {
+ if (LexStart[0] == '\n' || LexStart[0] == '\r') {
+ ++LexStart;
+ break;
+ }
+
+ --LexStart;
+ }
+ return LexStart;
+}
+
static SourceLocation getBeginningOfFileToken(SourceLocation Loc,
const SourceManager &SM,
const LangOptions &LangOpts) {
@@ -467,27 +495,15 @@ static SourceLocation getBeginningOfFileToken(SourceLocation Loc,
// Back up from the current location until we hit the beginning of a line
// (or the buffer). We'll relex from that point.
- const char *BufStart = Buffer.data();
- if (LocInfo.second >= Buffer.size())
- return Loc;
-
- const char *StrData = BufStart+LocInfo.second;
- if (StrData[0] == '\n' || StrData[0] == '\r')
+ const char *StrData = Buffer.data() + LocInfo.second;
+ const char *LexStart = findBeginningOfLine(Buffer, LocInfo.second);
+ if (!LexStart || LexStart == StrData)
return Loc;
-
- const char *LexStart = StrData;
- while (LexStart != BufStart) {
- if (LexStart[0] == '\n' || LexStart[0] == '\r') {
- ++LexStart;
- break;
- }
-
- --LexStart;
- }
// Create a lexer starting at the beginning of this token.
SourceLocation LexerStartLoc = Loc.getLocWithOffset(-LocInfo.second);
- Lexer TheLexer(LexerStartLoc, LangOpts, BufStart, LexStart, Buffer.end());
+ Lexer TheLexer(LexerStartLoc, LangOpts, Buffer.data(), LexStart,
+ Buffer.end());
TheLexer.SetCommentRetentionState(true);
// Lex tokens until we find the token that contains the source location.
@@ -535,8 +551,6 @@ namespace {
enum PreambleDirectiveKind {
PDK_Skipped,
- PDK_StartIf,
- PDK_EndIf,
PDK_Unknown
};
@@ -559,8 +573,6 @@ std::pair<unsigned, bool> Lexer::ComputePreamble(StringRef Buffer,
bool InPreprocessorDirective = false;
Token TheTok;
- Token IfStartTok;
- unsigned IfCount = 0;
SourceLocation ActiveCommentLoc;
unsigned MaxLineOffset = 0;
@@ -643,33 +655,18 @@ std::pair<unsigned, bool> Lexer::ComputePreamble(StringRef Buffer,
.Case("sccs", PDK_Skipped)
.Case("assert", PDK_Skipped)
.Case("unassert", PDK_Skipped)
- .Case("if", PDK_StartIf)
- .Case("ifdef", PDK_StartIf)
- .Case("ifndef", PDK_StartIf)
+ .Case("if", PDK_Skipped)
+ .Case("ifdef", PDK_Skipped)
+ .Case("ifndef", PDK_Skipped)
.Case("elif", PDK_Skipped)
.Case("else", PDK_Skipped)
- .Case("endif", PDK_EndIf)
+ .Case("endif", PDK_Skipped)
.Default(PDK_Unknown);
switch (PDK) {
case PDK_Skipped:
continue;
- case PDK_StartIf:
- if (IfCount == 0)
- IfStartTok = HashTok;
-
- ++IfCount;
- continue;
-
- case PDK_EndIf:
- // Mismatched #endif. The preamble ends here.
- if (IfCount == 0)
- break;
-
- --IfCount;
- continue;
-
case PDK_Unknown:
// We don't know what this directive is; stop at the '#'.
break;
@@ -690,16 +687,13 @@ std::pair<unsigned, bool> Lexer::ComputePreamble(StringRef Buffer,
} while (true);
SourceLocation End;
- if (IfCount)
- End = IfStartTok.getLocation();
- else if (ActiveCommentLoc.isValid())
+ if (ActiveCommentLoc.isValid())
End = ActiveCommentLoc; // don't truncate a decl comment.
else
End = TheTok.getLocation();
return std::make_pair(End.getRawEncoding() - StartLoc.getRawEncoding(),
- IfCount? IfStartTok.isAtStartOfLine()
- : TheTok.isAtStartOfLine());
+ TheTok.isAtStartOfLine());
}
/// AdvanceToTokenCharacter - Given a location that specifies the start of a
@@ -1038,6 +1032,27 @@ bool Lexer::isIdentifierBodyChar(char c, const LangOptions &LangOpts) {
return isIdentifierBody(c, LangOpts.DollarIdents);
}
+StringRef Lexer::getIndentationForLine(SourceLocation Loc,
+ const SourceManager &SM) {
+ if (Loc.isInvalid() || Loc.isMacroID())
+ return "";
+ std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(Loc);
+ if (LocInfo.first.isInvalid())
+ return "";
+ bool Invalid = false;
+ StringRef Buffer = SM.getBufferData(LocInfo.first, &Invalid);
+ if (Invalid)
+ return "";
+ const char *Line = findBeginningOfLine(Buffer, LocInfo.second);
+ if (!Line)
+ return "";
+ StringRef Rest = Buffer.substr(Line - Buffer.data());
+ size_t NumWhitespaceChars = Rest.find_first_not_of(" \t");
+ return NumWhitespaceChars == StringRef::npos
+ ? ""
+ : Rest.take_front(NumWhitespaceChars);
+}
+
//===----------------------------------------------------------------------===//
// Diagnostics forwarding code.
//===----------------------------------------------------------------------===//
@@ -1171,6 +1186,8 @@ const char *Lexer::SkipEscapedNewLines(const char *P) {
// If not a trigraph for escape, bail out.
if (P[1] != '?' || P[2] != '/')
return P;
+ // FIXME: Take LangOpts into account; the language might not
+ // support trigraphs.
AfterEscape = P+3;
} else {
return P;
@@ -1282,12 +1299,6 @@ Slash:
Size += EscapedNewLineSize;
Ptr += EscapedNewLineSize;
- // If the char that we finally got was a \n, then we must have had
- // something like \<newline><newline>. We don't want to consume the
- // second newline.
- if (*Ptr == '\n' || *Ptr == '\r' || *Ptr == '\0')
- return ' ';
-
// Use slow version to accumulate a correct size field.
return getCharAndSizeSlow(Ptr, Size, Tok);
}
@@ -1338,12 +1349,6 @@ Slash:
Size += EscapedNewLineSize;
Ptr += EscapedNewLineSize;
- // If the char that we finally got was a \n, then we must have had
- // something like \<newline><newline>. We don't want to consume the
- // second newline.
- if (*Ptr == '\n' || *Ptr == '\r' || *Ptr == '\0')
- return ' ';
-
// Use slow version to accumulate a correct size field.
return getCharAndSizeSlowNoWarn(Ptr, Size, LangOpts);
}
@@ -2070,8 +2075,11 @@ bool Lexer::SkipLineComment(Token &Result, const char *CurPtr,
// Scan over the body of the comment. The common case, when scanning, is that
// the comment contains normal ascii characters with nothing interesting in
// them. As such, optimize for this case with the inner loop.
+ //
+ // This loop terminates with CurPtr pointing at the newline (or end of buffer)
+ // character that ends the line comment.
char C;
- do {
+ while (true) {
C = *CurPtr;
// Skip over characters in the fast loop.
while (C != 0 && // Potentially EOF.
@@ -2088,10 +2096,12 @@ bool Lexer::SkipLineComment(Token &Result, const char *CurPtr,
HasSpace = true;
}
- if (*EscapePtr == '\\') // Escaped newline.
+ if (*EscapePtr == '\\')
+ // Escaped newline.
CurPtr = EscapePtr;
else if (EscapePtr[0] == '/' && EscapePtr[-1] == '?' &&
- EscapePtr[-2] == '?') // Trigraph-escaped newline.
+ EscapePtr[-2] == '?' && LangOpts.Trigraphs)
+ // Trigraph-escaped newline.
CurPtr = EscapePtr-2;
else
break; // This is a newline, we're done.
@@ -2140,9 +2150,9 @@ bool Lexer::SkipLineComment(Token &Result, const char *CurPtr,
}
}
- if (CurPtr == BufferEnd+1) {
- --CurPtr;
- break;
+ if (C == '\r' || C == '\n' || CurPtr == BufferEnd + 1) {
+ --CurPtr;
+ break;
}
if (C == '\0' && isCodeCompletionPoint(CurPtr-1)) {
@@ -2150,8 +2160,7 @@ bool Lexer::SkipLineComment(Token &Result, const char *CurPtr,
cutOffLexing();
return false;
}
-
- } while (C != '\n' && C != '\r');
+ }
// Found but did not consume the newline. Notify comment handlers about the
// comment unless we're in a #if 0 block.
@@ -2490,6 +2499,7 @@ void Lexer::ReadToEndOfLine(SmallVectorImpl<char> *Result) {
break;
}
// FALL THROUGH.
+ LLVM_FALLTHROUGH;
case '\r':
case '\n':
// Okay, we found the end of the line. First, back up past the \0, \r, \n.
@@ -2540,6 +2550,11 @@ bool Lexer::LexEndOfFile(Token &Result, const char *CurPtr) {
return true;
}
+ if (PP->isRecordingPreamble() && PP->isInPrimaryFile()) {
+ PP->setRecordedPreambleConditionalStack(ConditionalStack);
+ ConditionalStack.clear();
+ }
+
// Issue diagnostics for unterminated #if and missing newline.
// If we are in a #if directive, emit an error.
@@ -2722,6 +2737,37 @@ bool Lexer::HandleEndOfConflictMarker(const char *CurPtr) {
return false;
}
+static const char *findPlaceholderEnd(const char *CurPtr,
+ const char *BufferEnd) {
+ if (CurPtr == BufferEnd)
+ return nullptr;
+ BufferEnd -= 1; // Scan until the second last character.
+ for (; CurPtr != BufferEnd; ++CurPtr) {
+ if (CurPtr[0] == '#' && CurPtr[1] == '>')
+ return CurPtr + 2;
+ }
+ return nullptr;
+}
+
+bool Lexer::lexEditorPlaceholder(Token &Result, const char *CurPtr) {
+ assert(CurPtr[-1] == '<' && CurPtr[0] == '#' && "Not a placeholder!");
+ if (!PP || !PP->getPreprocessorOpts().LexEditorPlaceholders || LexingRawMode)
+ return false;
+ const char *End = findPlaceholderEnd(CurPtr + 1, BufferEnd);
+ if (!End)
+ return false;
+ const char *Start = CurPtr - 1;
+ if (!LangOpts.AllowEditorPlaceholders)
+ Diag(Start, diag::err_placeholder_in_source);
+ Result.startToken();
+ FormTokenWithChars(Result, End, tok::raw_identifier);
+ Result.setRawIdentifierData(Start);
+ PP->LookUpIdentifierInfo(Result);
+ Result.setFlag(Token::IsEditorPlaceholder);
+ BufferPtr = End;
+ return true;
+}
+
bool Lexer::isCodeCompletionPoint(const char *CurPtr) const {
if (PP && PP->isCodeCompletionEnabled()) {
SourceLocation Loc = FileLoc.getLocWithOffset(CurPtr-BufferStart);
@@ -3203,6 +3249,7 @@ LexNextToken:
return LexCharConstant(Result, ConsumeChar(CurPtr, SizeTmp, Result),
tok::wide_char_constant);
// FALL THROUGH, treating L like the start of an identifier.
+ LLVM_FALLTHROUGH;
// C99 6.4.2: Identifiers.
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
@@ -3479,6 +3526,8 @@ LexNextToken:
} else if (LangOpts.Digraphs && Char == '%') { // '<%' -> '{'
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::l_brace;
+ } else if (Char == '#' && lexEditorPlaceholder(Result, CurPtr)) {
+ return true;
} else {
Kind = tok::less;
}
@@ -3603,17 +3652,19 @@ LexNextToken:
// UCNs (C99 6.4.3, C++11 [lex.charset]p2)
case '\\':
- if (uint32_t CodePoint = tryReadUCN(CurPtr, BufferPtr, &Result)) {
- if (CheckUnicodeWhitespace(Result, CodePoint, CurPtr)) {
- if (SkipWhitespace(Result, CurPtr, TokAtPhysicalStartOfLine))
- return true; // KeepWhitespaceMode
+ if (!LangOpts.AsmPreprocessor) {
+ if (uint32_t CodePoint = tryReadUCN(CurPtr, BufferPtr, &Result)) {
+ if (CheckUnicodeWhitespace(Result, CodePoint, CurPtr)) {
+ if (SkipWhitespace(Result, CurPtr, TokAtPhysicalStartOfLine))
+ return true; // KeepWhitespaceMode
+
+ // We only saw whitespace, so just try again with this lexer.
+ // (We manually eliminate the tail call to avoid recursion.)
+ goto LexNextToken;
+ }
- // We only saw whitespace, so just try again with this lexer.
- // (We manually eliminate the tail call to avoid recursion.)
- goto LexNextToken;
+ return LexUnicode(Result, CodePoint, CurPtr);
}
-
- return LexUnicode(Result, CodePoint, CurPtr);
}
Kind = tok::unknown;
OpenPOWER on IntegriCloud