From: Corentin Jabot Date: Fri, 17 Jun 2022 14:23:41 +0000 (+0200) Subject: [Clang] Add a warning on invalid UTF-8 in comments. X-Git-Tag: upstream/15.0.7~2549 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=e3dc56805f1029dd5959e4c69196a287961afb8d;p=platform%2Fupstream%2Fllvm.git [Clang] Add a warning on invalid UTF-8 in comments. Introduce an off-by default `-Winvalid-utf8` warning that detects invalid UTF-8 code units sequences in comments. Invalid UTF-8 in other places is already diagnosed, as that cannot appear in identifiers and other grammar constructs. The warning is off by default as its likely to be somewhat disruptive otherwise. This warning allows clang to conform to the yet-to be approved WG21 "P2295R5 Support for UTF-8 as a portable source file encoding" paper. Reviewed By: aaron.ballman, #clang-language-wg Differential Revision: https://reviews.llvm.org/D128059 --- diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst index 0f542e0..c50e1b8 100644 --- a/clang/docs/ReleaseNotes.rst +++ b/clang/docs/ReleaseNotes.rst @@ -279,6 +279,8 @@ Improvements to Clang's diagnostics unevaluated operands of a ``typeid`` expression, as they are now modeled correctly in the CFG. This fixes `Issue 21668 `_. +- Added ``-Winvalid-utf8`` which diagnoses invalid UTF-8 code unit sequences in + comments. Non-comprehensive list of changes in this release ------------------------------------------------- @@ -576,7 +578,7 @@ AST Matchers - Added ``forEachTemplateArgument`` matcher which creates a match every time a ``templateArgument`` matches the matcher supplied to it. - + - Added ``objcStringLiteral`` matcher which matches ObjectiveC String literal expressions. diff --git a/clang/include/clang/Basic/DiagnosticLexKinds.td b/clang/include/clang/Basic/DiagnosticLexKinds.td index ac86076..38ee022 100644 --- a/clang/include/clang/Basic/DiagnosticLexKinds.td +++ b/clang/include/clang/Basic/DiagnosticLexKinds.td @@ -113,6 +113,8 @@ def warn_four_char_character_literal : Warning< // Unicode and UCNs def err_invalid_utf8 : Error< "source file is not valid UTF-8">; +def warn_invalid_utf8_in_comment : Extension< + "invalid UTF-8 in comment">, InGroup>; def err_character_not_allowed : Error< "unexpected character ">; def err_character_not_allowed_identifier : Error< diff --git a/clang/lib/Lex/Lexer.cpp b/clang/lib/Lex/Lexer.cpp index 6820057..351e518 100644 --- a/clang/lib/Lex/Lexer.cpp +++ b/clang/lib/Lex/Lexer.cpp @@ -2392,13 +2392,37 @@ bool Lexer::SkipLineComment(Token &Result, const char *CurPtr, // // This loop terminates with CurPtr pointing at the newline (or end of buffer) // character that ends the line comment. + + // C++23 [lex.phases] p1 + // Diagnose invalid UTF-8 if the corresponding warning is enabled, emitting a + // diagnostic only once per entire ill-formed subsequence to avoid + // emiting to many diagnostics (see http://unicode.org/review/pr-121.html). + bool UnicodeDecodingAlreadyDiagnosed = false; + char C; while (true) { C = *CurPtr; // Skip over characters in the fast loop. - while (C != 0 && // Potentially EOF. - C != '\n' && C != '\r') // Newline or DOS-style newline. + while (isASCII(C) && C != 0 && // Potentially EOF. + C != '\n' && C != '\r') { // Newline or DOS-style newline. C = *++CurPtr; + UnicodeDecodingAlreadyDiagnosed = false; + } + + if (!isASCII(C)) { + unsigned Length = llvm::getUTF8SequenceSize( + (const llvm::UTF8 *)CurPtr, (const llvm::UTF8 *)BufferEnd); + if (Length == 0) { + if (!UnicodeDecodingAlreadyDiagnosed && !isLexingRawMode()) + Diag(CurPtr, diag::warn_invalid_utf8_in_comment); + UnicodeDecodingAlreadyDiagnosed = true; + ++CurPtr; + } else { + UnicodeDecodingAlreadyDiagnosed = false; + CurPtr += Length; + } + continue; + } const char *NextLine = CurPtr; if (C != 0) { @@ -2665,6 +2689,12 @@ bool Lexer::SkipBlockComment(Token &Result, const char *CurPtr, if (C == '/') C = *CurPtr++; + // C++23 [lex.phases] p1 + // Diagnose invalid UTF-8 if the corresponding warning is enabled, emitting a + // diagnostic only once per entire ill-formed subsequence to avoid + // emiting to many diagnostics (see http://unicode.org/review/pr-121.html). + bool UnicodeDecodingAlreadyDiagnosed = false; + while (true) { // Skip over all non-interesting characters until we find end of buffer or a // (probably ending) '/' character. @@ -2673,14 +2703,24 @@ bool Lexer::SkipBlockComment(Token &Result, const char *CurPtr, // doesn't check for '\0'. !(PP && PP->getCodeCompletionFileLoc() == FileLoc)) { // While not aligned to a 16-byte boundary. - while (C != '/' && ((intptr_t)CurPtr & 0x0F) != 0) + while (C != '/' && (intptr_t)CurPtr % 16 != 0) { + if (!isASCII(C)) { + CurPtr--; + goto MultiByteUTF8; + } C = *CurPtr++; - + } if (C == '/') goto FoundSlash; #ifdef __SSE2__ __m128i Slashes = _mm_set1_epi8('/'); - while (CurPtr+16 <= BufferEnd) { + while (CurPtr + 16 < BufferEnd) { + int Mask = _mm_movemask_epi8(*(const __m128i *)CurPtr); + if (LLVM_UNLIKELY(Mask != 0)) { + CurPtr += llvm::countTrailingZeros(Mask); + goto MultiByteUTF8; + } + // look for slashes int cmp = _mm_movemask_epi8(_mm_cmpeq_epi8(*(const __m128i*)CurPtr, Slashes)); if (cmp != 0) { @@ -2693,21 +2733,41 @@ bool Lexer::SkipBlockComment(Token &Result, const char *CurPtr, CurPtr += 16; } #elif __ALTIVEC__ + __vector unsigned char LongUTF = {0x80, 0x80, 0x80, 0x80, 0x80, 0x80, + 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, + 0x80, 0x80, 0x80, 0x80}; __vector unsigned char Slashes = { '/', '/', '/', '/', '/', '/', '/', '/', '/', '/', '/', '/', '/', '/', '/', '/' }; - while (CurPtr + 16 <= BufferEnd && - !vec_any_eq(*(const __vector unsigned char *)CurPtr, Slashes)) + while (CurPtr + 16 < BufferEnd) { + if (LLVM_UNLIKELY( + vec_any_ge(*(const __vector unsigned char *)CurPtr, LongUTF))) + goto MultiByteUTF8; + if (vec_any_eq(*(const __vector unsigned char *)CurPtr, Slashes)) { + C = *CurPtr++; + break; + } CurPtr += 16; + } + #else - // Scan for '/' quickly. Many block comments are very large. - while (CurPtr[0] != '/' && - CurPtr[1] != '/' && - CurPtr[2] != '/' && - CurPtr[3] != '/' && - CurPtr+4 < BufferEnd) { - CurPtr += 4; + while (CurPtr + 16 <= BufferEnd) { + bool HasNonASCII = false; + for (unsigned I = 0; I < 16; ++I) { + HasNonASCII |= !isASCII(CurPtr[I]); + } + + if (LLVM_UNLIKELY(HasNonASCII)) + goto MultiByteUTF8; + + bool HasSlash = false; + for (unsigned I = 0; I < 16; ++I) { + HasSlash |= CurPtr[I] == '/'; + } + if (HasSlash) + break; + CurPtr += 16; } #endif @@ -2715,9 +2775,28 @@ bool Lexer::SkipBlockComment(Token &Result, const char *CurPtr, C = *CurPtr++; } - // Loop to scan the remainder. - while (C != '/' && C != '\0') - C = *CurPtr++; + // Loop to scan the remainder, warning on invalid UTF-8 + // if the corresponding warning is enabled, emitting a diagnostic only once + // per sequence that cannot be decoded. + while (C != '/' && C != '\0') { + if (isASCII(C)) { + UnicodeDecodingAlreadyDiagnosed = false; + C = *CurPtr++; + continue; + } + MultiByteUTF8: + unsigned Length = llvm::getUTF8SequenceSize( + (const llvm::UTF8 *)CurPtr, (const llvm::UTF8 *)BufferEnd); + if (Length == 0) { + if (!UnicodeDecodingAlreadyDiagnosed && !isLexingRawMode()) + Diag(CurPtr, diag::warn_invalid_utf8_in_comment); + UnicodeDecodingAlreadyDiagnosed = true; + C = *CurPtr++; + continue; + } + UnicodeDecodingAlreadyDiagnosed = false; + C = *(CurPtr += Length - 1); + } if (C == '/') { FoundSlash: diff --git a/clang/test/Lexer/comment-invalid-utf8.c b/clang/test/Lexer/comment-invalid-utf8.c new file mode 100644 index 0000000..b8bf551 --- /dev/null +++ b/clang/test/Lexer/comment-invalid-utf8.c @@ -0,0 +1,27 @@ +// RUN: %clang_cc1 -fsyntax-only %s -Winvalid-utf8 -verify=expected +// RUN: %clang_cc1 -fsyntax-only %s -verify=nowarn +// nowarn-no-diagnostics + +// This file is purposefully encoded as windows-1252 +// be careful when modifying. + +//€ +// expected-warning@-1 {{invalid UTF-8 in comment}} + +// € ‚ƒ„…†‡ˆ‰ Š ‹ Œ Ž +// expected-warning@-1 6{{invalid UTF-8 in comment}} + +/*€*/ +// expected-warning@-1 {{invalid UTF-8 in comment}} + +/*€ ‚ƒ„…†‡ˆ‰ Š ‹ Œ Ž*/ +// expected-warning@-1 6{{invalid UTF-8 in comment}} + +/* +€ +*/ +// expected-warning@-2 {{invalid UTF-8 in comment}} + +// abcd +// €abcd +// expected-warning@-1 {{invalid UTF-8 in comment}} diff --git a/llvm/include/llvm/Support/ConvertUTF.h b/llvm/include/llvm/Support/ConvertUTF.h index 662f3ac..1e05cfe 100644 --- a/llvm/include/llvm/Support/ConvertUTF.h +++ b/llvm/include/llvm/Support/ConvertUTF.h @@ -181,6 +181,8 @@ Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd); Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd); +unsigned getUTF8SequenceSize(const UTF8 *source, const UTF8 *sourceEnd); + unsigned getNumBytesForUTF8(UTF8 firstByte); /*************************************************************************/ diff --git a/llvm/lib/Support/ConvertUTF.cpp b/llvm/lib/Support/ConvertUTF.cpp index e24a918..c494110 100644 --- a/llvm/lib/Support/ConvertUTF.cpp +++ b/llvm/lib/Support/ConvertUTF.cpp @@ -417,6 +417,16 @@ Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) { return isLegalUTF8(source, length); } +/* + * Exported function to return the size of the first utf-8 code unit sequence, + * Or 0 if the sequence is not valid; + */ +unsigned getUTF8SequenceSize(const UTF8 *source, const UTF8 *sourceEnd) { + int length = trailingBytesForUTF8[*source] + 1; + return (length > sourceEnd - source && isLegalUTF8(source, length)) ? length + : 0; +} + /* --------------------------------------------------------------------- */ static unsigned