Author: sstwcw Date: 2025-07-21T15:40:28Z New Revision: 12a3afe47d4e5fcc97eb44271c00ace7cc8e4ff2
URL: https://github.com/llvm/llvm-project/commit/12a3afe47d4e5fcc97eb44271c00ace7cc8e4ff2 DIFF: https://github.com/llvm/llvm-project/commit/12a3afe47d4e5fcc97eb44271c00ace7cc8e4ff2.diff LOG: [clang-format] Remove code related to trigraphs (#148640) When reviewing #147156, the reviewers pointed out that we didn't need to support the trigraph. The code never handled it right. In the debug build, this kind of input caused the assertion in the function `countLeadingWhitespace` to fail. The release build without assertions outputted `?` `?` `/` separated by spaces. ```C #define A ??/ int i; ``` This is because the code in `countLeadingWhitespace` assumed that the underlying lexer recognized the entire `??/` sequence as a single token. In fact, the lexer recognized it as 3 separate tokens. The flag to make the lexer recognize trigraphs was never enabled. This patch enables the flag in the underlying lexer. This way, the program now either turns the trigraph into a single `\` or removes it altogether if the line is short enough. There are operators like the `??=` in C#. So the flag is not enabled for all input languages. Instead the check for the token size is moved from the assert line into the if line. The problem was introduced by my own patch 370bee480139 from about 3 years ago. I added code to count the number of characters in the escape sequence probably just because the block of code used to have a comment saying someone should add the feature. Maybe I forgot to enable assertions when I ran the code. I found the problem because reviewing pull request 145243 made me look at the code again. Added: Modified: clang/lib/Format/FormatTokenLexer.cpp clang/unittests/Format/FormatTest.cpp Removed: ################################################################################ diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp index 49da3160daf50..3f4aa52a87d2e 100644 --- a/clang/lib/Format/FormatTokenLexer.cpp +++ b/clang/lib/Format/FormatTokenLexer.cpp @@ -1198,7 +1198,7 @@ void FormatTokenLexer::truncateToken(size_t NewLen) { /// Count the length of leading whitespace in a token. static size_t countLeadingWhitespace(StringRef Text) { // Basically counting the length matched by this regex. - // "^([\n\r\f\v \t]|(\\\\|\\?\\?/)[\n\r])+" + // "^([\n\r\f\v \t]|\\\\[\n\r])+" // Directly using the regex turned out to be slow. With the regex // version formatting all files in this directory took about 1.25 // seconds. This version took about 0.5 seconds. @@ -1222,13 +1222,6 @@ static size_t countLeadingWhitespace(StringRef Text) { break; // Splice found, consume it. Cur = Lookahead + 1; - } else if (Cur[0] == '?' && Cur[1] == '?' && Cur[2] == '/' && - (Cur[3] == '\n' || Cur[3] == '\r')) { - // Newlines can also be escaped by a '?' '?' '/' trigraph. By the way, the - // characters are quoted individually in this comment because if we write - // them together some compilers warn that we have a trigraph in the code. - assert(End - Cur >= 4); - Cur += 4; } else { break; } @@ -1300,22 +1293,16 @@ FormatToken *FormatTokenLexer::getNextToken() { Style.TabWidth - (Style.TabWidth ? Column % Style.TabWidth : 0); break; case '\\': - case '?': - case '/': - // The text was entirely whitespace when this loop was entered. Thus - // this has to be an escape sequence. - assert(Text.substr(i, 4) == "\?\?/\r" || - Text.substr(i, 4) == "\?\?/\n" || - (i >= 1 && (Text.substr(i - 1, 4) == "\?\?/\r" || - Text.substr(i - 1, 4) == "\?\?/\n")) || - (i >= 2 && (Text.substr(i - 2, 4) == "\?\?/\r" || - Text.substr(i - 2, 4) == "\?\?/\n")) || - (Text[i] == '\\' && [&]() -> bool { - size_t j = i + 1; - while (j < Text.size() && isHorizontalWhitespace(Text[j])) - ++j; - return j < Text.size() && (Text[j] == '\n' || Text[j] == '\r'); - }())); + // The code preceding the loop and in the countLeadingWhitespace + // function guarantees that Text is entirely whitespace, not including + // comments but including escaped newlines. So the character shows up, + // then it has to be in an escape sequence. + assert([&]() -> bool { + size_t j = i + 1; + while (j < Text.size() && isHorizontalWhitespace(Text[j])) + ++j; + return j < Text.size() && (Text[j] == '\n' || Text[j] == '\r'); + }()); InEscape = true; break; default: diff --git a/clang/unittests/Format/FormatTest.cpp b/clang/unittests/Format/FormatTest.cpp index 30f965651a8cf..7e3d2a9d8aa95 100644 --- a/clang/unittests/Format/FormatTest.cpp +++ b/clang/unittests/Format/FormatTest.cpp @@ -6681,6 +6681,17 @@ TEST_F(FormatTest, EscapedNewlines) { " int x(int a);", AlignLeft); + // Escaped with a trigraph. The program just has to avoid crashing. + verifyNoCrash("#define A \?\?/\n" + "int i;\?\?/\n" + " int j;"); + verifyNoCrash("#define A \?\?/\r\n" + "int i;\?\?/\r\n" + " int j;"); + verifyNoCrash("#define A \?\?/\n" + "int i;", + getGoogleStyle(FormatStyle::LK_CSharp)); + // CRLF line endings verifyFormat("#define A \\\r\n int i; \\\r\n int j;", "#define A \\\r\nint i;\\\r\n int j;", Narrow); _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
