kevcadieux created this revision.
Herald added a project: All.
kevcadieux requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.
This change fixes a clang-format unit test failure introduced by D124748
<https://reviews.llvm.org/D124748>. The `countLeadingWhitespace` function was
calling `isspace` with values that could fall outside the valid input range.
The valid input range for `isspace` is unsigned 0-255. Values outside this
range produce undefined behavior, which on Windows manifests as an assertion
being raised in the debug runtime libraries. `countLeadingWhitespace` was
calling `isspace` with a signed char that could produce a negative value if the
underlying byte's value was 128 or above, which can happen for non-ASCII
encodings. The fix is to use `StringRef`'s `bytes_begin` and `bytes_end`
iterators to read the values as unsigned chars instead.
This bug can be reproduced by building the `check-clang-unit` target with a
DEBUG configuration under Windows. This change is already covered by existing
unit tests.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D128786
Files:
clang/lib/Format/FormatTokenLexer.cpp
Index: clang/lib/Format/FormatTokenLexer.cpp
===================================================================
--- clang/lib/Format/FormatTokenLexer.cpp
+++ clang/lib/Format/FormatTokenLexer.cpp
@@ -864,8 +864,10 @@
// 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.
- const char *Cur = Text.begin();
- while (Cur < Text.end()) {
+ const unsigned char *const Begin = Text.bytes_begin();
+ const unsigned char *const End = Text.bytes_end();
+ const unsigned char *Cur = Begin;
+ while (Cur < End) {
if (isspace(Cur[0])) {
++Cur;
} else if (Cur[0] == '\\' && (Cur[1] == '\n' || Cur[1] == '\r')) {
@@ -874,20 +876,20 @@
// The source has a null byte at the end. So the end of the entire input
// isn't reached yet. Also the lexer doesn't break apart an escaped
// newline.
- assert(Text.end() - Cur >= 2);
+ assert(End - Cur >= 2);
Cur += 2;
} 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(Text.end() - Cur >= 4);
+ assert(End - Cur >= 4);
Cur += 4;
} else {
break;
}
}
- return Cur - Text.begin();
+ return Cur - Begin;
}
FormatToken *FormatTokenLexer::getNextToken() {
Index: clang/lib/Format/FormatTokenLexer.cpp
===================================================================
--- clang/lib/Format/FormatTokenLexer.cpp
+++ clang/lib/Format/FormatTokenLexer.cpp
@@ -864,8 +864,10 @@
// 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.
- const char *Cur = Text.begin();
- while (Cur < Text.end()) {
+ const unsigned char *const Begin = Text.bytes_begin();
+ const unsigned char *const End = Text.bytes_end();
+ const unsigned char *Cur = Begin;
+ while (Cur < End) {
if (isspace(Cur[0])) {
++Cur;
} else if (Cur[0] == '\\' && (Cur[1] == '\n' || Cur[1] == '\r')) {
@@ -874,20 +876,20 @@
// The source has a null byte at the end. So the end of the entire input
// isn't reached yet. Also the lexer doesn't break apart an escaped
// newline.
- assert(Text.end() - Cur >= 2);
+ assert(End - Cur >= 2);
Cur += 2;
} 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(Text.end() - Cur >= 4);
+ assert(End - Cur >= 4);
Cur += 4;
} else {
break;
}
}
- return Cur - Text.begin();
+ return Cur - Begin;
}
FormatToken *FormatTokenLexer::getNextToken() {
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
