diff options
| author | Richard Smith <richard-llvm@metafoo.co.uk> | 2012-03-08 21:59:28 +0000 |
|---|---|---|
| committer | Richard Smith <richard-llvm@metafoo.co.uk> | 2012-03-08 21:59:28 +0000 |
| commit | 49d517467c3dcd2c67e8a6c740ba5160e37625f7 (patch) | |
| tree | a41241684cb33d87947bea6ae6a0c7caf07a8933 /lib/Basic/ConvertUTF.c | |
| parent | 188158db29f50443b6e412f2a40c800b2669c957 (diff) | |
When checking the encoding of an 8-bit string literal, don't just check the
first codepoint! Also, don't reject empty raw string literals for spurious
"encoding" issues. Also, don't rely on undefined behavior in ConvertUTF.c.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@152344 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Basic/ConvertUTF.c')
| -rw-r--r-- | lib/Basic/ConvertUTF.c | 22 |
1 files changed, 19 insertions, 3 deletions
diff --git a/lib/Basic/ConvertUTF.c b/lib/Basic/ConvertUTF.c index b3fa916934..e1970039e1 100644 --- a/lib/Basic/ConvertUTF.c +++ b/lib/Basic/ConvertUTF.c @@ -387,7 +387,7 @@ static Boolean isLegalUTF8(const UTF8 *source, int length) { */ Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) { int length = trailingBytesForUTF8[*source]+1; - if (source+length > sourceEnd) { + if (length > sourceEnd - source) { return false; } return isLegalUTF8(source, length); @@ -395,6 +395,22 @@ Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) { /* --------------------------------------------------------------------- */ +/* + * Exported function to return whether a UTF-8 string is legal or not. + * This is not used here; it's just exported. + */ +Boolean isLegalUTF8String(const UTF8 *source, const UTF8 *sourceEnd) { + while (source != sourceEnd) { + int length = trailingBytesForUTF8[*source] + 1; + if (length > sourceEnd - source || !isLegalUTF8(source, length)) + return false; + source += length; + } + return true; +} + +/* --------------------------------------------------------------------- */ + ConversionResult ConvertUTF8toUTF16 ( const UTF8** sourceStart, const UTF8* sourceEnd, UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) { @@ -404,7 +420,7 @@ ConversionResult ConvertUTF8toUTF16 ( while (source < sourceEnd) { UTF32 ch = 0; unsigned short extraBytesToRead = trailingBytesForUTF8[*source]; - if (source + extraBytesToRead >= sourceEnd) { + if (extraBytesToRead >= sourceEnd - source) { result = sourceExhausted; break; } /* Do this check whether lenient or strict */ @@ -477,7 +493,7 @@ ConversionResult ConvertUTF8toUTF32 ( while (source < sourceEnd) { UTF32 ch = 0; unsigned short extraBytesToRead = trailingBytesForUTF8[*source]; - if (source + extraBytesToRead >= sourceEnd) { + if (extraBytesToRead >= sourceEnd - source) { result = sourceExhausted; break; } /* Do this check whether lenient or strict */ |