When a bad UTF-8 encoding or bogus escape sequence is encountered in a
string literal, produce a diagnostic pointing at the erroneous character
range, not at the start of the literal.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@163459 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Basic/ConvertUTFWrapper.cpp b/lib/Basic/ConvertUTFWrapper.cpp
index a1b3f7f..6be3828 100644
--- a/lib/Basic/ConvertUTFWrapper.cpp
+++ b/lib/Basic/ConvertUTFWrapper.cpp
@@ -13,16 +13,19 @@
namespace clang {
bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
- char *&ResultPtr) {
+ char *&ResultPtr, const UTF8 *&ErrorPtr) {
assert(WideCharWidth == 1 || WideCharWidth == 2 || WideCharWidth == 4);
ConversionResult result = conversionOK;
// Copy the character span over.
if (WideCharWidth == 1) {
- if (!isLegalUTF8String(reinterpret_cast<const UTF8*>(Source.begin()),
- reinterpret_cast<const UTF8*>(Source.end())))
+ const UTF8 *Pos = reinterpret_cast<const UTF8*>(Source.begin());
+ if (!isLegalUTF8String(&Pos, reinterpret_cast<const UTF8*>(Source.end()))) {
result = sourceIllegal;
- memcpy(ResultPtr, Source.data(), Source.size());
- ResultPtr += Source.size();
+ ErrorPtr = Pos;
+ } else {
+ memcpy(ResultPtr, Source.data(), Source.size());
+ ResultPtr += Source.size();
+ }
} else if (WideCharWidth == 2) {
const UTF8 *sourceStart = (const UTF8*)Source.data();
// FIXME: Make the type of the result buffer correct instead of
@@ -34,6 +37,8 @@
&targetStart, targetStart + 2*Source.size(), flags);
if (result == conversionOK)
ResultPtr = reinterpret_cast<char*>(targetStart);
+ else
+ ErrorPtr = sourceStart;
} else if (WideCharWidth == 4) {
const UTF8 *sourceStart = (const UTF8*)Source.data();
// FIXME: Make the type of the result buffer correct instead of
@@ -45,6 +50,8 @@
&targetStart, targetStart + 4*Source.size(), flags);
if (result == conversionOK)
ResultPtr = reinterpret_cast<char*>(targetStart);
+ else
+ ErrorPtr = sourceStart;
}
assert((result != targetExhausted)
&& "ConvertUTF8toUTFXX exhausted target buffer");
@@ -67,4 +74,3 @@
}
} // end namespace clang
-