6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-11-01 15:11:24 +00:00
Code Issues Projects Releases Wiki Activity

Have the UTF conversion wrappers append a null terminator.

Browse Source 
This is especially useful for the UTF8 -> UTF16 direction, since
there is no equivalent of llvm::SmallString<> for wide characters.
This means that anyone who wants a null terminated string is forced
to manually push and pop their own null terminator.

Reviewed by: Reid Kleckner.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227143 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Zachary Turner 2015-01-26 22:05:50 +00:00
parent 3ba85ab23a
commit b9a39da95e
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
lib/Support/ConvertUTFWrapper.cpp
View File

@ -109,8 +109,9 @@ bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out) {
if (Src[0] == UNI_UTF16_BYTE_ORDER_MARK_NATIVE)
Src++;
// Just allocate enough space up front. We'll shrink it later.
Out.resize(SrcBytes.size() * UNI_MAX_UTF8_BYTES_PER_CODE_POINT);
// Just allocate enough space up front. We'll shrink it later. Allocate
// enough that we can fit a null terminator without reallocating.
Out.resize(SrcBytes.size() * UNI_MAX_UTF8_BYTES_PER_CODE_POINT + 1);
UTF8 *Dst = reinterpret_cast<UTF8 *>(&Out[0]);
UTF8 *DstEnd = Dst + Out.size();
@ -124,6 +125,8 @@ bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out) {
}
Out.resize(reinterpret_cast<char *>(Dst) - &Out[0]);
Out.push_back(0);
Out.pop_back();
return true;
}
@ -140,8 +143,10 @@ bool convertUTF8ToUTF16String(StringRef SrcUTF8,
// Allocate the same number of UTF-16 code units as UTF-8 code units. Encoding
// as UTF-16 should always require the same amount or less code units than the
// UTF-8 encoding.
DstUTF16.resize(SrcUTF8.size());
// UTF-8 encoding. Allocate one extra byte for the null terminator though,
// so that someone calling DstUTF16.data() gets a null terminated string.
// We resize down later so we don't have to worry that this over allocates.
DstUTF16.resize(SrcUTF8.size()+1);
UTF16 *Dst = &DstUTF16[0];
UTF16 *DstEnd = Dst + DstUTF16.size();
@ -155,6 +160,8 @@ bool convertUTF8ToUTF16String(StringRef SrcUTF8,
}
DstUTF16.resize(Dst - &DstUTF16[0]);
DstUTF16.push_back(0);
DstUTF16.pop_back();
return true;
}