6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-06-23 17:24:48 +00:00
Code Issues Projects Releases Wiki Activity

[Support] Add a Unicode conversion wrapper from UTF16 to UTF8

Browse Source 
This is to support parsing UTF16 response files in LLVM/lib/Option for
lld and clang.

Reviewers: hans

Differential Revision: http://llvm-reviews.chandlerc.com/D1138

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186426 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Reid Kleckner
2013-07-16 17:14:33 +00:00
parent 5a5ebb7f9f
commit 06c847e83e
4 changed files with 143 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
include/llvm/Support/ConvertUTF.h
View File

@ -87,8 +87,8 @@
------------------------------------------------------------------------ */
#ifndef CLANG_BASIC_CONVERTUTF_H
#define CLANG_BASIC_CONVERTUTF_H
#ifndef LLVM_SUPPORT_CONVERTUTF_H
#define LLVM_SUPPORT_CONVERTUTF_H
/* ---------------------------------------------------------------------
The following 4 definitions are compiler-specific.
@ -112,6 +112,9 @@ typedef unsigned char Boolean; /* 0 or 1 */
#define UNI_MAX_UTF8_BYTES_PER_CODE_POINT 4
#define UNI_UTF16_BYTE_ORDER_MARK_NATIVE 0xFEFF
#define UNI_UTF16_BYTE_ORDER_MARK_SWAPPED 0xFFFE
typedef enum {
conversionOK, /* conversion successful */
sourceExhausted, /* partial character in source, but hit end */
@ -165,6 +168,7 @@ unsigned getNumBytesForUTF8(UTF8 firstByte);
/*************************************************************************/
/* Below are LLVM-specific wrappers of the functions above. */
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/StringRef.h"
namespace llvm {
@ -219,6 +223,22 @@ static inline ConversionResult convertUTF8Sequence(const UTF8 **source,
return sourceExhausted;
return ConvertUTF8toUTF32(source, *source + size, &target, target + 1, flags);
}
/**
* Returns true if a blob of text starts with a UTF-16 big or little endian byte
* order mark.
*/
bool hasUTF16ByteOrderMark(ArrayRef<char> SrcBytes);
/**
* Converts a stream of raw bytes assumed to be UTF16 into a UTF8 std::string.
*
* \param [in] SrcBytes A buffer of what is assumed to be UTF-16 encoded text.
* \param [out] Out Converted UTF-8 is stored here on success.
* \returns true on success
*/
bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out);
} /* end namespace llvm */
#endif