mirror of
https://github.com/zeek/zeek.git
synced 2025-10-02 06:38:20 +00:00
233 lines
9.2 KiB
C
233 lines
9.2 KiB
C
/*===--- ConvertUTF.h - Universal Character Names conversions ---------------===
|
|
*
|
|
* The LLVM Compiler Infrastructure
|
|
*
|
|
* This file is distributed under the University of Illinois Open Source
|
|
* License:
|
|
*
|
|
* University of Illinois/NCSA
|
|
* Open Source License
|
|
*
|
|
* Copyright (c) 2003-2014 University of Illinois at Urbana-Champaign.
|
|
* All rights reserved.
|
|
*
|
|
* Developed by:
|
|
*
|
|
* LLVM Team
|
|
*
|
|
* University of Illinois at Urbana-Champaign
|
|
*
|
|
* http://llvm.org
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person
|
|
* obtaining a copy of this software and associated documentation
|
|
* files (the "Software"), to deal with the Software without
|
|
* restriction, including without limitation the rights to use,
|
|
* copy, modify, merge, publish, distribute, sublicense, and/or
|
|
* sell copies of the Software, and to permit persons to whom the
|
|
* Software is furnished to do so, subject to the following
|
|
* conditions:
|
|
*
|
|
* * Redistributions of source code must retain the above
|
|
* copyright notice, this list of conditions and the
|
|
* following disclaimers.
|
|
*
|
|
* * Redistributions in binary form must reproduce the
|
|
* above copyright notice, this list of conditions and
|
|
* the following disclaimers in the documentation and/or
|
|
* other materials provided with the distribution.
|
|
*
|
|
* * Neither the names of the LLVM Team, University of
|
|
* Illinois at Urbana-Champaign, nor the names of its
|
|
* contributors may be used to endorse or promote
|
|
* products derived from this Software without specific
|
|
* prior written permission.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
|
|
* OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
* NONINFRINGEMENT. IN NO EVENT SHALL THE CONTRIBUTORS OR
|
|
* COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
|
|
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
|
|
* USE OR OTHER DEALINGS WITH THE SOFTWARE.
|
|
*
|
|
*==------------------------------------------------------------------------==*/
|
|
/*
|
|
* Copyright 2001-2004 Unicode, Inc.
|
|
*
|
|
* Disclaimer
|
|
*
|
|
* This source code is provided as is by Unicode, Inc. No claims are
|
|
* made as to fitness for any particular purpose. No warranties of any
|
|
* kind are expressed or implied. The recipient agrees to determine
|
|
* applicability of information provided. If this file has been
|
|
* purchased on magnetic or optical media from Unicode, Inc., the
|
|
* sole remedy for any claim will be exchange of defective media
|
|
* within 90 days of receipt.
|
|
*
|
|
* Limitations on Rights to Redistribute This Code
|
|
*
|
|
* Unicode, Inc. hereby grants the right to freely use the information
|
|
* supplied in this file in the creation of products supporting the
|
|
* Unicode Standard, and to make copies of this file in any form
|
|
* for internal or external distribution as long as this notice
|
|
* remains attached.
|
|
*/
|
|
|
|
/* ---------------------------------------------------------------------
|
|
|
|
Conversions between UTF32, UTF-16, and UTF-8. Header file.
|
|
|
|
Several funtions are included here, forming a complete set of
|
|
conversions between the three formats. UTF-7 is not included
|
|
here, but is handled in a separate source file.
|
|
|
|
Each of these routines takes pointers to input buffers and output
|
|
buffers. The input buffers are const.
|
|
|
|
Each routine converts the text between *sourceStart and sourceEnd,
|
|
putting the result into the buffer between *targetStart and
|
|
targetEnd. Note: the end pointers are *after* the last item: e.g.
|
|
*(sourceEnd - 1) is the last item.
|
|
|
|
!!! NOTE: The source and end pointers must be aligned properly !!!
|
|
|
|
The return result indicates whether the conversion was successful,
|
|
and if not, whether the problem was in the source or target buffers.
|
|
(Only the first encountered problem is indicated.)
|
|
|
|
After the conversion, *sourceStart and *targetStart are both
|
|
updated to point to the end of last text successfully converted in
|
|
the respective buffers.
|
|
|
|
Input parameters:
|
|
sourceStart - pointer to a pointer to the source buffer.
|
|
The contents of this are modified on return so that
|
|
it points at the next thing to be converted.
|
|
targetStart - similarly, pointer to pointer to the target buffer.
|
|
sourceEnd, targetEnd - respectively pointers to the ends of the
|
|
two buffers, for overflow checking only.
|
|
|
|
These conversion functions take a ConversionFlags argument. When this
|
|
flag is set to strict, both irregular sequences and isolated surrogates
|
|
will cause an error. When the flag is set to lenient, both irregular
|
|
sequences and isolated surrogates are converted.
|
|
|
|
Whether the flag is strict or lenient, all illegal sequences will cause
|
|
an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
|
|
or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
|
|
must check for illegal sequences.
|
|
|
|
When the flag is set to lenient, characters over 0x10FFFF are converted
|
|
to the replacement character; otherwise (when the flag is set to strict)
|
|
they constitute an error.
|
|
|
|
Output parameters:
|
|
The value "sourceIllegal" is returned from some routines if the input
|
|
sequence is malformed. When "sourceIllegal" is returned, the source
|
|
value will point to the illegal value that caused the problem. E.g.,
|
|
in UTF-8 when a sequence is malformed, it points to the start of the
|
|
malformed sequence.
|
|
|
|
Author: Mark E. Davis, 1994.
|
|
Rev History: Rick McGowan, fixes & updates May 2001.
|
|
Fixes & updates, Sept 2001.
|
|
|
|
------------------------------------------------------------------------ */
|
|
|
|
#pragma once
|
|
|
|
/* ---------------------------------------------------------------------
|
|
The following 4 definitions are compiler-specific.
|
|
The C standard does not guarantee that wchar_t has at least
|
|
16 bits, so wchar_t is no less portable than unsigned short!
|
|
All should be unsigned values to avoid sign extension during
|
|
bit mask & shift operations.
|
|
------------------------------------------------------------------------ */
|
|
|
|
typedef unsigned int UTF32; /* at least 32 bits */
|
|
typedef unsigned short UTF16; /* at least 16 bits */
|
|
typedef unsigned char UTF8; /* typically 8 bits */
|
|
typedef unsigned char Boolean; /* 0 or 1 */
|
|
|
|
/* Some fundamental constants */
|
|
#define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
|
|
#define UNI_MAX_BMP (UTF32)0x0000FFFF
|
|
#define UNI_MAX_UTF16 (UTF32)0x0010FFFF
|
|
#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
|
|
#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
|
|
|
|
#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 */
|
|
targetExhausted, /* insuff. room in target for conversion */
|
|
sourceIllegal /* source sequence is illegal/malformed */
|
|
} ConversionResult;
|
|
|
|
typedef enum {
|
|
strictConversion = 0,
|
|
lenientConversion
|
|
} ConversionFlags;
|
|
|
|
/* This is for C++ and does no harm in C */
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
ConversionResult ConvertUTF8toUTF16 (
|
|
const UTF8** sourceStart, const UTF8* sourceEnd,
|
|
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
|
|
|
|
/**
|
|
* Convert a partial UTF8 sequence to UTF32. If the sequence ends in an
|
|
* incomplete code unit sequence, returns \c sourceExhausted.
|
|
*/
|
|
ConversionResult ConvertUTF8toUTF32Partial(
|
|
const UTF8** sourceStart, const UTF8* sourceEnd,
|
|
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
|
|
|
|
/**
|
|
* Convert a partial UTF8 sequence to UTF32. If the sequence ends in an
|
|
* incomplete code unit sequence, returns \c sourceIllegal.
|
|
*/
|
|
ConversionResult ConvertUTF8toUTF32(
|
|
const UTF8** sourceStart, const UTF8* sourceEnd,
|
|
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
|
|
|
|
/* NOTE: The source and end pointers must be aligned properly. */
|
|
ConversionResult ConvertUTF16toUTF8 (
|
|
const UTF16** sourceStart, const UTF16* sourceEnd,
|
|
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
|
|
|
|
/* NOTE: The source and end pointers must be aligned properly. */
|
|
ConversionResult ConvertUTF32toUTF8 (
|
|
const UTF32** sourceStart, const UTF32* sourceEnd,
|
|
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
|
|
|
|
/* NOTE: The source and end pointers must be aligned properly. */
|
|
ConversionResult ConvertUTF16toUTF32 (
|
|
const UTF16** sourceStart, const UTF16* sourceEnd,
|
|
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
|
|
|
|
/* NOTE: The source and end pointers must be aligned properly. */
|
|
ConversionResult ConvertUTF32toUTF16 (
|
|
const UTF32** sourceStart, const UTF32* sourceEnd,
|
|
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
|
|
|
|
Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
|
|
|
|
Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd);
|
|
|
|
unsigned getNumBytesForUTF8(UTF8 firstByte);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
/* --------------------------------------------------------------------- */
|