annotate include/llvm/Support/ConvertUTF.h @ 148:63bd29f05246

merged
author Shinji KONO <kono@ie.u-ryukyu.ac.jp>
date Wed, 14 Aug 2019 19:46:37 +0900
parents c2174574ed3a
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
1 /*===--- ConvertUTF.h - Universal Character Names conversions ---------------===
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
2 *
147
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
3 * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
4 * See https://llvm.org/LICENSE.txt for license information.
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
5 * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
6 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
7 *==------------------------------------------------------------------------==*/
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
8 /*
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
9 * Copyright 2001-2004 Unicode, Inc.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
10 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
11 * Disclaimer
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
12 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
13 * This source code is provided as is by Unicode, Inc. No claims are
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
14 * made as to fitness for any particular purpose. No warranties of any
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
15 * kind are expressed or implied. The recipient agrees to determine
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
16 * applicability of information provided. If this file has been
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
17 * purchased on magnetic or optical media from Unicode, Inc., the
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
18 * sole remedy for any claim will be exchange of defective media
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
19 * within 90 days of receipt.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
20 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
21 * Limitations on Rights to Redistribute This Code
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
22 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
23 * Unicode, Inc. hereby grants the right to freely use the information
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
24 * supplied in this file in the creation of products supporting the
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
25 * Unicode Standard, and to make copies of this file in any form
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
26 * for internal or external distribution as long as this notice
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
27 * remains attached.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
28 */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
29
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
30 /* ---------------------------------------------------------------------
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
31
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
32 Conversions between UTF32, UTF-16, and UTF-8. Header file.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
33
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
34 Several funtions are included here, forming a complete set of
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
35 conversions between the three formats. UTF-7 is not included
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
36 here, but is handled in a separate source file.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
37
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
38 Each of these routines takes pointers to input buffers and output
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
39 buffers. The input buffers are const.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
40
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
41 Each routine converts the text between *sourceStart and sourceEnd,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
42 putting the result into the buffer between *targetStart and
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
43 targetEnd. Note: the end pointers are *after* the last item: e.g.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
44 *(sourceEnd - 1) is the last item.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
45
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
46 The return result indicates whether the conversion was successful,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
47 and if not, whether the problem was in the source or target buffers.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
48 (Only the first encountered problem is indicated.)
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
49
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
50 After the conversion, *sourceStart and *targetStart are both
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
51 updated to point to the end of last text successfully converted in
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
52 the respective buffers.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
53
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
54 Input parameters:
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
55 sourceStart - pointer to a pointer to the source buffer.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
56 The contents of this are modified on return so that
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
57 it points at the next thing to be converted.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
58 targetStart - similarly, pointer to pointer to the target buffer.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
59 sourceEnd, targetEnd - respectively pointers to the ends of the
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
60 two buffers, for overflow checking only.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
61
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
62 These conversion functions take a ConversionFlags argument. When this
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
63 flag is set to strict, both irregular sequences and isolated surrogates
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
64 will cause an error. When the flag is set to lenient, both irregular
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
65 sequences and isolated surrogates are converted.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
66
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
67 Whether the flag is strict or lenient, all illegal sequences will cause
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
68 an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
69 or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
70 must check for illegal sequences.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
71
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
72 When the flag is set to lenient, characters over 0x10FFFF are converted
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
73 to the replacement character; otherwise (when the flag is set to strict)
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
74 they constitute an error.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
75
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
76 Output parameters:
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
77 The value "sourceIllegal" is returned from some routines if the input
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
78 sequence is malformed. When "sourceIllegal" is returned, the source
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
79 value will point to the illegal value that caused the problem. E.g.,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
80 in UTF-8 when a sequence is malformed, it points to the start of the
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
81 malformed sequence.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
82
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
83 Author: Mark E. Davis, 1994.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
84 Rev History: Rick McGowan, fixes & updates May 2001.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
85 Fixes & updates, Sept 2001.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
86
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
87 ------------------------------------------------------------------------ */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
88
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
89 #ifndef LLVM_SUPPORT_CONVERTUTF_H
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
90 #define LLVM_SUPPORT_CONVERTUTF_H
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
91
121
803732b1fca8 LLVM 5.0
kono
parents: 120
diff changeset
92 #include <cstddef>
120
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
93 #include <string>
147
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
94 #include <system_error>
120
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
95
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
96 // Wrap everything in namespace llvm so that programs can link with llvm and
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
97 // their own version of the unicode libraries.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
98
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
99 namespace llvm {
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
100
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
101 /* ---------------------------------------------------------------------
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
102 The following 4 definitions are compiler-specific.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
103 The C standard does not guarantee that wchar_t has at least
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
104 16 bits, so wchar_t is no less portable than unsigned short!
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
105 All should be unsigned values to avoid sign extension during
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
106 bit mask & shift operations.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
107 ------------------------------------------------------------------------ */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
108
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
109 typedef unsigned int UTF32; /* at least 32 bits */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
110 typedef unsigned short UTF16; /* at least 16 bits */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
111 typedef unsigned char UTF8; /* typically 8 bits */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
112 typedef unsigned char Boolean; /* 0 or 1 */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
113
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
114 /* Some fundamental constants */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
115 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
116 #define UNI_MAX_BMP (UTF32)0x0000FFFF
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
117 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
118 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
119 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
120
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
121 #define UNI_MAX_UTF8_BYTES_PER_CODE_POINT 4
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
122
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
123 #define UNI_UTF16_BYTE_ORDER_MARK_NATIVE 0xFEFF
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
124 #define UNI_UTF16_BYTE_ORDER_MARK_SWAPPED 0xFFFE
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
125
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
126 typedef enum {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
127 conversionOK, /* conversion successful */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
128 sourceExhausted, /* partial character in source, but hit end */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
129 targetExhausted, /* insuff. room in target for conversion */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
130 sourceIllegal /* source sequence is illegal/malformed */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
131 } ConversionResult;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
132
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
133 typedef enum {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
134 strictConversion = 0,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
135 lenientConversion
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
136 } ConversionFlags;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
137
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
138 ConversionResult ConvertUTF8toUTF16 (
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
139 const UTF8** sourceStart, const UTF8* sourceEnd,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
140 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
141
77
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
142 /**
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
143 * Convert a partial UTF8 sequence to UTF32. If the sequence ends in an
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
144 * incomplete code unit sequence, returns \c sourceExhausted.
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
145 */
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
146 ConversionResult ConvertUTF8toUTF32Partial(
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
147 const UTF8** sourceStart, const UTF8* sourceEnd,
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
148 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
149
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
150 /**
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
151 * Convert a partial UTF8 sequence to UTF32. If the sequence ends in an
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
152 * incomplete code unit sequence, returns \c sourceIllegal.
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
153 */
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
154 ConversionResult ConvertUTF8toUTF32(
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
155 const UTF8** sourceStart, const UTF8* sourceEnd,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
156 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
157
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
158 ConversionResult ConvertUTF16toUTF8 (
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
159 const UTF16** sourceStart, const UTF16* sourceEnd,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
160 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
161
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
162 ConversionResult ConvertUTF32toUTF8 (
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
163 const UTF32** sourceStart, const UTF32* sourceEnd,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
164 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
165
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
166 ConversionResult ConvertUTF16toUTF32 (
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
167 const UTF16** sourceStart, const UTF16* sourceEnd,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
168 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
169
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
170 ConversionResult ConvertUTF32toUTF16 (
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
171 const UTF32** sourceStart, const UTF32* sourceEnd,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
172 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
173
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
174 Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
175
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
176 Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
177
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
178 unsigned getNumBytesForUTF8(UTF8 firstByte);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
179
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
180 /*************************************************************************/
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
181 /* Below are LLVM-specific wrappers of the functions above. */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
182
120
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
183 template <typename T> class ArrayRef;
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
184 template <typename T> class SmallVectorImpl;
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
185 class StringRef;
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
186
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
187 /**
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
188 * Convert an UTF8 StringRef to UTF8, UTF16, or UTF32 depending on
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
189 * WideCharWidth. The converted data is written to ResultPtr, which needs to
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
190 * point to at least WideCharWidth * (Source.Size() + 1) bytes. On success,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
191 * ResultPtr will point one after the end of the copied string. On failure,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
192 * ResultPtr will not be changed, and ErrorPtr will be set to the location of
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
193 * the first character which could not be converted.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
194 * \return true on success.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
195 */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
196 bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
197 char *&ResultPtr, const UTF8 *&ErrorPtr);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
198
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
199 /**
120
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
200 * Converts a UTF-8 StringRef to a std::wstring.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
201 * \return true on success.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
202 */
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
203 bool ConvertUTF8toWide(llvm::StringRef Source, std::wstring &Result);
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
204
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
205 /**
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
206 * Converts a UTF-8 C-string to a std::wstring.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
207 * \return true on success.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
208 */
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
209 bool ConvertUTF8toWide(const char *Source, std::wstring &Result);
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
210
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
211 /**
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
212 * Converts a std::wstring to a UTF-8 encoded std::string.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
213 * \return true on success.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
214 */
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
215 bool convertWideToUTF8(const std::wstring &Source, std::string &Result);
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
216
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
217
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
218 /**
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
219 * Convert an Unicode code point to UTF8 sequence.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
220 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
221 * \param Source a Unicode code point.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
222 * \param [in,out] ResultPtr pointer to the output buffer, needs to be at least
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
223 * \c UNI_MAX_UTF8_BYTES_PER_CODE_POINT bytes. On success \c ResultPtr is
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
224 * updated one past end of the converted sequence.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
225 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
226 * \returns true on success.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
227 */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
228 bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
229
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
230 /**
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
231 * Convert the first UTF8 sequence in the given source buffer to a UTF32
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
232 * code point.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
233 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
234 * \param [in,out] source A pointer to the source buffer. If the conversion
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
235 * succeeds, this pointer will be updated to point to the byte just past the
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
236 * end of the converted sequence.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
237 * \param sourceEnd A pointer just past the end of the source buffer.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
238 * \param [out] target The converted code
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
239 * \param flags Whether the conversion is strict or lenient.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
240 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
241 * \returns conversionOK on success
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
242 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
243 * \sa ConvertUTF8toUTF32
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
244 */
121
803732b1fca8 LLVM 5.0
kono
parents: 120
diff changeset
245 inline ConversionResult convertUTF8Sequence(const UTF8 **source,
803732b1fca8 LLVM 5.0
kono
parents: 120
diff changeset
246 const UTF8 *sourceEnd,
803732b1fca8 LLVM 5.0
kono
parents: 120
diff changeset
247 UTF32 *target,
803732b1fca8 LLVM 5.0
kono
parents: 120
diff changeset
248 ConversionFlags flags) {
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
249 if (*source == sourceEnd)
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
250 return sourceExhausted;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
251 unsigned size = getNumBytesForUTF8(**source);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
252 if ((ptrdiff_t)size > sourceEnd - *source)
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
253 return sourceExhausted;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
254 return ConvertUTF8toUTF32(source, *source + size, &target, target + 1, flags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
255 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
256
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
257 /**
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
258 * Returns true if a blob of text starts with a UTF-16 big or little endian byte
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
259 * order mark.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
260 */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
261 bool hasUTF16ByteOrderMark(ArrayRef<char> SrcBytes);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
262
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
263 /**
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
264 * Converts a stream of raw bytes assumed to be UTF16 into a UTF8 std::string.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
265 *
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
266 * \param [in] SrcBytes A buffer of what is assumed to be UTF-16 encoded text.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
267 * \param [out] Out Converted UTF-8 is stored here on success.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
268 * \returns true on success
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
269 */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
270 bool convertUTF16ToUTF8String(ArrayRef<char> SrcBytes, std::string &Out);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
271
83
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
272 /**
120
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
273 * Converts a UTF16 string into a UTF8 std::string.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
274 *
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
275 * \param [in] Src A buffer of UTF-16 encoded text.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
276 * \param [out] Out Converted UTF-8 is stored here on success.
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
277 * \returns true on success
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
278 */
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
279 bool convertUTF16ToUTF8String(ArrayRef<UTF16> Src, std::string &Out);
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
280
1172e4bd9c6f update 4.0.0
mir3636
parents: 83
diff changeset
281 /**
83
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
282 * Converts a UTF-8 string into a UTF-16 string with native endianness.
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
283 *
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
284 * \returns true on success
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
285 */
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
286 bool convertUTF8ToUTF16String(StringRef SrcUTF8,
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
287 SmallVectorImpl<UTF16> &DstUTF16);
60c9769439b8 LLVM 3.7
Tatsuki IHA <e125716@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
288
147
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
289 #if defined(_WIN32)
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
290 namespace sys {
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
291 namespace windows {
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
292 std::error_code UTF8ToUTF16(StringRef utf8, SmallVectorImpl<wchar_t> &utf16);
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
293 /// Convert to UTF16 from the current code page used in the system
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
294 std::error_code CurCPToUTF16(StringRef utf8, SmallVectorImpl<wchar_t> &utf16);
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
295 std::error_code UTF16ToUTF8(const wchar_t *utf16, size_t utf16_len,
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
296 SmallVectorImpl<char> &utf8);
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
297 /// Convert from UTF16 to the current code page used in the system
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
298 std::error_code UTF16ToCurCP(const wchar_t *utf16, size_t utf16_len,
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
299 SmallVectorImpl<char> &utf8);
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
300 } // namespace windows
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
301 } // namespace sys
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
302 #endif
c2174574ed3a LLVM 10
Shinji KONO <kono@ie.u-ryukyu.ac.jp>
parents: 121
diff changeset
303
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
304 } /* end namespace llvm */
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
305
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
306 #endif