1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
|
/*
* 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. Source code file.
Author: Mark E. Davis, 1994.
Rev History: Rick McGowan, fixes & updates May 2001.
Sept 2001: fixed const & error conditions per
mods suggested by S. Parent & A. Lillich.
June 2002: Tim Dodd added detection and handling of incomplete
source sequences, enhanced error detection, added casts
to eliminate compiler warnings.
July 2003: slight mods to back out aggressive FFFE detection.
Jan 2004: updated switches in from-UTF8 conversions.
Oct 2004: updated to use UNI_MAX_LEGAL_UTF32 in UTF-32 conversions.
See the header file "ConvertUTF.h" for complete documentation.
------------------------------------------------------------------------ */
#include "ConvertUTF.h"
#ifdef CVTUTF_DEBUG
#include <stdio.h>
#endif
namespace replxx {
#define UNI_SUR_HIGH_START (UTF32)0xD800
#define UNI_SUR_LOW_END (UTF32)0xDFFF
/* --------------------------------------------------------------------- */
/*
* Index into the table below with the first byte of a UTF-8 sequence to
* get the number of trailing bytes that are supposed to follow it.
* Note that *legal* UTF-8 values can't have 4 or 5-bytes. The table is
* left as-is for anyone who may want to do such conversion, which was
* allowed in earlier algorithms.
*/
static const char trailingBytesForUTF8[256] = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
};
/*
* Magic values subtracted from a buffer value during UTF8 conversion.
* This table contains as many values as there might be trailing bytes
* in a UTF-8 sequence.
*/
static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL,
0x03C82080UL, 0xFA082080UL, 0x82082080UL };
/*
* Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
* into the first byte, depending on how many bytes follow. There are
* as many entries in this table as there are UTF-8 sequence types.
* (I.e., one byte sequence, two byte... etc.). Remember that sequencs
* for *legal* UTF-8 will be 4 or fewer bytes total.
*/
static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
/* --------------------------------------------------------------------- */
/* The interface converts a whole buffer to avoid function-call overhead.
* Constants have been gathered. Loops & conditionals have been removed as
* much as possible for efficiency, in favor of drop-through switches.
* (See "Note A" at the bottom of the file for equivalent code.)
* If your compiler supports it, the "isLegalUTF8" call can be turned
* into an inline function.
*/
/* --------------------------------------------------------------------- */
/*
* Utility routine to tell whether a sequence of bytes is legal UTF-8.
* This must be called with the length pre-determined by the first byte.
* If not calling this from ConvertUTF8to*, then the length can be set by:
* length = trailingBytesForUTF8[*source]+1;
* and the sequence is illegal right away if there aren't that many bytes
* available.
* If presented with a length > 4, this returns false. The Unicode
* definition of UTF-8 goes up to 4-byte sequences.
*/
static bool isLegalUTF8(const UTF8 *source, int length) {
UTF8 a;
const UTF8 *srcptr = source+length;
switch (length) {
default: return false;
/* Everything else falls through when "true"... */
case 4: { if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false; } /* fall through */
case 3: { if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false; } /* fall through */
case 2: {
if ((a = (*--srcptr)) > 0xBF) return false;
switch (*source) {
/* no fall-through in this inner switch */
case 0xE0: if (a < 0xA0) return false; break;
case 0xED: if (a > 0x9F) return false; break;
case 0xF0: if (a < 0x90) return false; break;
case 0xF4: if (a > 0x8F) return false; break;
default: if (a < 0x80) return false;
}
} /* fall through */
case 1: { if (*source >= 0x80 && *source < 0xC2) return false; } /* fall through */
}
if (*source > 0xF4) return false;
return true;
}
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF32toUTF8 (
const UTF32** sourceStart, const UTF32* sourceEnd,
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
ConversionResult result = conversionOK;
const UTF32* source = *sourceStart;
UTF8* target = *targetStart;
while (source < sourceEnd) {
UTF32 ch;
unsigned short bytesToWrite = 0;
const UTF32 byteMask = 0xBF;
const UTF32 byteMark = 0x80;
ch = *source++;
if (flags == strictConversion ) {
/* UTF-16 surrogate values are illegal in UTF-32 */
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
--source; /* return to the illegal value itself */
result = sourceIllegal;
break;
}
}
/*
* Figure out how many bytes the result will require. Turn any
* illegally large UTF32 things (> Plane 17) into replacement chars.
*/
if (ch < (UTF32)0x80) { bytesToWrite = 1;
} else if (ch < (UTF32)0x800) { bytesToWrite = 2;
} else if (ch < (UTF32)0x10000) { bytesToWrite = 3;
} else if (ch <= UNI_MAX_LEGAL_UTF32) { bytesToWrite = 4;
} else { bytesToWrite = 3;
ch = UNI_REPLACEMENT_CHAR;
result = sourceIllegal;
}
target += bytesToWrite;
if (target > targetEnd) {
--source; /* Back up source pointer! */
target -= bytesToWrite; result = targetExhausted; break;
}
switch (bytesToWrite) { /* note: everything falls through. */
case 4: { *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6; } /* fall through */
case 3: { *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6; } /* fall through */
case 2: { *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6; } /* fall through */
case 1: { *--target = (UTF8) (ch | firstByteMark[bytesToWrite]); } /* fall through */
}
target += bytesToWrite;
}
*sourceStart = source;
*targetStart = target;
return result;
}
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF8toUTF32 (
const UTF8** sourceStart, const UTF8* sourceEnd,
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
ConversionResult result = conversionOK;
const UTF8* source = *sourceStart;
UTF32* target = *targetStart;
while (source < sourceEnd) {
UTF32 ch = 0;
unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
if (source + extraBytesToRead >= sourceEnd) {
result = sourceExhausted; break;
}
/* Do this check whether lenient or strict */
if (! isLegalUTF8(source, extraBytesToRead+1)) {
result = sourceIllegal;
break;
}
/*
* The cases all fall through. See "Note A" below.
*/
switch (extraBytesToRead) {
case 5: { ch += *source++; ch <<= 6; } /* fall through */
case 4: { ch += *source++; ch <<= 6; } /* fall through */
case 3: { ch += *source++; ch <<= 6; } /* fall through */
case 2: { ch += *source++; ch <<= 6; } /* fall through */
case 1: { ch += *source++; ch <<= 6; } /* fall through */
case 0: { ch += *source++; } /* fall through */
}
ch -= offsetsFromUTF8[extraBytesToRead];
if (target >= targetEnd) {
source -= (extraBytesToRead+1); /* Back up the source pointer! */
result = targetExhausted; break;
}
if (ch <= UNI_MAX_LEGAL_UTF32) {
/*
* UTF-16 surrogate values are illegal in UTF-32, and anything
* over Plane 17 (> 0x10FFFF) is illegal.
*/
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
if (flags == strictConversion) {
source -= (extraBytesToRead+1); /* return to the illegal value itself */
result = sourceIllegal;
break;
} else {
*target++ = UNI_REPLACEMENT_CHAR;
}
} else {
*target++ = ch;
}
} else { /* i.e., ch > UNI_MAX_LEGAL_UTF32 */
result = sourceIllegal;
*target++ = UNI_REPLACEMENT_CHAR;
}
}
*sourceStart = source;
*targetStart = target;
return result;
}
}
/* ---------------------------------------------------------------------
Note A.
The fall-through switches in UTF-8 reading code save a
temp variable, some decrements & conditionals. The switches
are equivalent to the following loop:
{
int tmpBytesToRead = extraBytesToRead+1;
do {
ch += *source++;
--tmpBytesToRead;
if (tmpBytesToRead) ch <<= 6;
} while (tmpBytesToRead > 0);
}
In UTF-8 writing code, the switches on "bytesToWrite" are
similarly unrolled loops.
--------------------------------------------------------------------- */
|
