File: utf8.c

package info (click to toggle)
tidy 20080116cvs-2
  • links: PTS
  • area: main
  • in suites: lenny
  • size: 7,296 kB
  • ctags: 3,259
  • sloc: ansic: 30,069; sh: 9,060; xml: 317; makefile: 41
file content (539 lines) | stat: -rw-r--r-- 15,431 bytes parent folder | download | duplicates (6)
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
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
/* utf8.c -- convert characters to/from UTF-8

  (c) 1998-2007 (W3C) MIT, ERCIM, Keio University
  See tidy.h for the copyright notice.

  CVS Info :

    $Author: arnaud02 $ 
    $Date: 2007/05/30 16:47:31 $ 
    $Revision: 1.10 $ 

  Uses public interfaces to abstract input source and output
  sink, which may be user supplied or either FILE* or memory
  based Tidy implementations.  Encoding support is uniform
  regardless of I/O mechanism.

  Note, UTF-8 encoding, by itself, does not affect the actual
  "codepoints" of the underlying character encoding.  In the
  cases of ASCII, Latin1, Unicode (16-bit, BMP), these all 
  refer to ISO-10646 "codepoints".  For anything else, they
  refer to some other "codepoint" set.

  Put another way, UTF-8 is a variable length method to 
  represent any non-negative integer value.  The glyph 
  that a integer value represents is unchanged and defined
  externally (e.g. by ISO-10646, Big5, Win1252, MacRoman,
  Latin2-9, and so on).

  Put still another way, UTF-8 is more of a _transfer_ encoding
  than a _character_ encoding, per se.
*/

#include "tidy.h"
#include "forward.h"
#include "utf8.h"

/* 
UTF-8 encoding/decoding functions
Return # of bytes in UTF-8 sequence; result < 0 if illegal sequence

Also see below for UTF-16 encoding/decoding functions

References :

1) UCS Transformation Format 8 (UTF-8):
ISO/IEC 10646-1:1996 Amendment 2 or ISO/IEC 10646-1:2000 Annex D
<http://anubis.dkuug.dk/JTC1/SC2/WG2/docs/n1335>
<http://www.cl.cam.ac.uk/~mgk25/ucs/ISO-10646-UTF-8.html>

Table 4 - Mapping from UCS-4 to UTF-8

2) Unicode standards:
<http://www.unicode.org/unicode/standard/standard.html>

3) Legal UTF-8 byte sequences:
<http://www.unicode.org/unicode/uni2errata/UTF-8_Corrigendum.html>

Code point          1st byte    2nd byte    3rd byte    4th byte
----------          --------    --------    --------    --------
U+0000..U+007F      00..7F
U+0080..U+07FF      C2..DF      80..BF
U+0800..U+0FFF      E0          A0..BF      80..BF
U+1000..U+FFFF      E1..EF      80..BF      80..BF
U+10000..U+3FFFF    F0          90..BF      80..BF      80..BF
U+40000..U+FFFFF    F1..F3      80..BF      80..BF      80..BF
U+100000..U+10FFFF  F4          80..8F      80..BF      80..BF

The definition of UTF-8 in Annex D of ISO/IEC 10646-1:2000 also
allows for the use of five- and six-byte sequences to encode
characters that are outside the range of the Unicode character
set; those five- and six-byte sequences are illegal for the use
of UTF-8 as a transformation of Unicode characters. ISO/IEC 10646
does not allow mapping of unpaired surrogates, nor U+FFFE and U+FFFF
(but it does allow other noncharacters).

4) RFC 2279: UTF-8, a transformation format of ISO 10646:
<http://www.ietf.org/rfc/rfc2279.txt>

5) UTF-8 and Unicode FAQ:
<http://www.cl.cam.ac.uk/~mgk25/unicode.html>

6) Markus Kuhn's UTF-8 decoder stress test file:
<http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt>

7) UTF-8 Demo:
<http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-demo.txt>

8) UTF-8 Sampler:
<http://www.columbia.edu/kermit/utf8.html>

9) Transformation Format for 16 Planes of Group 00 (UTF-16):
ISO/IEC 10646-1:1996 Amendment 1 or ISO/IEC 10646-1:2000 Annex C
<http://anubis.dkuug.dk/JTC1/SC2/WG2/docs/n2005/n2005.pdf>
<http://www.cl.cam.ac.uk/~mgk25/ucs/ISO-10646-UTF-16.html>

10) RFC 2781: UTF-16, an encoding of ISO 10646:
<http://www.ietf.org/rfc/rfc2781.txt>

11) UTF-16 invalid surrogate pairs:
<http://www.unicode.org/unicode/faq/utf_bom.html#16>

UTF-16       UTF-8          UCS-4
D83F DFF*    F0 9F BF B*    0001FFF*
D87F DFF*    F0 AF BF B*    0002FFF*
D8BF DFF*    F0 BF BF B*    0003FFF*
D8FF DFF*    F1 8F BF B*    0004FFF*
D93F DFF*    F1 9F BF B*    0005FFF*
D97F DFF*    F1 AF BF B*    0006FFF*
                ...
DBBF DFF*    F3 BF BF B*    000FFFF*
DBFF DFF*    F4 8F BF B*    0010FFF*

* = E or F
                                   
1010  A
1011  B
1100  C
1101  D
1110  E
1111  F

*/

#define kNumUTF8Sequences        7
#define kMaxUTF8Bytes            4

#define kUTF8ByteSwapNotAChar    0xFFFE
#define kUTF8NotAChar            0xFFFF

#define kMaxUTF8FromUCS4         0x10FFFF

#define kUTF16SurrogatesBegin    0x10000
#define kMaxUTF16FromUCS4        0x10FFFF

/* UTF-16 surrogate pair areas */
#define kUTF16LowSurrogateBegin  0xD800
#define kUTF16LowSurrogateEnd    0xDBFF
#define kUTF16HighSurrogateBegin 0xDC00
#define kUTF16HighSurrogateEnd   0xDFFF


/* offsets into validUTF8 table below */
static const int offsetUTF8Sequences[kMaxUTF8Bytes + 1] =
{
    0, /* 1 byte */
    1, /* 2 bytes */
    2, /* 3 bytes */
    4, /* 4 bytes */
    kNumUTF8Sequences /* must be last */
};

static const struct validUTF8Sequence
{
     uint lowChar;
     uint highChar;
     int  numBytes;
     byte validBytes[8];
} validUTF8[kNumUTF8Sequences] =
{
/*   low       high   #bytes  byte 1      byte 2      byte 3      byte 4 */
    {0x0000,   0x007F,   1, {0x00, 0x7F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}},
    {0x0080,   0x07FF,   2, {0xC2, 0xDF, 0x80, 0xBF, 0x00, 0x00, 0x00, 0x00}},
    {0x0800,   0x0FFF,   3, {0xE0, 0xE0, 0xA0, 0xBF, 0x80, 0xBF, 0x00, 0x00}},
    {0x1000,   0xFFFF,   3, {0xE1, 0xEF, 0x80, 0xBF, 0x80, 0xBF, 0x00, 0x00}},
    {0x10000,  0x3FFFF,  4, {0xF0, 0xF0, 0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF}},
    {0x40000,  0xFFFFF,  4, {0xF1, 0xF3, 0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF}},
    {0x100000, 0x10FFFF, 4, {0xF4, 0xF4, 0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF}} 
};

int TY_(DecodeUTF8BytesToChar)( uint* c, uint firstByte, ctmbstr successorBytes,
                                TidyInputSource* inp, int* count )
{
    byte tempbuf[10];
    byte *buf = &tempbuf[0];
    uint ch = 0, n = 0;
    int i, bytes = 0;
    Bool hasError = no;
    
    if ( successorBytes )
        buf = (byte*) successorBytes;
        
    /* special check if we have been passed an EOF char */
    if ( firstByte == EndOfStream )
    {
        /* at present */
        *c = firstByte;
        *count = 1;
        return 0;
    }

    ch = firstByte; /* first byte is passed in separately */
    
    if (ch <= 0x7F) /* 0XXX XXXX one byte */
    {
        n = ch;
        bytes = 1;
    }
    else if ((ch & 0xE0) == 0xC0)  /* 110X XXXX  two bytes */
    {
        n = ch & 31;
        bytes = 2;
    }
    else if ((ch & 0xF0) == 0xE0)  /* 1110 XXXX  three bytes */
    {
        n = ch & 15;
        bytes = 3;
    }
    else if ((ch & 0xF8) == 0xF0)  /* 1111 0XXX  four bytes */
    {
        n = ch & 7;
        bytes = 4;
    }
    else if ((ch & 0xFC) == 0xF8)  /* 1111 10XX  five bytes */
    {
        n = ch & 3;
        bytes = 5;
        hasError = yes;
    }
    else if ((ch & 0xFE) == 0xFC)  /* 1111 110X  six bytes */
    {
        n = ch & 1;
        bytes = 6;
        hasError = yes;
    }
    else
    {
        /* not a valid first byte of a UTF-8 sequence */
        n = ch;
        bytes = 1;
        hasError = yes;
    }

    /* successor bytes should have the form 10XX XXXX */

    /* If caller supplied buffer, use it.  Else see if caller
    ** supplied an input source, use that.
    */
    if ( successorBytes )
    {
        for ( i=0; i < bytes-1; ++i )
        {
            if ( !buf[i] || (buf[i] & 0xC0) != 0x80 )
            {
                hasError = yes;
                bytes = i+1;
                break;
            }
            n = (n << 6) | (buf[i] & 0x3F);
        }
    }
    else if ( inp )
    {
        for ( i=0; i < bytes-1 && !inp->eof(inp->sourceData); ++i )
        {
            int b = inp->getByte( inp->sourceData );
            buf[i] = (tmbchar) b;

            /* End of data or illegal successor byte value */
            if ( b == EOF || (buf[i] & 0xC0) != 0x80 )
            {
                hasError = yes;
                bytes = i+1;
                if ( b != EOF )
                    inp->ungetByte( inp->sourceData, buf[i] );
                break;
            }
            n = (n << 6) | (buf[i] & 0x3F);
        }
    }
    else if ( bytes > 1 )
    {
        hasError = yes;
        bytes = 1;
    }
    
    if (!hasError && ((n == kUTF8ByteSwapNotAChar) || (n == kUTF8NotAChar)))
        hasError = yes;
        
    if (!hasError && (n > kMaxUTF8FromUCS4))
        hasError = yes;

#if 0 /* Breaks Big5 D8 - DF */
    if (!hasError && (n >= kUTF16LowSurrogateBegin) && (n <= kUTF16HighSurrogateEnd))
        /* unpaired surrogates not allowed */
        hasError = yes;
#endif

    if (!hasError)
    {
        int lo, hi;
        
        lo = offsetUTF8Sequences[bytes - 1];
        hi = offsetUTF8Sequences[bytes] - 1;
        
        /* check for overlong sequences */
        if ((n < validUTF8[lo].lowChar) || (n > validUTF8[hi].highChar))
            hasError = yes;
        else
        {
            hasError = yes; /* assume error until proven otherwise */
        
            for (i = lo; i <= hi; i++)
            {
                int tempCount;
                byte theByte;
                
                for (tempCount = 0; tempCount < bytes; tempCount++)
                {
                    if (!tempCount)
                        theByte = (tmbchar) firstByte;
                    else
                        theByte = buf[tempCount - 1];
                        
                    if ( theByte >= validUTF8[i].validBytes[(tempCount * 2)] &&
                         theByte <= validUTF8[i].validBytes[(tempCount * 2) + 1] )
                        hasError = no;
                    if (hasError)
                        break;
                }
            }
        }
    }

#if 1 && defined(_DEBUG)
    if ( hasError )
    {
       /* debug */
       fprintf( stderr, "UTF-8 decoding error of %d bytes : ", bytes );
       fprintf( stderr, "0x%02x ", firstByte );
       for (i = 1; i < bytes; i++)
           fprintf( stderr, "0x%02x ", buf[i - 1] );
       fprintf( stderr, " = U+%04ulx\n", n );
    }
#endif

    *count = bytes;
    *c = n;
    if ( hasError )
        return -1;
    return 0;
}

int TY_(EncodeCharToUTF8Bytes)( uint c, tmbstr encodebuf,
                                TidyOutputSink* outp, int* count )
{
    byte tempbuf[10] = {0};
    byte* buf = &tempbuf[0];
    int bytes = 0;
    Bool hasError = no;
    
    if ( encodebuf )
        buf = (byte*) encodebuf;
        
    if (c <= 0x7F)  /* 0XXX XXXX one byte */
    {
        buf[0] = (tmbchar) c;
        bytes = 1;
    }
    else if (c <= 0x7FF)  /* 110X XXXX  two bytes */
    {
        buf[0] = (tmbchar) ( 0xC0 | (c >> 6) );
        buf[1] = (tmbchar) ( 0x80 | (c & 0x3F) );
        bytes = 2;
    }
    else if (c <= 0xFFFF)  /* 1110 XXXX  three bytes */
    {
        buf[0] = (tmbchar) (0xE0 | (c >> 12));
        buf[1] = (tmbchar) (0x80 | ((c >> 6) & 0x3F));
        buf[2] = (tmbchar) (0x80 | (c & 0x3F));
        bytes = 3;
        if ( c == kUTF8ByteSwapNotAChar || c == kUTF8NotAChar )
            hasError = yes;
#if 0 /* Breaks Big5 D8 - DF */
        else if ( c >= kUTF16LowSurrogateBegin && c <= kUTF16HighSurrogateEnd )
            /* unpaired surrogates not allowed */
            hasError = yes;
#endif
    }
    else if (c <= 0x1FFFFF)  /* 1111 0XXX  four bytes */
    {
        buf[0] = (tmbchar) (0xF0 | (c >> 18));
        buf[1] = (tmbchar) (0x80 | ((c >> 12) & 0x3F));
        buf[2] = (tmbchar) (0x80 | ((c >> 6) & 0x3F));
        buf[3] = (tmbchar) (0x80 | (c & 0x3F));
        bytes = 4;
        if (c > kMaxUTF8FromUCS4)
            hasError = yes;
    }
    else if (c <= 0x3FFFFFF)  /* 1111 10XX  five bytes */
    {
        buf[0] = (tmbchar) (0xF8 | (c >> 24));
        buf[1] = (tmbchar) (0x80 | (c >> 18));
        buf[2] = (tmbchar) (0x80 | ((c >> 12) & 0x3F));
        buf[3] = (tmbchar) (0x80 | ((c >> 6) & 0x3F));
        buf[4] = (tmbchar) (0x80 | (c & 0x3F));
        bytes = 5;
        hasError = yes;
    }
    else if (c <= 0x7FFFFFFF)  /* 1111 110X  six bytes */
    {
        buf[0] = (tmbchar) (0xFC | (c >> 30));
        buf[1] = (tmbchar) (0x80 | ((c >> 24) & 0x3F));
        buf[2] = (tmbchar) (0x80 | ((c >> 18) & 0x3F));
        buf[3] = (tmbchar) (0x80 | ((c >> 12) & 0x3F));
        buf[4] = (tmbchar) (0x80 | ((c >> 6) & 0x3F));
        buf[5] = (tmbchar) (0x80 | (c & 0x3F));
        bytes = 6;
        hasError = yes;
    }
    else
        hasError = yes;
        
    /* don't output invalid UTF-8 byte sequence to a stream */
    if ( !hasError && outp != NULL )
    {
        int ix;
        for ( ix=0; ix < bytes; ++ix )
          outp->putByte( outp->sinkData, buf[ix] );
    }

#if 1 && defined(_DEBUG)
    if ( hasError )
    {
        int i;
        fprintf( stderr, "UTF-8 encoding error for U+%x : ", c );
        for (i = 0; i < bytes; i++)
            fprintf( stderr, "0x%02x ", buf[i] );
        fprintf( stderr, "\n" );
    }
#endif
    
    *count = bytes;
    if (hasError)
        return -1;
    return 0;
}


/* return one less than the number of bytes used by the UTF-8 byte sequence */
/* str points to the UTF-8 byte sequence */
/* the Unicode char is returned in *ch */
uint TY_(GetUTF8)( ctmbstr str, uint *ch )
{
    uint n;
    int bytes;

    int err;
    
    bytes = 0;
    
    /* first byte "str[0]" is passed in separately from the */
    /* rest of the UTF-8 byte sequence starting at "str[1]" */
    err = TY_(DecodeUTF8BytesToChar)( &n, str[0], str+1, NULL, &bytes );
    if (err)
    {
#if 1 && defined(_DEBUG)
        fprintf(stderr, "pprint UTF-8 decoding error for U+%x : ", n);
#endif
        n = 0xFFFD; /* replacement char */
    }

    *ch = n;
    return bytes - 1;
}

/* store char c as UTF-8 encoded byte stream */
tmbstr TY_(PutUTF8)( tmbstr buf, uint c )
{
    int err, count = 0;
        
    err = TY_(EncodeCharToUTF8Bytes)( c, buf, NULL, &count );
    if (err)
    {
#if 1 && defined(_DEBUG)
        fprintf(stderr, "pprint UTF-8 encoding error for U+%x : ", c);
#endif
        /* replacement char 0xFFFD encoded as UTF-8 */
        buf[0] = (byte) 0xEF;
        buf[1] = (byte) 0xBF;
        buf[2] = (byte) 0xBD;
        count = 3;
    }
    
    buf += count;
    return buf;
}

Bool    TY_(IsValidUTF16FromUCS4)( tchar ucs4 )
{
  return ( ucs4 <= kMaxUTF16FromUCS4 );
}

Bool    TY_(IsHighSurrogate)( tchar ch )
{
    return ( ch >= kUTF16HighSurrogateBegin && ch <= kUTF16HighSurrogateEnd );
}
Bool    TY_(IsLowSurrogate)( tchar ch )
{
    return ( ch >= kUTF16LowSurrogateBegin && ch <= kUTF16LowSurrogateEnd );
}

tchar   TY_(CombineSurrogatePair)( tchar high, tchar low )
{
    assert( TY_(IsHighSurrogate)(high) && TY_(IsLowSurrogate)(low) );
    return ( ((low - kUTF16LowSurrogateBegin) * 0x400) + 
             high - kUTF16HighSurrogateBegin + 0x10000 );
}

Bool   TY_(SplitSurrogatePair)( tchar utf16, tchar* low, tchar* high )
{
    Bool status = ( TY_(IsValidCombinedChar)( utf16 ) && high && low );
    if ( status )
    {
        *low  = (utf16 - kUTF16SurrogatesBegin) / 0x400 + kUTF16LowSurrogateBegin;
        *high = (utf16 - kUTF16SurrogatesBegin) % 0x400 + kUTF16HighSurrogateBegin;
    }
    return status;
}

Bool    TY_(IsValidCombinedChar)( tchar ch )
{
    return ( ch >= kUTF16SurrogatesBegin &&
             (ch & 0x0000FFFE) != 0x0000FFFE &&
             (ch & 0x0000FFFF) != 0x0000FFFF );
}

Bool    TY_(IsCombinedChar)( tchar ch )
{
    return ( ch >= kUTF16SurrogatesBegin );
}

/*
 * local variables:
 * mode: c
 * indent-tabs-mode: nil
 * c-basic-offset: 4
 * eval: (c-set-offset 'substatement-open 0)
 * end:
 */