summaryrefslogtreecommitdiffstats
path: root/intl/icu/source/common/punycode.cpp
blob: 1d2ccb342e601eb1a2898996b0889bf25218427a (plain)
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
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 2002-2011, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  punycode.cpp
*   encoding:   US-ASCII
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2002jan31
*   created by: Markus W. Scherer
*/


/* This ICU code derived from: */
/*
punycode.c 0.4.0 (2001-Nov-17-Sat)
http://www.cs.berkeley.edu/~amc/idn/
Adam M. Costello
http://www.nicemice.net/amc/

Disclaimer and license

    Regarding this entire document or any portion of it (including
    the pseudocode and C code), the author makes no guarantees and
    is not responsible for any damage resulting from its use.  The
    author grants irrevocable permission to anyone to use, modify,
    and distribute it in any way that does not diminish the rights
    of anyone else to use, modify, and distribute it, provided that
    redistributed derivative works do not contain misleading author or
    version information.  Derivative works need not be licensed under
    similar terms.
*/
/*
 * ICU modifications:
 * - ICU data types and coding conventions
 * - ICU string buffer handling with implicit source lengths
 *   and destination preflighting
 * - UTF-16 handling
 */

#include "unicode/utypes.h"

#if !UCONFIG_NO_IDNA

#include "unicode/ustring.h"
#include "unicode/utf.h"
#include "unicode/utf16.h"
#include "ustr_imp.h"
#include "cstring.h"
#include "cmemory.h"
#include "punycode.h"
#include "uassert.h"


/* Punycode ----------------------------------------------------------------- */

/* Punycode parameters for Bootstring */
#define BASE            36
#define TMIN            1
#define TMAX            26
#define SKEW            38
#define DAMP            700
#define INITIAL_BIAS    72
#define INITIAL_N       0x80

/* "Basic" Unicode/ASCII code points */
#define _HYPHEN         0X2d
#define DELIMITER       _HYPHEN

#define _ZERO_          0X30
#define _NINE           0x39

#define _SMALL_A        0X61
#define _SMALL_Z        0X7a

#define _CAPITAL_A      0X41
#define _CAPITAL_Z      0X5a

#define IS_BASIC(c) ((c)<0x80)
#define IS_BASIC_UPPERCASE(c) (_CAPITAL_A<=(c) && (c)<=_CAPITAL_Z)

/**
 * digitToBasic() returns the basic code point whose value
 * (when used for representing integers) is d, which must be in the
 * range 0 to BASE-1. The lowercase form is used unless the uppercase flag is
 * nonzero, in which case the uppercase form is used.
 */
static inline char
digitToBasic(int32_t digit, UBool uppercase) {
    /*  0..25 map to ASCII a..z or A..Z */
    /* 26..35 map to ASCII 0..9         */
    if(digit<26) {
        if(uppercase) {
            return (char)(_CAPITAL_A+digit);
        } else {
            return (char)(_SMALL_A+digit);
        }
    } else {
        return (char)((_ZERO_-26)+digit);
    }
}

/**
 * basicToDigit[] contains the numeric value of a basic code
 * point (for use in representing integers) in the range 0 to
 * BASE-1, or -1 if b is does not represent a value.
 */
static const int8_t
basicToDigit[256]={
    -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,

    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
    26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1,

    -1,  0,  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, -1, -1, -1, -1, -1,

    -1,  0,  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, -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, -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, -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, -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, -1, -1, -1, -1, -1
};

static inline char
asciiCaseMap(char b, UBool uppercase) {
    if(uppercase) {
        if(_SMALL_A<=b && b<=_SMALL_Z) {
            b-=(_SMALL_A-_CAPITAL_A);
        }
    } else {
        if(_CAPITAL_A<=b && b<=_CAPITAL_Z) {
            b+=(_SMALL_A-_CAPITAL_A);
        }
    }
    return b;
}

/* Punycode-specific Bootstring code ---------------------------------------- */

/*
 * The following code omits the {parts} of the pseudo-algorithm in the spec
 * that are not used with the Punycode parameter set.
 */

/* Bias adaptation function. */
static int32_t
adaptBias(int32_t delta, int32_t length, UBool firstTime) {
    int32_t count;

    if(firstTime) {
        delta/=DAMP;
    } else {
        delta/=2;
    }

    delta+=delta/length;
    for(count=0; delta>((BASE-TMIN)*TMAX)/2; count+=BASE) {
        delta/=(BASE-TMIN);
    }

    return count+(((BASE-TMIN+1)*delta)/(delta+SKEW));
}

#define MAX_CP_COUNT    200

U_CFUNC int32_t
u_strToPunycode(const UChar *src, int32_t srcLength,
                UChar *dest, int32_t destCapacity,
                const UBool *caseFlags,
                UErrorCode *pErrorCode) {

    int32_t cpBuffer[MAX_CP_COUNT];
    int32_t n, delta, handledCPCount, basicLength, destLength, bias, j, m, q, k, t, srcCPCount;
    UChar c, c2;

    /* argument checking */
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }

    if(src==NULL || srcLength<-1 || (dest==NULL && destCapacity!=0)) {
        *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }

    /*
     * Handle the basic code points and
     * convert extended ones to UTF-32 in cpBuffer (caseFlag in sign bit):
     */
    srcCPCount=destLength=0;
    if(srcLength==-1) {
        /* NUL-terminated input */
        for(j=0; /* no condition */; ++j) {
            if((c=src[j])==0) {
                break;
            }
            if(srcCPCount==MAX_CP_COUNT) {
                /* too many input code points */
                *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
                return 0;
            }
            if(IS_BASIC(c)) {
                cpBuffer[srcCPCount++]=0;
                if(destLength<destCapacity) {
                    dest[destLength]=
                        caseFlags!=NULL ?
                            asciiCaseMap((char)c, caseFlags[j]) :
                            (char)c;
                }
                ++destLength;
            } else {
                n=(caseFlags!=NULL && caseFlags[j])<<31L;
                if(U16_IS_SINGLE(c)) {
                    n|=c;
                } else if(U16_IS_LEAD(c) && U16_IS_TRAIL(c2=src[j+1])) {
                    ++j;
                    n|=(int32_t)U16_GET_SUPPLEMENTARY(c, c2);
                } else {
                    /* error: unmatched surrogate */
                    *pErrorCode=U_INVALID_CHAR_FOUND;
                    return 0;
                }
                cpBuffer[srcCPCount++]=n;
            }
        }
    } else {
        /* length-specified input */
        for(j=0; j<srcLength; ++j) {
            if(srcCPCount==MAX_CP_COUNT) {
                /* too many input code points */
                *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
                return 0;
            }
            c=src[j];
            if(IS_BASIC(c)) {
                cpBuffer[srcCPCount++]=0;
                if(destLength<destCapacity) {
                    dest[destLength]=
                        caseFlags!=NULL ?
                            asciiCaseMap((char)c, caseFlags[j]) :
                            (char)c;
                }
                ++destLength;
            } else {
                n=(caseFlags!=NULL && caseFlags[j])<<31L;
                if(U16_IS_SINGLE(c)) {
                    n|=c;
                } else if(U16_IS_LEAD(c) && (j+1)<srcLength && U16_IS_TRAIL(c2=src[j+1])) {
                    ++j;
                    n|=(int32_t)U16_GET_SUPPLEMENTARY(c, c2);
                } else {
                    /* error: unmatched surrogate */
                    *pErrorCode=U_INVALID_CHAR_FOUND;
                    return 0;
                }
                cpBuffer[srcCPCount++]=n;
            }
        }
    }

    /* Finish the basic string - if it is not empty - with a delimiter. */
    basicLength=destLength;
    if(basicLength>0) {
        if(destLength<destCapacity) {
            dest[destLength]=DELIMITER;
        }
        ++destLength;
    }

    /*
     * handledCPCount is the number of code points that have been handled
     * basicLength is the number of basic code points
     * destLength is the number of chars that have been output
     */

    /* Initialize the state: */
    n=INITIAL_N;
    delta=0;
    bias=INITIAL_BIAS;

    /* Main encoding loop: */
    for(handledCPCount=basicLength; handledCPCount<srcCPCount; /* no op */) {
        /*
         * All non-basic code points < n have been handled already.
         * Find the next larger one:
         */
        for(m=0x7fffffff, j=0; j<srcCPCount; ++j) {
            q=cpBuffer[j]&0x7fffffff; /* remove case flag from the sign bit */
            if(n<=q && q<m) {
                m=q;
            }
        }

        /*
         * Increase delta enough to advance the decoder's
         * <n,i> state to <m,0>, but guard against overflow:
         */
        if(m-n>(0x7fffffff-MAX_CP_COUNT-delta)/(handledCPCount+1)) {
            *pErrorCode=U_INTERNAL_PROGRAM_ERROR;
            return 0;
        }
        delta+=(m-n)*(handledCPCount+1);
        n=m;

        /* Encode a sequence of same code points n */
        for(j=0; j<srcCPCount; ++j) {
            q=cpBuffer[j]&0x7fffffff; /* remove case flag from the sign bit */
            if(q<n) {
                ++delta;
            } else if(q==n) {
                /* Represent delta as a generalized variable-length integer: */
                for(q=delta, k=BASE; /* no condition */; k+=BASE) {

                    /** RAM: comment out the old code for conformance with draft-ietf-idn-punycode-03.txt

                    t=k-bias;
                    if(t<TMIN) {
                        t=TMIN;
                    } else if(t>TMAX) {
                        t=TMAX;
                    }
                    */

                    t=k-bias;
                    if(t<TMIN) {
                        t=TMIN;
                    } else if(k>=(bias+TMAX)) {
                        t=TMAX;
                    }

                    if(q<t) {
                        break;
                    }

                    if(destLength<destCapacity) {
                        dest[destLength]=digitToBasic(t+(q-t)%(BASE-t), 0);
                    }
                    ++destLength;
                    q=(q-t)/(BASE-t);
                }

                if(destLength<destCapacity) {
                    dest[destLength]=digitToBasic(q, (UBool)(cpBuffer[j]<0));
                }
                ++destLength;
                bias=adaptBias(delta, handledCPCount+1, (UBool)(handledCPCount==basicLength));
                delta=0;
                ++handledCPCount;
            }
        }

        ++delta;
        ++n;
    }

    return u_terminateUChars(dest, destCapacity, destLength, pErrorCode);
}

U_CFUNC int32_t
u_strFromPunycode(const UChar *src, int32_t srcLength,
                  UChar *dest, int32_t destCapacity,
                  UBool *caseFlags,
                  UErrorCode *pErrorCode) {
    int32_t n, destLength, i, bias, basicLength, j, in, oldi, w, k, digit, t,
            destCPCount, firstSupplementaryIndex, cpLength;
    UChar b;

    /* argument checking */
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }

    if(src==NULL || srcLength<-1 || (dest==NULL && destCapacity!=0)) {
        *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }

    if(srcLength==-1) {
        srcLength=u_strlen(src);
    }

    /*
     * Handle the basic code points:
     * Let basicLength be the number of input code points
     * before the last delimiter, or 0 if there is none,
     * then copy the first basicLength code points to the output.
     *
     * The two following loops iterate backward.
     */
    for(j=srcLength; j>0;) {
        if(src[--j]==DELIMITER) {
            break;
        }
    }
    destLength=basicLength=destCPCount=j;
    U_ASSERT(destLength>=0);

    while(j>0) {
        b=src[--j];
        if(!IS_BASIC(b)) {
            *pErrorCode=U_INVALID_CHAR_FOUND;
            return 0;
        }

        if(j<destCapacity) {
            dest[j]=(UChar)b;

            if(caseFlags!=NULL) {
                caseFlags[j]=IS_BASIC_UPPERCASE(b);
            }
        }
    }

    /* Initialize the state: */
    n=INITIAL_N;
    i=0;
    bias=INITIAL_BIAS;
    firstSupplementaryIndex=1000000000;

    /*
     * Main decoding loop:
     * Start just after the last delimiter if any
     * basic code points were copied; start at the beginning otherwise.
     */
    for(in=basicLength>0 ? basicLength+1 : 0; in<srcLength; /* no op */) {
        /*
         * in is the index of the next character to be consumed, and
         * destCPCount is the number of code points in the output array.
         *
         * Decode a generalized variable-length integer into delta,
         * which gets added to i.  The overflow checking is easier
         * if we increase i as we go, then subtract off its starting
         * value at the end to obtain delta.
         */
        for(oldi=i, w=1, k=BASE; /* no condition */; k+=BASE) {
            if(in>=srcLength) {
                *pErrorCode=U_ILLEGAL_CHAR_FOUND;
                return 0;
            }

            digit=basicToDigit[(uint8_t)src[in++]];
            if(digit<0) {
                *pErrorCode=U_INVALID_CHAR_FOUND;
                return 0;
            }
            if(digit>(0x7fffffff-i)/w) {
                /* integer overflow */
                *pErrorCode=U_ILLEGAL_CHAR_FOUND;
                return 0;
            }

            i+=digit*w;
            /** RAM: comment out the old code for conformance with draft-ietf-idn-punycode-03.txt  
            t=k-bias;
            if(t<TMIN) {
                t=TMIN;
            } else if(t>TMAX) {
                t=TMAX;
            }
            */
            t=k-bias;
            if(t<TMIN) {
                t=TMIN;
            } else if(k>=(bias+TMAX)) {
                t=TMAX;
            }
            if(digit<t) {
                break;
            }

            if(w>0x7fffffff/(BASE-t)) {
                /* integer overflow */
                *pErrorCode=U_ILLEGAL_CHAR_FOUND;
                return 0;
            }
            w*=BASE-t;
        }

        /*
         * Modification from sample code:
         * Increments destCPCount here,
         * where needed instead of in for() loop tail.
         */
        ++destCPCount;
        bias=adaptBias(i-oldi, destCPCount, (UBool)(oldi==0));

        /*
         * i was supposed to wrap around from (incremented) destCPCount to 0,
         * incrementing n each time, so we'll fix that now:
         */
        if(i/destCPCount>(0x7fffffff-n)) {
            /* integer overflow */
            *pErrorCode=U_ILLEGAL_CHAR_FOUND;
            return 0;
        }

        n+=i/destCPCount;
        i%=destCPCount;
        /* not needed for Punycode: */
        /* if (decode_digit(n) <= BASE) return punycode_invalid_input; */

        if(n>0x10ffff || U_IS_SURROGATE(n)) {
            /* Unicode code point overflow */
            *pErrorCode=U_ILLEGAL_CHAR_FOUND;
            return 0;
        }

        /* Insert n at position i of the output: */
        cpLength=U16_LENGTH(n);
        if(dest!=NULL && ((destLength+cpLength)<=destCapacity)) {
            int32_t codeUnitIndex;

            /*
             * Handle indexes when supplementary code points are present.
             *
             * In almost all cases, there will be only BMP code points before i
             * and even in the entire string.
             * This is handled with the same efficiency as with UTF-32.
             *
             * Only the rare cases with supplementary code points are handled
             * more slowly - but not too bad since this is an insertion anyway.
             */
            if(i<=firstSupplementaryIndex) {
                codeUnitIndex=i;
                if(cpLength>1) {
                    firstSupplementaryIndex=codeUnitIndex;
                } else {
                    ++firstSupplementaryIndex;
                }
            } else {
                codeUnitIndex=firstSupplementaryIndex;
                U16_FWD_N(dest, codeUnitIndex, destLength, i-codeUnitIndex);
            }

            /* use the UChar index codeUnitIndex instead of the code point index i */
            if(codeUnitIndex<destLength) {
                uprv_memmove(dest+codeUnitIndex+cpLength,
                             dest+codeUnitIndex,
                             (destLength-codeUnitIndex)*U_SIZEOF_UCHAR);
                if(caseFlags!=NULL) {
                    uprv_memmove(caseFlags+codeUnitIndex+cpLength,
                                 caseFlags+codeUnitIndex,
                                 destLength-codeUnitIndex);
                }
            }
            if(cpLength==1) {
                /* BMP, insert one code unit */
                dest[codeUnitIndex]=(UChar)n;
            } else {
                /* supplementary character, insert two code units */
                dest[codeUnitIndex]=U16_LEAD(n);
                dest[codeUnitIndex+1]=U16_TRAIL(n);
            }
            if(caseFlags!=NULL) {
                /* Case of last character determines uppercase flag: */
                caseFlags[codeUnitIndex]=IS_BASIC_UPPERCASE(src[in-1]);
                if(cpLength==2) {
                    caseFlags[codeUnitIndex+1]=FALSE;
                }
            }
        }
        destLength+=cpLength;
        U_ASSERT(destLength>=0);
        ++i;
    }

    return u_terminateUChars(dest, destCapacity, destLength, pErrorCode);
}

/* ### check notes on overflow handling - only necessary if not IDNA? are these Punycode functions to be public? */

#endif /* #if !UCONFIG_NO_IDNA */