summaryrefslogtreecommitdiff
path: root/Build/source/libs/icu/icu-xetex/samples/uciter8/uciter8.c
blob: 6c705538f646f041ee4fa6a2ee4d685659e1d9a3 (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
/*
*******************************************************************************
*
*   Copyright (C) 2003-2007, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  uciter8.c
*   encoding:   US-ASCII
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2003jan10
*   created by: Markus W. Scherer
*
*   This file contains sample code that illustrates reading
*   8-bit Unicode text leniently, accepting a mix of UTF-8 and CESU-8
*   and also accepting single surrogates.
*/

#include <stdio.h>
#include <string.h>
#include "unicode/utypes.h"
#include "unicode/uiter.h"
#include "uit_len8.h"

#define LENGTHOF(array) (sizeof(array)/sizeof((array)[0]))

#define log_err printf

/* UCharIterator test ------------------------------------------------------- */

/*
 * The following code is a copy of the UCharIterator test code in
 * source/test/cintltst/custrtst.c,
 * testing the lenient-8 iterator instead of the UTF-8 one.
 */

/*
 * Compare results from two iterators, should be same.
 * Assume that the text is not empty and that
 * iteration start==0 and iteration limit==length.
 */
static void
compareIterators(UCharIterator *iter1, const char *n1,
                 UCharIterator *iter2, const char *n2) {
    int32_t i, pos1, pos2, middle, length;
    UChar32 c1, c2;

    /* compare lengths */
    length=iter1->getIndex(iter1, UITER_LENGTH);
    pos2=iter2->getIndex(iter2, UITER_LENGTH);
    if(length!=pos2) {
        log_err("%s->getIndex(length)=%d != %d=%s->getIndex(length)\n", n1, length, pos2, n2);
        return;
    }

    /* set into the middle */
    middle=length/2;

    pos1=iter1->move(iter1, middle, UITER_ZERO);
    if(pos1!=middle) {
        log_err("%s->move(from 0 to middle %d)=%d does not move to the middle\n", n1, middle, pos1);
        return;
    }

    pos2=iter2->move(iter2, middle, UITER_ZERO);
    if(pos2!=middle) {
        log_err("%s->move(from 0 to middle %d)=%d does not move to the middle\n", n2, middle, pos2);
        return;
    }

    /* test current() */
    c1=iter1->current(iter1);
    c2=iter2->current(iter2);
    if(c1!=c2) {
        log_err("%s->current()=U+%04x != U+%04x=%s->current() at middle=%d\n", n1, c1, c2, n2, middle);
        return;
    }

    /* move forward 3 UChars */
    for(i=0; i<3; ++i) {
        c1=iter1->next(iter1);
        c2=iter2->next(iter2);
        if(c1!=c2) {
            log_err("%s->next()=U+%04x != U+%04x=%s->next() at %d (started in middle)\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT));
            return;
        }
    }

    /* move backward 5 UChars */
    for(i=0; i<5; ++i) {
        c1=iter1->previous(iter1);
        c2=iter2->previous(iter2);
        if(c1!=c2) {
            log_err("%s->previous()=U+%04x != U+%04x=%s->previous() at %d (started in middle)\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT));
            return;
        }
    }

    /* iterate forward from the beginning */
    pos1=iter1->move(iter1, 0, UITER_START);
    if(pos1<0) {
        log_err("%s->move(start) failed\n", n1);
        return;
    }
    if(!iter1->hasNext(iter1)) {
        log_err("%s->hasNext() at the start returns FALSE\n", n1);
        return;
    }

    pos2=iter2->move(iter2, 0, UITER_START);
    if(pos2<0) {
        log_err("%s->move(start) failed\n", n2);
        return;
    }
    if(!iter2->hasNext(iter2)) {
        log_err("%s->hasNext() at the start returns FALSE\n", n2);
        return;
    }

    do {
        c1=iter1->next(iter1);
        c2=iter2->next(iter2);
        if(c1!=c2) {
            log_err("%s->next()=U+%04x != U+%04x=%s->next() at %d\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT));
            return;
        }
    } while(c1>=0);

    if(iter1->hasNext(iter1)) {
        log_err("%s->hasNext() at the end returns TRUE\n", n1);
        return;
    }
    if(iter2->hasNext(iter2)) {
        log_err("%s->hasNext() at the end returns TRUE\n", n2);
        return;
    }

    /* back to the middle */
    pos1=iter1->move(iter1, middle, UITER_ZERO);
    if(pos1!=middle) {
        log_err("%s->move(from end to middle %d)=%d does not move to the middle\n", n1, middle, pos1);
        return;
    }

    pos2=iter2->move(iter2, middle, UITER_ZERO);
    if(pos2!=middle) {
        log_err("%s->move(from end to middle %d)=%d does not move to the middle\n", n2, middle, pos2);
        return;
    }

    /* move to index 1 */
    pos1=iter1->move(iter1, 1, UITER_ZERO);
    if(pos1!=1) {
        log_err("%s->move(from middle %d to 1)=%d does not move to 1\n", n1, middle, pos1);
        return;
    }

    pos2=iter2->move(iter2, 1, UITER_ZERO);
    if(pos2!=1) {
        log_err("%s->move(from middle %d to 1)=%d does not move to 1\n", n2, middle, pos2);
        return;
    }

    /* iterate backward from the end */
    pos1=iter1->move(iter1, 0, UITER_LIMIT);
    if(pos1<0) {
        log_err("%s->move(limit) failed\n", n1);
        return;
    }
    if(!iter1->hasPrevious(iter1)) {
        log_err("%s->hasPrevious() at the end returns FALSE\n", n1);
        return;
    }

    pos2=iter2->move(iter2, 0, UITER_LIMIT);
    if(pos2<0) {
        log_err("%s->move(limit) failed\n", n2);
        return;
    }
    if(!iter2->hasPrevious(iter2)) {
        log_err("%s->hasPrevious() at the end returns FALSE\n", n2);
        return;
    }

    do {
        c1=iter1->previous(iter1);
        c2=iter2->previous(iter2);
        if(c1!=c2) {
            log_err("%s->previous()=U+%04x != U+%04x=%s->previous() at %d\n", n1, c1, c2, n2, iter1->getIndex(iter1, UITER_CURRENT));
            return;
        }
    } while(c1>=0);

    if(iter1->hasPrevious(iter1)) {
        log_err("%s->hasPrevious() at the start returns TRUE\n", n1);
        return;
    }
    if(iter2->hasPrevious(iter2)) {
        log_err("%s->hasPrevious() at the start returns TRUE\n", n2);
        return;
    }
}

/*
 * Test the iterator's getState() and setState() functions.
 * iter1 and iter2 must be set up for the same iterator type and the same string
 * but may be physically different structs (different addresses).
 *
 * Assume that the text is not empty and that
 * iteration start==0 and iteration limit==length.
 * It must be 2<=middle<=length-2.
 */
static void
testIteratorState(UCharIterator *iter1, UCharIterator *iter2, const char *n, int32_t middle) {
    UChar32 u[4];

    UErrorCode errorCode;
    UChar32 c;
    uint32_t state;
    int32_t i, j;

    /* get four UChars from the middle of the string */
    iter1->move(iter1, middle-2, UITER_ZERO);
    for(i=0; i<4; ++i) {
        c=iter1->next(iter1);
        if(c<0) {
            /* the test violates the assumptions, see comment above */
            log_err("test error: %s[%d]=%d\n", n, middle-2+i, c);
            return;
        }
        u[i]=c;
    }

    /* move to the middle and get the state */
    iter1->move(iter1, -2, UITER_CURRENT);
    state=uiter_getState(iter1);

    /* set the state into the second iterator and compare the results */
    errorCode=U_ZERO_ERROR;
    uiter_setState(iter2, state, &errorCode);
    if(U_FAILURE(errorCode)) {
        log_err("%s->setState(0x%x) failed: %s\n", n, state, u_errorName(errorCode));
        return;
    }

    c=iter2->current(iter2);
    if(c!=u[2]) {
        log_err("%s->current(at %d)=U+%04x!=U+%04x\n", n, middle, c, u[2]);
    }

    c=iter2->previous(iter2);
    if(c!=u[1]) {
        log_err("%s->previous(at %d)=U+%04x!=U+%04x\n", n, middle-1, c, u[1]);
    }

    iter2->move(iter2, 2, UITER_CURRENT);
    c=iter2->next(iter2);
    if(c!=u[3]) {
        log_err("%s->next(at %d)=U+%04x!=U+%04x\n", n, middle+1, c, u[3]);
    }

    iter2->move(iter2, -3, UITER_CURRENT);
    c=iter2->previous(iter2);
    if(c!=u[0]) {
        log_err("%s->previous(at %d)=U+%04x!=U+%04x\n", n, middle-2, c, u[0]);
    }

    /* move the second iterator back to the middle */
    iter2->move(iter2, 1, UITER_CURRENT);
    iter2->next(iter2);

    /* check that both are in the middle */
    i=iter1->getIndex(iter1, UITER_CURRENT);
    j=iter2->getIndex(iter2, UITER_CURRENT);
    if(i!=middle) {
        log_err("%s->getIndex(current)=%d!=%d as expected\n", n, i, middle);
    }
    if(i!=j) {
        log_err("%s->getIndex(current)=%d!=%d after setState()\n", n, j, i);
    }

    /* compare lengths */
    i=iter1->getIndex(iter1, UITER_LENGTH);
    j=iter2->getIndex(iter2, UITER_LENGTH);
    if(i!=j) {
        log_err("%s->getIndex(length)=%d!=%d before/after setState()\n", n, i, j);
    }
}

static void
TestLenient8Iterator() {
    static const UChar text[]={
        0x61, 0x62, 0x63,
        /* dffd 107fd             d801    dffd - in UTF-16, U+107fd=<d801 dffd> */
        0xdffd, 0xd801, 0xdffd, 0xd801, 0xdffd, 
        0x78, 0x79, 0x7a, 0
    };
    static const uint8_t bytes[]={
        0x61, 0x62, 0x63,
        /* dffd            107fd                    d801               dffd - mixture */
        0xed, 0xbf, 0xbd,  0xf0, 0x90, 0x9f, 0xbd,  0xed, 0xa0, 0x81,  0xed, 0xbf, 0xbd,
        0x78, 0x79, 0x7a, 0
    };

    UCharIterator iter1, iter2;
    UChar32 c1, c2;
    int32_t length;

    puts("test a UCharIterator for lenient 8-bit Unicode (accept single surrogates)");

    /* compare the same string between UTF-16 and lenient-8 UCharIterators */
    uiter_setString(&iter1, text, -1);
    uiter_setLenient8(&iter2, (const char *)bytes, sizeof(bytes)-1);
    compareIterators(&iter1, "UTF16Iterator", &iter2, "Lenient8Iterator");

    /* try again with length=-1 */
    uiter_setLenient8(&iter2, (const char *)bytes, -1);
    compareIterators(&iter1, "UTF16Iterator", &iter2, "Lenient8Iterator_1");

    /* test get/set state */
    length=LENGTHOF(text)-1;
    uiter_setLenient8(&iter1, (const char*)bytes, -1);
    testIteratorState(&iter1, &iter2, "Lenient8IteratorState", length/2);
    testIteratorState(&iter1, &iter2, "Lenient8IteratorStatePlus1", length/2+1);

    /* ---------------------------------------------------------------------- */

    puts("no output so far means that the lenient-8 iterator works fine");

    puts("iterate forward:\nUTF-16\tlenient-8");
    uiter_setString(&iter1, text, -1);
    iter1.move(&iter1, 0, UITER_START);
    iter2.move(&iter2, 0, UITER_START);
    for(;;) {
        c1=iter1.next(&iter1);
        c2=iter2.next(&iter2);
        if(c1<0 && c2<0) {
            break;
        }
        if(c1<0) {
            printf("\t%04x\n", c2);
        } else if(c2<0) {
            printf("%04x\n", c1);
        } else {
            printf("%04x\t%04x\n", c1, c2);
        }
    }
}

extern int
main(int argc, const char *argv[]) {
    TestLenient8Iterator();
    return 0;
}