aboutsummaryrefslogtreecommitdiffhomepage
path: root/src/core/SkUtils.cpp
blob: 1eb2a7df43b1bc1337bab27c2f6d016fe31a528c (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
/*
 * Copyright 2006 The Android Open Source Project
 *
 * Use of this source code is governed by a BSD-style license that can be
 * found in the LICENSE file.
 */


#include "SkUtils.h"

/*  0xxxxxxx    1 total
    10xxxxxx    // never a leading byte
    110xxxxx    2 total
    1110xxxx    3 total
    11110xxx    4 total

    11 10 01 01 xx xx xx xx 0...
    0xE5XX0000
    0xE5 << 24
*/

static bool utf8_byte_is_valid(uint8_t c) {
    return c < 0xF5 && (c & 0xFE) != 0xC0;
}
static bool utf8_byte_is_continuation(uint8_t c) {
    return  (c & 0xC0) == 0x80;
}
static bool utf8_byte_is_leading_byte(uint8_t c) {
    return utf8_byte_is_valid(c) && !utf8_byte_is_continuation(c);
}

#ifdef SK_DEBUG
    static void assert_utf8_leadingbyte(unsigned c) {
        SkASSERT(utf8_byte_is_leading_byte(SkToU8(c)));
    }

    int SkUTF8_LeadByteToCount(unsigned c) {
        assert_utf8_leadingbyte(c);
        return (((0xE5 << 24) >> (c >> 4 << 1)) & 3) + 1;
    }
#else
    #define assert_utf8_leadingbyte(c)
#endif

/**
 * @returns -1  iff invalid UTF8 byte,
 *           0  iff UTF8 continuation byte,
 *           1  iff ASCII byte,
 *           2  iff leading byte of 2-byte sequence,
 *           3  iff leading byte of 3-byte sequence, and
 *           4  iff leading byte of 4-byte sequence.
 *
 * I.e.: if return value > 0, then gives length of sequence.
*/
static int utf8_byte_type(uint8_t c) {
    if (c < 0x80) {
        return 1;
    } else if (c < 0xC0) {
        return 0;
    } else if (c < 0xF5 && (c & 0xFE) != 0xC0) { // "octet values C0, C1, F5 to FF never appear"
        return (((0xE5 << 24) >> ((unsigned)c >> 4 << 1)) & 3) + 1;
    } else {
        return -1;
    }
}
static bool utf8_type_is_valid_leading_byte(int type) { return type > 0; }

int SkUTF8_CountUnichars(const char utf8[]) {
    SkASSERT(utf8);

    int count = 0;

    for (;;) {
        int c = *(const uint8_t*)utf8;
        if (c == 0) {
            break;
        }
        utf8 += SkUTF8_LeadByteToCount(c);
        count += 1;
    }
    return count;
}

// SAFE: returns -1 if invalid UTF-8
int SkUTF8_CountUnicharsWithError(const char utf8[], size_t byteLength) {
    SkASSERT(utf8 || 0 == byteLength);

    int         count = 0;
    const char* stop = utf8 + byteLength;

    while (utf8 < stop) {
        int type = utf8_byte_type(*(const uint8_t*)utf8);
        SkASSERT(type >= -1 && type <= 4);
        if (!utf8_type_is_valid_leading_byte(type) ||
            utf8 + type > stop) {  // Sequence extends beyond end.
            return -1;
        }
        while(type-- > 1) {
            ++utf8;
            if (!utf8_byte_is_continuation(*(const uint8_t*)utf8)) {
                return -1;
            }
        }
        ++utf8;
        ++count;
    }
    return count;
}

SkUnichar SkUTF8_ToUnichar(const char utf8[]) {
    SkASSERT(utf8);

    const uint8_t*  p = (const uint8_t*)utf8;
    int             c = *p;
    int             hic = c << 24;

    assert_utf8_leadingbyte(c);

    if (hic < 0) {
        uint32_t mask = (uint32_t)~0x3F;
        hic = SkLeftShift(hic, 1);
        do {
            c = (c << 6) | (*++p & 0x3F);
            mask <<= 5;
        } while ((hic = SkLeftShift(hic, 1)) < 0);
        c &= ~mask;
    }
    return c;
}

// SAFE: returns -1 on invalid UTF-8 sequence.
SkUnichar SkUTF8_NextUnicharWithError(const char** ptr, const char* end) {
    SkASSERT(ptr && *ptr);
    SkASSERT(*ptr < end);
    const uint8_t*  p = (const uint8_t*)*ptr;
    int             c = *p;
    int             hic = c << 24;

    if (!utf8_byte_is_leading_byte(c)) {
        return -1;
    }
    if (hic < 0) {
        uint32_t mask = (uint32_t)~0x3F;
        hic = SkLeftShift(hic, 1);
        do {
            ++p;
            if (p >= (const uint8_t*)end) {
                return -1;
            }
            // check before reading off end of array.
            uint8_t nextByte = *p;
            if (!utf8_byte_is_continuation(nextByte)) {
                return -1;
            }
            c = (c << 6) | (nextByte & 0x3F);
            mask <<= 5;
        } while ((hic = SkLeftShift(hic, 1)) < 0);
        c &= ~mask;
    }
    *ptr = (char*)p + 1;
    return c;
}

SkUnichar SkUTF8_NextUnichar(const char** ptr) {
    SkASSERT(ptr && *ptr);

    const uint8_t*  p = (const uint8_t*)*ptr;
    int             c = *p;
    int             hic = c << 24;

    assert_utf8_leadingbyte(c);

    if (hic < 0) {
        uint32_t mask = (uint32_t)~0x3F;
        hic = SkLeftShift(hic, 1);
        do {
            c = (c << 6) | (*++p & 0x3F);
            mask <<= 5;
        } while ((hic = SkLeftShift(hic, 1)) < 0);
        c &= ~mask;
    }
    *ptr = (char*)p + 1;
    return c;
}

SkUnichar SkUTF8_PrevUnichar(const char** ptr) {
    SkASSERT(ptr && *ptr);

    const char* p = *ptr;

    if (*--p & 0x80) {
        while (*--p & 0x40) {
            ;
        }
    }

    *ptr = (char*)p;
    return SkUTF8_NextUnichar(&p);
}

size_t SkUTF8_FromUnichar(SkUnichar uni, char utf8[]) {
    if ((uint32_t)uni > 0x10FFFF) {
        SkDEBUGFAIL("bad unichar");
        return 0;
    }

    if (uni <= 127) {
        if (utf8) {
            *utf8 = (char)uni;
        }
        return 1;
    }

    char    tmp[4];
    char*   p = tmp;
    size_t  count = 1;

    SkDEBUGCODE(SkUnichar orig = uni;)

    while (uni > 0x7F >> count) {
        *p++ = (char)(0x80 | (uni & 0x3F));
        uni >>= 6;
        count += 1;
    }

    if (utf8) {
        p = tmp;
        utf8 += count;
        while (p < tmp + count - 1) {
            *--utf8 = *p++;
        }
        *--utf8 = (char)(~(0xFF >> count) | uni);
    }

    SkASSERT(utf8 == nullptr || orig == SkUTF8_ToUnichar(utf8));
    return count;
}

///////////////////////////////////////////////////////////////////////////////

int SkUTF16_CountUnichars(const uint16_t src[]) {
    SkASSERT(src);

    int count = 0;
    unsigned c;
    while ((c = *src++) != 0) {
        SkASSERT(!SkUTF16_IsLowSurrogate(c));
        if (SkUTF16_IsHighSurrogate(c)) {
            c = *src++;
            SkASSERT(SkUTF16_IsLowSurrogate(c));
        }
        count += 1;
    }
    return count;
}

int SkUTF16_CountUnichars(const uint16_t src[], int numberOf16BitValues) {
    SkASSERT(src);

    const uint16_t* stop = src + numberOf16BitValues;
    int count = 0;
    while (src < stop) {
        unsigned c = *src++;
        SkASSERT(!SkUTF16_IsLowSurrogate(c));
        if (SkUTF16_IsHighSurrogate(c)) {
            SkASSERT(src < stop);
            c = *src++;
            SkASSERT(SkUTF16_IsLowSurrogate(c));
        }
        count += 1;
    }
    return count;
}

SkUnichar SkUTF16_NextUnichar(const uint16_t** srcPtr) {
    SkASSERT(srcPtr && *srcPtr);

    const uint16_t* src = *srcPtr;
    SkUnichar       c = *src++;

    SkASSERT(!SkUTF16_IsLowSurrogate(c));
    if (SkUTF16_IsHighSurrogate(c)) {
        unsigned c2 = *src++;
        SkASSERT(SkUTF16_IsLowSurrogate(c2));

        // c = ((c & 0x3FF) << 10) + (c2 & 0x3FF) + 0x10000
        // c = (((c & 0x3FF) + 64) << 10) + (c2 & 0x3FF)
        c = (c << 10) + c2 + (0x10000 - (0xD800 << 10) - 0xDC00);
    }
    *srcPtr = src;
    return c;
}

SkUnichar SkUTF16_PrevUnichar(const uint16_t** srcPtr) {
    SkASSERT(srcPtr && *srcPtr);

    const uint16_t* src = *srcPtr;
    SkUnichar       c = *--src;

    SkASSERT(!SkUTF16_IsHighSurrogate(c));
    if (SkUTF16_IsLowSurrogate(c)) {
        unsigned c2 = *--src;
        SkASSERT(SkUTF16_IsHighSurrogate(c2));
        c = (c2 << 10) + c + (0x10000 - (0xD800 << 10) - 0xDC00);
    }
    *srcPtr = src;
    return c;
}

size_t SkUTF16_FromUnichar(SkUnichar uni, uint16_t dst[]) {
    SkASSERT((unsigned)uni <= 0x10FFFF);

    int extra = (uni > 0xFFFF);

    if (dst) {
        if (extra) {
            // dst[0] = SkToU16(0xD800 | ((uni - 0x10000) >> 10));
            // dst[0] = SkToU16(0xD800 | ((uni >> 10) - 64));
            dst[0] = SkToU16((0xD800 - 64) + (uni >> 10));
            dst[1] = SkToU16(0xDC00 | (uni & 0x3FF));

            SkASSERT(SkUTF16_IsHighSurrogate(dst[0]));
            SkASSERT(SkUTF16_IsLowSurrogate(dst[1]));
        } else {
            dst[0] = SkToU16(uni);
            SkASSERT(!SkUTF16_IsHighSurrogate(dst[0]));
            SkASSERT(!SkUTF16_IsLowSurrogate(dst[0]));
        }
    }
    return 1 + extra;
}

size_t SkUTF16_ToUTF8(const uint16_t utf16[], int numberOf16BitValues,
                      char utf8[]) {
    SkASSERT(numberOf16BitValues >= 0);
    if (numberOf16BitValues <= 0) {
        return 0;
    }

    SkASSERT(utf16 != nullptr);

    const uint16_t* stop = utf16 + numberOf16BitValues;
    size_t          size = 0;

    if (utf8 == nullptr) {    // just count
        while (utf16 < stop) {
            size += SkUTF8_FromUnichar(SkUTF16_NextUnichar(&utf16), nullptr);
        }
    } else {
        char* start = utf8;
        while (utf16 < stop) {
            utf8 += SkUTF8_FromUnichar(SkUTF16_NextUnichar(&utf16), utf8);
        }
        size = utf8 - start;
    }
    return size;
}

const char SkHexadecimalDigits::gUpper[16] =
           { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };
const char SkHexadecimalDigits::gLower[16] =
           { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f' };