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
|
#include <stdint.h>
#include <stdlib.h>
#include <harfbuzz-external.h>
#include <harfbuzz-impl.h>
#include <harfbuzz-shaper.h>
#include "harfbuzz-unicode.h"
#include "tables/grapheme-break-properties.h"
#include "tables/mirroring-properties.h"
#include "tables/script-properties.h"
uint32_t
utf16_to_code_point(const uint16_t *chars, size_t len, ssize_t *iter) {
const uint16_t v = chars[(*iter)++];
if (HB_IsHighSurrogate(v)) {
// surrogate pair
if (*iter >= len) {
// the surrogate is incomplete.
return HB_InvalidCodePoint;
}
const uint16_t v2 = chars[(*iter)++];
if (!HB_IsLowSurrogate(v2)) {
// invalidate surrogate pair.
return HB_InvalidCodePoint;
}
return HB_SurrogateToUcs4(v, v2);
}
if (HB_IsLowSurrogate(v)) {
// this isn't a valid code point
return HB_InvalidCodePoint;
}
return v;
}
uint32_t
utf16_to_code_point_prev(const uint16_t *chars, size_t len, ssize_t *iter) {
const uint16_t v = chars[(*iter)--];
if (HB_IsLowSurrogate(v)) {
// surrogate pair
if (*iter < 0) {
// the surrogate is incomplete.
return HB_InvalidCodePoint;
}
const uint16_t v2 = chars[(*iter)--];
if (!HB_IsHighSurrogate(v2)) {
// invalidate surrogate pair.
return HB_InvalidCodePoint;
}
return HB_SurrogateToUcs4(v2, v);
}
if (HB_IsHighSurrogate(v)) {
// this isn't a valid code point
return HB_InvalidCodePoint;
}
return v;
}
static int
script_property_cmp(const void *vkey, const void *vcandidate) {
const uint32_t key = (uint32_t) (intptr_t) vkey;
const struct script_property *candidate = vcandidate;
if (key < candidate->range_start) {
return -1;
} else if (key > candidate->range_end) {
return 1;
} else {
return 0;
}
}
HB_Script
code_point_to_script(uint32_t cp) {
const void *vprop = bsearch((void *) (intptr_t) cp, script_properties,
script_properties_count,
sizeof(struct script_property),
script_property_cmp);
if (!vprop)
return HB_Script_Common;
return ((const struct script_property *) vprop)->script;
}
char
hb_utf16_script_run_next(unsigned *num_code_points, HB_ScriptItem *output,
const uint16_t *chars, size_t len, ssize_t *iter) {
if (*iter == len)
return 0;
output->pos = *iter;
const uint32_t init_cp = utf16_to_code_point(chars, len, iter);
unsigned cps = 1;
if (init_cp == HB_InvalidCodePoint)
return 0;
const HB_Script init_script = code_point_to_script(init_cp);
HB_Script current_script = init_script;
output->script = init_script;
for (;;) {
if (*iter == len)
break;
const ssize_t prev_iter = *iter;
const uint32_t cp = utf16_to_code_point(chars, len, iter);
if (cp == HB_InvalidCodePoint)
return 0;
cps++;
const HB_Script script = code_point_to_script(cp);
if (script != current_script) {
if (current_script == init_script == HB_Script_Inherited) {
// If we started off as inherited, we take whatever we can find.
output->script = script;
current_script = script;
continue;
} else if (script == HB_Script_Inherited) {
continue;
} else {
*iter = prev_iter;
cps--;
break;
}
}
}
if (output->script == HB_Script_Inherited)
output->script = HB_Script_Common;
output->length = *iter - output->pos;
if (num_code_points)
*num_code_points = cps;
return 1;
}
char
hb_utf16_script_run_prev(unsigned *num_code_points, HB_ScriptItem *output,
const uint16_t *chars, size_t len, ssize_t *iter) {
if (*iter == (size_t) -1)
return 0;
const size_t ending_index = *iter;
const uint32_t init_cp = utf16_to_code_point_prev(chars, len, iter);
unsigned cps = 1;
if (init_cp == HB_InvalidCodePoint)
return 0;
const HB_Script init_script = code_point_to_script(init_cp);
HB_Script current_script = init_script;
output->script = init_script;
for (;;) {
if (*iter < 0)
break;
const ssize_t prev_iter = *iter;
const uint32_t cp = utf16_to_code_point_prev(chars, len, iter);
if (cp == HB_InvalidCodePoint)
return 0;
cps++;
const HB_Script script = code_point_to_script(cp);
if (script != current_script) {
if (current_script == init_script == HB_Script_Inherited) {
// If we started off as inherited, we take whatever we can find.
output->script = script;
current_script = script;
continue;
} else if (script == HB_Script_Inherited) {
// Just assume that whatever follows this combining character is within
// the same script. This is incorrect if you had language1 + combining
// char + language 2, but that is rare and this code is suspicious
// anyway.
continue;
} else {
*iter = prev_iter;
cps--;
break;
}
}
}
if (output->script == HB_Script_Inherited)
output->script = HB_Script_Common;
output->pos = *iter + 1;
output->length = ending_index - *iter;
if (num_code_points)
*num_code_points = cps;
return 1;
}
static int
grapheme_break_property_cmp(const void *vkey, const void *vcandidate) {
const uint32_t key = (uint32_t) (intptr_t) vkey;
const struct grapheme_break_property *candidate = vcandidate;
if (key < candidate->range_start) {
return -1;
} else if (key > candidate->range_end) {
return 1;
} else {
return 0;
}
}
HB_GraphemeClass
HB_GetGraphemeClass(HB_UChar32 ch) {
const void *vprop = bsearch((void *) (intptr_t) ch, grapheme_break_properties,
grapheme_break_properties_count,
sizeof(struct grapheme_break_property),
grapheme_break_property_cmp);
if (!vprop)
return HB_Grapheme_Other;
return ((const struct grapheme_break_property *) vprop)->klass;
}
HB_WordClass
HB_GetWordClass(HB_UChar32 ch) {
abort();
return 0;
}
HB_SentenceClass
HB_GetSentenceClass(HB_UChar32 ch) {
abort();
return 0;
}
void
HB_GetGraphemeAndLineBreakClass(HB_UChar32 ch, HB_GraphemeClass *gclass, HB_LineBreakClass *breakclass) {
*gclass = HB_GetGraphemeClass(ch);
*breakclass = HB_GetLineBreakClass(ch);
}
static int
mirroring_property_cmp(const void *vkey, const void *vcandidate) {
const uint32_t key = (uint32_t) (intptr_t) vkey;
const struct mirroring_property *candidate = vcandidate;
if (key < candidate->a) {
return -1;
} else if (key > candidate->a) {
return 1;
} else {
return 0;
}
}
HB_UChar16
HB_GetMirroredChar(HB_UChar16 ch) {
const void *mprop = bsearch((void *) (intptr_t) ch, mirroring_properties,
mirroring_properties_count,
sizeof(struct mirroring_property),
mirroring_property_cmp);
if (!mprop)
return ch;
return ((const struct mirroring_property *) mprop)->b;
}
void *
HB_Library_Resolve(const char *library, const char *symbol) {
abort();
return NULL;
}
void *
HB_TextCodecForMib(int mib) {
abort();
return NULL;
}
char *
HB_TextCodec_ConvertFromUnicode(void *codec, const HB_UChar16 *unicode, hb_uint32 length, hb_uint32 *outputLength) {
abort();
return NULL;
}
void
HB_TextCodec_FreeResult(char *v) {
abort();
}
|