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
|
/* Line breaking of UTF-32 strings.
Copyright (C) 2001-2003, 2006-2024 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2001.
This file is free software.
It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
You can redistribute it and/or modify it under either
- the terms of the GNU Lesser General Public License as published
by the Free Software Foundation, either version 3, or (at your
option) any later version, or
- the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option)
any later version, or
- the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".
This file is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License and the GNU General Public License
for more details.
You should have received a copy of the GNU Lesser General Public
License and of the GNU General Public License along with this
program. If not, see <https://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "unilbrk.h"
#include "unilbrk/internal.h"
#include <stdlib.h>
#include "unilbrk/lbrktables.h"
#include "uniwidth/cjk.h"
/* This file implements
Unicode Standard Annex #14 <https://www.unicode.org/reports/tr14/>. */
void
u32_possible_linebreaks_loop (const uint32_t *s, size_t n, const char *encoding,
int cr, char *p)
{
if (n > 0)
{
int LBP_AI_REPLACEMENT = (is_cjk_encoding (encoding) ? LBP_ID1 : LBP_AL);
const uint32_t *s_end = s + n;
int prev_prop = LBP_BK; /* line break property of last character */
int last_prop = LBP_BK; /* line break property of last non-space character */
char *seen_space = NULL; /* Was a space seen after the last non-space character? */
/* Number of consecutive regional indicator (RI) characters seen
immediately before the current point. */
size_t ri_count = 0;
do
{
ucs4_t uc = *s;
s++;
int prop = unilbrkprop_lookup (uc);
if (prop == LBP_BK || prop == LBP_LF || prop == LBP_CR)
{
/* (LB4,LB5,LB6) Mandatory break. */
*p = UC_BREAK_MANDATORY;
/* cr is either LBP_CR or -1. In the first case, recognize
a CR-LF sequence. */
if (prev_prop == cr && prop == LBP_LF)
p[-1] = UC_BREAK_CR_BEFORE_LF;
prev_prop = prop;
last_prop = LBP_BK;
seen_space = NULL;
}
else
{
/* Resolve property values whose behaviour is not fixed. */
switch (prop)
{
case LBP_AI:
/* Resolve ambiguous. */
prop = LBP_AI_REPLACEMENT;
break;
case LBP_CB:
/* This is arbitrary. */
prop = LBP_ID1;
break;
case LBP_SA:
/* We don't handle complex scripts yet.
Treat LBP_SA like LBP_XX. */
case LBP_XX:
/* This is arbitrary. */
prop = LBP_AL;
break;
case LBP_QU2:
/* For (LB15a): Replace LBP_QU2 with LBP_QU1 if the previous
character's line break property was not one of
BK, CR, LF, OP, QU, GL, SP, ZW. */
switch (prev_prop)
{
case LBP_BK:
case LBP_CR:
case LBP_LF:
case LBP_OP1: case LBP_OP2:
case LBP_QU1: case LBP_QU2: case LBP_QU3:
case LBP_GL:
case LBP_SP:
case LBP_ZW:
break;
default:
prop = LBP_QU1;
break;
}
break;
case LBP_QU3:
/* For (LB15b): Replace LBP_QU3 with LBP_QU1 if the next
character's line break property is not one of
BK, CR, LF, SP, GL, WJ, CL, QU, CP, EX, IS, SY, ZW. */
{
int next_prop;
if (s < s_end)
{
ucs4_t next_uc = *s;
next_prop = unilbrkprop_lookup (next_uc);
}
else
next_prop = LBP_BK;
switch (next_prop)
{
case LBP_BK:
case LBP_CR:
case LBP_LF:
case LBP_SP:
case LBP_GL:
case LBP_WJ:
case LBP_CL:
case LBP_QU1: case LBP_QU2: case LBP_QU3:
case LBP_CP1: case LBP_CP2:
case LBP_EX:
case LBP_IS:
case LBP_SY:
case LBP_ZW:
break;
default:
prop = LBP_QU1;
break;
}
}
break;
}
/* Deal with spaces and combining characters. */
if (prop == LBP_SP)
{
/* (LB7) Don't break just before a space. */
*p = UC_BREAK_PROHIBITED;
seen_space = p;
}
else if (prop == LBP_ZW)
{
/* (LB7) Don't break just before a zero-width space. */
*p = UC_BREAK_PROHIBITED;
last_prop = LBP_ZW;
seen_space = NULL;
}
else if (prop == LBP_CM || prop == LBP_ZWJ)
{
/* (LB9) Don't break just before a combining character or
zero-width joiner, except immediately after a mandatory
break character, space, or zero-width space. */
if (last_prop == LBP_BK)
{
/* (LB4,LB5,LB6) Don't break at the beginning of a line. */
*p = UC_BREAK_PROHIBITED;
/* (LB10) Treat CM or ZWJ as AL. */
last_prop = LBP_AL;
seen_space = NULL;
}
else if (last_prop == LBP_ZW || seen_space != NULL)
{
/* (LB8) Break after zero-width space. */
/* (LB18) Break after spaces.
We do *not* implement the "legacy support for space
character as base for combining marks" because now the
NBSP CM sequence is recommended instead of SP CM. */
*p = UC_BREAK_POSSIBLE;
/* (LB10) Treat CM or ZWJ as AL. */
last_prop = LBP_AL;
seen_space = NULL;
}
else
{
/* Treat X CM as if it were X. */
*p = UC_BREAK_PROHIBITED;
}
}
else
{
/* prop must be usable as an index for table 7.3 of UTR #14. */
if (!(prop >= 0 && prop < sizeof (unilbrk_table) / sizeof (unilbrk_table[0])))
abort ();
if (last_prop == LBP_BK)
{
/* (LB4,LB5,LB6) Don't break at the beginning of a line. */
*p = UC_BREAK_PROHIBITED;
}
else if (last_prop == LBP_ZW)
{
/* (LB8) Break after zero-width space. */
*p = UC_BREAK_POSSIBLE;
}
else if (prev_prop == LBP_ZWJ)
{
/* (LB8a) Don't break right after a zero-width joiner. */
*p = UC_BREAK_PROHIBITED;
}
else if (last_prop == LBP_RI && prop == LBP_RI)
{
/* (LB30a) Break between two regional indicator symbols
if and only if there are an even number of regional
indicators preceding the position of the break. */
*p = (seen_space != NULL || (ri_count % 2) == 0
? UC_BREAK_POSSIBLE
: UC_BREAK_PROHIBITED);
}
else if (prev_prop == LBP_HL_BA)
{
/* (LB21a) Don't break after Hebrew + Hyphen/Break-After. */
*p = UC_BREAK_PROHIBITED;
}
else
{
switch (unilbrk_table [last_prop] [prop])
{
case D:
*p = UC_BREAK_POSSIBLE;
break;
case I:
*p = (seen_space != NULL ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED);
break;
case P:
*p = UC_BREAK_PROHIBITED;
break;
default:
abort ();
}
}
last_prop = prop;
seen_space = NULL;
}
prev_prop = (prev_prop == LBP_HL && (prop == LBP_HY || prop == LBP_BA)
? LBP_HL_BA
: prop);
}
if (prop == LBP_RI)
ri_count++;
else
ri_count = 0;
p++;
}
while (s < s_end);
}
}
#if defined IN_LIBUNISTRING
/* For backward compatibility with older versions of libunistring. */
# undef u32_possible_linebreaks
void
u32_possible_linebreaks (const uint32_t *s, size_t n, const char *encoding,
char *p)
{
u32_possible_linebreaks_loop (s, n, encoding, -1, p);
}
#endif
void
u32_possible_linebreaks_v2 (const uint32_t *s, size_t n, const char *encoding,
char *p)
{
u32_possible_linebreaks_loop (s, n, encoding, LBP_CR, p);
}
|
