| 1 |
lars |
1 |
<?php
|
|
|
2 |
|
|
|
3 |
require_once(HTML2PS_DIR.'error.php');
|
|
|
4 |
|
|
|
5 |
// Non-tailorable Line Breaking Classes
|
|
|
6 |
define('UC_LINE_BREAK_BK', 1);
|
|
|
7 |
define('UC_LINE_BREAK_CR', 2);
|
|
|
8 |
define('UC_LINE_BREAK_LF', 3);
|
|
|
9 |
define('UC_LINE_BREAK_CM', 4);
|
|
|
10 |
define('UC_LINE_BREAK_NL', 5);
|
|
|
11 |
define('UC_LINE_BREAK_SG', 6);
|
|
|
12 |
define('UC_LINE_BREAK_WJ', 7);
|
|
|
13 |
define('UC_LINE_BREAK_ZW', 8);
|
|
|
14 |
define('UC_LINE_BREAK_GL', 9);
|
|
|
15 |
define('UC_LINE_BREAK_SP', 10);
|
|
|
16 |
|
|
|
17 |
// Break opportunities
|
|
|
18 |
define('UC_LINE_BREAK_B2', 11);
|
|
|
19 |
define('UC_LINE_BREAK_BA', 12);
|
|
|
20 |
define('UC_LINE_BREAK_BB', 13);
|
|
|
21 |
define('UC_LINE_BREAK_HY', 14);
|
|
|
22 |
define('UC_LINE_BREAK_CB', 15);
|
|
|
23 |
|
|
|
24 |
// Characters Prohibiting Certain Breaks
|
|
|
25 |
define('UC_LINE_BREAK_CL', 16);
|
|
|
26 |
define('UC_LINE_BREAK_EX', 17);
|
|
|
27 |
define('UC_LINE_BREAK_IN', 18);
|
|
|
28 |
define('UC_LINE_BREAK_NS', 19);
|
|
|
29 |
define('UC_LINE_BREAK_OP', 20);
|
|
|
30 |
define('UC_LINE_BREAK_QU', 21);
|
|
|
31 |
|
|
|
32 |
// Numeric Context
|
|
|
33 |
define('UC_LINE_BREAK_IS', 22);
|
|
|
34 |
define('UC_LINE_BREAK_NU', 23);
|
|
|
35 |
define('UC_LINE_BREAK_PO', 24);
|
|
|
36 |
define('UC_LINE_BREAK_PR', 25);
|
|
|
37 |
define('UC_LINE_BREAK_SY', 26);
|
|
|
38 |
|
|
|
39 |
// Other Characters
|
|
|
40 |
define('UC_LINE_BREAK_AI', 27);
|
|
|
41 |
define('UC_LINE_BREAK_AL', 28);
|
|
|
42 |
define('UC_LINE_BREAK_H2', 29);
|
|
|
43 |
define('UC_LINE_BREAK_H3', 30);
|
|
|
44 |
define('UC_LINE_BREAK_ID', 31);
|
|
|
45 |
define('UC_LINE_BREAK_JL', 32);
|
|
|
46 |
define('UC_LINE_BREAK_JV', 33);
|
|
|
47 |
define('UC_LINE_BREAK_JT', 34);
|
|
|
48 |
define('UC_LINE_BREAK_SA', 35);
|
|
|
49 |
define('UC_LINE_BREAK_XX', 36);
|
|
|
50 |
|
|
|
51 |
// Break modes
|
|
|
52 |
define('LB_PROHIBITED', 1);
|
|
|
53 |
define('LB_INDIRECT', 2);
|
|
|
54 |
define('LB_PROHIBITED_CM', 3);
|
|
|
55 |
define('LB_INDIRECT_CM', 4);
|
|
|
56 |
define('LB_DIRECT', 5);
|
|
|
57 |
define('LB_EXPLICIT', 6);
|
|
|
58 |
|
|
|
59 |
$GLOBALS['_g_line_break_class_table'] =
|
|
|
60 |
array(UC_LINE_BREAK_OP => array(UC_LINE_BREAK_OP => LB_PROHIBITED,
|
|
|
61 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
62 |
UC_LINE_BREAK_QU => LB_PROHIBITED,
|
|
|
63 |
UC_LINE_BREAK_GL => LB_PROHIBITED,
|
|
|
64 |
UC_LINE_BREAK_NS => LB_PROHIBITED,
|
|
|
65 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
66 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
67 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
68 |
UC_LINE_BREAK_PR => LB_PROHIBITED,
|
|
|
69 |
UC_LINE_BREAK_PO => LB_PROHIBITED,
|
|
|
70 |
UC_LINE_BREAK_NU => LB_PROHIBITED,
|
|
|
71 |
UC_LINE_BREAK_AL => LB_PROHIBITED,
|
|
|
72 |
UC_LINE_BREAK_ID => LB_PROHIBITED,
|
|
|
73 |
UC_LINE_BREAK_IN => LB_PROHIBITED,
|
|
|
74 |
UC_LINE_BREAK_HY => LB_PROHIBITED,
|
|
|
75 |
UC_LINE_BREAK_BA => LB_PROHIBITED,
|
|
|
76 |
UC_LINE_BREAK_BB => LB_PROHIBITED,
|
|
|
77 |
UC_LINE_BREAK_B2 => LB_PROHIBITED,
|
|
|
78 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
79 |
UC_LINE_BREAK_CM => LB_PROHIBITED_CM,
|
|
|
80 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
81 |
UC_LINE_BREAK_H2 => LB_PROHIBITED,
|
|
|
82 |
UC_LINE_BREAK_H3 => LB_PROHIBITED,
|
|
|
83 |
UC_LINE_BREAK_JL => LB_PROHIBITED,
|
|
|
84 |
UC_LINE_BREAK_JV => LB_PROHIBITED,
|
|
|
85 |
UC_LINE_BREAK_JT => LB_PROHIBITED),
|
|
|
86 |
UC_LINE_BREAK_CL => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
87 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
88 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
89 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
90 |
UC_LINE_BREAK_NS => LB_PROHIBITED,
|
|
|
91 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
92 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
93 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
94 |
UC_LINE_BREAK_PR => LB_INDIRECT,
|
|
|
95 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
96 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
97 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
98 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
99 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
100 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
101 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
102 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
103 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
104 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
105 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
106 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
107 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
108 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
109 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
110 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
111 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
112 |
UC_LINE_BREAK_QU => array(UC_LINE_BREAK_OP => LB_PROHIBITED,
|
|
|
113 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
114 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
115 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
116 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
117 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
118 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
119 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
120 |
UC_LINE_BREAK_PR => LB_INDIRECT,
|
|
|
121 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
122 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
123 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
124 |
UC_LINE_BREAK_ID => LB_INDIRECT,
|
|
|
125 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
126 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
127 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
128 |
UC_LINE_BREAK_BB => LB_INDIRECT,
|
|
|
129 |
UC_LINE_BREAK_B2 => LB_INDIRECT,
|
|
|
130 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
131 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
132 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
133 |
UC_LINE_BREAK_H2 => LB_INDIRECT,
|
|
|
134 |
UC_LINE_BREAK_H3 => LB_INDIRECT,
|
|
|
135 |
UC_LINE_BREAK_JL => LB_INDIRECT,
|
|
|
136 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
137 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
138 |
UC_LINE_BREAK_GL => array(UC_LINE_BREAK_OP => LB_INDIRECT,
|
|
|
139 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
140 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
141 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
142 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
143 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
144 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
145 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
146 |
UC_LINE_BREAK_PR => LB_INDIRECT,
|
|
|
147 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
148 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
149 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
150 |
UC_LINE_BREAK_ID => LB_INDIRECT,
|
|
|
151 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
152 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
153 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
154 |
UC_LINE_BREAK_BB => LB_INDIRECT,
|
|
|
155 |
UC_LINE_BREAK_B2 => LB_INDIRECT,
|
|
|
156 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
157 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
158 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
159 |
UC_LINE_BREAK_H2 => LB_INDIRECT,
|
|
|
160 |
UC_LINE_BREAK_H3 => LB_INDIRECT,
|
|
|
161 |
UC_LINE_BREAK_JL => LB_INDIRECT,
|
|
|
162 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
163 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
164 |
UC_LINE_BREAK_NS => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
165 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
166 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
167 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
168 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
169 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
170 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
171 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
172 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
173 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
174 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
175 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
176 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
177 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
178 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
179 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
180 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
181 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
182 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
183 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
184 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
185 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
186 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
187 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
188 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
189 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
190 |
UC_LINE_BREAK_EX => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
191 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
192 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
193 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
194 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
195 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
196 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
197 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
198 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
199 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
200 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
201 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
202 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
203 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
204 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
205 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
206 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
207 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
208 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
209 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
210 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
211 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
212 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
213 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
214 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
215 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
216 |
UC_LINE_BREAK_SY => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
217 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
218 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
219 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
220 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
221 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
222 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
223 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
224 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
225 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
226 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
227 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
228 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
229 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
230 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
231 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
232 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
233 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
234 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
235 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
236 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
237 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
238 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
239 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
240 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
241 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
242 |
UC_LINE_BREAK_IS => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
243 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
244 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
245 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
246 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
247 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
248 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
249 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
250 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
251 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
252 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
253 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
254 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
255 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
256 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
257 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
258 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
259 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
260 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
261 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
262 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
263 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
264 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
265 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
266 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
267 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
268 |
UC_LINE_BREAK_PR => array(UC_LINE_BREAK_OP => LB_INDIRECT,
|
|
|
269 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
270 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
271 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
272 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
273 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
274 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
275 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
276 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
277 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
278 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
279 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
280 |
UC_LINE_BREAK_ID => LB_INDIRECT,
|
|
|
281 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
282 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
283 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
284 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
285 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
286 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
287 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
288 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
289 |
UC_LINE_BREAK_H2 => LB_INDIRECT,
|
|
|
290 |
UC_LINE_BREAK_H3 => LB_INDIRECT,
|
|
|
291 |
UC_LINE_BREAK_JL => LB_INDIRECT,
|
|
|
292 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
293 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
294 |
UC_LINE_BREAK_PO => array(UC_LINE_BREAK_OP => LB_INDIRECT,
|
|
|
295 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
296 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
297 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
298 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
299 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
300 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
301 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
302 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
303 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
304 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
305 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
306 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
307 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
308 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
309 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
310 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
311 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
312 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
313 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
314 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
315 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
316 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
317 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
318 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
319 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
320 |
UC_LINE_BREAK_NU => array(UC_LINE_BREAK_OP => LB_INDIRECT,
|
|
|
321 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
322 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
323 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
324 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
325 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
326 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
327 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
328 |
UC_LINE_BREAK_PR => LB_INDIRECT,
|
|
|
329 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
330 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
331 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
332 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
333 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
334 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
335 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
336 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
337 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
338 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
339 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
340 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
341 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
342 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
343 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
344 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
345 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
346 |
UC_LINE_BREAK_AL => array(UC_LINE_BREAK_OP => LB_INDIRECT,
|
|
|
347 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
348 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
349 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
350 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
351 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
352 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
353 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
354 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
355 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
356 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
357 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
358 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
359 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
360 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
361 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
362 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
363 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
364 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
365 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
366 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
367 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
368 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
369 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
370 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
371 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
372 |
UC_LINE_BREAK_ID => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
373 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
374 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
375 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
376 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
377 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
378 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
379 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
380 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
381 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
382 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
383 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
384 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
385 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
386 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
387 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
388 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
389 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
390 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
391 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
392 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
393 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
394 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
395 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
396 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
397 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
398 |
UC_LINE_BREAK_IN => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
399 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
400 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
401 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
402 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
403 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
404 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
405 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
406 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
407 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
408 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
409 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
410 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
411 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
412 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
413 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
414 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
415 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
416 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
417 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
418 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
419 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
420 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
421 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
422 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
423 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
424 |
UC_LINE_BREAK_HY => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
425 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
426 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
427 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
428 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
429 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
430 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
431 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
432 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
433 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
434 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
435 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
436 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
437 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
438 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
439 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
440 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
441 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
442 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
443 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
444 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
445 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
446 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
447 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
448 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
449 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
450 |
UC_LINE_BREAK_BA => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
451 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
452 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
453 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
454 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
455 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
456 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
457 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
458 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
459 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
460 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
461 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
462 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
463 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
464 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
465 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
466 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
467 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
468 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
469 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
470 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
471 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
472 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
473 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
474 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
475 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
476 |
UC_LINE_BREAK_BB => array(UC_LINE_BREAK_OP => LB_INDIRECT,
|
|
|
477 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
478 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
479 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
480 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
481 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
482 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
483 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
484 |
UC_LINE_BREAK_PR => LB_INDIRECT,
|
|
|
485 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
486 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
487 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
488 |
UC_LINE_BREAK_ID => LB_INDIRECT,
|
|
|
489 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
490 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
491 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
492 |
UC_LINE_BREAK_BB => LB_INDIRECT,
|
|
|
493 |
UC_LINE_BREAK_B2 => LB_INDIRECT,
|
|
|
494 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
495 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
496 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
497 |
UC_LINE_BREAK_H2 => LB_INDIRECT,
|
|
|
498 |
UC_LINE_BREAK_H3 => LB_INDIRECT,
|
|
|
499 |
UC_LINE_BREAK_JL => LB_INDIRECT,
|
|
|
500 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
501 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
502 |
UC_LINE_BREAK_B2 => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
503 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
504 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
505 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
506 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
507 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
508 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
509 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
510 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
511 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
512 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
513 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
514 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
515 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
516 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
517 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
518 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
519 |
UC_LINE_BREAK_B2 => LB_PROHIBITED,
|
|
|
520 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
521 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
522 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
523 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
524 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
525 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
526 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
527 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
528 |
UC_LINE_BREAK_ZW => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
529 |
UC_LINE_BREAK_CL => LB_DIRECT,
|
|
|
530 |
UC_LINE_BREAK_QU => LB_DIRECT,
|
|
|
531 |
UC_LINE_BREAK_GL => LB_DIRECT,
|
|
|
532 |
UC_LINE_BREAK_NS => LB_DIRECT,
|
|
|
533 |
UC_LINE_BREAK_EX => LB_DIRECT,
|
|
|
534 |
UC_LINE_BREAK_SY => LB_DIRECT,
|
|
|
535 |
UC_LINE_BREAK_IS => LB_DIRECT,
|
|
|
536 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
537 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
538 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
539 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
540 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
541 |
UC_LINE_BREAK_IN => LB_DIRECT,
|
|
|
542 |
UC_LINE_BREAK_HY => LB_DIRECT,
|
|
|
543 |
UC_LINE_BREAK_BA => LB_DIRECT,
|
|
|
544 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
545 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
546 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
547 |
UC_LINE_BREAK_CM => LB_DIRECT,
|
|
|
548 |
UC_LINE_BREAK_WJ => LB_DIRECT,
|
|
|
549 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
550 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
551 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
552 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
553 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
554 |
UC_LINE_BREAK_CM => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
555 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
556 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
557 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
558 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
559 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
560 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
561 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
562 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
563 |
UC_LINE_BREAK_PO => LB_DIRECT,
|
|
|
564 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
565 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
566 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
567 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
568 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
569 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
570 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
571 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
572 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
573 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
574 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
575 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
576 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
577 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
578 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
579 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
580 |
UC_LINE_BREAK_WJ => array(UC_LINE_BREAK_OP => LB_INDIRECT,
|
|
|
581 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
582 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
583 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
584 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
585 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
586 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
587 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
588 |
UC_LINE_BREAK_PR => LB_INDIRECT,
|
|
|
589 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
590 |
UC_LINE_BREAK_NU => LB_INDIRECT,
|
|
|
591 |
UC_LINE_BREAK_AL => LB_INDIRECT,
|
|
|
592 |
UC_LINE_BREAK_ID => LB_INDIRECT,
|
|
|
593 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
594 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
595 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
596 |
UC_LINE_BREAK_BB => LB_INDIRECT,
|
|
|
597 |
UC_LINE_BREAK_B2 => LB_INDIRECT,
|
|
|
598 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
599 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
600 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
601 |
UC_LINE_BREAK_H2 => LB_INDIRECT,
|
|
|
602 |
UC_LINE_BREAK_H3 => LB_INDIRECT,
|
|
|
603 |
UC_LINE_BREAK_JL => LB_INDIRECT,
|
|
|
604 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
605 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
606 |
UC_LINE_BREAK_H2 => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
607 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
608 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
609 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
610 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
611 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
612 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
613 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
614 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
615 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
616 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
617 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
618 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
619 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
620 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
621 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
622 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
623 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
624 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
625 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
626 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
627 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
628 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
629 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
630 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
631 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
632 |
UC_LINE_BREAK_H3 => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
633 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
634 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
635 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
636 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
637 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
638 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
639 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
640 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
641 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
642 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
643 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
644 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
645 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
646 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
647 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
648 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
649 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
650 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
651 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
652 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
653 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
654 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
655 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
656 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
657 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
658 |
UC_LINE_BREAK_JL => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
659 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
660 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
661 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
662 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
663 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
664 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
665 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
666 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
667 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
668 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
669 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
670 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
671 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
672 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
673 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
674 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
675 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
676 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
677 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
678 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
679 |
UC_LINE_BREAK_H2 => LB_INDIRECT,
|
|
|
680 |
UC_LINE_BREAK_H3 => LB_INDIRECT,
|
|
|
681 |
UC_LINE_BREAK_JL => LB_INDIRECT,
|
|
|
682 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
683 |
UC_LINE_BREAK_JT => LB_DIRECT),
|
|
|
684 |
UC_LINE_BREAK_JV => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
685 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
686 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
687 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
688 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
689 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
690 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
691 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
692 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
693 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
694 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
695 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
696 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
697 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
698 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
699 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
700 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
701 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
702 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
703 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
704 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
705 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
706 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
707 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
708 |
UC_LINE_BREAK_JV => LB_INDIRECT,
|
|
|
709 |
UC_LINE_BREAK_JT => LB_INDIRECT),
|
|
|
710 |
UC_LINE_BREAK_JT => array(UC_LINE_BREAK_OP => LB_DIRECT,
|
|
|
711 |
UC_LINE_BREAK_CL => LB_PROHIBITED,
|
|
|
712 |
UC_LINE_BREAK_QU => LB_INDIRECT,
|
|
|
713 |
UC_LINE_BREAK_GL => LB_INDIRECT,
|
|
|
714 |
UC_LINE_BREAK_NS => LB_INDIRECT,
|
|
|
715 |
UC_LINE_BREAK_EX => LB_PROHIBITED,
|
|
|
716 |
UC_LINE_BREAK_SY => LB_PROHIBITED,
|
|
|
717 |
UC_LINE_BREAK_IS => LB_PROHIBITED,
|
|
|
718 |
UC_LINE_BREAK_PR => LB_DIRECT,
|
|
|
719 |
UC_LINE_BREAK_PO => LB_INDIRECT,
|
|
|
720 |
UC_LINE_BREAK_NU => LB_DIRECT,
|
|
|
721 |
UC_LINE_BREAK_AL => LB_DIRECT,
|
|
|
722 |
UC_LINE_BREAK_ID => LB_DIRECT,
|
|
|
723 |
UC_LINE_BREAK_IN => LB_INDIRECT,
|
|
|
724 |
UC_LINE_BREAK_HY => LB_INDIRECT,
|
|
|
725 |
UC_LINE_BREAK_BA => LB_INDIRECT,
|
|
|
726 |
UC_LINE_BREAK_BB => LB_DIRECT,
|
|
|
727 |
UC_LINE_BREAK_B2 => LB_DIRECT,
|
|
|
728 |
UC_LINE_BREAK_ZW => LB_PROHIBITED,
|
|
|
729 |
UC_LINE_BREAK_CM => LB_INDIRECT_CM,
|
|
|
730 |
UC_LINE_BREAK_WJ => LB_PROHIBITED,
|
|
|
731 |
UC_LINE_BREAK_H2 => LB_DIRECT,
|
|
|
732 |
UC_LINE_BREAK_H3 => LB_DIRECT,
|
|
|
733 |
UC_LINE_BREAK_JL => LB_DIRECT,
|
|
|
734 |
UC_LINE_BREAK_JV => LB_DIRECT,
|
|
|
735 |
UC_LINE_BREAK_JT => LB_INDIRECT));
|
|
|
736 |
|
|
|
737 |
/**
|
|
|
738 |
* See CSS 2.1 16.6.1 The 'white-space' processing model
|
|
|
739 |
*/
|
|
|
740 |
class InlineContentBuilder {
|
|
|
741 |
function InlineContentBuilder() {
|
|
|
742 |
}
|
|
|
743 |
|
|
|
744 |
function add_line_break(&$box, &$pipeline) {
|
|
|
745 |
$break_box =& new BRBox();
|
|
|
746 |
$break_box->readCSS($pipeline->get_current_css_state());
|
|
|
747 |
$box->add_child($break_box);
|
|
|
748 |
}
|
|
|
749 |
|
|
|
750 |
function build(&$box, $text, &$pipeline) {
|
|
|
751 |
error_no_method('build', get_class($this));
|
|
|
752 |
}
|
|
|
753 |
|
|
|
754 |
function break_into_lines($content) {
|
|
|
755 |
return preg_split('/[\r\n]/u', $content);
|
|
|
756 |
}
|
|
|
757 |
|
|
|
758 |
function break_into_words($content) {
|
|
|
759 |
$content = trim($content);
|
|
|
760 |
if ($content == '') {
|
|
|
761 |
return array();
|
|
|
762 |
};
|
|
|
763 |
|
|
|
764 |
// Extract Unicode characters from the raw content data
|
|
|
765 |
$ptr = 0;
|
|
|
766 |
$utf8_chars = array();
|
|
|
767 |
$ucs2_chars = array();
|
|
|
768 |
$size = strlen($content);
|
|
|
769 |
while ($ptr < $size) {
|
|
|
770 |
$utf8_char = ManagerEncoding::get_next_utf8_char($content, $ptr);
|
|
|
771 |
$utf8_chars[] = $utf8_char;
|
|
|
772 |
$ucs2_chars[] = utf8_to_code($utf8_char);
|
|
|
773 |
};
|
|
|
774 |
|
|
|
775 |
// Get unicode line breaking classes
|
|
|
776 |
$classes = array_map(array($this, 'get_line_break_class'), $ucs2_chars);
|
|
|
777 |
$this->find_line_break($classes, $breaks, count($classes));
|
|
|
778 |
|
|
|
779 |
// Make words array
|
|
|
780 |
$words = array();
|
|
|
781 |
$word = '';
|
|
|
782 |
for ($i = 0, $size = count($breaks); $i < $size; $i++) {
|
|
|
783 |
$word .= $utf8_chars[$i];
|
|
|
784 |
|
|
|
785 |
$break = $breaks[$i];
|
|
|
786 |
if ($break == LB_INDIRECT ||
|
|
|
787 |
$break == LB_INDIRECT_CM ||
|
|
|
788 |
$break == LB_DIRECT ||
|
|
|
789 |
$break == LB_EXPLICIT) {
|
|
|
790 |
$words[] = trim($word);
|
|
|
791 |
$word = '';
|
|
|
792 |
};
|
|
|
793 |
};
|
|
|
794 |
|
|
|
795 |
return $words;
|
|
|
796 |
}
|
|
|
797 |
|
|
|
798 |
function find_complex_break($current_class, $classes, &$breaks, $offset, $length) {
|
|
|
799 |
if ($offset >= $length) {
|
|
|
800 |
return 0;
|
|
|
801 |
};
|
|
|
802 |
|
|
|
803 |
for ($i = $offset; $i < $length; $i++) {
|
|
|
804 |
// TODO
|
|
|
805 |
$breaks[$i - 1] = LB_PROHIBITED;
|
|
|
806 |
if ($classes[$i] != UC_LINE_BREAK_SA) {
|
|
|
807 |
break;
|
|
|
808 |
};
|
|
|
809 |
};
|
|
|
810 |
|
|
|
811 |
return $i;
|
|
|
812 |
}
|
|
|
813 |
|
|
|
814 |
function find_line_break($classes, &$breaks, $length) {
|
|
|
815 |
if (!$length) {
|
|
|
816 |
return 0;
|
|
|
817 |
};
|
|
|
818 |
|
|
|
819 |
$class = $classes[0]; // class of 'before' character
|
|
|
820 |
|
|
|
821 |
if ($class == UC_LINE_BREAK_LF ||
|
|
|
822 |
$class == UC_LINE_BREAK_NL) {
|
|
|
823 |
$class = UL_LINE_BREAK_BK;
|
|
|
824 |
}
|
|
|
825 |
|
|
|
826 |
// loop over all pairs in the string up to a hard break
|
|
|
827 |
for ($i = 1; ($i < $length) && ($class != UC_LINE_BREAK_BK); $i++) {
|
|
|
828 |
// handle explicit breaks here
|
|
|
829 |
// handle BK, NL and LF explicitly
|
|
|
830 |
if ($classes[$i] == UC_LINE_BREAK_BK ||
|
|
|
831 |
$classes[$i] == UC_LINE_BREAK_NL ||
|
|
|
832 |
$classes[$i] == UC_LINE_BREAK_LF) {
|
|
|
833 |
$breaks[$i-1] = LB_PROHIBITED;
|
|
|
834 |
$class = UC_LINE_BREAK_BK;
|
|
|
835 |
continue;
|
|
|
836 |
}
|
|
|
837 |
|
|
|
838 |
// handle CR explicitly
|
|
|
839 |
if ($classes[$i] == UC_LINE_BREAK_CR) {
|
|
|
840 |
$breaks[$i-1] = LB_PROHIBITED;
|
|
|
841 |
$class = UC_LINE_BREAK_CR;
|
|
|
842 |
continue;
|
|
|
843 |
}
|
|
|
844 |
|
|
|
845 |
// handle spaces explicitly
|
|
|
846 |
if ($classes[$i] == UC_LINE_BREAK_SP) {
|
|
|
847 |
$breaks[$i-1] = LB_PROHIBITED;
|
|
|
848 |
continue;
|
|
|
849 |
};
|
|
|
850 |
|
|
|
851 |
// handle complex scripts in a separate function
|
|
|
852 |
if ($classes[$i] == UC_LINE_BREAK_SA) {
|
|
|
853 |
$i += $this->find_complex_break($class, $classes, $breaks, $i, $length);
|
|
|
854 |
|
|
|
855 |
if ($i < $length) {
|
|
|
856 |
$class = $classes[$i];
|
|
|
857 |
continue;
|
|
|
858 |
};
|
|
|
859 |
};
|
|
|
860 |
|
|
|
861 |
// lookup pair table information
|
|
|
862 |
$current_class = $classes[$i];
|
|
|
863 |
|
|
|
864 |
$break = $GLOBALS['_g_line_break_class_table'][$class][$current_class];
|
|
|
865 |
$breaks[$i - 1] = $break;
|
|
|
866 |
|
|
|
867 |
if ($break == LB_INDIRECT) {
|
|
|
868 |
if ($classes[$i - 1] == UC_LINE_BREAK_SP) {
|
|
|
869 |
$breaks[$i - 1] = LB_INDIRECT;
|
|
|
870 |
} else {
|
|
|
871 |
$breaks[$i - 1] = LB_PROHIBITED;
|
|
|
872 |
};
|
|
|
873 |
|
|
|
874 |
// handle breaks involving a combining mark
|
|
|
875 |
} elseif ($break == LB_INDIRECT_CM) {
|
|
|
876 |
$breaks[$i - 1]= LB_PROHIBITED;
|
|
|
877 |
|
|
|
878 |
if ($classes[$i - 1] == UC_LINE_BREAK_SP) {
|
|
|
879 |
$breaks[$i - 1] = LB_INDIRECT_CM;
|
|
|
880 |
} else {
|
|
|
881 |
continue; // do not update cls
|
|
|
882 |
};
|
|
|
883 |
} elseif ($break == LB_PROHIBITED_CM) {
|
|
|
884 |
$breaks[$i - 1] = LB_PROHIBITED_CM;
|
|
|
885 |
|
|
|
886 |
if ($classes[$i - 1] != UC_LINE_BREAK_SP) {
|
|
|
887 |
continue;
|
|
|
888 |
};
|
|
|
889 |
};
|
|
|
890 |
|
|
|
891 |
// save cls of 'before' character (unless bypassed by 'continue')
|
|
|
892 |
$class = $classes[$i];
|
|
|
893 |
};
|
|
|
894 |
|
|
|
895 |
$breaks[$i-1] = LB_EXPLICIT;
|
|
|
896 |
|
|
|
897 |
return $i;
|
|
|
898 |
}
|
|
|
899 |
|
|
|
900 |
function is_break_allowed($previous_class, $current_class) {
|
|
|
901 |
return true;
|
|
|
902 |
}
|
|
|
903 |
|
|
|
904 |
function get_line_break_class($ucs2_char) {
|
|
|
905 |
static $class_cache = array();
|
|
|
906 |
|
|
|
907 |
if (!isset($class_cache[$ucs2_char])) {
|
|
|
908 |
$table_handle = $this->get_line_break_class_table_handle();
|
|
|
909 |
fseek($table_handle, $ucs2_char /* as integer */ , SEEK_SET);
|
|
|
910 |
$class_cache[$ucs2_char] = ord(fread($table_handle, 1));
|
|
|
911 |
};
|
|
|
912 |
|
|
|
913 |
// Apply rule LB1 from the Unicode algorithm:
|
|
|
914 |
//
|
|
|
915 |
// Assign a line breaking class to each code point of the
|
|
|
916 |
// input. Resolve AI, CB, SA, SG, and XX into other line breaking
|
|
|
917 |
// classes depending on criteria outside the scope of this
|
|
|
918 |
// algorithm.
|
|
|
919 |
//
|
|
|
920 |
// In the absence of such criteria, it is recommended that classes
|
|
|
921 |
// AI, SA, SG, and XX be resolved to AL, except that characters of
|
|
|
922 |
// class SA that have General_Category Mn or Mc be resolved to CM
|
|
|
923 |
// (see SA). Unresolved class CB is handled in rule LB20.
|
|
|
924 |
|
|
|
925 |
// Resolve AI, SA, SG, and XX to AL
|
|
|
926 |
if (in_array($class_cache[$ucs2_char],
|
|
|
927 |
array(UC_LINE_BREAK_AI,
|
|
|
928 |
UC_LINE_BREAK_SA,
|
|
|
929 |
UC_LINE_BREAK_SG,
|
|
|
930 |
UC_LINE_BREAK_XX))) {
|
|
|
931 |
return UC_LINE_BREAK_AL;
|
|
|
932 |
};
|
|
|
933 |
|
|
|
934 |
return $class_cache[$ucs2_char];
|
|
|
935 |
}
|
|
|
936 |
|
|
|
937 |
function get_line_break_class_table_handle() {
|
|
|
938 |
static $table_handle = null;
|
|
|
939 |
|
|
|
940 |
if (is_null($table_handle)) {
|
|
|
941 |
$filename = CACHE_DIR.'unicode.lb.classes.dat';
|
|
|
942 |
if (!file_exists($filename)) {
|
|
|
943 |
$this->generate_line_break_class_table($filename);
|
|
|
944 |
};
|
|
|
945 |
|
|
|
946 |
$table_handle = fopen($filename, 'rb');
|
|
|
947 |
flock($table_handle, LOCK_SH);
|
|
|
948 |
};
|
|
|
949 |
|
|
|
950 |
return $table_handle;
|
|
|
951 |
}
|
|
|
952 |
|
|
|
953 |
function generate_line_break_class_table($output_filename) {
|
|
|
954 |
$class_codes = array('BK' => 1,
|
|
|
955 |
'CR' => 2,
|
|
|
956 |
'LF' => 3,
|
|
|
957 |
'CM' => 4,
|
|
|
958 |
'NL' => 5,
|
|
|
959 |
'SG' => 6,
|
|
|
960 |
'WJ' => 7,
|
|
|
961 |
'ZW' => 8,
|
|
|
962 |
'GL' => 9,
|
|
|
963 |
'SP' => 10,
|
|
|
964 |
'B2' => 11,
|
|
|
965 |
'BA' => 12,
|
|
|
966 |
'BB' => 13,
|
|
|
967 |
'HY' => 14,
|
|
|
968 |
'CB' => 15,
|
|
|
969 |
'CL' => 16,
|
|
|
970 |
'EX' => 17,
|
|
|
971 |
'IN' => 18,
|
|
|
972 |
'NS' => 19,
|
|
|
973 |
'OP' => 20,
|
|
|
974 |
'QU' => 21,
|
|
|
975 |
'IS' => 22,
|
|
|
976 |
'NU' => 23,
|
|
|
977 |
'PO' => 24,
|
|
|
978 |
'PR' => 25,
|
|
|
979 |
'SY' => 26,
|
|
|
980 |
'AI' => 27,
|
|
|
981 |
'AL' => 28,
|
|
|
982 |
'H2' => 29,
|
|
|
983 |
'H3' => 30,
|
|
|
984 |
'ID' => 31,
|
|
|
985 |
'JL' => 32,
|
|
|
986 |
'JV' => 33,
|
|
|
987 |
'JT' => 34,
|
|
|
988 |
'SA' => 35,
|
|
|
989 |
'XX' => 36);
|
|
|
990 |
|
|
|
991 |
$output_handle = fopen($output_filename, 'wb');
|
|
|
992 |
flock($output_handle, LOCK_EX);
|
|
|
993 |
|
|
|
994 |
$input_handle = fopen(HTML2PS_DIR.'/data/LineBreak.txt', 'r');
|
|
|
995 |
$last_position = 0;
|
|
|
996 |
while ($line = fgets($input_handle)) {
|
|
|
997 |
$line = trim($line);
|
|
|
998 |
|
|
|
999 |
if (strlen($line) == 0 || $line[0] == '#') {
|
|
|
1000 |
continue;
|
|
|
1001 |
};
|
|
|
1002 |
|
|
|
1003 |
if (preg_match('/^([0-9a-f]+);(\w\w) #/i', $line, $matches)) {
|
|
|
1004 |
$unicode_position = hexdec($matches[1]);
|
|
|
1005 |
$class = $matches[2];
|
|
|
1006 |
|
|
|
1007 |
if ($unicode_position > $last_position + 1) {
|
|
|
1008 |
fwrite($output_handle, str_repeat(chr(0), $unicode_position - $last_position - 1));
|
|
|
1009 |
};
|
|
|
1010 |
|
|
|
1011 |
fwrite($output_handle, chr($class_codes[$class]));
|
|
|
1012 |
|
|
|
1013 |
$last_position = $unicode_position;
|
|
|
1014 |
} elseif (preg_match('/^([0-9a-f]+)\.\.([0-9a-f]+);(\w\w) #/i', $line, $matches)) {
|
|
|
1015 |
$unicode_start_position = hexdec($matches[1]);
|
|
|
1016 |
$unicode_end_position = hexdec($matches[2]);
|
|
|
1017 |
$class = $matches[3];
|
|
|
1018 |
|
|
|
1019 |
if ($unicode_start_position > $last_position + 1) {
|
|
|
1020 |
fwrite($output_handle, str_repeat(chr(0), $unicode_start_position - $last_position - 1));
|
|
|
1021 |
};
|
|
|
1022 |
|
|
|
1023 |
fwrite($output_handle, str_repeat(chr($class_codes[$class]), $unicode_end_position - $unicode_start_position + 1));
|
|
|
1024 |
|
|
|
1025 |
$last_position = $unicode_end_position;
|
|
|
1026 |
} else {
|
|
|
1027 |
var_dump($line); die();
|
|
|
1028 |
}
|
|
|
1029 |
};
|
|
|
1030 |
|
|
|
1031 |
fclose($input_handle);
|
|
|
1032 |
|
|
|
1033 |
flock($output_handle, LOCK_UN);
|
|
|
1034 |
fclose($output_handle);
|
|
|
1035 |
}
|
|
|
1036 |
|
|
|
1037 |
function collapse_whitespace($content) {
|
|
|
1038 |
return preg_replace('/[\r\n\t ]+/u', ' ', $content);
|
|
|
1039 |
}
|
|
|
1040 |
|
|
|
1041 |
function remove_leading_linefeeds($content) {
|
|
|
1042 |
return preg_replace('/^ *[\r\n]+/u', '', $content);
|
|
|
1043 |
}
|
|
|
1044 |
|
|
|
1045 |
function remove_trailing_linefeeds($content) {
|
|
|
1046 |
return preg_replace('/[\r\n]+$/u', '', $content);
|
|
|
1047 |
}
|
|
|
1048 |
}
|
|
|
1049 |
|
|
|
1050 |
?>
|