1 |
|
|
/* $OpenBSD: yacc.y,v 1.10 2016/05/08 15:25:44 schwarze Exp $ */ |
2 |
|
|
/* $NetBSD: yacc.y,v 1.24 2004/01/05 23:23:36 jmmv Exp $ */ |
3 |
|
|
|
4 |
|
|
%{ |
5 |
|
|
/*- |
6 |
|
|
* Copyright (c) 1993 |
7 |
|
|
* The Regents of the University of California. All rights reserved. |
8 |
|
|
* |
9 |
|
|
* This code is derived from software contributed to Berkeley by |
10 |
|
|
* Paul Borman at Krystal Technologies. |
11 |
|
|
* |
12 |
|
|
* Redistribution and use in source and binary forms, with or without |
13 |
|
|
* modification, are permitted provided that the following conditions |
14 |
|
|
* are met: |
15 |
|
|
* 1. Redistributions of source code must retain the above copyright |
16 |
|
|
* notice, this list of conditions and the following disclaimer. |
17 |
|
|
* 2. Redistributions in binary form must reproduce the above copyright |
18 |
|
|
* notice, this list of conditions and the following disclaimer in the |
19 |
|
|
* documentation and/or other materials provided with the distribution. |
20 |
|
|
* 3. Neither the name of the University nor the names of its contributors |
21 |
|
|
* may be used to endorse or promote products derived from this software |
22 |
|
|
* without specific prior written permission. |
23 |
|
|
* |
24 |
|
|
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND |
25 |
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
26 |
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
27 |
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE |
28 |
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
29 |
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS |
30 |
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
31 |
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
32 |
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY |
33 |
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
34 |
|
|
* SUCH DAMAGE. |
35 |
|
|
*/ |
36 |
|
|
|
37 |
|
|
#include <sys/types.h> |
38 |
|
|
#include <netinet/in.h> /* Needed by <arpa/inet.h> on NetBSD 1.5. */ |
39 |
|
|
#include <arpa/inet.h> /* Needed for htonl on POSIX systems. */ |
40 |
|
|
|
41 |
|
|
#include <err.h> |
42 |
|
|
#include "locale/runetype.h" |
43 |
|
|
#include <stddef.h> |
44 |
|
|
#include <stdio.h> |
45 |
|
|
#include <stdlib.h> |
46 |
|
|
#include <string.h> |
47 |
|
|
#include <unistd.h> |
48 |
|
|
#include <ctype.h> |
49 |
|
|
|
50 |
|
|
#include "ldef.h" |
51 |
|
|
|
52 |
|
|
const char *locale_file = "<stdout>"; |
53 |
|
|
|
54 |
|
|
rune_map maplower = { { 0, }, }; |
55 |
|
|
rune_map mapupper = { { 0, }, }; |
56 |
|
|
rune_map types = { { 0, }, }; |
57 |
|
|
|
58 |
|
|
_RuneLocale new_locale = { { 0, }, }; |
59 |
|
|
|
60 |
|
|
rune_t charsetbits = (rune_t)0x00000000; |
61 |
|
|
#if 0 |
62 |
|
|
rune_t charsetmask = (rune_t)0x0000007f; |
63 |
|
|
#endif |
64 |
|
|
rune_t charsetmask = (rune_t)0xffffffff; |
65 |
|
|
|
66 |
|
|
void set_map(rune_map *, rune_list *, u_int32_t); |
67 |
|
|
void add_map(rune_map *, rune_list *, u_int32_t); |
68 |
|
|
|
69 |
|
|
int main(int, char *[]); |
70 |
|
|
int yyerror(const char *s); |
71 |
|
|
void *xmalloc(size_t sz); |
72 |
|
|
u_int32_t *xlalloc(size_t sz); |
73 |
|
|
u_int32_t *xrelalloc(u_int32_t *old, size_t sz); |
74 |
|
|
void dump_tables(void); |
75 |
|
|
int yyparse(void); |
76 |
|
|
extern int yylex(void); |
77 |
|
|
%} |
78 |
|
|
|
79 |
|
|
%union { |
80 |
|
|
rune_t rune; |
81 |
|
|
int i; |
82 |
|
|
char *str; |
83 |
|
|
|
84 |
|
|
rune_list *list; |
85 |
|
|
} |
86 |
|
|
|
87 |
|
|
%token <rune> RUNE |
88 |
|
|
%token LBRK |
89 |
|
|
%token RBRK |
90 |
|
|
%token THRU |
91 |
|
|
%token MAPLOWER |
92 |
|
|
%token MAPUPPER |
93 |
|
|
%token DIGITMAP |
94 |
|
|
%token <i> LIST |
95 |
|
|
%token <str> VARIABLE |
96 |
|
|
%token CHARSET |
97 |
|
|
%token ENCODING |
98 |
|
|
%token INVALID |
99 |
|
|
%token <str> STRING |
100 |
|
|
|
101 |
|
|
%type <list> list |
102 |
|
|
%type <list> map |
103 |
|
|
|
104 |
|
|
|
105 |
|
|
%% |
106 |
|
|
|
107 |
|
|
locale : /* empty */ |
108 |
|
|
| table |
109 |
|
|
{ dump_tables(); } |
110 |
|
|
; |
111 |
|
|
|
112 |
|
|
table : entry |
113 |
|
|
| table entry |
114 |
|
|
; |
115 |
|
|
|
116 |
|
|
entry : ENCODING STRING |
117 |
|
|
{ strncpy(new_locale.rl_encoding, $2, sizeof(new_locale.rl_encoding)); } |
118 |
|
|
| VARIABLE |
119 |
|
|
{ new_locale.rl_variable_len = strlen($1) + 1; |
120 |
|
|
new_locale.rl_variable = strdup($1); |
121 |
|
|
} |
122 |
|
|
| CHARSET RUNE |
123 |
|
|
{ charsetbits = $2; charsetmask = 0x0000007f; } |
124 |
|
|
| CHARSET RUNE RUNE |
125 |
|
|
{ charsetbits = $2; charsetmask = $3; } |
126 |
|
|
| CHARSET STRING |
127 |
|
|
{ int final = $2[strlen($2) - 1] & 0x7f; |
128 |
|
|
charsetbits = final << 24; |
129 |
|
|
if ($2[0] == '$') { |
130 |
|
|
charsetmask = 0x00007f7f; |
131 |
|
|
if (strchr(",-./", $2[1])) |
132 |
|
|
charsetbits |= 0x80; |
133 |
|
|
if (0xd0 <= final && final <= 0xdf) |
134 |
|
|
charsetmask |= 0x007f0000; |
135 |
|
|
} else { |
136 |
|
|
charsetmask = 0x0000007f; |
137 |
|
|
if (strchr(",-./", $2[0])) |
138 |
|
|
charsetbits |= 0x80; |
139 |
|
|
if (strlen($2) == 2 && $2[0] == '!') |
140 |
|
|
charsetbits |= ((0x80 | $2[0]) << 16); |
141 |
|
|
} |
142 |
|
|
|
143 |
|
|
/* |
144 |
|
|
* special rules |
145 |
|
|
*/ |
146 |
|
|
if (charsetbits == ('B' << 24) |
147 |
|
|
&& charsetmask == 0x0000007f) { |
148 |
|
|
/*ASCII: 94B*/ |
149 |
|
|
charsetbits = 0; |
150 |
|
|
charsetmask = 0x0000007f; |
151 |
|
|
} else if (charsetbits == (('A' << 24) | 0x80) |
152 |
|
|
&& charsetmask == 0x0000007f) { |
153 |
|
|
/*Latin1: 96A*/ |
154 |
|
|
charsetbits = 0x80; |
155 |
|
|
charsetmask = 0x0000007f; |
156 |
|
|
} |
157 |
|
|
} |
158 |
|
|
| INVALID RUNE |
159 |
|
|
{ new_locale.rl_invalid_rune = $2; } |
160 |
|
|
| LIST list |
161 |
|
|
{ set_map(&types, $2, $1); } |
162 |
|
|
| MAPLOWER map |
163 |
|
|
{ set_map(&maplower, $2, 0); } |
164 |
|
|
| MAPUPPER map |
165 |
|
|
{ set_map(&mapupper, $2, 0); } |
166 |
|
|
| DIGITMAP mapignore |
167 |
|
|
{ } |
168 |
|
|
; |
169 |
|
|
|
170 |
|
|
list : RUNE |
171 |
|
|
{ |
172 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
173 |
|
|
$$->min = ($1 & charsetmask) | charsetbits; |
174 |
|
|
$$->max = ($1 & charsetmask) | charsetbits; |
175 |
|
|
$$->map = 0; |
176 |
|
|
$$->next = 0; |
177 |
|
|
} |
178 |
|
|
| RUNE THRU RUNE |
179 |
|
|
{ |
180 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
181 |
|
|
$$->min = ($1 & charsetmask) | charsetbits; |
182 |
|
|
$$->max = ($3 & charsetmask) | charsetbits; |
183 |
|
|
$$->map = 0; |
184 |
|
|
$$->next = 0; |
185 |
|
|
} |
186 |
|
|
| list RUNE |
187 |
|
|
{ |
188 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
189 |
|
|
$$->min = ($2 & charsetmask) | charsetbits; |
190 |
|
|
$$->max = ($2 & charsetmask) | charsetbits; |
191 |
|
|
$$->map = 0; |
192 |
|
|
$$->next = $1; |
193 |
|
|
} |
194 |
|
|
| list RUNE THRU RUNE |
195 |
|
|
{ |
196 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
197 |
|
|
$$->min = ($2 & charsetmask) | charsetbits; |
198 |
|
|
$$->max = ($4 & charsetmask) | charsetbits; |
199 |
|
|
$$->map = 0; |
200 |
|
|
$$->next = $1; |
201 |
|
|
} |
202 |
|
|
; |
203 |
|
|
|
204 |
|
|
map : LBRK RUNE RUNE RBRK |
205 |
|
|
{ |
206 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
207 |
|
|
$$->min = ($2 & charsetmask) | charsetbits; |
208 |
|
|
$$->max = ($2 & charsetmask) | charsetbits; |
209 |
|
|
$$->map = $3; |
210 |
|
|
$$->next = 0; |
211 |
|
|
} |
212 |
|
|
| map LBRK RUNE RUNE RBRK |
213 |
|
|
{ |
214 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
215 |
|
|
$$->min = ($3 & charsetmask) | charsetbits; |
216 |
|
|
$$->max = ($3 & charsetmask) | charsetbits; |
217 |
|
|
$$->map = $4; |
218 |
|
|
$$->next = $1; |
219 |
|
|
} |
220 |
|
|
| LBRK RUNE THRU RUNE ':' RUNE RBRK |
221 |
|
|
{ |
222 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
223 |
|
|
$$->min = ($2 & charsetmask) | charsetbits; |
224 |
|
|
$$->max = ($4 & charsetmask) | charsetbits; |
225 |
|
|
$$->map = $6; |
226 |
|
|
$$->next = 0; |
227 |
|
|
} |
228 |
|
|
| map LBRK RUNE THRU RUNE ':' RUNE RBRK |
229 |
|
|
{ |
230 |
|
|
$$ = xmalloc(sizeof(rune_list)); |
231 |
|
|
$$->min = ($3 & charsetmask) | charsetbits; |
232 |
|
|
$$->max = ($5 & charsetmask) | charsetbits; |
233 |
|
|
$$->map = $7; |
234 |
|
|
$$->next = $1; |
235 |
|
|
} |
236 |
|
|
; |
237 |
|
|
|
238 |
|
|
mapignore : LBRK RUNE RUNE RBRK { } |
239 |
|
|
| map LBRK RUNE RUNE RBRK { } |
240 |
|
|
| LBRK RUNE THRU RUNE ':' RUNE RBRK { } |
241 |
|
|
| map LBRK RUNE THRU RUNE ':' RUNE RBRK { } |
242 |
|
|
; |
243 |
|
|
%% |
244 |
|
|
|
245 |
|
|
int debug = 0; |
246 |
|
|
FILE *ofile; |
247 |
|
|
|
248 |
|
|
int |
249 |
|
|
main(int ac, char *av[]) |
250 |
|
|
{ |
251 |
|
|
int x; |
252 |
|
|
|
253 |
|
|
extern char *optarg; |
254 |
|
|
extern int optind; |
255 |
|
|
|
256 |
|
|
if (pledge("stdio rpath wpath cpath", NULL) == -1) { |
257 |
|
|
perror("pledge"); |
258 |
|
|
exit(1); |
259 |
|
|
} |
260 |
|
|
|
261 |
|
|
while ((x = getopt(ac, av, "do:")) != -1) { |
262 |
|
|
switch(x) { |
263 |
|
|
case 'd': |
264 |
|
|
debug = 1; |
265 |
|
|
break; |
266 |
|
|
case 'o': |
267 |
|
|
locale_file = optarg; |
268 |
|
|
if ((ofile = fopen(locale_file, "w")) == 0) |
269 |
|
|
err(1, "unable to open output file %s", locale_file); |
270 |
|
|
break; |
271 |
|
|
default: |
272 |
|
|
usage: |
273 |
|
|
fprintf(stderr, |
274 |
|
|
"usage: mklocale [-d] [src-file] language/LC_CTYPE\n" |
275 |
|
|
" mklocale [-d] -o language/LC_CTYPE src-file\n"); |
276 |
|
|
exit(1); |
277 |
|
|
} |
278 |
|
|
} |
279 |
|
|
|
280 |
|
|
switch (ac - optind) { |
281 |
|
|
case 0: |
282 |
|
|
break; |
283 |
|
|
case 1: |
284 |
|
|
if (freopen(av[optind], "r", stdin) == 0) |
285 |
|
|
err(1, "unable to open input file %s", av[optind]); |
286 |
|
|
break; |
287 |
|
|
default: |
288 |
|
|
goto usage; |
289 |
|
|
} |
290 |
|
|
for (x = 0; x < _CACHED_RUNES; ++x) { |
291 |
|
|
mapupper.map[x] = x; |
292 |
|
|
maplower.map[x] = x; |
293 |
|
|
} |
294 |
|
|
new_locale.rl_invalid_rune = _DEFAULT_INVALID_RUNE; |
295 |
|
|
memcpy(new_locale.rl_magic, _RUNE_MAGIC_1, sizeof(new_locale.rl_magic)); |
296 |
|
|
|
297 |
|
|
yyparse(); |
298 |
|
|
|
299 |
|
|
return 0; |
300 |
|
|
} |
301 |
|
|
|
302 |
|
|
int |
303 |
|
|
yyerror(const char *s) |
304 |
|
|
{ |
305 |
|
|
fprintf(stderr, "%s\n", s); |
306 |
|
|
|
307 |
|
|
return 0; |
308 |
|
|
} |
309 |
|
|
|
310 |
|
|
void * |
311 |
|
|
xmalloc(size_t sz) |
312 |
|
|
{ |
313 |
|
|
void *r = malloc(sz); |
314 |
|
|
if (!r) { |
315 |
|
|
perror("xmalloc"); |
316 |
|
|
abort(); |
317 |
|
|
} |
318 |
|
|
return(r); |
319 |
|
|
} |
320 |
|
|
|
321 |
|
|
u_int32_t * |
322 |
|
|
xlalloc(size_t sz) |
323 |
|
|
{ |
324 |
|
|
u_int32_t *r = reallocarray(NULL, sz, sizeof(u_int32_t)); |
325 |
|
|
if (!r) { |
326 |
|
|
perror("xlalloc"); |
327 |
|
|
abort(); |
328 |
|
|
} |
329 |
|
|
return(r); |
330 |
|
|
} |
331 |
|
|
|
332 |
|
|
u_int32_t * |
333 |
|
|
xrelalloc(u_int32_t *old, size_t sz) |
334 |
|
|
{ |
335 |
|
|
u_int32_t *r = reallocarray(old, sz, sizeof(u_int32_t)); |
336 |
|
|
if (!r) { |
337 |
|
|
perror("xrelalloc"); |
338 |
|
|
abort(); |
339 |
|
|
} |
340 |
|
|
return(r); |
341 |
|
|
} |
342 |
|
|
|
343 |
|
|
void |
344 |
|
|
set_map(rune_map *map, rune_list *list, u_int32_t flag) |
345 |
|
|
{ |
346 |
|
|
list->map &= charsetmask; |
347 |
|
|
list->map |= charsetbits; |
348 |
|
|
while (list) { |
349 |
|
|
rune_list *nlist = list->next; |
350 |
|
|
add_map(map, list, flag); |
351 |
|
|
list = nlist; |
352 |
|
|
} |
353 |
|
|
} |
354 |
|
|
|
355 |
|
|
void |
356 |
|
|
add_map(rune_map *map, rune_list *list, u_int32_t flag) |
357 |
|
|
{ |
358 |
|
|
rune_t i; |
359 |
|
|
rune_list *lr = 0; |
360 |
|
|
rune_list *r; |
361 |
|
|
rune_t run; |
362 |
|
|
|
363 |
|
|
while (list->min < _CACHED_RUNES && list->min <= list->max) { |
364 |
|
|
if (flag) |
365 |
|
|
map->map[list->min++] |= flag; |
366 |
|
|
else |
367 |
|
|
map->map[list->min++] = list->map++; |
368 |
|
|
} |
369 |
|
|
|
370 |
|
|
if (list->min > list->max) { |
371 |
|
|
free(list); |
372 |
|
|
return; |
373 |
|
|
} |
374 |
|
|
|
375 |
|
|
run = list->max - list->min + 1; |
376 |
|
|
|
377 |
|
|
if (!(r = map->root) || (list->max < r->min - 1) |
378 |
|
|
|| (!flag && list->max == r->min - 1)) { |
379 |
|
|
if (flag) { |
380 |
|
|
list->types = xlalloc(run); |
381 |
|
|
for (i = 0; i < run; ++i) |
382 |
|
|
list->types[i] = flag; |
383 |
|
|
} |
384 |
|
|
list->next = map->root; |
385 |
|
|
map->root = list; |
386 |
|
|
return; |
387 |
|
|
} |
388 |
|
|
|
389 |
|
|
for (r = map->root; r && r->max + 1 < list->min; r = r->next) |
390 |
|
|
lr = r; |
391 |
|
|
|
392 |
|
|
if (!r) { |
393 |
|
|
/* |
394 |
|
|
* We are off the end. |
395 |
|
|
*/ |
396 |
|
|
if (flag) { |
397 |
|
|
list->types = xlalloc(run); |
398 |
|
|
for (i = 0; i < run; ++i) |
399 |
|
|
list->types[i] = flag; |
400 |
|
|
} |
401 |
|
|
list->next = 0; |
402 |
|
|
lr->next = list; |
403 |
|
|
return; |
404 |
|
|
} |
405 |
|
|
|
406 |
|
|
if (list->max < r->min - 1) { |
407 |
|
|
/* |
408 |
|
|
* We come before this range and we do not intersect it. |
409 |
|
|
* We are not before the root node, it was checked before the loop |
410 |
|
|
*/ |
411 |
|
|
if (flag) { |
412 |
|
|
list->types = xlalloc(run); |
413 |
|
|
for (i = 0; i < run; ++i) |
414 |
|
|
list->types[i] = flag; |
415 |
|
|
} |
416 |
|
|
list->next = lr->next; |
417 |
|
|
lr->next = list; |
418 |
|
|
return; |
419 |
|
|
} |
420 |
|
|
|
421 |
|
|
/* |
422 |
|
|
* At this point we have found that we at least intersect with |
423 |
|
|
* the range pointed to by `r', we might intersect with one or |
424 |
|
|
* more ranges beyond `r' as well. |
425 |
|
|
*/ |
426 |
|
|
|
427 |
|
|
if (!flag && list->map - list->min != r->map - r->min) { |
428 |
|
|
/* |
429 |
|
|
* There are only two cases when we are doing case maps and |
430 |
|
|
* our maps needn't have the same offset. When we are adjoining |
431 |
|
|
* but not intersecting. |
432 |
|
|
*/ |
433 |
|
|
if (list->max + 1 == r->min) { |
434 |
|
|
lr->next = list; |
435 |
|
|
list->next = r; |
436 |
|
|
return; |
437 |
|
|
} |
438 |
|
|
if (list->min - 1 == r->max) { |
439 |
|
|
list->next = r->next; |
440 |
|
|
r->next = list; |
441 |
|
|
return; |
442 |
|
|
} |
443 |
|
|
fprintf(stderr, "Error: conflicting map entries\n"); |
444 |
|
|
exit(1); |
445 |
|
|
} |
446 |
|
|
|
447 |
|
|
if (list->min >= r->min && list->max <= r->max) { |
448 |
|
|
/* |
449 |
|
|
* Subset case. |
450 |
|
|
*/ |
451 |
|
|
|
452 |
|
|
if (flag) { |
453 |
|
|
for (i = list->min; i <= list->max; ++i) |
454 |
|
|
r->types[i - r->min] |= flag; |
455 |
|
|
} |
456 |
|
|
free(list); |
457 |
|
|
return; |
458 |
|
|
} |
459 |
|
|
if (list->min <= r->min && list->max >= r->max) { |
460 |
|
|
/* |
461 |
|
|
* Superset case. Make him big enough to hold us. |
462 |
|
|
* We might need to merge with the guy after him. |
463 |
|
|
*/ |
464 |
|
|
if (flag) { |
465 |
|
|
list->types = xlalloc(list->max - list->min + 1); |
466 |
|
|
|
467 |
|
|
for (i = list->min; i <= list->max; ++i) |
468 |
|
|
list->types[i - list->min] = flag; |
469 |
|
|
|
470 |
|
|
for (i = r->min; i <= r->max; ++i) |
471 |
|
|
list->types[i - list->min] |= r->types[i - r->min]; |
472 |
|
|
|
473 |
|
|
free(r->types); |
474 |
|
|
r->types = list->types; |
475 |
|
|
} else { |
476 |
|
|
r->map = list->map; |
477 |
|
|
} |
478 |
|
|
r->min = list->min; |
479 |
|
|
r->max = list->max; |
480 |
|
|
free(list); |
481 |
|
|
} else if (list->min < r->min) { |
482 |
|
|
/* |
483 |
|
|
* Our tail intersects his head. |
484 |
|
|
*/ |
485 |
|
|
if (flag) { |
486 |
|
|
list->types = xlalloc(r->max - list->min + 1); |
487 |
|
|
|
488 |
|
|
for (i = r->min; i <= r->max; ++i) |
489 |
|
|
list->types[i - list->min] = r->types[i - r->min]; |
490 |
|
|
|
491 |
|
|
for (i = list->min; i < r->min; ++i) |
492 |
|
|
list->types[i - list->min] = flag; |
493 |
|
|
|
494 |
|
|
for (i = r->min; i <= list->max; ++i) |
495 |
|
|
list->types[i - list->min] |= flag; |
496 |
|
|
|
497 |
|
|
free(r->types); |
498 |
|
|
r->types = list->types; |
499 |
|
|
} else { |
500 |
|
|
r->map = list->map; |
501 |
|
|
} |
502 |
|
|
r->min = list->min; |
503 |
|
|
free(list); |
504 |
|
|
return; |
505 |
|
|
} else { |
506 |
|
|
/* |
507 |
|
|
* Our head intersects his tail. |
508 |
|
|
* We might need to merge with the guy after him. |
509 |
|
|
*/ |
510 |
|
|
if (flag) { |
511 |
|
|
r->types = xrelalloc(r->types, list->max - r->min + 1); |
512 |
|
|
|
513 |
|
|
for (i = list->min; i <= r->max; ++i) |
514 |
|
|
r->types[i - r->min] |= flag; |
515 |
|
|
|
516 |
|
|
for (i = r->max+1; i <= list->max; ++i) |
517 |
|
|
r->types[i - r->min] = flag; |
518 |
|
|
} |
519 |
|
|
r->max = list->max; |
520 |
|
|
free(list); |
521 |
|
|
} |
522 |
|
|
|
523 |
|
|
/* |
524 |
|
|
* Okay, check to see if we grew into the next guy(s) |
525 |
|
|
*/ |
526 |
|
|
while ((lr = r->next) && r->max >= lr->min) { |
527 |
|
|
if (flag) { |
528 |
|
|
if (r->max >= lr->max) { |
529 |
|
|
/* |
530 |
|
|
* Good, we consumed all of him. |
531 |
|
|
*/ |
532 |
|
|
for (i = lr->min; i <= lr->max; ++i) |
533 |
|
|
r->types[i - r->min] |= lr->types[i - lr->min]; |
534 |
|
|
} else { |
535 |
|
|
/* |
536 |
|
|
* "append" him on to the end of us. |
537 |
|
|
*/ |
538 |
|
|
r->types = xrelalloc(r->types, lr->max - r->min + 1); |
539 |
|
|
|
540 |
|
|
for (i = lr->min; i <= r->max; ++i) |
541 |
|
|
r->types[i - r->min] |= lr->types[i - lr->min]; |
542 |
|
|
|
543 |
|
|
for (i = r->max+1; i <= lr->max; ++i) |
544 |
|
|
r->types[i - r->min] = lr->types[i - lr->min]; |
545 |
|
|
|
546 |
|
|
r->max = lr->max; |
547 |
|
|
} |
548 |
|
|
} else { |
549 |
|
|
if (lr->max > r->max) |
550 |
|
|
r->max = lr->max; |
551 |
|
|
} |
552 |
|
|
|
553 |
|
|
r->next = lr->next; |
554 |
|
|
|
555 |
|
|
if (flag) |
556 |
|
|
free(lr->types); |
557 |
|
|
free(lr); |
558 |
|
|
} |
559 |
|
|
} |
560 |
|
|
|
561 |
|
|
void |
562 |
|
|
dump_tables() |
563 |
|
|
{ |
564 |
|
|
int x, n; |
565 |
|
|
rune_list *list; |
566 |
|
|
_FileRuneLocale file_new_locale; |
567 |
|
|
FILE *fp = (ofile ? ofile : stdout); |
568 |
|
|
|
569 |
|
|
memset(&file_new_locale, 0, sizeof(file_new_locale)); |
570 |
|
|
|
571 |
|
|
/* |
572 |
|
|
* See if we can compress some of the istype arrays |
573 |
|
|
*/ |
574 |
|
|
for(list = types.root; list; list = list->next) { |
575 |
|
|
list->map = list->types[0]; |
576 |
|
|
for (x = 1; x < list->max - list->min + 1; ++x) { |
577 |
|
|
if (list->types[x] != list->map) { |
578 |
|
|
list->map = 0; |
579 |
|
|
break; |
580 |
|
|
} |
581 |
|
|
} |
582 |
|
|
} |
583 |
|
|
|
584 |
|
|
memcpy(&file_new_locale.frl_magic, new_locale.rl_magic, |
585 |
|
|
sizeof(file_new_locale.frl_magic)); |
586 |
|
|
memcpy(&file_new_locale.frl_encoding, new_locale.rl_encoding, |
587 |
|
|
sizeof(file_new_locale.frl_encoding)); |
588 |
|
|
|
589 |
|
|
file_new_locale.frl_invalid_rune = htonl(new_locale.rl_invalid_rune); |
590 |
|
|
|
591 |
|
|
/* |
592 |
|
|
* Fill in our tables. Do this in network order so that |
593 |
|
|
* diverse machines have a chance of sharing data. |
594 |
|
|
* (Machines like Crays cannot share with little machines due to |
595 |
|
|
* word size. Sigh. We tried.) |
596 |
|
|
*/ |
597 |
|
|
for (x = 0; x < _CACHED_RUNES; ++x) { |
598 |
|
|
file_new_locale.frl_runetype[x] = htonl(types.map[x]); |
599 |
|
|
file_new_locale.frl_maplower[x] = htonl(maplower.map[x]); |
600 |
|
|
file_new_locale.frl_mapupper[x] = htonl(mapupper.map[x]); |
601 |
|
|
} |
602 |
|
|
|
603 |
|
|
/* |
604 |
|
|
* Count up how many ranges we will need for each of the extents. |
605 |
|
|
*/ |
606 |
|
|
list = types.root; |
607 |
|
|
|
608 |
|
|
while (list) { |
609 |
|
|
new_locale.rl_runetype_ext.rr_nranges++; |
610 |
|
|
list = list->next; |
611 |
|
|
} |
612 |
|
|
file_new_locale.frl_runetype_ext.frr_nranges = |
613 |
|
|
htonl(new_locale.rl_runetype_ext.rr_nranges); |
614 |
|
|
|
615 |
|
|
list = maplower.root; |
616 |
|
|
|
617 |
|
|
while (list) { |
618 |
|
|
new_locale.rl_maplower_ext.rr_nranges++; |
619 |
|
|
list = list->next; |
620 |
|
|
} |
621 |
|
|
file_new_locale.frl_maplower_ext.frr_nranges = |
622 |
|
|
htonl(new_locale.rl_maplower_ext.rr_nranges); |
623 |
|
|
|
624 |
|
|
list = mapupper.root; |
625 |
|
|
|
626 |
|
|
while (list) { |
627 |
|
|
new_locale.rl_mapupper_ext.rr_nranges++; |
628 |
|
|
list = list->next; |
629 |
|
|
} |
630 |
|
|
file_new_locale.frl_mapupper_ext.frr_nranges = |
631 |
|
|
htonl(new_locale.rl_mapupper_ext.rr_nranges); |
632 |
|
|
|
633 |
|
|
file_new_locale.frl_variable_len = htonl(new_locale.rl_variable_len); |
634 |
|
|
|
635 |
|
|
/* |
636 |
|
|
* Okay, we are now ready to write the new locale file. |
637 |
|
|
*/ |
638 |
|
|
|
639 |
|
|
/* |
640 |
|
|
* PART 1: The _RuneLocale structure |
641 |
|
|
*/ |
642 |
|
|
if (fwrite((char *)&file_new_locale, sizeof(file_new_locale), 1, fp) != 1) |
643 |
|
|
err(1, "writing _RuneLocale to %s", locale_file); |
644 |
|
|
/* |
645 |
|
|
* PART 2: The runetype_ext structures (not the actual tables) |
646 |
|
|
*/ |
647 |
|
|
for (list = types.root, n = 0; list != NULL; list = list->next, n++) { |
648 |
|
|
_FileRuneEntry re; |
649 |
|
|
|
650 |
|
|
memset(&re, 0, sizeof(re)); |
651 |
|
|
re.fre_min = htonl(list->min); |
652 |
|
|
re.fre_max = htonl(list->max); |
653 |
|
|
re.fre_map = htonl(list->map); |
654 |
|
|
|
655 |
|
|
if (fwrite((char *)&re, sizeof(re), 1, fp) != 1) |
656 |
|
|
err(1, "writing runetype_ext #%d to %s", n, locale_file); |
657 |
|
|
} |
658 |
|
|
/* |
659 |
|
|
* PART 3: The maplower_ext structures |
660 |
|
|
*/ |
661 |
|
|
for (list = maplower.root, n = 0; list != NULL; list = list->next, n++) { |
662 |
|
|
_FileRuneEntry re; |
663 |
|
|
|
664 |
|
|
memset(&re, 0, sizeof(re)); |
665 |
|
|
re.fre_min = htonl(list->min); |
666 |
|
|
re.fre_max = htonl(list->max); |
667 |
|
|
re.fre_map = htonl(list->map); |
668 |
|
|
|
669 |
|
|
if (fwrite((char *)&re, sizeof(re), 1, fp) != 1) |
670 |
|
|
err(1, "writing maplower_ext #%d to %s", n, locale_file); |
671 |
|
|
} |
672 |
|
|
/* |
673 |
|
|
* PART 4: The mapupper_ext structures |
674 |
|
|
*/ |
675 |
|
|
for (list = mapupper.root, n = 0; list != NULL; list = list->next, n++) { |
676 |
|
|
_FileRuneEntry re; |
677 |
|
|
|
678 |
|
|
memset(&re, 0, sizeof(re)); |
679 |
|
|
re.fre_min = htonl(list->min); |
680 |
|
|
re.fre_max = htonl(list->max); |
681 |
|
|
re.fre_map = htonl(list->map); |
682 |
|
|
|
683 |
|
|
if (fwrite((char *)&re, sizeof(re), 1, fp) != 1) |
684 |
|
|
err(1, "writing mapupper_ext #%d to %s", n, locale_file); |
685 |
|
|
} |
686 |
|
|
/* |
687 |
|
|
* PART 5: The runetype_ext tables |
688 |
|
|
*/ |
689 |
|
|
for (list = types.root, n = 0; list != NULL; list = list->next, n++) { |
690 |
|
|
for (x = 0; x < list->max - list->min + 1; ++x) |
691 |
|
|
list->types[x] = htonl(list->types[x]); |
692 |
|
|
|
693 |
|
|
if (!list->map) { |
694 |
|
|
if (fwrite((char *)list->types, |
695 |
|
|
(list->max - list->min + 1) * sizeof(u_int32_t), |
696 |
|
|
1, fp) != 1) |
697 |
|
|
err(1, "writing runetype_ext table #%d to %s", n, locale_file); |
698 |
|
|
} |
699 |
|
|
} |
700 |
|
|
/* |
701 |
|
|
* PART 5: And finally the variable data |
702 |
|
|
*/ |
703 |
|
|
if (new_locale.rl_variable_len != 0 && |
704 |
|
|
fwrite((char *)new_locale.rl_variable, |
705 |
|
|
new_locale.rl_variable_len, 1, fp) != 1) |
706 |
|
|
err(1, "writing variable data to %s", locale_file); |
707 |
|
|
fclose(fp); |
708 |
|
|
|
709 |
|
|
if (!debug) |
710 |
|
|
return; |
711 |
|
|
|
712 |
|
|
if (new_locale.rl_encoding[0]) |
713 |
|
|
fprintf(stderr, "ENCODING %s\n", new_locale.rl_encoding); |
714 |
|
|
if (new_locale.rl_variable) |
715 |
|
|
fprintf(stderr, "VARIABLE %s\n", |
716 |
|
|
(char *)new_locale.rl_variable); |
717 |
|
|
|
718 |
|
|
fprintf(stderr, "\nMAPLOWER:\n\n"); |
719 |
|
|
|
720 |
|
|
for (x = 0; x < _CACHED_RUNES; ++x) { |
721 |
|
|
if (isprint(maplower.map[x])) |
722 |
|
|
fprintf(stderr, " '%c'", (int)maplower.map[x]); |
723 |
|
|
else if (maplower.map[x]) |
724 |
|
|
fprintf(stderr, "%04x", maplower.map[x]); |
725 |
|
|
else |
726 |
|
|
fprintf(stderr, "%4x", 0); |
727 |
|
|
if ((x & 0xf) == 0xf) |
728 |
|
|
fprintf(stderr, "\n"); |
729 |
|
|
else |
730 |
|
|
fprintf(stderr, " "); |
731 |
|
|
} |
732 |
|
|
fprintf(stderr, "\n"); |
733 |
|
|
|
734 |
|
|
for (list = maplower.root; list; list = list->next) |
735 |
|
|
fprintf(stderr, "\t%04x - %04x : %04x\n", list->min, list->max, list->map); |
736 |
|
|
|
737 |
|
|
fprintf(stderr, "\nMAPUPPER:\n\n"); |
738 |
|
|
|
739 |
|
|
for (x = 0; x < _CACHED_RUNES; ++x) { |
740 |
|
|
if (isprint(mapupper.map[x])) |
741 |
|
|
fprintf(stderr, " '%c'", (int)mapupper.map[x]); |
742 |
|
|
else if (mapupper.map[x]) |
743 |
|
|
fprintf(stderr, "%04x", mapupper.map[x]); |
744 |
|
|
else |
745 |
|
|
fprintf(stderr, "%4x", 0); |
746 |
|
|
if ((x & 0xf) == 0xf) |
747 |
|
|
fprintf(stderr, "\n"); |
748 |
|
|
else |
749 |
|
|
fprintf(stderr, " "); |
750 |
|
|
} |
751 |
|
|
fprintf(stderr, "\n"); |
752 |
|
|
|
753 |
|
|
for (list = mapupper.root; list; list = list->next) |
754 |
|
|
fprintf(stderr, "\t%04x - %04x : %04x\n", list->min, list->max, list->map); |
755 |
|
|
|
756 |
|
|
|
757 |
|
|
fprintf(stderr, "\nTYPES:\n\n"); |
758 |
|
|
|
759 |
|
|
for (x = 0; x < _CACHED_RUNES; ++x) { |
760 |
|
|
u_int32_t r = types.map[x]; |
761 |
|
|
|
762 |
|
|
if (r) { |
763 |
|
|
if (isprint(x)) |
764 |
|
|
fprintf(stderr, " '%c':%2d", x, (int)(r & 0xff)); |
765 |
|
|
else |
766 |
|
|
fprintf(stderr, "%04x:%2d", x, (int)(r & 0xff)); |
767 |
|
|
|
768 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_A) ? "alph" : ""); |
769 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_C) ? "ctrl" : ""); |
770 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_D) ? "dig" : ""); |
771 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_G) ? "graf" : ""); |
772 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_L) ? "low" : ""); |
773 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_P) ? "punc" : ""); |
774 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_S) ? "spac" : ""); |
775 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_U) ? "upp" : ""); |
776 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_X) ? "xdig" : ""); |
777 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_B) ? "blnk" : ""); |
778 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_R) ? "prnt" : ""); |
779 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_I) ? "ideo" : ""); |
780 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_T) ? "spec" : ""); |
781 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_Q) ? "phon" : ""); |
782 |
|
|
fprintf(stderr, "\n"); |
783 |
|
|
} |
784 |
|
|
} |
785 |
|
|
|
786 |
|
|
for (list = types.root; list; list = list->next) { |
787 |
|
|
if (list->map && list->min + 3 < list->max) { |
788 |
|
|
u_int32_t r = list->map; |
789 |
|
|
|
790 |
|
|
fprintf(stderr, "%04x:%2d", list->min, r & 0xff); |
791 |
|
|
|
792 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_A) ? "alph" : ""); |
793 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_C) ? "ctrl" : ""); |
794 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_D) ? "dig" : ""); |
795 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_G) ? "graf" : ""); |
796 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_L) ? "low" : ""); |
797 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_P) ? "punc" : ""); |
798 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_S) ? "spac" : ""); |
799 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_U) ? "upp" : ""); |
800 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_X) ? "xdig" : ""); |
801 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_B) ? "blnk" : ""); |
802 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_R) ? "prnt" : ""); |
803 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_I) ? "ideo" : ""); |
804 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_T) ? "spec" : ""); |
805 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_Q) ? "phon" : ""); |
806 |
|
|
fprintf(stderr, "\n...\n"); |
807 |
|
|
|
808 |
|
|
fprintf(stderr, "%04x:%2d", list->max, r & 0xff); |
809 |
|
|
|
810 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_A) ? "alph" : ""); |
811 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_C) ? "ctrl" : ""); |
812 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_D) ? "dig" : ""); |
813 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_G) ? "graf" : ""); |
814 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_L) ? "low" : ""); |
815 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_P) ? "punc" : ""); |
816 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_S) ? "spac" : ""); |
817 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_U) ? "upp" : ""); |
818 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_X) ? "xdig" : ""); |
819 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_B) ? "blnk" : ""); |
820 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_R) ? "prnt" : ""); |
821 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_I) ? "ideo" : ""); |
822 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_T) ? "spec" : ""); |
823 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_Q) ? "phon" : ""); |
824 |
|
|
fprintf(stderr, " %1u", (unsigned)((r & _RUNETYPE_SWM)>>_RUNETYPE_SWS)); |
825 |
|
|
fprintf(stderr, "\n"); |
826 |
|
|
} else |
827 |
|
|
for (x = list->min; x <= list->max; ++x) { |
828 |
|
|
u_int32_t r = ntohl(list->types[x - list->min]); |
829 |
|
|
|
830 |
|
|
if (r) { |
831 |
|
|
fprintf(stderr, "%04x:%2d", x, (int)(r & 0xff)); |
832 |
|
|
|
833 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_A) ? "alph" : ""); |
834 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_C) ? "ctrl" : ""); |
835 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_D) ? "dig" : ""); |
836 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_G) ? "graf" : ""); |
837 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_L) ? "low" : ""); |
838 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_P) ? "punc" : ""); |
839 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_S) ? "spac" : ""); |
840 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_U) ? "upp" : ""); |
841 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_X) ? "xdig" : ""); |
842 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_B) ? "blnk" : ""); |
843 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_R) ? "prnt" : ""); |
844 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_I) ? "ideo" : ""); |
845 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_T) ? "spec" : ""); |
846 |
|
|
fprintf(stderr, " %4s", (r & _RUNETYPE_Q) ? "phon" : ""); |
847 |
|
|
fprintf(stderr, " %1u", (unsigned)((r & _RUNETYPE_SWM)>>_RUNETYPE_SWS)); |
848 |
|
|
fprintf(stderr, "\n"); |
849 |
|
|
} |
850 |
|
|
} |
851 |
|
|
} |
852 |
|
|
} |