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
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
|
/* GNU Emacs case conversion functions.
Copyright (C) 1985, 1994, 1997, 1998, 1999, 2001, 2002, 2003, 2004,
2005, 2006, 2007, 2008 Free Software Foundation, Inc.
This file is part of GNU Emacs.
GNU Emacs is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
GNU Emacs 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 General Public License for more details.
You should have received a copy of the GNU General Public License
along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
#include "lisp.h"
#include "buffer.h"
#include "character.h"
#include "commands.h"
#include "syntax.h"
#include "composite.h"
#include "keymap.h"
enum case_action {CASE_UP, CASE_DOWN, CASE_CAPITALIZE, CASE_CAPITALIZE_UP};
Lisp_Object Qidentity;
Lisp_Object
casify_object (flag, obj)
enum case_action flag;
Lisp_Object obj;
{
register int c, c1;
register int inword = flag == CASE_DOWN;
/* If the case table is flagged as modified, rescan it. */
if (NILP (XCHAR_TABLE (current_buffer->downcase_table)->extras[1]))
Fset_case_table (current_buffer->downcase_table);
if (INTEGERP (obj))
{
int flagbits = (CHAR_ALT | CHAR_SUPER | CHAR_HYPER
| CHAR_SHIFT | CHAR_CTL | CHAR_META);
int flags = XINT (obj) & flagbits;
int multibyte = ! NILP (current_buffer->enable_multibyte_characters);
/* If the character has higher bits set
above the flags, return it unchanged.
It is not a real character. */
if ((unsigned) XFASTINT (obj) > (unsigned) flagbits)
return obj;
c1 = XFASTINT (obj) & ~flagbits;
/* FIXME: Even if enable-multibyte-characters is nil, we may
manipulate multibyte chars. This means we have a bug for latin-1
chars since when we receive an int 128-255 we can't tell whether
it's an eight-bit byte or a latin-1 char. */
if (c1 >= 256)
multibyte = 1;
if (! multibyte)
MAKE_CHAR_MULTIBYTE (c1);
c = DOWNCASE (c1);
if (inword)
XSETFASTINT (obj, c | flags);
else if (c == (XFASTINT (obj) & ~flagbits))
{
if (! inword)
c = UPCASE1 (c1);
if (! multibyte)
MAKE_CHAR_UNIBYTE (c);
XSETFASTINT (obj, c | flags);
}
return obj;
}
if (!STRINGP (obj))
wrong_type_argument (Qchar_or_string_p, obj);
else if (!STRING_MULTIBYTE (obj))
{
EMACS_INT i;
EMACS_INT size = SCHARS (obj);
obj = Fcopy_sequence (obj);
for (i = 0; i < size; i++)
{
c = SREF (obj, i);
MAKE_CHAR_MULTIBYTE (c);
c1 = c;
if (inword && flag != CASE_CAPITALIZE_UP)
c = DOWNCASE (c);
else if (!UPPERCASEP (c)
&& (!inword || flag != CASE_CAPITALIZE_UP))
c = UPCASE1 (c1);
if ((int) flag >= (int) CASE_CAPITALIZE)
inword = (SYNTAX (c) == Sword);
if (c != c1)
{
MAKE_CHAR_UNIBYTE (c);
/* If the char can't be converted to a valid byte, just don't
change it. */
if (c >= 0 && c < 256)
SSET (obj, i, c);
}
}
return obj;
}
else
{
EMACS_INT i, i_byte, size = SCHARS (obj);
int len;
USE_SAFE_ALLOCA;
unsigned char *dst, *o;
/* Over-allocate by 12%: this is a minor overhead, but should be
sufficient in 99.999% of the cases to avoid a reallocation. */
EMACS_INT o_size = SBYTES (obj) + SBYTES (obj) / 8 + MAX_MULTIBYTE_LENGTH;
SAFE_ALLOCA (dst, void *, o_size);
o = dst;
for (i = i_byte = 0; i < size; i++, i_byte += len)
{
if ((o - dst) + MAX_MULTIBYTE_LENGTH > o_size)
{ /* Not enough space for the next char: grow the destination. */
unsigned char *old_dst = dst;
o_size += o_size; /* Probably overkill, but extremely rare. */
SAFE_ALLOCA (dst, void *, o_size);
bcopy (old_dst, dst, o - old_dst);
o = dst + (o - old_dst);
}
c = STRING_CHAR_AND_LENGTH (SDATA (obj) + i_byte, 0, len);
if (inword && flag != CASE_CAPITALIZE_UP)
c = DOWNCASE (c);
else if (!UPPERCASEP (c)
&& (!inword || flag != CASE_CAPITALIZE_UP))
c = UPCASE1 (c);
if ((int) flag >= (int) CASE_CAPITALIZE)
inword = (SYNTAX (c) == Sword);
o += CHAR_STRING (c, o);
}
eassert (o - dst <= o_size);
obj = make_multibyte_string (dst, size, o - dst);
SAFE_FREE ();
return obj;
}
}
DEFUN ("upcase", Fupcase, Supcase, 1, 1, 0,
doc: /* Convert argument to upper case and return that.
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy.
See also `capitalize', `downcase' and `upcase-initials'. */)
(obj)
Lisp_Object obj;
{
return casify_object (CASE_UP, obj);
}
DEFUN ("downcase", Fdowncase, Sdowncase, 1, 1, 0,
doc: /* Convert argument to lower case and return that.
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy. */)
(obj)
Lisp_Object obj;
{
return casify_object (CASE_DOWN, obj);
}
DEFUN ("capitalize", Fcapitalize, Scapitalize, 1, 1, 0,
doc: /* Convert argument to capitalized form and return that.
This means that each word's first character is upper case
and the rest is lower case.
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy. */)
(obj)
Lisp_Object obj;
{
return casify_object (CASE_CAPITALIZE, obj);
}
/* Like Fcapitalize but change only the initials. */
DEFUN ("upcase-initials", Fupcase_initials, Supcase_initials, 1, 1, 0,
doc: /* Convert the initial of each word in the argument to upper case.
Do not change the other letters of each word.
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy. */)
(obj)
Lisp_Object obj;
{
return casify_object (CASE_CAPITALIZE_UP, obj);
}
/* flag is CASE_UP, CASE_DOWN or CASE_CAPITALIZE or CASE_CAPITALIZE_UP.
b and e specify range of buffer to operate on. */
void
casify_region (flag, b, e)
enum case_action flag;
Lisp_Object b, e;
{
register int c;
register int inword = flag == CASE_DOWN;
register int multibyte = !NILP (current_buffer->enable_multibyte_characters);
EMACS_INT start, end;
EMACS_INT start_byte, end_byte;
EMACS_INT first = -1, last; /* Position of first and last changes. */
EMACS_INT opoint = PT;
EMACS_INT opoint_byte = PT_BYTE;
if (EQ (b, e))
/* Not modifying because nothing marked */
return;
/* If the case table is flagged as modified, rescan it. */
if (NILP (XCHAR_TABLE (current_buffer->downcase_table)->extras[1]))
Fset_case_table (current_buffer->downcase_table);
validate_region (&b, &e);
start = XFASTINT (b);
end = XFASTINT (e);
modify_region (current_buffer, start, end, 0);
record_change (start, end - start);
start_byte = CHAR_TO_BYTE (start);
end_byte = CHAR_TO_BYTE (end);
while (start < end)
{
int c2, len;
if (multibyte)
{
c = FETCH_MULTIBYTE_CHAR (start_byte);
len = CHAR_BYTES (c);
}
else
{
c = FETCH_BYTE (start_byte);
MAKE_CHAR_MULTIBYTE (c);
len = 1;
}
c2 = c;
if (inword && flag != CASE_CAPITALIZE_UP)
c = DOWNCASE (c);
else if (!UPPERCASEP (c)
&& (!inword || flag != CASE_CAPITALIZE_UP))
c = UPCASE1 (c);
if ((int) flag >= (int) CASE_CAPITALIZE)
inword = ((SYNTAX (c) == Sword) && (inword || !SYNTAX_PREFIX (c)));
if (c != c2)
{
last = start;
if (first < 0)
first = start;
if (! multibyte)
{
MAKE_CHAR_UNIBYTE (c);
FETCH_BYTE (start_byte) = c;
}
else if (ASCII_CHAR_P (c2) && ASCII_CHAR_P (c))
FETCH_BYTE (start_byte) = c;
else
{
int tolen = CHAR_BYTES (c);
int j;
unsigned char str[MAX_MULTIBYTE_LENGTH];
CHAR_STRING (c, str);
if (len == tolen)
{
/* Length is unchanged. */
for (j = 0; j < len; ++j)
FETCH_BYTE (start_byte + j) = str[j];
}
else
{
/* Replace one character with the other,
keeping text properties the same. */
replace_range_2 (start, start_byte,
start + 1, start_byte + len,
str, 1, tolen,
0);
len = tolen;
}
}
}
start++;
start_byte += len;
}
if (PT != opoint)
TEMP_SET_PT_BOTH (opoint, opoint_byte);
if (first >= 0)
{
signal_after_change (first, last + 1 - first, last + 1 - first);
update_compositions (first, last + 1, CHECK_ALL);
}
}
DEFUN ("upcase-region", Fupcase_region, Supcase_region, 2, 2, "r",
doc: /* Convert the region to upper case. In programs, wants two arguments.
These arguments specify the starting and ending character numbers of
the region to operate on. When used as a command, the text between
point and the mark is operated on.
See also `capitalize-region'. */)
(beg, end)
Lisp_Object beg, end;
{
casify_region (CASE_UP, beg, end);
return Qnil;
}
DEFUN ("downcase-region", Fdowncase_region, Sdowncase_region, 2, 2, "r",
doc: /* Convert the region to lower case. In programs, wants two arguments.
These arguments specify the starting and ending character numbers of
the region to operate on. When used as a command, the text between
point and the mark is operated on. */)
(beg, end)
Lisp_Object beg, end;
{
casify_region (CASE_DOWN, beg, end);
return Qnil;
}
DEFUN ("capitalize-region", Fcapitalize_region, Scapitalize_region, 2, 2, "r",
doc: /* Convert the region to capitalized form.
Capitalized form means each word's first character is upper case
and the rest of it is lower case.
In programs, give two arguments, the starting and ending
character positions to operate on. */)
(beg, end)
Lisp_Object beg, end;
{
casify_region (CASE_CAPITALIZE, beg, end);
return Qnil;
}
/* Like Fcapitalize_region but change only the initials. */
DEFUN ("upcase-initials-region", Fupcase_initials_region,
Supcase_initials_region, 2, 2, "r",
doc: /* Upcase the initial of each word in the region.
Subsequent letters of each word are not changed.
In programs, give two arguments, the starting and ending
character positions to operate on. */)
(beg, end)
Lisp_Object beg, end;
{
casify_region (CASE_CAPITALIZE_UP, beg, end);
return Qnil;
}
static Lisp_Object
operate_on_word (arg, newpoint)
Lisp_Object arg;
EMACS_INT *newpoint;
{
Lisp_Object val;
int farend;
int iarg;
CHECK_NUMBER (arg);
iarg = XINT (arg);
farend = scan_words (PT, iarg);
if (!farend)
farend = iarg > 0 ? ZV : BEGV;
*newpoint = PT > farend ? PT : farend;
XSETFASTINT (val, farend);
return val;
}
DEFUN ("upcase-word", Fupcase_word, Supcase_word, 1, 1, "p",
doc: /* Convert following word (or ARG words) to upper case, moving over.
With negative argument, convert previous words but do not move.
See also `capitalize-word'. */)
(arg)
Lisp_Object arg;
{
Lisp_Object beg, end;
EMACS_INT newpoint;
XSETFASTINT (beg, PT);
end = operate_on_word (arg, &newpoint);
casify_region (CASE_UP, beg, end);
SET_PT (newpoint);
return Qnil;
}
DEFUN ("downcase-word", Fdowncase_word, Sdowncase_word, 1, 1, "p",
doc: /* Convert following word (or ARG words) to lower case, moving over.
With negative argument, convert previous words but do not move. */)
(arg)
Lisp_Object arg;
{
Lisp_Object beg, end;
EMACS_INT newpoint;
XSETFASTINT (beg, PT);
end = operate_on_word (arg, &newpoint);
casify_region (CASE_DOWN, beg, end);
SET_PT (newpoint);
return Qnil;
}
DEFUN ("capitalize-word", Fcapitalize_word, Scapitalize_word, 1, 1, "p",
doc: /* Capitalize the following word (or ARG words), moving over.
This gives the word(s) a first character in upper case
and the rest lower case.
With negative argument, capitalize previous words but do not move. */)
(arg)
Lisp_Object arg;
{
Lisp_Object beg, end;
EMACS_INT newpoint;
XSETFASTINT (beg, PT);
end = operate_on_word (arg, &newpoint);
casify_region (CASE_CAPITALIZE, beg, end);
SET_PT (newpoint);
return Qnil;
}
void
syms_of_casefiddle ()
{
Qidentity = intern ("identity");
staticpro (&Qidentity);
defsubr (&Supcase);
defsubr (&Sdowncase);
defsubr (&Scapitalize);
defsubr (&Supcase_initials);
defsubr (&Supcase_region);
defsubr (&Sdowncase_region);
defsubr (&Scapitalize_region);
defsubr (&Supcase_initials_region);
defsubr (&Supcase_word);
defsubr (&Sdowncase_word);
defsubr (&Scapitalize_word);
}
void
keys_of_casefiddle ()
{
initial_define_key (control_x_map, Ctl('U'), "upcase-region");
Fput (intern ("upcase-region"), Qdisabled, Qt);
initial_define_key (control_x_map, Ctl('L'), "downcase-region");
Fput (intern ("downcase-region"), Qdisabled, Qt);
initial_define_key (meta_map, 'u', "upcase-word");
initial_define_key (meta_map, 'l', "downcase-word");
initial_define_key (meta_map, 'c', "capitalize-word");
}
/* arch-tag: 60a73c66-5489-47e7-a81f-cead4057c526
(do not change this comment) */
|