1 /* GNU Emacs routines to deal with category tables.
2 Copyright (C) 1998, 2001, 2004, 2005, 2006 Free Software Foundation, Inc.
3 Copyright (C) 1995, 1997, 1998, 1999
4 National Institute of Advanced Industrial Science and Technology (AIST)
5 Registration Number H14PRO021
7 National Institute of Advanced Industrial Science and Technology (AIST)
8 Registration Number H13PRO009
10 This file is part of GNU Emacs.
12 GNU Emacs is free software; you can redistribute it and/or modify
13 it under the terms of the GNU General Public License as published by
14 the Free Software Foundation; either version 2, or (at your option)
17 GNU Emacs is distributed in the hope that it will be useful,
18 but WITHOUT ANY WARRANTY; without even the implied warranty of
19 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
20 GNU General Public License for more details.
22 You should have received a copy of the GNU General Public License
23 along with GNU Emacs; see the file COPYING. If not, write to
24 the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
25 Boston, MA 02110-1301, USA. */
28 /* Here we handle three objects: category, category set, and category
29 table. Read comments in the file category.h to understand them. */
35 #include "character.h"
40 /* The version number of the latest category table. Each category
41 table has a unique version number. It is assigned a new number
42 also when it is modified. When a regular expression is compiled
43 into the struct re_pattern_buffer, the version number of the
44 category table (of the current buffer) at that moment is also
45 embedded in the structure.
47 For the moment, we are not using this feature. */
48 static int category_table_version
;
50 Lisp_Object Qcategory_table
, Qcategoryp
, Qcategorysetp
, Qcategory_table_p
;
52 /* Variables to determine word boundary. */
53 Lisp_Object Vword_combining_categories
, Vword_separating_categories
;
55 /* Temporary internal variable used in macro CHAR_HAS_CATEGORY. */
56 Lisp_Object _temp_category_set
;
59 /* Category set staff. */
61 DEFUN ("make-category-set", Fmake_category_set
, Smake_category_set
, 1, 1, 0,
62 doc
: /* Return a newly created category-set which contains CATEGORIES.
63 CATEGORIES is a string of category mnemonics.
64 The value is a bool-vector which has t at the indices corresponding to
67 Lisp_Object categories
;
72 CHECK_STRING (categories
);
73 val
= MAKE_CATEGORY_SET
;
75 if (STRING_MULTIBYTE (categories
))
76 error ("Multibyte string in `make-category-set'");
78 len
= SCHARS (categories
);
83 XSETFASTINT (category
, SREF (categories
, len
));
84 CHECK_CATEGORY (category
);
85 SET_CATEGORY_SET (val
, category
, Qt
);
93 Lisp_Object
check_category_table ();
95 DEFUN ("define-category", Fdefine_category
, Sdefine_category
, 2, 3, 0,
96 doc
: /* Define CATEGORY as a category which is described by DOCSTRING.
97 CATEGORY should be an ASCII printing character in the range ` ' to `~'.
98 DOCSTRING is the documentation string of the category.
99 The category is defined only in category table TABLE, which defaults to
100 the current buffer's category table. */)
101 (category
, docstring
, table
)
102 Lisp_Object category
, docstring
, table
;
104 CHECK_CATEGORY (category
);
105 CHECK_STRING (docstring
);
106 table
= check_category_table (table
);
108 if (!NILP (CATEGORY_DOCSTRING (table
, XFASTINT (category
))))
109 error ("Category `%c' is already defined", XFASTINT (category
));
110 CATEGORY_DOCSTRING (table
, XFASTINT (category
)) = docstring
;
115 DEFUN ("category-docstring", Fcategory_docstring
, Scategory_docstring
, 1, 2, 0,
116 doc
: /* Return the documentation string of CATEGORY, as defined in TABLE.
117 TABLE should be a category table and defaults to the current buffer's
120 Lisp_Object category
, table
;
122 CHECK_CATEGORY (category
);
123 table
= check_category_table (table
);
125 return CATEGORY_DOCSTRING (table
, XFASTINT (category
));
128 DEFUN ("get-unused-category", Fget_unused_category
, Sget_unused_category
,
130 doc
: /* Return a category which is not yet defined in TABLE.
131 If no category remains available, return nil.
132 The optional argument TABLE specifies which category table to modify;
133 it defaults to the current buffer's category table. */)
139 table
= check_category_table (table
);
141 for (i
= ' '; i
<= '~'; i
++)
142 if (NILP (CATEGORY_DOCSTRING (table
, i
)))
143 return make_number (i
);
149 /* Category-table staff. */
151 DEFUN ("category-table-p", Fcategory_table_p
, Scategory_table_p
, 1, 1, 0,
152 doc
: /* Return t if ARG is a category table. */)
156 if (CHAR_TABLE_P (arg
)
157 && EQ (XCHAR_TABLE (arg
)->purpose
, Qcategory_table
))
162 /* If TABLE is nil, return the current category table. If TABLE is
163 not nil, check the validity of TABLE as a category table. If
164 valid, return TABLE itself, but if not valid, signal an error of
165 wrong-type-argument. */
168 check_category_table (table
)
171 register Lisp_Object tem
;
173 return current_buffer
->category_table
;
174 while (tem
= Fcategory_table_p (table
), NILP (tem
))
175 table
= wrong_type_argument (Qcategory_table_p
, table
);
179 DEFUN ("category-table", Fcategory_table
, Scategory_table
, 0, 0, 0,
180 doc
: /* Return the current category table.
181 This is the one specified by the current buffer. */)
184 return current_buffer
->category_table
;
187 DEFUN ("standard-category-table", Fstandard_category_table
,
188 Sstandard_category_table
, 0, 0, 0,
189 doc
: /* Return the standard category table.
190 This is the one used for new buffers. */)
193 return Vstandard_category_table
;
198 copy_category_entry (table
, c
, val
)
199 Lisp_Object table
, c
, val
;
201 val
= Fcopy_sequence (val
);
203 char_table_set_range (table
, XINT (XCAR (c
)), XINT (XCDR (c
)), val
);
205 char_table_set (table
, XINT (c
), val
);
208 /* Return a copy of category table TABLE. We can't simply use the
209 function copy-sequence because no contents should be shared between
210 the original and the copy. This function is called recursively by
211 binding TABLE to a sub char table. */
214 copy_category_table (table
)
217 table
= copy_char_table (table
);
219 if (! NILP (XCHAR_TABLE (table
)->defalt
))
220 XCHAR_TABLE (table
)->defalt
221 = Fcopy_sequence (XCHAR_TABLE (table
)->defalt
);
222 XCHAR_TABLE (table
)->extras
[0]
223 = Fcopy_sequence (XCHAR_TABLE (table
)->extras
[0]);
224 map_char_table (copy_category_entry
, Qnil
, table
, table
);
229 DEFUN ("copy-category-table", Fcopy_category_table
, Scopy_category_table
,
231 doc
: /* Construct a new category table and return it.
232 It is a copy of the TABLE, which defaults to the standard category table. */)
237 check_category_table (table
);
239 table
= Vstandard_category_table
;
241 return copy_category_table (table
);
244 DEFUN ("make-category-table", Fmake_category_table
, Smake_category_table
,
246 doc
: /* Construct a new and empty category table and return it. */)
252 val
= Fmake_char_table (Qcategory_table
, Qnil
);
253 XCHAR_TABLE (val
)->defalt
= MAKE_CATEGORY_SET
;
254 for (i
= 0; i
< (1 << CHARTAB_SIZE_BITS_0
); i
++)
255 XCHAR_TABLE (val
)->contents
[i
] = MAKE_CATEGORY_SET
;
256 Fset_char_table_extra_slot (val
, make_number (0),
257 Fmake_vector (make_number (95), Qnil
));
261 DEFUN ("set-category-table", Fset_category_table
, Sset_category_table
, 1, 1, 0,
262 doc
: /* Specify TABLE as the category table for the current buffer.
268 table
= check_category_table (table
);
269 current_buffer
->category_table
= table
;
270 /* Indicate that this buffer now has a specified category table. */
271 idx
= PER_BUFFER_VAR_IDX (category_table
);
272 SET_PER_BUFFER_VALUE_P (current_buffer
, idx
, 1);
278 char_category_set (c
)
281 return CHAR_TABLE_REF (current_buffer
->category_table
, c
);
284 DEFUN ("char-category-set", Fchar_category_set
, Schar_category_set
, 1, 1, 0,
285 doc
: /* Return the category set of CHAR. */)
290 return CATEGORY_SET (XFASTINT (ch
));
293 DEFUN ("category-set-mnemonics", Fcategory_set_mnemonics
,
294 Scategory_set_mnemonics
, 1, 1, 0,
295 doc
: /* Return a string containing mnemonics of the categories in CATEGORY-SET.
296 CATEGORY-SET is a bool-vector, and the categories \"in\" it are those
297 that are indexes where t occurs in the bool-vector.
298 The return value is a string containing those same categories. */)
300 Lisp_Object category_set
;
305 CHECK_CATEGORY_SET (category_set
);
308 for (i
= 32; i
< 127; i
++)
309 if (CATEGORY_MEMBER (i
, category_set
))
313 return build_string (str
);
317 set_category_set (category_set
, category
, val
)
318 Lisp_Object category_set
, category
, val
;
321 int idx
= XINT (category
) / 8;
322 unsigned char bits
= 1 << (XINT (category
) % 8);
325 XCATEGORY_SET (category_set
)->data
[idx
] &= ~bits
;
327 XCATEGORY_SET (category_set
)->data
[idx
] |= bits
;
331 DEFUN ("modify-category-entry", Fmodify_category_entry
,
332 Smodify_category_entry
, 2, 4, 0,
333 doc
: /* Modify the category set of CHARACTER by adding CATEGORY to it.
334 The category is changed only for table TABLE, which defaults to
335 the current buffer's category table.
336 CHARACTER can be either a single character or a cons representing the
337 lower and upper ends of an inclusive character range to modify.
338 If optional fourth argument RESET is non-nil,
339 then delete CATEGORY from the category set instead of adding it. */)
340 (character
, category
, table
, reset
)
341 Lisp_Object character
, category
, table
, reset
;
343 Lisp_Object set_value
; /* Actual value to be set in category sets. */
344 Lisp_Object category_set
;
348 if (INTEGERP (character
))
350 CHECK_CHARACTER (character
);
351 start
= end
= XFASTINT (character
);
355 CHECK_CONS (character
);
356 CHECK_CHARACTER_CAR (character
);
357 CHECK_CHARACTER_CDR (character
);
358 start
= XFASTINT (XCAR (character
));
359 end
= XFASTINT (XCDR (character
));
362 CHECK_CATEGORY (category
);
363 table
= check_category_table (table
);
365 if (NILP (CATEGORY_DOCSTRING (table
, XFASTINT (category
))))
366 error ("Undefined category: %c", XFASTINT (category
));
368 set_value
= NILP (reset
) ? Qt
: Qnil
;
372 category_set
= char_table_ref_and_range (table
, start
, &from
, &to
);
373 if (CATEGORY_MEMBER (XFASTINT (category
), category_set
) != NILP (reset
))
375 category_set
= Fcopy_sequence (category_set
);
376 SET_CATEGORY_SET (category_set
, category
, set_value
);
378 char_table_set_range (table
, start
, end
, category_set
);
380 char_table_set_range (table
, start
, to
, category_set
);
388 /* Return 1 if there is a word boundary between two word-constituent
389 characters C1 and C2 if they appear in this order, else return 0.
390 Use the macro WORD_BOUNDARY_P instead of calling this function
394 word_boundary_p (c1
, c2
)
397 Lisp_Object category_set1
, category_set2
;
401 if (CHAR_CHARSET (c1
) == CHAR_CHARSET (c2
))
403 tail
= Vword_separating_categories
;
408 tail
= Vword_combining_categories
;
412 category_set1
= CATEGORY_SET (c1
);
413 if (NILP (category_set1
))
414 return default_result
;
415 category_set2
= CATEGORY_SET (c2
);
416 if (NILP (category_set2
))
417 return default_result
;
419 for (; CONSP (tail
); tail
= XCDR (tail
))
421 Lisp_Object elt
= XCAR (tail
);
424 && CATEGORYP (XCAR (elt
))
425 && CATEGORYP (XCDR (elt
))
426 && CATEGORY_MEMBER (XFASTINT (XCAR (elt
)), category_set1
)
427 && CATEGORY_MEMBER (XFASTINT (XCDR (elt
)), category_set2
))
428 return !default_result
;
430 return default_result
;
435 init_category_once ()
437 /* This has to be done here, before we call Fmake_char_table. */
438 Qcategory_table
= intern ("category-table");
439 staticpro (&Qcategory_table
);
441 /* Intern this now in case it isn't already done.
442 Setting this variable twice is harmless.
443 But don't staticpro it here--that is done in alloc.c. */
444 Qchar_table_extra_slots
= intern ("char-table-extra-slots");
446 /* Now we are ready to set up this property, so we can
447 create category tables. */
448 Fput (Qcategory_table
, Qchar_table_extra_slots
, make_number (2));
450 Vstandard_category_table
= Fmake_char_table (Qcategory_table
, Qnil
);
451 /* Set a category set which contains nothing to the default. */
452 XCHAR_TABLE (Vstandard_category_table
)->defalt
= MAKE_CATEGORY_SET
;
453 Fset_char_table_extra_slot (Vstandard_category_table
, make_number (0),
454 Fmake_vector (make_number (95), Qnil
));
460 Qcategoryp
= intern ("categoryp");
461 staticpro (&Qcategoryp
);
462 Qcategorysetp
= intern ("categorysetp");
463 staticpro (&Qcategorysetp
);
464 Qcategory_table_p
= intern ("category-table-p");
465 staticpro (&Qcategory_table_p
);
467 DEFVAR_LISP ("word-combining-categories", &Vword_combining_categories
,
468 doc
: /* List of pair (cons) of categories to determine word boundary.
470 Emacs treats a sequence of word constituent characters as a single
471 word (i.e. finds no word boundary between them) iff they belongs to
472 the same charset. But, exceptions are allowed in the following cases.
474 \(1) The case that characters are in different charsets is controlled
475 by the variable `word-combining-categories'.
477 Emacs finds no word boundary between characters of different charsets
478 if they have categories matching some element of this list.
480 More precisely, if an element of this list is a cons of category CAT1
481 and CAT2, and a multibyte character C1 which has CAT1 is followed by
482 C2 which has CAT2, there's no word boundary between C1 and C2.
484 For instance, to tell that ASCII characters and Latin-1 characters can
485 form a single word, the element `(?l . ?l)' should be in this list
486 because both characters have the category `l' (Latin characters).
488 \(2) The case that character are in the same charset is controlled by
489 the variable `word-separating-categories'.
491 Emacs find a word boundary between characters of the same charset
492 if they have categories matching some element of this list.
494 More precisely, if an element of this list is a cons of category CAT1
495 and CAT2, and a multibyte character C1 which has CAT1 is followed by
496 C2 which has CAT2, there's a word boundary between C1 and C2.
498 For instance, to tell that there's a word boundary between Japanese
499 Hiragana and Japanese Kanji (both are in the same charset), the
500 element `(?H . ?C) should be in this list. */);
502 Vword_combining_categories
= Qnil
;
504 DEFVAR_LISP ("word-separating-categories", &Vword_separating_categories
,
505 doc
: /* List of pair (cons) of categories to determine word boundary.
506 See the documentation of the variable `word-combining-categories'. */);
508 Vword_separating_categories
= Qnil
;
510 defsubr (&Smake_category_set
);
511 defsubr (&Sdefine_category
);
512 defsubr (&Scategory_docstring
);
513 defsubr (&Sget_unused_category
);
514 defsubr (&Scategory_table_p
);
515 defsubr (&Scategory_table
);
516 defsubr (&Sstandard_category_table
);
517 defsubr (&Scopy_category_table
);
518 defsubr (&Smake_category_table
);
519 defsubr (&Sset_category_table
);
520 defsubr (&Schar_category_set
);
521 defsubr (&Scategory_set_mnemonics
);
522 defsubr (&Smodify_category_entry
);
524 category_table_version
= 0;
527 /* arch-tag: 74ebf524-121b-4d9c-bd68-07f8d708b211
528 (do not change this comment) */