Mercurial > hg > xemacs-beta
annotate src/mule-charset.c @ 5124:623d57b7fbe8 ben-lisp-object
separate regular and disksave finalization, print method fixes.
Create separate disksave method and make the finalize method only be for
actual object finalization, not disksave finalization.
Fix places where 0 was given in place of a printer -- print methods are
mandatory, and internal objects formerly without a print method now must
explicitly specify internal_object_printer().
Change the defn of CONSOLE_LIVE_P to avoid problems in some weird situations.
-------------------- ChangeLog entries follow: --------------------
src/ChangeLog addition:
2010-01-20 Ben Wing <ben@xemacs.org>
* alloc.c:
* alloc.c (very_old_free_lcrecord):
* alloc.c (disksave_object_finalization_1):
* alloc.c (make_lcrecord_list):
* alloc.c (alloc_managed_lcrecord):
* alloc.c (free_managed_lcrecord):
* alloc.c (sweep_lcrecords_1):
* buffer.c:
* bytecode.c:
* bytecode.c (Fcompiled_function_p):
* chartab.c:
* console-impl.h:
* console-impl.h (CONSOLE_TYPE_P):
* console.c:
* console.c (set_quit_events):
* data.c:
* data.c (Fmake_ephemeron):
* database.c:
* database.c (finalize_database):
* database.c (Fclose_database):
* device-msw.c:
* device-msw.c (finalize_devmode):
* device-msw.c (allocate_devmode):
* device.c:
* elhash.c:
* elhash.c (finalize_hash_table):
* eval.c:
* eval.c (bind_multiple_value_limits):
* event-stream.c:
* event-stream.c (finalize_command_builder):
* events.c:
* events.c (mark_event):
* extents.c:
* extents.c (finalize_extent_info):
* extents.c (uninit_buffer_extents):
* faces.c:
* file-coding.c:
* file-coding.c (finalize_coding_system):
* file-coding.h:
* file-coding.h (struct coding_system_methods):
* file-coding.h (struct detector):
* floatfns.c:
* floatfns.c (extract_float):
* fns.c:
* fns.c (Fidentity):
* font-mgr.c (finalize_fc_pattern):
* font-mgr.c (finalize_fc_config):
* frame.c:
* glyphs.c:
* glyphs.c (finalize_image_instance):
* glyphs.c (unmap_subwindow_instance_cache_mapper):
* gui.c:
* gui.c (gui_error):
* keymap.c:
* lisp.h (struct Lisp_Symbol):
* lrecord.h:
* lrecord.h (struct lrecord_implementation):
* lrecord.h (MC_ALLOC_CALL_FINALIZER):
* lrecord.h (MC_ALLOC_CALL_FINALIZER_FOR_DISKSAVE):
* lrecord.h (DEFINE_DUMPABLE_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_SIZABLE_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_SIZABLE_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_FROB_BLOCK_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_FROB_BLOCK_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_FROB_BLOCK_SIZABLE_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_INTERNAL_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_SIZABLE_INTERNAL_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_SIZABLE_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_SIZABLE_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_FROB_BLOCK_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_FROB_BLOCK_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_FROB_BLOCK_SIZABLE_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_INTERNAL_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_SIZABLE_INTERNAL_LISP_OBJECT):
* lrecord.h (MAKE_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_MODULE_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_MODULE_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_MODULE_SIZABLE_LISP_OBJECT):
* lrecord.h (DEFINE_DUMPABLE_MODULE_SIZABLE_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_MODULE_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_MODULE_GENERAL_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_MODULE_SIZABLE_LISP_OBJECT):
* lrecord.h (DEFINE_NODUMP_MODULE_SIZABLE_GENERAL_LISP_OBJECT):
* lrecord.h (MAKE_MODULE_LISP_OBJECT):
* lstream.c:
* lstream.c (finalize_lstream):
* lstream.c (disksave_lstream):
* marker.c:
* marker.c (finalize_marker):
* mule-charset.c (make_charset):
* number.c:
* objects.c:
* objects.c (finalize_color_instance):
* objects.c (finalize_font_instance):
* opaque.c:
* opaque.c (make_opaque_ptr):
* process-nt.c:
* process-nt.c (nt_finalize_process_data):
* process-nt.c (nt_deactivate_process):
* process.c:
* process.c (finalize_process):
* procimpl.h (struct process_methods):
* scrollbar.c:
* scrollbar.c (free_scrollbar_instance):
* specifier.c (finalize_specifier):
* symbols.c:
* toolbar.c:
* toolbar.c (Ftoolbar_button_p):
* tooltalk.c:
* ui-gtk.c:
* ui-gtk.c (emacs_gtk_object_finalizer):
* ui-gtk.c (allocate_emacs_gtk_boxed_data):
* window.c:
* window.c (finalize_window):
* window.c (mark_window_as_deleted):
Separate out regular and disksave finalization. Instead of a
FOR_DISKSAVE argument to the finalizer, create a separate object
method `disksaver'. Make `finalizer' have only one argument.
Go through and separate out all finalize methods into finalize
and disksave. Delete lots of thereby redundant disksave checking.
Delete places that signal an error if we attempt to disksave --
all of these objects are non-dumpable and we will get an error
from pdump anyway if we attempt to dump them. After this is done,
only one object remains that has a disksave method -- lstream.
Change DEFINE_*_LISP_OBJECT_WITH_PROPS to DEFINE_*_GENERAL_LISP_OBJECT,
which is used for specifying either property methods or disksave
methods (or in the future, any other less-used methods).
Remove the for_disksave argument to finalize_process_data. Don't
provide a disksaver for processes because no one currently needs
it.
Clean up various places where objects didn't provide a print method.
It was made mandatory in previous changes, and all methods now
either provide their own print method or use internal_object_printer
or external_object_printer.
Change the definition of CONSOLE_LIVE_P to use the contype enum
rather than looking into the conmeths structure -- in some weird
situations with dead objects, the conmeths structure is NULL,
and printing such objects from debug_print() will crash if we try
to look into the conmeths structure.
| author | Ben Wing <ben@xemacs.org> |
|---|---|
| date | Wed, 20 Jan 2010 07:05:57 -0600 |
| parents | d1247f3cc363 |
| children | b5df3737028a |
| rev | line source |
|---|---|
| 428 | 1 /* Functions to handle multilingual characters. |
| 2 Copyright (C) 1992, 1995 Free Software Foundation, Inc. | |
| 3 Copyright (C) 1995 Sun Microsystems, Inc. | |
| 3025 | 4 Copyright (C) 2001, 2002, 2004, 2005 Ben Wing. |
| 428 | 5 |
| 6 This file is part of XEmacs. | |
| 7 | |
| 8 XEmacs is free software; you can redistribute it and/or modify it | |
| 9 under the terms of the GNU General Public License as published by the | |
| 10 Free Software Foundation; either version 2, or (at your option) any | |
| 11 later version. | |
| 12 | |
| 13 XEmacs is distributed in the hope that it will be useful, but WITHOUT | |
| 14 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | |
| 15 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License | |
| 16 for more details. | |
| 17 | |
| 18 You should have received a copy of the GNU General Public License | |
| 19 along with XEmacs; see the file COPYING. If not, write to | |
| 20 the Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
| 21 Boston, MA 02111-1307, USA. */ | |
| 22 | |
| 23 /* Synched up with: FSF 20.3. Not in FSF. */ | |
| 24 | |
| 25 /* Rewritten by Ben Wing <ben@xemacs.org>. */ | |
| 26 | |
| 27 #include <config.h> | |
| 28 #include "lisp.h" | |
| 29 | |
| 30 #include "buffer.h" | |
| 31 #include "chartab.h" | |
| 32 #include "elhash.h" | |
| 33 #include "device.h" | |
| 34 #include "faces.h" | |
| 771 | 35 #include "lstream.h" |
| 428 | 36 #include "mule-ccl.h" |
| 872 | 37 #include "objects.h" |
| 3659 | 38 #include "specifier.h" |
| 428 | 39 |
| 40 /* The various pre-defined charsets. */ | |
| 41 | |
| 42 Lisp_Object Vcharset_ascii; | |
| 43 Lisp_Object Vcharset_control_1; | |
| 44 Lisp_Object Vcharset_latin_iso8859_1; | |
| 45 Lisp_Object Vcharset_latin_iso8859_2; | |
| 46 Lisp_Object Vcharset_latin_iso8859_3; | |
| 47 Lisp_Object Vcharset_latin_iso8859_4; | |
| 48 Lisp_Object Vcharset_thai_tis620; | |
| 49 Lisp_Object Vcharset_greek_iso8859_7; | |
| 50 Lisp_Object Vcharset_hebrew_iso8859_8; | |
| 51 Lisp_Object Vcharset_katakana_jisx0201; | |
| 52 Lisp_Object Vcharset_latin_jisx0201; | |
| 53 Lisp_Object Vcharset_cyrillic_iso8859_5; | |
| 54 Lisp_Object Vcharset_latin_iso8859_9; | |
| 728 | 55 Lisp_Object Vcharset_latin_iso8859_15; |
| 428 | 56 Lisp_Object Vcharset_japanese_jisx0208_1978; |
| 57 Lisp_Object Vcharset_chinese_gb2312; | |
| 58 Lisp_Object Vcharset_japanese_jisx0208; | |
| 59 Lisp_Object Vcharset_korean_ksc5601; | |
| 60 Lisp_Object Vcharset_japanese_jisx0212; | |
| 61 Lisp_Object Vcharset_chinese_cns11643_1; | |
| 62 Lisp_Object Vcharset_chinese_cns11643_2; | |
| 63 Lisp_Object Vcharset_chinese_big5_1; | |
| 64 Lisp_Object Vcharset_chinese_big5_2; | |
| 65 Lisp_Object Vcharset_composite; | |
| 66 | |
| 67 struct charset_lookup *chlook; | |
| 68 | |
| 1204 | 69 static const struct memory_description charset_lookup_description_1[] = { |
| 771 | 70 { XD_LISP_OBJECT_ARRAY, offsetof (struct charset_lookup, charset_by_leading_byte), NUM_LEADING_BYTES+4*128*2 }, |
| 428 | 71 { XD_END } |
| 72 }; | |
| 73 | |
| 1204 | 74 static const struct sized_memory_description charset_lookup_description = { |
| 440 | 75 sizeof (struct charset_lookup), |
| 428 | 76 charset_lookup_description_1 |
| 77 }; | |
| 78 | |
| 79 Lisp_Object Qcharsetp; | |
| 80 | |
| 3664 | 81 /* Qdoc_string, Qdimension, Qchars, Qfinal defined in general.c */ |
| 82 Lisp_Object Qregistries, Qgraphic, Qregistry; | |
| 428 | 83 Lisp_Object Qdirection; |
| 84 Lisp_Object Qreverse_direction_charset; | |
| 85 Lisp_Object Qshort_name, Qlong_name; | |
| 86 | |
|
4691
3ba90c659d01
Move Qfrom_unicode to general-slots.h, fix the native Win32 build.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4491
diff
changeset
|
87 Lisp_Object Qto_unicode; |
| 771 | 88 |
| 89 Lisp_Object | |
| 428 | 90 Qlatin_iso8859_1, |
| 91 Qlatin_iso8859_2, | |
| 92 Qlatin_iso8859_3, | |
| 93 Qlatin_iso8859_4, | |
| 94 Qthai_tis620, | |
| 95 Qgreek_iso8859_7, | |
| 96 Qhebrew_iso8859_8, | |
| 97 Qkatakana_jisx0201, | |
| 98 Qlatin_jisx0201, | |
| 99 Qcyrillic_iso8859_5, | |
| 100 Qlatin_iso8859_9, | |
| 728 | 101 Qlatin_iso8859_15, |
| 428 | 102 Qjapanese_jisx0208_1978, |
| 103 Qchinese_gb2312, | |
| 104 Qjapanese_jisx0208, | |
| 105 Qkorean_ksc5601, | |
| 106 Qjapanese_jisx0212, | |
| 107 Qchinese_cns11643_1, | |
| 108 Qchinese_cns11643_2, | |
| 109 Qchinese_big5_1, | |
| 110 Qchinese_big5_2, | |
| 111 Qcomposite; | |
| 112 | |
| 113 Lisp_Object Ql2r, Qr2l; | |
| 114 | |
| 115 Lisp_Object Vcharset_hash_table; | |
| 116 | |
| 117 | |
| 118 /************************************************************************/ | |
| 119 /* charset object */ | |
| 120 /************************************************************************/ | |
| 121 | |
| 122 static Lisp_Object | |
| 123 mark_charset (Lisp_Object obj) | |
| 124 { | |
| 440 | 125 Lisp_Charset *cs = XCHARSET (obj); |
| 428 | 126 |
| 127 mark_object (cs->short_name); | |
| 128 mark_object (cs->long_name); | |
| 129 mark_object (cs->doc_string); | |
| 3659 | 130 mark_object (cs->registries); |
| 428 | 131 mark_object (cs->ccl_program); |
| 132 return cs->name; | |
| 133 } | |
| 134 | |
| 135 static void | |
| 2286 | 136 print_charset (Lisp_Object obj, Lisp_Object printcharfun, |
| 137 int UNUSED (escapeflag)) | |
| 428 | 138 { |
| 440 | 139 Lisp_Charset *cs = XCHARSET (obj); |
| 428 | 140 |
| 141 if (print_readably) | |
| 563 | 142 printing_unreadable_object ("#<charset %s 0x%x>", |
| 793 | 143 XSTRING_DATA (XSYMBOL (CHARSET_NAME (cs))-> |
| 563 | 144 name), |
| 145 cs->header.uid); | |
| 428 | 146 |
| 771 | 147 write_fmt_string_lisp (printcharfun, "#<charset %s %S %S %S", 4, |
| 148 CHARSET_NAME (cs), CHARSET_SHORT_NAME (cs), | |
| 149 CHARSET_LONG_NAME (cs), CHARSET_DOC_STRING (cs)); | |
| 150 write_fmt_string (printcharfun, " %s %s cols=%d g%d final='%c' reg=", | |
| 151 CHARSET_TYPE (cs) == CHARSET_TYPE_94 ? "94" : | |
| 152 CHARSET_TYPE (cs) == CHARSET_TYPE_96 ? "96" : | |
| 153 CHARSET_TYPE (cs) == CHARSET_TYPE_94X94 ? "94x94" : | |
| 154 "96x96", | |
| 155 CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? "l2r" : | |
| 156 "r2l", | |
| 157 CHARSET_COLUMNS (cs), | |
| 158 CHARSET_GRAPHIC (cs), | |
| 159 CHARSET_FINAL (cs)); | |
| 3659 | 160 print_internal (CHARSET_REGISTRIES (cs), printcharfun, 0); |
| 771 | 161 write_fmt_string (printcharfun, " 0x%x>", cs->header.uid); |
| 162 } | |
| 163 | |
| 1204 | 164 static const struct memory_description charset_description[] = { |
| 165 { XD_INT, offsetof (Lisp_Charset, dimension) }, | |
| 166 { XD_INT, offsetof (Lisp_Charset, from_unicode_levels) }, | |
| 440 | 167 { XD_LISP_OBJECT, offsetof (Lisp_Charset, name) }, |
| 168 { XD_LISP_OBJECT, offsetof (Lisp_Charset, doc_string) }, | |
| 3659 | 169 { XD_LISP_OBJECT, offsetof (Lisp_Charset, registries) }, |
| 440 | 170 { XD_LISP_OBJECT, offsetof (Lisp_Charset, short_name) }, |
| 171 { XD_LISP_OBJECT, offsetof (Lisp_Charset, long_name) }, | |
| 172 { XD_LISP_OBJECT, offsetof (Lisp_Charset, reverse_direction_charset) }, | |
| 173 { XD_LISP_OBJECT, offsetof (Lisp_Charset, ccl_program) }, | |
| 771 | 174 { XD_UNION, offsetof (Lisp_Charset, to_unicode_table), |
| 2775 | 175 XD_INDIRECT (0, 0), { &to_unicode_description }, XD_FLAG_NO_KKCC }, |
| 771 | 176 { XD_UNION, offsetof (Lisp_Charset, from_unicode_table), |
| 2775 | 177 XD_INDIRECT (1, 0), { &from_unicode_description }, XD_FLAG_NO_KKCC }, |
| 428 | 178 { XD_END } |
| 179 }; | |
| 180 | |
|
5118
e0db3c197671
merge up to latest default branch, doesn't compile yet
Ben Wing <ben@xemacs.org>
diff
changeset
|
181 DEFINE_DUMPABLE_LISP_OBJECT ("charset", charset, |
|
5124
623d57b7fbe8
separate regular and disksave finalization, print method fixes.
Ben Wing <ben@xemacs.org>
parents:
5120
diff
changeset
|
182 mark_charset, print_charset, 0, |
|
623d57b7fbe8
separate regular and disksave finalization, print method fixes.
Ben Wing <ben@xemacs.org>
parents:
5120
diff
changeset
|
183 0, 0, charset_description, Lisp_Charset); |
| 428 | 184 /* Make a new charset. */ |
| 446 | 185 /* #### SJT Should generic properties be allowed? */ |
| 428 | 186 static Lisp_Object |
| 771 | 187 make_charset (int id, Lisp_Object name, int rep_bytes, |
| 188 int type, int columns, int graphic, | |
| 867 | 189 Ibyte final, int direction, Lisp_Object short_name, |
| 428 | 190 Lisp_Object long_name, Lisp_Object doc, |
| 3439 | 191 Lisp_Object reg, int overwrite, int encode_as_utf_8) |
| 428 | 192 { |
| 193 Lisp_Object obj; | |
| 771 | 194 Lisp_Charset *cs; |
| 195 | |
| 196 if (!overwrite) | |
| 197 { | |
|
5117
3742ea8250b5
Checking in final CVS version of workspace 'ben-lisp-object'
Ben Wing <ben@xemacs.org>
parents:
3025
diff
changeset
|
198 obj = ALLOC_LISP_OBJECT (charset); |
|
3742ea8250b5
Checking in final CVS version of workspace 'ben-lisp-object'
Ben Wing <ben@xemacs.org>
parents:
3025
diff
changeset
|
199 cs = XCHARSET (obj); |
| 771 | 200 |
| 201 if (final) | |
| 202 { | |
| 203 /* some charsets do not have final characters. This includes | |
| 204 ASCII, Control-1, Composite, and the two faux private | |
| 205 charsets. */ | |
| 206 assert (NILP (chlook-> | |
| 207 charset_by_attributes[type][final][direction])); | |
| 208 chlook->charset_by_attributes[type][final][direction] = obj; | |
| 209 } | |
| 440 | 210 |
| 771 | 211 assert (NILP (chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE])); |
| 212 chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE] = obj; | |
| 213 } | |
| 214 else | |
| 215 { | |
| 216 Lisp_Object ret; | |
| 217 /* Actually overwrite the properties of the existing charset. | |
| 218 We do this because until now charsets could never be "deleted", | |
| 219 so parts of the code don't bother to GC charsets. */ | |
| 220 obj = chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE]; | |
| 221 cs = XCHARSET (obj); | |
| 222 assert (EQ (chlook->charset_by_attributes[type][final][direction], | |
| 223 obj)); | |
| 224 | |
| 225 ret = Fremhash (XCHARSET_NAME (obj), Vcharset_hash_table); | |
| 226 assert (!NILP (ret)); | |
| 227 } | |
| 428 | 228 |
| 229 CHARSET_ID (cs) = id; | |
| 230 CHARSET_NAME (cs) = name; | |
| 231 CHARSET_SHORT_NAME (cs) = short_name; | |
| 232 CHARSET_LONG_NAME (cs) = long_name; | |
| 233 CHARSET_REP_BYTES (cs) = rep_bytes; | |
| 234 CHARSET_DIRECTION (cs) = direction; | |
| 235 CHARSET_TYPE (cs) = type; | |
| 236 CHARSET_COLUMNS (cs) = columns; | |
| 237 CHARSET_GRAPHIC (cs) = graphic; | |
| 238 CHARSET_FINAL (cs) = final; | |
| 239 CHARSET_DOC_STRING (cs) = doc; | |
| 3659 | 240 CHECK_VECTOR(reg); |
| 241 CHARSET_REGISTRIES (cs) = reg; | |
| 3439 | 242 CHARSET_ENCODE_AS_UTF_8 (cs) = encode_as_utf_8 ? 1 : 0; |
| 428 | 243 CHARSET_CCL_PROGRAM (cs) = Qnil; |
| 244 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil; | |
| 245 | |
| 771 | 246 CHARSET_DIMENSION (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 || |
| 247 CHARSET_TYPE (cs) == CHARSET_TYPE_96) ? 1 : 2; | |
| 248 CHARSET_CHARS (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 || | |
| 249 CHARSET_TYPE (cs) == CHARSET_TYPE_94X94) ? 94 : 96; | |
| 428 | 250 |
| 771 | 251 if (id == LEADING_BYTE_ASCII || id == LEADING_BYTE_CONTROL_1 |
| 252 #ifdef ENABLE_COMPOSITE_CHARS | |
| 253 || id == LEADING_BYTE_COMPOSITE | |
| 254 #endif | |
| 255 ) | |
| 256 assert (!overwrite); | |
| 257 else | |
| 428 | 258 { |
| 771 | 259 if (overwrite) |
| 260 free_charset_unicode_tables (obj); | |
| 261 init_charset_unicode_tables (obj); | |
| 428 | 262 } |
| 263 | |
| 264 /* Some charsets are "faux" and don't have names or really exist at | |
| 265 all except in the leading-byte table. */ | |
| 266 if (!NILP (name)) | |
| 771 | 267 { |
| 268 assert (NILP (Fgethash (name, Vcharset_hash_table, Qnil))); | |
| 269 Fputhash (name, obj, Vcharset_hash_table); | |
| 270 } | |
| 271 | |
| 272 recalculate_unicode_precedence (); | |
| 3659 | 273 setup_charset_initial_specifier_tags (obj); |
| 274 | |
| 428 | 275 return obj; |
| 276 } | |
| 277 | |
| 278 static int | |
| 279 get_unallocated_leading_byte (int dimension) | |
| 280 { | |
| 281 int lb; | |
| 282 | |
| 283 if (dimension == 1) | |
| 284 { | |
| 771 | 285 if (chlook->next_allocated_1_byte_leading_byte > |
| 286 MAX_LEADING_BYTE_PRIVATE_1) | |
| 428 | 287 lb = 0; |
| 288 else | |
| 442 | 289 lb = chlook->next_allocated_1_byte_leading_byte++; |
| 428 | 290 } |
| 291 else | |
| 292 { | |
| 1747 | 293 /* awfully fragile, but correct */ |
| 294 #if MAX_LEADING_BYTE_PRIVATE_2 == 255 | |
| 295 if (chlook->next_allocated_2_byte_leading_byte == 0) | |
| 1749 | 296 #else |
| 771 | 297 if (chlook->next_allocated_2_byte_leading_byte > |
| 298 MAX_LEADING_BYTE_PRIVATE_2) | |
| 1747 | 299 #endif |
| 428 | 300 lb = 0; |
| 301 else | |
| 442 | 302 lb = chlook->next_allocated_2_byte_leading_byte++; |
| 428 | 303 } |
| 304 | |
| 305 if (!lb) | |
| 563 | 306 invalid_operation |
| 771 | 307 ("No more character sets free for this dimension", make_int (dimension)); |
| 428 | 308 |
| 309 return lb; | |
| 310 } | |
| 311 | |
| 312 | |
| 313 /************************************************************************/ | |
| 314 /* Basic charset Lisp functions */ | |
| 315 /************************************************************************/ | |
| 316 | |
| 788 | 317 void |
| 318 get_charset_limits (Lisp_Object charset, int *low, int *high) | |
| 319 { | |
| 320 Lisp_Charset *cs = XCHARSET (charset); | |
| 321 | |
| 322 if (EQ (charset, Vcharset_ascii)) *low = 0, *high = 127; | |
| 323 else if (EQ (charset, Vcharset_control_1)) *low = 0, *high = 31; | |
| 324 else if (CHARSET_CHARS (cs) == 94) *low = 33, *high = 126; | |
| 325 else /* CHARSET_CHARS (cs) == 96) */ *low = 32, *high = 127; | |
| 326 } | |
| 327 | |
| 428 | 328 DEFUN ("charsetp", Fcharsetp, 1, 1, 0, /* |
| 329 Return non-nil if OBJECT is a charset. | |
| 330 */ | |
| 331 (object)) | |
| 332 { | |
| 333 return CHARSETP (object) ? Qt : Qnil; | |
| 334 } | |
| 335 | |
| 336 DEFUN ("find-charset", Ffind_charset, 1, 1, 0, /* | |
| 337 Retrieve the charset of the given name. | |
| 338 If CHARSET-OR-NAME is a charset object, it is simply returned. | |
| 339 Otherwise, CHARSET-OR-NAME should be a symbol. If there is no such charset, | |
| 340 nil is returned. Otherwise the associated charset object is returned. | |
| 341 */ | |
| 342 (charset_or_name)) | |
| 343 { | |
| 344 if (CHARSETP (charset_or_name)) | |
| 345 return charset_or_name; | |
| 346 | |
| 347 CHECK_SYMBOL (charset_or_name); | |
| 348 return Fgethash (charset_or_name, Vcharset_hash_table, Qnil); | |
| 349 } | |
| 350 | |
| 351 DEFUN ("get-charset", Fget_charset, 1, 1, 0, /* | |
| 352 Retrieve the charset of the given name. | |
| 353 Same as `find-charset' except an error is signalled if there is no such | |
| 354 charset instead of returning nil. | |
| 355 */ | |
| 356 (name)) | |
| 357 { | |
| 358 Lisp_Object charset = Ffind_charset (name); | |
| 359 | |
| 360 if (NILP (charset)) | |
| 563 | 361 invalid_argument ("No such charset", name); |
| 428 | 362 return charset; |
| 363 } | |
| 364 | |
| 365 /* We store the charsets in hash tables with the names as the key and the | |
| 366 actual charset object as the value. Occasionally we need to use them | |
| 367 in a list format. These routines provide us with that. */ | |
| 368 struct charset_list_closure | |
| 369 { | |
| 370 Lisp_Object *charset_list; | |
| 371 }; | |
| 372 | |
| 373 static int | |
| 2286 | 374 add_charset_to_list_mapper (Lisp_Object UNUSED (key), Lisp_Object value, |
| 428 | 375 void *charset_list_closure) |
| 376 { | |
| 377 /* This function can GC */ | |
| 378 struct charset_list_closure *chcl = | |
| 379 (struct charset_list_closure*) charset_list_closure; | |
| 380 Lisp_Object *charset_list = chcl->charset_list; | |
| 381 | |
| 382 *charset_list = Fcons (XCHARSET_NAME (value), *charset_list); | |
| 383 return 0; | |
| 384 } | |
| 385 | |
| 386 DEFUN ("charset-list", Fcharset_list, 0, 0, 0, /* | |
| 387 Return a list of the names of all defined charsets. | |
| 388 */ | |
| 389 ()) | |
| 390 { | |
| 391 Lisp_Object charset_list = Qnil; | |
| 392 struct gcpro gcpro1; | |
| 393 struct charset_list_closure charset_list_closure; | |
| 394 | |
| 395 GCPRO1 (charset_list); | |
| 396 charset_list_closure.charset_list = &charset_list; | |
| 397 elisp_maphash (add_charset_to_list_mapper, Vcharset_hash_table, | |
| 398 &charset_list_closure); | |
| 399 UNGCPRO; | |
| 400 | |
| 401 return charset_list; | |
| 402 } | |
| 403 | |
| 404 DEFUN ("charset-name", Fcharset_name, 1, 1, 0, /* | |
| 444 | 405 Return the name of charset CHARSET. |
| 428 | 406 */ |
| 407 (charset)) | |
| 408 { | |
| 409 return XCHARSET_NAME (Fget_charset (charset)); | |
| 410 } | |
| 411 | |
| 446 | 412 /* #### SJT Should generic properties be allowed? */ |
| 428 | 413 DEFUN ("make-charset", Fmake_charset, 3, 3, 0, /* |
| 414 Define a new character set. | |
| 415 This function is for use with Mule support. | |
| 416 NAME is a symbol, the name by which the character set is normally referred. | |
| 417 DOC-STRING is a string describing the character set. | |
| 418 PROPS is a property list, describing the specific nature of the | |
| 419 character set. Recognized properties are: | |
| 420 | |
| 3025 | 421 `short-name' Short version of the charset name (ex: Latin-1) |
| 422 `long-name' Long version of the charset name (ex: ISO8859-1 (Latin-1)) | |
| 3659 | 423 `registries' A vector of possible XLFD REGISTRY-ENCODING combinations for |
| 424 this character set. Note that this is not a regular expression. | |
| 3025 | 425 `dimension' Number of octets used to index a character in this charset. |
| 428 | 426 Either 1 or 2. Defaults to 1. |
| 3025 | 427 `columns' Number of columns used to display a character in this charset. |
| 428 | 428 Only used in TTY mode. (Under X, the actual width of a |
| 429 character can be derived from the font used to display the | |
| 430 characters.) If unspecified, defaults to the dimension | |
| 431 (this is almost always the correct value). | |
| 3025 | 432 `chars' Number of characters in each dimension (94 or 96). |
| 428 | 433 Defaults to 94. Note that if the dimension is 2, the |
| 434 character set thus described is 94x94 or 96x96. | |
| 3025 | 435 `final' Final byte of ISO 2022 escape sequence. Must be |
| 428 | 436 supplied. Each combination of (DIMENSION, CHARS) defines a |
| 437 separate namespace for final bytes. Note that ISO | |
| 438 2022 restricts the final byte to the range | |
| 439 0x30 - 0x7E if dimension == 1, and 0x30 - 0x5F if | |
| 440 dimension == 2. Note also that final bytes in the range | |
| 441 0x30 - 0x3F are reserved for user-defined (not official) | |
| 442 character sets. | |
| 3025 | 443 `graphic' 0 (use left half of font on output) or 1 (use right half |
| 428 | 444 of font on output). Defaults to 0. For example, for |
| 445 a font whose registry is ISO8859-1, the left half | |
| 446 (octets 0x20 - 0x7F) is the `ascii' character set, while | |
| 447 the right half (octets 0xA0 - 0xFF) is the `latin-1' | |
| 3025 | 448 character set. With `graphic' set to 0, the octets |
| 428 | 449 will have their high bit cleared; with it set to 1, |
| 450 the octets will have their high bit set. | |
| 3025 | 451 `direction' `l2r' (left-to-right) or `r2l' (right-to-left). |
| 452 Defaults to `l2r'. | |
| 453 `ccl-program' A compiled CCL program used to convert a character in | |
| 428 | 454 this charset into an index into the font. This is in |
| 3025 | 455 addition to the `graphic' property. The CCL program |
| 428 | 456 is passed the octets of the character, with the high |
| 457 bit cleared and set depending upon whether the value | |
| 3025 | 458 of the `graphic' property is 0 or 1. |
| 3439 | 459 `encode-as-utf-8' |
| 460 If non-nil, the charset will be written out using the UTF-8 | |
| 461 escape syntax in ISO 2022-oriented coding systems. Used for | |
| 462 supporting characters we know are part of Unicode but not of | |
| 463 any other known character set in escape-quoted and compound | |
| 464 text. | |
| 428 | 465 */ |
| 466 (name, doc_string, props)) | |
| 467 { | |
| 771 | 468 int id, dimension = 1, chars = 94, graphic = 0, columns = -1; |
| 867 | 469 Ibyte final = 0; |
| 428 | 470 int direction = CHARSET_LEFT_TO_RIGHT; |
| 471 int type; | |
| 3659 | 472 Lisp_Object registries = Qnil; |
| 771 | 473 Lisp_Object charset = Qnil; |
| 428 | 474 Lisp_Object ccl_program = Qnil; |
| 475 Lisp_Object short_name = Qnil, long_name = Qnil; | |
| 3439 | 476 int encode_as_utf_8 = 0; |
| 771 | 477 Lisp_Object existing_charset; |
| 478 int temporary = UNBOUNDP (name); | |
| 428 | 479 |
| 771 | 480 /* NOTE: name == Qunbound is a directive from the iso2022 code to |
| 481 create a temporary charset for an unknown final. We allow the final | |
| 482 to be overwritten with a real charset later on. */ | |
| 483 | |
| 428 | 484 if (!NILP (doc_string)) |
| 485 CHECK_STRING (doc_string); | |
| 771 | 486 if (!UNBOUNDP (name)) |
| 487 { | |
| 488 CHECK_SYMBOL (name); | |
| 428 | 489 |
| 771 | 490 charset = Ffind_charset (name); |
| 491 if (!NILP (charset)) | |
| 492 invalid_operation ("Cannot redefine existing charset", name); | |
| 493 } | |
| 428 | 494 |
| 442 | 495 { |
| 496 EXTERNAL_PROPERTY_LIST_LOOP_3 (keyword, value, props) | |
| 497 { | |
| 498 if (EQ (keyword, Qshort_name)) | |
| 499 { | |
| 500 CHECK_STRING (value); | |
| 501 short_name = value; | |
| 502 } | |
| 428 | 503 |
| 519 | 504 else if (EQ (keyword, Qlong_name)) |
| 442 | 505 { |
| 506 CHECK_STRING (value); | |
| 507 long_name = value; | |
| 508 } | |
| 428 | 509 |
| 442 | 510 else if (EQ (keyword, Qdimension)) |
| 511 { | |
| 512 CHECK_INT (value); | |
| 513 dimension = XINT (value); | |
| 514 if (dimension < 1 || dimension > 2) | |
| 3025 | 515 invalid_constant ("Invalid value for `dimension'", value); |
| 442 | 516 } |
| 428 | 517 |
| 442 | 518 else if (EQ (keyword, Qchars)) |
| 519 { | |
| 520 CHECK_INT (value); | |
| 521 chars = XINT (value); | |
| 522 if (chars != 94 && chars != 96) | |
| 3025 | 523 invalid_constant ("Invalid value for `chars'", value); |
| 442 | 524 } |
| 428 | 525 |
| 442 | 526 else if (EQ (keyword, Qcolumns)) |
| 527 { | |
| 528 CHECK_INT (value); | |
| 529 columns = XINT (value); | |
| 530 if (columns != 1 && columns != 2) | |
| 3025 | 531 invalid_constant ("Invalid value for `columns'", value); |
| 442 | 532 } |
| 428 | 533 |
| 442 | 534 else if (EQ (keyword, Qgraphic)) |
| 535 { | |
| 536 CHECK_INT (value); | |
| 537 graphic = XINT (value); | |
| 538 if (graphic < 0 || graphic > 1) | |
| 3025 | 539 invalid_constant ("Invalid value for `graphic'", value); |
| 442 | 540 } |
| 428 | 541 |
| 3659 | 542 else if (EQ (keyword, Qregistries)) |
| 543 { | |
| 544 CHECK_VECTOR (value); | |
| 545 registries = value; | |
| 546 } | |
| 547 | |
| 442 | 548 else if (EQ (keyword, Qregistry)) |
| 549 { | |
| 3659 | 550 Lisp_Object quoted_registry; |
| 551 | |
| 442 | 552 CHECK_STRING (value); |
| 3659 | 553 quoted_registry = Fregexp_quote(value); |
| 3662 | 554 if (qxestrcmp(XSTRING_DATA(quoted_registry), |
| 3659 | 555 XSTRING_DATA(value))) |
| 556 { | |
| 557 warn_when_safe | |
| 558 (Qregistry, Qwarning, | |
| 559 "Regexps no longer allowed for charset-registry. " | |
| 560 "Treating %s as string", XSTRING_DATA(value)); | |
| 561 } | |
| 562 registries = vector1(value); | |
| 442 | 563 } |
| 428 | 564 |
| 442 | 565 else if (EQ (keyword, Qdirection)) |
| 566 { | |
| 567 if (EQ (value, Ql2r)) | |
| 568 direction = CHARSET_LEFT_TO_RIGHT; | |
| 569 else if (EQ (value, Qr2l)) | |
| 570 direction = CHARSET_RIGHT_TO_LEFT; | |
| 571 else | |
| 3025 | 572 invalid_constant ("Invalid value for `direction'", value); |
| 442 | 573 } |
| 428 | 574 |
| 3439 | 575 else if (EQ (keyword, Qencode_as_utf_8)) |
| 576 { | |
| 577 encode_as_utf_8 = NILP (value) ? 0 : 1; | |
| 578 } | |
| 579 | |
| 442 | 580 else if (EQ (keyword, Qfinal)) |
| 581 { | |
| 582 CHECK_CHAR_COERCE_INT (value); | |
| 583 final = XCHAR (value); | |
| 584 if (final < '0' || final > '~') | |
| 3025 | 585 invalid_constant ("Invalid value for `final'", value); |
| 442 | 586 } |
| 587 else if (EQ (keyword, Qccl_program)) | |
| 588 { | |
|
4745
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
589 /* This errors if VALUE is not a valid CCL program. */ |
|
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
590 ccl_program = get_ccl_program (value); |
| 442 | 591 } |
| 592 else | |
| 563 | 593 invalid_constant ("Unrecognized property", keyword); |
| 442 | 594 } |
| 595 } | |
| 428 | 596 |
| 597 if (!final) | |
| 3025 | 598 invalid_argument ("`final' must be specified", Qunbound); |
| 428 | 599 if (dimension == 2 && final > 0x5F) |
| 563 | 600 invalid_constant |
| 428 | 601 ("Final must be in the range 0x30 - 0x5F for dimension == 2", |
| 602 make_char (final)); | |
| 603 | |
| 604 if (dimension == 1) | |
| 605 type = (chars == 94) ? CHARSET_TYPE_94 : CHARSET_TYPE_96; | |
| 606 else | |
| 607 type = (chars == 94) ? CHARSET_TYPE_94X94 : CHARSET_TYPE_96X96; | |
| 608 | |
| 826 | 609 existing_charset = charset_by_attributes (type, final, direction); |
| 771 | 610 |
| 611 if (!NILP (existing_charset) && !XCHARSET (existing_charset)->temporary) | |
| 578 | 612 invalid_argument |
| 793 | 613 ("Character set already defined for this DIMENSION/CHARS/FINAL/DIRECTION combo", |
| 771 | 614 existing_charset); |
| 615 | |
| 616 if (!NILP (existing_charset)) | |
| 617 /* Reuse same leading byte */ | |
| 618 id = XCHARSET_ID (existing_charset); | |
| 619 else | |
| 620 id = get_unallocated_leading_byte (dimension); | |
| 428 | 621 |
| 771 | 622 if (temporary) |
| 623 { | |
| 867 | 624 Ibyte tempname[80]; |
| 428 | 625 |
| 771 | 626 qxesprintf (tempname, "___temporary___%d__", id); |
| 627 name = intern_int (tempname); | |
| 628 } | |
| 428 | 629 if (NILP (doc_string)) |
| 630 doc_string = build_string (""); | |
| 3659 | 631 if (NILP (registries)) |
| 632 registries = make_vector(0, Qnil); | |
| 428 | 633 if (NILP (short_name)) |
| 793 | 634 short_name = XSYMBOL (name)->name; |
| 428 | 635 if (NILP (long_name)) |
| 636 long_name = doc_string; | |
| 637 if (columns == -1) | |
| 638 columns = dimension; | |
| 771 | 639 |
| 428 | 640 charset = make_charset (id, name, dimension + 2, type, columns, graphic, |
| 771 | 641 final, direction, short_name, long_name, |
| 3659 | 642 doc_string, registries, !NILP (existing_charset), |
| 3439 | 643 encode_as_utf_8); |
| 771 | 644 |
| 645 XCHARSET (charset)->temporary = temporary; | |
| 428 | 646 if (!NILP (ccl_program)) |
| 647 XCHARSET_CCL_PROGRAM (charset) = ccl_program; | |
| 771 | 648 |
| 793 | 649 { |
| 650 Lisp_Object revdircs = | |
| 826 | 651 charset_by_attributes (type, final, |
| 793 | 652 direction == CHARSET_LEFT_TO_RIGHT ? |
| 653 CHARSET_RIGHT_TO_LEFT : CHARSET_LEFT_TO_RIGHT); | |
| 654 if (!NILP (revdircs)) | |
| 655 { | |
| 656 XCHARSET_REVERSE_DIRECTION_CHARSET (revdircs) = charset; | |
| 657 XCHARSET_REVERSE_DIRECTION_CHARSET (charset) = revdircs; | |
| 658 } | |
| 659 } | |
| 660 | |
| 428 | 661 return charset; |
| 662 } | |
| 663 | |
| 664 DEFUN ("make-reverse-direction-charset", Fmake_reverse_direction_charset, | |
| 665 2, 2, 0, /* | |
| 666 Make a charset equivalent to CHARSET but which goes in the opposite direction. | |
| 667 NEW-NAME is the name of the new charset. Return the new charset. | |
| 668 */ | |
| 669 (charset, new_name)) | |
| 670 { | |
| 671 Lisp_Object new_charset = Qnil; | |
| 3439 | 672 int id, dimension, columns, graphic, encode_as_utf_8; |
| 867 | 673 Ibyte final; |
| 428 | 674 int direction, type; |
| 3659 | 675 Lisp_Object registries, doc_string, short_name, long_name; |
| 440 | 676 Lisp_Charset *cs; |
| 428 | 677 |
| 678 charset = Fget_charset (charset); | |
| 679 if (!NILP (XCHARSET_REVERSE_DIRECTION_CHARSET (charset))) | |
| 563 | 680 invalid_operation ("Charset already has reverse-direction charset", |
| 793 | 681 charset); |
| 428 | 682 |
| 683 CHECK_SYMBOL (new_name); | |
| 684 if (!NILP (Ffind_charset (new_name))) | |
| 563 | 685 invalid_operation ("Cannot redefine existing charset", new_name); |
| 428 | 686 |
| 687 cs = XCHARSET (charset); | |
| 688 | |
| 689 type = CHARSET_TYPE (cs); | |
| 690 columns = CHARSET_COLUMNS (cs); | |
| 691 dimension = CHARSET_DIMENSION (cs); | |
| 692 id = get_unallocated_leading_byte (dimension); | |
| 693 | |
| 694 graphic = CHARSET_GRAPHIC (cs); | |
| 695 final = CHARSET_FINAL (cs); | |
| 696 direction = CHARSET_RIGHT_TO_LEFT; | |
| 697 if (CHARSET_DIRECTION (cs) == CHARSET_RIGHT_TO_LEFT) | |
| 698 direction = CHARSET_LEFT_TO_RIGHT; | |
| 699 doc_string = CHARSET_DOC_STRING (cs); | |
| 700 short_name = CHARSET_SHORT_NAME (cs); | |
| 701 long_name = CHARSET_LONG_NAME (cs); | |
| 3659 | 702 registries = CHARSET_REGISTRIES (cs); |
| 3439 | 703 encode_as_utf_8 = CHARSET_ENCODE_AS_UTF_8 (cs); |
| 428 | 704 |
| 705 new_charset = make_charset (id, new_name, dimension + 2, type, columns, | |
| 706 graphic, final, direction, short_name, long_name, | |
| 3659 | 707 doc_string, registries, 0, encode_as_utf_8); |
| 428 | 708 |
| 709 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset; | |
| 710 XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset; | |
| 711 | |
| 712 return new_charset; | |
| 713 } | |
| 714 | |
| 715 DEFUN ("charset-reverse-direction-charset", Fcharset_reverse_direction_charset, | |
| 716 1, 1, 0, /* | |
| 717 Return the reverse-direction charset parallel to CHARSET, if any. | |
| 718 This is the charset with the same properties (in particular, the same | |
| 719 dimension, number of characters per dimension, and final byte) as | |
| 720 CHARSET but whose characters are displayed in the opposite direction. | |
| 721 */ | |
| 722 (charset)) | |
| 723 { | |
| 724 charset = Fget_charset (charset); | |
| 725 return XCHARSET_REVERSE_DIRECTION_CHARSET (charset); | |
| 726 } | |
| 727 | |
| 728 DEFUN ("charset-from-attributes", Fcharset_from_attributes, 3, 4, 0, /* | |
| 729 Return a charset with the given DIMENSION, CHARS, FINAL, and DIRECTION. | |
| 730 If DIRECTION is omitted, both directions will be checked (left-to-right | |
| 731 will be returned if character sets exist for both directions). | |
| 732 */ | |
| 733 (dimension, chars, final, direction)) | |
| 734 { | |
| 735 int dm, ch, fi, di = -1; | |
| 736 int type; | |
| 737 Lisp_Object obj = Qnil; | |
| 738 | |
| 739 CHECK_INT (dimension); | |
| 740 dm = XINT (dimension); | |
| 741 if (dm < 1 || dm > 2) | |
| 563 | 742 invalid_constant ("Invalid value for DIMENSION", dimension); |
| 428 | 743 |
| 744 CHECK_INT (chars); | |
| 745 ch = XINT (chars); | |
| 746 if (ch != 94 && ch != 96) | |
| 563 | 747 invalid_constant ("Invalid value for CHARS", chars); |
| 428 | 748 |
| 749 CHECK_CHAR_COERCE_INT (final); | |
| 750 fi = XCHAR (final); | |
| 751 if (fi < '0' || fi > '~') | |
| 563 | 752 invalid_constant ("Invalid value for FINAL", final); |
| 428 | 753 |
| 754 if (EQ (direction, Ql2r)) | |
| 755 di = CHARSET_LEFT_TO_RIGHT; | |
| 756 else if (EQ (direction, Qr2l)) | |
| 757 di = CHARSET_RIGHT_TO_LEFT; | |
| 758 else if (!NILP (direction)) | |
| 563 | 759 invalid_constant ("Invalid value for DIRECTION", direction); |
| 428 | 760 |
| 761 if (dm == 2 && fi > 0x5F) | |
| 563 | 762 invalid_constant |
| 428 | 763 ("Final must be in the range 0x30 - 0x5F for dimension == 2", final); |
| 764 | |
| 765 if (dm == 1) | |
| 766 type = (ch == 94) ? CHARSET_TYPE_94 : CHARSET_TYPE_96; | |
| 767 else | |
| 768 type = (ch == 94) ? CHARSET_TYPE_94X94 : CHARSET_TYPE_96X96; | |
| 769 | |
| 770 if (di == -1) | |
| 771 { | |
| 826 | 772 obj = charset_by_attributes (type, fi, CHARSET_LEFT_TO_RIGHT); |
| 428 | 773 if (NILP (obj)) |
| 826 | 774 obj = charset_by_attributes (type, fi, CHARSET_RIGHT_TO_LEFT); |
| 428 | 775 } |
| 776 else | |
| 826 | 777 obj = charset_by_attributes (type, fi, di); |
| 428 | 778 |
| 779 if (CHARSETP (obj)) | |
| 780 return XCHARSET_NAME (obj); | |
| 781 return obj; | |
| 782 } | |
| 783 | |
| 784 DEFUN ("charset-short-name", Fcharset_short_name, 1, 1, 0, /* | |
| 785 Return short name of CHARSET. | |
| 786 */ | |
| 787 (charset)) | |
| 788 { | |
| 789 return XCHARSET_SHORT_NAME (Fget_charset (charset)); | |
| 790 } | |
| 791 | |
| 792 DEFUN ("charset-long-name", Fcharset_long_name, 1, 1, 0, /* | |
| 793 Return long name of CHARSET. | |
| 794 */ | |
| 795 (charset)) | |
| 796 { | |
| 797 return XCHARSET_LONG_NAME (Fget_charset (charset)); | |
| 798 } | |
| 799 | |
| 800 DEFUN ("charset-description", Fcharset_description, 1, 1, 0, /* | |
| 801 Return description of CHARSET. | |
| 802 */ | |
| 803 (charset)) | |
| 804 { | |
| 805 return XCHARSET_DOC_STRING (Fget_charset (charset)); | |
| 806 } | |
| 807 | |
| 808 DEFUN ("charset-dimension", Fcharset_dimension, 1, 1, 0, /* | |
| 809 Return dimension of CHARSET. | |
| 810 */ | |
| 811 (charset)) | |
| 812 { | |
| 813 return make_int (XCHARSET_DIMENSION (Fget_charset (charset))); | |
| 814 } | |
| 815 | |
| 816 DEFUN ("charset-property", Fcharset_property, 2, 2, 0, /* | |
| 446 | 817 Return property PROP of CHARSET, a charset object or symbol naming a charset. |
| 428 | 818 Recognized properties are those listed in `make-charset', as well as |
| 3025 | 819 `name' and `doc-string'. |
| 428 | 820 */ |
| 821 (charset, prop)) | |
| 822 { | |
| 440 | 823 Lisp_Charset *cs; |
| 428 | 824 |
| 825 charset = Fget_charset (charset); | |
| 826 cs = XCHARSET (charset); | |
| 827 | |
| 828 CHECK_SYMBOL (prop); | |
| 829 if (EQ (prop, Qname)) return CHARSET_NAME (cs); | |
| 830 if (EQ (prop, Qshort_name)) return CHARSET_SHORT_NAME (cs); | |
| 831 if (EQ (prop, Qlong_name)) return CHARSET_LONG_NAME (cs); | |
| 832 if (EQ (prop, Qdoc_string)) return CHARSET_DOC_STRING (cs); | |
| 833 if (EQ (prop, Qdimension)) return make_int (CHARSET_DIMENSION (cs)); | |
| 834 if (EQ (prop, Qcolumns)) return make_int (CHARSET_COLUMNS (cs)); | |
| 835 if (EQ (prop, Qgraphic)) return make_int (CHARSET_GRAPHIC (cs)); | |
| 836 if (EQ (prop, Qfinal)) return make_char (CHARSET_FINAL (cs)); | |
| 837 if (EQ (prop, Qchars)) return make_int (CHARSET_CHARS (cs)); | |
| 3659 | 838 if (EQ (prop, Qregistries)) return CHARSET_REGISTRIES (cs); |
| 3439 | 839 if (EQ (prop, Qencode_as_utf_8)) |
| 840 return CHARSET_ENCODE_AS_UTF_8 (cs) ? Qt : Qnil; | |
| 428 | 841 if (EQ (prop, Qccl_program)) return CHARSET_CCL_PROGRAM (cs); |
| 842 if (EQ (prop, Qdirection)) | |
| 843 return CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? Ql2r : Qr2l; | |
| 844 if (EQ (prop, Qreverse_direction_charset)) | |
| 845 { | |
| 846 Lisp_Object obj = CHARSET_REVERSE_DIRECTION_CHARSET (cs); | |
| 446 | 847 /* #### Is this translation OK? If so, error checking sufficient? */ |
| 848 return CHARSETP (obj) ? XCHARSET_NAME (obj) : obj; | |
| 428 | 849 } |
| 563 | 850 invalid_constant ("Unrecognized charset property name", prop); |
| 1204 | 851 RETURN_NOT_REACHED (Qnil); |
| 428 | 852 } |
| 853 | |
| 854 DEFUN ("charset-id", Fcharset_id, 1, 1, 0, /* | |
| 855 Return charset identification number of CHARSET. | |
| 856 */ | |
| 857 (charset)) | |
| 858 { | |
| 793 | 859 return make_int (XCHARSET_LEADING_BYTE (Fget_charset (charset))); |
| 428 | 860 } |
| 861 | |
| 862 /* #### We need to figure out which properties we really want to | |
| 863 allow to be set. */ | |
| 864 | |
| 865 DEFUN ("set-charset-ccl-program", Fset_charset_ccl_program, 2, 2, 0, /* | |
| 3025 | 866 Set the `ccl-program' property of CHARSET to CCL-PROGRAM. |
| 428 | 867 */ |
| 868 (charset, ccl_program)) | |
| 869 { | |
| 870 charset = Fget_charset (charset); | |
|
4745
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
871 XCHARSET_CCL_PROGRAM (charset) = get_ccl_program (ccl_program); |
|
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
872 |
| 510 | 873 face_property_was_changed (Vdefault_face, Qfont, Qglobal); |
| 428 | 874 return Qnil; |
| 875 } | |
| 876 | |
| 3676 | 877 void |
| 878 set_charset_registries(Lisp_Object charset, Lisp_Object registries) | |
| 879 { | |
| 880 XCHARSET_REGISTRIES (charset) = registries; | |
| 881 invalidate_charset_font_caches (charset); | |
| 882 face_property_was_changed (Vdefault_face, Qfont, Qglobal); | |
| 883 } | |
| 884 | |
| 3711 | 885 DEFUN ("set-charset-registries", Fset_charset_registries, 2, 3, 0, /* |
| 3659 | 886 Set the `registries' property of CHARSET to REGISTRIES. |
| 887 | |
| 888 REGISTRIES is an ordered vector of strings that describe the X11 | |
| 889 CHARSET_REGISTRY and the CHARSET_ENCODINGs appropriate for this charset. | |
| 890 Separate each registry from the corresponding encoding with a dash. The | |
| 891 strings are not regular expressions, in contrast to the old behavior of | |
| 892 the `charset-registry' property. | |
| 893 | |
| 894 One reason to call this function might be if you're in Japan and you'd | |
| 895 prefer the backslash to display as a Yen sign; the corresponding syntax | |
| 896 would be: | |
| 897 | |
| 898 (set-charset-registries 'ascii ["jisx0201.1976-0"]) | |
| 899 | |
| 3711 | 900 If optional argument FORCE is non-nil, avoid sanity-checking the elements of |
| 901 REGISTRIES. Normally the strings are checked to make sure they contain no | |
| 902 XLFD wild cards and that they contain at least one hyphen; the only context | |
| 903 in which one might want not to do this is in order to use a font which | |
| 904 doesn't have a full XLFD--and thus, an effective | |
| 905 CHARSET_REGISTRY-CHARSET_ENCODING of ""--to display ASCII. | |
| 906 | |
| 907 We recommend strongly that you specify a full XLFD, since this makes | |
| 908 multilingual and variant font handling work much better. To get the full | |
| 909 XLFD of any font, start xfd with the short name as the pattern argument: | |
| 910 | |
| 911 xfd -fn 8x16kana | |
| 912 | |
| 913 and use the text that appears at the top of the window. | |
| 428 | 914 */ |
| 3711 | 915 (charset, registries, force)) |
| 428 | 916 { |
| 3659 | 917 int i; |
| 428 | 918 charset = Fget_charset (charset); |
| 3659 | 919 CHECK_VECTOR (registries); |
| 920 | |
| 921 for (i = 0; i < XVECTOR_LENGTH(registries); ++i) | |
| 922 { | |
| 923 CHECK_STRING (XVECTOR_DATA(registries)[i]); | |
| 3711 | 924 |
| 925 if (!NILP(force)) | |
| 926 { | |
| 927 continue; | |
| 928 } | |
| 929 | |
| 3659 | 930 if (NULL == qxestrchr(XSTRING_DATA(XVECTOR_DATA(registries)[i]), '-')) |
| 931 { | |
| 932 invalid_argument("Not an X11 REGISTRY-ENCODING combination", | |
| 933 XVECTOR_DATA(registries)[i]); | |
| 934 } | |
| 3676 | 935 |
| 936 if (qxestrchr(XSTRING_DATA(XVECTOR_DATA(registries)[i]), '*') || | |
| 937 qxestrchr(XSTRING_DATA(XVECTOR_DATA(registries)[i]), '?')) | |
| 938 { | |
| 939 invalid_argument | |
| 940 ("XLFD wildcards not allowed in charset-registries", | |
| 941 XVECTOR_DATA(registries)[i]); | |
| 942 | |
| 943 } | |
| 3659 | 944 } |
| 945 | |
| 3676 | 946 set_charset_registries(charset, registries); |
| 947 | |
| 428 | 948 return Qnil; |
| 949 } | |
| 950 | |
| 3681 | 951 DEFUN ("charsets-in-region", Fcharsets_in_region, 2, 3, 0, /* |
| 952 Return a list of the charsets in the region between START and END. | |
| 953 BUFFER defaults to the current buffer if omitted. | |
| 954 */ | |
| 955 (start, end, buffer)) | |
| 956 { | |
| 957 /* This function can GC */ | |
| 958 struct buffer *buf = decode_buffer (buffer, 1); | |
| 959 Charbpos pos, stop; /* Limits of the region. */ | |
| 960 Lisp_Object res = Qnil; | |
| 961 int charsets[NUM_LEADING_BYTES]; | |
| 962 Ibyte lb; | |
| 963 struct gcpro gcpro1; | |
| 964 | |
| 965 memset(charsets, 0, sizeof(charsets)); | |
| 966 get_buffer_range_char (buf, start, end, &pos, &stop, 0); | |
| 967 | |
| 968 GCPRO1 (res); | |
| 969 while (pos < stop) | |
| 970 { | |
| 971 lb = ichar_leading_byte(BUF_FETCH_CHAR (buf, pos)); | |
| 972 if (0 == charsets[lb - MIN_LEADING_BYTE]) | |
| 973 { | |
| 974 charsets[lb - MIN_LEADING_BYTE] = 1; | |
| 975 res = Fcons (XCHARSET_NAME(charset_by_leading_byte(lb)), res); | |
| 976 } | |
| 977 ++pos; | |
| 978 } | |
| 979 UNGCPRO; | |
| 980 | |
| 981 return res; | |
| 982 } | |
| 983 | |
| 428 | 984 |
| 985 /************************************************************************/ | |
| 771 | 986 /* memory usage */ |
| 428 | 987 /************************************************************************/ |
| 988 | |
| 771 | 989 #ifdef MEMORY_USAGE_STATS |
| 428 | 990 |
| 771 | 991 struct charset_stats |
| 992 { | |
| 993 int from_unicode; | |
| 994 int to_unicode; | |
| 995 int other; | |
| 996 }; | |
| 428 | 997 |
| 771 | 998 static void |
| 999 compute_charset_usage (Lisp_Object charset, struct charset_stats *stats, | |
| 1000 struct overhead_stats *ovstats) | |
| 428 | 1001 { |
| 771 | 1002 struct Lisp_Charset *c = XCHARSET (charset); |
| 1003 xzero (*stats); | |
|
5120
d1247f3cc363
latest work on lisp-object workspace;
Ben Wing <ben@xemacs.org>
parents:
5119
diff
changeset
|
1004 stats->other += LISP_OBJECT_STORAGE_SIZE (c, sizeof (*c), ovstats); |
| 771 | 1005 stats->from_unicode += compute_from_unicode_table_size (charset, ovstats); |
| 1006 stats->to_unicode += compute_to_unicode_table_size (charset, ovstats); | |
| 438 | 1007 } |
| 1008 | |
| 771 | 1009 DEFUN ("charset-memory-usage", Fcharset_memory_usage, 1, 1, 0, /* |
| 1010 Return stats about the memory usage of charset CHARSET. | |
| 1011 The values returned are in the form of an alist of usage types and | |
| 1012 byte counts. The byte counts attempt to encompass all the memory used | |
| 1013 by the charset (separate from the memory logically associated with a | |
| 1014 charset or frame), including internal structures and any malloc() | |
| 1015 overhead associated with them. In practice, the byte counts are | |
| 1016 underestimated for various reasons, e.g. because certain memory usage | |
| 1017 is very hard to determine \(e.g. the amount of memory used inside the | |
| 1018 Xt library or inside the X server). | |
| 428 | 1019 |
| 771 | 1020 Multiple slices of the total memory usage may be returned, separated |
| 1021 by a nil. Each slice represents a particular view of the memory, a | |
| 1022 particular way of partitioning it into groups. Within a slice, there | |
| 1023 is no overlap between the groups of memory, and each slice collectively | |
| 1024 represents all the memory concerned. | |
| 1025 */ | |
| 1026 (charset)) | |
| 1027 { | |
| 1028 struct charset_stats stats; | |
| 1029 struct overhead_stats ovstats; | |
| 1030 Lisp_Object val = Qnil; | |
| 428 | 1031 |
| 771 | 1032 charset = Fget_charset (charset); |
| 1033 xzero (ovstats); | |
| 1034 compute_charset_usage (charset, &stats, &ovstats); | |
| 428 | 1035 |
| 771 | 1036 val = acons (Qfrom_unicode, make_int (stats.from_unicode), val); |
| 1037 val = acons (Qto_unicode, make_int (stats.to_unicode), val); | |
| 1038 val = Fcons (Qnil, val); | |
| 1039 val = acons (Qactually_requested, make_int (ovstats.was_requested), val); | |
| 1040 val = acons (Qmalloc_overhead, make_int (ovstats.malloc_overhead), val); | |
| 1041 val = acons (Qgap_overhead, make_int (ovstats.gap_overhead), val); | |
| 1042 val = acons (Qdynarr_overhead, make_int (ovstats.dynarr_overhead), val); | |
| 1043 | |
| 1044 return Fnreverse (val); | |
| 428 | 1045 } |
| 1046 | |
| 771 | 1047 #endif /* MEMORY_USAGE_STATS */ |
| 428 | 1048 |
| 1049 | |
| 1050 /************************************************************************/ | |
| 1051 /* initialization */ | |
| 1052 /************************************************************************/ | |
| 1053 | |
| 1054 void | |
| 1055 syms_of_mule_charset (void) | |
| 1056 { | |
|
5117
3742ea8250b5
Checking in final CVS version of workspace 'ben-lisp-object'
Ben Wing <ben@xemacs.org>
parents:
3025
diff
changeset
|
1057 INIT_LISP_OBJECT (charset); |
| 442 | 1058 |
| 428 | 1059 DEFSUBR (Fcharsetp); |
| 1060 DEFSUBR (Ffind_charset); | |
| 1061 DEFSUBR (Fget_charset); | |
| 1062 DEFSUBR (Fcharset_list); | |
| 1063 DEFSUBR (Fcharset_name); | |
| 1064 DEFSUBR (Fmake_charset); | |
| 1065 DEFSUBR (Fmake_reverse_direction_charset); | |
| 793 | 1066 DEFSUBR (Fcharset_reverse_direction_charset); |
| 428 | 1067 DEFSUBR (Fcharset_from_attributes); |
| 1068 DEFSUBR (Fcharset_short_name); | |
| 1069 DEFSUBR (Fcharset_long_name); | |
| 1070 DEFSUBR (Fcharset_description); | |
| 1071 DEFSUBR (Fcharset_dimension); | |
| 1072 DEFSUBR (Fcharset_property); | |
| 1073 DEFSUBR (Fcharset_id); | |
| 1074 DEFSUBR (Fset_charset_ccl_program); | |
| 3659 | 1075 DEFSUBR (Fset_charset_registries); |
| 3681 | 1076 DEFSUBR (Fcharsets_in_region); |
| 428 | 1077 |
| 771 | 1078 #ifdef MEMORY_USAGE_STATS |
| 1079 DEFSUBR (Fcharset_memory_usage); | |
| 428 | 1080 #endif |
| 1081 | |
| 563 | 1082 DEFSYMBOL (Qcharsetp); |
| 3659 | 1083 DEFSYMBOL (Qregistries); |
| 563 | 1084 DEFSYMBOL (Qfinal); |
| 1085 DEFSYMBOL (Qgraphic); | |
| 3659 | 1086 DEFSYMBOL (Qregistry); |
| 563 | 1087 DEFSYMBOL (Qdirection); |
| 1088 DEFSYMBOL (Qreverse_direction_charset); | |
| 1089 DEFSYMBOL (Qshort_name); | |
| 1090 DEFSYMBOL (Qlong_name); | |
| 428 | 1091 |
| 771 | 1092 DEFSYMBOL (Qto_unicode); |
| 1093 | |
| 563 | 1094 DEFSYMBOL (Ql2r); |
| 1095 DEFSYMBOL (Qr2l); | |
| 428 | 1096 |
| 1097 /* Charsets, compatible with FSF 20.3 | |
| 1098 Naming convention is Script-Charset[-Edition] */ | |
| 563 | 1099 DEFSYMBOL (Qlatin_iso8859_1); |
| 1100 DEFSYMBOL (Qlatin_iso8859_2); | |
| 1101 DEFSYMBOL (Qlatin_iso8859_3); | |
| 1102 DEFSYMBOL (Qlatin_iso8859_4); | |
| 1103 DEFSYMBOL (Qthai_tis620); | |
| 1104 DEFSYMBOL (Qgreek_iso8859_7); | |
| 1105 DEFSYMBOL (Qhebrew_iso8859_8); | |
| 1106 DEFSYMBOL (Qkatakana_jisx0201); | |
| 1107 DEFSYMBOL (Qlatin_jisx0201); | |
| 1108 DEFSYMBOL (Qcyrillic_iso8859_5); | |
| 1109 DEFSYMBOL (Qlatin_iso8859_9); | |
| 728 | 1110 DEFSYMBOL (Qlatin_iso8859_15); |
| 563 | 1111 DEFSYMBOL (Qjapanese_jisx0208_1978); |
| 1112 DEFSYMBOL (Qchinese_gb2312); | |
| 1113 DEFSYMBOL (Qjapanese_jisx0208); | |
| 1114 DEFSYMBOL (Qkorean_ksc5601); | |
| 1115 DEFSYMBOL (Qjapanese_jisx0212); | |
| 1116 DEFSYMBOL (Qchinese_cns11643_1); | |
| 1117 DEFSYMBOL (Qchinese_cns11643_2); | |
| 1118 DEFSYMBOL (Qchinese_big5_1); | |
| 1119 DEFSYMBOL (Qchinese_big5_2); | |
| 428 | 1120 |
| 563 | 1121 DEFSYMBOL (Qcomposite); |
| 428 | 1122 } |
| 1123 | |
| 1124 void | |
| 1125 vars_of_mule_charset (void) | |
| 1126 { | |
| 1127 int i, j, k; | |
| 1128 | |
| 452 | 1129 chlook = xnew_and_zero (struct charset_lookup); /* zero for Purify. */ |
| 2367 | 1130 dump_add_root_block_ptr (&chlook, &charset_lookup_description); |
| 428 | 1131 |
| 1132 /* Table of charsets indexed by leading byte. */ | |
| 1133 for (i = 0; i < countof (chlook->charset_by_leading_byte); i++) | |
| 1134 chlook->charset_by_leading_byte[i] = Qnil; | |
| 1135 | |
| 1136 /* Table of charsets indexed by type/final-byte/direction. */ | |
| 1137 for (i = 0; i < countof (chlook->charset_by_attributes); i++) | |
| 1138 for (j = 0; j < countof (chlook->charset_by_attributes[0]); j++) | |
| 1139 for (k = 0; k < countof (chlook->charset_by_attributes[0][0]); k++) | |
| 1140 chlook->charset_by_attributes[i][j][k] = Qnil; | |
| 1141 | |
| 442 | 1142 chlook->next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1; |
| 1143 chlook->next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2; | |
| 771 | 1144 |
| 1145 staticpro (&Vcharset_hash_table); | |
| 1146 Vcharset_hash_table = | |
| 1147 make_lisp_hash_table (50, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ); | |
| 428 | 1148 } |
| 1149 | |
| 1150 void | |
| 1151 complex_vars_of_mule_charset (void) | |
| 1152 { | |
| 1153 /* Predefined character sets. We store them into variables for | |
| 1154 ease of access. */ | |
| 1155 | |
| 1156 staticpro (&Vcharset_ascii); | |
| 1157 Vcharset_ascii = | |
| 1158 make_charset (LEADING_BYTE_ASCII, Qascii, 1, | |
| 1159 CHARSET_TYPE_94, 1, 0, 'B', | |
| 1160 CHARSET_LEFT_TO_RIGHT, | |
| 1161 build_string ("ASCII"), | |
| 771 | 1162 build_msg_string ("ASCII"), |
| 1163 build_msg_string ("ASCII (ISO646 IRV)"), | |
| 3659 | 1164 vector1(build_string("iso8859-1")), 0, 0); |
| 428 | 1165 staticpro (&Vcharset_control_1); |
| 1166 Vcharset_control_1 = | |
| 1167 make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2, | |
| 1168 CHARSET_TYPE_94, 1, 1, 0, | |
| 1169 CHARSET_LEFT_TO_RIGHT, | |
| 1170 build_string ("C1"), | |
| 771 | 1171 build_msg_string ("Control characters"), |
| 1172 build_msg_string ("Control characters 128-191"), | |
| 3659 | 1173 vector1(build_string("iso8859-1")), 0, 0); |
| 428 | 1174 staticpro (&Vcharset_latin_iso8859_1); |
| 1175 Vcharset_latin_iso8859_1 = | |
| 1176 make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2, | |
| 1177 CHARSET_TYPE_96, 1, 1, 'A', | |
| 1178 CHARSET_LEFT_TO_RIGHT, | |
| 1179 build_string ("Latin-1"), | |
| 771 | 1180 build_msg_string ("ISO8859-1 (Latin-1)"), |
| 1181 build_msg_string ("ISO8859-1 (Latin-1)"), | |
| 3659 | 1182 vector1(build_string("iso8859-1")), 0, 0); |
| 428 | 1183 staticpro (&Vcharset_latin_iso8859_2); |
| 1184 Vcharset_latin_iso8859_2 = | |
| 1185 make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2, | |
| 1186 CHARSET_TYPE_96, 1, 1, 'B', | |
| 1187 CHARSET_LEFT_TO_RIGHT, | |
| 1188 build_string ("Latin-2"), | |
| 771 | 1189 build_msg_string ("ISO8859-2 (Latin-2)"), |
| 1190 build_msg_string ("ISO8859-2 (Latin-2)"), | |
| 3659 | 1191 vector1(build_string("iso8859-2")), 0, 0); |
| 428 | 1192 staticpro (&Vcharset_latin_iso8859_3); |
| 1193 Vcharset_latin_iso8859_3 = | |
| 1194 make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2, | |
| 1195 CHARSET_TYPE_96, 1, 1, 'C', | |
| 1196 CHARSET_LEFT_TO_RIGHT, | |
| 1197 build_string ("Latin-3"), | |
| 771 | 1198 build_msg_string ("ISO8859-3 (Latin-3)"), |
| 1199 build_msg_string ("ISO8859-3 (Latin-3)"), | |
| 3659 | 1200 vector1(build_string("iso8859-3")), 0, 0); |
| 428 | 1201 staticpro (&Vcharset_latin_iso8859_4); |
| 1202 Vcharset_latin_iso8859_4 = | |
| 1203 make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2, | |
| 1204 CHARSET_TYPE_96, 1, 1, 'D', | |
| 1205 CHARSET_LEFT_TO_RIGHT, | |
| 1206 build_string ("Latin-4"), | |
| 771 | 1207 build_msg_string ("ISO8859-4 (Latin-4)"), |
| 1208 build_msg_string ("ISO8859-4 (Latin-4)"), | |
| 3816 | 1209 vector1(build_string("iso8859-4")), 0, 0); |
| 428 | 1210 staticpro (&Vcharset_thai_tis620); |
| 1211 Vcharset_thai_tis620 = | |
| 1212 make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2, | |
| 1213 CHARSET_TYPE_96, 1, 1, 'T', | |
| 1214 CHARSET_LEFT_TO_RIGHT, | |
| 1215 build_string ("TIS620"), | |
| 771 | 1216 build_msg_string ("TIS620 (Thai)"), |
| 1217 build_msg_string ("TIS620.2529 (Thai)"), | |
| 3659 | 1218 vector1(build_string("tis620.2529-1")), 0, 0); |
| 428 | 1219 staticpro (&Vcharset_greek_iso8859_7); |
| 1220 Vcharset_greek_iso8859_7 = | |
| 1221 make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2, | |
| 1222 CHARSET_TYPE_96, 1, 1, 'F', | |
| 1223 CHARSET_LEFT_TO_RIGHT, | |
| 1224 build_string ("ISO8859-7"), | |
| 771 | 1225 build_msg_string ("ISO8859-7 (Greek)"), |
| 1226 build_msg_string ("ISO8859-7 (Greek)"), | |
| 3659 | 1227 vector1(build_string("iso8859-7")), 0, 0); |
| 428 | 1228 staticpro (&Vcharset_hebrew_iso8859_8); |
| 1229 Vcharset_hebrew_iso8859_8 = | |
| 1230 make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2, | |
| 1231 CHARSET_TYPE_96, 1, 1, 'H', | |
| 1232 CHARSET_RIGHT_TO_LEFT, | |
| 1233 build_string ("ISO8859-8"), | |
| 771 | 1234 build_msg_string ("ISO8859-8 (Hebrew)"), |
| 1235 build_msg_string ("ISO8859-8 (Hebrew)"), | |
| 3659 | 1236 vector1(build_string ("iso8859-8")), 0, 0); |
| 428 | 1237 staticpro (&Vcharset_katakana_jisx0201); |
| 1238 Vcharset_katakana_jisx0201 = | |
| 1239 make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2, | |
| 1240 CHARSET_TYPE_94, 1, 1, 'I', | |
| 1241 CHARSET_LEFT_TO_RIGHT, | |
| 1242 build_string ("JISX0201 Kana"), | |
| 771 | 1243 build_msg_string ("JISX0201.1976 (Japanese Kana)"), |
| 1244 build_msg_string ("JISX0201.1976 Japanese Kana"), | |
| 3659 | 1245 vector1(build_string ("jisx0201.1976-0")), 0, 0); |
| 428 | 1246 staticpro (&Vcharset_latin_jisx0201); |
| 1247 Vcharset_latin_jisx0201 = | |
| 1248 make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2, | |
| 1249 CHARSET_TYPE_94, 1, 0, 'J', | |
| 1250 CHARSET_LEFT_TO_RIGHT, | |
| 1251 build_string ("JISX0201 Roman"), | |
| 771 | 1252 build_msg_string ("JISX0201.1976 (Japanese Roman)"), |
| 1253 build_msg_string ("JISX0201.1976 Japanese Roman"), | |
| 3659 | 1254 vector1(build_string ("jisx0201.1976-0")), 0, 0); |
| 428 | 1255 staticpro (&Vcharset_cyrillic_iso8859_5); |
| 1256 Vcharset_cyrillic_iso8859_5 = | |
| 1257 make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2, | |
| 1258 CHARSET_TYPE_96, 1, 1, 'L', | |
| 1259 CHARSET_LEFT_TO_RIGHT, | |
| 1260 build_string ("ISO8859-5"), | |
| 771 | 1261 build_msg_string ("ISO8859-5 (Cyrillic)"), |
| 1262 build_msg_string ("ISO8859-5 (Cyrillic)"), | |
| 3659 | 1263 vector1(build_string ("iso8859-5")), 0, 0); |
| 428 | 1264 staticpro (&Vcharset_latin_iso8859_9); |
| 1265 Vcharset_latin_iso8859_9 = | |
| 1266 make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2, | |
| 1267 CHARSET_TYPE_96, 1, 1, 'M', | |
| 1268 CHARSET_LEFT_TO_RIGHT, | |
| 1269 build_string ("Latin-5"), | |
| 771 | 1270 build_msg_string ("ISO8859-9 (Latin-5)"), |
| 1271 build_msg_string ("ISO8859-9 (Latin-5)"), | |
| 3659 | 1272 vector1(build_string ("iso8859-9")), 0, 0); |
| 728 | 1273 staticpro (&Vcharset_latin_iso8859_15); |
| 1274 Vcharset_latin_iso8859_15 = | |
| 1275 make_charset (LEADING_BYTE_LATIN_ISO8859_15, Qlatin_iso8859_15, 2, | |
| 1276 CHARSET_TYPE_96, 1, 1, 'b', | |
| 1277 CHARSET_LEFT_TO_RIGHT, | |
| 1278 build_string ("Latin-9"), | |
| 771 | 1279 build_msg_string ("ISO8859-15 (Latin-9)"), |
| 1280 build_msg_string ("ISO8859-15 (Latin-9)"), | |
| 3659 | 1281 vector1(build_string ("iso8859-15")), 0, 0); |
| 428 | 1282 staticpro (&Vcharset_japanese_jisx0208_1978); |
| 1283 Vcharset_japanese_jisx0208_1978 = | |
| 1284 make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3, | |
| 1285 CHARSET_TYPE_94X94, 2, 0, '@', | |
| 1286 CHARSET_LEFT_TO_RIGHT, | |
| 1287 build_string ("JISX0208.1978"), | |
| 771 | 1288 build_msg_string ("JISX0208.1978 (Japanese)"), |
| 1289 build_msg_string | |
| 428 | 1290 ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"), |
| 3659 | 1291 vector2(build_string("jisx0208.1978-0"), |
| 1292 build_string("jisc6226.1978-0")), 0, 0); | |
| 428 | 1293 staticpro (&Vcharset_chinese_gb2312); |
| 1294 Vcharset_chinese_gb2312 = | |
| 1295 make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3, | |
| 1296 CHARSET_TYPE_94X94, 2, 0, 'A', | |
| 1297 CHARSET_LEFT_TO_RIGHT, | |
| 1298 build_string ("GB2312"), | |
| 771 | 1299 build_msg_string ("GB2312)"), |
| 1300 build_msg_string ("GB2312 Chinese simplified"), | |
| 3659 | 1301 vector2(build_string("gb2312.1980-0"), |
| 1302 build_string("gb2312.80&gb8565.88-0")), 0, 0); | |
| 428 | 1303 staticpro (&Vcharset_japanese_jisx0208); |
| 1304 Vcharset_japanese_jisx0208 = | |
| 1305 make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3, | |
| 1306 CHARSET_TYPE_94X94, 2, 0, 'B', | |
| 1307 CHARSET_LEFT_TO_RIGHT, | |
| 1308 build_string ("JISX0208"), | |
| 771 | 1309 build_msg_string ("JISX0208.1983/1990 (Japanese)"), |
| 1310 build_msg_string ("JISX0208.1983/1990 Japanese Kanji"), | |
| 3659 | 1311 vector2(build_string("jisx0208.1983-0"), |
| 1312 build_string("jisx0208.1990-0")), 0, 0); | |
| 428 | 1313 staticpro (&Vcharset_korean_ksc5601); |
| 1314 Vcharset_korean_ksc5601 = | |
| 1315 make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3, | |
| 1316 CHARSET_TYPE_94X94, 2, 0, 'C', | |
| 1317 CHARSET_LEFT_TO_RIGHT, | |
| 1318 build_string ("KSC5601"), | |
| 771 | 1319 build_msg_string ("KSC5601 (Korean"), |
| 1320 build_msg_string ("KSC5601 Korean Hangul and Hanja"), | |
| 3659 | 1321 vector1(build_string("ksc5601.1987-0")), 0, 0); |
| 428 | 1322 staticpro (&Vcharset_japanese_jisx0212); |
| 1323 Vcharset_japanese_jisx0212 = | |
| 1324 make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3, | |
| 1325 CHARSET_TYPE_94X94, 2, 0, 'D', | |
| 1326 CHARSET_LEFT_TO_RIGHT, | |
| 1327 build_string ("JISX0212"), | |
| 771 | 1328 build_msg_string ("JISX0212 (Japanese)"), |
| 1329 build_msg_string ("JISX0212 Japanese Supplement"), | |
| 3659 | 1330 vector1(build_string("jisx0212.1990-0")), 0, 0); |
| 428 | 1331 |
| 3659 | 1332 #define CHINESE_CNS_PLANE(n) "cns11643.1992-" n |
| 428 | 1333 staticpro (&Vcharset_chinese_cns11643_1); |
| 1334 Vcharset_chinese_cns11643_1 = | |
| 1335 make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 3, | |
| 1336 CHARSET_TYPE_94X94, 2, 0, 'G', | |
| 1337 CHARSET_LEFT_TO_RIGHT, | |
| 1338 build_string ("CNS11643-1"), | |
| 771 | 1339 build_msg_string ("CNS11643-1 (Chinese traditional)"), |
| 1340 build_msg_string | |
| 428 | 1341 ("CNS 11643 Plane 1 Chinese traditional"), |
| 3659 | 1342 vector1(build_string (CHINESE_CNS_PLANE("1"))), 0, 0); |
| 428 | 1343 staticpro (&Vcharset_chinese_cns11643_2); |
| 1344 Vcharset_chinese_cns11643_2 = | |
| 1345 make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3, | |
| 1346 CHARSET_TYPE_94X94, 2, 0, 'H', | |
| 1347 CHARSET_LEFT_TO_RIGHT, | |
| 1348 build_string ("CNS11643-2"), | |
| 771 | 1349 build_msg_string ("CNS11643-2 (Chinese traditional)"), |
| 1350 build_msg_string | |
| 428 | 1351 ("CNS 11643 Plane 2 Chinese traditional"), |
| 3659 | 1352 vector1(build_string (CHINESE_CNS_PLANE("2"))), 0, 0); |
| 428 | 1353 staticpro (&Vcharset_chinese_big5_1); |
| 1354 Vcharset_chinese_big5_1 = | |
| 1355 make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3, | |
| 1356 CHARSET_TYPE_94X94, 2, 0, '0', | |
| 1357 CHARSET_LEFT_TO_RIGHT, | |
| 1358 build_string ("Big5"), | |
| 771 | 1359 build_msg_string ("Big5 (Level-1)"), |
| 1360 build_msg_string | |
| 428 | 1361 ("Big5 Level-1 Chinese traditional"), |
| 3659 | 1362 vector1(build_string ("big5.eten-0")), 0, 0); |
| 428 | 1363 staticpro (&Vcharset_chinese_big5_2); |
| 1364 Vcharset_chinese_big5_2 = | |
| 1365 make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3, | |
| 1366 CHARSET_TYPE_94X94, 2, 0, '1', | |
| 1367 CHARSET_LEFT_TO_RIGHT, | |
| 1368 build_string ("Big5"), | |
| 771 | 1369 build_msg_string ("Big5 (Level-2)"), |
| 1370 build_msg_string | |
| 428 | 1371 ("Big5 Level-2 Chinese traditional"), |
| 3659 | 1372 vector1(build_string ("big5.eten-0")), 0, 0); |
| 428 | 1373 |
| 1374 | |
| 1375 #ifdef ENABLE_COMPOSITE_CHARS | |
| 1376 /* #### For simplicity, we put composite chars into a 96x96 charset. | |
| 1377 This is going to lead to problems because you can run out of | |
| 1378 room, esp. as we don't yet recycle numbers. */ | |
| 1379 staticpro (&Vcharset_composite); | |
| 1380 Vcharset_composite = | |
| 1381 make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, 3, | |
| 1382 CHARSET_TYPE_96X96, 2, 0, 0, | |
| 1383 CHARSET_LEFT_TO_RIGHT, | |
| 1384 build_string ("Composite"), | |
| 771 | 1385 build_msg_string ("Composite characters"), |
| 1386 build_msg_string ("Composite characters"), | |
| 3659 | 1387 vector1(build_string ("")), 0, 0); |
| 771 | 1388 #else |
| 1389 /* We create a hack so that we have a way of storing ESC 0 and ESC 1 | |
| 1390 sequences as "characters", so that they will be output correctly. */ | |
| 1391 staticpro (&Vcharset_composite); | |
| 1392 Vcharset_composite = | |
| 1393 make_charset (LEADING_BYTE_COMPOSITE_REPLACEMENT, Qcomposite, 2, | |
| 1394 CHARSET_TYPE_96, 1, 1, '|', | |
| 1395 CHARSET_LEFT_TO_RIGHT, | |
| 1396 build_string ("Composite hack"), | |
| 1397 build_msg_string ("Composite characters hack"), | |
| 1398 build_msg_string ("Composite characters hack"), | |
| 3659 | 1399 vector1(build_string ("")), 0, 0); |
| 428 | 1400 #endif /* ENABLE_COMPOSITE_CHARS */ |
| 1401 } |