Mercurial > hg > xemacs-beta
view src/chartab.h @ 4690:257b468bf2ca
Move the #'query-coding-region implementation to C.
This is necessary because there is no reasonable way to access the
corresponding mswindows-multibyte functionality from Lisp, and we need such
functionality if we're going to have a reliable and portable
#'query-coding-region implementation. However, this change doesn't yet
provide #'query-coding-region for the mswindow-multibyte coding systems,
there should be no functional differences between an XEmacs with this change
and one without it.
src/ChangeLog addition:
2009-09-19 Aidan Kehoe <kehoea@parhasard.net>
Move the #'query-coding-region implementation to C.
This is necessary because there is no reasonable way to access the
corresponding mswindows-multibyte functionality from Lisp, and we
need such functionality if we're going to have a reliable and
portable #'query-coding-region implementation. However, this
change doesn't yet provide #'query-coding-region for the
mswindow-multibyte coding systems, there should be no functional
differences between an XEmacs with this change and one without it.
* mule-coding.c (struct fixed_width_coding_system):
Add a new coding system type, fixed_width, and implement it. It
uses the CCL infrastructure but has a much simpler creation API,
and its own query_method, formerly in lisp/mule/mule-coding.el.
* unicode.c:
Move the Unicode query method implementation here from
unicode.el.
* lisp.h: Declare Fmake_coding_system_internal, Fcopy_range_table
here.
* intl-win32.c (complex_vars_of_intl_win32):
Use Fmake_coding_system_internal, not Fmake_coding_system.
* general-slots.h: Add Qsucceeded, Qunencodable, Qinvalid_sequence
here.
* file-coding.h (enum coding_system_variant):
Add fixed_width_coding_system here.
(struct coding_system_methods):
Add query_method and query_lstream_method to the coding system
methods.
Provide flags for the query methods.
Declare the default query method; initialise it correctly in
INITIALIZE_CODING_SYSTEM_TYPE.
* file-coding.c (default_query_method):
New function, the default query method for coding systems that do
not set it. Moved from coding.el.
(make_coding_system_1):
Accept new elements in PROPS in #'make-coding-system; aliases, a
list of aliases; safe-chars and safe-charsets (these were
previously accepted but not saved); and category.
(Fmake_coding_system_internal):
New function, what used to be #'make-coding-system--on Mule
builds, we've now moved some of the functionality of this to
Lisp.
(Fcoding_system_canonical_name_p):
Move this earlier in the file, since it's now called from within
make_coding_system_1.
(Fquery_coding_region):
Move the implementation of this here, from coding.el.
(complex_vars_of_file_coding):
Call Fmake_coding_system_internal, not Fmake_coding_system;
specify safe-charsets properties when we're a mule build.
* extents.h (mouse_highlight_priority, Fset_extent_priority,
Fset_extent_face, Fmap_extents):
Make these available to other C files.
lisp/ChangeLog addition:
2009-09-19 Aidan Kehoe <kehoea@parhasard.net>
Move the #'query-coding-region implementation to C.
* coding.el:
Consolidate code that depends on the presence or absence of Mule
at the end of this file.
(default-query-coding-region, query-coding-region):
Move these functions to C.
(default-query-coding-region-safe-charset-skip-chars-map):
Remove this variable, the corresponding C variable is
Vdefault_query_coding_region_chartab_cache in file-coding.c.
(query-coding-string): Update docstring to reflect actual multiple
values, be more careful about not modifying a range table that
we're currently mapping over.
(encode-coding-char): Make the implementation of this simpler.
(featurep 'mule): Autoload #'make-coding-system from
mule/make-coding-system.el if we're a mule build; provide an
appropriate compiler macro.
Do various non-mule compatibility things if we're not a mule
build.
* update-elc.el (additional-dump-dependencies):
Add mule/make-coding-system as a dump time dependency if we're a
mule build.
* unicode.el (ccl-encode-to-ucs-2):
(decode-char):
(encode-char):
Move these earlier in the file, for the sake of some byte compile
warnings.
(unicode-query-coding-region):
Move this to unicode.c
* mule/make-coding-system.el:
New file, not dumped. Contains the functionality to rework the
arguments necessary for fixed-width coding systems, and contains
the implementation of #'make-coding-system, which now calls
#'make-coding-system-internal.
* mule/vietnamese.el (viscii):
* mule/latin.el (iso-8859-2):
(windows-1250):
(iso-8859-3):
(iso-8859-4):
(iso-8859-14):
(iso-8859-15):
(iso-8859-16):
(iso-8859-9):
(macintosh):
(windows-1252):
* mule/hebrew.el (iso-8859-8):
* mule/greek.el (iso-8859-7):
(windows-1253):
* mule/cyrillic.el (iso-8859-5):
(koi8-r):
(koi8-u):
(windows-1251):
(alternativnyj):
(koi8-ru):
(koi8-t):
(koi8-c):
(koi8-o):
* mule/arabic.el (iso-8859-6):
(windows-1256):
Move all these coding systems to being of type fixed-width, not of
type CCL. This allows the distinct query-coding-region for them to
be in C, something which will eventually allow us to implement
query-coding-region for the mswindows-multibyte coding systems.
* mule/general-late.el (posix-charset-to-coding-system-hash):
Document why we're pre-emptively persuading the byte compiler that
the ELC for this file needs to be written using escape-quoted.
Call #'set-unicode-query-skip-chars-args, now the Unicode
query-coding-region implementation is in C.
* mule/thai-xtis.el (tis-620):
Don't bother checking whether we're XEmacs or not here.
* mule/mule-coding.el:
Move the eight bit fixed-width functionality from this file to
make-coding-system.el.
tests/ChangeLog addition:
2009-09-19 Aidan Kehoe <kehoea@parhasard.net>
* automated/mule-tests.el:
Check a coding system's type, not an 8-bit-fixed property, for
whether that coding system should be treated as a fixed-width
coding system.
* automated/query-coding-tests.el:
Don't test the query coding functionality for mswindows-multibyte
coding systems, it's not yet implemented.
author | Aidan Kehoe <kehoea@parhasard.net> |
---|---|
date | Sat, 19 Sep 2009 22:53:13 +0100 |
parents | 1e7cc382eb16 |
children | e0db3c197671 |
line wrap: on
line source
/* Declarations having to do with Mule char tables. Copyright (C) 1992 Free Software Foundation, Inc. Copyright (C) 1995 Sun Microsystems, Inc. Copyright (C) 2002, 2003 Ben Wing. This file is part of XEmacs. XEmacs 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 2, or (at your option) any later version. XEmacs 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 XEmacs; see the file COPYING. If not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ /* Synched up with: Mule 2.3. Not synched with FSF. This file was written independently of the FSF implementation, and is not compatible. */ #ifndef INCLUDED_chartab_h_ #define INCLUDED_chartab_h_ #include "charset.h" /************************************************************************/ /* Char Tables */ /************************************************************************/ /* Under Mule, we use a complex representation (see below). When not under Mule, there are only 256 possible characters so we just represent them directly. */ #ifdef MULE struct Lisp_Char_Table_Entry { struct LCRECORD_HEADER header; /* In the interests of simplicity, we just use a fixed 96-entry table. If we felt like being smarter, we could make this variable-size and add an offset value into this structure. */ Lisp_Object level2[96]; }; typedef struct Lisp_Char_Table_Entry Lisp_Char_Table_Entry; DECLARE_LRECORD (char_table_entry, Lisp_Char_Table_Entry); #define XCHAR_TABLE_ENTRY(x) \ XRECORD (x, char_table_entry, Lisp_Char_Table_Entry) #define wrap_char_table_entry(p) wrap_record (p, char_table_entry) #define CHAR_TABLE_ENTRYP(x) RECORDP (x, char_table_entry) /* #define CHECK_CHAR_TABLE_ENTRY(x) CHECK_RECORD (x, char_table_entry) char table entries should never escape to Lisp */ #endif /* MULE */ enum char_table_type { CHAR_TABLE_TYPE_GENERIC, #ifdef MULE CHAR_TABLE_TYPE_CATEGORY, #endif CHAR_TABLE_TYPE_SYNTAX, CHAR_TABLE_TYPE_DISPLAY, CHAR_TABLE_TYPE_CHAR }; #ifdef MULE #define NUM_ASCII_CHARS 160 #else #define NUM_ASCII_CHARS 256 #endif struct Lisp_Char_Table { struct LCRECORD_HEADER header; Lisp_Object ascii[NUM_ASCII_CHARS]; Lisp_Object default_; Lisp_Object parent; /* #### not yet implemented */ #ifdef MULE /* We basically duplicate the Mule vectors-of-vectors implementation. We can do this because we know a great deal about the sorts of things we are going to be indexing. The current implementation is as follows: ascii[0-159] is used for ASCII and Control-1 characters. level1[0 .. (NUM_LEADING_BYTES-1)] indexes charsets by leading byte (subtract MIN_LEADING_BYTE from the leading byte). If the value of this is not an opaque, then it specifies a value for all characters in the charset. Otherwise, it will be a 96-Lisp-Object opaque that we created, specifying a value for each row. If the value of this is not an opaque, then it specifies a value for all characters in the row. Otherwise, it will be a 96-Lisp-Object opaque that we created, specifying a value for each character. NOTE: 1) This will fail if some C routine passes an opaque to Fput_char_table(). Currently this is not a problem since all char tables that are created are Lisp-visible and thus no one should ever be putting an opaque in a char table. Another possibility is to consider adding a type to */ Lisp_Object level1[NUM_LEADING_BYTES]; #endif /* MULE */ enum char_table_type type; /* stuff used for syntax tables */ Lisp_Object mirror_table; /* points to mirror table for this table (a cache for quicker access), or a back pointer if MIRROR_TABLE_P. */ Lisp_Object next_table; /* DO NOT mark through this. */ char dirty; /* nonzero if mirror dirty and needs updating. */ char mirror_table_p; /* nonzero if this is a mirror table. */ }; typedef struct Lisp_Char_Table Lisp_Char_Table; DECLARE_LRECORD (char_table, Lisp_Char_Table); #define XCHAR_TABLE(x) XRECORD (x, char_table, Lisp_Char_Table) #define wrap_char_table(p) wrap_record (p, char_table) #define CHAR_TABLEP(x) RECORDP (x, char_table) #define CHECK_CHAR_TABLE(x) CHECK_RECORD (x, char_table) #define CONCHECK_CHAR_TABLE(x) CONCHECK_RECORD (x, char_table) #define CHAR_TABLE_TYPE(ct) ((ct)->type) #define XCHAR_TABLE_TYPE(ct) CHAR_TABLE_TYPE (XCHAR_TABLE (ct)) Lisp_Object get_non_ascii_char_table_value (Lisp_Char_Table *ct, int leading_byte, Ichar c); DECLARE_INLINE_HEADER ( Lisp_Object get_char_table_1 (Ichar ch, Lisp_Object table) ) { Lisp_Object retval; Lisp_Char_Table *ct = XCHAR_TABLE (table); #ifdef MULE if (ch < NUM_ASCII_CHARS) retval = ct->ascii[ch]; else { unsigned char lb = ichar_leading_byte (ch); if (!CHAR_TABLE_ENTRYP (ct->level1[lb - MIN_LEADING_BYTE])) retval = ct->level1[lb - MIN_LEADING_BYTE]; else retval = get_non_ascii_char_table_value (ct, lb, ch); } #else /* not MULE */ retval = ct->ascii[(unsigned char) ch]; #endif /* not MULE */ if (!UNBOUNDP (retval)) return retval; else return ct->default_; } #ifdef ERROR_CHECK_TYPES DECLARE_INLINE_HEADER ( Lisp_Object get_char_table (Ichar ch, Lisp_Object table) ) { assert (!XCHAR_TABLE (table)->mirror_table_p); return get_char_table_1 (ch, table); } #else #define get_char_table(ch, table) get_char_table_1 (ch, table) #endif enum chartab_range_type { CHARTAB_RANGE_ALL, #ifdef MULE CHARTAB_RANGE_CHARSET, CHARTAB_RANGE_ROW, #endif CHARTAB_RANGE_CHAR }; struct chartab_range { enum chartab_range_type type; Ichar ch; Lisp_Object charset; int row; }; void set_char_table_default (Lisp_Object table, Lisp_Object value); void put_char_table (Lisp_Object table, struct chartab_range *range, Lisp_Object val); int map_char_table (Lisp_Object table, struct chartab_range *range, int (*fn) (struct chartab_range *range, Lisp_Object table, Lisp_Object val, void *arg), void *arg); void prune_syntax_tables (void); Lisp_Object get_range_char_table (struct chartab_range *range, Lisp_Object table, Lisp_Object multi); #ifdef ERROR_CHECK_TYPES Lisp_Object updating_mirror_get_range_char_table (struct chartab_range *range, Lisp_Object table, Lisp_Object multi); #else #define updating_mirror_get_range_char_table get_range_char_table #endif void copy_char_table_range (Lisp_Object from, Lisp_Object to, struct chartab_range *range); int word_boundary_p (Ichar c1, Ichar c2); EXFUN (Fcopy_char_table, 1); EXFUN (Fmake_char_table, 1); EXFUN (Fput_char_table, 3); EXFUN (Fget_char_table, 2); extern Lisp_Object Vall_syntax_tables; #ifdef MULE int check_category_char (Ichar ch, Lisp_Object ctbl, int designator, int not_p); extern Lisp_Object Vstandard_category_table; #define CATEGORY_DESIGNATORP(x) \ (CHARP (x) && XCHAR (x) >= 32 && XCHAR (x) <= 126) #define CHECK_CATEGORY_DESIGNATOR(x) do { \ if (!CATEGORY_DESIGNATORP (x)) \ dead_wrong_type_argument (Qcategory_designator_p, x); \ } while (0) #define CONCHECK_CATEGORY_DESIGNATOR(x) do { \ if (!CATEGORY_DESIGNATORP (x)) \ x = wrong_type_argument (Qcategory_designator_p, x); \ } while (0) #define CATEGORY_TABLE_VALUEP(x) \ (NILP (x) || (BIT_VECTORP (x) && (bit_vector_length (XBIT_VECTOR (x)) == 95))) #define CHECK_CATEGORY_TABLE_VALUE(x) do { \ if (!CATEGORY_TABLE_VALUEP (x)) \ dead_wrong_type_argument (Qcategory_table_value_p, x); \ } while (0) #define CONCHECK_CATEGORY_TABLE_VALUE(x) do { \ if (!CATEGORY_TABLE_VALUEP (x)) \ x = wrong_type_argument (Qcategory_table_value_p, x); \ } while (0) #endif /* MULE */ #endif /* INCLUDED_chartab_h_ */