comparison src/intl-win32.c @ 2367:ecf1ebac70d8

[xemacs-hg @ 2004-11-04 23:05:23 by ben] commit mega-patch configure.in: Turn off -Winline and -Wchar-subscripts. Use the right set of cflags when compiling modules. Rewrite ldap configuration to separate the inclusion of lber (needed in recent Cygwin) from the basic checks for the needed libraries. add a function for MAKE_JUNK_C; initially code was added to generate xemacs.def using this, but it will need to be rewritten. add an rm -f for junk.c to avoid weird Cygwin bug with cp -f onto an existing file. Sort list of auto-detected functions and eliminate unused checks for stpcpy, setlocale and getwd. Add autodetection of Cygwin scanf problems BETA: Rewrite section on configure to indicate what flags are important and what not. digest-doc.c, make-dump-id.c, profile.c, sorted-doc.c: Add proper decls for main(). make-msgfile.c: Document that this is old junk. Move proposal to text.c. make-msgfile.lex: Move proposal to text.c. make-mswin-unicode.pl: Convert error-generating code so that the entire message will be seen as a single unrecognized token. mule/mule-ccl.el: Update docs. lispref/mule.texi: Update CCL docs. ldap/eldap.c: Mule-ize. Use EXTERNAL_LIST_LOOP_2 instead of deleted EXTERNAL_LIST_LOOP. * XEmacs 21.5.18 "chestnut" is released. --------------------------------------------------------------- MULE-RELATED WORK: --------------------------------------------------------------- --------------------------- byte-char conversion --------------------------- buffer.c, buffer.h, insdel.c, text.c: Port FSF algorithm for byte-char conversion, replacing broken previous version. Track the char position of the gap. Add functions to do char-byte conversion downwards as well as upwards. Move comments about algorithm workings to internals manual. --------------------------- work on types --------------------------- alloc.c, console-x-impl.h, dump-data.c, dump-data.h, dumper.c, dialog-msw.c, dired-msw.c, doc.c, editfns.c, esd.c, event-gtk.h, event-msw.c, events.c, file-coding.c, file-coding.h, fns.c, glyphs-eimage.c, glyphs-gtk.c, glyphs-msw.c, glyphs-shared.c, glyphs-x.c, glyphs.c, glyphs.h, gui.c, hpplay.c, imgproc.c, intl-win32.c, lrecord.h, lstream.c, keymap.c, lisp.h, libsst.c, linuxplay.c, miscplay.c, miscplay.h, mule-coding.c, nas.c, nt.c, ntheap.c, ntplay.c, objects-msw.c, objects-tty.c, objects-x.c, print.c, process-nt.c, process.c, redisplay.h, select-common.h, select-gtk.c, select-x.c, sgiplay.c, sound.c, sound.h, sunplay.c, sysfile.h, sysdep.c, syswindows.h, text.c, unexnt.c, win32.c, xgccache.c: Further work on types. This creates a full set of types for all the basic semantics of `char' that I have so far identified, so that its semantics can always be identified for the purposes of proper Mule-safe code, and the raw use of `char' always avoided. (1) More type renaming, for consistency of naming. Char_ASCII -> Ascbyte UChar_ASCII -> UAscbyte Char_Binary -> CBinbyte UChar_Binary -> Binbyte SChar_Binary -> SBinbyte (2) Introduce Rawbyte, CRawbyte, Boolbyte, Chbyte, UChbyte, and Bitbyte and use them. (3) New types Itext, Wexttext and Textcount for separating out the concepts of bytes and textual units (different under UTF-16 and UTF-32, which are potential internal encodings). (4) qxestr*_c -> qxestr*_ascii. lisp.h: New; goes with other qxe() functions. #### Maybe goes in a different section. lisp.h: Group generic int-type defs together with EMACS_INT defs. lisp.h: * lisp.h (WEXTTEXT_IS_WIDE) New defns. lisp.h: New type to replace places where int occurs as a boolean. It's signed because occasionally people may want to use -1 as an error value, and because unsigned ints are viral -- see comments in the internals manual against using them. dynarr.c: int -> Bytecount. --------------------------- Mule-izing --------------------------- device-x.c: Partially Mule-ize. dumper.c, dumper.h: Mule-ize. Use Rawbyte. Use stderr_out not printf. Use wext_*(). sysdep.c, syswindows.h, text.c: New Wexttext API for manipulation of external text that may be Unicode (e.g. startup code under Windows). emacs.c: Mule-ize. Properly deal with argv in external encoding. Use wext_*() and Wexttext. Use Rawbyte. #if 0 some old junk on SCO that is unlikely to be correct. Rewrite allocation code in run-temacs. emacs.c, symsinit.h, win32.c: Rename win32 init function and call it even earlier, to initialize mswindows_9x_p even earlier, for use in startup code (XEUNICODE_P). process.c: Use _wenviron not environ under Windows, to get Unicode environment variables. event-Xt.c: Mule-ize drag-n-drop related stuff. dragdrop.c, dragdrop.h, frame-x.c: Mule-ize. text.h: Add some more stand-in defines for particular kinds of conversion; use in Mule-ization work in frame-x.c etc. --------------------------- Freshening --------------------------- intl-auto-encap-win32.c, intl-auto-encap-win32.h: Regenerate. --------------------------- Unicode-work --------------------------- intl-win32.c, syswindows.h: Factor out common options to MultiByteToWideChar and WideCharToMultiByte. Add convert_unicode_to_multibyte_malloc() and convert_unicode_to_multibyte_dynarr() and use. Add stuff for alloca() conversion of multibyte/unicode. alloc.c: Use dfc_external_data_len() in case of unicode coding system. alloc.c, mule-charset.c: Don't zero out and reinit charset Unicode tables. This fucks up dump-time loading. Anyway, either we load them at dump time or run time, never both. unicode.c: Dump the blank tables as well. --------------------------------------------------------------- DOCUMENTATION, MOSTLY MULE-RELATED: --------------------------------------------------------------- EmacsFrame.c, emodules.c, event-Xt.c, fileio.c, input-method-xlib.c, mule-wnnfns.c, redisplay-gtk.c, redisplay-tty.c, redisplay-x.c, regex.c, sysdep.c: Add comment about Mule work needed. text.h: Add more documentation describing why DFC routines were not written to return their value. Add some other DFC documentation. console-msw.c, console-msw.h: Add pointer to docs in win32.c. emacs.c: Add comments on sources of doc info. text.c, charset.h, unicode.c, intl-win32.c, intl-encap-win32.c, text.h, file-coding.c, mule-coding.c: Collect background comments and related to text matters and internationalization, and proposals for work to be done, in text.c or Internals manual, stuff related to specific textual API's in text.h, and stuff related to internal implementation of Unicode conversion in unicode.c. Put lots of pointers to the comments to make them easier to find. s/mingw32.h, s/win32-common.h, s/win32-native.h, s/windowsnt.h, win32.c: Add bunches of new documentation on the different kinds of builds and environments under Windows and how they work. Collect this info in win32.c. Add pointers to these docs in the relevant s/* files. emacs.c: Document places with long comments. Remove comment about exiting, move to internals manual, put in pointer. event-stream.c: Move docs about event queues and focus to internals manual, put in pointer. events.h: Move docs about event stream callbacks to internals manual, put in pointer. profile.c, redisplay.c, signal.c: Move documentation to the Internals manual. process-nt.c: Add pointer to comment in win32-native.el. lisp.h: Add comments about some comment conventions. lisp.h: Add comment about the second argument. device-msw.c, redisplay-msw.c: @@#### comments are out-of-date. --------------------------------------------------------------- PDUMP WORK (MOTIVATED BY UNICODE CHANGES) --------------------------------------------------------------- alloc.c, buffer.c, bytecode.c, console-impl.h, console.c, device.c, dumper.c, lrecord.h, elhash.c, emodules.h, events.c, extents.c, frame.c, glyphs.c, glyphs.h, mule-charset.c, mule-coding.c, objects.c, profile.c, rangetab.c, redisplay.c, specifier.c, specifier.h, window.c, lstream.c, file-coding.h, file-coding.c: PDUMP: Properly implement dump_add_root_block(), which never worked before, and is necessary for dumping Unicode tables. Pdump name changes for accuracy: XD_STRUCT_PTR -> XD_BLOCK_PTR. XD_STRUCT_ARRAY -> XD_BLOCK_ARRAY. XD_C_STRING -> XD_ASCII_STRING. *_structure_* -> *_block_*. lrecord.h: some comments added about dump_add_root_block() vs dump_add_root_block_ptr(). extents.c: remove incorrect comment about pdump problems with gap array. --------------------------------------------------------------- ALLOCATION --------------------------------------------------------------- abbrev.c, alloc.c, bytecode.c, casefiddle.c, device-msw.c, device-x.c, dired-msw.c, doc.c, doprnt.c, dragdrop.c, editfns.c, emodules.c, file-coding.c, fileio.c, filelock.c, fns.c, glyphs-eimage.c, glyphs-gtk.c, glyphs-msw.c, glyphs-x.c, gui-msw.c, gui-x.c, imgproc.c, intl-win32.c, lread.c, menubar-gtk.c, menubar.c, nt.c, objects-msw.c, objects-x.c, print.c, process-nt.c, process-unix.c, process.c, realpath.c, redisplay.c, search.c, select-common.c, symbols.c, sysdep.c, syswindows.h, text.c, text.h, ui-byhand.c: New macros {alloca,xnew}_{itext,{i,ext,raw,bin,asc}bytes} for more convenient allocation of these commonly requested items. Modify functions to use alloca_ibytes, alloca_array, alloca_extbytes, xnew_ibytes, etc. also XREALLOC_ARRAY, xnew. alloc.c: Rewrite the allocation functions to factor out repeated code. Add assertions for freeing dumped data. lisp.h: Moved down and consolidated with other allocation stuff. lisp.h, dynarr.c: New functions for allocation that's very efficient when mostly in LIFO order. lisp.h, text.c, text.h: Factor out some stuff for general use by alloca()-conversion funs. text.h, lisp.h: Fill out convenience routines for allocating various kinds of bytes and put them in lisp.h. Use them in place of xmalloc(), ALLOCA(). text.h: Fill out the convenience functions so the _MALLOC() kinds match the alloca() kinds. --------------------------------------------------------------- ERROR-CHECKING --------------------------------------------------------------- text.h: Create ASSERT_ASCTEXT_ASCII() and ASSERT_ASCTEXT_ASCII_LEN() from similar Eistring checkers and change the Eistring checkers to use them instead. --------------------------------------------------------------- MACROS IN LISP.H --------------------------------------------------------------- lisp.h: Redo GCPRO declarations. Create a "base" set of functions that can be used to generate any kind of gcpro sets -- regular, ngcpro, nngcpro, private ones used in GC_EXTERNAL_LIST_LOOP_2. buffer.c, callint.c, chartab.c, console-msw.c, device-x.c, dialog-msw.c, dired.c, extents.c, ui-gtk.c, rangetab.c, nt.c, mule-coding.c, minibuf.c, menubar-msw.c, menubar.c, menubar-gtk.c, lread.c, lisp.h, gutter.c, glyphs.c, glyphs-widget.c, fns.c, fileio.c, file-coding.c, specifier.c: Eliminate EXTERNAL_LIST_LOOP, which does not check for circularities. Use EXTERNAL_LIST_LOOP_2 instead or EXTERNAL_LIST_LOOP_3 or EXTERNAL_PROPERTY_LIST_LOOP_3 or GC_EXTERNAL_LIST_LOOP_2 (new macro). Removed/redid comments on EXTERNAL_LIST_LOOP. --------------------------------------------------------------- SPACING FIXES --------------------------------------------------------------- callint.c, hftctl.c, number-gmp.c, process-unix.c: Spacing fixes. --------------------------------------------------------------- FIX FOR GEOMETRY PROBLEM IN FIRST FRAME --------------------------------------------------------------- unicode.c: Add workaround for newlib bug in sscanf() [should be fixed by release 1.5.12 of Cygwin]. toolbar.c: bug fix for problem of initial frame being 77 chars wide on Windows. will be overridden by my other ws. --------------------------------------------------------------- FIX FOR LEAKING PROCESS HANDLES: --------------------------------------------------------------- process-nt.c: Fixes for leaking handles. Inspired by work done by Adrian Aichner <adrian@xemacs.org>. --------------------------------------------------------------- FIX FOR CYGWIN BUG (Unicode-related): --------------------------------------------------------------- unicode.c: Add workaround for newlib bug in sscanf() [should be fixed by release 1.5.12 of Cygwin]. --------------------------------------------------------------- WARNING FIXES: --------------------------------------------------------------- console-stream.c: `reinit' is unused. compiler.h, event-msw.c, frame-msw.c, intl-encap-win32.c, text.h: Add stuff to deal with ANSI-aliasing warnings I got. regex.c: Gather includes together to avoid warning. --------------------------------------------------------------- CHANGES TO INITIALIZATION ROUTINES: --------------------------------------------------------------- buffer.c, emacs.c, console.c, debug.c, device-x.c, device.c, dragdrop.c, emodules.c, eval.c, event-Xt.c, event-gtk.c, event-msw.c, event-stream.c, event-tty.c, events.c, extents.c, faces.c, file-coding.c, fileio.c, font-lock.c, frame-msw.c, glyphs-widget.c, glyphs.c, gui-x.c, insdel.c, lread.c, lstream.c, menubar-gtk.c, menubar-x.c, minibuf.c, mule-wnnfns.c, objects-msw.c, objects.c, print.c, scrollbar-x.c, search.c, select-x.c, text.c, undo.c, unicode.c, window.c, symsinit.h: Call reinit_*() functions directly from emacs.c, for clarity. Factor out some redundant init code. Move disallowed stuff that had crept into vars_of_glyphs() into complex_vars_of_glyphs(). Call init_eval_semi_early() from eval.c not in the middle of vars_of_() in emacs.c since there should be no order dependency in the latter calls. --------------------------------------------------------------- ARMAGEDDON: --------------------------------------------------------------- alloc.c, emacs.c, lisp.h, print.c: Rename inhibit_non_essential_printing_operations to inhibit_non_essential_conversion_operations. text.c: Assert on !inhibit_non_essential_conversion_operations. console-msw.c, print.c: Don't do conversion in SetConsoleTitle or FindWindow to avoid problems during armageddon. Put #errors for NON_ASCII_INTERNAL_FORMAT in places where problems would arise. --------------------------------------------------------------- CHANGES TO THE BUILD PROCEDURE: --------------------------------------------------------------- config.h.in, s/cxux.h, s/usg5-4-2.h, m/powerpc.h: Add comment about correct ordering of this file. Rearrange everything to follow this -- put all #undefs together and before the s&m files. Add undefs for HAVE_ALLOCA, C_ALLOCA, BROKEN_ALLOCA_IN_FUNCTION_CALLS, STACK_DIRECTION. Remove unused HAVE_STPCPY, HAVE_GETWD, HAVE_SETLOCALE. m/gec63.h: Deleted; totally broken, not used at all, not in FSF. m/7300.h, m/acorn.h, m/alliant-2800.h, m/alliant.h, m/altos.h, m/amdahl.h, m/apollo.h, m/att3b.h, m/aviion.h, m/celerity.h, m/clipper.h, m/cnvrgnt.h, m/convex.h, m/cydra5.h, m/delta.h, m/delta88k.h, m/dpx2.h, m/elxsi.h, m/ews4800r.h, m/gould.h, m/hp300bsd.h, m/hp800.h, m/hp9000s300.h, m/i860.h, m/ibmps2-aix.h, m/ibmrs6000.h, m/ibmrt-aix.h, m/ibmrt.h, m/intel386.h, m/iris4d.h, m/iris5d.h, m/iris6d.h, m/irist.h, m/isi-ov.h, m/luna88k.h, m/m68k.h, m/masscomp.h, m/mg1.h, m/mips-nec.h, m/mips-siemens.h, m/mips.h, m/news.h, m/nh3000.h, m/nh4000.h, m/ns32000.h, m/orion105.h, m/pfa50.h, m/plexus.h, m/pmax.h, m/powerpc.h, m/pyrmips.h, m/sequent-ptx.h, m/sequent.h, m/sgi-challenge.h, m/symmetry.h, m/tad68k.h, m/tahoe.h, m/targon31.h, m/tekxd88.h, m/template.h, m/tower32.h, m/tower32v3.h, m/ustation.h, m/vax.h, m/wicat.h, m/xps100.h: Delete C_ALLOCA, HAVE_ALLOCA, STACK_DIRECTION, BROKEN_ALLOCA_IN_FUNCTION_CALLS. All of this is auto-detected. When in doubt, I followed recent FSF sources, which also have these things deleted.
author ben
date Thu, 04 Nov 2004 23:08:28 +0000
parents ba4677f54a05
children 3d8143fc88e1
comparison
equal deleted inserted replaced
2366:2a392e0c390a 2367:ecf1ebac70d8
1 /* Win32 internationalization functions. 1 /* Win32 internationalization functions.
2 Copyright (C) 2000, 2001, 2002 Ben Wing. 2 Copyright (C) 2000, 2001, 2002, 2004 Ben Wing.
3 Copyright (C) 2000 IKEYAMA Tomonori. 3 Copyright (C) 2000 IKEYAMA Tomonori.
4 4
5 This file is part of XEmacs. 5 This file is part of XEmacs.
6 6
7 XEmacs is free software; you can redistribute it and/or modify it 7 XEmacs is free software; you can redistribute it and/or modify it
51 int _getmbcp (void); 51 int _getmbcp (void);
52 #else 52 #else
53 # define NO_EXT_MULTIBYTE_FEATURES 53 # define NO_EXT_MULTIBYTE_FEATURES
54 #endif 54 #endif
55 55
56
57
58 /*
59
60 Detailed info on Microsoft Windows-Related Multilingual Issues:
61
62 (Info-goto-node "(internals)Microsoft Windows-Related Multilingual Issues")
63 */
64
56 Lisp_Object Qmswindows_multibyte, Qmswindows_multibyte_to_unicode; 65 Lisp_Object Qmswindows_multibyte, Qmswindows_multibyte_to_unicode;
57 Lisp_Object Qmswindows_tstr, Qmswindows_unicode; 66 Lisp_Object Qmswindows_tstr, Qmswindows_unicode;
58 Lisp_Object Qmswindows_multibyte_system_default; 67 Lisp_Object Qmswindows_multibyte_system_default;
59 68
60 Lisp_Object Qansi, Qoem, Qmac, Qebcdic; 69 Lisp_Object Qansi, Qoem, Qmac, Qebcdic;
71 80
72 /************************************************************************/ 81 /************************************************************************/
73 /* Language/locale/code page conversion functions */ 82 /* Language/locale/code page conversion functions */
74 /************************************************************************/ 83 /************************************************************************/
75 84
76 /* There are various different ways of representing the vague concept
77 of "language", and it can be very confusing. So:
78
79 -- The C library has the concept of "locale", which is a
80 combination of language and country, and which controls the way
81 currency and dates are displayed, the encoding of data, etc.
82
83 -- XEmacs has the concept of "language environment", more or less
84 like a locale; although currently in most cases it just refers to
85 the language, and no sub-language distinctions are
86 made. (Exceptions are with Chinese, which has different language
87 environments for Taiwan and mainland China, due to the different
88 encodings and writing systems.)
89
90 -- Windows has a number of different language concepts:
91
92 1. There are "languages" and "sublanguages", which correspond to
93 the languages and countries of the C library -- e.g. LANG_ENGLISH
94 and SUBLANG_ENGLISH_US. These are identified by 8-bit integers,
95 called the "primary language identifier" and "sublanguage
96 identifier", respectively. These are combined into a 16-bit
97 integer or "language identifier" by MAKELANGID().
98
99 2. The language identifier in turn is combined with a "sort
100 identifier" (and optionally a "sort version") to yield a 32-bit
101 integer called a "locale identifier" (type LCID), which identifies
102 locales -- the primary means of distinguishing language/regional
103 settings and similar to C library locales.
104
105 3. "Code pages" identify different text encodings (i.e. a set of
106 supported characters, an enumeration of those characters [i.e. an
107 association of character with number or number pair; there may be
108 disjoint ranges of numbers supported]), and a way of encoding a
109 stream of those characters into an 8-bit data stream). All of the
110 encodings are either one-byte or mixed one-byte/two-byte encodings,
111 all non-modal; in the mixed encodings, two-byte characters have the
112 first byte >= 128, although the second byte may or may not be
113 restricted to this range, depending on the encoding. Code pages
114 are similar to XEmacs "charsets"; the latter also define a set of
115 supported characters and an enumeration of those characters (but
116 code pages in additionally define an encoding, which charsets don't
117 do). Code pages often function in Windows like charsets in XEmacs.
118
119 4. Every Windows locale has a specific code page associated with
120 it; more than one locale can share a code page -- e.g. all the
121 Western European languages, including English, do.
122
123 5. Windows also has an "input locale identifier" (aka "keyboard
124 layout id") or HKL, which is a 32-bit integer composed of the
125 16-bit language identifier and a 16-bit "device identifier", which
126 originally specified a particular keyboard layout (e.g. the locale
127 "US English" can have the QWERTY layout, the Dvorak layout, etc.),
128 but has been expanded to include speech-to-text converters and
129 other non-keyboard ways of inputting text. Note that both the HKL
130 and LCID share the language identifier in the lower 16 bits, and in
131 both cases a 0 in the upper 16 bits means "default" (sort order or
132 device), providing a way to convert between HKL's, LCID's, and
133 language identifiers (i.e. language/sublanguage pairs). The
134 default keyboard layout for a language is (as far as I can
135 determine) established using the Regional Settings control panel
136 applet, where you can add input locales as combinations of language
137 (actually language/sublanguage) and layout; presumably if you list
138 only one input locale with a particular language, the corresponding
139 layout is the default for that language. But what if you list more
140 than one? You can specify a single default input locale, but there
141 appears to be no way to do so on a per-language basis.
142 */
143
144 struct lang_to_string 85 struct lang_to_string
145 { 86 {
146 int code; 87 int code;
147 char *string; 88 char *string;
148 }; 89 };
673 int table_size) 614 int table_size)
674 { 615 {
675 int i; 616 int i;
676 617
677 for (i = 0; i < table_size; i++) 618 for (i = 0; i < table_size; i++)
678 if (!strcmp ((char *) XSTRING_DATA (lang), table[i].string)) 619 if (!qxestrcmp_ascii (XSTRING_DATA (lang), table[i].string))
679 return table[i].code; 620 return table[i].code;
680 return -1; 621 return -1;
681 } 622 }
682 623
683 static int 624 static int
686 { 627 {
687 int i; 628 int i;
688 629
689 for (i = 0; i < table_size; i++) 630 for (i = 0; i < table_size; i++)
690 if (table[i].string && 631 if (table[i].string &&
691 !strcmp ((char *) XSTRING_DATA (lang), table[i].string)) 632 !qxestrcmp_ascii (XSTRING_DATA (lang), table[i].string))
692 return table[i].code; 633 return table[i].code;
693 634
694 if (!strcmp ((char *) XSTRING_DATA (lang), "NEUTRAL")) 635 if (!qxestrcmp_ascii (XSTRING_DATA (lang), "NEUTRAL"))
695 return SUBLANG_NEUTRAL; 636 return SUBLANG_NEUTRAL;
696 if (!strcmp ((char *) XSTRING_DATA (lang), "DEFAULT")) 637 if (!qxestrcmp_ascii (XSTRING_DATA (lang), "DEFAULT"))
697 return SUBLANG_DEFAULT; 638 return SUBLANG_DEFAULT;
698 if (!strcmp ((char *) XSTRING_DATA (lang), "SYS_DEFAULT")) 639 if (!qxestrcmp_ascii (XSTRING_DATA (lang), "SYS_DEFAULT"))
699 return SUBLANG_SYS_DEFAULT; 640 return SUBLANG_SYS_DEFAULT;
700 641
701 return -1; 642 return -1;
702 } 643 }
703 644
1091 LCID lcid = NILP (locale) ? current_locale : locale_to_lcid (locale); 1032 LCID lcid = NILP (locale) ? current_locale : locale_to_lcid (locale);
1092 return make_int (mswindows_locale_to_oem_code_page (lcid)); 1033 return make_int (mswindows_locale_to_oem_code_page (lcid));
1093 } 1034 }
1094 1035
1095 static DWORD 1036 static DWORD
1096 int_from_hex (Char_ASCII *s) 1037 int_from_hex (Ascbyte *s)
1097 { 1038 {
1098 DWORD val = 0; 1039 DWORD val = 0;
1099 static Char_ASCII hex[] = "0123456789abcdefABCDEF"; 1040 static Ascbyte hex[] = "0123456789abcdefABCDEF";
1100 Char_ASCII *p; 1041 Ascbyte *p;
1101 1042
1102 while (*s && (p = strchr (hex, *s)) != NULL) 1043 while (*s && (p = strchr (hex, *s)) != NULL)
1103 { 1044 {
1104 int digit = p - hex; 1045 int digit = p - hex;
1105 if (digit > 15) 1046 if (digit > 15)
1113 /* We need to build a global list, since the EnumSystemLocale callback 1054 /* We need to build a global list, since the EnumSystemLocale callback
1114 function isn't given a context pointer. */ 1055 function isn't given a context pointer. */
1115 static Lisp_Object Vmswindows_valid_locales; 1056 static Lisp_Object Vmswindows_valid_locales;
1116 1057
1117 static BOOL CALLBACK 1058 static BOOL CALLBACK
1118 enum_locale_fn (Char_ASCII *localeNum) 1059 enum_locale_fn (Ascbyte *localeNum)
1119 { 1060 {
1120 DWORD id = int_from_hex (localeNum); 1061 DWORD id = int_from_hex (localeNum);
1121 Vmswindows_valid_locales = 1062 Vmswindows_valid_locales =
1122 Fcons (lcid_to_locale ((LCID) id), Vmswindows_valid_locales); 1063 Fcons (lcid_to_locale ((LCID) id), Vmswindows_valid_locales);
1123 return TRUE; 1064 return TRUE;
1483 The return value is a list of pairs of language id and layout id. 1424 The return value is a list of pairs of language id and layout id.
1484 */ 1425 */
1485 ()) 1426 ())
1486 { 1427 {
1487 int num_layouts = GetKeyboardLayoutList (0, NULL); 1428 int num_layouts = GetKeyboardLayoutList (0, NULL);
1488 HKL * layouts = (HKL *) ALLOCA (num_layouts * sizeof (HKL)); 1429 HKL *layouts = alloca_array (HKL, num_layouts);
1489 Lisp_Object obj = Qnil; 1430 Lisp_Object obj = Qnil;
1490 1431
1491 if (GetKeyboardLayoutList (num_layouts, layouts) == num_layouts) 1432 if (GetKeyboardLayoutList (num_layouts, layouts) == num_layouts)
1492 { 1433 {
1493 while (--num_layouts >= 0) 1434 while (--num_layouts >= 0)
1680 1621
1681 wchar_t * 1622 wchar_t *
1682 wcsdup (const wchar_t *str) 1623 wcsdup (const wchar_t *str)
1683 { 1624 {
1684 int len = wcslen (str) + 1; 1625 int len = wcslen (str) + 1;
1685 void *val = xmalloc (len * sizeof (wchar_t)); 1626 wchar_t *val = xnew_array (wchar_t, len);
1686 1627
1687 if (val == 0) return 0; 1628 if (val == 0) return 0;
1688 return (wchar_t *) memcpy (val, str, len * sizeof (wchar_t)); 1629 return (wchar_t *) memcpy (val, str, len * sizeof (wchar_t));
1689 } 1630 }
1690 1631
1922 print_internal (mswindows_multibyte_to_unicode_getprop (cs, Qcode_page), printcharfun, 0); 1863 print_internal (mswindows_multibyte_to_unicode_getprop (cs, Qcode_page), printcharfun, 0);
1923 } 1864 }
1924 write_c_string (printcharfun, ")"); 1865 write_c_string (printcharfun, ")");
1925 } 1866 }
1926 1867
1868 /* ----------------------------------------------------------------------- */
1869 /* Unicode/Multibyte converters */
1870 /* ----------------------------------------------------------------------- */
1871
1927 /* Convert multibyte to Unicode according to the specified code page 1872 /* Convert multibyte to Unicode according to the specified code page
1928 and return the value as a malloc()ed string. This currently exists 1873 and return the value as a malloc()ed string. This currently exists
1929 because the TO_INTERNAL_FORMAT() mechanism -- the normal way to do 1874 because the TO_INTERNAL_FORMAT() mechanism -- the normal way to do
1930 such conversions -- has no way of passing in a parameter to control 1875 such conversions -- has no way of passing in a parameter to control
1931 the operation. We could use a global variable to pass this value 1876 the operation. We could use a global variable to pass this value
1932 in, but that runs the risk of causing problems due to reentrancy. 1877 in, but that runs the risk of causing problems due to reentrancy.
1933 (You might say, yeah, right, how can TO_INTERNAL_FORMAT() get 1878 (You might say, yeah, right, how can TO_INTERNAL_FORMAT() get
1934 called recursively merely when I'm doing a simple conversion 1879 called recursively merely when I'm doing a simple conversion
1935 operation? It turns out this can and does happen, consistently, as 1880 operation? It turns out this can and does happen, consistently, as
1936 a result of calling QUIT -- it happens consistently for complicated 1881 a result of calling QUIT -- it happens consistently for complicated
1937 reasons outlined in event-msw.c, WM_KEYDOWN handling.) */ 1882 reasons outlined in event-msw.c, WM_KEYDOWN handling.)
1883
1884 NOTE: These functions are also used at startup. */
1938 1885
1939 Extbyte * 1886 Extbyte *
1940 convert_multibyte_to_unicode_malloc (const Extbyte *src, Bytecount n, 1887 convert_multibyte_to_unicode_malloc (const Extbyte *src, Bytecount n,
1941 int cp, Bytecount *size_out) 1888 int cp, Bytecount *size_out)
1942 { 1889 {
1943 Bytecount nout = MultiByteToWideChar (cp, 0, src, n, 0, 0); 1890 Charcount nout = MultiByteToWideChar (cp, MBTOWC_OPTIONS, src, n, 0, 0);
1944 Extbyte *outp = xnew_array (Extbyte, nout * sizeof (WCHAR)); 1891 Extbyte *outp = xnew_array (Extbyte, nout * sizeof (WCHAR));
1945 1892
1946 MultiByteToWideChar (cp, 0, src, n, (LPWSTR) outp, nout); 1893 MultiByteToWideChar (cp, MBTOWC_OPTIONS, src, n, (LPWSTR) outp, nout);
1947 if (size_out) 1894 if (size_out)
1948 *size_out = nout * sizeof (WCHAR); 1895 *size_out = nout * sizeof (WCHAR);
1949 return outp; 1896 return outp;
1950 } 1897 }
1951 1898
1899 Extbyte *
1900 convert_unicode_to_multibyte_malloc (const Extbyte *src, Bytecount n,
1901 int cp, Bytecount *size_out)
1902 {
1903 Bytecount nout = WideCharToMultiByte (cp, WCTOMB_OPTIONS, (LPWSTR) src,
1904 n / sizeof (WCHAR),
1905 0, 0, WCTOMB_INVALID_STRING, 0);
1906 Extbyte *outp = xnew_array (Extbyte, nout);
1907
1908 WideCharToMultiByte (cp, WCTOMB_OPTIONS, (LPWSTR) src,
1909 n / sizeof (WCHAR), (LPSTR) outp, nout,
1910 WCTOMB_INVALID_STRING, 0);
1911 if (size_out)
1912 *size_out = nout;
1913 return outp;
1914 }
1915
1952 /* Convert MS Windows multibyte to internal, with specified code page. 1916 /* Convert MS Windows multibyte to internal, with specified code page.
1953 See above for why this exists, and the TO_INTERNAL_FORMAT() macros 1917 See above for why this exists, and the TO_INTERNAL_FORMAT() macros
1954 aren't just used. */ 1918 aren't just used. */
1955 1919
1956 Ibyte * 1920 Ibyte *
1970 *size_out = size; 1934 *size_out = size;
1971 1935
1972 return intdata; 1936 return intdata;
1973 } 1937 }
1974 1938
1939 static void
1940 unicode_multibyte_convert_now_damn_it (const void *src, Bytecount src_size,
1941 int to_unicode, void **dst,
1942 Bytecount *dst_size, int cp)
1943 {
1944 if (to_unicode)
1945 {
1946 Charcount nout = MultiByteToWideChar (cp, MBTOWC_OPTIONS, (LPSTR) src,
1947 src_size, 0, 0);
1948 Extbyte *outp = (Extbyte *) stack_like_malloc (nout * sizeof (WCHAR));
1949
1950 MultiByteToWideChar (cp, MBTOWC_OPTIONS, (LPSTR) src, src_size,
1951 (LPWSTR) outp, nout);
1952 *dst = (void *) outp;
1953 *dst_size = nout * sizeof (WCHAR);
1954 }
1955 else
1956 {
1957 Bytecount nout = WideCharToMultiByte (cp, WCTOMB_OPTIONS, (LPWSTR) src,
1958 src_size / sizeof (WCHAR),
1959 0, 0, WCTOMB_INVALID_STRING, 0);
1960 Extbyte *outp = (Extbyte *) stack_like_malloc (nout);
1961
1962 WideCharToMultiByte (cp, WCTOMB_OPTIONS, (LPWSTR) src,
1963 src_size / sizeof (WCHAR), (LPSTR) outp, nout,
1964 WCTOMB_INVALID_STRING, 0);
1965 *dst = (void *) outp;
1966 *dst_size = nout;
1967 }
1968 }
1969
1970 Bytecount
1971 unicode_multibyte_convert_size (const char *srctext, const void *src,
1972 Bytecount src_size, int to_unicode, int cp)
1973 {
1974 alloca_convert_vals vals;
1975
1976 assert (find_pos_of_existing_active_alloca_convert (srctext) < 0);
1977
1978 vals.srctext = srctext;
1979
1980 unicode_multibyte_convert_now_damn_it (src, src_size, to_unicode, &vals.dst,
1981 &vals.dst_size, cp);
1982
1983 Dynarr_add (active_alloca_convert, vals);
1984 return vals.dst_size;
1985 }
1986
1987 void *
1988 unicode_multibyte_convert_copy_data (const char *srctext, void *alloca_data)
1989 {
1990 alloca_convert_vals *vals;
1991 int i = find_pos_of_existing_active_alloca_convert (srctext);
1992
1993 assert (i >= 0);
1994 vals = Dynarr_atp (active_alloca_convert, i);
1995 assert (alloca_data);
1996 memcpy (alloca_data, vals->dst, vals->dst_size);
1997 stack_like_free (vals->dst);
1998 Dynarr_delete (active_alloca_convert, i);
1999 return alloca_data;
2000 }
2001
1975 /* Convert multibyte to Unicode according to the specified code page 2002 /* Convert multibyte to Unicode according to the specified code page
1976 and append the results onto the specified Dynarr. See above. */ 2003 and append the results onto the specified Dynarr. See above. */
1977 2004
1978 void 2005 void
1979 convert_multibyte_to_unicode_dynarr (const Extbyte *src, Bytecount n, 2006 convert_multibyte_to_unicode_dynarr (const Extbyte *src, Bytecount n,
1980 int cp, unsigned_char_dynarr *dst) 2007 int cp, unsigned_char_dynarr *dst)
1981 { 2008 {
1982 Bytecount nout = MultiByteToWideChar (cp, 0, src, n, 0, 0); 2009 Charcount nout = MultiByteToWideChar (cp, MBTOWC_OPTIONS, src, n, 0, 0);
1983 void *outp; 2010 void *outp;
1984 2011
1985 Dynarr_add_many (dst, 0, nout * sizeof (WCHAR)); 2012 Dynarr_add_many (dst, 0, nout * sizeof (WCHAR));
1986 /* dynarr's buffer may be realloc()ed by call above, so access it after */ 2013 /* dynarr's buffer may be realloc()ed by call above, so access it after */
1987 outp = Dynarr_atp (dst, Dynarr_length (dst) - nout * sizeof (WCHAR)); 2014 outp = Dynarr_atp (dst, Dynarr_length (dst) - nout * sizeof (WCHAR));
1988 MultiByteToWideChar (cp, 0, src, n, (LPWSTR) outp, nout); 2015 MultiByteToWideChar (cp, MBTOWC_OPTIONS, src, n, (LPWSTR) outp, nout);
1989 } 2016 }
2017
2018 void
2019 convert_unicode_to_multibyte_dynarr (const Extbyte *src, Bytecount n,
2020 int cp, unsigned_char_dynarr *dst)
2021 {
2022 Bytecount nout = WideCharToMultiByte (cp, WCTOMB_OPTIONS, (LPWSTR) src,
2023 n / sizeof (WCHAR),
2024 0, 0, WCTOMB_INVALID_STRING, 0);
2025 void *outp;
2026
2027 Dynarr_add_many (dst, 0, nout);
2028 /* dynarr's buffer may be realloc()ed by call above, so access it after */
2029 outp = Dynarr_atp (dst, Dynarr_length (dst) - nout);
2030 WideCharToMultiByte (cp, WCTOMB_OPTIONS, (LPWSTR) src,
2031 n / sizeof (WCHAR), (LPSTR) outp, nout,
2032 WCTOMB_INVALID_STRING, 0);
2033 }
2034
1990 2035
1991 /* Convert MS Windows multibyte to Unicode. */ 2036 /* Convert MS Windows multibyte to Unicode. */
1992 2037
1993 static Bytecount 2038 static Bytecount
1994 mswindows_multibyte_to_unicode_convert (struct coding_stream *str, 2039 mswindows_multibyte_to_unicode_convert (struct coding_stream *str,
2052 n--; 2097 n--;
2053 } 2098 }
2054 else 2099 else
2055 data->partial_byte_present = 0; 2100 data->partial_byte_present = 0;
2056 2101
2057 { 2102 convert_unicode_to_multibyte_dynarr ((Extbyte *) new_src, n, data->cp,
2058 int nout = WideCharToMultiByte (data->cp, WC_COMPOSITECHECK, 2103 dst);
2059 (LPWSTR) new_src, n / sizeof (WCHAR),
2060 0, 0, "~", 0);
2061 void *outp;
2062
2063 Dynarr_add_many (dst, 0, nout);
2064 /* dynarr's buffer may be realloc()ed by call above, so access it
2065 after */
2066 outp = Dynarr_atp (dst, Dynarr_length (dst) - nout);
2067 WideCharToMultiByte (data->cp, WC_COMPOSITECHECK, (LPWSTR) new_src,
2068 n / sizeof (WCHAR),
2069 (LPSTR) outp, nout, "~", 0);
2070 }
2071 } 2104 }
2072 return orign; 2105 return orign;
2073 } 2106 }
2074 2107
2075 static enum source_sink_type 2108 static enum source_sink_type