view src/charset.h @ 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 184461bc8de4
children 3d8143fc88e1
line wrap: on
line source

/* Header for charsets.
   Copyright (C) 1992, 1995 Free Software Foundation, Inc.
   Copyright (C) 1995 Sun Microsystems, Inc.
   Copyright (C) 2001, 2002 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 in FSF. */

/* Rewritten by Ben Wing <ben@xemacs.org>. */

#ifndef INCLUDED_charset_h_
#define INCLUDED_charset_h_



#ifndef MULE

/************************************************************************/
/*                            fake charset defs                         */
/************************************************************************/

/* used when MULE is not defined, so that Charset-type stuff can still
   be done */

#define Vcharset_ascii Qnil

#define ichar_charset(ch) Vcharset_ascii
#define ichar_leading_byte(ch) LEADING_BYTE_ASCII
#define ichar_len(ch) 1
#define ichar_len_fmt(ch, fmt) 1
#define LEADING_BYTE_ASCII 0x80
#define NUM_LEADING_BYTES 1
#define MIN_LEADING_BYTE 0x80
#define CHARSETP(cs) 1
#define charset_by_leading_byte(lb) Vcharset_ascii
#define XCHARSET_LEADING_BYTE(cs) LEADING_BYTE_ASCII
#define XCHARSET_GRAPHIC(cs) -1
#define XCHARSET_COLUMNS(cs) 1
#define XCHARSET_DIMENSION(cs) 1
#define BREAKUP_ICHAR(ch, charset, byte1, byte2) do {	\
  (charset) = Vcharset_ascii;				\
  (byte1) = (ch);					\
  (byte2) = 0;						\
} while (0)

#else /* MULE */


/************************************************************************/
/*                    Definition of leading bytes                       */
/************************************************************************/

#define MIN_LEADING_BYTE		0x7F

/** The following are for 1-byte characters in an official charset. **/
enum LEADING_BYTE_OFFICIAL_1
{
  MIN_LEADING_BYTE_OFFICIAL_1 = 0x80,
  /* LEADING_BYTE_LATIN_ISO8859_1 *MUST* be equal to
     MIN_LEADING_BYTE_OFFICIAL_1. */
  LEADING_BYTE_LATIN_ISO8859_1 =  /* 0x80 Right half of ISO 8859-1 */
    MIN_LEADING_BYTE_OFFICIAL_1,
  LEADING_BYTE_LATIN_ISO8859_2,   /* 0x81 Right half of ISO 8859-2 */
  LEADING_BYTE_LATIN_ISO8859_3,   /* 0x82 Right half of ISO 8859-3 */
  LEADING_BYTE_LATIN_ISO8859_4,   /* 0x83 Right half of ISO 8859-4 */
  LEADING_BYTE_THAI_TIS620,       /* 0x84 TIS620-2533 */
  LEADING_BYTE_GREEK_ISO8859_7,   /* 0x85 Right half of ISO 8859-7 */
  LEADING_BYTE_ARABIC_ISO8859_6,  /* 0x86 Right half of ISO 8859-6 */
  LEADING_BYTE_HEBREW_ISO8859_8,  /* 0x87 Right half of ISO 8859-8 */
  LEADING_BYTE_KATAKANA_JISX0201, /* 0x88 Right half of JIS X0201-1976 */
  LEADING_BYTE_LATIN_JISX0201,    /* 0x89 Left  half of JIS X0201-1976 */
  LEADING_BYTE_CYRILLIC_ISO8859_5,/* 0x8A Right half of ISO 8859-5 */
  LEADING_BYTE_LATIN_ISO8859_9,   /* 0x8B Right half of ISO 8859-9 */
  LEADING_BYTE_LATIN_ISO8859_15,  /* 0x8C Right half of ISO 8859-15 */
#ifdef ENABLE_COMPOSITE_CHARS
  LEADING_BYTE_COMPOSITE,         /* 0x8D For a composite character */
  MAX_LEADING_BYTE_OFFICIAL_1 =
    LEADING_BYTE_COMPOSITE - 1,
#else
    /* Does not need to be the last entry, but simplifies things */
  LEADING_BYTE_COMPOSITE_REPLACEMENT, /* 0x8D Replaces ESC 0 - ESC 4 in a
                                         buffer */
  MAX_LEADING_BYTE_OFFICIAL_1 =
    LEADING_BYTE_COMPOSITE_REPLACEMENT,
#endif
                                  /* 0x8E Unused */
};

/* These next 2 + LEADING_BYTE_COMPOSITE need special treatment in a string
   and/or character */

#define LEADING_BYTE_ASCII		0x7F /* Not used except in arrays
						indexed by leading byte */
#define LEADING_BYTE_CONTROL_1          0x8F /* represent normal 80-9F */

/** The following are for 2-byte characters in an official charset. **/
enum LEADING_BYTE_OFFICIAL_2
{
  MIN_LEADING_BYTE_OFFICIAL_2 = 0x90,
  LEADING_BYTE_JAPANESE_JISX0208_1978 =
    MIN_LEADING_BYTE_OFFICIAL_2,       /* 0x90 Japanese JIS X0208-1978 */
  LEADING_BYTE_CHINESE_GB2312,         /* 0x91 Chinese Hanzi GB2312-1980 */
  LEADING_BYTE_JAPANESE_JISX0208,      /* 0x92 Japanese JIS X0208-1983 */
  LEADING_BYTE_KOREAN_KSC5601,         /* 0x93 Hangul KS C5601-1987 */
  LEADING_BYTE_JAPANESE_JISX0212,      /* 0x94 Japanese JIS X0212-1990 */
  LEADING_BYTE_CHINESE_CNS11643_1,     /* 0x95 Chinese CNS11643 Set 1 */
  LEADING_BYTE_CHINESE_CNS11643_2,     /* 0x96 Chinese CNS11643 Set 2 */
  LEADING_BYTE_CHINESE_BIG5_1,         /* 0x97 Big5 Level 1 */
  LEADING_BYTE_CHINESE_BIG5_2,         /* 0x98 Big5 Level 2 */
  MAX_LEADING_BYTE_OFFICIAL_2 =
    LEADING_BYTE_CHINESE_BIG5_2,

                                       /* 0x99 unused */
                                       /* 0x9A unused */
                                       /* 0x9B unused */
                                       /* 0x9C unused */
                                       /* 0x9D unused */
};


/** The following are for 1- and 2-byte characters in a private charset. **/

#define PRE_LEADING_BYTE_PRIVATE_1	0x9E	/* 1-byte char-set */
#define PRE_LEADING_BYTE_PRIVATE_2	0x9F	/* 2-byte char-set */

#define MIN_LEADING_BYTE_PRIVATE_1	0xA0
#define MAX_LEADING_BYTE_PRIVATE_1	0xEF
#define MIN_LEADING_BYTE_PRIVATE_2	0xF0
#define MAX_LEADING_BYTE_PRIVATE_2	0xFF

#define NUM_LEADING_BYTES 129


/************************************************************************/
/*                    Operations on leading bytes                       */
/************************************************************************/

/* Is this leading byte for a private charset? */

#define leading_byte_private_p(lb) ((lb) >= MIN_LEADING_BYTE_PRIVATE_1)

/* Is this a prefix for a private leading byte? */

DECLARE_INLINE_HEADER (
int
leading_byte_prefix_p (Ibyte lb)
)
{
  return (lb == PRE_LEADING_BYTE_PRIVATE_1 ||
	  lb == PRE_LEADING_BYTE_PRIVATE_2);
}

/* Given a private leading byte, return the leading byte prefix stored
   in a string. */

#define private_leading_byte_prefix(lb)			\
  ((unsigned int) (lb) < MIN_LEADING_BYTE_PRIVATE_2 ?	\
   PRE_LEADING_BYTE_PRIVATE_1 :				\
   PRE_LEADING_BYTE_PRIVATE_2)


/************************************************************************/
/*            Information about a particular character set              */
/************************************************************************/

struct Lisp_Charset
{
  struct lcrecord_header header;

  int id;
  Lisp_Object name;
  Lisp_Object doc_string;
  Lisp_Object registry;
  Lisp_Object short_name;
  Lisp_Object long_name;

  Lisp_Object reverse_direction_charset;

  Lisp_Object ccl_program;

  /* Unicode translation tables.  See unicode.c for the format of these
     tables, and discussion of how they are initialized.
  */
  void *to_unicode_table;
  void *from_unicode_table;
  int from_unicode_levels;

  /* Final byte of this character set in ISO2022 designating escape
     sequence */
  Ibyte final;

  /* Number of bytes (1 - 4) required in the internal representation
     for characters in this character set.  This is *not* the
     same as the dimension of the character set). */
  int rep_bytes;

  /* Number of columns a character in this charset takes up, on TTY
     devices.  Not used for X devices. */
  int columns;

  /* Direction of this character set */
  int direction;

  /* Type of this character set (94, 96, 94x94, 96x96) */
  int type;

  /* Number of bytes used in encoding of this character set (1 or 2) */
  int dimension;

  /* Number of chars in each dimension (usually 94 or 96) */
  int chars;

  /* Which half of font to be used to display this character set */
  int graphic;

  /* If set, this is a "temporary" charset created when we encounter
     an unknown final.  This is so that we can successfully compile
     and load such files.  We allow a real charset to be created on top
     of this temporary charset. */
  unsigned int temporary :1;
};
typedef struct Lisp_Charset Lisp_Charset;

DECLARE_LRECORD (charset, Lisp_Charset);
#define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
#define wrap_charset(p) wrap_record (p, charset)
#define CHARSETP(x) RECORDP (x, charset)
#define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
#define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)

#define CHARSET_TYPE_94    0	/* This charset includes 94    characters. */
#define CHARSET_TYPE_96    1	/* This charset includes 96    characters. */
#define CHARSET_TYPE_94X94 2	/* This charset includes 94x94 characters. */
#define CHARSET_TYPE_96X96 3	/* This charset includes 96x96 characters. */

#define CHARSET_LEFT_TO_RIGHT	0
#define CHARSET_RIGHT_TO_LEFT	1

/* Leading byte and id have been regrouped. -- OG */
#define CHARSET_ID(cs)		 ((cs)->id)
#define CHARSET_LEADING_BYTE(cs) ((Ibyte) CHARSET_ID (cs))
#define CHARSET_NAME(cs)	 ((cs)->name)
#define CHARSET_SHORT_NAME(cs)	 ((cs)->short_name)
#define CHARSET_LONG_NAME(cs)	 ((cs)->long_name)
#define CHARSET_REP_BYTES(cs)	 ((cs)->rep_bytes)
#define CHARSET_COLUMNS(cs)	 ((cs)->columns)
#define CHARSET_GRAPHIC(cs)	 ((cs)->graphic)
#define CHARSET_TYPE(cs)	 ((cs)->type)
#define CHARSET_DIRECTION(cs)	 ((cs)->direction)
#define CHARSET_FINAL(cs)	 ((cs)->final)
#define CHARSET_DOC_STRING(cs)	 ((cs)->doc_string)
#define CHARSET_REGISTRY(cs)	 ((cs)->registry)
#define CHARSET_CCL_PROGRAM(cs)  ((cs)->ccl_program)
#define CHARSET_DIMENSION(cs)	 ((cs)->dimension)
#define CHARSET_CHARS(cs)	 ((cs)->chars)
#define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
#define CHARSET_TO_UNICODE_TABLE(cs) ((cs)->to_unicode_table)
#define CHARSET_FROM_UNICODE_TABLE(cs) ((cs)->from_unicode_table)
#define CHARSET_FROM_UNICODE_LEVELS(cs) ((cs)->from_unicode_levels)


#define CHARSET_PRIVATE_P(cs) leading_byte_private_p (CHARSET_LEADING_BYTE (cs))

#define XCHARSET_ID(cs)		  CHARSET_ID           (XCHARSET (cs))
#define XCHARSET_NAME(cs)	  CHARSET_NAME         (XCHARSET (cs))
#define XCHARSET_SHORT_NAME(cs)	  CHARSET_SHORT_NAME   (XCHARSET (cs))
#define XCHARSET_LONG_NAME(cs)	  CHARSET_LONG_NAME    (XCHARSET (cs))
#define XCHARSET_REP_BYTES(cs)	  CHARSET_REP_BYTES    (XCHARSET (cs))
#define XCHARSET_COLUMNS(cs)	  CHARSET_COLUMNS      (XCHARSET (cs))
#define XCHARSET_GRAPHIC(cs)      CHARSET_GRAPHIC      (XCHARSET (cs))
#define XCHARSET_TYPE(cs)	  CHARSET_TYPE         (XCHARSET (cs))
#define XCHARSET_DIRECTION(cs)	  CHARSET_DIRECTION    (XCHARSET (cs))
#define XCHARSET_FINAL(cs)	  CHARSET_FINAL        (XCHARSET (cs))
#define XCHARSET_DOC_STRING(cs)	  CHARSET_DOC_STRING   (XCHARSET (cs))
#define XCHARSET_REGISTRY(cs)	  CHARSET_REGISTRY     (XCHARSET (cs))
#define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
#define XCHARSET_CCL_PROGRAM(cs)  CHARSET_CCL_PROGRAM  (XCHARSET (cs))
#define XCHARSET_DIMENSION(cs)	  CHARSET_DIMENSION    (XCHARSET (cs))
#define XCHARSET_CHARS(cs)	  CHARSET_CHARS        (XCHARSET (cs))
#define XCHARSET_PRIVATE_P(cs)	  CHARSET_PRIVATE_P    (XCHARSET (cs))
#define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
  CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
#define XCHARSET_TO_UNICODE_TABLE(cs) \
  CHARSET_TO_UNICODE_TABLE (XCHARSET (cs))
#define XCHARSET_FROM_UNICODE_TABLE(cs) \
  CHARSET_FROM_UNICODE_TABLE (XCHARSET (cs))
#define XCHARSET_FROM_UNICODE_LEVELS(cs) \
  CHARSET_FROM_UNICODE_LEVELS (XCHARSET (cs))

struct charset_lookup
{
  /* Table of charsets indexed by leading byte. */
  Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];

  /* Table of charsets indexed by type/final-byte/direction. */
  Lisp_Object charset_by_attributes[4][128][2];
  Ibyte next_allocated_1_byte_leading_byte;
  Ibyte next_allocated_2_byte_leading_byte;
};

extern struct charset_lookup *chlook;

DECLARE_INLINE_HEADER (
Lisp_Object
charset_by_leading_byte (int lb)
)
{
#ifdef ERROR_CHECK_TEXT
  /* When error-checking is on, x86 GCC 2.95.2 -O3 miscompiles the
     following unless we introduce `tem'. */
  int tem = lb;
  text_checking_assert (tem >= MIN_LEADING_BYTE && tem <= 0xFF);
#endif
  return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
}

DECLARE_INLINE_HEADER (
Lisp_Object
charset_by_attributes (int type, int final, int dir)
)
{
  type_checking_assert (type  < countof (chlook->charset_by_attributes) &&
			final < countof (chlook->charset_by_attributes[0]) &&
			dir   < countof (chlook->charset_by_attributes[0][0]));
  return chlook->charset_by_attributes[type][final][dir];
}


/************************************************************************/
/*                        Dealing with characters                       */
/************************************************************************/

/* The bit fields of character are divided into 3 parts:
   FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */

#define ICHAR_FIELD1_MASK (0x1F << 14)
#define ICHAR_FIELD2_MASK (0x7F << 7)
#define ICHAR_FIELD3_MASK 0x7F

/* Macros to access each field of a character code of C.  */

#define ichar_field1(c) (((c) & ICHAR_FIELD1_MASK) >> 14)
#define ichar_field2(c) (((c) & ICHAR_FIELD2_MASK) >> 7)
#define ichar_field3(c)  ((c) & ICHAR_FIELD3_MASK)

/* Field 1, if non-zero, usually holds a leading byte for a
   dimension-2 charset.  Field 2, if non-zero, usually holds a leading
   byte for a dimension-1 charset. */

/* Converting between field values and leading bytes.  */

#define FIELD2_TO_OFFICIAL_LEADING_BYTE (MIN_LEADING_BYTE_OFFICIAL_1 - 1)
#define FIELD2_TO_PRIVATE_LEADING_BYTE  0x80

#define FIELD1_TO_OFFICIAL_LEADING_BYTE (MIN_LEADING_BYTE_OFFICIAL_2 - 1)
#define FIELD1_TO_PRIVATE_LEADING_BYTE  0xE1

/* Minimum and maximum allowed values for the fields. */

#define MIN_ICHAR_FIELD2_OFFICIAL \
  (MIN_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)
#define MAX_ICHAR_FIELD2_OFFICIAL \
  (MAX_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)

#define MIN_ICHAR_FIELD1_OFFICIAL \
  (MIN_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
#define MAX_ICHAR_FIELD1_OFFICIAL \
  (MAX_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)

#define MIN_ICHAR_FIELD2_PRIVATE \
  (MIN_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
#define MAX_ICHAR_FIELD2_PRIVATE \
  (MAX_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)

#define MIN_ICHAR_FIELD1_PRIVATE \
  (MIN_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
#define MAX_ICHAR_FIELD1_PRIVATE \
  (MAX_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)

/* Minimum character code of each <type> character.  */

#define MIN_CHAR_OFFICIAL_TYPE9N    (MIN_ICHAR_FIELD2_OFFICIAL <<  7)
#define MIN_CHAR_PRIVATE_TYPE9N     (MIN_ICHAR_FIELD2_PRIVATE  <<  7)
#define MIN_CHAR_OFFICIAL_TYPE9NX9N (MIN_ICHAR_FIELD1_OFFICIAL << 14)
#define MIN_CHAR_PRIVATE_TYPE9NX9N  (MIN_ICHAR_FIELD1_PRIVATE  << 14)
#define MIN_CHAR_COMPOSITION        (0x1F << 14)

/* Leading byte of a character.

   NOTE: This takes advantage of the fact that
   FIELD2_TO_OFFICIAL_LEADING_BYTE and
   FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
   */

DECLARE_INLINE_HEADER (
Ibyte
ichar_leading_byte (Ichar c)
)
{
  if (ichar_ascii_p (c))
    return LEADING_BYTE_ASCII;
  else if (c < 0xA0)
    return LEADING_BYTE_CONTROL_1;
  else if (c < MIN_CHAR_OFFICIAL_TYPE9NX9N)
    return ichar_field2 (c) + FIELD2_TO_OFFICIAL_LEADING_BYTE;
  else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N)
    return ichar_field1 (c) + FIELD1_TO_OFFICIAL_LEADING_BYTE;
  else if (c < MIN_CHAR_COMPOSITION)
    return ichar_field1 (c) + FIELD1_TO_PRIVATE_LEADING_BYTE;
  else
    {
#ifdef ENABLE_COMPOSITE_CHARS
      return LEADING_BYTE_COMPOSITE;
#else
      abort();
      return 0;
#endif /* ENABLE_COMPOSITE_CHARS */
    }
}

DECLARE_INLINE_HEADER (
Bytecount
ichar_len (Ichar c)
)
{
  if (ichar_ascii_p (c))
    return 1;
  else if (c < MIN_CHAR_OFFICIAL_TYPE9NX9N)
    return 2;
  else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N)
    return 3; /* dimension-2 official or dimension-1 private */
  else if (c < MIN_CHAR_COMPOSITION)
    return 4;
  else
    {
#ifdef ENABLE_COMPOSITE_CHARS
#error Not yet implemented
#else
      abort();
      return 0;
#endif /* ENABLE_COMPOSITE_CHARS */
    }
}

DECLARE_INLINE_HEADER (
Bytecount
ichar_len_fmt (Ichar c, Internal_Format fmt)
)
{
  switch (fmt)
    {
    case FORMAT_DEFAULT:
      return ichar_len (c);
    case FORMAT_16_BIT_FIXED:
      return 2;
    case FORMAT_32_BIT_FIXED:
      return 4;
    default:
      text_checking_assert (fmt == FORMAT_8_BIT_FIXED);
      return 1;
    }
}

#define ichar_charset(c) charset_by_leading_byte (ichar_leading_byte (c))

/* Return a character whose charset is CHARSET and position-codes are C1
   and C2.  TYPE9N character ignores C2. (For typical charsets, i.e. not
   ASCII, Control-1 or Composite, C1 and C2 will be in the range of 32 to
   127 or 33 to 126.  See `make-char'.)

   NOTE: This takes advantage of the fact that
   FIELD2_TO_OFFICIAL_LEADING_BYTE and
   FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
   */

DECLARE_INLINE_HEADER (
Ichar
make_ichar (Lisp_Object charset, int c1, int c2)
)
{
  Ichar retval;
  if (EQ (charset, Vcharset_ascii))
    retval = c1;
  else if (EQ (charset, Vcharset_control_1))
    retval = c1 | 0x80;
#ifdef ENABLE_COMPOSITE_CHARS
  else if (EQ (charset, Vcharset_composite))
    retval = (0x1F << 14) | ((c1) << 7) | (c2);
#endif
  else if (XCHARSET_DIMENSION (charset) == 1)
    retval = ((XCHARSET_LEADING_BYTE (charset) -
	       FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7) | (c1);
  else if (!XCHARSET_PRIVATE_P (charset))
    retval = ((XCHARSET_LEADING_BYTE (charset) -
	       FIELD1_TO_OFFICIAL_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
  else
    retval = ((XCHARSET_LEADING_BYTE (charset) -
	       FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
  text_checking_assert (valid_ichar_p (retval));
  return retval;
}

/* BREAKUP_ICHAR_1_UNSAFE assumes that the charset has already been
   calculated, and just computes c1 and c2.

   BREAKUP_ICHAR also computes and stores the charset. */

#define BREAKUP_ICHAR_1_UNSAFE(c, charset, c1, c2)	\
  XCHARSET_DIMENSION (charset) == 1			\
  ? ((c1) = ichar_field3 (c), (c2) = 0)		\
  : ((c1) = ichar_field2 (c),				\
     (c2) = ichar_field3 (c))

DECLARE_INLINE_HEADER (
void
breakup_ichar_1 (Ichar c, Lisp_Object *charset, int *c1, int *c2)
)
{
  text_checking_assert (valid_ichar_p (c));
  *charset = ichar_charset (c);
  BREAKUP_ICHAR_1_UNSAFE (c, *charset, *c1, *c2);
}

/* BREAKUP_ICHAR separates an Ichar into its components.  The charset of
   character C is set to CHARSET, and the position-codes of C are set to C1
   and C2.  C2 of TYPE9N character is 0.  */

#define BREAKUP_ICHAR(c, charset, c1, c2) \
  breakup_ichar_1 (c, &(charset), &(c1), &(c2))

void get_charset_limits (Lisp_Object charset, int *low, int *high);
int ichar_to_unicode (Ichar chr);

#endif /* MULE */

#endif /* INCLUDED_charset_h_ */