view src/casefiddle.c @ 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 ecf1ebac70d8
children 6bc1f3f6cf0d
line wrap: on
line source

/* XEmacs case conversion functions.
   Copyright (C) 1985, 1992, 1993, 1994, 1997, 1998 Free Software Foundation, Inc.
   Copyright (C) 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: FSF 19.34, but substantially rewritten by Martin. */

#include <config.h>
#include "lisp.h"

#include "buffer.h"
#include "insdel.h"
#include "syntax.h"

enum case_action {CASE_UP, CASE_DOWN, CASE_CAPITALIZE, CASE_CAPITALIZE_UP};

static Lisp_Object
casify_object (enum case_action flag, Lisp_Object string_or_char,
	       Lisp_Object buffer)
{
  struct buffer *buf = decode_buffer (buffer, 0);

 retry:

  if (CHAR_OR_CHAR_INTP (string_or_char))
    {
      Ichar c;
      CHECK_CHAR_COERCE_INT (string_or_char);
      c = XCHAR (string_or_char);
      c = (flag == CASE_DOWN) ? DOWNCASE (buf, c) : UPCASE (buf, c);
      return make_char (c);
    }

  if (STRINGP (string_or_char))
    {
      Lisp_Object syntax_table = buf->mirror_syntax_table;
      Ibyte *storage =
	alloca_ibytes (XSTRING_LENGTH (string_or_char) * MAX_ICHAR_LEN);
      Ibyte *newp = storage;
      Ibyte *oldp = XSTRING_DATA (string_or_char);
      Ibyte *endp = oldp + XSTRING_LENGTH (string_or_char);
      int wordp = 0, wordp_prev;

      while (oldp < endp)
	{
	  Ichar c = itext_ichar (oldp);
	  switch (flag)
	    {
	    case CASE_UP:
	      c = UPCASE (buf, c);
	      break;
	    case CASE_DOWN:
	      c = DOWNCASE (buf, c);
	      break;
	    case CASE_CAPITALIZE:
	    case CASE_CAPITALIZE_UP:
	      wordp_prev = wordp;
	      wordp = WORD_SYNTAX_P (syntax_table, c);
	      if (!wordp) break;
	      if (wordp_prev)
		{
		  if (flag == CASE_CAPITALIZE)
		    c = DOWNCASE (buf, c);
		}
	      else
		c = UPCASE (buf, c);
	      break;
	    }

	  newp += set_itext_ichar (newp, c);
	  INC_IBYTEPTR (oldp);
	}

      return make_string (storage, newp - storage);
    }

  string_or_char = wrong_type_argument (Qchar_or_string_p, string_or_char);
  goto retry;
}

DEFUN ("upcase", Fupcase, 1, 2, 0, /*
Convert STRING-OR-CHAR to upper case and return that.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
See also `capitalize', `downcase' and `upcase-initials'.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_UP, string_or_char, buffer);
}

DEFUN ("downcase", Fdowncase, 1, 2, 0, /*
Convert STRING-OR-CHAR to lower case and return that.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_DOWN, string_or_char, buffer);
}

DEFUN ("capitalize", Fcapitalize, 1, 2, 0, /*
Convert STRING-OR-CHAR to capitalized form and return that.
This means that each word's first character is upper case
and the rest is lower case.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_CAPITALIZE, string_or_char, buffer);
}

/* Like Fcapitalize but change only the initial characters.  */

DEFUN ("upcase-initials", Fupcase_initials, 1, 2, 0, /*
Convert the initial of each word in STRING-OR-CHAR to upper case.
Do not change the other letters of each word.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_CAPITALIZE_UP, string_or_char, buffer);
}

/* flag is CASE_UP, CASE_DOWN or CASE_CAPITALIZE or CASE_CAPITALIZE_UP.
   START and END specify range of buffer to operate on. */

static void
casify_region_internal (enum case_action flag, Lisp_Object start,
			Lisp_Object end, struct buffer *buf)
{
  /* This function can GC */
  Charbpos pos, s, e;
  Lisp_Object syntax_table = buf->mirror_syntax_table;
  int mccount;
  int wordp = 0, wordp_prev;

  if (EQ (start, end))
    /* Not modifying because nothing marked */
    return;

  get_buffer_range_char (buf, start, end, &s, &e, 0);

  mccount = begin_multiple_change (buf, s, e);
  record_change (buf, s, e - s);

  for (pos = s; pos < e; pos++)
    {
      Ichar oldc = BUF_FETCH_CHAR (buf, pos);
      Ichar c = oldc;

      switch (flag)
	{
	case CASE_UP:
	  c = UPCASE (buf, oldc);
	  break;
	case CASE_DOWN:
	  c = DOWNCASE (buf, oldc);
	  break;
	case CASE_CAPITALIZE:
	case CASE_CAPITALIZE_UP:
	  /* !!#### need to revalidate the start and end pointers in case
	     the buffer was changed */
	  wordp_prev = wordp;
	  wordp = WORD_SYNTAX_P (syntax_table, c);
	  if (!wordp) continue;
	  if (wordp_prev)
	    {
	      if (flag == CASE_CAPITALIZE)
		c = DOWNCASE (buf, c);
	    }
	  else
	    c = UPCASE (buf, c);
	  break;
	}

      if (oldc == c) continue;
      buffer_replace_char (buf, pos, c, 1, (pos == s));
      BUF_MODIFF (buf)++;
    }

  end_multiple_change (buf, mccount);
}

static Lisp_Object
casify_region (enum case_action flag, Lisp_Object start, Lisp_Object end,
	       Lisp_Object buffer)
{
  casify_region_internal (flag, start, end, decode_buffer (buffer, 1));
  return Qnil;
}

DEFUN ("upcase-region", Fupcase_region, 2, 3, "r", /*
Convert the region to upper case.  In programs, wants two arguments.
These arguments specify the starting and ending character numbers of
 the region to operate on.  When used as a command, the text between
 point and the mark is operated on.
See also `capitalize-region'.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  /* This function can GC */
  return casify_region (CASE_UP, start, end, buffer);
}

DEFUN ("downcase-region", Fdowncase_region, 2, 3, "r", /*
Convert the region to lower case.  In programs, wants two arguments.
These arguments specify the starting and ending character numbers of
 the region to operate on.  When used as a command, the text between
 point and the mark is operated on.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  /* This function can GC */
  return casify_region (CASE_DOWN, start, end, buffer);
}

DEFUN ("capitalize-region", Fcapitalize_region, 2, 3, "r", /*
Convert the region to capitalized form.
Capitalized form means each word's first character is upper case
 and the rest of it is lower case.
In programs, give two arguments, the starting and ending
 character positions to operate on.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  /* This function can GC */
  return casify_region (CASE_CAPITALIZE, start, end, buffer);
}

/* Like Fcapitalize_region but change only the initials.  */

DEFUN ("upcase-initials-region", Fupcase_initials_region, 2, 3, "r", /*
Upcase the initial of each word in the region.
Subsequent letters of each word are not changed.
In programs, give two arguments, the starting and ending
 character positions to operate on.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  return casify_region (CASE_CAPITALIZE_UP, start, end, buffer);
}


static Lisp_Object
casify_word (enum case_action flag, Lisp_Object arg, Lisp_Object buffer)
{
  Charbpos farend;
  struct buffer *buf = decode_buffer (buffer, 1);

  CHECK_INT (arg);

  farend = scan_words (buf, BUF_PT (buf), XINT (arg));
  if (!farend)
    farend = XINT (arg) > 0 ? BUF_ZV (buf) : BUF_BEGV (buf);

  casify_region_internal (flag, make_int (BUF_PT (buf)), make_int (farend), buf);
  BUF_SET_PT (buf, max (BUF_PT (buf), farend));
  return Qnil;
}

DEFUN ("upcase-word", Fupcase_word, 1, 2, "p", /*
Convert following word (or COUNT words) to upper case, moving over.
With negative argument, convert previous words but do not move.
See also `capitalize-word'.
Optional second arg BUFFER defaults to the current buffer.
*/
       (count, buffer))
{
  /* This function can GC */
  return casify_word (CASE_UP, count, buffer);
}

DEFUN ("downcase-word", Fdowncase_word, 1, 2, "p", /*
Convert following word (or COUNT words) to lower case, moving over.
With negative argument, convert previous words but do not move.
Optional second arg BUFFER defaults to the current buffer.
*/
       (count, buffer))
{
  /* This function can GC */
  return casify_word (CASE_DOWN, count, buffer);
}

DEFUN ("capitalize-word", Fcapitalize_word, 1, 2, "p", /*
Capitalize the following word (or COUNT words), moving over.
This gives the word(s) a first character in upper case
 and the rest lower case.
With negative argument, capitalize previous words but do not move.
Optional second arg BUFFER defaults to the current buffer.
*/
       (count, buffer))
{
  /* This function can GC */
  return casify_word (CASE_CAPITALIZE, count, buffer);
}


void
syms_of_casefiddle (void)
{
  DEFSUBR (Fupcase);
  DEFSUBR (Fdowncase);
  DEFSUBR (Fcapitalize);
  DEFSUBR (Fupcase_initials);
  DEFSUBR (Fupcase_region);
  DEFSUBR (Fdowncase_region);
  DEFSUBR (Fcapitalize_region);
  DEFSUBR (Fupcase_initials_region);
  DEFSUBR (Fupcase_word);
  DEFSUBR (Fdowncase_word);
  DEFSUBR (Fcapitalize_word);
}