view src/casefiddle.c @ 4921:17362f371cc2

add more byte-code assertions and better failure output -------------------- ChangeLog entries follow: -------------------- src/ChangeLog addition: 2010-02-03 Ben Wing <ben@xemacs.org> * alloc.c (Fmake_byte_code): * bytecode.h: * lisp.h: * lread.c: * lread.c (readevalloop): * lread.c (Fread): * lread.c (Fread_from_string): * lread.c (read_list_conser): * lread.c (read_list): * lread.c (vars_of_lread): * symbols.c: * symbols.c (Fdefine_function): Turn on the "compiled-function annotation hack". Implement it properly by hooking into Fdefalias(). Note in the docstring to `defalias' that we do this. Remove some old broken code and change code that implemented the old kludgy way of hooking into the Lisp reader into bracketed by `#ifdef COMPILED_FUNCTION_ANNOTATION_HACK_OLD_WAY', which is not enabled. Also enable byte-code metering when DEBUG_XEMACS -- this is a form of profiling for computing histograms of which sequences of two bytecodes are used most often. * bytecode-ops.h: * bytecode-ops.h (OPCODE): New file. Extract out all the opcodes and declare them using OPCODE(), a bit like frame slots and such. This way the file can be included multiple times if necessary to iterate multiple times over the byte opcodes. * bytecode.c: * bytecode.c (NUM_REMEMBERED_BYTE_OPS): * bytecode.c (OPCODE): * bytecode.c (assert_failed_with_remembered_ops): * bytecode.c (READ_UINT_2): * bytecode.c (READ_INT_1): * bytecode.c (READ_INT_2): * bytecode.c (PEEK_INT_1): * bytecode.c (PEEK_INT_2): * bytecode.c (JUMP_RELATIVE): * bytecode.c (JUMP_NEXT): * bytecode.c (PUSH): * bytecode.c (POP_WITH_MULTIPLE_VALUES): * bytecode.c (DISCARD): * bytecode.c (UNUSED): * bytecode.c (optimize_byte_code): * bytecode.c (optimize_compiled_function): * bytecode.c (Fbyte_code): * bytecode.c (vars_of_bytecode): * bytecode.c (init_opcode_table_multi_op): * bytecode.c (reinit_vars_of_bytecode): * emacs.c (main_1): * eval.c (funcall_compiled_function): * symsinit.h: Any time we change either the instruction pointer or the stack pointer, assert that we're going to move it to a valid location. This should catch failures right when they occur rather than sometime later. This requires that we pass in another couple of parameters into some functions (only with error-checking enabled, see below). Also keep track, using a circular queue, of the last 100 byte opcodes seen, and when we hit an assert failure during byte-code execution, output the contents of the queue in a nice readable fashion. This requires that bytecode-ops.h be included a second time so that a table mapping opcodes to the name of their operation can be constructed. This table is constructed in new function reinit_vars_of_bytecode(). Everything in the last two paras happens only when ERROR_CHECK_BYTE_CODE. Add some longish comments describing how the arrays that hold the stack and instructions, and the pointers used to access them, work. * gc.c: Import some code from my `latest-fix' workspace to mark the staticpro's in order from lowest to highest, rather than highest to lowest, so it's easier to debug when something goes wrong. * lisp.h (abort_with_message): Renamed from abort_with_msg(). * symbols.c (defsymbol_massage_name_1): * symbols.c (defsymbol_nodump): * symbols.c (defsymbol): * symbols.c (defkeyword): * symeval.h (DEFVAR_SYMVAL_FWD_OBJECT): Make the various calls to staticpro() instead call staticpro_1(), passing in the name of the C var being staticpro'ed, so that it shows up in staticpro_names. Otherwise staticpro_names just has 1000+ copies of the word `location'.
author Ben Wing <ben@xemacs.org>
date Wed, 03 Feb 2010 08:01:55 -0600
parents 6bc1f3f6cf0d
children 308d34e9f07d
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,
                  CASE_CANONICALIZE};

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);
      if (flag == CASE_DOWN)
	{
	  c = DOWNCASE (buf, c);
	}
      else if (flag == CASE_UP)
	{
	  c = UPCASE (buf, c);
	}
      else
	{
	  c = CANONCASE (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_CANONICALIZE:
	      c = CANONCASE (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 ("canoncase", Fcanoncase, 1, 2, 0, /*
Convert STRING-OR-CHAR to its canonical lowercase form 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.

For any N characters that are equivalent in case-insensitive searching,
their canonical lowercase character will be the same.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_CANONICALIZE, 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 (Fcanoncase);
  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);
}