Mercurial > hg > xemacs-beta
view src/tparam.c @ 4407:4ee73bbe4f8e
Always use boyer_moore in ASCII or Latin-1 buffers with ASCII search strings.
2007-12-26 Aidan Kehoe <kehoea@parhasard.net>
* casetab.c:
Extend and correct some case table documentation.
* search.c (search_buffer):
Correct a bug where only the first entry for a character in the
case equivalence table was examined in determining if the
Boyer-Moore search algorithm is appropriate.
If there are case mappings outside of the charset and row of the
characters specified in the search string, those case mappings can
be safely ignored (and Boyer-Moore search can be used) if we know
from the buffer statistics that the corresponding characters cannot
occur.
* search.c (boyer_moore):
Assert that we haven't been passed a string with varying
characters sets or rows within character sets. That's what
simple_search is for.
In the very rare event that a character in the search string has a
canonical case mapping that is not in the same character set and
row, don't try to search for the canonical character, search for
some other character that is in the the desired character set and
row. Assert that the case table isn't corrupt.
Do not search for any character case mappings that cannot possibly
occur in the buffer, given the buffer metadata about its
contents.
author | Aidan Kehoe <kehoea@parhasard.net> |
---|---|
date | Wed, 26 Dec 2007 17:30:16 +0100 |
parents | facf3239ba30 |
children | 308d34e9f07d |
line wrap: on
line source
/* Merge parameters into a termcap entry string. Copyright (C) 1985, 1987, 1992, 1993, 1994 Free Software Foundation, Inc. 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: Not synched with FSF. */ /* config.h may rename various library functions such as malloc. */ #include <config.h> #include "lisp.h" #undef realloc #undef malloc #define realloc xrealloc #define malloc xmalloc /* Assuming STRING is the value of a termcap string entry containing `%' constructs to expand parameters, merge in parameter values and store result in block OUTSTRING points to. LEN is the length of OUTSTRING. If more space is needed, a block is allocated with `malloc'. The value returned is the address of the resulting string. This may be OUTSTRING or may be the address of a block got with `malloc'. In the latter case, the caller must free the block. The fourth and following args to tparam serve as the parameter values. */ static char *tparam1 (const char *string, char *outstring, int len, const char *up, const char *left, int *argp); /* XEmacs: renamed this function because just tparam() conflicts with ncurses */ char *emacs_tparam (const char *string, char *outstring, int len, int arg0, int arg1, int arg2, int arg3); char * emacs_tparam (const char *string, char *outstring, int len, int arg0, int arg1, int arg2, int arg3) { int arg[4]; arg[0] = arg0; arg[1] = arg1; arg[2] = arg2; arg[3] = arg3; return tparam1 (string, outstring, len, 0, 0, arg); } const char *BC; const char *UP; static char tgoto_buf[50]; char *tgoto (const char *cm, int hpos, int vpos); char * tgoto (const char *cm, int hpos, int vpos) { int args[2]; if (!cm) return 0; args[0] = vpos; args[1] = hpos; return tparam1 (cm, tgoto_buf, 50, UP, BC, args); } static char * tparam1 (const char *string, char *outstring, int len, const char *up, const char *left, int *argp) { int c; const char *p = string; char *op = outstring; char *outend; int outlen = 0; int tem; int *old_argp = argp; int doleft = 0; int doup = 0; outend = outstring + len; while (1) { /* If the buffer might be too short, make it bigger. */ if (op + 5 >= outend) { char *new_; if (outlen == 0) { outlen = len + 40; new_ = (char *) malloc (outlen); outend += 40; memcpy (new_, outstring, op - outstring); } else { outend += outlen; outlen *= 2; new_ = (char *) realloc (outstring, outlen); } op += new_ - outstring; outend += new_ - outstring; outstring = new_; } c = *p++; if (!c) break; if (c == '%') { c = *p++; tem = *argp; switch (c) { case 'd': /* %d means output in decimal. */ if (tem < 10) goto onedigit; if (tem < 100) goto twodigit; case '3': /* %3 means output in decimal, 3 digits. */ if (tem > 999) { *op++ = tem / 1000 + '0'; tem %= 1000; } *op++ = tem / 100 + '0'; case '2': /* %2 means output in decimal, 2 digits. */ twodigit: tem %= 100; *op++ = tem / 10 + '0'; onedigit: *op++ = tem % 10 + '0'; argp++; break; case 'C': /* For c-100: print quotient of value by 96, if nonzero, then do like %+. */ if (tem >= 96) { *op++ = tem / 96; tem %= 96; } case '+': /* %+x means add character code of char x. */ tem += *p++; case '.': /* %. means output as character. */ if (left) { /* If want to forbid output of 0 and \n and \t, and this is one of them, increment it. */ while (tem == 0 || tem == '\n' || tem == '\t') { tem++; if (argp == old_argp) doup++, outend -= strlen (up); else doleft++, outend -= strlen (left); } } *op++ = tem | 0200; case 'f': /* %f means discard next arg. */ argp++; break; case 'b': /* %b means back up one arg (and re-use it). */ argp--; break; case 'r': /* %r means interchange following two args. */ argp[0] = argp[1]; argp[1] = tem; old_argp++; break; case '>': /* %>xy means if arg is > char code of x, */ if (argp[0] > *p++) /* then add char code of y to the arg, */ argp[0] += *p; /* and in any case don't output. */ p++; /* Leave the arg to be output later. */ break; case 'a': /* %a means arithmetic. */ /* Next character says what operation. Add or subtract either a constant or some other arg. */ /* First following character is + to add or - to subtract or = to assign. */ /* Next following char is 'p' and an arg spec (0100 plus position of that arg relative to this one) or 'c' and a constant stored in a character. */ tem = p[2] & 0177; if (p[1] == 'p') tem = argp[tem - 0100]; if (p[0] == '-') argp[0] -= tem; else if (p[0] == '+') argp[0] += tem; else if (p[0] == '*') argp[0] *= tem; else if (p[0] == '/') argp[0] /= tem; else argp[0] = tem; p += 3; break; case 'i': /* %i means add one to arg, */ argp[0] ++; /* and leave it to be output later. */ argp[1] ++; /* Increment the following arg, too! */ break; case '%': /* %% means output %; no arg. */ goto ordinary; case 'n': /* %n means xor each of next two args with 140. */ argp[0] ^= 0140; argp[1] ^= 0140; break; case 'm': /* %m means xor each of next two args with 177. */ argp[0] ^= 0177; argp[1] ^= 0177; break; case 'B': /* %B means express arg as BCD char code. */ argp[0] += 6 * (tem / 10); break; case 'D': /* %D means weird Delta Data transformation. */ argp[0] -= 2 * (tem % 16); break; } } else /* Ordinary character in the argument string. */ ordinary: *op++ = c; } *op = 0; while (doup-- > 0) strcat (op, up); while (doleft-- > 0) strcat (op, left); return outstring; }