Mercurial > hg > xemacs-beta
view src/dragdrop.c @ 5648:3f4a234f4672
Support non-ASCII correctly in character classes, test this.
src/ChangeLog addition:
2012-04-21 Aidan Kehoe <kehoea@parhasard.net>
Support non-ASCII correctly in character classes ([:alnum:] and
friends).
* regex.c:
* regex.c (ISBLANK, ISUNIBYTE): New. Make these and friends
independent of the locale, since we want them to be consistent in
XEmacs.
* regex.c (print_partial_compiled_pattern): Print the flags for
charset_mule; don't print non-ASCII as the character values in
ranges, this breaks with locales.
* regex.c (enum):
Define various flags the charset_mule and charset_mule_not opcodes
can now take.
* regex.c (CHAR_CLASS_MAX_LENGTH): Update this.
* regex.c (re_iswctype, re_wctype): New, from GNU.
* regex.c (re_wctype_can_match_non_ascii): New; used when deciding
on whether to use charset_mule or the ASCII-only regex character
set opcode.
* regex.c (regex_compile):
Error correctly on long, non-existent character class names.
Break out the handling of charsets that can match non-ASCII into a
separate clause. Use compile_char_class when compiling character
classes.
* regex.c (compile_char_class): New. Used in regex_compile when
compiling character sets that may match non-ASCII.
* regex.c (re_compile_fastmap):
If there are flags set for charset_mule or charset_mule_not, we
can't use the fastmap (since we need to check syntax table values
that aren't available there).
* regex.c (re_match_2_internal):
Check the new flags passed to the charset_mule{,_not} opcode,
observe them if appropriate.
* regex.h:
* regex.h (enum):
Expose re_wctype_t here, imported from GNU.
tests/ChangeLog addition:
2012-04-21 Aidan Kehoe <kehoea@parhasard.net>
* automated/regexp-tests.el:
* automated/regexp-tests.el (Assert-char-class):
Check that #'string-match errors correctly with an over-long
character class name.
Add tests for character class functionality that supports
non-ASCII characters. These tests expose bugs in GNU Emacs
24.0.94.2, but pass under current XEmacs.
author | Aidan Kehoe <kehoea@parhasard.net> |
---|---|
date | Sat, 21 Apr 2012 18:58:28 +0100 |
parents | 308d34e9f07d |
children |
line wrap: on
line source
/* Drag'n'Drop definitions created 03-may-98 by Oliver Graf <ograf@fga.de> Copyright (C) 1998 Oliver Graf <ograf@fga.de> Copyright (C) 2004 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 3 of the License, 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. If not, see <http://www.gnu.org/licenses/>. */ /* Synched up with: Not in FSF. */ /* This file should be Mule-ized. */ /* A short introduction to the new Drag'n'Drop Model: A drop generates a extended misc-user-event, as defined in events.[ch]. This event contains the same as a eval and a button event. The function of a drop is set to 'dragdrop-drop-dispatch' which will be defined in ../lisp/dragdrop.el. The object of the misc-user-event has the following format: ( TYPE . DATA ) TYPE is one of `dragdrop-MIME' and `dragdrop-URL' DATA - if TYPE is `dragdrop-URL', DATA is a list of valid URL strings. It is always a list, also if only one URL string is within it. - if TYPE is `dragdrop-MIME', DATA is a list of MIME elements. Each can be a string or a list. if it is a string it is the pure MIME data complete with header and body. if it is a list it should look like ( MIME-TYPE MIME-ENCODING MIME-DATA ) MIME-TYPE list of type and key.value conses. Same as in tm-view MIME-ENC the same (a string in this case) MIME-DATA is a string */ #include <config.h> #include "lisp.h" #include "dragdrop.h" /* The supported protocol list */ Lisp_Object Vdragdrop_protocols; /* Drag'n'Drop data types known by XEmacs */ Lisp_Object Qdragdrop_MIME; Lisp_Object Qdragdrop_URL; /* External defined functions to handle Drag'n'Drop */ Lisp_Object Qdragdrop_drop_dispatch; /* from wget -- thanxx Hrvoje */ /* A list of unsafe characters for encoding, as per RFC1738. '@' and ':' (not listed in RFC) were added because of user/password encoding, and \033 for safe printing. */ #define URL_UNSAFE " <>\"#%{}|\\^~[]`@:\033" /* HEX digit -> ASCII char */ #define HEXD2ASC(x) (((x) < 10) ? ((x) + '0') : ((x) - 10 + 'A')) /* Encodes the unsafe characters (listed in URL_UNSAFE) in a given string, returning a malloc-ed %XX encoded string. if method is != NULL it is prepended to the string. */ Ibyte * dnd_url_hexify_string (const Ibyte *s, const Ibyte *m) { const Ibyte *b; Ibyte *p, *res; Bytecount i; b = s; for (i = 0; *s; s++, i++) if (strchr (URL_UNSAFE, *s)) i += 2; /* Two more characters (hex digits) */ if (m) { res = xnew_ibytes (i + ITEXT_ZTERM_SIZE + qxestrlen (m)); qxestrcpy (res, m); p = res + qxestrlen (m); } else { res = xnew_ibytes (i + ITEXT_ZTERM_SIZE); p = res; } for (s = b; *s; s++) if (strchr (URL_UNSAFE, *s)) { const Ibyte c = *s; *p++ = '%'; *p++ = HEXD2ASC (c >> 4); *p++ = HEXD2ASC (c & 0xf); } else *p++ = *s; *p = '\0'; return res; } void syms_of_dragdrop (void) { DEFSYMBOL (Qdragdrop_MIME); DEFSYMBOL (Qdragdrop_URL); DEFSYMBOL (Qdragdrop_drop_dispatch); } void vars_of_dragdrop (void) { Fprovide (intern ("dragdrop-api")); DEFVAR_CONST_LISP ("dragdrop-protocols", &Vdragdrop_protocols /* A list of supported Drag'n'drop protocols. Each element is the feature symbol of the protocol. */ ); Vdragdrop_protocols = Qnil; #ifdef HAVE_MS_WINDOWS Vdragdrop_protocols = Fcons (Qmswindows, Vdragdrop_protocols); #endif #ifdef HAVE_CDE Vdragdrop_protocols = Fcons (intern ("cde"), Vdragdrop_protocols); #endif #ifdef HAVE_GTK Vdragdrop_protocols = Fcons (Qgtk, Vdragdrop_protocols); #endif }