view lisp/extents.el @ 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

;;; extents.el --- miscellaneous extent functions not written in C

;; Copyright (C) 1993-4, 1997 Free Software Foundation, Inc.
;; Copyright (C) 2000 Ben Wing.

;; Keywords: internal, dumped

;; 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.

;;; Commentary:

;;; Authorship:

;; Created 1995 Ben Wing.
;; mapcar-extents (and extent-list?) from stig@hackvan.com, c. 1996.

;;; Code:

;; an alternative to map-extents.
(defun mapcar-extents (function &optional predicate buffer-or-string from to
				flags property value)
  "Apply FUNCTION to all extents which overlap a region in BUFFER-OR-STRING.
The region is delimited by FROM and TO.  FUNCTION is called with
one argument, the extent.  A list of the values returned by FUNCTION
is returned.  An optional PREDICATE may be used to further limit the
extents over which FUNCTION is mapped.  The optional arguments FLAGS,
PROPERTY, and VALUE may also be used to control the extents passed to
PREDICATE or FUNCTION.  See also `map-extents'."
  (let (*result*)
    (map-extents (if predicate
                     #'(lambda (ex junk)
                         (and (funcall predicate ex)
                              (setq *result* (cons (funcall function ex)
                                                   *result*)))
                         nil)
                   #'(lambda (ex junk)
                         (setq *result* (cons (funcall function ex)
                                              *result*))
                         nil))
                 buffer-or-string from to nil flags property value)
    (nreverse *result*)))

(defun extent-list (&optional buffer-or-string from to flags property value)
  "Return a list of the extents in BUFFER-OR-STRING.
BUFFER-OR-STRING defaults to the current buffer if omitted.
FROM and TO can be used to limit the range over which extents are
returned; if omitted, all extents in the buffer or string are returned.

More specifically, if a range is specified using FROM and TO, only
extents that overlap the range (i.e. begin or end inside of the range)
are included in the list.  FROM and TO default to the beginning and
end of BUFFER-OR-STRING, respectively.

FLAGS controls how end cases are treated.  For a discussion of this,
and exactly what ``overlap'' means, see `map-extents'.  PROPERTY and VALUE
are also as in `map-extents'.

If you want to map a function over the extents in a buffer or string,
consider using `map-extents' or `mapcar-extents' instead.

See also `extents-at'."
  (mapcar-extents 'identity nil buffer-or-string from to flags property value))

(defun extent-at-event (event &optional property before at-flag)
  "Return the smallest extent under EVENT, if any.
PROPERTY, BEFORE, and AT-FLAG are as in `extent-at'."
  (let* ((win (event-window event))
	 (p (event-point event)))
    (and win p (extent-at p (window-buffer win) property before at-flag))))

(defun extents-at-event (event &optional property before at-flag)
  "Return a list of all extents under EVENT.
PROPERTY, BEFORE, and AT-FLAG are as in `extent-at'."
  (let* ((win (event-window event))
	 (p (event-point event)))
    (and win p (extents-at p (window-buffer win) property before at-flag))))

(defun extent-string (extent)
  "Return the string delimited by the bounds of EXTENT."
  (let ((object (extent-object extent)))
    (if (bufferp object)
	(buffer-substring (extent-start-position extent)
			  (extent-end-position extent)
			  object)
      (substring object
		 (extent-start-position extent)
		 (extent-end-position extent)))))

(defun extent-descendants (extent)
  "Return a list of all descendants of EXTENT, including EXTENT.
This recursively applies `extent-children' to any children of
EXTENT, until no more children can be found."
  (let ((children (extent-children extent)))
    (if children
	(mapcan 'extent-descendants children)
      (list extent))))

(defun set-extent-keymap (extent keymap)
  "Set EXTENT's `keymap' property to KEYMAP."
  (set-extent-property extent 'keymap keymap))

(defun extent-keymap (extent)
  "Return EXTENT's `keymap' property."
  (extent-property extent 'keymap))

;;; extents.el ends here