annotate lisp/xml.el @ 55253:d33879ad154a

(xml-debug-print-internal): Don't add newline and indentation to text nodes and write empty elements as empty tags instead of opening and closing tags. (xml-debug-print): Take optional indent-string argument. (xml-print): Alias for xml-debug-print.
author Alex Schroeder <alex@gnu.org>
date Fri, 30 Apr 2004 20:00:19 +0000
parents 42293f0612cc
children 7ac80356d84c
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
1 ;;; xml.el --- XML parser
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
2
54243
586ffda6e9f9 (xml-get-attribute-or-nil): Simplify.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 53384
diff changeset
3 ;; Copyright (C) 2000, 01, 03, 2004 Free Software Foundation, Inc.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
4
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
5 ;; Author: Emmanuel Briot <briot@gnat.com>
51697
79747466c43b Record new maintainer.
Richard M. Stallman <rms@gnu.org>
parents: 51334
diff changeset
6 ;; Maintainer: Mark A. Hershberger <mah@everybody.org>
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
7 ;; Keywords: xml, data
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
8
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
9 ;; This file is part of GNU Emacs.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
10
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
11 ;; GNU Emacs is free software; you can redistribute it and/or modify
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
12 ;; it under the terms of the GNU General Public License as published by
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
13 ;; the Free Software Foundation; either version 2, or (at your option)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
14 ;; any later version.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
15
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
16 ;; GNU Emacs is distributed in the hope that it will be useful,
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
19 ;; GNU General Public License for more details.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
20
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
21 ;; You should have received a copy of the GNU General Public License
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
22 ;; along with GNU Emacs; see the file COPYING. If not, write to the
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
23 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
24 ;; Boston, MA 02111-1307, USA.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
25
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
26 ;;; Commentary:
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
27
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
28 ;; This file contains a somewhat incomplete non-validating XML parser. It
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
29 ;; parses a file, and returns a list that can be used internally by
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
30 ;; any other Lisp libraries.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
31
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
32 ;;; FILE FORMAT
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
33
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
34 ;; The document type declaration may either be ignored or (optionally)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
35 ;; parsed, but currently the parsing will only accept element
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
36 ;; declarations. The XML file is assumed to be well-formed. In case
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
37 ;; of error, the parsing stops and the XML file is shown where the
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
38 ;; parsing stopped.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
39 ;;
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
40 ;; It also knows how to ignore comments and processing instructions.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
41 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
42 ;; The XML file should have the following format:
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
43 ;; <node1 attr1="name1" attr2="name2" ...>value
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
44 ;; <node2 attr3="name3" attr4="name4">value2</node2>
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
45 ;; <node3 attr5="name5" attr6="name6">value3</node3>
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
46 ;; </node1>
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
47 ;; Of course, the name of the nodes and attributes can be anything. There can
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
48 ;; be any number of attributes (or none), as well as any number of children
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
49 ;; below the nodes.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
50 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
51 ;; There can be only top level node, but with any number of children below.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
52
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
53 ;;; LIST FORMAT
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
54
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
55 ;; The functions `xml-parse-file', `xml-parse-region' and
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
56 ;; `xml-parse-tag' return a list with the following format:
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
57 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
58 ;; xml-list ::= (node node ...)
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
59 ;; node ::= (qname attribute-list . child_node_list)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
60 ;; child_node_list ::= child_node child_node ...
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
61 ;; child_node ::= node | string
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
62 ;; qname ::= (:namespace-uri . "name") | "name"
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
63 ;; attribute_list ::= ((qname . "value") (qname . "value") ...)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
64 ;; | nil
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
65 ;; string ::= "..."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
66 ;;
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
67 ;; Some macros are provided to ease the parsing of this list.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
68 ;; Whitespace is preserved. Fixme: There should be a tree-walker that
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
69 ;; can remove it.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
70
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
71 ;; TODO:
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
72 ;; * xml:base, xml:space support
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
73 ;; * more complete DOCTYPE parsing
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
74 ;; * pi support
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
75
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
76 ;;; Code:
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
77
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
78 ;; Note that {buffer-substring,match-string}-no-properties were
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
79 ;; formerly used in several places, but that removes composition info.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
80
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
81 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
82 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
83 ;;** Macros to parse the list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
84 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
85 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
86
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
87 (defsubst xml-node-name (node)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
88 "Return the tag associated with NODE.
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
89 Without namespace-aware parsing, the tag is a symbol.
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
90
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
91 With namespace-aware parsing, the tag is a cons of a string
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
92 representing the uri of the namespace with the local name of the
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
93 tag. For example,
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
94
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
95 <foo>
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
96
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
97 would be represented by
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
98
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
99 '(\"\" . \"foo\")."
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
100
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
101 (car node))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
102
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
103 (defsubst xml-node-attributes (node)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
104 "Return the list of attributes of NODE.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
105 The list can be nil."
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
106 (nth 1 node))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
107
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
108 (defsubst xml-node-children (node)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
109 "Return the list of children of NODE.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
110 This is a list of nodes, and it can be nil."
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
111 (cddr node))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
112
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
113 (defun xml-get-children (node child-name)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
114 "Return the children of NODE whose tag is CHILD-NAME.
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
115 CHILD-NAME should match the value returned by `xml-node-name'."
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
116 (let ((match ()))
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
117 (dolist (child (xml-node-children node))
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
118 (if (and (listp child)
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
119 (equal (xml-node-name child) child-name))
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
120 (push child match)))
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
121 (nreverse match)))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
122
53375
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
123 (defun xml-get-attribute-or-nil (node attribute)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
124 "Get from NODE the value of ATTRIBUTE.
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
125 Return nil if the attribute was not found.
53375
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
126
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
127 See also `xml-get-attribute'."
54243
586ffda6e9f9 (xml-get-attribute-or-nil): Simplify.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 53384
diff changeset
128 (cdr (assoc attribute (xml-node-attributes node))))
53375
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
129
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
130 (defsubst xml-get-attribute (node attribute)
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
131 "Get from NODE the value of ATTRIBUTE.
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
132 An empty string is returned if the attribute was not found.
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
133
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
134 See also `xml-get-attribute-or-nil'."
e085973399ee (xml-get-attribute-or-nil): New function, like
Eli Zaretskii <eliz@is.elta.co.il>
parents: 53011
diff changeset
135 (or (xml-get-attribute-or-nil node attribute) ""))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
136
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
137 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
138 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
139 ;;** Creating the list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
140 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
141 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
142
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
143 ;;;###autoload
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
144 (defun xml-parse-file (file &optional parse-dtd parse-ns)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
145 "Parse the well-formed XML file FILE.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
146 If FILE is already visited, use its buffer and don't kill it.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
147 Returns the top node with all its children.
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
148 If PARSE-DTD is non-nil, the DTD is parsed rather than skipped.
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
149 If PARSE-NS is non-nil, then QNAMES are expanded."
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
150 (let ((keep))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
151 (if (get-file-buffer file)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
152 (progn
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
153 (set-buffer (get-file-buffer file))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
154 (setq keep (point)))
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
155 (let (auto-mode-alist) ; no need for xml-mode
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
156 (find-file file)))
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
157
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
158 (let ((xml (xml-parse-region (point-min)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
159 (point-max)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
160 (current-buffer)
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
161 parse-dtd parse-ns)))
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
162 (if keep
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
163 (goto-char keep)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
164 (kill-buffer (current-buffer)))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
165 xml)))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
166
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
167 ;; Note that this is setup so that we can do whitespace-skipping with
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
168 ;; `(skip-syntax-forward " ")', inter alia. Previously this was slow
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
169 ;; compared with `re-search-forward', but that has been fixed. Also
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
170 ;; note that the standard syntax table contains other characters with
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
171 ;; whitespace syntax, like NBSP, but they are invalid in contexts in
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
172 ;; which we might skip whitespace -- specifically, they're not
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
173 ;; NameChars [XML 4].
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
174
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
175 (defvar xml-syntax-table
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
176 (let ((table (make-syntax-table)))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
177 ;; Get space syntax correct per XML [3].
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
178 (dotimes (c 31)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
179 (modify-syntax-entry c "." table)) ; all are space in standard table
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
180 (dolist (c '(?\t ?\n ?\r)) ; these should be space
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
181 (modify-syntax-entry c " " table))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
182 ;; For skipping attributes.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
183 (modify-syntax-entry ?\" "\"" table)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
184 (modify-syntax-entry ?' "\"" table)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
185 ;; Non-alnum name chars should be symbol constituents (`-' and `_'
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
186 ;; are OK by default).
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
187 (modify-syntax-entry ?. "_" table)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
188 (modify-syntax-entry ?: "_" table)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
189 ;; XML [89]
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
190 (dolist (c '(#x00B7 #x02D0 #x02D1 #x0387 #x0640 #x0E46 #x0EC6 #x3005
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
191 #x3031 #x3032 #x3033 #x3034 #x3035 #x309D #x309E #x30FC
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
192 #x30FD #x30FE))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
193 (modify-syntax-entry (decode-char 'ucs c) "w" table))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
194 ;; Fixme: rest of [4]
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
195 table)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
196 "Syntax table used by `xml-parse-region'.")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
197
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
198 ;; XML [5]
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
199 ;; Note that [:alpha:] matches all multibyte chars with word syntax.
51105
aac5eaf1454e (xml-name-regexp): Wrap in `eval-and-compile'.
John Paul Wallington <jpw@pobox.com>
parents: 51102
diff changeset
200 (eval-and-compile
aac5eaf1454e (xml-name-regexp): Wrap in `eval-and-compile'.
John Paul Wallington <jpw@pobox.com>
parents: 51102
diff changeset
201 (defconst xml-name-regexp "[[:alpha:]_:][[:alnum:]._:-]*"))
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
202
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
203 ;; Fixme: This needs re-writing to deal with the XML grammar properly, i.e.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
204 ;; document ::= prolog element Misc*
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
205 ;; prolog ::= XMLDecl? Misc* (doctypedecl Misc*)?
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
206
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
207 ;;;###autoload
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
208 (defun xml-parse-region (beg end &optional buffer parse-dtd parse-ns)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
209 "Parse the region from BEG to END in BUFFER.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
210 If BUFFER is nil, it defaults to the current buffer.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
211 Returns the XML list for the region, or raises an error if the region
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
212 is not well-formed XML.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
213 If PARSE-DTD is non-nil, the DTD is parsed rather than skipped,
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
214 and returned as the first element of the list.
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
215 If PARSE-NS is non-nil, then QNAMES are expanded."
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
216 (save-restriction
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
217 (narrow-to-region beg end)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
218 ;; Use fixed syntax table to ensure regexp char classes and syntax
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
219 ;; specs DTRT.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
220 (with-syntax-table (standard-syntax-table)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
221 (let ((case-fold-search nil) ; XML is case-sensitive.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
222 xml result dtd)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
223 (save-excursion
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
224 (if buffer
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
225 (set-buffer buffer))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
226 (goto-char (point-min))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
227 (while (not (eobp))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
228 (if (search-forward "<" nil t)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
229 (progn
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
230 (forward-char -1)
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
231 (setq result (xml-parse-tag parse-dtd parse-ns))
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
232 (if (and xml result)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
233 ;; translation of rule [1] of XML specifications
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
234 (error "XML files can have only one toplevel tag")
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
235 (cond
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
236 ((null result))
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
237 ((and (listp (car result))
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
238 parse-dtd)
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
239 (setq dtd (car result))
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
240 (if (cdr result) ; possible leading comment
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
241 (add-to-list 'xml (cdr result))))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
242 (t
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
243 (add-to-list 'xml result)))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
244 (goto-char (point-max))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
245 (if parse-dtd
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
246 (cons dtd (nreverse xml))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
247 (nreverse xml)))))))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
248
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
249 (defun xml-maybe-do-ns (name default xml-ns)
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
250 "Perform any namespace expansion.
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
251 NAME is the name to perform the expansion on.
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
252 DEFAULT is the default namespace. XML-NS is a cons of namespace
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
253 names to uris. When namespace-aware parsing is off, then XML-NS
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
254 is nil.
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
255
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
256 During namespace-aware parsing, any name without a namespace is
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
257 put into the namespace identified by DEFAULT. nil is used to
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
258 specify that the name shouldn't be given a namespace."
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
259 (if (consp xml-ns)
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
260 (let* ((nsp (string-match ":" name))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
261 (lname (if nsp (substring name (match-end 0)) name))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
262 (prefix (if nsp (substring name 0 (match-beginning 0)) default))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
263 (special (and (string-equal lname "xmlns") (not prefix)))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
264 ;; Setting default to nil will insure that there is not
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
265 ;; matching cons in xml-ns. In which case we
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
266 (ns (or (cdr (assoc (if special "xmlns" prefix)
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
267 xml-ns))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
268 :)))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
269 (cons ns (if special "" lname)))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
270 (intern name)))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
271
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
272 (defun xml-parse-tag (&optional parse-dtd parse-ns)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
273 "Parse the tag at point.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
274 If PARSE-DTD is non-nil, the DTD of the document, if any, is parsed and
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
275 returned as the first element in the list.
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
276 If PARSE-NS is non-nil, then QNAMES are expanded.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
277 Returns one of:
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
278 - a list : the matching node
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
279 - nil : the point is not looking at a tag.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
280 - a pair : the first element is the DTD, the second is the node."
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
281 (let ((xml-ns (if (consp parse-ns)
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
282 parse-ns
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
283 (if parse-ns
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
284 (list
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
285 ;; Default for empty prefix is no namespace
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
286 (cons "" :)
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
287 ;; "xml" namespace
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
288 (cons "xml" :http://www.w3.org/XML/1998/namespace)
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
289 ;; We need to seed the xmlns namespace
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
290 (cons "xmlns" :http://www.w3.org/2000/xmlns/))))))
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
291 (cond
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
292 ;; Processing instructions (like the <?xml version="1.0"?> tag at the
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
293 ;; beginning of a document).
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
294 ((looking-at "<\\?")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
295 (search-forward "?>")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
296 (skip-syntax-forward " ")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
297 (xml-parse-tag parse-dtd xml-ns))
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
298 ;; Character data (CDATA) sections, in which no tag should be interpreted
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
299 ((looking-at "<!\\[CDATA\\[")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
300 (let ((pos (match-end 0)))
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
301 (unless (search-forward "]]>" nil t)
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
302 (error "CDATA section does not end anywhere in the document"))
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
303 (buffer-substring pos (match-beginning 0))))
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
304 ;; DTD for the document
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
305 ((looking-at "<!DOCTYPE")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
306 (let (dtd)
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
307 (if parse-dtd
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
308 (setq dtd (xml-parse-dtd))
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
309 (xml-skip-dtd))
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
310 (skip-syntax-forward " ")
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
311 (if dtd
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
312 (cons dtd (xml-parse-tag nil xml-ns))
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
313 (xml-parse-tag nil xml-ns))))
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
314 ;; skip comments
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
315 ((looking-at "<!--")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
316 (search-forward "-->")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
317 nil)
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
318 ;; end tag
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
319 ((looking-at "</")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
320 '())
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
321 ;; opening tag
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
322 ((looking-at "<\\([^/>[:space:]]+\\)")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
323 (goto-char (match-end 1))
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
324
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
325 ;; Parse this node
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
326 (let* ((node-name (match-string 1))
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
327 ;; Parse the attribute list.
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
328 (attrs (xml-parse-attlist xml-ns))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
329 children pos)
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
330
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
331 ;; add the xmlns:* attrs to our cache
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
332 (when (consp xml-ns)
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
333 (dolist (attr attrs)
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
334 (when (and (consp (car attr))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
335 (eq :http://www.w3.org/2000/xmlns/
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
336 (caar attr)))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
337 (push (cons (cdar attr) (intern (concat ":" (cdr attr))))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
338 xml-ns))))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
339
54936
9204ad91984c (xml-parse-tag): Avoid overwriting node-name.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54877
diff changeset
340 (setq children (list attrs (xml-maybe-do-ns node-name "" xml-ns)))
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
341
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
342 ;; is this an empty element ?
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
343 (if (looking-at "/>")
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
344 (progn
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
345 (forward-char 2)
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
346 (nreverse children))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
347
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
348 ;; is this a valid start tag ?
40030
7507bd185307 (xml-parse-tag): Use eq on char-after's return value.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 39407
diff changeset
349 (if (eq (char-after) ?>)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
350 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
351 (forward-char 1)
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
352 ;; Now check that we have the right end-tag. Note that this
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
353 ;; one might contain spaces after the tag name
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
354 (let ((end (concat "</" node-name "\\s-*>")))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
355 (while (not (looking-at end))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
356 (cond
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
357 ((looking-at "</")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
358 (error "XML: Invalid end tag (expecting %s) at pos %d"
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
359 node-name (point)))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
360 ((= (char-after) ?<)
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
361 (let ((tag (xml-parse-tag nil xml-ns)))
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
362 (when tag
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
363 (push tag children))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
364 (t
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
365 (setq pos (point))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
366 (search-forward "<")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
367 (forward-char -1)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
368 (let ((string (buffer-substring pos (point)))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
369 (pos 0))
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
370
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
371 ;; Clean up the string. As per XML
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
372 ;; specifications, the XML processor should
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
373 ;; always pass the whole string to the
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
374 ;; application. But \r's should be replaced:
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
375 ;; http://www.w3.org/TR/2000/REC-xml-20001006#sec-line-ends
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
376 (while (string-match "\r\n?" string pos)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
377 (setq string (replace-match "\n" t t string))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
378 (setq pos (1+ (match-beginning 0))))
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
379
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
380 (setq string (xml-substitute-special string))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
381 (setq children
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
382 (if (stringp (car children))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
383 ;; The two strings were separated by a comment.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
384 (cons (concat (car children) string)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
385 (cdr children))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
386 (cons string children))))))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
387
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
388 (goto-char (match-end 0))
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
389 (nreverse children))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
390 ;; This was an invalid start tag
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
391 (error "XML: Invalid attribute list")))))
51930
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
392 (t ;; This is not a tag.
608552c82ffc (xml-parse-tag): Namespace support.
Juanma Barranquero <lekktu@gmail.com>
parents: 51697
diff changeset
393 (error "XML: Invalid character")))))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
394
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
395 (defun xml-parse-attlist (&optional xml-ns)
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
396 "Return the attribute-list after point.
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
397 Leave point at the first non-blank character after the tag."
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
398 (let ((attlist ())
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
399 end-pos name)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
400 (skip-syntax-forward " ")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
401 (while (looking-at (eval-when-compile
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
402 (concat "\\(" xml-name-regexp "\\)\\s-*=\\s-*")))
54877
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
403 (setq end-pos (match-end 0))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
404 (setq name (xml-maybe-do-ns (match-string 1) nil xml-ns))
1bf7ef48f54f (xml-maybe-do-ns): New function to handle namespace
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54243
diff changeset
405 (goto-char end-pos)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
406
50144
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
407 ;; See also: http://www.w3.org/TR/2000/REC-xml-20001006#AVNormalize
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
408
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
409 ;; Do we have a string between quotes (or double-quotes),
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
410 ;; or a simple word ?
50144
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
411 (if (looking-at "\"\\([^\"]*\\)\"")
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
412 (setq end-pos (match-end 0))
50210
575aa6820adc (xml-parse-attlist): typo in attribute parsing.
Juanma Barranquero <lekktu@gmail.com>
parents: 50144
diff changeset
413 (if (looking-at "'\\([^']*\\)'")
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
414 (setq end-pos (match-end 0))
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
415 (error "XML: Attribute values must be given between quotes")))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
416
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
417 ;; Each attribute must be unique within a given element
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
418 (if (assoc name attlist)
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
419 (error "XML: each attribute must be unique within an element"))
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
420
50144
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
421 ;; Multiple whitespace characters should be replaced with a single one
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
422 ;; in the attributes
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
423 (let ((string (match-string 1))
50144
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
424 (pos 0))
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
425 (replace-regexp-in-string "\\s-\\{2,\\}" " " string)
50144
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
426 (push (cons name (xml-substitute-special string)) attlist))
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
427
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
428 (goto-char end-pos)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
429 (skip-syntax-forward " "))
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
430 (nreverse attlist)))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
431
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
432 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
433 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
434 ;;** The DTD (document type declaration)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
435 ;;** The following functions know how to skip or parse the DTD of
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
436 ;;** a document
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
437 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
438 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
439
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
440 ;; Fixme: This fails at least if the DTD contains conditional sections.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
441
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
442 (defun xml-skip-dtd ()
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
443 "Skip the DTD at point.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
444 This follows the rule [28] in the XML specifications."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
445 (forward-char (length "<!DOCTYPE"))
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
446 (if (looking-at "\\s-*>")
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
447 (error "XML: invalid DTD (excepting name of the document)"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
448 (condition-case nil
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
449 (progn
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
450 (forward-sexp)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
451 (skip-syntax-forward " ")
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
452 (if (looking-at "\\[")
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
453 (re-search-forward "]\\s-*>")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
454 (search-forward ">")))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
455 (error (error "XML: No end to the DTD"))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
456
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
457 (defun xml-parse-dtd ()
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
458 "Parse the DTD at point."
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
459 (forward-char (eval-when-compile (length "<!DOCTYPE")))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
460 (skip-syntax-forward " ")
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
461 (if (looking-at ">")
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
462 (error "XML: invalid DTD (excepting name of the document)"))
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
463
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
464 ;; Get the name of the document
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
465 (looking-at xml-name-regexp)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
466 (let ((dtd (list (match-string 0) 'dtd))
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
467 type element end-pos)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
468 (goto-char (match-end 0))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
469
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
470 (skip-syntax-forward " ")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
471 ;; XML [75]
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
472 (cond ((looking-at "PUBLIC\\s-+")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
473 (goto-char (match-end 0))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
474 (unless (or (re-search-forward
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
475 "\\=\"\\([[:space:][:alnum:]-'()+,./:=?;!*#@$_%]*\\)\""
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
476 nil t)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
477 (re-search-forward
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
478 "\\='\\([[:space:][:alnum:]-()+,./:=?;!*#@$_%]*\\)'"
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
479 nil t))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
480 (error "XML: missing public id"))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
481 (let ((pubid (match-string 1)))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
482 (unless (or (re-search-forward "\\='\\([^']*\\)'" nil t)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
483 (re-search-forward "\\=\"\\([^\"]*\\)\"" nil t))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
484 (error "XML: missing system id"))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
485 (push (list pubid (match-string 1) 'public) dtd)))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
486 ((looking-at "SYSTEM\\s-+")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
487 (goto-char (match-end 0))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
488 (unless (or (re-search-forward "\\='\\([^']*\\)'" nil t)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
489 (re-search-forward "\\=\"\\([^\"]*\\)\"" nil t))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
490 (error "XML: missing system id"))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
491 (push (list (match-string 1) 'system) dtd)))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
492 (skip-syntax-forward " ")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
493 (if (eq ?> (char-after))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
494 (forward-char)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
495 (skip-syntax-forward " ")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
496 (if (not (eq (char-after) ?\[))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
497 (error "XML: bad DTD")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
498 (forward-char)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
499 ;; Parse the rest of the DTD
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
500 ;; Fixme: Deal with ENTITY, ATTLIST, NOTATION, PIs.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
501 (while (not (looking-at "\\s-*\\]"))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
502 (skip-syntax-forward " ")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
503 (cond
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
504
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
505 ;; Translation of rule [45] of XML specifications
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
506 ((looking-at
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
507 "<!ELEMENT\\s-+\\([[:alnum:].%;]+\\)\\s-+\\([^>]+\\)>")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
508
52975
6958c2be0aa9 Allow comments following the top-level element.
Eli Zaretskii <eliz@gnu.org>
parents: 52401
diff changeset
509 (setq element (match-string 1)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
510 type (match-string-no-properties 2))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
511 (setq end-pos (match-end 0))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
512
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
513 ;; Translation of rule [46] of XML specifications
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
514 (cond
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
515 ((string-match "^EMPTY[ \t\n\r]*$" type) ;; empty declaration
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
516 (setq type 'empty))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
517 ((string-match "^ANY[ \t\n\r]*$" type) ;; any type of contents
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
518 (setq type 'any))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
519 ((string-match "^(\\(.*\\))[ \t\n\r]*$" type) ;; children ([47])
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
520 (setq type (xml-parse-elem-type (match-string 1 type))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
521 ((string-match "^%[^;]+;[ \t\n\r]*$" type) ;; substitution
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
522 nil)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
523 (t
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
524 (error "XML: Invalid element type in the DTD")))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
525
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
526 ;; rule [45]: the element declaration must be unique
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
527 (if (assoc element dtd)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
528 (error "XML: element declarations must be unique in a DTD (<%s>)"
53011
45bd3ad34572 (xml-parse-dtd): Fix misplaced paren.
Andreas Schwab <schwab@suse.de>
parents: 52975
diff changeset
529 element))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
530
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
531 ;; Store the element in the DTD
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
532 (push (list element type) dtd)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
533 (goto-char end-pos))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
534 ((looking-at "<!--")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
535 (search-forward "-->"))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
536
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
537 (t
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
538 (error "XML: Invalid DTD item")))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
539
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
540 ;; Skip the end of the DTD
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
541 (search-forward ">"))))
53011
45bd3ad34572 (xml-parse-dtd): Fix misplaced paren.
Andreas Schwab <schwab@suse.de>
parents: 52975
diff changeset
542 (nreverse dtd)))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
543
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
544 (defun xml-parse-elem-type (string)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
545 "Convert element type STRING into a Lisp structure."
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
546
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
547 (let (elem modifier)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
548 (if (string-match "(\\([^)]+\\))\\([+*?]?\\)" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
549 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
550 (setq elem (match-string 1 string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
551 modifier (match-string 2 string))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
552 (if (string-match "|" elem)
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
553 (setq elem (cons 'choice
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
554 (mapcar 'xml-parse-elem-type
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
555 (split-string elem "|"))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
556 (if (string-match "," elem)
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
557 (setq elem (cons 'seq
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
558 (mapcar 'xml-parse-elem-type
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
559 (split-string elem ",")))))))
50144
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
560 (if (string-match "[ \t\n\r]*\\([^+*?]+\\)\\([+*?]?\\)" string)
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
561 (setq elem (match-string 1 string)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
562 modifier (match-string 2 string))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
563
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
564 (if (and (stringp elem) (string= elem "#PCDATA"))
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
565 (setq elem 'pcdata))
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
566
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
567 (cond
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
568 ((string= modifier "+")
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
569 (list '+ elem))
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
570 ((string= modifier "*")
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
571 (list '* elem))
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
572 ((string= modifier "?")
49787
6269b5c10aec (xml-parse-elem-type): Fix use of character constant.
Juanma Barranquero <lekktu@gmail.com>
parents: 49133
diff changeset
573 (list '\? elem))
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
574 (t
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
575 elem))))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
576
50144
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
577 ;;*******************************************************************
ff1b1d15e1f2 (xml-ucs-to-string): New function to convert Unicode codepoints to strings.
Juanma Barranquero <lekktu@gmail.com>
parents: 50081
diff changeset
578 ;;**
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
579 ;;** Substituting special XML sequences
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
580 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
581 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
582
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
583 (eval-when-compile
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
584 (defvar str)) ; dynamic from replace-regexp-in-string
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
585
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
586 ;; Fixme: Take declared entities from the DTD when they're available.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
587 (defun xml-substitute-entity (match)
54937
42293f0612cc Doc fixes.
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 54936
diff changeset
588 "Subroutine of `xml-substitute-special'."
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
589 (save-match-data
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
590 (let ((match1 (match-string 1 str)))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
591 (cond ((string= match1 "lt") "<")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
592 ((string= match1 "gt") ">")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
593 ((string= match1 "apos") "'")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
594 ((string= match1 "quot") "\"")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
595 ((string= match1 "amp") "&")
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
596 ((and (string-match "#\\([0-9]+\\)" match1)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
597 (let ((c (decode-char
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
598 'ucs
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
599 (string-to-number (match-string 1 match1)))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
600 (if c (string c))))) ; else unrepresentable
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
601 ((and (string-match "#x\\([[:xdigit:]]+\\)" match1)
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
602 (let ((c (decode-char
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
603 'ucs
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
604 (string-to-number (match-string 1 match1) 16))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
605 (if c (string c)))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
606 ;; Default to asis. Arguably, unrepresentable code points
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
607 ;; might be best replaced with U+FFFD.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
608 (t match)))))
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
609
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
610 (defun xml-substitute-special (string)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
611 "Return STRING, after subsituting entity references."
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
612 ;; This originally made repeated passes through the string from the
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
613 ;; beginning, which isn't correct, since then either "&amp;amp;" or
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
614 ;; "&#38;amp;" won't DTRT.
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
615 (replace-regexp-in-string "&\\([^;]+\\);"
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
616 #'xml-substitute-entity string t t))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
617
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
618 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
619 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
620 ;;** Printing a tree.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
621 ;;** This function is intended mainly for debugging purposes.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
622 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
623 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
624
55253
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
625 (defun xml-debug-print (xml &optional indent-string)
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
626 "Outputs the XML in the current buffer.
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
627 XML can be a tree or a list of nodes.
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
628 The first line is indented with the optional INDENT-STRING."
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
629 (setq indent-string (or indent-string ""))
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
630 (dolist (node xml)
55253
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
631 (xml-debug-print-internal node indent-string)))
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
632
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
633 (defalias 'xml-print 'xml-debug-print)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
634
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
635 (defun xml-debug-print-internal (xml indent-string)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
636 "Outputs the XML tree in the current buffer.
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
637 The first line is indented with INDENT-STRING."
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
638 (let ((tree xml)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
639 attlist)
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
640 (insert indent-string ?< (symbol-name (xml-node-name tree)))
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
641
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
642 ;; output the attribute list
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
643 (setq attlist (xml-node-attributes tree))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
644 (while attlist
51102
d604b76d3bbd Doc fixes.
Dave Love <fx@gnu.org>
parents: 50210
diff changeset
645 (insert ?\ (symbol-name (caar attlist)) "=\"" (cdar attlist) ?\")
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
646 (setq attlist (cdr attlist)))
49036
466922eb2b8d (xml-substitute-special): Move "&amp;" -> "&" last.
Thien-Thi Nguyen <ttn@gnuvola.org>
parents: 48869
diff changeset
647
42031
54db4085a7df Use setq rather than (set 'foo bar).
Stefan Monnier <monnier@iro.umontreal.ca>
parents: 40030
diff changeset
648 (setq tree (xml-node-children tree))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
649
55253
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
650 (if (null tree)
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
651 (insert ?/ ?>)
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
652 (insert ?>)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
653
55253
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
654 ;; output the children
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
655 (dolist (node tree)
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
656 (cond
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
657 ((listp node)
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
658 (insert ?\n)
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
659 (xml-debug-print-internal node (concat indent-string " ")))
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
660 ((stringp node) (insert node))
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
661 (t
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
662 (error "Invalid XML tree"))))
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
663
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
664 (when (not (and (null (cdr tree))
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
665 (stringp (car tree))))
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
666 (insert ?\n indent-string))
d33879ad154a (xml-debug-print-internal): Don't add newline and
Alex Schroeder <alex@gnu.org>
parents: 54937
diff changeset
667 (insert ?< ?/ (symbol-name (xml-node-name xml)) ?>))))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
668
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
669 (provide 'xml)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
670
52401
695cf19ef79e Add arch taglines
Miles Bader <miles@gnu.org>
parents: 51930
diff changeset
671 ;;; arch-tag: 5864b283-5a68-4b59-a20d-36a72b353b9b
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
672 ;;; xml.el ends here