annotate lisp/xml.el @ 40030:7507bd185307

(xml-parse-tag): Use eq on char-after's return value.
author Stefan Monnier <monnier@iro.umontreal.ca>
date Thu, 18 Oct 2001 20:22:53 +0000
parents e6b056005c49
children 54db4085a7df
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
37958
d1fdbba91c71 (xml-parse-tag): The document may contain invalid characters.
Gerd Moellmann <gerd@gnu.org>
parents: 34825
diff changeset
3 ;; Copyright (C) 2000, 2001 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>
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
6 ;; Maintainer: Emmanuel Briot <briot@gnat.com>
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
7 ;; Keywords: xml
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
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
28 ;; This file contains a full XML parser. It parses a file, and returns a list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
29 ;; that can be used internally by any other lisp file.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
30 ;; See some example in todo.el
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
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
34 ;; It does not parse the DTD, if present in the XML file, but knows how to
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
35 ;; ignore it. The XML file is assumed to be well-formed. In case of error, the
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
36 ;; parsing stops and the XML file is shown where the parsing stopped.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
37 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
38 ;; It also knows how to ignore comments, as well as the special ?xml? tag
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
39 ;; in the XML file.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
40 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
41 ;; 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
42 ;; <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
43 ;; <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
44 ;; <node3 attr5="name5" attr6="name6">value3</node3>
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
45 ;; </node1>
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
46 ;; Of course, the name of the nodes and attributes can be anything. There can
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
47 ;; 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
48 ;; below the nodes.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
49 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
50 ;; 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
51
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
52 ;;; LIST FORMAT
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
53
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
54 ;; The functions `xml-parse-file' and `xml-parse-tag' return a list with
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
55 ;; the following format:
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
56 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
57 ;; xml-list ::= (node node ...)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
58 ;; node ::= (tag_name attribute-list . child_node_list)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
59 ;; child_node_list ::= child_node child_node ...
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
60 ;; child_node ::= node | string
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
61 ;; tag_name ::= string
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
62 ;; attribute_list ::= (("attribute" . "value") ("attribute" . "value") ...)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
63 ;; | nil
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
64 ;; string ::= "..."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
65 ;;
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
66 ;; Some macros are provided to ease the parsing of this list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
67
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
68 ;;; Code:
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
69
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
70 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
71 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
72 ;;** Macros to parse the list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
73 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
74 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
75
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
76 (defmacro xml-node-name (node)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
77 "Return the tag associated with NODE.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
78 The tag is a lower-case symbol."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
79 (list 'car node))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
80
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
81 (defmacro xml-node-attributes (node)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
82 "Return the list of attributes of NODE.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
83 The list can be nil."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
84 (list 'nth 1 node))
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 (defmacro xml-node-children (node)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
87 "Return the list of children of NODE.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
88 This is a list of nodes, and it can be nil."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
89 (list 'cddr node))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
90
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
91 (defun xml-get-children (node child-name)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
92 "Return the children of NODE whose tag is CHILD-NAME.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
93 CHILD-NAME should be a lower case symbol."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
94 (let ((children (xml-node-children node))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
95 match)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
96 (while children
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
97 (if (car children)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
98 (if (equal (xml-node-name (car children)) child-name)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
99 (set 'match (append match (list (car children))))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
100 (set 'children (cdr children)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
101 match))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
102
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
103 (defun xml-get-attribute (node attribute)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
104 "Get from NODE the value of ATTRIBUTE.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
105 An empty string is returned if the attribute was not found."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
106 (if (xml-node-attributes node)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
107 (let ((value (assoc attribute (xml-node-attributes node))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
108 (if value
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
109 (cdr value)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
110 ""))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
111 ""))
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 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
114 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
115 ;;** Creating the list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
116 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
117 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
118
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
119 (defun xml-parse-file (file &optional parse-dtd)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
120 "Parse the well-formed XML FILE.
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
121 If FILE is already edited, this will keep the buffer alive.
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
122 Returns the top node with all its children.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
123 If PARSE-DTD is non-nil, the DTD is parsed rather than skipped."
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
124 (let ((keep))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
125 (if (get-file-buffer file)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
126 (progn
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
127 (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
128 (setq keep (point)))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
129 (find-file file))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
130
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
131 (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
132 (point-max)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
133 (current-buffer)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
134 parse-dtd)))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
135 (if keep
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
136 (goto-char keep)
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
137 (kill-buffer (current-buffer)))
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
138 xml)))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
139
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
140 (defun xml-parse-region (beg end &optional buffer parse-dtd)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
141 "Parse the region from BEG to END in BUFFER.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
142 If BUFFER is nil, it defaults to the current buffer.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
143 Returns the XML list for the region, or raises an error if the region
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
144 is not a well-formed XML file.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
145 If PARSE-DTD is non-nil, the DTD is parsed rather than skipped,
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
146 and returned as the first element of the list"
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
147 (let (xml result dtd)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
148 (save-excursion
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
149 (if buffer
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
150 (set-buffer buffer))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
151 (goto-char beg)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
152 (while (< (point) end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
153 (if (search-forward "<" end t)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
154 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
155 (forward-char -1)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
156 (if (null xml)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
157 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
158 (set 'result (xml-parse-tag end parse-dtd))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
159 (cond
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
160 ((listp (car result))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
161 (set 'dtd (car result))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
162 (add-to-list 'xml (cdr result)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
163 (t
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
164 (add-to-list 'xml result))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
165
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
166 ;; translation of rule [1] of XML specifications
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
167 (error "XML files can have only one toplevel tag")))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
168 (goto-char end)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
169 (if parse-dtd
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
170 (cons dtd (reverse xml))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
171 (reverse xml)))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
172
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
173
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
174 (defun xml-parse-tag (end &optional parse-dtd)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
175 "Parse the tag that is just in front of point.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
176 The end tag must be found before the position END in the current buffer.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
177 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
178 returned as the first element in the list.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
179 Returns one of:
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
180 - a list : the matching node
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
181 - nil : the point is not looking at a tag.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
182 - a cons cell: the first element is the DTD, the second is the node"
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
183 (cond
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
184 ;; Processing instructions (like the <?xml version="1.0"?> tag at the
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
185 ;; beginning of a document)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
186 ((looking-at "<\\?")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
187 (search-forward "?>" end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
188 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
189 (xml-parse-tag end))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
190 ;; Character data (CDATA) sections, in which no tag should be interpreted
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
191 ((looking-at "<!\\[CDATA\\[")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
192 (let ((pos (match-end 0)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
193 (unless (search-forward "]]>" end t)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
194 (error "CDATA section does not end anywhere in the document"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
195 (buffer-substring-no-properties pos (match-beginning 0))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
196 ;; DTD for the document
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
197 ((looking-at "<!DOCTYPE")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
198 (let (dtd)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
199 (if parse-dtd
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
200 (set 'dtd (xml-parse-dtd end))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
201 (xml-skip-dtd end))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
202 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
203 (if dtd
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
204 (cons dtd (xml-parse-tag end))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
205 (xml-parse-tag end))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
206 ;; skip comments
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
207 ((looking-at "<!--")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
208 (search-forward "-->" end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
209 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
210 (xml-parse-tag end))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
211 ;; end tag
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
212 ((looking-at "</")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
213 '())
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
214 ;; opening tag
33977
fd338013d333 (xml-parse-tag): Fix finding opening tag. A tag name
Kenichi Handa <handa@m17n.org>
parents: 30779
diff changeset
215 ((looking-at "<\\([^/> \t\n]+\\)")
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
216 (let* ((node-name (match-string 1))
30779
aa097d8d4f1a (xml-parse-tag, xml-parse-attlist): Do not downcase
Gerd Moellmann <gerd@gnu.org>
parents: 30329
diff changeset
217 (children (list (intern node-name)))
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
218 (case-fold-search nil) ;; XML is case-sensitive
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
219 pos)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
220 (goto-char (match-end 1))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
221
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
222 ;; parses the attribute list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
223 (set 'children (append children (list (xml-parse-attlist end))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
224
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
225 ;; is this an empty element ?
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
226 (if (looking-at "/>")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
227 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
228 (forward-char 2)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
229 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
230 (append children '("")))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
231
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
232 ;; 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
233 (if (eq (char-after) ?>)
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
234 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
235 (forward-char 1)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
236 (skip-chars-forward " \t\n")
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
237 ;; Now check that we have the right end-tag. Note that this one might
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
238 ;; contain spaces after the tag name
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
239 (while (not (looking-at (concat "</" node-name "[ \t\n]*>")))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
240 (cond
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
241 ((looking-at "</")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
242 (error (concat
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
243 "XML: invalid syntax -- invalid end tag (expecting "
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
244 node-name
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
245 ") at pos " (number-to-string (point)))))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
246 ((= (char-after) ?<)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
247 (set 'children (append children (list (xml-parse-tag end)))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
248 (t
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
249 (set 'pos (point))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
250 (search-forward "<" end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
251 (forward-char -1)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
252 (let ((string (buffer-substring-no-properties pos (point)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
253 (pos 0))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
254
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
255 ;; Clean up the string (no newline characters)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
256 ;; Not done, since as per XML specifications, the XML processor
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
257 ;; should always pass the whole string to the application.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
258 ;; (while (string-match "\\s +" string pos)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
259 ;; (set 'string (replace-match " " t t string))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
260 ;; (set 'pos (1+ (match-beginning 0))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
261
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
262 (set 'children (append children
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
263 (list (xml-substitute-special string))))))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
264 (goto-char (match-end 0))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
265 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
266 (if (> (point) end)
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
267 (error "XML: End tag for %s not found before end of region"
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
268 node-name))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
269 children
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
270 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
271
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
272 ;; This was an invalid start tag
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
273 (error "XML: Invalid attribute list")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
274 ))))
37958
d1fdbba91c71 (xml-parse-tag): The document may contain invalid characters.
Gerd Moellmann <gerd@gnu.org>
parents: 34825
diff changeset
275 (t ;; This is not a tag.
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
276 (error "XML: Invalid character"))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
277 ))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
278
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
279 (defun xml-parse-attlist (end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
280 "Return the attribute-list that point is looking at.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
281 The search for attributes end at the position END in the current buffer.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
282 Leaves the point on the first non-blank character after the tag."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
283 (let ((attlist '())
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
284 name)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
285 (skip-chars-forward " \t\n")
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
286 (while (looking-at "\\([a-zA-Z_:][-a-zA-Z0-9._:]*\\)[ \t\n]*=[ \t\n]*")
30779
aa097d8d4f1a (xml-parse-tag, xml-parse-attlist): Do not downcase
Gerd Moellmann <gerd@gnu.org>
parents: 30329
diff changeset
287 (set 'name (intern (match-string 1)))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
288 (goto-char (match-end 0))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
289
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
290 ;; Do we have a string between quotes (or double-quotes),
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
291 ;; or a simple word ?
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
292 (unless (looking-at "\"\\([^\"]+\\)\"")
39407
e6b056005c49 (xml-parse-attlist): Quotes around attributes must be the
Gerd Moellmann <gerd@gnu.org>
parents: 38409
diff changeset
293 (unless (looking-at "'\\([^']+\\)'")
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
294 (error "XML: Attribute values must be given between quotes")))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
295
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
296 ;; Each attribute must be unique within a given element
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
297 (if (assoc name attlist)
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
298 (error "XML: each attribute must be unique within an element"))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
299
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
300 (set 'attlist (append attlist
34825
2cad4cde52bd (top level comment): Updated to reflect the fact that
Gerd Moellmann <gerd@gnu.org>
parents: 33977
diff changeset
301 (list (cons name (match-string-no-properties 1)))))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
302 (goto-char (match-end 0))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
303 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
304 (if (> (point) end)
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
305 (error "XML: end of attribute list not found before end of region"))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
306 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
307 attlist
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
308 ))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
309
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
310 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
311 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
312 ;;** The DTD (document type declaration)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
313 ;;** The following functions know how to skip or parse the DTD of
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
314 ;;** a document
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
315 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
316 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
317
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
318 (defun xml-skip-dtd (end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
319 "Skip the DTD that point is looking at.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
320 The DTD must end before the position END in the current buffer.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
321 The point must be just before the starting tag of the DTD.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
322 This follows the rule [28] in the XML specifications."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
323 (forward-char (length "<!DOCTYPE"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
324 (if (looking-at "[ \t\n]*>")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
325 (error "XML: invalid DTD (excepting name of the document)"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
326 (condition-case nil
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
327 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
328 (forward-word 1) ;; name of the document
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
329 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
330 (if (looking-at "\\[")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
331 (re-search-forward "\\][ \t\n]*>" end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
332 (search-forward ">" end)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
333 (error (error "XML: No end to the DTD"))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
334
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
335 (defun xml-parse-dtd (end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
336 "Parse the DTD that point is looking at.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
337 The DTD must end before the position END in the current buffer."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
338 (let (dtd type element end-pos)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
339 (forward-char (length "<!DOCTYPE"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
340 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
341 (if (looking-at ">")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
342 (error "XML: invalid DTD (excepting name of the document)"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
343
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
344 ;; Get the name of the document
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
345 (looking-at "\\sw+")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
346 (set 'dtd (list 'dtd (match-string-no-properties 0)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
347 (goto-char (match-end 0))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
348
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
349 (skip-chars-forward " \t\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
350
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
351 ;; External DTDs => don't know how to handle them yet
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
352 (if (looking-at "SYSTEM")
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
353 (error "XML: Don't know how to handle external DTDs"))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
354
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
355 (if (not (= (char-after) ?\[))
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
356 (error "XML: Unknown declaration in the DTD"))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
357
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
358 ;; Parse the rest of the DTD
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
359 (forward-char 1)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
360 (while (and (not (looking-at "[ \t\n]*\\]"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
361 (<= (point) end))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
362 (cond
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
363
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
364 ;; Translation of rule [45] of XML specifications
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
365 ((looking-at
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
366 "[\t \n]*<!ELEMENT[ \t\n]+\\([a-zA-Z0-9.%;]+\\)[ \t\n]+\\([^>]+\\)>")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
367
30779
aa097d8d4f1a (xml-parse-tag, xml-parse-attlist): Do not downcase
Gerd Moellmann <gerd@gnu.org>
parents: 30329
diff changeset
368 (setq element (intern (match-string-no-properties 1))
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
369 type (match-string-no-properties 2))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
370 (set 'end-pos (match-end 0))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
371
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
372 ;; Translation of rule [46] of XML specifications
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
373 (cond
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
374 ((string-match "^EMPTY[ \t\n]*$" type) ;; empty declaration
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
375 (set 'type 'empty))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
376 ((string-match "^ANY[ \t\n]*$" type) ;; any type of contents
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
377 (set 'type 'any))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
378 ((string-match "^(\\(.*\\))[ \t\n]*$" type) ;; children ([47])
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
379 (set 'type (xml-parse-elem-type (match-string-no-properties 1 type))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
380 ((string-match "^%[^;]+;[ \t\n]*$" type) ;; substitution
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
381 nil)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
382 (t
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
383 (error "XML: Invalid element type in the DTD")))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
384
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
385 ;; rule [45]: the element declaration must be unique
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
386 (if (assoc element dtd)
38409
153f1b1f2efd Emacs lisp coding convention fixes.
Pavel Janík <Pavel@Janik.cz>
parents: 37958
diff changeset
387 (error "XML: elements declaration must be unique in a DTD (<%s>)"
30329
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
388 (symbol-name element)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
389
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
390 ;; Store the element in the DTD
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
391 (set 'dtd (append dtd (list (list element type))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
392 (goto-char end-pos)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
393 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
394
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
395
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
396 (t
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
397 (error "XML: Invalid DTD item"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
398 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
399 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
400
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
401 ;; Skip the end of the DTD
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
402 (search-forward ">" end)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
403 dtd
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
404 ))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
405
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
406
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
407 (defun xml-parse-elem-type (string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
408 "Convert a STRING for an element type into an elisp structure."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
409
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
410 (let (elem modifier)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
411 (if (string-match "(\\([^)]+\\))\\([+*?]?\\)" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
412 (progn
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
413 (setq elem (match-string 1 string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
414 modifier (match-string 2 string))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
415 (if (string-match "|" elem)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
416 (set 'elem (append '(choice)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
417 (mapcar 'xml-parse-elem-type
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
418 (split-string elem "|"))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
419 (if (string-match "," elem)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
420 (set 'elem (append '(seq)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
421 (mapcar 'xml-parse-elem-type
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
422 (split-string elem ","))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
423 )))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
424 (if (string-match "[ \t\n]*\\([^+*?]+\\)\\([+*?]?\\)" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
425 (setq elem (match-string 1 string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
426 modifier (match-string 2 string))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
427
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
428 (if (and (stringp elem)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
429 (string= elem "#PCDATA"))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
430 (set 'elem 'pcdata))
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 (cond
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
433 ((string= modifier "+")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
434 (list '+ elem))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
435 ((string= modifier "*")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
436 (list '* elem))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
437 ((string= modifier "?")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
438 (list '? elem))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
439 (t
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
440 elem))))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
441
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
442
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
443 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
444 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
445 ;;** Substituting special XML sequences
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
446 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
447 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
448
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
449 (defun xml-substitute-special (string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
450 "Return STRING, after subsituting special XML sequences."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
451 (while (string-match "&amp;" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
452 (set 'string (replace-match "&" t nil string)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
453 (while (string-match "&lt;" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
454 (set 'string (replace-match "<" t nil string)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
455 (while (string-match "&gt;" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
456 (set 'string (replace-match ">" t nil string)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
457 (while (string-match "&apos;" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
458 (set 'string (replace-match "'" t nil string)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
459 (while (string-match "&quot;" string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
460 (set 'string (replace-match "\"" t nil string)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
461 string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
462
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
463 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
464 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
465 ;;** Printing a tree.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
466 ;;** This function is intended mainly for debugging purposes.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
467 ;;**
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
468 ;;*******************************************************************
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
469
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
470 (defun xml-debug-print (xml)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
471 (while xml
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
472 (xml-debug-print-internal (car xml) "")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
473 (set 'xml (cdr xml)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
474 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
475
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
476 (defun xml-debug-print-internal (xml &optional indent-string)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
477 "Outputs the XML tree in the current buffer.
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
478 The first line indented with INDENT-STRING."
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
479 (let ((tree xml)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
480 attlist)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
481 (unless indent-string
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
482 (set 'indent-string ""))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
483
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
484 (insert indent-string "<" (symbol-name (xml-node-name tree)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
485
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
486 ;; output the attribute list
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
487 (set 'attlist (xml-node-attributes tree))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
488 (while attlist
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
489 (insert " ")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
490 (insert (symbol-name (caar attlist)) "=\"" (cdar attlist) "\"")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
491 (set 'attlist (cdr attlist)))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
492
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
493 (insert ">")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
494
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
495 (set 'tree (xml-node-children tree))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
496
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
497 ;; output the children
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
498 (while tree
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
499 (cond
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
500 ((listp (car tree))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
501 (insert "\n")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
502 (xml-debug-print-internal (car tree) (concat indent-string " "))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
503 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
504 ((stringp (car tree))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
505 (insert (car tree))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
506 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
507 (t
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
508 (error "Invalid XML tree")))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
509 (set 'tree (cdr tree))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
510 )
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
511
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
512 (insert "\n" indent-string
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
513 "</" (symbol-name (xml-node-name xml)) ">")
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
514 ))
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
515
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
516 (provide 'xml)
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
517
1ea701655cf8 *** empty log message ***
Gerd Moellmann <gerd@gnu.org>
parents:
diff changeset
518 ;;; xml.el ends here