1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* This file is part of the Ariadne Component Library. |
5
|
|
|
* |
6
|
|
|
* (c) Muze <[email protected]> |
7
|
|
|
* |
8
|
|
|
* For the full copyright and license information, please view the LICENSE |
9
|
|
|
* file that was distributed with this source code. |
10
|
|
|
*/ |
11
|
|
|
|
12
|
|
|
namespace arc; |
13
|
|
|
|
14
|
|
|
/** |
15
|
|
|
* Any method statically called on this class |
16
|
|
|
* will reroute the call to the XML writer instance at |
17
|
|
|
* \arc\xml::$writer. Except for the methods: |
18
|
|
|
* parse, css2XPath, name, value, attribute, comment, cdata and preamble |
19
|
|
|
* If you need those call the Writer instance directly |
20
|
|
|
*/ |
21
|
|
|
class xml |
22
|
|
|
{ |
23
|
|
|
/** |
24
|
|
|
* @var xml\Writer The writer instance to use by default |
25
|
|
|
*/ |
26
|
|
|
public static $writer = null; |
27
|
|
|
|
28
|
6 |
|
public static function __callStatic( $name, $args ) |
29
|
|
|
{ |
30
|
6 |
|
if ( !isset(static::$writer) ) { |
31
|
2 |
|
static::$writer = new xml\Writer(); |
32
|
1 |
|
} |
33
|
6 |
|
return call_user_func_array( [ static::$writer, $name ], $args ); |
34
|
|
|
} |
35
|
|
|
|
36
|
|
|
/** |
37
|
|
|
* This parses an XML string and returns a Proxy |
38
|
|
|
* @param string|Proxy $xml |
39
|
|
|
* @return Proxy |
40
|
|
|
* @throws \arc\UnknownError |
41
|
|
|
*/ |
42
|
17 |
|
public static function parse( $xml=null, $encoding = null ) |
43
|
|
|
{ |
44
|
16 |
|
$parser = new xml\Parser(); |
45
|
17 |
|
return $parser->parse( $xml, $encoding ); |
46
|
|
|
} |
47
|
|
|
|
48
|
|
|
/** |
49
|
|
|
* This method turns a single CSS 2 selector into an XPath query |
50
|
|
|
* @param string $cssSelector |
51
|
|
|
* @return string |
52
|
|
|
*/ |
53
|
8 |
|
public static function css2XPath( $cssSelector ) |
54
|
1 |
|
{ |
55
|
8 |
|
$tag = '(?:\w+\|)?\w+'; |
56
|
|
|
/* based on work by Tijs Verkoyen - http://blog.verkoyen.eu/blog/p/detail/css-selector-to-xpath-query/ */ |
57
|
|
|
$translateList = array( |
58
|
|
|
// E F: Matches any F element that is a descendant of an E element |
59
|
8 |
|
'/('.$tag.')\s+(?=(?:[^"]*"[^"]*")*[^"]*$)('.$tag.')/' |
60
|
8 |
|
=> '\1//\2', |
61
|
|
|
// E > F: Matches any F element that is a child of an element E |
62
|
8 |
|
'/('.$tag.')\s*>\s*('.$tag.')/' |
63
|
8 |
|
=> '\1/\2', |
64
|
|
|
// E:first-child: Matches element E when E is the first child of its parent |
65
|
8 |
|
'/('.$tag.'|(\w+\|)?\*):first-child/' |
66
|
8 |
|
=> '*[1]/self::\1', |
67
|
|
|
// Matches E:checked, E:disabled or E:selected (and just for scrutinizer: this is not code!) |
68
|
8 |
|
'/('.$tag.'|(\w+\|)?\*):(checked|disabled|selected)/' |
69
|
8 |
|
=> '\1 [ @\3 ]', |
70
|
|
|
// E + F: Matches any F element immediately preceded by an element |
71
|
8 |
|
'/('.$tag.')\s*\+\s*('.$tag.')/' |
72
|
8 |
|
=> '\1/following-sibling::*[1]/self::\2', |
73
|
|
|
// E ~ F: Matches any F element preceded by an element |
74
|
8 |
|
'/('.$tag.')\s*\~\s*('.$tag.')/' |
75
|
8 |
|
=> '\1/following-sibling::*/self::\2', |
76
|
|
|
// E[foo]: Matches any E element with the "foo" attribute set (whatever the value) |
77
|
8 |
|
'/('.$tag.')\[([\w\-]+)]/' |
78
|
8 |
|
=> '\1 [ @\2 ]', |
79
|
|
|
// E[foo="warning"]: Matches any E element whose "foo" attribute value is exactly equal to "warning" |
80
|
8 |
|
'/('.$tag.')\[([\w\-]+)\=\"(.*)\"]/' |
81
|
8 |
|
=> '\1[ contains( concat( " ", normalize-space(@\2), " " ), concat( " ", "\3", " " ) ) ]', |
82
|
|
|
// .warning: HTML only. The same as *[class~="warning"] |
83
|
|
|
'/(^|\s)\.([\w\-]+)+/' |
84
|
8 |
|
=> '*[ contains( concat( " ", normalize-space(@class), " " ), concat( " ", "\2", " " ) ) ]', |
85
|
|
|
// div.warning: HTML only. The same as DIV[class~="warning"] |
86
|
8 |
|
'/('.$tag.'|(\w+\|)?\*)\.([\w\-]+)+/' |
87
|
8 |
|
=> '\1[ contains( concat( " ", normalize-space(@class), " " ), concat( " ", "\3", " " ) ) ]', |
88
|
|
|
// E#myid: Matches any E element with id-attribute equal to "myid" |
89
|
8 |
|
'/('.$tag.')\#([\w\-]+)/' |
90
|
8 |
|
=> "\\1[@id='\\2']", |
91
|
|
|
// #myid: Matches any E element with id-attribute equal to "myid" |
92
|
|
|
'/\#([\w\-]+)/' |
93
|
8 |
|
=> "*[@id='\\1']", |
94
|
|
|
// namespace| |
95
|
|
|
'/(\w+)\|/' |
96
|
4 |
|
=> "\\1:" |
|
|
|
|
97
|
4 |
|
); |
98
|
|
|
|
99
|
8 |
|
$cssSelectors = array_keys($translateList); |
100
|
8 |
|
$xPathQueries = array_values($translateList); |
101
|
|
|
do { |
102
|
8 |
|
$continue = false; |
103
|
8 |
|
$cssSelector = (string) preg_replace($cssSelectors, $xPathQueries, $cssSelector); |
104
|
8 |
|
foreach ( $cssSelectors as $selector ) { |
105
|
8 |
|
if ( preg_match($selector, $cssSelector) ) { |
106
|
2 |
|
$continue = true; |
107
|
5 |
|
break; |
108
|
|
|
} |
109
|
4 |
|
} |
110
|
8 |
|
} while ( $continue ); |
111
|
8 |
|
return '//'.$cssSelector; |
112
|
|
|
} |
113
|
|
|
|
114
|
|
|
/** |
115
|
|
|
* Returns a guaranteed valid XML name. Removes illegal characters from the name. |
116
|
|
|
* @param string $name |
117
|
|
|
* @return string |
118
|
|
|
*/ |
119
|
6 |
|
public static function name( $name) |
120
|
|
|
{ |
121
|
6 |
|
return preg_replace( '/^[^:a-z_]*/isU', '', |
122
|
6 |
|
preg_replace( '/[^-.0-9:a-z_]/isU', '', $name |
123
|
3 |
|
) ); |
124
|
|
|
} |
125
|
|
|
|
126
|
|
|
/** |
127
|
|
|
* Returns a guaranteed valid XML attribute value. Removes illegal characters. |
128
|
|
|
* @param string|array|bool $value |
129
|
|
|
* @return string |
130
|
|
|
*/ |
131
|
8 |
|
public static function value( $value) |
132
|
|
|
{ |
133
|
8 |
|
if (is_array( $value )) { |
134
|
|
|
$content = array_reduce( $value, function( $result, $value) |
135
|
|
|
{ |
136
|
|
|
return $result . ' ' . static::value( $value ); |
137
|
|
|
} ); |
138
|
8 |
|
} else if (is_bool( $value )) { |
139
|
|
|
$content = $value ? 'true' : 'false'; |
140
|
|
|
} else { |
141
|
8 |
|
$value = (string) $value; |
142
|
8 |
|
if (preg_match( '/^\s*<!\[CDATA\[/', $value )) { |
143
|
|
|
$content = $value; |
144
|
|
|
} else { |
145
|
8 |
|
$content = htmlspecialchars( (string) $value, ENT_QUOTES, 'UTF-8' ); |
146
|
|
|
} |
147
|
|
|
} |
148
|
8 |
|
return $content; |
149
|
|
|
} |
150
|
|
|
|
151
|
|
|
/** |
152
|
|
|
* Returns a guaranteed valid XML attribute. Removes illegal characters. |
153
|
|
|
* @param string $name |
154
|
|
|
* @param string|array|bool $value |
155
|
|
|
* @return string |
156
|
|
|
*/ |
157
|
6 |
|
public static function attribute( $name, $value) |
158
|
|
|
{ |
159
|
6 |
|
return ' ' . static::name( $name ) . '="' . static::value( $value ) . '"'; |
160
|
|
|
} |
161
|
|
|
|
162
|
|
|
/** |
163
|
|
|
* Returns a guaranteed valid XML comment. Removes illegal characters. |
164
|
|
|
* @param string $content |
165
|
|
|
* @return string |
166
|
|
|
*/ |
167
|
4 |
|
public static function comment( $content) |
168
|
|
|
{ |
169
|
4 |
|
return static::raw('<!-- ' . static::value( $content ) . ' -->'); |
170
|
|
|
} |
171
|
|
|
|
172
|
|
|
/** |
173
|
|
|
* Returns a guaranteed valid XML CDATA string. Removes illegal characters. |
174
|
|
|
* @param string $content |
175
|
|
|
* @return string |
176
|
|
|
*/ |
177
|
4 |
|
public static function cdata( $content) |
178
|
|
|
{ |
179
|
4 |
|
return static::raw('<![CDATA[' . str_replace( ']]>', ']]>', $content ) . ']]>'); |
180
|
|
|
} |
181
|
|
|
|
182
|
|
|
/** |
183
|
|
|
* Returns an XML preamble. |
184
|
|
|
* @param string $version Defaults to '1.0' |
185
|
|
|
* @param string $encoding Defaults to null |
186
|
|
|
* @param string $standalone Defaults to null |
187
|
|
|
* @return string |
188
|
|
|
*/ |
189
|
2 |
|
public static function preamble( $version = '1.0', $encoding = null, $standalone = null) |
190
|
|
|
{ |
191
|
2 |
|
if (isset($standalone)) { |
192
|
|
|
if ($standalone === 'false') { |
193
|
|
|
$standalone = 'no'; |
194
|
|
|
} else if ($standalone !== 'no') { |
195
|
|
|
$standalone = ( $standalone ? 'yes' : 'no' ); |
196
|
|
|
} |
197
|
|
|
$standalone = static::attribute( 'standalone', $standalone ); |
198
|
|
|
} else { |
199
|
2 |
|
$standalone = ''; |
200
|
|
|
} |
201
|
2 |
|
$preamble = '<?xml version="' . static::value($version) . '"'; |
202
|
2 |
|
if (isset( $encoding )) { |
203
|
|
|
$preamble .= ' " encoding="' . static::value($encoding) . '"'; |
204
|
|
|
} |
205
|
2 |
|
$preamble .= $standalone . ' ?>'; |
206
|
2 |
|
return $preamble; |
207
|
|
|
} |
208
|
|
|
|
209
|
6 |
|
public static function raw( $contents='' ) { |
210
|
6 |
|
return new xml\RawXML($contents); |
211
|
|
|
} |
212
|
|
|
|
213
|
|
|
} |
PHP provides two ways to mark string literals. Either with single quotes
'literal'
or with double quotes"literal"
. The difference between these is that string literals in double quotes may contain variables with are evaluated at run-time as well as escape sequences.String literals in single quotes on the other hand are evaluated very literally and the only two characters that needs escaping in the literal are the single quote itself (
\'
) and the backslash (\\
). Every other character is displayed as is.Double quoted string literals may contain other variables or more complex escape sequences.
will print an indented:
Single is Value
If your string literal does not contain variables or escape sequences, it should be defined using single quotes to make that fact clear.
For more information on PHP string literals and available escape sequences see the PHP core documentation.