1 | <?php |
---|
2 | |
---|
3 | /****************************************************************************** |
---|
4 | * |
---|
5 | * Filename: XML.php |
---|
6 | * |
---|
7 | * Description: Provides functions for parsing and constructing XML information |
---|
8 | * |
---|
9 | * Author: Evan Hunter |
---|
10 | * |
---|
11 | * Date: 27/7/2004 |
---|
12 | * |
---|
13 | * Project: JPEG Metadata |
---|
14 | * |
---|
15 | * Revision: 1.10 |
---|
16 | * |
---|
17 | * Changes: 1.00 -> 1.10 : Changed read_xml_array_from_text to fix problem that |
---|
18 | * caused the whitespace (especially newlines) to be |
---|
19 | * destroyed when converting xml text to an xml array |
---|
20 | * |
---|
21 | * URL: http://electronics.ozhiker.com |
---|
22 | * |
---|
23 | * License: This file is part of the PHP JPEG Metadata Toolkit. |
---|
24 | * |
---|
25 | * The PHP JPEG Metadata Toolkit is free software; you can |
---|
26 | * redistribute it and/or modify it under the terms of the |
---|
27 | * GNU General Public License as published by the Free Software |
---|
28 | * Foundation; either version 2 of the License, or (at your |
---|
29 | * option) any later version. |
---|
30 | * |
---|
31 | * The PHP JPEG Metadata Toolkit is distributed in the hope |
---|
32 | * that it will be useful, but WITHOUT ANY WARRANTY; without |
---|
33 | * even the implied warranty of MERCHANTABILITY or FITNESS |
---|
34 | * FOR A PARTICULAR PURPOSE. See the GNU General Public License |
---|
35 | * for more details. |
---|
36 | * |
---|
37 | * You should have received a copy of the GNU General Public |
---|
38 | * License along with the PHP JPEG Metadata Toolkit; if not, |
---|
39 | * write to the Free Software Foundation, Inc., 59 Temple |
---|
40 | * Place, Suite 330, Boston, MA 02111-1307 USA |
---|
41 | * |
---|
42 | * If you require a different license for commercial or other |
---|
43 | * purposes, please contact the author: evan@ozhiker.com |
---|
44 | * |
---|
45 | ******************************************************************************/ |
---|
46 | |
---|
47 | include_once INCLUDE_PATH.'Unicode.php'; // Unicode is required as XML is always Unicode encoded |
---|
48 | |
---|
49 | |
---|
50 | /****************************************************************************** |
---|
51 | * |
---|
52 | * Function: read_xml_array_from_text |
---|
53 | * |
---|
54 | * Description: Parses a string containing XML, and returns the resulting |
---|
55 | * tree structure array, which contains all the XML information. |
---|
56 | * Note: White space and comments in the XML are ignored |
---|
57 | * Note: All text information contained in the tree structure |
---|
58 | * is encoded as Unicode UTF-8. Hence text will appear as |
---|
59 | * normal ASCII except where there is an extended character. |
---|
60 | * |
---|
61 | * Parameters: xmltext - a string containing the XML to be parsed |
---|
62 | * |
---|
63 | * Returns: output - the tree structure array containing the XML information |
---|
64 | * FALSE - if an error occured |
---|
65 | * |
---|
66 | ******************************************************************************/ |
---|
67 | |
---|
68 | function read_xml_array_from_text( $xmltext ) |
---|
69 | { |
---|
70 | // Check if there actually is any text to parse |
---|
71 | if ( trim( $xmltext ) == "" ) |
---|
72 | { |
---|
73 | return FALSE; |
---|
74 | } |
---|
75 | |
---|
76 | // Create an instance of a xml parser to parse the XML text |
---|
77 | $xml_parser = xml_parser_create( "UTF-8" ); |
---|
78 | |
---|
79 | |
---|
80 | // Change: Fixed problem that caused the whitespace (especially newlines) to be destroyed when converting xml text to an xml array, as of revision 1.10 |
---|
81 | |
---|
82 | // We would like to remove unneccessary white space, but this will also |
---|
83 | // remove things like newlines (
) in the XML values, so white space |
---|
84 | // will have to be removed later |
---|
85 | if ( xml_parser_set_option($xml_parser,XML_OPTION_SKIP_WHITE,0) == FALSE ) |
---|
86 | { |
---|
87 | // Error setting case folding - destroy the parser and return |
---|
88 | xml_parser_free($xml_parser); |
---|
89 | return FALSE; |
---|
90 | } |
---|
91 | |
---|
92 | // to use XML code correctly we have to turn case folding |
---|
93 | // (uppercasing) off. XML is case sensitive and upper |
---|
94 | // casing is in reality XML standards violation |
---|
95 | if ( xml_parser_set_option($xml_parser,XML_OPTION_CASE_FOLDING,0) == FALSE ) |
---|
96 | { |
---|
97 | // Error setting case folding - destroy the parser and return |
---|
98 | xml_parser_free($xml_parser); |
---|
99 | return FALSE; |
---|
100 | } |
---|
101 | |
---|
102 | // Parse the XML text into a array structure |
---|
103 | if ( xml_parse_into_struct($xml_parser, $xmltext, $vals, $index) == 0 ) |
---|
104 | { |
---|
105 | // Error Parsing XML - destroy the parser and return |
---|
106 | xml_parser_free($xml_parser); |
---|
107 | return FALSE; |
---|
108 | } |
---|
109 | |
---|
110 | // Destroy the xml parser |
---|
111 | xml_parser_free($xml_parser); |
---|
112 | |
---|
113 | |
---|
114 | // Change: Fixed problem that caused the whitespace (especially newlines) to be destroyed when converting xml text to an xml array, as of revision 1.10 |
---|
115 | |
---|
116 | // Since the xml was processed with whitespace enabled, it will have many values which are |
---|
117 | // only whitespace. These need to be removed to make a sensible array. |
---|
118 | |
---|
119 | $newvals = array( ); |
---|
120 | |
---|
121 | // Cycle through each of the items |
---|
122 | foreach( $vals as $valno => $val ) |
---|
123 | { |
---|
124 | // If the item has a whitespace only value, remove it |
---|
125 | if ( ( array_key_exists( 'value', $val ) ) && (trim( $val[ 'value' ] ) == "" ) ) |
---|
126 | { |
---|
127 | unset( $val[ 'value' ] ); |
---|
128 | } |
---|
129 | // If the item has a value (which will be non blank now) or is of type other than cdata, add it to the new array |
---|
130 | if ( ( $val[ 'type' ] != 'cdata' ) || ( array_key_exists( 'value', $val ) ) ) |
---|
131 | { |
---|
132 | $newvals[] = $val; |
---|
133 | } |
---|
134 | |
---|
135 | } |
---|
136 | |
---|
137 | // The xml_parse_into_struct function returns a flat version |
---|
138 | // of the XML data, where each tag has a level number attached. |
---|
139 | // This is very difficult to work with, so it needs to be |
---|
140 | // converted to a tree structure before being returned |
---|
141 | return xml_get_children($newvals, $i=0); |
---|
142 | |
---|
143 | } |
---|
144 | |
---|
145 | /****************************************************************************** |
---|
146 | * End of Function: read_xml_array_from_text |
---|
147 | ******************************************************************************/ |
---|
148 | |
---|
149 | |
---|
150 | |
---|
151 | |
---|
152 | |
---|
153 | /****************************************************************************** |
---|
154 | * |
---|
155 | * Function: write_xml_array_to_text |
---|
156 | * |
---|
157 | * Description: Takes a tree structure array (in the same format as returned |
---|
158 | * by read_xml_array_from_text, and constructs a string containing |
---|
159 | * the equivalent XML. This function is recursive, and produces |
---|
160 | * XML which has correct indents. |
---|
161 | * Note: All text information contained in the tree structure |
---|
162 | * can be either 7-bit ASCII or encoded as Unicode UTF-8, |
---|
163 | * since UTF-8 passes 7-bit ASCII text unchanged. |
---|
164 | * |
---|
165 | * Parameters: xmlarray - the tree structure array containing the information to |
---|
166 | * be converted to XML |
---|
167 | * indentlevel - the indent level of the top level tags (usually zero) |
---|
168 | * |
---|
169 | * Returns: output - the string containing the equivalent XML |
---|
170 | * FALSE - if an error occured |
---|
171 | * |
---|
172 | ******************************************************************************/ |
---|
173 | |
---|
174 | function write_xml_array_to_text( $xmlarray, $indentlevel ) |
---|
175 | { |
---|
176 | // Create a string to receive the XML |
---|
177 | $output_xml_text = ""; |
---|
178 | |
---|
179 | |
---|
180 | // Cycle through each xml element at this level |
---|
181 | foreach ($xmlarray as $xml_elem) |
---|
182 | { |
---|
183 | |
---|
184 | // Add the indent, then the cleaned tag name to the output |
---|
185 | $output_xml_text .= str_repeat ( " ", $indentlevel ) . "<" . xml_UTF8_clean( $xml_elem['tag'] ); |
---|
186 | |
---|
187 | // Check if there are any attributes for this tag |
---|
188 | if (array_key_exists('attributes',$xml_elem)) |
---|
189 | { |
---|
190 | // There are attributes |
---|
191 | // Cycle through each attribute for this tag |
---|
192 | foreach ($xml_elem['attributes'] as $xml_attr_name => $xml_attr_val) |
---|
193 | { |
---|
194 | // Add the cleaned attribute name, and cleaned attribute value to the output |
---|
195 | $output_xml_text .= " ". xml_UTF8_clean( $xml_attr_name ) ." ='" . xml_UTF8_clean( $xml_attr_val ) ."'"; |
---|
196 | } |
---|
197 | } |
---|
198 | |
---|
199 | // Add the 'greater-than' to close this tag to the output |
---|
200 | $output_xml_text .= ">"; |
---|
201 | |
---|
202 | // Check if this element has any text inside it. |
---|
203 | if (array_key_exists('value',$xml_elem) ) |
---|
204 | { |
---|
205 | // There is text for this element - clean it and add it to the output |
---|
206 | $output_xml_text .= xml_UTF8_clean( $xml_elem['value'] ); |
---|
207 | } |
---|
208 | |
---|
209 | // Check if there are any lower levels contained by this element |
---|
210 | if (array_key_exists('children',$xml_elem) ) |
---|
211 | { |
---|
212 | // There are sub-elements for this element |
---|
213 | |
---|
214 | // Add a newline to the output, so the sub-elements start on a fresh line |
---|
215 | $output_xml_text .= "\n"; |
---|
216 | |
---|
217 | // Recursively call this function to output the sub-elements, and add the result to the output |
---|
218 | $output_xml_text .= write_xml_array_to_text( $xml_elem['children'], $indentlevel + 1 ); |
---|
219 | |
---|
220 | // Add an indent to the output for the closing tag, since we are on a new line due to the sub-elements |
---|
221 | $output_xml_text .= str_repeat ( " ", $indentlevel ); |
---|
222 | } |
---|
223 | |
---|
224 | // Add the cleaned closing tag to the output |
---|
225 | $output_xml_text .= "</" .xml_UTF8_clean($xml_elem['tag']) . ">\n"; |
---|
226 | } |
---|
227 | |
---|
228 | // Return the XML text |
---|
229 | return $output_xml_text; |
---|
230 | } |
---|
231 | |
---|
232 | /****************************************************************************** |
---|
233 | * End of Function: write_xml_array_to_text |
---|
234 | ******************************************************************************/ |
---|
235 | |
---|
236 | |
---|
237 | |
---|
238 | |
---|
239 | |
---|
240 | |
---|
241 | |
---|
242 | |
---|
243 | |
---|
244 | |
---|
245 | |
---|
246 | |
---|
247 | |
---|
248 | |
---|
249 | |
---|
250 | |
---|
251 | |
---|
252 | |
---|
253 | |
---|
254 | |
---|
255 | |
---|
256 | |
---|
257 | |
---|
258 | /****************************************************************************** |
---|
259 | * |
---|
260 | * INTERNAL FUNCTIONS |
---|
261 | * |
---|
262 | ******************************************************************************/ |
---|
263 | |
---|
264 | |
---|
265 | |
---|
266 | |
---|
267 | |
---|
268 | |
---|
269 | /****************************************************************************** |
---|
270 | * |
---|
271 | * Internal Function: xml_get_children |
---|
272 | * |
---|
273 | * Description: Used by the read_xml_array_from_text function. |
---|
274 | * This function recursively converts the values retrieved from |
---|
275 | * the xml_parse_into_struct function into a tree structure array, |
---|
276 | * which is much more useful and easier to use. |
---|
277 | * |
---|
278 | * Parameters: input_xml_array - the flat array of XML elements retrieved |
---|
279 | * from xml_parse_into_struct |
---|
280 | * $item_num - the number of the element at which the conversion |
---|
281 | * should start (usually zero when called from another |
---|
282 | * function, this is used for recursion) |
---|
283 | * |
---|
284 | * Returns: children - the tree structure array containing XML elements |
---|
285 | * FALSE - if an error occured |
---|
286 | * |
---|
287 | ******************************************************************************/ |
---|
288 | |
---|
289 | function xml_get_children( &$input_xml_array, &$item_num ) |
---|
290 | { |
---|
291 | |
---|
292 | // Make an array to receive the output XML tree structure |
---|
293 | $children = array(); |
---|
294 | |
---|
295 | |
---|
296 | // Cycle through all the elements of the input XML array |
---|
297 | while ( $item_num < count( $input_xml_array ) ) |
---|
298 | { |
---|
299 | // Retrieve the current array element |
---|
300 | $v = &$input_xml_array[ $item_num++ ]; |
---|
301 | |
---|
302 | // Check what type of XML array element this is, and process accordingly |
---|
303 | |
---|
304 | switch ( $v['type'] ) |
---|
305 | { |
---|
306 | case 'cdata': // This is a non parsed Character Data tag |
---|
307 | case 'complete': // This is a pair of XML matching tags possibly with text (but no tags) inside |
---|
308 | $children[] = xml_get_child( $v ); |
---|
309 | break; |
---|
310 | |
---|
311 | case 'open': // This is a single opening tag |
---|
312 | // Recursively get the children for this opening tag |
---|
313 | $children[] = xml_get_child( $v, xml_get_children( $input_xml_array, $item_num ) ); |
---|
314 | break; // This is a single opening tag |
---|
315 | |
---|
316 | case 'close': // This is a single closing tag |
---|
317 | break 2; // leave "while" loop (and the function) |
---|
318 | } |
---|
319 | } |
---|
320 | |
---|
321 | // Return the results |
---|
322 | return $children; |
---|
323 | } |
---|
324 | |
---|
325 | /****************************************************************************** |
---|
326 | * End of Function: xml_get_children |
---|
327 | ******************************************************************************/ |
---|
328 | |
---|
329 | |
---|
330 | /****************************************************************************** |
---|
331 | * |
---|
332 | * Internal Function: xml_get_child |
---|
333 | * |
---|
334 | * Description: Used by the xml_get_children function. |
---|
335 | * Takes an element from an array provided by xml_parse_into_struct |
---|
336 | * and returns an element for a tree structure array |
---|
337 | * |
---|
338 | * Parameters: input_xml_item - the item from the array provided by xml_parse_into_struct |
---|
339 | * children - an array of sub-elements to be added to the tree |
---|
340 | * structure array. Null or missing value indicate no |
---|
341 | * sub-elements are to be added. |
---|
342 | * |
---|
343 | * Returns: child - the element for a tree structure array |
---|
344 | * FALSE - if an error occured |
---|
345 | * |
---|
346 | ******************************************************************************/ |
---|
347 | |
---|
348 | function xml_get_child( &$input_xml_item, $children = NULL ) |
---|
349 | { |
---|
350 | // Create an array to receive the child structure |
---|
351 | $child = array(); |
---|
352 | |
---|
353 | // If the input item has the 'tag' element set, copy it to the child |
---|
354 | if ( isset( $input_xml_item['tag'] ) ) |
---|
355 | { |
---|
356 | $child['tag'] = $input_xml_item['tag'] ; |
---|
357 | } |
---|
358 | |
---|
359 | // If the input item has the 'value' element set, copy it to the child |
---|
360 | if ( isset( $input_xml_item['value'] ) ) |
---|
361 | { |
---|
362 | $child['value'] = $input_xml_item['value'] ; |
---|
363 | } |
---|
364 | |
---|
365 | // If the input item has the 'attributes' element set, copy it to the child |
---|
366 | if ( isset( $input_xml_item['attributes'] ) ) |
---|
367 | { |
---|
368 | $child['attributes'] = $input_xml_item['attributes']; |
---|
369 | } |
---|
370 | |
---|
371 | // If children have been specified, add them to the child |
---|
372 | if ( is_array( $children ) ) |
---|
373 | { |
---|
374 | $child['children'] = $children; |
---|
375 | } |
---|
376 | |
---|
377 | // Return the child structure |
---|
378 | return $child; |
---|
379 | } |
---|
380 | |
---|
381 | /****************************************************************************** |
---|
382 | * End of Function: xml_get_children |
---|
383 | ******************************************************************************/ |
---|
384 | |
---|
385 | |
---|
386 | |
---|
387 | |
---|
388 | |
---|
389 | |
---|
390 | |
---|
391 | |
---|
392 | |
---|
393 | |
---|
394 | |
---|
395 | |
---|
396 | ?> |
---|