2 /* vim: set expandtab tabstop=4 shiftwidth=4: */
4 // +----------------------------------------------------------------------+
6 // +----------------------------------------------------------------------+
7 // | Copyright (c) 1997-2002 The PHP Group |
8 // +----------------------------------------------------------------------+
9 // | This source file is subject to version 3.0 of the PHP license, |
10 // | that is bundled with this package in the file LICENSE, and is |
11 // | available at through the world-wide-web at |
12 // | http://www.php.net/license/3_0.txt. |
13 // | If you did not receive a copy of the PHP license and are unable to |
14 // | obtain it through the world-wide-web, please send a note to |
15 // | license@php.net so we can mail you a copy immediately. |
16 // +----------------------------------------------------------------------+
17 // | Authors: Alexander Zhukov <alex@veresk.ru> Original port from Python |
18 // | Authors: Harry Fuecks <hfuecks@phppatterns.com> Port to PEAR + more |
19 // | Authors: Many @ Sitepointforums Advanced PHP Forums |
20 // +----------------------------------------------------------------------+
25 * Main parser components
26 * @package XML_HTMLSax3
32 if (!defined('XML_HTMLSAX3')) {
33 define('XML_HTMLSAX3', 'include/Pear/XML_HTMLSax3/');
35 require_once(XML_HTMLSAX3 . 'HTMLSax3/States.php');
36 require_once(XML_HTMLSAX3 . 'HTMLSax3/Decorators.php');
40 * @package XML_HTMLSax3
44 class XML_HTMLSax3_StateParser {
46 * Instance of user front end class to be passed to callbacks
52 * User defined object for handling elements
56 var $handler_object_element;
58 * User defined open tag handler method
62 var $handler_method_opening;
64 * User defined close tag handler method
68 var $handler_method_closing;
70 * User defined object for handling data in elements
74 var $handler_object_data;
76 * User defined data handler method
80 var $handler_method_data;
82 * User defined object for handling processing instructions
86 var $handler_object_pi;
88 * User defined processing instruction handler method
92 var $handler_method_pi;
94 * User defined object for handling JSP/ASP tags
98 var $handler_object_jasp;
100 * User defined JSP/ASP handler method
104 var $handler_method_jasp;
106 * User defined object for handling XML escapes
110 var $handler_object_escape;
112 * User defined XML escape handler method
116 var $handler_method_escape;
118 * User defined handler object or NullHandler
122 var $handler_default;
124 * Parser options determining parsing behavior
128 var $parser_options = array();
130 * XML document being parsed
136 * Position in XML document relative to start (0)
142 * Length of the XML document in characters
148 * Array of state objects
152 var $State = array();
155 * Constructs XML_HTMLSax3_StateParser setting up states
156 * @var XML_HTMLSax3 instance of user front end class
159 function XML_HTMLSax3_StateParser (& $htmlsax) {
160 $this->htmlsax = & $htmlsax;
161 $this->State[XML_HTMLSAX3_STATE_START] = new XML_HTMLSax3_StartingState();
163 $this->State[XML_HTMLSAX3_STATE_CLOSING_TAG] = new XML_HTMLSax3_ClosingTagState();
164 $this->State[XML_HTMLSAX3_STATE_TAG] = new XML_HTMLSax3_TagState();
165 $this->State[XML_HTMLSAX3_STATE_OPENING_TAG] = new XML_HTMLSax3_OpeningTagState();
167 $this->State[XML_HTMLSAX3_STATE_PI] = new XML_HTMLSax3_PiState();
168 $this->State[XML_HTMLSAX3_STATE_JASP] = new XML_HTMLSax3_JaspState();
169 $this->State[XML_HTMLSAX3_STATE_ESCAPE] = new XML_HTMLSax3_EscapeState();
173 * Moves the position back one character
177 function unscanCharacter() {
178 $this->position -= 1;
182 * Moves the position forward one character
186 function ignoreCharacter() {
187 $this->position += 1;
191 * Returns the next character from the XML document or void if at end
195 function scanCharacter() {
196 if ($this->position < $this->length) {
197 return $this->rawtext{$this->position++};
202 * Returns a string from the current position to the next occurance
203 * of the supplied string
204 * @param string string to search until
208 function scanUntilString($string) {
209 $start = $this->position;
210 $this->position = strpos($this->rawtext, $string, $start);
211 if ($this->position === FALSE) {
212 $this->position = $this->length;
214 return substr($this->rawtext, $start, $this->position - $start);
218 * Returns a string from the current position until the first instance of
219 * one of the characters in the supplied string argument
220 * @param string string to search until
225 function scanUntilCharacters($string) {}
228 * Moves the position forward past any whitespace characters
233 function ignoreWhitespace() {}
236 * Begins the parsing operation, setting up any decorators, depending on
237 * parse options invoking _parse() to execute parsing
238 * @param string XML document to parse
242 function parse($data) {
243 if ($this->parser_options['XML_OPTION_TRIM_DATA_NODES']==1) {
244 $decorator = new XML_HTMLSax3_Trim(
245 $this->handler_object_data,
246 $this->handler_method_data);
247 $this->handler_object_data =& $decorator;
248 $this->handler_method_data = 'trimData';
250 if ($this->parser_options['XML_OPTION_CASE_FOLDING']==1) {
251 $open_decor = new XML_HTMLSax3_CaseFolding(
252 $this->handler_object_element,
253 $this->handler_method_opening,
254 $this->handler_method_closing);
255 $this->handler_object_element =& $open_decor;
256 $this->handler_method_opening ='foldOpen';
257 $this->handler_method_closing ='foldClose';
259 if ($this->parser_options['XML_OPTION_LINEFEED_BREAK']==1) {
260 $decorator = new XML_HTMLSax3_Linefeed(
261 $this->handler_object_data,
262 $this->handler_method_data);
263 $this->handler_object_data =& $decorator;
264 $this->handler_method_data = 'breakData';
266 if ($this->parser_options['XML_OPTION_TAB_BREAK']==1) {
267 $decorator = new XML_HTMLSax3_Tab(
268 $this->handler_object_data,
269 $this->handler_method_data);
270 $this->handler_object_data =& $decorator;
271 $this->handler_method_data = 'breakData';
273 if ($this->parser_options['XML_OPTION_ENTITIES_UNPARSED']==1) {
274 $decorator = new XML_HTMLSax3_Entities_Unparsed(
275 $this->handler_object_data,
276 $this->handler_method_data);
277 $this->handler_object_data =& $decorator;
278 $this->handler_method_data = 'breakData';
280 if ($this->parser_options['XML_OPTION_ENTITIES_PARSED']==1) {
281 $decorator = new XML_HTMLSax3_Entities_Parsed(
282 $this->handler_object_data,
283 $this->handler_method_data);
284 $this->handler_object_data =& $decorator;
285 $this->handler_method_data = 'breakData';
287 // Note switched on by default
288 if ($this->parser_options['XML_OPTION_STRIP_ESCAPES']==1) {
289 $decorator = new XML_HTMLSax3_Escape_Stripper(
290 $this->handler_object_escape,
291 $this->handler_method_escape);
292 $this->handler_object_escape =& $decorator;
293 $this->handler_method_escape = 'strip';
295 $this->rawtext = $data;
296 $this->length = strlen($data);
302 * Performs the parsing itself, delegating calls to a specific parser
304 * @param constant state object to parse with
308 function _parse($state = XML_HTMLSAX3_STATE_START) {
310 $state = $this->State[$state]->parse($this);
311 } while ($state != XML_HTMLSAX3_STATE_STOP &&
312 $this->position < $this->length);
317 * Parser for PHP Versions below 4.3.0. Uses a slower parsing mechanism than
318 * the equivalent PHP 4.3.0+ subclass of StateParser
319 * @package XML_HTMLSax3
321 * @see XML_HTMLSax3_StateParser_Gtet430
323 class XML_HTMLSax3_StateParser_Lt430 extends XML_HTMLSax3_StateParser {
325 * Constructs XML_HTMLSax3_StateParser_Lt430 defining available
327 * @var XML_HTMLSax3 instance of user front end class
330 function XML_HTMLSax3_StateParser_Lt430(& $htmlsax) {
331 parent::XML_HTMLSax3_StateParser($htmlsax);
332 $this->parser_options['XML_OPTION_TRIM_DATA_NODES'] = 0;
333 $this->parser_options['XML_OPTION_CASE_FOLDING'] = 0;
334 $this->parser_options['XML_OPTION_LINEFEED_BREAK'] = 0;
335 $this->parser_options['XML_OPTION_TAB_BREAK'] = 0;
336 $this->parser_options['XML_OPTION_ENTITIES_PARSED'] = 0;
337 $this->parser_options['XML_OPTION_ENTITIES_UNPARSED'] = 0;
338 $this->parser_options['XML_OPTION_STRIP_ESCAPES'] = 0;
342 * Returns a string from the current position until the first instance of
343 * one of the characters in the supplied string argument
344 * @param string string to search until
348 function scanUntilCharacters($string) {
349 $startpos = $this->position;
350 while ($this->position < $this->length && strpos($string, $this->rawtext{$this->position}) === FALSE) {
353 return substr($this->rawtext, $startpos, $this->position - $startpos);
357 * Moves the position forward past any whitespace characters
361 function ignoreWhitespace() {
362 while ($this->position < $this->length &&
363 strpos(" \n\r\t", $this->rawtext{$this->position}) !== FALSE) {
369 * Begins the parsing operation, setting up the unparsed XML entities
370 * decorator if necessary then delegating further work to parent
371 * @param string XML document to parse
375 function parse($data) {
376 parent::parse($data);
381 * Parser for PHP Versions equal to or greater than 4.3.0. Uses a faster
382 * parsing mechanism than the equivalent PHP < 4.3.0 subclass of StateParser
383 * @package XML_HTMLSax3
385 * @see XML_HTMLSax3_StateParser_Lt430
387 class XML_HTMLSax3_StateParser_Gtet430 extends XML_HTMLSax3_StateParser {
389 * Constructs XML_HTMLSax3_StateParser_Gtet430 defining available
391 * @var XML_HTMLSax3 instance of user front end class
394 function XML_HTMLSax3_StateParser_Gtet430(& $htmlsax) {
395 parent::XML_HTMLSax3_StateParser($htmlsax);
396 $this->parser_options['XML_OPTION_TRIM_DATA_NODES'] = 0;
397 $this->parser_options['XML_OPTION_CASE_FOLDING'] = 0;
398 $this->parser_options['XML_OPTION_LINEFEED_BREAK'] = 0;
399 $this->parser_options['XML_OPTION_TAB_BREAK'] = 0;
400 $this->parser_options['XML_OPTION_ENTITIES_PARSED'] = 0;
401 $this->parser_options['XML_OPTION_ENTITIES_UNPARSED'] = 0;
402 $this->parser_options['XML_OPTION_STRIP_ESCAPES'] = 0;
405 * Returns a string from the current position until the first instance of
406 * one of the characters in the supplied string argument.
407 * @param string string to search until
411 function scanUntilCharacters($string) {
412 $startpos = $this->position;
413 $length = strcspn($this->rawtext, $string, $startpos);
414 $this->position += $length;
415 return substr($this->rawtext, $startpos, $length);
419 * Moves the position forward past any whitespace characters
423 function ignoreWhitespace() {
424 $this->position += strspn($this->rawtext, " \n\r\t", $this->position);
428 * Begins the parsing operation, setting up the parsed and unparsed
429 * XML entity decorators if necessary then delegating further work
431 * @param string XML document to parse
435 function parse($data) {
436 parent::parse($data);
441 * Default NullHandler for methods which were not set by user
442 * @package XML_HTMLSax3
445 class XML_HTMLSax3_NullHandler {
447 * Generic handler method which does nothing
451 function DoNothing() {
456 * User interface class. All user calls should only be made to this class
457 * @package XML_HTMLSax3
462 * Instance of concrete subclass of XML_HTMLSax3_StateParser
463 * @var XML_HTMLSax3_StateParser
469 * Constructs XML_HTMLSax3 selecting concrete StateParser subclass
470 * depending on PHP version being used as well as setting the default
471 * NullHandler for all callbacks<br />
474 * $myHandler = new MyHandler();
475 * $parser = new XML_HTMLSax3();
476 * $parser->set_object($myHandler);
477 * $parser->set_option('XML_OPTION_CASE_FOLDING');
478 * $parser->set_element_handler('myOpenHandler','myCloseHandler');
479 * $parser->set_data_handler('myDataHandler');
480 * $parser->parser($xml);
484 function XML_HTMLSax3() {
485 if (version_compare(phpversion(), '4.3', 'ge')) {
486 $this->state_parser = new XML_HTMLSax3_StateParser_Gtet430($this);
488 $this->state_parser = new XML_HTMLSax3_StateParser_Lt430($this);
490 $nullhandler = new XML_HTMLSax3_NullHandler();
491 $this->set_object($nullhandler);
492 $this->set_element_handler('DoNothing', 'DoNothing');
493 $this->set_data_handler('DoNothing');
494 $this->set_pi_handler('DoNothing');
495 $this->set_jasp_handler('DoNothing');
496 $this->set_escape_handler('DoNothing');
500 * Sets the user defined handler object. Returns a PEAR Error
501 * if supplied argument is not an object.
502 * @param object handler object containing SAX callback methods
506 function set_object(&$object) {
507 if ( is_object($object) ) {
508 $this->state_parser->handler_default =& $object;
511 $GLOBALS['log']->info('XML_HTMLSax3::set_object requires '.
512 'an object instance');
517 * Sets a parser option. By default all options are switched off.
518 * Returns a PEAR Error if option is invalid<br />
519 * <b>Available options:</b>
521 * <li>XML_OPTION_TRIM_DATA_NODES: trim whitespace off the beginning
522 * and end of data passed to the data handler</li>
523 * <li>XML_OPTION_LINEFEED_BREAK: linefeeds result in additional data
525 * <li>XML_OPTION_TAB_BREAK: tabs result in additional data handler
527 * <li>XML_OPTION_ENTITIES_UNPARSED: XML entities are returned as
528 * seperate data handler calls in unparsed form</li>
529 * <li>XML_OPTION_ENTITIES_PARSED: (PHP 4.3.0+ only) XML entities are
530 * returned as seperate data handler calls and are parsed with
531 * PHP's html_entity_decode() function</li>
532 * <li>XML_OPTION_STRIP_ESCAPES: strips out the -- -- comment markers
533 * or CDATA markup inside an XML escape, if found.</li>
535 * To get HTMLSax to behave in the same way as the native PHP SAX parser,
536 * using it's default state, you need to switch on XML_OPTION_LINEFEED_BREAK,
537 * XML_OPTION_ENTITIES_PARSED and XML_OPTION_CASE_FOLDING
538 * @param string name of parser option
539 * @param int (optional) 1 to switch on, 0 for off
543 function set_option($name, $value=1) {
544 if ( array_key_exists($name,$this->state_parser->parser_options) ) {
545 $this->state_parser->parser_options[$name] = $value;
548 $GLOBALS['log']->info('XML_HTMLSax3::set_option('.$name.') illegal');
553 * Sets the data handler method which deals with the contents of XML
555 * The handler method must accept two arguments, the first being an
556 * instance of XML_HTMLSax3 and the second being the contents of an
559 * function myDataHander(& $parser,$data){}
561 * @param string name of method
566 function set_data_handler($data_method) {
567 $this->state_parser->handler_object_data =& $this->state_parser->handler_default;
568 $this->state_parser->handler_method_data = $data_method;
572 * Sets the open and close tag handlers
573 * <br />The open handler method must accept three arguments; the parser,
574 * the tag name and an array of attributes e.g.
576 * function myOpenHander(& $parser,$tagname,$attrs=array()){}
578 * The close handler method must accept two arguments; the parser and
581 * function myCloseHander(& $parser,$tagname){}
583 * @param string name of open method
584 * @param string name of close method
589 function set_element_handler($opening_method, $closing_method) {
590 $this->state_parser->handler_object_element =& $this->state_parser->handler_default;
591 $this->state_parser->handler_method_opening = $opening_method;
592 $this->state_parser->handler_method_closing = $closing_method;
596 * Sets the processing instruction handler method e.g. for PHP open
597 * and close tags<br />
598 * The handler method must accept three arguments; the parser, the
599 * PI target and data inside the PI
601 * function myPIHander(& $parser,$target, $data){}
603 * @param string name of method
608 function set_pi_handler($pi_method) {
609 $this->state_parser->handler_object_pi =& $this->state_parser->handler_default;
610 $this->state_parser->handler_method_pi = $pi_method;
614 * Sets the XML escape handler method e.g. for comments and doctype
616 * The handler method must accept two arguments; the parser and the
617 * contents of the escaped section
619 * function myEscapeHander(& $parser, $data){}
621 * @param string name of method
626 function set_escape_handler($escape_method) {
627 $this->state_parser->handler_object_escape =& $this->state_parser->handler_default;
628 $this->state_parser->handler_method_escape = $escape_method;
632 * Sets the JSP/ASP markup handler<br />
633 * The handler method must accept two arguments; the parser and
634 * body of the JASP tag
636 * function myJaspHander(& $parser, $data){}
638 * @param string name of method
643 function set_jasp_handler ($jasp_method) {
644 $this->state_parser->handler_object_jasp =& $this->state_parser->handler_default;
645 $this->state_parser->handler_method_jasp = $jasp_method;
649 * Returns the current string position of the "cursor" inside the XML
651 * <br />Intended for use from within a user defined handler called
652 * via the $parser reference e.g.
654 * function myDataHandler(& $parser,$data) {
655 * echo( 'Current position: '.$parser->get_current_position() );
662 function get_current_position() {
663 return $this->state_parser->position;
667 * Returns the string length of the XML document being parsed
671 function get_length() {
672 return $this->state_parser->length;
676 * Start parsing some XML
677 * @param string XML document
681 function parse($data) {
682 $this->state_parser->parse($data);