docs/include/classes/XML/XML_HTMLSax/HTMLSax/XML_HTMLSax_States.php

   1 <?php
   2 /* vim: set expandtab tabstop=4 shiftwidth=4: */
   3 //
   4 // +----------------------------------------------------------------------+
   5 // | PHP Version 4                                                        |
   6 // +----------------------------------------------------------------------+
   7 // | Copyright (c) 1997-2002 The PHP Group                                |
   8 // +----------------------------------------------------------------------+
   9 // | This source file is subject to version 2.02 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 // +----------------------------------------------------------------------+
  21 //
  22 // $Id$
  23 //
  24 /**
  25 * Main parser components
  26 * @package XML_HTMLSax
  27 * @version $Id$
  28 */
  29 /**
  30 * Define parser states
  31 */
  32 define('XML_HTMLSAX_STATE_STOP', 0);
  33 define('XML_HTMLSAX_STATE_START', 1);
  34 define('XML_HTMLSAX_STATE_TAG', 2);
  35 define('XML_HTMLSAX_STATE_OPENING_TAG', 3);
  36 define('XML_HTMLSAX_STATE_CLOSING_TAG', 4);
  37 define('XML_HTMLSAX_STATE_ESCAPE', 6);
  38 define('XML_HTMLSAX_STATE_JASP', 7);
  39 define('XML_HTMLSAX_STATE_PI', 8);
  40 /**
  41 * StartingState searches for the start of any XML tag
  42 * @package XML_HTMLSax
  43 * @access protected
  44 */
  45 class XML_HTMLSax_StartingState  {
  46     /**
  47     * @param XML_HTMLSax_StateParser subclass
  48     * @return constant XML_HTMLSAX_STATE_TAG
  49     * @access protected
  50     */
  51     function parse(&$context) {
  52         $data = $context->scanUntilString('<');
  53         if ($data != '') {
  54             $context->handler_object_data->
  55                 {$context->handler_method_data}($context->htmlsax, $data);
  56         }
  57         $context->IgnoreCharacter();
  58         return XML_HTMLSAX_STATE_TAG;
  59     }
  60 }
  61 /**
  62 * Decides which state to move one from after StartingState
  63 * @package XML_HTMLSax
  64 * @access protected
  65 */
  66 class XML_HTMLSax_TagState {
  67     /**
  68     * @param XML_HTMLSax_StateParser subclass
  69     * @return constant the next state to move into
  70     * @access protected
  71     */
  72     function parse(&$context) {
  73         switch($context->ScanCharacter()) {
  74         case '/':
  75             return XML_HTMLSAX_STATE_CLOSING_TAG;
  76             break;
  77         case '?':
  78             return XML_HTMLSAX_STATE_PI;
  79             break;
  80         case '%':
  81             return XML_HTMLSAX_STATE_JASP;
  82             break;
  83         case '!':
  84             return XML_HTMLSAX_STATE_ESCAPE;
  85             break;
  86         default:
  87             $context->unscanCharacter();
  88             return XML_HTMLSAX_STATE_OPENING_TAG;
  89         }
  90     }
  91 }
  92 /**
  93 * Dealing with closing XML tags
  94 * @package XML_HTMLSax
  95 * @access protected
  96 */
  97 class XML_HTMLSax_ClosingTagState {
  98     /**
  99     * @param XML_HTMLSax_StateParser subclass
 100     * @return constant XML_HTMLSAX_STATE_START
 101     * @access protected
 102     */
 103     function parse(&$context) {
 104         $tag = $context->scanUntilCharacters('/>');
 105         if ($tag != '') {
 106             $char = $context->scanCharacter();
 107             if ($char == '/') {
 108                 $char = $context->scanCharacter();
 109                 if ($char != '>') {
 110                     $context->unscanCharacter();
 111                 }
 112             }
 113             $context->handler_object_element->
 114                 {$context->handler_method_closing}($context->htmlsax, $tag, FALSE);
 115         }
 116         return XML_HTMLSAX_STATE_START;
 117     }
 118 }
 119 /**
 120 * Dealing with opening XML tags
 121 * @package XML_HTMLSax
 122 * @access protected
 123 */
 124 class XML_HTMLSax_OpeningTagState {
 125     /**
 126     * Handles attributes
 127     * @param string attribute name
 128     * @param string attribute value
 129     * @return void
 130     * @access protected
 131     * @see XML_HTMLSax_AttributeStartState
 132     */
 133     function parseAttributes(&$context) {
 134         $Attributes = array();
 135
 136         $context->ignoreWhitespace();
 137         $attributename = $context->scanUntilCharacters("=/> \n\r\t");
 138         while ($attributename != '') {
 139             $attributevalue = NULL;
 140             $context->ignoreWhitespace();
 141             $char = $context->scanCharacter();
 142             if ($char == '=') {
 143                 $context->ignoreWhitespace();
 144                 $char = $context->ScanCharacter();
 145                 if ($char == '"') {
 146                     $attributevalue= $context->scanUntilString('"');
 147                     $context->IgnoreCharacter();
 148                 } else if ($char == "'") {
 149                     $attributevalue = $context->scanUntilString("'");
 150                     $context->IgnoreCharacter();
 151                 } else {
 152                     $context->unscanCharacter();
 153                     $attributevalue =
 154                         $context->scanUntilCharacters("> \n\r\t");
 155                 }
 156             } else if ($char !== NULL) {
 157                 $attributevalue = true;
 158                 $context->unscanCharacter();
 159             }
 160             $Attributes[$attributename] = $attributevalue;
 161
 162             $context->ignoreWhitespace();
 163             $attributename = $context->scanUntilCharacters("=/> \n\r\t");
 164         }
 165         return $Attributes;
 166     }
 167
 168     /**
 169     * @param XML_HTMLSax_StateParser subclass
 170     * @return constant XML_HTMLSAX_STATE_START
 171     * @access protected
 172     */
 173     function parse(&$context) {
 174         $tag = $context->scanUntilCharacters("/> \n\r\t");
 175         if ($tag != '') {
 176             $this->attrs = array();
 177             $Attributes = $this->parseAttributes($context);
 178             $char = $context->scanCharacter();
 179             if ($char == '/') {
 180                 $char = $context->scanCharacter();
 181                 if ($char != '>') {
 182                     $context->unscanCharacter();
 183                 }
 184                 $context->handler_object_element->
 185                     {$context->handler_method_opening}($context->htmlsax, $tag,
 186                     $Attributes, TRUE);
 187                 $context->handler_object_element->
 188                     {$context->handler_method_closing}($context->htmlsax, $tag,
 189                     TRUE);
 190             } else {
 191                 $context->handler_object_element->
 192                     {$context->handler_method_opening}($context->htmlsax, $tag,
 193                     $Attributes, FALSE);
 194             }
 195         }
 196         return XML_HTMLSAX_STATE_START;
 197     }
 198 }
 199
 200 /**
 201 * Deals with XML escapes handling comments and CDATA correctly
 202 * @package XML_HTMLSax
 203 * @access protected
 204 */
 205 class XML_HTMLSax_EscapeState {
 206     /**
 207     * @param XML_HTMLSax_StateParser subclass
 208     * @return constant XML_HTMLSAX_STATE_START
 209     * @access protected
 210     */
 211     function parse(&$context) {
 212         if ($context->parser_options['XML_OPTION_FULL_ESCAPES']==0) {
 213             $char = $context->ScanCharacter();
 214             if ($char == '-') {
 215                 $char = $context->ScanCharacter();
 216                 if ($char == '-') {
 217                     $text = $context->scanUntilString('-->');
 218                     $context->IgnoreCharacter();
 219                     $context->IgnoreCharacter();
 220                 } else {
 221                     $context->unscanCharacter();
 222                     $text = $context->scanUntilString('>');
 223                 }
 224             } else if ( $char == '[') {
 225                 $context->scanUntilString('CDATA[');
 226                 for ( $i=0;$i<6;$i++ ) {
 227                     $context->IgnoreCharacter();
 228                 }
 229                 $text = $context->scanUntilString(']]>');
 230                 $context->IgnoreCharacter();
 231                 $context->IgnoreCharacter();
 232             } else {
 233                 $context->unscanCharacter();
 234                 $text = $context->scanUntilString('>');
 235             }
 236         } else {
 237             $text = $context->scanUntilString('>');
 238         }
 239         $context->IgnoreCharacter();
 240         if ($text != '') {
 241             $context->handler_object_escape->
 242             {$context->handler_method_escape}($context->htmlsax, $text);
 243         }
 244         return XML_HTMLSAX_STATE_START;
 245     }
 246 }
 247 /**
 248 * Deals with JASP/ASP markup
 249 * @package XML_HTMLSax
 250 * @access protected
 251 */
 252 class XML_HTMLSax_JaspState {
 253     /**
 254     * @param XML_HTMLSax_StateParser subclass
 255     * @return constant XML_HTMLSAX_STATE_START
 256     * @access protected
 257     */
 258     function parse(&$context) {
 259         $text = $context->scanUntilString('%>');
 260         if ($text != '') {
 261             $context->handler_object_jasp->
 262                 {$context->handler_method_jasp}($context->htmlsax, $text);
 263         }
 264         $context->IgnoreCharacter();
 265         $context->IgnoreCharacter();
 266         return XML_HTMLSAX_STATE_START;
 267     }
 268 }
 269 /**
 270 * Deals with XML processing instructions
 271 * @package XML_HTMLSax
 272 * @access protected
 273 */
 274 class XML_HTMLSax_PiState {
 275     /**
 276     * @param XML_HTMLSax_StateParser subclass
 277     * @return constant XML_HTMLSAX_STATE_START
 278     * @access protected
 279     */
 280     function parse(&$context) {
 281         $target = $context->scanUntilCharacters(" \n\r\t");
 282         $data = $context->scanUntilString('?>');
 283         if ($data != '') {
 284             $context->handler_object_pi->
 285             {$context->handler_method_pi}($context->htmlsax, $target, $data);
 286         }
 287         $context->IgnoreCharacter();
 288         $context->IgnoreCharacter();
 289         return XML_HTMLSAX_STATE_START;
 290     }
 291 }
 292 ?>