| 1 | <?php
|
|---|
| 2 | # Copyright by Magnus Manske (2005 - 2006)
|
|---|
| 3 | # Released under GPL
|
|---|
| 4 |
|
|---|
| 5 | @set_time_limit ( 0 ) ; # No time limit
|
|---|
| 6 | ini_set ('memory_limit', 1024*1024*64); # 64MB upper limit
|
|---|
| 7 | ini_set('user_agent','MSIE 4\.0b2;'); # Fake user agent
|
|---|
| 8 |
|
|---|
| 9 | if( !defined( 'MEDIAWIKI' ) ) { # Stand-alone
|
|---|
| 10 | include_once ( "default.php" ) ; # Which will include local.php, if available
|
|---|
| 11 | }
|
|---|
| 12 |
|
|---|
| 13 | require_once ( "mediawiki_converter.php" ) ;
|
|---|
| 14 |
|
|---|
| 15 | ## TIMER FUNCTION
|
|---|
| 16 |
|
|---|
| 17 | function microtime_float()
|
|---|
| 18 | {
|
|---|
| 19 | list($usec, $sec) = explode(" ", microtime());
|
|---|
| 20 | return ((float)$usec + (float)$sec);
|
|---|
| 21 | }
|
|---|
| 22 |
|
|---|
| 23 | function get_form ( $as_extension = false ) {
|
|---|
| 24 | global $xmlg ;
|
|---|
| 25 |
|
|---|
| 26 | $_wt = get_param ( 'whatsthis' , 'articlelist' ) ;
|
|---|
| 27 | $wt['wikitext'] = $wt['articlelist'] = $wt['listpagename'] = "" ;
|
|---|
| 28 | $wt[$_wt] = 'checked' ;
|
|---|
| 29 |
|
|---|
| 30 | $xmlg["site_base_url"] = get_param('site',$xmlg["site_base_url"]) ;
|
|---|
| 31 | $_out = get_param ( 'output_format' , 'xml' ) ;
|
|---|
| 32 | $out['xml'] = $out['text'] = $out['translated_text'] = $out['xhtml'] = $out['docbook_xml'] = $out['docbook_pdf'] = $out['docbook_html'] =
|
|---|
| 33 | $out['odt_xml'] = $out['odt'] = '' ;
|
|---|
| 34 | $out[$_out] = 'checked' ;
|
|---|
| 35 | $useapi_checked = $xmlg["useapi"] ? 'checked' : '' ;
|
|---|
| 36 |
|
|---|
| 37 | $optional = array () ;
|
|---|
| 38 | if ( isset ( $xmlg['docbook']['command_pdf'] ) ) {
|
|---|
| 39 | $optional[] = "<INPUT {$out['docbook_pdf']} type='radio' name='output_format' value='docbook_pdf'>DocBook PDF" ;
|
|---|
| 40 | }
|
|---|
| 41 | if ( isset ( $xmlg['docbook']['command_html'] ) ) {
|
|---|
| 42 | $optional[] = "<INPUT {$out['docbook_html']} type='radio' name='output_format' value='docbook_html'>DocBook HTML" ;
|
|---|
| 43 | }
|
|---|
| 44 | if ( isset ( $xmlg['zip_odt'] ) ) {
|
|---|
| 45 | $optional[] = "<INPUT {$out['odt_xml']} type='radio' name='output_format' value='odt_xml'>OpenOffice XML" ;
|
|---|
| 46 | $optional[] = "<INPUT {$out['odt']} type='radio' name='output_format' value='odt'>OpenOffice ODT" .
|
|---|
| 47 | "<input type='checkbox' name='odt_footnote' value='1' ".(get_param('odt_footnote',false)?'checked':'').">References as endnotes (instead of footnotes)" ;
|
|---|
| 48 | }
|
|---|
| 49 | $optional = "<br/>" . implode ( "<br/>" , $optional ) ;
|
|---|
| 50 |
|
|---|
| 51 | # dub sez... working images
|
|---|
| 52 | if ( $as_extension ) $site = "<input type='hidden' name='site' value='".$xmlg["site_base_url"]."'/>" ;
|
|---|
| 53 | else $site = "Site : http://<input type='text' name='site' value='".$xmlg["site_base_url"]."'/>/index.php<br/>" ;
|
|---|
| 54 |
|
|---|
| 55 | $additional = array() ;
|
|---|
| 56 | if ( $xmlg['allow_get'] ) {
|
|---|
| 57 | $additional[] = "This page can be called with parameters: w2x.php?doit=1&whatsthis=articlelist&site=en.wikipedia.org/w&output_format=odt&text=Biochemistry" ;
|
|---|
| 58 | $additional[] = "For additional parameters, see <a href='README'>here</a>" ;
|
|---|
| 59 | }
|
|---|
| 60 |
|
|---|
| 61 | # Plain text translation options
|
|---|
| 62 | $a = array (
|
|---|
| 63 | 'en' => 'English',
|
|---|
| 64 | 'de' => 'German',
|
|---|
| 65 | 'fr' => 'French',
|
|---|
| 66 | 'es' => 'Spanish',
|
|---|
| 67 | 'it' => 'Italian',
|
|---|
| 68 | ) ;
|
|---|
| 69 | asort ( $a ) ;
|
|---|
| 70 | $tttlo = "" ;
|
|---|
| 71 | foreach ( $a AS $b => $c ) {
|
|---|
| 72 | $tttlo .= "<option value='{$b}'>{$c}</option>" ;
|
|---|
| 73 | }
|
|---|
| 74 |
|
|---|
| 75 | $additional = "<div style='text-align:center; border-top:1px solid black;width:100%;font-size:12px'>" .
|
|---|
| 76 | implode ( "<br/>" , $additional ) .
|
|---|
| 77 | "</div>" ;
|
|---|
| 78 |
|
|---|
| 79 | return "<form method='post'>
|
|---|
| 80 | <h2>Paste article list or wikitext here</h2>
|
|---|
| 81 | <table border='0' width='100%'><tr>
|
|---|
| 82 | <td valign='top'><textarea rows='20' cols='80' style='width:100%' name='text'>" .
|
|---|
| 83 | get_param ( 'text' , '' ) .
|
|---|
| 84 | "</textarea></td>
|
|---|
| 85 | <td width='200px' valign='top' nowrap>
|
|---|
| 86 | <INPUT checked type='radio' name='use_templates' value='all'>Use all templates<br/>
|
|---|
| 87 | <INPUT type='radio' name='use_templates' value='none'>Do not use templates<br/>
|
|---|
| 88 | <INPUT type='radio' name='use_templates' value='these'>Use these templates<br/>
|
|---|
| 89 | <INPUT type='radio' name='use_templates' value='notthese'>Use all but these templates<br/>
|
|---|
| 90 | <textarea rows='15' cols='30' style='width:100%' name='templates'></textarea>
|
|---|
| 91 | </td></tr></table>
|
|---|
| 92 | <table border='0'><tr>
|
|---|
| 93 | <td valign='top'>
|
|---|
| 94 | This is<br/>
|
|---|
| 95 | <INPUT {$wt['wikitext']} type='radio' name='whatsthis' value='wikitext'>raw wikitext <br/>
|
|---|
| 96 | <INPUT {$wt['articlelist']} type='radio' name='whatsthis' value='articlelist'>a list of articles<br/>
|
|---|
| 97 | <INPUT {$wt['listpagename']} type='radio' name='whatsthis' value='listpagename'>the name of an article with a list of pages<br/>
|
|---|
| 98 |
|
|---|
| 99 | {$site}
|
|---|
| 100 | <input type='checkbox' name='useapi' value='1' id='useapi' $useapi_checked /><label for='useapi'>Use API</label><br/>
|
|---|
| 101 | Title : <input type='text' name='document_title' value='' size=40/><br/>
|
|---|
| 102 | <input type='checkbox' name='add_gfdl' value='1' checked>Include GFDL (for some output formats)</input><br/>
|
|---|
| 103 | <input type='checkbox' name='keep_categories' value='1' checked>Keep categories</input><br/>
|
|---|
| 104 | <input type='checkbox' name='keep_interlanguage' value='1' checked>Keep interlanguage links</input><br/>
|
|---|
| 105 | <input type='submit' name='doit' value='Convert'/>
|
|---|
| 106 | </td><td valign='top' style='border-left:1px black solid'>
|
|---|
| 107 | <b>Output</b>
|
|---|
| 108 | <br/><INPUT {$out['xml']} type='radio' name='output_format' value='xml'>XML
|
|---|
| 109 | <br/><INPUT {$out['text']} type='radio' name='output_format' value='text'>Plain text
|
|---|
| 110 | <input type='checkbox' name='plaintext_markup' value='1' ".(get_param('plaintext_markup',true)?'checked':'').">Use *_/ markup</input>
|
|---|
| 111 | <input type='checkbox' name='plaintext_prelink' value='1' ".(get_param('plaintext_prelink',true)?'checked':'').">Put → before internal links</input>
|
|---|
| 112 | <br/><INPUT {$out['translated_text']} type='radio' name='output_format' value='translated_text'>Plain text, google-translated to
|
|---|
| 113 | <select name='translated_text_target_language'>{$tttlo}</select> (works only for wikipedia/wikibooks)
|
|---|
| 114 | <br/><INPUT {$out['xhtml']} type='radio' name='output_format' value='xhtml'>XHTML
|
|---|
| 115 | <input type='checkbox' name='xhtml_justify' value='1' ".(get_param('xhtml_justify',true)?'checked':'').">Align paragraphs as 'justify'</input>
|
|---|
| 116 | <input type='checkbox' name='xhtml_logical_markup' value='1' ".(get_param('xhtml_logical_markup',true)?'checked':'').">Use logical markup (e.g., 'strong' instead of 'b')</input>
|
|---|
| 117 | <input type='checkbox' name='xhtml_source' value='1' ".(get_param('xhtml_source',false)?'checked':'').">Return source XHTML</input>
|
|---|
| 118 | <br/><INPUT {$out['docbook_xml']} type='radio' name='output_format' value='docbook_xml'>DocBook XML
|
|---|
| 119 | {$optional}
|
|---|
| 120 | </tr></table>
|
|---|
| 121 | </form>
|
|---|
| 122 | <p>
|
|---|
| 123 | Known issues:
|
|---|
| 124 | <ul>
|
|---|
| 125 | <li>In templates, {{{variables}}} used within <nowiki> tags will be replaced as well (too lazy to strip them)</li>
|
|---|
| 126 | <li>HTML comments are removed (instead of converted into XML tags)</li>
|
|---|
| 127 | </ul>{$additional}
|
|---|
| 128 | </p>" ;
|
|---|
| 129 | }
|
|---|
| 130 |
|
|---|
| 131 | function get_param ( $s , $default = NULL ) {
|
|---|
| 132 | global $xmlg ;
|
|---|
| 133 | if ( $xmlg['allow_get'] ) {
|
|---|
| 134 | if ( isset ( $_REQUEST[$s] ) ) {
|
|---|
| 135 | return $_REQUEST[$s] ;
|
|---|
| 136 | } else {
|
|---|
| 137 | return $default ;
|
|---|
| 138 | }
|
|---|
| 139 | } else {
|
|---|
| 140 | if ( isset ( $_POST[$s] ) ) {
|
|---|
| 141 | return $_POST[$s] ;
|
|---|
| 142 | } else {
|
|---|
| 143 | return $default ;
|
|---|
| 144 | }
|
|---|
| 145 | }
|
|---|
| 146 | }
|
|---|
| 147 |
|
|---|
| 148 | # add one article to the stack of to-be-converted articles
|
|---|
| 149 | function push_article ( &$aArticles, $article ) {
|
|---|
| 150 |
|
|---|
| 151 | # convert _ to ' '
|
|---|
| 152 | $a = trim( $article );
|
|---|
| 153 | if ( $a != "" ) {
|
|---|
| 154 | $aArticles[] = preg_replace( '/_/', ' ', $a );
|
|---|
| 155 | }
|
|---|
| 156 |
|
|---|
| 157 | }
|
|---|
| 158 |
|
|---|
| 159 | # Append XML, or links to XML temporary files
|
|---|
| 160 | function append_to_xml ( &$xml , $new_xml ) {
|
|---|
| 161 | global $xmlg ;
|
|---|
| 162 | if ( $xmlg["use_xml_temp_files"] ) { # Use temp files
|
|---|
| 163 | if ( !is_array ( $xml ) ) $xml = array () ;
|
|---|
| 164 |
|
|---|
| 165 | do {
|
|---|
| 166 | $tmp_file_name = tempnam ( $xmlg["temp_dir"] , "XMLTMP" ) ;
|
|---|
| 167 | $tmp_file = fopen($tmp_file_name, 'wb') ;
|
|---|
| 168 | } while ( $tmp_file === false ) ;
|
|---|
| 169 | fwrite ( $tmp_file , $new_xml ) ;
|
|---|
| 170 | fclose ( $tmp_file ) ;
|
|---|
| 171 |
|
|---|
| 172 | $xml[] = $tmp_file_name ;
|
|---|
| 173 | } else { # Do not use temp files
|
|---|
| 174 | $xml .= $new_xml ;
|
|---|
| 175 | }
|
|---|
| 176 | }
|
|---|
| 177 |
|
|---|
| 178 | # Returns the next article XML, or false
|
|---|
| 179 | function xml_shift ( &$xml ) {
|
|---|
| 180 | if ( !is_array ( $xml ) ) { # Do not use temp files
|
|---|
| 181 | if ( $xml != '' ) {
|
|---|
| 182 | $x = $xml ;
|
|---|
| 183 | $xml = array () ;
|
|---|
| 184 | return $x ;
|
|---|
| 185 | }
|
|---|
| 186 | return false ;
|
|---|
| 187 | } else { # Use temp files
|
|---|
| 188 | if ( count ( $xml ) == 0 ) return false ;
|
|---|
| 189 | $x = array_shift ( $xml ) ;
|
|---|
| 190 | $ret = file_get_contents ( $x ) ;
|
|---|
| 191 | unlink ( $x ) ;
|
|---|
| 192 | return $ret ;
|
|---|
| 193 | }
|
|---|
| 194 | }
|
|---|
| 195 |
|
|---|
| 196 | # Free temporary XML files, if any
|
|---|
| 197 | # Should not be necessary if xml_shift was used
|
|---|
| 198 | function xml_cleanup ( &$xml ) {
|
|---|
| 199 | global $xmlg ;
|
|---|
| 200 | if ( !$xmlg["use_xml_temp_files"] ) return ; # not using temp files
|
|---|
| 201 | if ( !is_array ( $xml ) ) return false ;
|
|---|
| 202 | foreach ( $xml AS $x ) {
|
|---|
| 203 | unlink ( $x ) ;
|
|---|
| 204 | }
|
|---|
| 205 | $xml = array () ;
|
|---|
| 206 | }
|
|---|
| 207 |
|
|---|
| 208 |
|
|---|
| 209 | ## MAIN PROGRAM
|
|---|
| 210 |
|
|---|
| 211 | if ( get_param('doit',false) ) { # Process
|
|---|
| 212 | $wikitext = stripslashes ( get_param('text') ) ;
|
|---|
| 213 |
|
|---|
| 214 | if( !defined( 'MEDIAWIKI' ) ) { # Stand-alone
|
|---|
| 215 | $content_provider = new ContentProviderHTTP ;
|
|---|
| 216 | } else { # MediaWiki extension
|
|---|
| 217 | $content_provider = new ContentProviderMySQL ;
|
|---|
| 218 | }
|
|---|
| 219 | $converter = new MediaWikiConverter ;
|
|---|
| 220 |
|
|---|
| 221 | $xmlg["useapi"] = isset ( $_REQUEST['useapi'] ) ;
|
|---|
| 222 | $xmlg["book_title"] = get_param('document_title');
|
|---|
| 223 | $xmlg["site_base_url"] = get_param('site') ;
|
|---|
| 224 | $xmlg["resolvetemplates"] = get_param('use_templates','all') ;
|
|---|
| 225 | $xmlg['templates'] = explode ( "\n" , get_param('templates','') ) ;
|
|---|
| 226 | $xmlg['add_gfdl'] = get_param('add_gfdl',false) ;
|
|---|
| 227 | $xmlg['keep_interlanguage'] = get_param('keep_interlanguage',false) ;
|
|---|
| 228 | $xmlg['keep_categories'] = get_param('keep_categories',false) ;
|
|---|
| 229 |
|
|---|
| 230 | # the article list
|
|---|
| 231 | $aArticles = array () ;
|
|---|
| 232 |
|
|---|
| 233 | $t = microtime_float() ;
|
|---|
| 234 | $xml = "" ;
|
|---|
| 235 |
|
|---|
| 236 | $format = get_param('output_format') ;
|
|---|
| 237 | $whatsthis = get_param('whatsthis') ;
|
|---|
| 238 |
|
|---|
| 239 | # Catch listnamepage
|
|---|
| 240 | if ( $whatsthis == "listpagename" ) {
|
|---|
| 241 | $listpage = trim ( array_shift ( explode ( "\n" , $wikitext ) ) ) ;
|
|---|
| 242 | $wikitext = $content_provider->get_wiki_text ( $listpage ) ;
|
|---|
| 243 | $lines = explode ( "\n" , $wikitext ) ;
|
|---|
| 244 | $wikitext = array () ;
|
|---|
| 245 | foreach ( $lines AS $l ) {
|
|---|
| 246 | $l1 = substr ( $l , 0 , 1 ) ;
|
|---|
| 247 | if ( $l1 != '*' && $l1 != '#' && $l1 != ':' ) continue ;
|
|---|
| 248 | $l = explode ( '[[' , $l , 2 ) ;
|
|---|
| 249 | $l = trim ( array_shift ( explode ( ']]' , array_pop ( $l ) , 2 ) ) ) ;
|
|---|
| 250 | if ( $l == '' ) continue ;
|
|---|
| 251 | $wikitext[] = $l ;
|
|---|
| 252 | }
|
|---|
| 253 | $wikitext = implode ( "\n" , $wikitext ) ;
|
|---|
| 254 | $whatsthis = 'articlelist' ;
|
|---|
| 255 | }
|
|---|
| 256 |
|
|---|
| 257 | # QUICK HACK! NEEDS TO WORK!
|
|---|
| 258 | if ( $format == "odt" || $format == "odt_xml" || $format == "docbook_pdf" || $format == "docbook_html" || $format == "docbook_xml" ) {
|
|---|
| 259 | $xmlg["allow_xml_temp_files"] = false ;
|
|---|
| 260 | }
|
|---|
| 261 |
|
|---|
| 262 | if ( $whatsthis == "wikitext" ) {
|
|---|
| 263 | $content_provider->first_title = "Raw wikitext page" ;
|
|---|
| 264 | $wiki2xml_authors = array () ;
|
|---|
| 265 | $xml = $converter->article2xml ( "" , $wikitext , $xmlg ) ;
|
|---|
| 266 | } else {
|
|---|
| 267 | if ( $xmlg['allow_xml_temp_files'] ) $xmlg['use_xml_temp_files'] = true ;
|
|---|
| 268 |
|
|---|
| 269 | foreach ( explode ( "\n" , $wikitext ) AS $a ) {
|
|---|
| 270 | push_article( $aArticles, $a );
|
|---|
| 271 | }
|
|---|
| 272 |
|
|---|
| 273 | # set the first article name as the default title
|
|---|
| 274 | if ($xmlg["book_title"] == '') {
|
|---|
| 275 | $xmlg["book_title"] = $aArticles[0];
|
|---|
| 276 | }
|
|---|
| 277 | # as long as we have articles to convert (this might change in between!)
|
|---|
| 278 | while ( $a = array_shift( $aArticles ) ) {
|
|---|
| 279 | $wiki2xml_authors = array () ;
|
|---|
| 280 |
|
|---|
| 281 | # Article page|Article name
|
|---|
| 282 | $a = explode ( '|' , $a ) ;
|
|---|
| 283 | if ( count ( $a ) == 1 ) $a[] = $a[0] ;
|
|---|
| 284 | $title_page = trim ( array_shift ( $a ) ) ;
|
|---|
| 285 | $title_name = trim ( array_pop ( $a ) ) ;
|
|---|
| 286 |
|
|---|
| 287 | $wikitext = $content_provider->get_wiki_text ( $title_page ) ;
|
|---|
| 288 | add_authors ( $content_provider->authors ) ;
|
|---|
| 289 | append_to_xml ( $xml , $converter->article2xml ( $title_name , $wikitext , $xmlg, $aArticles ) ) ;
|
|---|
| 290 | #$xml .= $converter->article2xml ( $title_name , $wikitext , $xmlg, &$aArticles ) ;
|
|---|
| 291 | }
|
|---|
| 292 | }
|
|---|
| 293 | $t = microtime_float() - $t ;
|
|---|
| 294 | $tt = round( $t, 3 ) ;
|
|---|
| 295 | $lt = round( $content_provider->load_time, 3 ) ;
|
|---|
| 296 | $t = round( $t - $lt, 3) ;
|
|---|
| 297 |
|
|---|
| 298 | $xmlg['xml_articles_header'] = "<articles xmlns:xhtml=\" \" loadtime='{$lt} sec' rendertime='{$t} sec' totaltime='{$tt} sec'>" ;
|
|---|
| 299 |
|
|---|
| 300 | # Output format
|
|---|
| 301 | if ( $format == "xml" ) {
|
|---|
| 302 | header('Content-type: text/xml; charset=utf-8');
|
|---|
| 303 | print "<?xml version='1.0' encoding='UTF-8' ?>\n" ;
|
|---|
| 304 | print xml_articles_header() ;
|
|---|
| 305 | while ( $x = xml_shift ( $xml ) ) print $x ;
|
|---|
| 306 | print "</articles>" ;
|
|---|
| 307 | } else if ( $format == "text" ) {
|
|---|
| 308 | $xmlg['plaintext_markup'] = get_param('plaintext_markup',false) ;
|
|---|
| 309 | $xmlg['plaintext_prelink'] = get_param('plaintext_prelink',false) ;
|
|---|
| 310 | $out = $converter->articles2text ( $xml , $xmlg ) ;
|
|---|
| 311 | $out = str_replace ( "\n" , "<br/>" , $out ) ;
|
|---|
| 312 | header('Content-type: text/html; charset=utf-8');
|
|---|
| 313 | print $out ;
|
|---|
| 314 |
|
|---|
| 315 | } else if ( $format == "translated_text" ) {
|
|---|
| 316 | $xmlg['plaintext_markup'] = false ;
|
|---|
| 317 | $xmlg['plaintext_prelink'] = false ;
|
|---|
| 318 | $out = $converter->articles2text ( $xml , $xmlg ) ;
|
|---|
| 319 | #$out = str_replace ( "\n" , "<br/>" , $out ) ;
|
|---|
| 320 | #header('Content-type: text/html; charset=utf-8');
|
|---|
| 321 | #print $out ;
|
|---|
| 322 | $out = explode ( "\n" , $out ) ;
|
|---|
| 323 | array_shift ( $out ) ;
|
|---|
| 324 | $out = trim ( implode ( "\n" , $out ) ) ;
|
|---|
| 325 | $source_language = array_shift ( explode ( '.' , $xmlg["site_base_url"] ) ) ;
|
|---|
| 326 | $target_language = get_param ( 'translated_text_target_language' , 'en' ) ;
|
|---|
| 327 | $langpair = urlencode ( "{$source_language}|{$target_language}" ) ;
|
|---|
| 328 | $url = "http://www.google.com/translate_t?langpair={$langpair}&text=" . urlencode ( utf8_decode ( $out ) ) ;
|
|---|
| 329 | echo file_get_contents ( $url ) ;
|
|---|
| 330 |
|
|---|
| 331 | } else if ( $format == "xhtml" ) {
|
|---|
| 332 | $xmlg['xhtml_justify'] = get_param ( 'xhtml_justify' , false ) ;
|
|---|
| 333 | $xmlg['xhtml_logical_markup'] = get_param ( 'xhtml_logical_markup' , false ) ;
|
|---|
| 334 | $xmlg['xhtml_source'] = get_param ( 'xhtml_source' , false ) ;
|
|---|
| 335 |
|
|---|
| 336 | if ( $xmlg['xhtml_source'] ) {
|
|---|
| 337 | header('Content-type: text/xml; charset=utf-8');
|
|---|
| 338 | #header('Content-type: text/html; charset=utf-8');
|
|---|
| 339 | $s = $converter->articles2xhtml ( $xml , $xmlg ) ;
|
|---|
| 340 | $s = str_replace ( '>' , ">\n" , $s ) ;
|
|---|
| 341 | $s = str_replace ( '<' , "\n<" , $s ) ;
|
|---|
| 342 | $s = str_replace ( "\n\n" , "\n" , $s ) ;
|
|---|
| 343 | echo trim ( $s ) ;
|
|---|
| 344 | #echo str_replace ( "\n" , '<br/>' , htmlentities ( trim ( $s ) ) ) ;
|
|---|
| 345 | } else {
|
|---|
| 346 | # Header hack for IE
|
|---|
| 347 | if ( stristr($_SERVER["HTTP_ACCEPT"],"application/xhtml+xml") ) {
|
|---|
| 348 | header("Content-type: application/xhtml+xml");
|
|---|
| 349 | } else {
|
|---|
| 350 | header("Content-type: text/html");
|
|---|
| 351 | }
|
|---|
| 352 | echo $converter->articles2xhtml ( $xml , $xmlg ) ;
|
|---|
| 353 | }
|
|---|
| 354 |
|
|---|
| 355 | } else if ( $format == "odt" || $format == "odt_xml" ) {
|
|---|
| 356 | if ( isset ( $_REQUEST['odt_footnote'] ) ) $xmlg["odt_footnote"] = 'endnote' ;
|
|---|
| 357 | if ( $xmlg['sourcedir'] == '.' ) $cwd = getcwd() ;
|
|---|
| 358 | else $cwd = $xmlg['sourcedir'] ;
|
|---|
| 359 | $template_file = $cwd . '/template.odt' ;
|
|---|
| 360 |
|
|---|
| 361 | $dir_file = tempnam($xmlg["temp_dir"], "ODD");
|
|---|
| 362 | $dir = $dir_file . "-DIR" ;
|
|---|
| 363 | $xmlg['image_destination'] = $dir . "/Pictures" ;
|
|---|
| 364 |
|
|---|
| 365 | $zipdir = $cwd ;
|
|---|
| 366 | if ( isset ( $xmlg["zip_odt_path"] ) ) # Windows strange bug workaround
|
|---|
| 367 | $zipdir = $xmlg["zip_odt_path"] ;
|
|---|
| 368 |
|
|---|
| 369 | chdir ( $zipdir ) ;
|
|---|
| 370 |
|
|---|
| 371 | # Unzip template
|
|---|
| 372 | $cmd = $xmlg['unzip_odt'] ;
|
|---|
| 373 | $cmd = str_replace ( '$1' , escapeshellarg ( $template_file ) , $cmd ) ;
|
|---|
| 374 | $cmd = str_replace ( '$2' , escapeshellarg ( $dir ) , $cmd ) ;
|
|---|
| 375 | exec ( $cmd ) ;
|
|---|
| 376 |
|
|---|
| 377 | # Convert XML to ODT
|
|---|
| 378 | chdir ( $cwd ) ;
|
|---|
| 379 | if ( $format == "odt_xml" ) $content_provider->block_file_download = true ;
|
|---|
| 380 | $out = $converter->articles2odt ( $xml , $xmlg ) ;
|
|---|
| 381 | chdir ( $zipdir ) ;
|
|---|
| 382 |
|
|---|
| 383 | # Create ODT structure
|
|---|
| 384 | $handle = fopen ( $dir . "/content.xml" , "w" ) ;
|
|---|
| 385 | if ($handle) {
|
|---|
| 386 | fwrite ( $handle , $out ) ;
|
|---|
| 387 | fclose ( $handle ) ;
|
|---|
| 388 | # Generate temporary ODT file
|
|---|
| 389 | $out_file = tempnam('', "ODT");
|
|---|
| 390 | $cmd = $xmlg['zip_odt'] ;
|
|---|
| 391 | $cmd = str_replace ( '$1' , escapeshellarg ( $out_file ) , $cmd ) ;
|
|---|
| 392 |
|
|---|
| 393 | if ( $xmlg['is_windows'] ) {
|
|---|
| 394 | $cmd = str_replace ( '$2' , escapeshellarg ( $dir . "/" ) , $cmd ) ;
|
|---|
| 395 | } else {
|
|---|
| 396 | $cmd = str_replace ( '$2' , escapeshellarg ( './' ) , $cmd ) ;
|
|---|
| 397 | # linux/unix zip needs to be in the directory, otherwise it will
|
|---|
| 398 | # include needless parts into the directory structure
|
|---|
| 399 | chdir ($dir);
|
|---|
| 400 | # remove the output if it for some reason already exists
|
|---|
| 401 | }
|
|---|
| 402 |
|
|---|
| 403 | @unlink ( $out_file ) ;
|
|---|
| 404 | exec ( $cmd ) ;
|
|---|
| 405 |
|
|---|
| 406 | if ( $format == "odt" ) { # Return ODT file
|
|---|
| 407 | $filename = $xmlg["book_title"] ;
|
|---|
| 408 | if (!preg_match('/\.[a-zA-Z]{3}$/',$filename)) { $filename .= '.odt'; }
|
|---|
| 409 | if (!preg_match('/\.[a-zA-Z]{3}$/',$out_file)) { $out_file .= '.zip'; }
|
|---|
| 410 | header('Content-type: application/vnd.oasis.opendocument.text; charset=utf-8');
|
|---|
| 411 | header('Content-Disposition: inline; filename="'.$filename.'"');
|
|---|
| 412 | # XXX TODO: error handling here
|
|---|
| 413 | $handle = fopen($out_file, 'rb');
|
|---|
| 414 | fpassthru ( $handle ) ;
|
|---|
| 415 | fclose ( $handle ) ;
|
|---|
| 416 | } else { # Return XML
|
|---|
| 417 | header('Content-type: text/xml; charset=utf-8');
|
|---|
| 418 | print str_replace ( ">" , ">\n" , $out ) ;
|
|---|
| 419 | }
|
|---|
| 420 |
|
|---|
| 421 | # Cleanup
|
|---|
| 422 | SureRemoveDir ( $dir ) ;
|
|---|
| 423 | @rmdir ( $dir ) ;
|
|---|
| 424 | @unlink ( $dir_file ) ;
|
|---|
| 425 | @unlink ( $out_file ) ;
|
|---|
| 426 | chdir ( $cwd ) ;
|
|---|
| 427 | } # error occured
|
|---|
| 428 |
|
|---|
| 429 | } else if ( $format == "docbook_xml" ) {
|
|---|
| 430 | $out = $converter->articles2docbook_xml ( $xml , $xmlg ) ;
|
|---|
| 431 | header('Content-type: text/xml; charset=utf-8');
|
|---|
| 432 | print $out ;
|
|---|
| 433 | } else if ( $format == "docbook_pdf" || $format == "docbook_html" ) {
|
|---|
| 434 | $filetype = substr ( $format , 8 ) ;
|
|---|
| 435 | $filename = $converter->articles2docbook_pdf ( $xml , $xmlg , strtoupper ( $filetype ) ) ;
|
|---|
| 436 |
|
|---|
| 437 | if ( file_exists ( $filename ) ) {
|
|---|
| 438 | $fp = fopen($filename, 'rb');
|
|---|
| 439 | if ( $format == "docbook_pdf" ) {
|
|---|
| 440 | header('Content-Type: application/pdf');
|
|---|
| 441 | header("Content-Length: " . (string) filesize($filename));
|
|---|
| 442 | header('Content-Disposition: attachment; filename="'.$xmlg["book_title"].'.pdf"');
|
|---|
| 443 | } else if ( $format == "docbook_html" ) {
|
|---|
| 444 | header('Content-Type: text/html');
|
|---|
| 445 | header("Content-Length: " . (string) filesize($filename));
|
|---|
| 446 | header('Content-Disposition: inline; filename="'.$xmlg["book_title"].'.html"');
|
|---|
| 447 | }
|
|---|
| 448 | fpassthru($fp);
|
|---|
| 449 | fclose ( $fp ) ;
|
|---|
| 450 | }
|
|---|
| 451 |
|
|---|
| 452 | # Cleanup
|
|---|
| 453 | $pdf_dir = dirname ( dirname ( $filename ) ) ;
|
|---|
| 454 | SureRemoveDir ( $pdf_dir ) ;
|
|---|
| 455 | @rmdir ( $pdf_dir ) ;
|
|---|
| 456 | }
|
|---|
| 457 | xml_cleanup ( $xml ) ;
|
|---|
| 458 | exit ;
|
|---|
| 459 | } else { # Show the form
|
|---|
| 460 | if( !defined( 'MEDIAWIKI' ) ) { # Stand-alone
|
|---|
| 461 | header('Content-type: text/html; charset=utf-8');
|
|---|
| 462 | print "
|
|---|
| 463 | <html><head></head><body>
|
|---|
| 464 | <h1>Magnus' magic MediaWiki-to-XML-to-stuff converter</h1>
|
|---|
| 465 | <p>All written in PHP - so portable, <s>so incredibly slow...</s> <i>about as fast as the original MediaWiki parser!</i> <small>(For the source, see <a href='http://www.mediawiki.org/wiki/Subversion'>here</a>, trunk 'wiki2xml', directory 'php')</small></p>" ;
|
|---|
| 466 | $xmlg["useapi"] = 1 ;
|
|---|
| 467 | print get_form () ;
|
|---|
| 468 | print "</body></html>" ;
|
|---|
| 469 | } else { # MediaWiki extension
|
|---|
| 470 | $out = get_form ( true ) ;
|
|---|
| 471 | }
|
|---|
| 472 |
|
|---|
| 473 | }
|
|---|
| 474 |
|
|---|
| 475 | #<input type='checkbox' name='resolvetemplates' value='1' checked>Automatically resolve templates</input><br/>
|
|---|
| 476 |
|
|---|
| 477 | ?>
|
|---|
