| Index: trunk/wiki2xml/php/xml2xhtml.php |
| — | — | @@ -139,7 +139,6 @@ |
| 140 | 140 | function tag_extension ( $open , &$attrs ) { |
| 141 | 141 | if( !defined( 'MEDIAWIKI' ) ) return ; # Only as MediaWiki extension |
| 142 | 142 | |
| 143 | | - |
| 144 | 143 | if ( $open ) { |
| 145 | 144 | $this->extension_name = $attrs['EXTENSION_NAME'] ; |
| 146 | 145 | $this->extension_attrs = $attrs ; |
| — | — | @@ -158,6 +157,7 @@ |
| 159 | 158 | if ( $extension_text == "" ) $extension_text = "<{$this->extension_name}/>" ; |
| 160 | 159 | else $extension_text = "<{$this->extension_name}>{$extension_text}</{$this->extension_name}>" ; |
| 161 | 160 | $options = new ParserOptions ; |
| | 161 | + |
| 162 | 162 | $s = $wgParser->parse ( $extension_text , $wgTitle , $options , false ) ; |
| 163 | 163 | $this->add ( $s->getText() ) ; |
| 164 | 164 | } |
| — | — | @@ -509,4 +509,4 @@ |
| 510 | 510 | xml_parser_free($xml_parser_handle); |
| 511 | 511 | } |
| 512 | 512 | |
| 513 | | -?> |
| \ No newline at end of file |
| | 513 | +?> |
| Index: trunk/wiki2xml/php/wiki2xml.php |
| — | — | @@ -20,6 +20,7 @@ |
| 21 | 21 | "s" => "xhtml:s", |
| 22 | 22 | "p" => "xhtml:p", |
| 23 | 23 | "br" => "xhtml:br", |
| | 24 | + "em" => "xhtml:em", |
| 24 | 25 | "div" => "xhtml:div", |
| 25 | 26 | "span" => "xhtml:span", |
| 26 | 27 | "big" => "xhtml:big", |
| — | — | @@ -289,7 +290,9 @@ |
| 290 | 291 | $between = str_replace ( "<includeonly>" , "" , $between ) ; |
| 291 | 292 | $between = str_replace ( "</includeonly>" , "" , $between ) ; |
| 292 | 293 | |
| 293 | | - # Replacing template variables. ATTENTION: Template variables within <nowiki> sections of templates will be replaced as well! |
| | 294 | + # Replacing template variables. |
| | 295 | + # ATTENTION: Template variables within <nowiki> sections of templates will be replaced as well! |
| | 296 | + |
| 294 | 297 | $this->replace_template_variables ( $between , $variables ) ; |
| 295 | 298 | |
| 296 | 299 | # Change source (!) |
| — | — | @@ -739,11 +742,13 @@ |
| 740 | 743 | function p_html ( &$a , &$xml ) |
| 741 | 744 | { |
| 742 | 745 | if ( !$this->nextis ( $a , "<" , false ) ) return false ; |
| | 746 | + |
| 743 | 747 | $b = $a ; |
| 744 | 748 | $x = "" ; |
| 745 | 749 | $tag = "" ; |
| 746 | 750 | $closing = false ; |
| 747 | 751 | $selfclosing = false ; |
| | 752 | + |
| 748 | 753 | if ( !$this->p_html_tag ( $b , $x , $tag , $closing , $selfclosing ) ) return false ; |
| 749 | 754 | |
| 750 | 755 | if ( isset ( $this->directhtmltags[$tag] ) ) |
| — | — | @@ -793,6 +798,7 @@ |
| 794 | 799 | |
| 795 | 800 | # What happens in between? |
| 796 | 801 | $between = substr ( $this->w , $begin , $last - $begin ) ; |
| | 802 | + |
| 797 | 803 | if ( $tag != "pre" && $tag != "nowiki" && $tag != "math" ) |
| 798 | 804 | { |
| 799 | 805 | if ( $tag == 'gallery' ) { |
| — | — | @@ -891,7 +897,7 @@ |
| 892 | 898 | $selfclosing = true ; |
| 893 | 899 | } |
| 894 | 900 | |
| 895 | | - # Parsing arrtibutes |
| | 901 | + # Parsing attributes |
| 896 | 902 | $ob = $b ; |
| 897 | 903 | $q = "" ; |
| 898 | 904 | while ( $q != "" || ( $b < $this->wl && $this->w[$b] != '>' && $this->w[$b] != '/' ) ) { |
| Index: trunk/wiki2xml/php/README |
| — | — | @@ -20,8 +20,38 @@ |
| 21 | 21 | |
| 22 | 22 | svn co http://svn.wikimedia.org/svnroot/mediawiki/trunk/wiki2xml |
| 23 | 23 | |
| 24 | | -=head2 Copy files |
| | 24 | +=head2 Extension or cgi-bin? |
| 25 | 25 | |
| | 26 | +There are two ways to install wiki2xml: |
| | 27 | + |
| | 28 | + As extension: Special::Wiki2XML |
| | 29 | + As cgi-bin: http://example.com/wiki/wiki2xml/w2x |
| | 30 | + |
| | 31 | +The former should be prefered. |
| | 32 | + |
| | 33 | +=head2 As Extension |
| | 34 | + |
| | 35 | +To enable wiki2xml as extension, put all files in the C<< php >> directory into a |
| | 36 | +C<< wiki2xml >> subdirectory of your MediaWiki extensions directory. |
| | 37 | + |
| | 38 | + htdocs |
| | 39 | + \- wiki |
| | 40 | + \- extensions |
| | 41 | + \- wiki2xml <-- create this directory |
| | 42 | + \- w2x.php <-- copy files here |
| | 43 | + \- wiki2xml.php etc. |
| | 44 | + |
| | 45 | +Then add |
| | 46 | + |
| | 47 | + require_once ("extensions/wiki2xml/extension.php"); |
| | 48 | + |
| | 49 | +to your C<< LocalSettings.php >>. The extension can then be accessed as |
| | 50 | +C<< [[Special:Wiki2XML]] >>. |
| | 51 | + |
| | 52 | +=head2 cgi-bin - Copy files |
| | 53 | + |
| | 54 | +The alternative method is to install wiki2xml as cgi-bin script: |
| | 55 | + |
| 26 | 56 | Copy the subdirectory C<< ./php/ >> to your server's C<< wiki/ >> |
| 27 | 57 | directory as a subdirectory named C<< w2x >>: |
| 28 | 58 | |
| — | — | @@ -31,6 +61,8 @@ |
| 32 | 62 | \- w2x.php |
| 33 | 63 | \- wiki2xml.php etc |
| 34 | 64 | |
| | 65 | +Access it as C<< http://example.com/wiki/w2x/w2x.php >>. |
| | 66 | + |
| 35 | 67 | =head2 Configuration |
| 36 | 68 | |
| 37 | 69 | The configuration is stored in C<< default.php >> and C<< local.php >>. |
| — | — | @@ -55,43 +87,31 @@ |
| 56 | 88 | |
| 57 | 89 | =head1 USAGE |
| 58 | 90 | |
| 59 | | -Open the following in your browser: |
| | 91 | +Open the correct URL (depending on install type, see above) in your browser. |
| 60 | 92 | |
| 61 | | - http://example.com/wiki/w2x/w2x.php |
| | 93 | +Wiki2xml should present you with a form with a textarea and several buttons. |
| 62 | 94 | |
| 63 | | -It should present you with a form with a textarea and several buttons. |
| 64 | | - |
| 65 | 95 | =head2 Using URL parameters |
| 66 | 96 | |
| 67 | | -Parameters:
|
| 68 | | -doit=1
|
| 69 | | -text=lines_of_text_or_titles
|
| 70 | | -whatsthis=wikitext/articlelist
|
| 71 | | -site=en.wikipedia.org/w
|
| 72 | | -output_format=xml/text/xhtml/docbook_xml/odt_xml/odt
|
| 73 | | -
|
| 74 | | -Optional:
|
| 75 | | -use_templates=all/none/these/notthese
|
| 76 | | -templates=lines_of_templates
|
| 77 | | -document_title=
|
| 78 | | -add_gfdl=1
|
| 79 | | -keep_categories=1
|
| 80 | | -keep_interlanguage=1
|
| | 97 | +Parameters: |
| 81 | 98 | |
| | 99 | + doit=1 |
| | 100 | + text=lines_of_text_or_titles |
| | 101 | + whatsthis=wikitext/articlelist |
| | 102 | + site=en.wikipedia.org/w |
| | 103 | + output_format=xml/text/xhtml/docbook_xml/odt_xml/odt |
| 82 | 104 | |
| 83 | | -=head1 EXTENSION |
| | 105 | +Optional: |
| 84 | 106 | |
| 85 | | -To enable this as extension, put all files in the C<< php >> directory into a |
| 86 | | -C<< wiki2xml >> subdirectory of your MediaWiki extensions directory. |
| | 107 | + use_templates=all/none/these/notthese |
| | 108 | + templates=lines_of_templates |
| | 109 | + document_title= |
| | 110 | + add_gfdl=1 |
| | 111 | + keep_categories=1 |
| | 112 | + keep_interlanguage=1 |
| | 113 | + |
| 87 | 114 | |
| 88 | | -Then add |
| 89 | 115 | |
| 90 | | - require_once ("extensions/wiki2xml/extension.php"); |
| 91 | | - |
| 92 | | -to your C<< LocalSettings.php >>. The extension can then be accessed as |
| 93 | | -C<< [[Special:Wiki2XML]] >>. |
| 94 | | - |
| 95 | | - |
| 96 | 116 | =head1 TROUBLESHOOTING |
| 97 | 117 | |
| 98 | 118 | If you get errors like the following: |
| Index: trunk/wiki2xml/php/w2x.php |
| — | — | @@ -124,6 +124,22 @@ |
| 125 | 125 | } |
| 126 | 126 | } |
| 127 | 127 | |
| | 128 | +# add one article to the stack of to-be-converted articles |
| | 129 | +function push_article ( &$aArticles, $article ) { |
| | 130 | + |
| | 131 | + # convert _ to ' ' |
| | 132 | + $a = trim( $article ); |
| | 133 | + if ( $a != "" ) { |
| | 134 | + $aArticles[] = preg_replace( '/_/', ' ', $a ); |
| | 135 | + } |
| | 136 | + |
| | 137 | +} |
| | 138 | + |
| | 139 | +# remove one article from the stack of to-be-converted articles |
| | 140 | +function pop_article ( $aArticles ) { |
| | 141 | + return array_pop ( $aArticles ) ; |
| | 142 | +} |
| | 143 | + |
| 128 | 144 | ## MAIN PROGRAM |
| 129 | 145 | |
| 130 | 146 | if ( get_param('doit',false) ) { # Process |
| — | — | @@ -143,6 +159,9 @@ |
| 144 | 160 | $xmlg['add_gfdl'] = get_param('add_gfdl',false) ; |
| 145 | 161 | $xmlg['keep_interlanguage'] = get_param('keep_interlanguage',false) ; |
| 146 | 162 | $xmlg['keep_categories'] = get_param('keep_categories',false) ; |
| | 163 | + |
| | 164 | + # the article list |
| | 165 | + $aArticles = array () ; |
| 147 | 166 | |
| 148 | 167 | $t = microtime_float() ; |
| 149 | 168 | $xml = "" ; |
| — | — | @@ -150,28 +169,33 @@ |
| 151 | 170 | $wiki2xml_authors = array () ; |
| 152 | 171 | $xml = $converter->article2xml ( "" , $wikitext , $xmlg ) ; |
| 153 | 172 | } else { |
| 154 | | - $t = microtime_float() ; |
| 155 | | - $articles = explode ( "\n" , $wikitext ) ; |
| | 173 | + foreach ( explode ( "\n" , $wikitext ) AS $a ) { |
| | 174 | + push_article( &$aArticles, $a ); |
| | 175 | + } |
| | 176 | + |
| | 177 | + # set the first article name as the default title |
| 156 | 178 | if ($xmlg["book_title"] == '') { |
| 157 | | - $xmlg["book_title"] = $articles[0]; |
| | 179 | + $xmlg["book_title"] = $aArticles[0]; |
| 158 | 180 | } |
| 159 | | - foreach ( $articles AS $a ) { |
| | 181 | + # as long as we have articles to convert (this might change in between!) |
| | 182 | + while ( $a = array_shift( $aArticles ) ) { |
| 160 | 183 | $wiki2xml_authors = array () ; |
| 161 | | - $a = trim ( $a ) ; |
| 162 | | - if ( $a == "" ) continue ; |
| | 184 | + |
| | 185 | + # Article page|Article name |
| 163 | 186 | $a = explode ( '|' , $a ) ; |
| 164 | 187 | if ( count ( $a ) == 1 ) $a[] = $a[0] ; |
| 165 | 188 | $title_page = trim ( array_shift ( $a ) ) ; |
| 166 | 189 | $title_name = trim ( array_pop ( $a ) ) ; |
| | 190 | + |
| 167 | 191 | $wikitext = $content_provider->get_wiki_text ( $title_page ) ; |
| 168 | 192 | add_authors ( $content_provider->authors ) ; |
| 169 | | - $xml .= $converter->article2xml ( $title_name , $wikitext , $xmlg ) ; |
| | 193 | + $xml .= $converter->article2xml ( $title_name , $wikitext , $xmlg, &$aArticles ) ; |
| 170 | 194 | } |
| 171 | 195 | } |
| 172 | 196 | $t = microtime_float() - $t ; |
| 173 | | - $tt = $t ; |
| 174 | | - $lt = $content_provider->load_time ; |
| 175 | | - $t -= $lt ; |
| | 197 | + $tt = round( $t, 3 ) ; |
| | 198 | + $lt = round( $content_provider->load_time, 3 ) ; |
| | 199 | + $t = round( $t - $lt, 3) ; |
| 176 | 200 | |
| 177 | 201 | $xml = "<articles xmlns:xhtml=\" \" loadtime='{$lt} sec' rendertime='{$t} sec' totaltime='{$tt} sec'>\n{$xml}\n</articles>" ; |
| 178 | 202 | |
| Index: trunk/wiki2xml/php/content_provider.php |
| — | — | @@ -19,12 +19,14 @@ |
| 20 | 20 | return in_array ( $title , $this->article_list ) ; |
| 21 | 21 | } |
| 22 | 22 | |
| 23 | | - /** |
| 24 | | - * Gets the numeric namespace |
| 25 | | - * "-8" = category link |
| 26 | | - * "-9" = interlanguage link |
| 27 | | - */ |
| 28 | | - function get_namespace_id ( $text ) { |
| | 23 | + /** |
| | 24 | + * XXX TODO: why are some negative? |
| | 25 | + * Gets the numeric namespace |
| | 26 | + * "6" = images |
| | 27 | + * "-8" = category link |
| | 28 | + * "-9" = interlanguage link |
| | 29 | + * "11" = templates |
| | 30 | + */ function get_namespace_id ( $text ) { |
| 29 | 31 | $text = strtoupper ( $text ) ; |
| 30 | 32 | $text = explode ( ":" , $text , 2 ) ; |
| 31 | 33 | if ( count ( $text ) != 2 ) return 0 ; |
| — | — | @@ -38,6 +40,7 @@ |
| 39 | 41 | |
| 40 | 42 | # Horrible manual hack, for now |
| 41 | 43 | if ( $text == "IMAGE" || $text == "BILD" ) $ns = 6 ; |
| | 44 | + if ( $text == "TEMPLATE" || $text == "VORLAGE" ) $ns = 11 ; |
| 42 | 45 | |
| 43 | 46 | return $ns ; |
| 44 | 47 | } |
| — | — | @@ -276,7 +279,8 @@ |
| 277 | 280 | |
| 278 | 281 | } |
| 279 | 282 | |
| 280 | | -# Access through text file structure |
| | 283 | +# Access through MySQL interface |
| | 284 | +# (Used via the extension via Special::wiki2XML) |
| 281 | 285 | class ContentProviderMySQL extends ContentProviderHTTP { |
| 282 | 286 | |
| 283 | 287 | function do_get_contents ( $title ) { |
| — | — | @@ -301,15 +305,13 @@ |
| 302 | 306 | } |
| 303 | 307 | |
| 304 | 308 | function get_page_text ( $page , $allow_redirect = true ) { |
| 305 | | - /* |
| 306 | | - $filename = $this->get_file_location ( 0 , $page ) ; |
| 307 | | - $filename = $filename->fullname . $this->file_ending ; |
| 308 | | - if ( !file_exists ( $filename ) ) return "" ; |
| 309 | | - $text = trim ( file_get_contents ( $filename ) ) ; |
| 310 | | - */ |
| 311 | | - |
| 312 | 309 | $title = Title::newFromText ( $page ) ; |
| 313 | 310 | $article = new Article ( $title ) ; |
| | 311 | + |
| | 312 | + # article does not exist? |
| | 313 | + if (!$article->exists()) { |
| | 314 | + return ""; |
| | 315 | + } |
| 314 | 316 | $text = $article->getContent () ; |
| 315 | 317 | |
| 316 | 318 | # REDIRECT? |