[jbossws-commits] JBossWS SVN: r3798 - in projects/wiki: extensions and 3 other directories.

Author: heiko.braun(a)jboss.com Date: 2007-07-04 15:14:29 -0400 (Wed, 04 Jul 2007) New Revision: 3798 Added: projects/wiki/extensions/SpecialPdfPrint.php projects/wiki/extensions/wiki2xml/ projects/wiki/extensions/wiki2xml/CREDITS projects/wiki/extensions/wiki2xml/README projects/wiki/extensions/wiki2xml/TODO projects/wiki/extensions/wiki2xml/browse_texts.php projects/wiki/extensions/wiki2xml/content_provider.php projects/wiki/extensions/wiki2xml/default.php projects/wiki/extensions/wiki2xml/extension.php projects/wiki/extensions/wiki2xml/filter_named_entities.php projects/wiki/extensions/wiki2xml/gfdl.xml projects/wiki/extensions/wiki2xml/global_functions.php projects/wiki/extensions/wiki2xml/mediawiki_converter.php projects/wiki/extensions/wiki2xml/sample_local.php projects/wiki/extensions/wiki2xml/template.odt projects/wiki/extensions/wiki2xml/test.xml projects/wiki/extensions/wiki2xml/w2x.php projects/wiki/extensions/wiki2xml/wiki2xml.php projects/wiki/extensions/wiki2xml/xhtml.xslt projects/wiki/extensions/wiki2xml/xml2docbook_xml.php projects/wiki/extensions/wiki2xml/xml2odt.php projects/wiki/extensions/wiki2xml/xml2tree.php projects/wiki/extensions/wiki2xml/xml2txt.php projects/wiki/extensions/wiki2xml/xml2xhtml.php projects/wiki/extensions/wiki2xml/xmldump2files.php Modified: projects/wiki/LocalSettings.php projects/wiki/skins/Devmo.php projects/wiki/skins/devmo/css/wikiprint.css Log: Add pdf conversion, wiki2xml extensions Modified: projects/wiki/LocalSettings.php =================================================================== --- projects/wiki/LocalSettings.php 2007-07-04 11:33:22 UTC (rev 3797) +++ projects/wiki/LocalSettings.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -147,4 +147,10 @@ $recaptcha_public_key = '6LeaFQAAAAAAANdJOabOzJZc2XIPMX9GaTUeu6zu'; $recaptcha_private_key = '6LeaFQAAAAAAADf35ShIh9BuBytm8o_Vs58VaDQr'; +# PDF export +#require_once("extensions/SpecialPdfPrint.php"); + +# WIKI2XML +require_once ("extensions/wiki2xml/extension.php"); + ?> Added: projects/wiki/extensions/SpecialPdfPrint.php =================================================================== --- projects/wiki/extensions/SpecialPdfPrint.php (rev 0) +++ projects/wiki/extensions/SpecialPdfPrint.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,124 @@ +<?php + +// http://www.mediawiki.org/wiki/Extension:Pdf_Export + +if (!defined('MEDIAWIKI')) die(); +require_once ("$IP/includes/SpecialPage.php"); + +$wgExtensionFunctions[] = 'wfSpecialPdf'; +$wgExtensionCredits['specialpage'][] = array( + 'name' => 'Pdf', + 'author' =>' Thomas Hempel', + 'description' => 'prints a page as pdf', + 'url' => 'http://www.mediawiki.org/wiki/Extension:Pdf_Export' +); + +$wgHooks['SkinTemplateBuildNavUrlsNav_urlsAfterPermalink'][] = 'wfSpecialPdfNav'; + +# The monobook hook doesn't work, i added it straight to the Devmo.php page -> see 'Toolbox' there +#$wgHooks['MonoBookTemplateToolboxEnd'][] = 'wfSpecialPdfToolbox'; + +function wfSpecialPdf() { + global $IP, $wgMessageCache; + + $wgMessageCache->addMessages( + array( + 'pdfprint' => 'PdfPrint' , + 'pdf_print_link' => 'Print as PDF')); + + class SpecialPdf extends SpecialPage { + var $title; + var $article; + var $html; + var $parserOptions; + var $bhtml; + + function SpecialPdf() { + SpecialPage::SpecialPage( 'PdfPrint' ); + } + + function execute( $par ) { + global $wgRequest; + global $wgOut; + global $wgUser; + global $wgParser; + global $wgScriptPath; + global $wgServer; + + $page = isset( $par ) ? $par : $wgRequest->getText( 'page' ); + $title = Title::newFromText( $page ); + $article = new Article ($title); + $wgOut->setPrintable(); + $wgOut->disable(); + $parserOptions = ParserOptions::newFromUser( $wgUser ); + $parserOptions->setEditSection( false ); + $parserOptions->setTidy(true); + $wgParser->mShowToc = false; + $parserOutput = $wgParser->parse( $article->preSaveTransform( $article->getContent() ) ."\n\n", + $title, $parserOptions ); + + $bhtml = $parserOutput->getText(); + $bhtml = utf8_decode($bhtml); + + $bhtml = str_replace ($wgScriptPath, $wgServer . $wgScriptPath, $bhtml); + $bhtml = str_replace ('/w/',$wgServer . '/w/', $bhtml); + + + $html = "<html><head><title>" . utf8_decode($page) . "</title></head>"; + # TODO: somehow we need to tweak the styles here + $html .= "<link rel=\"stylesheet\" type=\"text/css\" media=\"all\" href=\"http://localhost/mediawiki/skins/devmo/css/base.css\">"; + $html .= "<link rel=\"stylesheet\" type=\"text/css\" media=\"all\" href=\"http://localhost/mediawiki/skins/devmo/css/wiki.css\">"; + $html .= "<link rel=\"stylesheet\" type=\"text/css\" media=\"all\" href=\"http://localhost/mediawiki/skins/devmo/css/wikiprint.css\">"; + $html .= "<body>" . $bhtml . "</body></html>"; + + // make a temporary directory with an unique name + $mytemp = "/tmp/f" .time(). "-" .rand() . ".html"; + $article_f = fopen($mytemp,'w'); + fwrite($article_f, $html); + fclose($article_f); + putenv("HTMLDOC_NOCGI=1"); + + # Write the content type to the client... + header("Content-Type: application/pdf"); + header(sprintf('Content-Disposition: attachment; filename="%s.pdf"', $page)); + flush(); + + # if the page is on a HTTPS server and contains images that are on the HTTPS server AND also reachable with HTTP + # uncomment the next line + + #system("perl -pi -e 's/img src=\"https:\/\//img src=\"http:\/\//g' '$mytemp'"); + + # Run HTMLDOC to provide the PDF file to the user... + passthru("htmldoc -t pdf14 --charset iso-8859-1 --color --quiet --jpeg --webpage '$mytemp'"); + + #unlink ($mytemp); + + } + } + SpecialPage::addPage (new SpecialPdf()); +} + +function wfSpecialPdfNav( &$skintemplate, &$nav_urls, &$oldid, &$revid ) { + $nav_urls['pdfprint'] = array( + 'text' => wfMsg( 'pdf_print_link' ), + 'href' => $skintemplate->makeSpecialUrl( 'PdfPrint', "page=" . wfUrlencode( "{$skintemplate->thispage}" ) ) + ); + + return true; +} + +function wfSpecialPdfToolbox( &$monobook ) { + if ( isset( $monobook->data['nav_urls']['pdfprint'] ) ) { + if ( $monobook->data['nav_urls']['pdfprint']['href'] == '' ) { + ?><li id="t-ispdf"><?php echo $monobook->msg( 'pdf_print_link' ); ?></li><?php + } else { + ?><li id="t-pdf"><?php + ?><a href="<?php echo htmlspecialchars( $monobook->data['nav_urls']['pdfprint']['href'] ) ?>"><?php + echo $monobook->msg( 'pdf_print_link' ); + ?></a><?php + ?></li><?php + } + } + return true; +} +?> Added: projects/wiki/extensions/wiki2xml/CREDITS =================================================================== --- projects/wiki/extensions/wiki2xml/CREDITS (rev 0) +++ projects/wiki/extensions/wiki2xml/CREDITS 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,8 @@ +wiki2xml is (c) by Magnus Manske 2005-2006 and released under the GPL. + +The following people (in alphabetic order) contributed to this project: + +Magnus Manske <magnus.manske(a)web.de&gt; Everything Tels didn't do ;-) + +Tels <nospam-abuse(a)bloodgate.com&gt; Linux fixes, OpenOffice output + REDME and doc Added: projects/wiki/extensions/wiki2xml/README =================================================================== --- projects/wiki/extensions/wiki2xml/README (rev 0) +++ projects/wiki/extensions/wiki2xml/README 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,138 @@ +=pod + +=head1 INTRODUCTION + +You can read this document better with: + + perldoc README + +Otherwise, please just ignore the funny characters. + +=head1 NAME + +WIKI2XML - Wikitext to XML converter + +=head1 INSTALLATION + +=head2 Download/Checkout + +Check out the current release from SVN: + + svn co http://svn.wikimedia.org/svnroot/mediawiki/trunk/wiki2xml + +=head2 Extension or cgi-bin? + +There are two ways to install wiki2xml: + + As extension: Special::Wiki2XML + As cgi-bin: http://example.com/wiki/wiki2xml/w2x + +The former should be prefered. + +=head2 As Extension + +To enable wiki2xml as extension, put all files in the C<< php >> directory into a +C<< wiki2xml >> subdirectory of your MediaWiki extensions directory. + + htdocs + \- wiki + \- extensions + \- wiki2xml <-- create this directory + \- w2x.php <-- copy files here + \- wiki2xml.php etc. + +Then add + + require_once ("extensions/wiki2xml/extension.php"); + +to your C<< LocalSettings.php >>. The extension can then be accessed as +C<< [[Special:Wiki2XML]] >>. + +=head2 cgi-bin - Copy files + +The alternative method is to install wiki2xml as cgi-bin script: + +Copy the subdirectory C<< ./php/ >> to your server's C<< wiki/ >> +directory as a subdirectory named C<< w2x >>: + + htdocs + \- wiki + \- w2x <-- here + \- w2x.php + \- wiki2xml.php etc + +Access it as C<< http://example.com/wiki/w2x/w2x.php >>. + +=head2 Configuration + +The configuration is stored in C<< default.php >> and C<< local.php >>. + +There is a C<< sample_local.php >> file, copy it to C<< local.php >> +and then edit it to match your configuration. + +On a Unix/Linux server the following can be used as a starting point: + + # Directory for temporary files: + $xmlg["temp_dir"] = "/tmp"; + + # Path to the zip/unzip programs; can be omitted if in default + # executable path: + #$xmlg["zip_odt_path"] = ""; + + # Command to zip directory $1 to file $2: + $xmlg["zip_odt"] = 'zip -r9 $1 $2'; + + # Command to unzip file $1 to directory $2: + $xmlg["unzip_odt"] = 'unzip -x $1 -d $2'; + +=head1 USAGE + +Open the correct URL (depending on install type, see above) in your browser. + +Wiki2xml should present you with a form with a textarea and several buttons. + +=head2 Using URL parameters + +Parameters: + + doit=1 + text=lines_of_text_or_titles + whatsthis=wikitext/articlelist + site=en.wikipedia.org/w + output_format=xml/text/xhtml/docbook_xml/odt_xml/odt + +Optional: + + use_templates=all/none/these/notthese + templates=lines_of_templates + document_title= + add_gfdl=1 + keep_categories=1 + keep_interlanguage=1 + + + +=head1 TROUBLESHOOTING + +If you get errors like the following: + + Warning: fopen(/tmp/ODD6Rq1qt-DIR/content.xml): failed to open stream: + No such file or directory in /.../wiki/wiki2xml/w2x.php on line 112 + +then make sure that the tmp directory you selected is really writable by +your webserver. + +=head2 OpenOffice Output + +For OpenOffice output, the converter will extract a file called C<< template.odt >> +into the temp directory. It will then replace/modify the files in it, zip it +up again and then offer the browser the resulting file as a download. + +=head1 AUTHOR + +Copyright 2005-2006 by Magnus Manske <magnus.manske(a)web.de&gt; + +Released under the GPL. + +=cut + Added: projects/wiki/extensions/wiki2xml/TODO =================================================================== --- projects/wiki/extensions/wiki2xml/TODO (rev 0) +++ projects/wiki/extensions/wiki2xml/TODO 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,7 @@ +* Articles with '_' result in 'Main_Page' instead of 'Main Page' as headline +* Sublists, and numbered lists are wrong +* the ODT output could use a more strict separation between template and + generated XML +* support for <div style="..."> where "..." is text-align, font-size, + border, etc + \ No newline at end of file Added: projects/wiki/extensions/wiki2xml/browse_texts.php =================================================================== --- projects/wiki/extensions/wiki2xml/browse_texts.php (rev 0) +++ projects/wiki/extensions/wiki2xml/browse_texts.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,67 @@ +<?php + +require_once ( "default.php" ) ; +require_once ( "global_functions.php" ) ; +require_once ( "filter_named_entities.php" ) ; +require_once ( "content_provider.php" ) ; +require_once ( "wiki2xml.php" ) ; +require_once ( "xml2xhtml.php" ) ; +require_once ( "mediawiki_converter.php" ) ; + +# FUNCTIONS + +function get_param ( $key , $default = "" ) { + if ( !isset ( $_REQUEST[$key] ) ) return $default ; + return $_REQUEST[$key] ; +} + +# MAIN + +@set_time_limit ( 0 ) ; # No time limit + +$xmlg = array ( + 'site_base_url' => "SBU" , + 'resolvetemplates' => true , + 'templates' => array () , + 'namespace_template' => 'Vorlage' , +) ; + +$content_provider = new ContentProviderTextFile ; +$converter = new MediaWikiConverter ; + +$title = urldecode ( get_param ( 'title' , urlencode ( 'Main Page' ) ) ) ; +$xmlg['page_title'] = $title ; + +$format = strtolower ( get_param ( 'format' , 'xhtml' ) ) ; +$content_provider->basedir = $base_text_dir ; + +$text = $content_provider->get_wiki_text ( $title ) ; +$xml = $converter->article2xml ( $title , $text , $xmlg ) ; + +if ( $format =="xml" ) { + # XML + header('Content-type: text/xml; charset=utf-8'); + print "<?xml version='1.0' encoding='UTF-8' ?>\n" ; + print $xml ; +} else if ( $format == "text" ) { + # Plain text + $xmlg['plaintext_markup'] = true ; + $xmlg['plaintext_prelink'] = true ; + $out = $converter->articles2text ( $xml , $xmlg ) ; + $out = str_replace ( "\n" , "<br/>" , $out ) ; + header('Content-type: text/html; charset=utf-8'); + print $out ; +} else { + # XHTML + if ( stristr($_SERVER["HTTP_ACCEPT"],"application/xhtml+xml") ) { + # Skipping the "strict" part ;-) + header("Content-type: text/html; charset=utf-8"); +# header("Content-type: application/xhtml+xml"); + } else { + # Header hack for IE + header("Content-type: text/html; charset=utf-8"); + } + print $converter->articles2xhtml ( $xml , $xmlg ) ; +} + +?> Added: projects/wiki/extensions/wiki2xml/content_provider.php =================================================================== --- projects/wiki/extensions/wiki2xml/content_provider.php (rev 0) +++ projects/wiki/extensions/wiki2xml/content_provider.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,353 @@ +<?php + +# Abstract base class +class ContentProvider { + var $load_time = 0 ; # Time to load text and templates, to judge actual parsing speed + var $article_list = array () ; + var $authors = array () ; + var $block_file_download = false ; + + function get_wiki_text ( $title , $do_cache = false ) { return "" ; } # dummy + function get_template_text ( $title ) { return "" ; } # dummy + + function add_article ( $title ) { + $this->article_list[] = urlencode ( trim ( $title ) ) ; + } + + function is_an_article ( $title ) { + $title = urlencode ( trim ( $title ) ) ; + return in_array ( $title , $this->article_list ) ; + } + + /** + * XXX TODO: why are some negative? + * Gets the numeric namespace + * "6" = images + * "-8" = category link + * "-9" = interlanguage link + * "11" = templates + */ function get_namespace_id ( $text ) { + $text = strtoupper ( $text ) ; + $text = explode ( ":" , $text , 2 ) ; + if ( count ( $text ) != 2 ) return 0 ; + $text = trim ( array_shift ( $text ) ) ; + if ( $text == "" ) return 0 ; + $ns = 0 ; + + if ( $text == "CATEGORY" || $text == "KATEGORIE" ) return -8 ; # Hackish, for category link + if ( strlen ( $text ) < 4 ) return -9 ; # Hackish, for interlanguage link + if ( $text == "SIMPLE" ) return -9 ; + + # Horrible manual hack, for now + if ( $text == "IMAGE" || $text == "BILD" ) $ns = 6 ; + if ( $text == "TEMPLATE" || $text == "VORLAGE" ) $ns = 11 ; + + return $ns ; + } + + function copyimagefromwiki ( $name , $url = "" ) { + global $xmlg ; + $dir = $xmlg['image_destination'] ; + if ( $url == "" ) + $url = $this->get_image_url ( name ) ; + $fname = urlencode ( $name ) ; + $target = $dir . "/" . $fname ; + if ( !file_exists ( $target ) && !$this->block_file_download ) { + @mkdir ( $dir ) ; + @copy ( $url , $target ) ; + } + return $fname ; + } + + function myurlencode ( $t ) { + $t = str_replace ( " " , "_" , $t ) ; + $t = urlencode ( $t ) ; + return $t ; + } + + + function get_image_url ( $name ) { + global $xmlg ; + $site = $xmlg['site_base_url'] ; + $parts = explode ( ".wikipedia.org/" , $site ) ; + $parts2 = explode ( ".wikibooks.org/" , $site ) ; + + $image = utf8_encode ( $name ) ; + $image2 = ucfirst ( str_replace ( " " , "_" , $name ) ) ; + $m = md5( $image2 ) ; + $m1 = substr ( $m , 0 , 1 ) ; + $m2 = substr ( $m , 0 , 2 ) ; + $i = "{$m1}/{$m2}/" . $this->myurlencode ( ucfirst ( $name ) ) ; + + + if ( count ($parts ) > 1 ) { + $lang = array_shift ( $parts ) ; + $url = "http://upload.wikimedia.org/wikipedia/{$lang}/{$i}" ; + $url2 = "http://upload.wikimedia.org/wikipedia/commons/{$i}" ; + $h = @fopen ( $url , "r" ) ; + if ( $h === false ) $url = $url2 ; + else fclose ( $h ) ; + } else if ( count ($parts2 ) > 1 ) { + $lang = array_shift ( $parts2 ) ; + $url = "http://upload.wikimedia.org/wikibooks/{$lang}/{$i}" ; + $url2 = "http://upload.wikimedia.org/wikipedia/commons/{$i}" ; + $h = @fopen ( $url , "r" ) ; + if ( $h === false ) $url = $url2 ; + else fclose ( $h ) ; + } else { + $url = "http://{$site}/images/{$i}" ; + } +# print "<a href='{$url}'>{$url}</a><br/>" ; + return $url ; + } + + function do_show_images () { + return true ; + } + +} + + +# Access through HTTP protocol +class ContentProviderHTTP extends ContentProvider { + var $article_cache = array () ; + var $first_title = "" ; + var $load_error ; + + function between_tag ( $tag , &$text ) { + $a = explode ( "<{$tag}" , $text , 2 ) ; + if ( count ( $a ) == 1 ) return "" ; + $a = explode ( ">" , " " . array_pop ( $a ) , 2 ) ; + if ( count ( $a ) == 1 ) return "" ; + $a = explode ( "</{$tag}>" , array_pop ( $a ) , 2 ) ; + if ( count ( $a ) == 1 ) return "" ; + return array_shift ( $a ) ; + } + + function do_get_contents ( $title ) { + global $xmlg ; + $use_se = false ; + if ( isset ( $xmlg["use_special_export"] ) && $xmlg["use_special_export"] == 1 ) $use_se = true ; + + if ( $use_se ) { + $url = "http://" . $xmlg["site_base_url"] . "/index.php?listauthors=1&title=Special:Export/" . urlencode ( $title ) ; + } else { + if ( $xmlg["use_toolserver_url"] ) { +# $url = "http://" . $xmlg["site_base_url"] . "/index.php?action=raw&title=" . urlencode ( $title ) ; + $u = urlencode ( $title ) ; + $site = array_shift ( explode ( "/" , $xmlg["site_base_url"] ) ) ; + $url = "http://tools.wikimedia.de/~daniel/WikiSense/WikiProxy.php?wiki={$site}&title={$u}&rev=0&go=Fetch" ; + } else { + $url = "http://" . $xmlg["site_base_url"] . "/index.php?action=raw&title=" . urlencode ( $title ) ; + } + } + $s = @file_get_contents ( $url ) ; + + if ( $use_se ) { + $text = html_entity_decode ( $this->between_tag ( "text" , $s ) ) ; + $this->authors = array () ; + $authors = $this->between_tag ( "contributors" , $s ) ; + $authors = explode ( "</contributor><contributor>" , $authors ) ; + foreach ( $authors AS $author ) { + $id = $this->between_tag ( "id" , $author ) ; + if ( $id == '0' || $id == '' ) continue ; # Skipping IPs and (possibly) broken entries + $name = $this->between_tag ( "username" , $author ) ; + $this->authors[] = $name ; + } + $s = $text ; + } + return $s ; + } + + function get_wiki_text ( $title , $do_cache = false ) { + global $xmlg ; + $load_error = false ; + $title = trim ( $title ) ; + if ( $title == "" ) return "" ; # Just in case... + if ( isset ( $this->article_cache[$title] ) ) # Already in the cache + return $this->article_cache[$title] ; + + if ( $this->first_title == "" ) $this->first_title = $title ; + + # Retrieve it + $t1 = microtime_float() ; + $s = $this->do_get_contents ( $title ) ; + if ( strtoupper ( substr ( $s , 0 , 9 ) ) == "#REDIRECT" ) { + $t2 = explode ( "[[" , $s , 2 ) ; + $t2 = array_pop ( $t2 ) ; + $t2 = explode ( "]]" , $t2 , 2 ) ; + $t2 = array_shift ( $t2 ) ; + $s = $this->do_get_contents ( $t2 ) ; + } + $this->load_time += microtime_float() - $t1 ; + + $comp = '<!DOCTYPE html PUBLIC "-//W3C//DTD' ; + if ( substr ( $s , 0 , strlen ( $comp ) ) == $comp ) $s = "" ; # Catching wrong title error + + if ( $do_cache ) $this->article_cache[$title] = $s ; + return $s ; + } + + function get_local_url ( $title ) { + return "/" . array_pop ( explode ( "/" , $this->get_var ( 'site_base_url' ) , 2 ) ) . "/index.php?title=" . urlencode ( $title ) ; + } + + function get_server_url () { + return "http://" . array_shift ( explode ( "/" , $this->get_var ( 'site_base_url' ) , 2 ) ) ; + } + + function get_full_url ( $title ) { + return $this->get_server_url () . $this->get_local_url ( $title ) ; + } + + function get_namespace_template () { + return $this->get_var ( 'namespace_template' ) ; + } + + function get_var ( $var ) { + global $xmlg ; + if ( !isset ( $xmlg[$var] ) ) return false ; + return $xmlg[$var] ; + } + + function get_template_text ( $title ) { + # Check for fix variables + if ( $title == "PAGENAME" ) return $this->first_title ; + if ( $title == "PAGENAMEE" ) return urlencode ( $this->first_title ) ; + if ( $title == "SERVER" ) return $this->get_server_url () ; + if ( $title == "CURRENTDAYNAME" ) return date ( "l" ) ; + if ( strtolower ( substr ( $title , 0 , 9 ) ) == "localurl:" ) + return $this->get_local_url ( substr ( $title , 9 ) ) ; + + $title = trim ( $title ) ; + if ( count ( explode ( ":" , $title , 2 ) ) == 1 ) # Does the template title contain a ":"? + $title = $this->get_namespace_template() . ":" . $title ; + else if ( substr ( $title , 0 , 1 ) == ":" ) # Main namespace + $title = substr ( $title , 1 ) ; + return $this->get_wiki_text ( $title , true ) ; # Cache template texts + } + + function get_internal_link ( $target , $text ) { + return $text ; # Dummy + } +} + + + + +# Access through text file structure +class ContentProviderTextFile extends ContentProviderHTTP { + var $file_ending = ".txt" ; + + function do_get_contents ( $title ) { + return $this->get_page_text ( $title ) ; + } + + /** + Called from outside + Could probably remained unchanged from HTTP class, but this is shorter, and caching is irrelevant for text files (disk cache) + */ + function get_wiki_text ( $title , $do_cache = false ) { + $title = trim ( $title ) ; + if ( $title == "" ) return "" ; # Just in case... + if ( $this->first_title == "" ) { + $this->first_title = $title ; + } + $text = $this->get_page_text ( $title ) ; + return $text ; + } + + function get_file_location ( $ns , $title ) { + return get_file_location_global ( $this->basedir , $ns , $title , false ) ; + } + + function get_page_text ( $page , $allow_redirect = true ) { + $filename = $this->get_file_location ( 0 , $page ) ; + $filename = $filename->fullname . $this->file_ending ; + if ( !file_exists ( $filename ) ) return "" ; + $text = trim ( file_get_contents ( $filename ) ) ; + + # REDIRECT? + if ( $allow_redirect && strtoupper ( substr ( $text , 0 , 9 ) ) == "#REDIRECT" ) { + $text = substr ( $text , 9 ) ; + $text = array_shift ( explode ( "\n" , $text , 2 ) ) ; + $text = str_replace ( "[[" , "" , $text ) ; + $text = str_replace ( "]]" , "" , $text ) ; + $text = ucfirst ( trim ( $text ) ) ; + $text = $this->get_page_text ( $text , false ) ; + } + return $text ; + } + + function get_internal_link ( $target , $text ) { + $file = $this->get_file_location ( 0 , $target ) ; + if ( !file_exists ( $file->fullname.$this->file_ending ) ) return $text ; + else return "<a href='browse_texts.php?title=" . urlencode ( $target ) . "'>{$text}</a>" ; + } + + function do_show_images () { + return false ; + } + +} + +# Access through MySQL interface +# (Used via the extension via Special::wiki2XML) +class ContentProviderMySQL extends ContentProviderHTTP { + + function do_get_contents ( $title ) { + return $this->get_page_text ( $title ) ; + } + + /** + Called from outside + */ + function get_wiki_text ( $title , $do_cache = false ) { + $title = trim ( $title ) ; + if ( $title == "" ) return "" ; # Just in case... + if ( $this->first_title == "" ) { + $this->first_title = $title ; + } + $text = $this->get_page_text ( $title ) ; + return $text ; + } + + function get_file_location ( $ns , $title ) { + return get_file_location_global ( $this->basedir , $ns , $title , false ) ; + } + + function get_page_text ( $page , $allow_redirect = true ) { + $title = Title::newFromText ( $page ) ; + $article = new Article ( $title ) ; + + # article does not exist? + if (!$article->exists()) { + return ""; + } + $text = $article->getContent () ; + + # REDIRECT? + if ( $allow_redirect && strtoupper ( substr ( $text , 0 , 9 ) ) == "#REDIRECT" ) { + $text = substr ( $text , 9 ) ; + $text = array_shift ( explode ( "\n" , $text , 2 ) ) ; + $text = str_replace ( "[[" , "" , $text ) ; + $text = str_replace ( "]]" , "" , $text ) ; + $text = ucfirst ( trim ( $text ) ) ; + $text = $this->get_page_text ( $text , false ) ; + } + return $text ; + } + + function get_internal_link ( $target , $text ) { + $file = $this->get_file_location ( 0 , $target ) ; + if ( !file_exists ( $file->fullname.$this->file_ending ) ) return $text ; + else return "<a href='browse_texts.php?title=" . urlencode ( $target ) . "'>{$text}</a>" ; + } + + function do_show_images () { + return false ; + } + +} + +?> Added: projects/wiki/extensions/wiki2xml/default.php =================================================================== --- projects/wiki/extensions/wiki2xml/default.php (rev 0) +++ projects/wiki/extensions/wiki2xml/default.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,22 @@ +<?php + +$xmlg["namespace_template"] = "Template" ; +$xmlg["site_base_url"] = "en.wikipedia.org/w" ; +$xmlg["book_title"] = "No title" ; +$xmlg['sourcedir'] = "." ; +$xmlg["temp_dir"] = "/tmp" ; +$xmlg['is_windows'] = false ; +$xmlg['allow_get'] = false ; +$xmlg["use_toolserver_url"] = false ; +$xmlg["odt_footnote"] = 'footnote' ; +$xmlg["allow_xml_temp_files"] = true ; +$xmlg["use_xml_temp_files"] = false ; +$xmlg["xhtml_source"] = false ; +$xmlg['xhtml_justify'] = false ; +$xmlg['xhtml_logical_markup'] = false ; +$xmlg['text_hide_images'] = false ; +$xmlg['text_hide_tables'] = false ; + +@include ( "local.php" ) ; + +?> Added: projects/wiki/extensions/wiki2xml/extension.php =================================================================== --- projects/wiki/extensions/wiki2xml/extension.php (rev 0) +++ projects/wiki/extensions/wiki2xml/extension.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,77 @@ +<?php +/* +To enable this extension, put all files in this directory into a "wiki2xml" +subdirectory of your MediaWiki extensions directory. +Also, add + require_once ( "extensions/wiki2xml/extension.php" ) ; +to your LocalSettings.php +The extension will then be accessed as [[Special:Wiki2XML]]. +*/ + +if( !defined( 'MEDIAWIKI' ) ) die(); + +# Integrating into the MediaWiki environment + +$wgExtensionCredits['Wiki2XML'][] = array( + 'name' => 'Wiki2XML', + 'description' => 'An extension to convert wiki markup into XML.', + 'author' => 'Magnus Manske' +); + +$wgExtensionFunctions[] = 'wfWiki2XMLExtension'; + +# for Special::Version: +$wgExtensionCredits['parserhook'][] = array( + 'name' => 'wiki2xml extension', + 'author' => 'Magnus Manske et al.', + 'url' => 'http://en.wikipedia.org/wiki/User:Magnus_Manske', + 'version' => 'v0.02', +); + + +#_____________________________________________________________________________ + +/** + * The special page + */ +function wfWiki2XMLExtension() { # Checked for HTML and MySQL insertion attacks + global $IP, $wgMessageCache; +# wfTasksAddCache(); + + // FIXME : i18n + $wgMessageCache->addMessage( 'wiki2xml', 'Wiki2XML' ); + + require_once $IP.'/includes/SpecialPage.php'; + + class SpecialWiki2XML extends SpecialPage { + + /** + * Constructor + */ + function SpecialWiki2XML() { # Checked for HTML and MySQL insertion attacks + SpecialPage::SpecialPage( 'Wiki2XML' ); + $this->includable( true ); + } + + /** + * Special page main function + */ + function execute( $par = null ) { # Checked for HTML and MySQL insertion attacks + global $wgOut, $wgRequest, $wgUser, $wgTitle, $IP; + $fname = 'Special::Tasks:execute'; + global $xmlg , $html_named_entities_mapping_mine, $content_provider; + include_once ( "default.php" ) ; + $xmlg['sourcedir'] = $IP.'/extensions/wiki2xml' ; + include_once ( "w2x.php" ) ; + + $this->setHeaders(); + $wgOut->addHtml( $out ); + } + + } # end of class + + SpecialPage::addPage( new SpecialWiki2XML ); +} + + +?> Added: projects/wiki/extensions/wiki2xml/filter_named_entities.php =================================================================== --- projects/wiki/extensions/wiki2xml/filter_named_entities.php (rev 0) +++ projects/wiki/extensions/wiki2xml/filter_named_entities.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,281 @@ +<?php +/** + * This file is to compensate for a bug in PHP4 and early PHP5 versions + * which do not replace some entities correctly + */ + +$html_named_entities_mapping_mine = array ( + // Obtained with: + // less /usr/share/xml/entities/xhtml/*.ent|grep '^<!ENTITY'|sed -e 's/^<\!ENTITY[ \t]*\([A-Za-z0-9]*\)[ \t]*"&#\([0-9]*\);".*$/"\1"=>\2,/' > /home/dom/data/2005/04/entities-table +'nbsp'=>160, +'iexcl'=>161, +'cent'=>162, +'pound'=>163, +'curren'=>164, +'yen'=>165, +'brvbar'=>166, +'sect'=>167, +'uml'=>168, +'copy'=>169, +'ordf'=>170, +'laquo'=>171, +'not'=>172, +'shy'=>173, +'reg'=>174, +'macr'=>175, +'deg'=>176, +'plusmn'=>177, +'sup2'=>178, +'sup3'=>179, +'acute'=>180, +'micro'=>181, +'para'=>182, +'middot'=>183, +'cedil'=>184, +'sup1'=>185, +'ordm'=>186, +'raquo'=>187, +'frac14'=>188, +'frac12'=>189, +'frac34'=>190, +'iquest'=>191, +'Agrave'=>192, +'Aacute'=>193, +'Acirc'=>194, +'Atilde'=>195, +'Auml'=>196, +'Aring'=>197, +'AElig'=>198, +'Ccedil'=>199, +'Egrave'=>200, +'Eacute'=>201, +'Ecirc'=>202, +'Euml'=>203, +'Igrave'=>204, +'Iacute'=>205, +'Icirc'=>206, +'Iuml'=>207, +'ETH'=>208, +'Ntilde'=>209, +'Ograve'=>210, +'Oacute'=>211, +'Ocirc'=>212, +'Otilde'=>213, +'Ouml'=>214, +'times'=>215, +'Oslash'=>216, +'Ugrave'=>217, +'Uacute'=>218, +'Ucirc'=>219, +'Uuml'=>220, +'Yacute'=>221, +'THORN'=>222, +'szlig'=>223, +'agrave'=>224, +'aacute'=>225, +'acirc'=>226, +'atilde'=>227, +'auml'=>228, +'aring'=>229, +'aelig'=>230, +'ccedil'=>231, +'egrave'=>232, +'eacute'=>233, +'ecirc'=>234, +'euml'=>235, +'igrave'=>236, +'iacute'=>237, +'icirc'=>238, +'iuml'=>239, +'eth'=>240, +'ntilde'=>241, +'ograve'=>242, +'oacute'=>243, +'ocirc'=>244, +'otilde'=>245, +'ouml'=>246, +'divide'=>247, +'oslash'=>248, +'ugrave'=>249, +'uacute'=>250, +'ucirc'=>251, +'uuml'=>252, +'yacute'=>253, +'thorn'=>254, +'yuml'=>255, +'quot'=>34, +'amp'=>38, +'lt'=>60, +'gt'=>62, +'OElig'=>338, +'oelig'=>339, +'Scaron'=>352, +'scaron'=>353, +'Yuml'=>376, +'circ'=>710, +'tilde'=>732, +'ensp'=>8194, +'emsp'=>8195, +'thinsp'=>8201, +'zwnj'=>8204, +'zwj'=>8205, +'lrm'=>8206, +'rlm'=>8207, +'ndash'=>8211, +'mdash'=>8212, +'lsquo'=>8216, +'rsquo'=>8217, +'sbquo'=>8218, +'ldquo'=>8220, +'rdquo'=>8221, +'bdquo'=>8222, +'dagger'=>8224, +'Dagger'=>8225, +'permil'=>8240, +'lsaquo'=>8249, +'rsaquo'=>8250, +'euro'=>8364, +'fnof'=>402, +'Alpha'=>913, +'Beta'=>914, +'Gamma'=>915, +'Delta'=>916, +'Epsilon'=>917, +'Zeta'=>918, +'Eta'=>919, +'Theta'=>920, +'Iota'=>921, +'Kappa'=>922, +'Lambda'=>923, +'Mu'=>924, +'Nu'=>925, +'Xi'=>926, +'Omicron'=>927, +'Pi'=>928, +'Rho'=>929, +'Sigma'=>931, +'Tau'=>932, +'Upsilon'=>933, +'Phi'=>934, +'Chi'=>935, +'Psi'=>936, +'Omega'=>937, +'alpha'=>945, +'beta'=>946, +'gamma'=>947, +'delta'=>948, +'epsilon'=>949, +'zeta'=>950, +'eta'=>951, +'theta'=>952, +'iota'=>953, +'kappa'=>954, +'lambda'=>955, +'mu'=>956, +'nu'=>957, +'xi'=>958, +'omicron'=>959, +'pi'=>960, +'rho'=>961, +'sigmaf'=>962, +'sigma'=>963, +'tau'=>964, +'upsilon'=>965, +'phi'=>966, +'chi'=>967, +'psi'=>968, +'omega'=>969, +'thetasym'=>977, +'upsih'=>978, +'piv'=>982, +'bull'=>8226, +'hellip'=>8230, +'prime'=>8242, +'Prime'=>8243, +'oline'=>8254, +'frasl'=>8260, +'weierp'=>8472, +'image'=>8465, +'real'=>8476, +'trade'=>8482, +'alefsym'=>8501, +'larr'=>8592, +'uarr'=>8593, +'rarr'=>8594, +'darr'=>8595, +'harr'=>8596, +'crarr'=>8629, +'lArr'=>8656, +'uArr'=>8657, +'rArr'=>8658, +'dArr'=>8659, +'hArr'=>8660, +'forall'=>8704, +'part'=>8706, +'exist'=>8707, +'empty'=>8709, +'nabla'=>8711, +'isin'=>8712, +'notin'=>8713, +'ni'=>8715, +'prod'=>8719, +'sum'=>8721, +'minus'=>8722, +'lowast'=>8727, +'radic'=>8730, +'prop'=>8733, +'infin'=>8734, +'ang'=>8736, +'and'=>8743, +'or'=>8744, +'cap'=>8745, +'cup'=>8746, +'int'=>8747, +'there4'=>8756, +'sim'=>8764, +'cong'=>8773, +'asymp'=>8776, +'ne'=>8800, +'equiv'=>8801, +'le'=>8804, +'ge'=>8805, +'sub'=>8834, +'sup'=>8835, +'nsub'=>8836, +'sube'=>8838, +'supe'=>8839, +'oplus'=>8853, +'otimes'=>8855, +'perp'=>8869, +'sdot'=>8901, +'lceil'=>8968, +'rceil'=>8969, +'lfloor'=>8970, +'rfloor'=>8971, +'lang'=>9001, +'rang'=>9002, +'loz'=>9674, +'spades'=>9824, +'clubs'=>9827, +'hearts'=>9829, +'diams'=>9830, +'32'=>32, +); + +function utf8_chr($code) +{ + if($code<128) return chr($code); + else if($code<2048) return chr(($code>>6)+192).chr(($code&63)+128); + else if($code<65536) return chr(($code>>12)+224).chr((($code>>6)&63)+128).chr(($code&63)+128); + else if($code<2097152) return chr($code>>18+240).chr((($code>>12)&63)+128).chr(($code>>6)&63+128).chr($code&63+128); +} + +function filter_named_entities(&$content) { + global $html_named_entities_mapping_mine; + foreach($html_named_entities_mapping_mine as $name => $value) { + $content=str_replace('&'.$name.';',utf8_chr ( $value ),$content); + } + $content=str_replace('�','i',$content); # Ugly hack +} + +?> Added: projects/wiki/extensions/wiki2xml/gfdl.xml =================================================================== --- projects/wiki/extensions/wiki2xml/gfdl.xml (rev 0) +++ projects/wiki/extensions/wiki2xml/gfdl.xml 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,446 @@ +<appendix id="gfdl"> +<appendixinfo> +<title>GNU Free Documentation License</title> + + <pubdate>Version 1.2, November 2002</pubdate> + <copyright><year>2000,2001,2002</year> + <holder>Free Software Foundation, Inc.</holder></copyright> + <legalnotice id="gfdl-legalnotice"> + <para><address>Free Software Foundation, Inc. + <street>51 Franklin St, Fifth Floor</street>, + <city>Boston</city>, + <state>MA</state> + <postcode>02110-1301</postcode> + <country>USA</country> + </address></para> + <para>Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed.</para> + </legalnotice> + <releaseinfo>Version 1.2, November 2002</releaseinfo> +</appendixinfo> + +<title>GNU Free Documentation License</title> +<section id="gfdl-0"><title>PREAMBLE</title> + +<para>The purpose of this License is to make a manual, textbook, or +other functional and useful document "free" in the sense of freedom: to +assure everyone the effective freedom to copy and redistribute it, with +or without modifying it, either commercially or noncommercially. +Secondarily, this License preserves for the author and publisher a way +to get credit for their work, while not being considered responsible for +modifications made by others.</para> + +<para>This License is a kind of "copyleft", which means that derivative +works of the document must themselves be free in the same sense. It +complements the GNU General Public License, which is a copyleft license +designed for free software.</para> + +<para>We have designed this License in order to use it for manuals for +free software, because free software needs free documentation: a free +program should come with manuals providing the same freedoms that the +software does. But this License is not limited to software manuals; it +can be used for any textual work, regardless of subject matter or +whether it is published as a printed book. We recommend this License +principally for works whose purpose is instruction or reference.</para> +</section> + +<section id="gfdl-1"><title>APPLICABILITY AND DEFINITIONS</title> + +<para id="gfdl-doc">This License applies to any manual or other work, in +any medium, that contains a notice placed by the copyright holder saying +it can be distributed under the terms of this License. Such a notice +grants a world-wide, royalty-free license, unlimited in duration, to use +that work under the conditions stated herein. The "Document", below, +refers to any such manual or work. Any member of the public is a +licensee, and is addressed as "you". You accept the license if you +copy, modify or distribute the work in a way requiring permission under +copyright law.</para> + +<para id="gfdl-mod-ver">A "Modified Version" of the Document means any +work containing the Document or a portion of it, either copied verbatim, +or with modifications and/or translated into another language.</para> + +<para id="gfdl-secnd-sect">A "Secondary Section" is a named appendix or +a front-matter section of the Document that deals exclusively with the +relationship of the publishers or authors of the Document to the +Document's overall subject (or to related matters) and contains nothing +that could fall directly within that overall subject. (Thus, if the +Document is in part a textbook of mathematics, a Secondary Section may +not explain any mathematics.) The relationship could be a matter of +historical connection with the subject or with related matters, or of +legal, commercial, philosophical, ethical or political position +regarding them.</para> + +<para id="gfdl-inv-sect">The "Invariant Sections" are certain Secondary +Sections whose titles are designated, as being those of Invariant +Sections, in the notice that says that the Document is released under +this License. If a section does not fit the above definition of +Secondary then it is not allowed to be designated as Invariant. The +Document may contain zero Invariant Sections. If the Document does not +identify any Invariant Sections then there are none.</para> + +<para id="gfdl-cov-text">The "Cover Texts" are certain short passages of +text that are listed, as Front-Cover Texts or Back-Cover Texts, in the +notice that says that the Document is released under this License. A +Front-Cover Text may be at most 5 words, and a Back-Cover Text may be at +most 25 words.</para> + +<para id="gfdl-transparent">A "Transparent" copy of the Document means a +machine-readable copy, represented in a format whose specification is +available to the general public, that is suitable for revising the +document straightforwardly with generic text editors or (for images +composed of pixels) generic paint programs or (for drawings) some widely +available drawing editor, and that is suitable for input to text +formatters or for automatic translation to a variety of formats suitable +for input to text formatters. A copy made in an otherwise Transparent +file format whose markup, or absence of markup, has been arranged to +thwart or discourage subsequent modification by readers is not +Transparent. An image format is not Transparent if used for any +substantial amount of text. A copy that is not "Transparent" is called +"Opaque".</para> + +<para>Examples of suitable formats for Transparent copies include plain +ASCII without markup, Texinfo input format, LaTeX input format, SGML or +XML using a publicly available DTD, and standard-conforming simple HTML, +PostScript or PDF designed for human modification. Examples of +transparent image formats include PNG, XCF and JPG. Opaque formats +include proprietary formats that can be read and edited only by +proprietary word processors, SGML or XML for which the DTD and/or +processing tools are not generally available, and the machine-generated +HTML, PostScript or PDF produced by some word processors for output +purposes only.</para> + +<para id="gfdl-title-page">The "Title Page" means, for a printed book, +the title page itself, plus such following pages as are needed to hold, +legibly, the material this License requires to appear in the title page. +For works in formats which do not have any title page as such, "Title +Page" means the text near the most prominent appearance of the work's +title, preceding the beginning of the body of the text.</para> + +<para id="gfdl-entitled">A section "Entitled XYZ" means a named subunit +of the Document whose title either is precisely XYZ or contains XYZ in +parentheses following text that translates XYZ in another language. +(Here XYZ stands for a specific section name mentioned below, such as +"Acknowledgements", "Dedications", "Endorsements", or "History".) To +"Preserve the Title" of such a section when you modify the Document +means that it remains a section "Entitled XYZ" according to this +definition.</para> + +<para>The Document may include Warranty Disclaimers next to the notice +which states that this License applies to the Document. These Warranty +Disclaimers are considered to be included by reference in this License, +but only as regards disclaiming warranties: any other implication that +these Warranty Disclaimers may have is void and has no effect on the +meaning of this License.</para> +</section> + +<section id="gfdl-2"><title>VERBATIM COPYING</title> + +<para>You may copy and distribute the Document in any medium, either +commercially or noncommercially, provided that this License, the +copyright notices, and the license notice saying this License applies to +the Document are reproduced in all copies, and that you add no other +conditions whatsoever to those of this License. You may not use +technical measures to obstruct or control the reading or further copying +of the copies you make or distribute. However, you may accept +compensation in exchange for copies. If you distribute a large enough +number of copies you must also follow the conditions in section 3. +</para> + +<para>You may also lend copies, under the same conditions stated above, +and you may publicly display copies.</para> +</section> + +<section id="gfdl-3"><title>COPYING IN QUANTITY</title> + +<para>If you publish printed copies (or copies in media that commonly +have printed covers) of the Document, numbering more than 100, and the +Document's license notice requires Cover Texts, you must enclose the +copies in covers that carry, clearly and legibly, all these Cover Texts: +Front-Cover Texts on the front cover, and Back-Cover Texts on the back +cover. Both covers must also clearly and legibly identify you as the +publisher of these copies. The front cover must present the full title +with all words of the title equally prominent and visible. You may add +other material on the covers in addition. Copying with changes limited +to the covers, as long as they preserve the title of the Document and +satisfy these conditions, can be treated as verbatim copying in other +respects.</para> + +<para>If the required texts for either cover are too voluminous to fit +legibly, you should put the first ones listed (as many as fit +reasonably) on the actual cover, and continue the rest onto adjacent +pages.</para> + +<para>If you publish or distribute Opaque copies of the Document +numbering more than 100, you must either include a machine-readable +Transparent copy along with each Opaque copy, or state in or with each +Opaque copy a computer-network location from which the general +network-using public has access to download using public-standard +network protocols a complete Transparent copy of the Document, free of +added material. If you use the latter option, you must take reasonably +prudent steps, when you begin distribution of Opaque copies in quantity, +to ensure that this Transparent copy will remain thus accessible at the +stated location until at least one year after the last time you +distribute an Opaque copy (directly or through your agents or retailers) +of that edition to the public.</para> + +<para>It is requested, but not required, that you contact the authors of +the Document well before redistributing any large number of copies, to +give them a chance to provide you with an updated version of the +Document.</para> +</section> + +<section id="gfdl-4"><title>MODIFICATIONS</title> + +<para>You may copy and distribute a Modified Version of the Document +under the conditions of sections 2 and 3 above, provided that you +release the Modified Version under precisely this License, with the +Modified Version filling the role of the Document, thus licensing +distribution and modification of the Modified Version to whoever +possesses a copy of it. In addition, you must do these things in the +Modified Version:</para> + +<orderedlist id="gfdl-modif-cond" numeration="upperalpha"> + <title>GNU FDL Modification Conditions</title> +<listitem><simpara>Use in the Title Page (and on the covers, if any) a + title distinct from that of the Document, and from those of previous + versions (which should, if there were any, be listed in the History + section of the Document). You may use the same title as a previous + version if the original publisher of that version gives permission. +</simpara></listitem> +<listitem><simpara>List on the Title Page, as authors, one or more + persons or entities responsible for authorship of the modifications in + the Modified Version, together with at least five of the principal + authors of the Document (all of its principal authors, if it has fewer + than five), unless they release you from this requirement. +</simpara></listitem> +<listitem><simpara>State on the Title page the name of the publisher of + the Modified Version, as the publisher.</simpara></listitem> +<listitem><simpara>Preserve all the copyright notices of the Document. +</simpara></listitem> +<listitem><simpara>Add an appropriate copyright notice for your + modifications adjacent to the other copyright notices. +</simpara></listitem> +<listitem><simpara>Include, immediately after the copyright notices, a + license notice giving the public permission to use the Modified + Version under the terms of this License, in the form shown in the + <link linkend="gfdl-addendum">Addendum</link> below. +</simpara></listitem> +<listitem><simpara>Preserve in that license notice the full lists of + Invariant Sections and required Cover Texts given in the Document's + license notice.</simpara></listitem> +<listitem><simpara>Include an unaltered copy of this License. +</simpara></listitem> +<listitem><simpara>Preserve the section Entitled "History", Preserve its + Title, and add to it an item stating at least the title, year, new + authors, and publisher of the Modified Version as given on the Title + Page. If there is no section Entitled "History" in the Document, + create one stating the title, year, authors, and publisher of the + Document as given on its Title Page, then add an item describing the + Modified Version as stated in the previous sentence. +</simpara></listitem> +<listitem><simpara>Preserve the network location, if any, given in the + Document for public access to a Transparent copy of the Document, and + likewise the network locations given in the Document for previous + versions it was based on. These may be placed in the "History" + section. You may omit a network location for a work that was + published at least four years before the Document itself, or if the + original publisher of the version it refers to gives permission. +</simpara></listitem> +<listitem><simpara>For any section Entitled "Acknowledgements" or + "Dedications", Preserve the Title of the section, and preserve in the + section all the substance and tone of each of the contributor + acknowledgements and/or dedications given therein. +</simpara></listitem> +<listitem><simpara>Preserve all the Invariant Sections of the Document, + unaltered in their text and in their titles. Section numbers or the + equivalent are not considered part of the section titles. +</simpara></listitem> +<listitem><simpara>Delete any section Entitled "Endorsements". + Such a section may not be included in the Modified Version. +</simpara></listitem> +<listitem><simpara>Do not retitle any existing section to be Entitled + "Endorsements" or to conflict in title with any Invariant Section. +</simpara></listitem> +<listitem><simpara>Preserve any Warranty Disclaimers. +</simpara></listitem> +</orderedlist> + +<para>If the Modified Version includes new front-matter sections or +appendices that qualify as Secondary Sections and contain no material +copied from the Document, you may at your option designate some or all +of these sections as invariant. To do this, add their titles to the +list of Invariant Sections in the Modified Version's license notice. +These titles must be distinct from any other section titles.</para> + +<para>You may add a section Entitled "Endorsements", provided it +contains nothing but endorsements of your Modified Version by various +parties--for example, statements of peer review or that the text has +been approved by an organization as the authoritative definition of a +standard.</para> + +<para>You may add a passage of up to five words as a Front-Cover Text, +and a passage of up to 25 words as a Back-Cover Text, to the end of the +list of Cover Texts in the Modified Version. Only one passage of +Front-Cover Text and one of Back-Cover Text may be added by (or through +arrangements made by) any one entity. If the Document already includes +a cover text for the same cover, previously added by you or by +arrangement made by the same entity you are acting on behalf of, you may +not add another; but you may replace the old one, on explicit permission +from the previous publisher that added the old one.</para> + +<para>The author(s) and publisher(s) of the Document do not by this +License give permission to use their names for publicity for or to +assert or imply endorsement of any Modified Version.</para> +</section> + +<section id="gfdl-5"><title>COMBINING DOCUMENTS</title> + +<para>You may combine the Document with other documents released under +this License, under the terms defined in <link linkend="gfdl-4">section +4</link> above for modified versions, provided that you include in the +combination all of the Invariant Sections of all of the original +documents, unmodified, and list them all as Invariant Sections of your +combined work in its license notice, and that you preserve all their +Warranty Disclaimers.</para> + +<para>The combined work need only contain one copy of this License, and +multiple identical Invariant Sections may be replaced with a single +copy. If there are multiple Invariant Sections with the same name but +different contents, make the title of each such section unique by adding +at the end of it, in parentheses, the name of the original author or +publisher of that section if known, or else a unique number. Make the +same adjustment to the section titles in the list of Invariant Sections +in the license notice of the combined work.</para> + +<para>In the combination, you must combine any sections Entitled +"History" in the various original documents, forming one section +Entitled "History"; likewise combine any sections Entitled +"Acknowledgements", and any sections Entitled "Dedications". You must +delete all sections Entitled "Endorsements".</para> +</section> + +<section id="gfdl-6"><title>COLLECTIONS OF DOCUMENTS</title> + +<para>You may make a collection consisting of the Document and other +documents released under this License, and replace the individual copies +of this License in the various documents with a single copy that is +included in the collection, provided that you follow the rules of this +License for verbatim copying of each of the documents in all other +respects.</para> + +<para>You may extract a single document from such a collection, and +distribute it individually under this License, provided you insert a +copy of this License into the extracted document, and follow this +License in all other respects regarding verbatim copying of that +document.</para> +</section> + +<section id="gfdl-7"><title>AGGREGATION WITH INDEPENDENT WORKS</title> + +<para>A compilation of the Document or its derivatives with other +separate and independent documents or works, in or on a volume of a +storage or distribution medium, is called an "aggregate" if the +copyright resulting from the compilation is not used to limit the legal +rights of the compilation's users beyond what the individual works +permit. When the Document is included in an aggregate, this License does +not apply to the other works in the aggregate which are not themselves +derivative works of the Document.</para> + +<para>If the Cover Text requirement of section 3 is applicable to these +copies of the Document, then if the Document is less than one half of +the entire aggregate, the Document's Cover Texts may be placed on covers +that bracket the Document within the aggregate, or the electronic +equivalent of covers if the Document is in electronic form. Otherwise +they must appear on printed covers that bracket the whole +aggregate.</para> +</section> + +<section id="gfdl-8"><title>TRANSLATION</title> + +<para>Translation is considered a kind of modification, so you may +distribute translations of the Document under the terms of section 4. +Replacing Invariant Sections with translations requires special +permission from their copyright holders, but you may include +translations of some or all Invariant Sections in addition to the +original versions of these Invariant Sections. You may include a +translation of this License, and all the license notices in the +Document, and any Warranty Disclaimers, provided that you also include +the original English version of this License and the original versions +of those notices and disclaimers. In case of a disagreement between the +translation and the original version of this License or a notice or +disclaimer, the original version will prevail.</para> + +<para>If a section in the Document is Entitled "Acknowledgements", +"Dedications", or "History", the requirement (section 4) to Preserve its +Title (section 1) will typically require changing the actual +title.</para> +</section> + +<section id="gfdl-9"><title>TERMINATION</title> + +<para>You may not copy, modify, sublicense, or distribute the Document +except as expressly provided for under this License. Any other attempt +to copy, modify, sublicense or distribute the Document is void, and will +automatically terminate your rights under this License. However, +parties who have received copies, or rights, from you under this License +will not have their licenses terminated so long as such parties remain +in full compliance.</para> +</section> + +<section id="gfdl-10"><title>FUTURE REVISIONS OF THIS LICENSE</title> + +<para>The Free Software Foundation may publish new, revised versions of +the GNU Free Documentation License from time to time. Such new versions +will be similar in spirit to the present version, but may differ in +detail to address new problems or concerns. See +http://www.gnu.org/copyleft/.</para> + +<para>Each version of the License is given a distinguishing version +number. If the Document specifies that a particular numbered version of +this License "or any later version" applies to it, you have the option +of following the terms and conditions either of that specified version +or of any later version that has been published (not as a draft) by the +Free Software Foundation. If the Document does not specify a version +number of this License, you may choose any version ever published (not +as a draft) by the Free Software Foundation.</para> +</section> + +<section id="gfdl-addendum"><title>ADDENDUM: How to use this License for + your documents</title> + +<para>To use this License in a document you have written, include a copy +of the License in the document and put the following copyright and +license notices just after the title page:</para> + +<blockquote id="copyright-sample"> + <title>Sample Invariant Sections list</title><para> + Copyright (c) YEAR YOUR NAME. + Permission is granted to copy, distribute and/or modify this document + under the terms of the GNU Free Documentation License, Version 1.2 + or any later version published by the Free Software Foundation; + with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. + A copy of the license is included in the section entitled "GNU + Free Documentation License". +</para></blockquote> + +<para>If you have Invariant Sections, Front-Cover Texts and Back-Cover +Texts, replace the "with...Texts." line with this:</para> + +<blockquote id="inv-cover-sample"> + <title>Sample Invariant Sections list</title> +<para> + with the Invariant Sections being LIST THEIR TITLES, with the + Front-Cover Texts being LIST, and with the Back-Cover Texts being LIST. +</para></blockquote> + +<para>If you have Invariant Sections without Cover Texts, or some other +combination of the three, merge those two alternatives to suit the +situation.</para> + +<para>If your document contains nontrivial examples of program code, we +recommend releasing these examples in parallel under your choice of free +software license, such as the GNU General Public License, to permit +their use in free software.</para> +</section> +</appendix> Added: projects/wiki/extensions/wiki2xml/global_functions.php =================================================================== --- projects/wiki/extensions/wiki2xml/global_functions.php (rev 0) +++ projects/wiki/extensions/wiki2xml/global_functions.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,43 @@ +<?php + +# Add authors to global list +function add_authors ( $authors ) { + global $wiki2xml_authors ; + foreach ( $authors AS $author ) { + if ( !in_array ( $author , $wiki2xml_authors ) ) { + $wiki2xml_authors[] = $author ; + } + } +} + +function add_author ( $author ) { + add_authors ( array ( $author ) ) ; + } + + +# For text file structure creation and browsing +function get_file_location_global ( $basedir , $ns , $title , $make_dirs = false ) { + $title = urlencode ( $title ) ; + $title = str_replace ( ":" , "_" , $title ) ; + $m = md5 ( $title ) ; + $ret = "" ; + $ret->file = $title ; + if ( $ret->file == "Con" ) $ret->file = "_Con" ; # Windows can't create files named "con.txt" (!), workaround + $ret->dir = $basedir . "/" . $ns ; + if ( $make_dirs ) @mkdir ( $ret->dir ) ; + $ret->dir .= "/" . substr ( $m , 0 , 1 ) ; + if ( $make_dirs ) @mkdir ( $ret->dir ) ; + $ret->dir .= "/" . substr ( $m , 1 , 2 ) ; + if ( $make_dirs ) @mkdir ( $ret->dir ) ; + $ret->fullname = $ret->dir . "/" . $ret->file ; + return $ret ; +} + + +function xml_articles_header() { + global $xmlg ; +# if ( !isset ( $xmlg['xml_articles_header'] ) ) return "" ; + return $xmlg['xml_articles_header'] ; +} + +?> Added: projects/wiki/extensions/wiki2xml/mediawiki_converter.php =================================================================== --- projects/wiki/extensions/wiki2xml/mediawiki_converter.php (rev 0) +++ projects/wiki/extensions/wiki2xml/mediawiki_converter.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,288 @@ +<?php + +# PHP4 and early PHP5 bug workaround: +require_once ( "filter_named_entities.php" ) ; + +require_once ( "global_functions.php" ) ; +require_once ( "wiki2xml.php" ) ; +require_once ( "content_provider.php" ) ; + +# A funtion to remove directories and subdirectories +# Modified from php.net +function SureRemoveDir($dir) { + if(!$dh = @opendir($dir)) return; + while (($obj = readdir($dh))) { + if($obj=='.' || $obj=='..') continue; + if (!(a)unlink($dir.&#39;/&#39;.$obj)) { + SureRemoveDir($dir.'/'.$obj); + } + } + @closedir ( $dh ) ; + @rmdir($dir) ; +} + +/** + * The main converter class + */ +class MediaWikiConverter { + + /** + * Converts a single article in MediaWiki format to XML + */ + function article2xml ( $title , &$text , $params = array () ) { + global $content_provider , $wiki2xml_authors ; + $ot = $title ; + $title = urlencode ( $title ) ; + $p = new wiki2xml ; + $p->auto_fill_templates = $params['resolvetemplates'] ; + $p->template_list = array () ; ; + foreach ( $params['templates'] AS $x ) { + $x = trim ( ucfirst ( $x ) ) ; + if ( $x != "" ) $p->template_list[] = $x ; + } + $xml = '<article' ; + if ( $title != "" ) { + $xml .= " title='{$title}'" ; + $content_provider->add_article ( urldecode ( $ot ) ) ; + } + $xml .= '>' ; + $xml .= $p->parse ( $text ) ; + if ( count ( $wiki2xml_authors ) > 0 ) { + $xml .= "<authors>" ; + foreach ( $wiki2xml_authors AS $author ) + $xml .= "<author>{$author}</author>" ; + $xml .= "</authors>" ; + } + $xml .= "</article>" ; + return $xml ; + } + + /** + * Converts XML to plain text + */ + function articles2text ( &$xml , $params = array () ) { + global $wiki2xml_authors ; + require_once ( "xml2txt.php" ) ; + + $wiki2xml_authors = array () ; + $x2t = new xml2php ; + $tree = $x2t->scanString ( $xml ) ; + if ( $params['plaintext_markup'] ) { + $tree->bold = '*' ; + $tree->italics = '/' ; + $tree->underline = '_' ; + } + if ( $params['plaintext_prelink'] ) { + $tree->pre_link = "&rarr;" ; + } + + $text = trim ( $tree->parse ( $tree ) ) ; + + $authors = "" ; + if ( count ( $wiki2xml_authors ) > 0 ) { + asort ( $wiki2xml_authors ) ; + $authors = "\n--------------------\nTHE ABOVE TEXT IS LICENSED UNDER THE GFDL. CONTRIBUTORS INCLUDE:\n\n" . + implode ( ", " , $wiki2xml_authors ) ; + } + + return $text . $authors ; + } + + /** + * Converts XML to XHTML + */ + function articles2xhtml ( &$xml , $params = array () ) { + global $xml2xhtml ; + require_once ( "xml2xhtml.php" ) ; + $lang = "EN" ; # Dummy + + $ret = "" ; + $ret .= '<?xml version="1.0" encoding="UTF-8" ?>' ; + $ret .= '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//' . $lang . '" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">' ; + if ( !$params['xhtml_source'] ) + $ret .= '<html xmlns="http://www.w3.org/1999/xhtml">' ; + else $ret .= '<html>' ; + $ret .= '<head>' ; + #$ret .= '<link rel="stylesheet" type="text/css" media="screen,projection" href="http://de.wikipedia.org/skins-1.5/monobook/main.css" />' ; + #$ret .= '<link rel="stylesheet" type="text/css" media="print" href="http://en.wikipedia.org/skins-1.5/common/commonPrint.css" />' ; + $ret .= '<link rel="stylesheet" type="text/css" href="href://' ; + $ret .= $params["site_base_url"] . 'index.php?title=MediaWiki:Common.css&amp;action=raw" />' ; + #$ret .= '<link rel="stylesheet" type="text/css" href="href://' ; + #$ret .= $params["site_base_url"] . 'index.php?title=MediaWiki:Monobook.css&amp;action=raw" />' ; + $ret .= '<title>' ; + if ( isset ( $params['page_title'] ) ) $ret .= $params['page_title'] ; + else $ret .= $params["book_title"] ; + $ret .= '</title>' ; + $ret .= '</head>' ; + $ret .= '<body>' ; + + convert_xml_xhtml ( $xml ) ; + $ret .= $xml2xhtml->s ; + +# $xml2xhtml = new XML2XHTML ; +# $ret .= $xml2xhtml->scan_xml ( $xml ) ; + + $ret .= '</body>' ; + $ret .= '</html>' ; + return $ret ; + } + + /** + * Converts XML to ODT XML + */ + function articles2odt ( &$xml , $params = array () , $use_gfdl = false ) { + global $wiki2xml_authors , $xml2odt ; + require_once ( "xml2odt.php" ) ; + + # XML text to tree + $xml2odt = new XML2ODT ; + $wiki2xml_authors = array () ; + $x2t = new xml2php ; + $tree = $x2t->scanString ( $xml ) ; + + # Tree to ODT + $out = "<?xml version='1.0' encoding='UTF-8' ?>\n" ; + $body = $tree->parse ( $tree ) ; + $out .= $xml2odt->get_odt_start () ; + $out .= '<office:body><office:text>' ; + $out .= $body ; + $out .= '</office:text></office:body>' ; + $out .= "</office:document-content>" ; + return $out ; + } + + /** + * Converts XML to DocBook XML + */ + function articles2docbook_xml ( &$xml , $params = array () , $use_gfdl = false ) { + global $wiki2xml_authors ; + require_once ( "xml2docbook_xml.php" ) ; + + $wiki2xml_authors = array () ; + $x2t = new xml2php ; + $tree = $x2t->scanString ( $xml ) ; + + # Chosing DTD; parameter-given or default + $dtd = "" ; + if ( isset ( $params['docbook']['dtd'] ) ) + $dtd = $params['docbook']['dtd'] ; + if ( $dtd == "" ) $dtd = 'http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd' ; + + $out = "<?xml version='1.0' encoding='UTF-8' ?>\n" ; + $out .= '<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN" "' . $dtd . '"' ; + if ( $use_gfdl ) { + $out .= "\n[<!ENTITY gfdl SYSTEM \"gfdl.xml\">]\n" ; + } + $out .= ">\n\n<book>\n" ; + $out2 = trim ( $tree->parse ( $tree ) ) ; + + $out .= "<bookinfo>" ; + $out .= "<title>" . $params['book_title'] . "</title>" ; + if ( count ( $wiki2xml_authors ) > 0 ) { + asort ( $wiki2xml_authors ) ; + $out .= "<authorgroup>" ; + foreach ( $wiki2xml_authors AS $author ) { + $out .= "<author><othername>{$author}</othername></author>" ; + } + $out .= "</authorgroup>" ; + } + $out .= "<legalnotice><para>" ; + $out .= "Permission to use, copy, modify and distribute this document under the GNU Free Documentation License (GFDL)." ; + $out .= "</para></legalnotice>" ; + $out .= "</bookinfo>" ; + + $out .= $out2 ; +/* + if ( count ( $wiki2xml_authors ) > 0 ) { + asort ( $wiki2xml_authors ) ; + $out .= "<appendix>" ; + $out .= "<title>List of contributors</title>" ; + $out .= "<para>All text in this document is licensed under the GFDL. The following is a list of contributors (anonymous editors are not listed).</para>" ; + $out .= "<para>" ; + $out .= implode ( ", " , $wiki2xml_authors ) ; + $out .= "</para>" ; + $out .= "</appendix>" ; + } +*/ + if ( $use_gfdl ) { + $out .= "\n&gfdl;\n" ; + } + + $out .= "\n</book>\n" ; + + return $out ; + } + + /** + * Converts XML to PDF via DocBook + * Requires special parameters in local.php to be set (see sample_local.php) + * Uses articles2docbook_xml + */ + function articles2docbook_pdf ( &$xml , $params = array () , $mode = "PDF" ) { + global $xmlg ; + $docbook_xml = $this->articles2docbook_xml ( $xml , $params , $params['add_gfdl'] ) ; + + # Create temporary directory + $temp_dir = "MWC" ; + $temp_dir .= substr ( mt_rand() , 0 , 4 ) ; + $temp_dir = tempnam ( $params['docbook']['temp_dir'], $temp_dir ) ; + $project = basename ( $temp_dir ) ; + unlink ( $temp_dir ) ; # It is currently a file, so... + mkdir ( $temp_dir ) ; + + # Write XML file + $xml_file = $temp_dir . "/" . $project . ".xml" ; + $handle = fopen ( $xml_file , 'wb' ) ; + fwrite ( $handle , utf8_encode ( $docbook_xml ) ) ; + fclose ( $handle ) ; + if ( $params['add_gfdl'] ) { + copy ( $xmlg['sourcedir'] . "/gfdl.xml" , $temp_dir . "/gfdl.xml" ) ; + } + + if ( $params['docbook']['out_dir'] ) { + $output_dir = $params['docbook']['out_dir']; + } else { + $output_dir = $params['docbook']['temp_dir']; + } + + + # Call converter + if ( $mode == "PDF" ) { + $command = str_replace ( "%1" , $xml_file , $params['docbook']['command_pdf'] ) ; + $out_subdir = 'pdf' ; + } else if ( $mode == "HTML" ) { + $command = str_replace ( "%1" , $xml_file , $params['docbook']['command_html'] ) ; + $out_subdir = 'html' ; + } + + # PHP4 does not have recursive mkdir + $output_dir = $output_dir . '/' . $out_subdir ; + if ( ! file_exists( $output_dir ) ) { + mkdir ( $output_dir ) ; + } + $output_dir = $output_dir . '/' . $project; + if ( ! file_exists( $output_dir ) ) { + mkdir ( $output_dir ) ; + } + + $command = $command . ' --nochunks --output ' . $output_dir; + + exec ( $command ) ; + + # Cleanup xml file + SureRemoveDir ( $temp_dir ) ; + + # Check if everything is OK + $output_filename = $output_dir . '/' . $project . '.' . $out_subdir ; + if ( !file_exists ( $output_filename ) ) { + header('Content-type: text/html; charset=utf-8'); + print "ERROR : Document was not created: Docbook creator has failed! Command was: $command. output_filename = $output_filename" ; + } + + # Return pdf filename + return $output_filename ; + } +} + + +?> Added: projects/wiki/extensions/wiki2xml/sample_local.php =================================================================== --- projects/wiki/extensions/wiki2xml/sample_local.php (rev 0) +++ projects/wiki/extensions/wiki2xml/sample_local.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,74 @@ +<?php + +/** + * You can create your own local.php file, similar to this one, to configure + * your local installation. + * If you do not create a local.php file, the scripts will run with + * default settings. + */ + +$xmlg["site_base_url"] = "127.0.0.1/phase3" ; +$xmlg["use_special_export"] = 1 ; + +# Directory for temporary files: +$xmlg["temp_dir"] = "C:/windows/temp" ; + +$xmlg["docbook"] = array ( + "command_pdf" => "C:/docbook/bat/docbook_pdf.bat %1" , + "command_html" => "C:/docbook/bat/docbook_html.bat %1" , + "temp_dir" => "C:/docbook/repository" , + "out_dir" => "C:/docbook/output" , + "dtd" => "file:/c:/docbook/dtd/docbookx.dtd" +) ; + +/* To allow parameters passed as URL parameter ($_GET), set +$xmlg['allow_get'] = true ; + +Parameters: +doit=1 +text=lines_of_text_or_titles +whatsthis=wikitext/articlelist +site=en.wikipedia.org/w +output_format=xml/text/xhtml/docbook_xml/odt_xml/odt + +Optional: +use_templates=all/none/these/notthese +templates=lines_of_templates +document_title= +add_gfdl=1 +keep_categories=1 +keep_interlanguage=1 +*/ + + + +# To use the toolserver text access, set +# $xmlg["use_toolserver_url"] = true ; +# $xmlg["use_special_export"] = false ; + +# On Windows, set +# $xmlg['is_windows'] = true ; + +### Uncomment the following to use Special:Export and (potentially) automatic +### authors list; a little slower, though: +#$xmlg["use_special_export"] = 1 ; + + +### Uncomment and localize the following to offer ODT export + +# Path to the zip/unzip programs; can be omitted if in path: +#$xmlg["zip_odt_path"] = "E:\\Program Files\\7-Zip" ; + +# Command to zip directory $1 to file $2; +# NOTE THE '*' AFTER '$2' FOR WINDOWS ONLY! +#$xmlg["zip_odt"] = '7z.exe a -r -tzip $1 $2*' ; + +# Command to unzip file $1 to directory $2: +#$xmlg["unzip_odt"] = '7z.exe x $1 -o$2' ; + + +# If you want to do text-file browsing, run "xmldump2files.php" once +# (see settings there), then set this: +# $base_text_dir = "C:/dewiki-20060327-pages-articles" ; + +?> Added: projects/wiki/extensions/wiki2xml/template.odt =================================================================== (Binary files differ) Property changes on: projects/wiki/extensions/wiki2xml/template.odt ___________________________________________________________________ Name: svn:mime-type + application/octet-stream Added: projects/wiki/extensions/wiki2xml/test.xml =================================================================== --- projects/wiki/extensions/wiki2xml/test.xml (rev 0) +++ projects/wiki/extensions/wiki2xml/test.xml 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,35 @@ +<?xml version='1.0' encoding='UTF-8' ?> +<articles loadtime='0 sec' rendertime='0.0158550739288 sec' totaltime='0.0158550739288 sec'> +<article title='Main+Page'> +<paragraph> +You have reached a<space/><italics>developper</italics><space/>mediawiki installation :)</paragraph> +<paragraph> +Don't trust anything you might find here and expect crashes !</paragraph> +<paragraph> +<link><target>User:Hashar</target><part>Hashar</part></link><space/>23:48, 13 April 2006 (CEST)</paragraph> +<paragraph> +<link><target>TOTO</target></link></paragraph> +<paragraph> +<link><target>redircat</target></link></paragraph> +<paragraph> +number of articles:<space/><xhtml:div class='noarticletext'>There is currently no text in this page, you can<space/><link><target>Special:Search/Wiki2XML</target><part>search for this page title</part></link><space/>in other pages or<space/><link type='external' href='http://twenkill.dyndns.org/wiki?title=Special:Wiki2XML&amp;... this page</link>.</xhtml:div></paragraph> +<paragraph> + <xhtml:pre>Oh no this is some ugly code</xhtml:pre> +</paragraph> +<list type='numbered'> + <listitem>numb 1</listitem> + <listitem>numb 2</listitem> + <listitem>numb 3</listitem> +</list> +<paragraph> +And unordered:</paragraph> +<list type='bullet'> + <listitem>yeah 1</listitem> + <listitem><link type='external' href='http://www.google.com/'>Google</link></listitem... + <listitem>yeah 3</listitem> +</list> +<paragraph> + <link><target>Tobedoom</target></link> +</paragraph> +</article> +</articles> Added: projects/wiki/extensions/wiki2xml/w2x.php =================================================================== --- projects/wiki/extensions/wiki2xml/w2x.php (rev 0) +++ projects/wiki/extensions/wiki2xml/w2x.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,471 @@ +<?php +# Copyright by Magnus Manske (2005 - 2006) +# Released under GPL + +@set_time_limit ( 0 ) ; # No time limit +ini_set('user_agent','MSIE 4\.0b2;'); # Fake user agent + +if( !defined( 'MEDIAWIKI' ) ) { # Stand-alone + include_once ( "default.php" ) ; # Which will include local.php, if available +} + +require_once ( "mediawiki_converter.php" ) ; + +## TIMER FUNCTION + +function microtime_float() +{ + list($usec, $sec) = explode(" ", microtime()); + return ((float)$usec + (float)$sec); +} + +function get_form ( $as_extension = false ) { + global $xmlg ; + + $_wt = get_param ( 'whatsthis' , 'articlelist' ) ; + $wt['wikitext'] = $wt['articlelist'] = $wt['listpagename'] = "" ; + $wt[$_wt] = 'checked' ; + + $xmlg["site_base_url"] = get_param('site',$xmlg["site_base_url"]) ; + $_out = get_param ( 'output_format' , 'xml' ) ; + $out['xml'] = $out['text'] = $out['translated_text'] = $out['xhtml'] = $out['docbook_xml'] = $out['docbook_pdf'] = $out['docbook_html'] = + $out['odt_xml'] = $out['odt'] = '' ; + $out[$_out] = 'checked' ; + + $optional = array () ; + if ( isset ( $xmlg['docbook']['command_pdf'] ) ) { + $optional[] = "<INPUT {$out['docbook_pdf']} type='radio' name='output_format' value='docbook_pdf'>DocBook PDF" ; + } + if ( isset ( $xmlg['docbook']['command_html'] ) ) { + $optional[] = "<INPUT {$out['docbook_html']} type='radio' name='output_format' value='docbook_html'>DocBook HTML" ; + } + if ( isset ( $xmlg['zip_odt'] ) ) { + $optional[] = "<INPUT {$out['odt_xml']} type='radio' name='output_format' value='odt_xml'>OpenOffice XML" ; + $optional[] = "<INPUT {$out['odt']} type='radio' name='output_format' value='odt'>OpenOffice ODT" . + "<input type='checkbox' name='odt_footnote' value='1' ".(get_param('odt_footnote',false)?'checked':'').">References as endnotes (instead of footnotes)" ; + } + $optional = "<br/>" . implode ( "<br/>" , $optional ) ; + + if ( $as_extension ) $site = "<input type='hidden' name='site' value=''/>" ; + else $site = "Site : http://<input type='text' name='site' value='".$xmlg["site_base_url"]."'/>/index.php<br/>" ; + + $additional = array() ; + if ( $xmlg['allow_get'] ) { + $additional[] = "This page can be called with parameters: w2x.php?doit=1&whatsthis=articlelist&site=en.wikipedia.org/w&... ; + $additional[] = "For additional parameters, see <a href='README'>here</a>" ; + } + + # Plain text translation options + $a = array ( + 'en' => 'English', + 'de' => 'German', + 'fr' => 'French', + 'es' => 'Spanish', + 'it' => 'Italian', + ) ; + asort ( $a ) ; + $tttlo = "" ; + foreach ( $a AS $b => $c ) { + $tttlo .= "<option value='{$b}'>{$c}</option>" ; + } + + $additional = "<div style='text-align:center; border-top:1px solid black;width:100%;font-size:12px'>" . + implode ( "<br/>" , $additional ) . + "</div>" ; + +return "<form method='post'> +<h2>Paste article list or wikitext here</h2> +<table border='0' width='100%'><tr> +<td valign='top'><textarea rows='20' cols='80' style='width:100%' name='text'>" . +get_param ( 'text' , '' ) . +"</textarea></td> +<td width='200px' valign='top' nowrap> +<INPUT checked type='radio' name='use_templates' value='all'>Use all templates<br/> +<INPUT type='radio' name='use_templates' value='none'>Do not use templates<br/> +<INPUT type='radio' name='use_templates' value='these'>Use these templates<br/> +<INPUT type='radio' name='use_templates' value='notthese'>Use all but these templates<br/> +<textarea rows='15' cols='30' style='width:100%' name='templates'></textarea> +</td></tr></table> +<table border='0'><tr> +<td valign='top'> +This is<br/> +<INPUT {$wt['wikitext']} type='radio' name='whatsthis' value='wikitext'>raw wikitext <br/> +<INPUT {$wt['articlelist']} type='radio' name='whatsthis' value='articlelist'>a list of articles<br/> +<INPUT {$wt['listpagename']} type='radio' name='whatsthis' value='listpagename'>the name of an article with a list of pages<br/> + +{$site} +Title : <input type='text' name='document_title' value='' size=40/><br/> +<input type='checkbox' name='add_gfdl' value='1' checked>Include GFDL (for some output formats)</input><br/> +<input type='checkbox' name='keep_categories' value='1' checked>Keep categories</input><br/> +<input type='checkbox' name='keep_interlanguage' value='1' checked>Keep interlanguage links</input><br/> +<input type='submit' name='doit' value='Convert'/> +</td><td valign='top' style='border-left:1px black solid'> +<b>Output</b> +<br/><INPUT {$out['xml']} type='radio' name='output_format' value='xml'>XML +<br/><INPUT {$out['text']} type='radio' name='output_format' value='text'>Plain text + <input type='checkbox' name='plaintext_markup' value='1' ".(get_param('plaintext_markup',true)?'checked':'').">Use *_/ markup</input> + <input type='checkbox' name='plaintext_prelink' value='1' ".(get_param('plaintext_prelink',true)?'checked':'').">Put &rarr; before internal links</input> +<br/><INPUT {$out['translated_text']} type='radio' name='output_format' value='translated_text'>Plain text, google-translated to + <select name='translated_text_target_language'>{$tttlo}</select> (works only for wikipedia/wikibooks) +<br/><INPUT {$out['xhtml']} type='radio' name='output_format' value='xhtml'>XHTML + <input type='checkbox' name='xhtml_justify' value='1' ".(get_param('xhtml_justify',true)?'checked':'').">Align paragraphs as 'justify'</input> + <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> + <input type='checkbox' name='xhtml_source' value='1' ".(get_param('xhtml_source',false)?'checked':'').">Return source XHTML</input> +<br/><INPUT {$out['docbook_xml']} type='radio' name='output_format' value='docbook_xml'>DocBook XML +{$optional} +</tr></table> +</form> +<p> +Known issues: +<ul> +<li>In templates, {{{variables}}} used within &lt;nowiki&gt; tags will be replaced as well (too lazy to strip them)</li> +<li>HTML comments are removed (instead of converted into XML tags)</li> +</ul>{$additional} +</p>" ; +} + +function get_param ( $s , $default = NULL ) { + global $xmlg ; + if ( $xmlg['allow_get'] ) { + if ( isset ( $_REQUEST[$s] ) ) { + return $_REQUEST[$s] ; + } else { + return $default ; + } + } else { + if ( isset ( $_POST[$s] ) ) { + return $_POST[$s] ; + } else { + return $default ; + } + } +} + +# add one article to the stack of to-be-converted articles +function push_article ( &$aArticles, $article ) { + + # convert _ to ' ' + $a = trim( $article ); + if ( $a != "" ) { + $aArticles[] = preg_replace( '/_/', ' ', $a ); + } + +} + +# Append XML, or links to XML temporary files +function append_to_xml ( &$xml , $new_xml ) { + global $xmlg ; + if ( $xmlg["use_xml_temp_files"] ) { # Use temp files + if ( !is_array ( $xml ) ) $xml = array () ; + + do { + $tmp_file_name = tempnam ( $xmlg["temp_dir"] , "XMLTMP" ) ; + $tmp_file = fopen($tmp_file_name, 'wb') ; + } while ( $tmp_file === false ) ; + fwrite ( $tmp_file , $new_xml ) ; + fclose ( $tmp_file ) ; + + $xml[] = $tmp_file_name ; + } else { # Do not use temp files + $xml .= $new_xml ; + } +} + +# Returns the next article XML, or false +function xml_shift ( &$xml ) { + if ( !is_array ( $xml ) ) { # Do not use temp files + if ( $xml != '' ) { + $x = $xml ; + $xml = array () ; + return $x ; + } + return false ; + } else { # Use temp files + if ( count ( $xml ) == 0 ) return false ; + $x = array_shift ( $xml ) ; + $ret = file_get_contents ( $x ) ; + unlink ( $x ) ; + return $ret ; + } +} + +# Free temporary XML files, if any +# Should not be necessary if xml_shift was used +function xml_cleanup ( &$xml ) { + global $xmlg ; + if ( !$xmlg["use_xml_temp_files"] ) return ; # not using temp files + if ( !is_array ( $xml ) ) return false ; + foreach ( $xml AS $x ) { + unlink ( $x ) ; + } + $xml = array () ; +} + + +## MAIN PROGRAM + +if ( get_param('doit',false) ) { # Process + $wikitext = stripslashes ( get_param('text') ) ; + + if( !defined( 'MEDIAWIKI' ) ) { # Stand-alone + $content_provider = new ContentProviderHTTP ; + } else { # MediaWiki extension + $content_provider = new ContentProviderMySQL ; + } + $converter = new MediaWikiConverter ; + + $xmlg["book_title"] = get_param('document_title'); + $xmlg["site_base_url"] = get_param('site') ; + $xmlg["resolvetemplates"] = get_param('use_templates','all') ; + $xmlg['templates'] = explode ( "\n" , get_param('templates','') ) ; + $xmlg['add_gfdl'] = get_param('add_gfdl',false) ; + $xmlg['keep_interlanguage'] = get_param('keep_interlanguage',false) ; + $xmlg['keep_categories'] = get_param('keep_categories',false) ; + + # the article list + $aArticles = array () ; + + $t = microtime_float() ; + $xml = "" ; + + $format = get_param('output_format') ; + $whatsthis = get_param('whatsthis') ; + + # Catch listnamepage + if ( $whatsthis == "listpagename" ) { + $listpage = trim ( array_shift ( explode ( "\n" , $wikitext ) ) ) ; + $wikitext = $content_provider->get_wiki_text ( $listpage ) ; + $lines = explode ( "\n" , $wikitext ) ; + $wikitext = array () ; + foreach ( $lines AS $l ) { + $l1 = substr ( $l , 0 , 1 ) ; + if ( $l1 != '*' && $l1 != '#' && $l1 != ':' ) continue ; + $l = explode ( '[[' , $l , 2 ) ; + $l = trim ( array_shift ( explode ( ']]' , array_pop ( $l ) , 2 ) ) ) ; + if ( $l == '' ) continue ; + $wikitext[] = $l ; + } + $wikitext = implode ( "\n" , $wikitext ) ; + $whatsthis = 'articlelist' ; + } + + # QUICK HACK! NEEDS TO WORK! + if ( $format == "odt" || $format == "odt_xml" || $format == "docbook_pdf" || $format == "docbook_html" || $format == "docbook_xml" ) { + $xmlg["allow_xml_temp_files"] = false ; + } + + if ( $whatsthis == "wikitext" ) { + $content_provider->first_title = "Raw wikitext page" ; + $wiki2xml_authors = array () ; + $xml = $converter->article2xml ( "" , $wikitext , $xmlg ) ; + } else { + if ( $xmlg['allow_xml_temp_files'] ) $xmlg['use_xml_temp_files'] = true ; + + foreach ( explode ( "\n" , $wikitext ) AS $a ) { + push_article( $aArticles, $a ); + } + + # set the first article name as the default title + if ($xmlg["book_title"] == '') { + $xmlg["book_title"] = $aArticles[0]; + } + # as long as we have articles to convert (this might change in between!) + while ( $a = array_shift( $aArticles ) ) { + $wiki2xml_authors = array () ; + + # Article page|Article name + $a = explode ( '|' , $a ) ; + if ( count ( $a ) == 1 ) $a[] = $a[0] ; + $title_page = trim ( array_shift ( $a ) ) ; + $title_name = trim ( array_pop ( $a ) ) ; + + $wikitext = $content_provider->get_wiki_text ( $title_page ) ; + add_authors ( $content_provider->authors ) ; + append_to_xml ( $xml , $converter->article2xml ( $title_name , $wikitext , $xmlg, $aArticles ) ) ; + #$xml .= $converter->article2xml ( $title_name , $wikitext , $xmlg, &$aArticles ) ; + } + } + $t = microtime_float() - $t ; + $tt = round( $t, 3 ) ; + $lt = round( $content_provider->load_time, 3 ) ; + $t = round( $t - $lt, 3) ; + + $xmlg['xml_articles_header'] = "<articles xmlns:xhtml=\" \" loadtime='{$lt} sec' rendertime='{$t} sec' totaltime='{$tt} sec'>" ; + + # Output format + if ( $format == "xml" ) { + header('Content-type: text/xml; charset=utf-8'); + print "<?xml version='1.0' encoding='UTF-8' ?>\n" ; + print xml_articles_header() ; + while ( $x = xml_shift ( $xml ) ) print $x ; + print "</articles>" ; + } else if ( $format == "text" ) { + $xmlg['plaintext_markup'] = get_param('plaintext_markup',false) ; + $xmlg['plaintext_prelink'] = get_param('plaintext_prelink',false) ; + $out = $converter->articles2text ( $xml , $xmlg ) ; + $out = str_replace ( "\n" , "<br/>" , $out ) ; + header('Content-type: text/html; charset=utf-8'); + print $out ; + + } else if ( $format == "translated_text" ) { + $xmlg['plaintext_markup'] = false ; + $xmlg['plaintext_prelink'] = false ; + $out = $converter->articles2text ( $xml , $xmlg ) ; + #$out = str_replace ( "\n" , "<br/>" , $out ) ; + #header('Content-type: text/html; charset=utf-8'); + #print $out ; + $out = explode ( "\n" , $out ) ; + array_shift ( $out ) ; + $out = trim ( implode ( "\n" , $out ) ) ; + $source_language = array_shift ( explode ( '.' , $xmlg["site_base_url"] ) ) ; + $target_language = get_param ( 'translated_text_target_language' , 'en' ) ; + $langpair = urlencode ( "{$source_language}|{$target_language}" ) ; + $url = "http://www.google.com/translate_t?langpair={$langpair}&text=" . urlencode ( utf8_decode ( $out ) ) ; + echo file_get_contents ( $url ) ; + + } else if ( $format == "xhtml" ) { + $xmlg['xhtml_justify'] = get_param ( 'xhtml_justify' , false ) ; + $xmlg['xhtml_logical_markup'] = get_param ( 'xhtml_logical_markup' , false ) ; + $xmlg['xhtml_source'] = get_param ( 'xhtml_source' , false ) ; + + if ( $xmlg['xhtml_source'] ) { + header('Content-type: text/xml; charset=utf-8'); + #header('Content-type: text/html; charset=utf-8'); + $s = $converter->articles2xhtml ( $xml , $xmlg ) ; + $s = str_replace ( '>' , ">\n" , $s ) ; + $s = str_replace ( '<' , "\n<" , $s ) ; + $s = str_replace ( "\n\n" , "\n" , $s ) ; + echo trim ( $s ) ; + #echo str_replace ( "\n" , '<br/>' , htmlentities ( trim ( $s ) ) ) ; + } else { + # Header hack for IE + if ( stristr($_SERVER["HTTP_ACCEPT"],"application/xhtml+xml") ) { + header("Content-type: application/xhtml+xml"); + } else { + header("Content-type: text/html"); + } + echo $converter->articles2xhtml ( $xml , $xmlg ) ; + } + + } else if ( $format == "odt" || $format == "odt_xml" ) { + if ( isset ( $_REQUEST['odt_footnote'] ) ) $xmlg["odt_footnote"] = 'endnote' ; + if ( $xmlg['sourcedir'] == '.' ) $cwd = getcwd() ; + else $cwd = $xmlg['sourcedir'] ; + $template_file = $cwd . '/template.odt' ; + + $dir_file = tempnam($xmlg["temp_dir"], "ODD"); + $dir = $dir_file . "-DIR" ; + $xmlg['image_destination'] = $dir . "/Pictures" ; + + $zipdir = $cwd ; + if ( isset ( $xmlg["zip_odt_path"] ) ) # Windows strange bug workaround + $zipdir = $xmlg["zip_odt_path"] ; + + chdir ( $zipdir ) ; + + # Unzip template + $cmd = $xmlg['unzip_odt'] ; + $cmd = str_replace ( '$1' , escapeshellarg ( $template_file ) , $cmd ) ; + $cmd = str_replace ( '$2' , escapeshellarg ( $dir ) , $cmd ) ; + exec ( $cmd ) ; + + # Convert XML to ODT + chdir ( $cwd ) ; + if ( $format == "odt_xml" ) $content_provider->block_file_download = true ; + $out = $converter->articles2odt ( $xml , $xmlg ) ; + chdir ( $zipdir ) ; + + # Create ODT structure + $handle = fopen ( $dir . "/content.xml" , "w" ) ; + if ($handle) { + fwrite ( $handle , $out ) ; + fclose ( $handle ) ; + # Generate temporary ODT file + $out_file = tempnam('', "ODT"); + $cmd = $xmlg['zip_odt'] ; + $cmd = str_replace ( '$1' , escapeshellarg ( $out_file ) , $cmd ) ; + + if ( $xmlg['is_windows'] ) { + $cmd = str_replace ( '$2' , escapeshellarg ( $dir . "/" ) , $cmd ) ; + } else { + $cmd = str_replace ( '$2' , escapeshellarg ( './' ) , $cmd ) ; + # linux/unix zip needs to be in the directory, otherwise it will + # include needless parts into the directory structure + chdir ($dir); + # remove the output if it for some reason already exists + } + + @unlink ( $out_file ) ; + exec ( $cmd ) ; + + if ( $format == "odt" ) { # Return ODT file + $filename = $xmlg["book_title"] ; + if (!preg_match('/\.[a-zA-Z]{3}$/',$filename)) { $filename .= '.odt'; } + if (!preg_match('/\.[a-zA-Z]{3}$/',$out_file)) { $out_file .= '.zip'; } + header('Content-type: application/vnd.oasis.opendocument.text; charset=utf-8'); + header('Content-Disposition: inline; filename="'.$filename.'"'); + # XXX TODO: error handling here + $handle = fopen($out_file, 'rb'); + fpassthru ( $handle ) ; + fclose ( $handle ) ; + } else { # Return XML + header('Content-type: text/xml; charset=utf-8'); + print str_replace ( ">" , ">\n" , $out ) ; + } + + # Cleanup + SureRemoveDir ( $dir ) ; + @rmdir ( $dir ) ; + @unlink ( $dir_file ) ; + @unlink ( $out_file ) ; + chdir ( $cwd ) ; + } # error occured + + } else if ( $format == "docbook_xml" ) { + $out = $converter->articles2docbook_xml ( $xml , $xmlg ) ; + header('Content-type: text/xml; charset=utf-8'); + print $out ; + } else if ( $format == "docbook_pdf" || $format == "docbook_html" ) { + $filetype = substr ( $format , 8 ) ; + $filename = $converter->articles2docbook_pdf ( $xml , $xmlg , strtoupper ( $filetype ) ) ; + + if ( file_exists ( $filename ) ) { + $fp = fopen($filename, 'rb'); + if ( $format == "docbook_pdf" ) { + header('Content-Type: application/pdf'); + header("Content-Length: " . (string) filesize($filename)); + header('Content-Disposition: attachment; filename="'.$xmlg["book_title"].'.pdf"'); + } else if ( $format == "docbook_html" ) { + header('Content-Type: text/html'); + header("Content-Length: " . (string) filesize($filename)); + header('Content-Disposition: inline; filename="'.$xmlg["book_title"].'.html"'); + } + fpassthru($fp); + fclose ( $fp ) ; + } + + # Cleanup + $pdf_dir = dirname ( dirname ( $filename ) ) ; + SureRemoveDir ( $pdf_dir ) ; + @rmdir ( $pdf_dir ) ; + } + xml_cleanup ( $xml ) ; + exit ; +} else { # Show the form + if( !defined( 'MEDIAWIKI' ) ) { # Stand-alone + header('Content-type: text/html; charset=utf-8'); + print " +<html><head></head><body> +<h1>Magnus' magic MediaWiki-to-XML-to-stuff converter</h1> +<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>" ; + print get_form () ; + print "</body></html>" ; + } else { # MediaWiki extension + $out = get_form ( true ) ; + } + +} + +#<input type='checkbox' name='resolvetemplates' value='1' checked>Automatically resolve templates</input><br/> + +?> Added: projects/wiki/extensions/wiki2xml/wiki2xml.php =================================================================== --- projects/wiki/extensions/wiki2xml/wiki2xml.php (rev 0) +++ projects/wiki/extensions/wiki2xml/wiki2xml.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,1452 @@ +<?php +# Copyright by Magnus Manske (2005) +# Released under GPL + +$wiki2xml_authors = array () ; + +class wiki2xml + { + var $cnt = 0 ; # For debugging purposes + var $protocols = array ( "http" , "https" , "news" , "ftp" , "irc" , "mailto" ) ; + var $errormessage = "ERROR!" ; + var $compensate_markup_errors = true; + var $auto_fill_templates = 'all' ; # Will try and replace templates right inline, instead of using <template> tags; requires global $content_provider + var $use_space_tag = true ; # Use <space/> instead of spaces before and after tags + var $allowed = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890 +-#:;.,%="\'\\' ; + var $directhtmltags = array ( + "b" => "xhtml:b", + "i" => "xhtml:i", + "u" => "xhtml:u", + "s" => "xhtml:s", + "p" => "xhtml:p", + "br" => "xhtml:br", + "em" => "xhtml:em", + "div" => "xhtml:div", + "span" => "xhtml:span", + "big" => "xhtml:big", + "small" => "xhtml:small", + "sub" => "xhtml:sub", + "sup" => "xhtml:sup", + "font" => "xhtml:font", + "center" => "xhtml:center", + "table" => "xhtml:table", + "tr" => "xhtml:tr", + "th" => "xhtml:th", + "td" => "xhtml:td", + "pre" => "xhtml:pre", + "code" => "xhtml:code", + "caption" => "xhtml:caption", + "cite" => "xhtml:cite", + "ul" => "xhtml:ul", + "ol" => "xhtml:ol", + "li" => "xhtml:li", + "tt" => "xhtml:tt", + "h1" => "xhtml:h1", + "h2" => "xhtml:h2", + "h3" => "xhtml:h3", + "h4" => "xhtml:h4", + "h5" => "xhtml:h5", + "h6" => "xhtml:h6", + "h7" => "xhtml:h7", + "h8" => "xhtml:h8", + "h9" => "xhtml:h9", + ) ; + + var $w ; # The wiki text + var $wl ; # The wiki text length + var $bold_italics ; + var $tables = array () ; # List of open tables + var $profile = array () ; + + # Some often used functions + + /** + * Matches a function to the current text (default:once) + */ + function once ( &$a , &$xml , $f , $atleastonce = true , $many = false ) + { + $f = "p_{$f}" ; + $cnt = 0 ; +# print $f . " : " . htmlentities ( substr ( $this->w , $a , 20 ) ) . "<br/>" ; flush () ; +# if ( !isset ( $this->profile[$f] ) ) $this->profile[$f] = 0 ; # PROFILING + do { +# $this->profile[$f]++ ; # PROFILING + $matched = $this->$f ( $a , $xml ) ; + if ( $matched && $many ) $again = true ; + else $again = false ; + if ( $matched ) $cnt++ ; + } while ( $again ) ; + if ( !$atleastonce ) return true ; + if ( $cnt > 0 ) return true ; + return false ; + } + + function onceormore ( &$a , &$xml , $f ) + { + return $this->once ( $a , $xml , $f , true , true ) ; + } + + function nextis ( &$a , $t , $movecounter = true ) + { + if ( substr ( $this->w , $a , strlen ( $t ) ) != $t ) return false ; + if ( $movecounter ) $a += strlen ( $t ) ; + return true ; + } + + function nextchar ( &$a , &$x ) + { + if ( $a >= $this->wl ) return false ; + $x .= htmlspecialchars ( $this->w[$a] ) ; + $a++ ; + return true ; + } + + function ischaracter ( $c ) + { + if ( $c >= 'A' && $c <= 'Z' ) return true ; + if ( $c >= 'a' && $c <= 'z' ) return true ; + return false ; + } + + function skipblanks ( &$a , $blank = " " ) + { + while ( $a < $this->wl ) + { + if ( $this->w[$a] != $blank ) return ; + $a++ ; + } + } + + ############## + + + function p_internal_link_target ( &$a , &$xml , $closeit = "]]" ) + { + return $this->p_internal_link_text ( $a , $xml , true , $closeit ) ; + } + + function p_internal_link_text2 ( &$a , &$xml , $closeit ) + { + $bi = $this->bold_italics ; + $ret = $this->p_internal_link_text ( $a , $xml , false , $closeit , false ) ; + if ( $closeit == ']]' && '' != $this->bold_italics ) $ret = false ; # Dirty hack to ensure good XML; FIXME!!! + return $ret ; + } + + function p_internal_link_text ( &$a , &$xml , $istarget = false , $closeit = "]]" , $mark = true ) + { + $b = $a ; + $x = "" ; + if ( $b >= $this->wl ) return false ; + $bi = $this->bold_italics ; + $this->bold_italics = '' ; + $closeit1 = $closeit[0] ; + while ( 1 ) + { + if ( $b >= $this->wl ) { + $this->bold_italics = $bi ; + return false ; + } + $c = $this->w[$b] ; + if ( $closeit != "}}" && $c == "\n" ) { + $this->bold_italics = $bi ; + return false ; + } + if ( $c == "|" ) break ; + if ( $c == $closeit1 && $this->nextis ( $b , $closeit , false ) ) break ; + if ( !$istarget ) { + if ( $c == "[" && $this->once ( $b , $x , "internal_link" ) ) continue ; + if ( $c == "[" && $this->once ( $b , $x , "external_link" ) ) continue ; + if ( $c == "{" && $this->once ( $b , $x , "template_variable" ) ) continue ; + if ( $c == "{" && $this->once ( $b , $x , "template" ) ) continue ; + if ( $c == "<" && $this->once ( $b , $x , "html" ) ) continue ; + if ( $c == "'" && $this->p_bold ( $b , $x , "internal_link_text2" , $closeit ) ) { break ; } + if ( $c == "'" && $this->p_italics ( $b , $x , "internal_link_text2" , $closeit ) ) { break ; } + if ( $b + 10 < $this->wl && + ( $this->w[$a+5] == '/' && $this->w[$a+7] == '/' ) && + $this->once ( $b , $x , "external_freelink" ) ) continue ; + } else { + if ( $c == "{" && $this->once ( $b , $x , "template" ) ) continue ; + } + $x .= htmlspecialchars ( $c ) ; + $b++ ; +/* if ( $b >= $this->wl ) { + $this->bold_italics = $bi ; + return false ; + }*/ + } + + if ( $closeit == "}}" && !$istarget ) { + $xml .= substr ( $this->w , $a , $b - $a ) ; + $a = $b ; + $this->bold_italics = $bi ; + return true ; + } + + $x = trim ( str_replace ( "\n" , "" , $x ) ) ; + if ( $mark ) + { + if ( $istarget ) $xml .= "<target>{$x}</target>" ; + else $xml .= "<part>{$x}</part>" ; + + } + else $xml .= $x ; + $a = $b ; + $this->bold_italics = $bi ; + return true ; + } + + function p_internal_link_trail ( &$a , &$xml ) + { + $b = $a ; + $x = "" ; + while ( 1 ) + { + $c = "" ; + + if ( !$this->nextchar ( $b , $c ) ) break ; + + if ( $this->ischaracter ( $c ) ) + { + $x .= $c ; + } + else + { + $b-- ; + break ; + } + } + if ( $x == "" ) return false ; # No link trail + $xml .= "<trail>{$x}</trail>" ; + $a = $b ; + return true ; + } + + function p_internal_link ( &$a , &$xml ) + { + $x = "" ; + $b = $a ; + if ( !$this->nextis ( $b , "[[" ) ) return false ; + if ( !$this->p_internal_link_target ( $b , $x , "]]" ) ) return false ; + while ( 1 ) + { + if ( $this->nextis ( $b , "]]" ) ) break ; + if ( !$this->nextis ( $b , "|" ) ) return false ; + if ( !$this->p_internal_link_text ( $b , $x , false , "]]" ) ) return false ; + } + $this->p_internal_link_trail ( $b , $x ) ; + $xml .= "<link>{$x}</link>" ; + $a = $b ; + return true ; + } + + function p_magic_variable ( &$a , &$xml ) + { + $x = "" ; + $b = $a ; + if ( !$this->nextis ( $b , "__" ) ) return false ; + $varname = "" ; + for ( $c = $b ; $c < $this->wl && $this->w[$c] != '_' ; $c++ ) + $varname .= $this->w[$c] ; + if ( !$this->nextis ( $c , "__" ) ) return false ; + $xml .= "<magic_variable>{$varname}</magic_variable>" ; + $a = $c ; + return true ; + } + + # Template and template variable, utilizing parts of the internal link methods + function p_template ( &$a , &$xml ) + { + global $content_provider ; + $x = "" ; + $b = $a ; + if ( !$this->nextis ( $b , "{{" ) ) return false ; +# if ( $this->nextis ( $b , "{" , false ) ) return false ; # Template names may not start with "{" + if ( !$this->p_internal_link_target ( $b , $x , "}}" ) ) return false ; + $target = $x ; + $variables = array () ; + $vcount = 1 ; + while ( 1 ) + { + if ( $this->nextis ( $b , "}}" ) ) break ; + if ( !$this->nextis ( $b , "|" ) ) return false ; + $l1 = strlen ( $x ) ; + if ( !$this->p_internal_link_text ( $b , $x , false , "}}" ) ) return false ; + $v = substr ( $x , $l1 ) ; + $v = explode ( "=" , $v ) ; + if ( count ( $v ) < 2 ) $vk = $vcount ; + else $vk = trim ( array_shift ( $v ) ) ; + $vv = array_shift ( $v ) ; + $variables[$vk] = $vv ; + if ( !isset ( $variables[$vcount] ) ) $variables[$vcount] = $vv ; + $vcount++ ; + } + + $target = array_pop ( @explode ( ">" , $target , 2 ) ) ; + $target = array_shift ( @explode ( "<" , $target , 2 ) ) ; + if ( $this->auto_fill_templates == 'all' ) $replace_template = true ; + else if ( $this->auto_fill_templates == 'none' ) $replace_template = false ; + else { + $found = in_array ( ucfirst ( $target ) , $this->template_list ) ; + if ( $found AND $this->auto_fill_templates == 'these' ) $replace_template = true ; + else if ( !$found AND $this->auto_fill_templates == 'notthese' ) $replace_template = true ; + else $replace_template = false ; + } + + if ( substr ( $target , 0 , 1 ) == '#' ) { # Try template logic + $between = $this->process_template_logic ( $target , $variables ) ; + # Change source (!) + $w1 = substr ( $this->w , 0 , $a ) ; + $w2 = substr ( $this->w , $b ) ; + $this->w = $w1 . $between . $w2 ; + $this->wl = strlen ( $this->w ) ; + } else if ( $replace_template ) { # Do not generate <template> sections, but rather replace the template call with the template text + + # Get template text + $between = trim ( $content_provider->get_template_text ( $target ) ) ; + add_authors ( $content_provider->authors ) ; + + # Removing <noinclude> stuff + $between = preg_replace( '?<noinclude>.*</noinclude>?msU', '', $between); + $between = str_replace ( "<include>" , "" , $between ) ; + $between = str_replace ( "</include>" , "" , $between ) ; + $between = str_replace ( "<includeonly>" , "" , $between ) ; + $between = str_replace ( "</includeonly>" , "" , $between ) ; + + # Remove HTML comments + $between = preg_replace( '?<!--.*-->?msU', '', $between) ; + + # Replacing template variables. + # ATTENTION: Template variables within <nowiki> sections of templates will be replaced as well! + + if ( $a > 0 && substr ( $between , 0 , 2 ) == '{|' ) + $between = "\n" . $between ; + + $this->replace_template_variables ( $between , $variables ) ; + + # Change source (!) + $w1 = substr ( $this->w , 0 , $a ) ; + $w2 = substr ( $this->w , $b ) ; + $this->w = $w1 . $between . $w2 ; + $this->wl = strlen ( $this->w ) ; + } else { + $xml .= "<template>{$x}</template>" ; + $a = $b ; + } + return true ; + } + + function process_template_logic ( $title , $variables ) { + + # TODO : Process title and variables for sub-template-replacements + + if ( substr ( $title , 0 , 4 ) == "#if:" ) { + $title = trim ( substr ( $title , 4 ) ) ; + if ( $title == '' ) return array_pop ( $variables ) ; # ELSE + return array_shift ( $variables ) ; # THEN + } + + if ( substr ( $title , 0 , 8 ) == "#switch:" ) { + $title = trim ( array_pop ( explode ( ':' , $title , 2 ) ) ) ; + foreach ( $variables AS $v ) { + $v = explode ( '=' , $v , 2 ) ; + $key = trim ( array_shift ( $v ) ) ; + if ( $key != $title ) continue ; # Wrong key + return array_pop ( $v ) ; # Correct key, return value + } + } + + # BAD PARSER FUNCTION! Ignoring... + return $title ; + } + + function replace_template_variables ( &$text , &$variables ) { + for ( $a = 0 ; $a+3 < strlen ( $text ) ; $a++ ) { + if ( $text[$a] != '{' ) continue ; + while ( $this->p_template_replace_single_variable ( $text , $a , $variables ) ) ; + } + } + + function p_template_replace_single_variable ( &$text , $a , &$variables ) { + if ( substr ( $text , $a , 3 ) != '{{{' ) return false ; + $b = $a + 3 ; + + # Name + $start = $b ; + $count = 0 ; + while ( $b < strlen ( $text ) && ( $text[$b] != '|' || $count > 0 ) && ( substr ( $text , $b , 3 ) != '}}}' || $count > 0 ) ) { + if ( $this->p_template_replace_single_variable ( $text , $b , $variables ) ) continue ; + if ( $text[$b] == '{' ) $count++ ; + if ( $text[$b] == '}' ) $count-- ; + $b++ ; + } + if ( $b >= strlen ( $text ) ) return false ; + $name = trim ( substr ( $text , $start , $b - $start ) ) ; + + # Default value + $value = "" ; + if ( $text[$b] == '|' ) { + $b++ ; + $start = $b ; + $count = 0 ; + while ( $b < strlen ( $text ) && ( substr ( $text , $b , 3 ) != '}}}' || $count > 0 ) ) { + if ( $this->p_template_replace_single_variable ( $text , $b , $variables ) ) continue ; + if ( $text[$b] == '{' ) $count++ ; + if ( $text[$b] == '}' ) $count-- ; + $b++ ; + } + if ( $b >= strlen ( $text ) ) return false ; + $value = trim ( substr ( $text , $start , $b - $start ) ) ;#$start - $b - 1 ) ) ; + } + + // Replace + $b += 3 ; # }}} + if ( isset ( $variables[$name] ) ) { + $value = $variables[$name] ; + } + $text = substr ( $text , 0 , $a ) . $value . substr ( $text , $b ) ; + + return true ; + } + + function p_template_variable ( &$a , &$xml ) + { + $x = "" ; + $b = $a ; + if ( !$this->nextis ( $b , "{{{" ) ) return false ; + if ( !$this->p_internal_link_text ( $b , $x , false , "}}}" ) ) return false ; + if ( !$this->nextis ( $b , "}}}" ) ) return false ; + $xml .= "<templatevar>{$x}</templatevar>" ; + $a = $b ; + return true ; + } + + # Bold / italics + function p_bold ( &$a , &$xml , $recurse = "restofline" , $end = "" ) + { + return $this->p_intwined ( $a , $xml , "bold" , "'''" , $recurse , $end ) ; + } + + function p_italics ( &$a , &$xml , $recurse = "restofline" , $end = "" ) + { + return $this->p_intwined ( $a , $xml , "italics" , "''" , $recurse , $end ) ; + } + + function p_intwined ( &$a , &$xml , $tag , $markup , $recurse , $end ) + { + $b = $a ; + if ( !$this->nextis ( $b , $markup ) ) return false ; + $id = substr ( ucfirst ( $tag ) , 0 , 1 ) ; + $bi = $this->bold_italics ; + $open = false ; + if ( substr ( $this->bold_italics , -1 ) == $id ) + { + $x = "</{$tag}>" ; + $this->bold_italics = substr ( $this->bold_italics , 0 , -1 ) ; + } + else + { + $pos = strpos ( $this->bold_italics , $id ) ; + if ( false !== $pos ) return false ; # Can't close a tag that ain't open + $open = true ; + $x = "<{$tag}>" ; + $this->bold_italics .= $id ; + } + + if ( $end == "" ) + { + $res = $this->once ( $b , $x , $recurse ) ; + } + else + { + $r = "p_{$recurse}" ; + $res = $this->$r ( $b , $x , $end ) ; + } + + $this->bold_italics = $bi ; + if ( !$res ) + { + return false ; + } + $xml .= $x ; + $a = $b ; + return true ; + } + + function scanplaintext ( &$a , &$xml , $goodstop , $badstop ) + { + $b = $a ; + $x = "" ; + while ( $b < $this->wl ) + { + if ( $this->w[$b] == "{" && $this->once ( $b , $x , "template" ) ) continue ; + foreach ( $goodstop AS $s ) + if ( $this->nextis ( $b , $s , false ) ) break 2 ; + foreach ( $badstop AS $s ) + if ( $this->nextis ( $b , $s , false ) ) return false ; + $c = $this->w[$b] ; + $x .= htmlspecialchars ( $c ) ; + $b++ ; + } + if ( count ( $goodstop ) > 0 && $b >= $this->wl ) return false ; # Reached end; not good + $a = $b ; + $xml .= $x ; + return true ; + } + + # External link + function p_external_freelink ( &$a , &$xml , $mark = true ) + { + if ( $this->wl <= $a + 10 ) return false ; # Can't have an URL shorter than that + if ( $this->w[$a+5] != '/' && $this->w[$a+7] != '/' ) return false ; # Shortcut for protocols 3-6 chars length + $protocol = "" ; + $b = $a ; +# while ( $this->w[$b] == "{" && $this->once ( $b , $x , "template" ) ) $b = $a ; + foreach ( $this->protocols AS $p ) + { + if ( $this->nextis ( $b , $p . "://" ) ) + { + $protocol = $p ; + break ; + } + } + if ( $protocol == "" ) return false ; + $x = "{$protocol}://" ; + while ( $b < $this->wl ) + { + $c = $this->w[$b] ; + if ( $c == "{" && $this->once ( $b , $x , "template" ) ) continue ; + if ( $c == "\n" || $c == " " || $c == '|' ) break ; + if ( !$mark && $c == "]" ) break ; + $x .= htmlspecialchars ( $c ) ; + $b++ ; + } + if ( substr ( $x , -1 ) == "." || substr ( $x , -1 ) == "," ) + { + $x = substr ( $x , 0 , -1 ) ; + $b-- ; + } + $a = $b ; + $x = htmlspecialchars ( $x , ENT_QUOTES ) ; + if ( $mark ) $xml .= "<link type='external' href='$x'/>" ; + else $xml .= $x ; + return true ; + } + + function p_external_link ( &$a , &$xml , $mark = true ) + { + $b = $a ; + if ( !$this->nextis ( $b , "[" ) ) return false ; + $url = "" ; + $c = $b ; + $x = "" ; + while ( $c < $this->wl && $this->w[$c] == "{" && $this->once ( $c , $x , "template" ) ) $c = $b ; + if ( $c >= $this->wl ) return false ; + $x = "" ; + if ( !$this->p_external_freelink ( $b , $url , false ) ) return false ; + $this->skipblanks ( $b ) ; + if ( !$this->scanplaintext ( $b , $x , array ( "]" ) , array ( "\n" ) ) ) return false ; + $a = $b + 1 ; + $xml .= "<link type='external' href='{$url}'>{$x}</link>" ; + return true ; + } + + # Heading + function p_heading ( &$a , &$xml ) + { + if ( $a >= $this->wl || $this->w[$a] != '=' ) return false ; + $b = $a ; + $level = 0 ; + $h = "" ; + $x = "" ; + while ( $this->nextis ( $b , "=" ) ) + { + $level++ ; + $h .= "=" ; + } + $this->skipblanks ( $b ) ; + if ( !$this->once ( $b , $x , "restofline" ) ) return false ; + if ( $this->compensate_markup_errors ) $x = trim ( $x ) ; + else if ( $x != trim ( $x ) ) $xml .= "<error type='heading' reason='trailing blank'/>" ; + if ( substr ( $x , -$level ) != $h ) return false ; # No match + + $x = trim ( substr ( $x , 0 , -$level ) ) ; + $level -= 1 ; + $a = $b ; + $xml .= "<heading level='" . ($level+1) . "'>{$x}</heading>" ; + return true ; + } + + # Line + # Often used function for parsing the rest of a text line + function p_restofline ( &$a , &$xml , $closeit = array() ) + { + $b = $a ; + $x = "" ; + $override = false ; + while ( $b < $this->wl && !$override ) + { + $c = $this->w[$b] ; + if ( $c == "\n" ) { $b++ ; break ; } + foreach ( $closeit AS $z ) + if ( $this->nextis ( $b , $z , false ) ) break ; + if ( $c == "_" && $this->once ( $b , $x , "magic_variable" ) ) continue ; + if ( $c == "[" && $this->once ( $b , $x , "internal_link" ) ) continue ; + if ( $c == "[" && $this->once ( $b , $x , "external_link" ) ) continue ; + if ( $c == "{" && $this->once ( $b , $x , "template_variable" ) ) continue ; + if ( $c == "{" && $this->once ( $b , $x , "template" ) ) continue ; + if ( $c == "{" && $this->p_table ( $b , $x ) ) continue ; + if ( $c == "<" && $this->once ( $b , $x , "html" ) ) continue ; + if ( $c == "'" && $this->once ( $b , $x , "bold" ) ) { $override = true ; break ; } + if ( $c == "'" && $this->once ( $b , $x , "italics" ) ) { $override = true ; break ; } + if ( $b + 10 < $this->wl && + ( $this->w[$a+5] == '/' && $this->w[$a+7] == '/' ) && + $this->once ( $b , $x , "external_freelink" ) ) continue ; + + # Just an ordinary character + $x .= htmlspecialchars ( $c ) ; + $b++ ; + if ( $b >= $this->wl ) break ; + } + if ( !$override && $this->bold_italics != "" ) + { + return false ; + } + $xml .= $x ; + $a = $b ; + return true ; + } + + function p_line ( &$a , &$xml , $force ) + { + if ( $a >= $this->wl ) return false ; # Already at the end of the text + $c = $this->w[$a] ; + if ( !$force ) + { + if ( $c == '*' || $c == ':' || $c == '#' || $c == ';' || $c == ' ' || $c == "\n" ) return false ; # Not a suitable beginning + if ( $this->nextis ( $a , "{|" , false ) ) return false ; # Table + if ( count ( $this->tables ) > 0 && $this->nextis ( $a , "|" , false ) ) return false ; # Table + if ( count ( $this->tables ) > 0 && $this->nextis ( $a , "!" , false ) ) return false ; # Table + if ( $this->nextis ( $a , "=" , false ) ) return false ; # Heading + if ( $this->nextis ( $a , "----" , false ) ) return false ; # <hr> + } + $this->bold_italics = "" ; + return $this->once ( $a , $xml , "restofline" ) ; + } + + function p_blankline ( &$a , &$xml ) + { + if ( $this->nextis ( $a , "\n" ) ) return true ; + return false ; + } + + function p_block_lines ( &$a , &$xml , $force = false ) + { + $x = "" ; + $b = $a ; + if ( !$this->p_line ( $b , $x , $force ) ) return false ; + while ( $this->p_line ( $b , $x , false ) ) ; + while ( $this->p_blankline ( $b , $x ) ) ; # Skip coming blank lines + $xml .= "<paragraph>{$x}</paragraph>" ; + $a = $b ; + return true ; + } + + + + # PRE block + # Parses a line starting with ' ' + function p_preline ( &$a , &$xml ) + { + if ( $a >= $this->wl ) return false ; # Already at the end of the text + if ( $this->w[$a]!= ' ' ) return false ; # Not a preline + + $a++ ; + $this->bold_italics = "" ; + $x = "" ; + $ret = $this->once ( $a , $x , "restofline" ) ; + if ( $ret ) { + $xml .= "<preline>" . $x . "</preline>" ; + } + return $ret ; + } + + # Parses a block of lines each starting with ' ' + function p_block_pre ( &$a , &$xml ) + { + $x = "" ; + $b = $a ; + if ( !$this->once ( $b , $x , "preline" , true , true ) ) return false ; + $this->once ( $b , $x , "blankline" , false , true ) ; + $xml .= "<preblock>{$x}</preblock>" ; + $a = $b ; + return true ; + } + + # LIST block + # Returns a list tag depending on the wiki markup + function listtag ( $c , $open = true ) + { + if ( !$open ) return "</list>" ; + $r = "" ; + if ( $c == '#' ) $r = "numbered" ; + if ( $c == '*' ) $r = "bullet" ; + if ( $c == ':' ) $r = "ident" ; + if ( $c == ';' ) $r = "def" ; + if ( $r != "" ) $r = " type='{$r}'" ; + $r = "<list{$r}>" ; + return $r ; + } + + # Opens/closes list tags + function fixlist ( $last , $cur ) + { + $r = "" ; + $olast = $last ; + $ocur = $cur ; + $ocommon = "" ; + + # Remove matching parts + while ( $last != "" && $cur != "" && $last[0] == $cur[0] ) + { + $ocommon = $cur[0] ; + $cur = substr ( $cur , 1 ) ; + $last = substr ( $last , 1 ) ; + } + + # Close old tags + $fixitemtag = false ; + if ( $last != "" && $ocommon != "" ) $fixitemtag = true ; + while ( $last != "" ) + { + $r .= "</listitem>" . $this->listtag ( substr ( $last , -1 ) , false ) ; + $last = substr ( $last , 0 , -1 ) ; + } + if ( $fixitemtag ) $r .= "</listitem><listitem>" ; + + # Open new tags + while ( $cur != "" ) + { + $r .= $this->listtag ( $cur[0] ) . "<listitem>" ; + $cur = substr ( $cur , 1 ) ; + } + + return $r ; + } + + # Parses a single list line + function p_list_line ( &$a , &$xml , &$last ) + { + $cur = "" ; + do { + $lcur = $cur ; + while ( $this->nextis ( $a , "*" ) ) $cur .= "*" ; + while ( $this->nextis ( $a , "#" ) ) $cur .= "#" ; + while ( $this->nextis ( $a , ":" ) ) $cur .= ":" ; + while ( $this->nextis ( $a , ";" ) ) $cur .= ";" ; + } while ( $cur != $lcur ) ; + + $unchanged = false ; +# if ( substr ( $cur , 0 , strlen ( $last ) ) == $last ) $unchanged = true ; + if ( $last == $cur ) $unchanged = true ; + $xml .= $this->fixlist ( $last , $cur ) ; + + if ( $cur == "" ) return false ; # Not a list line + $last = $cur ; + $this->skipblanks ( $a ) ; + + if ( $unchanged ) $xml .= "</listitem><listitem>" ; + if ( $cur == ";" ) # Definition + { + $b = $a ; + while ( $b < $this->wl && $this->w[$b] != "\n" && $this->w[$b] != ':' ) $b++ ; + if ( $b >= $this->wl || $this->w[$b] == "\n" ) + { + $xml .= "<defkey>" ; + $this->p_restofline ( $a , $xml ) ; + $xml .= "</defkey>" ; + } + else + { + $xml .= "<defkey>" ; + $this->w[$b] = "\n" ; + $this->p_restofline ( $a , $xml ) ; + $xml .= "</defkey>" ; + $xml .= "<defval>" ; + $this->p_restofline ( $a , $xml ) ; + $xml .= "</defval>" ; + } + } + else $this->p_restofline ( $a , $xml ) ; + return true ; + } + + # Checks for a list block ( those nasty things starting with '*', '#', or the like... + function p_block_list ( &$a , &$xml ) + { + $last = "" ; + $found = false ; + while ( $this->p_list_line ( $a , $xml , $last ) ) $found = true ; + return $found ; + } + + # HTML + # This function detects a HTML tag, finds the matching close tag, + # parses everything in between, and returns everything as an extension. + # Returns false otherwise. + function p_html ( &$a , &$xml ) + { + if ( !$this->nextis ( $a , "<" , false ) ) return false ; + + $b = $a ; + $x = "" ; + $tag = "" ; + $closing = false ; + $selfclosing = false ; + + if ( !$this->p_html_tag ( $b , $x , $tag , $closing , $selfclosing ) ) return false ; + + if ( isset ( $this->directhtmltags[$tag] ) ) + { + $tag_open = "<" . $this->directhtmltags[$tag] ; + $tag_close = "</" . $this->directhtmltags[$tag] . ">" ; + } + else + { + $tag_open = "<extension extension_name='{$tag}'" ; + $tag_close = "</extension>" ; + } + + # Is this tag self-closing? + if ( $selfclosing ) + { + $a = $b ; + $xml .= $tag_open . $x . ">" . $tag_close ; + return true ; + } + + # Find the matching close tag + # TODO : The simple open/close counter should be replaced with a + # stack to allow for tolerating half-broken HTML, + # such as unclosed <li> tags + $begin = $b ; + $cnt = 1 ; + $tag2 = "" ; + while ( $cnt > 0 && $b < $this->wl ) + { + $x2 = "" ; + $last = $b ; + if ( !$this->p_html_tag ( $b , $x2 , $tag2 , $closing , $selfclosing ) ) + { + if ( $tag != "nowiki" && $this->w[$b] == '{' && $this->p_template ( $b , $x ) ) # Template, doesn't alter $b or $x + continue ; + $b++ ; + continue ; + } + if ( $tag != $tag2 ) continue ; + if ( $selfclosing ) continue ; + if ( $closing ) $cnt-- ; + else $cnt++ ; + } + + if ( $cnt > 0 ) return false ; # Tag was never closed + + # What happens in between? + $between = substr ( $this->w , $begin , $last - $begin ) ; + + if ( $tag != "pre" && $tag != "nowiki" && $tag != "math" ) + { + if ( $tag == 'gallery' ) { + $this->gallery2wiki ( $between ) ; + $tag_open = "" ; + $tag_close = "" ; + } + + # Parse the part in between the tags + $subparser = new wiki2xml ; + $between2 = $subparser->parse ( $between ) ; + + # Was the parsing correct? + if ( $between2 != $this->errormessage ) + $between = $this->strip_single_paragraph ( $between2 ) ; # No <paragraph> for inline HTML tags + else + $between = htmlspecialchars ( $between ) ; # Incorrect markup, use safe wiki source instead + } + else $between = htmlspecialchars ( $between ) ; # No wiki parsing in here + + $a = $b ; + if ( $tag_open != "" ) $xml .= $tag_open . $x . ">" ; + $xml .= $between ; + if ( $tag_close != "" ) $xml .= $tag_close ; + return true ; + } + + /** + * Converts the lines within a <gallery> to wiki tables + */ + function gallery2wiki ( &$text ) { + $lines = explode ( "\n" , trim ( $text ) ) ; + $text = "{| style='border-collapse: collapse; border: 1px solid grey;'\n" ; + $cnt = 0 ; + foreach ( $lines AS $line ) { + if ( $cnt >= 4 ) { + $cnt = 0 ; + $text .= "|--\n" ; + } + $a = explode ( "|" , $line , 2 ) ; + if ( count ( $a ) == 1 ) { # Generate caption from file name + $b = $a[0] ; + $b = explode ( ":" , $b , 2 ) ; + $b = array_pop ( $b ) ; + $b = explode ( "." , $b ) ; + array_pop ( $b ) ; + $a[] = implode ( "." , $b ) ; + } + $link = array_shift ( $a ) ; + $caption = array_pop ( $a ) ; + $text .= "|valign=top align=left|[[{$link}|thumb|center|]]<br/>{$caption}\n" ; + $cnt++ ; + } + $text .= "|}\n" ; + } + + function strip_single_paragraph ( $s ) + { + if ( substr_count ( $s , "paragraph>" ) == 2 && + substr ( $s , 0 , 11 ) == "<paragraph>" && + substr ( $s , -12 ) == "</paragraph>" ) + $s = substr ( $s , 11 , -12 ) ; + return $s ; + } + + # This function checks for and parses a HTML tag + # Only to be called from p_html, as it returns only a partial extension tag! + function p_html_tag ( &$a , &$xml , &$tag , &$closing , &$selfclosing ) + { + if ( $this->w[$a] != '<' ) return false ; + $b = $a + 1 ; + $this->skipblanks ( $b ) ; + $tag = "" ; + $attrs = array () ; + if ( !$this->scanplaintext ( $b , $tag , array ( " " , ">" ) , array ( "\n" ) ) ) return false ; + + $this->skipblanks ( $b ) ; + if ( $b >= $this->wl ) return false ; + + $tag = trim ( strtolower ( $tag ) ) ; + $closing = false ; + $selfclosing = false ; + + # Is closing tag? + if ( substr ( $tag , 0 , 1 ) == "/" ) + { + $tag = substr ( $tag , 1 ) ; + $closing = true ; + $this->skipblanks ( $b ) ; + if ( $b >= $this->wl ) return false ; + } + + if ( substr ( $tag , -1 ) == "/" ) + { + $tag = substr ( $tag , 0 , -1 ) ; + $selfclosing = true ; + } + + # Parsing attributes + $ob = $b ; + $q = "" ; + while ( $b < $this->wl && ( $q != "" || ( $this->w[$b] != '>' && $this->w[$b] != '/' ) ) ) { + if ( $this->w[$b] == '"' || $this->w[$b] == "'" ) { + if ( $q == "" ) $q = $this->w[$b] ; + else if ( $this->w[$b] == $q ) $q = "" ; + } + $b++ ; + } + if ( $b >= $this->wl ) return false ; + $attrs = $this->preparse_attributes ( substr ( $this->w , $ob , $b - $ob + 1 ) ) ; + + # Is self closing? + if ( $tag == 'br' ) $selfclosing = true ; # Always regard <br> as <br/> + if ( $this->w[$b] == '/' ) + { + $b++ ; + $this->skipblanks ( $b ) ; + $selfclosing = true ; + } + + $this->skipblanks ( $b ) ; + if ( $b >= $this->wl ) return false ; + if ( $this->w[$b] != '>' ) return false ; + + $a = $b + 1 ; + if ( count ( $attrs ) > 0 ) + { + $xml = " " . implode ( " " , $attrs ) ; + } + return true ; + } + + # This function replaces templates and separates HTML attributes. + # It is used for both HTML tags and wiki tables + function preparse_attributes ( $x ) + { + # Creating a temporary new parser to run the attribute list in + $np = new wiki2xml ; + $np->w = $x ; + $np->wl = strlen ( $x ) ; + + # Replacing templates, and '<' and '>' in parameters + $c = 0 ; + $q = "" ; + while ( $q != "" || ( $c < $np->wl && $np->w[$c] != '>' && $np->w[$c] != '/' ) ) + { + $y = $np->w[$c] ; + if ( $np->nextis ( $c , "{{" , false ) ) { + $xx = "" ; + if ( $np->p_template ( $c , $xx ) ) continue ; + else $c++ ; + } else if ( $y == "'" || $y == '"' ) { + if ( $q == "" ) $q = $y ; + else if ( $y == $q ) $q = "" ; + $c++ ; + } else if ( $q != "" && ( $y == '<' || $y == '>' ) ) { + $y = htmlentities ( $y ) ; + $np->w = substr ( $np->w , 0 , $c ) . $y . substr ( $np->w , $c + 1 ) ; + $np->wl += strlen ( $y ) - 1 ; + } else $c++ ; + if ( $c >= $np->wl ) return array () ; + } + + $attrs = array () ; + $c = 0 ; + + # Seeking attributes + while ( $np->w[$c] != '>' && $np->w[$c] != '/' ) + { + $attr = "" ; + if ( !$np->p_html_attr ( $c , $attr ) ) break ; + if ( $attr != "" ) { + $key = array_shift ( explode ( "=" , $attr , 2 ) ) ; + if ( !isset ( $attrs[$key] ) && substr ( $attr , -3 , 3 ) != '=""' ) { + $attrs[$key] = $attr ; + } + } + $np->skipblanks ( $c ) ; + if ( $c >= $np->wl ) return array () ; + } + if ( substr ( $np->w , $c ) != ">" AND substr ( $np->w , $c ) != "/" ) return array() ; + + return $attrs ; + } + + + # This function scans a single HTML tag attribute and returns it as <attr name='key'>value</attr> + function p_html_attr ( &$a , &$xml ) + { + $b = $a ; + $this->skipblanks ( $b ) ; + if ( $b >= $this->wl ) return false ; + $name = "" ; + if ( !$this->scanplaintext ( $b , $name , array ( " " , "=" , ">" , "/" ) , array ( "\n" ) ) ) return false ; + + $this->skipblanks ( $b ) ; + if ( $b >= $this->wl ) return false ; + $name = trim ( strtolower ( $name ) ) ; + + # Trying to catch illegal names; should be replaced with regexp + $n2 = "" ; + for ( $q = 0 ; $q < strlen ( $name ) ; $q++ ) { + if ( $name[$q] == '_' OR ( $name[$q] >= 'a' AND $name[$q] <= 'z' ) ) + $n2 .= $name[$q] ; + } + $name = trim ( $n2 ) ; + if ( $name == 'extension_name' ) return false ; # Not allowed, because used internally + if ( $name == '' ) return false ; + + # Determining value + $value = "" ; + if ( $this->w[$b] == "=" ) + { + $b++ ; + $this->skipblanks ( $b ) ; + if ( $b >= $this->wl ) return false ; + $q = "" ; + $is_q = false ; + if ( $this->w[$b] == '"' || $this->w[$b] == "'" ) + { + $q = $this->w[$b] ; + $b++ ; + if ( $b >= $this->wl ) return false ; + $is_q = true ; + } + while ( $b < $this->wl ) + { + $c = $this->w[$b] ; + if ( $c == $q ) + { + $b++ ; + if ( $is_q ) break ; + return false ; # Broken attribute value + } + if ( $this->nextis ( $b , "\\{$q}" ) ) # Ignore escaped quotes + { + $value .= "\\{$q}" ; + continue ; + } + if ( $c == "\n" ) return false ; # Line break before value end + if ( !$is_q && ( $c == ' ' || $c == '>' || $c == '/' ) ) break ; + $value .= htmlspecialchars ( $c ) ; + $b++ ; + } + } + if ( $name == "" ) return true ; + + $a = $b ; + if ( $q == "'" ) $q = "'" ; + else $q = '"' ; + $xml = "{$name}={$q}{$value}{$q}" ; + #$xml .= "<attr name='{$name}'>{$value}</attr>" ; + return true ; + } + + # Horizontal ruler (<hr> / ----) + function p_hr ( &$a , &$xml ) + { + if ( !$this->nextis ( $a , "----" ) ) return false ; + $this->skipblanks ( $a , "-" ) ; + $this->skipblanks ( $a ) ; + $xml .= "<hr/>" ; + return true ; + } + + # TABLE + # Scans the rest of the line as HTML attributes and returns the usual <attrs><attr> string + function scanattributes ( &$a ) + { + $x = "" ; + while ( $a < $this->wl ) + { + if ( $this->w[$a] == "\n" ) break ; + $x .= $this->w[$a] ; + $a++ ; + } + $x .= ">" ; + + $attrs = $this->preparse_attributes ( $x ) ; + + $ret = "" ; + if ( count ( $attrs ) > 0 ) + { + #$ret .= "<attrs>" ; + $ret .= " " . implode ( " " , $attrs ) ; + #$ret .= "</attrs>" ; + } + return $ret ; + } + + # Finds the first of the given items; does *not* alter $a + function scanahead ( $a , $matches ) + { + while ( $a < $this->wl ) + { + foreach ( $matches AS $x ) + { + if ( $this->nextis ( $a , $x , false ) ) + { + return $a ; + } + } + $a++ ; + } + return -1 ; # Not found + } + + + # The main table parsing function + function p_table ( &$a , &$xml ) + { + if ( $a >= $this->wl ) return false ; + $c = $this->w[$a] ; + if ( $c == "{" && $this->nextis ( $a , "{|" , false ) ) + return $this->p_table_open ( $a , $xml ) ; + +# print "p_table for " . htmlentities ( substr ( $this->w , $a ) ) . "<br/><br/>" ; flush () ; + + if ( count ( $this->tables ) == 0 ) return false ; # No tables open, nothing to do + + # Compatability for table cell lines starting with blanks; *evil MediaWiki parser!* + $b = $a ; + $this->skipblanks ( $b ) ; + if ( $b >= $this->wl ) return false ; + $c = $this->w[$b] ; + + if ( $c != "|" && $c != "!" ) return false ; # No possible table markup + + if ( $c == "|" && $this->nextis ( $b , "|}" , false ) ) return $this->p_table_close ( $b , $xml ) ; + + #if ( $this->nextis ( $a , "|" , false ) || $this->nextis ( $a , "!" , false ) ) + return $this->p_table_element ( $b , $xml , true ) ; + } + + function lasttable () + { + return $this->tables[count($this->tables)-1] ; + } + + # Returns the attributes for table cells + function tryfindparams ( &$a ) + { + $n = strspn ( $this->w , $this->allowed , $a ) ; # PHP 4.3.0 and above +# $n = strspn ( substr ( $this->w , $a ) , $this->allowed ) ; # PHP < 4.3.0 + if ( $n == 0 ) return "" ; # None found + + $b = $a + $n ; + if ( $b >= $this->wl ) return "" ; + if ( $this->w[$b] != "|" && $this->w[$b] != "!" ) return "" ; + if ( $this->nextis ( $b , "||" , false ) ) return "" ; # Reached a ||, so return blank string + if ( $this->nextis ( $b , "!!" , false ) ) return "" ; # Reached a ||, so return blank string + $this->w[$b] = "\n" ; + $ret = $this->scanattributes ( $a ) ; + $this->w[$b] = "|" ; + $a = $b + 1 ; + return $ret ; + } + + function p_table_element ( &$a , &$xml , $newline = false ) + { +# print "p_table_element for " . htmlentities ( substr ( $this->w , $a ) ) . "<br/><br/>" ; flush () ; + $b = $a ; + $this->skipblanks ( $b ) ; # Compatability for table cells starting with blanks; *evil MediaWiki parser!* + if ( $b >= $this->wl ) return false ; # End of the game + $x = "" ; + if ( $newline && $this->nextis ( $b , "|-" ) ) # Table row + { + $this->skipblanks ( $b , "-" ) ; + $this->skipblanks ( $b ) ; + + $attrs = $this->scanattributes ( $b ) ; + if ( $this->tables[count($this->tables)-1]->is_row_open ) $x .= "</tablerow>" ; + else $this->tables[count($this->tables)-1]->is_row_open = true ; + $this->tables[count($this->tables)-1]->had_row = true ; + $x .= "<tablerow{$attrs}>" ; + $y = "" ; + $this->p_restofcell ( $b , $y ) ; + } + else if ( $newline && $this->nextis ( $b , "|+" ) ) # Table caption + { + $this->skipblanks ( $b ) ; + $attrs = $this->tryfindparams ( $b ) ; + $this->skipblanks ( $b ) ; + if ( $this->tables[count($this->tables)-1]->is_row_open ) $x .= "</tablerow>" ; + $this->tables[count($this->tables)-1]->is_row_open = false ; + + $y = "" ; + if ( !$this->p_restofcell ( $b , $y ) ) return false ; + $x .= "<tablecaption{$attrs}>{$y}</tablecaption>" ; + } + else # TD or TH + { + $c = $this->w[$b] ; + $b++ ; + $tag = "error" ; + if ( $c == '|' ) $tag = "tablecell" ; + else if ( $c == '!' ) $tag = "tablehead" ; + $attrs = $this->tryfindparams ( $b ) ; + $this->skipblanks ( $b ) ; + if ( !$this->p_restofcell ( $b , $x ) ) return false ; + + if ( substr ( $x , 0 , 1 ) == "|" ) # Crude fix to compensate for MediaWiki "tolerant" parsing + $x = substr ( $x , 1 ) ; + $x = "<{$tag}{$attrs}>{$x}</{$tag}>" ; + $this->tables[count($this->tables)-1]->had_cell = true ; + if ( !$this->tables[count($this->tables)-1]->is_row_open ) + { + $this->tables[count($this->tables)-1]->is_row_open = true ; + $this->tables[count($this->tables)-1]->had_row = true ; + $x = "<tablerow>{$x}" ; + } + } + + $a = $b ; + $xml .= $x ; + return true ; + } + + # Finds the substring that composes the table cell, + # then runs a new parser on it + function p_restofcell ( &$a , &$xml ) + { + # Get substring for cell + $b = $a ; + $sameline = true ; + $x = "" ; + $itables = 0 ; + while ( $b < $this->wl ) + { + $c = $this->w[$b] ; + if ( $c == "<" && $this->once ( $b , $x , "html" ) ) continue ; # Up front to catch pre and nowiki + if ( $c == "\n" ) { $sameline = false ; } + if ( $c == "\n" && $this->nextis ( $b , "\n{|" ) ) { $itables++ ; continue ; } + if ( $c == "\n" && $itables > 0 && $this->nextis ( $b , "\n|}" ) ) { $itables-- ; continue ; } + + if ( ( $c == "\n" && $this->nextis ( $b , "\n|" , false ) ) OR + ( $c == "\n" && $this->nextis ( $b , "\n!" , false ) ) OR + ( $c == "\n" && $this->nextis ( $b , "\n |" , false ) ) OR # MediaWiki parser madness compensator + ( $c == "\n" && $this->nextis ( $b , "\n !" , false ) ) OR # MediaWiki parser madness compensator + ( $c == "|" && $sameline && $this->nextis ( $b , "||" , false ) ) OR + ( $c == "!" && $sameline && $this->nextis ( $b , "!!" , false ) ) ) + { + if ( $itables == 0 ) break ; + $b += 2 ; + } + + if ( $c == "[" && $this->once ( $b , $x , "internal_link" ) ) continue ; + if ( $c == "{" && $this->once ( $b , $x , "template_variable" ) ) continue ; + if ( $c == "{" && $this->once ( $b , $x , "template" ) ) continue ; + $b++ ; + } + +# if ( $itables > 0 ) return false ; + + # Parse cell substring + $s = substr ( $this->w , $a , $b - $a ) ; + $p = new wiki2xml ; + $x = $p->parse ( $s ) ; + if ( $x == $this->errormessage ) return false ; + + $a = $b + 1 ; + $xml .= $this->strip_single_paragraph ( $x ) ; + return true ; + } + + function p_table_close ( &$a , &$xml ) + { + if ( count ( $this->tables ) == 0 ) return false ; + $b = $a ; + if ( !$this->nextis ( $b , "|}" ) ) return false ; + if ( !$this->tables[count($this->tables)-1]->had_row ) return false ; # Table but no row was used + if ( !$this->tables[count($this->tables)-1]->had_cell ) return false ; # Table but no cell was used + $x = "" ; + if ( $this->tables[count($this->tables)-1]->is_row_open ) $x .= "</tablerow>" ; + unset ( $this->tables[count($this->tables)-1] ) ; + $x .= "</table>" ; + $xml .= $x ; + $a = $b ; + while ( $this->nextis ( $a , "\n" ) ) ; + return true ; + } + + function p_table_open ( &$a , &$xml ) + { + $b = $a ; + if ( !$this->nextis ( $b , "{|" ) ) return false ; + + $this->is_row_open = false ; + + # Add table to stack + $nt->is_row_open = false ; + $nt->had_row = false ; + $nt->had_cell = false ; + $this->tables[count($this->tables)] = $nt ; + + $x = "<table" ; + $x .= $this->scanattributes ( $b ) . ">" ; + while ( $this->nextis ( $b , "\n" ) ) ; + + while ( !$this->p_table_close ( $b , $x ) ) + { + if ( $b >= $this->wl ) + { + unset ( $this->tables[count($this->tables)-1] ) ; + return false ; + } + if ( $this->p_table_open ( $b , $x ) ) continue ; + if ( !$this->p_table_element ( $b , $x , true ) ) # No |} and no table element + { + unset ( $this->tables[count($this->tables)-1] ) ; + return false ; + } + } + $a = $b ; + $xml .= $x ; + return true ; + } + + #----------------------------------- + # Parse the article + function p_article ( &$a , &$xml ) + { + $x = "" ; + $b = $a ; + while ( $b < $this->wl ) + { + if ( $this->onceormore ( $b , $x , "heading" ) ) continue ; + if ( $this->onceormore ( $b , $x , "block_lines" ) ) continue ; + if ( $this->onceormore ( $b , $x , "block_pre" ) ) continue ; + if ( $this->onceormore ( $b , $x , "block_list" ) ) continue ; + if ( $this->onceormore ( $b , $x , "hr" ) ) continue ; + if ( $this->onceormore ( $b , $x , "table" ) ) continue ; + if ( $this->onceormore ( $b , $x , "blankline" ) ) continue ; + if ( $this->p_block_lines ( $b , $x , true ) ) continue ; + # The last resort! It should never come to this! + if ( !$this->compensate_markup_errors ) $xml .= "<error type='general' reason='no matching markup'/>" ; + $xml .= htmlspecialchars ( $this->w[$b] ) ; + $b++ ; + } + $a = $b ; + $xml .= $x ; + +# asort ( $this->profile ) ; +# $p = "" ; +# foreach ( $this->profile AS $k => $v ) $p .= "<p>{$k} : {$v}</p>" ; +# $xml = "<debug>{$this->cnt}{$p}</debug>" . $xml ; + return true ; + } + + # The only function to be called directly from outside the class + function parse ( &$wiki ) + { + $this->w = rtrim ( $wiki ) ; + + # Fix line endings + $cc = count_chars ( $wiki , 0 ) ; + if ( $cc[10] > 0 && $cc[13] == 0 ) + $this->w = str_replace ( "\r" , "\n" , $this->w ) ; + $this->w = str_replace ( "\r" , "" , $this->w ) ; + + # Remove HTML comments + $this->w = preg_replace( '?<!--.*-->?msU', '', $this->w); + + # Run the thing! +# $this->tables = array () ; + $this->wl = strlen ( $this->w ) ; + $xml = "" ; + $a = 0 ; + if ( !$this->p_article ( $a , $xml ) ) return $this->errormessage ; + + # XML cleanup + $ol = -1 ; + while ( $ol != strlen ( $xml ) ) { + $ol = strlen ( $xml ) ; + $xml = str_replace ( "<preline> " , "<preline><space/>" , $xml ) ; + $xml = str_replace ( "<space/> " , "<space/><space/>" , $xml ) ; + } + $ol = -1 ; + while ( $ol != strlen ( $xml ) ) { + $ol = strlen ( $xml ) ; + $xml = str_replace ( " " , " " , $xml ) ; + } + $ol = -1 ; + while ( $this->use_space_tag && $ol != strlen ( $xml ) ) { + $ol = strlen ( $xml ) ; + $xml = str_replace ( "> " , "><space/>" , $xml ) ; + $xml = str_replace ( " <" , "<space/><" , $xml ) ; + } + $xml = str_replace ( '<tablerow></tablerow>' , '' , $xml ) ; + + return $xml ; + } + + } + +?> Added: projects/wiki/extensions/wiki2xml/xhtml.xslt =================================================================== --- projects/wiki/extensions/wiki2xml/xhtml.xslt (rev 0) +++ projects/wiki/extensions/wiki2xml/xhtml.xslt 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,123 @@ +<?xml version="1.0" encoding="utf-8"?> +<!-- + XSLT for wiki2xml + + usage: /usr/bin/xsltproc xhtml.xslt yourfile.xml + + Given a wiki syntax article, use wiki2xml by Magnus Manke to convert it + as a XML document. Save the XML in a file (ex: yourfile.xml) then launch + xlstproc that will happylly apply this stylesheet to the xml document + and output some XHTML. + + + Author: + Ashar Voultoiz <hashar(a)altern.org + License: + http://www.gnu.org/copyleft/gpl.html GNU General Public Licence 2.0 or later + + Copyright © 2006 Ashar Voultoiz + +--> +<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"> +<xsl:output + method="html" indent="yes" + encoding="utf-8" + doctype-system="http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.... + doctype-public="-//W3C//DTD XHTML 1.0 Transitional//EN" +/> + +<xsl:template match="/"> + <xsl:apply-templates /> +</xsl:template> + +<xsl:template match="/articles"> + <xsl:apply-templates /> +</xsl:template> + +<xsl:template match="/articles/article"> +<html> +<head> + <title><xsl:value-of select="@title" /></title> + <style type="text/css" media="screen,projection">@import "http://en.wikipedia.org/w/skins-1.5/monobook/main.css";</style> +</head> +<body class="ns-0 ltr"> +<div id="globalWrapper"> + <div id="column-content"> + <div id="content"> + <h1 class="firstHeading"><xsl:value-of select="@title" /></h1> + <div id="bodyContent"> + <h3 id="siteSub">Generated with xhtml.xslt</h3> + <div id="contentSub"></div> + </div> + <xsl:apply-templates /> + </div> + </div> +</div> +</body> +</html> +</xsl:template> + +<xsl:template match="paragraph"> + <p><xsl:apply-templates /></p> +</xsl:template> + +<xsl:template match="list"> + <xsl:choose> + <xsl:when test="@type = numbered"> + <ol><xsl:apply-templates/></ol> + </xsl:when> + <xsl:when test="@type = bullet"> + <ul><xsl:apply-templates/></ul> + </xsl:when> + <xsl:otherwise> + <ul><xsl:apply-templates/></ul> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<xsl:template match="listitem"> +<li><xsl:apply-templates /></li> +</xsl:template> + +<xsl:template match="space"> +<xsl:text disable-output-escaping="yes">&amp;nbsp;</xsl:text><xsl:apply-templates /> +</xsl:template> + +<xsl:template match="italics"> +<i><xsl:apply-templates /></i> +</xsl:template> + +<xsl:template match="link"> + <xsl:choose> + <xsl:when test="@type='external'" > + <xsl:text disable-output-escaping="yes">&lt;a href="</xsl:text><xsl:value-of select="@href" /> + <xsl:text disable-output-escaping="yes">"&gt;</xsl:text> + <xsl:value-of select="."/> + <xsl:text disable-output-escaping="yes">&lt;/a&gt;</xsl:text> + </xsl:when> + <xsl:otherwise> + <xsl:text disable-output-escaping="yes">&lt;a href="http://yourhost/wiki/</xsl:text> + <xsl:apply-templates select="target"/> + <xsl:text disable-output-escaping="yes">"&gt;</xsl:text> + <xsl:choose> + <xsl:when test="child::part"> + <xsl:apply-templates select="part"/> + </xsl:when> + <xsl:otherwise> + <xsl:apply-templates select="target"/> + </xsl:otherwise> + </xsl:choose> + <xsl:text disable-output-escaping="yes">&lt;/a&gt;</xsl:text> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<xsl:template match="target"> +<xsl:apply-templates/> +</xsl:template> + +<xsl:template match="part"> +<xsl:apply-templates/> +</xsl:template> + +</xsl:stylesheet> Added: projects/wiki/extensions/wiki2xml/xml2docbook_xml.php =================================================================== --- projects/wiki/extensions/wiki2xml/xml2docbook_xml.php (rev 0) +++ projects/wiki/extensions/wiki2xml/xml2docbook_xml.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,456 @@ +<?php + +/** + * This file contains the /element/ class needed by xml2tree.php + * to create a tree which is then converted into DocBook XML + */ + +class element { + var $name = ''; + var $attrs = array (); + var $children = array (); + + # Temporary variables for link tags + var $link_target = "" ; + var $link_trail = "" ; + var $link_parts = array () ; + + # Variables only used by $tree root + var $list = array () ; + var $opentags = array () ; + var $sections = array () ; + + /** + * Parse the children ... why won't anybody think of the children? + */ + function sub_parse(& $tree) { + $ret = '' ; + $temp = "" ; + foreach ($this->children as $key => $child) { + if (is_string($child)) { + $temp .= $child ; + } elseif ($child->name != 'ATTRS') { + $ret .= $this->add_temp_text ( $temp ) ; + $sub = $child->parse ( $tree , "" , $this ) ; + if ( $this->name == 'LINK' ) { + if ( $child->name == 'TARGET' ) $this->link_target = $sub ; + else if ( $child->name == 'PART' ) $this->link_parts[] = $sub ; + else if ( $child->name == 'TRAIL' ) $this->link_trail = $sub ; + } + $ret .= $sub ; + } + } + return $ret . $this->add_temp_text ( $temp ) ; + } + + function fix_text ( $s ) { + $s = html_entity_decode ( $s ) ; + filter_named_entities ( $s ) ; + $s = str_replace ( "&" , "&amp;" , $s ) ; + $s = str_replace ( "<" , "&lt;" , $s ) ; + $s = str_replace ( ">" , "&gt;" , $s ) ; + return utf8_decode ( $s ) ; + } + + function add_temp_text ( &$temp ) { + $s = $temp ; + $temp = "" ; + return $this->fix_text ( $s ) ; + } + + function add_new ( $tag , &$tree ) { + return $this->ensure_new ( $tag , $tree , "<{$tag}>\n" ) ; + } + + function ensure_new ( $tag , &$tree , $opttag = "" ) { + if ( $opttag == "" ) { # Catching special case (currently, <section>) + foreach ( $tree->opentags AS $o ) { + if ( $o == $tag ) return "" ; # Already open + } + } + array_push ( $tree->opentags , $tag ) ; + if ( $opttag == "" ) return "<{$tag}>\n" ; + else return $opttag ; + } + + function close_last ( $tag , &$tree , $all = false ) { + $found = false ; + foreach ( $tree->opentags AS $o ) { + if ( $o == $tag ) $found = true ; + } + if ( !$found ) return "" ; # Already closed + $ret = "\n" ; + while ( count ( $tree->opentags ) > 0 ) { + $o = array_pop ( $tree->opentags ) ; + $ret .= "</{$o}>\n" ; + if ( $o == $tag ) { + if ( $all ) return $ret . $this->close_last ( $tag , $tree , true ) ; + else return $ret ; + } + } + } + + function handle_extensions ( &$tree ) { + global $content_provider ; + $sub = "" ; + $name = strtolower ( $this->attrs['EXTENSION_NAME'] ) ; + $ot = $tree->opentags ; + $tree->opentags = array () ; + if ( $name == 'ref' ) + $sub .= $this->ensure_new ( 'para' , $tree ) ; + $sub .= $this->sub_parse ( $tree ) ; + while ( count ( $tree->opentags ) > 0 ) + $sub .= "</" . array_pop ( $tree->opentags ) . ">\n" ; + $tree->opentags = $ot ; + if ( $name == 'ref' ) { + $ret = '<footnote>' . $sub . '</footnote>' ; + } else { + $ret = $sub ; + } + return $ret ; + } + + function internal_id ( $title ) { + #return urlencode ( $title ) ; + $ret = "" ; + for ( $a = 0 ; $a < strlen ( $title ) ; $a++ ) { + if ( ( $title[$a] >= 'A' && $title[$a] <= 'Z' ) || + ( $title[$a] >= 'a' && $title[$a] <= 'z' ) || + ( $title[$a] >= '0' && $title[$a] <= '9' ) ) + $ret .= $title[$a] ; + else $ret .= "_" ; + } + return $ret ; + } + + function handle_link ( &$tree ) { + global $content_provider ; + $ot = $tree->opentags ; + $sub = $this->sub_parse ( $tree ) ; + $tree->opentags = $ot ; + $link = "" ; + if ( isset ( $this->attrs['TYPE'] ) AND strtolower ( $this->attrs['TYPE'] ) == 'external' ) { # External link + $href = htmlentities ( $this->attrs['HREF'] ) ; + if ( trim ( $sub ) == "" ) { + $sub = $href ; + $sub = explode ( '://' , $sub , 2 ) ; + $sub = explode ( '/' , array_pop ( $sub ) , 2 ) ; + $sub = array_shift ( $sub ) ; + } + $sub = $this->fix_text ( $sub ) ; + $link = "<ulink url=\"{$href}\"><citetitle>{$sub}</citetitle></ulink>" ; + } else { # Internal link + if ( count ( $this->link_parts ) > 0 ) { + $link = array_pop ( $this->link_parts ) ; + array_push ( $this->link_parts , $link ) ; # Compensating array_pop + } + $link_text = $link ; + if ( $link == "" ) $link = $this->link_target ; + $link .= $this->link_trail ; + + $ns = $content_provider->get_namespace_id ( $this->link_target ) ; + + + if ( $ns == 6 ) { # Image + $nstext = explode ( ":" , $this->link_target , 2 ) ; + $target = array_pop ( $nstext ) ; + $nstext = array_shift ( $nstext ) ; + + $text = array_pop ( $this->link_parts ) ; + $is_thumb = false ; + $align = '' ; + $width = '' ; + foreach ( $this->link_parts AS $s ) { + $s = trim ( $s ) ; + if ( $s == 'thumb' ) { + $is_thumb = true ; + if ( $align == '' ) $align = 'right' ; + if ( $width == '' ) $width = '200px' ; + } + } + + $href = $content_provider->get_image_url ( $target ) ; + + $link = "<mediaobject>\n<imageobject>\n<imagedata" ; + $link .= " fileref=\"{$href}\"" ; +# if ( $align != '' ) $link .= " align='{$align}'" ; # Deactivated until DocBook supports floating images; meanwhile: + if ( $align == 'center' ) $link .= " align='{$align}'" ; + if ( $width != '' ) $link .= " width='$width' scalefit='1'" ; # depth='$width' + $link .= "/>\n</imageobject>\n" ; + $link .= "<textobject>\n" ; + $link .= "<phrase>{$text}</phrase>\n" ; + $link .= "</textobject>\n" ; + if ( $is_thumb ) { + $link .= "<caption>\n" ; + if ( substr ( $text , 0 , 5 ) == '<para' ) $link .= $text ; # Para-noia! + else $link .= "<para>{$text}</para>\n" ; + $link .= "</caption>\n" ; + } + $link .= "</mediaobject>\n" ; + } else if ( $ns == -9 ) { # Interlanguage link + $sub = $this->link_target ; + $nstext = explode ( ":" , $sub , 2 ) ; + $name = array_pop ( $nstext ) ; + $nstext = array_shift ( $nstext ) ; + + $href = "http://{$nstext}.wikipedia.org/wiki/" . htmlentities ( $name ) ; + $link = "<ulink url=\"{$href}\"><citetitle>{$sub}</citetitle></ulink>" ; + } else if ( $ns == -8 ) { # Category link + if ( $link_text == "!" || $link_text == '*' ) $link = "" ; + else $link = " ({$link})" ; + $link = "" . $this->link_target . $link . "" ; + } else { + if ( $content_provider->is_an_article ( $this->link_target ) ) { + $lt = $this->internal_id ( trim ( $this->link_target ) ) ; + $lt = str_replace ( "+" , "_" , $lt ) ; + $link = "<link linkend='{$lt}'>{$link}</link>" ; + } else { + #$link = "<link linkend='{$lt}'>{$link}</link>" ; + } + } + } + return $link ; + } + + function make_tgroup ( &$tree ) { + $num_rows = 0 ; + $max_num_cols = 0 ; + $caption = "" ; + foreach ($this->children AS $key1 => $row) { + if (is_string($row)) continue ; + elseif ($row->name == 'TABLECAPTION') { + $caption .= $row->parse ( $tree , "DOCAPTION" , $this ) ; + continue ; + } elseif ($row->name != 'TABLEROW') continue ; + $num_rows++ ; + $num_cols = 0 ; + foreach ( $row->children AS $key2 => $col ) { + if (is_string($col)) continue ; + if ($col->name != 'TABLECELL' && $col->name != 'TABLEHEAD') continue ; + if ( isset ( $col->attrs['COLSPAN'] ) ) $num_cols += $col->attrs['COLSPAN'] ; + else $num_cols++ ; + } + if ( $num_cols > $max_num_cols ) + $max_num_cols = $num_cols ; + } + return "<title>{$caption}</title><tgroup cols='{$max_num_cols}'>" ; + } + + function top_tag ( &$tree ) { + if ( count ( $tree->opentags ) == 0 ) return "" ; + $x = array_pop ( $tree->opentags ) ; + array_push ( $tree->opentags , $x ) ; + return $x ; + } + + function convert_xhtml_tags ( &$oldtag , &$tree , &$ret ) { + if ( substr ( $oldtag , 0 , 6 ) != 'XHTML:' ) + return false ; + + $tag = substr ( $oldtag , 6 ) ; + if ( $tag == 'UL' || $tag == 'OL' ) { + $ot = $tree->opentags ; + $r = "" ; + $found = false ; + while ( count ( $ot ) > 0 ) { + $x = array_pop ( $ot ) ; + $r .= "</{$x}>\n" ; + $found = true ; + if ( $x == 'para' ) break ; +# if ( $x == 'listitem' ) break ; + $found = false ; + } + if ( !$found ) return false ; + $tree->opentags = $ot ; + if ( $tag == 'UL' ) $this->attrs['TYPE'] = "bullet" ; + if ( $tag == 'OL' ) $this->attrs['TYPE'] = "numbered" ; + $oldtag = 'LIST' ; + $ret .= $r ; + return true ; + } else if ( $tag == 'LI' ) { +# $tt = $this->top_tag ( $tree ) ; +# print $tt . "<br/>" ; +# if ( $tt != 'itemizedlist' && $tt != 'orderedlist' ) return false ; + $oldtag = 'LISTITEM' ; + } + + return false ; # No match + } + + /* + * Parse the tag + */ + function parse ( &$tree , $param = "" , $root = "" ) { + global $content_provider ; + $ret = ''; + $tag = $this->name ; + $close_tag = "" ; + + # Pre-fixing XHTML to wiki tags + $xhtml_conversion = $this->convert_xhtml_tags ( $tag , $tree , $ret ) ; + + if ( $tag == 'SPACE' ) { + return ' ' ; # Speedup + } else if ( $tag == 'ARTICLES' ) { + # dummy, to prevent default action to be called + } else if ( $tag == 'AUTHORS' ) { + # dummy, to prevent default action to be called + } else if ( $tag == 'AUTHOR' ) { + add_author ( $this->sub_parse ( $tree ) ) ; + return "" ; + } else if ( $tag == 'ARTICLE' ) { + $title = isset ( $this->attrs["TITLE"] ) ? $this->attrs["TITLE"] : "Untiteled" ; + $id = $this->internal_id ( $title ) ; + $ret .= "<article id='{$id}'>\n"; + $ret .= "<title>" . urldecode ( $title ) . "</title>\n" ; + } else if ( $tag == 'LINK' ) { + return $this->handle_link ( $tree ) ; # Shortcut + } else if ( $tag == 'EXTENSION' ) { + return $this->handle_extensions ( $tree ) ; # Shortcut + } else if ( $tag == 'HEADING' ) { + $level = count ( $tree->sections ) ; + $wanted = $this->attrs["LEVEL"] ; + $ret .= $this->close_last ( "para" , $tree ) ; + while ( $level >= $wanted ) { + $x = array_pop ( $tree->sections ) ; + if ( $x == 1 ) { + $ret .= $this->close_last ( "section" , $tree ) ; + } + $level-- ; + } + while ( $level < $wanted ) { + $level++ ; + if ( $level < $wanted ) { + array_push ( $tree->sections , 0 ) ; + } else { + $ret .= $this->ensure_new ( "section" , $tree , "<section>" ) ; + array_push ( $tree->sections , 1 ) ; + } + } + $ret .= "<title>" ; + } else if ( $tag == 'PARAGRAPH' || $tag == 'XHTML:P' ) { # Paragraph + $ret .= $this->close_last ( "para" , $tree ) ; + $ret .= $this->ensure_new ( "para" , $tree ) ; + } else if ( $tag == 'LIST' ) { # List + $ret .= $this->close_last ( "para" , $tree ) ; + $list_type = strtolower ( $this->attrs['TYPE'] ) ; + if ( $list_type == 'bullet' || $list_type == 'ident' || $list_type == 'def' ) $ret .= '<itemizedlist mark="opencircle">' ; + else if ( $list_type == 'numbered' ) $ret .= '<orderedlist numeration="arabic">' ; + } else if ( $tag == 'LISTITEM' ) { # List item + $ret .= $this->close_last ( "para" , $tree ) ; + $ret .= "<listitem>\n" ; + $ret .= $this->ensure_new ( "para" , $tree ) ; + + + } else if ( $tag == 'TABLE' ) { # Table + $ret .= $this->add_new ( "table" , $tree ) ; +# $ret .= "<title></title>" ; + $ret .= $this->make_tgroup ( $tree ) ; + $ret .= "<tbody>" ; + } else if ( $tag == 'TABLEROW' ) { # Tablerow + $retl_before = strlen ( $ret ) ; + $ret .= $this->add_new ( "row" , $tree ) ; + $retl_after = strlen ( trim ( $ret ) ) ; + } else if ( $tag == 'TABLEHEAD' ) { # Tablehead + $ret .= $this->add_new ( "entry" , $tree ) ; + } else if ( $tag == 'TABLECELL' ) { # Tablecell + $old_ret = $ret ; + $ret .= $this->add_new ( "entry" , $tree ) ; + } else if ( $tag == 'TABLECAPTION' ) { # Tablecaption + if ( $param != "DOCAPTION" ) return "" ; +# $ret .= $this->add_new ( "title" , $tree ) ; + + + } else if ( $tag == 'BOLD' || $tag == 'XHTML:STRONG' || $tag == 'XHTML:B' ) { # <b> or ''' + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= '<emphasis role="bold">' ; + $close_tag = "emphasis" ; + } else if ( $tag == 'ITALICS' || $tag == 'XHTML:EM' || $tag == 'XHTML:I' ) { # <i> or '' + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= '<emphasis>' ; + $close_tag = "emphasis" ; + } else if ( $tag == 'XHTML:TT' ) { # <tt> + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= '<literal>' ; + $close_tag = "literal" ; + } else if ( $tag == 'XHTML:SUB' ) { # <sub> + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= '<subscript>' ; + $close_tag = "subscript" ; + } else if ( $tag == 'XHTML:SUP' ) { # <sup> + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= '<superscript>' ; + $close_tag = "superscript" ; + } else if ( $tag == 'XHTML:SUP' ) { # <sup> + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= '<superscript>' ; + $close_tag = "superscript" ; + } else if ( $tag == 'PRELINE' OR $tag == 'XHTML:PRE' ) { # <pre> + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= '<programlisting>' ; + $close_tag = "programlisting" ; + } else if ( $tag == 'DEFVAL' ) { + $ret .= $this->ensure_new ( "para" , $tree ) ; + $ret .= " : " ; + } else { # Default : normal text + $ret .= $this->ensure_new ( "para" , $tree ) ; + } + + + + # Get the sub-items + $length_between = strlen ( $ret ) ; + if ( $tag != 'MAGIC_VARIABLE' && $tag != 'TEMPLATE' ) { + $ret .= $this->sub_parse ( $tree ) ; + } + $length_between = strlen ( $ret ) - $length_between ; + + + + # Close tags + if ( $tag == 'LIST' ) { + $ret .= $this->close_last ( "para" , $tree ) ; + if ( $list_type == 'bullet' || $list_type == 'ident' || $list_type == 'def' ) $ret .= "</itemizedlist>\n" ; + else if ( $list_type == 'numbered' ) $ret .= "</orderedlist>\n" ; + if ( $xhtml_conversion ) + $ret .= $this->ensure_new ( "para" , $tree ) ; + } else if ( $tag == 'LISTITEM' ) { + $ret .= $this->close_last ( "para" , $tree ) ; + $ret .= "</listitem>\n" ; + } else if ( $close_tag != "" ) { + $ret .= "</{$close_tag}>" ; + } else if ( $tag == 'HEADING' ) { + $ret .= "</title>\n" ; + + + } else if ( $tag == 'TABLE' ) { # Table + $ret .= "</tbody>" ; + $ret .= "</tgroup>" ; + $ret .= $this->close_last ( "table" , $tree ) ; + } else if ( $tag == 'TABLEROW' ) { # Tablerow + if ( strlen ( trim ( $ret ) ) == $retl_after ) { + $ret = substr ( $ret , 0 , $retl_before ) ; + $this->close_last ( "row" , $tree ) ; + } else $ret .= $this->close_last ( "row" , $tree ) ; + } else if ( $tag == 'TABLEHEAD' ) { # Tablehead !!!! + $ret .= $this->close_last ( "entry" , $tree ) ; + } else if ( $tag == 'TABLECELL' ) { # Tablecell + $ret .= $this->close_last ( "entry" , $tree ) ; +# if ( $length_between == 0 ) $ret = $old_ret ; + } else if ( $tag == 'TABLECAPTION' ) { # Tablecaption +# $ret .= $this->close_last ( "title" , $tree ) ; + + + } else if ( $tag == 'ARTICLE' ) { + $ret .= $this->close_last ( "section" , $tree , true ) ; + $ret .= $this->close_last ( "para" , $tree ) ; + $ret .= "</article>"; + } + + return $ret; + } +} + +require_once ( "xml2tree.php" ) ; # Uses the "element" class defined above + +?> Added: projects/wiki/extensions/wiki2xml/xml2odt.php =================================================================== --- projects/wiki/extensions/wiki2xml/xml2odt.php (rev 0) +++ projects/wiki/extensions/wiki2xml/xml2odt.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,667 @@ +<?php + +class TextStyle { + var $name = "" ; + var $bold = false ; + var $italics = false ; + var $underline = false ; + var $count = 0 ; +} + +class XML2ODT { + var $tags ; + var $textstyle_current ; + var $textstyles = array () ; + var $listcode = "" ; + var $list_is_open = false ; + var $list_list = array () ; + var $list_item_name = array () ; + var $image_counter = 0 ; + var $image_frames = array () ; + var $table_counter = 0 ; + var $open_tables = array () ; + var $table_styles = array () ; + var $col_styles = array () ; + var $cell_styles = array () ; + var $col_counter = array () ; + var $row_counter = array () ; + var $footnote_counter = 0 ; + var $article_counter = 0 ; + var $footnote_index = array () ; + var $footnote_text = array () ; + + function XML2ODT () { + $this->textstyle_current = new TextStyle ; + $this->textstyle_current->name = "T0" ; + $this->textstyles['T0'] = $this->textstyle_current ; + $this->tags = array () ; + } + + function get_url ( $title ) { + global $xmlg ; + $url = "http://" . $xmlg["site_base_url"] . "/index.php?title=" . urlencode ( $title ) ; + return $url ; + } + + function get_footnote_id ( $name , &$text ) { + $name = trim ( strtolower ( $name ) ) ; + if ( $name != "" && isset ( $this->footnote_index[$name] ) ) { + $this->footnote_counter++ ; + if ( trim ( $text ) == "" ) $text = $this->footnote_text[$name] ; + return $this->footnote_counter ; + } else { + $this->footnote_counter++ ; + if ( $name != "" ) { + $this->footnote_index[$name] = $this->footnote_counter ; + $this->footnote_text[$name] = $text ; + } + return $this->footnote_counter ; + } + } + + function get_image_frames () { + $ret = "" ; + foreach ( $this->image_frames AS $f ) { + $name = $f->name ; + $align = $f->align ; + $ret .= '<style:style style:name="' . $name . '" style:family="graphic" style:parent-style-name="Graphics">' . + '<style:graphic-properties ' . + ' fo:margin-left="' . $f->left . + '" fo:margin-right="' . $f->right . + '" fo:margin-top="' . $f->top . + '" fo:margin-bottom="' . $f->bottom . + '" style:run-through="foreground" style:wrap="parallel" style:number-wrapped-paragraphs="no-limit" ' . + 'style:wrap-contour="false" style:vertical-pos="top" style:vertical-rel="paragraph" style:horizontal-pos="' . + $align . '" style:horizontal-rel="paragraph" ' . + 'style:mirror="none" fo:clip="rect(0cm 0cm 0cm 0cm)" draw:luminance="0%" draw:contrast="0%" draw:red="0%" draw:green="0%" draw:blue="0%" ' . + 'draw:gamma="100%" draw:color-inversion="false" draw:image-opacity="100%" draw:color-mode="standard"/></style:style>' ; + } + return $ret ; + } + + function get_image_frame ( $align , $margin = false ) { + $i = "fr" . $this->image_counter ; + $o->name = $i ; + $o->align = $align ; + $o->left = $margin && $align == 'right' ? '0.1cm' : '0cm' ; + $o->right = $margin && $align == 'left' ? '0.1cm' : '0cm' ; + $o->top = '0cm' ; + $o->bottom = $margin ? '0.1cm' : '0cm' ; + $this->image_frames[$i] = $o ; + return $i ; + } + + function get_table_style ( &$tag ) { + $this->table_counter++ ; + $ret = "Table" . $this->table_counter ; + $this->open_tables[] = $ret ; + $o->name = $ret ; + $o->cols = 0 ; + $this->table_styles[$ret] = $o ; + $this->col_counter[$ret] = 0 ; + $this->row_counter[$ret] = 0 ; + return $ret ; + } + + function get_top_table_name () { + $x = array_pop ( $this->open_tables ) ; + $this->open_tables[] = $x ; + return $x ; + } + + function get_column_style () { + $t = $this->get_top_table_name () ; + $cn = $t . "." . chr ( 65 + $this->col_counter[$t] ) ; + $cc = $cn . $this->row_counter[$t] ; + $this->col_counter[$t]++ ; + if ( !isset ( $this->col_styles[$cn] ) ) { + $this->table_styles[$t]->cols = $this->col_counter[$t] ; + $o->name = $cn ; + $this->col_styles[$cn] = $o ; + } + return $cc ; + } + + function reset_column () { + $t = $this->get_top_table_name () ; + $this->col_counter[$t] = 0 ; + $this->row_counter[$t]++ ; + } + + function get_table_styles () { + $ret = "" ; + + # Tables + foreach ( $this->table_styles AS $ts ) { + $ret .= '<style:style style:name="' . $ts->name . '" style:family="table">' . + '<style:table-properties style:width="auto" table:align="margins"/>' . + '</style:style>' ; + } + + # Columns + foreach ( $this->col_styles AS $cs ) { + $ret .= '<style:style style:name="' . $cs->name . '" style:family="table-column">' . + '<style:table-column-properties style:column-width="auto" style:rel-column-width="1*"/>' . + '</style:style>' ; + } + + return $ret ; + } + + function ensure_list_open () { + if ( $this->list_is_open ) return "" ; + $this->list_is_open = true ; + if ( substr ( $this->listcode , -1 ) == '#' ) $o->type = 'numbered' ; + else $o->type = 'bullet' ; + $o->depth = strlen ( $this->listcode ) ; + $o->number = count ( $this->list_list ) + 1 ; + $this->list_list[] = $o ; + while ( count ( $this->list_item_name ) <= $o->depth ) $this->list_item_name[] = "" ; + $this->list_item_name[$o->depth] = 'PL' . $o->number ; + return '<text:list text:style-name="List_20_' . $o->number . '">' ; + } + + function ensure_list_closed () { + if ( !$this->list_is_open ) return "" ; + $this->list_is_open = false ; + $ret = "" ; + $ot = $this->tags ; + do { + $x = array_pop ( $this->tags ) ; + $ret .= "</{$x}>" ; + } while ( $x != "text:list-item" && count ( $this->tags ) > 0 ) ; + if ( $x != "text:list-item" ) { + $ret = "" ; + $this->tags = $ot ; + } + $ret .= "</text:list>" ; + return $ret ; + } + + function get_text_style ( $find ) { + $found = "" ; + foreach ( $this->textstyles AS $k => $ts ) { + if ( $ts->bold != $find->bold ) continue ; + if ( $ts->italics != $find->italics ) continue ; + if ( $ts->underline != $find->underline ) continue ; + $this->textstyles[$k]->count++ ; + return $ts ; + } + + # Create new style + $found = "T" . count ( $this->textstyles ) ; + $find->name = $found ; + $find->count = 1 ; + $this->textstyles[$found] = $find ; + return $find ; + } + + function get_styles_xml () { + $ret = '<office:automatic-styles>' ; + + # Default styles + $ret .= '<style:style style:name="PHR" style:family="paragraph" style:parent-style-name="Standard">' . + '<style:paragraph-properties fo:padding="0.074cm" fo:border-left="none" fo:border-right="none" fo:border-top="none" fo:border-bottom="0.002cm solid #000000" style:join-border="false"/>' . + '</style:style>' . + '<style:style style:name="PAGEBREAK" style:family="paragraph" style:parent-style-name="Standard">' . + '<style:paragraph-properties fo:break-before="page"/>' . + '</style:style>' ; + + # Text styles + foreach ( $this->textstyles AS $ts ) { + if ( $ts->count == 0 ) { + $ret .= '<style:style style:name="' . $ts->name . '" style:family="paragraph">' ; + $ret .= '<style:paragraph-properties fo:text-align="justify" style:justify-single-word="false"/>' ; + } else { + $ret .= '<style:style style:name="' . $ts->name . '" style:family="text">' ; + $ret .= '<style:text-properties' ; + if ( $ts->italics ) $ret .= ' fo:font-style="italic" style:font-style-asian="italic" style:font-style-complex="italic"' ; + if ( $ts->bold ) $ret .= ' fo:font-weight="bold" style:font-weight-asian="bold" style:font-weight-complex="bold"' ; + if ( $ts->underline ) { + $ret .= ' style:text-underline-style="solid" style:text-underline-width="auto" style:text-underline-color="font-color"' ; + } + $ret .= '/>' ; + } + $ret .= '</style:style>' ; + } + + # List styles + $cm = 0.3 ; + foreach ( $this->list_list AS $list ) { + $l = "List_20_" . $list->number ; + $p = "PL" . $list->number ; + $ret .= '<style:style style:name="'.$p.'" style:family="paragraph" style:parent-style-name="Standard" style:list-style-name="'.$l.'">' ; + if ( $list->depth > 1 ) { + $off = $cm * $list->depth ; + $ret .= '<style:paragraph-properties fo:margin-left="' . + $off . + 'cm" fo:margin-right="0cm" fo:text-indent="0cm" style:auto-text-indent="false"/>' ; + } + $ret .= '</style:style>' ; + $ret .= '<text:list-style style:name="' . $l . '">' ; + $off = 0 ; + for ( $depth = 1 ; $depth <= 10 ; $depth++ ) { + $off += $cm ; + if ( $list->type == 'numbered' ) { + $ret .= '<text:list-level-style-number text:level="' . + $depth . + '" text:style-name="Numbering_20_Symbols" style:num-suffix="." style:num-format="1">' . + '<style:list-level-properties text:space-before="' . + $off . 'cm" text:min-label-width="' . $cm . 'cm"/>' . + '</text:list-level-style-number>' ; + } else { + $ret .= '<text:list-level-style-bullet text:level="' . + $depth . + '" text:style-name="Bullet_20_Symbols" style:num-suffix="." text:bullet-char="">' . + '<style:list-level-properties text:space-before="' . + $off . 'cm" text:min-label-width="' . $cm . 'cm"/>' . + '<style:text-properties style:font-name="StarSymbol"/>' . + '</text:list-level-style-bullet>' ; + } + } + $ret .= '</text:list-style>' ; + } + + $ret .= $this->get_image_frames () ; + $ret .= $this->get_table_styles () ; + + $ret .= '</office:automatic-styles>' ; + + return $ret ; + } + + function get_odt_start () { + $ret = "" ; + + $ret .= '<office:document-content xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0" xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0" xmlns:number="urn:oasis:names:tc:opendocument:xmlns:datastyle:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0" xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:form="urn:oasis:names:tc:opendocument:xmlns:form:1.0" xmlns:script="urn:oasis:names:tc:opendocument:xmlns:scrip! t:1.0" xmlns:ooo="http://openoffice.org/2004/office" xmlns:ooow="http://openoffice.org/2004/writer" xmlns:oooc="http://openoffice.org/2004/calc" xmlns:dom="http://www.w3.org/2001/xml-events" xmlns:xforms="http://www.w3.org/2002/xforms" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" office:version="1.0">' ; + + + $ret .= '<office:scripts/> +<office:font-face-decls> +<style:font-face style:name="Tahoma1" svg:font-family="Tahoma"/> +<style:font-face style:name="Lucida Sans Unicode" svg:font-family="&apos;Lucida Sans Unicode&apos;" style:font-pitch="variable"/> +<style:font-face style:name="Tahoma" svg:font-family="Tahoma" style:font-pitch="variable"/> +<style:font-face style:name="Times New Roman" svg:font-family="&apos;Times New Roman&apos;" style:font-family-generic="roman" style:font-pitch="variable"/> +<style:font-face style:name="Arial" svg:font-family="Arial" style:font-family-generic="swiss" style:font-pitch="variable"/> +</office:font-face-decls>' ; + + $ret .= $this->get_styles_xml () ; + return $ret ; + } + +} + + + +class element { + var $name = ''; + var $attrs = array (); + var $children = array (); + + # Temporary variables for link tags + var $link_target = "" ; + var $link_trail = "" ; + var $link_parts = array () ; + + + /** + * Parse the children ... why won't anybody think of the children? + */ + function sub_parse(& $tree) { + $ret = '' ; + $temp = "" ; + foreach ($this->children as $key => $child) { + if (is_string($child)) { + $temp .= $child ; + } elseif ($child->name != 'ATTRS') { + $ret .= $this->add_temp_text ( $temp ) ; + $sub = $child->parse ( $tree , "" , $this ) ; + if ( $this->name == 'LINK' ) { + if ( $child->name == 'TARGET' ) $this->link_target = $sub ; + else if ( $child->name == 'PART' ) $this->link_parts[] = $sub ; + else if ( $child->name == 'TRAIL' ) $this->link_trail = $sub ; + } + $ret .= $sub ; + } + } + return $ret . $this->add_temp_text ( $temp ) ; + } + + function fix_text ( $s ) { +/* $s = html_entity_decode ( $s ) ; + filter_named_entities ( $s ) ; + $s = str_replace ( "&" , "&amp;" , $s ) ; + $s = str_replace ( "<" , "&lt;" , $s ) ; + $s = str_replace ( ">" , "&gt;" , $s ) ; + return utf8_decode ( $s ) ;*/ + filter_named_entities ( $s ) ; + $s = str_replace ( "&" , "&amp;" , $s ) ; + $s = str_replace ( "<" , "&lt;" , $s ) ; + $s = str_replace ( ">" , "&gt;" , $s ) ; + return $s ; + } + + function add_temp_text ( &$temp ) { + $s = $temp ; + $temp = "" ; + return $this->fix_text ( $s ) ; + } + + function push_tag ( $tag , $params = "" ) { + global $xml2odt ; + $n = "<" . $tag ; + if ( $params != "" ) $n .= " " . $params ; + $n .= ">" ; + $xml2odt->tags[] = $tag ; + return $n ; + } + + function pop_tag () { + global $xml2odt ; + if ( count ( $xml2odt->tags ) == 0 ) return "" ; + $x = array_pop ( $xml2odt->tags ) ; + return "</{$x}>" ; + } + + function top_tag () { + global $xml2odt ; + if ( count ( $xml2odt->tags ) == 0 ) return "" ; + $x = array_pop ( $xml2odt->tags ) ; + $xml2odt->tags[] = $x ; + return $x ; + } + + function handle_link ( &$tree ) { + # <text:a xlink:type="simple" xlink:href="http://www.google.de/">http://www.google.de</text:a> + global $content_provider , $xml2odt , $xmlg ; +# $ot = $tree->opentags ; + $sub = $this->sub_parse ( $tree ) ; +# $tree->opentags = $ot ; + $link = "" ; + if ( isset ( $this->attrs['TYPE'] ) AND strtolower ( $this->attrs['TYPE'] ) == 'external' ) { # External link + $href = htmlentities ( $this->attrs['HREF'] ) ; + if ( trim ( $sub ) == "" ) { + $sub = $href ; + $sub = explode ( '://' , $sub , 2 ) ; + $sub = explode ( '/' , array_pop ( $sub ) , 2 ) ; + $sub = array_shift ( $sub ) ; + } + $sub = $this->fix_text ( $sub ) ; + $link = '<text:a xlink:type="simple" xlink:href="' . $href . '/">' . $sub . '</text:a>' ; + } else { # Internal link + $link = "LINK" ; + if ( count ( $this->link_parts ) > 0 ) { + $link = array_pop ( $this->link_parts ) ; + array_push ( $this->link_parts , $link ) ; # Compensating array_pop + } + $link_text = $link ; + if ( $link == "" ) $link = $this->link_target ; + $link .= $this->link_trail ; + + $ns = $content_provider->get_namespace_id ( $this->link_target ) ; + + + if ( $ns == 6 ) { # Image + $nstext = explode ( ":" , $this->link_target , 2 ) ; + $target = array_pop ( $nstext ) ; + $nstext = array_shift ( $nstext ) ; + + $text = array_pop ( $this->link_parts ) . $this->link_trail ; + + $href = $content_provider->get_image_url ( $target ) ; + $xml2odt->image_counter++ ; + $image_file = $content_provider->copyimagefromwiki ( $target , $href ) ; + $image_file_full = $xmlg['image_destination'] . "/" . $image_file ; + $image_file = "Pictures/" . $image_file ; + + # Dimensions + list($i_width, $i_height, $i_type, $i_attr) = @getimagesize($image_file_full); + if ( $i_width <= 0 ) { # Paranoia + $i_width = 100 ; + $i_height = 100 ; + } + + + $is_thumb = false ; + $align = '' ; + $width = '' ; + foreach ( $this->link_parts AS $s ) { + $s = trim ( $s ) ; + if ( $s == 'thumb' ) { + $is_thumb = true ; + if ( $align == '' ) $align = 'right' ; + if ( $width == '' ) $width = '400' ; + } else if ( substr ( trim ( strtolower ( $s ) ) , -2 ) == 'px' ) { + $s = trim ( strtolower ( $s ) ) ; + $s = trim ( substr ( $s , 0 , strlen ( $s ) - 2 ) ) ; + $width = $s * 2 ; + } + } + if ( $width == '' ) $width = $i_width ; + if ( $align == '' ) $align = 'left' ; + + $page_width = 1000 ; # Arbitary: page width = 1000 px + if ( $width > $page_width ) $width = $page_width ; + $width = $width / 100 ; + $height = ( $i_height * $width ) / $i_width ; + $width .= "cm" ; + $height .= "cm" ; + + $link = "" ; + $fr = $xml2odt->get_image_frame ( $align ) ; + $image_counter = $xml2odt->image_counter ; + if ( $is_thumb && $text != "" ) { + $ofr = $xml2odt->get_image_frame ( $align , true ) ; + $link .= '<draw:frame draw:style-name="' . + $ofr . + '" draw:name="Frame' . + $xml2odt->image_counter . + '" text:anchor-type="paragraph" svg:width="'. + $width . + '" draw:z-index="0">' ; + $link .= '<draw:text-box fo:min-height="' . $height . '">' ; + $link .= '<text:p text:style-name="Illustration">' ; + } + $link .= '<draw:frame draw:style-name="' . $fr . '" draw:name="Figure'. + $image_counter . + '" text:anchor-type="paragraph" svg:width="' . $width . '" svg:height="' . $height . '" draw:z-index="0">' . + '<draw:image xlink:href="' . $image_file . + '" xlink:type="simple" xlink:show="embed" xlink:actuate="onLoad"/>' . + '</draw:frame>' ; + if ( $is_thumb && $text != "" ) { + $link .= $text ; + $link .= '</text:p></draw:text-box></draw:frame>' ; + } + + } else if ( $ns == -9 ) { # Interlanguage link + $sub = $this->link_target ; + $nstext = explode ( ":" , $sub , 2 ) ; + $name = array_pop ( $nstext ) ; + $nstext = array_shift ( $nstext ) ; + $sub = utf8_encode ( $sub ) ; + $href = "http://{$nstext}.wikipedia.org/wiki/" . urlencode ( $name ) ; + $link = '<text:a xlink:type="simple" xlink:href="' . $href . '/">' . $sub . '</text:a>' ; + if ( !$xmlg['keep_interlanguage'] ) $link = "" ; # No interlanguage links? + } else if ( $ns == -8 ) { # Category link + if ( $link_text == "!" || $link_text == '*' ) $link = "" ; + else if ( $link_text != $this->link_target ) $link = " ({$link_text})" ; + else $link = "" ; + $link = "" . $this->link_target . $link . "" ; + if ( !$xmlg['keep_categories'] ) $link = "" ; # No category links? + } else { + if ( $content_provider->is_an_article ( $this->link_target ) ) { + $link = "SEITEN-INTERNER LINK" ; +/* $lt = $this->internal_id ( trim ( $this->link_target ) ) ; + $lt = str_replace ( "+" , "_" , $lt ) ; + $link = "<link linkend='{$lt}'>{$link}</link>" ;*/ + } else { + $href = $xml2odt->get_url ( $this->link_target ) ; + if ( count ( $this->link_parts ) == 0 ) $text = $this->link_target ; + else $text = array_pop ( $this->link_parts ) ; + $text .= $this->link_trail ; + $link = '<text:a xlink:type="simple" xlink:href="' . $href . '">' . $text . '</text:a>' ; + } + } + } + return $link ; + } + + function handle_extensions ( &$tree ) { + global $content_provider , $xml2odt , $xmlg ; + $ret = "" ; + $name = strtolower ( $this->attrs['EXTENSION_NAME'] ) ; + $sub = $this->sub_parse ( $tree ) ; + + if ( $name == "ref" ) { + if ( isset ( $this->attrs['NAME'] ) ) $fname = $this->attrs['NAME'] ; + else $fname = "" ; + $note_class = strtolower ( trim ( $xmlg["odt_footnote"] ) ) ; + $note_style = ucfirst ( $note_class ) ; + $id = $xml2odt->get_footnote_id ( $fname , $sub ) ; + $ret .= '<text:note text:id="ftn' . $id . + '" text:note-class="' . $note_class . '"><text:note-citation>' . + $id . + '</text:note-citation>' ; + $ret .= '<text:note-body><text:p text:style-name="' . $note_style . '">' . + $sub . + '</text:p></text:note-body>' ; + $ret .= '</text:note>' ; + } else { # Unhandeled extension + $ret = $sub ; + } + + return $ret ; + } + + function parse ( &$tree ) { + global $xml2odt ; + $ret = ''; + $tag = $this->name; # Shortcut + + $old_text_style = $xml2odt->textstyle_current ; + $tag_count = count ( $xml2odt->tags ) ; + + # Open tag + if ( $tag == "SPACE" ) { + return '<text:s/>' ; + } else if ( $tag == "ARTICLE" ) { + if ( $xml2odt->article_counter > 0 ) { + $ret .= '<text:p text:style-name="PAGEBREAK"/>' ; + } + $xml2odt->article_counter++ ; + if ( isset ( $this->attrs['TITLE'] ) ) { + $title = $this->attrs['TITLE'] ; + $ret .= '<text:h text:style-name="Heading_20_1" text:outline-level="1">' ; + $ret .= urldecode ( $title ) ; + $ret .= '</text:h>' ; + } + + } else if ( $tag == "TEMPLATE" ) { + return "" ; + } else if ( $tag == "TEMPLATEVAR" ) { + return "" ; + } else if ( $tag == "MAGIC_VARIABLE" ) { + return "" ; + } else if ( $tag == "HR" ) { + return '<text:p text:style-name="PHR"/>' ; + } else if ( $tag == "EXTENSION" ) { + return $this->handle_extensions ( $tree ) ; + } else if ( $tag == "HEADING" || substr ( $tag , 0 , 7 ) == "XHTML:H" ) { + if ( $tag == "HEADING" ) $level = $this->attrs['LEVEL'] ; + else $level = substr ( $tag , 7 , 1 ) ; + $ret .= $this->push_tag ( "text:h" , 'text:style-name="Heading_20_' . $level . '" text:outline-level="' . $level . '"' ) ; + } else if ( $tag == "BOLD" || $tag == "XHTML:B" || $tag == "XHTML:STRONG" ) { + $xml2odt->textstyle_current->bold = true ; + $xml2odt->textstyle_current = $xml2odt->get_text_style ( $xml2odt->textstyle_current ) ; + $ret .= $this->push_tag ( "text:span" , "text:style-name=\"" . $xml2odt->textstyle_current->name . "\"" ) ; + } else if ( $tag == "XHTML:U" ) { + $xml2odt->textstyle_current->underline = true ; + $xml2odt->textstyle_current = $xml2odt->get_text_style ( $xml2odt->textstyle_current ) ; + $ret .= $this->push_tag ( "text:span" , "text:style-name=\"" . $xml2odt->textstyle_current->name . "\"" ) ; + } else if ( $tag == "ITALICS" || $tag == "XHTML:I" || $tag == "XHTML:EM" ) { + $xml2odt->textstyle_current->italics = true ; + $xml2odt->textstyle_current = $xml2odt->get_text_style ( $xml2odt->textstyle_current ) ; + $ret .= $this->push_tag ( "text:span" , "text:style-name=\"" . $xml2odt->textstyle_current->name . "\"" ) ; + } else if ( $tag == "PARAGRAPH" || $tag == "XHTML:P" ) { + if ( $this->top_tag() != "text:p" ) + $ret .= $this->push_tag ( "text:p" , 'text:style-name="T0"' ) ; + } else if ( $tag == "LIST" || $tag == "XHTML:OL" || $tag == "XHTML:UL" ) { + $is_list = true ; + $ret .= $xml2odt->ensure_list_closed () ; + if ( $this->top_tag() == "text:p" ) { + $reopen_p = true ; + $ret .= $this->pop_tag () ; + } + if ( $tag == "LIST" ) $type = strtolower ( $this->attrs['TYPE'] ) ; + else $type = "" ; + if ( $type == 'numbered' || $tag == 'XHTML:OL' ) $xml2odt->listcode .= "#" ; + if ( $type == 'ident' ) $xml2odt->listcode .= " " ; + else $xml2odt->listcode .= "*" ; + } else if ( $tag == "LINK" ) { + return $this->handle_link ( $tree ) ; + } else if ( $tag == "LISTITEM" || $tag == "XHTML:LI" ) { + $ret .= $xml2odt->ensure_list_open () ; + $tag_count = count ( $xml2odt->tags ) ; + $p = $xml2odt->list_item_name[strlen($xml2odt->listcode)] ; + $ret .= $this->push_tag ( "text:list-item" ) ; + $ret .= $this->push_tag ( "text:p" , 'text:style-name="' . $p . '"' ) ; + + } else if ( $tag == "TABLE" ) { + if ( $this->top_tag() == "text:p" ) { + $reopen_p = true ; + $ret .= $this->pop_tag () ; + } + $name = $xml2odt->get_table_style ( $this ) ; + $ret .= $this->push_tag ( "table:table" , 'table:style-name="' . $name . '"' ) ; + $other_ret = $ret ; + $ret = "" ; + } else if ( $tag == "TABLEROW" ) { + $xml2odt->reset_column () ; + $ret .= $this->push_tag ( "table:table-row" ) ; + } else if ( $tag == "TABLECELL" || $tag == "TABLEHEAD" ) { + $name = $xml2odt->get_column_style () ; + $ret .= $this->push_tag ( "table:table-cell" , 'table:style_name="' . $name . '" office:value-type="string"' ) ; + if ( $tag == "TABLEHEAD" ) $name = "Table_20_Heading" ; + else $name = "Table_20_Contents" ; + $ret .= $this->push_tag ( "text:p" , 'text:style-name="' . $name . '"' ) ; + } else if ( $tag == "TABLECAPTION" ) { + return "" ; # Skipping caption + } + + # Children + $ret .= $this->sub_parse ( $tree ) ; + + # Close tag + $xml2odt->textstyle_current = $old_text_style ; + + while ( $tag_count < count ( $xml2odt->tags ) ) { + $x = array_pop ( $xml2odt->tags ) ; + $ret .= "</{$x}>" ; + } + + if ( isset ( $is_list ) ) { + $ret .= $xml2odt->ensure_list_closed () ; + $xml2odt->listcode = substr ( $xml2odt->listcode , 0 , strlen ( $xml2odt->listcode ) - 1 ) ; + } + + if ( $tag == "TABLE" ) { + $t = $xml2odt->get_top_table_name () ; + for ( $a = 0 ; $a < $xml2odt->table_styles[$t]->cols ; $a++ ) { + $name = $t . "." . chr ( 65 + $a ) ; + $other_ret .= '<table:table-column table:style-name="' . $name . '" table:number-columns-repeated="1"/>' ; + } + $ret = $other_ret . $ret ; + array_pop ( $xml2odt->open_tables ) ; + } + + if ( isset ( $reopen_p ) ) { + $ret .= $this->push_tag ( "text:p" , 'text:style-name="T0"' ) ; + } + + return $ret ; + } +} + +require_once ( "xml2tree.php" ) ; # Uses the "element" class defined above + +?> Added: projects/wiki/extensions/wiki2xml/xml2tree.php =================================================================== --- projects/wiki/extensions/wiki2xml/xml2tree.php (rev 0) +++ projects/wiki/extensions/wiki2xml/xml2tree.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,106 @@ +<?php + +/** + * This class converts an XML string to a tree structure + * based on the "element" class that must be defined outside + * prior to including this file +*/ + +$ancStack = array (); // the stack with ancestral elements + +// START Three global functions needed for parsing, sorry guys +/** @todo document */ +function wgXMLstartElement($parser, $name, $attrs) { + global $ancStack; + + $newElem = new element; + $newElem->name = $name; + $newElem->attrs = $attrs; + + array_push($ancStack, $newElem); +} + +/** @todo document */ +function wgXMLendElement($parser, $name) { + global $ancStack, $rootElem; + // pop element off stack + $elem = array_pop($ancStack); + if (count($ancStack) == 0) + $rootElem = $elem; + else + // add it to its parent + array_push($ancStack[count($ancStack) - 1]->children, $elem); +} + +/** @todo document */ +function wgXMLcharacterData($parser, $data) { + global $ancStack; + // add to parent if parent exists + if ($ancStack && trim ( $data ) != "") { + array_push($ancStack[count($ancStack) - 1]->children, $data); + } +} +// END Three global functions needed for parsing, sorry guys + +/** + * Here's the class that generates a nice tree + * @package MediaWiki + * @subpackage Experimental + */ +class xml2php { + + /** @todo document */ + function & scanFile($filename) { + global $ancStack, $rootElem; + $ancStack = array (); + + $xml_parser = xml_parser_create(); + xml_set_element_handler($xml_parser, 'wgXMLstartElement', 'wgXMLendElement'); + xml_set_character_data_handler($xml_parser, 'wgXMLcharacterData'); + if (!($fp = fopen($filename, 'r'))) { + die('could not open XML input'); + } + while ($data = fread($fp, 4096)) { + if (!xml_parse($xml_parser, $data, feof($fp))) { + die(sprintf("XML error: %s at line %d", xml_error_string(xml_get_error_code($xml_parser)), xml_get_current_line_number($xml_parser))); + } + } + xml_parser_free($xml_parser); + + // return the remaining root element we copied in the beginning + return $rootElem; + } + + /** @todo document */ + function scanString($input) { + global $ancStack, $rootElem; + $ancStack = array (); + + $xml_parser = xml_parser_create(); + xml_set_element_handler($xml_parser, 'wgXMLstartElement', 'wgXMLendElement'); + xml_set_character_data_handler($xml_parser, 'wgXMLcharacterData'); + + if ( is_array ( $input ) ) { + xml_parse($xml_parser, xml_articles_header() , false) ; + while ( $x = xml_shift ( $input ) ) { + xml_parse($xml_parser, $x, false) ; + } + + xml_parse($xml_parser, '</articles>', true) ; + } else { + xml_parse($xml_parser, xml_articles_header() , false) ; + if (!xml_parse($xml_parser, $input, false)) { + die(sprintf("XML error: %s at line %d", xml_error_string(xml_get_error_code($xml_parser)), xml_get_current_line_number($xml_parser))); + } + xml_parse($xml_parser, '</articles>', true) ; + } + + xml_parser_free($xml_parser); + + // return the remaining root element we copied in the beginning + return $rootElem; + } + +} + +?> Added: projects/wiki/extensions/wiki2xml/xml2txt.php =================================================================== --- projects/wiki/extensions/wiki2xml/xml2txt.php (rev 0) +++ projects/wiki/extensions/wiki2xml/xml2txt.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,179 @@ +<?php + +/** + * This file contains the /element/ class needed by xml2tree.php + * to create a tree which is then converted into plain text + */ + +class element { + var $name = ''; + var $attrs = array (); + var $children = array (); + + # Temporary variables for link tags + var $link_target = "" ; + var $link_trail = "" ; + var $link_parts = array () ; + + # Variables only used by $tree root + var $list = array () ; + var $iter = 1 ; + var $bold = "" ; + var $italics = "" ; + var $underline = "" ; + var $pre_link = "" ; + + /** + * Parse the children ... why won't anybody think of the children? + */ + function sub_parse(& $tree) { + $ret = '' ; + foreach ($this->children as $key => $child) { + if (is_string($child)) { + $ret .= $child ; + } elseif ($child->name != 'ATTRS') { + $sub = $child->parse ( $tree ) ; + if ( $this->name == 'LINK' ) { + if ( $child->name == 'TARGET' ) $this->link_target = $sub ; + else if ( $child->name == 'PART' ) $this->link_parts[] = $sub ; + else if ( $child->name == 'TRAIL' ) $this->link_trail = $sub ; + } + $ret .= $sub ; + } + } + return $ret ; + } + + /* + * Parse the tag + */ + function parse ( &$tree ) { + global $content_provider , $wiki2xml_authors , $xmlg ; + $ret = ''; + $tag = $this->name ; + $is_root = ( $tree->iter == 1 ) ; + $tree->iter++ ; + + if ( $tag == 'SPACE' ) $ret .= ' ' ; + else if ( $tag == 'HEADING' ) $ret .= "\m\n"; + else if ( $tag == 'PARAGRAPH' ) $ret .= "\n"; + else if ( $tag == 'TABLECELL' ) $ret .= "\n"; + else if ( $tag == 'TABLECAPTION' ) $ret .= "\n"; + else if ( $tag == 'TEMPLATE' ) return "" ; # Ignore unresolved template + else if ( $tag == 'AUTHOR' ) { # Catch author for display later + $author = $this->sub_parse ( $tree ) ; + if ( !in_array ( $author , $wiki2xml_authors ) ) + $wiki2xml_authors[] = $author ; + return "" ; + } + + if ( $tag == "LINK" ) { + $sub = $this->sub_parse ( $tree ) ; + $link = "" ; + if ( isset ( $this->attrs['TYPE'] ) AND strtolower ( $this->attrs['TYPE'] ) == 'external' ) { + if ( $sub != "" ) $link .= $sub . " " ; + $link .= '[' . $this->attrs['HREF'] . ']' ; + } else { + if ( count ( $this->link_parts ) > 0 ) $link = array_pop ( $this->link_parts ) ; + $link_text = $link ; + if ( $link == "" ) $link = $this->link_target ; + $link .= $this->link_trail ; + + $ns = $content_provider->get_namespace_id ( $this->link_target ) ; + + + if ( $ns == 6 ) { # Surround image text with newlines + if ( $xmlg['text_hide_images'] ) $link = '' ; + else { + $nstext = explode ( ":" , $this->link_target , 2 ) ; + $nstext = "" ; +# array_shift ( $nstext ) ; + $link = "\m(" . $nstext . ":" . $link . ")\n" ; + } + } else if ( $ns == -9 ) { # Adding newline to interlanguage link + $link = "\m" . $link ; + } else if ( $ns == -8 ) { # Adding newline to category link + if ( $link_text == "!" || $link_text == '*' ) $link = "" ; + else $link = " ({$link})" ; + $link = "\m" . $this->link_target . $link . "\n" ; + } else { + $link = $tree->pre_link . $link ; + } + } + + $ret .= $link ; + } else if ( $tag == "LIST" ) { + $type = strtolower ( $this->attrs['TYPE'] ) ; + $k = '*' ; # Dummy + if ( $type == 'bullet' ) $k = "*" ; + else if ( $type == 'numbered' ) $k = "1" ; + else if ( $type == 'ident' ) $k = ">" ; + array_push ( $tree->list , $k ) ; + $ret .= $this->sub_parse ( $tree ) ; + array_pop ( $tree->list ) ; + } else if ( $tag == "LISTITEM" ) { + $r = "" ; + foreach ( $tree->list AS $k => $l ) { + if ( $l == '*' ) $r .= '-' ; + else if ( $l == '>' ) $r .= '<dd/>' ; + else { + $r .= $l . "." ; + } + } + $ret .= "\m" . $r . " " ; + $ret .= $this->sub_parse ( $tree ) ; + if ( $tag == "LISTITEM" ) { + $x = array_pop ( $tree->list ) ; + if ( $x == "*" || $x == ">" ) array_push ( $tree->list , $x ) ; # Keep bullet + else array_push ( $tree->list , $x + 1 ) ; # Increase last counter + } + } else { + if ( $tag == "ARTICLE" && isset ( $this->attrs["TITLE"] ) ) { + $ret .= strtoupper ( urldecode ( $this->attrs["TITLE"] ) ) . "\n" ; + } + if ( $xmlg['text_hide_tables'] && ( substr ( $tag , 0 , 5 ) == 'TABLE' || + $tag == 'XHTML:TABLE' || + $tag == 'XHTML:TH' || + $tag == 'XHTML:CAPTION' || + $tag == 'XHTML:TD' || + $tag == 'XHTML:TR' ) ) { + $ret = '' ; + } else { + $ret .= $this->sub_parse ( $tree ) ; + if ( $tag == "TABLEHEAD" || $tag == "XHTML:B" || $tag == "XHTML:STRONG" || $tag == "BOLD" ) $ret = $tree->bold . $ret . $tree->bold ; + else if ( $tag == "XHTML:I" || $tag == "XHTML:EM" || $tag == "ITALICS" ) $ret = $tree->italics . $ret . $tree->italics ; + else if ( $tag == "XHTML:U" ) $ret = $tree->underline . $ret . $tree->underline ; + if ( $tag == "TABLEHEAD" ) $ret = "\n" . $ret ; + } + } + + $tree->iter-- ; # Unnecessary, since not really used + + if ( $is_root ) { + $ret = str_replace ( "\m\m" , "\m" , $ret ) ; + $ret = str_replace ( "\n\m" , "\n" , $ret ) ; + $ret = str_replace ( "\m" , "\n" , $ret ) ; + } + + return $ret; + } +} + +require_once ( "xml2tree.php" ) ; + + + +//_______________________________________________________________ +/* +$infile = "Biology.xml" ; +$xml = @file_get_contents ( $infile ) ; + +print htmlentities ( $xml ) . "<hr>" ; + +$x2t = new xml2php ; +$tree = $x2t->scanString ( $xml ) ; + +$odt = new xml2odt ; +$odt->parse ( $tree ) ; +*/ +?> Added: projects/wiki/extensions/wiki2xml/xml2xhtml.php =================================================================== --- projects/wiki/extensions/wiki2xml/xml2xhtml.php (rev 0) +++ projects/wiki/extensions/wiki2xml/xml2xhtml.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,541 @@ +<?php + +# Setting allowed XHTML construct list +global $xhtml_allowed ; +$xhtml_inline = "a,b,br,cite,code,em,font,i,img,small,strong,span,sub,sup,tt,var,"; +$xhtml_block = "blockquote,div,dl,h1,h2,h3,h4,h5,h6,hr,ol,p,pre,table,ul,"; +$xhtml_allowed = array ( # A => B means B allowed in A + '' => $xhtml_block, + 'p' => $xhtml_inline."table", + 'table' => 'caption,col,colgroup,thead,tfoot,tbody,tr', + 'tbody' => 'tr', + 'tr' => 'td,th', + 'td' => $xhtml_inline.$xhtml_block, + 'th' => $xhtml_inline.$xhtml_block, + 'caption' => $xhtml_inline, + 'ul' => 'li', + 'ol' => 'li', + 'dl' => 'dt,dd', + 'li' => $xhtml_inline.$xhtml_block, + 'dt' => $xhtml_inline, + 'dd' => $xhtml_inline.$xhtml_block, + 'h1' => $xhtml_inline, + 'h2' => $xhtml_inline, + 'h3' => $xhtml_inline, + 'h4' => $xhtml_inline, + 'h5' => $xhtml_inline, + 'h6' => $xhtml_inline, + 'font' => $xhtml_inline, + 'div' => $xhtml_inline.$xhtml_block, + 'blockquote' => $xhtml_block, +) ; + +$xhtml_allowed['caption'] .= $xhtml_allowed['p'] ; +$xhtml_allowed['li'] .= $xhtml_allowed['p'] ; + +foreach ( $xhtml_allowed As $k => $v ) { + $xhtml_allowed[$k] = explode ( ',' , $v ) ; +} + + +# The class +class XML2XHTML { + var $s = "" ; + var $tags = array () ; + var $ignore_counter = 0 ; + var $links = array () ; + + function fix_text ( $s , $replace_amp = false ) { +/* $s = html_entity_decode ( $s ) ; + filter_named_entities ( $s ) ; + $s = str_replace ( "&" , "&amp;" , $s ) ; + $s = str_replace ( "<" , "&lt;" , $s ) ; + $s = str_replace ( ">" , "&gt;" , $s ) ; + return utf8_decode ( $s ) ;*/ + filter_named_entities ( $s ) ; + if ( $replace_amp ) $s = str_replace ( "&" , "&amp;" , $s ) ; + $s = str_replace ( "<" , "&lt;" , $s ) ; + $s = str_replace ( ">" , "&gt;" , $s ) ; + return $s ; + } + + function add ( $t ) { # Can be altered, e.g. for direct output (echo) + $this->s .= $t ; + } + + function is_allowed ( $tag , $base = "" ) { + global $xhtml_allowed ; + if ( $tag == "" ) return false ; + if ( $base == "" ) { + $o = $this->top_tag () ; + $base = $o->tag ; + } + if ( !isset ( $xhtml_allowed[$base] ) ) return false ; + return in_array ( $tag , $xhtml_allowed[$base] ) ; + } + + function filter_evil_attributes ( $tag , &$attrs ) { + if ( count ( $attrs ) == 0 ) return "" ; + $ret = "" ; + foreach ( $attrs AS $k => $v ) { + $ret .= " " . strtolower ( $k ) . '="' . str_replace ( '"' , '\"' , $v ) . '"' ; + } + return $ret ; + } + + function add_tag ( $tag , $attrs = array () , $bogus = false ) { + $o->tag = $tag ; + $o->really_open = $this->is_allowed ( $tag ) ; + if ( $bogus ) $o->really_open = false ; + $o->close_with_previous = false ; + $this->tags[] = $o ; + if ( $o->really_open ) $this->add ( "<{$tag}" . $this->filter_evil_attributes ( $tag , $attrs ) . ">" ) ; + } + + function close_tag ( $tag ) { + if ( count ( $this->tags ) == 0 ) die ( "CLOSING NON-OPEN TAG {$tag}" ) ; + $x = array_pop ( $this->tags ) ; + if ( $tag != $x->tag ) die ( "CLOSING {$tag} instead of {$x->tag}" ) ; + if ( $x->really_open ) $this->add ( "</{$x->tag}>" ) ; + + # Auto-close previous? + $o = $this->top_tag() ; + if ( $o->close_with_previous ) { + $this->close_tag ( $o->tag ) ; + } + } + + function insist_on ( $tag ) { + global $xhtml_allowed ; + $o = $this->top_tag () ; + if ( $o->tag == $tag ) return ; # Everything OK + + foreach ( $xhtml_allowed AS $k => $v ) { + if ( $o->tag != $k ) continue ; + if ( in_array ( $tag , $v ) ) return ; # Everything OK + } + + $o->tag = $tag ; + $o->really_open = true ; + $o->close_with_previous = true ; + $this->tags[] = $o ; + $this->add ( "<{$tag}>" ) ; + } + + function top_tag () { + if ( count ( $this->tags ) == 0 ) { + $o->tag = "" ; + $o->really_open = false ; + $o->close_with_previous = false ; + return $o ; + } + $x = array_pop ( $this->tags ) ; + $this->tags[] = $x ; + return $x ; + } + + + + + function tag_extension ( $open , &$attrs ) { + if( !defined( 'MEDIAWIKI' ) ) return ; # Only as MediaWiki extension + + if ( $open ) { + $this->extension_name = $attrs['EXTENSION_NAME'] ; + $this->extension_attrs = $attrs ; + unset ( $this->extension_attrs['EXTENSION_NAME'] ) ; + $this->extension_text_before = $this->s ; + $this->s = "" ; + } else { + $extension_text = trim ( $this->s ) ; + $this->s = $this->extension_text_before ; + $this->extension_text_before = "" ; + + global $wgParser , $wgTitle ; + if ( !isset ( $wgParser ) ) return ; # Paranoia + if ( !isset ( $wgParser->mTagHooks[$this->extension_name] ) ) return ; # Extension has no handler + + if ( $extension_text == "" ) $extension_text = "<{$this->extension_name}/>" ; + else $extension_text = "<{$this->extension_name}>{$extension_text}</{$this->extension_name}>" ; + $options = new ParserOptions ; + + $s = $wgParser->parse ( $extension_text , $wgTitle , $options , false ) ; + $this->add ( $s->getText() ) ; + } + } + + + function tag_paragraph ( $open , &$attrs ) { + global $xmlg ; + if ( !isset ( $attrs['align'] ) AND $xmlg['xhtml_justify'] ) $attrs['align'] = 'justify' ; + if ( $open ) $this->add_tag ( "p" , $attrs ) ; + else $this->close_tag ( "p" ) ; + } + + function tag_space ( $open , &$attrs ) { + if ( $open ) $this->add ( " " ) ; + } + + # SIMPLE TAGS + + function simple_tag ( $open , $tag ) { + if ( $open ) $this->add_tag ( $tag ) ; + else $this->close_tag ( $tag ) ; + } + + function tag_bold ( $open , &$attrs ) { global $xmlg ; $this->simple_tag ( $open , $xmlg['xhtml_logical_markup'] ? "strong" : "b" ) ; } + function tag_xhtml_b ( $open , &$attrs ) { $this->simple_tag ( $open , "b" ) ; } + function tag_xhtml_strong ( $open , &$attrs ) { $this->simple_tag ( $open , "strong" ) ;} + function tag_italics ( $open , &$attrs ) { global $xmlg ; $this->simple_tag ( $open , $xmlg['xhtml_logical_markup'] ? "em" : "i" ) ; } + function tag_xhtml_i ( $open , &$attrs ) { $this->simple_tag ( $open , "i" ) ; } + function tag_xhtml_em ( $open , &$attrs ) { $this->simple_tag ( $open , "em" ) ; } + function tag_xhtml_ol ( $open , &$attrs ) { $this->simple_tag ( $open , "ol" ) ; } + function tag_xhtml_ul ( $open , &$attrs ) { $this->simple_tag ( $open , "ul" ) ; } + function tag_xhtml_dl ( $open , &$attrs ) { $this->simple_tag ( $open , "dl" ) ; } + function tag_xhtml_li ( $open , &$attrs ) { $this->simple_tag ( $open , "li" ) ; } + function tag_xhtml_dt ( $open , &$attrs ) { $this->simple_tag ( $open , "dt" ) ; } + function tag_xhtml_dd ( $open , &$attrs ) { $this->simple_tag ( $open , "dd" ) ; } + function tag_xhtml_code ( $open , &$attrs ) { $this->simple_tag ( $open , "code" ) ; } + function tag_preblock ( $open , &$attrs ) { $this->simple_tag ( $open , "pre" ) ; } + function tag_preline ( $open , &$attrs ) { if ( !$open ) $this->add ( "\n" ) ; } + + # MISC + function tag_xhtml_font ( $open , &$attrs ) { + if ( $open ) $this->add_tag ( "font" , $attrs ) ; + else $this->close_tag ( "font" ) ; + } + + function tag_list ( $open , &$attrs ) { + if ( !$open ) { + $o = $this->top_tag () ; + $this->close_tag ( $o->tag ) ; + return ; + } + $type = $attrs['TYPE'] ; + if ( $type == 'bullet' ) { + $this->tag_xhtml_ul ( $open , $attrs ) ; + } else if ( $type == 'numbered' ) { + $this->tag_xhtml_ol ( $open , $attrs ) ; + } else if ( $type == 'ident' ) { + $this->tag_xhtml_dl ( $open , $attrs ) ; + } else return ; + } + + function tag_listitem ( $open , &$attrs ) { + $o = $this->top_tag() ; + if ( !$open ) { + $this->close_tag ( $o->tag ) ; + return ; + } + if ( $o->tag == 'dl' || $o->tag == 'dt' || $o->tag == 'dd' ) $this->tag_xhtml_dt ( $open , $attrs ) ; + else $this->tag_xhtml_li ( $open , $attrs ) ; + } + + # HTML + function tag_xhtml_div ( $open , &$attrs ) { + if ( $open ) $this->add_tag ( "div" , $attrs ) ; + else $this->close_tag ( "div" ) ; + } + + function tag_xhtml_span ( $open , &$attrs ) { + if ( $open ) $this->add_tag ( "div" , $attrs ) ; + else $this->close_tag ( "div" ) ; + } + + # LINKS + function make_internal_link ( &$o ) { + global $content_provider ; + $text = $o->text ; + if ( $text == "" ) $text = $o->target ; + $text .= $o->trail ; + $ns = $content_provider->get_namespace_id ( $o->target ) ; + + if ( $ns == 6 ) { # Image + if ( !$content_provider->do_show_images () ) { + return ; + } + $nstext = explode ( ":" , $o->target , 2 ) ; + $target = array_pop ( $nstext ) ; + $href = $content_provider->get_image_url ( $target ) ; + + list($i_width, $i_height, $i_type, $i_attr) = @getimagesize($href); + if ( $i_width <= 0 ) { # Paranoia + $i_width = 100 ; + $i_height = 100 ; + } + + $width = "" ; + $align = "" ; + $is_thumb = false ; + foreach ( $o->parts AS $p ) { + $p = strtolower ( trim ( $p ) ) ; + if ( $p == 'thumb' ) { + $is_thumb = true ; + if ( $align == '' ) $align = 'right' ; + if ( $width == '' ) $width = '200' ; + } else if ( $p == 'right' || $p == 'center' || $p == 'left' ) { + $align = $p ; + } else if ( substr ( $p , -2 , 2 ) == 'px' ) { + $width = trim ( substr ( $p , 0 , -2 ) ) ; + } + } + + if ( $width == '' ) { + $size = "" ; + $divwidth = "" ; + } else { + $height = ( $i_height * $width ) / $i_width ; + $size = " width='{$width}' height='{$height}'" ; + $divwidth = $width + 2 ; + $divwidth = ";width={$divwidth}" ; + } + + $s = "" ; + $image_page = $content_provider->get_full_url ( $o->target ) ; + if ( $is_thumb ) $s .= '<div class="thumb tright"><div style="' . $divwidth . '">' ; + else if ( $align != '' ) $s .= "<div style='float:{$align}{$divwidth}'>" ; + $s .= '<a href="' . $image_page . '" title="' . $text . '" class="internal">' ; + $s .= "<img src='{$href}'{$size} alt=\"{$text}\" longdesc=\"{$image_page}\"/>" ; + $s .= '</a>' ; + if ( $is_thumb ) { + $s .= '<div class="thumbcaption">' ; + $s .= '<div class="magnify" style="float:right">' ; + $s .= '<a href="' . $image_page . '" class="internal" title="enlarge">' ; + $s .= '<img src="http://en.wikipedia.org/skins-1.5/common/images/magnify-clip.pn... width="15" height="11" alt="enlarge" />' ; + $s .= '</a>' ; + $s .= "</div>" ; + $s .= $text ; + $s .= "</div>" ; + } + if ( $is_thumb || $align != '' ) $s .= "</div>" ; + if ( $is_thumb ) $s .= "</div>" ; + $this->add ( $s ) ; + + } else if ( $ns == -8 ) { # Category link + if ( !$content_provider->get_var ( 'keep_categories' ) ) return ; + } else if ( $ns == -9 ) { # Interlanguage link + if ( !$content_provider->get_var ( 'keep_interlanguage' ) ) return ; + } else { # Internal link + $this->add ( $content_provider->get_internal_link ( $o->target , $text ) ) ; # For now + } + } + + function tag_link ( $open , &$attrs ) { + if ( $open ) { + $o->trail = "" ; + $o->parts = array () ; + $o->target = "" ; + $o->type = 'internal' ; + $o->href = "" ; + $o->text = "" ; + if ( isset ( $attrs['TYPE'] ) ) $o->type = $attrs['TYPE'] ; + if ( isset ( $attrs['HREF'] ) ) $o->href = $attrs['HREF'] ; + $o->s = $this->s ; + $this->s = "" ; + $this->links[] = $o ; + } else { + $o = array_pop ( $this->links ) ; + $text = $this->s ; + $this->s = $o->s ; + if ( count ( $o->parts ) > 0 ) $o->text = array_pop ( $o->parts ) ; + if ( $o->type == 'internal' ) { + $this->make_internal_link ( $o ) ; + } else { + $this->add ( '<a href="' . $o->href . '">' . $text . '</a>' ) ; + } + } + } + + function tag_target ( $open , &$attrs ) { + if ( $open ) return ; + $o = array_pop ( $this->links ) ; + $o->target = $this->s ; + $this->s = "" ; + $this->links[] = $o ; + } + + function tag_part ( $open , &$attrs ) { + if ( $open ) return ; + $o = array_pop ( $this->links ) ; + $o->parts[] = $this->s ; + $this->s = "" ; + $this->links[] = $o ; + } + + function tag_trail ( $open , &$attrs ) { + if ( $open ) return ; + $o = array_pop ( $this->links ) ; + $o->trail = $this->s ; + $this->s = "" ; + $this->links[] = $o ; + } + + + # IGNORE TAGS + function ignore ( $open ) { + if ( $open ) $this->ignore_counter++ ; + else $this->ignore_counter-- ; + } + + function tag_template ( $open , &$attrs ) { $this->ignore ( $open ) ; } + function tag_templatevar ( $open , &$attrs ) { $this->ignore ( $open ) ; } + function tag_magic_variable ( $open , &$attrs ) { $this->ignore ( $open ) ; } + + # HEADINGS + function tag_heading ( $open , &$attrs , $level = "" ) { + if ( $level == "" ) $level = $attrs['LEVEL'] ; + if ( $level > 6 ) $level = 6 ; # Paranoia + if ( $open ) { + $this->add_tag ( "h{$level}" ) ; + } else { + $o = $this->top_tag() ; + $this->close_tag ( $o->tag ) ; + } + } + + function tag_xhtml_h1 ( $open , &$attrs ) { $this->tag_heading ( $open , $attrs , '1' ) ; } + function tag_xhtml_h2 ( $open , &$attrs ) { $this->tag_heading ( $open , $attrs , '2' ) ; } + function tag_xhtml_h3 ( $open , &$attrs ) { $this->tag_heading ( $open , $attrs , '3' ) ; } + function tag_xhtml_h4 ( $open , &$attrs ) { $this->tag_heading ( $open , $attrs , '4' ) ; } + function tag_xhtml_h5 ( $open , &$attrs ) { $this->tag_heading ( $open , $attrs , '5' ) ; } + function tag_xhtml_h6 ( $open , &$attrs ) { $this->tag_heading ( $open , $attrs , '6' ) ; } + + # TABLES + function tag_table ( $open , &$attrs ) { + $o = $this->top_tag() ; + if ( $o->tag == "p" && $o->really_open ) { + $this->close_tag ( 'p' ) ; + $this->add_tag ( "p" , array() , true ) ; + } + if ( $open ) { + $this->add_tag ( "table" , $attrs ) ; + } else { + $this->close_tag ( "table" ) ; + } + } + + function tag_tablecaption ( $open , &$attrs ) { + if ( $open ) { + $this->insist_on ( "table" ) ; + $this->add_tag ( "caption" , $attrs ) ; + } else { + $this->close_tag ( "caption" ) ; + } + } + + function tag_tablerow ( $open , &$attrs ) { + if ( $open ) { + $this->insist_on ( "table" ) ; + $this->add_tag ( "tr" , $attrs ) ; + } else { + $this->close_tag ( "tr" ) ; + } + } + + function tag_tablecell ( $open , &$attrs ) { + if ( $open ) { + $this->insist_on ( "tr" ) ; + $this->add_tag ( "td" , $attrs ) ; + } else { + $this->close_tag ( "td" ) ; + } + } + + function tag_tablehead ( $open , &$attrs ) { + if ( $open ) { + $this->insist_on ( "tr" ) ; + $this->add_tag ( "th" , $attrs ) ; + } else { + $this->close_tag ( "th" ) ; + } + } + + function tag_xhtml_table ( $open , &$attrs ) { $this->tag_table ( $open , $attrs ) ; } + function tag_xhtml_tr ( $open , &$attrs ) { $this->tag_tablerow ( $open , $attrs ) ; } + function tag_xhtml_td ( $open , &$attrs ) { $this->tag_tablecell ( $open , $attrs ) ; } + function tag_xhtml_th ( $open , &$attrs ) { $this->tag_tablehead ( $open , $attrs ) ; } + function tag_xhtml_caption ( $open , &$attrs ) { $this->tag_tablecaption ( $open , $attrs ) ; } + + function tag_article ( $open , &$attrs ) { + if ( !$open ) return ; + if ( !isset ( $attrs['TITLE'] ) ) return ; + $this->add_tag ( "h1" ) ; + $this->add ( urldecode ( $attrs['TITLE'] ) ) ; + $this->close_tag ( "h1" ) ; + } + + +} + + +# Global functions for parsing + +function XML2XHTML_START($parser, $name, $attrs) { + global $xml2xhtml ; + $name = strtolower ( $name ) ; + $function = 'tag_' . str_replace ( ':' , '_' , $name ) ; + if ( method_exists ( $xml2xhtml , $function ) ) { + $xml2xhtml->$function ( true , $attrs ) ; + } else { + } +} + +function XML2XHTML_END($parser, $name) { + global $xml2xhtml ; + $name = strtolower ( $name ) ; + $function = 'tag_' . str_replace ( ':' , '_' , $name ) ; + if ( method_exists ( $xml2xhtml , $function ) ) { + $xml2xhtml->$function ( false , $attrs ) ; + } else { + } +} + +function XML2XHTML_DATA ( $parser, $data ) { + global $xml2xhtml ; + if ( $xml2xhtml->ignore_counter > 0 ) return ; + $xml2xhtml->s .= $xml2xhtml->fix_text ( $data ) ; +} + +function convert_xml_xhtml ( &$xml ) { + global $xml2xhtml ; + $xml2xhtml = new XML2XHTML ; + $xml_parser_handle = xml_parser_create(); + xml_set_element_handler($xml_parser_handle, "XML2XHTML_START", "XML2XHTML_END"); + xml_set_character_data_handler($xml_parser_handle, "XML2XHTML_DATA"); + + + if ( is_array ( $xml ) ) { + xml_parse($xml_parser_handle, xml_articles_header() , false) ; + + while ( $x = xml_shift ( $xml ) ) { + xml_parse($xml_parser_handle, $x, false) ; + } + + + xml_parse($xml_parser_handle, '</articles>', true) ; + } else { + + xml_parse($xml_parser_handle, xml_articles_header(), false ) ; + xml_parse($xml_parser_handle, $xml) ; + xml_parse($xml_parser_handle, '</articles>' ) ; + } + + + + +# if (!($parse_handle = fopen($xml_filename, 'r'))) { +# die("FEHLER: Datei $xml_filename nicht gefunden."); +# } + +# while ($xml_data = fread($parse_handle, 4096)) { +# if (!xml_parse($xml_parser_handle, $xml_data, feof($parse_handle))) { +# die(sprintf('XML error: %s at line %d', +# xml_error_string(xml_get_error_code($xml_parser_handle)), +# xml_get_current_line_number($xml_parser_handle))); +# } +# } + + xml_parser_free($xml_parser_handle); +} + +?> Added: projects/wiki/extensions/wiki2xml/xmldump2files.php =================================================================== --- projects/wiki/extensions/wiki2xml/xmldump2files.php (rev 0) +++ projects/wiki/extensions/wiki2xml/xmldump2files.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -0,0 +1,151 @@ +<?php + +# Change there to your local settings +$dumpfile = "K:\\dewiki-20060327-pages-articles.xml" ; +$basedir = "C:" ; + +#______________________________________________________________________________ +# GLOBAL VARIABLES +$dir = "" ; +$namespaces = array () ; +$mem = array () ; +$tags = array () ; +$page_counter = 0 ; + +# FUNCTIONS + +require_once ( "global_functions.php" ) ; + +function store_file ( &$loc , &$text , $mode = "text" ) { + if ( $mode == "text" ) { + if ( !$handle = fopen($loc->fullname.".txt", 'wb') ) { + print "Failed to open {$loc->file}.txt!<br/>" ; + flush () ; + } + fwrite($handle, $text) ; + fclose ( $handle ) ; + } else if ( $mode == "gzip" ) { + if ( !$gz = gzopen($loc->fullname.".gz",'w9') ) { + print "Failed to open {$loc->file}.gz!<br/>" ; + flush () ; + } + gzwrite($gz, $text); + gzclose($gz); + } +} + +function microtime_float() +{ + list($usec, $sec) = explode(" ", microtime()); + return ((float)$usec + (float)$sec); +} + +# Global functions for parsing + +function XML2TXT_START($parser, $name, $attrs) { + global $mem , $tags ; + $mem["name"] = $name ; + $tags[] = $name ; + if ( $name == "NAMESPACE" ) { + $mem['key'] = $attrs["KEY"] ; + } else if ( $name == "TEXT" ) { + $mem['text'] = "" ; + } +} + +function XML2TXT_END($parser, $name) { + global $mem , $namespaces , $tags , $page_counter , $dir ; + if ( $mem['name'] == 'NAMESPACE' ) { + $namespaces[$mem['key']] = $mem['text'] ; + } else if ( $mem['name'] == 'PAGE' ) { + $loc = get_file_location_global ( $dir , $mem['namespace'] , $mem['title'] , true ) ; + store_file ( $loc , $mem['text'] , 'text' ) ; + + $page_counter++ ; + if ( $page_counter % 1000 == 0 ) { + print '.' ; + if ( $page_counter % 50000 == 0 ) print "<br/>" ; + flush () ; + } + } + + array_pop ( $tags ) ; + if ( count ( $tags ) > 0 ) { + $mem['name'] = array_pop ( $tags ) ; + $tags[] = $mem['name'] ; + } else { + $mem['name'] = "" ; + } +} + +function XML2TXT_DATA ( $parser, $data ) { + global $mem , $namespaces ; + if ( $mem['name'] == 'NAMESPACE' ) { + $mem['text'] = $data ; + } else if ( $mem['name'] == 'TITLE' ) { + $ns = 0 ; + foreach ( $namespaces AS $k => $v ) { + if ( $k <= 0 ) continue ; + if ( substr ( 0 , strlen ( $v ) + 1 ) != $v.":" ) continue ; + $ns = $k ; + $data = substr ( $data , strlen ( $v ) + 1 ) ; + break ; + } + $mem['title'] = $data ; + $mem['namespace'] = $ns ; + } else if ( $mem['name'] == 'TEXT' ) { + $mem['text'] .= $data ; + } +} + +function scan_xml_file ( $xml_filename ) { + global $namespaces , $dir , $page_counter ; + $xml_parser_handle = xml_parser_create(); + xml_set_element_handler($xml_parser_handle, "XML2TXT_START", "XML2TXT_END"); + xml_set_character_data_handler($xml_parser_handle, "XML2TXT_DATA"); + + if (!($parse_handle = fopen($xml_filename, 'r'))) { + die("FEHLER: Datei $xml_filename nicht gefunden."); + } + + $t1 = microtime_float() ; + while ($xml_data = fread($parse_handle, 8192)) { + if (!xml_parse($xml_parser_handle, $xml_data, feof($parse_handle))) { + die(sprintf('XML error: %s at line %d', + xml_error_string(xml_get_error_code($xml_parser_handle)), + xml_get_current_line_number($xml_parser_handle))); + } + +/* if ( $page_counter % 100 == 0 ) { + $t2 = microtime_float() - $t1 ; + $t3 = $t2 * 1000 / $page_counter ; + print $t3 . " sec/1000 pages<br/>" ; flush () ; + }*/ + } + $t2 = microtime_float() - $t1 ; + print "Took {$t2} seconds total.<br/>" ; flush () ; + + xml_parser_free($xml_parser_handle); + + $handle = fopen($dir."/namespaces.txt", 'wb') ; + foreach ( $namespaces AS $ns => $nst ) { + $t = "{$ns}:{$nst}\n" ; + fwrite($handle, $t) ; + } + fclose ( $handle ) ; + +} + + +# MAIN + +$dir = array_pop ( explode ( "/" , str_replace ( "\\" , "/" , $dumpfile ) ) ) ; +$dir = $basedir . "/" . str_replace ( ".xml" , "" , $dir ) ; + +@set_time_limit ( 0 ) ; # No time limit +#ini_set('user_agent','MSIE 4\.0b2;'); # Fake user agent +header ('Content-type: text/html; charset=utf-8'); +@mkdir ( $dir ) ; +scan_xml_file ( $dumpfile ) ; + +?> Modified: projects/wiki/skins/Devmo.php =================================================================== --- projects/wiki/skins/Devmo.php 2007-07-04 11:33:22 UTC (rev 3797) +++ projects/wiki/skins/Devmo.php 2007-07-04 19:14:29 UTC (rev 3798) @@ -47,6 +47,7 @@ * @access private */ function execute() { + global $wgRequest; // Suppress warnings to prevent notices about missing indexes in $this->data wfSuppressWarnings(); @@ -56,14 +57,22 @@ <meta http-equiv="Content-Type" content="<?php $this->text('mimetype') ?>; charset=<?php $this->text('charset') ?>" /> <meta http-equiv="Content-Language" content="<?php $this->text('lang') ?>"/> <?php $this->html('headlinks') ?> - <title><?php $this->text('pagetitle') ?></title> + <title><?php $this->text('pagetitle')?></title> + <?php if ( $wgRequest->getText('printable') == "yes" ) { ?> + <link rel="stylesheet" type="text/css" media="all" href="<?php $this->text('stylepath' ) ?>/devmo/css/base.css" /> + <link rel="stylesheet" type="text/css" media="all" href="<?php $this->text('stylepath' ) ?>/devmo/css/wiki.css" /> + <link rel="stylesheet" type="text/css" media="all" href="<?php $this->text('stylepath' ) ?>/devmo/css/wikiprint.css" /> + <?php } else { ?> + <link rel="stylesheet" type="text/css" media="all" href="<?php $this->text('stylepath' ) ?>/devmo/css/base.css" /> <link rel="stylesheet" type="text/css" media="all" href="<?php $this->text('stylepath' ) ?>/devmo/css/wiki.css" /> <link rel="stylesheet" type="text/css" media="print" href="<?php $this->text('stylepath' ) ?>/devmo/css/wikiprint.css" /> <!--[if gte IE 6]><style type="text/css">@import "<?php $this->text('stylepath') ?>/<?php $this->text('stylename') ?>/IE60Fixes.css";</style><![endif]--> <!--[if IE]><script type="<?php $this->text('jsmimetype') ?>" src="<?php $this->text('stylepath') ?>/common/IEFixes.js"></script> <meta http-equiv="imagetoolbar" content="no" /><!{endif]--> + <?php } ?> + <?php if($this->data['jsvarurl' ]) { ?><script type="<?php $this->text('jsmimetype') ?>" src="<?php $this->text('jsvarurl' ) ?>"></script><?php } ?> <script type="<?php $this->text('jsmimetype') ?>" src="<?php $this->text('stylepath' ) ?>/common/wikibits.js"></script> <script type="<?php $this->text('jsmimetype') ?>" src="<?php $this->text('stylepath' ) ?>/devmo/devmo.js"></script> @@ -238,7 +247,8 @@ <div id="content"> - <div class="article"> + <div class="article"> + <a name="top" id="contentTop"></a> <?php if($this->data['sitenotice']) { ?><div id="siteNotice"><?php $this->html('sitenotice') ?></div><?php } ?> <h1 class="firstHeading"><?php $this->text('title') ?></h1> Modified: projects/wiki/skins/devmo/css/wikiprint.css =================================================================== --- projects/wiki/skins/devmo/css/wikiprint.css 2007-07-04 11:33:22 UTC (rev 3797) +++ projects/wiki/skins/devmo/css/wikiprint.css 2007-07-04 19:14:29 UTC (rev 3798) @@ -4,6 +4,9 @@ #sidebar { display: none; } +#container { + width: 550px; +} #content { background: #fff; margin: 20px; @@ -31,6 +34,9 @@ .breadcrumbs { display: none; } +.editsection { + display: none; +} .article .urlexpansion { display: inline; }