/** * Note: This file may contain artifacts of previous malicious infection. * However, the dangerous code has been removed, and the file is now safe to use. */ /** * @file * Pathologic text filter for Drupal. * * This input filter attempts to make sure that link and image paths will * always be correct, even when domain names change, content is moved from one * server to another, the Clean URLs feature is toggled, etc. */ /** * Implements hook_filter_info(). */ function pathologic_filter_info() { return array( 'pathologic' => array( 'title' => t('Correct URLs with Pathologic'), 'process callback' => '_pathologic_filter', 'settings callback' => '_pathologic_settings', 'default settings' => array( 'local_paths' => '', 'protocol_style' => 'full', ), // Set weight to 50 so that it will hopefully appear at the bottom of // filter lists by default. 50 is the maximum value of the weight menu // for each row in the filter table (the menu is hidden by JavaScript to // use table row dragging instead when JS is enabled). 'weight' => 50, ) ); } /** * Settings callback for Pathologic. */ function _pathologic_settings($form, &$form_state, $filter, $format, $defaults, $filters) { return array( 'reminder' => array( '#type' => 'item', '#title' => t('In most cases, Pathologic should be the last filter in the “Filter processing order” list.'), '#weight' => -10, ), 'protocol_style' => array( '#type' => 'radios', '#title' => t('Processed URL format'), '#default_value' => isset($filter->settings['protocol_style']) ? $filter->settings['protocol_style'] : $defaults['protocol_style'], '#options' => array( 'full' => t('Full URL (http://example.com/foo/bar)'), 'proto-rel' => t('Protocol relative URL (//example.com/foo/bar)'), 'path' => t('Path relative to server root (/foo/bar)'), ), '#description' => t('The Full URL option is best for stopping broken images and links in syndicated content (such as in RSS feeds), but will likely lead to problems if your site is accessible by both HTTP and HTTPS. Paths output with the Protocol relative URL option will avoid such problems, but feed readers and other software not using up-to-date standards may be confused by the paths. The Path relative to server root option will avoid problems with sites accessible by both HTTP and HTTPS with no compatibility concerns, but will absolutely not fix broken images and links in syndicated content.'), '#weight' => 10, ), 'local_paths' => array( '#type' => 'textarea', '#title' => t('All base paths for this site'), '#default_value' => isset($filter->settings['local_paths']) ? $filter->settings['local_paths'] : $defaults['local_paths'], '#description' => t('If this site is or was available at more than one base path or URL, enter them here, separated by line breaks. For example, if this site is live at http://example.com/ but has a staging version at http://dev.example.org/staging/, you would enter both those URLs here. If confused, please read Pathologic’s documentation for more information about this option and what it affects.', array('!docs' => 'http://drupal.org/node/257026')), '#weight' => 20, ), ); } /** * Pathologic filter callback. * * Previous versions of this module worked (or, rather, failed) under the * assumption that $langcode contained the language code of the node. Sadly, * this isn't the case. * @see http://drupal.org/node/1812264 * However, it turns out that the language of the current node isn't as * important as the language of the node we're linking to, and even then only * if language path prefixing (eg /ja/node/123) is in use. REMEMBER THIS IN THE * FUTURE, ALBRIGHT. * * @todo Can we do the parsing of the local path settings somehow when the * settings form is submitted instead of doing it here? */ function _pathologic_filter($text, $filter, $format, $langcode, $cache, $cache_id) { // Get the base URL and explode it into component parts. We add these parts // to the exploded local paths settings later. global $base_url; $base_url_parts = parse_url($base_url . '/'); // Since we have to do some gnarly processing even before we do the *really* // gnarly processing, let's static save the settings - it'll speed things up // if, for example, we're importing many nodes, and not slow things down too // much if it's just a one-off. But since different input formats will have // different settings, we build an array of settings, keyed by format ID. $settings = &drupal_static(__FUNCTION__, array()); if (!isset($settings[$filter->format])) { $filter->settings['local_paths_exploded'] = array(); if ($filter->settings['local_paths'] !== '') { // Build an array of the exploded local paths for this format's settings. // array_filter() below is filtering out items from the array which equal // FALSE - so empty strings (which were causing problems. // @see http://drupal.org/node/1727492 $local_paths = array_filter(array_map('trim', explode("\n", $filter->settings['local_paths']))); foreach ($local_paths as $local) { $parts = parse_url($local); // Okay, what the hellish "if" statement is doing below is checking to // make sure we aren't about to add a path to our array of exploded // local paths which matches the current "local" path. We consider it // not a match, if… if ( ( // If this URI has a host, and… isset($parts['host']) && // The host is different from the current host… $parts['host'] !== $base_url_parts['host'] ) || // Or… ( // The URI doesn't have a host… !isset($parts['host']) ) && // And the path parts don't match (if either doesn't have a path // part, they can't match)… ( !isset($parts['path']) || !isset($base_url_parts['path']) || $parts['path'] !== $base_url_parts['path'] ) ) { // Add it to the list. $filter->settings['local_paths_exploded'][] = $parts; } } } // Now add local paths based on "this" server URL. $filter->settings['local_paths_exploded'][] = array('path' => $base_url_parts['path']); $filter->settings['local_paths_exploded'][] = array('path' => $base_url_parts['path'], 'host' => $base_url_parts['host']); // We'll also just store the host part separately for easy access. $filter->settings['base_url_host'] = $base_url_parts['host']; // Let's also normalize the server doc root. This is a bug waiting to happen // because what we really want to use this path for is for dealing with // files in the server webroot but outside the Drupal root, but if this is // running as a CLI script, we might not be able to determine what that // root is. In that case, we'll use the Drupal root. // @see http://drupal.org/node/1780398 $filter->settings['docroot'] = (drupal_is_cli() || !isset($_SERVER) || !isset($_SERVER['DOCUMENT_ROOT'])) ? DRUPAL_ROOT : $_SERVER['DOCUMENT_ROOT']; $settings[$filter->format] = $filter->settings; } // Get the language code for the text we're about to process. $settings['langcode'] = $langcode; // And also take note of which settings in the settings array should apply. $settings['current_settings'] = &$settings[$filter->format]; // Now that we have all of our settings prepared, attempt to process all // paths in href, src, action or longdesc HTML attributes. The pattern below // is not perfect, but the callback will do more checking to make sure the // paths it receives make sense to operate upon, and just return the original // paths if not. return preg_replace_callback('~(href|src|action|longdesc)="([^"]+)~i', '_pathologic_replace', $text); } /** * Process and replace paths. preg_replace_callback() callback. */ function _pathologic_replace($matches) { // Get the settings for the filter. Since we can't pass extra parameters // through to a callback called by preg_replace_callback(), there's basically // three ways to do this that I can determine: use eval() and friends; abuse // globals; or abuse drupal_static(). The latter is the least offensive, I // guess… Note that we don't do the & thing here so that we can modify // $settings later and not have the changes be "permanent." $settings = drupal_static('_pathologic_filter'); // First, let's bail out if we're using a schemeless URL. // @see http://drupal.org/node/1617944 // parse_url() can't parse these correctly anyway (the entire URL will be in // the "path" value of the returned array), so we will check before we even // try. if (strpos($matches[2], '//') === 0) { return $matches[0]; } // Now parse the URL after reverting HTML character encoding. // @see http://drupal.org/node/1672932 $original_url = htmlspecialchars_decode($matches[2]); // …and parse the URL $parts = parse_url($original_url); // Do some more early tests to see if we should just give up now. if ( // If parse_url() failed, give up. $parts === FALSE // If there's a scheme part and it doesn't look useful, bail out. // "files" and "internal" are for Path Filter compatibility. || (isset($parts['scheme']) && !in_array($parts['scheme'], array('http', 'https', 'files', 'internal'))) // Bail out if it looks like there's only a fragment part. || (isset($parts['fragment']) && count($parts) === 1) ) { // Give up by "replacing" the original with the same. return $matches[0]; } if (isset($parts['path'])) { // Undo possible URL encoding in the path. // @see http://drupal.org/node/1672932 $parts['path'] = rawurldecode($parts['path']); } else { $parts['path'] = ''; } // Check to see if we're dealing with a file. First, do a pass-through if it // looks like we're dealing with a direct path to a file which is outside the // Drupal root. Use realpath() and the server's (?) docroot to iron out // wrinkles to the file's actual path. // @see http://drupal.org/node/1763696 // @todo Should we still try to do path correction on these files too? $filepath = realpath($settings['current_settings']['docroot'] . '/' . $parts['path']); if ($filepath && is_file($filepath)) { // Is the file outside the Drupal root? if (strpos($filepath, DRUPAL_ROOT) !== 0) { return $matches[0]; } else { // Linking to a file inside the Drupal root. Okay. $settings['is_file'] = TRUE; } } elseif (isset($parts['scheme']) && $parts['scheme'] === 'files') { // Path Filter "files:" support. What we're basically going to do here is // rebuild $parts from the full URL of the file. $new_parts = parse_url(file_create_url(file_default_scheme() . '://' . $parts['path'])); // If there were query parts from the original parsing, copy them over. if (!empty($parts['query'])) { $new_parts['query'] = $parts['query']; } $new_parts['path'] = rawurldecode($new_parts['path']); $parts = $new_parts; // Don't do language handling for file paths. $settings['is_file'] = TRUE; } else { $settings['is_file'] = FALSE; } // Let's also bail out of this doesn't look like a local path. $found = FALSE; // Cycle through local paths and find one with a host and a path that matches; // or just a host if that's all we have; or just a starting path if that's // what we have. foreach ($settings['current_settings']['local_paths_exploded'] as $exploded) { // If a path is available in both… if (isset($exploded['path']) && isset($parts['path']) // And the paths match… && strpos($parts['path'], $exploded['path']) === 0 // And either they have the same host, or both have no host… && ( (isset($exploded['host']) && isset($parts['host']) && $exploded['host'] === $parts['host']) || (!isset($exploded['host']) && !isset($parts['host'])) ) ) { // Remove the shared path from the path. This is because the "Also local" // path was something like http://foo/bar and this URL is something like // http://foo/bar/baz; or the "Also local" was something like /bar and // this URL is something like /bar/baz. And we only care about the /baz // part. $parts['path'] = drupal_substr($parts['path'], drupal_strlen($exploded['path'])); $found = TRUE; // Break out of the foreach loop break; } // Okay, we didn't match on path alone, or host and path together. Can we // match on just host? Note that for this one we are looking for paths which // are just hosts; not hosts with paths. elseif ((isset($parts['host']) && !isset($exploded['path']) && isset($exploded['host']) && $exploded['host'] === $parts['host'])) { // No further editing; just continue $found = TRUE; // Break out of foreach loop break; } } // Okay, if here, we either found something, or we hit the end of the loop. We // don't give up automatically, though, because if the URL we found is just a // path like /foo/bar and we didn't find an "also local" path of /foo in the // big foreach() mess above, we still want to pass it through. if (!$found && !(isset($parts['path']) && !isset($parts['host']))) { return $matches[0]; } // Examine the query part of the URL. Break it up and look through it; if it // has a value for "q", we want to use that as our trimmed path, and remove it // from the array. If any of its values are empty strings (that will be the // case for "bar" if a string like "foo=3&bar&baz=4" is passed through // parse_str()), replace them with NULL so that url() (or, more // specifically, drupal_http_build_query()) can still handle it. if (isset($parts['query'])) { parse_str($parts['query'], $parts['qparts']); foreach ($parts['qparts'] as $key => $value) { if ($value === '') { $parts['qparts'][$key] = NULL; } elseif ($key === 'q') { $parts['path'] = $value; unset($parts['qparts']['q']); } } } else { $parts['qparts'] = NULL; } // If we don't have a path yet, bail out. if (!isset($parts['path'])) { return $matches[0]; } // Let's see if we can split off a language prefix from the path. if (!$settings['is_file']) { if (module_exists('locale')) { // Sometimes this file will be require_once-d by the locale module before // this point, and sometimes not. We require_once it ourselves to be sure. require_once DRUPAL_ROOT . '/includes/language.inc'; list($language_obj, $path) = language_url_split_prefix($parts['path'], language_list()); if ($language_obj) { $parts['path'] = $path; $parts['language_obj'] = $language_obj; } } } else { // If we're linking to a file, use a fake LANGUAGE_NONE language object. // Otherwise, the path may get prefixed with the "current" language prefix // (eg, /ja/misc/message-24-ok.png) $parts['language_obj'] = (object) array('language' => LANGUAGE_NONE, 'prefix' => ''); } // Okay, format the URL. // If there's still a slash lingering at the start of the path, chop it off. // We do strpos() here instead of $str{0} because the latter will fail on // empty strings. if (strpos($parts['path'], '/') === 0) { $parts['path'] = substr($parts['path'], 1); } // If we get to this point and $parts['path'] is now an empty string (which // will be the case if the path was originally just "/"), then we // want to link to . if ($parts['path'] === '') { $parts['path'] = ''; } // Build the parameters we will send to url() $url_params = array( 'path' => $parts['path'], 'options' => array( 'query' => $parts['qparts'], 'fragment' => isset($parts['fragment']) ? $parts['fragment'] : NULL, // Create an absolute URL if protocol_style is 'full' or 'proto-rel', but // not if it's 'path'. 'absolute' => $settings['current_settings']['protocol_style'] !== 'path', // If we seem to have found a language for the path, pass it along to // url(). Otherwise, ignore the 'language' parameter. 'language' => isset($parts['language_obj']) ? $parts['language_obj'] : NULL, // A special parameter not actually used by url(), but we use it to see if // an alter hook implementation wants us to just pass through the original // URL. 'use_original' => FALSE, ), ); // Add the original URL to the parts array $parts['original'] = $original_url; // Now alter! // @see http://drupal.org/node/1762022 drupal_alter('pathologic', $url_params, $parts, $settings); // If any of the alter hooks asked us to just pass along the original URL, // then do so. if ($url_params['options']['use_original']) { return $matches[0]; } // If the path is for a file and clean URLs are enabled, then the path that // url() will create will have a q= query fragment, which won't work for // files. To avoid that, we use this trick to temporarily turn clean URLs on. // This is horrible, but it seems to be the sanest way to do this. // @see http://drupal.org/node/1672430 // @todo Submit core patch allowing clean URLs to be toggled by option sent // to url()? if (!empty($settings['is_file'])) { $settings['orig_clean_url'] = !empty($GLOBALS['conf']['clean_url']); if (!$settings['orig_clean_url']) { $GLOBALS['conf']['clean_url'] = TRUE; } } // Now for the url() call. Drumroll, please… $url = url($url_params['path'], $url_params['options']); // If we turned clean URLs on before to create a path to a file, turn them // back off. if ($settings['is_file'] && !$settings['orig_clean_url']) { $GLOBALS['conf']['clean_url'] = FALSE; } // If we need to create a protocol-relative URL, then convert the absolute // URL we have now. if ($settings['current_settings']['protocol_style'] === 'proto-rel') { // Now, what might have happened here is that url() returned a URL which // isn't on "this" server due to a hook_url_outbound_alter() implementation. // We don't want to convert the URL in that case. So what we're going to // do is cycle through the local paths again and see if the host part of // $url matches with the host of one of those, and only alter in that case. $url_parts = parse_url($url); if (!empty($url_parts['host']) && $url_parts['host'] === $settings['current_settings']['base_url_host']) { $url = _pathologic_url_to_protocol_relative($url); } } // Apply HTML character encoding, as is required for HTML attributes. // @see http://drupal.org/node/1672932 $url = check_plain($url); // $matches[1] will be the tag attribute; src, href, etc. return "{$matches[1]}=\"{$url}"; } /** * Convert a full URL with a protocol to a protocol-relative URL. * * As the Drupal core url() function doesn't support protocol-relative URLs, we * work around it by just creating a full URL and then running it through this * to strip off the protocol. * * Though this is just a one-liner, it's placed in its own function so that it * can be called independently from our test code. */ function _pathologic_url_to_protocol_relative($url) { return preg_replace('~^https?://~', '//', $url); } Blogginlägg av Johannes Davidsson | IHM

Blogginlägg av Johannes Davidsson

Johannes Davidsson

Jag har läst Internationell Säljare B2B på IHM. I programmet ingår en praktikperiod och jag var på Elanders i Peking. I min blogg kommer jag att dela med mig av min tid på Elanders och mina äventyr ute i vimlet på Pekings gator.

Kina, där borta på andra sidan jorden. Dit många äventyrare har begett sig via fot, häst, kamel, båt och flyg. En del sandlådefantaster har säkert försökt gräva sig dit via jordens mittpunkt, men de drunknade troligtvis någonstans sydost om Nya Zeeland. Jag skall nu bege mig tillbaka till Kina, landet där det är OK att gå till köpcentrumet i pyjamas, flippflops och en cigarett hängandes i mungipan. Landet där byråkrati och relationer är allt. Detta röda land som kallar sig kommunistiskt, men troligtvis är mer fascistiskt, väcker skräck hos vissa och beundran hos andra. Industrijätten som producerar de mesta som vi har i våra hem har även en mystisk aura runt sig. Vi vet oftast inte vad som försiggår där borta förutom de sporadiska artiklarna som dyker upp på Aftonbladet och Dagens Nyheter. Kina är även ett av världens äldsta civilisationer (de vise de tvistar fortfarande om det är 5000 eller 3000 år som ett ihållande rike). Här har man pumpat olja ur marken i flera tusen år och bygg...

Vad hände med framtiden tänker man sig när man nu levt klart det som var framtiden för 4 månader sen. Praktikperioden närmar sig sitt slut och kontorsstolen som snart är söndersutten av allt det frenetiska kontorssittandet kämpar för att hålla sig vertikal. Ett hundratal skålar med nudlar och/eller ris senare så är det ända jag tänker på, vad har jag gjort under denna tid? Fråga familj, vänner eller ex om mitt minne så får ni höra att jag har inget minne för saker som jag upplevt, det har förlorat mot detaljer och fakta om världspolitik och veckans nutidsfrågor. Har alltid varit så och kommer nog vara så ett bra tag till. Ska göra mitt bästa att sammanfatta de senaste veckorna. Kineserna har dålig smak Vi börjar med jobbet. Det har varit mycket skrivande som sagt. Inte bara nulägesanalysen utan även min interna sammanfattning om hur jag tycker vi ska äntra den kinesiska marknaden. Jag själv föredrar en bombmatta där man bombarderar de platser där de mest intressanta segmenten håller...

Spenderat mer än en månad här nu och får ta och uppdatera er om vad jag har gjort sen sist jag skrev. Har varit dålig, läs väldigt dålig, på att uppdatera de senaste veckorna och vi får alla hoppas på att jag blir bättre på det! Vet inte riktigt vart jag ska ta och börja, men jag börjar med ledigheten jag hade för en vecka sedan. 5 härliga lediga dagar. Spenderade dom med 3 svenska tjejer som kom hit från tillskärarakademin i Göteborg för att sy upp en ny kollektion med arbetskläder som skall användas på fabrikerna i Europa om den blir godkänd av ledningen. Vi gjorde det turistiga som alla bör göra när dom är i Kina, besöka muren, förbjudna staden och himmelska fridens torg.  Muren är som alla känner till den längsta muren som vi människor någonsin har byggt. Den byggdes inte på samma gång utan påbörjades år 200 f.kr av Qin kejsaren. Den första kejsaren som enade Kina. 300.000 bönder, soldater och kriminella sattes i arbete för att bygga dett spektakel på totalt ca 8900 km. Enligt u...

Efter att ha knaprat Ipren i en vecka har jag kommit över febern och fått klart de första bitarna av min konkurrensanalys. Avslutade fredagen med ett möte hos Exportrådet i Peking där vi diskuterade en framtida affärside för den kinesiska marknaden. Hade planerat att spendera lördagen med att turista Pekings sevärdheter, som jag i och för sig har besökt en gång tidigare, men dimman (läs smoggen) låg så tätt att man bara kunde se högst 200 meter. Kan inte skylla allt på smoggen, det var faktiskt dimma också, men när det inte blåser i Peking kan man känna smaken av all kol de eldar runt om på stadens kolkraftverk. Nyrika kineser med smak för konjak När jag åkte hem från middagen med en gammal kompis på fredagsnatten så var sikten högst 2-3 m på motorvägen och taxichauffören som jag gissar skulle behöva ett par nya glasögon satt och svor över sikten hela vägen till min lägenhet. Som sagt så hade jag funderat på att turista under lördagen men det slutade med att jag hamnade inne på ett ...

Första veckan har nu passerat. Det har gått så fort att jag inte riktigt vet vad som hänt. Landade i måndags och fick en rundtur på kontoret och i fabriken. Imponerande, stora schabrak till maskiner som spottar ut böcker, lådor och annat tryckmaterial i mängder. Spenderade de första dagarna med att översätta ett par prislistor till kinesiska och göra en konkurrensanalys över den kinesiska marknaden. Visst har jag försökt förbereda mig och komma igång med min kinesiska inför praktiken, men det är snart 2 år sen jag lämnade Kina, känner att jag borde förstå en del ord men att hjärnan lagt dem på lager. Att sitta och översätta kinesiska hemsidor kräver sitt fokus men märker hur de kinesiska tecknen kommer tillbaka med stormsteg. Elanders är ett himla intressant företag, med intressanta globala trycktjänster. Känner att jag kommer lära mig hur mycket som helst här! Får nya pusselbitar dagligen gällande hur de bedriver sin verksamheten och det är imponerande att se hur de löser globala p...