directory

Author: wcz-txp

README.md

@@ -0,0 +1,28 @@
+Unicode-url-for-Textpattern
+===========================
+
+Plugin for using unicode urls instead of transliterations to ASCII characters
+
+wcz_utf8_url – uses UTF-8 permlinks instead of transliterated ones for SEO
+
+Features
+
+    automatically handles non ASCII characters
+    integrated function for updating all of your existing titles – use on your OWN risk —> <txp:update_urls />
+    works with German, Russian, Ukrainian (on live sites)
+    tested with Japanese
+
+
+Tested with:
+
+    Textpattern 4.4.0+, MySQL 5.1.49, PHP 5.3.3 (Debian Squeeze)
+
+
+
+To do
+
+    make list of “small words” a parameter
+
+Feedback
+
+Comments are most welcome.

wcz_utf8_url-0.1.4.txt

@@ -0,0 +1,59 @@
+# wcz_utf8_url v0.1.4
+# Automatic UTF-8 permlinks
+# whocarez
+# 
+
+# ......................................................................
+# This is a plugin for Textpattern - http://textpattern.com/
+# To install: textpattern > admin > plugins
+# Paste the following text into the 'Install plugin' box:
+# ......................................................................
+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wcz_utf8_url.php

@@ -0,0 +1,83 @@
+<?php
+
+// This is a PLUGIN TEMPLATE.
+
+// Copy this file to a new name like abc_myplugin.php.  Edit the code, then
+// run this file at the command line to produce a plugin for distribution:
+// $ php abc_myplugin.php > abc_myplugin-0.1.txt
+
+// Plugin name is optional.  If unset, it will be extracted from the current
+// file name. Uncomment and edit this line to override:
+$plugin['name'] = 'wcz_utf8_url';
+
+$plugin['version'] = '0.1.4';
+$plugin['author'] = 'whocarez';
+$plugin['author_uri'] = '';
+$plugin['description'] = 'Automatic UTF-8 permlinks';
+$plugin['type'] = 1; // 0 for regular plugin; 1 if it includes admin-side code
+$plugin['order'] = 5; # use 5 as a default; ranges from 1 to 9
+
+
+@include_once('zem_tpl.php');
+
+if (0) {
+?>
+# --- BEGIN PLUGIN HELP ---
+
+Just install and activate.
+Adjust Textpattern->Advanced Options->“Maximum URL length (in characters)” to your needs.
+
+# --- END PLUGIN HELP ---
+<?php
+}
+
+# --- BEGIN PLUGIN CODE ---
+
+/*
+    wcz_utf8_url - Makes UTF-8 permlinks for SEO
+
+    Written by whocarez with help of the Textpattern Community
+
+    Released under the GNU General Public License 3
+    See: http://www.gnu.org/licenses/gpl.html
+
+    Version history:
+    0.1.4		- minor fix of preserving already existing dashes/minuses
+    0.1.3		- added remove small words
+    0.1.2		- minor fixes with double dashes and trimming the url string
+    0.1.1		- minor fixes
+    0.1.0		- initial release
+
+*/
+
+register_callback('wcz_utf8_url','sanitize_for_url');
+function wcz_utf8_url($event,$step,$text) {
+
+// replace slash and backslash before deleting unneeded signs, you may consider to add some more replacings e.g. € with Euro or евро
+    $text = str_replace(array("1+1","$","€","%","/","\\"),array("1plus1"," Dollar"," Euro"," Prozent"," "," "),$text);
+// Remove all unneeded symbols ...
+    $text = preg_replace("/[\p{P}\p{No}\p{Nl}\p{M}\p{C}\p{S}]/u","-",$text);
+// Collapse spaces, minuses, (back-)slashes and non-words
+    $text = preg_replace('/[\s\-\/\\\\]+/', '-', $text);
+// Trim url string
+    $text = trim($text,"-");
+// Remove small words
+//    $text = preg_replace("/(^|-)[\p{Ll}\p{Lu}\p{Lt}\p{Lo}]{1,2}(?=-|$)/u","", $text);
+
+$text = trim(preg_replace("/(^|-)(([\p{Ll}\p{Lu}\p{Lt}\p{Lo}]{1,3})(?<!new|wer|wen|wie|was|wo|wem|how|who|zug|uni|job|gps|bus|tod|tot|eko|öko|eu|dai|gai|hiv|df|ing|ua|upa|oun|omv|otp|ss|umc|twi|tvi|usa|uno|bio|see|kuh|fuß|not|kot|tür|sex|uhu|rat|dvd|cd|tau|rot|tor|tat|bit|sau|ehe|gut|mfg|ard|zdf|rtl|mdr|tee|uhr|zoo|zeh|rss|xml|pdf|axt|fan|nuß|neu|fkk|aal|bug|ost|alt|rom|ddr|fdj|sed|kgb|fbi|cia|sbu|ohr|age|ece|bip|mts|gus|ntn|cme|ntn|iwf|wto|scm|man|uah|eon|nbu|obi|tv|isd|ilo|akw|who|ooo|stb|gas|em))(?=-|$)/ui","", $text),"-");
+// Remove all non-whitelisted characters
+    $text = preg_replace("/[^\p{Ll}\p{Lu}\p{Lt}\p{Lo}\p{Nd}\-_]/u","",$text);
+    $text = trim(mb_strtolower($text),'-');
+    return $text;
+}
+
+function update_urls() {
+$rs = safe_rows('Title','textpattern','1=1');
+foreach($rs as $a)
+safe_update('textpattern',"url_title='".sanitizeForUrl($a['Title'])."'","Title='".doSlash($a['Title'])."'");
+
+}
+
+# --- END PLUGIN CODE ---
+
+?>

zem_tpl.php

@@ -0,0 +1,77 @@
+<?php
+
+// Either copy classTextile.php to your plugin directory, or uncomment the following
+// line and edit it to give the location where classTextile.php can be found
+#ini_set('include_path', ini_get('include_path') . ':/full/path/to/textile');
+
+if (empty($test)) {
+	echo compile_plugin();
+	exit;
+}
+
+// -----------------------------------------------------
+
+function extract_section($lines, $section) {
+	$result = "";
+	
+	$start_delim = "# --- BEGIN PLUGIN $section ---";
+	$end_delim = "# --- END PLUGIN $section ---";
+
+	$start = array_search($start_delim, $lines) + 1;
+	$end = array_search($end_delim, $lines);
+
+	$content = array_slice($lines, $start, $end-$start);
+
+	return join("\n", $content);
+
+}
+
+function compile_plugin($file='') {
+	global $plugin;
+
+	if (empty($file))
+		$file = $_SERVER['SCRIPT_FILENAME'];
+
+	if (!isset($plugin['name'])) {
+		$plugin['name'] = basename($file, '.php');
+	}
+
+	# Read the contents of this file, and strip line ends
+	$content = file($file);
+	for ($i=0; $i < count($content); $i++) {
+		$content[$i] = rtrim($content[$i]);
+	}
+
+	$plugin['help'] = extract_section($content, 'HELP');
+	$plugin['code'] = extract_section($content, 'CODE');
+
+	@include('classTextile.php');
+	if (class_exists('Textile')) {
+		$textile = new Textile();
+		$plugin['help'] = $textile->TextileThis($plugin['help']);
+	}
+
+	$plugin['md5'] = md5( $plugin['code'] );
+
+	// to produce a copy of the plugin for distribution, load this file in a browser. 
+
+	header('Content-type: text/plain');
+	$header = <<<EOF
+# {$plugin['name']} v{$plugin['version']}
+# {$plugin['description']}
+# {$plugin['author']}
+# {$plugin['author_uri']}
+
+# ......................................................................
+# This is a plugin for Textpattern - http://textpattern.com/
+# To install: textpattern > admin > plugins
+# Paste the following text into the 'Install plugin' box:
+# ......................................................................
+EOF;
+
+	return $header . "\n\n" . trim(chunk_split(base64_encode(serialize($plugin)), 72)). "\n";
+
+}
+
+
+?>