Added urlify to try and create webbie auto-suggestions out of whatever unicode stuff gets thrown in as a name. Currently this will only work for latin/european/cyrillic/russian, but possible to extend to ideographic forms.

This commit is contained in:
friendica 2012-07-30 18:51:44 -07:00
parent 194c52aee5
commit 02cc436ec7
12 changed files with 347 additions and 3 deletions

3
library/urlify/.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
vendor
composer.phar
composer.lock

10
library/urlify/INSTALL Normal file
View File

@ -0,0 +1,10 @@
To install URLify, you can add it as a dependency ar by downloading the composer.phar executable.
$ curl -s http://getcomposer.org/installer | php
and run install
$ php composer.phar install
For more details, see http://getcomposer.org.

70
library/urlify/README.md Normal file
View File

@ -0,0 +1,70 @@
# URLify for PHP
A PHP port of [URLify.js](https://github.com/django/django/blob/master/django/contrib/admin/static/admin/js/urlify.js)
from the Django project. Handles symbols from Latin languages, Greek, Turkish,
Russian, Ukrainian, Czech, Polish, and Latvian. Symbols it cannot transliterate
it will simply omit.
* Author: [jbroadway](http://github.com/jbroadway)
* License: MIT
## Usage:
To generate slugs for URLs:
```php
<?php
echo URLify::filter (' J\'étudie le français ');
// "jetudie-le-francais"
echo URLify::filter ('Lo siento, no hablo español.');
// "lo-siento-no-hablo-espanol"
?>
```
To simply transliterate characters:
```php
<?php
echo URLify::downcode ('J\'étudie le français');
// "J'etudie le francais"
echo URLify::downcode ('Lo siento, no hablo español.');
// "Lo siento, no hablo espanol."
/* Or use transliterate() alias: */
echo URLify::transliterate ('Lo siento, no hablo español.');
// "Lo siento, no hablo espanol."
?>
```
To extend the character list:
```php
<?php
URLify::add_chars (array (
'¿' => '?', '®' => '(r)', '¼' => '1/4',
'¼' => '1/2', '¾' => '3/4', '¶' => 'P'
));
echo URLify::downcode ('¿ ® ¼ ¼ ¾ ¶');
// "? (r) 1/2 1/2 3/4 P"
?>
```
To extend the list of words to remove:
```php
<?php
URLify::remove_words (array ('remove', 'these', 'too'));
?>
```

188
library/urlify/URLify.php Normal file
View File

@ -0,0 +1,188 @@
<?php
/**
* A PHP port of URLify.js from the Django project
* (https://github.com/django/django/blob/master/django/contrib/admin/static/admin/js/urlify.js).
* Handles symbols from Latin languages, Greek, Turkish, Russian, Ukrainian,
* Czech, Polish, and Latvian. Symbols it cannot transliterate
* it will simply omit.
*
* Usage:
*
* echo URLify::filter (' J\'étudie le français ');
* // "jetudie-le-francais"
*
* echo URLify::filter ('Lo siento, no hablo español.');
* // "lo-siento-no-hablo-espanol"
*/
class URLify {
public static $maps = array (
'latin_map' => array (
'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', 'Æ' => 'AE', 'Ç' =>
'C', 'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I',
'Ï' => 'I', 'Ð' => 'D', 'Ñ' => 'N', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' =>
'O', 'Ő' => 'O', 'Ø' => 'O', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'Ű' => 'U',
'Ý' => 'Y', 'Þ' => 'TH', 'ß' => 'ss', 'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' =>
'a', 'å' => 'a', 'æ' => 'ae', 'ç' => 'c', 'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e',
'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'ð' => 'd', 'ñ' => 'n', 'ò' => 'o', 'ó' =>
'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o', 'ő' => 'o', 'ø' => 'o', 'ù' => 'u', 'ú' => 'u',
'û' => 'u', 'ü' => 'u', 'ű' => 'u', 'ý' => 'y', 'þ' => 'th', 'ÿ' => 'y'
),
'latin_symbols_map' => array (
'©' => '(c)'
),
'greek_map' => array (
'α' => 'a', 'β' => 'b', 'γ' => 'g', 'δ' => 'd', 'ε' => 'e', 'ζ' => 'z', 'η' => 'h', 'θ' => '8',
'ι' => 'i', 'κ' => 'k', 'λ' => 'l', 'μ' => 'm', 'ν' => 'n', 'ξ' => '3', 'ο' => 'o', 'π' => 'p',
'ρ' => 'r', 'σ' => 's', 'τ' => 't', 'υ' => 'y', 'φ' => 'f', 'χ' => 'x', 'ψ' => 'ps', 'ω' => 'w',
'ά' => 'a', 'έ' => 'e', 'ί' => 'i', 'ό' => 'o', 'ύ' => 'y', 'ή' => 'h', 'ώ' => 'w', 'ς' => 's',
'ϊ' => 'i', 'ΰ' => 'y', 'ϋ' => 'y', 'ΐ' => 'i',
'Α' => 'A', 'Β' => 'B', 'Γ' => 'G', 'Δ' => 'D', 'Ε' => 'E', 'Ζ' => 'Z', 'Η' => 'H', 'Θ' => '8',
'Ι' => 'I', 'Κ' => 'K', 'Λ' => 'L', 'Μ' => 'M', 'Ν' => 'N', 'Ξ' => '3', 'Ο' => 'O', 'Π' => 'P',
'Ρ' => 'R', 'Σ' => 'S', 'Τ' => 'T', 'Υ' => 'Y', 'Φ' => 'F', 'Χ' => 'X', 'Ψ' => 'PS', 'Ω' => 'W',
'Ά' => 'A', 'Έ' => 'E', 'Ί' => 'I', 'Ό' => 'O', 'Ύ' => 'Y', 'Ή' => 'H', 'Ώ' => 'W', 'Ϊ' => 'I',
'Ϋ' => 'Y'
),
'turkish_map' => array (
'ş' => 's', 'Ş' => 'S', 'ı' => 'i', 'İ' => 'I', 'ç' => 'c', 'Ç' => 'C', 'ü' => 'u', 'Ü' => 'U',
'ö' => 'o', 'Ö' => 'O', 'ğ' => 'g', 'Ğ' => 'G'
),
'russian_map' => array (
'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd', 'е' => 'e', 'ё' => 'yo', 'ж' => 'zh',
'з' => 'z', 'и' => 'i', 'й' => 'j', 'к' => 'k', 'л' => 'l', 'м' => 'm', 'н' => 'n', 'о' => 'o',
'п' => 'p', 'р' => 'r', 'с' => 's', 'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'h', 'ц' => 'c',
'ч' => 'ch', 'ш' => 'sh', 'щ' => 'sh', 'ъ' => '', 'ы' => 'y', 'ь' => '', 'э' => 'e', 'ю' => 'yu',
'я' => 'ya',
'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', 'Е' => 'E', 'Ё' => 'Yo', 'Ж' => 'Zh',
'З' => 'Z', 'И' => 'I', 'Й' => 'J', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N', 'О' => 'O',
'П' => 'P', 'Р' => 'R', 'С' => 'S', 'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'H', 'Ц' => 'C',
'Ч' => 'Ch', 'Ш' => 'Sh', 'Щ' => 'Sh', 'Ъ' => '', 'Ы' => 'Y', 'Ь' => '', 'Э' => 'E', 'Ю' => 'Yu',
'Я' => 'Ya'
),
'ukrainian_map' => array (
'Є' => 'Ye', 'І' => 'I', 'Ї' => 'Yi', 'Ґ' => 'G', 'є' => 'ye', 'і' => 'i', 'ї' => 'yi', 'ґ' => 'g'
),
'czech_map' => array (
'č' => 'c', 'ď' => 'd', 'ě' => 'e', 'ň' => 'n', 'ř' => 'r', 'š' => 's', 'ť' => 't', 'ů' => 'u',
'ž' => 'z', 'Č' => 'C', 'Ď' => 'D', 'Ě' => 'E', 'Ň' => 'N', 'Ř' => 'R', 'Š' => 'S', 'Ť' => 'T',
'Ů' => 'U', 'Ž' => 'Z'
),
'polish_map' => array (
'ą' => 'a', 'ć' => 'c', 'ę' => 'e', 'ł' => 'l', 'ń' => 'n', 'ó' => 'o', 'ś' => 's', 'ź' => 'z',
'ż' => 'z', 'Ą' => 'A', 'Ć' => 'C', 'Ę' => 'e', 'Ł' => 'L', 'Ń' => 'N', 'Ó' => 'O', 'Ś' => 'S',
'Ź' => 'Z', 'Ż' => 'Z'
),
'latvian_map' => array (
'ā' => 'a', 'č' => 'c', 'ē' => 'e', 'ģ' => 'g', 'ī' => 'i', 'ķ' => 'k', 'ļ' => 'l', 'ņ' => 'n',
'š' => 's', 'ū' => 'u', 'ž' => 'z', 'Ā' => 'A', 'Č' => 'C', 'Ē' => 'E', 'Ģ' => 'G', 'Ī' => 'i',
'Ķ' => 'k', 'Ļ' => 'L', 'Ņ' => 'N', 'Š' => 'S', 'Ū' => 'u', 'Ž' => 'Z'
)
);
/**
* List of words to remove from URLs.
*/
public static $remove_list = array (
'a', 'an', 'as', 'at', 'before', 'but', 'by', 'for', 'from',
'is', 'in', 'into', 'like', 'of', 'off', 'on', 'onto', 'per',
'since', 'than', 'the', 'this', 'that', 'to', 'up', 'via',
'with'
);
/**
* The character map.
*/
private static $map = array ();
/**
* The character list as a string.
*/
private static $chars = '';
/**
* The character list as a regular expression.
*/
private static $regex = '';
/**
* Initializes the character map.
*/
private static function init () {
if (count (self::$map) > 0) {
return;
}
foreach (self::$maps as $map) {
foreach ($map as $orig => $conv) {
self::$map[$orig] = $conv;
self::$chars .= $orig;
}
}
self::$regex = '/[' . self::$chars . ']/u';
}
/**
* Add new characters to the list. `$map` should be a hash.
*/
public static function add_chars ($map) {
if (! is_array ($map)) {
throw new LogicException ('$map must be an associative array.');
}
self::$maps[] = $map;
self::$map = array ();
self::$chars = '';
}
/**
* Append words to the remove list. Accepts either single words
* or an array of words.
*/
public static function remove_words ($words) {
$words = is_array ($words) ? $words : array ($words);
self::$remove_list = array_merge (self::$remove_list, $words);
}
/**
* Transliterates characters to their ASCII equivalents.
*/
public static function downcode ($text) {
self::init ();
if (preg_match_all (self::$regex, $text, $matches)) {
for ($i = 0; $i < count ($matches[0]); $i++) {
$char = $matches[0][$i];
if (isset (self::$map[$char])) {
$text = str_replace ($char, self::$map[$char], $text);
}
}
}
return $text;
}
/**
* Filters a string, e.g., "Petty theft" to "petty-theft"
*/
public static function filter ($text, $length = 60) {
$text = self::downcode ($text);
// remove all these words from the string before urlifying
$text = preg_replace ('/\b(' . join ('|', self::$remove_list) . ')\b/i', '', $text);
// if downcode doesn't hit, the char will be stripped here
$text = preg_replace ('/[^-\w\s]/', '', $text); // remove unneeded chars
$text = preg_replace ('/^\s+|\s+$/', '', $text); // trim leading/trailing spaces
$text = preg_replace ('/[-\s]+/', '-', $text); // convert spaces to hyphens
$text = strtolower ($text); // convert to lowercase
return trim (substr ($text, 0, $length), '-'); // trim to first $length chars
}
/**
* Alias of `URLify::downcode()`.
*/
public static function transliterate ($text) {
return self::downcode ($text);
}
}
?>

View File

@ -0,0 +1,21 @@
{
"name": "jbroadway/urlify",
"type": "library",
"description": "PHP port of URLify.js from the Django project. Transliterates non-ascii characters for use in URLs.",
"keywords": ["urlify","transliterate","translit","transliteration","url","encode","slug","link","iconv"],
"homepage": "https://github.com/jbroadway/urlify",
"license": "MIT",
"authors": [
{
"name": "Johnny Broadway",
"email": "johnny@johnnybroadway.com",
"homepage": "http://www.johnnybroadway.com/"
}
],
"require": {
"php": ">=5.3.0"
},
"autoload": {
"psr-0": { "URLify": "" }
}
}

View File

@ -0,0 +1,31 @@
<?php
class URLifyTest extends PHPUnit_Framework_TestCase {
function test_downcode () {
$this->assertEquals (' J\'etudie le francais ', URLify::downcode (' J\'étudie le français '));
$this->assertEquals ('Lo siento, no hablo espanol.', URLify::downcode ('Lo siento, no hablo español.'));
$this->assertEquals ('F3PWS', URLify::downcode ('ΦΞΠΏΣ'));
}
function test_filter () {
$this->assertEquals ('jetudie-le-francais', URLify::filter (' J\'étudie le français '));
$this->assertEquals ('lo-siento-no-hablo-espanol', URLify::filter ('Lo siento, no hablo español.'));
$this->assertEquals ('f3pws', URLify::filter ('ΦΞΠΏΣ'));
}
function test_add_chars () {
$this->assertEquals ('¿ ® ¼ ¼ ¾ ¶', URLify::downcode ('¿ ® ¼ ¼ ¾ ¶'));
URLify::add_chars (array (
'¿' => '?', '®' => '(r)', '¼' => '1/4',
'¼' => '1/2', '¾' => '3/4', '¶' => 'P'
));
$this->assertEquals ('? (r) 1/2 1/2 3/4 P', URLify::downcode ('¿ ® ¼ ¼ ¾ ¶'));
}
function test_remove_words () {
$this->assertEquals ('foo-bar', URLify::filter ('foo bar'));
URLify::remove_words (array ('foo', 'bar'));
$this->assertEquals ('', URLify::filter ('foo bar'));
}
}
?>

View File

@ -0,0 +1,9 @@
<?php
set_error_handler(function () {
echo file_get_contents(dirname(__DIR__).'/INSTALL');
exit(1);
}, E_ALL);
require_once dirname(__DIR__) . '/vendor/autoload.php';
restore_error_handler();

View File

@ -0,0 +1,8 @@
<phpunit bootstrap="bootstrap.php">
<testsuite name="URLify Test Suite">
<directory>.</directory>
</testsuite>
<logging>
<log type="coverage-text" target="php://stdout" showUncoveredFiles="false"/>
</logging>
</phpunit>

View File

@ -127,7 +127,7 @@ EOT;
}
else {
$r = q("SELECT `id` FROM `item` WHERE `id` = '%s' OR `uri` = '%s' LIMIT 1",
$r = q("SELECT `id`,`deleted` FROM `item` WHERE `id` = '%s' OR `uri` = '%s' LIMIT 1",
dbesc($item_id),
dbesc($item_id)
);

View File

@ -737,6 +737,10 @@ msgstr ""
msgid "Example: bob@example.com, mary@example.com"
msgstr ""
#: ../../mod/editpost.php:135 ../../include/conversation.php:1166
msgid "Friendica mobile web"
msgstr ""
#: ../../mod/dfrn_request.php:93
msgid "This introduction has already been accepted."
msgstr ""

View File

@ -1 +1 @@
2012-07-29.30
2012-07-30.31

View File

@ -5,6 +5,6 @@
{{ for $events as $event }}
<div class="event-list" id="event-$event.id"></a> <a href="events/$event.link">$event.title</a> $event.date </div>
{{ endfor }}
</div></div>
</div>
{{ endif }}