Skip to content

Improve transliteration filter #33060

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: 2.4-develop
Choose a base branch
from
Open

Improve transliteration filter #33060

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
220 changes: 219 additions & 1 deletion lib/internal/Magento/Framework/Filter/Test/Unit/TranslitTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,211 @@ class TranslitTest extends TestCase
*/
protected $model;

/**
* @var string[]
*/
protected $automatedConversions = [
'À' => 'a',
'Á' => 'a',
'Â' => 'a',
'Ä' => 'a',
'Å' => 'a',
'Ç' => 'c',
'È' => 'e',
'É' => 'e',
'Ë' => 'e',
'Ì' => 'i',
'Í' => 'i',
'Î' => 'i',
'Ï' => 'i',
'Ò' => 'o',
'Ó' => 'o',
'Ô' => 'o',
'Õ' => 'o',
'Ö' => 'o',
'Ù' => 'u',
'Ú' => 'u',
'Û' => 'u',
'Ü' => 'u',
'Ý' => 'y',
'à' => 'a',
'á' => 'a',
'â' => 'a',
'ä' => 'a',
'å' => 'a',
'ç' => 'c',
'è' => 'e',
'é' => 'e',
'ê' => 'e',
'ë' => 'e',
'ì' => 'i',
'í' => 'i',
'î' => 'i',
'ï' => 'i',
'ò' => 'o',
'ó' => 'o',
'ô' => 'o',
'õ' => 'o',
'ö' => 'o',
'ù' => 'u',
'ú' => 'u',
'û' => 'u',
'ü' => 'u',
'ý' => 'y',
'ÿ' => 'y',
'Ā' => 'a',
'ā' => 'a',
'Ă' => 'a',
'ă' => 'a',
'Ą' => 'a',
'ą' => 'a',
'Ć' => 'c',
'ć' => 'c',
'Ĉ' => 'c',
'ĉ' => 'c',
'Ċ' => 'c',
'ċ' => 'c',
'Č' => 'c',
'č' => 'c',
'Ď' => 'd',
'ď' => 'd',
'Ē' => 'e',
'ē' => 'e',
'Ĕ' => 'e',
'ĕ' => 'e',
'Ė' => 'e',
'ė' => 'e',
'Ę' => 'e',
'ę' => 'e',
'Ě' => 'e',
'ě' => 'e',
'Ĝ' => 'g',
'ĝ' => 'g',
'Ğ' => 'g',
'ğ' => 'g',
'Ġ' => 'g',
'ġ' => 'g',
'Ģ' => 'g',
'ģ' => 'g',
'Ĥ' => 'h',
'ĥ' => 'h',
'Ĩ' => 'i',
'ĩ' => 'i',
'Ī' => 'i',
'ī' => 'i',
'Ĭ' => 'i',
'ĭ' => 'i',
'Į' => 'i',
'į' => 'i',
'İ' => 'i',
'Ĵ' => 'j',
'ĵ' => 'j',
'Ķ' => 'k',
'ķ' => 'k',
'Ĺ' => 'l',
'ĺ' => 'l',
'Ļ' => 'l',
'ļ' => 'l',
'Ľ' => 'l',
'ľ' => 'l',
'Ń' => 'n',
'ń' => 'n',
'Ņ' => 'n',
'ņ' => 'n',
'Ň' => 'n',
'ň' => 'n',
'Ō' => 'o',
'ō' => 'o',
'Ŏ' => 'o',
'ŏ' => 'o',
'Ő' => 'o',
'ő' => 'o',
'Ŕ' => 'r',
'ŕ' => 'r',
'Ŗ' => 'r',
'ŗ' => 'r',
'Ř' => 'r',
'ř' => 'r',
'Ś' => 's',
'ś' => 's',
'Ŝ' => 's',
'ŝ' => 's',
'Ş' => 's',
'ş' => 's',
'Š' => 's',
'š' => 's',
'Ţ' => 't',
'ţ' => 't',
'Ť' => 't',
'ť' => 't',
'Ũ' => 'u',
'ũ' => 'u',
'Ū' => 'u',
'ū' => 'u',
'Ŭ' => 'u',
'ŭ' => 'u',
'Ů' => 'u',
'ů' => 'u',
'Ű' => 'u',
'ű' => 'u',
'Ų' => 'u',
'ų' => 'u',
'Ŵ' => 'w',
'ŵ' => 'w',
'Ŷ' => 'y',
'ŷ' => 'y',
'Ÿ' => 'y',
'Ź' => 'z',
'ź' => 'z',
'Ż' => 'z',
'ż' => 'z',
'Ž' => 'z',
'ž' => 'z',
'Ơ' => 'o',
'ơ' => 'o',
'Ư' => 'u',
'ư' => 'u',
'Ǎ' => 'a',
'ǎ' => 'a',
'Ǐ' => 'i',
'ǐ' => 'i',
'Ǒ' => 'o',
'ǒ' => 'o',
'Ǔ' => 'u',
'ǔ' => 'u',
'Ǖ' => 'u',
'ǖ' => 'u',
'Ǘ' => 'u',
'ǘ' => 'u',
'Ǚ' => 'u',
'ǚ' => 'u',
'Ǜ' => 'u',
'ǜ' => 'u',
'Ǻ' => 'a',
'ǻ' => 'a',
'Ǽ' => 'ae',
'ǽ' => 'ae',
'Ǿ' => 'o',
'ǿ' => 'o',
'Ї' => 'i',
'ї' => 'i',
'ά' => 'a',
'Ά' => 'a',
'έ' => 'e',
'Έ' => 'e',
'ή' => 'i',
'ί' => 'i',
'ϊ' => 'i',
'ΐ' => 'i',
'Ί' => 'i',
'ό' => 'o',
'Ό' => 'o',
'ύ' => 'u',
'Ύ' => 'y',
'ώ' => 'o',
'Ώ' => 'o',
];

protected function setUp(): void
{
$objectManager = new ObjectManager($this);
Expand Down Expand Up @@ -47,7 +252,8 @@ public function testFilter($testString, $result, $resultIconv, $isIconv)
public function filterDataProvider()
{
$isIconv = '"libiconv"' == ICONV_IMPL;
return [

$data = [
['test', 'test', 'test', $isIconv],
['привет мир', 'privet mir', 'privet mir', $isIconv],
[
Expand All @@ -56,6 +262,12 @@ public function filterDataProvider()
'Weiss, Goldmann, Gobel, Weiss, Gothe, Goethe und Gotz',
$isIconv
],
[
'Brasília, português, Hà Nội, tiếng Việt, Москва, русский язык',
'Brasilia, portugues, Ha Noi, tieng Viet, moskva, russkij jazyk',
'Brasilia, portugues, Ha Noi, tieng Viet, moskva, russkij jazyk',
$isIconv
],
[
'❤ ☀ ☆ ☂ ☻ ♞ ☯ ☭ ☢ € → ☎ ❄ ♫ ✂ ▷ ✇ ♎ ⇧ ☮',
'❤ ☀ ☆ ☂ ☻ ♞ ☯ ☭ ☢ € → ☎ ❄ ♫ ✂ ▷ ✇ ♎ ⇧ ☮',
Expand All @@ -65,6 +277,12 @@ public function filterDataProvider()
['™', 'tm', 'tm', $isIconv],
['লক্ষ্য এনালগ ওয়াচ টি ২০', 'laksoa enaalaga oyaoaca tai 20', 'laksoa enaalaga oyaoaca tai 20', $isIconv]
];

foreach ($this->automatedConversions as $from => $to) {
$data[] = [ $from, $to, $to, $isIconv ];
}

return $data;
}

public function testFilterConfigured()
Expand Down
Loading