Merge pull request #336 from yankl/yiddish

Add Yiddish language ruleset
cocur · Dec 25, 2023 · 8672df7 · 8672df7
2 parents af14505 + c0ada2d
commit 8672df7
Show file tree

Hide file tree

Showing 5 changed files with 108 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -17,7 +17,7 @@ Developed by [Florian Eckerstorfer](https://florian.ec) in Vienna, Europe with t
 ## Features
 
 -   Removes all special characters from a string.
--   Provides custom replacements for Arabic, Austrian, Azerbaijani, Brazilian Portuguese, Bulgarian, Burmese, Chinese, Croatian, Czech, Esperanto, Estonian, Finnish, French, Georgian, German, Greek, Hindi, Hungarian, Italian, Latvian, Lithuanian, Macedonian, Norwegian, Polish, Romanian, Russian, Serbian, Spanish, Swedish, Turkish, Ukrainian and Vietnamese special characters. Instead of removing these characters, Slugify approximates them (e.g., `ae` replaces `ä`).
+-   Provides custom replacements for Arabic, Austrian, Azerbaijani, Brazilian Portuguese, Bulgarian, Burmese, Chinese, Croatian, Czech, Esperanto, Estonian, Finnish, French, Georgian, German, Greek, Hindi, Hungarian, Italian, Latvian, Lithuanian, Macedonian, Norwegian, Polish, Romanian, Russian, Serbian, Spanish, Swedish, Turkish, Ukrainian, Vietnamese and Yiddish special characters. Instead of removing these characters, Slugify approximates them (e.g., `ae` replaces `ä`).
 -   No external dependencies.
 -   PSR-4 compatible.
 -   Compatible with PHP >= 8.

diff --git a/Resources/rules/yiddish.json b/Resources/rules/yiddish.json
@@ -0,0 +1,52 @@
+{
+    "יאַ": "ya",
+    "אַ": "a",
+    "אָ": "o",
+    "יאָ": "yo",
+    "א": "",
+    "בֿ": "v",
+    "ב": "b",
+    "ג": "g",
+    "ד": "d",
+    "ה": "h",
+    "װ": "v",
+    "וו": "v",
+    "יױ": "yoy",
+    "ױ": "oy",
+    "יוי": "yoy",
+    "וי": "oy",
+    "יו": "yu",
+    "ו": "u",
+    "ז": "z",
+    "ח": "kh",
+    "ט": "t",
+    "יײַ": "yay",
+    "ײַ": "ay",
+    "יי": "ey",
+    "ײ": "ey",
+    "יע": "ye",
+    "ייִ": "yi",
+    "יִ": "i",
+    "י": "i",
+    "כּ": "k",
+    "כ": "kh",
+    "ך": "kh",
+    "ל": "l",
+    "מ": "m",
+    "ם": "m",
+    "נ": "n",
+    "ן": "n",
+    "ס": "s",
+    "ע": "e",
+    "פּ": "p",
+    "פֿ": "f",
+    "פ": "ph",
+    "צ": "ts",
+    "ץ": "ts",
+    "ק": "k",
+    "ר": "r",
+    "שֹ": "s",
+    "ש": "sh",
+    "תּ": "t",
+    "ת": "s"
+}
diff --git a/src/RuleProvider/DefaultRuleProvider.php b/src/RuleProvider/DefaultRuleProvider.php
@@ -10896,6 +10896,59 @@ class DefaultRuleProvider implements RuleProviderInterface
     'Ỷ' => 'Y',
     'Ỹ' => 'Y',
   ),
+  'yiddish' => 
+  array (
+    'יאַ' => 'ya',
+    'אַ' => 'a',
+    'אָ' => 'o',
+    'יאָ' => 'yo',
+    'א' => '',
+    'בֿ' => 'v',
+    'ב' => 'b',
+    'ג' => 'g',
+    'ד' => 'd',
+    'ה' => 'h',
+    'װ' => 'v',
+    'וו' => 'v',
+    'יױ' => 'yoy',
+    'ױ' => 'oy',
+    'יוי' => 'yoy',
+    'וי' => 'oy',
+    'יו' => 'yu',
+    'ו' => 'u',
+    'ז' => 'z',
+    'ח' => 'kh',
+    'ט' => 't',
+    'יײַ' => 'yay',
+    'ײַ' => 'ay',
+    'יי' => 'ey',
+    'ײ' => 'ey',
+    'יע' => 'ye',
+    'ייִ' => 'yi',
+    'יִ' => 'i',
+    'י' => 'i',
+    'כּ' => 'k',
+    'כ' => 'kh',
+    'ך' => 'kh',
+    'ל' => 'l',
+    'מ' => 'm',
+    'ם' => 'm',
+    'נ' => 'n',
+    'ן' => 'n',
+    'ס' => 's',
+    'ע' => 'e',
+    'פּ' => 'p',
+    'פֿ' => 'f',
+    'פ' => 'ph',
+    'צ' => 'ts',
+    'ץ' => 'ts',
+    'ק' => 'k',
+    'ר' => 'r',
+    'שֹ' => 's',
+    'ש' => 'sh',
+    'תּ' => 't',
+    'ת' => 's',
+  ),
 )/*INSERT_END*/;
 
     /**

diff --git a/src/Slugify.php b/src/Slugify.php
@@ -53,6 +53,7 @@ class Slugify implements SlugifyInterface
             // Languages are preferred if they appear later, list is ordered by number of
             // websites in that language
             // https://en.wikipedia.org/wiki/Languages_used_on_the_Internet#Content_languages_for_websites
+            'yiddish',
             'armenian',
             'azerbaijani',
             'burmese',

diff --git a/tests/SlugifyTest.php b/tests/SlugifyTest.php
@@ -260,6 +260,7 @@ public function defaultRuleProvider()
             [str_repeat('hi🇦🇹', 5000), substr(str_repeat('hi-', 5000), 0, -1)],
             ['Č Ć Ž Š Đ č ć ž š đ', 'c-c-z-s-d-c-c-z-s-d'],
             ['Ą Č Ę Ė Į Š Ų Ū Ž ą č ę ė į š ų ū ž', 'a-c-e-e-i-s-u-u-z-a-c-e-e-i-s-u-u-z'],
+            ['יאַן אַ טאָן יאָ אי רבֿ גיב דו האַװ האַוו יױרן יוירן אַזױ אַזוי יום־כּיפּור חנוכּה יײַכל מײַן בלײך ניי יע ייִדיש פֿליִען צוך סם פ קץ תּורת־אמת', 'yan-a-ton-yo-i-rv-gib-du-hav-hav-yoyrn-yoyrn-azoy-azoy-yum-kipur-khnukh-yaykhl-mayn-bleykh-ney-ye-yidish-flien-tsukh-sm-ph-kts-turs-ms'],
         ];
     }