Sort language YAML file alphabetically (#303)

.github/workflows/php.yml

@@ -23,5 +23,13 @@ jobs:
       - name: Running phpcs
         run: composer run-script cs
 
+      # The yaml-sort-checker library requires PHP 8.1 or higher,
+      # but we want to support older PHP versions,
+      # so we install the library here
+      # and not using composer.json
+      - name: Running yaml-sort-checker
+        if: ${{ matrix.php >= '8.1' }}
+        run: composer run-script yaml-sort-check
+
       - name: Run tests
         run: php ./vendor/bin/phpunit

composer.json

@@ -50,6 +50,7 @@
 	"scripts": {
 		"fix": "phpcbf",
 		"cs": "phpcs -sp",
+		"yaml-sort-check": "composer require mhujer/yaml-sort-checker; yaml-sort-checker",
 		"test": [
 			"@composer validate --no-interaction",
 			"phpunit",

data/langdb.yaml

@@ -28,8 +28,8 @@ languages:
   ale: [Latn, [AM, AS], unangam tunuu]
   ale-cyrl: [Cyrl, [AS], унаӈам тунуу]
   aln: [Latn, [EU], Gegë]
-  alt: [Cyrl, [EU, AS], алтай тил]
   als: [sq]
+  alt: [Cyrl, [EU, AS], алтай тил]
   am: [Ethi, [AF], አማርኛ]
   ami: [Latn, [AS], Pangcah]
   an: [Latn, [EU], aragonés]
@@ -64,8 +64,8 @@ languages:
  # CLDR uses az-latn and az-arab.
   az: [az-latn]
   az-arab: [Arab, [AS, ME], تۆرکجه]
-  az-latn: [Latn, [EU, ME], azərbaycanca]
   az-cyrl: [Cyrl, [EU, ME], азәрбајҹанҹа]
+  az-latn: [Latn, [EU, ME], azərbaycanca]
   azb: [az-arab]
   azj: [az-latn]
   ba: [Cyrl, [EU], башҡортса]
@@ -76,21 +76,21 @@ languages:
   bar: [Latn, [EU], Boarisch]
   bas: [Latn, [AF], ɓasaá]
   bat-smg: [sgs]
-  bbc-latn: [Latn, [AS], Batak Toba]
-  bbc-batk: [Batk, [AS], ᯅᯖᯂ᯲ ᯖᯬᯅ]
   bbc: [bbc-latn]
+  bbc-batk: [Batk, [AS], ᯅᯖᯂ᯲ ᯖᯬᯅ]
+  bbc-latn: [Latn, [AS], Batak Toba]
   bcc: [Arab, [AS, ME], جهلسری بلوچی]
   bci: [Latn, [AF], wawle]
   bcl: [Latn, [AS], Bikol Central]
   bdr: [Latn, [AS], Bajau Sama]
+  be: [Cyrl, [EU], беларуская]
   be-tarask: [Cyrl, [EU], беларуская (тарашкевіца)]
   be-x-old: [be-tarask]
-  be: [Cyrl, [EU], беларуская]
   bem: [Latn, [AF], IciBemba]
   bew: [Latn, [AS], Betawi]
   bfa: [Latn, [AF], Bari]
-  bft: [Arab, [AS], بلتی]
   bfq: [Taml, [AS], படகா]
+  bft: [Arab, [AS], بلتی]
   bg: [Cyrl, [EU], български]
   bgc: [Deva, [AS], हरियाणवी]
   bgn: [Arab, [AS, ME], روچ کپتین بلوچی]
@@ -105,8 +105,8 @@ languages:
   bm: [Latn, [AF], bamanankan]
   bn: [Beng, [AS], বাংলা]
   bnn: [Latn, [AS], bunun]
-  bom: [Latn, [AF], bèrom]
   bo: [Tibt, [AS], བོད་ཡིག]
+  bom: [Latn, [AF], bèrom]
   bpy: [Beng, [AS], বিষ্ণুপ্রিয়া মণিপুরী]
   bqi: [Arab, [AS, ME], بختیاری]
   br: [Latn, [EU], brezhoneg]
@@ -131,8 +131,8 @@ languages:
   ccp: [Cakm, [AS], 𑄌𑄋𑄴𑄟𑄳𑄦]
  # FIXME cdo will be modified later to split to Latin and Chinese more cleanly
   cdo: [Latn, [AS], Mìng-dĕ̤ng-ngṳ̄]
-  cdo-latn: [Latn, [AS], Mìng-dĕ̤ng-ngṳ̄ Bàng-uâ-cê]
   cdo-hani: [Hani, [AS], 閩東語（漢字）]
+  cdo-latn: [Latn, [AS], Mìng-dĕ̤ng-ngṳ̄ Bàng-uâ-cê]
   ce: [Cyrl, [EU], нохчийн]
   ceb: [Latn, [AS], Cebuano]
   ch: [Latn, [PA], Chamoru]
@@ -148,12 +148,12 @@ languages:
   chr: [Cher, [AM], ᏣᎳᎩ]
   chy: [Latn, [AM], Tsetsêhestâhese]
   ciw: [Latn, [AM], Anishinaabemowin]
+  cjk: [Latn, [AF], cokwe]
   cjy: [cjy-hant]
   cjy-hans: [Hans, [AS], 晋语（简化字）]
   cjy-hant: [Hant, [AS], 晉語]
   ckb: [Arab, [ME], کوردی]
   ckt: [Cyrl, [AS], ԓыгъоравэтԓьэн]
-  cjk: [Latn, [AF], cokwe]
   cnh: [Latn, [AS], Lai holh]
   cnr: [cnr-latn]
   cnr-cyrl: [Cyrl, [EU], црногорски]
@@ -161,10 +161,10 @@ languages:
   co: [Latn, [EU], corsu]
   cop: [Copt, [AF, ME], ϯⲙⲉⲧⲣⲉⲙⲛ̀ⲭⲏⲙⲓ]
   cps: [Latn, [AS], Capiceño]
+  cpx: [cpx-hant]
   cpx-hans: [Hans, [AS], 莆仙语（简体）]
   cpx-hant: [Hant, [AS], 莆仙語（繁體）]
   cpx-latn: [Latn, [AS], Pó-sing-gṳ̂ (Báⁿ-uā-ci̍)]
-  cpx: [cpx-hant]
   cr: [Cans, [AM], ᓀᐦᐃᔭᐍᐏᐣ]
   cr-cans: [cr]
   cr-latn: [Latn, [AM], Nēhiyawēwin]
@@ -182,10 +182,10 @@ languages:
   dag: [Latn, [AF], dagbanli]
   dar: [Cyrl, [EU], дарган]
   ddn: [Latn, [AF], dendi]
+  de: [Latn, [EU], Deutsch]
   de-at: [Latn, [EU], Österreichisches Deutsch]
   de-ch: [Latn, [EU], Schweizer Hochdeutsch]
   de-formal: [Latn, [EU], Deutsch (Sie-Form)]
-  de: [Latn, [EU], Deutsch]
   dga: [Latn, [AF], Dagaare]
  # In ISO 639, it refers to Rek Dinka. It may
  # be changed like that here, too, but for
@@ -206,15 +206,15 @@ languages:
   el: [Grek, [EU], Ελληνικά]
   elm: [Latn, [AF], Eleme]
   eml: [Latn, [EU], emiliàn e rumagnòl]
+  en: [Latn, [EU, AM, AF, ME, AS, PA, WW], English]
   en-ca: [Latn, [AM], Canadian English]
   en-gb: [Latn, [EU, AS, PA], British English]
   en-simple: [Latn, [WW], Simple English]
   en-us: [Latn, [AM], American English]
-  en: [Latn, [EU, AM, AF, ME, AS, PA, WW], English]
   eo: [Latn, [WW], Esperanto]
+  es: [Latn, [EU, AM, AF, WW, PA], español]
   es-419: [Latn, [AM], español de América Latina]
   es-formal: [Latn, [EU, AM, AF, WW], español (formal)]
-  es: [Latn, [EU, AM, AF, WW, PA], español]
   es-ni: [Latn, [AM], español nicaragüense]
   esu: [Latn, [AM], "Yup'ik"]
   et: [Latn, [EU], eesti]
@@ -250,9 +250,9 @@ languages:
   gaa: [Latn, [AF], Ga]
   gag: [Latn, [EU], Gagauz]
   gah: [Latn, [AS], Alekano]
+  gan: [Hant, [AS], 贛語]
   gan-hans: [Hans, [AS], 赣语（简体）]
   gan-hant: [gan]
-  gan: [Hant, [AS], 贛語]
  # In ISO 639, it refers to West Central Oromo. It may
  # be changed like that here, too, but for
  # now, redirect it to macro Oromo.
@@ -288,10 +288,10 @@ languages:
   ha-latn: [ha]
   hai: [Latn, [AM], X̱aat Kíl]
   hak: [Latn, [AS], Hak-kâ-fa]
-  haw: [Latn, [AM, PA], Hawaiʻi]
-  he: [Hebr, [ME], עברית]
   hak-hans: [Hans, [AS], 客家语（简体）]
   hak-hant: [Hant, [AS], 客家語（繁體）]
+  haw: [Latn, [AM, PA], Hawaiʻi]
+  he: [Hebr, [ME], עברית]
   hi: [Deva, [AS], हिन्दी]
   hif: [Latn, [PA, AS], Fiji Hindi]
   hif-deva: [Deva, [AS], फ़ीजी हिन्दी]
@@ -306,8 +306,8 @@ languages:
   hsb: [Latn, [EU], hornjoserbsce]
   hsn: [Hans, [AS], 湘语]
   ht: [Latn, [AM], Kreyòl ayisyen]
-  hu-formal: [Latn, [EU], Magyar (magázó)]
   hu: [Latn, [EU], magyar]
+  hu-formal: [Latn, [EU], Magyar (magázó)]
   hy: [Armn, [EU, ME], հայերեն]
   hyw: [Armn, [EU, ME], Արեւմտահայերէն]
   hz: [Latn, [AF], Otsiherero]
@@ -345,9 +345,9 @@ languages:
   kab: [Latn, [AF, EU], Taqbaylit]
   kac: [Latn, [AS], Jinghpaw]
   kam: [Latn, [AF], kĩkamba]
+  kbd: [Cyrl, [EU, ME], адыгэбзэ]
   kbd-cyrl: [kbd]
   kbd-latn: [Latn, [EU], Qabardjajəbza]
-  kbd: [Cyrl, [EU, ME], адыгэбзэ]
   kbp: [Latn, [AF], Kabɩyɛ]
   kcg: [Latn, [AF], Tyap]
   kck: [Latn, [AF], tjikalanga]
@@ -379,8 +379,8 @@ languages:
  # now, redirect it to macro Kanuri.
   knc: [kr]
   knn: [Deva, [AS], महाराष्ट्रीय कोंकणी]
-  ko-kp: [Kore, [AS], 조선말]
   ko: [Kore, [AS], 한국어]
+  ko-kp: [Kore, [AS], 조선말]
   koi: [Cyrl, [EU], перем коми]
   koy: [Latn, [AM], "Denaakkenaageʼ"]
   kr: [Latn, [AF], kanuri]
@@ -388,9 +388,9 @@ languages:
   kri: [Latn, [AF], Krio]
   krj: [Latn, [AS], Kinaray-a]
   krl: [Latn, [EU], Karjala]
+  ks: [ks-arab]
   ks-arab: [Arab, [AS], کٲشُر]
   ks-deva: [Deva, [AS], कॉशुर]
-  ks: [ks-arab]
   ksf: [Latn, [AF], Bafia]
   ksh: [Latn, [EU], Ripoarisch]
   ksw: [Mymr, [AS], စှီၤ]
@@ -398,15 +398,15 @@ languages:
   ku: [ku-latn]
   ku-arab: [Arab, [EU, ME], كوردي]
   ku-latn: [Latn, [EU, ME], kurdî]
-  kus: [Latn, [AF], Kʋsaal]
   kum: [Cyrl, [EU], къумукъ]
+  kus: [Latn, [AF], Kʋsaal]
   kv: [Cyrl, [EU], коми]
   kw: [Latn, [EU], kernowek]
   ky: [Cyrl, [AS], кыргызча]
   la: [Latn, [EU], Latina]
   lad: [lad-latn]
-  lad-latn: [Latn, [ME, EU, AM], Ladino]
   lad-hebr: [Hebr, [ME, EU, AM], לאדינו]
+  lad-latn: [Latn, [ME, EU, AM], Ladino]
   lag: [Latn, [AF], Kilaangi]
   lb: [Latn, [EU], Lëtzebuergesch]
   lbe: [Cyrl, [EU], лакку]
@@ -425,8 +425,8 @@ languages:
   ln: [Latn, [AF], lingála]
   lo: [Laoo, [AS], ລາວ]
   loz: [Latn, [AF], Silozi]
-  lt: [Latn, [EU], lietuvių]
   lrc: [Arab, [AS, ME], لۊری شومالی]
+  lt: [Latn, [EU], lietuvių]
   ltg: [Latn, [EU], latgaļu]
   lua: [Latn, [AF], ciluba]
   lud: [Latn, [EU], lüüdi]
@@ -492,16 +492,16 @@ languages:
   nap: [Latn, [EU], Napulitano]
   nb: [Latn, [EU], norsk (bokmål)]
   nd: [Latn, [AF], siNdebele saseNyakatho]
-  nds-nl: [Latn, [EU], Nedersaksisch]
   nds: [Latn, [EU], Plattdüütsch]
+  nds-nl: [Latn, [EU], Nedersaksisch]
   ne: [Deva, [AS], नेपाली]
   new: [Deva, [AS], नेपाल भाषा]
   ng: [Latn, [AF], Oshiwambo]
   nia: [Latn, [AS], Li Niha]
   niu: [Latn, [PA], ko e vagahau Niuē]
   njo: [Latn, [AS], Ao]
-  nl-informal: [Latn, [EU, AM], Nederlands (informeel)]
   nl: [Latn, [EU, AM], Nederlands]
+  nl-informal: [Latn, [EU, AM], Nederlands (informeel)]
   nmz: [Latn, [AF], nawdm]
   nn: [Latn, [EU], norsk (nynorsk)]
   nn-hognorsk: [Latn, [EU], norsk (høgnorsk)]
@@ -568,8 +568,8 @@ languages:
   prg: [Latn, [EU], Prūsiskan]
   prs: [Arab, [AS, ME], دری]
   ps: [Arab, [AS, ME], پښتو]
-  pt-br: [Latn, [AM], português do Brasil]
   pt: [Latn, [EU, AM, AS, PA, AF, WW], português]
+  pt-br: [Latn, [AM], português do Brasil]
   pwn: [Latn, [AS], pinayuanan]
   qu: [Latn, [AM], Runa Simi]
   quc: [Latn, [AM], "K'iche'"]
@@ -631,19 +631,19 @@ languages:
   se-fi: [Latn, [EU], davvisámegiella (Suoma bealde)]
   se-no: [Latn, [EU], davvisámegiella (Norgga bealde)]
   se-se: [Latn, [EU], davvisámegiella (Ruoŧa bealde)]
-  ses: [Latn, [AF], Koyraboro Senni]
   sei: [Latn, [AM], Cmique Itom]
+  ses: [Latn, [AF], Koyraboro Senni]
   sg: [Latn, [AF], Sängö]
   sgs: [Latn, [EU], žemaitėška]
   sh: [Latn, [EU], srpskohrvatski]
   sh-cyrl: [Cyrl, [EU], српскохрватски]
   sh-latn: [sh]
+  shi: [shi-latn]
   shi-latn: [Latn, [AF], Taclḥit]
   shi-tfng: [Tfng, [AF], ⵜⴰⵛⵍⵃⵉⵜ]
-  shi: [shi-latn]
   shn: [Mymr, [AS], လိၵ်ႈတႆး]
-  shy-latn: [Latn, [AF], tacawit]
   shy: [shy-latn]
+  shy-latn: [Latn, [AF], tacawit]
   si: [Sinh, [AS], සිංහල]
   simple: [en-simple]
   sjd: [Cyrl, [EU], кӣллт са̄мь кӣлл]
@@ -651,17 +651,12 @@ languages:
   sjo: [Mong, [AS], ᠰᡞᠪᡝ ᡤᡞᠰᡠᠨ]
   sju: [Latn, [EU], ubmejesámiengiälla]
   sk: [Latn, [EU], slovenčina]
+  skr: [skr-arab]
+  skr-arab: [Arab, [AS], سرائیکی]
   sl: [Latn, [EU], slovenščina]
   sli: [Latn, [EU], Schläsch]
   slr: [Latn, [AS], Salırça]
   sly: [Latn, [AS], Bahasa Selayar]
-  skr-arab: [Arab, [AS], سرائیکی]
-  skr: [skr-arab]
-  srq: [Latn, [AM], mbia cheë]
-  syc: [Syrc, [ME], ܣܘܪܝܝܐ]
-  syl: [Sylo, [AS], ꠍꠤꠟꠐꠤ]
-  syl-beng: [Beng, [AS], সিলেটি]
-  syl-sylo: [syl]
   sm: [Latn, [PA], Gagana Samoa]
   sma: [Latn, [EU], åarjelsaemien]
   smj: [Latn, [EU], julevsámegiella]
@@ -672,12 +667,13 @@ languages:
   son: [Latn, [AF], soŋay]
   sq: [Latn, [EU], shqip]
   sr: [sr-cyrl]
-  sr-ec: [sr-cyrl]
   sr-cyrl: [Cyrl, [EU], српски]
+  sr-ec: [sr-cyrl]
   sr-el: [sr-latn]
   sr-latn: [Latn, [EU], srpski]
   srn: [Latn, [AM, EU], Sranantongo]
   sro: [Latn, [EU], sardu campidanesu]
+  srq: [Latn, [AM], mbia cheë]
   ss: [Latn, [AF], SiSwati]
   st: [Latn, [AF], Sesotho]
   stq: [Latn, [EU], Seeltersk]
@@ -685,25 +681,29 @@ languages:
   su: [Latn, [AS], Sunda]
   sv: [Latn, [EU], svenska]
   sw: [Latn, [AF], Kiswahili]
-  swh: [sw]
   swb: [Latn, [AF], Shikomoro]
+  swh: [sw]
   sxu: [Latn, [EU], Säggssch]
+  syc: [Syrc, [ME], ܣܘܪܝܝܐ]
+  syl: [Sylo, [AS], ꠍꠤꠟꠐꠤ]
+  syl-beng: [Beng, [AS], সিলেটি]
+  syl-sylo: [syl]
   szl: [Latn, [EU], ślůnski]
   szy: [Latn, [AS], Sakizaya]
   ta: [Taml, [AS], தமிழ்]
  # This is initially added for Wikimiedia MinT, which outputs Tifinagh.
  # Perhaps some day it can be changed to Latin as default.
+  taq: [taq-tfng]
   taq-latn: [Latn, [AF], təmajəq]
   taq-tfng: [Latn, [AF], ⵜⴰⵎⴰⵌⴰⵆ]
-  taq: [taq-tfng]
   tay: [Latn, [AS], Tayal]
   tcy: [Knda, [AS], ತುಳು]
   tdd: [Tale, [AS], ᥖᥭᥰᥖᥬᥳᥑᥨᥒᥰ]
   te: [Telu, [AS], తెలుగు]
   tet: [Latn, [AS, PA], tetun]
+  tg: [tg-cyrl]
   tg-cyrl: [Cyrl, [AS], тоҷикӣ]
   tg-latn: [Latn, [AS], tojikī]
-  tg: [tg-cyrl]
   th: [Thai, [AS], ไทย]
   ti: [Ethi, [AF], ትግርኛ]
   tig: [Ethi, [AF], ትግረ]
@@ -741,18 +741,18 @@ languages:
  # Arabic seems to have the largest number of users and is the main script in the Wikipedia.
   ug: [ug-arab]
   ug-arab: [Arab, [AS], ئۇيغۇرچە]
-  ug-latn: [Latn, [AS], uyghurche]
   ug-cyrl: [Cyrl, [AS], уйғурчә]
+  ug-latn: [Latn, [AS], uyghurche]
   uk: [Cyrl, [EU], українська]
   umb: [Latn, [AF], umbundu]
   umu: [Latn, [AM], Huluníixsuwaakan]
   ur: [Arab, [AS, ME], اردو]
+  uz: [Latn, [AS], oʻzbekcha]
   uz-cyrl: [Cyrl, [AS], ўзбекча]
   uz-latn: [uz]
-  uz: [Latn, [AS], oʻzbekcha]
   uzn: [uz]
-  ve: [Latn, [AF], Tshivenda]
   vai: [Vaii, [AF], ꕙꔤ]
+  ve: [Latn, [AF], Tshivenda]
   vec: [Latn, [EU, AM], vèneto]
   vep: [Latn, [EU], vepsän kel’]
   vi: [Latn, [AS], Tiếng Việt]
@@ -790,6 +790,7 @@ languages:
   zgh: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ ⵜⴰⵏⴰⵡⴰⵢⵜ]
  # world? (may apply to many varieties of Chinese)
   zh: [Hans, [AS, PA, AM], 中文]
+  zh-cdo: [cdo]
   zh-classical: [lzh]
   zh-cn: [Hans, [AS], 中文（中国大陆）]
   zh-hans: [Hans, [AS, PA, AM], 中文（简体）]
@@ -801,7 +802,6 @@ languages:
   zh-sg: [Hans, [AS], 中文（新加坡）]
   zh-tw: [Hant, [AS], 中文（台灣）]
   zh-yue: [yue]
-  zh-cdo: [cdo]
   zsm: [ms]
   zu: [Latn, [AF], isiZulu]
   zun: [Latn, [AM], "Shiwi'ma"]

yaml-sort-checker.yml

@@ -0,0 +1,7 @@
+files:
+  data/langdb.yaml:
+    excludedSections:
+      - scriptgroups
+      - rtlscripts
+      - regiongroups
+  yaml-sort-checker.yml: