scuffed-code/icu4c/source/test/testdata/localeMatcherTest.txt

1961 lines
48 KiB
Plaintext

# © 2017 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html#License
#
# Data-driven test for the language/locale matcher.
# Format:
#
# Everything after "#" is a comment.
# ** test: This line starts a group of test cases.
#
# Lines starting with an '@' sign provide matcher parameters.
# @supported=<comma-separated supported languages>
# @default=<default language> # no value = no explicit default
# @favor=[normal|script] # no value = no explicit setting
# @threshold=<number 0..100> # no value = no explicit setting
#
# A line with ">>" is a getBestMatch() test case:
# <comma-separated desired languages> >> match | desired | combined
# - match is the expected best supported language
# - desired is the expected best desired language
# - combined is the expected result of combine(match, desired)
# An expected language can be "null" to check for the matcher returning null.
# An empty or omitted value is not tested. (Omitted = not even the '|' separator.)
#
# ** test: A new test group resets all matcher parameters.
## X
** test: testParentLocales
# es-419, es-AR, and es-MX are in a cluster; es is in a different one
@supported=es-419, es-ES
es-AR >> es-419
@supported=es-ES, es-419
es-AR >> es-419
@supported=es-419, es
es-AR >> es-419
@supported=es, es-419
es-AR >> es-419
@supported=es-MX, es
es-AR >> es-MX
@supported=es, es-MX
es-AR >> es-MX
# en-GB, en-AU, and en-NZ are in a cluster; en in a different one
@supported=en-GB, en-US
en-AU >> en-GB
@supported=en-US, en-GB
en-AU >> en-GB
@supported=en-GB, en
en-AU >> en-GB
@supported=en, en-GB
en-AU >> en-GB
@supported=en-NZ, en-US
en-AU >> en-NZ
@supported=en-US, en-NZ
en-AU >> en-NZ
@supported=en-NZ, en
en-AU >> en-NZ
@supported=en, en-NZ
en-AU >> en-NZ
# pt-AU and pt-PT in one cluster; pt-BR in another
@supported=pt-PT, pt-BR
pt-AO >> pt-PT
@supported=pt-BR, pt-PT
pt-AO >> pt-PT
@supported=pt-PT, pt
pt-AO >> pt-PT
@supported=pt, pt-PT
pt-AO >> pt-PT
@supported=zh-MO, zh-TW
zh-HK >> zh-MO
@supported=zh-TW, zh-MO
zh-HK >> zh-MO
@supported=zh-MO, zh-CN
zh-HK >> zh-MO
@supported=zh-CN, zh-MO
zh-HK >> zh-MO
@supported=zh-MO, zh
zh-HK >> zh-MO
@supported=zh, zh-MO
zh-HK >> zh-MO
@favor=script
@supported=es-419, es-ES
es-AR >> es-419
@supported=es-ES, es-419
es-AR >> es-419
@supported=es-419, es
es-AR >> es-419
@supported=es, es-419
es-AR >> es-419
@supported=es-MX, es
es-AR >> es-MX
@supported=es, es-MX
es-AR >> es-MX
@supported=en-GB, en-US
en-AU >> en-GB
@supported=en-US, en-GB
en-AU >> en-GB
@supported=en-GB, en
en-AU >> en-GB
@supported=en, en-GB
en-AU >> en-GB
@supported=en-NZ, en-US
en-AU >> en-NZ
@supported=en-US, en-NZ
en-AU >> en-NZ
@supported=en-NZ, en
en-AU >> en-NZ
@supported=en, en-NZ
en-AU >> en-NZ
@supported=pt-PT, pt-BR
pt-AO >> pt-PT
@supported=pt-BR, pt-PT
pt-AO >> pt-PT
@supported=pt-PT, pt
pt-AO >> pt-PT
@supported=pt, pt-PT
pt-AO >> pt-PT
@supported=zh-MO, zh-TW
zh-HK >> zh-MO
@supported=zh-TW, zh-MO
zh-HK >> zh-MO
@supported=zh-MO, zh-CN
zh-HK >> zh-MO
@supported=zh-CN, zh-MO
zh-HK >> zh-MO
@supported=zh-MO, zh
zh-HK >> zh-MO
@supported=zh, zh-MO
zh-HK >> zh-MO
** test: testChinese
@supported=zh-CN, zh-TW, iw
zh-Hant-TW >> zh-TW
zh-Hant >> zh-TW
zh-TW >> zh-TW
zh-Hans-CN >> zh-CN
zh-CN >> zh-CN
zh >> zh-CN
@favor=script
zh-Hant-TW >> zh-TW
zh-Hant >> zh-TW
zh-TW >> zh-TW
zh-Hans-CN >> zh-CN
zh-CN >> zh-CN
zh >> zh-CN
** test: testenGB
@supported=fr, en, en-GB, es-419, es-MX, es
en-NZ >> en-GB
es-ES >> es
es-AR >> es-419
es-MX >> es-MX
@favor=script
en-NZ >> en-GB
es-ES >> es
es-AR >> es-419
es-MX >> es-MX
** test: testFallbacks
@supported=91, en, hi
sa >> hi
@favor=script
sa >> hi
** test: testBasics
@supported=fr, en-GB, en
en-GB >> en-GB
en >> en
fr >> fr
ja >> fr # return first if no match
@favor=script
en-GB >> en-GB
en >> en
fr >> fr
ja >> fr
** test: testFallback
# check that script fallbacks are handled right
@supported=zh-CN, zh-TW, iw
zh-Hant >> zh-TW
zh >> zh-CN
zh-Hans-CN >> zh-CN
zh-Hant-HK >> zh-TW
he-IT >> iw
@favor=script
zh-Hant >> zh-TW
zh >> zh-CN
zh-Hans-CN >> zh-CN
zh-Hant-HK >> zh-TW
he-IT >> iw
** test: testSpecials
# check that nearby languages are handled
@supported=en, fil, ro, nn
tl >> fil
mo >> ro
nb >> nn
# make sure default works
ja >> en
@favor=script
tl >> fil
mo >> ro
nb >> nn
ja >> en
** test: testRegionalSpecials
# verify that en-AU is closer to en-GB than to en (which is en-US)
@supported=en, en-GB, es, es-419
es-MX >> es-419
en-AU >> en-GB
es-ES >> es
@favor=script
es-MX >> es-419
en-AU >> en-GB
es-ES >> es
** test: testHK
# HK and MO are closer to each other for Hant than to TW
@supported=zh, zh-TW, zh-MO
zh-HK >> zh-MO
@supported=zh, zh-TW, zh-HK
zh-MO >> zh-HK
@favor=script
@supported=zh, zh-TW, zh-MO
zh-HK >> zh-MO
@supported=zh, zh-TW, zh-HK
zh-MO >> zh-HK
** test: testMatch-matchOnMazimized
@supported=zh, zh-Hant
und-TW >> zh-Hant # und-TW should be closer to zh-Hant than to zh
@supported=en-Hant-TW, und-TW
zh-Hant >> und-TW # zh-Hant should be closer to und-TW than to en-Hant-TW
zh >> und-TW # zh should be closer to und-TW than to en-Hant-TW
@favor=script
@supported=zh, zh-Hant
und-TW >> zh-Hant
@supported=en-Hant-TW, und-TW
zh-Hant >> und-TW
zh >> und-TW
** test: testMatchGrandfatheredCode
@supported=fr, i-klingon, en-Latn-US
en-GB-oed >> en-Latn-US
@favor=script
en-GB-oed >> en-Latn-US
** test: testGetBestMatchForList-exactMatch
@supported=fr, en-GB, ja, es-ES, es-MX
ja, de >> ja
@favor=script
ja, de >> ja
** test: testGetBestMatchForList-simpleVariantMatch
@supported=fr, en-GB, ja, es-ES, es-MX
de, en-US >> en-GB # Intentionally avoiding a perfect-match or two candidates for variant matches.
# Fallback.
de, zh >> fr
@favor=script
de, en-US >> en-GB
de, zh >> fr
** test: testGetBestMatchForList-matchOnMaximized
# Check that if the preference is maximized already, it works as well.
@supported=en, ja
ja-Jpan-JP, en-AU >> ja # Match for ja-Jpan-JP (maximized already)
# ja-JP matches ja on likely subtags, and it's listed first, thus it wins over the second preference en-GB.
ja-JP, en-US >> ja # Match for ja-Jpan-JP (maximized already)
# Check that if the preference is maximized already, it works as well.
ja-Jpan-JP, en-US >> ja # Match for ja-Jpan-JP (maximized already)
@favor=script
ja-Jpan-JP, en-AU >> ja
ja-JP, en-US >> ja
ja-Jpan-JP, en-US >> ja
** test: testGetBestMatchForList-noMatchOnMaximized
# Regression test for http://b/5714572 .
# de maximizes to de-DE. Pick the exact match for the secondary language instead.
@supported=en, de, fr, ja
de-CH, fr >> de
@favor=script
de-CH, fr >> de
** test: testBestMatchForTraditionalChinese
# Scenario: An application that only supports Simplified Chinese (and some other languages),
# but does not support Traditional Chinese. zh-Hans-CN could be replaced with zh-CN, zh, or
# zh-Hans, it wouldn't make much of a difference.
# The script distance (simplified vs. traditional Han) is considered small enough
# to be an acceptable match. The regional difference is considered almost insignificant.
@supported=fr, zh-Hans-CN, en-US
zh-TW >> zh-Hans-CN
zh-Hant >> zh-Hans-CN
# For geopolitical reasons, you might want to avoid a zh-Hant -> zh-Hans match.
# In this case, if zh-TW, zh-HK or a tag starting with zh-Hant is requested, you can
# change your call to getBestMatch to include a 2nd language preference.
# "en" is a better match since its distance to "en-US" is closer than the distance
# from "zh-TW" to "zh-CN" (script distance).
zh-TW, en >> en-US
zh-Hant-CN, en >> en-US
zh-Hans, en >> zh-Hans-CN
@favor=script
zh-TW >> zh-Hans-CN
zh-Hant >> zh-Hans-CN
zh-TW, en >> en-US
zh-Hant-CN, en >> en-US
zh-Hans, en >> zh-Hans-CN
** test: testUndefined
# When the undefined language doesn't match anything in the list,
# getBestMatch returns the default, as usual.
@supported=it, fr
und >> it
# When it *does* occur in the list, bestMatch returns it, as expected.
@supported=it, und
und >> und
# The unusual part: max("und") = "en-Latn-US", and since matching is based on maximized
# tags, the undefined language would normally match English. But that would produce the
# counterintuitive results that getBestMatch("und", XLocaleMatcher("it,en")) would be "en", and
# getBestMatch("en", XLocaleMatcher("it,und")) would be "und".
# To avoid that, we change the matcher's definitions of max
# so that max("und")="und". That produces the following, more desirable
# results:
@supported=it, en
und >> it
@supported=it, und
en >> it
@favor=script
@supported=it, fr
und >> it
@supported=it, und
und >> und
@supported=it, en
und >> it
@supported=it, und
en >> it
** test: testGetBestMatch-regionDistance
@supported=es-AR, es
es-MX >> es-AR
@supported=fr, en, en-GB
en-CA >> en-GB
@supported=de-AT, de-DE, de-CH
de >> de-DE
@favor=script
@supported=es-AR, es
es-MX >> es-AR
@supported=fr, en, en-GB
en-CA >> en-GB
@supported=de-AT, de-DE, de-CH
de >> de-DE
** test: testAsymmetry
@supported=mul, nl
af >> nl # af => nl
@supported=mul, af
nl >> mul # but nl !=> af
@favor=script
@supported=mul, nl
af >> nl
@supported=mul, af
nl >> mul
** test: testGetBestMatchForList-matchOnMaximized2
# ja-JP matches ja on likely subtags, and it's listed first, thus it wins over the second preference en-GB.
@supported=fr, en-GB, ja, es-ES, es-MX
ja-JP, en-GB >> ja # Match for ja-JP, with likely region subtag
# Check that if the preference is maximized already, it works as well.
ja-Jpan-JP, en-GB >> ja # Match for ja-Jpan-JP (maximized already)
@favor=script
ja-JP, en-GB >> ja
ja-Jpan-JP, en-GB >> ja
** test: testGetBestMatchForList-closeEnoughMatchOnMaximized
@supported=en-GB, en, de, fr, ja
de-CH, fr >> de
en-US, ar, nl, de, ja >> en
@favor=script
de-CH, fr >> de
en-US, ar, nl, de, ja >> en
** test: testGetBestMatchForPortuguese
# pt might be supported and not pt-PT
# European user who prefers Spanish over Brazilian Portuguese as a fallback.
@supported=pt-PT, pt-BR, es, es-419
pt-PT, es, pt >> pt-PT
@supported=pt-PT, pt, es, es-419
pt-PT, es, pt >> pt-PT # pt implicit
# Brazilian user who prefers South American Spanish over European Portuguese as a fallback.
# The asymmetry between this case and above is because it's "pt-PT" that's missing between the
# matchers as "pt-BR" is a much more common language.
@supported=pt-PT, pt-BR, es, es-419
pt, es-419, pt-PT >> pt-BR
pt-PT, es, pt >> pt-PT
@supported=pt-PT, pt, es, es-419
pt-PT, es, pt >> pt-PT
pt, es-419, pt-PT >> pt
@supported=pt-BR, es, es-419
pt, es-419, pt-PT >> pt-BR
# Code that adds the user's country can get "pt-US" for a user's language.
# That should fall back to "pt-BR".
@supported=pt-PT, pt-BR, es, es-419
pt-US, pt-PT >> pt-BR
@supported=pt-PT, pt, es, es-419
pt-US, pt-PT, pt >> pt # pt-BR implicit
@favor=script
@supported=pt-PT, pt-BR, es, es-419
pt-PT, es, pt >> pt-PT
@supported=pt-PT, pt, es, es-419
pt-PT, es, pt >> pt-PT
@supported=pt-PT, pt-BR, es, es-419
pt, es-419, pt-PT >> pt-BR
pt-PT, es, pt >> pt-PT
@supported=pt-PT, pt, es, es-419
pt-PT, es, pt >> pt-PT
pt, es-419, pt-PT >> pt
@supported=pt-BR, es, es-419
pt, es-419, pt-PT >> pt-BR
@supported=pt-PT, pt-BR, es, es-419
pt-US, pt-PT >> pt-BR
@supported=pt-PT, pt, es, es-419
pt-US, pt-PT, pt >> pt
** test: testVariantWithScriptMatch 1 and 2
@supported=fr, en, sv
en-GB >> en
@supported=en, sv
en-GB, sv >> en
@favor=script
@supported=fr, en, sv
en-GB >> en
@supported=en, sv
en-GB, sv >> en
** test: testLongLists
@supported=en, sv
sv >> sv
@supported=af, am, ar, az, be, bg, bn, bs, ca, cs, cy, da, de, el, en, en-GB, es, es-419, et, eu, fa, fi, fil, fr, ga, gl, gu, hi, hr, hu, hy, id, is, it, iw, ja, ka, kk, km, kn, ko, ky, lo, lt, lv, mk, ml, mn, mr, ms, my, ne, nl, no, pa, pl, pt, pt-PT, ro, ru, si, sk, sl, sq, sr, sr-Latn, sv, sw, ta, te, th, tr, uk, ur, uz, vi, zh-CN, zh-TW, zu
sv >> sv
@supported=af, af-NA, af-ZA, agq, agq-CM, ak, ak-GH, am, am-ET, ar, ar-001, ar-AE, ar-BH, ar-DJ, ar-DZ, ar-EG, ar-EH, ar-ER, ar-IL, ar-IQ, ar-JO, ar-KM, ar-KW, ar-LB, ar-LY, ar-MA, ar-MR, ar-OM, ar-PS, ar-QA, ar-SA, ar-SD, ar-SO, ar-SS, ar-SY, ar-TD, ar-TN, ar-YE, as, as-IN, asa, asa-TZ, ast, ast-ES, az, az-Cyrl, az-Cyrl-AZ, az-Latn, az-Latn-AZ, bas, bas-CM, be, be-BY, bem, bem-ZM, bez, bez-TZ, bg, bg-BG, bm, bm-ML, bn, bn-BD, bn-IN, bo, bo-CN, bo-IN, br, br-FR, brx, brx-IN, bs, bs-Cyrl, bs-Cyrl-BA, bs-Latn, bs-Latn-BA, ca, ca-AD, ca-ES, ca-ES-VALENCIA, ca-FR, ca-IT, ce, ce-RU, cgg, cgg-UG, chr, chr-US, ckb, ckb-IQ, ckb-IR, cs, cs-CZ, cu, cu-RU, cy, cy-GB, da, da-DK, da-GL, dav, dav-KE, de, de-AT, de-BE, de-CH, de-DE, de-LI, de-LU, dje, dje-NE, dsb, dsb-DE, dua, dua-CM, dyo, dyo-SN, dz, dz-BT, ebu, ebu-KE, ee, ee-GH, ee-TG, el, el-CY, el-GR, en, en-001, en-150, en-AG, en-AI, en-AS, en-AT, en-AU, en-BB, en-BE, en-BI, en-BM, en-BS, en-BW, en-BZ, en-CA, en-CC, en-CH, en-CK, en-CM, en-CX, en-CY, en-DE, en-DG, en-DK, en-DM, en-ER, en-FI, en-FJ, en-FK, en-FM, en-GB, en-GD, en-GG, en-GH, en-GI, en-GM, en-GU, en-GY, en-HK, en-IE, en-IL, en-IM, en-IN, en-IO, en-JE, en-JM, en-KE, en-KI, en-KN, en-KY, en-LC, en-LR, en-LS, en-MG, en-MH, en-MO, en-MP, en-MS, en-MT, en-MU, en-MW, en-MY, en-NA, en-NF, en-NG, en-NL, en-NR, en-NU, en-NZ, en-PG, en-PH, en-PK, en-PN, en-PR, en-PW, en-RW, en-SB, en-SC, en-SD, en-SE, en-SG, en-SH, en-SI, en-SL, en-SS, en-SX, en-SZ, en-TC, en-TK, en-TO, en-TT, en-TV, en-TZ, en-UG, en-UM, en-US, en-US-POSIX, en-VC, en-VG, en-VI, en-VU, en-WS, en-ZA, en-ZM, en-ZW, eo, eo-001, es, es-419, es-AR, es-BO, es-CL, es-CO, es-CR, es-CU, es-DO, es-EA, es-EC, es-ES, es-GQ, es-GT, es-HN, es-IC, es-MX, es-NI, es-PA, es-PE, es-PH, es-PR, es-PY, es-SV, es-US, es-UY, es-VE, et, et-EE, eu, eu-ES, ewo, ewo-CM, fa, fa-AF, fa-IR, ff, ff-CM, ff-GN, ff-MR, ff-SN, fi, fi-FI, fil, fil-PH, fo, fo-DK, fo-FO, fr, fr-BE, fr-BF, fr-BI, fr-BJ, fr-BL, fr-CA, fr-CD, fr-CF, fr-CG, fr-CH, fr-CI, fr-CM, fr-DJ, fr-DZ, fr-FR, fr-GA, fr-GF, fr-GN, fr-GP, fr-GQ, fr-HT, fr-KM, fr-LU, fr-MA, fr-MC, fr-MF, fr-MG, fr-ML, fr-MQ, fr-MR, fr-MU, fr-NC, fr-NE, fr-PF, fr-PM, fr-RE, fr-RW, fr-SC, fr-SN, fr-SY, fr-TD, fr-TG, fr-TN, fr-VU, fr-WF, fr-YT, fur, fur-IT, fy, fy-NL, ga, ga-IE, gd, gd-GB, gl, gl-ES, gsw, gsw-CH, gsw-FR, gsw-LI, gu, gu-IN, guz, guz-KE, gv, gv-IM, ha, ha-GH, ha-NE, ha-NG, haw, haw-US, he, he-IL, hi, hi-IN, hr, hr-BA, hr-HR, hsb, hsb-DE, hu, hu-HU, hy, hy-AM, id, id-ID, ig, ig-NG, ii, ii-CN, is, is-IS, it, it-CH, it-IT, it-SM, ja, ja-JP, jgo, jgo-CM, jmc, jmc-TZ, ka, ka-GE, kab, kab-DZ, kam, kam-KE, kde, kde-TZ, kea, kea-CV, khq, khq-ML, ki, ki-KE, kk, kk-KZ, kkj, kkj-CM, kl, kl-GL, kln, kln-KE, km, km-KH, kn, kn-IN, ko, ko-KP, ko-KR, kok, kok-IN, ks, ks-IN, ksb, ksb-TZ, ksf, ksf-CM, ksh, ksh-DE, kw, kw-GB, ky, ky-KG, lag, lag-TZ, lb, lb-LU, lg, lg-UG, lkt, lkt-US, ln, ln-AO, ln-CD, ln-CF, ln-CG, lo, lo-LA, lrc, lrc-IQ, lrc-IR, lt, lt-LT, lu, lu-CD, luo, luo-KE, luy, luy-KE, lv, lv-LV, mas, mas-KE, mas-TZ, mer, mer-KE, mfe, mfe-MU, mg, mg-MG, mgh, mgh-MZ, mgo, mgo-CM, mk, mk-MK, ml, ml-IN, mn, mn-MN, mr, mr-IN, ms, ms-BN, ms-MY, ms-SG, mt, mt-MT, mua, mua-CM, my, my-MM, mzn, mzn-IR, naq, naq-NA, nb, nb-NO, nb-SJ, nd, nd-ZW, ne, ne-IN, ne-NP, nl, nl-AW, nl-BE, nl-BQ, nl-CW, nl-NL, nl-SR, nl-SX, nmg, nmg-CM, nn, nn-NO, nnh, nnh-CM, nus, nus-SS, nyn, nyn-UG, om, om-ET, om-KE, or, or-IN, os, os-GE, os-RU, pa, pa-Arab, pa-Arab-PK, pa-Guru, pa-Guru-IN, pl, pl-PL, prg, prg-001, ps, ps-AF, pt, pt-AO, pt-BR, pt-CV, pt-GW, pt-MO, pt-MZ, pt-PT, pt-ST, pt-TL, qu, qu-BO, qu-EC, qu-PE, rm, rm-CH, rn, rn-BI, ro, ro-MD, ro-RO, rof, rof-TZ, root, ru, ru-BY, ru-KG, ru-KZ, ru-MD, ru-RU, ru-UA, rw, rw-RW, rwk, rwk-TZ, sah, sah-RU, saq, saq-KE, sbp, sbp-TZ, se, se-FI, se-NO, se-SE, seh, seh-MZ, ses, ses-ML, sg, sg-CF, shi, shi-Latn, shi-Latn-MA, shi-Tfng, shi-Tfng-MA, si, si-LK, sk, sk-SK, sl, sl-SI, smn, smn-FI, sn, sn-ZW, so, so-DJ, so-ET, so-KE, so-SO, sq, sq-AL, sq-MK, sq-XK, sr, sr-Cyrl, sr-Cyrl-BA, sr-Cyrl-ME, sr-Cyrl-RS, sr-Cyrl-XK, sr-Latn, sr-Latn-BA, sr-Latn-ME, sr-Latn-RS, sr-Latn-XK, sv, sv-AX, sv-FI, sv-SE, sw, sw-CD, sw-KE, sw-TZ, sw-UG, ta, ta-IN, ta-LK, ta-MY, ta-SG, te, te-IN, teo, teo-KE, teo-UG, th, th-TH, ti, ti-ER, ti-ET, tk, tk-TM, to, to-TO, tr, tr-CY, tr-TR, twq, twq-NE, tzm, tzm-MA, ug, ug-CN, uk, uk-UA, ur, ur-IN, ur-PK, uz, uz-Arab, uz-Arab-AF, uz-Cyrl, uz-Cyrl-UZ, uz-Latn, uz-Latn-UZ, vai, vai-Latn, vai-Latn-LR, vai-Vaii, vai-Vaii-LR, vi, vi-VN, vo, vo-001, vun, vun-TZ, wae, wae-CH, xog, xog-UG, yav, yav-CM, yi, yi-001, yo, yo-BJ, yo-NG, zgh, zgh-MA, zh, zh-Hans, zh-Hans-CN, zh-Hans-HK, zh-Hans-MO, zh-Hans-SG, zh-Hant, zh-Hant-HK, zh-Hant-MO, zh-Hant-TW, zu, zu-ZA
sv >> sv
@favor=script
@supported=en, sv
sv >> sv
@supported=af, am, ar, az, be, bg, bn, bs, ca, cs, cy, da, de, el, en, en-GB, es, es-419, et, eu, fa, fi, fil, fr, ga, gl, gu, hi, hr, hu, hy, id, is, it, iw, ja, ka, kk, km, kn, ko, ky, lo, lt, lv, mk, ml, mn, mr, ms, my, ne, nl, no, pa, pl, pt, pt-PT, ro, ru, si, sk, sl, sq, sr, sr-Latn, sv, sw, ta, te, th, tr, uk, ur, uz, vi, zh-CN, zh-TW, zu
sv >> sv
@supported=af, af-NA, af-ZA, agq, agq-CM, ak, ak-GH, am, am-ET, ar, ar-001, ar-AE, ar-BH, ar-DJ, ar-DZ, ar-EG, ar-EH, ar-ER, ar-IL, ar-IQ, ar-JO, ar-KM, ar-KW, ar-LB, ar-LY, ar-MA, ar-MR, ar-OM, ar-PS, ar-QA, ar-SA, ar-SD, ar-SO, ar-SS, ar-SY, ar-TD, ar-TN, ar-YE, as, as-IN, asa, asa-TZ, ast, ast-ES, az, az-Cyrl, az-Cyrl-AZ, az-Latn, az-Latn-AZ, bas, bas-CM, be, be-BY, bem, bem-ZM, bez, bez-TZ, bg, bg-BG, bm, bm-ML, bn, bn-BD, bn-IN, bo, bo-CN, bo-IN, br, br-FR, brx, brx-IN, bs, bs-Cyrl, bs-Cyrl-BA, bs-Latn, bs-Latn-BA, ca, ca-AD, ca-ES, ca-ES-VALENCIA, ca-FR, ca-IT, ce, ce-RU, cgg, cgg-UG, chr, chr-US, ckb, ckb-IQ, ckb-IR, cs, cs-CZ, cu, cu-RU, cy, cy-GB, da, da-DK, da-GL, dav, dav-KE, de, de-AT, de-BE, de-CH, de-DE, de-LI, de-LU, dje, dje-NE, dsb, dsb-DE, dua, dua-CM, dyo, dyo-SN, dz, dz-BT, ebu, ebu-KE, ee, ee-GH, ee-TG, el, el-CY, el-GR, en, en-001, en-150, en-AG, en-AI, en-AS, en-AT, en-AU, en-BB, en-BE, en-BI, en-BM, en-BS, en-BW, en-BZ, en-CA, en-CC, en-CH, en-CK, en-CM, en-CX, en-CY, en-DE, en-DG, en-DK, en-DM, en-ER, en-FI, en-FJ, en-FK, en-FM, en-GB, en-GD, en-GG, en-GH, en-GI, en-GM, en-GU, en-GY, en-HK, en-IE, en-IL, en-IM, en-IN, en-IO, en-JE, en-JM, en-KE, en-KI, en-KN, en-KY, en-LC, en-LR, en-LS, en-MG, en-MH, en-MO, en-MP, en-MS, en-MT, en-MU, en-MW, en-MY, en-NA, en-NF, en-NG, en-NL, en-NR, en-NU, en-NZ, en-PG, en-PH, en-PK, en-PN, en-PR, en-PW, en-RW, en-SB, en-SC, en-SD, en-SE, en-SG, en-SH, en-SI, en-SL, en-SS, en-SX, en-SZ, en-TC, en-TK, en-TO, en-TT, en-TV, en-TZ, en-UG, en-UM, en-US, en-US-POSIX, en-VC, en-VG, en-VI, en-VU, en-WS, en-ZA, en-ZM, en-ZW, eo, eo-001, es, es-419, es-AR, es-BO, es-CL, es-CO, es-CR, es-CU, es-DO, es-EA, es-EC, es-ES, es-GQ, es-GT, es-HN, es-IC, es-MX, es-NI, es-PA, es-PE, es-PH, es-PR, es-PY, es-SV, es-US, es-UY, es-VE, et, et-EE, eu, eu-ES, ewo, ewo-CM, fa, fa-AF, fa-IR, ff, ff-CM, ff-GN, ff-MR, ff-SN, fi, fi-FI, fil, fil-PH, fo, fo-DK, fo-FO, fr, fr-BE, fr-BF, fr-BI, fr-BJ, fr-BL, fr-CA, fr-CD, fr-CF, fr-CG, fr-CH, fr-CI, fr-CM, fr-DJ, fr-DZ, fr-FR, fr-GA, fr-GF, fr-GN, fr-GP, fr-GQ, fr-HT, fr-KM, fr-LU, fr-MA, fr-MC, fr-MF, fr-MG, fr-ML, fr-MQ, fr-MR, fr-MU, fr-NC, fr-NE, fr-PF, fr-PM, fr-RE, fr-RW, fr-SC, fr-SN, fr-SY, fr-TD, fr-TG, fr-TN, fr-VU, fr-WF, fr-YT, fur, fur-IT, fy, fy-NL, ga, ga-IE, gd, gd-GB, gl, gl-ES, gsw, gsw-CH, gsw-FR, gsw-LI, gu, gu-IN, guz, guz-KE, gv, gv-IM, ha, ha-GH, ha-NE, ha-NG, haw, haw-US, he, he-IL, hi, hi-IN, hr, hr-BA, hr-HR, hsb, hsb-DE, hu, hu-HU, hy, hy-AM, id, id-ID, ig, ig-NG, ii, ii-CN, is, is-IS, it, it-CH, it-IT, it-SM, ja, ja-JP, jgo, jgo-CM, jmc, jmc-TZ, ka, ka-GE, kab, kab-DZ, kam, kam-KE, kde, kde-TZ, kea, kea-CV, khq, khq-ML, ki, ki-KE, kk, kk-KZ, kkj, kkj-CM, kl, kl-GL, kln, kln-KE, km, km-KH, kn, kn-IN, ko, ko-KP, ko-KR, kok, kok-IN, ks, ks-IN, ksb, ksb-TZ, ksf, ksf-CM, ksh, ksh-DE, kw, kw-GB, ky, ky-KG, lag, lag-TZ, lb, lb-LU, lg, lg-UG, lkt, lkt-US, ln, ln-AO, ln-CD, ln-CF, ln-CG, lo, lo-LA, lrc, lrc-IQ, lrc-IR, lt, lt-LT, lu, lu-CD, luo, luo-KE, luy, luy-KE, lv, lv-LV, mas, mas-KE, mas-TZ, mer, mer-KE, mfe, mfe-MU, mg, mg-MG, mgh, mgh-MZ, mgo, mgo-CM, mk, mk-MK, ml, ml-IN, mn, mn-MN, mr, mr-IN, ms, ms-BN, ms-MY, ms-SG, mt, mt-MT, mua, mua-CM, my, my-MM, mzn, mzn-IR, naq, naq-NA, nb, nb-NO, nb-SJ, nd, nd-ZW, ne, ne-IN, ne-NP, nl, nl-AW, nl-BE, nl-BQ, nl-CW, nl-NL, nl-SR, nl-SX, nmg, nmg-CM, nn, nn-NO, nnh, nnh-CM, nus, nus-SS, nyn, nyn-UG, om, om-ET, om-KE, or, or-IN, os, os-GE, os-RU, pa, pa-Arab, pa-Arab-PK, pa-Guru, pa-Guru-IN, pl, pl-PL, prg, prg-001, ps, ps-AF, pt, pt-AO, pt-BR, pt-CV, pt-GW, pt-MO, pt-MZ, pt-PT, pt-ST, pt-TL, qu, qu-BO, qu-EC, qu-PE, rm, rm-CH, rn, rn-BI, ro, ro-MD, ro-RO, rof, rof-TZ, root, ru, ru-BY, ru-KG, ru-KZ, ru-MD, ru-RU, ru-UA, rw, rw-RW, rwk, rwk-TZ, sah, sah-RU, saq, saq-KE, sbp, sbp-TZ, se, se-FI, se-NO, se-SE, seh, seh-MZ, ses, ses-ML, sg, sg-CF, shi, shi-Latn, shi-Latn-MA, shi-Tfng, shi-Tfng-MA, si, si-LK, sk, sk-SK, sl, sl-SI, smn, smn-FI, sn, sn-ZW, so, so-DJ, so-ET, so-KE, so-SO, sq, sq-AL, sq-MK, sq-XK, sr, sr-Cyrl, sr-Cyrl-BA, sr-Cyrl-ME, sr-Cyrl-RS, sr-Cyrl-XK, sr-Latn, sr-Latn-BA, sr-Latn-ME, sr-Latn-RS, sr-Latn-XK, sv, sv-AX, sv-FI, sv-SE, sw, sw-CD, sw-KE, sw-TZ, sw-UG, ta, ta-IN, ta-LK, ta-MY, ta-SG, te, te-IN, teo, teo-KE, teo-UG, th, th-TH, ti, ti-ER, ti-ET, tk, tk-TM, to, to-TO, tr, tr-CY, tr-TR, twq, twq-NE, tzm, tzm-MA, ug, ug-CN, uk, uk-UA, ur, ur-IN, ur-PK, uz, uz-Arab, uz-Arab-AF, uz-Cyrl, uz-Cyrl-UZ, uz-Latn, uz-Latn-UZ, vai, vai-Latn, vai-Latn-LR, vai-Vaii, vai-Vaii-LR, vi, vi-VN, vo, vo-001, vun, vun-TZ, wae, wae-CH, xog, xog-UG, yav, yav-CM, yi, yi-001, yo, yo-BJ, yo-NG, zgh, zgh-MA, zh, zh-Hans, zh-Hans-CN, zh-Hans-HK, zh-Hans-MO, zh-Hans-SG, zh-Hant, zh-Hant-HK, zh-Hant-MO, zh-Hant-TW, zu, zu-ZA
sv >> sv
** test: test8288
@supported=it, en
und >> it
und, en >> en
# examples from
# http://unicode.org/repos/cldr/tags/latest/common/bcp47/
# http://unicode.org/repos/cldr/tags/latest/common/validity/variant.xml
@favor=script
und >> it
und, en >> en
** test: testUnHack
@supported=en-NZ, en-IT
en-US >> en-NZ
@favor=script
en-US >> en-NZ
** test: testEmptySupported => null
en >> null
# testVariantsAndExtensions
** test: tests the .combine() method
@supported=und, fr
fr-BE-fonipa >> fr | | fr-BE-fonipa
@supported=und, fr-CA
fr-BE-fonipa >> fr-CA | | fr-BE-fonipa
@supported=und, fr-fonupa
fr-BE-fonipa >> fr-fonupa | | fr-BE-fonipa
@supported=und, no
nn-BE-fonipa >> no | | no-BE-fonipa
@supported=und, en-GB-u-sd-gbsct
en-fonipa-u-nu-Arab-ca-buddhist-t-m0-iso-i0-pinyin >> en-GB-u-sd-gbsct | | en-GB-fonipa-u-nu-Arab-ca-buddhist-t-m0-iso-i0-pinyin
@supported=en-PSCRACK, de-PSCRACK, fr-PSCRACK, pt-PT-PSCRACK
fr-PSCRACK >> fr-PSCRACK
fr >> en-PSCRACK
de-CH >> en-PSCRACK
@favor=script
@supported=und, fr
fr-BE-fonipa >> fr
@supported=und, fr-CA
fr-BE-fonipa >> fr-CA
@supported=und, fr-fonupa
fr-BE-fonipa >> fr-fonupa
@supported=und, no
nn-BE-fonipa >> no | | no-BE-fonipa
@supported=und, en-GB-u-sd-gbsct
en-fonipa-u-nu-Arab-ca-buddhist-t-m0-iso-i0-pinyin >> en-GB-u-sd-gbsct | | en-GB-fonipa-u-nu-Arab-ca-buddhist-t-m0-iso-i0-pinyin
@supported=en-PSCRACK, de-PSCRACK, fr-PSCRACK, pt-PT-PSCRACK
fr-PSCRACK >> fr-PSCRACK
fr >> en-PSCRACK
de-CH >> en-PSCRACK
** test: testClusters
# we favor es-419 over others in cluster. Clusters: es- {ES, MA, EA} {419, AR, MX}
@supported=und, es, es-MA, es-MX, es-419
es-AR >> es-419
@supported=und, es-MA, es, es-419, es-MX
es-AR >> es-419
@supported=und, es, es-MA, es-MX, es-419
es-EA >> es
@supported=und, es-MA, es, es-419, es-MX
es-EA >> es
# of course, fall back to within cluster
@supported=und, es, es-MA, es-MX
es-AR >> es-MX
@supported=und, es-MA, es, es-MX
es-AR >> es-MX
@supported=und, es-MA, es-MX, es-419
es-EA >> es-MA
@supported=und, es-MA, es-419, es-MX
es-EA >> es-MA
# we favor es-GB over others in cluster. Clusters: en- {US, GU, VI} {GB, IN, ZA}
@supported=und, en, en-GU, en-IN, en-GB
en-ZA >> en-GB
@supported=und, en-GU, en, en-GB, en-IN
en-ZA >> en-GB
@supported=und, en, en-GU, en-IN, en-GB
en-VI >> en
@supported=und, en-GU, en, en-GB, en-IN
en-VI >> en
# of course, fall back to within cluster
@supported=und, en, en-GU, en-IN
en-ZA >> en-IN
@supported=und, en-GU, en, en-IN
en-ZA >> en-IN
@supported=und, en-GU, en-IN, en-GB
en-VI >> en-GU
@supported=und, en-GU, en-GB, en-IN
en-VI >> en-GU
@favor=script
@supported=und, es, es-MA, es-MX, es-419
es-AR >> es-419
@supported=und, es-MA, es, es-419, es-MX
es-AR >> es-419
@supported=und, es, es-MA, es-MX, es-419
es-EA >> es
@supported=und, es-MA, es, es-419, es-MX
es-EA >> es
@supported=und, es, es-MA, es-MX
es-AR >> es-MX
@supported=und, es-MA, es, es-MX
es-AR >> es-MX
@supported=und, es-MA, es-MX, es-419
es-EA >> es-MA
@supported=und, es-MA, es-419, es-MX
es-EA >> es-MA
@supported=und, en, en-GU, en-IN, en-GB
en-ZA >> en-GB
@supported=und, en-GU, en, en-GB, en-IN
en-ZA >> en-GB
@supported=und, en, en-GU, en-IN, en-GB
en-VI >> en
@supported=und, en-GU, en, en-GB, en-IN
en-VI >> en
@supported=und, en, en-GU, en-IN
en-ZA >> en-IN
@supported=und, en-GU, en, en-IN
en-ZA >> en-IN
@supported=und, en-GU, en-IN, en-GB
en-VI >> en-GU
@supported=und, en-GU, en-GB, en-IN
en-VI >> en-GU
** test: testThreshold
@supported=50, und, fr-CA-fonupa
@threshold=60
fr-BE-fonipa >> fr-CA-fonupa | | fr-BE-fonipa
@supported=und, fr-Cyrl-CA-fonupa
fr-BE-fonipa >> fr-Cyrl-CA-fonupa | | fr-Cyrl-BE-fonipa
@threshold=50
fr-BE-fonipa >> und
@favor=script
@supported=50, und, fr-CA-fonupa
@threshold=
fr-BE-fonipa >> fr-CA-fonupa | | fr-BE-fonipa
@supported=und, fr-Cyrl-CA-fonupa
fr-BE-fonipa >> und
** test: testScriptFirst
@supported=ru, fr
zh, pl >> ru
zh-Cyrl, pl >> ru
@supported=hr, en-Cyrl
sr >> hr
@supported=da, ru, hr
sr >> da
@favor=script
@supported=ru, fr
zh, pl >> fr
zh-Cyrl, pl >> ru
@supported=hr, en-Cyrl
sr >> en-Cyrl
@supported=da, ru, hr
sr >> ru
## III
** test: testBasicsWithDefault
@supported=en-GB, en
@default=fr
en-GB >> en-GB
en-US >> en
fr >> fr
ja >> fr
@favor=script
en-GB >> en-GB
en-US >> en
fr >> en
ja >> fr
** test: testEmptyWithDefault
@default=en
fr >> en
** test: testGetBestMatchForList_exactMatch
@supported=fr, en-GB, ja, es-ES, es-MX
ja, de >> ja
** test: testGetBestMatchForList_simpleVariantMatch
# Intentionally avoiding a perfect-match or two candidates for variant matches.
@supported=fr, en-GB, ja, es-ES, es-MX
de, en-US >> en-GB
# Fall back.
de, zh >> fr
** test: TestEuHack
@supported=en-NZ, en-IT
en-US >> en-NZ
** test: TestBasics
@supported=fr, en-GB, en
en-GB >> en-GB
en-US >> en
fr-FR >> fr
ja-JP >> fr
zu >> en
# For a language that doesn't match anything, return the default.
zxx >> fr
@favor=script
en-GB >> en-GB
en-US >> en
fr-FR >> fr
ja-JP >> fr
zu >> en
zxx >> en
** test: TestExactMatch
@supported=fr, en-GB, ja, es-ES, es-MX
ja, de >> ja
** test: TestSimpleVariantMatch
@supported=fr, en-GB, ja, es-ES, es-MX
de, en-US >> en-GB
de, zh >> fr
** test: TestMatchOnMaximized
# ja-JP matches ja on likely subtags, and it's listed first, thus it wins
# over the secondary preference en-GB.
@supported=fr, en-GB, ja, es-ES, es-MX
ja-JP, en-GB >> ja
# Check that if the preference is maximized already, it works as well.
ja-Jpan-JP, en-GB >> ja
@supported=fr, zh-Hant, en
zh, en >> en
@favor=script
zh, en >> en
** test: TestCloseEnoughMatchOnMaximized
@supported=en-GB, en, de, fr, ja
de-CH, fr >> de
en-US, ar, nl, de, ja >> en
** test: TestGetBestMatchForPortuguese
# 1. a supported set containing an explicit pt: {pt-PT, pt-BR, es, es-419}
# 2. a supported set containing an implicit pt: {pt-PT, pt, es, es-419}
# 3. a supported set containing no pt: {pt-BR, es, es-419}
# European user who prefers Spanish over Brazilian Portuguese as a fallback.
@supported=pt-PT, pt-BR, es, es-419
pt-PT, es, pt >> pt-PT
@supported=pt-PT, pt, es, es-419
pt-PT, es, pt >> pt-PT
@supported=pt-BR, es, es-419
pt-PT, es, pt >> pt-BR
# Brazilian user who prefers South American Spanish over European Portuguese
# as a fallback. The asymmetry between this case and above is because it's
# "pt-PT" that's missing between the matchers.
@supported=pt-PT, pt-BR, es, es-419
pt, es-419, pt-PT >> pt-BR
@supported=pt-PT, pt, es, es-419
pt, es-419, pt-PT >> pt
@supported=pt-BR, es, es-419
pt, es-419, pt-PT >> pt-BR
# Sometimes we get "pt-US" for a user's language (which CLDR doesn't
# recognize) but we deal with that as a synonym for "pt-BR".
@supported=pt-PT, pt-BR, es, es-419
pt-US, pt-PT >> pt-BR
@supported=pt-PT, pt, es, es-419
pt-US, pt-PT >> pt
@favor=script
@supported=pt-BR, es, es-419
pt-PT, es, pt >> pt-BR
@supported=pt-PT, pt, es, es-419
pt-US, pt-PT >> pt
** test: TestScriptAndRegion
@supported=en-GB, en
en-CA >> en-GB
# fr-CA is a "close enough" match to "fr" to be returned in favor of "en-GB"
@supported=fr, en-GB, en
fr-CA, en-CA >> fr
@supported=zh-Hant, zh-TW
zh-HK >> zh-Hant
@favor=script
@supported=en-GB, en
en-CA >> en-GB
@supported=fr, en-GB, en
fr-CA, en-CA >> fr
@supported=zh-Hant, zh-TW
zh-HK >> zh-Hant
** test: TestFallback
@supported=zh-CN, zh-TW, iw
zh-Hant >> zh-TW
zh >> zh-CN
zh-Hans-CN >> zh-CN
zh-Hant-HK >> zh-TW
he-IT >> iw
** test: TestFallbackWithDefault
# Check that script fallbacks are handled right and that we don't have to
# fall back to the default.
@supported=zh-CN, zh-TW, iw
@default=fr
zh-Hant >> zh-TW
zh >> zh-CN
zh-Hans-CN >> zh-CN
zh-Hant-HK >> zh-TW
he-IT >> iw
@favor=script
zh-Hant >> zh-TW
zh >> zh-CN
zh-Hans-CN >> zh-CN
zh-Hant-HK >> zh-TW
he-IT >> iw
** test: TestSpecials
# Check that nearby languages are handled.
@supported=en, fil, ro, nn
tl >> fil
mo >> ro
nb >> nn
ja >> en # Make sure default works.
** test: TestRegionalSpecials
# Verify that en-AU is closer to en-GB than to en (which is en-US).
@supported=en, en-GB, es-ES, es-419
en-AU >> en-GB
# Following 2 cases test closer/smaller region difference.
es-MX >> es-419
es-PT >> es-ES
@favor=script
en-AU >> en-GB
es-MX >> es-419
es-PT >> es-ES
** test: TestEmpty
fr >> null
** test: TestUndefined
# When the undefined language doesn't match anything in the list,
# return the default.
@supported=it, fr
und >> it
# When it *does* occur in the list, return it.
@supported=it, und
und >> und
# The unusual part:
# max("und") = "en-Latn-US", and since matching is based on
# maximized tags, the undefined language would normally match
# English. But that would produce the counterintuitive results
# that BestMatchFor("und", LanguageMatcher("it,en")) would be "en",
# and BestMatchFor("en", LanguageMatcher("it,und")) would be "und".
# To avoid that, we change the matcher's definitions of max
# (AddLikelySubtagsWithDefaults) so that max("und")="und". That
# produces the following, more desirable results:
@supported=it, en
und >> it
@supported=it, und
en >> it
** test: TestVariantWithScriptMatch
@supported=fr, en, sv
en-GB >> en
en-GB, sv >> en
@favor=script
en-GB, sv >> en
** test: Serbian
@supported=und, sr
sr-ME >> sr
@supported=und, sr-ME
sr >> sr-ME
@supported=und, sr-Latn
bs >> und
@supported=und, bs
sr-Latn >> und
@supported=und, sr
bs >> und
@supported=und, bs
sr >> und
@supported=und, sr-Latn
sr >> sr-Latn
@supported=und, sr
sr-Latn >> sr
@favor=script
sr-ME >> sr
@supported=und, sr-ME
sr >> sr-ME
@supported=und, sr-Latn
bs >> sr-Latn
@supported=und, bs
sr-Latn >> bs
@supported=und, sr
bs >> und
@supported=und, bs
sr >> und
@supported=und, sr-Latn
sr >> sr-Latn
@supported=und, sr
sr-Latn >> sr
** test: MatchGooglePrivateUseSubtag
@supported=fr, x-bork, en-Latn-US
x-piglatin >> fr
x-bork >> x-bork
@supported=fr, en-GB, x-bork, es-ES, es-419
x-piglatin >> fr
x-bork >> x-bork
@favor=script
@supported=fr, x-bork, en-Latn-US
x-piglatin >> x-bork
x-bork >> x-bork
@supported=fr, en-GB, x-bork, es-ES, es-419
x-piglatin >> x-bork
x-bork >> x-bork
** test: MatchGrandfatheredCode
@supported=fr, i-klingon, en-Latn-US
en-GB-oed >> en-Latn-US
i-klingon >> tlh
@favor=script
en-GB-oed >> en-Latn-US
i-klingon >> tlh
** test: MatchGooglePseudoLocale
# Google pseudo locales using variant subtags.
# (See below for the region code based pseudo locales.)
@supported=fr, en-PSACCENT, ar-PSBIDI, en-PSCRACK, zh-Hans-PSCRACK, pt-PT-PSCRACK, pt
de >> fr
en-US >> fr
en >> fr
ar-PSBIDI >> ar-PSBIDI
en-PSACCENT >> en-PSACCENT
en-PSCRACK >> en-PSCRACK
pt-BR >> pt
pt-PT-PSCRACK >> pt-PT-PSCRACK
zh-Hans-PSCRACK >> zh-Hans-PSCRACK
@favor=script
de >> fr
en-US >> fr
en >> fr
ar-PSBIDI >> ar-PSBIDI
en-PSACCENT >> en-PSACCENT
en-PSCRACK >> en-PSCRACK
pt-BR >> pt
pt-PT-PSCRACK >> pt-PT-PSCRACK
zh-Hans-PSCRACK >> zh-Hans-PSCRACK
** test: MatchGooglePseudoLocaleWithFallbacks
# Pseudo locales based on the fall back option (XA..XC region codes).
@supported=fr, en-XA, ar-XB, en-XC, zh-Hans-XC, pt
de >> fr
en-US >> fr
en >> fr
ar-XB >> ar-XB
en-XA >> en-XA
en-XC >> en-XC
pt-BR >> pt
zh-Hans-XC >> zh-Hans-XC
@favor=script
de >> fr
en-US >> fr
en >> fr
ar-XB >> ar-XB
en-XA >> en-XA
en-XC >> en-XC
pt-BR >> pt
zh-Hans-XC >> zh-Hans-XC
** test: DoNotMatchGooglePseudoLocale
@supported=fr, en-XA, ar-XB, en-PSACCENT, ar-PSBIDI, en-DE, pt, ar-SY, ar-PSCRACK
de >> fr
# We wouldn't want to return pseudo locales when there's a good match for an
# ordinary locale.
# Note: If LanguageMatcher was not aware of PSACCENT, it would consider the
# distance from "en" to "en-PSACCENT" smaller than to "en-DE" (the standard
# variant distance is smaller than a region distance).
en >> en-DE
ar-EG >> ar-SY
pt-BR >> pt
ar-XB >> ar-XB
ar-PSBIDI >> ar-PSBIDI
en-XA >> en-XA
en-PSACCENT >> en-PSACCENT
ar-PSCRACK >> ar-PSCRACK
@favor=script
de >> en-DE
en >> en-DE
ar-EG >> ar-SY
pt-BR >> pt
ar-XB >> ar-XB
ar-PSBIDI >> ar-PSBIDI
en-XA >> en-XA
en-PSACCENT >> en-PSACCENT
ar-PSCRACK >> ar-PSCRACK
** test: BestMatchForTraditionalChinese
# Scenario: An application that only supports Simplified Chinese (and some
# other languages), but does not support Traditional Chinese. zh-Hans-CN
# could be replaced with zh-CN, zh, or zh-Hans, it wouldn't make much of a
# difference.
# The script distance (simplified vs. traditional Han) is considered small
# enough to be an acceptable match. The regional difference is considered
# almost insignificant.
@supported=fr, zh-Hans-CN, en-US
zh-TW >> zh-Hans-CN
zh-Hant >> zh-Hans-CN
# For geopolitical reasons, you might want to avoid a zh-Hant -> zh-Hans
# match. In this case, if zh-TW, zh-HK or a tag starting with zh-Hant is
# requested, you can change your call to getBestMatch to include a 2nd
# language preference. "en" is a better match since its distance to "en-US"
# is closer than the distance from "zh-TW" to "zh-CN" (script distance).
zh-TW, en >> en-US
zh-Hant-CN, en >> en-US
zh-Hans, en >> zh-Hans-CN
** test: MaxBeforeEquals
# Compare maximized forms of earlier items before testing equality
# of later items.
@supported=en, fr-CA
en-US, fr-CA >> en
@favor=script
en-US, fr-CA >> en
** test: SiblingDefaultRegion
@supported=de-AT, de-DE, de-CH
de >> de-DE
** test: ReturnDefaultInsteadOfNullForEmptyPriorityList
@default=und
de >> und
** test: ReturnSpecifiedDefaultForNoMatch
@supported=de, en, fr
@default=und
hi >> und
@favor=script
hi >> und
** test: MatchedLanguageIgnoresDefault
@supported=de, en, fr
@default=und
fr >> fr
@favor=script
fr >> fr
## GenX
** test: TwoSpanishes
@supported=es, es-MX
@default=und
es-001 >> es
und >> und
ca >> und
gl-ES >> es
es >> es
es-MX >> es-MX
es-002 >> es
es-003 >> es-MX
es-005 >> es-MX
es-019 >> es-MX
es-029 >> es-MX
es-419 >> es-MX
es-142 >> es
es-150 >> es
es-AD >> es
es-AR >> es-MX
es-BO >> es-MX
es-BZ >> es-MX
es-CA >> es-MX
es-CL >> es-MX
es-CO >> es-MX
es-CR >> es-MX
es-CU >> es-MX
es-DO >> es-MX
es-EC >> es-MX
es-ES >> es
es-GI >> es
es-GQ >> es
es-GT >> es-MX
es-HN >> es-MX
es-NI >> es-MX
es-PA >> es-MX
es-PE >> es-MX
es-PH >> es
es-PR >> es-MX
es-PY >> es-MX
es-SV >> es-MX
es-US >> es-MX
es-UY >> es-MX
es-VE >> es-MX
@favor=script
es-001 >> es
und >> und
ca >> es
gl-ES >> es
es >> es
es-MX >> es-MX
es-002 >> es
es-003 >> es-MX
es-005 >> es-MX
es-019 >> es-MX
es-029 >> es-MX
es-419 >> es-MX
es-142 >> es
es-150 >> es
es-AD >> es
es-AR >> es-MX
es-BO >> es-MX
es-BZ >> es-MX
es-CA >> es-MX
es-CL >> es-MX
es-CO >> es-MX
es-CR >> es-MX
es-CU >> es-MX
es-DO >> es-MX
es-EC >> es-MX
es-ES >> es
es-GI >> es
es-GQ >> es
es-GT >> es-MX
es-HN >> es-MX
es-NI >> es-MX
es-PA >> es-MX
es-PE >> es-MX
es-PH >> es
es-PR >> es-MX
es-PY >> es-MX
es-SV >> es-MX
es-US >> es-MX
es-UY >> es-MX
es-VE >> es-MX
** test: Three Spanishes
@supported=es, es-419, es-MX
@default=und
es-001 >> es
und >> und
ca >> und
gl-ES >> es
es >> es
es-419 >> es-419
es-002 >> es
es-003 >> es-419
es-005 >> es-419
es-019 >> es-419
es-029 >> es-419
es-142 >> es
es-150 >> es
es-AD >> es
es-AR >> es-419
es-BO >> es-419
es-BZ >> es-419
es-CA >> es-419
es-CL >> es-419
es-CO >> es-419
es-CR >> es-419
es-CU >> es-419
es-DO >> es-419
es-EC >> es-419
es-ES >> es
es-GI >> es
es-GQ >> es
es-GT >> es-419
es-HN >> es-419
es-MX >> es-MX
es-NI >> es-419
es-PA >> es-419
es-PE >> es-419
es-PH >> es
es-PR >> es-419
es-PY >> es-419
es-SV >> es-419
es-US >> es-419
es-UY >> es-419
es-VE >> es-419
@favor=script
es-001 >> es
und >> und
ca >> es
gl-ES >> es
es >> es
es-419 >> es-419
es-002 >> es
es-003 >> es-419
es-005 >> es-419
es-019 >> es-419
es-029 >> es-419
es-142 >> es
es-150 >> es
es-AD >> es
es-AR >> es-419
es-BO >> es-419
es-BZ >> es-419
es-CA >> es-419
es-CL >> es-419
es-CO >> es-419
es-CR >> es-419
es-CU >> es-419
es-DO >> es-419
es-EC >> es-419
es-ES >> es
es-GI >> es
es-GQ >> es
es-GT >> es-419
es-HN >> es-419
es-MX >> es-MX
es-NI >> es-419
es-PA >> es-419
es-PE >> es-419
es-PH >> es
es-PR >> es-419
es-PY >> es-419
es-SV >> es-419
es-US >> es-419
es-UY >> es-419
es-VE >> es-419
** test: Englishes
@supported=en-GB, en-US
@default=und
und >> und
ja >> und
fr-CA >> und
# Great Britain fallback
en-AU >> en-GB
en-BZ >> en-GB
en-CA >> en-GB
en-IN >> en-GB
en-IE >> en-GB
en-JM >> en-GB
en-NZ >> en-GB
en-PK >> en-GB
en-TT >> en-GB
en-ZA >> en-GB
# United States fallback
en-US >> en-US
en >> en-US
@favor=script
und >> und
ja >> und
fr-CA >> en-US
en-AU >> en-GB
en-BZ >> en-GB
en-CA >> en-GB
en-IN >> en-GB
en-IE >> en-GB
en-JM >> en-GB
en-NZ >> en-GB
en-PK >> en-GB
en-TT >> en-GB
en-ZA >> en-GB
en-US >> en-US
en >> en-US
** test: TestFallback
# manyEnMatcher
@supported=en-GB, en-US, en, en-AU
@default=und
und >> und
ja >> und
fr-CA >> und
# nonUsMatcher
fr >> und
# onlyAuMatcher
@supported=en-AU, ja, ca
fr >> und
# noEnMatcher
@supported=pl, ja, ca
fr >> und
@favor=script
@supported=en-GB, en-US, en, en-AU
und >> und
ja >> und
fr-CA >> en-US
fr >> en-US
@supported=en-AU, ja, ca
fr >> en-AU
@supported=pl, ja, ca
fr >> pl
## Go
** test: basics
@supported=fr, en-GB, en
en-GB >> en-GB
en-US >> en
fr-FR >> fr
ja-JP >> fr
** test: script fallbacks
@supported=zh-CN, zh-TW, iw
zh-Hant >> zh-TW
zh >> zh-CN
zh-Hans-CN >> zh-CN
zh-Hant-HK >> zh-TW
@default=iw
he-IT >> iw
@favor=script
he-IT >> iw
** test: language-specific script fallbacks 1
@supported=en, sr, nl
sr-Latn >> sr
sh >> en
hr >> en
bs >> en
nl-Cyrl >> en # Mark: Expected value should be en not sr. Script difference exceeds threshold, so can't be nl
@favor=script
sr-Latn >> sr
hr >> en
bs >> en
nl-Cyrl >> sr
** test: language-specific script fallbacks 2
@supported=en, sr-Latn
sr >> sr-Latn
sr-Cyrl >> sr-Latn
@default=und
hr >> und
@favor=script
@default=
sr >> sr-Latn
sr-Cyrl >> sr-Latn
@default=und
hr >> en
** test: don't match hr to sr-Latn
@supported=en, sr-Latn
hr >> en
@favor=script
hr >> en
** test: both deprecated and not
@supported=fil, tl, iw, he
he-IT >> iw
he >> iw
iw >> iw
fil-IT >> fil
fil >> fil
tl >> fil
@favor=script
he-IT >> iw
he >> iw
iw >> iw
fil-IT >> fil
fil >> fil
tl >> fil
** test: nearby languages: Nynorsk to Bokmål
@supported=en, nb
nn >> nb
@favor=script
nn >> nb
** test: nearby languages: Danish does not match nn
@supported=en, nn
da >> en
@favor=script
da >> en
** test: nearby languages: Danish matches no
@supported=en, no
da >> no
@favor=script
da >> no
** test: nearby languages: Danish matches nb
@supported=en, nb
da >> nb
** test: prefer matching languages over language variants.
@supported=nn, en-GB
no, en-US >> nn
nb, en-US >> nn
@favor=script
no, en-US >> nn
nb, en-US >> nn
** test: deprecated version is closer than same language with other differences
@supported=nl, he, en-GB
iw, en-US >> he
@favor=script
iw, en-US >> he
** test: macro equivalent is closer than same language with other differences
@supported=nl, zh, en-GB, no
cmn, en-US >> zh
nb, en-US >> no
@favor=script
cmn, en-US >> zh
nb, en-US >> no
** test: legacy equivalent is closer than same language with other differences
@supported=nl, fil, en-GB
tl, en-US >> fil
@favor=script
tl, en-US >> fil
** test: distinguish near equivalents
@supported=en, ro, mo, ro-MD
ro >> ro
mo >> ro # ro=mo for the locale matcher
ro-MD >> ro-MD
@favor=script
ro >> ro
mo >> ro # ro=mo for the locale matcher
ro-MD >> ro-MD
** test: maximization of legacy
@supported=sr-Cyrl, sr-Latn, ro, ro-MD
sh >> sr-Latn
mo >> ro
@favor=script
sh >> sr-Latn
mo >> ro
** test: empty
fr >> null
en >> null
** test: private use subtags
@supported=fr, en-GB, x-bork, es-ES, es-419
x-piglatin >> fr
x-bork >> x-bork
** test: grandfathered codes
@supported=fr, i-klingon, en-Latn-US
en-GB-oed >> en-Latn-US
i-klingon >> tlh
** test: simple variant match
@supported=fr, en-GB, ja, es-ES, es-MX
de, en-US >> en-GB
de, zh >> fr
** test: best match for traditional Chinese
@supported=fr, zh-Hans-CN, en-US
zh-TW >> zh-Hans-CN
zh-Hant >> zh-Hans-CN
zh-TW, en >> en-US
zh-Hant-CN, en >> en-US
zh-Hans, en >> zh-Hans-CN
** test: return most originally similar among likely-subtags equivalent locales
@supported=af, af-Latn, af-Arab
af >> af
af-ZA >> af
af-Latn-ZA >> af-Latn
af-Latn >> af-Latn
@favor=script
af >> af
af-ZA >> af
af-Latn-ZA >> af-Latn
af-Latn >> af-Latn
@supported=nl, nl-NL, nl-BE
@favor=
nl >> nl
nl-Latn >> nl
nl-Latn-NL >> nl-NL
nl-NL >> nl-NL
@favor=script
nl >> nl
nl-Latn >> nl
nl-Latn-NL >> nl-NL
nl-NL >> nl-NL
@supported=nl, nl-Latn, nl-NL, nl-BE
@favor=
nl >> nl
nl-Latn >> nl-Latn
nl-NL >> nl-NL
nl-Latn-NL >> nl-Latn
@favor=script
nl >> nl
nl-Latn >> nl-Latn
nl-NL >> nl-NL
nl-Latn-NL >> nl-Latn
** test: region may replace matched if matched is enclosing
@supported=es-419, es
@default=es-MX
es-MX >> es-419
@default=
es-SG >> es
@favor=script
@default=es-MX
es-MX >> es-419
@default=
es-SG >> es
** test: region distance Portuguese
@supported=pt, pt-PT
pt-ES >> pt-PT
@favor=script
pt-ES >> pt-PT
** test: if no preferred locale specified, pick top language, not regional
@supported=en, fr, fr-CA, fr-CH
fr-US >> fr
@favor=script
fr-US >> fr
** test: region distance German
@supported=de-AT, de-DE, de-CH
de >> de-DE
** test: en-AU is closer to en-GB than to en (which is en-US)
@supported=en, en-GB, es-ES, es-419
en-AU >> en-GB
@default=es-MX
es-MX >> es-419
@default=
es-PT >> es-ES
@favor=script
en-AU >> en-GB
es-MX >> es-419
@default=
es-PT >> es-ES
** test: undefined
@supported=it, fr
und >> it
** test: und does not match en
@supported=it, en
und >> it
** test: undefined in priority list
@supported=it, und
und >> und
en >> it
** test: undefined
@supported=it, fr, zh
und-FR >> fr
und-CN >> zh
und-Hans >> zh
und-Hant >> zh
und-Latn >> it
@favor=script
und-FR >> fr
und-CN >> zh
und-Hans >> zh
und-Hant >> zh
und-Latn >> it
** test: match on maximized tag
@supported=fr, en-GB, ja, es-ES, es-MX
ja-JP, en-GB >> ja
ja-Jpan-JP, en-GB >> ja
** test: pick best maximized tag
@supported=ja, ja-Jpan-US, ja-JP, en, ru
ja-Jpan, ru >> ja
ja-JP, ru >> ja-JP
ja-US, ru >> ja-Jpan-US
@favor=script
ja-Jpan, ru >> ja
ja-JP, ru >> ja-JP
ja-US, ru >> ja-Jpan-US
** test: termination: pick best maximized match
@supported=ja, ja-Jpan, ja-JP, en, ru
ja-Jpan-JP, ru >> ja-Jpan
ja-Jpan, ru >> ja-Jpan
@favor=script
ja-Jpan-JP, ru >> ja-Jpan
ja-Jpan, ru >> ja-Jpan
** test: same language over exact, but distinguish when user is explicit
@supported=fr, en-GB, ja, es-ES, es-MX
ja, de >> ja
@supported=en, de, fr, ja
de-CH, fr >> de
@supported=en-GB, nl
en, nl >> en-GB
en, nl, en-GB >> en-GB
@favor=script
@supported=fr, en-GB, ja, es-ES, es-MX
ja, de >> ja
@supported=en, de, fr, ja
de-CH, fr >> de
@supported=en-GB, nl
en, nl >> en-GB
en, nl, en-GB >> en-GB
** test: parent relation preserved
@supported=en, en-US, en-GB, es, es-419, pt, pt-BR, pt-PT, zh, zh-Hant, zh-Hant-HK
en-150 >> en-GB
en-AU >> en-GB
en-BE >> en-GB
en-GG >> en-GB
en-GI >> en-GB
en-HK >> en-GB
en-IE >> en-GB
en-IM >> en-GB
en-IN >> en-GB
en-JE >> en-GB
en-MT >> en-GB
en-NZ >> en-GB
en-PK >> en-GB
en-SG >> en-GB
en-DE >> en-GB
@default=es-AR
es-AR >> es-419
@default=es-BO
es-BO >> es-419
@default=es-CL
es-CL >> es-419
@default=es-CO
es-CO >> es-419
@default=es-CR
es-CR >> es-419
@default=es-CU
es-CU >> es-419
@default=es-DO
es-DO >> es-419
@default=es-EC
es-EC >> es-419
@default=es-GT
es-GT >> es-419
@default=es-HN
es-HN >> es-419
@default=es-MX
es-MX >> es-419
@default=es-NI
es-NI >> es-419
@default=es-PA
es-PA >> es-419
@default=es-PE
es-PE >> es-419
@default=es-PR
es-PR >> es-419
@default=
es-PT >> es
@default=es-PY
es-PY >> es-419
@default=es-SV
es-SV >> es-419
@default=
es-US >> es-419
@default=es-UY
es-UY >> es-419
@default=es-VE
es-VE >> es-419
@default=
pt-AO >> pt-PT
pt-CV >> pt-PT
pt-GW >> pt-PT
pt-MO >> pt-PT
pt-MZ >> pt-PT
pt-ST >> pt-PT
pt-TL >> pt-PT
@favor=script
en-150 >> en-GB
en-AU >> en-GB
en-BE >> en-GB
en-GG >> en-GB
en-GI >> en-GB
en-HK >> en-GB
en-IE >> en-GB
en-IM >> en-GB
en-IN >> en-GB
en-JE >> en-GB
en-MT >> en-GB
en-NZ >> en-GB
en-PK >> en-GB
en-SG >> en-GB
en-DE >> en-GB
@default=es-AR
es-AR >> es-419
@default=es-BO
es-BO >> es-419
@default=es-CL
es-CL >> es-419
@default=es-CO
es-CO >> es-419
@default=es-CR
es-CR >> es-419
@default=es-CU
es-CU >> es-419
@default=es-DO
es-DO >> es-419
@default=es-EC
es-EC >> es-419
@default=es-GT
es-GT >> es-419
@default=es-HN
es-HN >> es-419
@default=es-MX
es-MX >> es-419
@default=es-NI
es-NI >> es-419
@default=es-PA
es-PA >> es-419
@default=es-PE
es-PE >> es-419
@default=es-PR
es-PR >> es-419
@default=
es-PT >> es
@default=es-PY
es-PY >> es-419
@default=es-SV
es-SV >> es-419
@default=
es-US >> es-419
@default=es-UY
es-UY >> es-419
@default=es-VE
es-VE >> es-419
@default=
pt-AO >> pt-PT
pt-CV >> pt-PT
pt-GW >> pt-PT
pt-MO >> pt-PT
pt-MZ >> pt-PT
pt-ST >> pt-PT
pt-TL >> pt-PT
** test: preserve extensions
@supported=en, de, sl-NEDIS
@default=de-u-co-phonebk
de-FR-u-co-phonebk >> de
@default=sl-NEDIS-u-cu-eur
sl-NEDIS-u-cu-eur >> sl-NEDIS
sl-u-cu-eur >> sl-NEDIS
sl-HR-NEDIS-u-cu-eur >> sl-NEDIS
@default=de-t-m0-iso-i0-pinyin
de-t-m0-iso-i0-pinyin >> de
@favor=script
@default=de-u-co-phonebk
de-FR-u-co-phonebk >> de
@default=sl-NEDIS-u-cu-eur
sl-NEDIS-u-cu-eur >> sl-NEDIS
sl-u-cu-eur >> sl-NEDIS
sl-HR-NEDIS-u-cu-eur >> sl-NEDIS
@default=de-t-m0-iso-i0-pinyin
de-t-m0-iso-i0-pinyin >> de
## ULS
** test: testEmptyUserLanguagesGetsEmpty_getBestMatches
@supported=de
>> de
** test: testNoStrongMatchGetsEmpty_getBestMatches
@supported=de
fr >> de
@favor=script
fr >> de
** test: testLooseMatchForGeneral_getBestMatches
@supported=es-419
es-MX >> es-419
@favor=script
es-MX >> es-419
** test: testLooseMatchForEnglish_getBestMatches
@supported=en, en-GB
en-CA >> en-GB
@favor=script
en-CA >> en-GB
** test: testLooseMatchForChinese_getBestMatches
@supported=zh
zh-TW >> zh
@favor=script
zh-TW >> zh
## Geo
** test: testGetBestMatchWithMinMatchScore
@supported=fr-FR, fr, fr-CA, en
@default=und
fr >> fr
@supported=en, fr, fr-CA
fr-FR >> fr # Parent match is chosen.
@supported=en, fr-CA
fr-FR >> fr-CA # Sibling match is chosen.
@supported=fr-CA, fr-FR
fr >> fr-FR # Inferred region match is chosen.
fr-SN >> fr-FR
@supported=en, fr-FR
fr >> fr-FR # Child match is chosen.
@supported=de, en, it
fr >> und
@supported=iw, en
iw-Latn >> und
@supported=iw, no
ru >> und
@supported=iw-Latn, iw-Cyrl, iw
ru >> und
@supported=iw, iw-Latn
ru >> und
en >> und
@supported=en, uk
ru >> und
@supported=zh-TW, en
zh-CN >> zh-TW
@supported=ja
ru >> und
@favor=script
@supported=fr-FR, fr, fr-CA, en
fr >> fr
@supported=en, fr, fr-CA
fr-FR >> fr
@supported=en, fr-CA
fr-FR >> fr-CA
@supported=fr-CA, fr-FR
fr >> fr-FR
fr-SN >> fr-FR
@supported=en, fr-FR
fr >> fr-FR
@supported=de, en, it
fr >> en
@supported=iw, en
iw-Latn >> en
@supported=iw, no
ru >> und
@supported=iw-Latn, iw-Cyrl, iw
ru >> iw-Cyrl
@supported=iw, iw-Latn
ru >> und
en >> iw-Latn
@supported=en, uk
ru >> uk
@supported=zh-TW, en
zh-CN >> zh-TW
@supported=ja
ru >> und
** test: favor a more-default locale among equally imperfect matches
@supported=fr-CA, fr-CH, fr-FR, fr-GB
fr-SN >> fr-FR
@supported=sr-Latn, sr-Cyrl, sr-Grek
@threshold=60
sr-Thai >> sr-Cyrl