11 | | /* Valid languages are extracted from <http://de.wikipedia.org/w/api.php?action=sitematrix&format=xml>, which may change, so this is a warning only. */ |
12 | | *[wikipedia =~ /^[a-zA-Z_-]{2,12}:/][wikipedia !~ /^https?:\/\//][wikipedia !~ /^(aa|ab|ace|af|ak|als|am|an|ang|ar|arc|arz|as|ast|av|ay|az|ba|bar|bat-smg|bcl|be|be-x-old|bg|bh|bi|bjn|bm|bn|bo|bpy|br|bs|bug|bxr|ca|cbk-zam|cdo|ce|ceb|ch|cho|chr|chy|ckb|co|cr|crh|cs|csb|cu|cv|cy|cz|da|de|diq|dk|dsb|dv|dz|ee|el|eml|en|eo|epo|es|et|eu|ext|fa|ff|fi|fiu-vro|fj|fo|fr|frp|frr|fur|fy|ga|gag|gan|gd|gl|glk|gn|got|gu|gv|ha|hak|haw|he|hi|hif|ho|hr|hsb|ht|hu|hy|hz|ia|id|ie|ig|ii|ik|ilo|io|is|it|iu|ja|jbo|jp|jv|ka|kaa|kab|kbd|kg|ki|kj|kk|kl|km|kn|ko|koi|kr|krc|ks|ksh|ku|kv|kw|ky|la|lad|lb|lbe|lez|lg|li|lij|lmo|ln|lo|lt|ltg|lv|map-bms|mdf|mg|mh|mhr|mi|minnan|mk|ml|mn|mo|mr|mrj|ms|mt|mus|mwl|my|myv|mzn|na|nah|nan|nap|nb|nds|nds-nl|ne|new|ng|nl|nn|no|nov|nrm|nso|nv|ny|oc|om|or|os|pa|pag|pam|pap|pcd|pdc|pfl|pi|pih|pl|pms|pnb|pnt|ps|pt|qu|rm|rmy|rn|ro|roa-rup|roa-tara|ru|rue|rw|sa|sah|sc|scn|sco|sd|se|sg|sh|si|simple|sk|sl|sm|sn|so|sq|sr|srn|ss|st|stq|su|sv|sw|szl|ta|te|tet|tg|th|ti|tk|tl|tn|to|tpi|tr|ts|tt|tum|tw|ty|udm|ug|uk|ur|uz|ve|vec|vep|vi|vls|vo|wa|war|wo|wuu|xal|xh|xmf|yi|yo|za|zea|zh|zh-cfr|zh-classical|zh-min-nan|zh-yue|zu):/] { |
| 11 | /* Valid languages are extracted from <https://www.wikidata.org/w/api.php?action=help&modules=wbgetentities> (languages field), which may change, so this is a warning only. |
| 12 | Also includes "cz" and "be-x-old" because they can be auto-fixed */ |
| 13 | *[wikipedia =~ /^[-a-z]{2,12}:/][wikipedia !~ /^https?:\/\//][wikipedia !~ /^(aa|ab|ace|ady|ady-cyrl|aeb|aeb-arab|aeb-latn|af|ak|aln|als|am|an|ang|anp|ar|arc|arn|arq|ary|arz|as|ase|ast|av|avk|awa|ay|az|azb|ba|ban|bar|bat-smg|bbc|bbc-latn|bcc|bcl|be|be-tarask|be-x-old|bg|bgn|bh|bho|bi|bjn|bm|bn|bo|bpy|bqi|br|brh|bs|bto|bug|bxr|ca|cbk-zam|cdo|ce|ceb|ch|cho|chr|chy|ckb|co|cps|cr|crh|crh-cyrl|crh-latn|cs|csb|cu|cv|cy|cz|da|de|de-at|de-ch|de-formal|din|diq|dsb|dtp|dty|dv|dz|ee|egl|el|eml|en|en-ca|en-gb|eo|es|et|eu|ext|fa|ff|fi|fit|fiu-vro|fj|fo|fr|frc|frp|frr|fur|fy|ga|gag|gan|gan-hans|gan-hant|gd|gl|glk|gn|gom|gom-deva|gom-latn|gor|got|grc|gsw|gu|gv|ha|hak|haw|he|hi|hif|hif-latn|hil|ho|hr|hrx|hsb|ht|hu|hy|hz|ia|id|ie|ig|ii|ik|ike-cans|ike-latn|ilo|inh|io|is|it|iu|ja|jam|jbo|jut|jv|ka|kaa|kab|kbd|kbd-cyrl|kea|kg|khw|ki|kiu|kj|kk|kk-arab|kk-cn|kk-cyrl|kk-kz|kk-latn|kk-tr|kl|km|kn|ko|ko-kp|koi|kr|krc|kri|krj|krl|ks|ks-arab|ks-deva|ksh|ku|ku-arab|ku-latn|kv|kw|ky|la|lad|lb|lbe|lez|lfn|lg|li|lij|liv|lki|lmo|ln|lo|loz|lrc|lt|ltg|lus|luz|lv|lzh|lzz|mai|map-bms|mdf|mg|mh|mhr|mi|min|mk|ml|mn|mo|mr|mrj|ms|mt|mus|mwl|my|myv|mzn|na|nah|nan|nap|nb|nds|nds-nl|ne|new|ng|niu|nl|nl-informal|nn|no|nod|nov|nrm|nso|nv|ny|nys|oc|olo|om|or|os|ota|pa|pag|pam|pap|pcd|pdc|pdt|pfl|pi|pih|pl|pms|pnb|pnt|prg|ps|pt|pt-br|qu|qug|rgn|rif|rm|rmy|rn|ro|roa-rup|roa-tara|ru|rue|rup|ruq|ruq-cyrl|ruq-latn|rw|rwr|sa|sah|sat|sc|scn|sco|sd|sdc|sdh|se|sei|ses|sg|sgs|sh|shi|shi-latn|shi-tfng|shn|si|simple|sje|sk|sl|sli|sm|sma|smj|sn|so|sq|sr|sr-ec|sr-el|srn|srq|ss|st|stq|su|sv|sw|szl|ta|tcy|te|tet|tg|tg-cyrl|tg-latn|th|ti|tk|tl|tly|tn|to|tokipona|tpi|tr|tru|ts|tt|tt-cyrl|tt-latn|tum|tw|ty|tyv|tzm|udm|ug|ug-arab|ug-latn|uk|ur|uz|uz-cyrl|uz-latn|ve|vec|vep|vi|vls|vmf|vo|vot|vro|wa|war|wo|wuu|xal|xh|xmf|yi|yo|yue|za|zea|zh|zh-classical|zh-cn|zh-hans|zh-hant|zh-hk|zh-min-nan|zh-mo|zh-my|zh-sg|zh-tw|zh-yue|zu):/] { |
| 26 | |
| 27 | *[wikipedia =~ /^be-x-old:/] { |
| 28 | throwWarning: tr("''be-x-old'' wikipedia language is obsolete, use ''be-tarask'' instead"); |
| 29 | fixAdd: concat("wikipedia=be-tarask:", get(regexp_match("^be-x-old:(.+)$", tag("wikipedia")),1)); |
| 30 | assertMatch: "node wikipedia=be-x-old:foo"; |
| 31 | assertNoMatch: "node wikipedia=abe-x-old:foo"; |
| 32 | } |
| 33 | |
| 34 | *[wikipedia =~ /^cz:/] { |
| 35 | throwWarning: tr("''cz'' wikipedia language is invalid, use ''cs'' instead"); |
| 36 | fixAdd: concat("wikipedia=cs:", get(regexp_match("^cz:(.+)$", tag("wikipedia")),1)); |
| 37 | assertMatch: "node wikipedia=cz:foo"; |
| 38 | assertNoMatch: "node wikipedia=en:cz:foo"; |
| 39 | } |
| 40 | |
| 41 | *[wikipedia =~ /^[-a-z]{2,12}: /] { |
| 42 | throwWarning: tr("there should be no space after the wikipedia language code"); |
| 43 | fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.*)$", tag("wikipedia")),1), trim(get(regexp_match("^([-a-z]+:) +(.*)$", tag("wikipedia")),2))); |
| 44 | assertMatch: "node wikipedia=en: foo"; |
| 45 | assertNoMatch: "node wikipedia=en:foo"; |
| 46 | } |
| 47 | |
| 48 | /* All wikipedias except "jbo" automatically capitalize first letter of the page title. |
| 49 | To see the latest list, see <https://noc.wikimedia.org/conf/highlight.php?file=InitialiseSettings.php> |
| 50 | and look for 'wgCapitalLinks' setting. */ |
| 51 | *[wikipedia =~ /^[-a-z]{2,12}:\p{Ll}/][wikipedia !~ /^jbo:/] { |
| 52 | throwWarning: tr("wikipedia page title should have first letter capitalized"); |
| 53 | fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.)(.*)$", tag("wikipedia")),1), upper(get(regexp_match("^([-a-z]+:)(.)(.*)$", tag("wikipedia")),2)), get(regexp_match("^([-a-z]+:)(.)(.*)$", tag("wikipedia")),3)); |
| 54 | assertMatch: "node wikipedia=en:foo"; |
| 55 | assertNoMatch: "node wikipedia=en:Foo"; |
| 56 | assertMatch: "node wikipedia=ru:абв"; |
| 57 | assertNoMatch: "node wikipedia=ru:Абв"; |
| 58 | } |
| 59 | |
| 60 | *[wikipedia =~ /^[-a-z]{2,12}:.*_/] { |
| 61 | throwWarning: tr("wikipedia page title should have spaces instead of underscores (''_''→'' '')"); |
| 62 | fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),1), trim(replace(get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),2), "_", " "))); |
| 63 | assertMatch: "node wikipedia=en:foo_bar"; |
| 64 | assertNoMatch: "node wikipedia=en:foo bar"; |
| 65 | } |