Index: data/validator/wikipedia.mapcss =================================================================== --- data/validator/wikipedia.mapcss (revision 11650) +++ data/validator/wikipedia.mapcss (working copy) @@ -1,24 +1,110 @@ /* validation for the wikipedia=* tag - see ticket #8383 */ /* If there is no language at all, this is broken. Also catches 'wikipedia' used as 'email', 'website', 'ele' [sic!] ... */ -*[wikipedia][wikipedia !~ /^[a-zA-Z_-]{2,12}:/] { - throwError: tr("no wikipedia-language given, use ''wikipedia''=''language:page title''"); +*[wikipedia][wikipedia !~ /^[-a-z]{2,12}:/] { + throwError: tr("wikipedia tag has no language given, use ''wikipedia''=''language:page title''"); assertMatch: "node wikipedia=Foobar"; assertNoMatch: "node wikipedia=en:Foobar"; assertNoMatch: "node wikipedia=en-GB:Foobar"; } -/* Valid languages are extracted from , which may change, so this is a warning only. */ -*[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):/] { - throwWarning: tr("unknown language prefix in wikipedia tag"); +/* Valid languages are extracted from (languages field), which may change, so this is a warning only. + Also includes "cz" and "be-x-old" because they can be auto-fixed */ +*[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):/] { + throwWarning: tr("wikipedia tag has an unknown language prefix"); assertMatch: "node wikipedia=X-Y-Z:Foobar"; assertNoMatch: "node wikipedia=en:Foobar"; } -*[wikipedia =~ /https?:\/\//] { - throwWarning: tr("deprecated format for wikipedia tag"); +*[wikipedia =~ /^https?:\/\//], +*[wikipedia =~ /^[-a-z]{2,12}:https?:\/\//] { + throwWarning: tr("wikipedia tag format is deprecated"); suggestAlternative: tr("''wikipedia''=''language:page title''"); group: tr("deprecated tagging"); assertMatch: "node wikipedia=http://en.wikipedia.org/wiki/OpenStreetMap"; assertNoMatch: "node wikipedia=en:OpenStreetMap"; } + +*[wikipedia =~ /^be-x-old:/] { + throwWarning: tr("wikipedia ''be-x-old'' language is obsolete, use ''be-tarask'' instead"); + fixAdd: concat("wikipedia=be-tarask:", get(regexp_match("^be-x-old:(.+)$", tag("wikipedia")),1)); + assertMatch: "node wikipedia=be-x-old:foo"; + assertNoMatch: "node wikipedia=abe-x-old:foo"; +} + +*[wikipedia =~ /^cz:/] { + throwWarning: tr("wikipedia ''cz'' language is invalid, use ''cs'' instead"); + fixAdd: concat("wikipedia=cs:", get(regexp_match("^cz:(.+)$", tag("wikipedia")),1)); + assertMatch: "node wikipedia=cz:foo"; + assertNoMatch: "node wikipedia=en:cz:foo"; +} + +*[wikipedia =~ /^[-a-z]{2,12}:.*%[0-9A-F][0-9A-F]/] { + throwError: tr("wikipedia title should not have URL-encoded values like ''%27''"); + fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.*)$", tag("wikipedia")),1), trim(replace(URL_decode(get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),2)), "_", " "))); + assertMatch: "node wikipedia=en:Foo%27s"; + assertNoMatch: "node wikipedia=en:Foo"; +} + +*[wikipedia =~ /^[-a-z]{2,12}: /] { + throwWarning: tr("wikipedia title should not start with a space after language code"); + fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.*)$", tag("wikipedia")),1), trim(get(regexp_match("^([-a-z]+:)(.*)$", tag("wikipedia")),2))); + assertMatch: "node wikipedia=en: foo"; + assertNoMatch: "node wikipedia=en:foo"; +} + +*[wikipedia =~ /^[-a-z]{2,12}:wiki\//] { + throwWarning: tr("wikipedia title should not have ''wiki/'' prefix"); + fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)wiki/(.*)$", tag("wikipedia")),1), trim(get(regexp_match("^([-a-z]+:)wiki/(.*)$", tag("wikipedia")),2))); + assertMatch: "node wikipedia=en: foo"; + assertNoMatch: "node wikipedia=en:foo"; +} + +/* All wikipedias except "jbo" automatically capitalize first letter of the page title. + To see the latest list, see + and look for 'wgCapitalLinks' setting. */ +*[wikipedia =~ /^[-a-z]{2,12}:\p{Ll}/][wikipedia !~ /^jbo:/][wikipedia !~ /^[-a-z]{2,12}:https?:/] { + throwWarning: tr("wikipedia page title should have first letter capitalized"); + 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]+:)(.)(.*)$", tag("wikipedia")),3)); + assertMatch: "node wikipedia=en:foo"; + assertNoMatch: "node wikipedia=en:Foo"; + assertMatch: "node wikipedia=ru:абв"; + assertNoMatch: "node wikipedia=ru:Абв"; +} + +*[wikipedia =~ /^[-a-z]{2,12}:.*_/][wikipedia !~ /^[-a-z]{2,12}:https?:/] { + throwWarning: tr("wikipedia page title should have spaces instead of underscores (''_''→'' '')"); + fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),1), trim(replace(get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),2), "_", " "))); + assertMatch: "node wikipedia=en:foo_bar"; + assertNoMatch: "node wikipedia=en:foo bar"; +} + +*[wikipedia ^= "da:da:"], +*[wikipedia ^= "da:dk:"], +*[wikipedia ^= "de:de:"], +*[wikipedia ^= "dk:dk:"], +*[wikipedia ^= "en:de:"], +*[wikipedia ^= "en:en:"], +*[wikipedia ^= "en:es:"], +*[wikipedia ^= "en:eu:"], +*[wikipedia ^= "en:fr:"], +*[wikipedia ^= "en:ja:"], +*[wikipedia ^= "en:pl:"], +*[wikipedia ^= "en:pt:"], +*[wikipedia ^= "en:zh:"], +*[wikipedia ^= "es:es:"], +*[wikipedia ^= "eu:eu:"], +*[wikipedia ^= "fr:fr:"], +*[wikipedia ^= "ja:ja:"], +*[wikipedia ^= "pl:en:"], +*[wikipedia ^= "pl:pl:"], +*[wikipedia ^= "pt:pt:"], +*[wikipedia ^= "ru:fr:"], +*[wikipedia ^= "ru:ru:"], +*[wikipedia ^= "zh:zh:"] { + throwWarning: tr("wikipedia language seems to be duplicated, e.g. en:en:Foo"); + fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)([-a-z]+:)(.*)$", tag("wikipedia")),2), trim(get(regexp_match("^([-a-z]+:)([-a-z]+:)(.*)$", tag("wikipedia")),3))); + assertMatch: "node wikipedia=en:en:Foo"; + assertMatch: "node wikipedia=en:fr:Foo"; + assertNoMatch: "node wikipedia=en:Bar"; +} Index: src/org/openstreetmap/josm/gui/mappaint/mapcss/ExpressionFactory.java =================================================================== --- src/org/openstreetmap/josm/gui/mappaint/mapcss/ExpressionFactory.java (revision 11650) +++ src/org/openstreetmap/josm/gui/mappaint/mapcss/ExpressionFactory.java (working copy) @@ -831,6 +831,51 @@ } /** + * Converts string {@code s} to uppercase. + * @param s The source string + * @return The resulting string + * @see String#toUpperCase() + */ + public static String upper(String s) { + return s == null ? null : s.toUpperCase(); + } + + /** + * Converts string {@code s} to lowercase. + * @param s The source string + * @return The resulting string + * @see String#toLowerCase() + */ + public static String lower(String s) { + return s == null ? null : s.toLowerCase(); + } + + /** + * Trim whitespaces from the string {@code s}. + * @param s The source string + * @return The resulting string + * @see String#trim() + */ + public static String trim(String s) { + return s == null ? null : s.trim(); + } + + /** + * Percent-decode a string. (See https://en.wikipedia.org/wiki/Percent-encoding) + * This is especially useful for wikipedia titles + * @param s url-encoded string + * @return the decoded string, or original in case of an error + */ + public static String URL_decode(String s) { + if (s == null) return null; + try { + return Utils.decodeUrl(s); + } catch (java.lang.Exception e) { + return s; + } + } + + /** * Percent-encode a string. (See https://en.wikipedia.org/wiki/Percent-encoding) * This is especially useful for data urls, e.g. * concat("data:image/svg+xml,", URL_encode("<svg>...</svg>"));