Ticket #14425: wikipedia-validations.3.patch
File wikipedia-validations.3.patch, 10.9 KB (added by , 7 years ago) |
---|
-
data/validator/wikipedia.mapcss
1 1 /* validation for the wikipedia=* tag - see ticket #8383 */ 2 2 3 3 /* If there is no language at all, this is broken. Also catches 'wikipedia' used as 'email', 'website', 'ele' [sic!] ... */ 4 *[wikipedia][wikipedia !~ /^[ a-zA-Z_-]{2,12}:/] {5 throwError: tr(" no wikipedia-language given, use ''wikipedia''=''language:page title''");4 *[wikipedia][wikipedia !~ /^[-a-z]{2,12}:/] { 5 throwError: tr("wikipedia tag has no language given, use ''wikipedia''=''language:page title''"); 6 6 assertMatch: "node wikipedia=Foobar"; 7 7 assertNoMatch: "node wikipedia=en:Foobar"; 8 8 assertNoMatch: "node wikipedia=en-GB:Foobar"; 9 9 } 10 10 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):/] { 13 throwWarning: tr("unknown language prefix in wikipedia tag"); 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):/] { 14 throwWarning: tr("wikipedia tag has an unknown language prefix"); 14 15 assertMatch: "node wikipedia=X-Y-Z:Foobar"; 15 16 assertNoMatch: "node wikipedia=en:Foobar"; 16 17 } 17 18 18 *[wikipedia =~ /https?:\/\//] { 19 throwWarning: tr("deprecated format for wikipedia tag"); 19 *[wikipedia =~ /^https?:\/\//], 20 *[wikipedia =~ /^[-a-z]{2,12}:https?:\/\//] { 21 throwWarning: tr("wikipedia tag format is deprecated"); 20 22 suggestAlternative: tr("''wikipedia''=''language:page title''"); 21 23 group: tr("deprecated tagging"); 22 24 assertMatch: "node wikipedia=http://en.wikipedia.org/wiki/OpenStreetMap"; 23 25 assertNoMatch: "node wikipedia=en:OpenStreetMap"; 24 26 } 27 28 *[wikipedia =~ /^be-x-old:/] { 29 throwWarning: tr("wikipedia ''be-x-old'' language is obsolete, use ''be-tarask'' instead"); 30 fixAdd: concat("wikipedia=be-tarask:", get(regexp_match("^be-x-old:(.+)$", tag("wikipedia")),1)); 31 assertMatch: "node wikipedia=be-x-old:foo"; 32 assertNoMatch: "node wikipedia=abe-x-old:foo"; 33 } 34 35 *[wikipedia =~ /^cz:/] { 36 throwWarning: tr("wikipedia ''cz'' language is invalid, use ''cs'' instead"); 37 fixAdd: concat("wikipedia=cs:", get(regexp_match("^cz:(.+)$", tag("wikipedia")),1)); 38 assertMatch: "node wikipedia=cz:foo"; 39 assertNoMatch: "node wikipedia=en:cz:foo"; 40 } 41 42 *[wikipedia =~ /^[-a-z]{2,12}:.*%[0-9A-F][0-9A-F]/] { 43 throwError: tr("wikipedia title should not have URL-encoded values like ''%27''"); 44 fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.*)$", tag("wikipedia")),1), trim(replace(URL_decode(get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),2)), "_", " "))); 45 assertMatch: "node wikipedia=en:Foo%27s"; 46 assertNoMatch: "node wikipedia=en:Foo"; 47 } 48 49 *[wikipedia =~ /^[-a-z]{2,12}: /] { 50 throwWarning: tr("wikipedia title should not start with a space after language code"); 51 fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.*)$", tag("wikipedia")),1), trim(get(regexp_match("^([-a-z]+:)(.*)$", tag("wikipedia")),2))); 52 assertMatch: "node wikipedia=en: foo"; 53 assertNoMatch: "node wikipedia=en:foo"; 54 } 55 56 *[wikipedia =~ /^[-a-z]{2,12}:wiki\//] { 57 throwWarning: tr("wikipedia title should not have ''wiki/'' prefix"); 58 fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)wiki/(.*)$", tag("wikipedia")),1), trim(get(regexp_match("^([-a-z]+:)wiki/(.*)$", tag("wikipedia")),2))); 59 assertMatch: "node wikipedia=en: foo"; 60 assertNoMatch: "node wikipedia=en:foo"; 61 } 62 63 /* All wikipedias except "jbo" automatically capitalize first letter of the page title. 64 To see the latest list, see <https://noc.wikimedia.org/conf/highlight.php?file=InitialiseSettings.php> 65 and look for 'wgCapitalLinks' setting. */ 66 *[wikipedia =~ /^[-a-z]{2,12}:\p{Ll}/][wikipedia !~ /^jbo:/][wikipedia !~ /^[-a-z]{2,12}:https?:/] { 67 throwWarning: tr("wikipedia page title should have first letter capitalized"); 68 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]+:)(.)(.*)$", tag("wikipedia")),3)); 69 assertMatch: "node wikipedia=en:foo"; 70 assertNoMatch: "node wikipedia=en:Foo"; 71 assertMatch: "node wikipedia=ru:абв"; 72 assertNoMatch: "node wikipedia=ru:Абв"; 73 } 74 75 *[wikipedia =~ /^[-a-z]{2,12}:.*_/][wikipedia !~ /^[-a-z]{2,12}:https?:/] { 76 throwWarning: tr("wikipedia page title should have spaces instead of underscores (''_''→'' '')"); 77 fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),1), trim(replace(get(regexp_match("^([-a-z]+:)(.+)$", tag("wikipedia")),2), "_", " "))); 78 assertMatch: "node wikipedia=en:foo_bar"; 79 assertNoMatch: "node wikipedia=en:foo bar"; 80 } 81 82 *[wikipedia ^= "da:da:"], 83 *[wikipedia ^= "da:dk:"], 84 *[wikipedia ^= "de:de:"], 85 *[wikipedia ^= "dk:dk:"], 86 *[wikipedia ^= "en:de:"], 87 *[wikipedia ^= "en:en:"], 88 *[wikipedia ^= "en:es:"], 89 *[wikipedia ^= "en:eu:"], 90 *[wikipedia ^= "en:fr:"], 91 *[wikipedia ^= "en:ja:"], 92 *[wikipedia ^= "en:pl:"], 93 *[wikipedia ^= "en:pt:"], 94 *[wikipedia ^= "en:zh:"], 95 *[wikipedia ^= "es:es:"], 96 *[wikipedia ^= "eu:eu:"], 97 *[wikipedia ^= "fr:fr:"], 98 *[wikipedia ^= "ja:ja:"], 99 *[wikipedia ^= "pl:en:"], 100 *[wikipedia ^= "pl:pl:"], 101 *[wikipedia ^= "pt:pt:"], 102 *[wikipedia ^= "ru:fr:"], 103 *[wikipedia ^= "ru:ru:"], 104 *[wikipedia ^= "zh:zh:"] { 105 throwWarning: tr("wikipedia language seems to be duplicated, e.g. en:en:Foo"); 106 fixAdd: concat("wikipedia=", get(regexp_match("^([-a-z]+:)([-a-z]+:)(.*)$", tag("wikipedia")),2), trim(get(regexp_match("^([-a-z]+:)([-a-z]+:)(.*)$", tag("wikipedia")),3))); 107 assertMatch: "node wikipedia=en:en:Foo"; 108 assertMatch: "node wikipedia=en:fr:Foo"; 109 assertNoMatch: "node wikipedia=en:Bar"; 110 } -
src/org/openstreetmap/josm/gui/mappaint/mapcss/ExpressionFactory.java
831 831 } 832 832 833 833 /** 834 * Converts string {@code s} to uppercase. 835 * @param s The source string 836 * @return The resulting string 837 * @see String#toUpperCase() 838 */ 839 public static String upper(String s) { 840 return s == null ? null : s.toUpperCase(); 841 } 842 843 /** 844 * Converts string {@code s} to lowercase. 845 * @param s The source string 846 * @return The resulting string 847 * @see String#toLowerCase() 848 */ 849 public static String lower(String s) { 850 return s == null ? null : s.toLowerCase(); 851 } 852 853 /** 854 * Trim whitespaces from the string {@code s}. 855 * @param s The source string 856 * @return The resulting string 857 * @see String#trim() 858 */ 859 public static String trim(String s) { 860 return s == null ? null : s.trim(); 861 } 862 863 /** 864 * Percent-decode a string. (See https://en.wikipedia.org/wiki/Percent-encoding) 865 * This is especially useful for wikipedia titles 866 * @param s url-encoded string 867 * @return the decoded string, or original in case of an error 868 */ 869 public static String URL_decode(String s) { 870 if (s == null) return null; 871 try { 872 return Utils.decodeUrl(s); 873 } catch (java.lang.Exception e) { 874 return s; 875 } 876 } 877 878 /** 834 879 * Percent-encode a string. (See https://en.wikipedia.org/wiki/Percent-encoding) 835 880 * This is especially useful for data urls, e.g. 836 881 * <code>concat("data:image/svg+xml,", URL_encode("<svg>...</svg>"));</code>