Non-Latin WikiWords

Fix bug in WikiWord processing
reproted by Alexander Hambug.

Also fix Cyrillic Capital/Lowercase
regexps.
This commit is contained in:
Jacques Distler 2010-07-22 14:08:21 -05:00
parent 0a87548324
commit f6e9d17f9b
2 changed files with 6 additions and 5 deletions

View file

@ -181,7 +181,7 @@ class WikiContent < ActiveSupport::SafeBuffer
@options[:engine].apply_to(copy) @options[:engine].apply_to(copy)
copy.inside_chunks(@options[:hide_chunks]) do |id| copy.inside_chunks(@options[:hide_chunks]) do |id|
@chunks_by_id[id.to_i].revert @chunks_by_id[id.to_i].revert if @chunks_by_id[id.to_i]
end end
end end

View file

@ -8,16 +8,17 @@ module WikiWords
I18N_HIGHER_CASE_LETTERS = I18N_HIGHER_CASE_LETTERS =
"ÀÁÂÃÄÅĀĄĂÆÇĆČĈĊĎĐÈÉÊËĒĘĚĔĖĜĞĠĢĤĦÌÍÎÏĪĨĬĮİIJĴĶŁĽĹĻĿÑŃŇŅŊÒÓÔÕÖØŌŐŎŒŔŘŖŚŠŞŜȘŤŢŦȚÙÚÛÜŪŮŰŬŨŲŴŶŸȲÝŹŽŻ" + "ÀÁÂÃÄÅĀĄĂÆÇĆČĈĊĎĐÈÉÊËĒĘĚĔĖĜĞĠĢĤĦÌÍÎÏĪĨĬĮİIJĴĶŁĽĹĻĿÑŃŇŅŊÒÓÔÕÖØŌŐŎŒŔŘŖŚŠŞŜȘŤŢŦȚÙÚÛÜŪŮŰŬŨŲŴŶŸȲÝŹŽŻ" +
"ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩ" + "ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩ" +
"ΆΈΉΊΌΎΏѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӁӃӅӇӉӋӍӏӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӸЖ" + "ЀЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀӁӃӅӇӉӋӍӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸӺӼӾԀԂԄԆԈԊԌԎԐԒԔԖԘԚԜԞԠԢ" +
"ԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖ" "ԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖ"
I18N_LOWER_CASE_LETTERS = I18N_LOWER_CASE_LETTERS =
"àáâãäåāąăæçćĉċčďđèéêëēęěĕėƒĝğġģĥħìíîïīĩĭįıijĵķĸłľĺļŀñńňņʼnŋòóôõöøōŏőœŕřŗśŝšşșťţŧțùúûüūůűŭũųŵýÿŷžżźÞþßſð" + "àáâãäåāąăæçćĉċčďđèéêëēęěĕėƒĝğġģĥħìíîïīĩĭįıijĵķĸłľĺļŀñńňņʼnŋòóôõöøōŏőœŕřŗśŝšşșťţŧțùúûüūůűŭũųŵýÿŷžżźÞþßſð" +
"άέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώΐ" + "άέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώΐ" +
"абвгдежзийклмнопрстуфхцчшщъыьэюяѐёђѓєѕіїјљћќѝўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҌҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӀӂӄӆӈӊӌӎӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӹ" + "абвгдежзийклмнопрстуфхцчшщъыьэюяѐёђѓєѕіїјљњћќѝўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӏӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹӻӽӿԁԃԅԇԉԋԍԏԑԓԕԗԙԛԝԟԡԣ" +
"աբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտրցւփքօֆև" "աբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտրցւփքօֆև"
WIKI_WORD_PATTERN = '[A-Z' + I18N_HIGHER_CASE_LETTERS + ']+[a-z' + I18N_LOWER_CASE_LETTERS + ']+[A-Z' + I18N_HIGHER_CASE_LETTERS + ']\w+' WIKI_WORD_PATTERN = '[A-Z' + I18N_HIGHER_CASE_LETTERS + ']+[a-z' + I18N_LOWER_CASE_LETTERS + ']+[A-Z' + I18N_HIGHER_CASE_LETTERS +
'][A-Za-z0-9_' + I18N_HIGHER_CASE_LETTERS + I18N_LOWER_CASE_LETTERS + ']+'
CAMEL_CASED_WORD_BORDER = /([a-z#{I18N_LOWER_CASE_LETTERS}])([A-Z#{I18N_HIGHER_CASE_LETTERS}])/u CAMEL_CASED_WORD_BORDER = /([a-z#{I18N_LOWER_CASE_LETTERS}])([A-Z#{I18N_HIGHER_CASE_LETTERS}])/u
def self.separate(wiki_word) def self.separate(wiki_word)