From: Kevin Israel Date: Sun, 26 May 2013 10:12:12 +0000 (-0400) Subject: Generate Utf8Case.ser directly from UnicodeData.txt X-Git-Tag: 1.31.0-rc.0~17278^2 X-Git-Url: https://git.cyclocoop.org/%7B%24www_url%7Dadmin/compta/exercices/journal.php?a=commitdiff_plain;h=74557dedd02f17ae5115eaf51089e79f7277a353;p=lhc%2Fweb%2Fwiklou.git Generate Utf8Case.ser directly from UnicodeData.txt This allows getting rid of serialized/serialize.php. I also moved includes/normal/Utf8CaseGenerate.php to maintenance/language/ generateUtf8Case.php and updated it to subclass Maintenance, as it seems to be largely unrelated to normalization. Using version 6.0.0 of UnicodeData.txt, the updated script generates exactly the same serialized output as was previously checked in. Also updated the Makefile to reflect the current set of .ser files and added some .gitignore entries. Change-Id: I05afece3dc4505a9f43993ac4d7726b37d9c6956 --- diff --git a/includes/normal/.gitignore b/includes/normal/.gitignore new file mode 100644 index 0000000000..0dea457973 --- /dev/null +++ b/includes/normal/.gitignore @@ -0,0 +1,7 @@ +/CompositionExclusions.txt +/DerivedNormalizationProps.txt +/NormalizationCorrections.txt +/NormalizationTest.txt +/UTF-8-test.txt +/UnicodeData.txt +/testdata diff --git a/includes/normal/Makefile b/includes/normal/Makefile index 66348ee377..76cb68bab0 100644 --- a/includes/normal/Makefile +++ b/includes/normal/Makefile @@ -16,14 +16,11 @@ PHP=php FETCH=wget #FETCH=fetch -all : UtfNormalData.inc Utf8Case.php +all : UtfNormalData.inc UtfNormalData.inc : UtfNormalGenerate.php UtfNormalUtil.php UnicodeData.txt CompositionExclusions.txt NormalizationCorrections.txt DerivedNormalizationProps.txt $(PHP) UtfNormalGenerate.php -Utf8Case.php : Utf8CaseGenerate.php UtfNormalUtil.php UnicodeData.txt - $(PHP) Utf8CaseGenerate.php - test : testutf8 UtfNormalTest.php UtfNormalData.inc NormalizationTest.txt $(PHP) UtfNormalTest.php diff --git a/includes/normal/Utf8Case.php b/includes/normal/Utf8Case.php deleted file mode 100644 index abc56e4c65..0000000000 --- a/includes/normal/Utf8Case.php +++ /dev/null @@ -1,2109 +0,0 @@ - 'A', - 'b' => 'B', - 'c' => 'C', - 'd' => 'D', - 'e' => 'E', - 'f' => 'F', - 'g' => 'G', - 'h' => 'H', - 'i' => 'I', - 'j' => 'J', - 'k' => 'K', - 'l' => 'L', - 'm' => 'M', - 'n' => 'N', - 'o' => 'O', - 'p' => 'P', - 'q' => 'Q', - 'r' => 'R', - 's' => 'S', - 't' => 'T', - 'u' => 'U', - 'v' => 'V', - 'w' => 'W', - 'x' => 'X', - 'y' => 'Y', - 'z' => 'Z', - 'µ' => 'Μ', - 'à' => 'À', - 'á' => 'Á', - 'â' => 'Â', - 'ã' => 'Ã', - 'ä' => 'Ä', - 'å' => 'Å', - 'æ' => 'Æ', - 'ç' => 'Ç', - 'è' => 'È', - 'é' => 'É', - 'ê' => 'Ê', - 'ë' => 'Ë', - 'ì' => 'Ì', - 'í' => 'Í', - 'î' => 'Î', - 'ï' => 'Ï', - 'ð' => 'Ð', - 'ñ' => 'Ñ', - 'ò' => 'Ò', - 'ó' => 'Ó', - 'ô' => 'Ô', - 'õ' => 'Õ', - 'ö' => 'Ö', - 'ø' => 'Ø', - 'ù' => 'Ù', - 'ú' => 'Ú', - 'û' => 'Û', - 'ü' => 'Ü', - 'ý' => 'Ý', - 'þ' => 'Þ', - 'ÿ' => 'Ÿ', - 'ā' => 'Ā', - 'ă' => 'Ă', - 'ą' => 'Ą', - 'ć' => 'Ć', - 'ĉ' => 'Ĉ', - 'ċ' => 'Ċ', - 'č' => 'Č', - 'ď' => 'Ď', - 'đ' => 'Đ', - 'ē' => 'Ē', - 'ĕ' => 'Ĕ', - 'ė' => 'Ė', - 'ę' => 'Ę', - 'ě' => 'Ě', - 'ĝ' => 'Ĝ', - 'ğ' => 'Ğ', - 'ġ' => 'Ġ', - 'ģ' => 'Ģ', - 'ĥ' => 'Ĥ', - 'ħ' => 'Ħ', - 'ĩ' => 'Ĩ', - 'ī' => 'Ī', - 'ĭ' => 'Ĭ', - 'į' => 'Į', - 'ı' => 'I', - 'ij' => 'IJ', - 'ĵ' => 'Ĵ', - 'ķ' => 'Ķ', - 'ĺ' => 'Ĺ', - 'ļ' => 'Ļ', - 'ľ' => 'Ľ', - 'ŀ' => 'Ŀ', - 'ł' => 'Ł', - 'ń' => 'Ń', - 'ņ' => 'Ņ', - 'ň' => 'Ň', - 'ŋ' => 'Ŋ', - 'ō' => 'Ō', - 'ŏ' => 'Ŏ', - 'ő' => 'Ő', - 'œ' => 'Œ', - 'ŕ' => 'Ŕ', - 'ŗ' => 'Ŗ', - 'ř' => 'Ř', - 'ś' => 'Ś', - 'ŝ' => 'Ŝ', - 'ş' => 'Ş', - 'š' => 'Š', - 'ţ' => 'Ţ', - 'ť' => 'Ť', - 'ŧ' => 'Ŧ', - 'ũ' => 'Ũ', - 'ū' => 'Ū', - 'ŭ' => 'Ŭ', - 'ů' => 'Ů', - 'ű' => 'Ű', - 'ų' => 'Ų', - 'ŵ' => 'Ŵ', - 'ŷ' => 'Ŷ', - 'ź' => 'Ź', - 'ż' => 'Ż', - 'ž' => 'Ž', - 'ſ' => 'S', - 'ƀ' => 'Ƀ', - 'ƃ' => 'Ƃ', - 'ƅ' => 'Ƅ', - 'ƈ' => 'Ƈ', - 'ƌ' => 'Ƌ', - 'ƒ' => 'Ƒ', - 'ƕ' => 'Ƕ', - 'ƙ' => 'Ƙ', - 'ƚ' => 'Ƚ', - 'ƞ' => 'Ƞ', - 'ơ' => 'Ơ', - 'ƣ' => 'Ƣ', - 'ƥ' => 'Ƥ', - 'ƨ' => 'Ƨ', - 'ƭ' => 'Ƭ', - 'ư' => 'Ư', - 'ƴ' => 'Ƴ', - 'ƶ' => 'Ƶ', - 'ƹ' => 'Ƹ', - 'ƽ' => 'Ƽ', - 'ƿ' => 'Ƿ', - 'Dž' => 'DŽ', - 'dž' => 'DŽ', - 'Lj' => 'LJ', - 'lj' => 'LJ', - 'Nj' => 'NJ', - 'nj' => 'NJ', - 'ǎ' => 'Ǎ', - 'ǐ' => 'Ǐ', - 'ǒ' => 'Ǒ', - 'ǔ' => 'Ǔ', - 'ǖ' => 'Ǖ', - 'ǘ' => 'Ǘ', - 'ǚ' => 'Ǚ', - 'ǜ' => 'Ǜ', - 'ǝ' => 'Ǝ', - 'ǟ' => 'Ǟ', - 'ǡ' => 'Ǡ', - 'ǣ' => 'Ǣ', - 'ǥ' => 'Ǥ', - 'ǧ' => 'Ǧ', - 'ǩ' => 'Ǩ', - 'ǫ' => 'Ǫ', - 'ǭ' => 'Ǭ', - 'ǯ' => 'Ǯ', - 'Dz' => 'DZ', - 'dz' => 'DZ', - 'ǵ' => 'Ǵ', - 'ǹ' => 'Ǹ', - 'ǻ' => 'Ǻ', - 'ǽ' => 'Ǽ', - 'ǿ' => 'Ǿ', - 'ȁ' => 'Ȁ', - 'ȃ' => 'Ȃ', - 'ȅ' => 'Ȅ', - 'ȇ' => 'Ȇ', - 'ȉ' => 'Ȉ', - 'ȋ' => 'Ȋ', - 'ȍ' => 'Ȍ', - 'ȏ' => 'Ȏ', - 'ȑ' => 'Ȑ', - 'ȓ' => 'Ȓ', - 'ȕ' => 'Ȕ', - 'ȗ' => 'Ȗ', - 'ș' => 'Ș', - 'ț' => 'Ț', - 'ȝ' => 'Ȝ', - 'ȟ' => 'Ȟ', - 'ȣ' => 'Ȣ', - 'ȥ' => 'Ȥ', - 'ȧ' => 'Ȧ', - 'ȩ' => 'Ȩ', - 'ȫ' => 'Ȫ', - 'ȭ' => 'Ȭ', - 'ȯ' => 'Ȯ', - 'ȱ' => 'Ȱ', - 'ȳ' => 'Ȳ', - 'ȼ' => 'Ȼ', - 'ȿ' => 'Ȿ', - 'ɀ' => 'Ɀ', - 'ɂ' => 'Ɂ', - 'ɇ' => 'Ɇ', - 'ɉ' => 'Ɉ', - 'ɋ' => 'Ɋ', - 'ɍ' => 'Ɍ', - 'ɏ' => 'Ɏ', - 'ɐ' => 'Ɐ', - 'ɑ' => 'Ɑ', - 'ɒ' => 'Ɒ', - 'ɓ' => 'Ɓ', - 'ɔ' => 'Ɔ', - 'ɖ' => 'Ɖ', - 'ɗ' => 'Ɗ', - 'ə' => 'Ə', - 'ɛ' => 'Ɛ', - 'ɠ' => 'Ɠ', - 'ɣ' => 'Ɣ', - 'ɥ' => 'Ɥ', - 'ɨ' => 'Ɨ', - 'ɩ' => 'Ɩ', - 'ɫ' => 'Ɫ', - 'ɯ' => 'Ɯ', - 'ɱ' => 'Ɱ', - 'ɲ' => 'Ɲ', - 'ɵ' => 'Ɵ', - 'ɽ' => 'Ɽ', - 'ʀ' => 'Ʀ', - 'ʃ' => 'Ʃ', - 'ʈ' => 'Ʈ', - 'ʉ' => 'Ʉ', - 'ʊ' => 'Ʊ', - 'ʋ' => 'Ʋ', - 'ʌ' => 'Ʌ', - 'ʒ' => 'Ʒ', - 'ͅ' => 'Ι', - 'ͱ' => 'Ͱ', - 'ͳ' => 'Ͳ', - 'ͷ' => 'Ͷ', - 'ͻ' => 'Ͻ', - 'ͼ' => 'Ͼ', - 'ͽ' => 'Ͽ', - 'ά' => 'Ά', - 'έ' => 'Έ', - 'ή' => 'Ή', - 'ί' => 'Ί', - 'α' => 'Α', - 'β' => 'Β', - 'γ' => 'Γ', - 'δ' => 'Δ', - 'ε' => 'Ε', - 'ζ' => 'Ζ', - 'η' => 'Η', - 'θ' => 'Θ', - 'ι' => 'Ι', - 'κ' => 'Κ', - 'λ' => 'Λ', - 'μ' => 'Μ', - 'ν' => 'Ν', - 'ξ' => 'Ξ', - 'ο' => 'Ο', - 'π' => 'Π', - 'ρ' => 'Ρ', - 'ς' => 'Σ', - 'σ' => 'Σ', - 'τ' => 'Τ', - 'υ' => 'Υ', - 'φ' => 'Φ', - 'χ' => 'Χ', - 'ψ' => 'Ψ', - 'ω' => 'Ω', - 'ϊ' => 'Ϊ', - 'ϋ' => 'Ϋ', - 'ό' => 'Ό', - 'ύ' => 'Ύ', - 'ώ' => 'Ώ', - 'ϐ' => 'Β', - 'ϑ' => 'Θ', - 'ϕ' => 'Φ', - 'ϖ' => 'Π', - 'ϗ' => 'Ϗ', - 'ϙ' => 'Ϙ', - 'ϛ' => 'Ϛ', - 'ϝ' => 'Ϝ', - 'ϟ' => 'Ϟ', - 'ϡ' => 'Ϡ', - 'ϣ' => 'Ϣ', - 'ϥ' => 'Ϥ', - 'ϧ' => 'Ϧ', - 'ϩ' => 'Ϩ', - 'ϫ' => 'Ϫ', - 'ϭ' => 'Ϭ', - 'ϯ' => 'Ϯ', - 'ϰ' => 'Κ', - 'ϱ' => 'Ρ', - 'ϲ' => 'Ϲ', - 'ϵ' => 'Ε', - 'ϸ' => 'Ϸ', - 'ϻ' => 'Ϻ', - 'а' => 'А', - 'б' => 'Б', - 'в' => 'В', - 'г' => 'Г', - 'д' => 'Д', - 'е' => 'Е', - 'ж' => 'Ж', - 'з' => 'З', - 'и' => 'И', - 'й' => 'Й', - 'к' => 'К', - 'л' => 'Л', - 'м' => 'М', - 'н' => 'Н', - 'о' => 'О', - 'п' => 'П', - 'р' => 'Р', - 'с' => 'С', - 'т' => 'Т', - 'у' => 'У', - 'ф' => 'Ф', - 'х' => 'Х', - 'ц' => 'Ц', - 'ч' => 'Ч', - 'ш' => 'Ш', - 'щ' => 'Щ', - 'ъ' => 'Ъ', - 'ы' => 'Ы', - 'ь' => 'Ь', - 'э' => 'Э', - 'ю' => 'Ю', - 'я' => 'Я', - 'ѐ' => 'Ѐ', - 'ё' => 'Ё', - 'ђ' => 'Ђ', - 'ѓ' => 'Ѓ', - 'є' => 'Є', - 'ѕ' => 'Ѕ', - 'і' => 'І', - 'ї' => 'Ї', - 'ј' => 'Ј', - 'љ' => 'Љ', - 'њ' => 'Њ', - 'ћ' => 'Ћ', - 'ќ' => 'Ќ', - 'ѝ' => 'Ѝ', - 'ў' => 'Ў', - 'џ' => 'Џ', - 'ѡ' => 'Ѡ', - 'ѣ' => 'Ѣ', - 'ѥ' => 'Ѥ', - 'ѧ' => 'Ѧ', - 'ѩ' => 'Ѩ', - 'ѫ' => 'Ѫ', - 'ѭ' => 'Ѭ', - 'ѯ' => 'Ѯ', - 'ѱ' => 'Ѱ', - 'ѳ' => 'Ѳ', - 'ѵ' => 'Ѵ', - 'ѷ' => 'Ѷ', - 'ѹ' => 'Ѹ', - 'ѻ' => 'Ѻ', - 'ѽ' => 'Ѽ', - 'ѿ' => 'Ѿ', - 'ҁ' => 'Ҁ', - 'ҋ' => 'Ҋ', - 'ҍ' => 'Ҍ', - 'ҏ' => 'Ҏ', - 'ґ' => 'Ґ', - 'ғ' => 'Ғ', - 'ҕ' => 'Ҕ', - 'җ' => 'Җ', - 'ҙ' => 'Ҙ', - 'қ' => 'Қ', - 'ҝ' => 'Ҝ', - 'ҟ' => 'Ҟ', - 'ҡ' => 'Ҡ', - 'ң' => 'Ң', - 'ҥ' => 'Ҥ', - 'ҧ' => 'Ҧ', - 'ҩ' => 'Ҩ', - 'ҫ' => 'Ҫ', - 'ҭ' => 'Ҭ', - 'ү' => 'Ү', - 'ұ' => 'Ұ', - 'ҳ' => 'Ҳ', - 'ҵ' => 'Ҵ', - 'ҷ' => 'Ҷ', - 'ҹ' => 'Ҹ', - 'һ' => 'Һ', - 'ҽ' => 'Ҽ', - 'ҿ' => 'Ҿ', - 'ӂ' => 'Ӂ', - 'ӄ' => 'Ӄ', - 'ӆ' => 'Ӆ', - 'ӈ' => 'Ӈ', - 'ӊ' => 'Ӊ', - 'ӌ' => 'Ӌ', - 'ӎ' => 'Ӎ', - 'ӏ' => 'Ӏ', - 'ӑ' => 'Ӑ', - 'ӓ' => 'Ӓ', - 'ӕ' => 'Ӕ', - 'ӗ' => 'Ӗ', - 'ә' => 'Ә', - 'ӛ' => 'Ӛ', - 'ӝ' => 'Ӝ', - 'ӟ' => 'Ӟ', - 'ӡ' => 'Ӡ', - 'ӣ' => 'Ӣ', - 'ӥ' => 'Ӥ', - 'ӧ' => 'Ӧ', - 'ө' => 'Ө', - 'ӫ' => 'Ӫ', - 'ӭ' => 'Ӭ', - 'ӯ' => 'Ӯ', - 'ӱ' => 'Ӱ', - 'ӳ' => 'Ӳ', - 'ӵ' => 'Ӵ', - 'ӷ' => 'Ӷ', - 'ӹ' => 'Ӹ', - 'ӻ' => 'Ӻ', - 'ӽ' => 'Ӽ', - 'ӿ' => 'Ӿ', - 'ԁ' => 'Ԁ', - 'ԃ' => 'Ԃ', - 'ԅ' => 'Ԅ', - 'ԇ' => 'Ԇ', - 'ԉ' => 'Ԉ', - 'ԋ' => 'Ԋ', - 'ԍ' => 'Ԍ', - 'ԏ' => 'Ԏ', - 'ԑ' => 'Ԑ', - 'ԓ' => 'Ԓ', - 'ԕ' => 'Ԕ', - 'ԗ' => 'Ԗ', - 'ԙ' => 'Ԙ', - 'ԛ' => 'Ԛ', - 'ԝ' => 'Ԝ', - 'ԟ' => 'Ԟ', - 'ԡ' => 'Ԡ', - 'ԣ' => 'Ԣ', - 'ԥ' => 'Ԥ', - 'ԧ' => 'Ԧ', - 'ա' => 'Ա', - 'բ' => 'Բ', - 'գ' => 'Գ', - 'դ' => 'Դ', - 'ե' => 'Ե', - 'զ' => 'Զ', - 'է' => 'Է', - 'ը' => 'Ը', - 'թ' => 'Թ', - 'ժ' => 'Ժ', - 'ի' => 'Ի', - 'լ' => 'Լ', - 'խ' => 'Խ', - 'ծ' => 'Ծ', - 'կ' => 'Կ', - 'հ' => 'Հ', - 'ձ' => 'Ձ', - 'ղ' => 'Ղ', - 'ճ' => 'Ճ', - 'մ' => 'Մ', - 'յ' => 'Յ', - 'ն' => 'Ն', - 'շ' => 'Շ', - 'ո' => 'Ո', - 'չ' => 'Չ', - 'պ' => 'Պ', - 'ջ' => 'Ջ', - 'ռ' => 'Ռ', - 'ս' => 'Ս', - 'վ' => 'Վ', - 'տ' => 'Տ', - 'ր' => 'Ր', - 'ց' => 'Ց', - 'ւ' => 'Ւ', - 'փ' => 'Փ', - 'ք' => 'Ք', - 'օ' => 'Օ', - 'ֆ' => 'Ֆ', - 'ᵹ' => 'Ᵹ', - 'ᵽ' => 'Ᵽ', - 'ḁ' => 'Ḁ', - 'ḃ' => 'Ḃ', - 'ḅ' => 'Ḅ', - 'ḇ' => 'Ḇ', - 'ḉ' => 'Ḉ', - 'ḋ' => 'Ḋ', - 'ḍ' => 'Ḍ', - 'ḏ' => 'Ḏ', - 'ḑ' => 'Ḑ', - 'ḓ' => 'Ḓ', - 'ḕ' => 'Ḕ', - 'ḗ' => 'Ḗ', - 'ḙ' => 'Ḙ', - 'ḛ' => 'Ḛ', - 'ḝ' => 'Ḝ', - 'ḟ' => 'Ḟ', - 'ḡ' => 'Ḡ', - 'ḣ' => 'Ḣ', - 'ḥ' => 'Ḥ', - 'ḧ' => 'Ḧ', - 'ḩ' => 'Ḩ', - 'ḫ' => 'Ḫ', - 'ḭ' => 'Ḭ', - 'ḯ' => 'Ḯ', - 'ḱ' => 'Ḱ', - 'ḳ' => 'Ḳ', - 'ḵ' => 'Ḵ', - 'ḷ' => 'Ḷ', - 'ḹ' => 'Ḹ', - 'ḻ' => 'Ḻ', - 'ḽ' => 'Ḽ', - 'ḿ' => 'Ḿ', - 'ṁ' => 'Ṁ', - 'ṃ' => 'Ṃ', - 'ṅ' => 'Ṅ', - 'ṇ' => 'Ṇ', - 'ṉ' => 'Ṉ', - 'ṋ' => 'Ṋ', - 'ṍ' => 'Ṍ', - 'ṏ' => 'Ṏ', - 'ṑ' => 'Ṑ', - 'ṓ' => 'Ṓ', - 'ṕ' => 'Ṕ', - 'ṗ' => 'Ṗ', - 'ṙ' => 'Ṙ', - 'ṛ' => 'Ṛ', - 'ṝ' => 'Ṝ', - 'ṟ' => 'Ṟ', - 'ṡ' => 'Ṡ', - 'ṣ' => 'Ṣ', - 'ṥ' => 'Ṥ', - 'ṧ' => 'Ṧ', - 'ṩ' => 'Ṩ', - 'ṫ' => 'Ṫ', - 'ṭ' => 'Ṭ', - 'ṯ' => 'Ṯ', - 'ṱ' => 'Ṱ', - 'ṳ' => 'Ṳ', - 'ṵ' => 'Ṵ', - 'ṷ' => 'Ṷ', - 'ṹ' => 'Ṹ', - 'ṻ' => 'Ṻ', - 'ṽ' => 'Ṽ', - 'ṿ' => 'Ṿ', - 'ẁ' => 'Ẁ', - 'ẃ' => 'Ẃ', - 'ẅ' => 'Ẅ', - 'ẇ' => 'Ẇ', - 'ẉ' => 'Ẉ', - 'ẋ' => 'Ẋ', - 'ẍ' => 'Ẍ', - 'ẏ' => 'Ẏ', - 'ẑ' => 'Ẑ', - 'ẓ' => 'Ẓ', - 'ẕ' => 'Ẕ', - 'ẛ' => 'Ṡ', - 'ạ' => 'Ạ', - 'ả' => 'Ả', - 'ấ' => 'Ấ', - 'ầ' => 'Ầ', - 'ẩ' => 'Ẩ', - 'ẫ' => 'Ẫ', - 'ậ' => 'Ậ', - 'ắ' => 'Ắ', - 'ằ' => 'Ằ', - 'ẳ' => 'Ẳ', - 'ẵ' => 'Ẵ', - 'ặ' => 'Ặ', - 'ẹ' => 'Ẹ', - 'ẻ' => 'Ẻ', - 'ẽ' => 'Ẽ', - 'ế' => 'Ế', - 'ề' => 'Ề', - 'ể' => 'Ể', - 'ễ' => 'Ễ', - 'ệ' => 'Ệ', - 'ỉ' => 'Ỉ', - 'ị' => 'Ị', - 'ọ' => 'Ọ', - 'ỏ' => 'Ỏ', - 'ố' => 'Ố', - 'ồ' => 'Ồ', - 'ổ' => 'Ổ', - 'ỗ' => 'Ỗ', - 'ộ' => 'Ộ', - 'ớ' => 'Ớ', - 'ờ' => 'Ờ', - 'ở' => 'Ở', - 'ỡ' => 'Ỡ', - 'ợ' => 'Ợ', - 'ụ' => 'Ụ', - 'ủ' => 'Ủ', - 'ứ' => 'Ứ', - 'ừ' => 'Ừ', - 'ử' => 'Ử', - 'ữ' => 'Ữ', - 'ự' => 'Ự', - 'ỳ' => 'Ỳ', - 'ỵ' => 'Ỵ', - 'ỷ' => 'Ỷ', - 'ỹ' => 'Ỹ', - 'ỻ' => 'Ỻ', - 'ỽ' => 'Ỽ', - 'ỿ' => 'Ỿ', - 'ἀ' => 'Ἀ', - 'ἁ' => 'Ἁ', - 'ἂ' => 'Ἂ', - 'ἃ' => 'Ἃ', - 'ἄ' => 'Ἄ', - 'ἅ' => 'Ἅ', - 'ἆ' => 'Ἆ', - 'ἇ' => 'Ἇ', - 'ἐ' => 'Ἐ', - 'ἑ' => 'Ἑ', - 'ἒ' => 'Ἒ', - 'ἓ' => 'Ἓ', - 'ἔ' => 'Ἔ', - 'ἕ' => 'Ἕ', - 'ἠ' => 'Ἠ', - 'ἡ' => 'Ἡ', - 'ἢ' => 'Ἢ', - 'ἣ' => 'Ἣ', - 'ἤ' => 'Ἤ', - 'ἥ' => 'Ἥ', - 'ἦ' => 'Ἦ', - 'ἧ' => 'Ἧ', - 'ἰ' => 'Ἰ', - 'ἱ' => 'Ἱ', - 'ἲ' => 'Ἲ', - 'ἳ' => 'Ἳ', - 'ἴ' => 'Ἴ', - 'ἵ' => 'Ἵ', - 'ἶ' => 'Ἶ', - 'ἷ' => 'Ἷ', - 'ὀ' => 'Ὀ', - 'ὁ' => 'Ὁ', - 'ὂ' => 'Ὂ', - 'ὃ' => 'Ὃ', - 'ὄ' => 'Ὄ', - 'ὅ' => 'Ὅ', - 'ὑ' => 'Ὑ', - 'ὓ' => 'Ὓ', - 'ὕ' => 'Ὕ', - 'ὗ' => 'Ὗ', - 'ὠ' => 'Ὠ', - 'ὡ' => 'Ὡ', - 'ὢ' => 'Ὢ', - 'ὣ' => 'Ὣ', - 'ὤ' => 'Ὤ', - 'ὥ' => 'Ὥ', - 'ὦ' => 'Ὦ', - 'ὧ' => 'Ὧ', - 'ὰ' => 'Ὰ', - 'ά' => 'Ά', - 'ὲ' => 'Ὲ', - 'έ' => 'Έ', - 'ὴ' => 'Ὴ', - 'ή' => 'Ή', - 'ὶ' => 'Ὶ', - 'ί' => 'Ί', - 'ὸ' => 'Ὸ', - 'ό' => 'Ό', - 'ὺ' => 'Ὺ', - 'ύ' => 'Ύ', - 'ὼ' => 'Ὼ', - 'ώ' => 'Ώ', - 'ᾀ' => 'ᾈ', - 'ᾁ' => 'ᾉ', - 'ᾂ' => 'ᾊ', - 'ᾃ' => 'ᾋ', - 'ᾄ' => 'ᾌ', - 'ᾅ' => 'ᾍ', - 'ᾆ' => 'ᾎ', - 'ᾇ' => 'ᾏ', - 'ᾐ' => 'ᾘ', - 'ᾑ' => 'ᾙ', - 'ᾒ' => 'ᾚ', - 'ᾓ' => 'ᾛ', - 'ᾔ' => 'ᾜ', - 'ᾕ' => 'ᾝ', - 'ᾖ' => 'ᾞ', - 'ᾗ' => 'ᾟ', - 'ᾠ' => 'ᾨ', - 'ᾡ' => 'ᾩ', - 'ᾢ' => 'ᾪ', - 'ᾣ' => 'ᾫ', - 'ᾤ' => 'ᾬ', - 'ᾥ' => 'ᾭ', - 'ᾦ' => 'ᾮ', - 'ᾧ' => 'ᾯ', - 'ᾰ' => 'Ᾰ', - 'ᾱ' => 'Ᾱ', - 'ᾳ' => 'ᾼ', - 'ι' => 'Ι', - 'ῃ' => 'ῌ', - 'ῐ' => 'Ῐ', - 'ῑ' => 'Ῑ', - 'ῠ' => 'Ῠ', - 'ῡ' => 'Ῡ', - 'ῥ' => 'Ῥ', - 'ῳ' => 'ῼ', - 'ⅎ' => 'Ⅎ', - 'ⅰ' => 'Ⅰ', - 'ⅱ' => 'Ⅱ', - 'ⅲ' => 'Ⅲ', - 'ⅳ' => 'Ⅳ', - 'ⅴ' => 'Ⅴ', - 'ⅵ' => 'Ⅵ', - 'ⅶ' => 'Ⅶ', - 'ⅷ' => 'Ⅷ', - 'ⅸ' => 'Ⅸ', - 'ⅹ' => 'Ⅹ', - 'ⅺ' => 'Ⅺ', - 'ⅻ' => 'Ⅻ', - 'ⅼ' => 'Ⅼ', - 'ⅽ' => 'Ⅽ', - 'ⅾ' => 'Ⅾ', - 'ⅿ' => 'Ⅿ', - 'ↄ' => 'Ↄ', - 'ⓐ' => 'Ⓐ', - 'ⓑ' => 'Ⓑ', - 'ⓒ' => 'Ⓒ', - 'ⓓ' => 'Ⓓ', - 'ⓔ' => 'Ⓔ', - 'ⓕ' => 'Ⓕ', - 'ⓖ' => 'Ⓖ', - 'ⓗ' => 'Ⓗ', - 'ⓘ' => 'Ⓘ', - 'ⓙ' => 'Ⓙ', - 'ⓚ' => 'Ⓚ', - 'ⓛ' => 'Ⓛ', - 'ⓜ' => 'Ⓜ', - 'ⓝ' => 'Ⓝ', - 'ⓞ' => 'Ⓞ', - 'ⓟ' => 'Ⓟ', - 'ⓠ' => 'Ⓠ', - 'ⓡ' => 'Ⓡ', - 'ⓢ' => 'Ⓢ', - 'ⓣ' => 'Ⓣ', - 'ⓤ' => 'Ⓤ', - 'ⓥ' => 'Ⓥ', - 'ⓦ' => 'Ⓦ', - 'ⓧ' => 'Ⓧ', - 'ⓨ' => 'Ⓨ', - 'ⓩ' => 'Ⓩ', - 'ⰰ' => 'Ⰰ', - 'ⰱ' => 'Ⰱ', - 'ⰲ' => 'Ⰲ', - 'ⰳ' => 'Ⰳ', - 'ⰴ' => 'Ⰴ', - 'ⰵ' => 'Ⰵ', - 'ⰶ' => 'Ⰶ', - 'ⰷ' => 'Ⰷ', - 'ⰸ' => 'Ⰸ', - 'ⰹ' => 'Ⰹ', - 'ⰺ' => 'Ⰺ', - 'ⰻ' => 'Ⰻ', - 'ⰼ' => 'Ⰼ', - 'ⰽ' => 'Ⰽ', - 'ⰾ' => 'Ⰾ', - 'ⰿ' => 'Ⰿ', - 'ⱀ' => 'Ⱀ', - 'ⱁ' => 'Ⱁ', - 'ⱂ' => 'Ⱂ', - 'ⱃ' => 'Ⱃ', - 'ⱄ' => 'Ⱄ', - 'ⱅ' => 'Ⱅ', - 'ⱆ' => 'Ⱆ', - 'ⱇ' => 'Ⱇ', - 'ⱈ' => 'Ⱈ', - 'ⱉ' => 'Ⱉ', - 'ⱊ' => 'Ⱊ', - 'ⱋ' => 'Ⱋ', - 'ⱌ' => 'Ⱌ', - 'ⱍ' => 'Ⱍ', - 'ⱎ' => 'Ⱎ', - 'ⱏ' => 'Ⱏ', - 'ⱐ' => 'Ⱐ', - 'ⱑ' => 'Ⱑ', - 'ⱒ' => 'Ⱒ', - 'ⱓ' => 'Ⱓ', - 'ⱔ' => 'Ⱔ', - 'ⱕ' => 'Ⱕ', - 'ⱖ' => 'Ⱖ', - 'ⱗ' => 'Ⱗ', - 'ⱘ' => 'Ⱘ', - 'ⱙ' => 'Ⱙ', - 'ⱚ' => 'Ⱚ', - 'ⱛ' => 'Ⱛ', - 'ⱜ' => 'Ⱜ', - 'ⱝ' => 'Ⱝ', - 'ⱞ' => 'Ⱞ', - 'ⱡ' => 'Ⱡ', - 'ⱥ' => 'Ⱥ', - 'ⱦ' => 'Ⱦ', - 'ⱨ' => 'Ⱨ', - 'ⱪ' => 'Ⱪ', - 'ⱬ' => 'Ⱬ', - 'ⱳ' => 'Ⱳ', - 'ⱶ' => 'Ⱶ', - 'ⲁ' => 'Ⲁ', - 'ⲃ' => 'Ⲃ', - 'ⲅ' => 'Ⲅ', - 'ⲇ' => 'Ⲇ', - 'ⲉ' => 'Ⲉ', - 'ⲋ' => 'Ⲋ', - 'ⲍ' => 'Ⲍ', - 'ⲏ' => 'Ⲏ', - 'ⲑ' => 'Ⲑ', - 'ⲓ' => 'Ⲓ', - 'ⲕ' => 'Ⲕ', - 'ⲗ' => 'Ⲗ', - 'ⲙ' => 'Ⲙ', - 'ⲛ' => 'Ⲛ', - 'ⲝ' => 'Ⲝ', - 'ⲟ' => 'Ⲟ', - 'ⲡ' => 'Ⲡ', - 'ⲣ' => 'Ⲣ', - 'ⲥ' => 'Ⲥ', - 'ⲧ' => 'Ⲧ', - 'ⲩ' => 'Ⲩ', - 'ⲫ' => 'Ⲫ', - 'ⲭ' => 'Ⲭ', - 'ⲯ' => 'Ⲯ', - 'ⲱ' => 'Ⲱ', - 'ⲳ' => 'Ⲳ', - 'ⲵ' => 'Ⲵ', - 'ⲷ' => 'Ⲷ', - 'ⲹ' => 'Ⲹ', - 'ⲻ' => 'Ⲻ', - 'ⲽ' => 'Ⲽ', - 'ⲿ' => 'Ⲿ', - 'ⳁ' => 'Ⳁ', - 'ⳃ' => 'Ⳃ', - 'ⳅ' => 'Ⳅ', - 'ⳇ' => 'Ⳇ', - 'ⳉ' => 'Ⳉ', - 'ⳋ' => 'Ⳋ', - 'ⳍ' => 'Ⳍ', - 'ⳏ' => 'Ⳏ', - 'ⳑ' => 'Ⳑ', - 'ⳓ' => 'Ⳓ', - 'ⳕ' => 'Ⳕ', - 'ⳗ' => 'Ⳗ', - 'ⳙ' => 'Ⳙ', - 'ⳛ' => 'Ⳛ', - 'ⳝ' => 'Ⳝ', - 'ⳟ' => 'Ⳟ', - 'ⳡ' => 'Ⳡ', - 'ⳣ' => 'Ⳣ', - 'ⳬ' => 'Ⳬ', - 'ⳮ' => 'Ⳮ', - 'ⴀ' => 'Ⴀ', - 'ⴁ' => 'Ⴁ', - 'ⴂ' => 'Ⴂ', - 'ⴃ' => 'Ⴃ', - 'ⴄ' => 'Ⴄ', - 'ⴅ' => 'Ⴅ', - 'ⴆ' => 'Ⴆ', - 'ⴇ' => 'Ⴇ', - 'ⴈ' => 'Ⴈ', - 'ⴉ' => 'Ⴉ', - 'ⴊ' => 'Ⴊ', - 'ⴋ' => 'Ⴋ', - 'ⴌ' => 'Ⴌ', - 'ⴍ' => 'Ⴍ', - 'ⴎ' => 'Ⴎ', - 'ⴏ' => 'Ⴏ', - 'ⴐ' => 'Ⴐ', - 'ⴑ' => 'Ⴑ', - 'ⴒ' => 'Ⴒ', - 'ⴓ' => 'Ⴓ', - 'ⴔ' => 'Ⴔ', - 'ⴕ' => 'Ⴕ', - 'ⴖ' => 'Ⴖ', - 'ⴗ' => 'Ⴗ', - 'ⴘ' => 'Ⴘ', - 'ⴙ' => 'Ⴙ', - 'ⴚ' => 'Ⴚ', - 'ⴛ' => 'Ⴛ', - 'ⴜ' => 'Ⴜ', - 'ⴝ' => 'Ⴝ', - 'ⴞ' => 'Ⴞ', - 'ⴟ' => 'Ⴟ', - 'ⴠ' => 'Ⴠ', - 'ⴡ' => 'Ⴡ', - 'ⴢ' => 'Ⴢ', - 'ⴣ' => 'Ⴣ', - 'ⴤ' => 'Ⴤ', - 'ⴥ' => 'Ⴥ', - 'ꙁ' => 'Ꙁ', - 'ꙃ' => 'Ꙃ', - 'ꙅ' => 'Ꙅ', - 'ꙇ' => 'Ꙇ', - 'ꙉ' => 'Ꙉ', - 'ꙋ' => 'Ꙋ', - 'ꙍ' => 'Ꙍ', - 'ꙏ' => 'Ꙏ', - 'ꙑ' => 'Ꙑ', - 'ꙓ' => 'Ꙓ', - 'ꙕ' => 'Ꙕ', - 'ꙗ' => 'Ꙗ', - 'ꙙ' => 'Ꙙ', - 'ꙛ' => 'Ꙛ', - 'ꙝ' => 'Ꙝ', - 'ꙟ' => 'Ꙟ', - 'ꙡ' => 'Ꙡ', - 'ꙣ' => 'Ꙣ', - 'ꙥ' => 'Ꙥ', - 'ꙧ' => 'Ꙧ', - 'ꙩ' => 'Ꙩ', - 'ꙫ' => 'Ꙫ', - 'ꙭ' => 'Ꙭ', - 'ꚁ' => 'Ꚁ', - 'ꚃ' => 'Ꚃ', - 'ꚅ' => 'Ꚅ', - 'ꚇ' => 'Ꚇ', - 'ꚉ' => 'Ꚉ', - 'ꚋ' => 'Ꚋ', - 'ꚍ' => 'Ꚍ', - 'ꚏ' => 'Ꚏ', - 'ꚑ' => 'Ꚑ', - 'ꚓ' => 'Ꚓ', - 'ꚕ' => 'Ꚕ', - 'ꚗ' => 'Ꚗ', - 'ꜣ' => 'Ꜣ', - 'ꜥ' => 'Ꜥ', - 'ꜧ' => 'Ꜧ', - 'ꜩ' => 'Ꜩ', - 'ꜫ' => 'Ꜫ', - 'ꜭ' => 'Ꜭ', - 'ꜯ' => 'Ꜯ', - 'ꜳ' => 'Ꜳ', - 'ꜵ' => 'Ꜵ', - 'ꜷ' => 'Ꜷ', - 'ꜹ' => 'Ꜹ', - 'ꜻ' => 'Ꜻ', - 'ꜽ' => 'Ꜽ', - 'ꜿ' => 'Ꜿ', - 'ꝁ' => 'Ꝁ', - 'ꝃ' => 'Ꝃ', - 'ꝅ' => 'Ꝅ', - 'ꝇ' => 'Ꝇ', - 'ꝉ' => 'Ꝉ', - 'ꝋ' => 'Ꝋ', - 'ꝍ' => 'Ꝍ', - 'ꝏ' => 'Ꝏ', - 'ꝑ' => 'Ꝑ', - 'ꝓ' => 'Ꝓ', - 'ꝕ' => 'Ꝕ', - 'ꝗ' => 'Ꝗ', - 'ꝙ' => 'Ꝙ', - 'ꝛ' => 'Ꝛ', - 'ꝝ' => 'Ꝝ', - 'ꝟ' => 'Ꝟ', - 'ꝡ' => 'Ꝡ', - 'ꝣ' => 'Ꝣ', - 'ꝥ' => 'Ꝥ', - 'ꝧ' => 'Ꝧ', - 'ꝩ' => 'Ꝩ', - 'ꝫ' => 'Ꝫ', - 'ꝭ' => 'Ꝭ', - 'ꝯ' => 'Ꝯ', - 'ꝺ' => 'Ꝺ', - 'ꝼ' => 'Ꝼ', - 'ꝿ' => 'Ꝿ', - 'ꞁ' => 'Ꞁ', - 'ꞃ' => 'Ꞃ', - 'ꞅ' => 'Ꞅ', - 'ꞇ' => 'Ꞇ', - 'ꞌ' => 'Ꞌ', - 'ꞑ' => 'Ꞑ', - 'ꞡ' => 'Ꞡ', - 'ꞣ' => 'Ꞣ', - 'ꞥ' => 'Ꞥ', - 'ꞧ' => 'Ꞧ', - 'ꞩ' => 'Ꞩ', - 'ａ' => 'Ａ', - 'ｂ' => 'Ｂ', - 'ｃ' => 'Ｃ', - 'ｄ' => 'Ｄ', - 'ｅ' => 'Ｅ', - 'ｆ' => 'Ｆ', - 'ｇ' => 'Ｇ', - 'ｈ' => 'Ｈ', - 'ｉ' => 'Ｉ', - 'ｊ' => 'Ｊ', - 'ｋ' => 'Ｋ', - 'ｌ' => 'Ｌ', - 'ｍ' => 'Ｍ', - 'ｎ' => 'Ｎ', - 'ｏ' => 'Ｏ', - 'ｐ' => 'Ｐ', - 'ｑ' => 'Ｑ', - 'ｒ' => 'Ｒ', - 'ｓ' => 'Ｓ', - 'ｔ' => 'Ｔ', - 'ｕ' => 'Ｕ', - 'ｖ' => 'Ｖ', - 'ｗ' => 'Ｗ', - 'ｘ' => 'Ｘ', - 'ｙ' => 'Ｙ', - 'ｚ' => 'Ｚ', - '𐐨' => '𐐀', - '𐐩' => '𐐁', - '𐐪' => '𐐂', - '𐐫' => '𐐃', - '𐐬' => '𐐄', - '𐐭' => '𐐅', - '𐐮' => '𐐆', - '𐐯' => '𐐇', - '𐐰' => '𐐈', - '𐐱' => '𐐉', - '𐐲' => '𐐊', - '𐐳' => '𐐋', - '𐐴' => '𐐌', - '𐐵' => '𐐍', - '𐐶' => '𐐎', - '𐐷' => '𐐏', - '𐐸' => '𐐐', - '𐐹' => '𐐑', - '𐐺' => '𐐒', - '𐐻' => '𐐓', - '𐐼' => '𐐔', - '𐐽' => '𐐕', - '𐐾' => '𐐖', - '𐐿' => '𐐗', - '𐑀' => '𐐘', - '𐑁' => '𐐙', - '𐑂' => '𐐚', - '𐑃' => '𐐛', - '𐑄' => '𐐜', - '𐑅' => '𐐝', - '𐑆' => '𐐞', - '𐑇' => '𐐟', - '𐑈' => '𐐠', - '𐑉' => '𐐡', - '𐑊' => '𐐢', - '𐑋' => '𐐣', - '𐑌' => '𐐤', - '𐑍' => '𐐥', - '𐑎' => '𐐦', - '𐑏' => '𐐧' -); - -/** - * Translation array to get lower case character - */ -$wikiLowerChars = array( - 'A' => 'a', - 'B' => 'b', - 'C' => 'c', - 'D' => 'd', - 'E' => 'e', - 'F' => 'f', - 'G' => 'g', - 'H' => 'h', - 'I' => 'i', - 'J' => 'j', - 'K' => 'k', - 'L' => 'l', - 'M' => 'm', - 'N' => 'n', - 'O' => 'o', - 'P' => 'p', - 'Q' => 'q', - 'R' => 'r', - 'S' => 's', - 'T' => 't', - 'U' => 'u', - 'V' => 'v', - 'W' => 'w', - 'X' => 'x', - 'Y' => 'y', - 'Z' => 'z', - 'À' => 'à', - 'Á' => 'á', - 'Â' => 'â', - 'Ã' => 'ã', - 'Ä' => 'ä', - 'Å' => 'å', - 'Æ' => 'æ', - 'Ç' => 'ç', - 'È' => 'è', - 'É' => 'é', - 'Ê' => 'ê', - 'Ë' => 'ë', - 'Ì' => 'ì', - 'Í' => 'í', - 'Î' => 'î', - 'Ï' => 'ï', - 'Ð' => 'ð', - 'Ñ' => 'ñ', - 'Ò' => 'ò', - 'Ó' => 'ó', - 'Ô' => 'ô', - 'Õ' => 'õ', - 'Ö' => 'ö', - 'Ø' => 'ø', - 'Ù' => 'ù', - 'Ú' => 'ú', - 'Û' => 'û', - 'Ü' => 'ü', - 'Ý' => 'ý', - 'Þ' => 'þ', - 'Ā' => 'ā', - 'Ă' => 'ă', - 'Ą' => 'ą', - 'Ć' => 'ć', - 'Ĉ' => 'ĉ', - 'Ċ' => 'ċ', - 'Č' => 'č', - 'Ď' => 'ď', - 'Đ' => 'đ', - 'Ē' => 'ē', - 'Ĕ' => 'ĕ', - 'Ė' => 'ė', - 'Ę' => 'ę', - 'Ě' => 'ě', - 'Ĝ' => 'ĝ', - 'Ğ' => 'ğ', - 'Ġ' => 'ġ', - 'Ģ' => 'ģ', - 'Ĥ' => 'ĥ', - 'Ħ' => 'ħ', - 'Ĩ' => 'ĩ', - 'Ī' => 'ī', - 'Ĭ' => 'ĭ', - 'Į' => 'į', - 'İ' => 'i', - 'IJ' => 'ij', - 'Ĵ' => 'ĵ', - 'Ķ' => 'ķ', - 'Ĺ' => 'ĺ', - 'Ļ' => 'ļ', - 'Ľ' => 'ľ', - 'Ŀ' => 'ŀ', - 'Ł' => 'ł', - 'Ń' => 'ń', - 'Ņ' => 'ņ', - 'Ň' => 'ň', - 'Ŋ' => 'ŋ', - 'Ō' => 'ō', - 'Ŏ' => 'ŏ', - 'Ő' => 'ő', - 'Œ' => 'œ', - 'Ŕ' => 'ŕ', - 'Ŗ' => 'ŗ', - 'Ř' => 'ř', - 'Ś' => 'ś', - 'Ŝ' => 'ŝ', - 'Ş' => 'ş', - 'Š' => 'š', - 'Ţ' => 'ţ', - 'Ť' => 'ť', - 'Ŧ' => 'ŧ', - 'Ũ' => 'ũ', - 'Ū' => 'ū', - 'Ŭ' => 'ŭ', - 'Ů' => 'ů', - 'Ű' => 'ű', - 'Ų' => 'ų', - 'Ŵ' => 'ŵ', - 'Ŷ' => 'ŷ', - 'Ÿ' => 'ÿ', - 'Ź' => 'ź', - 'Ż' => 'ż', - 'Ž' => 'ž', - 'Ɓ' => 'ɓ', - 'Ƃ' => 'ƃ', - 'Ƅ' => 'ƅ', - 'Ɔ' => 'ɔ', - 'Ƈ' => 'ƈ', - 'Ɖ' => 'ɖ', - 'Ɗ' => 'ɗ', - 'Ƌ' => 'ƌ', - 'Ǝ' => 'ǝ', - 'Ə' => 'ə', - 'Ɛ' => 'ɛ', - 'Ƒ' => 'ƒ', - 'Ɠ' => 'ɠ', - 'Ɣ' => 'ɣ', - 'Ɩ' => 'ɩ', - 'Ɨ' => 'ɨ', - 'Ƙ' => 'ƙ', - 'Ɯ' => 'ɯ', - 'Ɲ' => 'ɲ', - 'Ɵ' => 'ɵ', - 'Ơ' => 'ơ', - 'Ƣ' => 'ƣ', - 'Ƥ' => 'ƥ', - 'Ʀ' => 'ʀ', - 'Ƨ' => 'ƨ', - 'Ʃ' => 'ʃ', - 'Ƭ' => 'ƭ', - 'Ʈ' => 'ʈ', - 'Ư' => 'ư', - 'Ʊ' => 'ʊ', - 'Ʋ' => 'ʋ', - 'Ƴ' => 'ƴ', - 'Ƶ' => 'ƶ', - 'Ʒ' => 'ʒ', - 'Ƹ' => 'ƹ', - 'Ƽ' => 'ƽ', - 'DŽ' => 'dž', - 'Dž' => 'dž', - 'LJ' => 'lj', - 'Lj' => 'lj', - 'NJ' => 'nj', - 'Nj' => 'nj', - 'Ǎ' => 'ǎ', - 'Ǐ' => 'ǐ', - 'Ǒ' => 'ǒ', - 'Ǔ' => 'ǔ', - 'Ǖ' => 'ǖ', - 'Ǘ' => 'ǘ', - 'Ǚ' => 'ǚ', - 'Ǜ' => 'ǜ', - 'Ǟ' => 'ǟ', - 'Ǡ' => 'ǡ', - 'Ǣ' => 'ǣ', - 'Ǥ' => 'ǥ', - 'Ǧ' => 'ǧ', - 'Ǩ' => 'ǩ', - 'Ǫ' => 'ǫ', - 'Ǭ' => 'ǭ', - 'Ǯ' => 'ǯ', - 'DZ' => 'dz', - 'Dz' => 'dz', - 'Ǵ' => 'ǵ', - 'Ƕ' => 'ƕ', - 'Ƿ' => 'ƿ', - 'Ǹ' => 'ǹ', - 'Ǻ' => 'ǻ', - 'Ǽ' => 'ǽ', - 'Ǿ' => 'ǿ', - 'Ȁ' => 'ȁ', - 'Ȃ' => 'ȃ', - 'Ȅ' => 'ȅ', - 'Ȇ' => 'ȇ', - 'Ȉ' => 'ȉ', - 'Ȋ' => 'ȋ', - 'Ȍ' => 'ȍ', - 'Ȏ' => 'ȏ', - 'Ȑ' => 'ȑ', - 'Ȓ' => 'ȓ', - 'Ȕ' => 'ȕ', - 'Ȗ' => 'ȗ', - 'Ș' => 'ș', - 'Ț' => 'ț', - 'Ȝ' => 'ȝ', - 'Ȟ' => 'ȟ', - 'Ƞ' => 'ƞ', - 'Ȣ' => 'ȣ', - 'Ȥ' => 'ȥ', - 'Ȧ' => 'ȧ', - 'Ȩ' => 'ȩ', - 'Ȫ' => 'ȫ', - 'Ȭ' => 'ȭ', - 'Ȯ' => 'ȯ', - 'Ȱ' => 'ȱ', - 'Ȳ' => 'ȳ', - 'Ⱥ' => 'ⱥ', - 'Ȼ' => 'ȼ', - 'Ƚ' => 'ƚ', - 'Ⱦ' => 'ⱦ', - 'Ɂ' => 'ɂ', - 'Ƀ' => 'ƀ', - 'Ʉ' => 'ʉ', - 'Ʌ' => 'ʌ', - 'Ɇ' => 'ɇ', - 'Ɉ' => 'ɉ', - 'Ɋ' => 'ɋ', - 'Ɍ' => 'ɍ', - 'Ɏ' => 'ɏ', - 'Ͱ' => 'ͱ', - 'Ͳ' => 'ͳ', - 'Ͷ' => 'ͷ', - 'Ά' => 'ά', - 'Έ' => 'έ', - 'Ή' => 'ή', - 'Ί' => 'ί', - 'Ό' => 'ό', - 'Ύ' => 'ύ', - 'Ώ' => 'ώ', - 'Α' => 'α', - 'Β' => 'β', - 'Γ' => 'γ', - 'Δ' => 'δ', - 'Ε' => 'ε', - 'Ζ' => 'ζ', - 'Η' => 'η', - 'Θ' => 'θ', - 'Ι' => 'ι', - 'Κ' => 'κ', - 'Λ' => 'λ', - 'Μ' => 'μ', - 'Ν' => 'ν', - 'Ξ' => 'ξ', - 'Ο' => 'ο', - 'Π' => 'π', - 'Ρ' => 'ρ', - 'Σ' => 'σ', - 'Τ' => 'τ', - 'Υ' => 'υ', - 'Φ' => 'φ', - 'Χ' => 'χ', - 'Ψ' => 'ψ', - 'Ω' => 'ω', - 'Ϊ' => 'ϊ', - 'Ϋ' => 'ϋ', - 'Ϗ' => 'ϗ', - 'Ϙ' => 'ϙ', - 'Ϛ' => 'ϛ', - 'Ϝ' => 'ϝ', - 'Ϟ' => 'ϟ', - 'Ϡ' => 'ϡ', - 'Ϣ' => 'ϣ', - 'Ϥ' => 'ϥ', - 'Ϧ' => 'ϧ', - 'Ϩ' => 'ϩ', - 'Ϫ' => 'ϫ', - 'Ϭ' => 'ϭ', - 'Ϯ' => 'ϯ', - 'ϴ' => 'θ', - 'Ϸ' => 'ϸ', - 'Ϲ' => 'ϲ', - 'Ϻ' => 'ϻ', - 'Ͻ' => 'ͻ', - 'Ͼ' => 'ͼ', - 'Ͽ' => 'ͽ', - 'Ѐ' => 'ѐ', - 'Ё' => 'ё', - 'Ђ' => 'ђ', - 'Ѓ' => 'ѓ', - 'Є' => 'є', - 'Ѕ' => 'ѕ', - 'І' => 'і', - 'Ї' => 'ї', - 'Ј' => 'ј', - 'Љ' => 'љ', - 'Њ' => 'њ', - 'Ћ' => 'ћ', - 'Ќ' => 'ќ', - 'Ѝ' => 'ѝ', - 'Ў' => 'ў', - 'Џ' => 'џ', - 'А' => 'а', - 'Б' => 'б', - 'В' => 'в', - 'Г' => 'г', - 'Д' => 'д', - 'Е' => 'е', - 'Ж' => 'ж', - 'З' => 'з', - 'И' => 'и', - 'Й' => 'й', - 'К' => 'к', - 'Л' => 'л', - 'М' => 'м', - 'Н' => 'н', - 'О' => 'о', - 'П' => 'п', - 'Р' => 'р', - 'С' => 'с', - 'Т' => 'т', - 'У' => 'у', - 'Ф' => 'ф', - 'Х' => 'х', - 'Ц' => 'ц', - 'Ч' => 'ч', - 'Ш' => 'ш', - 'Щ' => 'щ', - 'Ъ' => 'ъ', - 'Ы' => 'ы', - 'Ь' => 'ь', - 'Э' => 'э', - 'Ю' => 'ю', - 'Я' => 'я', - 'Ѡ' => 'ѡ', - 'Ѣ' => 'ѣ', - 'Ѥ' => 'ѥ', - 'Ѧ' => 'ѧ', - 'Ѩ' => 'ѩ', - 'Ѫ' => 'ѫ', - 'Ѭ' => 'ѭ', - 'Ѯ' => 'ѯ', - 'Ѱ' => 'ѱ', - 'Ѳ' => 'ѳ', - 'Ѵ' => 'ѵ', - 'Ѷ' => 'ѷ', - 'Ѹ' => 'ѹ', - 'Ѻ' => 'ѻ', - 'Ѽ' => 'ѽ', - 'Ѿ' => 'ѿ', - 'Ҁ' => 'ҁ', - 'Ҋ' => 'ҋ', - 'Ҍ' => 'ҍ', - 'Ҏ' => 'ҏ', - 'Ґ' => 'ґ', - 'Ғ' => 'ғ', - 'Ҕ' => 'ҕ', - 'Җ' => 'җ', - 'Ҙ' => 'ҙ', - 'Қ' => 'қ', - 'Ҝ' => 'ҝ', - 'Ҟ' => 'ҟ', - 'Ҡ' => 'ҡ', - 'Ң' => 'ң', - 'Ҥ' => 'ҥ', - 'Ҧ' => 'ҧ', - 'Ҩ' => 'ҩ', - 'Ҫ' => 'ҫ', - 'Ҭ' => 'ҭ', - 'Ү' => 'ү', - 'Ұ' => 'ұ', - 'Ҳ' => 'ҳ', - 'Ҵ' => 'ҵ', - 'Ҷ' => 'ҷ', - 'Ҹ' => 'ҹ', - 'Һ' => 'һ', - 'Ҽ' => 'ҽ', - 'Ҿ' => 'ҿ', - 'Ӏ' => 'ӏ', - 'Ӂ' => 'ӂ', - 'Ӄ' => 'ӄ', - 'Ӆ' => 'ӆ', - 'Ӈ' => 'ӈ', - 'Ӊ' => 'ӊ', - 'Ӌ' => 'ӌ', - 'Ӎ' => 'ӎ', - 'Ӑ' => 'ӑ', - 'Ӓ' => 'ӓ', - 'Ӕ' => 'ӕ', - 'Ӗ' => 'ӗ', - 'Ә' => 'ә', - 'Ӛ' => 'ӛ', - 'Ӝ' => 'ӝ', - 'Ӟ' => 'ӟ', - 'Ӡ' => 'ӡ', - 'Ӣ' => 'ӣ', - 'Ӥ' => 'ӥ', - 'Ӧ' => 'ӧ', - 'Ө' => 'ө', - 'Ӫ' => 'ӫ', - 'Ӭ' => 'ӭ', - 'Ӯ' => 'ӯ', - 'Ӱ' => 'ӱ', - 'Ӳ' => 'ӳ', - 'Ӵ' => 'ӵ', - 'Ӷ' => 'ӷ', - 'Ӹ' => 'ӹ', - 'Ӻ' => 'ӻ', - 'Ӽ' => 'ӽ', - 'Ӿ' => 'ӿ', - 'Ԁ' => 'ԁ', - 'Ԃ' => 'ԃ', - 'Ԅ' => 'ԅ', - 'Ԇ' => 'ԇ', - 'Ԉ' => 'ԉ', - 'Ԋ' => 'ԋ', - 'Ԍ' => 'ԍ', - 'Ԏ' => 'ԏ', - 'Ԑ' => 'ԑ', - 'Ԓ' => 'ԓ', - 'Ԕ' => 'ԕ', - 'Ԗ' => 'ԗ', - 'Ԙ' => 'ԙ', - 'Ԛ' => 'ԛ', - 'Ԝ' => 'ԝ', - 'Ԟ' => 'ԟ', - 'Ԡ' => 'ԡ', - 'Ԣ' => 'ԣ', - 'Ԥ' => 'ԥ', - 'Ԧ' => 'ԧ', - 'Ա' => 'ա', - 'Բ' => 'բ', - 'Գ' => 'գ', - 'Դ' => 'դ', - 'Ե' => 'ե', - 'Զ' => 'զ', - 'Է' => 'է', - 'Ը' => 'ը', - 'Թ' => 'թ', - 'Ժ' => 'ժ', - 'Ի' => 'ի', - 'Լ' => 'լ', - 'Խ' => 'խ', - 'Ծ' => 'ծ', - 'Կ' => 'կ', - 'Հ' => 'հ', - 'Ձ' => 'ձ', - 'Ղ' => 'ղ', - 'Ճ' => 'ճ', - 'Մ' => 'մ', - 'Յ' => 'յ', - 'Ն' => 'ն', - 'Շ' => 'շ', - 'Ո' => 'ո', - 'Չ' => 'չ', - 'Պ' => 'պ', - 'Ջ' => 'ջ', - 'Ռ' => 'ռ', - 'Ս' => 'ս', - 'Վ' => 'վ', - 'Տ' => 'տ', - 'Ր' => 'ր', - 'Ց' => 'ց', - 'Ւ' => 'ւ', - 'Փ' => 'փ', - 'Ք' => 'ք', - 'Օ' => 'օ', - 'Ֆ' => 'ֆ', - 'Ⴀ' => 'ⴀ', - 'Ⴁ' => 'ⴁ', - 'Ⴂ' => 'ⴂ', - 'Ⴃ' => 'ⴃ', - 'Ⴄ' => 'ⴄ', - 'Ⴅ' => 'ⴅ', - 'Ⴆ' => 'ⴆ', - 'Ⴇ' => 'ⴇ', - 'Ⴈ' => 'ⴈ', - 'Ⴉ' => 'ⴉ', - 'Ⴊ' => 'ⴊ', - 'Ⴋ' => 'ⴋ', - 'Ⴌ' => 'ⴌ', - 'Ⴍ' => 'ⴍ', - 'Ⴎ' => 'ⴎ', - 'Ⴏ' => 'ⴏ', - 'Ⴐ' => 'ⴐ', - 'Ⴑ' => 'ⴑ', - 'Ⴒ' => 'ⴒ', - 'Ⴓ' => 'ⴓ', - 'Ⴔ' => 'ⴔ', - 'Ⴕ' => 'ⴕ', - 'Ⴖ' => 'ⴖ', - 'Ⴗ' => 'ⴗ', - 'Ⴘ' => 'ⴘ', - 'Ⴙ' => 'ⴙ', - 'Ⴚ' => 'ⴚ', - 'Ⴛ' => 'ⴛ', - 'Ⴜ' => 'ⴜ', - 'Ⴝ' => 'ⴝ', - 'Ⴞ' => 'ⴞ', - 'Ⴟ' => 'ⴟ', - 'Ⴠ' => 'ⴠ', - 'Ⴡ' => 'ⴡ', - 'Ⴢ' => 'ⴢ', - 'Ⴣ' => 'ⴣ', - 'Ⴤ' => 'ⴤ', - 'Ⴥ' => 'ⴥ', - 'Ḁ' => 'ḁ', - 'Ḃ' => 'ḃ', - 'Ḅ' => 'ḅ', - 'Ḇ' => 'ḇ', - 'Ḉ' => 'ḉ', - 'Ḋ' => 'ḋ', - 'Ḍ' => 'ḍ', - 'Ḏ' => 'ḏ', - 'Ḑ' => 'ḑ', - 'Ḓ' => 'ḓ', - 'Ḕ' => 'ḕ', - 'Ḗ' => 'ḗ', - 'Ḙ' => 'ḙ', - 'Ḛ' => 'ḛ', - 'Ḝ' => 'ḝ', - 'Ḟ' => 'ḟ', - 'Ḡ' => 'ḡ', - 'Ḣ' => 'ḣ', - 'Ḥ' => 'ḥ', - 'Ḧ' => 'ḧ', - 'Ḩ' => 'ḩ', - 'Ḫ' => 'ḫ', - 'Ḭ' => 'ḭ', - 'Ḯ' => 'ḯ', - 'Ḱ' => 'ḱ', - 'Ḳ' => 'ḳ', - 'Ḵ' => 'ḵ', - 'Ḷ' => 'ḷ', - 'Ḹ' => 'ḹ', - 'Ḻ' => 'ḻ', - 'Ḽ' => 'ḽ', - 'Ḿ' => 'ḿ', - 'Ṁ' => 'ṁ', - 'Ṃ' => 'ṃ', - 'Ṅ' => 'ṅ', - 'Ṇ' => 'ṇ', - 'Ṉ' => 'ṉ', - 'Ṋ' => 'ṋ', - 'Ṍ' => 'ṍ', - 'Ṏ' => 'ṏ', - 'Ṑ' => 'ṑ', - 'Ṓ' => 'ṓ', - 'Ṕ' => 'ṕ', - 'Ṗ' => 'ṗ', - 'Ṙ' => 'ṙ', - 'Ṛ' => 'ṛ', - 'Ṝ' => 'ṝ', - 'Ṟ' => 'ṟ', - 'Ṡ' => 'ṡ', - 'Ṣ' => 'ṣ', - 'Ṥ' => 'ṥ', - 'Ṧ' => 'ṧ', - 'Ṩ' => 'ṩ', - 'Ṫ' => 'ṫ', - 'Ṭ' => 'ṭ', - 'Ṯ' => 'ṯ', - 'Ṱ' => 'ṱ', - 'Ṳ' => 'ṳ', - 'Ṵ' => 'ṵ', - 'Ṷ' => 'ṷ', - 'Ṹ' => 'ṹ', - 'Ṻ' => 'ṻ', - 'Ṽ' => 'ṽ', - 'Ṿ' => 'ṿ', - 'Ẁ' => 'ẁ', - 'Ẃ' => 'ẃ', - 'Ẅ' => 'ẅ', - 'Ẇ' => 'ẇ', - 'Ẉ' => 'ẉ', - 'Ẋ' => 'ẋ', - 'Ẍ' => 'ẍ', - 'Ẏ' => 'ẏ', - 'Ẑ' => 'ẑ', - 'Ẓ' => 'ẓ', - 'Ẕ' => 'ẕ', - 'ẞ' => 'ß', - 'Ạ' => 'ạ', - 'Ả' => 'ả', - 'Ấ' => 'ấ', - 'Ầ' => 'ầ', - 'Ẩ' => 'ẩ', - 'Ẫ' => 'ẫ', - 'Ậ' => 'ậ', - 'Ắ' => 'ắ', - 'Ằ' => 'ằ', - 'Ẳ' => 'ẳ', - 'Ẵ' => 'ẵ', - 'Ặ' => 'ặ', - 'Ẹ' => 'ẹ', - 'Ẻ' => 'ẻ', - 'Ẽ' => 'ẽ', - 'Ế' => 'ế', - 'Ề' => 'ề', - 'Ể' => 'ể', - 'Ễ' => 'ễ', - 'Ệ' => 'ệ', - 'Ỉ' => 'ỉ', - 'Ị' => 'ị', - 'Ọ' => 'ọ', - 'Ỏ' => 'ỏ', - 'Ố' => 'ố', - 'Ồ' => 'ồ', - 'Ổ' => 'ổ', - 'Ỗ' => 'ỗ', - 'Ộ' => 'ộ', - 'Ớ' => 'ớ', - 'Ờ' => 'ờ', - 'Ở' => 'ở', - 'Ỡ' => 'ỡ', - 'Ợ' => 'ợ', - 'Ụ' => 'ụ', - 'Ủ' => 'ủ', - 'Ứ' => 'ứ', - 'Ừ' => 'ừ', - 'Ử' => 'ử', - 'Ữ' => 'ữ', - 'Ự' => 'ự', - 'Ỳ' => 'ỳ', - 'Ỵ' => 'ỵ', - 'Ỷ' => 'ỷ', - 'Ỹ' => 'ỹ', - 'Ỻ' => 'ỻ', - 'Ỽ' => 'ỽ', - 'Ỿ' => 'ỿ', - 'Ἀ' => 'ἀ', - 'Ἁ' => 'ἁ', - 'Ἂ' => 'ἂ', - 'Ἃ' => 'ἃ', - 'Ἄ' => 'ἄ', - 'Ἅ' => 'ἅ', - 'Ἆ' => 'ἆ', - 'Ἇ' => 'ἇ', - 'Ἐ' => 'ἐ', - 'Ἑ' => 'ἑ', - 'Ἒ' => 'ἒ', - 'Ἓ' => 'ἓ', - 'Ἔ' => 'ἔ', - 'Ἕ' => 'ἕ', - 'Ἠ' => 'ἠ', - 'Ἡ' => 'ἡ', - 'Ἢ' => 'ἢ', - 'Ἣ' => 'ἣ', - 'Ἤ' => 'ἤ', - 'Ἥ' => 'ἥ', - 'Ἦ' => 'ἦ', - 'Ἧ' => 'ἧ', - 'Ἰ' => 'ἰ', - 'Ἱ' => 'ἱ', - 'Ἲ' => 'ἲ', - 'Ἳ' => 'ἳ', - 'Ἴ' => 'ἴ', - 'Ἵ' => 'ἵ', - 'Ἶ' => 'ἶ', - 'Ἷ' => 'ἷ', - 'Ὀ' => 'ὀ', - 'Ὁ' => 'ὁ', - 'Ὂ' => 'ὂ', - 'Ὃ' => 'ὃ', - 'Ὄ' => 'ὄ', - 'Ὅ' => 'ὅ', - 'Ὑ' => 'ὑ', - 'Ὓ' => 'ὓ', - 'Ὕ' => 'ὕ', - 'Ὗ' => 'ὗ', - 'Ὠ' => 'ὠ', - 'Ὡ' => 'ὡ', - 'Ὢ' => 'ὢ', - 'Ὣ' => 'ὣ', - 'Ὤ' => 'ὤ', - 'Ὥ' => 'ὥ', - 'Ὦ' => 'ὦ', - 'Ὧ' => 'ὧ', - 'ᾈ' => 'ᾀ', - 'ᾉ' => 'ᾁ', - 'ᾊ' => 'ᾂ', - 'ᾋ' => 'ᾃ', - 'ᾌ' => 'ᾄ', - 'ᾍ' => 'ᾅ', - 'ᾎ' => 'ᾆ', - 'ᾏ' => 'ᾇ', - 'ᾘ' => 'ᾐ', - 'ᾙ' => 'ᾑ', - 'ᾚ' => 'ᾒ', - 'ᾛ' => 'ᾓ', - 'ᾜ' => 'ᾔ', - 'ᾝ' => 'ᾕ', - 'ᾞ' => 'ᾖ', - 'ᾟ' => 'ᾗ', - 'ᾨ' => 'ᾠ', - 'ᾩ' => 'ᾡ', - 'ᾪ' => 'ᾢ', - 'ᾫ' => 'ᾣ', - 'ᾬ' => 'ᾤ', - 'ᾭ' => 'ᾥ', - 'ᾮ' => 'ᾦ', - 'ᾯ' => 'ᾧ', - 'Ᾰ' => 'ᾰ', - 'Ᾱ' => 'ᾱ', - 'Ὰ' => 'ὰ', - 'Ά' => 'ά', - 'ᾼ' => 'ᾳ', - 'Ὲ' => 'ὲ', - 'Έ' => 'έ', - 'Ὴ' => 'ὴ', - 'Ή' => 'ή', - 'ῌ' => 'ῃ', - 'Ῐ' => 'ῐ', - 'Ῑ' => 'ῑ', - 'Ὶ' => 'ὶ', - 'Ί' => 'ί', - 'Ῠ' => 'ῠ', - 'Ῡ' => 'ῡ', - 'Ὺ' => 'ὺ', - 'Ύ' => 'ύ', - 'Ῥ' => 'ῥ', - 'Ὸ' => 'ὸ', - 'Ό' => 'ό', - 'Ὼ' => 'ὼ', - 'Ώ' => 'ώ', - 'ῼ' => 'ῳ', - 'Ω' => 'ω', - 'K' => 'k', - 'Å' => 'å', - 'Ⅎ' => 'ⅎ', - 'Ⅰ' => 'ⅰ', - 'Ⅱ' => 'ⅱ', - 'Ⅲ' => 'ⅲ', - 'Ⅳ' => 'ⅳ', - 'Ⅴ' => 'ⅴ', - 'Ⅵ' => 'ⅵ', - 'Ⅶ' => 'ⅶ', - 'Ⅷ' => 'ⅷ', - 'Ⅸ' => 'ⅸ', - 'Ⅹ' => 'ⅹ', - 'Ⅺ' => 'ⅺ', - 'Ⅻ' => 'ⅻ', - 'Ⅼ' => 'ⅼ', - 'Ⅽ' => 'ⅽ', - 'Ⅾ' => 'ⅾ', - 'Ⅿ' => 'ⅿ', - 'Ↄ' => 'ↄ', - 'Ⓐ' => 'ⓐ', - 'Ⓑ' => 'ⓑ', - 'Ⓒ' => 'ⓒ', - 'Ⓓ' => 'ⓓ', - 'Ⓔ' => 'ⓔ', - 'Ⓕ' => 'ⓕ', - 'Ⓖ' => 'ⓖ', - 'Ⓗ' => 'ⓗ', - 'Ⓘ' => 'ⓘ', - 'Ⓙ' => 'ⓙ', - 'Ⓚ' => 'ⓚ', - 'Ⓛ' => 'ⓛ', - 'Ⓜ' => 'ⓜ', - 'Ⓝ' => 'ⓝ', - 'Ⓞ' => 'ⓞ', - 'Ⓟ' => 'ⓟ', - 'Ⓠ' => 'ⓠ', - 'Ⓡ' => 'ⓡ', - 'Ⓢ' => 'ⓢ', - 'Ⓣ' => 'ⓣ', - 'Ⓤ' => 'ⓤ', - 'Ⓥ' => 'ⓥ', - 'Ⓦ' => 'ⓦ', - 'Ⓧ' => 'ⓧ', - 'Ⓨ' => 'ⓨ', - 'Ⓩ' => 'ⓩ', - 'Ⰰ' => 'ⰰ', - 'Ⰱ' => 'ⰱ', - 'Ⰲ' => 'ⰲ', - 'Ⰳ' => 'ⰳ', - 'Ⰴ' => 'ⰴ', - 'Ⰵ' => 'ⰵ', - 'Ⰶ' => 'ⰶ', - 'Ⰷ' => 'ⰷ', - 'Ⰸ' => 'ⰸ', - 'Ⰹ' => 'ⰹ', - 'Ⰺ' => 'ⰺ', - 'Ⰻ' => 'ⰻ', - 'Ⰼ' => 'ⰼ', - 'Ⰽ' => 'ⰽ', - 'Ⰾ' => 'ⰾ', - 'Ⰿ' => 'ⰿ', - 'Ⱀ' => 'ⱀ', - 'Ⱁ' => 'ⱁ', - 'Ⱂ' => 'ⱂ', - 'Ⱃ' => 'ⱃ', - 'Ⱄ' => 'ⱄ', - 'Ⱅ' => 'ⱅ', - 'Ⱆ' => 'ⱆ', - 'Ⱇ' => 'ⱇ', - 'Ⱈ' => 'ⱈ', - 'Ⱉ' => 'ⱉ', - 'Ⱊ' => 'ⱊ', - 'Ⱋ' => 'ⱋ', - 'Ⱌ' => 'ⱌ', - 'Ⱍ' => 'ⱍ', - 'Ⱎ' => 'ⱎ', - 'Ⱏ' => 'ⱏ', - 'Ⱐ' => 'ⱐ', - 'Ⱑ' => 'ⱑ', - 'Ⱒ' => 'ⱒ', - 'Ⱓ' => 'ⱓ', - 'Ⱔ' => 'ⱔ', - 'Ⱕ' => 'ⱕ', - 'Ⱖ' => 'ⱖ', - 'Ⱗ' => 'ⱗ', - 'Ⱘ' => 'ⱘ', - 'Ⱙ' => 'ⱙ', - 'Ⱚ' => 'ⱚ', - 'Ⱛ' => 'ⱛ', - 'Ⱜ' => 'ⱜ', - 'Ⱝ' => 'ⱝ', - 'Ⱞ' => 'ⱞ', - 'Ⱡ' => 'ⱡ', - 'Ɫ' => 'ɫ', - 'Ᵽ' => 'ᵽ', - 'Ɽ' => 'ɽ', - 'Ⱨ' => 'ⱨ', - 'Ⱪ' => 'ⱪ', - 'Ⱬ' => 'ⱬ', - 'Ɑ' => 'ɑ', - 'Ɱ' => 'ɱ', - 'Ɐ' => 'ɐ', - 'Ɒ' => 'ɒ', - 'Ⱳ' => 'ⱳ', - 'Ⱶ' => 'ⱶ', - 'Ȿ' => 'ȿ', - 'Ɀ' => 'ɀ', - 'Ⲁ' => 'ⲁ', - 'Ⲃ' => 'ⲃ', - 'Ⲅ' => 'ⲅ', - 'Ⲇ' => 'ⲇ', - 'Ⲉ' => 'ⲉ', - 'Ⲋ' => 'ⲋ', - 'Ⲍ' => 'ⲍ', - 'Ⲏ' => 'ⲏ', - 'Ⲑ' => 'ⲑ', - 'Ⲓ' => 'ⲓ', - 'Ⲕ' => 'ⲕ', - 'Ⲗ' => 'ⲗ', - 'Ⲙ' => 'ⲙ', - 'Ⲛ' => 'ⲛ', - 'Ⲝ' => 'ⲝ', - 'Ⲟ' => 'ⲟ', - 'Ⲡ' => 'ⲡ', - 'Ⲣ' => 'ⲣ', - 'Ⲥ' => 'ⲥ', - 'Ⲧ' => 'ⲧ', - 'Ⲩ' => 'ⲩ', - 'Ⲫ' => 'ⲫ', - 'Ⲭ' => 'ⲭ', - 'Ⲯ' => 'ⲯ', - 'Ⲱ' => 'ⲱ', - 'Ⲳ' => 'ⲳ', - 'Ⲵ' => 'ⲵ', - 'Ⲷ' => 'ⲷ', - 'Ⲹ' => 'ⲹ', - 'Ⲻ' => 'ⲻ', - 'Ⲽ' => 'ⲽ', - 'Ⲿ' => 'ⲿ', - 'Ⳁ' => 'ⳁ', - 'Ⳃ' => 'ⳃ', - 'Ⳅ' => 'ⳅ', - 'Ⳇ' => 'ⳇ', - 'Ⳉ' => 'ⳉ', - 'Ⳋ' => 'ⳋ', - 'Ⳍ' => 'ⳍ', - 'Ⳏ' => 'ⳏ', - 'Ⳑ' => 'ⳑ', - 'Ⳓ' => 'ⳓ', - 'Ⳕ' => 'ⳕ', - 'Ⳗ' => 'ⳗ', - 'Ⳙ' => 'ⳙ', - 'Ⳛ' => 'ⳛ', - 'Ⳝ' => 'ⳝ', - 'Ⳟ' => 'ⳟ', - 'Ⳡ' => 'ⳡ', - 'Ⳣ' => 'ⳣ', - 'Ⳬ' => 'ⳬ', - 'Ⳮ' => 'ⳮ', - 'Ꙁ' => 'ꙁ', - 'Ꙃ' => 'ꙃ', - 'Ꙅ' => 'ꙅ', - 'Ꙇ' => 'ꙇ', - 'Ꙉ' => 'ꙉ', - 'Ꙋ' => 'ꙋ', - 'Ꙍ' => 'ꙍ', - 'Ꙏ' => 'ꙏ', - 'Ꙑ' => 'ꙑ', - 'Ꙓ' => 'ꙓ', - 'Ꙕ' => 'ꙕ', - 'Ꙗ' => 'ꙗ', - 'Ꙙ' => 'ꙙ', - 'Ꙛ' => 'ꙛ', - 'Ꙝ' => 'ꙝ', - 'Ꙟ' => 'ꙟ', - 'Ꙡ' => 'ꙡ', - 'Ꙣ' => 'ꙣ', - 'Ꙥ' => 'ꙥ', - 'Ꙧ' => 'ꙧ', - 'Ꙩ' => 'ꙩ', - 'Ꙫ' => 'ꙫ', - 'Ꙭ' => 'ꙭ', - 'Ꚁ' => 'ꚁ', - 'Ꚃ' => 'ꚃ', - 'Ꚅ' => 'ꚅ', - 'Ꚇ' => 'ꚇ', - 'Ꚉ' => 'ꚉ', - 'Ꚋ' => 'ꚋ', - 'Ꚍ' => 'ꚍ', - 'Ꚏ' => 'ꚏ', - 'Ꚑ' => 'ꚑ', - 'Ꚓ' => 'ꚓ', - 'Ꚕ' => 'ꚕ', - 'Ꚗ' => 'ꚗ', - 'Ꜣ' => 'ꜣ', - 'Ꜥ' => 'ꜥ', - 'Ꜧ' => 'ꜧ', - 'Ꜩ' => 'ꜩ', - 'Ꜫ' => 'ꜫ', - 'Ꜭ' => 'ꜭ', - 'Ꜯ' => 'ꜯ', - 'Ꜳ' => 'ꜳ', - 'Ꜵ' => 'ꜵ', - 'Ꜷ' => 'ꜷ', - 'Ꜹ' => 'ꜹ', - 'Ꜻ' => 'ꜻ', - 'Ꜽ' => 'ꜽ', - 'Ꜿ' => 'ꜿ', - 'Ꝁ' => 'ꝁ', - 'Ꝃ' => 'ꝃ', - 'Ꝅ' => 'ꝅ', - 'Ꝇ' => 'ꝇ', - 'Ꝉ' => 'ꝉ', - 'Ꝋ' => 'ꝋ', - 'Ꝍ' => 'ꝍ', - 'Ꝏ' => 'ꝏ', - 'Ꝑ' => 'ꝑ', - 'Ꝓ' => 'ꝓ', - 'Ꝕ' => 'ꝕ', - 'Ꝗ' => 'ꝗ', - 'Ꝙ' => 'ꝙ', - 'Ꝛ' => 'ꝛ', - 'Ꝝ' => 'ꝝ', - 'Ꝟ' => 'ꝟ', - 'Ꝡ' => 'ꝡ', - 'Ꝣ' => 'ꝣ', - 'Ꝥ' => 'ꝥ', - 'Ꝧ' => 'ꝧ', - 'Ꝩ' => 'ꝩ', - 'Ꝫ' => 'ꝫ', - 'Ꝭ' => 'ꝭ', - 'Ꝯ' => 'ꝯ', - 'Ꝺ' => 'ꝺ', - 'Ꝼ' => 'ꝼ', - 'Ᵹ' => 'ᵹ', - 'Ꝿ' => 'ꝿ', - 'Ꞁ' => 'ꞁ', - 'Ꞃ' => 'ꞃ', - 'Ꞅ' => 'ꞅ', - 'Ꞇ' => 'ꞇ', - 'Ꞌ' => 'ꞌ', - 'Ɥ' => 'ɥ', - 'Ꞑ' => 'ꞑ', - 'Ꞡ' => 'ꞡ', - 'Ꞣ' => 'ꞣ', - 'Ꞥ' => 'ꞥ', - 'Ꞧ' => 'ꞧ', - 'Ꞩ' => 'ꞩ', - 'Ａ' => 'ａ', - 'Ｂ' => 'ｂ', - 'Ｃ' => 'ｃ', - 'Ｄ' => 'ｄ', - 'Ｅ' => 'ｅ', - 'Ｆ' => 'ｆ', - 'Ｇ' => 'ｇ', - 'Ｈ' => 'ｈ', - 'Ｉ' => 'ｉ', - 'Ｊ' => 'ｊ', - 'Ｋ' => 'ｋ', - 'Ｌ' => 'ｌ', - 'Ｍ' => 'ｍ', - 'Ｎ' => 'ｎ', - 'Ｏ' => 'ｏ', - 'Ｐ' => 'ｐ', - 'Ｑ' => 'ｑ', - 'Ｒ' => 'ｒ', - 'Ｓ' => 'ｓ', - 'Ｔ' => 'ｔ', - 'Ｕ' => 'ｕ', - 'Ｖ' => 'ｖ', - 'Ｗ' => 'ｗ', - 'Ｘ' => 'ｘ', - 'Ｙ' => 'ｙ', - 'Ｚ' => 'ｚ', - '𐐀' => '𐐨', - '𐐁' => '𐐩', - '𐐂' => '𐐪', - '𐐃' => '𐐫', - '𐐄' => '𐐬', - '𐐅' => '𐐭', - '𐐆' => '𐐮', - '𐐇' => '𐐯', - '𐐈' => '𐐰', - '𐐉' => '𐐱', - '𐐊' => '𐐲', - '𐐋' => '𐐳', - '𐐌' => '𐐴', - '𐐍' => '𐐵', - '𐐎' => '𐐶', - '𐐏' => '𐐷', - '𐐐' => '𐐸', - '𐐑' => '𐐹', - '𐐒' => '𐐺', - '𐐓' => '𐐻', - '𐐔' => '𐐼', - '𐐕' => '𐐽', - '𐐖' => '𐐾', - '𐐗' => '𐐿', - '𐐘' => '𐑀', - '𐐙' => '𐑁', - '𐐚' => '𐑂', - '𐐛' => '𐑃', - '𐐜' => '𐑄', - '𐐝' => '𐑅', - '𐐞' => '𐑆', - '𐐟' => '𐑇', - '𐐠' => '𐑈', - '𐐡' => '𐑉', - '𐐢' => '𐑊', - '𐐣' => '𐑋', - '𐐤' => '𐑌', - '𐐥' => '𐑍', - '𐐦' => '𐑎', - '𐐧' => '𐑏' -); diff --git a/includes/normal/Utf8CaseGenerate.php b/includes/normal/Utf8CaseGenerate.php deleted file mode 100644 index adc3ef22d8..0000000000 --- a/includes/normal/Utf8CaseGenerate.php +++ /dev/null @@ -1,112 +0,0 @@ - - * http://www.mediawiki.org/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * http://www.gnu.org/copyleft/gpl.html - * - * @file - * @ingroup UtfNormal - */ - -if( PHP_SAPI != 'cli' ) { - die( "Run me from the command line please.\n" ); -} - -require_once 'UtfNormalDefines.php'; -require_once 'UtfNormalUtil.php'; - -$in = fopen("UnicodeData.txt", "rt" ); -if( !$in ) { - print "Can't open UnicodeData.txt for reading.\n"; - print "If necessary, fetch this file from the internet:\n"; - print "http://www.unicode.org/Public/UNIDATA/UnicodeData.txt\n"; - exit(-1); -} -$wikiUpperChars = array(); -$wikiLowerChars = array(); - -print "Reading character definitions...\n"; -while( false !== ($line = fgets( $in ) ) ) { - $columns = explode(';', $line); - $codepoint = $columns[0]; - $name = $columns[1]; - $simpleUpper = $columns[12]; - $simpleLower = $columns[13]; - - $source = codepointToUtf8( hexdec( $codepoint ) ); - if( $simpleUpper ) { - $wikiUpperChars[$source] = codepointToUtf8( hexdec( $simpleUpper ) ); - } - if( $simpleLower ) { - $wikiLowerChars[$source] = codepointToUtf8( hexdec( $simpleLower ) ); - } -} -fclose( $in ); - -$out = fopen( "Utf8Case.php", "wt" ); -if( $out ) { - $outUpperChars = escapeArray( $wikiUpperChars ); - $outLowerChars = escapeArray( $wikiLowerChars ); - $outdata = "<" . "?php -/** - * Simple 1:1 upper/lowercase switching arrays for utf-8 text. - * Won't get context-sensitive things yet. - * - * Hack for bugs in ucfirst() and company - * - * These are pulled from memcached if possible, as this is faster than filling - * up a big array manually. - * - * @file - * @ingroup Language - */ - -/** - * Translation array to get upper case character - */ -\$wikiUpperChars = $outUpperChars; - -/** - * Translation array to get lower case character - */ -\$wikiLowerChars = $outLowerChars;\n"; - fputs( $out, $outdata ); - fclose( $out ); - print "Wrote out Utf8Case.php\n"; -} else { - print "Can't create file Utf8Case.php\n"; - exit(-1); -} - - -function escapeArray( $arr ) { - return "array(\n" . - implode( ",\n", - array_map( "escapeLine", - array_keys( $arr ), - array_values( $arr ) ) ) . - "\n)"; -} - -function escapeLine( $key, $val ) { - $encKey = escapeSingleString( $key ); - $encVal = escapeSingleString( $val ); - return "\t'$encKey' => '$encVal'"; -} diff --git a/maintenance/language/generateNormalizerData.php b/maintenance/language/generateNormalizerData.php deleted file mode 100644 index b638b63bfa..0000000000 --- a/maintenance/language/generateNormalizerData.php +++ /dev/null @@ -1,160 +0,0 @@ -addOption( 'unicode-data-file', 'The local location of the data file ' . - 'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true ); - } - - public function execute() { - if ( !$this->hasOption( 'unicode-data-file' ) ) { - $this->dataFile = 'UnicodeData.txt'; - if ( !file_exists( $this->dataFile ) ) { - $this->error( "Unable to find UnicodeData.txt. Please specify " . - "its location with --unicode-data-file=" ); - exit( 1 ); - } - } else { - $this->dataFile = $this->getOption( 'unicode-data-file' ); - if ( !file_exists( $this->dataFile ) ) { - $this->error( 'Unable to find the specified data file.' ); - exit( 1 ); - } - } - - $this->generateArabic(); - $this->generateMalayalam(); - } - - function generateArabic() { - $file = fopen( $this->dataFile, 'r' ); - if ( !$file ) { - $this->error( 'Unable to open the data file.' ); - exit( 1 ); - } - - // For the file format, see http://www.unicode.org/reports/tr44/ - $fieldNames = array( - 'Code', - 'Name', - 'General_Category', - 'Canonical_Combining_Class', - 'Bidi_Class', - 'Decomposition_Type_Mapping', - 'Numeric_Type_Value', - 'Bidi_Mirrored', - 'Unicode_1_Name', - 'ISO_Comment', - 'Simple_Uppercase_Mapping', - 'Simple_Lowercase_Mapping', - 'Simple_Titlecase_Mapping' - ); - - $pairs = array(); - - $lineNum = 0; - while ( false !== ( $line = fgets( $file ) ) ) { - ++$lineNum; - - # Strip comments - $line = trim( substr( $line, 0, strcspn( $line, '#' ) ) ); - if ( $line === '' ) { - continue; - } - - # Split fields - $numberedData = explode( ';', $line ); - $data = array(); - foreach ( $fieldNames as $number => $name ) { - $data[$name] = $numberedData[$number]; - } - - $code = base_convert( $data['Code'], 16, 10 ); - if ( ( $code >= 0xFB50 && $code <= 0xFDFF ) # Arabic presentation forms A - || ( $code >= 0xFE70 && $code <= 0xFEFF ) # Arabic presentation forms B - ) { - if ( $data['Decomposition_Type_Mapping'] === '' ) { - // No decomposition - continue; - } - if ( !preg_match( '/^ *(<\w*>) +([0-9A-F ]*)$/', - $data['Decomposition_Type_Mapping'], $m ) - ) { - $this->error( "Can't parse Decomposition_Type/Mapping on line $lineNum" ); - $this->error( $line ); - continue; - } - - $source = hexSequenceToUtf8( $data['Code'] ); - $dest = hexSequenceToUtf8( $m[2] ); - $pairs[$source] = $dest; - } - } - - global $IP; - file_put_contents( "$IP/serialized/normalize-ar.ser", serialize( $pairs ) ); - echo "ar: " . count( $pairs ) . " pairs written.\n"; - } - - function generateMalayalam() { - $hexPairs = array( - # From http://unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters - '0D23 0D4D 200D' => '0D7A', - '0D28 0D4D 200D' => '0D7B', - '0D30 0D4D 200D' => '0D7C', - '0D32 0D4D 200D' => '0D7D', - '0D33 0D4D 200D' => '0D7E', - - # From http://permalink.gmane.org/gmane.science.linguistics.wikipedia.technical/46413 - '0D15 0D4D 200D' => '0D7F', - ); - - $pairs = array(); - foreach ( $hexPairs as $hexSource => $hexDest ) { - $source = hexSequenceToUtf8( $hexSource ); - $dest = hexSequenceToUtf8( $hexDest ); - $pairs[$source] = $dest; - } - - global $IP; - file_put_contents( "$IP/serialized/normalize-ml.ser", serialize( $pairs ) ); - echo "ml: " . count( $pairs ) . " pairs written.\n"; - } -} - -$maintClass = 'GenerateNormalizerData'; -require_once RUN_MAINTENANCE_IF_MAIN; diff --git a/maintenance/language/generateNormalizerDataAr.php b/maintenance/language/generateNormalizerDataAr.php new file mode 100644 index 0000000000..ece0450fd5 --- /dev/null +++ b/maintenance/language/generateNormalizerDataAr.php @@ -0,0 +1,133 @@ +mDescription = 'Generate the normalizer data file for Arabic'; + $this->addOption( 'unicode-data-file', 'The local location of the data file ' . + 'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true ); + } + + public function getDbType() { + return Maintenance::DB_NONE; + } + + public function execute() { + if ( !$this->hasOption( 'unicode-data-file' ) ) { + $dataFile = 'UnicodeData.txt'; + if ( !file_exists( $dataFile ) ) { + $this->error( "Unable to find UnicodeData.txt. Please specify " . + "its location with --unicode-data-file=" ); + exit( 1 ); + } + } else { + $dataFile = $this->getOption( 'unicode-data-file' ); + if ( !file_exists( $dataFile ) ) { + $this->error( 'Unable to find the specified data file.' ); + exit( 1 ); + } + } + + $file = fopen( $dataFile, 'r' ); + if ( !$file ) { + $this->error( 'Unable to open the data file.' ); + exit( 1 ); + } + + // For the file format, see http://www.unicode.org/reports/tr44/ + $fieldNames = array( + 'Code', + 'Name', + 'General_Category', + 'Canonical_Combining_Class', + 'Bidi_Class', + 'Decomposition_Type_Mapping', + 'Numeric_Type_Value_6', + 'Numeric_Type_Value_7', + 'Numeric_Type_Value_8', + 'Bidi_Mirrored', + 'Unicode_1_Name', + 'ISO_Comment', + 'Simple_Uppercase_Mapping', + 'Simple_Lowercase_Mapping', + 'Simple_Titlecase_Mapping' + ); + + $pairs = array(); + + $lineNum = 0; + while ( false !== ( $line = fgets( $file ) ) ) { + ++$lineNum; + + # Strip comments + $line = trim( substr( $line, 0, strcspn( $line, '#' ) ) ); + if ( $line === '' ) { + continue; + } + + # Split fields + $numberedData = explode( ';', $line ); + $data = array(); + foreach ( $fieldNames as $number => $name ) { + $data[$name] = $numberedData[$number]; + } + + $code = base_convert( $data['Code'], 16, 10 ); + if ( ( $code >= 0xFB50 && $code <= 0xFDFF ) # Arabic presentation forms A + || ( $code >= 0xFE70 && $code <= 0xFEFF ) # Arabic presentation forms B + ) { + if ( $data['Decomposition_Type_Mapping'] === '' ) { + // No decomposition + continue; + } + if ( !preg_match( '/^ *(<\w*>) +([0-9A-F ]*)$/', + $data['Decomposition_Type_Mapping'], $m ) + ) { + $this->error( "Can't parse Decomposition_Type/Mapping on line $lineNum" ); + $this->error( $line ); + continue; + } + + $source = hexSequenceToUtf8( $data['Code'] ); + $dest = hexSequenceToUtf8( $m[2] ); + $pairs[$source] = $dest; + } + } + + global $IP; + file_put_contents( "$IP/serialized/normalize-ar.ser", serialize( $pairs ) ); + echo "ar: " . count( $pairs ) . " pairs written.\n"; + } +} + +$maintClass = 'GenerateNormalizerDataAr'; +require_once RUN_MAINTENANCE_IF_MAIN; diff --git a/maintenance/language/generateNormalizerDataMl.php b/maintenance/language/generateNormalizerDataMl.php new file mode 100644 index 0000000000..c7237cfed7 --- /dev/null +++ b/maintenance/language/generateNormalizerDataMl.php @@ -0,0 +1,69 @@ +mDescription = 'Generate the normalizer data file for Malayalam'; + } + + public function getDbType() { + return Maintenance::DB_NONE; + } + + public function execute() { + $hexPairs = array( + # From http://unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters + '0D23 0D4D 200D' => '0D7A', + '0D28 0D4D 200D' => '0D7B', + '0D30 0D4D 200D' => '0D7C', + '0D32 0D4D 200D' => '0D7D', + '0D33 0D4D 200D' => '0D7E', + + # From http://permalink.gmane.org/gmane.science.linguistics.wikipedia.technical/46413 + '0D15 0D4D 200D' => '0D7F', + ); + + $pairs = array(); + foreach ( $hexPairs as $hexSource => $hexDest ) { + $source = hexSequenceToUtf8( $hexSource ); + $dest = hexSequenceToUtf8( $hexDest ); + $pairs[$source] = $dest; + } + + global $IP; + file_put_contents( "$IP/serialized/normalize-ml.ser", serialize( $pairs ) ); + echo "ml: " . count( $pairs ) . " pairs written.\n"; + } +} + +$maintClass = 'GenerateNormalizerDataMl'; +require_once RUN_MAINTENANCE_IF_MAIN; diff --git a/maintenance/language/generateUtf8Case.php b/maintenance/language/generateUtf8Case.php new file mode 100644 index 0000000000..dbb70c16f6 --- /dev/null +++ b/maintenance/language/generateUtf8Case.php @@ -0,0 +1,129 @@ + + * http://www.mediawiki.org/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * http://www.gnu.org/copyleft/gpl.html + * + * @file + * @ingroup MaintenanceLanguage + */ + +require_once __DIR__ . '/../Maintenance.php'; + +/** + * Generates Utf8Case.ser from the Unicode Character Database and + * supplementary files. + * + * @ingroup MaintenanceLanguage + */ +class GenerateUtf8Case extends Maintenance { + + public function __construct() { + parent::__construct(); + $this->mDescription = 'Generate Utf8Case.ser from the Unicode Character Database ' . + 'and supplementary files'; + $this->addOption( 'unicode-data-file', 'The local location of the data file ' . + 'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true ); + } + + public function getDbType() { + return Maintenance::DB_NONE; + } + + public function execute() { + if ( !$this->hasOption( 'unicode-data-file' ) ) { + $dataFile = 'UnicodeData.txt'; + if ( !file_exists( $dataFile ) ) { + $this->error( "Unable to find UnicodeData.txt. Please specify " . + "its location with --unicode-data-file=" ); + exit( 1 ); + } + } else { + $dataFile = $this->getOption( 'unicode-data-file' ); + if ( !file_exists( $dataFile ) ) { + $this->error( 'Unable to find the specified data file.' ); + exit( 1 ); + } + } + + $file = fopen( $dataFile, 'r' ); + if ( !$file ) { + $this->error( 'Unable to open the data file.' ); + exit( 1 ); + } + + // For the file format, see http://www.unicode.org/reports/tr44/ + $fieldNames = array( + 'Code', + 'Name', + 'General_Category', + 'Canonical_Combining_Class', + 'Bidi_Class', + 'Decomposition_Type_Mapping', + 'Numeric_Type_Value_6', + 'Numeric_Type_Value_7', + 'Numeric_Type_Value_8', + 'Bidi_Mirrored', + 'Unicode_1_Name', + 'ISO_Comment', + 'Simple_Uppercase_Mapping', + 'Simple_Lowercase_Mapping', + 'Simple_Titlecase_Mapping' + ); + + $upper = array(); + $lower = array(); + + $lineNum = 0; + while ( false !== ( $line = fgets( $file ) ) ) { + ++$lineNum; + + # Strip comments + $line = trim( substr( $line, 0, strcspn( $line, '#' ) ) ); + if ( $line === '' ) { + continue; + } + + # Split fields + $numberedData = explode( ';', $line ); + $data = array(); + foreach ( $fieldNames as $number => $name ) { + $data[$name] = $numberedData[$number]; + } + + $source = hexSequenceToUtf8( $data['Code'] ); + if ( $data['Simple_Uppercase_Mapping'] ) { + $upper[$source] = hexSequenceToUtf8( $data['Simple_Uppercase_Mapping'] ); + } + if ( $data['Simple_Lowercase_Mapping'] ) { + $lower[$source] = hexSequenceToUtf8( $data['Simple_Lowercase_Mapping'] ); + } + } + + global $IP; + file_put_contents( "$IP/serialized/Utf8Case.ser", serialize( array( + 'wikiUpperChars' => $upper, + 'wikiLowerChars' => $lower, + ) ) ); + } +} + +$maintClass = 'GenerateUtf8Case'; +require_once RUN_MAINTENANCE_IF_MAIN; diff --git a/serialized/.gitignore b/serialized/.gitignore new file mode 100644 index 0000000000..d9d58dd989 --- /dev/null +++ b/serialized/.gitignore @@ -0,0 +1,4 @@ +/UnicodeData.txt +/allkeys.txt +/ucd.all.grouped.xml +/ucd.all.grouped.zip diff --git a/serialized/Makefile b/serialized/Makefile index 062155b684..c7e75063c6 100644 --- a/serialized/Makefile +++ b/serialized/Makefile @@ -1,7 +1,7 @@ - -SPECIAL_TARGETS=Utf8Case.ser +SPECIAL_TARGETS=Utf8Case.ser normalize-ar.ser normalize-ml.ser first-letters-root.ser ALL_TARGETS=$(SPECIAL_TARGETS) DIST_TARGETS=$(SPECIAL_TARGETS) +UNICODE_VERSION=6.0.0 .PHONY: all dist clean @@ -13,6 +13,26 @@ dist: $(DIST_TARGETS) clean: rm -f $(ALL_TARGETS) -Utf8Case.ser : ../includes/normal/Utf8Case.php - php serialize.php -o $@ $< +Utf8Case.ser: UnicodeData.txt + php ../maintenance/language/generateUtf8Case.php + +normalize-ar.ser: UnicodeData.txt + php ../maintenance/language/generateNormalizerDataAr.php + +normalize-ml.ser: + php ../maintenance/language/generateNormalizerDataMl.php + +first-letters-root.ser: allkeys.txt ucd.all.grouped.xml + php ../maintenance/language/generateCollationData.php + +UnicodeData.txt: + wget http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/UnicodeData.txt + +allkeys.txt: + wget http://www.unicode.org/Public/UCA/$(UNICODE_VERSION)/allkeys.txt + +ucd.all.grouped.xml: ucd.all.grouped.zip + unzip ucd.all.grouped.zip ucd.all.grouped.xml +ucd.all.grouped.zip: + wget http://www.unicode.org/Public/$(UNICODE_VERSION)/ucdxml/ucd.all.grouped.zip diff --git a/serialized/serialize.php b/serialized/serialize.php deleted file mode 100644 index 766c1a5116..0000000000 --- a/serialized/serialize.php +++ /dev/null @@ -1,95 +0,0 @@ - 50 ) { - global $stderr; - fwrite( $stderr, "Error: Recursion limit exceeded. Possible circular reference in array variable.\n" ); - exit( 2 ); - } - - if ( is_array( $var ) ) { - ++$recursionLevel; - $var = array_map( 'unixLineEndings', $var ); - --$recursionLevel; - } elseif ( is_string( $var ) ) { - $var = str_replace( "\r\n", "\n", $var ); - } - return $var; -}