diff options
Diffstat (limited to 'i18nutil/source/utility/unicode.cxx')
| -rw-r--r-- | i18nutil/source/utility/unicode.cxx | 772 |
1 files changed, 500 insertions, 272 deletions
diff --git a/i18nutil/source/utility/unicode.cxx b/i18nutil/source/utility/unicode.cxx index be34ea58f44a..e98afeeff3b8 100644 --- a/i18nutil/source/utility/unicode.cxx +++ b/i18nutil/source/utility/unicode.cxx @@ -24,8 +24,10 @@ #include <i18nutil/unicode.hxx> #include <sal/log.hxx> #include <unicode/numfmt.h> +#include <unicode/uchar.h> #include "unicode_data.h" #include <rtl/character.hxx> +#include <o3tl/string_view.hxx> #include <memory> // Workaround for glibc braindamage: @@ -65,18 +67,108 @@ unicode::getUnicodeScriptEnd( UnicodeScript type) { } sal_Int16 -unicode::getUnicodeType( const sal_Unicode ch ) { - static sal_Unicode c = 0x00; - static sal_Int16 r = 0x00; +unicode::getUnicodeType(const sal_uInt32 ch) +{ + static sal_uInt32 c = 0x00; + static sal_uInt32 r = 0x00; if (ch == c) return r; else c = ch; - sal_Int16 address = UnicodeTypeIndex[ch >> 8]; - r = static_cast<sal_Int16>( - (address < UnicodeTypeNumberBlock) - ? UnicodeTypeBlockValue[address] - : UnicodeTypeValue[((address - UnicodeTypeNumberBlock) << 8) + (ch & 0xff)]); + switch (u_charType(ch)) + { + case U_UNASSIGNED: + r = css::i18n::UnicodeType::UNASSIGNED; + break; + case U_UPPERCASE_LETTER: + r = css::i18n::UnicodeType::UPPERCASE_LETTER; + break; + case U_LOWERCASE_LETTER: + r = css::i18n::UnicodeType::LOWERCASE_LETTER; + break; + case U_TITLECASE_LETTER: + r = css::i18n::UnicodeType::TITLECASE_LETTER; + break; + case U_MODIFIER_LETTER: + r = css::i18n::UnicodeType::MODIFIER_LETTER; + break; + case U_OTHER_LETTER: + r = css::i18n::UnicodeType::OTHER_LETTER; + break; + case U_NON_SPACING_MARK: + r = css::i18n::UnicodeType::NON_SPACING_MARK; + break; + case U_ENCLOSING_MARK: + r = css::i18n::UnicodeType::ENCLOSING_MARK; + break; + case U_COMBINING_SPACING_MARK: + r = css::i18n::UnicodeType::COMBINING_SPACING_MARK; + break; + case U_DECIMAL_DIGIT_NUMBER: + r = css::i18n::UnicodeType::DECIMAL_DIGIT_NUMBER; + break; + case U_LETTER_NUMBER: + r = css::i18n::UnicodeType::LETTER_NUMBER; + break; + case U_OTHER_NUMBER: + r = css::i18n::UnicodeType::OTHER_NUMBER; + break; + case U_SPACE_SEPARATOR: + r = css::i18n::UnicodeType::SPACE_SEPARATOR; + break; + case U_LINE_SEPARATOR: + r = css::i18n::UnicodeType::LINE_SEPARATOR; + break; + case U_PARAGRAPH_SEPARATOR: + r = css::i18n::UnicodeType::PARAGRAPH_SEPARATOR; + break; + case U_CONTROL_CHAR: + r = css::i18n::UnicodeType::CONTROL; + break; + case U_FORMAT_CHAR: + r = css::i18n::UnicodeType::FORMAT; + break; + case U_PRIVATE_USE_CHAR: + r = css::i18n::UnicodeType::PRIVATE_USE; + break; + case U_SURROGATE: + r = css::i18n::UnicodeType::SURROGATE; + break; + case U_DASH_PUNCTUATION: + r = css::i18n::UnicodeType::DASH_PUNCTUATION; + break; + case U_INITIAL_PUNCTUATION: + r = css::i18n::UnicodeType::INITIAL_PUNCTUATION; + break; + case U_FINAL_PUNCTUATION: + r = css::i18n::UnicodeType::FINAL_PUNCTUATION; + break; + case U_CONNECTOR_PUNCTUATION: + r = css::i18n::UnicodeType::CONNECTOR_PUNCTUATION; + break; + case U_OTHER_PUNCTUATION: + r = css::i18n::UnicodeType::OTHER_PUNCTUATION; + break; + case U_MATH_SYMBOL: + r = css::i18n::UnicodeType::MATH_SYMBOL; + break; + case U_CURRENCY_SYMBOL: + r = css::i18n::UnicodeType::CURRENCY_SYMBOL; + break; + case U_MODIFIER_SYMBOL: + r = css::i18n::UnicodeType::MODIFIER_SYMBOL; + break; + case U_OTHER_SYMBOL: + r = css::i18n::UnicodeType::OTHER_SYMBOL; + break; + case U_START_PUNCTUATION: + r = css::i18n::UnicodeType::START_PUNCTUATION; + break; + case U_END_PUNCTUATION: + r = css::i18n::UnicodeType::END_PUNCTUATION; + break; + } + return r; } @@ -95,6 +187,11 @@ unicode::getUnicodeDirection( const sal_Unicode ch ) { return r; } +sal_uInt32 unicode::GetMirroredChar(sal_uInt32 nChar) { + nChar = u_charMirror(nChar); + return nChar; +} + #define bit(name) (1U << name) #define UPPERMASK bit(UnicodeType::UPPERCASE_LETTER) @@ -117,7 +214,7 @@ unicode::getUnicodeDirection( const sal_Unicode ch ) { bit(UnicodeType::PARAGRAPH_SEPARATOR) #define IsType(func, mask) \ -bool func( const sal_Unicode ch) {\ +bool func( const sal_uInt32 ch) {\ return (bit(getUnicodeType(ch)) & (mask)) != 0;\ } @@ -128,65 +225,207 @@ IsType(unicode::isSpace, SPACEMASK) #define CONTROLSPACE bit(0x09)|bit(0x0a)|bit(0x0b)|bit(0x0c)|bit(0x0d)|\ bit(0x1c)|bit(0x1d)|bit(0x1e)|bit(0x1f) -bool unicode::isWhiteSpace( const sal_Unicode ch) { +bool unicode::isWhiteSpace(const sal_uInt32 ch) +{ return (ch != 0xa0 && isSpace(ch)) || (ch <= 0x1F && (bit(ch) & (CONTROLSPACE))); } sal_Int16 unicode::getScriptClassFromUScriptCode(UScriptCode eScript) { //See unicode/uscript.h - static const sal_Int16 scriptTypes[] = + sal_Int16 nRet; + switch (eScript) { - ScriptType::WEAK, ScriptType::WEAK, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX, - ScriptType::ASIAN, ScriptType::LATIN, ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::LATIN, ScriptType::LATIN, - // 15 - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::ASIAN, ScriptType::ASIAN, ScriptType::COMPLEX, - ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN, - // 30 - ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::LATIN, ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - // 45 - ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN, - ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - // 60 - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::ASIAN, ScriptType::ASIAN, - // 75 - ScriptType::COMPLEX, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::LATIN, ScriptType::LATIN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - // 90 - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::WEAK, ScriptType::WEAK, ScriptType::COMPLEX, - // 105 - ScriptType::ASIAN, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::ASIAN, - // 120 - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::WEAK, ScriptType::WEAK, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - // 135 - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, ScriptType::COMPLEX, - ScriptType::COMPLEX, - ScriptType::WEAK - }; + case USCRIPT_INVALID_CODE: + case USCRIPT_COMMON: + case USCRIPT_INHERITED: + case USCRIPT_UNWRITTEN_LANGUAGES: + case USCRIPT_UNKNOWN: + case USCRIPT_MATHEMATICAL_NOTATION: + case USCRIPT_SYMBOLS: + case USCRIPT_CODE_LIMIT: + nRet = ScriptType::WEAK; + break; + case USCRIPT_ARMENIAN: + case USCRIPT_CHEROKEE: + case USCRIPT_COPTIC: + case USCRIPT_CYRILLIC: + case USCRIPT_GEORGIAN: + case USCRIPT_GOTHIC: + case USCRIPT_GREEK: + case USCRIPT_LATIN: + case USCRIPT_OGHAM: + case USCRIPT_OLD_ITALIC: + case USCRIPT_RUNIC: + case USCRIPT_CANADIAN_ABORIGINAL: + case USCRIPT_BRAILLE: + case USCRIPT_CYPRIOT: + case USCRIPT_OSMANYA: + case USCRIPT_SHAVIAN: + case USCRIPT_KATAKANA_OR_HIRAGANA: + case USCRIPT_GLAGOLITIC: + case USCRIPT_CIRTH: + case USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC: + case USCRIPT_OLD_HUNGARIAN: + case USCRIPT_LATIN_FRAKTUR: + case USCRIPT_LATIN_GAELIC: + nRet = ScriptType::LATIN; + break; + case USCRIPT_BOPOMOFO: + case USCRIPT_HAN: + case USCRIPT_HANGUL: + case USCRIPT_HIRAGANA: + case USCRIPT_KATAKANA: + case USCRIPT_YI: + case USCRIPT_SIMPLIFIED_HAN: + case USCRIPT_TRADITIONAL_HAN: + case USCRIPT_JAPANESE: + case USCRIPT_KOREAN: + case USCRIPT_TANGUT: + case USCRIPT_KHITAN_SMALL_SCRIPT: + nRet = ScriptType::ASIAN; + break; + case USCRIPT_ARABIC: + case USCRIPT_BENGALI: + case USCRIPT_DESERET: + case USCRIPT_DEVANAGARI: + case USCRIPT_ETHIOPIC: + case USCRIPT_GUJARATI: + case USCRIPT_GURMUKHI: + case USCRIPT_HEBREW: + case USCRIPT_KANNADA: + case USCRIPT_KHMER: + case USCRIPT_LAO: + case USCRIPT_MALAYALAM: + case USCRIPT_MONGOLIAN: + case USCRIPT_MYANMAR: + case USCRIPT_ORIYA: + case USCRIPT_SINHALA: + case USCRIPT_SYRIAC: + case USCRIPT_TAMIL: + case USCRIPT_TELUGU: + case USCRIPT_THAANA: + case USCRIPT_THAI: + case USCRIPT_TIBETAN: + case USCRIPT_TAGALOG: + case USCRIPT_HANUNOO: + case USCRIPT_BUHID: + case USCRIPT_TAGBANWA: + case USCRIPT_LIMBU: + case USCRIPT_LINEAR_B: + case USCRIPT_TAI_LE: + case USCRIPT_UGARITIC: + case USCRIPT_BUGINESE: + case USCRIPT_KHAROSHTHI: + case USCRIPT_SYLOTI_NAGRI: + case USCRIPT_NEW_TAI_LUE: + case USCRIPT_TIFINAGH: + case USCRIPT_OLD_PERSIAN: + case USCRIPT_BALINESE: + case USCRIPT_BATAK: + case USCRIPT_BLISSYMBOLS: + case USCRIPT_BRAHMI: + case USCRIPT_CHAM: + case USCRIPT_DEMOTIC_EGYPTIAN: + case USCRIPT_HIERATIC_EGYPTIAN: + case USCRIPT_EGYPTIAN_HIEROGLYPHS: + case USCRIPT_KHUTSURI: + case USCRIPT_PAHAWH_HMONG: + case USCRIPT_HARAPPAN_INDUS: + case USCRIPT_JAVANESE: + case USCRIPT_KAYAH_LI: + case USCRIPT_LEPCHA: + case USCRIPT_LINEAR_A: + case USCRIPT_MANDAEAN: + case USCRIPT_MAYAN_HIEROGLYPHS: + case USCRIPT_MEROITIC: + case USCRIPT_NKO: + case USCRIPT_ORKHON: + case USCRIPT_OLD_PERMIC: + case USCRIPT_PHAGS_PA: + case USCRIPT_PHOENICIAN: + case USCRIPT_PHONETIC_POLLARD: + case USCRIPT_RONGORONGO: + case USCRIPT_SARATI: + case USCRIPT_ESTRANGELO_SYRIAC: + case USCRIPT_WESTERN_SYRIAC: + case USCRIPT_EASTERN_SYRIAC: + case USCRIPT_TENGWAR: + case USCRIPT_VAI: + case USCRIPT_VISIBLE_SPEECH: + case USCRIPT_CUNEIFORM: + case USCRIPT_CARIAN: + case USCRIPT_LANNA: + case USCRIPT_LYCIAN: + case USCRIPT_LYDIAN: + case USCRIPT_OL_CHIKI: + case USCRIPT_REJANG: + case USCRIPT_SAURASHTRA: + case USCRIPT_SIGN_WRITING: + case USCRIPT_SUNDANESE: + case USCRIPT_MOON: + case USCRIPT_MEITEI_MAYEK: + case USCRIPT_IMPERIAL_ARAMAIC: + case USCRIPT_AVESTAN: + case USCRIPT_CHAKMA: + case USCRIPT_KAITHI: + case USCRIPT_MANICHAEAN: + case USCRIPT_INSCRIPTIONAL_PAHLAVI: + case USCRIPT_PSALTER_PAHLAVI: + case USCRIPT_BOOK_PAHLAVI: + case USCRIPT_INSCRIPTIONAL_PARTHIAN: + case USCRIPT_SAMARITAN: + case USCRIPT_TAI_VIET: + case USCRIPT_BAMUM: + case USCRIPT_LISU: + case USCRIPT_NAKHI_GEBA: + case USCRIPT_OLD_SOUTH_ARABIAN: + case USCRIPT_BASSA_VAH: + case USCRIPT_DUPLOYAN_SHORTAND: + case USCRIPT_ELBASAN: + case USCRIPT_GRANTHA: + case USCRIPT_KPELLE: + case USCRIPT_LOMA: + case USCRIPT_MENDE: + case USCRIPT_MEROITIC_CURSIVE: + case USCRIPT_OLD_NORTH_ARABIAN: + case USCRIPT_NABATAEAN: + case USCRIPT_PALMYRENE: + case USCRIPT_SINDHI: + case USCRIPT_WARANG_CITI: + default: // anything new is going to be pretty wild + nRet = ScriptType::COMPLEX; + break; + } + return nRet; +} - sal_Int16 nRet; - if (eScript < USCRIPT_COMMON) - nRet = ScriptType::WEAK; - else if (static_cast<size_t>(eScript) >= SAL_N_ELEMENTS(scriptTypes)) - nRet = ScriptType::COMPLEX; // anything new is going to be pretty wild +sal_Int16 unicode::getScriptClassFromLanguageTag( const LanguageTag& rLanguageTag ) +{ + constexpr int32_t nBuf = 42; + UScriptCode aBuf[nBuf]; + if (rLanguageTag.hasScript()) + { + aBuf[0] = static_cast<UScriptCode>(u_getPropertyValueEnum( UCHAR_SCRIPT, + OUStringToOString( rLanguageTag.getScript(), RTL_TEXTENCODING_ASCII_US).getStr())); + } else - nRet = scriptTypes[eScript]; - return nRet; + { + OUString aName; + if (rLanguageTag.getCountry().isEmpty()) + aName = rLanguageTag.getLanguage(); + else + aName = rLanguageTag.getLanguage() + "-" + rLanguageTag.getCountry(); + UErrorCode status = U_ZERO_ERROR; + const int32_t nScripts = uscript_getCode( + OUStringToOString( aName, RTL_TEXTENCODING_ASCII_US).getStr(), + aBuf, nBuf, &status); + // U_BUFFER_OVERFLOW_ERROR would be set with too many scripts for buffer + // and required capacity returned, but really.. + if (nScripts == 0 || !U_SUCCESS(status)) + return css::i18n::ScriptType::LATIN; + } + return getScriptClassFromUScriptCode( aBuf[0]); } OString unicode::getExemplarLanguageForUScriptCode(UScriptCode eScript) @@ -196,604 +435,594 @@ OString unicode::getExemplarLanguageForUScriptCode(UScriptCode eScript) { case USCRIPT_CODE_LIMIT: case USCRIPT_INVALID_CODE: - sRet = "zxx"; + sRet = "zxx"_ostr; break; case USCRIPT_COMMON: case USCRIPT_INHERITED: - sRet = "und"; + sRet = "und"_ostr; break; case USCRIPT_MATHEMATICAL_NOTATION: case USCRIPT_SYMBOLS: - sRet = "zxx"; + sRet = "zxx"_ostr; break; case USCRIPT_UNWRITTEN_LANGUAGES: case USCRIPT_UNKNOWN: - sRet = "und"; + sRet = "und"_ostr; break; case USCRIPT_ARABIC: - sRet = "ar"; + sRet = "ar"_ostr; break; case USCRIPT_ARMENIAN: - sRet = "hy"; + sRet = "hy"_ostr; break; case USCRIPT_BENGALI: - sRet = "bn"; + sRet = "bn"_ostr; break; case USCRIPT_BOPOMOFO: - sRet = "zh"; + sRet = "zh"_ostr; break; case USCRIPT_CHEROKEE: - sRet = "chr"; + sRet = "chr"_ostr; break; case USCRIPT_COPTIC: - sRet = "cop"; + sRet = "cop"_ostr; break; case USCRIPT_CYRILLIC: - sRet = "ru"; + sRet = "ru"_ostr; break; case USCRIPT_DESERET: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_DEVANAGARI: - sRet = "hi"; + sRet = "hi"_ostr; break; case USCRIPT_ETHIOPIC: - sRet = "am"; + sRet = "am"_ostr; break; case USCRIPT_GEORGIAN: - sRet = "ka"; + sRet = "ka"_ostr; break; case USCRIPT_GOTHIC: - sRet = "got"; + sRet = "got"_ostr; break; case USCRIPT_GREEK: - sRet = "el"; + sRet = "el"_ostr; break; case USCRIPT_GUJARATI: - sRet = "gu"; + sRet = "gu"_ostr; break; case USCRIPT_GURMUKHI: - sRet = "pa"; + sRet = "pa"_ostr; break; case USCRIPT_HAN: - sRet = "zh"; + sRet = "zh"_ostr; break; case USCRIPT_HANGUL: - sRet = "ko"; + sRet = "ko"_ostr; break; case USCRIPT_HEBREW: - sRet = "hr"; + sRet = "hr"_ostr; break; case USCRIPT_HIRAGANA: - sRet = "ja"; + sRet = "ja"_ostr; break; case USCRIPT_KANNADA: - sRet = "kn"; + sRet = "kn"_ostr; break; case USCRIPT_KATAKANA: - sRet = "ja"; + sRet = "ja"_ostr; break; case USCRIPT_KHMER: - sRet = "km"; + sRet = "km"_ostr; break; case USCRIPT_LAO: - sRet = "lo"; + sRet = "lo"_ostr; break; case USCRIPT_LATIN: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_MALAYALAM: - sRet = "ml"; + sRet = "ml"_ostr; break; case USCRIPT_MONGOLIAN: - sRet = "mn"; + sRet = "mn"_ostr; break; case USCRIPT_MYANMAR: - sRet = "my"; + sRet = "my"_ostr; break; case USCRIPT_OGHAM: - sRet = "pgl"; + sRet = "pgl"_ostr; break; case USCRIPT_OLD_ITALIC: - sRet = "osc"; + sRet = "osc"_ostr; break; case USCRIPT_ORIYA: - sRet = "or"; + sRet = "or"_ostr; break; case USCRIPT_RUNIC: - sRet = "ang"; + sRet = "ang"_ostr; break; case USCRIPT_SINHALA: - sRet = "si"; + sRet = "si"_ostr; break; case USCRIPT_SYRIAC: - sRet = "syr"; + sRet = "syr"_ostr; break; case USCRIPT_TAMIL: - sRet = "ta"; + sRet = "ta"_ostr; break; case USCRIPT_TELUGU: - sRet = "te"; + sRet = "te"_ostr; break; case USCRIPT_THAANA: - sRet = "dv"; + sRet = "dv"_ostr; break; case USCRIPT_THAI: - sRet = "th"; + sRet = "th"_ostr; break; case USCRIPT_TIBETAN: - sRet = "bo"; + sRet = "bo"_ostr; break; case USCRIPT_CANADIAN_ABORIGINAL: - sRet = "iu"; + sRet = "iu"_ostr; break; case USCRIPT_YI: - sRet = "ii"; + sRet = "ii"_ostr; break; case USCRIPT_TAGALOG: - sRet = "tl"; + sRet = "tl"_ostr; break; case USCRIPT_HANUNOO: - sRet = "hnn"; + sRet = "hnn"_ostr; break; case USCRIPT_BUHID: - sRet = "bku"; + sRet = "bku"_ostr; break; case USCRIPT_TAGBANWA: - sRet = "tbw"; + sRet = "tbw"_ostr; break; case USCRIPT_BRAILLE: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_CYPRIOT: - sRet = "ecy"; + sRet = "ecy"_ostr; break; case USCRIPT_LIMBU: - sRet = "lif"; + sRet = "lif"_ostr; break; case USCRIPT_LINEAR_B: - sRet = "gmy"; + sRet = "gmy"_ostr; break; case USCRIPT_OSMANYA: - sRet = "so"; + sRet = "so"_ostr; break; case USCRIPT_SHAVIAN: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_TAI_LE: - sRet = "tdd"; + sRet = "tdd"_ostr; break; case USCRIPT_UGARITIC: - sRet = "uga"; + sRet = "uga"_ostr; break; case USCRIPT_KATAKANA_OR_HIRAGANA: - sRet = "ja"; + sRet = "ja"_ostr; break; case USCRIPT_BUGINESE: - sRet = "bug"; + sRet = "bug"_ostr; break; case USCRIPT_GLAGOLITIC: - sRet = "ch"; + sRet = "ch"_ostr; break; case USCRIPT_KHAROSHTHI: - sRet = "pra"; + sRet = "pra"_ostr; break; case USCRIPT_SYLOTI_NAGRI: - sRet = "syl"; + sRet = "syl"_ostr; break; case USCRIPT_NEW_TAI_LUE: - sRet = "khb"; + sRet = "khb"_ostr; break; case USCRIPT_TIFINAGH: - sRet = "tmh"; + sRet = "tmh"_ostr; break; case USCRIPT_OLD_PERSIAN: - sRet = "peo"; + sRet = "peo"_ostr; break; case USCRIPT_BALINESE: - sRet = "ban"; + sRet = "ban"_ostr; break; case USCRIPT_BATAK: - sRet = "btk"; + sRet = "btk"_ostr; break; case USCRIPT_BLISSYMBOLS: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_BRAHMI: - sRet = "pra"; + sRet = "pra"_ostr; break; case USCRIPT_CHAM: - sRet = "cja"; + sRet = "cja"_ostr; break; case USCRIPT_CIRTH: - sRet = "sjn"; + sRet = "sjn"_ostr; break; case USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC: - sRet = "cu"; + sRet = "cu"_ostr; break; case USCRIPT_DEMOTIC_EGYPTIAN: case USCRIPT_HIERATIC_EGYPTIAN: case USCRIPT_EGYPTIAN_HIEROGLYPHS: - sRet = "egy"; + sRet = "egy"_ostr; break; case USCRIPT_KHUTSURI: - sRet = "ka"; + sRet = "ka"_ostr; break; case USCRIPT_SIMPLIFIED_HAN: - sRet = "zh"; + sRet = "zh"_ostr; break; case USCRIPT_TRADITIONAL_HAN: - sRet = "zh"; + sRet = "zh"_ostr; break; case USCRIPT_PAHAWH_HMONG: - sRet = "blu"; + sRet = "blu"_ostr; break; case USCRIPT_OLD_HUNGARIAN: - sRet = "ohu"; + sRet = "ohu"_ostr; break; case USCRIPT_HARAPPAN_INDUS: - sRet = "xiv"; + sRet = "xiv"_ostr; break; case USCRIPT_JAVANESE: - sRet = "kaw"; + sRet = "kaw"_ostr; break; case USCRIPT_KAYAH_LI: - sRet = "eky"; + sRet = "eky"_ostr; break; case USCRIPT_LATIN_FRAKTUR: - sRet = "de"; + sRet = "de"_ostr; break; case USCRIPT_LATIN_GAELIC: - sRet = "ga"; + sRet = "ga"_ostr; break; case USCRIPT_LEPCHA: - sRet = "lep"; + sRet = "lep"_ostr; break; case USCRIPT_LINEAR_A: - sRet = "ecr"; + sRet = "ecr"_ostr; break; case USCRIPT_MAYAN_HIEROGLYPHS: - sRet = "myn"; + sRet = "myn"_ostr; break; case USCRIPT_MEROITIC: - sRet = "xmr"; + sRet = "xmr"_ostr; break; case USCRIPT_NKO: - sRet = "nqo"; + sRet = "nqo"_ostr; break; case USCRIPT_ORKHON: - sRet = "otk"; + sRet = "otk"_ostr; break; case USCRIPT_OLD_PERMIC: - sRet = "kv"; + sRet = "kv"_ostr; break; case USCRIPT_PHAGS_PA: - sRet = "xng"; + sRet = "xng"_ostr; break; case USCRIPT_PHOENICIAN: - sRet = "phn"; + sRet = "phn"_ostr; break; case USCRIPT_PHONETIC_POLLARD: - sRet = "hmd"; + sRet = "hmd"_ostr; break; case USCRIPT_RONGORONGO: - sRet = "rap"; + sRet = "rap"_ostr; break; case USCRIPT_SARATI: - sRet = "qya"; + sRet = "qya"_ostr; break; case USCRIPT_ESTRANGELO_SYRIAC: - sRet = "syr"; + sRet = "syr"_ostr; break; case USCRIPT_WESTERN_SYRIAC: - sRet = "tru"; + sRet = "tru"_ostr; break; case USCRIPT_EASTERN_SYRIAC: - sRet = "aii"; + sRet = "aii"_ostr; break; case USCRIPT_TENGWAR: - sRet = "sjn"; + sRet = "sjn"_ostr; break; case USCRIPT_VAI: - sRet = "vai"; + sRet = "vai"_ostr; break; case USCRIPT_VISIBLE_SPEECH: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_CUNEIFORM: - sRet = "akk"; + sRet = "akk"_ostr; break; case USCRIPT_CARIAN: - sRet = "xcr"; + sRet = "xcr"_ostr; break; case USCRIPT_JAPANESE: - sRet = "ja"; + sRet = "ja"_ostr; break; case USCRIPT_LANNA: - sRet = "nod"; + sRet = "nod"_ostr; break; case USCRIPT_LYCIAN: - sRet = "xlc"; + sRet = "xlc"_ostr; break; case USCRIPT_LYDIAN: - sRet = "xld"; + sRet = "xld"_ostr; break; case USCRIPT_OL_CHIKI: - sRet = "sat"; + sRet = "sat"_ostr; break; case USCRIPT_REJANG: - sRet = "rej"; + sRet = "rej"_ostr; break; case USCRIPT_SAURASHTRA: - sRet = "saz"; + sRet = "saz"_ostr; break; case USCRIPT_SIGN_WRITING: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_SUNDANESE: - sRet = "su"; + sRet = "su"_ostr; break; case USCRIPT_MOON: - sRet = "en"; + sRet = "en"_ostr; break; case USCRIPT_MEITEI_MAYEK: - sRet = "mni"; + sRet = "mni"_ostr; break; case USCRIPT_IMPERIAL_ARAMAIC: - sRet = "arc"; + sRet = "arc"_ostr; break; case USCRIPT_AVESTAN: - sRet = "ae"; + sRet = "ae"_ostr; break; case USCRIPT_CHAKMA: - sRet = "ccp"; + sRet = "ccp"_ostr; break; case USCRIPT_KOREAN: - sRet = "ko"; + sRet = "ko"_ostr; break; case USCRIPT_KAITHI: - sRet = "awa"; + sRet = "awa"_ostr; break; case USCRIPT_MANICHAEAN: - sRet = "xmn"; + sRet = "xmn"_ostr; break; case USCRIPT_INSCRIPTIONAL_PAHLAVI: case USCRIPT_PSALTER_PAHLAVI: case USCRIPT_BOOK_PAHLAVI: case USCRIPT_INSCRIPTIONAL_PARTHIAN: - sRet = "xpr"; + sRet = "xpr"_ostr; break; case USCRIPT_SAMARITAN: - sRet = "heb"; + sRet = "heb"_ostr; break; case USCRIPT_TAI_VIET: - sRet = "blt"; + sRet = "blt"_ostr; break; case USCRIPT_MANDAEAN: /* Aliased to USCRIPT_MANDAIC in icu 4.6. */ - sRet = "mic"; + sRet = "mic"_ostr; break; case USCRIPT_NABATAEAN: - sRet = "mis-Nbat"; // Uncoded with script + sRet = "mis-Nbat"_ostr; // Uncoded with script break; case USCRIPT_PALMYRENE: - sRet = "mis-Palm"; // Uncoded with script + sRet = "mis-Palm"_ostr; // Uncoded with script break; case USCRIPT_BAMUM: - sRet = "bax"; + sRet = "bax"_ostr; break; case USCRIPT_LISU: - sRet = "lis"; + sRet = "lis"_ostr; break; case USCRIPT_NAKHI_GEBA: - sRet = "nxq"; + sRet = "nxq"_ostr; break; case USCRIPT_OLD_SOUTH_ARABIAN: - sRet = "xsa"; + sRet = "xsa"_ostr; break; case USCRIPT_BASSA_VAH: - sRet = "bsq"; + sRet = "bsq"_ostr; break; case USCRIPT_DUPLOYAN_SHORTAND: - sRet = "fr"; + sRet = "fr"_ostr; break; case USCRIPT_ELBASAN: - sRet = "sq"; + sRet = "sq"_ostr; break; case USCRIPT_GRANTHA: - sRet = "ta"; + sRet = "ta"_ostr; break; case USCRIPT_KPELLE: - sRet = "kpe"; + sRet = "kpe"_ostr; break; case USCRIPT_LOMA: - sRet = "lom"; + sRet = "lom"_ostr; break; case USCRIPT_MENDE: - sRet = "men"; + sRet = "men"_ostr; break; case USCRIPT_MEROITIC_CURSIVE: - sRet = "xmr"; + sRet = "xmr"_ostr; break; case USCRIPT_OLD_NORTH_ARABIAN: - sRet = "xna"; + sRet = "xna"_ostr; break; case USCRIPT_SINDHI: - sRet = "sd"; + sRet = "sd"_ostr; break; case USCRIPT_WARANG_CITI: - sRet = "hoc"; + sRet = "hoc"_ostr; break; -#if (U_ICU_VERSION_MAJOR_NUM > 4) || (U_ICU_VERSION_MAJOR_NUM == 4 && U_ICU_VERSION_MINOR_NUM >= 8) case USCRIPT_AFAKA: - sRet = "djk"; + sRet = "djk"_ostr; break; case USCRIPT_JURCHEN: - sRet = "juc"; + sRet = "juc"_ostr; break; case USCRIPT_MRO: - sRet = "cmr"; + sRet = "cmr"_ostr; break; case USCRIPT_NUSHU: - sRet = "mis-Nshu"; // Uncoded with script + sRet = "mis-Nshu"_ostr; // Uncoded with script break; case USCRIPT_SHARADA: - sRet = "sa"; + sRet = "sa"_ostr; break; case USCRIPT_SORA_SOMPENG: - sRet = "srb"; + sRet = "srb"_ostr; break; case USCRIPT_TAKRI: - sRet = "doi"; + sRet = "doi"_ostr; break; case USCRIPT_TANGUT: - sRet = "txg"; + sRet = "txg"_ostr; break; case USCRIPT_WOLEAI: - sRet = "woe"; + sRet = "woe"_ostr; break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 49) case USCRIPT_ANATOLIAN_HIEROGLYPHS: - sRet = "hlu"; + sRet = "hlu"_ostr; break; case USCRIPT_KHOJKI: - sRet = "gu"; + sRet = "gu"_ostr; break; case USCRIPT_TIRHUTA: - sRet = "mai"; + sRet = "mai"_ostr; break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 52) case USCRIPT_CAUCASIAN_ALBANIAN: - sRet = "xag"; + sRet = "xag"_ostr; break; case USCRIPT_MAHAJANI: - sRet = "mwr"; + sRet = "mwr"_ostr; break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 54) case USCRIPT_AHOM: - sRet = "aho"; + sRet = "aho"_ostr; break; case USCRIPT_HATRAN: - sRet = "qly-Hatr"; + sRet = "qly-Hatr"_ostr; break; case USCRIPT_MODI: - sRet = "mr-Modi"; + sRet = "mr-Modi"_ostr; break; case USCRIPT_MULTANI: - sRet = "skr-Mutl"; + sRet = "skr-Mutl"_ostr; break; case USCRIPT_PAU_CIN_HAU: - sRet = "ctd-Pauc"; + sRet = "ctd-Pauc"_ostr; break; case USCRIPT_SIDDHAM: - sRet = "sa-Sidd"; + sRet = "sa-Sidd"_ostr; break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 58) case USCRIPT_ADLAM: - sRet = "mis-Adlm"; // Adlam for Fulani, no language code + sRet = "mis-Adlm"_ostr; // Adlam for Fulani, no language code break; case USCRIPT_BHAIKSUKI: - sRet = "mis-Bhks"; // Bhaiksuki for some Buddhist texts, no language code + sRet = "mis-Bhks"_ostr; // Bhaiksuki for some Buddhist texts, no language code break; case USCRIPT_MARCHEN: - sRet = "bo-Marc"; + sRet = "bo-Marc"_ostr; break; case USCRIPT_NEWA: - sRet = "new-Newa"; + sRet = "new-Newa"_ostr; break; case USCRIPT_OSAGE: - sRet = "osa-Osge"; + sRet = "osa-Osge"_ostr; break; case USCRIPT_HAN_WITH_BOPOMOFO: - sRet = "mis-Hanb"; // Han with Bopomofo, zh-Hanb ? + sRet = "mis-Hanb"_ostr; // Han with Bopomofo, zh-Hanb ? break; case USCRIPT_JAMO: - sRet = "ko"; // Jamo - elements of Hangul Syllables + sRet = "ko"_ostr; // Jamo - elements of Hangul Syllables break; case USCRIPT_SYMBOLS_EMOJI: - sRet = "mis-Zsye"; // Emoji variant + sRet = "mis-Zsye"_ostr; // Emoji variant break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 60) case USCRIPT_MASARAM_GONDI: - sRet = "gon-Gonm"; // macro language code, could be wsg,esg,gno + sRet = "gon-Gonm"_ostr; // macro language code, could be wsg,esg,gno break; case USCRIPT_SOYOMBO: - sRet = "mn-Soyo"; // abugida to write Mongolian, also Tibetan and Sanskrit + sRet = "mn-Soyo"_ostr; // abugida to write Mongolian, also Tibetan and Sanskrit break; case USCRIPT_ZANABAZAR_SQUARE: - sRet = "mn-Zanb"; // abugida to write Mongolian + sRet = "mn-Zanb"_ostr; // abugida to write Mongolian break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 62) case USCRIPT_DOGRA: - sRet = "dgo"; // Dogri proper + sRet = "dgo"_ostr; // Dogri proper break; case USCRIPT_GUNJALA_GONDI: - sRet = "wsg"; // Adilabad Gondi + sRet = "wsg"_ostr; // Adilabad Gondi break; case USCRIPT_MAKASAR: - sRet = "mak"; + sRet = "mak"_ostr; break; case USCRIPT_MEDEFAIDRIN: - sRet = "dmf-Medf"; + sRet = "dmf-Medf"_ostr; break; case USCRIPT_HANIFI_ROHINGYA: - sRet = "rhg"; + sRet = "rhg"_ostr; break; case USCRIPT_SOGDIAN: - sRet = "sog"; + sRet = "sog"_ostr; break; case USCRIPT_OLD_SOGDIAN: - sRet = "sog"; + sRet = "sog"_ostr; break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 64) case USCRIPT_ELYMAIC: - sRet = "arc-Elym"; + sRet = "arc-Elym"_ostr; break; case USCRIPT_NYIAKENG_PUACHUE_HMONG: - sRet = "hmn-Hmnp"; // macrolanguage code + sRet = "hmn-Hmnp"_ostr; // macrolanguage code break; case USCRIPT_NANDINAGARI: - sRet = "sa-Nand"; + sRet = "sa-Nand"_ostr; break; case USCRIPT_WANCHO: - sRet = "nnp-Wcho"; + sRet = "nnp-Wcho"_ostr; break; -#endif -#if (U_ICU_VERSION_MAJOR_NUM >= 66) case USCRIPT_CHORASMIAN: - sRet = "xco-Chrs"; + sRet = "xco-Chrs"_ostr; break; case USCRIPT_DIVES_AKURU: - sRet = "dv-Diak"; + sRet = "dv-Diak"_ostr; break; case USCRIPT_KHITAN_SMALL_SCRIPT: - sRet = "zkt-Kits"; + sRet = "zkt-Kits"_ostr; break; case USCRIPT_YEZIDI: - sRet = "kmr-Yezi"; + sRet = "kmr-Yezi"_ostr; break; -#endif #if (U_ICU_VERSION_MAJOR_NUM >= 70) case USCRIPT_CYPRO_MINOAN: - sRet = "mis-Cpmn"; // Uncoded with script + sRet = "mis-Cpmn"_ostr; // Uncoded with script break; case USCRIPT_OLD_UYGHUR: - sRet = "oui-Ougr"; + sRet = "oui-Ougr"_ostr; break; case USCRIPT_TANGSA: - sRet = "nst-Tnsa"; + sRet = "nst-Tnsa"_ostr; break; case USCRIPT_TOTO: - sRet = "txo-Toto"; + sRet = "txo-Toto"_ostr; break; case USCRIPT_VITHKUQI: - sRet = "sq-Vith"; // macrolanguage code + sRet = "sq-Vith"_ostr; // macrolanguage code + break; +#endif +#if (U_ICU_VERSION_MAJOR_NUM >= 72) + case USCRIPT_KAWI: + sRet = "mis-Kawi"_ostr; // Uncoded with script + break; + case USCRIPT_NAG_MUNDARI: + sRet = "unr-Nagm"_ostr; break; #endif } @@ -1019,7 +1248,7 @@ OUString ToggleUnicodeCodepoint::StringToReplace() sIn = maInput.toString(); while( nUPlus != -1 ) { - nUnicode = sIn.copy(0, nUPlus).toUInt32(16); + nUnicode = o3tl::toUInt32(sIn.subView(0, nUPlus), 16); //prevent creating control characters or invalid Unicode values if( !rtl::isUnicodeCodePoint(nUnicode) || nUnicode < 0x20 ) maInput = sIn.subView(nUPlus); @@ -1062,7 +1291,7 @@ OUString ToggleUnicodeCodepoint::ReplacementString() } while( nUPlus > 0 ) { - nUnicode = sIn.copy(0, nUPlus).toUInt32(16); + nUnicode = o3tl::toUInt32(sIn.subView(0, nUPlus), 16); output.appendUtf32( nUnicode ); sIn = sIn.copy(nUPlus+2); @@ -1081,8 +1310,7 @@ OUString ToggleUnicodeCodepoint::ReplacementString() //pad with zeros - minimum length of 4. for( sal_Int32 i = 4 - aTmp.getLength(); i > 0; --i ) aTmp.insert( 0,"0" ); - output.append( "U+" ); - output.append( aTmp ); + output.append( "U+" + aTmp ); } } return output.makeStringAndClear(); |