package unicode

import "unicode"

unicode包提供数据和函数来测试Unicode代码点的一些属性。

Index

返回首页


  • Constants
  • Variables
  • type CaseRange
  • type Range16
  • type Range32
  • type RangeTable
  • type SpecialCase
  • func Is(rangeTab *RangeTable, r rune) bool
  • func In(r rune, ranges ...*RangeTable) bool
  • func IsOneOf(ranges []*RangeTable, r rune) bool
  • func IsSpace(r rune) bool
  • func IsDigit(r rune) bool
  • func IsNumber(r rune) bool
  • func IsLetter(r rune) bool
  • func IsGraphic(r rune) bool
  • func IsControl(r rune) bool
  • func IsMark(r rune) bool
  • func IsPrint(r rune) bool
  • func IsPunct(r rune) bool
  • func IsSymbol(r rune) bool
  • func IsLower(r rune) bool
  • func IsUpper(r rune) bool
  • func IsTitle(r rune) bool
  • func To(_case int, r rune) rune
  • func ToLower(r rune) rune
  • func ToUpper(r rune) rune
  • func ToTitle(r rune) rune
  • func SimpleFold(r rune) rune
  • Constants

    const (
        MaxRune         = '\U0010FFFF' // 最大的合法unicode码值
        ReplacementChar = '\uFFFD'     // 表示不合法的unicode码值
        MaxASCII        = '\u007F'     // 最大的ASCII值
        MaxLatin1       = '\u00FF'     // 最大的Latin-1值
    )
    const (
        UpperCase = iota
        LowerCase
        TitleCase
        MaxCase
    )

    下值可用于CaseRange类型里的数组类型Delta字段,用于码值映射。

    const (
        UpperLower = MaxRune + 1 // 不能是合法的delta值
    )

    如果一个CaseRange类型的的Delta字段使用了UpperLower,就表示该CaseRange表示的序列格式为:Upper Lower Upper Lower

    const Version = "6.3.0"

    Version是本包采用的unicode版本(以及Variables栏里那些乱七八糟的字符集的来源)。

    Variables

    var (
        Cc     = _Cc // Cc is the set of Unicode characters in category Cc.
        Cf     = _Cf // Cf is the set of Unicode characters in category Cf.
        Co     = _Co // Co is the set of Unicode characters in category Co.
        Cs     = _Cs // Cs is the set of Unicode characters in category Cs.
        Digit  = _Nd // Digit is the set of Unicode characters with the "decimal digit" property.
        Nd     = _Nd // Nd is the set of Unicode characters in category Nd.
        Letter = _L  // Letter/L is the set of Unicode letters, category L.
        L      = _L
        Lm     = _Lm // Lm is the set of Unicode characters in category Lm.
        Lo     = _Lo // Lo is the set of Unicode characters in category Lo.
        Lower  = _Ll // Lower is the set of Unicode lower case letters.
        Ll     = _Ll // Ll is the set of Unicode characters in category Ll.
        Mark   = _M  // Mark/M is the set of Unicode mark characters, category M.
        M      = _M
        Mc     = _Mc // Mc is the set of Unicode characters in category Mc.
        Me     = _Me // Me is the set of Unicode characters in category Me.
        Mn     = _Mn // Mn is the set of Unicode characters in category Mn.
        Nl     = _Nl // Nl is the set of Unicode characters in category Nl.
        No     = _No // No is the set of Unicode characters in category No.
        Number = _N  // Number/N is the set of Unicode number characters, category N.
        N      = _N
        Other  = _C // Other/C is the set of Unicode control and special characters, category C.
        C      = _C
        Pc     = _Pc // Pc is the set of Unicode characters in category Pc.
        Pd     = _Pd // Pd is the set of Unicode characters in category Pd.
        Pe     = _Pe // Pe is the set of Unicode characters in category Pe.
        Pf     = _Pf // Pf is the set of Unicode characters in category Pf.
        Pi     = _Pi // Pi is the set of Unicode characters in category Pi.
        Po     = _Po // Po is the set of Unicode characters in category Po.
        Ps     = _Ps // Ps is the set of Unicode characters in category Ps.
        Punct  = _P  // Punct/P is the set of Unicode punctuation characters, category P.
        P      = _P
        Sc     = _Sc // Sc is the set of Unicode characters in category Sc.
        Sk     = _Sk // Sk is the set of Unicode characters in category Sk.
        Sm     = _Sm // Sm is the set of Unicode characters in category Sm.
        So     = _So // So is the set of Unicode characters in category So.
        Space  = _Z  // Space/Z is the set of Unicode space characters, category Z.
        Z      = _Z
        Symbol = _S // Symbol/S is the set of Unicode symbol characters, category S.
        S      = _S
        Title  = _Lt // Title is the set of Unicode title case letters.
        Lt     = _Lt // Lt is the set of Unicode characters in category Lt.
        Upper  = _Lu // Upper is the set of Unicode upper case letters.
        Lu     = _Lu // Lu is the set of Unicode characters in category Lu.
        Zl     = _Zl // Zl is the set of Unicode characters in category Zl.
        Zp     = _Zp // Zp is the set of Unicode characters in category Zp.
        Zs     = _Zs // Zs is the set of Unicode characters in category Zs.
    )

    这些变量的类型是*RangeTable。

    var (
        Arabic                 = _Arabic                 // Arabic is the set of Unicode characters in script Arabic.
        Armenian               = _Armenian               // Armenian is the set of Unicode characters in script Armenian.
        Avestan                = _Avestan                // Avestan is the set of Unicode characters in script Avestan.
        Balinese               = _Balinese               // Balinese is the set of Unicode characters in script Balinese.
        Bamum                  = _Bamum                  // Bamum is the set of Unicode characters in script Bamum.
        Batak                  = _Batak                  // Batak is the set of Unicode characters in script Batak.
        Bengali                = _Bengali                // Bengali is the set of Unicode characters in script Bengali.
        Bopomofo               = _Bopomofo               // Bopomofo is the set of Unicode characters in script Bopomofo.
        Brahmi                 = _Brahmi                 // Brahmi is the set of Unicode characters in script Brahmi.
        Braille                = _Braille                // Braille is the set of Unicode characters in script Braille.
        Buginese               = _Buginese               // Buginese is the set of Unicode characters in script Buginese.
        Buhid                  = _Buhid                  // Buhid is the set of Unicode characters in script Buhid.
        Canadian_Aboriginal    = _Canadian_Aboriginal    // Canadian_Aboriginal is the set of Unicode characters in script Canadian_Aboriginal.
        Carian                 = _Carian                 // Carian is the set of Unicode characters in script Carian.
        Chakma                 = _Chakma                 // Chakma is the set of Unicode characters in script Chakma.
        Cham                   = _Cham                   // Cham is the set of Unicode characters in script Cham.
        Cherokee               = _Cherokee               // Cherokee is the set of Unicode characters in script Cherokee.
        Common                 = _Common                 // Common is the set of Unicode characters in script Common.
        Coptic                 = _Coptic                 // Coptic is the set of Unicode characters in script Coptic.
        Cuneiform              = _Cuneiform              // Cuneiform is the set of Unicode characters in script Cuneiform.
        Cypriot                = _Cypriot                // Cypriot is the set of Unicode characters in script Cypriot.
        Cyrillic               = _Cyrillic               // Cyrillic is the set of Unicode characters in script Cyrillic.
        Deseret                = _Deseret                // Deseret is the set of Unicode characters in script Deseret.
        Devanagari             = _Devanagari             // Devanagari is the set of Unicode characters in script Devanagari.
        Egyptian_Hieroglyphs   = _Egyptian_Hieroglyphs   // Egyptian_Hieroglyphs is the set of Unicode characters in script Egyptian_Hieroglyphs.
        Ethiopic               = _Ethiopic               // Ethiopic is the set of Unicode characters in script Ethiopic.
        Georgian               = _Georgian               // Georgian is the set of Unicode characters in script Georgian.
        Glagolitic             = _Glagolitic             // Glagolitic is the set of Unicode characters in script Glagolitic.
        Gothic                 = _Gothic                 // Gothic is the set of Unicode characters in script Gothic.
        Greek                  = _Greek                  // Greek is the set of Unicode characters in script Greek.
        Gujarati               = _Gujarati               // Gujarati is the set of Unicode characters in script Gujarati.
        Gurmukhi               = _Gurmukhi               // Gurmukhi is the set of Unicode characters in script Gurmukhi.
        Han                    = _Han                    // Han is the set of Unicode characters in script Han.
        Hangul                 = _Hangul                 // Hangul is the set of Unicode characters in script Hangul.
        Hanunoo                = _Hanunoo                // Hanunoo is the set of Unicode characters in script Hanunoo.
        Hebrew                 = _Hebrew                 // Hebrew is the set of Unicode characters in script Hebrew.
        Hiragana               = _Hiragana               // Hiragana is the set of Unicode characters in script Hiragana.
        Imperial_Aramaic       = _Imperial_Aramaic       // Imperial_Aramaic is the set of Unicode characters in script Imperial_Aramaic.
        Inherited              = _Inherited              // Inherited is the set of Unicode characters in script Inherited.
        Inscriptional_Pahlavi  = _Inscriptional_Pahlavi  // Inscriptional_Pahlavi is the set of Unicode characters in script Inscriptional_Pahlavi.
        Inscriptional_Parthian = _Inscriptional_Parthian // Inscriptional_Parthian is the set of Unicode characters in script Inscriptional_Parthian.
        Javanese               = _Javanese               // Javanese is the set of Unicode characters in script Javanese.
        Kaithi                 = _Kaithi                 // Kaithi is the set of Unicode characters in script Kaithi.
        Kannada                = _Kannada                // Kannada is the set of Unicode characters in script Kannada.
        Katakana               = _Katakana               // Katakana is the set of Unicode characters in script Katakana.
        Kayah_Li               = _Kayah_Li               // Kayah_Li is the set of Unicode characters in script Kayah_Li.
        Kharoshthi             = _Kharoshthi             // Kharoshthi is the set of Unicode characters in script Kharoshthi.
        Khmer                  = _Khmer                  // Khmer is the set of Unicode characters in script Khmer.
        Lao                    = _Lao                    // Lao is the set of Unicode characters in script Lao.
        Latin                  = _Latin                  // Latin is the set of Unicode characters in script Latin.
        Lepcha                 = _Lepcha                 // Lepcha is the set of Unicode characters in script Lepcha.
        Limbu                  = _Limbu                  // Limbu is the set of Unicode characters in script Limbu.
        Linear_B               = _Linear_B               // Linear_B is the set of Unicode characters in script Linear_B.
        Lisu                   = _Lisu                   // Lisu is the set of Unicode characters in script Lisu.
        Lycian                 = _Lycian                 // Lycian is the set of Unicode characters in script Lycian.
        Lydian                 = _Lydian                 // Lydian is the set of Unicode characters in script Lydian.
        Malayalam              = _Malayalam              // Malayalam is the set of Unicode characters in script Malayalam.
        Mandaic                = _Mandaic                // Mandaic is the set of Unicode characters in script Mandaic.
        Meetei_Mayek           = _Meetei_Mayek           // Meetei_Mayek is the set of Unicode characters in script Meetei_Mayek.
        Meroitic_Cursive       = _Meroitic_Cursive       // Meroitic_Cursive is the set of Unicode characters in script Meroitic_Cursive.
        Meroitic_Hieroglyphs   = _Meroitic_Hieroglyphs   // Meroitic_Hieroglyphs is the set of Unicode characters in script Meroitic_Hieroglyphs.
        Miao                   = _Miao                   // Miao is the set of Unicode characters in script Miao.
        Mongolian              = _Mongolian              // Mongolian is the set of Unicode characters in script Mongolian.
        Myanmar                = _Myanmar                // Myanmar is the set of Unicode characters in script Myanmar.
        New_Tai_Lue            = _New_Tai_Lue            // New_Tai_Lue is the set of Unicode characters in script New_Tai_Lue.
        Nko                    = _Nko                    // Nko is the set of Unicode characters in script Nko.
        Ogham                  = _Ogham                  // Ogham is the set of Unicode characters in script Ogham.
        Ol_Chiki               = _Ol_Chiki               // Ol_Chiki is the set of Unicode characters in script Ol_Chiki.
        Old_Italic             = _Old_Italic             // Old_Italic is the set of Unicode characters in script Old_Italic.
        Old_Persian            = _Old_Persian            // Old_Persian is the set of Unicode characters in script Old_Persian.
        Old_South_Arabian      = _Old_South_Arabian      // Old_South_Arabian is the set of Unicode characters in script Old_South_Arabian.
        Old_Turkic             = _Old_Turkic             // Old_Turkic is the set of Unicode characters in script Old_Turkic.
        Oriya                  = _Oriya                  // Oriya is the set of Unicode characters in script Oriya.
        Osmanya                = _Osmanya                // Osmanya is the set of Unicode characters in script Osmanya.
        Phags_Pa               = _Phags_Pa               // Phags_Pa is the set of Unicode characters in script Phags_Pa.
        Phoenician             = _Phoenician             // Phoenician is the set of Unicode characters in script Phoenician.
        Rejang                 = _Rejang                 // Rejang is the set of Unicode characters in script Rejang.
        Runic                  = _Runic                  // Runic is the set of Unicode characters in script Runic.
        Samaritan              = _Samaritan              // Samaritan is the set of Unicode characters in script Samaritan.
        Saurashtra             = _Saurashtra             // Saurashtra is the set of Unicode characters in script Saurashtra.
        Sharada                = _Sharada                // Sharada is the set of Unicode characters in script Sharada.
        Shavian                = _Shavian                // Shavian is the set of Unicode characters in script Shavian.
        Sinhala                = _Sinhala                // Sinhala is the set of Unicode characters in script Sinhala.
        Sora_Sompeng           = _Sora_Sompeng           // Sora_Sompeng is the set of Unicode characters in script Sora_Sompeng.
        Sundanese              = _Sundanese              // Sundanese is the set of Unicode characters in script Sundanese.
        Syloti_Nagri           = _Syloti_Nagri           // Syloti_Nagri is the set of Unicode characters in script Syloti_Nagri.
        Syriac                 = _Syriac                 // Syriac is the set of Unicode characters in script Syriac.
        Tagalog                = _Tagalog                // Tagalog is the set of Unicode characters in script Tagalog.
        Tagbanwa               = _Tagbanwa               // Tagbanwa is the set of Unicode characters in script Tagbanwa.
        Tai_Le                 = _Tai_Le                 // Tai_Le is the set of Unicode characters in script Tai_Le.
        Tai_Tham               = _Tai_Tham               // Tai_Tham is the set of Unicode characters in script Tai_Tham.
        Tai_Viet               = _Tai_Viet               // Tai_Viet is the set of Unicode characters in script Tai_Viet.
        Takri                  = _Takri                  // Takri is the set of Unicode characters in script Takri.
        Tamil                  = _Tamil                  // Tamil is the set of Unicode characters in script Tamil.
        Telugu                 = _Telugu                 // Telugu is the set of Unicode characters in script Telugu.
        Thaana                 = _Thaana                 // Thaana is the set of Unicode characters in script Thaana.
        Thai                   = _Thai                   // Thai is the set of Unicode characters in script Thai.
        Tibetan                = _Tibetan                // Tibetan is the set of Unicode characters in script Tibetan.
        Tifinagh               = _Tifinagh               // Tifinagh is the set of Unicode characters in script Tifinagh.
        Ugaritic               = _Ugaritic               // Ugaritic is the set of Unicode characters in script Ugaritic.
        Vai                    = _Vai                    // Vai is the set of Unicode characters in script Vai.
        Yi                     = _Yi                     // Yi is the set of Unicode characters in script Yi.
    )

    这些变量的类型也是*RangeTable。

    var (
        ASCII_Hex_Digit                    = _ASCII_Hex_Digit                    // ASCII_Hex_Digit is the set of Unicode characters with property ASCII_Hex_Digit.
        Bidi_Control                       = _Bidi_Control                       // Bidi_Control is the set of Unicode characters with property Bidi_Control.
        Dash                               = _Dash                               // Dash is the set of Unicode characters with property Dash.
        Deprecated                         = _Deprecated                         // Deprecated is the set of Unicode characters with property Deprecated.
        Diacritic                          = _Diacritic                          // Diacritic is the set of Unicode characters with property Diacritic.
        Extender                           = _Extender                           // Extender is the set of Unicode characters with property Extender.
        Hex_Digit                          = _Hex_Digit                          // Hex_Digit is the set of Unicode characters with property Hex_Digit.
        Hyphen                             = _Hyphen                             // Hyphen is the set of Unicode characters with property Hyphen.
        IDS_Binary_Operator                = _IDS_Binary_Operator                // IDS_Binary_Operator is the set of Unicode characters with property IDS_Binary_Operator.
        IDS_Trinary_Operator               = _IDS_Trinary_Operator               // IDS_Trinary_Operator is the set of Unicode characters with property IDS_Trinary_Operator.
        Ideographic                        = _Ideographic                        // Ideographic is the set of Unicode characters with property Ideographic.
        Join_Control                       = _Join_Control                       // Join_Control is the set of Unicode characters with property Join_Control.
        Logical_Order_Exception            = _Logical_Order_Exception            // Logical_Order_Exception is the set of Unicode characters with property Logical_Order_Exception.
        Noncharacter_Code_Point            = _Noncharacter_Code_Point            // Noncharacter_Code_Point is the set of Unicode characters with property Noncharacter_Code_Point.
        Other_Alphabetic                   = _Other_Alphabetic                   // Other_Alphabetic is the set of Unicode characters with property Other_Alphabetic.
        Other_Default_Ignorable_Code_Point = _Other_Default_Ignorable_Code_Point // Other_Default_Ignorable_Code_Point is the set of Unicode characters with property Other_Default_Ignorable_Code_Point.
        Other_Grapheme_Extend              = _Other_Grapheme_Extend              // Other_Grapheme_Extend is the set of Unicode characters with property Other_Grapheme_Extend.
        Other_ID_Continue                  = _Other_ID_Continue                  // Other_ID_Continue is the set of Unicode characters with property Other_ID_Continue.
        Other_ID_Start                     = _Other_ID_Start                     // Other_ID_Start is the set of Unicode characters with property Other_ID_Start.
        Other_Lowercase                    = _Other_Lowercase                    // Other_Lowercase is the set of Unicode characters with property Other_Lowercase.
        Other_Math                         = _Other_Math                         // Other_Math is the set of Unicode characters with property Other_Math.
        Other_Uppercase                    = _Other_Uppercase                    // Other_Uppercase is the set of Unicode characters with property Other_Uppercase.
        Pattern_Syntax                     = _Pattern_Syntax                     // Pattern_Syntax is the set of Unicode characters with property Pattern_Syntax.
        Pattern_White_Space                = _Pattern_White_Space                // Pattern_White_Space is the set of Unicode characters with property Pattern_White_Space.
        Quotation_Mark                     = _Quotation_Mark                     // Quotation_Mark is the set of Unicode characters with property Quotation_Mark.
        Radical                            = _Radical                            // Radical is the set of Unicode characters with property Radical.
        STerm                              = _STerm                              // STerm is the set of Unicode characters with property STerm.
        Soft_Dotted                        = _Soft_Dotted                        // Soft_Dotted is the set of Unicode characters with property Soft_Dotted.
        Terminal_Punctuation               = _Terminal_Punctuation               // Terminal_Punctuation is the set of Unicode characters with property Terminal_Punctuation.
        Unified_Ideograph                  = _Unified_Ideograph                  // Unified_Ideograph is the set of Unicode characters with property Unified_Ideograph.
        Variation_Selector                 = _Variation_Selector                 // Variation_Selector is the set of Unicode characters with property Variation_Selector.
        White_Space                        = _White_Space                        // White_Space is the set of Unicode characters with property White_Space.
    )

    这些变量的类型还是*RangeTable。

    var CaseRanges = _CaseRanges

    CaseRanges是描述具有非自映射的所有字母的大小写映射的表格。

    var Categories = map[string]*RangeTable{
        "C":  C,
        "Cc": Cc,
        "Cf": Cf,
        "Co": Co,
        "Cs": Cs,
        "L":  L,
        "Ll": Ll,
        "Lm": Lm,
        "Lo": Lo,
        "Lt": Lt,
        "Lu": Lu,
        "M":  M,
        "Mc": Mc,
        "Me": Me,
        "Mn": Mn,
        "N":  N,
        "Nd": Nd,
        "Nl": Nl,
        "No": No,
        "P":  P,
        "Pc": Pc,
        "Pd": Pd,
        "Pe": Pe,
        "Pf": Pf,
        "Pi": Pi,
        "Po": Po,
        "Ps": Ps,
        "S":  S,
        "Sc": Sc,
        "Sk": Sk,
        "Sm": Sm,
        "So": So,
        "Z":  Z,
        "Zl": Zl,
        "Zp": Zp,
        "Zs": Zs,
    }

    Categories是一组Unicode类别表.

    var FoldCategory = map[string]*RangeTable{
        "Common":    foldCommon,
        "Greek":     foldGreek,
        "Inherited": foldInherited,
        "L":         foldL,
        "Ll":        foldLl,
        "Lt":        foldLt,
        "Lu":        foldLu,
        "M":         foldM,
        "Mn":        foldMn,
    }

    FoldCategory将类别名称映射到类别外的代码点表,这些代码点在简单大小写折叠的情况下等同于类别内的代码点。如果没有类别名称的条目,则不存在这样的点。

    var FoldScript = map[string]*RangeTable{}

    FoldScript将脚本名称映射到脚本外的代码点表,这些代码点在简单案例折叠到脚本内的代码点之后是等同的。如果没有条目名称的条目,则没有这样的条目。

    var GraphicRanges = []*RangeTable{
        L, M, N, P, S, Zs,
    }

    GraphicRanges根据Unicode定义了一组图形字符。

    var PrintRanges = []*RangeTable{
        L, M, N, P, S,
    }

    PrintRanges根据Go定义一组可打印的字符。ASCII space, U+0020, 分开处理。

    var Properties = map[string]*RangeTable{
        "ASCII_Hex_Digit":                    ASCII_Hex_Digit,
        "Bidi_Control":                       Bidi_Control,
        "Dash":                               Dash,
        "Deprecated":                         Deprecated,
        "Diacritic":                          Diacritic,
        "Extender":                           Extender,
        "Hex_Digit":                          Hex_Digit,
        "Hyphen":                             Hyphen,
        "IDS_Binary_Operator":                IDS_Binary_Operator,
        "IDS_Trinary_Operator":               IDS_Trinary_Operator,
        "Ideographic":                        Ideographic,
        "Join_Control":                       Join_Control,
        "Logical_Order_Exception":            Logical_Order_Exception,
        "Noncharacter_Code_Point":            Noncharacter_Code_Point,
        "Other_Alphabetic":                   Other_Alphabetic,
        "Other_Default_Ignorable_Code_Point": Other_Default_Ignorable_Code_Point,
        "Other_Grapheme_Extend":              Other_Grapheme_Extend,
        "Other_ID_Continue":                  Other_ID_Continue,
        "Other_ID_Start":                     Other_ID_Start,
        "Other_Lowercase":                    Other_Lowercase,
        "Other_Math":                         Other_Math,
        "Other_Uppercase":                    Other_Uppercase,
        "Pattern_Syntax":                     Pattern_Syntax,
        "Pattern_White_Space":                Pattern_White_Space,
        "Quotation_Mark":                     Quotation_Mark,
        "Radical":                            Radical,
        "STerm":                              STerm,
        "Soft_Dotted":                        Soft_Dotted,
        "Terminal_Punctuation":               Terminal_Punctuation,
        "Unified_Ideograph":                  Unified_Ideograph,
        "Variation_Selector":                 Variation_Selector,
        "White_Space":                        White_Space,
    }

    Properties是Unicode属性表的集合。

    var Scripts = map[string]*RangeTable{
        "Arabic":                 Arabic,
        "Armenian":               Armenian,
        "Avestan":                Avestan,
        "Balinese":               Balinese,
        "Bamum":                  Bamum,
        "Batak":                  Batak,
        "Bengali":                Bengali,
        "Bopomofo":               Bopomofo,
        "Brahmi":                 Brahmi,
        "Braille":                Braille,
        "Buginese":               Buginese,
        "Buhid":                  Buhid,
        "Canadian_Aboriginal":    Canadian_Aboriginal,
        "Carian":                 Carian,
        "Chakma":                 Chakma,
        "Cham":                   Cham,
        "Cherokee":               Cherokee,
        "Common":                 Common,
        "Coptic":                 Coptic,
        "Cuneiform":              Cuneiform,
        "Cypriot":                Cypriot,
        "Cyrillic":               Cyrillic,
        "Deseret":                Deseret,
        "Devanagari":             Devanagari,
        "Egyptian_Hieroglyphs":   Egyptian_Hieroglyphs,
        "Ethiopic":               Ethiopic,
        "Georgian":               Georgian,
        "Glagolitic":             Glagolitic,
        "Gothic":                 Gothic,
        "Greek":                  Greek,
        "Gujarati":               Gujarati,
        "Gurmukhi":               Gurmukhi,
        "Han":                    Han,
        "Hangul":                 Hangul,
        "Hanunoo":                Hanunoo,
        "Hebrew":                 Hebrew,
        "Hiragana":               Hiragana,
        "Imperial_Aramaic":       Imperial_Aramaic,
        "Inherited":              Inherited,
        "Inscriptional_Pahlavi":  Inscriptional_Pahlavi,
        "Inscriptional_Parthian": Inscriptional_Parthian,
        "Javanese":               Javanese,
        "Kaithi":                 Kaithi,
        "Kannada":                Kannada,
        "Katakana":               Katakana,
        "Kayah_Li":               Kayah_Li,
        "Kharoshthi":             Kharoshthi,
        "Khmer":                  Khmer,
        "Lao":                    Lao,
        "Latin":                  Latin,
        "Lepcha":                 Lepcha,
        "Limbu":                  Limbu,
        "Linear_B":               Linear_B,
        "Lisu":                   Lisu,
        "Lycian":                 Lycian,
        "Lydian":                 Lydian,
        "Malayalam":              Malayalam,
        "Mandaic":                Mandaic,
        "Meetei_Mayek":           Meetei_Mayek,
        "Meroitic_Cursive":       Meroitic_Cursive,
        "Meroitic_Hieroglyphs":   Meroitic_Hieroglyphs,
        "Miao":                   Miao,
        "Mongolian":              Mongolian,
        "Myanmar":                Myanmar,
        "New_Tai_Lue":            New_Tai_Lue,
        "Nko":                    Nko,
        "Ogham":                  Ogham,
        "Ol_Chiki":               Ol_Chiki,
        "Old_Italic":             Old_Italic,
        "Old_Persian":            Old_Persian,
        "Old_South_Arabian":      Old_South_Arabian,
        "Old_Turkic":             Old_Turkic,
        "Oriya":                  Oriya,
        "Osmanya":                Osmanya,
        "Phags_Pa":               Phags_Pa,
        "Phoenician":             Phoenician,
        "Rejang":                 Rejang,
        "Runic":                  Runic,
        "Samaritan":              Samaritan,
        "Saurashtra":             Saurashtra,
        "Sharada":                Sharada,
        "Shavian":                Shavian,
        "Sinhala":                Sinhala,
        "Sora_Sompeng":           Sora_Sompeng,
        "Sundanese":              Sundanese,
        "Syloti_Nagri":           Syloti_Nagri,
        "Syriac":                 Syriac,
        "Tagalog":                Tagalog,
        "Tagbanwa":               Tagbanwa,
        "Tai_Le":                 Tai_Le,
        "Tai_Tham":               Tai_Tham,
        "Tai_Viet":               Tai_Viet,
        "Takri":                  Takri,
        "Tamil":                  Tamil,
        "Telugu":                 Telugu,
        "Thaana":                 Thaana,
        "Thai":                   Thai,
        "Tibetan":                Tibetan,
        "Tifinagh":               Tifinagh,
        "Ugaritic":               Ugaritic,
        "Vai":                    Vai,
        "Yi":                     Yi,
    }

    Scripts是一组Unicode脚本表。

    type CaseRange

    type CaseRange struct {
        Lo    uint32
        Hi    uint32
        Delta d // d为[MaxCase]rune的命名类型
    }

    代表简单的unicode码值的一一映射。范围为[Lo, Hi],步长为1。

    该范围内的每个值+Delta[UpperCase]表示对应的大写字母;

    该范围内的每个值+Delta[LowerCase]表示对应的小写字母;

    该范围内的每个值+Delta[TitleCase]表示对应的标题字母。

    Delta数组里的值可为负数或零。如果Delta数组是:

    {UpperLower, UpperLower, UpperLower}
    

    表示[Lo, Hi]范围的字符序列是交替的、对应的大写字母小写字母对。否则常数UpperLower不能用Delta数组里。

    type Range16

    type Range16 struct {
        Lo     uint16
        Hi     uint16
        Stride uint16
    }

    代表一系列16位unicode码值,范围为Lo到Hi(可以是Lo/Hi),步长为Stride。

    type Range32

    type Range32 struct {
        Lo     uint32
        Hi     uint32
        Stride uint32
    }

    代表一系列32位unicode码值,范围为Lo到Hi(可以是Lo/Hi),步长为Stride;Lo和Hi必须大于等于1<<16。

    type RangeTable

    type RangeTable struct {
        R16         []Range16
        R32         []Range32  // R32不能包含低于0x10000(即1<<16)的值
        LatinOffset int // R16字段中Hi <= MaxLatin1的成员数
    }

    通过列出集合中码值的范围,定义了一个unicode码值的集合。出于节省空间,范围保存在两个切片里,分别保存16位字符的范围和32位字符的范围。R16和R32必须是有序排列的,且互不重叠的。

    type SpecialCase

    type SpecialCase []CaseRange

    SpecialCase代表特定语言的字符映射,如土耳其语。本类型的方法(通过覆盖)定制了标准映射。

    var AzeriCase SpecialCase = _TurkishCase
    var TurkishCase SpecialCase = _TurkishCase

    func (SpecialCase) ToLower

    func (special SpecialCase) ToLower(r rune) rune

    按特定映射,返回对应的小写字母。

    func (SpecialCase) ToUpper

    func (special SpecialCase) ToUpper(r rune) rune

    按特定映射,返回对应的大写字母。

    func (SpecialCase) ToTitle

    func (special SpecialCase) ToTitle(r rune) rune

    按特定映射,返回对应的标题字母。

    func Is

    func Is(rangeTab *RangeTable, r rune) bool

    函数报告r是否在rangeTab指定的字符范围内。

    func In

    func In(r rune, ranges ...*RangeTable) bool

    函数报告r是否是给出的ranges字母集中的某个成员。

    func IsOneOf

    func IsOneOf(ranges []*RangeTable, r rune) bool

    函数报告r是否是ranges某个成员指定的字符范围内。本函数的功能类似In,应优先使用In函数。

    func IsSpace

    func IsSpace(r rune) bool

    IsSpace报告一个字符是否是空白字符。在Latin-1字符空间中,空白字符为:

    '\t', '\n', '\v', '\f', '\r', ' ', U+0085 (NEL), U+00A0 (NBSP).
    

    其它的空白字符请参见策略Z和属性Pattern_White_Space。

    Example
    fmt.Println(unicode.IsSpace(' ')) // true
    fmt.Println(unicode.IsSpace('\n')) // true
    fmt.Println(unicode.IsSpace('\t')) // true
    

    func IsDigit

    func IsDigit(r rune) bool

    IsDigit报告一个r字符是否是十进制数字字符。

    Example
    fmt.Println(unicode.IsDigit('0')) // true
    fmt.Println(unicode.IsDigit('9')) // true
    fmt.Println(unicode.IsDigit('A')) // false
    fmt.Println(unicode.IsDigit('f')) // false
    

    func IsNumber

    func IsNumber(r rune) bool

    IsNumber报告一个字符是否是数字字符,参见策略N。

    Example
    fmt.Println(unicode.IsNumber('0')) // true
    fmt.Println(unicode.IsNumber('9')) // true
    fmt.Println(unicode.IsNumber('A')) // false
    fmt.Println(unicode.IsNumber('f')) // false
    

    func IsLetter

    func IsLetter(r rune) bool

    IsLetter报告一个字符是否是字母,参见策略L。

    Example
    fmt.Println(unicode.IsLetter('0')) // false
    fmt.Println(unicode.IsLetter('9')) // false
    fmt.Println(unicode.IsLetter('A')) // true
    fmt.Println(unicode.IsLetter('z')) // true
    fmt.Println(unicode.IsLetter('😘')) // false
    

    func IsGraphic

    func IsGraphic(r rune) bool

    报告一个字符是否是unicode图形。包括字母、标记、数字、符号、标点、空白,参见L、M、N、P、S、Zs。

    Example
    fmt.Println(unicode.IsGraphic('0')) // true
    fmt.Println(unicode.IsGraphic('9')) // true
    fmt.Println(unicode.IsGraphic('A')) // true
    fmt.Println(unicode.IsGraphic('z')) // true
    fmt.Println(unicode.IsGraphic('😘')) // true
    fmt.Println(unicode.IsGraphic('尶')) // true
    

    func IsMark

    func IsMark(r rune) bool

    IsMark报告一个字符是否是标记字符,参见策略M。

    func IsPrint

    func IsPrint(r rune) bool

    IsPrint一个字符是否是go的可打印字符。本函数基本和IsGraphic一致,只是ASCII空白字符U+0020会返回假。

    func IsControl

    func IsControl(r rune) bool

    IsControl报告一个字符是否是控制字符,主要是策略C的字符和一些其他的字符如代理字符。

    func IsPunct

    func IsPunct(r rune) bool

    IsPunct报告一个字符是否是unicode标点字符,参见策略P。

    func IsSymbol

    func IsSymbol(r rune) bool

    IsPunct报告一个字符是否是unicode符号字符。

    func IsLower

    func IsLower(r rune) bool

    返回字符是否是小写字母。

    func IsUpper

    func IsUpper(r rune) bool

    返回字符是否是大写字母。

    func IsTitle

    func IsTitle(r rune) bool

    返回字符是否是标题字母。

    func To

    func To(_case int, r rune) rune

    返回_case指定的对应类型的字母:UpperCase、LowerCase、TitleCase。

    func ToLower

    func ToLower(r rune) rune

    返回对应的小写字母。

    func ToUpper

    func ToUpper(r rune) rune

    返回对应的大写字母。

    func ToTitle

    func ToTitle(r rune) rune

    返回对应的标题字母。

    func SimpleFold

    func SimpleFold(r rune) rune

    SimpleFold函数迭代在unicode标准字符映射中互相对应的unicode码值。在与r对应的码值中(包括r自身),会返回最小的那个大于r的字符(如果有);否则返回映射中最小的字符。

    举例:

    SimpleFold('A') = 'a'
    SimpleFold('a') = 'A'
    SimpleFold('K') = 'k'
    SimpleFold('k') = '\u212A' (Kelvin symbol, K)
    SimpleFold('\u212A') = 'K'
    SimpleFold('1') = '1'
    

    Bugs

    没有全字符(包含多个rune的字符)折叠的机制。