std.internal.unicode_tables

License

Boost License 1.0.

Authors

Dmitry Olshansky
struct blocks FCE hangul SCE scripts TrieEntry UnicodeProperty uniProps
fn fullCaseTable isControlGen isFormatGen isHangL isHangT isHangV isSpaceGen isWhiteGen simpleCaseTable

Types 8

structSCE

Simple Case Entry, wrapper around uint to extract bit fields from simpleCaseTable()

Fields
uint x
Methods
int ch() const
int n() const
int size() const
Constructors
this(uint x)
this(uint ch, ubyte n, ubyte size)
structFCE

Bit backed FullCaseEntry

Fields
ulong x
Methods
dchar[3] seq() const
ubyte n() const
ubyte size() const
ubyte entry_len() const
Constructors
this(ulong x)
this(dchar[3] seq, ubyte n, ubyte size, ubyte entry_len)
structUnicodeProperty
Fields
string name
ubyte[] compressed
structTrieEntry(T...)
Fields
immutable(size_t)[] offsets
immutable(size_t)[] sizes
immutable(size_t)[] data
structuniProps
Fields
_T ID_Start
_T Cs
_T Default_Ignorable_Code_Point
_T Pd
_T Unified_Ideograph
_T IDS_Binary_Operator
_T Sm
_T Pi
_T Other_Grapheme_Extend
_T Grapheme_Extend
_T Other_ID_Start
_T Pattern_Syntax
_T Modifier_Combining_Mark
_T Lu
_T Case_Ignorable
_T Lo
_T Pc
_T Bidi_Control
_T Co
_T Variation_Selector
_T Soft_Dotted
_T Noncharacter_Code_Point
_T Logical_Order_Exception
_T Cased
_T ID_Compat_Math_Continue
_T Math
_T No
_T ID_Continue
_T Me
_T Ideographic
_T Cf
_T So
_T White_Space
_T Sentence_Terminal
_T Lt
_T Other_Lowercase
_T Other_Alphabetic
_T XID_Continue
_T Cc
_T Regional_Indicator
_T Sc
_T IDS_Unary_Operator
_T Pf
_T Pe
_T Other_Uppercase
_T Cn
_T Hyphen
_T Other_Math
_T Ps
_T Zs
_T Alphabetic
_T XID_Start
_T Grapheme_Link
_T Dash
_T Nl
_T IDS_Trinary_Operator
_T Terminal_Punctuation
_T Nd
_T ID_Compat_Math_Start
_T Prepended_Concatenation_Mark
_T ASCII_Hex_Digit
_T Mc
_T Radical
_T Quotation_Mark
_T Other_Default_Ignorable_Code_Point
_T Join_Control
_T Grapheme_Base
_T Uppercase
_T Zl
_T Hex_Digit
_T Zp
_T Pattern_White_Space
_T Diacritic
_T Lowercase
_T Ll
_T Extender
_T Lm
_T Mn
_T Sk
_T Po
_T Deprecated
_T Other_ID_Continue
_U[] _tab
Methods
_U[] tab() @property pure
structblocks
Fields
_T CJK_Unified_Ideographs_Extension_G
_T Tai_Le
_T Coptic
_T Halfwidth_and_Fullwidth_Forms
_T Cyrillic
_T CJK_Radicals_Supplement
_T Thaana
_T Specials
_T Hangul_Jamo_Extended_B
_T Linear_B_Syllabary
_T Ogham
_T Arabic_Extended_C
_T Nabataean
_T Makasar
_T CJK_Unified_Ideographs_Extension_B
_T Siddham
_T Kana_Extended_A
_T Supplemental_Arrows_C
_T Kaktovik_Numerals
_T Combining_Diacritical_Marks
_T Vertical_Forms
_T Old_Sogdian
_T Old_South_Arabian
_T Cyrillic_Extended_C
_T Myanmar
_T Bassa_Vah
_T Tangut_Components_Supplement
_T Tai_Yo
_T Deseret
_T Phaistos_Disc
_T Common_Indic_Number_Forms
_T Unified_Canadian_Aboriginal_Syllabics_Extended
_T Kaithi
_T Medefaidrin
_T Arabic_Supplement
_T Yi_Radicals
_T Tai_Tham
_T Hiragana
_T Hangul_Compatibility_Jamo
_T Linear_B_Ideograms
_T Syriac_Supplement
_T Ahom
_T Beria_Erfe
_T Phonetic_Extensions
_T Nag_Mundari
_T Devanagari
_T Tibetan
_T Hanifi_Rohingya
_T Old_Uyghur
_T Enclosed_Ideographic_Supplement
_T Brahmi
_T Number_Forms
_T Mayan_Numerals
_T Ornamental_Dingbats
_T Todhri
_T Unified_Canadian_Aboriginal_Syllabics_Extended_A
_T Shorthand_Format_Controls
_T Greek_and_Coptic
_T Symbols_for_Legacy_Computing
_T CJK_Unified_Ideographs_Extension_I
_T Counting_Rod_Numerals
_T Ethiopic_Extended_B
_T Supplemental_Mathematical_Operators
_T Osage
_T Nushu
_T Chess_Symbols
_T Cuneiform
_T Takri
_T Enclosed_Alphanumeric_Supplement
_T Sutton_SignWriting
_T Miscellaneous_Technical
_T Old_Italic
_T Toto
_T Hanunoo
_T Lisu
_T Limbu
_T Saurashtra
_T Elbasan
_T Variation_Selectors_Supplement
_T Psalter_Pahlavi
_T Palmyrene
_T Tagbanwa
_T Tulu_Tigalari
_T Combining_Diacritical_Marks_for_Symbols
_T Dingbats
_T Nyiakeng_Puachue_Hmong
_T Combining_Half_Marks
_T CJK_Unified_Ideographs_Extension_F
_T Playing_Cards
_T Miscellaneous_Symbols_Supplement
_T Malayalam
_T Indic_Siyaq_Numbers
_T Variation_Selectors
_T Thai
_T Supplemental_Arrows_B
_T Zanabazar_Square
_T Ideographic_Symbols_and_Punctuation
_T Symbols_and_Pictographs_Extended_A
_T High_Private_Use_Surrogates
_T Supplementary_Private_Use_Area_A
_T Modifier_Tone_Letters
_T Samaritan
_T Egyptian_Hieroglyph_Format_Controls
_T Latin_Extended_Additional
_T Coptic_Epact_Numbers
_T Small_Form_Variants
_T Balinese
_T Mandaic
_T Block_Elements
_T Supplemental_Symbols_and_Pictographs
_T Miscellaneous_Mathematical_Symbols_A
_T Tifinagh
_T Arabic_Extended_A
_T Cyrillic_Extended_A
_T Syriac
_T Latin_Extended_E
_T Caucasian_Albanian
_T Soyombo
_T Syloti_Nagri
_T NKo
_T Tai_Viet
_T Low_Surrogates
_T Elymaic
_T Hatran
_T Sundanese_Supplement
_T CJK_Unified_Ideographs_Extension_H
_T Chorasmian
_T Kana_Extended_B
_T Glagolitic
_T Devanagari_Extended_A
_T Hangul_Syllables
_T Osmanya
_T Enclosed_CJK_Letters_and_Months
_T Meetei_Mayek_Extensions
_T Hangul_Jamo
_T Mro
_T Currency_Symbols
_T Bopomofo_Extended
_T Chakma
_T Pau_Cin_Hau
_T Latin_Extended_G
_T CJK_Unified_Ideographs
_T Znamenny_Musical_Notation
_T New_Tai_Lue
_T Modi
_T Bamum_Supplement
_T Cypro_Minoan
_T Basic_Latin
_T Multani
_T Sunuwar
_T Alchemical_Symbols
_T Bopomofo
_T Adlam
_T Khitan_Small_Script
_T CJK_Unified_Ideographs_Extension_J
_T Old_Turkic
_T Lao
_T Cherokee_Supplement
_T CJK_Compatibility_Ideographs
_T Kirat_Rai
_T Latin_Extended_F
_T Myanmar_Extended_C
_T Lisu_Supplement
_T Latin_Extended_A
_T Spacing_Modifier_Letters
_T Gothic
_T Sinhala_Archaic_Numbers
_T Egyptian_Hieroglyphs
_T Sinhala
_T Rejang
_T Glagolitic_Supplement
_T Lepcha
_T Optical_Character_Recognition
_T Greek_Extended
_T Miscellaneous_Symbols_and_Pictographs
_T Emoticons
_T Ol_Onal
_T Tirhuta
_T Marchen
_T Geometric_Shapes_Extended
_T Arabic_Presentation_Forms_A
_T Cyrillic_Extended_D
_T Phoenician
_T Wancho
_T Meroitic_Hieroglyphs
_T Alphabetic_Presentation_Forms
_T Linear_A
_T Mahjong_Tiles
_T Gurmukhi
_T Byzantine_Musical_Symbols
_T Transport_and_Map_Symbols
_T Unified_Canadian_Aboriginal_Syllabics
_T Khojki
_T Khudawadi
_T Newa
_T Dogra
_T Ancient_Greek_Musical_Notation
_T Cypriot_Syllabary
_T Latin_1_Supplement
_T Hangul_Jamo_Extended_A
_T Imperial_Aramaic
_T Tamil_Supplement
_T Oriya
_T Tai_Xuan_Jing_Symbols
_T Enclosed_Alphanumerics
_T Meetei_Mayek
_T Tagalog
_T Sundanese
_T CJK_Compatibility_Ideographs_Supplement
_T Cuneiform_Numbers_and_Punctuation
_T Ethiopic_Extended
_T Domino_Tiles
_T Old_Permic
_T Supplementary_Private_Use_Area_B
_T Shavian
_T Anatolian_Hieroglyphs
_T Lycian
_T Inscriptional_Pahlavi
_T Ancient_Greek_Numbers
_T Miao
_T CJK_Unified_Ideographs_Extension_E
_T Pahawh_Hmong
_T Tangut
_T Bengali
_T CJK_Compatibility_Forms
_T Vithkuqi
_T Supplemental_Punctuation
_T Armenian
_T Arabic_Presentation_Forms_B
_T Tangut_Components
_T Sogdian
_T Ottoman_Siyaq_Numbers
_T Buhid
_T Myanmar_Extended_A
_T Manichaean
_T Garay
_T Miscellaneous_Mathematical_Symbols_B
_T Latin_Extended_D
_T Avestan
_T Small_Kana_Extension
_T Ethiopic_Supplement
_T Arabic
_T Kayah_Li
_T Javanese
_T Gurung_Khema
_T Sharada_Supplement
_T Lydian
_T Aegean_Numbers
_T Symbols_for_Legacy_Computing_Supplement
_T Braille_Patterns
_T Buginese
_T CJK_Symbols_and_Punctuation
_T Batak
_T Combining_Diacritical_Marks_Supplement
_T High_Surrogates
_T Vedic_Extensions
_T Nandinagari
_T Kanbun
_T Arrows
_T Devanagari_Extended
_T Inscriptional_Parthian
_T Cham
_T Box_Drawing
_T Ugaritic
_T Georgian
_T Tangut_Supplement
_T Kana_Supplement
_T Sharada
_T Tamil
_T Old_Persian
_T Geometric_Shapes
_T Cherokee
_T Superscripts_and_Subscripts
_T CJK_Strokes
_T Letterlike_Symbols
_T CJK_Unified_Ideographs_Extension_D
_T Egyptian_Hieroglyphs_Extended_A
_T Yijing_Hexagram_Symbols
_T Georgian_Extended
_T Khmer_Symbols
_T Sora_Sompeng
_T Private_Use_Area
_T Kharoshthi
_T Dives_Akuru
_T Ancient_Symbols
_T Sidetic
_T Katakana
_T Tolong_Siki
_T Ideographic_Description_Characters
_T Cyrillic_Extended_B
_T Meroitic_Cursive
_T Mende_Kikakui
_T Rumi_Numeral_Symbols
_T Combining_Diacritical_Marks_Extended
_T Telugu
_T Cyrillic_Supplement
_T Ethiopic
_T Old_North_Arabian
_T IPA_Extensions
_T Vai
_T Latin_Extended_C
_T Bamum
_T Control_Pictures
_T Mongolian
_T Warang_Citi
_T Katakana_Phonetic_Extensions
_T Mathematical_Operators
_T Early_Dynastic_Cuneiform
_T Ol_Chiki
_T Mahajani
_T Myanmar_Extended_B
_T Khmer
_T Grantha
_T Kannada
_T Phags_pa
_T Mathematical_Alphanumeric_Symbols
_T Kawi
_T Musical_Symbols
_T Yezidi
_T Kangxi_Radicals
_T Phonetic_Extensions_Supplement
_T CJK_Unified_Ideographs_Extension_A
_T Mongolian_Supplement
_T Bhaiksuki
_T Hebrew
_T Gujarati
_T Tangsa
_T General_Punctuation
_T CJK_Compatibility
_T Yi_Syllables
_T Carian
_T Miscellaneous_Symbols
_T CJK_Unified_Ideographs_Extension_C
_T Miscellaneous_Symbols_and_Arrows
_T Old_Hungarian
_T Latin_Extended_B
_T Runic
_T Tags
_T Supplemental_Arrows_A
_T Masaram_Gondi
_T Arabic_Extended_B
_T Ethiopic_Extended_A
_T Duployan
_T Georgian_Supplement
_T Gunjala_Gondi
_T Arabic_Mathematical_Alphabetic_Symbols
_U[] _tab
Methods
_U[] tab() @property pure
structscripts
Fields
_T Old_Hungarian
_T Coptic
_T Ol_Chiki
_T Cyrillic
_T Thaana
_T Inscriptional_Parthian
_T Nabataean
_T Ogham
_T Meroitic_Hieroglyphs
_T Makasar
_T Siddham
_T Gurung_Khema
_T Old_Persian
_T Imperial_Aramaic
_T Myanmar
_T Deseret
_T Kaithi
_T Medefaidrin
_T Kayah_Li
_T Hiragana
_T Ahom
_T Devanagari
_T Tibetan
_T Nko
_T Brahmi
_T Todhri
_T Osage
_T Nushu
_T Cuneiform
_T Takri
_T Toto
_T Latin
_T Hanunoo
_T Limbu
_T Saurashtra
_T Lisu
_T Egyptian_Hieroglyphs
_T Elbasan
_T Palmyrene
_T Tagbanwa
_T Old_Italic
_T Caucasian_Albanian
_T Malayalam
_T Inherited
_T Sora_Sompeng
_T Linear_B
_T Nyiakeng_Puachue_Hmong
_T Meroitic_Cursive
_T Thai
_T Mende_Kikakui
_T Old_Sogdian
_T Old_Turkic
_T Samaritan
_T Old_South_Arabian
_T Hanifi_Rohingya
_T Balinese
_T Mandaic
_T SignWriting
_T Tifinagh
_T Tai_Viet
_T Syriac
_T Soyombo
_T Elymaic
_T Ol_Onal
_T Hatran
_T Chorasmian
_T Glagolitic
_T Osmanya
_T Linear_A
_T Kirat_Rai
_T Mro
_T Chakma
_T Modi
_T Bassa_Vah
_T Tulu_Tigalari
_T Han
_T Multani
_T Sunuwar
_T Bopomofo
_T Adlam
_T Khitan_Small_Script
_T Lao
_T Psalter_Pahlavi
_T Anatolian_Hieroglyphs
_T Canadian_Aboriginal
_T Common
_T Gothic
_T Yi
_T Sinhala
_T Rejang
_T Lepcha
_T Tai_Tham
_T Dives_Akuru
_T Meetei_Mayek
_T Tirhuta
_T Marchen
_T Wancho
_T Phoenician
_T Gurmukhi
_T Khudawadi
_T Khojki
_T Newa
_T Dogra
_T Oriya
_T Tagalog
_T Sundanese
_T Beria_Erfe
_T Old_Permic
_T Shavian
_T Lycian
_T Miao
_T Tangut
_T Bengali
_T Inscriptional_Pahlavi
_T Vithkuqi
_T Armenian
_T New_Tai_Lue
_T Sogdian
_T Buhid
_T Manichaean
_T Tai_Yo
_T Garay
_T Greek
_T Braille
_T Avestan
_T Arabic
_T Javanese
_T Lydian
_T Pau_Cin_Hau
_T Cypro_Minoan
_T Buginese
_T Batak
_T Nandinagari
_T Cham
_T Gunjala_Gondi
_T Cypriot
_T Ugaritic
_T Georgian
_T Sharada
_T Tamil
_T Cherokee
_T Pahawh_Hmong
_T Syloti_Nagri
_T Kharoshthi
_T Zanabazar_Square
_T Sidetic
_T Katakana
_T Telugu
_T Ethiopic
_T Vai
_T Bamum
_T Hangul
_T Mongolian
_T Nag_Mundari
_T Old_Uyghur
_T Mahajani
_T Khmer
_T Grantha
_T Kannada
_T Kawi
_T Yezidi
_T Tolong_Siki
_T Old_North_Arabian
_T Tai_Le
_T Hebrew
_T Gujarati
_T Tangsa
_T Carian
_T Bhaiksuki
_T Masaram_Gondi
_T Runic
_T Duployan
_T Warang_Citi
_T Phags_Pa
_U[] _tab
Methods
_U[] tab() @property pure
structhangul
Fields
_T V
_T T
_T LVT
_T L
_T LV
_U[] _tab
Methods
_U[] tab() @property pure

Functions 9

fnSCE simpleCaseTable(size_t i)
fnFCE fullCaseTable(size_t index) @property nothrow @nogc @safe pure
fnbool isFormatGen(dchar ch) @safe pure nothrow @nogc
fnbool isControlGen(dchar ch) @safe pure nothrow @nogc
fnbool isSpaceGen(dchar ch) @safe pure nothrow @nogc
fnbool isWhiteGen(dchar ch) @safe pure nothrow @nogc
fnbool isHangL(dchar ch) @safe pure nothrow @nogc
fnbool isHangV(dchar ch) @safe pure nothrow @nogc
fnbool isHangT(dchar ch) @safe pure nothrow @nogc