Functor UCharInfo.Make

module Make: functor (Config : ConfigInt.Type) -> Type

Parameters:

Config : ConfigInt.Type

Character Information

type general_category_type = [ `Cc
       | `Cf
       | `Cn
       | `Co
       | `Cs
       | `Ll
       | `Lm
       | `Lo
       | `Lt
       | `Lu
       | `Mc
       | `Me
       | `Mn
       | `Nd
       | `Nl
       | `No
       | `Pc
       | `Pd
       | `Pe
       | `Pf
       | `Pi
       | `Po
       | `Ps
       | `Sc
       | `Sk
       | `Sm
       | `So
       | `Zl
       | `Zp
       | `Zs ]

Type of Unicode general character categories. Each variant specifies

`Lu : Letter, Uppercase
`Ll : Letter, Lowercase
`Lt : Letter, Titlecase
`Mn : Mark, Non-Spacing
`Mc : Mark, Spacing Combining
`Me : Mark, Enclosing
`Nd : Number, Decimal Digit
`Nl : Number, Letter
`No : Number, Other
`Zs : Separator, Space
`Zl : Separator, Line
`Zp : Separator, Paragraph
`Cc : Other, Control
`Cf : Other, Format
`Cs : Other, Surrogate
`Co : Other, Private Use
`Cn : Other, Not Assigned
`Lm : Letter, Modifier
`Lo : Letter, Other
`Pc : Punctuation, Connector
`Pd : Punctuation, Dash
`Ps : Punctuation, Open
`Pe : Punctuation, Close
`Pi : Punctuation, Initial
`Pf : Punctuation, Final
`Po : Punctuation, Other
`Sm : Symbol, Math
`Sc : Symbol, Currency
`Sk : Symbol, Modifier
`So : Symbol, Other

val general_category : UChar.t -> general_category_type

val load_general_category_map : unit -> general_category_type UMap.t

type character_property_type = [ `Alphabetic
       | `Ascii_Hex_Digit
       | `Bidi_Control
       | `Default_Ignorable_Code_Point
       | `Deprecated
       | `Diacritic
       | `Extender
       | `Grapheme_Base
       | `Grapheme_Extend
       | `Grapheme_Link
       | `Hex_Digit
       | `Hyphen
       | `IDS_Binary_Operator
       | `IDS_Trinary_Operator
       | `ID_Continue
       | `ID_Start
       | `Ideographic
       | `Logical_Order_Exception
       | `Lowercase
       | `Math
       | `Noncharacter_Code_Point
       | `Other_Alphabetic
       | `Other_Grapheme_Extend
       | `Other_Lowercase
       | `Other_Math
       | `Other_Uppercase
       | `Other_default_Ignorable_Code_Point
       | `Quotation_Mark
       | `Radical
       | `Soft_Dotted
       | `Terminal_Punctuation
       | `Unified_Ideograph
       | `Uppercase
       | `White_Space
       | `XID_Continue
       | `XID_Start ]

Type of character properties

val load_property_tbl : character_property_type -> UCharTbl.Bool.t

Load the table for the given character type.

val load_property_tbl_by_name : string -> UCharTbl.Bool.t

Load the table for the given name of the character type. The name can be obtained by removing ` from its name of the polymorphic variant tag.

val load_property_set : character_property_type -> USet.t

Load the set of characters of the given character type.

val load_property_set_by_name : string -> USet.t

Load the set of characters of the given name of the character type. The name can be obtained by removing ` from its name of the polymorphic variant tag.

type script_type = [ `Arabic
       | `Armenian
       | `Bengali
       | `Bopomofo
       | `Buhid
       | `Canadian_Aboriginal
       | `Cherokee
       | `Common
       | `Cyrillic
       | `Deseret
       | `Devanagari
       | `Ethiopic
       | `Georgian
       | `Gothic
       | `Greek
       | `Gujarati
       | `Gurmukhi
       | `Han
       | `Hangul
       | `Hanunoo
       | `Hebrew
       | `Hiragana
       | `Inherited
       | `Kannada
       | `Katakana
       | `Khmer
       | `Lao
       | `Latin
       | `Malayalam
       | `Mongolian
       | `Myanmar
       | `Ogham
       | `Old_Italic
       | `Oriya
       | `Runic
       | `Sinhala
       | `Syriac
       | `Tagalog
       | `Tagbanwa
       | `Tamil
       | `Telugu
       | `Thaana
       | `Thai
       | `Tibetan
       | `Yi ]

Type for script type

val script : UChar.t -> script_type

val load_script_map : unit -> script_type UMap.t

casing

val load_to_lower1_tbl : unit -> UChar.t UCharTbl.t

val load_to_upper1_tbl : unit -> UChar.t UCharTbl.t

val load_to_title1_tbl : unit -> UChar.t UCharTbl.t

type casemap_condition = [ `AfterSoftDotted
       | `BeforeDot
       | `FinalSigma
       | `Locale of string
       | `MoreAbove
       | `Not of casemap_condition ]

type special_casing_property = {

	`lower : UChar.t list;`
	`title : UChar.t list;`
	`upper : UChar.t list;`
	`condition : casemap_condition list;`

}

val load_conditional_casing_tbl : unit -> special_casing_property list UCharTbl.t

val load_casefolding_tbl : unit -> UChar.t list UCharTbl.t

val combined_class : UChar.t -> int

Combined class A combined class is an integer of 0 -- 255, showing how this character interacts to other combined characters.

Decomposition

type decomposition_type = [ `Canon
       | `Circle
       | `Compat
       | `Final
       | `Font
       | `Fraction
       | `Initial
       | `Isolated
       | `Medial
       | `Narrow
       | `NoBreak
       | `Small
       | `Square
       | `Sub
       | `Super
       | `Vertical
       | `Wide ]

Types of decomposition.

type decomposition_info = [ `Canonform
       | `Composite of decomposition_type * UChar.t list
       | `HangulSyllable ]

val load_decomposition_tbl : unit -> decomposition_info UCharTbl.t

Canonical Composition

val load_composition_tbl : unit -> (UChar.t * UChar.t) list UCharTbl.t

The return value [(u_1, u'_1); ... (u_n, u'_1)] means for the given character u, u u_i forms the canonical composition u'_i. If u is a Hangul jamo, composition returns [].

val load_composition_exclusion_tbl : unit -> UCharTbl.Bool.t

Whether the given composed character is used in NFC or NFKC