package camomile

  1. Overview
  2. Docs
package camomile
Legend:
Library
Module
Module type
Parameter
Class
Class type

Character Information

type general_category_type = [
  1. | `Lu
    (*

    Letter, Uppercase

    *)
  2. | `Ll
    (*

    Letter, Lowercase

    *)
  3. | `Lt
    (*

    Letter, Titlecase

    *)
  4. | `Mn
    (*

    Mark, Non-Spacing

    *)
  5. | `Mc
    (*

    Mark, Spacing Combining

    *)
  6. | `Me
    (*

    Mark, Enclosing

    *)
  7. | `Nd
    (*

    Number, Decimal Digit

    *)
  8. | `Nl
    (*

    Number, Letter

    *)
  9. | `No
    (*

    Number, Other

    *)
  10. | `Zs
    (*

    Separator, Space

    *)
  11. | `Zl
    (*

    Separator, Line

    *)
  12. | `Zp
    (*

    Separator, Paragraph

    *)
  13. | `Cc
    (*

    Other, Control

    *)
  14. | `Cf
    (*

    Other, Format

    *)
  15. | `Cs
    (*

    Other, Surrogate

    *)
  16. | `Co
    (*

    Other, Private Use

    *)
  17. | `Cn
    (*

    Other, Not Assigned

    *)
  18. | `Lm
    (*

    Letter, Modifier

    *)
  19. | `Lo
    (*

    Letter, Other

    *)
  20. | `Pc
    (*

    Punctuation, Connector

    *)
  21. | `Pd
    (*

    Punctuation, Dash

    *)
  22. | `Ps
    (*

    Punctuation, Open

    *)
  23. | `Pe
    (*

    Punctuation, Close

    *)
  24. | `Pi
    (*

    Punctuation, Initial quote

    *)
  25. | `Pf
    (*

    Punctuation, Final quote

    *)
  26. | `Po
    (*

    Punctuation, Other

    *)
  27. | `Sm
    (*

    Symbol, Math

    *)
  28. | `Sc
    (*

    Symbol, Currency

    *)
  29. | `Sk
    (*

    Symbol, Modifier

    *)
  30. | `So
    (*

    Symbol, Other

    *)
]

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 = [
  1. | `Math
    (*

    Derived Core Properties

    *)
  2. | `Alphabetic
  3. | `Lowercase
  4. | `Uppercase
  5. | `ID_Start
  6. | `ID_Continue
  7. | `XID_Start
  8. | `XID_Continue
  9. | `Default_Ignorable_Code_Point
  10. | `Grapheme_Extend
  11. | `Grapheme_Base
  12. | `Bidi_Control
    (*

    Extended Properties

    *)
  13. | `White_Space
  14. | `Hyphen
  15. | `Quotation_Mark
  16. | `Terminal_Punctuation
  17. | `Other_Math
  18. | `Hex_Digit
  19. | `Ascii_Hex_Digit
  20. | `Other_Alphabetic
  21. | `Ideographic
  22. | `Diacritic
  23. | `Extender
  24. | `Other_Lowercase
  25. | `Other_Uppercase
  26. | `Noncharacter_Code_Point
  27. | `Other_Grapheme_Extend
  28. | `IDS_Binary_Operator
  29. | `IDS_Trinary_Operator
  30. | `Radical
  31. | `Unified_Ideograph
  32. | `Other_default_Ignorable_Code_Point
  33. | `Deprecated
  34. | `Soft_Dotted
  35. | `Logical_Order_Exception
]

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 = [
  1. | `Common
  2. | `Inherited
  3. | `Latin
  4. | `Greek
  5. | `Cyrillic
  6. | `Armenian
  7. | `Hebrew
  8. | `Arabic
  9. | `Syriac
  10. | `Thaana
  11. | `Devanagari
  12. | `Bengali
  13. | `Gurmukhi
  14. | `Gujarati
  15. | `Oriya
  16. | `Tamil
  17. | `Telugu
  18. | `Kannada
  19. | `Malayalam
  20. | `Sinhala
  21. | `Thai
  22. | `Lao
  23. | `Tibetan
  24. | `Myanmar
  25. | `Georgian
  26. | `Hangul
  27. | `Ethiopic
  28. | `Cherokee
  29. | `Canadian_Aboriginal
  30. | `Ogham
  31. | `Runic
  32. | `Khmer
  33. | `Mongolian
  34. | `Hiragana
  35. | `Katakana
  36. | `Bopomofo
  37. | `Han
  38. | `Yi
  39. | `Old_Italic
  40. | `Gothic
  41. | `Deseret
  42. | `Tagalog
  43. | `Hanunoo
  44. | `Buhid
  45. | `Tagbanwa
]

Type for script type

val script : UChar.t -> script_type
val load_script_map : unit -> script_type UMap.t
type version_type = [
  1. | `Nc
    (*

    undefined code point

    *)
  2. | `v1_0
  3. | `v1_1
  4. | `v2_0
  5. | `v2_1
  6. | `v3_0
  7. | `v3_1
  8. | `v3_2
]

age

val age : UChar.t -> version_type

age c unicode version in wich c was introduced

val older : version_type -> version_type -> bool

older v1 v2 is true if v1 is older ( or the same version ) than v2. Everithing is older than `Nc

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 = [
  1. | `Locale of string
  2. | `FinalSigma
  3. | `AfterSoftDotted
  4. | `MoreAbove
  5. | `BeforeDot
  6. | `Not of casemap_condition
]
type special_casing_property = {
  1. lower : UChar.t list;
  2. title : UChar.t list;
  3. upper : UChar.t list;
  4. 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 = [
  1. | `Canon
  2. | `Font
  3. | `NoBreak
  4. | `Initial
  5. | `Medial
  6. | `Final
  7. | `Isolated
  8. | `Circle
  9. | `Super
  10. | `Sub
  11. | `Vertical
  12. | `Wide
  13. | `Narrow
  14. | `Small
  15. | `Square
  16. | `Fraction
  17. | `Compat
]

Types of decomposition.

type decomposition_info = [
  1. | `Canonform
    (*

    Already in the canonical form

    *)
  2. | `HangulSyllable
    (*

    Hangul is treated algotighmically.

    *)
  3. | `Composite of decomposition_type * UChar.t list
    (*

    `Composite (dtype, text) means the given character is decomposed into text by dtype decomposition.

    *)
]
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

OCaml

Innovation. Community. Security.

GitHub Discord Twitter Peertube RSS
About
Changelog Releases Industrial Users Academic Users Why OCaml
Ecosystem
Packages Community Events OCaml Planet Jobs
Resources
Install OCaml Get Started Platform Tools Language Manual Standard Library API Books Exercises Papers OCaml Playground Logo
Policies
Carbon Footprint Governance Privacy Code of Conduct