mecab 0.0.0 (latest) · OCaml Package

Parameters

module S : StringIntf

Signature

Construction

val make : int -> CamomileLibraryDefault.Camomile.UChar.t -> S.t

val init : f:(int -> CamomileLibraryDefault.Camomile.UChar.t) -> int -> S.t

val of_ascii_string : string -> S.t

val to_ascii_string : S.t -> string

Iteration

val foldi : 
  f:(S.index -> 'a -> CamomileLibraryDefault.Camomile.UChar.t -> 'a) ->
  init:'a ->
  S.t ->
  'a

val fold : 
  f:('a -> CamomileLibraryDefault.Camomile.UChar.t -> 'a) ->
  init:'a ->
  S.t ->
  'a

val iteri : 
  f:(S.index -> CamomileLibraryDefault.Camomile.UChar.t -> unit) ->
  S.t ->
  unit

val iter : f:(CamomileLibraryDefault.Camomile.UChar.t -> unit) -> S.t -> unit

val mapi : 
  f:
    (S.index ->
      CamomileLibraryDefault.Camomile.UChar.t ->
      CamomileLibraryDefault.Camomile.UChar.t) ->
  S.t ->
  S.t

val map : 
  f:
    (CamomileLibraryDefault.Camomile.UChar.t ->
      CamomileLibraryDefault.Camomile.UChar.t) ->
  S.t ->
  S.t

val filter_mapi : 
  f:
    (S.index ->
      CamomileLibraryDefault.Camomile.UChar.t ->
      CamomileLibraryDefault.Camomile.UChar.t option) ->
  S.t ->
  S.t

val filter_map : 
  f:
    (CamomileLibraryDefault.Camomile.UChar.t ->
      CamomileLibraryDefault.Camomile.UChar.t option) ->
  S.t ->
  S.t

val concat_map : 
  f:(CamomileLibraryDefault.Camomile.UChar.t -> S.t) ->
  S.t ->
  S.t

Conversion

val to_list_map : 
  f:(CamomileLibraryDefault.Camomile.UChar.t -> 'a) ->
  S.t ->
  'a list

val to_list : S.t -> CamomileLibraryDefault.Camomile.UChar.t list

val of_list_map : 
  f:('a -> CamomileLibraryDefault.Camomile.UChar.t) ->
  'a list ->
  S.t

val of_list : CamomileLibraryDefault.Camomile.UChar.t list -> S.t

val trim : 
  ?drop:(CamomileLibraryDefault.Camomile.UChar.uchar -> bool) ->
  S.t ->
  S.t

val uppercase_ascii : S.t -> S.t

uppercase_ascii str replaces all occurrence of ASCII lowercase alphabets in string str into uppercase alphabets.

val lowercase_ascii : S.t -> S.t

lowercase_ascii str replaces all occurrence of ASCII uppercase alphabets in string str with lowercase alphabets.

val latinize_number_form : S.t -> S.t

latinize_number_form str replaces all occurrence of non-ASCII number forms [U+2150-U+218B] in string str with ASCII characters.

val latinize_enclosed_alpha : S.t -> S.t

latinize_enclosed_alpha str replaces all occurrence of non-ASCII enclosed alphabets [U+2460-U+24FF] in string str with ASCII characters.

val latinize_blank : S.t -> S.t

latinize_blank str replaces all occurrence of blank-like characters (that satisfy Char.is_blank) with ASCII spaces U+0020.

val halve_ascii : S.t -> S.t

halve_ascii str replaces all occurrence of full-width ASCII characters (that satisfy Char.is_wide_ascii) with corresponding ASCII characters.

val widen_kana : S.t -> S.t

widen_kana str converts all occurrence of half-width katakanas in string str into full-width katakanas.

val neologd_normalize : S.t -> S.t

Neologd-style normalization for Japanese texts.

see https://github.com/neologd/mecab-ipadic-neologd

see https://github.com/neologd/mecab-ipadic-neologd/wiki/Regexp.ja

package mecab

Parameters

Signature

Construction

Iteration

Conversion