package containers

  1. Overview
  2. Docs

Basic String Utils

type 'a iter = ('a -> unit) -> unit

Fast internal iterator.

  • since 2.8
type 'a gen = unit -> 'a option
include module type of struct include Stdlib.String end
type t = string
val make : int -> char -> string
val init : int -> (int -> char) -> string
val empty : string
val of_bytes : bytes -> string
val to_bytes : string -> bytes
val get : string -> int -> char
val concat : string -> string list -> string
val cat : string -> string -> string
val equal : t -> t -> bool
val starts_with : prefix:string -> string -> bool
val ends_with : suffix:string -> string -> bool
val contains_from : string -> int -> char -> bool
val rcontains_from : string -> int -> char -> bool
val contains : string -> char -> bool
val sub : string -> int -> int -> string
val map : (char -> char) -> string -> string
val mapi : (int -> char -> char) -> string -> string
val fold_left : ('a -> char -> 'a) -> 'a -> string -> 'a
val fold_right : (char -> 'a -> 'a) -> string -> 'a -> 'a
val trim : string -> string
val escaped : string -> string
val uppercase_ascii : string -> string
val lowercase_ascii : string -> string
val capitalize_ascii : string -> string
val uncapitalize_ascii : string -> string
val iteri : (int -> char -> unit) -> string -> unit
val index_from : string -> int -> char -> int
val index_from_opt : string -> int -> char -> int option
val rindex_from : string -> int -> char -> int
val rindex_from_opt : string -> int -> char -> int option
val index : string -> char -> int
val index_opt : string -> char -> int option
val rindex : string -> char -> int
val rindex_opt : string -> char -> int option
val to_seqi : t -> (int * char) Stdlib.Seq.t
val get_utf_8_uchar : t -> int -> Stdlib.Uchar.utf_decode
val is_valid_utf_8 : t -> bool
val get_utf_16be_uchar : t -> int -> Stdlib.Uchar.utf_decode
val is_valid_utf_16be : t -> bool
val get_utf_16le_uchar : t -> int -> Stdlib.Uchar.utf_decode
val is_valid_utf_16le : t -> bool
val create : int -> bytes
  • deprecated Use Bytes.create/BytesLabels.create instead.
val copy : string -> string
  • deprecated Strings now immutable: no need to copy
val fill : bytes -> int -> int -> char -> unit
  • deprecated Use Bytes.fill/BytesLabels.fill instead.
val uppercase : string -> string
  • deprecated Use String.uppercase_ascii/StringLabels.uppercase_ascii instead.
val lowercase : string -> string
  • deprecated Use String.lowercase_ascii/StringLabels.lowercase_ascii instead.
val capitalize : string -> string
  • deprecated Use String.capitalize_ascii/StringLabels.capitalize_ascii instead.
val uncapitalize : string -> string
  • deprecated Use String.uncapitalize_ascii/StringLabels.uncapitalize_ascii instead.
val get_uint8 : string -> int -> int
val get_int8 : string -> int -> int
val get_uint16_ne : string -> int -> int
val get_uint16_be : string -> int -> int
val get_uint16_le : string -> int -> int
val get_int16_ne : string -> int -> int
val get_int16_be : string -> int -> int
val get_int16_le : string -> int -> int
val get_int32_ne : string -> int -> int32
val get_int32_be : string -> int -> int32
val get_int32_le : string -> int -> int32
val get_int64_ne : string -> int -> int64
val get_int64_be : string -> int -> int64
val get_int64_le : string -> int -> int64
val unsafe_get : string -> int -> char
val unsafe_set : bytes -> int -> char -> unit
  • deprecated
val unsafe_blit : string -> int -> bytes -> int -> int -> unit
val unsafe_fill : bytes -> int -> int -> char -> unit
  • deprecated
val length : t -> int

length s returns the length (number of characters) of the given string s.

val blit : t -> int -> Stdlib.Bytes.t -> int -> int -> unit

blit src src_pos dst dst_pos len copies len characters from string src starting at character indice src_pos, to the Bytes sequence dst starting at character indice dst_pos. Like String.blit. Compatible with the -safe-string option.

  • raises Invalid_argument

    if indices are not valid.

val fold : ('a -> char -> 'a) -> 'a -> t -> 'a

fold f init s folds on chars by increasing index. Computes f(… (f (f init s.[0]) s.[1]) …) s.[n-1].

  • since 0.7
val foldi : ('a -> int -> char -> 'a) -> 'a -> t -> 'a

foldi f init s is just like fold, but it also passes in the index of each chars as second argument to the folded function f.

  • since 3.3

Conversions

val to_gen : t -> char gen

to_gen s returns the gen of characters contained in the string s.

val to_iter : t -> char iter

to_iter s returns the iter of characters contained in the string s.

  • since 2.8
val to_seq : t -> char Stdlib.Seq.t

to_seq s returns the Seq.t of characters contained in the string s. Renamed from to std_seq since 3.0.

  • since 3.0
val to_list : t -> char list

to_list s returns the list of characters contained in the string s.

val pp_buf : Stdlib.Buffer.t -> t -> unit

pp_buf buf s prints s to the buffer buf. Renamed from pp since 2.0.

val pp : Stdlib.Format.formatter -> t -> unit

pp f s prints the string s within quotes to the formatter f. Renamed from print since 2.0.

val compare : string -> string -> int

compare s1 s2 compares the strings s1 and s2 and returns an integer that indicates their relative position in the sort order.

val is_empty : string -> bool

is_empty s returns true iff s is empty (i.e. its length is 0).

  • since 1.5
val hash : string -> int

hash s returns the hash value of s.

val rev : string -> string

rev s returns the reverse of s.

  • since 0.17
val pad : ?side:[ `Left | `Right ] -> ?c:char -> int -> string -> string

pad ~side ~c n s ensures that the string s is at least n bytes long, and pads it on the side with c if it's not the case.

  • parameter side

    determines where padding occurs (default: `Left).

  • parameter c

    the char used to pad (default: ' ').

  • since 0.17
val of_char : char -> string

of_char 'a' is "a".

  • since 0.19
val of_gen : char gen -> string

of_gen gen converts a gen of characters to a string.

val of_iter : char iter -> string

of_iter iter converts an iter of characters to a string.

  • since 2.8
val of_seq : char Stdlib.Seq.t -> string

of_seq seq converts a seq of characters to a string. Renamed from of_std_seq since 3.0.

  • since 3.0
val of_list : char list -> string

of_list lc converts a list of characters lc to a string.

val of_array : char array -> string

of_array ac converts an array of characters ac to a string.

val to_array : string -> char array

to_array s returns the array of characters contained in the string s.

val find : ?start:int -> sub:string -> string -> int

find ~start ~sub s returns the starting index of the first occurrence of sub within s or -1.

  • parameter start

    starting position in s.

val find_all : ?start:int -> sub:string -> string -> int gen

find_all ~start ~sub s finds all occurrences of sub in s, even overlapping instances and returns them in a generator gen.

  • parameter start

    starting position in s.

  • since 0.17
val find_all_l : ?start:int -> sub:string -> string -> int list

find_all_l ~sub s finds all occurrences of sub in s and returns them in a list.

  • parameter start

    starting position in s.

  • since 0.17
val mem : ?start:int -> sub:string -> string -> bool

mem ~start ~sub s is true iff sub is a substring of s.

  • since 0.12
val rfind : sub:string -> string -> int

rfind ~sub s finds sub in string s from the right, returns its first index or -1. Should only be used with very small sub.

  • since 0.12
val replace : ?which:[ `Left | `Right | `All ] -> sub:string -> by:string -> string -> string

replace ~which ~sub ~by s replaces some occurrences of sub by by in s.

  • parameter which

    decides whether the occurrences to replace are:

    • `Left first occurrence from the left (beginning).
    • `Right first occurrence from the right (end).
    • `All all occurrences (default).
  • raises Invalid_argument

    if sub = "".

  • since 0.14
val is_sub : sub:string -> int -> string -> int -> sub_len:int -> bool

is_sub ~sub ~sub_pos s ~pos ~sub_len returns true iff the substring of sub starting at position sub_pos and of length sub_len is a substring of s starting at position pos.

val repeat : string -> int -> string

repeat s n creates a string by repeating the string s n times.

val prefix : pre:string -> string -> bool

prefix ~pre s returns true iff pre is a prefix of s.

val suffix : suf:string -> string -> bool

suffix ~suf s returns true iff suf is a suffix of s.

  • since 0.7
val chop_prefix : pre:string -> string -> string option

chop_prefix ~pre s removes pre from s if pre really is a prefix of s, returns None otherwise.

  • since 0.17
val chop_suffix : suf:string -> string -> string option

chop_suffix ~suf s removes suf from s if suf really is a suffix of s, returns None otherwise.

  • since 0.17
val take : int -> string -> string

take n s keeps only the n first chars of s.

  • since 0.17
val drop : int -> string -> string

drop n s removes the n first chars of s.

  • since 0.17
val take_drop : int -> string -> string * string

take_drop n s is take n s, drop n s.

  • since 0.17
val lines : string -> string list

lines s returns a list of the lines of s (splits along '\n').

  • since 0.10
val lines_gen : string -> string gen

lines_gen s returns the gen of the lines of s (splits along '\n').

  • since 0.10
val lines_iter : string -> string iter

lines_iter s returns the iter of the lines of s (splits along '\n').

  • since 3.2
val lines_seq : string -> string Stdlib.Seq.t

lines_seq s returns the Seq.t of the lines of s (splits along '\n').

  • since 3.2
val concat_gen : sep:string -> string gen -> string

concat_gen ~sep gen concatenates all strings of gen, separated with sep.

  • since 0.10
val concat_seq : sep:string -> string Stdlib.Seq.t -> string

concat_seq ~sep seq concatenates all strings of seq, separated with sep.

  • since 3.2
val concat_iter : sep:string -> string iter -> string

concat_iter ~sep iter concatenates all strings of iter, separated with sep.

  • since 3.2
val unlines : string list -> string

unlines ls concatenates all strings of ls, separated with '\n'.

  • since 0.10
val unlines_gen : string gen -> string

unlines_gen gen concatenates all strings of gen, separated with '\n'.

  • since 0.10
val unlines_iter : string iter -> string

unlines_iter iter concatenates all strings of iter, separated with '\n'.

  • since 3.2
val unlines_seq : string Stdlib.Seq.t -> string

unlines_seq seq concatenates all strings of seq, separated with '\n'.

  • since 3.2
val set : string -> int -> char -> string

set s i c creates a new string which is a copy of s, except for index i, which becomes c.

  • raises Invalid_argument

    if i is an invalid index.

  • since 0.12
val iter : (char -> unit) -> string -> unit

iter f s applies function f on each character of s. Alias to String.iter.

  • since 0.12
val filter_map : (char -> char option) -> string -> string

filter_map f s calls (f a0) (f a1) … (f an) where a0 … an are the characters of s. It returns the string of characters ci such as f ai = Some ci (when f returns None, the corresponding element of s is discarded).

  • since 0.17
val filter : (char -> bool) -> string -> string

filter f s discards characters of s not satisfying f.

  • since 0.17
val uniq : (char -> char -> bool) -> string -> string

uniq eq s remove consecutive duplicate characters in s.

  • since 3.4
val flat_map : ?sep:string -> (char -> string) -> string -> string

flat_map ~sep f s maps each chars of s to a string, then concatenates them all.

  • parameter sep

    optional separator between each generated string.

  • since 0.12
val for_all : (char -> bool) -> string -> bool

for_all f s is true iff all characters of s satisfy the predicate f.

  • since 0.12
val exists : (char -> bool) -> string -> bool

exists f s is true iff some character of s satisfy the predicate f.

  • since 0.12
val drop_while : (char -> bool) -> t -> t

drop_while f s discards any characters of s starting from the left, up to the first character c not satisfying f c.

  • since 2.2
val rdrop_while : (char -> bool) -> t -> t

rdrop_while f s discards any characters of s starting from the right, up to the first character c not satisfying f c.

  • since 2.2
val ltrim : t -> t

ltrim s trims space on the left (see String.trim for more details).

  • since 1.2
val rtrim : t -> t

rtrim s trims space on the right (see String.trim for more details).

  • since 1.2

Operations on 2 strings

val map2 : (char -> char -> char) -> string -> string -> string

map2 f s1 s2 maps pairs of chars.

  • raises Invalid_argument

    if the strings have not the same length.

  • since 0.12
val iter2 : (char -> char -> unit) -> string -> string -> unit

iter2 f s1 s2 iterates on pairs of chars.

  • raises Invalid_argument

    if the strings have not the same length.

  • since 0.12
val iteri2 : (int -> char -> char -> unit) -> string -> string -> unit

iteri2 f s1 s2 iterates on pairs of chars with their index.

  • raises Invalid_argument

    if the strings have not the same length.

  • since 0.12
val fold2 : ('a -> char -> char -> 'a) -> 'a -> string -> string -> 'a

fold2 f init s1 s2 folds on pairs of chars.

  • raises Invalid_argument

    if the strings have not the same length.

  • since 0.12
val for_all2 : (char -> char -> bool) -> string -> string -> bool

for_all2 f s1 s2 returns true iff all pairs of chars satisfy the predicate f.

  • raises Invalid_argument

    if the strings have not the same length.

  • since 0.12
val exists2 : (char -> char -> bool) -> string -> string -> bool

exists2 f s1 s2 returns true iff a pair of chars satisfy the predicate f.

  • raises Invalid_argument

    if the strings have not the same length.

  • since 0.12

Ascii functions

Those functions are deprecated in String since 4.03, so we provide a stable alias for them even in older versions.

val equal_caseless : string -> string -> bool

equal_caseless s1 s2 compares s1 and s2 without respect to ascii lowercase.

  • since 1.2

Finding

A relatively efficient algorithm for finding sub-strings.

  • since 1.0
module Find : sig ... end

Splitting

module Split : sig ... end
val split_on_char : char -> string -> string list

split_on_char by s splits the string s along the given char by.

  • since 1.2
val split : by:string -> string -> string list

split ~by s splits the string s along the given string by. Alias to Split.list_cpy.

  • since 1.2

Utils

val compare_versions : string -> string -> int

compare_versions s1 s2 compares version strings s1 and s2, considering that numbers are above text.

  • since 0.13
val compare_natural : string -> string -> int

compare_natural s1 s2 is the Natural Sort Order, comparing chunks of digits as natural numbers. https://en.wikipedia.org/wiki/Natural_sort_order

  • since 1.3
val edit_distance : ?cutoff:int -> string -> string -> int

edit_distance ~cutoff s1 s2 is the edition distance between the two strings s1 and s2. This satisfies the classical distance axioms: it is always positive, symmetric, and satisfies the formula distance s1 s2 + distance s2 s3 >= distance s1 s3.

  • parameter cutoff

    if provided, it's a cap on the number of iterations. (since 3.0). This is useful if you just want to check whether the edit distance is less or equal than 2 without (use edit_distance s1 s2 ~cutoff:3 <= 2). note that contrary to what was previously documented here, the result can still be higher than cutoff if it's reached in <cutoff iterations. However if the result is < cutoff then it is accurate.

Infix operators

  • since 3.0
module Infix : sig ... end
include module type of Infix
val (=) : t -> t -> bool
  • since 3.0
val (<>) : t -> t -> bool
  • since 3.0
val (<) : t -> t -> bool
  • since 3.0
val (<=) : t -> t -> bool
  • since 3.0
val (>=) : t -> t -> bool
  • since 3.0
val (>) : t -> t -> bool
  • since 3.0
OCaml

Innovation. Community. Security.