Module More.String

Strings.

include module type of Stdlib.String
type t = string
val make : int -> char -> string
val init : int -> (int -> char) -> string
val length : string -> int
val get : string -> int -> char
val of_bytes : bytes -> string
val to_bytes : string -> bytes
val blit : string -> int -> bytes -> int -> int -> unit
val concat : string -> string list -> string
val cat : string -> string -> string
val equal : t -> t -> bool
val compare : t -> t -> int
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 split_on_char : char -> string -> string list
val map : (char -> char) -> string -> string
val mapi : (int -> char -> char) -> string -> string
val fold_left : ('acc -> char -> 'acc) -> 'acc -> string -> 'acc
val fold_right : (char -> 'acc -> 'acc) -> string -> 'acc -> 'acc
val for_all : (char -> bool) -> string -> bool
val exists : (char -> bool) -> string -> bool
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 iter : (char -> unit) -> string -> unit
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_seq : t -> char Stdlib.Seq.t
val to_seqi : t -> (int * char) Stdlib.Seq.t
val of_seq : char Stdlib.Seq.t -> 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 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 hash : t -> int
val seeded_hash : int -> t -> int
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_blit : string -> int -> bytes -> int -> int -> unit

Strings

val empty : string

empty is "".

val head : string -> char option

head s if Some s.[0] if s <> "" and None otherwise.

val of_char : char -> string

of_char c is c as a string.

Predicates

val is_empty : string -> bool

is_empty s is equal empty s.

val includes : affix:string -> string -> bool

includes ~affix s is true iff there exists an index j such that for all indices i of affix, sub.[i] = s.[j+ 1].

Finding indices

val find_index : ?start:int -> (char -> bool) -> string -> int option

find_index ~start sat is the index of the first character of s that satisfies sat before or at start (defaults to 0).

val rfind_index : ?start:int -> (char -> bool) -> string -> int option

rfind_index ~start sat is the index of the first character of s that satisfies sat before or at start (defaults to String.length s - 1).

Finding and replacing substrings

val find_sub : ?start:int -> sub:string -> string -> int option

find_sub ~start ~sub s is the start position (if any) of the first occurence of sub in s after or at position start (which includes index start if it exists, defaults to 0). Note if you need to search for sub multiple times in s use find_all_sub it is more efficient.

  • raises Invalid_argument

    if start is not a valid position of s.

val rfind_sub : ?start:int -> sub:string -> string -> int option

rfind_sub ~start ~sub s is the start position (if any) of the first occurences of sub in s before or at position start (which includes index start if it exists, defaults to String.length s).

Note if you need to search for sub multiple times in s use rfind_all_sub it is more efficient.

  • raises Invalid_argument

    if start is not a valid position of s.

val find_all_sub : ?start:int -> (int -> 'acc -> 'acc) -> sub:string -> string -> 'acc -> 'acc

find_all_sub ~start f ~sub s acc, starting with acc, folds f over all non-overlapping starting positions of sub in s after or at position start (which includes index start if it exists, defaults to 0). This is acc if sub could not be found in s.

  • raises Invalid_argument

    if start is not a valid position of s.

val rfind_all_sub : ?start:int -> (int -> 'acc -> 'acc) -> sub:string -> string -> 'acc -> 'acc

rfind_all_sub ~start f ~sub s acc, starting with acc, folds f over all non-overlapping starting positions of sub in s before or at position start (which includes index start if it exists, defaults to String.length s). This is acc if sub could not be found in s.

  • raises Invalid_argument

    if start is not a valid position of s.

val replace_first : ?start:int -> sub:string -> by:string -> string -> string

replace_first ~start ~sub ~by s replaces in s the first occurence of sub at or after position start (defaults to 0) by by.

  • raises Invalid_argument

    if start is not a valid position of s.

val replace_all : ?start:int -> sub:string -> by:string -> string -> string

replace_all ~start ~sub ~by replaces in s all non-overlapping occurences of sub at or after position start (default to 0) by by.

  • raises Invalid_argument

    if start is not a valid position of s.

Extracting substrings

val subrange : ?first:int -> ?last:int -> string -> string

subrange ~first ~last s are the consecutive bytes of s whose indices exist in the range [first;last].

first defaults to 0 and last to String.length s - 1.

Note that both first and last can be any integer. If first > last the interval is empty and the empty string is returned.

Breaking

Breaking with magnitudes

val take : int -> string -> string

take n s are the first n bytes of s. This is s if n >= length s and "" if n <= 0.

val rtake : int -> string -> string

rtake n s are the last n bytes of s. This is s if n >= length s and "" if n <= 0.

val drop : int -> string -> string

drop n s is s without the first n bytes of s. This is "" if n >= length s and s if n <= 0.

val rdrop : int -> string -> string

rdrop n s is s without the last n bytes of s. This is "" if n >= length s and s if n <= 0.

val span : int -> string -> string * string

span n v is (take n v, drop n v).

val rspan : int -> string -> string * string

rspan n v is (rdrop n v, rtake n v).

Breaking with predicates

val take_while : (char -> bool) -> string -> string

take_while sat s are the first consecutive sat statisfying bytes of s.

val rtake_while : (char -> bool) -> string -> string

keep_right sat s are the last consecutive sat satisfying bytes of s.

val drop_while : (char -> bool) -> string -> string

drop_while sat s is s without the first consecutive sat satisfying bytes of s.

val rdrop_while : (char -> bool) -> string -> string

rdrop_while sat s is s without the last consecutive sat satisfying bytes of s.

val span_while : (char -> bool) -> string -> string * string

span_while sat s is (take_while sat s, drop_while sat s).

val rspan_while : (char -> bool) -> string -> string * string

rspan_while sat s is (rdrop_while sat s, rtake_while sat s).

Breaking with separators

val cut : sep:string -> string -> (string * string) option

cut ~sep s is either the pair Some (l,r) of the two (possibly empty) substrings of s that are delimited by the first match of the separator character sep or None if sep can't be matched in s. Matching starts from the left of s.

The invariant l ^ sep ^ r = s holds.

  • raises Invalid_argument

    if sep is the empty string.

val rcut : sep:string -> string -> (string * string) option

rcut ~sep s is like cut but matching starts on the right of s.

val split : ?drop_empty:bool -> sep:string -> string -> string list

split sep s is the list of all substrings of s that are delimited by matches of the non empty separator string sep. Empty substrings are omitted in the list if drop_empty is true (defaults to false).

Matching separators in s starts from the left of s (rev is false, default) or the end (rev is true). Once one is found, the separator is skipped and matching starts again, that is separator matches can't overlap. If there is no separator match in s, the list [s] is returned.

The following invariants hold:

  • concat ~sep (cuts ~drop_empty:false ~sep s) = s
  • cuts ~drop_empty:false ~sep s <> []
  • raises Invalid_argument

    if sep is the empty string.

val rsplit : ?drop_empty:bool -> sep:string -> string -> string list

rsplit sep s is like split but matching starts on the right of s.

Breaking lines

val fold_ascii_lines : strip_newlines:bool -> (int -> 'a -> string -> 'a) -> 'a -> string -> 'a

fold_ascii_lines ~strip_newlines f acc s folds over the lines of s by calling f linenum acc' line with linenum the one-based line number count, acc' the result of accumulating acc with f so far and line the data of the line (without the newline found in the data if strip_newlines is true).

Lines are delimited by newline sequences which are either one of "\n", "\r\n" or "\r". More precisely the function determines lines and line data as follows:

  • If s = "", the function considers there are no lines in s and acc is returned without f being called.
  • If s <> "", s is repeteadly split on the first newline sequences "\n", "\r\n" or "\r" into (left, newline, right), left (or left ^ newline when strip_newlines = false) is given to f and the process is repeated with right until a split can no longer be found. At that point this final string is given to f and the process stops.
val detach_ascii_newline : string -> string * string

detach_ascii_newline s is (data, endline) with:

  • endline either the suffix "\n", "\r\n" or "\r" of s or "" if s has no such suffix.
  • data the bytes before endline such that data ^ newline = s

Tokenize

val next_token : ?is_sep:(char -> bool) -> ?is_token:(char -> bool) -> string -> string * string

next_token ~is_sep ~is_token s skips characters satisfying is_sep from s, then gather zero or more consecutive characters satisfying is_token into a string which is returned along the remaining characters after that. is_sep defaults to Char.Ascii.is_white and is_token is Char.Ascii.is_graphic.

val tokens : ?is_sep:(char -> bool) -> string -> string list

tokens s are the strings separated by sequences of is_sep characters (default to Char.Ascii.is_white). The empty list is returned if s is empty or made only of separators.

Uniqueness

val distinct : string list -> string list

distinct ss is ss without duplicates, the list order is preserved.

val unique : ?limit:int -> exists:(string -> bool) -> string -> string

unique ~exist n is n if exists n is false or r = strf "%s~%d" n d with d the smallest integer such that exists r if false. If no d in [1;1e9] satisfies the condition Invalid_argument is raised, limit defaults to 1e9.

Spellchecking

val edit_distance : ?limit:int -> t -> t -> int

edit_distance s0 s1 is the number of single character edits (understood as insertion, deletion, substitution, transposition) that are needed to change s0 into s1.

If limit is provided the function returns with limit as soon as it was determined that s0 and s1 have distance of at least limit. This is faster if you have a fixed limit, for example for spellchecking.

The function assumes the strings are UTF-8 encoded and uses Uchar.t for the notion of character. Decoding errors are replaced by Uchar.rep. Normalizing the strings to NFC gives better results.

Note. This implements the simpler Optimal String Alignement (OSA) distance, not the Damerau-Levenshtein distance. With this function "ca" and "abc" have a distance of 3 not 2.

Available in 5.4.

val spellcheck : ?max_dist:(string -> int) -> ((string -> unit) -> unit) -> string -> string list

spellcheck iter_dict s are the strings enumerated by the iterator iter_dict whose edit distance to s is the smallest and at most max_dist s. If multiple corrections are returned their order is as found in iter_dict. The default max_dist s is:

  • 0 if s has 0 to 2 Unicode characters.
  • 1 if s has 3 to 4 Unicode characters.
  • 2 otherwise.

If your dictionary is a list l, a suitable iter_dict is given by (fun yield -> List.iter yield l).

All strings are assumed to be UTF-8 encoded, decoding errors are replaced by Uchar.rep characters.

Available in 5.4.

(Un)escaping bytes

The following functions can only (un)escape a single byte. See also these functions to convert a string to printable ASCII characters.

val byte_escaper : (char -> int) -> (bytes -> int -> char -> int) -> string -> string

byte_escaper char_len set_char is a byte escaper such that:

  • char_len c is the length of the unescaped byte c in the escaped form. If 1 is returned then c is assumed to be unchanged use byte_replacer if that does not hold
  • set_char b i c sets an unescaped byte c to its escaped form at index i in b and returns the next writable index. set_char is called regardless if c needs to be escaped or not in the latter case you must write c (use byte_replacer if that is not the case). No bounds check need to be performed on i or the returned value.

For any b, c and i the invariant i + char_len c = set_char b i c must hold.

Here's a small example that escapes '"' by prefixing them by backslashes. double quotes from strings:

let escape_dquotes s =
  let char_len = function '"' -> 2 | _ -> 1 in
  let set_char b i = function
  | '"' -> Bytes.set b i '\\'; Bytes.set b (i+1) '"'; i + 2
  | c -> Bytes.set b i c; i + 1
  in
  String.byte_escaper char_len set_char s
val byte_replacer : (char -> int) -> (bytes -> int -> char -> int) -> string -> string

byte_replacer char_len set_char is like byte_escaper but a byte can be substituted by another one by set_char.

exception Illegal_escape of int
val byte_unescaper : (string -> int -> int) -> (bytes -> int -> string -> int -> int) -> string -> (string, int) Stdlib.result

byte_unescaper char_len_at set_char is a byte unescaper such that:

  • char_len_at s i is the length of an escaped byte at index i of s. If 1 is returned then the byte is assumed to be unchanged by the unescape, use byte_unreplacer if that does not hold.
  • set_char b k s i sets at index k in b the unescaped byte read at index i in s and returns the next readable index in s. set_char is called regardless of wheter the byte at i must be unescaped or not in the latter case you must write s.i only (use byte_unreplacer if that is not the case). No bounds check need to be performed on k, i or the returned value.

For any b, s, k and i the invariant i + char_len_at s i = set_char b k s i must hold.

Both char_len_at and set_char may raise Illegal_escape i if the given index i has an illegal or truncated escape. The unescaper turns this exception into Error i if that happens.

val byte_unreplacer : (string -> int -> int) -> (bytes -> int -> string -> int -> int) -> string -> (string, int) Stdlib.result

byte_unreplacer char_len_at set_char is like byte_unescaper except set_char can set a different byte whenever char_len_at returns 1.

ASCII strings

module Ascii : sig ... end

ASCII string support.

Variable substitution

val subst_pct_vars : ?buf:Stdlib.Buffer.t -> (string -> string option) -> string -> string

subst_pct_vars ~buf vars s substitutes in s sub-strings of the form %%VAR%% by the value of vars "VAR" (if any).

ANSI stripping

val strip_ansi_escapes : string -> string

strip_ansi_escapes s removes ANSI escapes from s.

Formatting

val pp : string Fmt.t

pp ppf s prints s's bytes on ppf.

Sets and maps

module Set : sig ... end

String sets.

module Map : sig ... end

String maps.