Module Core_string

module Core_string: sig .. end

An extension of the standard StringLabels. If you open Core.Std, you'll get these in the String module.

type t = string

val typerep_of_t : t Typerep_lib.Std.Typerep.t

val typename_of_t : t Typerep_lib.Std.Typename.t

module Caseless: sig .. end

include Blit.S

include Container.S0

include Identifiable.S

val max_length : int

Maximum length of a string.

val length : t -> int

val get : t -> int -> char

val set : t -> int -> char -> unit

val create : int -> t

val make : int -> char -> t

val copy : t -> t

val init : int -> f:(int -> char) -> t

val fill : t -> pos:int -> len:int -> char -> unit

val (^) : t -> t -> t

String append. Also available unqualified, but re-exported here for documentation purposes.

val concat : ?sep:t -> t list -> t

concatanate all strings in the list using separator sep (default sep "")

val escaped : t -> t

Warning: Only returns a copy if changes are necessary! Special characters are represented by escape sequences, following the lexical conventions of Objective Caml.

val contains : ?pos:int -> ?len:int -> t -> char -> bool

val uppercase : t -> t

val lowercase : t -> t

val capitalize : t -> t

val uncapitalize : t -> t

val index : t -> char -> int option

val index_exn : t -> char -> int

val rindex : t -> char -> int option

val rindex_exn : t -> char -> int

val index_from : t -> int -> char -> int option

val index_from_exn : t -> int -> char -> int

val rindex_from : t -> int -> char -> int option

val rindex_from_exn : t -> int -> char -> int

module Search_pattern: sig .. end

Substring search and replace functions.

val substr_index : ?pos:int -> t -> pattern:t -> int option

val substr_index_exn : ?pos:int -> t -> pattern:t -> int

val substr_index_all : t -> may_overlap:bool -> pattern:t -> int list

val substr_replace_first : ?pos:int ->
       t ->
       pattern:t -> with_:t -> t

As with Search_pattern.replace_all, the result may still contain pattern.

val substr_replace_all : t ->
       pattern:t -> with_:t -> t

val is_substring : t -> substring:t -> bool

is_substring ~substring:"bar" "foo bar baz" is true

val slice : t -> int -> int -> t

slice s start stop gets a slice of s between start and stop. start and stop will be normalized before the access. (viz. Core_array.normalize).

val to_list_rev : t -> char list

Returns the reversed list of characters contained in a list.

val rev : t -> t

rev t returns t in reverse order.

val nget : t -> int -> char

nget s i Gets the char at normalized position i in s.

val nset : t -> int -> char -> unit

nset s i c Sets the char at normalized position i to c.

val is_suffix : t -> suffix:t -> bool

is_suffix s ~suffix returns true if s ends with suffix.

val is_prefix : t -> prefix:t -> bool

is_prefix s ~prefix returns true if s starts with prefix.

val lsplit2_exn : t -> on:char -> t * t

If the string s contains the character on, then

lsplit2_exn
    s ~on

returns a pair containing s split around the first appearance of on (from the left).
Raises Not_found When on cannot be found in s

val rsplit2_exn : t -> on:char -> t * t

If the string s contains the character on, then

rsplit2_exn
    s ~on

returns a pair containing s split around the first appearance of on (from the right).
Raises Not_found When on cannot be found in s

val lsplit2 : t -> on:char -> (t * t) option

lsplit2 line ~on optionally returns line split into two strings around the first appearance of on from the left

val rsplit2 : t -> on:char -> (t * t) option

rsplit2 line ~on optionally returns line split into two strings around the first appearance of on from the right

val split : t -> on:char -> t list

split s ~on
Returns a list of substrings of s that are separated by on. Consecutive on characters will cause multiple empty strings in the result. Splitting the empty string returns a list of the empty string, not the empty list.

val split_on_chars : t -> on:char list -> t list

split_on_chars s ~on
Returns a list of all substrings of s that are separated by one of the chars from on. on are not grouped. So a grouping of on in the source string will produce multiple empty string splits in the result.

val split_lines : t -> t list

split_lines t returns the list of lines that comprise t. The lines do not include the trailing "\n" or "\r\n".

val lfindi : ?pos:int -> t -> f:(int -> char -> bool) -> int option

lfindi ?pos t ~f returns the smallest i >= pos such that f i t.[i], if there is such an i. By default, pos = 0.

val rfindi : ?pos:int -> t -> f:(int -> char -> bool) -> int option

rfindi ?pos t ~f returns the largest i <= pos such that f i t.[i], if there is such an i. By default pos = length t - 1.

Warning: the following strip functions have copy-on-write semantics (i.e. they may return the same string passed in)

val lstrip : ?drop:(char -> bool) -> t -> t

lstrip ?drop s returns a string with consecutive chars satisfying drop (by default white space, e.g. tabs, spaces, newlines, and carriage returns) stripped from the beginning of s.

val rstrip : ?drop:(char -> bool) -> t -> t

rstrip ?drop s returns a string with consecutive chars satisfying drop (by default white space, e.g. tabs, spaces, newlines, and carriage returns) stripped from the end of s.

val strip : ?drop:(char -> bool) -> t -> t

strip ?drop s returns a string with consecutive chars satisfying drop (by default white space, e.g. tabs, spaces, newlines, and carriage returns) stripped from the beginning and end of s.

val map : t -> f:(char -> char) -> t

map f s applies f to each character in s, and returns the resulting string.

val mapi : t -> f:(int -> char -> char) -> t

mapi f s applies f to each character in s and its index, and returns the resulting string.

val foldi : t -> init:'a -> f:(int -> 'a -> char -> 'a) -> 'a

foldi works similarly to fold, but also pass in index of each character to f

val concat_map : ?sep:t ->
       t -> f:(char -> t) -> t

Like map, but allows replacement of a single character with zero or two or more characters.

val filter : t -> f:(char -> bool) -> t

filter s ~f:predicate discards characters not satisfying predicate

val tr : target:char -> replacement:char -> t -> t

tr target replacement s replaces every instance of target in s with replacement.

val tr_inplace : target:char -> replacement:char -> t -> unit

tr_inplace target replacement s destructively modifies s (in place!) replacing every instance of target in s with replacement.

val chop_suffix_exn : t -> suffix:t -> t

chop_suffix s ~suf returns a copy s without the trailing suff
Raises Invalid_argument is suff is not a suffix of s

val chop_prefix_exn : t -> prefix:t -> t

chop_prefix s ~pref returns a copy s without the leading pref
Raises Invalid_argument is pref is not a prefix of s

val chop_suffix : t -> suffix:t -> t option

val chop_prefix : t -> prefix:t -> t option

val suffix : t -> int -> t

suffix s n returns the longest suffix of s of length less than or equal to n

val prefix : t -> int -> t

prefix s n returns the longest prefix of s of length less than or equal to n

val drop_suffix : t -> int -> t

drop_suffix s n drops the longest suffix of s of length less than or equal to n

val drop_prefix : t -> int -> t

drop_prefix s n drops the longest prefix of s of length less than or equal to n

val concat_array : ?sep:t -> t array -> t

concat_array sep ar like String.concat, but operates on arrays

val hash : t -> int

slightly faster hash function on strings

val equal : t -> t -> bool

fast equality function on strings, doesn't use compare_val

val is_empty : t -> bool

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

module Infix: sig .. end

val of_char : char -> t

val of_char_list : char list -> t

module Escaping: sig .. end

Operations for escaping and unescaping strings, with paramaterized escape and escapeworthy characters.

val unsafe_get : string -> int -> char

val unsafe_set : string -> int -> char -> unit

val t_of_sexp : Sexplib.Sexp.t -> t

val sexp_of_t : t -> Sexplib.Sexp.t

val bin_t : t Bin_prot.Type_class.t

val bin_read_t : t Bin_prot.Read.reader

val __bin_read_t__ : (int -> t) Bin_prot.Read.reader

val bin_reader_t : t Bin_prot.Type_class.reader

val bin_size_t : t Bin_prot.Size.sizer

val bin_write_t : t Bin_prot.Write.writer

val bin_writer_t : t Bin_prot.Type_class.writer

Caseless compares and hashes strings ignoring case, so that for example Caseless.equal "OCaml" "ocaml" and Caseless.("apple" < "Banana") are true, and Caseless.Map, Caseless.Table lookup and Caseless.Set membership is case-insensitive.

Maximum length of a string.

String append. Also available unqualified, but re-exported here for documentation purposes.

Note that a ^ b must copy both a and b into a newly-allocated result string, so a ^ b ^ c ^ ... ^ z is quadratic in the number of strings. String.concat does not have this problem -- it allocates the result buffer only once. The Rope module provides a data structure which uses a similar trick to achieve fast concatenation at either end of a string.

concatanate all strings in the list using separator sep (default sep "")

Warning: Only returns a copy if changes are necessary! Special characters are represented by escape sequences, following the lexical conventions of Objective Caml.

Substring search and replace functions. They use the Knuth-Morris-Pratt algorithm (KMP) under the hood.

The functions in the Search_pattern module allow the program to preprocess the searched pattern once and then use it many times without further allocations.

create pattern preprocesses pattern as per KMP, building an int array of length length pattern. All inputs are valid.

pos < 0 or pos >= length string result in no match (hence index returns None and index_exn raises).

may_overlap determines whether after a successful match, index_all should start looking for another one at the very next position (~may_overlap:true), or jump to the end of that match and continue from there (~may_overlap:false), e.g.:

        index_all (create "aaa") ~may_overlap:false ~in_:"aaaaBaaaaaa" = [0; 5; 8]
        index_all (create "aaa") ~may_overlap:true  ~in_:"aaaaBaaaaaa" = [0; 1; 5; 6; 7; 8]

E.g. replace_all internally calls index_all ~may_overlap:false.

Note that the result of replace_all pattern ~in_:text ~with_:r may still contain pattern, e.g.

        replace_all (create "bc") ~in:"aabbcc" ~with_:"cb" = "aabcbc"

Substring search and replace convenience functions. They call Search_pattern.create and then forget the preprocessed pattern when the search is complete. pos < 0 or pos >= length t result in no match (hence substr_index returns None and substr_index_exn raises). may_overlap indicates whether to report overlapping matches, see Search_pattern.index_all.

As with Search_pattern.replace_all, the result may still contain pattern.

is_substring ~substring:"bar" "foo bar baz" is true

slice s start stop gets a slice of s between start and stop. start and stop will be normalized before the access. (viz. Core_array.normalize).

Returns the reversed list of characters contained in a list.

rev t returns t in reverse order.

nget s i Gets the char at normalized position i in s.

nset s i c Sets the char at normalized position i to c.

is_suffix s ~suffix returns true if s ends with suffix.

is_prefix s ~prefix returns true if s starts with prefix.

If the string s contains the character on, then

lsplit2_exn
    s ~on

returns a pair containing s split around the first appearance of on (from the left).

If the string s contains the character on, then

rsplit2_exn
    s ~on

returns a pair containing s split around the first appearance of on (from the right).

lsplit2 line ~on optionally returns line split into two strings around the first appearance of on from the left

rsplit2 line ~on optionally returns line split into two strings around the first appearance of on from the right

split s ~on

split_on_chars s ~on

split_lines t returns the list of lines that comprise t. The lines do not include the trailing "\n" or "\r\n".

lfindi ?pos t ~f returns the smallest i >= pos such that f i t.[i], if there is such an i. By default, pos = 0.

rfindi ?pos t ~f returns the largest i <= pos such that f i t.[i], if there is such an i. By default pos = length t - 1.

Warning: the following strip functions have copy-on-write semantics (i.e. they may return the same string passed in)

lstrip ?drop s returns a string with consecutive chars satisfying drop (by default white space, e.g. tabs, spaces, newlines, and carriage returns) stripped from the beginning of s.

rstrip ?drop s returns a string with consecutive chars satisfying drop (by default white space, e.g. tabs, spaces, newlines, and carriage returns) stripped from the end of s.

strip ?drop s returns a string with consecutive chars satisfying drop (by default white space, e.g. tabs, spaces, newlines, and carriage returns) stripped from the beginning and end of s.

map f s applies f to each character in s, and returns the resulting string.

mapi f s applies f to each character in s and its index, and returns the resulting string.

foldi works similarly to fold, but also pass in index of each character to f

Like map, but allows replacement of a single character with zero or two or more characters.

filter s ~f:predicate discards characters not satisfying predicate

tr target replacement s replaces every instance of target in s with replacement.

tr_inplace target replacement s destructively modifies s (in place!) replacing every instance of target in s with replacement.

chop_suffix s ~suf returns a copy s without the trailing suff

chop_prefix s ~pref returns a copy s without the leading pref

suffix s n returns the longest suffix of s of length less than or equal to n

prefix s n returns the longest prefix of s of length less than or equal to n

drop_suffix s n drops the longest suffix of s of length less than or equal to n

drop_prefix s n drops the longest prefix of s of length less than or equal to n

concat_array sep ar like String.concat, but operates on arrays

slightly faster hash function on strings

fast equality function on strings, doesn't use compare_val

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

Operations for escaping and unescaping strings, with paramaterized escape and escapeworthy characters. Escaping/unescaping using this module is more efficient than using Pcre. Benchmark code can be found in core/benchmarks/string_escaping.ml.

escape_gen_exn escapeworthy_map escape_char returns a function that will escape a string s as follows: if (c1,c2) is in escapeworthy_map, then all occurences of c1 are replaced by escape_char concatenated to c2.

Raises an exception if escapeworthy_map is not one-to-one. If escape_char is not in escapeworthy_map, then it will be escaped to itself.

escape ~escapeworthy ~escape_char s is

        escape_gen_exn ~escapeworthy_map:(List.zip_exn escapeworthy escapeworthy)
          ~escape_char

. Duplicates and escape_char will be removed from escapeworthy. So, no exception will be raised

unescape_gen_exn is the inverse operation of escape_gen_exn. That is,

      let escape = Staged.unstage (escape_gen_exn ~escapeworthy_map ~escape_char) in
      let unescape = Staged.unstage (unescape_gen_exn ~escapeworthy_map ~escape_char) in
      assert (s = unescape (escape s))

always succeed when ~escapeworthy_map is not causing exceptions.

unescape ~escape_char is defined as unescape_gen_exn ~map:[] ~escape_char

Any char in an escaped string is either escaping, escaped or literal. For example, for escaped string "0_a0__0" with escape_char as '_', pos 1 and 4 are escaping, 2 and 5 are escaped, and the rest are literal

is_char_escaping s ~escape_char pos return true if the char at pos is escaping, false otherwise.

is_char_escaped s ~escape_char pos return true if the char at pos is escaped, false otherwise.

is_literal s ~escape_char pos return true if the char at pos is not escaped or escaping.

index s ~escape_char char find the first literal (not escaped) instance of char in s starting from 0.

rindex s ~escape_char char find the first literal (not escaped) instance of char in s starting from the end of s and proceeding towards 0.

index_from s ~escape_char pos char find the first literal (not escaped) instance of char in s starting from pos and proceeding towards the end of s.

rindex_from s ~escape_char pos char find the first literal (not escaped) instance of char in s starting from pos and towards 0.

split s ~escape_char ~on

split_on_chars s ~on

lsplit2 s on escape_char splits s into a pair on the first literal instance of on (meaning the first unescaped instance) starting from the left.

rsplit2 s on escape_char splits s into a pair on the first literal instance of on (meaning the first unescaped instance) starting from the right.