Module Js.String

Provide bindings to JS string

JavaScript String API

type t = string;
let make: 'a => t;

make value converts the given value to a string

make 3.5 = "3.5";;
make [|1;2;3|]) = "1,2,3";;
let fromCharCode: int => t;

fromCharCode n creates a string containing the character corresponding to that number; n ranges from 0 to 65535. If out of range, the lower 16 bits of the value are used. Thus, fromCharCode 0x1F63A gives the same result as fromCharCode 0xF63A.

fromCharCode 65 = "A";;
fromCharCode 0x3c8 = {js|ψ|js};;
fromCharCode 0xd55c = {js|한|js};;
fromCharCode -64568 = {js|ψ|js};;
let fromCharCodeMany: array(int) => t;

fromCharCodeMany [|n1;n2;n3|] creates a string from the characters corresponding to the given numbers, using the same rules as fromCharCode.

fromCharCodeMany([|0xd55c, 0xae00, 33|]) = {js|한글!|js};;
let fromCodePoint: int => t;

fromCodePoint n creates a string containing the character corresponding to that numeric code point. If the number is not a valid code point, raises RangeError. Thus, fromCodePoint 0x1F63A will produce a correct value, unlike fromCharCode 0x1F63A, and fromCodePoint -5 will raise a RangeError.

fromCodePoint 65 = "A";;
fromCodePoint 0x3c8 = {js|ψ|js};;
fromCodePoint 0xd55c = {js|한|js};;
fromCodePoint 0x1f63a = {js|😺|js};;

ES2015

let fromCodePointMany: array(int) => t;

ES2015

fromCharCodeMany [|n1;n2;n3|] creates a string from the characters corresponding to the given code point numbers, using the same rules as fromCodePoint.

fromCodePointMany([|0xd55c; 0xae00; 0x1f63a|]) = {js|한글😺|js}
let length: t => int;

length s returns the length of the given string.

length "abcd" = 4;;
let get: t => int => t;

get s n returns as a string the character at the given index number. If n is out of range, this function returns undefined, so at some point this function may be modified to return t option.

get "Reason" 0 = "R";;
get "Reason" 4 = "o";;
get {js|Rẽasöń|js} 5 = {js|ń|js};;
let charAt: int => t => t;

charAt n s gets the character at index n within string s. If n is negative or greater than the length of s, returns the empty string. If the string contains characters outside the range \u0000-\uffff, it will return the first 16-bit value at that position in the string.

charAt 0, "Reason" = "R"
charAt( 12, "Reason") = "";
charAt( 5, {js|Rẽasöń|js} = {js|ń|js}
let charCodeAt: int => t => float;

charCodeAt n s returns the character code at position n in string s; the result is in the range 0-65535, unlke codePointAt, so it will not work correctly for characters with code points greater than or equal to 0x10000. The return type is float because this function returns NaN if n is less than zero or greater than the length of the string.

charCodeAt 0 {js|😺|js} returns 0xd83d
codePointAt 0 {js|😺|js} returns Some 0x1f63a
let codePointAt: int => t => option(int);

ES2015

codePointAt n s returns the code point at position n within string s as a Some value. The return value handles code points greater than or equal to 0x10000. If there is no code point at the given position, the function returns None.

codePointAt 1 {js|¿😺?|js} = Some 0x1f63a
codePointAt 5 "abc" = None
let concat: t => t => t;

concat append original returns a new string with append added after original.

concat "bell" "cow" = "cowbell";;
let concatMany: array(t) => t => t;

concat arr original returns a new string consisting of each item of an array of strings added to the original string.

concatMany [|"2nd"; "3rd"; "4th"|] "1st" = "1st2nd3rd4th";;
let endsWith: t => t => bool;

ES2015: endsWith substr str returns true if the str ends with substr, false otherwise.

endsWith "World!" "Hello, World!" = true;;
endsWith "world!" "Hello, World!" = false;; (* case-sensitive *)
endsWith "World" "Hello, World!" = false;; (* exact match *)
let endsWithFrom: t => int => t => bool;

ES2015

endsWithFrom ending len str returns true if the first len characters of str end with ending, false otherwise. If n is greater than or equal to the length of str, then it works like endsWith. (Honestly, this should have been named endsWithAt, but oh well.)

endsWithFrom "cd" 4 "abcd" = true;;
endsWithFrom "cd" 3 "abcde" = false;;
endsWithFrom "cde" 99 "abcde" = true;;
endsWithFrom "ple" 7 "example.dat" = true;;
let includes: t => t => bool;

ES2015

includes searchValue s returns true if searchValue is found anywhere within s, false otherwise.

includes "gram" "programmer" = true;;
includes "er" "programmer" = true;;
includes "pro" "programmer" = true;;
includes "xyz" "programmer" = false;;
let includesFrom: t => int => t => bool;

ES2015

includes searchValue start s returns true if searchValue is found anywhere within s starting at character number start (where 0 is the first character), false otherwise.

includesFrom "gram" 1 "programmer" = true;;
includesFrom "gram" 4 "programmer" = false;;
includesFrom {js|한|js} 1 {js|대한민국|js} = true;;
let indexOf: t => t => int;

indexOf searchValue s returns the position at which searchValue was first found within s, or -1 if searchValue is not in s.

indexOf "ok" "bookseller" = 2;;
indexOf "sell" "bookseller" = 4;;
indexOf "ee" "beekeeper" = 1;;
indexOf "xyz" "bookseller" = -1;;
let indexOfFrom: t => int => t => int;

indexOfFrom searchValue start s returns the position at which searchValue was found within s starting at character position start, or -1 if searchValue is not found in that portion of s. The return value is relative to the beginning of the string, no matter where the search started from.

indexOfFrom "ok" 1 "bookseller" = 2;;
indexOfFrom "sell" 2 "bookseller" = 4;;
indexOfFrom "sell" 5 "bookseller" = -1;;
indexOf "xyz" "bookseller" = -1;;
let lastIndexOf: t => t => int;

lastIndexOf searchValue s returns the position of the last occurrence of searchValue within s, searching backwards from the end of the string. Returns -1 if searchValue is not in s. The return value is always relative to the beginning of the string.

lastIndexOf "ok" "bookseller" = 2;;
lastIndexOf "ee" "beekeeper" = 4;;
lastIndexOf "xyz" "abcdefg" = -1;;
let lastIndexOfFrom: t => int => t => int;

lastIndexOfFrom searchValue start s returns the position of the last occurrence of searchValue within s, searching backwards from the given start position. Returns -1 if searchValue is not in s. The return value is always relative to the beginning of the string.

lastIndexOfFrom "ok" 6 "bookseller" = 2;;
lastIndexOfFrom "ee" 8 "beekeeper" = 4;;
lastIndexOfFrom "ee" 3 "beekeeper" = 1;;
lastIndexOfFrom "xyz" 4 "abcdefg" = -1;;
let localeCompare: t => t => float;

localeCompare comparison reference returns

  • a negative value if reference comes before comparison in sort order
  • zero if reference and comparison have the same sort order
  • a positive value if reference comes after comparison in sort order
(localeCompare "ant" "zebra") > 0.0;;
(localeCompare "zebra" "ant") < 0.0;;
(localeCompare "cat" "cat") = 0.0;;
(localeCompare "cat" "CAT") > 0.0;;
let match_: Js__.Js_re.t => t => option(array(option(t)));

match regexp str matches a string against the given regexp. If there is no match, it returns None. For regular expressions without the g modifier, if there is a match, the return value is Some array where the array contains:

  • The entire matched string
  • Any capture groups if the regexp had parentheses

For regular expressions with the g modifier, a matched expression returns Some array with all the matched substrings and no capture groups.

match [%re "/b[aeiou]t/"] "The better bats" = Some [|"bet"|]
match [%re "/b[aeiou]t/g"] "The better bats" = Some [|"bet";"bat"|]
match [%re "/(\\d+)-(\\d+)-(\\d+)/"] "Today is 2018-04-05." =
  Some [|"2018-04-05"; "2018"; "04"; "05"|]
match [%re "/b[aeiou]g/"] "The large container." = None
let normalize: t => t;

ES2015

normalize str returns the normalized Unicode string using Normalization Form Canonical (NFC) Composition.

Consider the character ã, which can be represented as the single codepoint \u00e3 or the combination of a lower case letter A \u0061 and a combining tilde \u0303. Normalization ensures that both can be stored in an equivalent binary representation.

let normalizeByForm: t => t => t;

normalize str form (ES2015) returns the normalized Unicode string using the specified form of normalization, which may be one of:

  • "NFC" — Normalization Form Canonical Composition.
  • "NFD" — Normalization Form Canonical Decomposition.
  • "NFKC" — Normalization Form Compatibility Composition.
  • "NFKD" — Normalization Form Compatibility Decomposition.
let repeat: int => t => t;

ES2015

repeat n s returns a string that consists of n repetitions of s. Raises RangeError if n is negative.

repeat 3 "ha" = "hahaha"
repeat 0 "empty" = ""
let replace: t => t => t => t;

replace substr newSubstr string returns a new string which is identical to string except with the first matching instance of substr replaced by newSubstr.

substr is treated as a verbatim string to match, not a regular expression.

replace "old" "new" "old string" = "new string"
replace "the" "this" "the cat and the dog" = "this cat and the dog"
let replaceByRe: Js__.Js_re.t => t => t => t;

replaceByRe regex replacement string returns a new string where occurrences matching regex have been replaced by replacement.

replaceByRe [%re "/[aeiou]/g"] "x" "vowels be gone" = "vxwxls bx gxnx"
replaceByRe [%re "/(\\w+) (\\w+)/"] "$2, $1" "Juan Fulano" = "Fulano, Juan"
let unsafeReplaceBy0: Js__.Js_re.t => (t => int => t => t) => t => t;

returns a new string with some or all matches of a pattern with no capturing parentheses replaced by the value returned from the given function. The function receives as its parameters the matched string, the offset at which the match begins, and the whole string being matched

let str = "beautiful vowels"
let re = [%re "/[aeiou]/g"]
let matchFn matchPart offset wholeString =
  Js.String.toUpperCase matchPart

let replaced = Js.String.unsafeReplaceBy0 re matchFn str

let () = Js.log replaced (* prints "bEAUtifUl vOwEls" *)
let unsafeReplaceBy1: Js__.Js_re.t => (t => t => int => t => t) => t => t;

returns a new string with some or all matches of a pattern with one set of capturing parentheses replaced by the value returned from the given function. The function receives as its parameters the matched string, the captured string, the offset at which the match begins, and the whole string being matched.

let str = "increment 23"
let re = [%re "/increment (\\d+)/g"]
let matchFn matchPart p1 offset wholeString =
  wholeString ^ " is " ^ (string_of_int ((int_of_string p1) + 1))

let replaced = Js.String.unsafeReplaceBy1 re matchFn str

let () = Js.log replaced (* prints "increment 23 is 24" *)
let unsafeReplaceBy2: Js__.Js_re.t => (t => t => t => int => t => t) => t => t;

returns a new string with some or all matches of a pattern with two sets of capturing parentheses replaced by the value returned from the given function. The function receives as its parameters the matched string, the captured strings, the offset at which the match begins, and the whole string being matched.

let str = "7 times 6"
let re = [%re "/(\\d+) times (\\d+)/"]
let matchFn matchPart p1 p2 offset wholeString =
  string_of_int ((int_of_string p1) * (int_of_string p2))

let replaced = Js.String.unsafeReplaceBy2 re matchFn str

let () = Js.log replaced (* prints "42" *)
let unsafeReplaceBy3: Js__.Js_re.t => (t => t => t => t => int => t => t) => t => t;

returns a new string with some or all matches of a pattern with three sets of capturing parentheses replaced by the value returned from the given function. The function receives as its parameters the matched string, the captured strings, the offset at which the match begins, and the whole string being matched.

search regexp str returns the starting position of the first match of regexp in the given str, or -1 if there is no match.

search [%re "/\\d+/"] "testing 1 2 3" = 8;;
search [%re "/\\d+/"] "no numbers" = -1;;
let slice: from:int => to_:int => t => t;

slice from:n1 to_:n2 str returns the substring of str starting at character n1 up to but not including n2

If either n1 or n2 is negative, then it is evaluated as length str - n1 (or length str - n2.

If n2 is greater than the length of str, then it is treated as length str.

If n1 is greater than n2, slice returns the empty string.

slice ~from:2 ~to_:5 "abcdefg" == "cde";;
slice ~from:2 ~to_:9 "abcdefg" == "cdefg";;
slice ~from:(-4) ~to_:(-2) "abcdefg" == "de";;
slice ~from:5 ~to_:1 "abcdefg" == "";;
let sliceToEnd: from:int => t => t;

sliceToEnd from: n str returns the substring of str starting at character n to the end of the string

If n is negative, then it is evaluated as length str - n.

If n is greater than the length of str, then sliceToEnd returns the empty string.

sliceToEnd ~from: 4 "abcdefg" == "efg";;
sliceToEnd ~from: (-2) "abcdefg" == "fg";;
sliceToEnd ~from: 7 "abcdefg" == "";;
let split: t => t => array(t);

split delimiter str splits the given str at every occurrence of delimiter and returns an array of the resulting substrings.

split "-" "2018-01-02" = [|"2018"; "01"; "02"|];;
split "," "a,b,,c" = [|"a"; "b"; ""; "c"|];;
split "::" "good::bad as great::awful" = [|"good"; "bad as great"; "awful"|];;
split ";" "has-no-delimiter" = [|"has-no-delimiter"|];;

;

let splitAtMost: t => limit:int => t => array(t);

splitAtMost delimiter ~limit: n str splits the given str at every occurrence of delimiter and returns an array of the first n resulting substrings. If n is negative or greater than the number of substrings, the array will contain all the substrings.

splitAtMost "/" ~limit: 3 "ant/bee/cat/dog/elk" = [|"ant"; "bee"; "cat"|];;
splitAtMost "/" ~limit: 0 "ant/bee/cat/dog/elk" = [| |];;
splitAtMost "/" ~limit: 9 "ant/bee/cat/dog/elk" = [|"ant"; "bee"; "cat"; "dog"; "elk"|];;
let splitLimited: t => int => t => array(t);

Deprecated - Please use splitAtMost

  • deprecated Please use splitAtMost
let splitByRe: Js__.Js_re.t => t => array(option(t));

splitByRe regex str splits the given str at every occurrence of regex and returns an array of the resulting substrings.

splitByRe [%re "/\\s*[,;]\\s*/"] "art; bed , cog ;dad" = [|Some "art"; Some "bed"; Some "cog"; Some "dad"|];;
splitByRe [%re "/[,;]/"] "has:no:match" = [|Some "has:no:match"|];;
splitByRe [%re "/(#)(:)?/"] "a#b#:c" = [|Some "a"; Some "#"; None; Some "b"; Some "#"; Some ":"; Some "c"|];;

;

let splitByReAtMost: Js__.Js_re.t => limit:int => t => array(option(t));

splitByReAtMost regex ~limit: n str splits the given str at every occurrence of regex and returns an array of the first n resulting substrings. If n is negative or greater than the number of substrings, the array will contain all the substrings.

splitByReAtMost [%re "/\\s*:\\s*/"] ~limit: 3 "one: two: three: four" = [|Some "one"; Some "two"; Some "three"|];;
splitByReAtMost [%re "/\\s*:\\s*/"] ~limit: 0 "one: two: three: four" = [| |];;
splitByReAtMost [%re "/\\s*:\\s*/"] ~limit: 8 "one: two: three: four" = [|Some "one"; Some "two"; Some "three"; Some "four"|];;
splitByReAtMost [%re "/(#)(:)?/"] ~limit:3 "a#b#:c" = [|Some "a"; Some "#"; None|];;

;

let splitRegexpLimited: Js__.Js_re.t => int => t => array(t);

Deprecated - Please use splitByReAtMost

  • deprecated Please use splitByReAtMost
let startsWith: t => t => bool;

ES2015: startsWith substr str returns true if the str starts with substr, false otherwise.

startsWith "Hello" "Hello, World!" = true;;
startsWith "hello" "Hello, World!" = false;; (* case-sensitive *)
startsWith "World" "Hello, World!" = false;; (* exact match *)
let startsWithFrom: t => int => t => bool;

ES2015: startsWithFrom substr n str returns true if the str starts with substr starting at position n, false otherwise. If n is negative, the search starts at the beginning of str.

startsWithFrom "Hello" 0 "Hello, World!" = true;;
startsWithFrom "World" 7 "Hello, World!" = true;;
startsWithFrom "World" 8 "Hello, World!" = false;;
let substr: from:int => t => t;

substr ~from: n str returns the substring of str from position n to the end of the string.

If n is less than zero, the starting position is the length of str - n.

If n is greater than or equal to the length of str, returns the empty string.

substr ~from: 3 "abcdefghij" = "defghij"
substr ~from: (-3) "abcdefghij" = "hij"
substr ~from: 12 "abcdefghij" = ""
let substrAtMost: from:int => length:int => t => t;

substrAtMost ~from: pos ~length: n str returns the substring of str of length n starting at position pos.

If pos is less than zero, the starting position is the length of str - pos.

If pos is greater than or equal to the length of str, returns the empty string.

If n is less than or equal to zero, returns the empty string.

substrAtMost ~from: 3 ~length: 4 "abcdefghij" = "defghij"
substrAtMost ~from: (-3) ~length: 4 "abcdefghij" = "hij"
substrAtMost ~from: 12 ~ length: 2 "abcdefghij" = ""
let substring: from:int => to_:int => t => t;

substring ~from: start ~to_: finish str returns characters start up to but not including finish from str.

If start is less than zero, it is treated as zero.

If finish is zero or negative, the empty string is returned.

If start is greater than finish, the start and finish points are swapped.

substring ~from: 3 ~to_: 6 "playground" = "ygr";;
substring ~from: 6 ~to_: 3 "playground" = "ygr";;
substring ~from: 4 ~to_: 12 "playground" = "ground";;
let substringToEnd: from:int => t => t;

substringToEnd ~from: start str returns the substring of str from position start to the end.

If start is less than or equal to zero, the entire string is returned.

If start is greater than or equal to the length of str, the empty string is returned.

substringToEnd ~from: 4 "playground" = "ground";;
substringToEnd ~from: (-3) "playground" = "playground";;
substringToEnd ~from: 12 "playground" = "";
let toLowerCase: t => t;

toLowerCase str converts str to lower case using the locale-insensitive case mappings in the Unicode Character Database. Notice that the conversion can give different results depending upon context, for example with the Greek letter sigma, which has two different lower case forms when it is the last character in a string or not.

toLowerCase "ABC" = "abc";;
toLowerCase {js|ΣΠ|js} = {js|σπ|js};;
toLowerCase {js|ΠΣ|js} = {js|πς|js};;
let toLocaleLowerCase: t => t;

toLocaleLowerCase str converts str to lower case using the current locale

let toUpperCase: t => t;

toUpperCase str converts str to upper case using the locale-insensitive case mappings in the Unicode Character Database. Notice that the conversion can expand the number of letters in the result; for example the German ß capitalizes to two Ses in a row.

toUpperCase "abc" = "ABC";;
toUpperCase {js|Straße|js} = {js|STRASSE|js};;
toLowerCase {js|πς|js} = {js|ΠΣ|js};;
let toLocaleUpperCase: t => t;

toLocaleUpperCase str converts str to upper case using the current locale

let trim: t => t;

trim str returns a string that is str with whitespace stripped from both ends. Internal whitespace is not removed.

trim "   abc def   " = "abc def"
trim "\n\r\t abc def \n\n\t\r " = "abc def"
let anchor: t => t => t;

ES2015

anchor anchorName anchorText creates a string with an HTML <a> element with name attribute of anchorName and anchorText as its content.

anchor "page1" "Page One" = "<a name=\"page1\">Page One</a>"

ES2015

link urlText linkText creates a string withan HTML <a> element with href attribute of urlText and linkText as its content.

link "page2.html" "Go to page two" = "<a href=\"page2.html\">Go to page two</a>"
let castToArrayLike: t => Js__.Js_array2.array_like(t);