module StringLabels: sig .. end
Strings.
A string s
of length n
is an indexable and immutable sequence
of n
bytes. For historical reasons these bytes are referred to
as characters.
The semantics of string functions is defined in terms of indices and positions. These are depicted and described as follows.
/* positions 0 1 2 3 4 n-1 n * +---+---+---+---+ +-----+ * indices | 0 | 1 | 2 | 3 | ... | n-1 | * +---+---+---+---+ +-----+ */
i
of s
is an integer in the range [0
;n-1
].
It represents the i
th byte (character) of s
which can be
accessed using the constant time string indexing operator
s.[i]
.i
of s
is an integer in the range
[0
;n
]. It represents either the point at the beginning of
the string, or the point between two indices, or the point at
the end of the string. The i
th byte index is between position
i
and i+1
.Two integers start
and len
are said to define a valid
substring of s
if len >= 0
and start
, start+len
are
positions of s
.
Unicode text. Strings being arbitrary sequences of bytes, they
can hold any kind of textual encoding. However the recommended
encoding for storing Unicode text in OCaml strings is UTF-8. This
is the encoding used by Unicode escapes in string literals. For
example the string "\u{1F42B}"
is the UTF-8 encoding of the
Unicode character U+1F42B.
Past mutability. OCaml strings used to be modifiable in place,
for instance via the String.set
and String.blit
functions. This use is nowadays only possible when the compiler is
put in "unsafe-string" mode by giving the -unsafe-string
command-line option. This compatibility mode makes the types
string
and bytes
(see Bytes.t
) interchangeable so that
functions expecting byte sequences can also accept strings as
arguments and modify them.
The distinction between bytes
and string
was introduced in
OCaml 4.02, and the "unsafe-string" compatibility mode was the
default until OCaml 4.05. Starting with 4.06, the compatibility
mode is opt-in; we intend to remove the option in the future.
The labeled version of this module can be used as described in the
StdLabels
module.
type t = string;
The type for strings.
let make: (int, char) => string;
make n c
is a string of length n
with each index holding the
character c
.
Invalid_argument
if n < 0
or n >
Sys.max_string_length
.let init: (int, ~f: int => char) => string;
init n ~f
is a string of length n
with index
i
holding the character f i
(called in increasing index order).
Invalid_argument
if n < 0
or n >
Sys.max_string_length
.let length: string => int;
length s
is the length (number of bytes/characters) of s
.
let get: (string, int) => char;
get s i
is the character at index i
in s
. This is the same
as writing s.[i]
.
Invalid_argument
if i
not an index of s
.Note. The (^)
binary operator concatenates two
strings.
let concat: (~sep: string, list(string)) => string;
concat ~sep ss
concatenates the list of strings ss
, inserting
the separator string sep
between each.
Invalid_argument
if the result is longer than
Sys.max_string_length
bytes.let equal: (t, t) => bool;
equal s0 s1
is true
if and only if s0
and s1
are character-wise
equal.
let compare: (t, t) => int;
compare s0 s1
sorts s0
and s1
in lexicographical order. compare
behaves like compare
on strings but may be more efficient.
let contains_from: (string, int, char) => bool;
contains_from s start c
is true
if and only if c
appears in s
after position start
.
Invalid_argument
if start
is not a valid position in s
.let rcontains_from: (string, int, char) => bool;
rcontains_from s stop c
is true
if and only if c
appears in s
before position stop+1
.
Invalid_argument
if stop < 0
or stop+1
is not a valid
position in s
.let contains: (string, char) => bool;
contains s c
is String.contains_from
s 0 c
.
let sub: (string, ~pos: int, ~len: int) => string;
sub s ~pos ~len
is a string of length len
, containing the
substring of s
that starts at position pos
and has length
len
.
Invalid_argument
if pos
and len
do not designate a valid
substring of s
.let split_on_char: (~sep: char, string) => list(string);
split_on_char ~sep s
is the list of all (possibly empty)
substrings of s
that are delimited by the character sep
.
The function's result is specified by the following invariants:
sep
as a separator returns a
string equal to the input (concat (make 1 sep)
(split_on_char sep s) = s
).sep
character.let map: (~f: char => char, string) => string;
map f s
is the string resulting from applying f
to all the
characters of s
in increasing order.
let mapi: (~f: (int, char) => char, string) => string;
mapi ~f s
is like StringLabels.map
but the index of the character is also
passed to f
.
let trim: string => string;
trim s
is s
without leading and trailing whitespace. Whitespace
characters are: ' '
, '\x0C'
(form feed), '\n'
, '\r'
, and '\t'
.
let escaped: string => string;
escaped s
is s
with special characters represented by escape
sequences, following the lexical conventions of OCaml.
All characters outside the US-ASCII printable range [0x20;0x7E] are escaped, as well as backslash (0x2F) and double-quote (0x22).
The function Scanf.unescaped
is a left inverse of escaped
,
i.e. Scanf.unescaped (escaped s) = s
for any string s
(unless
escaped s
fails).
Invalid_argument
if the result is longer than
Sys.max_string_length
bytes.let uppercase_ascii: string => string;
uppercase_ascii s
is s
with all lowercase letters
translated to uppercase, using the US-ASCII character set.
let lowercase_ascii: string => string;
lowercase_ascii s
is s
with all uppercase letters translated
to lowercase, using the US-ASCII character set.
let capitalize_ascii: string => string;
capitalize_ascii s
is s
with the first character set to
uppercase, using the US-ASCII character set.
let uncapitalize_ascii: string => string;
uncapitalize_ascii s
is s
with the first character set to lowercase,
using the US-ASCII character set.
let iter: (~f: char => unit, string) => unit;
iter ~f s
applies function f
in turn to all the characters of s
.
It is equivalent to f s.[0]; f s.[1]; ...; f s.[length s - 1]; ()
.
let iteri: (~f: (int, char) => unit, string) => unit;
iteri
is like StringLabels.iter
, but the function is also given the
corresponding character index.
let index_from: (string, int, char) => int;
index_from s i c
is the index of the first occurrence of c
in
s
after position i
.
Not_found
if c
does not occur in s
after position i
.Invalid_argument
if i
is not a valid position in s
.let index_from_opt: (string, int, char) => option(int);
index_from_opt s i c
is the index of the first occurrence of c
in s
after position i
(if any).
Invalid_argument
if i
is not a valid position in s
.let rindex_from: (string, int, char) => int;
rindex_from s i c
is the index of the last occurrence of c
in
s
before position i+1
.
Not_found
if c
does not occur in s
before position i+1
.Invalid_argument
if i+1
is not a valid position in s
.let rindex_from_opt: (string, int, char) => option(int);
rindex_from_opt s i c
is the index of the last occurrence of c
in s
before position i+1
(if any).
Invalid_argument
if i+1
is not a valid position in s
.let index: (string, char) => int;
index s c
is String.index_from
s 0 c
.
let index_opt: (string, char) => option(int);
index_opt s c
is String.index_from_opt
s 0 c
.
let rindex: (string, char) => int;
rindex s c
is String.rindex_from
s (length s - 1) c
.
let rindex_opt: (string, char) => option(int);
rindex_opt s c
is String.rindex_from_opt
s (length s - 1) c
.
let to_seq: t => Seq.t(char);
to_seq s
is a sequence made of the string's characters in
increasing order. In "unsafe-string"
mode, modifications of the string
during iteration will be reflected in the iterator.
let to_seqi: t => Seq.t((int, char));
to_seqi s
is like StringLabels.to_seq
but also tuples the corresponding index.
let of_seq: Seq.t(char) => t;
of_seq s
is a string made of the sequence's characters.
let create: int => bytes;
create n
returns a fresh byte sequence of length n
.
The sequence is uninitialized and contains arbitrary bytes.
Invalid_argument
if n < 0
or n >
Sys.max_string_length
.let set: (bytes, int, char) => unit;
set s n c
modifies byte sequence s
in place,
replacing the byte at index n
with c
.
You can also write s.[n] <- c
instead of set s n c
.
Invalid_argument
if n
is not a valid index in s
.let blit:
(~src: string, ~src_pos: int, ~dst: bytes, ~dst_pos: int, ~len: int) => unit;
blit ~src ~src_pos ~dst ~dst_pos ~len
copies len
bytes
from the string src
, starting at index src_pos
,
to byte sequence dst
, starting at character number dst_pos
.
Invalid_argument
if src_pos
and len
do not
designate a valid range of src
, or if dst_pos
and len
do not designate a valid range of dst
.let copy: string => string;
Return a copy of the given string.
let fill: (bytes, ~pos: int, ~len: int, char) => unit;
fill s ~pos ~len c
modifies byte sequence s
in place,
replacing len
bytes by c
, starting at pos
.
Invalid_argument
if pos
and len
do not
designate a valid substring of s
.let uppercase: string => string;
Return a copy of the argument, with all lowercase letters translated to uppercase, including accented letters of the ISO Latin-1 (8859-1) character set.
let lowercase: string => string;
Return a copy of the argument, with all uppercase letters translated to lowercase, including accented letters of the ISO Latin-1 (8859-1) character set.
let capitalize: string => string;
Return a copy of the argument, with the first character set to uppercase, using the ISO Latin-1 (8859-1) character set..
let uncapitalize: string => string;
Return a copy of the argument, with the first character set to lowercase, using the ISO Latin-1 (8859-1) character set.