module Bytes: BytesLabels;
let length: bytes => int;
Return the length (number of bytes) of the argument.
let get: (bytes, int) => char;
get s n returns the byte at index n in argument s.
Invalid_argument if n is not a valid index in s.let set: (bytes, int, char) => unit;
set s n c modifies s in place, replacing the byte at index n
with c.
Invalid_argument if n is not a valid index in s.let create: int => bytes;
create n returns a new 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 make: (int, char) => bytes;
make n c returns a new byte sequence of length n, filled with
the byte c.
Invalid_argument if n < 0 or n > Sys.max_string_length.let init: (int, ~f: int => char) => bytes;
init n f returns a fresh byte sequence of length n,
with character i initialized to the result of f i (in increasing
index order).
Invalid_argument if n < 0 or n > Sys.max_string_length.let empty: bytes;
A byte sequence of size 0.
let copy: bytes => bytes;
Return a new byte sequence that contains the same bytes as the argument.
let of_string: string => bytes;
Return a new byte sequence that contains the same bytes as the given string.
let to_string: bytes => string;
Return a new string that contains the same bytes as the given byte sequence.
let sub: (bytes, ~pos: int, ~len: int) => bytes;
sub s ~pos ~len returns a new byte sequence of length len,
containing the subsequence of s that starts at position pos
and has length len.
Invalid_argument if pos and len do not designate a
valid range of s.let sub_string: (bytes, ~pos: int, ~len: int) => string;
Same as BytesLabels.sub but return a string instead of a byte sequence.
let extend: (bytes, ~left: int, ~right: int) => bytes;
extend s ~left ~right returns a new byte sequence that contains
the bytes of s, with left uninitialized bytes prepended and
right uninitialized bytes appended to it. If left or right
is negative, then bytes are removed (instead of appended) from
the corresponding side of s.
Invalid_argument if the result length is negative or
longer than Sys.max_string_length bytes.let fill: (bytes, ~pos: int, ~len: int, char) => unit;
fill s ~pos ~len c modifies s in place, replacing len
characters with c, starting at pos.
Invalid_argument if pos and len do not designate a
valid range of s.let blit:
(~src: bytes, ~src_pos: int, ~dst: bytes, ~dst_pos: int, ~len: int) => unit;
blit ~src ~src_pos ~dst ~dst_pos ~len copies len bytes from sequence
src, starting at index src_pos, to sequence dst, starting at
index dst_pos. It works correctly even if src and dst are the
same byte sequence, and the source and destination intervals
overlap.
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 blit_string:
(~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 string
src, starting at index src_pos, to byte sequence dst,
starting at index 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 concat: (~sep: bytes, list(bytes)) => bytes;
concat ~sep sl concatenates the list of byte sequences sl,
inserting the separator byte sequence sep between each, and
returns the result as a new byte sequence.
Invalid_argument if the result is longer than
Sys.max_string_length bytes.let cat: (bytes, bytes) => bytes;
cat s1 s2 concatenates s1 and s2 and returns the result
as a new byte sequence.
Invalid_argument if the result is longer than
Sys.max_string_length bytes.let iter: (~f: char => unit, bytes) => unit;
iter ~f s applies function f in turn to all the bytes of s.
It is equivalent to f (get s 0); f (get s 1); ...; f (get s
(length s - 1)); ().
let iteri: (~f: (int, char) => unit, bytes) => unit;
Same as BytesLabels.iter, but the function is applied to the index of
the byte as first argument and the byte itself as second
argument.
let map: (~f: char => char, bytes) => bytes;
map ~f s applies function f in turn to all the bytes of s (in
increasing index order) and stores the resulting bytes in a new sequence
that is returned as the result.
let mapi: (~f: (int, char) => char, bytes) => bytes;
mapi ~f s calls f with each character of s and its
index (in increasing index order) and stores the resulting bytes
in a new sequence that is returned as the result.
let trim: bytes => bytes;
Return a copy of the argument, without leading and trailing
whitespace. The bytes regarded as whitespace are the ASCII
characters ' ', '\012', '\n', '\r', and '\t'.
let escaped: bytes => bytes;
Return a copy of the argument, with special characters represented by escape sequences, following the lexical conventions of OCaml. All characters outside the ASCII printable range (32..126) are escaped, as well as backslash and double-quote.
Invalid_argument if the result is longer than
Sys.max_string_length bytes.let index: (bytes, char) => int;
index s c returns the index of the first occurrence of byte c
in s.
Not_found if c does not occur in s.let index_opt: (bytes, char) => option(int);
index_opt s c returns the index of the first occurrence of byte c
in s or None if c does not occur in s.
let rindex: (bytes, char) => int;
rindex s c returns the index of the last occurrence of byte c
in s.
Not_found if c does not occur in s.let rindex_opt: (bytes, char) => option(int);
rindex_opt s c returns the index of the last occurrence of byte c
in s or None if c does not occur in s.
let index_from: (bytes, int, char) => int;
index_from s i c returns the index of the first occurrence of
byte c in s after position i. index s c is
equivalent to index_from s 0 c.
Invalid_argument if i is not a valid position in s.Not_found if c does not occur in s after position i.let index_from_opt: (bytes, int, char) => option(int);
index_from_opt s i c returns the index of the first occurrence of
byte c in s after position i or None if c does not occur in s
after position i.
index_opt s c is equivalent to index_from_opt s 0 c.
Invalid_argument if i is not a valid position in s.let rindex_from: (bytes, int, char) => int;
rindex_from s i c returns the index of the last occurrence of
byte c in s before position i+1. rindex s c is equivalent
to rindex_from s (length s - 1) c.
Invalid_argument if i+1 is not a valid position in s.Not_found if c does not occur in s before position i+1.let rindex_from_opt: (bytes, int, char) => option(int);
rindex_from_opt s i c returns the index of the last occurrence
of byte c in s before position i+1 or None if c does not
occur in s before position i+1. rindex_opt s c is equivalent to
rindex_from s (length s - 1) c.
Invalid_argument if i+1 is not a valid position in s.let contains: (bytes, char) => bool;
contains s c tests if byte c appears in s.
let contains_from: (bytes, int, char) => bool;
contains_from s start c tests if byte c appears in s after
position start. contains s c is equivalent to contains_from
s 0 c.
Invalid_argument if start is not a valid position in s.let rcontains_from: (bytes, int, char) => bool;
rcontains_from s stop c tests if byte c appears in s before
position stop+1.
Invalid_argument if stop < 0 or stop+1 is not a valid
position in s.let uppercase: bytes => bytes;
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: bytes => bytes;
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: bytes => bytes;
Return a copy of the argument, with the first character set to uppercase, using the ISO Latin-1 (8859-1) character set.
let uncapitalize: bytes => bytes;
Return a copy of the argument, with the first character set to lowercase, using the ISO Latin-1 (8859-1) character set.
let uppercase_ascii: bytes => bytes;
Return a copy of the argument, with all lowercase letters translated to uppercase, using the US-ASCII character set.
let lowercase_ascii: bytes => bytes;
Return a copy of the argument, with all uppercase letters translated to lowercase, using the US-ASCII character set.
let capitalize_ascii: bytes => bytes;
Return a copy of the argument, with the first character set to uppercase, using the US-ASCII character set.
let uncapitalize_ascii: bytes => bytes;
Return a copy of the argument, with the first character set to lowercase, using the US-ASCII character set.
type t = bytes;
An alias for the type of byte sequences.
let compare: (t, t) => int;
let equal: (t, t) => bool;
The equality function for byte sequences.
This section describes unsafe, low-level conversion functions
between bytes and string. They do not copy the internal data;
used improperly, they can break the immutability invariant on
strings provided by the -safe-string option. They are available for
expert library authors, but for most purposes you should use the
always-correct BytesLabels.to_string and BytesLabels.of_string instead.
let unsafe_to_string: bytes => string;
Unsafely convert a byte sequence into a string.
To reason about the use of unsafe_to_string, it is convenient to
consider an "ownership" discipline. A piece of code that
manipulates some data "owns" it; there are several disjoint ownership
modes, including:
Unique ownership is linear: passing the data to another piece of code means giving up ownership (we cannot write the data again). A unique owner may decide to make the data shared (giving up mutation rights on it), but shared data may not become uniquely-owned again.
unsafe_to_string s can only be used when the caller owns the byte
sequence s -- either uniquely or as shared immutable data. The
caller gives up ownership of s, and gains ownership of the
returned string.
There are two valid use-cases that respect this ownership discipline:
1. Creating a string by initializing and mutating a byte sequence that is never changed after initialization is performed.
let string_init len f : string =
let s = Bytes.create len in
for i = 0 to len - 1 do Bytes.set s i (f i) done;
Bytes.unsafe_to_string s
This function is safe because the byte sequence s will never be
accessed or mutated after unsafe_to_string is called. The
string_init code gives up ownership of s, and returns the
ownership of the resulting string to its caller.
Note that it would be unsafe if s was passed as an additional
parameter to the function f as it could escape this way and be
mutated in the future -- string_init would give up ownership of
s to pass it to f, and could not call unsafe_to_string
safely.
We have provided the String.init, String.map and
String.mapi functions to cover most cases of building
new strings. You should prefer those over to_string or
unsafe_to_string whenever applicable.
2. Temporarily giving ownership of a byte sequence to a function that expects a uniquely owned string and returns ownership back, so that we can mutate the sequence again after the call ended.
let bytes_length (s : bytes) =
String.length (Bytes.unsafe_to_string s)
In this use-case, we do not promise that s will never be mutated
after the call to bytes_length s. The String.length function
temporarily borrows unique ownership of the byte sequence
(and sees it as a string), but returns this ownership back to
the caller, which may assume that s is still a valid byte
sequence after the call. Note that this is only correct because we
know that String.length does not capture its argument -- it could
escape by a side-channel such as a memoization combinator.
The caller may not mutate s while the string is borrowed (it has
temporarily given up ownership). This affects concurrent programs,
but also higher-order functions: if String.length returned
a closure to be called later, s should not be mutated until this
closure is fully applied and returns ownership.
let unsafe_of_string: string => bytes;
Unsafely convert a shared string to a byte sequence that should not be mutated.
The same ownership discipline that makes unsafe_to_string
correct applies to unsafe_of_string: you may use it if you were
the owner of the string value, and you will own the return
bytes in the same mode.
In practice, unique ownership of string values is extremely difficult to reason about correctly. You should always assume strings are shared, never uniquely owned.
For example, string literals are implicitly shared by the compiler, so you never uniquely own them.
let incorrect = Bytes.unsafe_of_string "hello"
let s = Bytes.of_string "hello"
The first declaration is incorrect, because the string literal
"hello" could be shared by the compiler with other parts of the
program, and mutating incorrect is a bug. You must always use
the second version, which performs a copy and is thus correct.
Assuming unique ownership of strings that are not string
literals, but are (partly) built from string literals, is also
incorrect. For example, mutating unsafe_of_string ("foo" ^ s)
could mutate the shared string "foo" -- assuming a rope-like
representation of strings. More generally, functions operating on
strings will assume shared ownership, they do not preserve unique
ownership. It is thus incorrect to assume unique ownership of the
result of unsafe_of_string.
The only case we have reasonable confidence is safe is if the
produced bytes is shared -- used as an immutable byte
sequence. This is possibly useful for incremental migration of
low-level programs that manipulate immutable sequences of bytes
(for example Marshal.from_bytes) and previously used the
string type for this purpose.
let to_seq: t => Seq.t(char);
Iterate on the string, in increasing index order. Modifications of the string during iteration will be reflected in the iterator.
let to_seqi: t => Seq.t((int, char));
Iterate on the string, in increasing order, yielding indices along chars
let of_seq: Seq.t(char) => t;
Create a string from the generator
The functions in this section binary encode and decode integers to and from byte sequences.
All following functions raise Invalid_argument if the space
needed at index i to decode or encode the integer is not
available.
Little-endian (resp. big-endian) encoding means that least
(resp. most) significant bytes are stored first. Big-endian is
also known as network byte order. Native-endian encoding is
either little-endian or big-endian depending on Sys.big_endian.
32-bit and 64-bit integers are represented by the int32 and
int64 types, which can be interpreted either as signed or
unsigned numbers.
8-bit and 16-bit integers are represented by the int type,
which has more bits than the binary encoding. These extra bits
are handled as follows:
int values sign-extend
(resp. zero-extend) their result.int values truncate their input to their least significant
bytes.let get_uint8: (bytes, int) => int;
get_uint8 b i is b's unsigned 8-bit integer starting at byte index i.
let get_int8: (bytes, int) => int;
get_int8 b i is b's signed 8-bit integer starting at byte index i.
let get_uint16_ne: (bytes, int) => int;
get_uint16_ne b i is b's native-endian unsigned 16-bit integer
starting at byte index i.
let get_uint16_be: (bytes, int) => int;
get_uint16_be b i is b's big-endian unsigned 16-bit integer
starting at byte index i.
let get_uint16_le: (bytes, int) => int;
get_uint16_le b i is b's little-endian unsigned 16-bit integer
starting at byte index i.
let get_int16_ne: (bytes, int) => int;
get_int16_ne b i is b's native-endian signed 16-bit integer
starting at byte index i.
let get_int16_be: (bytes, int) => int;
get_int16_be b i is b's big-endian signed 16-bit integer
starting at byte index i.
let get_int16_le: (bytes, int) => int;
get_int16_le b i is b's little-endian signed 16-bit integer
starting at byte index i.
let get_int32_ne: (bytes, int) => int32;
get_int32_ne b i is b's native-endian 32-bit integer
starting at byte index i.
let get_int32_be: (bytes, int) => int32;
get_int32_be b i is b's big-endian 32-bit integer
starting at byte index i.
let get_int32_le: (bytes, int) => int32;
get_int32_le b i is b's little-endian 32-bit integer
starting at byte index i.
let get_int64_ne: (bytes, int) => int64;
get_int64_ne b i is b's native-endian 64-bit integer
starting at byte index i.
let get_int64_be: (bytes, int) => int64;
get_int64_be b i is b's big-endian 64-bit integer
starting at byte index i.
let get_int64_le: (bytes, int) => int64;
get_int64_le b i is b's little-endian 64-bit integer
starting at byte index i.
let set_uint8: (bytes, int, int) => unit;
set_uint8 b i v sets b's unsigned 8-bit integer starting at byte index
i to v.
let set_int8: (bytes, int, int) => unit;
set_int8 b i v sets b's signed 8-bit integer starting at byte index
i to v.
let set_uint16_ne: (bytes, int, int) => unit;
set_uint16_ne b i v sets b's native-endian unsigned 16-bit integer
starting at byte index i to v.
let set_uint16_be: (bytes, int, int) => unit;
set_uint16_be b i v sets b's big-endian unsigned 16-bit integer
starting at byte index i to v.
let set_uint16_le: (bytes, int, int) => unit;
set_uint16_le b i v sets b's little-endian unsigned 16-bit integer
starting at byte index i to v.
let set_int16_ne: (bytes, int, int) => unit;
set_int16_ne b i v sets b's native-endian signed 16-bit integer
starting at byte index i to v.
let set_int16_be: (bytes, int, int) => unit;
set_int16_be b i v sets b's big-endian signed 16-bit integer
starting at byte index i to v.
let set_int16_le: (bytes, int, int) => unit;
set_int16_le b i v sets b's little-endian signed 16-bit integer
starting at byte index i to v.
let set_int32_ne: (bytes, int, int32) => unit;
set_int32_ne b i v sets b's native-endian 32-bit integer
starting at byte index i to v.
let set_int32_be: (bytes, int, int32) => unit;
set_int32_be b i v sets b's big-endian 32-bit integer
starting at byte index i to v.
let set_int32_le: (bytes, int, int32) => unit;
set_int32_le b i v sets b's little-endian 32-bit integer
starting at byte index i to v.
let set_int64_ne: (bytes, int, int64) => unit;
set_int64_ne b i v sets b's native-endian 64-bit integer
starting at byte index i to v.
let set_int64_be: (bytes, int, int64) => unit;
set_int64_be b i v sets b's big-endian 64-bit integer
starting at byte index i to v.
let set_int64_le: (bytes, int, int64) => unit;
set_int64_le b i v sets b's little-endian 64-bit integer
starting at byte index i to v.