String type based on Bigarray
, for use in I/O and C-bindings
type t
= (Core_kernel__.Import.char, Bigarray.int8_unsigned_elt, Bigarray.c_layout) Bigarray.Array1.t
Type of bigstrings
include sig ... end
val t_of_sexp : Sexplib.Sexp.t ‑> t
val sexp_of_t : t ‑> Sexplib.Sexp.t
val compare : t ‑> t ‑> Core_kernel__.Import.int
val bin_t : t Bin_prot.Type_class.t
val bin_read_t : t Bin_prot.Read.reader
val __bin_read_t__ : (Core_kernel__.Import.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
val bin_shape_t : Bin_prot.Shape.t
include sig ... end
val t_frozen_of_sexp : Sexplib.Sexp.t ‑> t_frozen
val sexp_of_t_frozen : t_frozen ‑> Sexplib.Sexp.t
val hash_fold_t_frozen : Ppx_hash_lib.Std.Hash.state ‑> t_frozen ‑> Ppx_hash_lib.Std.Hash.state
val hash_t_frozen : t_frozen ‑> Ppx_hash_lib.Std.Hash.hash_value
val compare_t_frozen : t_frozen ‑> t_frozen ‑> Core_kernel__.Import.int
val bin_t_frozen : t_frozen Bin_prot.Type_class.t
val bin_read_t_frozen : t_frozen Bin_prot.Read.reader
val __bin_read_t_frozen__ : (Core_kernel__.Import.int ‑> t_frozen) Bin_prot.Read.reader
val bin_reader_t_frozen : t_frozen Bin_prot.Type_class.reader
val bin_size_t_frozen : t_frozen Bin_prot.Size.sizer
val bin_write_t_frozen : t_frozen Bin_prot.Write.writer
val bin_writer_t_frozen : t_frozen Bin_prot.Type_class.writer
val bin_shape_t_frozen : Bin_prot.Shape.t
include Core_kernel__.Import.Equal.S with type t := t
val equal : t Core_kernel__.Import.Equal.equal
val create : ?max_mem_waiting_gc:Byte_units.t ‑> Core_kernel__.Import.int ‑> t
create length
create
approach max_mem_waiting_gc
,
the pressure in the garbage collector to be more agressive will increase.length
.
Content is undefined.val init : Core_kernel__.Import.int ‑> f:(Core_kernel__.Import.int ‑> Core_kernel__.Import.char) ‑> t
init n ~f
creates a bigstring t
of length n
, with t.{i} = f i
val of_string : ?pos:Core_kernel__.Import.int ‑> ?len:Core_kernel__.Import.int ‑> Core_kernel__.Import.string ‑> t
of_string ?pos ?len str
len
in str
starting at position pos
.String.length str - pos
val to_string : ?pos:Core_kernel__.Import.int ‑> ?len:Core_kernel__.Import.int ‑> t ‑> Core_kernel__.Import.string
to_string ?pos ?len bstr
len
in bstr
starting at position pos
.length bstr - pos
val concat : ?sep:t ‑> t Core_kernel__.Import.list ‑> t
concat ?sep list
returns the concatenation of list
with sep
in between each.
val check_args : loc:Core_kernel__.Import.string ‑> pos:Core_kernel__.Import.int ‑> len:Core_kernel__.Import.int ‑> t ‑> Core_kernel__.Import.unit
check_args ~loc ~pos ~len bstr
checks the position and length
arguments pos
and len
for bigstrings bstr
.
loc
to indicate the calling context.val get_opt_len : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int Core_kernel__.Import.option ‑> Core_kernel__.Import.int
get_opt_len bstr ~pos opt_len
bstr
starting at position pos
and given optional length
opt_len
. This function does not check the validity of its
arguments. Use check_args for that purpose.external get : t ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.char = "%caml_ba_ref_1"
get t pos
returns the character at pos
external set : t ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.char ‑> Core_kernel__.Import.unit = "%caml_ba_set_1"
set t pos
sets the character at pos
external is_mmapped : t ‑> Core_kernel__.Import.bool = "bigstring_is_mmapped_stub"
is_mmapped bstr
bstr
is
memory-mapped.blit ~src ?src_pos ?src_len ~dst ?dst_pos ()
blits src_len
characters
from src
starting at position src_pos
to dst
at position dst_pos
.
include Blit.S with type t := t
val blit : (t, t) Base.Blit_intf.blit
val blito : (t, t) Base.Blit_intf.blito
val unsafe_blit : (t, t) Base.Blit_intf.blit
val sub : (t, t) Base.Blit_intf.sub
val subo : (t, t) Base.Blit_intf.subo
module To_string : Blit.S_distinct with type src := t with type dst := Core_kernel__.Import.string
module From_string : Blit.S_distinct with type src := Core_kernel__.Import.string with type dst := t
These functions write the "size-prefixed" bin-prot format that is used by, e.g.,
async's Writer.write_bin_prot
, Reader.read_bin_prot
and
Unpack_buffer.Unpack_one.create_bin_prot
.
val write_bin_prot : t ‑> ?pos:Core_kernel__.Import.int ‑> 'a Bin_prot.Type_class.writer ‑> 'a ‑> Core_kernel__.Import.int
write_bin_prot t writer a
writes a
to t
starting at pos
, and returns the index
in t
immediately after the last byte written. It raises if pos < 0
or if a
doesn't fit in t
.
val read_bin_prot : t ‑> ?pos:Core_kernel__.Import.int ‑> ?len:Core_kernel__.Import.int ‑> 'a Bin_prot.Type_class.reader ‑> ('a * Core_kernel__.Import.int) Or_error.t
The read_bin_prot*
functions read from the region of t
starting at pos
of length
len
. They return the index in t
immediately after the last byte read. They raise
if pos
and len
don't describe a region of t
.
val read_bin_prot_verbose_errors : t ‑> ?pos:Core_kernel__.Import.int ‑> ?len:Core_kernel__.Import.int ‑> 'a Bin_prot.Type_class.reader ‑> [ `Invalid_data of Error.t | `Not_enough_data | `Ok of 'a * Core_kernel__.Import.int ]
val map_file : shared:Core_kernel__.Import.bool ‑> Unix.file_descr ‑> Core_kernel__.Import.int ‑> t
map_file shared fd n
memory-maps n
characters of the data associated with
descriptor fd
to a bigstring. Iff shared
is true
, all changes to the bigstring
will be reflected in the file.
Users must keep in mind that operations on the resulting bigstring may result in disk operations which block the runtime. This is true for pure OCaml operations (such as t.
<- 1), and for calls to blit
. While some I/O operations may release the OCaml
lock, users should not expect this to be done for all operations on a bigstring
returned from map_file
.
val find : ?pos:Core_kernel__.Import.int ‑> ?len:Core_kernel__.Import.int ‑> Core_kernel__.Import.char ‑> t ‑> Core_kernel__.Import.int Core_kernel__.Import.option
find ?pos ?len char t
returns Some i
for the smallest i >= pos
such that
t.{i} = char
, or None
if there is no such i
.
length bstr - pos
external unsafe_find : t ‑> Core_kernel__.Import.char ‑> pos:Core_kernel__.Import.int ‑> len:Core_kernel__.Import.int ‑> Core_kernel__.Import.int = "bigstring_find"
Same as find
, but does no bounds checking, and returns a negative value instead of
None
if char
is not found.
external unsafe_destroy : t ‑> Core_kernel__.Import.unit = "bigstring_destroy_stub"
unsafe_destroy bstr
destroys the bigstring by deallocating its associated data or,
if memory-mapped, unmapping the corresponding file, and setting all dimensions to
zero. This effectively frees the associated memory or address-space resources
instantaneously. This feature helps working around a bug in the current OCaml
runtime, which does not correctly estimate how aggressively to reclaim such resources.
This operation is safe unless you have passed the bigstring to another thread that is performing operations on it at the same time. Access to the bigstring after this operation will yield array bounds exceptions.
Accessors for parsing binary values, analogous to binary_packing. These are in Bigstring rather than a separate module because:
1) Existing binary_packing requires copies and does not work with bigstrings 2) The accessors rely on the implementation of bigstring, and hence should changeshould the implementation of bigstring move away from Bigarray. 3) Bigstring already has some external C functions, so it didn't require many changes to the OMakefile ^_^.
In a departure from Binary_packing, the naming conventions are chosen to be close to C99 stdint types, as it's a more standard description and it is somewhat useful in making compact macros for the implementations. The accessor names contain endian-ness to allow for branch-free implementations
<accessor> ::= <unsafe><operation><type><endian><int> <unsafe> ::= unsafe_ | '' <operation> ::= get_ | set_ <type> ::= int16 | uint16 | int32 | int64 <endian> ::= _le | _be | '' <int> ::= _int | ''
The "unsafe_" prefix indicates that these functions do no bounds checking. Performance testing demonstrated that the bounds check was 2-3 times slower due to the fact that Bigstring.length is a C call, and not even a noalloc one. In practice, message parsers can check the size of an outer message once, and use the unsafe accessors for individual fields, so many bounds checks can end up being redundant as well. The situation could be improved by having bigarray cache the length/dimensions.
val unsafe_get_int8 : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_int8 : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_get_uint8 : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_uint8 : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_get_int16_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_int16_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_int16_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_set_int16_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_get_uint16_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_uint16_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_uint16_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_set_uint16_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_get_int32_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_int32_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_int32_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_set_int32_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_get_uint32_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_uint32_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_uint32_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_set_uint32_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
Similar to the usage in binary_packing, the below methods are treating the value being read (or written), as an ocaml immediate integer, as such it is actually 63 bits. If the user is confident that the range of values used in practice will not require 64 bit precision (i.e. Less than Max_Long), then we can avoid allocation and use an immediate. If the user is wrong, an exception will be thrown (for get).
val unsafe_get_int64_le_exn : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_int64_be_exn : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_int64_le_trunc : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_int64_be_trunc : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_int64_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_set_int64_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_get_uint64_be_exn : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_get_uint64_le_exn : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int
val unsafe_set_uint64_le : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_set_uint64_be : t ‑> pos:Core_kernel__.Import.int ‑> Core_kernel__.Import.int ‑> Core_kernel__.Import.unit
val unsafe_get_int32_t_le : t ‑> pos:Core_kernel__.Import.int ‑> Int32.t
val unsafe_get_int32_t_be : t ‑> pos:Core_kernel__.Import.int ‑> Int32.t
val unsafe_set_int32_t_le : t ‑> pos:Core_kernel__.Import.int ‑> Int32.t ‑> Core_kernel__.Import.unit
val unsafe_set_int32_t_be : t ‑> pos:Core_kernel__.Import.int ‑> Int32.t ‑> Core_kernel__.Import.unit
val unsafe_get_int64_t_le : t ‑> pos:Core_kernel__.Import.int ‑> Int64.t
val unsafe_get_int64_t_be : t ‑> pos:Core_kernel__.Import.int ‑> Int64.t
val unsafe_set_int64_t_le : t ‑> pos:Core_kernel__.Import.int ‑> Int64.t ‑> Core_kernel__.Import.unit
val unsafe_set_int64_t_be : t ‑> pos:Core_kernel__.Import.int ‑> Int64.t ‑> Core_kernel__.Import.unit
val get_tail_padded_fixed_string : padding:Core_kernel__.Import.char ‑> t ‑> pos:Core_kernel__.Import.int ‑> len:Core_kernel__.Import.int ‑> Core_kernel__.Import.unit ‑> Core_kernel__.Import.string
similar to Binary_packing.unpack_tail_padded_fixed_string
and
.pack_tail_padded_fixed_string
.
val set_tail_padded_fixed_string : padding:Core_kernel__.Import.char ‑> t ‑> pos:Core_kernel__.Import.int ‑> len:Core_kernel__.Import.int ‑> Core_kernel__.Import.string ‑> Core_kernel__.Import.unit
val get_head_padded_fixed_string : padding:Core_kernel__.Import.char ‑> t ‑> pos:Core_kernel__.Import.int ‑> len:Core_kernel__.Import.int ‑> Core_kernel__.Import.unit ‑> Core_kernel__.Import.string
val set_head_padded_fixed_string : padding:Core_kernel__.Import.char ‑> t ‑> pos:Core_kernel__.Import.int ‑> len:Core_kernel__.Import.int ‑> Core_kernel__.Import.string ‑> Core_kernel__.Import.unit