class IO::Buffer
IO::Buffer
is a low-level efficient buffer for input/output. There are three ways of using buffer:
-
Create an empty buffer with
::new
, fill it with data usingcopy
orset_value
,set_string
, get data withget_string
; -
Create a buffer mapped to some string with
::for
, then it could be used both for reading withget_string
orget_value
, and writing (writing will change the source string, too); -
Create a buffer mapped to some file with
::map
, then it could be used for reading and writing the underlying file.
Interaction with string and file memory is performed by efficient low-level C mechanisms like ‘memcpy`.
The class is meant to be an utility for implementing more high-level mechanisms like Fiber::SchedulerInterface#io_read and Fiber::SchedulerInterface#io_write.
Examples of usage:
Empty buffer:
buffer = IO::Buffer.new(8) # create empty 8-byte buffer # => # #<IO::Buffer 0x0000555f5d1a5c50+8 INTERNAL> # ... buffer # => # <IO::Buffer 0x0000555f5d156ab0+8 INTERNAL> # 0x00000000 00 00 00 00 00 00 00 00 buffer.set_string('test', 2) # put there bytes of the "test" string, starting from offset 2 # => 4 buffer.get_string # get the result # => "\x00\x00test\x00\x00"
Buffer from string:
string = 'data' buffer = IO::Buffer.for(string) # => # #<IO::Buffer 0x00007f3f02be9b18+4 SLICE> # ... buffer # => # #<IO::Buffer 0x00007f3f02be9b18+4 SLICE> # 0x00000000 64 61 74 61 data buffer.get_string(2) # read content starting from offset 2 # => "ta" buffer.set_string('---', 1) # write content, starting from offset 1 # => 3 buffer # => # #<IO::Buffer 0x00007f3f02be9b18+4 SLICE> # 0x00000000 64 2d 2d 2d d--- string # original string changed, too # => "d---"
Buffer from file:
File.write('test.txt', 'test data') # => 9 buffer = IO::Buffer.map(File.open('test.txt')) # => # #<IO::Buffer 0x00007f3f0768c000+9 MAPPED IMMUTABLE> # ... buffer.get_string(5, 2) # read 2 bytes, starting from offset 5 # => "da" buffer.set_string('---', 1) # attempt to write # in `set_string': Buffer is not writable! (IO::Buffer::AccessError) # To create writable file-mapped buffer # Open file for read-write, pass size, offset, and flags=0 buffer = IO::Buffer.map(File.open('test.txt', 'r+'), 9, 0, 0) buffer.set_string('---', 1) # => 3 -- bytes written File.read('test.txt') # => "t--- data"
The class is experimental and the interface is subject to change.
Constants
- BIG_ENDIAN
- DEFAULT_SIZE
- EXTERNAL
- HOST_ENDIAN
- INTERNAL
- LITTLE_ENDIAN
- LOCKED
- MAPPED
- NETWORK_ENDIAN
- PAGE_SIZE
- PRIVATE
- READONLY
- SHARED
Public Class Methods
Creates a IO::Buffer
from the given string’s memory. Without a block a frozen internal copy of the string is created efficiently and used as the buffer source. When a block is provided, the buffer is associated directly with the string’s internal data and updating the buffer will update the string.
Until free
is invoked on the buffer, either explicitly or via the garbage collector, the source string will be locked and cannot be modified.
If the string is frozen, it will create a read-only buffer which cannot be modified. If the string is shared, it may trigger a copy-on-write when using the block form.
string = 'test' buffer = IO::Buffer.for(string) buffer.external? #=> true buffer.get_string(0, 1) # => "t" string # => "best" buffer.resize(100) # in `resize': Cannot resize external buffer! (IO::Buffer::AccessError) IO::Buffer.for(string) do |buffer| buffer.set_string("T") string # => "Test" end
VALUE rb_io_buffer_type_for(VALUE klass, VALUE string) { StringValue(string); // If the string is frozen, both code paths are okay. // If the string is not frozen, if a block is not given, it must be frozen. if (rb_block_given_p()) { struct io_buffer_for_yield_instance_arguments arguments = { .klass = klass, .string = string, .instance = Qnil, .flags = 0, }; return rb_ensure(io_buffer_for_yield_instance, (VALUE)&arguments, io_buffer_for_yield_instance_ensure, (VALUE)&arguments); } else { // This internally returns the source string if it's already frozen. string = rb_str_tmp_frozen_acquire(string); return io_buffer_for_make_instance(klass, string, RB_IO_BUFFER_READONLY); } }
Create an IO::Buffer
for reading from file
by memory-mapping the file. file_io
should be a File
instance, opened for reading.
Optional size
and offset
of mapping can be specified.
By default, the buffer would be immutable (read only); to create a writable mapping, you need to open a file in read-write mode, and explicitly pass flags
argument without IO::Buffer::IMMUTABLE.
Example:
File.write('test.txt', 'test') buffer = IO::Buffer.map(File.open('test.txt'), nil, 0, IO::Buffer::READONLY) # => #<IO::Buffer 0x00000001014a0000+4 MAPPED READONLY> buffer.readonly? # => true buffer.get_string # => "test" buffer.set_string('b', 0) # `set_string': Buffer is not writable! (IO::Buffer::AccessError) # create read/write mapping: length 4 bytes, offset 0, flags 0 buffer = IO::Buffer.map(File.open('test.txt', 'r+'), 4, 0) buffer.set_string('b', 0) # => 1 # Check it File.read('test.txt') # => "best"
Note that some operating systems may not have cache coherency between mapped buffers and file reads.
static VALUE io_buffer_map(int argc, VALUE *argv, VALUE klass) { rb_check_arity(argc, 1, 4); // We might like to handle a string path? VALUE io = argv[0]; size_t size; if (argc >= 2 && !RB_NIL_P(argv[1])) { size = RB_NUM2SIZE(argv[1]); } else { rb_off_t file_size = rb_file_size(io); // Compiler can confirm that we handled file_size < 0 case: if (file_size < 0) { rb_raise(rb_eArgError, "Invalid negative file size!"); } // Here, we assume that file_size is positive: else if ((uintmax_t)file_size > SIZE_MAX) { rb_raise(rb_eArgError, "File larger than address space!"); } else { // This conversion should be safe: size = (size_t)file_size; } } rb_off_t offset = 0; if (argc >= 3) { offset = NUM2OFFT(argv[2]); } enum rb_io_buffer_flags flags = 0; if (argc >= 4) { flags = RB_NUM2UINT(argv[3]); } return rb_io_buffer_map(io, size, offset, flags); }
Create a new zero-filled IO::Buffer
of size
bytes. By default, the buffer will be internal: directly allocated chunk of the memory. But if the requested size
is more than OS-specific IO::Buffer::PAGE_SIZE
, the buffer would be allocated using the virtual memory mechanism (anonymous mmap
on Unix, VirtualAlloc
on Windows). The behavior can be forced by passing IO::Buffer::MAPPED
as a second parameter.
Examples
buffer = IO::Buffer.new(4) # => # #<IO::Buffer 0x000055b34497ea10+4 INTERNAL> # 0x00000000 00 00 00 00 .... buffer.get_string(0, 1) # => "\x00" buffer.set_string("test") buffer # => # #<IO::Buffer 0x000055b34497ea10+4 INTERNAL> # 0x00000000 74 65 73 74 test
VALUE rb_io_buffer_initialize(int argc, VALUE *argv, VALUE self) { io_buffer_experimental(); rb_check_arity(argc, 0, 2); struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); size_t size; if (argc > 0) { size = RB_NUM2SIZE(argv[0]); } else { size = RUBY_IO_BUFFER_DEFAULT_SIZE; } enum rb_io_buffer_flags flags = 0; if (argc >= 2) { flags = RB_NUM2UINT(argv[1]); } else { flags |= io_flags_for_size(size); } io_buffer_initialize(data, NULL, size, flags, Qnil); return self; }
Returns the size of the given data type(s) in bytes.
Example:
IO::Buffer.size_of(:u32) # => 4 IO::Buffer.size_of([:u32, :u32]) # => 8
static VALUE io_buffer_size_of(VALUE klass, VALUE data_type) { if (RB_TYPE_P(data_type, T_ARRAY)) { size_t total = 0; for (long i = 0; i < RARRAY_LEN(data_type); i++) { total += io_buffer_data_type_size(RB_SYM2ID(RARRAY_AREF(data_type, i))); } return SIZET2NUM(total); } else { return SIZET2NUM(io_buffer_data_type_size(RB_SYM2ID(data_type))); } }
Public Instance Methods
Generate a new buffer the same size as the source by applying the binary AND operation to the source, using the mask, repeating as necessary.
IO::Buffer.for("1234567890") & IO::Buffer.for("\xFF\x00\x00\xFF") # => # #<IO::Buffer 0x00005589b2758480+4 INTERNAL> # 0x00000000 31 00 00 34 35 00 00 38 39 00 1..45..89.
static VALUE io_buffer_and(VALUE self, VALUE mask) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); struct rb_io_buffer *mask_data = NULL; TypedData_Get_Struct(mask, struct rb_io_buffer, &rb_io_buffer_type, mask_data); io_buffer_check_mask(mask_data); VALUE output = rb_io_buffer_new(NULL, data->size, io_flags_for_size(data->size)); struct rb_io_buffer *output_data = NULL; TypedData_Get_Struct(output, struct rb_io_buffer, &rb_io_buffer_type, output_data); memory_and(output_data->base, data->base, data->size, mask_data->base, mask_data->size); return output; }
Buffers are compared by size and exact contents of the memory they are referencing using memcmp
.
static VALUE rb_io_buffer_compare(VALUE self, VALUE other) { const void *ptr1, *ptr2; size_t size1, size2; rb_io_buffer_get_bytes_for_reading(self, &ptr1, &size1); rb_io_buffer_get_bytes_for_reading(other, &ptr2, &size2); if (size1 < size2) { return RB_INT2NUM(-1); } if (size1 > size2) { return RB_INT2NUM(1); } return RB_INT2NUM(memcmp(ptr1, ptr2, size1)); }
Generate a new buffer the same size as the source by applying the binary XOR operation to the source, using the mask, repeating as necessary.
IO::Buffer.for("1234567890") ^ IO::Buffer.for("\xFF\x00\x00\xFF") # => # #<IO::Buffer 0x000055a2d5d10480+10 INTERNAL> # 0x00000000 ce 32 33 cb ca 36 37 c7 c6 30 .23..67..0
static VALUE io_buffer_xor(VALUE self, VALUE mask) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); struct rb_io_buffer *mask_data = NULL; TypedData_Get_Struct(mask, struct rb_io_buffer, &rb_io_buffer_type, mask_data); io_buffer_check_mask(mask_data); VALUE output = rb_io_buffer_new(NULL, data->size, io_flags_for_size(data->size)); struct rb_io_buffer *output_data = NULL; TypedData_Get_Struct(output, struct rb_io_buffer, &rb_io_buffer_type, output_data); memory_xor(output_data->base, data->base, data->size, mask_data->base, mask_data->size); return output; }
Modify the source buffer in place by applying the binary AND operation to the source, using the mask, repeating as necessary.
source = IO::Buffer.for("1234567890").dup # Make a read/write copy. # => # #<IO::Buffer 0x000056307a0d0c20+10 INTERNAL> # 0x00000000 31 32 33 34 35 36 37 38 39 30 1234567890 source.and!(IO::Buffer.for("\xFF\x00\x00\xFF")) # => # #<IO::Buffer 0x000056307a0d0c20+10 INTERNAL> # 0x00000000 31 00 00 34 35 00 00 38 39 00 1..45..89.
static VALUE io_buffer_and_inplace(VALUE self, VALUE mask) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); struct rb_io_buffer *mask_data = NULL; TypedData_Get_Struct(mask, struct rb_io_buffer, &rb_io_buffer_type, mask_data); io_buffer_check_mask(mask_data); io_buffer_check_overlaps(data, mask_data); void *base; size_t size; io_buffer_get_bytes_for_writing(data, &base, &size); memory_and_inplace(base, size, mask_data->base, mask_data->size); return self; }
Fill buffer with value
, starting with offset
and going for length
bytes.
buffer = IO::Buffer.for('test') # => # <IO::Buffer 0x00007fca40087c38+4 SLICE> # 0x00000000 74 65 73 74 test buffer.clear # => # <IO::Buffer 0x00007fca40087c38+4 SLICE> # 0x00000000 00 00 00 00 .... buf.clear(1) # fill with 1 # => # <IO::Buffer 0x00007fca40087c38+4 SLICE> # 0x00000000 01 01 01 01 .... buffer.clear(2, 1, 2) # fill with 2, starting from offset 1, for 2 bytes # => # <IO::Buffer 0x00007fca40087c38+4 SLICE> # 0x00000000 01 02 02 01 .... buffer.clear(2, 1) # fill with 2, starting from offset 1 # => # <IO::Buffer 0x00007fca40087c38+4 SLICE> # 0x00000000 01 02 02 02 ....
static VALUE io_buffer_clear(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 0, 3); struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); uint8_t value = 0; if (argc >= 1) { value = NUM2UINT(argv[0]); } size_t offset = 0; if (argc >= 2) { offset = NUM2SIZET(argv[1]); } size_t length; if (argc >= 3) { length = NUM2SIZET(argv[2]); } else { length = data->size - offset; } rb_io_buffer_clear(self, value, offset, length); return self; }
Efficiently copy data from a source IO::Buffer
into the buffer, at offset
using memcpy
. For copying String
instances, see set_string
.
buffer = IO::Buffer.new(32) # => # #<IO::Buffer 0x0000555f5ca22520+32 INTERNAL> # 0x00000000 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ # 0x00000010 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ * buffer.copy(IO::Buffer.for("test"), 8) # => 4 -- size of data copied buffer # => # #<IO::Buffer 0x0000555f5cf8fe40+32 INTERNAL> # 0x00000000 00 00 00 00 00 00 00 00 74 65 73 74 00 00 00 00 ........test.... # 0x00000010 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ *
copy
can be used to put data into strings associated with buffer:
string= "data: " # => "data: " buffer = IO::Buffer.for(string) buffer.copy(IO::Buffer.for("test"), 5) # => 4 string # => "data:test"
Attempt to copy into a read-only buffer will fail:
File.write('test.txt', 'test') buffer = IO::Buffer.map(File.open('test.txt'), nil, 0, IO::Buffer::READONLY) buffer.copy(IO::Buffer.for("test"), 8) # in `copy': Buffer is not writable! (IO::Buffer::AccessError)
See ::map
for details of creation of mutable file mappings, this will work:
buffer = IO::Buffer.map(File.open('test.txt', 'r+')) buffer.copy(IO::Buffer.for("boom"), 0) # => 4 File.read('test.txt') # => "boom"
Attempt to copy the data which will need place outside of buffer’s bounds will fail:
buffer = IO::Buffer.new(2) buffer.copy(IO::Buffer.for('test'), 0) # in `copy': Specified offset+length exceeds source size! (ArgumentError)
static VALUE io_buffer_copy(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 1, 4); struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); VALUE source = argv[0]; const void *source_base; size_t source_size; rb_io_buffer_get_bytes_for_reading(source, &source_base, &source_size); return io_buffer_copy_from(data, source_base, source_size, argc-1, argv+1); }
Iterates over the buffer, yielding each value
of data_type
starting from offset
.
If count
is given, only count
values will be yielded.
Example:
IO::Buffer.for("Hello World").each(:U8, 2, 2) do |offset, value| puts "#{offset}: #{value}" end # 2: 108 # 3: 108
static VALUE io_buffer_each(int argc, VALUE *argv, VALUE self) { RETURN_ENUMERATOR_KW(self, argc, argv, RB_NO_KEYWORDS); const void *base; size_t size; rb_io_buffer_get_bytes_for_reading(self, &base, &size); ID data_type; if (argc >= 1) { data_type = RB_SYM2ID(argv[0]); } else { data_type = RB_IO_BUFFER_DATA_TYPE_U8; } size_t offset; if (argc >= 2) { offset = NUM2SIZET(argv[1]); } else { offset = 0; } size_t count; if (argc >= 3) { count = NUM2SIZET(argv[2]); } else { count = (size - offset) / io_buffer_data_type_size(data_type); } for (size_t i = 0; i < count; i++) { size_t current_offset = offset; VALUE value = rb_io_buffer_get_value(base, size, data_type, &offset); rb_yield_values(2, SIZET2NUM(current_offset), value); } return self; }
Iterates over the buffer, yielding each byte starting from offset
.
If count
is given, only count
bytes will be yielded.
Example:
IO::Buffer.for("Hello World").each_byte(2, 2) do |offset, byte| puts "#{offset}: #{byte}" end # 2: 108 # 3: 108
static VALUE io_buffer_each_byte(int argc, VALUE *argv, VALUE self) { RETURN_ENUMERATOR_KW(self, argc, argv, RB_NO_KEYWORDS); const void *base; size_t size; rb_io_buffer_get_bytes_for_reading(self, &base, &size); size_t offset; if (argc >= 2) { offset = NUM2SIZET(argv[1]); } else { offset = 0; } size_t count; if (argc >= 3) { count = NUM2SIZET(argv[2]); } else { count = (size - offset); } for (size_t i = 0; i < count; i++) { unsigned char *value = (unsigned char *)base + i + offset; rb_yield(RB_INT2FIX(*value)); } return self; }
If the buffer has 0 size: it is created by ::new
with size 0, or with ::for
from an empty string. (Note that empty files can’t be mapped, so the buffer created with ::map
will never be empty.)
static VALUE rb_io_buffer_empty_p(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return RBOOL(data->size == 0); }
The buffer is external if it references the memory which is not allocated or mapped by the buffer itself.
A buffer created using ::for
has an external reference to the string’s memory.
External buffer can’t be resized.
static VALUE rb_io_buffer_external_p(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return RBOOL(data->flags & RB_IO_BUFFER_EXTERNAL); }
If the buffer references memory, release it back to the operating system.
-
for a mapped buffer (e.g. from file): unmap.
-
for a buffer created from scratch: free memory.
-
for a buffer created from string: undo the association.
After the buffer is freed, no further operations can’t be performed on it.
You can resize a freed buffer to re-allocate it.
Example:
buffer = IO::Buffer.for('test') buffer.free # => #<IO::Buffer 0x0000000000000000+0 NULL> buffer.get_value(:U8, 0) # in `get_value': The buffer is not allocated! (IO::Buffer::AllocationError) buffer.get_string # in `get_string': The buffer is not allocated! (IO::Buffer::AllocationError) buffer.null? # => true
VALUE rb_io_buffer_free(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); if (data->flags & RB_IO_BUFFER_LOCKED) { rb_raise(rb_eIOBufferLockedError, "Buffer is locked!"); } io_buffer_free(data); return self; }
Read a chunk or all of the buffer into a string, in the specified encoding
. If no encoding is provided Encoding::BINARY
is used.
buffer = IO::Buffer.for('test') buffer.get_string # => "test" buffer.get_string(2) # => "st" buffer.get_string(2, 1) # => "s"
static VALUE io_buffer_get_string(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 0, 3); struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); const void *base; size_t size; io_buffer_get_bytes_for_reading(data, &base, &size); size_t offset = 0; size_t length = size; rb_encoding *encoding = rb_ascii8bit_encoding(); if (argc >= 1) { offset = NUM2SIZET(argv[0]); } if (argc >= 2 && !RB_NIL_P(argv[1])) { length = NUM2SIZET(argv[1]); } else { length = size - offset; } if (argc >= 3) { encoding = rb_find_encoding(argv[2]); } io_buffer_validate_range(data, offset, length); return rb_enc_str_new((const char*)base + offset, length, encoding); }
Read from buffer a value of type
at offset
. data_type
should be one of symbols:
-
:U8
: unsigned integer, 1 byte -
:S8
: signed integer, 1 byte -
:u16
: unsigned integer, 2 bytes, little-endian -
:U16
: unsigned integer, 2 bytes, big-endian -
:s16
: signed integer, 2 bytes, little-endian -
:S16
: signed integer, 2 bytes, big-endian -
:u32
: unsigned integer, 4 bytes, little-endian -
:U32
: unsigned integer, 4 bytes, big-endian -
:s32
: signed integer, 4 bytes, little-endian -
:S32
: signed integer, 4 bytes, big-endian -
:u64
: unsigned integer, 8 bytes, little-endian -
:U64
: unsigned integer, 8 bytes, big-endian -
:s64
: signed integer, 8 bytes, little-endian -
:S64
: signed integer, 8 bytes, big-endian -
:f32
: float, 4 bytes, little-endian -
:F32
: float, 4 bytes, big-endian -
:f64
: double, 8 bytes, little-endian -
:F64
: double, 8 bytes, big-endian
A data type refers specifically to the type of binary data that is stored in the buffer. For example, a :u32
data type is a 32-bit unsigned integer in little-endian format.
Example:
string = [1.5].pack('f') # => "\x00\x00\xC0?" IO::Buffer.for(string).get_value(:f32, 0) # => 1.5
static VALUE io_buffer_get_value(VALUE self, VALUE type, VALUE _offset) { const void *base; size_t size; size_t offset = NUM2SIZET(_offset); rb_io_buffer_get_bytes_for_reading(self, &base, &size); return rb_io_buffer_get_value(base, size, RB_SYM2ID(type), &offset); }
Similar to get_value
, except that it can handle multiple data types and returns an array of values.
Example:
string = [1.5, 2.5].pack('ff') IO::Buffer.for(string).get_values([:f32, :f32], 0) # => [1.5, 2.5]
static VALUE io_buffer_get_values(VALUE self, VALUE data_types, VALUE _offset) { size_t offset = NUM2SIZET(_offset); const void *base; size_t size; rb_io_buffer_get_bytes_for_reading(self, &base, &size); if (!RB_TYPE_P(data_types, T_ARRAY)) { rb_raise(rb_eArgError, "Argument data_types should be an array!"); } VALUE array = rb_ary_new_capa(RARRAY_LEN(data_types)); for (long i = 0; i < RARRAY_LEN(data_types); i++) { VALUE type = rb_ary_entry(data_types, i); VALUE value = rb_io_buffer_get_value(base, size, RB_SYM2ID(type), &offset); rb_ary_push(array, value); } return array; }
static VALUE rb_io_buffer_hexdump(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); VALUE result = Qnil; if (io_buffer_validate(data) && data->base) { result = rb_str_buf_new(data->size*3 + (data->size/16)*12 + 1); io_buffer_hexdump(result, 16, data->base, data->size, 1); } return result; }
Make an internal copy of the source buffer. Updates to the copy will not affect the source buffer.
source = IO::Buffer.for("Hello World") # => # #<IO::Buffer 0x00007fd598466830+11 EXTERNAL READONLY SLICE> # 0x00000000 48 65 6c 6c 6f 20 57 6f 72 6c 64 Hello World buffer = source.dup # => # #<IO::Buffer 0x0000558cbec03320+11 INTERNAL> # 0x00000000 48 65 6c 6c 6f 20 57 6f 72 6c 64 Hello World
static VALUE rb_io_buffer_initialize_copy(VALUE self, VALUE source) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); const void *source_base; size_t source_size; rb_io_buffer_get_bytes_for_reading(source, &source_base, &source_size); io_buffer_initialize(data, NULL, source_size, io_flags_for_size(source_size), Qnil); return io_buffer_copy_from(data, source_base, source_size, 0, NULL); }
VALUE rb_io_buffer_inspect(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); VALUE result = rb_io_buffer_to_s(self); if (io_buffer_validate(data)) { // Limit the maximum size genearted by inspect. if (data->size <= 256) { io_buffer_hexdump(result, 16, data->base, data->size, 0); } } return result; }
If the buffer is internal, meaning it references memory allocated by the buffer itself.
An internal buffer is not associated with any external memory (e.g. string) or file mapping.
Internal buffers are created using ::new
and is the default when the requested size is less than the IO::Buffer::PAGE_SIZE
and it was not requested to be mapped on creation.
Internal buffers can be resized, and such an operation will typically invalidate all slices, but not always.
static VALUE rb_io_buffer_internal_p(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return RBOOL(data->flags & RB_IO_BUFFER_INTERNAL); }
Allows to process a buffer in exclusive way, for concurrency-safety. While the block is performed, the buffer is considered locked, and no other code can enter the lock. Also, locked buffer can’t be changed with resize
or free
.
The following operations acquire a lock: resize
, free
.
Locking is not thread safe. It is designed as a safety net around non-blocking system calls. You can only share a buffer between threads with appropriate synchronisation techniques.
Example:
buffer = IO::Buffer.new(4) buffer.locked? #=> false Fiber.schedule do buffer.locked do buffer.write(io) # theoretical system call interface end end Fiber.schedule do # in `locked': Buffer already locked! (IO::Buffer::LockedError) buffer.locked do buffer.set_string("test", 0) end end
VALUE rb_io_buffer_locked(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); if (data->flags & RB_IO_BUFFER_LOCKED) { rb_raise(rb_eIOBufferLockedError, "Buffer already locked!"); } data->flags |= RB_IO_BUFFER_LOCKED; VALUE result = rb_yield(self); data->flags &= ~RB_IO_BUFFER_LOCKED; return result; }
If the buffer is locked, meaning it is inside locked
block execution. Locked buffer can’t be resized or freed, and another lock can’t be acquired on it.
Locking is not thread safe, but is a semantic used to ensure buffers don’t move while being used by a system call.
Example:
buffer.locked do buffer.write(io) # theoretical system call interface end
static VALUE rb_io_buffer_locked_p(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return RBOOL(data->flags & RB_IO_BUFFER_LOCKED); }
If the buffer is mapped, meaning it references memory mapped by the buffer.
Mapped buffers are either anonymous, if created by ::new
with the IO::Buffer::MAPPED
flag or if the size was at least IO::Buffer::PAGE_SIZE
, or backed by a file if created with ::map
.
Mapped buffers can usually be resized, and such an operation will typically invalidate all slices, but not always.
static VALUE rb_io_buffer_mapped_p(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return RBOOL(data->flags & RB_IO_BUFFER_MAPPED); }
Modify the source buffer in place by applying the binary NOT operation to the source.
source = IO::Buffer.for("1234567890").dup # Make a read/write copy. # => # #<IO::Buffer 0x000056307a33a450+10 INTERNAL> # 0x00000000 31 32 33 34 35 36 37 38 39 30 1234567890 source.not! # => # #<IO::Buffer 0x000056307a33a450+10 INTERNAL> # 0x00000000 ce cd cc cb ca c9 c8 c7 c6 cf ..........
static VALUE io_buffer_not_inplace(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); void *base; size_t size; io_buffer_get_bytes_for_writing(data, &base, &size); memory_not_inplace(base, size); return self; }
If the buffer was freed with free
or was never allocated in the first place.
static VALUE rb_io_buffer_null_p(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return RBOOL(data->base == NULL); }
Modify the source buffer in place by applying the binary OR operation to the source, using the mask, repeating as necessary.
source = IO::Buffer.for("1234567890").dup # Make a read/write copy. # => # #<IO::Buffer 0x000056307a272350+10 INTERNAL> # 0x00000000 31 32 33 34 35 36 37 38 39 30 1234567890 source.or!(IO::Buffer.for("\xFF\x00\x00\xFF")) # => # #<IO::Buffer 0x000056307a272350+10 INTERNAL> # 0x00000000 ff 32 33 ff ff 36 37 ff ff 30 .23..67..0
static VALUE io_buffer_or_inplace(VALUE self, VALUE mask) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); struct rb_io_buffer *mask_data = NULL; TypedData_Get_Struct(mask, struct rb_io_buffer, &rb_io_buffer_type, mask_data); io_buffer_check_mask(mask_data); io_buffer_check_overlaps(data, mask_data); void *base; size_t size; io_buffer_get_bytes_for_writing(data, &base, &size); memory_or_inplace(base, size, mask_data->base, mask_data->size); return self; }
Read at most length
bytes from io
into the buffer, starting at from
, and put it in buffer starting from specified offset
. If an error occurs, return -errno
.
If offset
is not given, put it at the beginning of the buffer.
Example:
IO::Buffer.for('test') do |buffer| p buffer # => # <IO::Buffer 0x00007fca40087c38+4 SLICE> # 0x00000000 74 65 73 74 test # take 2 bytes from the beginning of urandom, # put them in buffer starting from position 2 buffer.pread(File.open('/dev/urandom', 'rb'), 0, 2, 2) p buffer # => # <IO::Buffer 0x00007f3bc65f2a58+4 EXTERNAL SLICE> # 0x00000000 05 35 73 74 te.5 end
static VALUE io_buffer_pread(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 3, 4); VALUE io = argv[0]; rb_off_t from = NUM2OFFT(argv[1]); size_t length; if (rb_int_negative_p(argv[2])) { rb_raise(rb_eArgError, "Length can't be negative!"); } length = NUM2SIZET(argv[2]); size_t offset = 0; if (argc >= 4) { if (rb_int_negative_p(argv[3])) { rb_raise(rb_eArgError, "Offset can't be negative!"); } offset = NUM2SIZET(argv[3]); } return rb_io_buffer_pread(self, io, from, length, offset); }
Writes length
bytes from buffer into io
, starting at offset
in the buffer. If an error occurs, return -errno
.
If offset
is not given, the bytes are taken from the beginning of the buffer. If the offset
is given and is beyond the end of the file, the gap will be filled with null (0 value) bytes.
out = File.open('output.txt', File::RDWR) # open for read/write, no truncation IO::Buffer.for('1234567').pwrite(out, 2, 3, 1)
This leads to 234
(3 bytes, starting from position 1) being written into output.txt
, starting from file position 2.
static VALUE io_buffer_pwrite(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 3, 4); VALUE io = argv[0]; rb_off_t from = NUM2OFFT(argv[1]); size_t length; if (rb_int_negative_p(argv[2])) { rb_raise(rb_eArgError, "Length can't be negative!"); } length = NUM2SIZET(argv[2]); size_t offset = 0; if (argc >= 4) { if (rb_int_negative_p(argv[3])) { rb_raise(rb_eArgError, "Offset can't be negative!"); } offset = NUM2SIZET(argv[3]); } return rb_io_buffer_pwrite(self, io, from, length, offset); }
Read at most length
bytes from io
into the buffer, starting at offset
. If an error occurs, return -errno
.
If offset
is not given, read from the beginning of the buffer.
If length
is 0, read nothing.
Example:
IO::Buffer.for('test') do |buffer| p buffer # => # <IO::Buffer 0x00007fca40087c38+4 SLICE> # 0x00000000 74 65 73 74 test buffer.read(File.open('/dev/urandom', 'rb'), 2) p buffer # => # <IO::Buffer 0x00007f3bc65f2a58+4 EXTERNAL SLICE> # 0x00000000 05 35 73 74 .5st end
static VALUE io_buffer_read(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 2, 3); VALUE io = argv[0]; if (rb_int_negative_p(argv[1])) { rb_raise(rb_eArgError, "Length can't be negative!"); } size_t length = NUM2SIZET(argv[1]); size_t offset = 0; if (argc >= 3) { if (rb_int_negative_p(argv[2])) { rb_raise(rb_eArgError, "Offset can't be negative!"); } offset = NUM2SIZET(argv[2]); } return rb_io_buffer_read(self, io, length, offset); }
If the buffer is read only, meaning the buffer cannot be modified using set_value
, set_string
or copy
and similar.
Frozen strings and read-only files create read-only buffers.
static VALUE io_buffer_readonly_p(VALUE self) { return RBOOL(rb_io_buffer_readonly_p(self)); }
Resizes a buffer to a new_size
bytes, preserving its content. Depending on the old and new size, the memory area associated with the buffer might be either extended, or rellocated at different address with content being copied.
buffer = IO::Buffer.new(4) buffer.set_string("test", 0) buffer.resize(8) # resize to 8 bytes # => # #<IO::Buffer 0x0000555f5d1a1630+8 INTERNAL> # 0x00000000 74 65 73 74 00 00 00 00 test....
External buffer (created with ::for
), and locked buffer can not be resized.
static VALUE io_buffer_resize(VALUE self, VALUE size) { rb_io_buffer_resize(self, NUM2SIZET(size)); return self; }
Efficiently copy data from a source String
into the buffer, at offset
using memcpy
.
buf = IO::Buffer.new(8) # => # #<IO::Buffer 0x0000557412714a20+8 INTERNAL> # 0x00000000 00 00 00 00 00 00 00 00 ........ # set data starting from offset 1, take 2 bytes starting from string's # second buf.set_string('test', 1, 2, 1) # => 2 buf # => # #<IO::Buffer 0x0000557412714a20+8 INTERNAL> # 0x00000000 00 65 73 00 00 00 00 00 .es.....
See also copy
for examples of how buffer writing might be used for changing associated strings and files.
static VALUE io_buffer_set_string(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 1, 4); struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); VALUE string = rb_str_to_str(argv[0]); const void *source_base = RSTRING_PTR(string); size_t source_size = RSTRING_LEN(string); return io_buffer_copy_from(data, source_base, source_size, argc-1, argv+1); }
Write to a buffer a value
of type
at offset
. type
should be one of symbols described in get_value
.
buffer = IO::Buffer.new(8) # => # #<IO::Buffer 0x0000555f5c9a2d50+8 INTERNAL> # 0x00000000 00 00 00 00 00 00 00 00 buffer.set_value(:U8, 1, 111) # => 1 buffer # => # #<IO::Buffer 0x0000555f5c9a2d50+8 INTERNAL> # 0x00000000 00 6f 00 00 00 00 00 00 .o......
Note that if the type
is integer and value
is Float
, the implicit truncation is performed:
buffer = IO::Buffer.new(8) buffer.set_value(:U32, 0, 2.5) buffer # => # #<IO::Buffer 0x0000555f5c9a2d50+8 INTERNAL> # 0x00000000 00 00 00 02 00 00 00 00 # ^^ the same as if we'd pass just integer 2
static VALUE io_buffer_set_value(VALUE self, VALUE type, VALUE _offset, VALUE value) { void *base; size_t size; size_t offset = NUM2SIZET(_offset); rb_io_buffer_get_bytes_for_writing(self, &base, &size); rb_io_buffer_set_value(base, size, RB_SYM2ID(type), &offset, value); return SIZET2NUM(offset); }
Write values
of data_types
at offset
to the buffer. data_types
should be an array of symbols as described in get_value
. values
should be an array of values to write.
Example:
buffer = IO::Buffer.new(8) buffer.set_values([:U8, :U16], 0, [1, 2]) buffer # => # #<IO::Buffer 0x696f717561746978+8 INTERNAL> # 0x00000000 01 00 02 00 00 00 00 00 ........
static VALUE io_buffer_set_values(VALUE self, VALUE data_types, VALUE _offset, VALUE values) { if (!RB_TYPE_P(data_types, T_ARRAY)) { rb_raise(rb_eArgError, "Argument data_types should be an array!"); } if (!RB_TYPE_P(values, T_ARRAY)) { rb_raise(rb_eArgError, "Argument values should be an array!"); } if (RARRAY_LEN(data_types) != RARRAY_LEN(values)) { rb_raise(rb_eArgError, "Argument data_types and values should have the same length!"); } size_t offset = NUM2SIZET(_offset); void *base; size_t size; rb_io_buffer_get_bytes_for_writing(self, &base, &size); for (long i = 0; i < RARRAY_LEN(data_types); i++) { VALUE type = rb_ary_entry(data_types, i); VALUE value = rb_ary_entry(values, i); rb_io_buffer_set_value(base, size, RB_SYM2ID(type), &offset, value); } return SIZET2NUM(offset); }
Returns the size of the buffer that was explicitly set (on creation with ::new
or on resize
), or deduced on buffer’s creation from string or file.
VALUE rb_io_buffer_size(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return SIZET2NUM(data->size); }
Produce another IO::Buffer
which is a slice (or view into) the current one starting at offset
bytes and going for length
bytes.
The slicing happens without copying of memory, and the slice keeps being associated with the original buffer’s source (string, or file), if any.
If the offset is not given, it will be zero. If the offset is negative, it will raise an ArgumentError
.
If the length is not given, the slice will be as long as the original buffer minus the specified offset. If the length is negative, it will raise an ArgumentError
.
Raises RuntimeError
if the offset+length
is out of the current buffer’s bounds.
Example:
string = 'test' buffer = IO::Buffer.for(string) slice = buffer.slice # => # #<IO::Buffer 0x0000000108338e68+4 SLICE> # 0x00000000 74 65 73 74 test buffer.slice(2) # => # #<IO::Buffer 0x0000000108338e6a+2 SLICE> # 0x00000000 73 74 st slice = buffer.slice(1, 2) # => # #<IO::Buffer 0x00007fc3d34ebc49+2 SLICE> # 0x00000000 65 73 es # Put "o" into 0s position of the slice slice.set_string('o', 0) slice # => # #<IO::Buffer 0x00007fc3d34ebc49+2 SLICE> # 0x00000000 6f 73 os # it is also visible at position 1 of the original buffer buffer # => # #<IO::Buffer 0x00007fc3d31e2d80+4 SLICE> # 0x00000000 74 6f 73 74 tost # ...and original string string # => tost
static VALUE io_buffer_slice(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 0, 2); struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); size_t offset = 0, length = 0; if (argc > 0) { if (rb_int_negative_p(argv[0])) { rb_raise(rb_eArgError, "Offset can't be negative!"); } offset = NUM2SIZET(argv[0]); } if (argc > 1) { if (rb_int_negative_p(argv[1])) { rb_raise(rb_eArgError, "Length can't be negative!"); } length = NUM2SIZET(argv[1]); } else { length = data->size - offset; } return rb_io_buffer_slice(data, self, offset, length); }
Short representation of the buffer. It includes the address, size and symbolic flags. This format is subject to change.
puts IO::Buffer.new(4) # uses to_s internally # #<IO::Buffer 0x000055769f41b1a0+4 INTERNAL>
VALUE rb_io_buffer_to_s(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); VALUE result = rb_str_new_cstr("#<"); rb_str_append(result, rb_class_name(CLASS_OF(self))); rb_str_catf(result, " %p+%"PRIdSIZE, data->base, data->size); if (data->base == NULL) { rb_str_cat2(result, " NULL"); } if (data->flags & RB_IO_BUFFER_EXTERNAL) { rb_str_cat2(result, " EXTERNAL"); } if (data->flags & RB_IO_BUFFER_INTERNAL) { rb_str_cat2(result, " INTERNAL"); } if (data->flags & RB_IO_BUFFER_MAPPED) { rb_str_cat2(result, " MAPPED"); } if (data->flags & RB_IO_BUFFER_SHARED) { rb_str_cat2(result, " SHARED"); } if (data->flags & RB_IO_BUFFER_LOCKED) { rb_str_cat2(result, " LOCKED"); } if (data->flags & RB_IO_BUFFER_READONLY) { rb_str_cat2(result, " READONLY"); } if (data->source != Qnil) { rb_str_cat2(result, " SLICE"); } if (!io_buffer_validate(data)) { rb_str_cat2(result, " INVALID"); } return rb_str_cat2(result, ">"); }
Transfers ownership to a new buffer, deallocating the current one.
Example:
buffer = IO::Buffer.new('test') other = buffer.transfer other # => # #<IO::Buffer 0x00007f136a15f7b0+4 SLICE> # 0x00000000 74 65 73 74 test buffer # => # #<IO::Buffer 0x0000000000000000+0 NULL> buffer.null? # => true
VALUE rb_io_buffer_transfer(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); if (data->flags & RB_IO_BUFFER_LOCKED) { rb_raise(rb_eIOBufferLockedError, "Cannot transfer ownership of locked buffer!"); } VALUE instance = rb_io_buffer_type_allocate(rb_class_of(self)); struct rb_io_buffer *transferred; TypedData_Get_Struct(instance, struct rb_io_buffer, &rb_io_buffer_type, transferred); *transferred = *data; io_buffer_zero(data); return instance; }
Returns whether the buffer data is accessible.
A buffer becomes invalid if it is a slice of another buffer which has been freed.
static VALUE rb_io_buffer_valid_p(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); return RBOOL(io_buffer_validate(data)); }
Returns an array of values of data_type
starting from offset
.
If count
is given, only count
values will be returned.
Example:
IO::Buffer.for("Hello World").values(:U8, 2, 2) # => [108, 108]
static VALUE io_buffer_values(int argc, VALUE *argv, VALUE self) { const void *base; size_t size; rb_io_buffer_get_bytes_for_reading(self, &base, &size); ID data_type; if (argc >= 1) { data_type = RB_SYM2ID(argv[0]); } else { data_type = RB_IO_BUFFER_DATA_TYPE_U8; } size_t offset; if (argc >= 2) { offset = NUM2SIZET(argv[1]); } else { offset = 0; } size_t count; if (argc >= 3) { count = NUM2SIZET(argv[2]); } else { count = (size - offset) / io_buffer_data_type_size(data_type); } VALUE array = rb_ary_new_capa(count); for (size_t i = 0; i < count; i++) { VALUE value = rb_io_buffer_get_value(base, size, data_type, &offset); rb_ary_push(array, value); } return array; }
Writes length
bytes from buffer into io
, starting at offset
in the buffer. If an error occurs, return -errno
.
If offset
is not given, the bytes are taken from the beginning of the buffer.
out = File.open('output.txt', 'wb') IO::Buffer.for('1234567').write(out, 3)
This leads to 123
being written into output.txt
static VALUE io_buffer_write(int argc, VALUE *argv, VALUE self) { rb_check_arity(argc, 2, 3); VALUE io = argv[0]; if (rb_int_negative_p(argv[1])) { rb_raise(rb_eArgError, "Length can't be negative!"); } size_t length = NUM2SIZET(argv[1]); size_t offset = 0; if (argc >= 3) { if (rb_int_negative_p(argv[2])) { rb_raise(rb_eArgError, "Offset can't be negative!"); } offset = NUM2SIZET(argv[2]); } return rb_io_buffer_write(self, io, length, offset); }
Modify the source buffer in place by applying the binary XOR operation to the source, using the mask, repeating as necessary.
source = IO::Buffer.for("1234567890").dup # Make a read/write copy. # => # #<IO::Buffer 0x000056307a25b3e0+10 INTERNAL> # 0x00000000 31 32 33 34 35 36 37 38 39 30 1234567890 source.xor!(IO::Buffer.for("\xFF\x00\x00\xFF")) # => # #<IO::Buffer 0x000056307a25b3e0+10 INTERNAL> # 0x00000000 ce 32 33 cb ca 36 37 c7 c6 30 .23..67..0
static VALUE io_buffer_xor_inplace(VALUE self, VALUE mask) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); struct rb_io_buffer *mask_data = NULL; TypedData_Get_Struct(mask, struct rb_io_buffer, &rb_io_buffer_type, mask_data); io_buffer_check_mask(mask_data); io_buffer_check_overlaps(data, mask_data); void *base; size_t size; io_buffer_get_bytes_for_writing(data, &base, &size); memory_xor_inplace(base, size, mask_data->base, mask_data->size); return self; }
Generate a new buffer the same size as the source by applying the binary OR operation to the source, using the mask, repeating as necessary.
IO::Buffer.for("1234567890") | IO::Buffer.for("\xFF\x00\x00\xFF") # => # #<IO::Buffer 0x0000561785ae3480+10 INTERNAL> # 0x00000000 ff 32 33 ff ff 36 37 ff ff 30 .23..67..0
static VALUE io_buffer_or(VALUE self, VALUE mask) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); struct rb_io_buffer *mask_data = NULL; TypedData_Get_Struct(mask, struct rb_io_buffer, &rb_io_buffer_type, mask_data); io_buffer_check_mask(mask_data); VALUE output = rb_io_buffer_new(NULL, data->size, io_flags_for_size(data->size)); struct rb_io_buffer *output_data = NULL; TypedData_Get_Struct(output, struct rb_io_buffer, &rb_io_buffer_type, output_data); memory_or(output_data->base, data->base, data->size, mask_data->base, mask_data->size); return output; }
Generate a new buffer the same size as the source by applying the binary NOT operation to the source.
~IO::Buffer.for("1234567890") # => # #<IO::Buffer 0x000055a5ac42f120+10 INTERNAL> # 0x00000000 ce cd cc cb ca c9 c8 c7 c6 cf ..........
static VALUE io_buffer_not(VALUE self) { struct rb_io_buffer *data = NULL; TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data); VALUE output = rb_io_buffer_new(NULL, data->size, io_flags_for_size(data->size)); struct rb_io_buffer *output_data = NULL; TypedData_Get_Struct(output, struct rb_io_buffer, &rb_io_buffer_type, output_data); memory_not(output_data->base, data->base, data->size); return output; }