1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
ruby--ruby/io_buffer.c

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

3300 lines
92 KiB
C
Raw Normal View History

2021-07-02 06:41:16 -04:00
/**********************************************************************
io_buffer.c
Copyright (C) 2021 Samuel Grant Dawson Williams
**********************************************************************/
#include "ruby/io.h"
#include "ruby/io/buffer.h"
#include "ruby/fiber/scheduler.h"
2021-07-02 06:41:16 -04:00
#include "internal.h"
#include "internal/array.h"
2021-07-02 06:41:16 -04:00
#include "internal/bits.h"
2021-11-09 21:42:57 -05:00
#include "internal/error.h"
#include "internal/numeric.h"
#include "internal/string.h"
#include "internal/thread.h"
2021-07-02 06:41:16 -04:00
VALUE rb_cIOBuffer;
2021-12-19 15:59:45 -05:00
VALUE rb_eIOBufferLockedError;
VALUE rb_eIOBufferAllocationError;
VALUE rb_eIOBufferAccessError;
2021-12-19 15:59:45 -05:00
VALUE rb_eIOBufferInvalidatedError;
VALUE rb_eIOBufferMaskError;
2021-12-19 15:59:45 -05:00
2021-07-02 06:41:16 -04:00
size_t RUBY_IO_BUFFER_PAGE_SIZE;
2021-12-18 15:56:52 -05:00
size_t RUBY_IO_BUFFER_DEFAULT_SIZE;
2021-07-02 06:41:16 -04:00
#ifdef _WIN32
#else
#include <unistd.h>
#include <sys/mman.h>
#endif
struct rb_io_buffer {
void *base;
size_t size;
enum rb_io_buffer_flags flags;
#if defined(_WIN32)
HANDLE mapping;
#endif
VALUE source;
};
2021-11-10 02:41:26 -05:00
static inline void *
io_buffer_map_memory(size_t size, int flags)
2021-07-02 06:41:16 -04:00
{
#if defined(_WIN32)
void * base = VirtualAlloc(0, size, MEM_COMMIT, PAGE_READWRITE);
if (!base) {
rb_sys_fail("io_buffer_map_memory:VirtualAlloc");
}
#else
int mmap_flags = MAP_ANONYMOUS;
if (flags & RB_IO_BUFFER_SHARED) {
mmap_flags |= MAP_SHARED;
} else {
mmap_flags |= MAP_PRIVATE;
}
void * base = mmap(NULL, size, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
2021-07-02 06:41:16 -04:00
if (base == MAP_FAILED) {
rb_sys_fail("io_buffer_map_memory:mmap");
}
#endif
return base;
}
2021-11-10 02:41:26 -05:00
static void
io_buffer_map_file(struct rb_io_buffer *data, int descriptor, size_t size, rb_off_t offset, enum rb_io_buffer_flags flags)
2021-07-02 06:41:16 -04:00
{
#if defined(_WIN32)
HANDLE file = (HANDLE)_get_osfhandle(descriptor);
if (!file) rb_sys_fail("io_buffer_map_descriptor:_get_osfhandle");
DWORD protect = PAGE_READONLY, access = FILE_MAP_READ;
2021-12-20 05:06:21 -05:00
if (flags & RB_IO_BUFFER_READONLY) {
data->flags |= RB_IO_BUFFER_READONLY;
2021-11-10 02:41:26 -05:00
}
else {
2021-07-02 06:41:16 -04:00
protect = PAGE_READWRITE;
access = FILE_MAP_WRITE;
}
HANDLE mapping = CreateFileMapping(file, NULL, protect, 0, 0, NULL);
if (!mapping) rb_sys_fail("io_buffer_map_descriptor:CreateFileMapping");
if (flags & RB_IO_BUFFER_PRIVATE) {
access |= FILE_MAP_COPY;
data->flags |= RB_IO_BUFFER_PRIVATE;
}
else {
// This buffer refers to external data.
data->flags |= RB_IO_BUFFER_EXTERNAL;
data->flags |= RB_IO_BUFFER_SHARED;
2021-07-02 06:41:16 -04:00
}
void *base = MapViewOfFile(mapping, access, (DWORD)(offset >> 32), (DWORD)(offset & 0xFFFFFFFF), size);
if (!base) {
CloseHandle(mapping);
rb_sys_fail("io_buffer_map_file:MapViewOfFile");
}
data->mapping = mapping;
#else
int protect = PROT_READ, access = 0;
2021-12-20 05:06:21 -05:00
if (flags & RB_IO_BUFFER_READONLY) {
data->flags |= RB_IO_BUFFER_READONLY;
2021-11-10 02:41:26 -05:00
}
else {
2021-07-02 06:41:16 -04:00
protect |= PROT_WRITE;
}
if (flags & RB_IO_BUFFER_PRIVATE) {
data->flags |= RB_IO_BUFFER_PRIVATE;
2021-11-10 02:41:26 -05:00
}
else {
// This buffer refers to external data.
data->flags |= RB_IO_BUFFER_EXTERNAL;
data->flags |= RB_IO_BUFFER_SHARED;
2021-07-02 06:41:16 -04:00
access |= MAP_SHARED;
}
void *base = mmap(NULL, size, protect, access, descriptor, offset);
if (base == MAP_FAILED) {
rb_sys_fail("io_buffer_map_file:mmap");
}
#endif
data->base = base;
data->size = size;
data->flags |= RB_IO_BUFFER_MAPPED;
}
2021-11-10 02:41:26 -05:00
static inline void
io_buffer_unmap(void* base, size_t size)
2021-07-02 06:41:16 -04:00
{
#ifdef _WIN32
VirtualFree(base, 0, MEM_RELEASE);
#else
munmap(base, size);
#endif
}
2021-11-10 02:41:26 -05:00
static void
io_buffer_experimental(void)
2021-11-09 21:42:57 -05:00
{
static int warned = 0;
if (warned) return;
warned = 1;
if (rb_warning_category_enabled_p(RB_WARN_CATEGORY_EXPERIMENTAL)) {
rb_category_warn(RB_WARN_CATEGORY_EXPERIMENTAL,
"IO::Buffer is experimental and both the Ruby and C interface may change in the future!"
);
}
}
2021-11-10 02:41:26 -05:00
static void
io_buffer_zero(struct rb_io_buffer *data)
2021-07-02 06:41:16 -04:00
{
data->base = NULL;
data->size = 0;
#if defined(_WIN32)
data->mapping = NULL;
#endif
data->source = Qnil;
}
2021-07-02 06:41:16 -04:00
static void
io_buffer_initialize(struct rb_io_buffer *data, void *base, size_t size, enum rb_io_buffer_flags flags, VALUE source)
{
2021-07-02 06:41:16 -04:00
if (base) {
// If we are provided a pointer, we use it.
2021-11-10 02:41:26 -05:00
}
else if (size) {
// If we are provided a non-zero size, we allocate it:
if (flags & RB_IO_BUFFER_INTERNAL) {
base = calloc(size, 1);
2021-11-10 02:41:26 -05:00
}
else if (flags & RB_IO_BUFFER_MAPPED) {
base = io_buffer_map_memory(size, flags);
2021-07-02 06:41:16 -04:00
}
if (!base) {
rb_raise(rb_eIOBufferAllocationError, "Could not allocate buffer!");
}
}
else {
// Otherwise we don't do anything.
return;
2021-07-02 06:41:16 -04:00
}
data->base = base;
data->size = size;
data->flags = flags;
2021-07-02 06:41:16 -04:00
data->source = source;
}
2021-11-10 02:41:26 -05:00
static int
io_buffer_free(struct rb_io_buffer *data)
2021-07-02 06:41:16 -04:00
{
if (data->base) {
if (data->flags & RB_IO_BUFFER_INTERNAL) {
free(data->base);
}
if (data->flags & RB_IO_BUFFER_MAPPED) {
io_buffer_unmap(data->base, data->size);
}
// Previously we had this, but we found out due to the way GC works, we
// can't refer to any other Ruby objects here.
// if (RB_TYPE_P(data->source, T_STRING)) {
// rb_str_unlocktmp(data->source);
// }
2021-07-02 06:41:16 -04:00
data->base = NULL;
#if defined(_WIN32)
if (data->mapping) {
CloseHandle(data->mapping);
data->mapping = NULL;
}
#endif
data->size = 0;
data->flags = 0;
data->source = Qnil;
2021-07-02 06:41:16 -04:00
return 1;
}
return 0;
}
2021-11-10 02:41:26 -05:00
void
rb_io_buffer_type_mark(void *_data)
2021-07-02 06:41:16 -04:00
{
struct rb_io_buffer *data = _data;
rb_gc_mark(data->source);
}
2021-11-10 02:41:26 -05:00
void
rb_io_buffer_type_free(void *_data)
2021-07-02 06:41:16 -04:00
{
struct rb_io_buffer *data = _data;
io_buffer_free(data);
free(data);
}
2021-11-10 02:41:26 -05:00
size_t
rb_io_buffer_type_size(const void *_data)
2021-07-02 06:41:16 -04:00
{
const struct rb_io_buffer *data = _data;
size_t total = sizeof(struct rb_io_buffer);
if (data->flags) {
total += data->size;
}
return total;
}
static const rb_data_type_t rb_io_buffer_type = {
.wrap_struct_name = "IO::Buffer",
.function = {
.dmark = rb_io_buffer_type_mark,
.dfree = rb_io_buffer_type_free,
.dsize = rb_io_buffer_type_size,
},
.data = NULL,
.flags = RUBY_TYPED_FREE_IMMEDIATELY,
};
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_type_allocate(VALUE self)
2021-07-02 06:41:16 -04:00
{
struct rb_io_buffer *data = NULL;
VALUE instance = TypedData_Make_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_zero(data);
2021-07-02 06:41:16 -04:00
return instance;
}
static VALUE
io_buffer_for_make_instance(VALUE klass, VALUE string)
{
VALUE instance = rb_io_buffer_type_allocate(klass);
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(instance, struct rb_io_buffer, &rb_io_buffer_type, data);
enum rb_io_buffer_flags flags = RB_IO_BUFFER_EXTERNAL;
if (RB_OBJ_FROZEN(string))
flags |= RB_IO_BUFFER_READONLY;
io_buffer_initialize(data, RSTRING_PTR(string), RSTRING_LEN(string), flags, string);
return instance;
}
struct io_buffer_for_yield_instance_arguments {
VALUE klass;
VALUE string;
VALUE instance;
};
static VALUE
2022-07-27 05:42:27 -04:00
io_buffer_for_yield_instance(VALUE _arguments)
{
struct io_buffer_for_yield_instance_arguments *arguments = (struct io_buffer_for_yield_instance_arguments *)_arguments;
rb_str_locktmp(arguments->string);
arguments->instance = io_buffer_for_make_instance(arguments->klass, arguments->string);
return rb_yield(arguments->instance);
}
static VALUE
io_buffer_for_yield_instance_ensure(VALUE _arguments)
{
struct io_buffer_for_yield_instance_arguments *arguments = (struct io_buffer_for_yield_instance_arguments *)_arguments;
if (arguments->instance != Qnil) {
rb_io_buffer_free(arguments->instance);
}
rb_str_unlocktmp(arguments->string);
return Qnil;
}
/*
* call-seq:
* IO::Buffer.for(string) -> readonly io_buffer
* IO::Buffer.for(string) {|io_buffer| ... read/write io_buffer ...}
*
* 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.
*
* 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,
};
2021-12-19 15:43:22 -05:00
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);
}
}
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_new(void *base, size_t size, enum rb_io_buffer_flags flags)
2021-07-02 06:41:16 -04:00
{
VALUE instance = rb_io_buffer_type_allocate(rb_cIOBuffer);
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(instance, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_initialize(data, base, size, flags, Qnil);
2021-07-02 06:41:16 -04:00
return instance;
}
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_map(VALUE io, size_t size, rb_off_t offset, enum rb_io_buffer_flags flags)
2021-07-02 06:41:16 -04:00
{
io_buffer_experimental();
2021-07-02 06:41:16 -04:00
VALUE instance = rb_io_buffer_type_allocate(rb_cIOBuffer);
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(instance, struct rb_io_buffer, &rb_io_buffer_type, data);
int descriptor = rb_io_descriptor(io);
io_buffer_map_file(data, descriptor, size, offset, flags);
return instance;
}
/*
* call-seq: IO::Buffer.map(file, [size, [offset, [flags]]]) -> io_buffer
*
* 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.
*/
2021-11-10 02:41:26 -05:00
static VALUE
io_buffer_map(int argc, VALUE *argv, VALUE klass)
2021-07-02 06:41:16 -04:00
{
rb_check_arity(argc, 1, 4);
2021-07-02 06:41:16 -04:00
// We might like to handle a string path?
2021-07-02 06:41:16 -04:00
VALUE io = argv[0];
size_t size;
if (argc >= 2 && !RB_NIL_P(argv[1])) {
2021-07-02 06:41:16 -04:00
size = RB_NUM2SIZE(argv[1]);
2021-11-10 02:41:26 -05:00
}
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;
}
2021-07-02 06:41:16 -04:00
}
rb_off_t offset = 0;
2021-07-02 06:41:16 -04:00
if (argc >= 3) {
offset = NUM2OFFT(argv[2]);
}
enum rb_io_buffer_flags flags = 0;
2021-07-02 06:41:16 -04:00
if (argc >= 4) {
flags = RB_NUM2UINT(argv[3]);
}
return rb_io_buffer_map(io, size, offset, flags);
}
// Compute the optimal allocation flags for a buffer of the given size.
static inline enum rb_io_buffer_flags
io_flags_for_size(size_t size)
{
if (size >= RUBY_IO_BUFFER_PAGE_SIZE) {
return RB_IO_BUFFER_MAPPED;
}
return RB_IO_BUFFER_INTERNAL;
}
/*
* call-seq: IO::Buffer.new([size = DEFAULT_SIZE, [flags = 0]]) -> io_buffer
*
* 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::Bufer::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
*/
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_initialize(int argc, VALUE *argv, VALUE self)
2021-07-02 06:41:16 -04:00
{
io_buffer_experimental();
rb_check_arity(argc, 0, 2);
2021-07-02 06:41:16 -04:00
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
2021-12-18 15:56:52 -05:00
size_t size;
if (argc > 0) {
size = RB_NUM2SIZE(argv[0]);
}
else {
2021-12-18 15:56:52 -05:00
size = RUBY_IO_BUFFER_DEFAULT_SIZE;
}
2021-07-02 06:41:16 -04:00
enum rb_io_buffer_flags flags = 0;
if (argc >= 2) {
flags = RB_NUM2UINT(argv[1]);
2021-11-10 02:41:26 -05:00
}
else {
flags |= io_flags_for_size(size);
2021-07-02 06:41:16 -04:00
}
io_buffer_initialize(data, NULL, size, flags, Qnil);
return self;
}
2021-11-10 02:41:26 -05:00
static int
io_buffer_validate_slice(VALUE source, void *base, size_t size)
2021-07-02 06:41:16 -04:00
{
void *source_base = NULL;
2021-07-02 06:41:16 -04:00
size_t source_size = 0;
if (RB_TYPE_P(source, T_STRING)) {
RSTRING_GETMEM(source, source_base, source_size);
2021-11-10 02:41:26 -05:00
}
else {
rb_io_buffer_get_bytes(source, &source_base, &source_size);
2021-07-02 06:41:16 -04:00
}
// Source is invalid:
if (source_base == NULL) return 0;
// Base is out of range:
if (base < source_base) return 0;
const void *source_end = (char*)source_base + source_size;
const void *end = (char*)base + size;
// End is out of range:
if (end > source_end) return 0;
// It seems okay:
return 1;
}
2021-11-10 02:41:26 -05:00
static int
io_buffer_validate(struct rb_io_buffer *data)
2021-07-02 06:41:16 -04:00
{
if (data->source != Qnil) {
// Only slices incur this overhead, unfortunately... better safe than sorry!
return io_buffer_validate_slice(data->source, data->base, data->size);
2021-11-10 02:41:26 -05:00
}
2021-11-10 03:46:32 -05:00
else {
2021-07-02 06:41:16 -04:00
return 1;
}
}
/*
* call-seq: to_s -> string
*
* 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>
*/
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_to_s(VALUE self)
2021-07-02 06:41:16 -04:00
{
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)));
2021-11-10 03:07:58 -05:00
rb_str_catf(result, " %p+%"PRIdSIZE, data->base, data->size);
2021-07-02 06:41:16 -04:00
if (data->base == NULL) {
rb_str_cat2(result, " NULL");
}
if (data->flags & RB_IO_BUFFER_EXTERNAL) {
rb_str_cat2(result, " EXTERNAL");
}
2021-07-02 06:41:16 -04:00
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");
}
2021-07-02 06:41:16 -04:00
if (data->flags & RB_IO_BUFFER_LOCKED) {
rb_str_cat2(result, " LOCKED");
}
2021-12-20 05:06:21 -05:00
if (data->flags & RB_IO_BUFFER_READONLY) {
rb_str_cat2(result, " READONLY");
2021-07-02 06:41:16 -04:00
}
if (data->source != Qnil) {
rb_str_cat2(result, " SLICE");
}
if (!io_buffer_validate(data)) {
rb_str_cat2(result, " INVALID");
}
return rb_str_cat2(result, ">");
}
2021-11-10 02:41:26 -05:00
static VALUE
io_buffer_hexdump(VALUE string, size_t width, char *base, size_t size, int first)
2021-07-02 06:41:16 -04:00
{
char *text = alloca(width+1);
text[width] = '\0';
for (size_t offset = 0; offset < size; offset += width) {
memset(text, '\0', width);
if (first) {
rb_str_catf(string, "0x%08" PRIxSIZE " ", offset);
first = 0;
}
else {
rb_str_catf(string, "\n0x%08" PRIxSIZE " ", offset);
}
2021-07-02 06:41:16 -04:00
for (size_t i = 0; i < width; i += 1) {
if (offset+i < size) {
unsigned char value = ((unsigned char*)base)[offset+i];
if (value < 127 && isprint(value)) {
text[i] = (char)value;
2021-11-10 02:41:26 -05:00
}
2021-11-10 03:46:32 -05:00
else {
2021-07-02 06:41:16 -04:00
text[i] = '.';
}
rb_str_catf(string, " %02x", value);
2021-11-10 02:41:26 -05:00
}
2021-11-10 03:46:32 -05:00
else {
2021-07-02 06:41:16 -04:00
rb_str_cat2(string, " ");
}
}
rb_str_catf(string, " %s", text);
}
return string;
}
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;
}
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_inspect(VALUE self)
2021-07-02 06:41:16 -04:00
{
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);
}
2021-07-02 06:41:16 -04:00
}
return result;
}
/*
* call-seq: size -> integer
*
* 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.
*/
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_size(VALUE self)
2021-07-02 06:41:16 -04:00
{
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
return SIZET2NUM(data->size);
}
/*
* call-seq: valid? -> true or false
*
* 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));
}
/*
* call-seq: null? -> true or false
*
* 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);
}
/*
2022-01-02 03:43:01 -05:00
* call-seq: empty? -> true or false
*
2022-01-02 03:43:01 -05:00
* 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.)
*/
2021-12-20 05:06:21 -05:00
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);
2021-12-20 05:06:21 -05:00
}
2022-01-02 03:43:01 -05:00
/*
* call-seq: external? -> true or false
*
* 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.
*/
2021-11-10 02:41:26 -05:00
static VALUE
rb_io_buffer_external_p(VALUE self)
2021-07-02 06:41:16 -04:00
{
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);
2021-07-02 06:41:16 -04:00
}
/*
* call-seq: internal? -> true or false
*
* 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.
*/
2021-11-10 02:41:26 -05:00
static VALUE
rb_io_buffer_internal_p(VALUE self)
2021-07-02 06:41:16 -04:00
{
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);
2021-07-02 06:41:16 -04:00
}
/*
* call-seq: mapped? -> true or false
*
* 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.
*/
2021-11-10 02:41:26 -05:00
static VALUE
rb_io_buffer_mapped_p(VALUE self)
2021-07-02 06:41:16 -04:00
{
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);
2021-07-02 06:41:16 -04:00
}
/*
* call-seq: shared? -> true or false
*
* If the buffer is _shared_, meaning it references memory that can be shared
* with other processes (and thus might change without being modified
* locally).
*/
static VALUE
rb_io_buffer_shared_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_SHARED);
}
/*
* call-seq: locked? -> true or false
*
* 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
*/
2021-11-10 02:41:26 -05:00
static VALUE
rb_io_buffer_locked_p(VALUE self)
2021-07-02 06:41:16 -04:00
{
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);
2021-07-02 06:41:16 -04:00
}
2021-12-20 05:06:21 -05:00
int
rb_io_buffer_readonly_p(VALUE self)
2021-07-02 06:41:16 -04:00
{
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
2021-12-20 05:06:21 -05:00
return data->flags & RB_IO_BUFFER_READONLY;
}
2022-01-02 03:43:01 -05:00
/*
* call-seq: readonly? -> true or false
*
* If the buffer is <i>read only</i>, 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.
*/
2021-12-20 05:06:21 -05:00
static VALUE
io_buffer_readonly_p(VALUE self)
{
return RBOOL(rb_io_buffer_readonly_p(self));
2021-07-02 06:41:16 -04:00
}
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_lock(VALUE self)
2021-07-02 06:41:16 -04:00
{
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) {
2021-12-19 15:59:45 -05:00
rb_raise(rb_eIOBufferLockedError, "Buffer already locked!");
2021-07-02 06:41:16 -04:00
}
data->flags |= RB_IO_BUFFER_LOCKED;
return self;
}
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_unlock(VALUE self)
2021-07-02 06:41:16 -04:00
{
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)) {
2021-12-19 15:59:45 -05:00
rb_raise(rb_eIOBufferLockedError, "Buffer not locked!");
2021-07-02 06:41:16 -04:00
}
data->flags &= ~RB_IO_BUFFER_LOCKED;
return self;
}
int
rb_io_buffer_try_unlock(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) {
data->flags &= ~RB_IO_BUFFER_LOCKED;
return 1;
}
return 0;
}
/*
* call-seq: locked { ... }
*
* 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
2022-01-02 03:43:01 -05:00
* buffer.set_string("test", 0)
* end
* end
*/
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_locked(VALUE self)
2021-07-02 06:41:16 -04:00
{
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) {
2021-12-19 15:59:45 -05:00
rb_raise(rb_eIOBufferLockedError, "Buffer already locked!");
2021-07-02 06:41:16 -04:00
}
data->flags |= RB_IO_BUFFER_LOCKED;
VALUE result = rb_yield(self);
data->flags &= ~RB_IO_BUFFER_LOCKED;
return result;
}
/*
* call-seq: free -> self
*
* 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
*/
2021-11-10 02:41:26 -05:00
VALUE
rb_io_buffer_free(VALUE self)
2021-07-02 06:41:16 -04:00
{
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) {
2021-12-19 15:59:45 -05:00
rb_raise(rb_eIOBufferLockedError, "Buffer is locked!");
2021-07-02 06:41:16 -04:00
}
io_buffer_free(data);
return self;
}
2021-11-10 02:41:26 -05:00
static inline void
io_buffer_validate_range(struct rb_io_buffer *data, size_t offset, size_t length)
2021-07-02 06:41:16 -04:00
{
if (offset + length > data->size) {
rb_raise(rb_eArgError, "Specified offset+length exceeds data size!");
2021-07-02 06:41:16 -04:00
}
}
/*
* call-seq: slice([offset = 0, [length]]) -> io_buffer
*
* 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 <tt>offset+length</tt> 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
rb_io_buffer_slice(struct rb_io_buffer *data, VALUE self, size_t offset, size_t length)
2021-07-02 06:41:16 -04:00
{
io_buffer_validate_range(data, offset, length);
2021-07-02 06:41:16 -04:00
VALUE instance = rb_io_buffer_type_allocate(rb_class_of(self));
struct rb_io_buffer *slice = NULL;
TypedData_Get_Struct(instance, struct rb_io_buffer, &rb_io_buffer_type, slice);
slice->base = (char*)data->base + offset;
slice->size = length;
// The source should be the root buffer:
if (data->source != Qnil)
slice->source = data->source;
else
slice->source = self;
return instance;
}
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);
}
int
rb_io_buffer_get_bytes(VALUE self, void **base, size_t *size)
{
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
if (io_buffer_validate(data)) {
if (data->base) {
*base = data->base;
*size = data->size;
return data->flags;
}
}
*base = NULL;
*size = 0;
return 0;
}
static inline void
io_buffer_get_bytes_for_writing(struct rb_io_buffer *data, void **base, size_t *size)
2021-07-02 06:41:16 -04:00
{
2021-12-20 05:06:21 -05:00
if (data->flags & RB_IO_BUFFER_READONLY) {
rb_raise(rb_eIOBufferAccessError, "Buffer is not writable!");
2021-07-02 06:41:16 -04:00
}
if (!io_buffer_validate(data)) {
rb_raise(rb_eIOBufferInvalidatedError, "Buffer is invalid!");
2021-07-02 06:41:16 -04:00
}
if (data->base) {
2021-07-02 06:41:16 -04:00
*base = data->base;
*size = data->size;
return;
}
rb_raise(rb_eIOBufferAllocationError, "The buffer is not allocated!");
2021-07-02 06:41:16 -04:00
}
2021-12-20 03:22:46 -05:00
void
rb_io_buffer_get_bytes_for_writing(VALUE self, void **base, size_t *size)
2021-12-20 03:22:46 -05:00
{
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_get_bytes_for_writing(data, base, size);
2021-12-20 03:22:46 -05:00
}
static void
io_buffer_get_bytes_for_reading(struct rb_io_buffer *data, const void **base, size_t *size)
2021-07-02 06:41:16 -04:00
{
if (!io_buffer_validate(data)) {
2021-12-19 15:59:45 -05:00
rb_raise(rb_eIOBufferInvalidatedError, "Buffer has been invalidated!");
2021-07-02 06:41:16 -04:00
}
if (data->base) {
2021-07-02 06:41:16 -04:00
*base = data->base;
*size = data->size;
return;
}
rb_raise(rb_eIOBufferAllocationError, "The buffer is not allocated!");
2021-07-02 06:41:16 -04:00
}
void
rb_io_buffer_get_bytes_for_reading(VALUE self, const void **base, size_t *size)
{
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_get_bytes_for_reading(data, base, size);
}
/*
* call-seq: transfer -> new_io_buffer
*
* 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)
2021-07-02 06:41:16 -04:00
{
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) {
2021-12-19 15:59:45 -05:00
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;
2021-07-02 06:41:16 -04:00
}
static void
io_buffer_resize_clear(struct rb_io_buffer *data, void* base, size_t size)
2021-07-02 06:41:16 -04:00
{
if (size > data->size) {
memset((unsigned char*)base+data->size, 0, size - data->size);
2021-07-02 06:41:16 -04:00
}
}
static void
io_buffer_resize_copy(struct rb_io_buffer *data, size_t size)
{
// Slow path:
struct rb_io_buffer resized;
io_buffer_initialize(&resized, NULL, size, io_flags_for_size(size), Qnil);
2021-07-02 06:41:16 -04:00
if (data->base) {
size_t preserve = data->size;
if (preserve > size) preserve = size;
memcpy(resized.base, data->base, preserve);
io_buffer_resize_clear(data, resized.base, size);
2021-07-02 06:41:16 -04:00
}
io_buffer_free(data);
*data = resized;
}
void
rb_io_buffer_resize(VALUE self, size_t size)
{
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
2021-07-02 06:41:16 -04:00
if (data->flags & RB_IO_BUFFER_LOCKED) {
2021-12-19 15:59:45 -05:00
rb_raise(rb_eIOBufferLockedError, "Cannot resize locked buffer!");
2021-07-02 06:41:16 -04:00
}
if (data->base == NULL) {
io_buffer_initialize(data, NULL, size, io_flags_for_size(size), Qnil);
return;
}
if (data->flags & RB_IO_BUFFER_EXTERNAL) {
rb_raise(rb_eIOBufferAccessError, "Cannot resize external buffer!");
2021-07-02 06:41:16 -04:00
}
#if defined(HAVE_MREMAP) && defined(MREMAP_MAYMOVE)
if (data->flags & RB_IO_BUFFER_MAPPED) {
void *base = mremap(data->base, data->size, size, MREMAP_MAYMOVE);
if (base == MAP_FAILED) {
rb_sys_fail("rb_io_buffer_resize:mremap");
}
io_buffer_resize_clear(data, base, size);
data->base = base;
data->size = size;
return;
}
#endif
if (data->flags & RB_IO_BUFFER_INTERNAL) {
void *base = realloc(data->base, size);
if (!base) {
rb_sys_fail("rb_io_buffer_resize:realloc");
}
io_buffer_resize_clear(data, base, size);
2021-07-02 06:41:16 -04:00
data->base = base;
data->size = size;
return;
2021-07-02 06:41:16 -04:00
}
io_buffer_resize_copy(data, size);
}
/*
* call-seq: resize(new_size) -> 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;
2021-07-02 06:41:16 -04:00
}
/*
* call-seq: <=>(other) -> true or false
*
* Buffers are compared by size and exact contents of the memory they are
* referencing using +memcmp+.
*/
2021-11-10 02:41:26 -05:00
static VALUE
rb_io_buffer_compare(VALUE self, VALUE other)
2021-07-02 06:41:16 -04:00
{
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);
2021-07-02 06:41:16 -04:00
if (size1 < size2) {
return RB_INT2NUM(-1);
}
if (size1 > size2) {
return RB_INT2NUM(1);
}
return RB_INT2NUM(memcmp(ptr1, ptr2, size1));
}
2021-11-21 02:12:03 -05:00
static void
io_buffer_validate_type(size_t size, size_t offset)
{
2021-07-02 06:41:16 -04:00
if (offset > size) {
rb_raise(rb_eArgError, "Type extends beyond end of buffer! (offset=%ld > size=%ld)", offset, size);
2021-07-02 06:41:16 -04:00
}
}
// Lower case: little endian.
// Upper case: big endian (network endian).
//
// :U8 | unsigned 8-bit integer.
// :S8 | signed 8-bit integer.
//
// :u16, :U16 | unsigned 16-bit integer.
// :s16, :S16 | signed 16-bit integer.
//
// :u32, :U32 | unsigned 32-bit integer.
// :s32, :S32 | signed 32-bit integer.
//
// :u64, :U64 | unsigned 64-bit integer.
// :s64, :S64 | signed 64-bit integer.
//
// :f32, :F32 | 32-bit floating point number.
// :f64, :F64 | 64-bit floating point number.
#define ruby_swap8(value) value
union swapf32 {
uint32_t integral;
float value;
};
2021-11-21 02:12:03 -05:00
static float
ruby_swapf32(float value)
2021-07-02 06:41:16 -04:00
{
union swapf32 swap = {.value = value};
swap.integral = ruby_swap32(swap.integral);
return swap.value;
}
union swapf64 {
uint64_t integral;
double value;
};
2021-11-21 02:12:03 -05:00
static double
ruby_swapf64(double value)
2021-07-02 06:41:16 -04:00
{
union swapf64 swap = {.value = value};
swap.integral = ruby_swap64(swap.integral);
return swap.value;
}
#define IO_BUFFER_DECLARE_TYPE(name, type, endian, wrap, unwrap, swap) \
static ID RB_IO_BUFFER_DATA_TYPE_##name; \
2021-07-02 06:41:16 -04:00
\
2021-11-10 02:41:26 -05:00
static VALUE \
io_buffer_read_##name(const void* base, size_t size, size_t *offset) \
2021-07-02 06:41:16 -04:00
{ \
io_buffer_validate_type(size, *offset + sizeof(type)); \
type value; \
memcpy(&value, (char*)base + *offset, sizeof(type)); \
if (endian != RB_IO_BUFFER_HOST_ENDIAN) value = swap(value); \
*offset += sizeof(type); \
return wrap(value); \
} \
\
2021-11-10 02:41:26 -05:00
static void \
io_buffer_write_##name(const void* base, size_t size, size_t *offset, VALUE _value) \
2021-07-02 06:41:16 -04:00
{ \
io_buffer_validate_type(size, *offset + sizeof(type)); \
type value = unwrap(_value); \
if (endian != RB_IO_BUFFER_HOST_ENDIAN) value = swap(value); \
memcpy((char*)base + *offset, &value, sizeof(type)); \
*offset += sizeof(type); \
} \
\
enum { \
RB_IO_BUFFER_DATA_TYPE_##name##_SIZE = sizeof(type) \
};
2021-07-02 06:41:16 -04:00
IO_BUFFER_DECLARE_TYPE(U8, uint8_t, RB_IO_BUFFER_BIG_ENDIAN, RB_UINT2NUM, RB_NUM2UINT, ruby_swap8)
IO_BUFFER_DECLARE_TYPE(S8, int8_t, RB_IO_BUFFER_BIG_ENDIAN, RB_INT2NUM, RB_NUM2INT, ruby_swap8)
IO_BUFFER_DECLARE_TYPE(u16, uint16_t, RB_IO_BUFFER_LITTLE_ENDIAN, RB_UINT2NUM, RB_NUM2UINT, ruby_swap16)
IO_BUFFER_DECLARE_TYPE(U16, uint16_t, RB_IO_BUFFER_BIG_ENDIAN, RB_UINT2NUM, RB_NUM2UINT, ruby_swap16)
IO_BUFFER_DECLARE_TYPE(s16, int16_t, RB_IO_BUFFER_LITTLE_ENDIAN, RB_INT2NUM, RB_NUM2INT, ruby_swap16)
IO_BUFFER_DECLARE_TYPE(S16, int16_t, RB_IO_BUFFER_BIG_ENDIAN, RB_INT2NUM, RB_NUM2INT, ruby_swap16)
IO_BUFFER_DECLARE_TYPE(u32, uint32_t, RB_IO_BUFFER_LITTLE_ENDIAN, RB_UINT2NUM, RB_NUM2UINT, ruby_swap32)
IO_BUFFER_DECLARE_TYPE(U32, uint32_t, RB_IO_BUFFER_BIG_ENDIAN, RB_UINT2NUM, RB_NUM2UINT, ruby_swap32)
IO_BUFFER_DECLARE_TYPE(s32, int32_t, RB_IO_BUFFER_LITTLE_ENDIAN, RB_INT2NUM, RB_NUM2INT, ruby_swap32)
IO_BUFFER_DECLARE_TYPE(S32, int32_t, RB_IO_BUFFER_BIG_ENDIAN, RB_INT2NUM, RB_NUM2INT, ruby_swap32)
IO_BUFFER_DECLARE_TYPE(u64, uint64_t, RB_IO_BUFFER_LITTLE_ENDIAN, RB_ULL2NUM, RB_NUM2ULL, ruby_swap64)
IO_BUFFER_DECLARE_TYPE(U64, uint64_t, RB_IO_BUFFER_BIG_ENDIAN, RB_ULL2NUM, RB_NUM2ULL, ruby_swap64)
IO_BUFFER_DECLARE_TYPE(s64, int64_t, RB_IO_BUFFER_LITTLE_ENDIAN, RB_LL2NUM, RB_NUM2LL, ruby_swap64)
IO_BUFFER_DECLARE_TYPE(S64, int64_t, RB_IO_BUFFER_BIG_ENDIAN, RB_LL2NUM, RB_NUM2LL, ruby_swap64)
IO_BUFFER_DECLARE_TYPE(f32, float, RB_IO_BUFFER_LITTLE_ENDIAN, DBL2NUM, NUM2DBL, ruby_swapf32)
IO_BUFFER_DECLARE_TYPE(F32, float, RB_IO_BUFFER_BIG_ENDIAN, DBL2NUM, NUM2DBL, ruby_swapf32)
IO_BUFFER_DECLARE_TYPE(f64, double, RB_IO_BUFFER_LITTLE_ENDIAN, DBL2NUM, NUM2DBL, ruby_swapf64)
IO_BUFFER_DECLARE_TYPE(F64, double, RB_IO_BUFFER_BIG_ENDIAN, DBL2NUM, NUM2DBL, ruby_swapf64)
#undef IO_BUFFER_DECLARE_TYPE
static inline size_t
io_buffer_data_type_size(ID data_type) {
#define IO_BUFFER_DATA_TYPE_SIZE(name) if (data_type == RB_IO_BUFFER_DATA_TYPE_##name) return RB_IO_BUFFER_DATA_TYPE_##name##_SIZE;
IO_BUFFER_DATA_TYPE_SIZE(U8)
IO_BUFFER_DATA_TYPE_SIZE(S8)
IO_BUFFER_DATA_TYPE_SIZE(u16)
IO_BUFFER_DATA_TYPE_SIZE(U16)
IO_BUFFER_DATA_TYPE_SIZE(s16)
IO_BUFFER_DATA_TYPE_SIZE(S16)
IO_BUFFER_DATA_TYPE_SIZE(u32)
IO_BUFFER_DATA_TYPE_SIZE(U32)
IO_BUFFER_DATA_TYPE_SIZE(s32)
IO_BUFFER_DATA_TYPE_SIZE(S32)
IO_BUFFER_DATA_TYPE_SIZE(u64)
IO_BUFFER_DATA_TYPE_SIZE(U64)
IO_BUFFER_DATA_TYPE_SIZE(s64)
IO_BUFFER_DATA_TYPE_SIZE(S64)
IO_BUFFER_DATA_TYPE_SIZE(f32)
IO_BUFFER_DATA_TYPE_SIZE(F32)
IO_BUFFER_DATA_TYPE_SIZE(f64)
IO_BUFFER_DATA_TYPE_SIZE(F64)
#undef IO_BUFFER_DATA_TYPE_SIZE
2021-07-02 06:41:16 -04:00
rb_raise(rb_eArgError, "Invalid type name!");
}
2021-07-02 06:41:16 -04:00
/*
* call-seq:
* size_of(data_type) -> byte size
* size_of(array of data_type) -> byte size
*
* 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)));
}
}
2021-07-02 06:41:16 -04:00
static inline VALUE
rb_io_buffer_get_value(const void* base, size_t size, ID data_type, size_t *offset)
2021-07-02 06:41:16 -04:00
{
#define IO_BUFFER_GET_VALUE(name) if (data_type == RB_IO_BUFFER_DATA_TYPE_##name) return io_buffer_read_##name(base, size, offset);
IO_BUFFER_GET_VALUE(U8)
IO_BUFFER_GET_VALUE(S8)
2022-07-27 05:24:22 -04:00
IO_BUFFER_GET_VALUE(u16)
IO_BUFFER_GET_VALUE(U16)
IO_BUFFER_GET_VALUE(s16)
IO_BUFFER_GET_VALUE(S16)
2022-07-27 05:24:22 -04:00
IO_BUFFER_GET_VALUE(u32)
IO_BUFFER_GET_VALUE(U32)
IO_BUFFER_GET_VALUE(s32)
IO_BUFFER_GET_VALUE(S32)
2022-07-27 05:24:22 -04:00
IO_BUFFER_GET_VALUE(u64)
IO_BUFFER_GET_VALUE(U64)
IO_BUFFER_GET_VALUE(s64)
IO_BUFFER_GET_VALUE(S64)
2022-07-27 05:24:22 -04:00
IO_BUFFER_GET_VALUE(f32)
IO_BUFFER_GET_VALUE(F32)
IO_BUFFER_GET_VALUE(f64)
IO_BUFFER_GET_VALUE(F64)
#undef IO_BUFFER_GET_VALUE
2021-07-02 06:41:16 -04:00
rb_raise(rb_eArgError, "Invalid type name!");
}
/*
* call-seq: get_value(data_type, offset) -> numeric
*
* 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
*/
2021-11-10 02:41:26 -05:00
static VALUE
2021-12-20 03:22:46 -05:00
io_buffer_get_value(VALUE self, VALUE type, VALUE _offset)
2021-07-02 06:41:16 -04:00
{
const void *base;
size_t size;
size_t offset = NUM2SIZET(_offset);
rb_io_buffer_get_bytes_for_reading(self, &base, &size);
2021-07-02 06:41:16 -04:00
return rb_io_buffer_get_value(base, size, RB_SYM2ID(type), &offset);
2021-07-02 06:41:16 -04:00
}
/*
* call-seq: get_values(data_types, offset) -> array
*
* 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;
}
/*
* call-seq:
* each(data_type, [offset, [count]]) {|offset, value| ...} -> self
* each(data_type, [offset, [count]]) -> enumerator
*
* 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;
}
/*
* call-seq: values(data_type, [offset, [count]]) -> array
*
* 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;
}
/*
* call-seq:
* each_byte([offset, [count]]) {|offset, byte| ...} -> self
* each_byte([offset, [count]]) -> enumerator
*
* 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;
}
static inline void
rb_io_buffer_set_value(const void* base, size_t size, ID data_type, size_t *offset, VALUE value)
2021-07-02 06:41:16 -04:00
{
#define IO_BUFFER_SET_VALUE(name) if (data_type == RB_IO_BUFFER_DATA_TYPE_##name) {io_buffer_write_##name(base, size, offset, value); return;}
IO_BUFFER_SET_VALUE(U8);
IO_BUFFER_SET_VALUE(S8);
2022-07-27 05:24:22 -04:00
IO_BUFFER_SET_VALUE(u16);
IO_BUFFER_SET_VALUE(U16);
IO_BUFFER_SET_VALUE(s16);
IO_BUFFER_SET_VALUE(S16);
2022-07-27 05:24:22 -04:00
IO_BUFFER_SET_VALUE(u32);
IO_BUFFER_SET_VALUE(U32);
IO_BUFFER_SET_VALUE(s32);
IO_BUFFER_SET_VALUE(S32);
2022-07-27 05:24:22 -04:00
IO_BUFFER_SET_VALUE(u64);
IO_BUFFER_SET_VALUE(U64);
IO_BUFFER_SET_VALUE(s64);
IO_BUFFER_SET_VALUE(S64);
2022-07-27 05:24:22 -04:00
IO_BUFFER_SET_VALUE(f32);
IO_BUFFER_SET_VALUE(F32);
IO_BUFFER_SET_VALUE(f64);
IO_BUFFER_SET_VALUE(F64);
#undef IO_BUFFER_SET_VALUE
2021-07-02 06:41:16 -04:00
rb_raise(rb_eArgError, "Invalid type name!");
}
/*
* call-seq: set_value(type, offset, value) -> offset
*
* 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
*/
2021-11-10 02:41:26 -05:00
static VALUE
2021-12-20 03:22:46 -05:00
io_buffer_set_value(VALUE self, VALUE type, VALUE _offset, VALUE value)
2021-07-02 06:41:16 -04:00
{
void *base;
size_t size;
size_t offset = NUM2SIZET(_offset);
rb_io_buffer_get_bytes_for_writing(self, &base, &size);
2021-07-02 06:41:16 -04:00
rb_io_buffer_set_value(base, size, RB_SYM2ID(type), &offset, value);
return SIZET2NUM(offset);
}
/*
* call-seq: set_values(data_types, offset, values) -> 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);
}
2021-07-02 06:41:16 -04:00
return SIZET2NUM(offset);
}
2021-12-20 03:22:46 -05:00
static void
io_buffer_memcpy(struct rb_io_buffer *data, size_t offset, const void *source_base, size_t source_offset, size_t source_size, size_t length)
{
void *base;
size_t size;
io_buffer_get_bytes_for_writing(data, &base, &size);
2021-12-20 03:22:46 -05:00
io_buffer_validate_range(data, offset, length);
2021-12-20 03:22:46 -05:00
if (source_offset + length > source_size) {
rb_raise(rb_eArgError, "The computed source range exceeds the size of the source!");
}
memcpy((unsigned char*)base+offset, (unsigned char*)source_base+source_offset, length);
}
// (offset, length, source_offset) -> length
static VALUE
io_buffer_copy_from(struct rb_io_buffer *data, const void *source_base, size_t source_size, int argc, VALUE *argv)
{
size_t offset;
size_t length;
size_t source_offset;
// The offset we copy into the buffer:
if (argc >= 1) {
offset = NUM2SIZET(argv[0]);
}
else {
2021-12-20 03:22:46 -05:00
offset = 0;
}
// The offset we start from within the string:
if (argc >= 3) {
source_offset = NUM2SIZET(argv[2]);
if (source_offset > source_size) {
rb_raise(rb_eArgError, "The given source offset is bigger than the source itself!");
}
}
else {
2021-12-20 03:22:46 -05:00
source_offset = 0;
}
// The length we are going to copy:
if (argc >= 2 && !RB_NIL_P(argv[1])) {
length = NUM2SIZET(argv[1]);
}
else {
2021-12-20 03:22:46 -05:00
// Default to the source offset -> source size:
length = source_size - source_offset;
}
io_buffer_memcpy(data, offset, source_base, source_offset, source_size, length);
return SIZET2NUM(length);
}
/*
* call-seq:
* dup -> io_buffer
* clone -> io_buffer
*
* 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);
}
/*
* call-seq:
* copy(source, [offset, [length, [source_offset]]]) -> size
*
* 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: "
2022-06-24 15:12:22 -04:00
* 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+'))
2022-01-02 03:43:01 -05:00
* 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)
2022-01-02 03:43:01 -05:00
* buffer.copy(IO::Buffer.for('test'), 0)
* # in `copy': Specified offset+length exceeds source size! (ArgumentError)
*/
2021-12-20 03:22:46 -05:00
static VALUE
io_buffer_copy(int argc, VALUE *argv, VALUE self)
{
rb_check_arity(argc, 1, 4);
2021-12-20 03:22:46 -05:00
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);
2021-12-20 03:22:46 -05:00
return io_buffer_copy_from(data, source_base, source_size, argc-1, argv+1);
}
/*
* call-seq: get_string([offset, [length, [encoding]]]) -> string
*
* 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);
}
2022-01-02 03:43:01 -05:00
/*
* call-seq: set_string(string, [offset, [length, [source_offset]]]) -> size
*
* 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.
*/
2021-12-20 03:22:46 -05:00
static VALUE
io_buffer_set_string(int argc, VALUE *argv, VALUE self)
{
rb_check_arity(argc, 1, 4);
2021-12-20 03:22:46 -05:00
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);
}
2021-11-21 02:12:03 -05:00
void
rb_io_buffer_clear(VALUE self, uint8_t value, size_t offset, size_t length)
2021-07-02 06:41:16 -04:00
{
void *base;
size_t size;
rb_io_buffer_get_bytes_for_writing(self, &base, &size);
2021-07-02 06:41:16 -04:00
if (offset + length > size) {
2021-12-19 15:59:45 -05:00
rb_raise(rb_eArgError, "The given offset + length out of bounds!");
2021-07-02 06:41:16 -04:00
}
memset((char*)base + offset, value, length);
}
/*
* call-seq: clear(value = 0, [offset, [length]]) -> 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 ....
*/
2021-11-10 02:41:26 -05:00
static VALUE
io_buffer_clear(int argc, VALUE *argv, VALUE self)
2021-07-02 06:41:16 -04:00
{
rb_check_arity(argc, 0, 3);
2021-12-20 03:22:46 -05:00
2021-07-02 06:41:16 -04:00
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;
2021-07-02 06:41:16 -04:00
if (argc >= 3) {
length = NUM2SIZET(argv[2]);
}
else {
length = data->size - offset;
2021-07-02 06:41:16 -04:00
}
rb_io_buffer_clear(self, value, offset, length);
return self;
}
static size_t
io_buffer_default_size(size_t page_size)
{
2021-12-24 20:33:49 -05:00
// Platform agnostic default size, based on empirical performance observation:
2021-12-18 15:56:52 -05:00
const size_t platform_agnostic_default_size = 64*1024;
// Allow user to specify custom default buffer size:
const char *default_size = getenv("RUBY_IO_BUFFER_DEFAULT_SIZE");
if (default_size) {
// For the purpose of setting a default size, 2^31 is an acceptable maximum:
int value = atoi(default_size);
// assuming sizeof(int) <= sizeof(size_t)
if (value > 0) {
return value;
}
}
if (platform_agnostic_default_size < page_size) {
return page_size;
}
return platform_agnostic_default_size;
}
struct io_buffer_read_internal_argument {
int descriptor;
void *base;
size_t size;
};
static VALUE
io_buffer_read_internal(void *_argument)
{
struct io_buffer_read_internal_argument *argument = _argument;
ssize_t result = read(argument->descriptor, argument->base, argument->size);
return rb_fiber_scheduler_io_result(result, errno);
}
VALUE
rb_io_buffer_read(VALUE self, VALUE io, size_t length, size_t offset)
{
VALUE scheduler = rb_fiber_scheduler_current();
if (scheduler != Qnil) {
VALUE result = rb_fiber_scheduler_io_read(scheduler, io, self, SIZET2NUM(length), SIZET2NUM(offset));
if (result != Qundef) {
return result;
}
}
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_validate_range(data, offset, length);
int descriptor = rb_io_descriptor(io);
void * base;
size_t size;
io_buffer_get_bytes_for_writing(data, &base, &size);
base = (unsigned char*)base + offset;
struct io_buffer_read_internal_argument argument = {
.descriptor = descriptor,
.base = base,
.size = length,
};
return rb_thread_io_blocking_region(io_buffer_read_internal, &argument, descriptor);
}
/*
* call-seq: read(io, [length, [offset]]) -> self
*
* Read at most +length+ bytes from +io+ into the buffer, starting at
* +offset+.
*
* If +length+ is not given, read until the end of the buffer.
*
* If +offset+ is not given, read from the beginning of the buffer.
*
* If +length+ is 0, read nothing.
*
* Example:
*
* buffer = IO::Buffer.for('test')
* # =>
* # <IO::Buffer 0x00007fca40087c38+4 SLICE>
* # 0x00000000 74 65 73 74 test
* buffer.read(File.open('/dev/urandom', 'rb'), 4)
* # =>
* # <IO::Buffer 0x00007fca40087c38+4 SLICE>
* # 0x00000000 2a 0e 0e 0e *...
*/
static VALUE
io_buffer_read(int argc, VALUE *argv, VALUE self)
{
rb_check_arity(argc, 2, 3);
VALUE io = argv[0];
size_t length;
if (argc >= 2) {
if (rb_int_negative_p(argv[1])) {
rb_raise(rb_eArgError, "Length can't be negative!");
}
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);
}
struct io_buffer_pread_internal_argument {
int descriptor;
void *base;
size_t size;
off_t offset;
};
static VALUE
io_buffer_pread_internal(void *_argument)
{
struct io_buffer_pread_internal_argument *argument = _argument;
#if defined(HAVE_PREAD)
ssize_t result = pread(argument->descriptor, argument->base, argument->size, argument->offset);
#else
// This emulation is not thread safe.
rb_off_t offset = lseek(argument->descriptor, 0, SEEK_CUR);
if (offset == (rb_off_t)-1)
return rb_fiber_scheduler_io_result(-1, errno);
if (lseek(argument->descriptor, argument->offset, SEEK_SET) == (rb_off_t)-1)
return rb_fiber_scheduler_io_result(-1, errno);
ssize_t result = read(argument->descriptor, argument->base, argument->size);
if (lseek(argument->descriptor, offset, SEEK_SET) == (rb_off_t)-1)
return rb_fiber_scheduler_io_result(-1, errno);
#endif
return rb_fiber_scheduler_io_result(result, errno);
}
VALUE
rb_io_buffer_pread(VALUE self, VALUE io, rb_off_t from, size_t length, size_t offset)
{
VALUE scheduler = rb_fiber_scheduler_current();
if (scheduler != Qnil) {
VALUE result = rb_fiber_scheduler_io_pread(scheduler, io, OFFT2NUM(from), self, SIZET2NUM(length), SIZET2NUM(offset));
if (result != Qundef) {
return result;
}
}
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_validate_range(data, 0, length);
int descriptor = rb_io_descriptor(io);
void * base;
size_t size;
io_buffer_get_bytes_for_writing(data, &base, &size);
struct io_buffer_pread_internal_argument argument = {
.descriptor = descriptor,
.base = base,
.size = length,
.offset = from,
};
return rb_thread_io_blocking_region(io_buffer_pread_internal, &argument, descriptor);
}
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);
}
struct io_buffer_write_internal_argument {
int descriptor;
const void *base;
size_t size;
};
static VALUE
io_buffer_write_internal(void *_argument)
{
struct io_buffer_write_internal_argument *argument = _argument;
ssize_t result = write(argument->descriptor, argument->base, argument->size);
return rb_fiber_scheduler_io_result(result, errno);
}
VALUE
rb_io_buffer_write(VALUE self, VALUE io, size_t length, size_t offset)
{
VALUE scheduler = rb_fiber_scheduler_current();
if (scheduler != Qnil) {
VALUE result = rb_fiber_scheduler_io_write(scheduler, io, self, SIZET2NUM(length), SIZET2NUM(offset));
if (result != Qundef) {
return result;
}
}
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_validate_range(data, offset, length);
int descriptor = rb_io_descriptor(io);
const void * base;
size_t size;
io_buffer_get_bytes_for_reading(data, &base, &size);
base = (unsigned char *)base + offset;
struct io_buffer_write_internal_argument argument = {
.descriptor = descriptor,
.base = base,
.size = length,
};
return rb_thread_io_blocking_region(io_buffer_write_internal, &argument, descriptor);
}
static VALUE
io_buffer_write(int argc, VALUE *argv, VALUE self)
{
rb_check_arity(argc, 2, 3);
VALUE io = argv[0];
size_t length;
if (argc >= 2) {
if (rb_int_negative_p(argv[1])) {
rb_raise(rb_eArgError, "Length can't be negative!");
}
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);
}
struct io_buffer_pwrite_internal_argument {
int descriptor;
const void *base;
size_t size;
off_t offset;
};
static VALUE
io_buffer_pwrite_internal(void *_argument)
{
struct io_buffer_pwrite_internal_argument *argument = _argument;
#if defined(HAVE_PWRITE)
ssize_t result = pwrite(argument->descriptor, argument->base, argument->size, argument->offset);
#else
// This emulation is not thread safe.
rb_off_t offset = lseek(argument->descriptor, 0, SEEK_CUR);
if (offset == (rb_off_t)-1)
return rb_fiber_scheduler_io_result(-1, errno);
if (lseek(argument->descriptor, argument->offset, SEEK_SET) == (rb_off_t)-1)
return rb_fiber_scheduler_io_result(-1, errno);
ssize_t result = write(argument->descriptor, argument->base, argument->size);
if (lseek(argument->descriptor, offset, SEEK_SET) == (rb_off_t)-1)
return rb_fiber_scheduler_io_result(-1, errno);
#endif
return rb_fiber_scheduler_io_result(result, errno);
}
VALUE
rb_io_buffer_pwrite(VALUE self, VALUE io, rb_off_t from, size_t length, size_t offset)
{
VALUE scheduler = rb_fiber_scheduler_current();
if (scheduler != Qnil) {
VALUE result = rb_fiber_scheduler_io_pwrite(scheduler, io, OFFT2NUM(from), self, SIZET2NUM(length), SIZET2NUM(offset));
if (result != Qundef) {
return result;
}
}
struct rb_io_buffer *data = NULL;
TypedData_Get_Struct(self, struct rb_io_buffer, &rb_io_buffer_type, data);
io_buffer_validate_range(data, 0, length);
int descriptor = rb_io_descriptor(io);
const void * base;
size_t size;
io_buffer_get_bytes_for_reading(data, &base, &size);
struct io_buffer_pwrite_internal_argument argument = {
.descriptor = descriptor,
.base = base,
.size = length,
.offset = from,
};
return rb_thread_io_blocking_region(io_buffer_pwrite_internal, &argument, descriptor);
}
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);
}
static inline void
io_buffer_check_mask(const struct rb_io_buffer *buffer)
{
if (buffer->size == 0)
rb_raise(rb_eIOBufferMaskError, "Zero-length mask given!");
}
static void
memory_and(unsigned char * restrict output, unsigned char * restrict base, size_t size, unsigned char * restrict mask, size_t mask_size)
{
for (size_t offset = 0; offset < size; offset += 1) {
output[offset] = base[offset] & mask[offset % mask_size];
}
}
/*
* call-seq:
* source & mask -> io_buffer
*
* 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;
}
static void
memory_or(unsigned char * restrict output, unsigned char * restrict base, size_t size, unsigned char * restrict mask, size_t mask_size)
{
for (size_t offset = 0; offset < size; offset += 1) {
output[offset] = base[offset] | mask[offset % mask_size];
}
}
/*
* call-seq:
* source | mask -> io_buffer
*
* 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;
}
static void
memory_xor(unsigned char * restrict output, unsigned char * restrict base, size_t size, unsigned char * restrict mask, size_t mask_size)
{
for (size_t offset = 0; offset < size; offset += 1) {
output[offset] = base[offset] ^ mask[offset % mask_size];
}
}
/*
* call-seq:
* source ^ mask -> io_buffer
*
* 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;
}
static void
memory_not(unsigned char * restrict output, unsigned char * restrict base, size_t size)
{
for (size_t offset = 0; offset < size; offset += 1) {
output[offset] = ~base[offset];
}
}
/*
* call-seq:
* ~source -> io_buffer
*
* 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;
}
static inline int
io_buffer_overlaps(const struct rb_io_buffer *a, const struct rb_io_buffer *b)
{
if (a->base > b->base) {
return io_buffer_overlaps(b, a);
}
return (b->base >= a->base) && (b->base <= (void*)((unsigned char *)a->base + a->size));
}
static inline void
io_buffer_check_overlaps(struct rb_io_buffer *a, struct rb_io_buffer *b)
{
if (io_buffer_overlaps(a, b))
rb_raise(rb_eIOBufferMaskError, "Mask overlaps source data!");
}
static void
memory_and_inplace(unsigned char * restrict base, size_t size, unsigned char * restrict mask, size_t mask_size)
{
for (size_t offset = 0; offset < size; offset += 1) {
base[offset] &= mask[offset % mask_size];
}
}
/*
* call-seq:
* source.and!(mask) -> io_buffer
*
* 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;
}
static void
memory_or_inplace(unsigned char * restrict base, size_t size, unsigned char * restrict mask, size_t mask_size)
{
for (size_t offset = 0; offset < size; offset += 1) {
base[offset] |= mask[offset % mask_size];
}
}
/*
* call-seq:
* source.or!(mask) -> io_buffer
*
* 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;
}
static void
memory_xor_inplace(unsigned char * restrict base, size_t size, unsigned char * restrict mask, size_t mask_size)
{
for (size_t offset = 0; offset < size; offset += 1) {
base[offset] ^= mask[offset % mask_size];
}
}
/*
* call-seq:
* source.xor!(mask) -> io_buffer
*
* 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;
}
static void
memory_not_inplace(unsigned char * restrict base, size_t size)
{
for (size_t offset = 0; offset < size; offset += 1) {
base[offset] = ~base[offset];
}
}
/*
* call-seq:
* source.not! -> io_buffer
*
* 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;
}
/*
* Document-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 using #copy or
* #set_value, #set_string, get data with #get_string;
* * Create a buffer mapped to some string with ::for, then it could be used
* both for reading with #get_string or #get_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
2022-05-08 20:07:46 -04:00
* like Fiber::SchedulerInterface#io_read and Fiber::SchedulerInterface#io_write.
*
* <b>Examples of usage:</b>
*
* 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'
2022-06-24 15:12:22 -04:00
* 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"
*
* <b>The class is experimental and the interface is subject to change.</b>
*/
2021-11-10 02:41:26 -05:00
void
Init_IO_Buffer(void)
2021-07-02 06:41:16 -04:00
{
rb_cIOBuffer = rb_define_class_under(rb_cIO, "Buffer", rb_cObject);
2021-12-19 15:59:45 -05:00
rb_eIOBufferLockedError = rb_define_class_under(rb_cIOBuffer, "LockedError", rb_eRuntimeError);
rb_eIOBufferAllocationError = rb_define_class_under(rb_cIOBuffer, "AllocationError", rb_eRuntimeError);
rb_eIOBufferAccessError = rb_define_class_under(rb_cIOBuffer, "AccessError", rb_eRuntimeError);
2021-12-19 15:59:45 -05:00
rb_eIOBufferInvalidatedError = rb_define_class_under(rb_cIOBuffer, "InvalidatedError", rb_eRuntimeError);
rb_eIOBufferMaskError = rb_define_class_under(rb_cIOBuffer, "MaskError", rb_eArgError);
2021-07-02 06:41:16 -04:00
rb_define_alloc_func(rb_cIOBuffer, rb_io_buffer_type_allocate);
rb_define_singleton_method(rb_cIOBuffer, "for", rb_io_buffer_type_for, 1);
2021-07-02 06:41:16 -04:00
#ifdef _WIN32
SYSTEM_INFO info;
GetSystemInfo(&info);
RUBY_IO_BUFFER_PAGE_SIZE = info.dwPageSize;
#else /* not WIN32 */
RUBY_IO_BUFFER_PAGE_SIZE = sysconf(_SC_PAGESIZE);
#endif
2021-12-18 15:56:52 -05:00
RUBY_IO_BUFFER_DEFAULT_SIZE = io_buffer_default_size(RUBY_IO_BUFFER_PAGE_SIZE);
// Efficient sizing of mapped buffers:
2021-07-02 06:41:16 -04:00
rb_define_const(rb_cIOBuffer, "PAGE_SIZE", SIZET2NUM(RUBY_IO_BUFFER_PAGE_SIZE));
2021-12-18 15:56:52 -05:00
rb_define_const(rb_cIOBuffer, "DEFAULT_SIZE", SIZET2NUM(RUBY_IO_BUFFER_DEFAULT_SIZE));
2021-07-02 06:41:16 -04:00
rb_define_singleton_method(rb_cIOBuffer, "map", io_buffer_map, -1);
// General use:
rb_define_method(rb_cIOBuffer, "initialize", rb_io_buffer_initialize, -1);
rb_define_method(rb_cIOBuffer, "initialize_copy", rb_io_buffer_initialize_copy, 1);
2021-07-02 06:41:16 -04:00
rb_define_method(rb_cIOBuffer, "inspect", rb_io_buffer_inspect, 0);
rb_define_method(rb_cIOBuffer, "hexdump", rb_io_buffer_hexdump, 0);
2021-07-02 06:41:16 -04:00
rb_define_method(rb_cIOBuffer, "to_s", rb_io_buffer_to_s, 0);
rb_define_method(rb_cIOBuffer, "size", rb_io_buffer_size, 0);
rb_define_method(rb_cIOBuffer, "valid?", rb_io_buffer_valid_p, 0);
2021-07-02 06:41:16 -04:00
// Ownership:
rb_define_method(rb_cIOBuffer, "transfer", rb_io_buffer_transfer, 0);
2021-07-02 06:41:16 -04:00
// Flags:
rb_define_const(rb_cIOBuffer, "EXTERNAL", RB_INT2NUM(RB_IO_BUFFER_EXTERNAL));
rb_define_const(rb_cIOBuffer, "INTERNAL", RB_INT2NUM(RB_IO_BUFFER_INTERNAL));
rb_define_const(rb_cIOBuffer, "MAPPED", RB_INT2NUM(RB_IO_BUFFER_MAPPED));
rb_define_const(rb_cIOBuffer, "SHARED", RB_INT2NUM(RB_IO_BUFFER_SHARED));
2021-07-02 06:41:16 -04:00
rb_define_const(rb_cIOBuffer, "LOCKED", RB_INT2NUM(RB_IO_BUFFER_LOCKED));
rb_define_const(rb_cIOBuffer, "PRIVATE", RB_INT2NUM(RB_IO_BUFFER_PRIVATE));
2021-12-20 05:06:21 -05:00
rb_define_const(rb_cIOBuffer, "READONLY", RB_INT2NUM(RB_IO_BUFFER_READONLY));
2021-07-02 06:41:16 -04:00
// Endian:
rb_define_const(rb_cIOBuffer, "LITTLE_ENDIAN", RB_INT2NUM(RB_IO_BUFFER_LITTLE_ENDIAN));
rb_define_const(rb_cIOBuffer, "BIG_ENDIAN", RB_INT2NUM(RB_IO_BUFFER_BIG_ENDIAN));
rb_define_const(rb_cIOBuffer, "HOST_ENDIAN", RB_INT2NUM(RB_IO_BUFFER_HOST_ENDIAN));
rb_define_const(rb_cIOBuffer, "NETWORK_ENDIAN", RB_INT2NUM(RB_IO_BUFFER_NETWORK_ENDIAN));
rb_define_method(rb_cIOBuffer, "null?", rb_io_buffer_null_p, 0);
2021-12-20 05:06:21 -05:00
rb_define_method(rb_cIOBuffer, "empty?", rb_io_buffer_empty_p, 0);
2021-07-02 06:41:16 -04:00
rb_define_method(rb_cIOBuffer, "external?", rb_io_buffer_external_p, 0);
rb_define_method(rb_cIOBuffer, "internal?", rb_io_buffer_internal_p, 0);
rb_define_method(rb_cIOBuffer, "mapped?", rb_io_buffer_mapped_p, 0);
rb_define_method(rb_cIOBuffer, "shared?", rb_io_buffer_shared_p, 0);
2021-07-02 06:41:16 -04:00
rb_define_method(rb_cIOBuffer, "locked?", rb_io_buffer_locked_p, 0);
2021-12-20 05:06:21 -05:00
rb_define_method(rb_cIOBuffer, "readonly?", io_buffer_readonly_p, 0);
2021-07-02 06:41:16 -04:00
// Locking to prevent changes while using pointer:
// rb_define_method(rb_cIOBuffer, "lock", rb_io_buffer_lock, 0);
// rb_define_method(rb_cIOBuffer, "unlock", rb_io_buffer_unlock, 0);
rb_define_method(rb_cIOBuffer, "locked", rb_io_buffer_locked, 0);
// Manipulation:
rb_define_method(rb_cIOBuffer, "slice", io_buffer_slice, -1);
2021-07-02 06:41:16 -04:00
rb_define_method(rb_cIOBuffer, "<=>", rb_io_buffer_compare, 1);
rb_define_method(rb_cIOBuffer, "resize", io_buffer_resize, 1);
2021-07-02 06:41:16 -04:00
rb_define_method(rb_cIOBuffer, "clear", io_buffer_clear, -1);
rb_define_method(rb_cIOBuffer, "free", rb_io_buffer_free, 0);
rb_include_module(rb_cIOBuffer, rb_mComparable);
#define IO_BUFFER_DEFINE_DATA_TYPE(name) RB_IO_BUFFER_DATA_TYPE_##name = rb_intern_const(#name)
IO_BUFFER_DEFINE_DATA_TYPE(U8);
IO_BUFFER_DEFINE_DATA_TYPE(S8);
IO_BUFFER_DEFINE_DATA_TYPE(u16);
IO_BUFFER_DEFINE_DATA_TYPE(U16);
IO_BUFFER_DEFINE_DATA_TYPE(s16);
IO_BUFFER_DEFINE_DATA_TYPE(S16);
IO_BUFFER_DEFINE_DATA_TYPE(u32);
IO_BUFFER_DEFINE_DATA_TYPE(U32);
IO_BUFFER_DEFINE_DATA_TYPE(s32);
IO_BUFFER_DEFINE_DATA_TYPE(S32);
IO_BUFFER_DEFINE_DATA_TYPE(u64);
IO_BUFFER_DEFINE_DATA_TYPE(U64);
IO_BUFFER_DEFINE_DATA_TYPE(s64);
IO_BUFFER_DEFINE_DATA_TYPE(S64);
IO_BUFFER_DEFINE_DATA_TYPE(f32);
IO_BUFFER_DEFINE_DATA_TYPE(F32);
IO_BUFFER_DEFINE_DATA_TYPE(f64);
IO_BUFFER_DEFINE_DATA_TYPE(F64);
#undef IO_BUFFER_DEFINE_DATA_TYPE
rb_define_singleton_method(rb_cIOBuffer, "size_of", io_buffer_size_of, 1);
2021-07-02 06:41:16 -04:00
// Data access:
2021-12-20 03:22:46 -05:00
rb_define_method(rb_cIOBuffer, "get_value", io_buffer_get_value, 2);
rb_define_method(rb_cIOBuffer, "get_values", io_buffer_get_values, 2);
rb_define_method(rb_cIOBuffer, "each", io_buffer_each, -1);
rb_define_method(rb_cIOBuffer, "values", io_buffer_values, -1);
rb_define_method(rb_cIOBuffer, "each_byte", io_buffer_each_byte, -1);
2021-12-20 03:22:46 -05:00
rb_define_method(rb_cIOBuffer, "set_value", io_buffer_set_value, 3);
rb_define_method(rb_cIOBuffer, "set_values", io_buffer_set_values, 3);
2021-12-20 03:22:46 -05:00
rb_define_method(rb_cIOBuffer, "copy", io_buffer_copy, -1);
rb_define_method(rb_cIOBuffer, "get_string", io_buffer_get_string, -1);
2021-12-20 03:22:46 -05:00
rb_define_method(rb_cIOBuffer, "set_string", io_buffer_set_string, -1);
// Binary data manipulations:
rb_define_method(rb_cIOBuffer, "&", io_buffer_and, 1);
rb_define_method(rb_cIOBuffer, "|", io_buffer_or, 1);
rb_define_method(rb_cIOBuffer, "^", io_buffer_xor, 1);
rb_define_method(rb_cIOBuffer, "~", io_buffer_not, 0);
rb_define_method(rb_cIOBuffer, "and!", io_buffer_and_inplace, 1);
rb_define_method(rb_cIOBuffer, "or!", io_buffer_or_inplace, 1);
rb_define_method(rb_cIOBuffer, "xor!", io_buffer_xor_inplace, 1);
rb_define_method(rb_cIOBuffer, "not!", io_buffer_not_inplace, 0);
// IO operations:
rb_define_method(rb_cIOBuffer, "read", io_buffer_read, -1);
rb_define_method(rb_cIOBuffer, "pread", io_buffer_pread, -1);
rb_define_method(rb_cIOBuffer, "write", io_buffer_write, -1);
rb_define_method(rb_cIOBuffer, "pwrite", io_buffer_pwrite, -1);
2021-07-02 06:41:16 -04:00
}