touch: add new commands

This commit is contained in:
nillerusr
2021-11-16 23:46:29 +03:00
parent f7cdca7ad2
commit d2f3cc44db
138 changed files with 46564 additions and 1231 deletions
@@ -0,0 +1,227 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file alone_decoder.c
/// \brief Decoder for LZMA_Alone files
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#include "alone_decoder.h"
#include "lzma_decoder.h"
#include "lz_decoder.h"
typedef struct {
lzma_next_coder next;
enum {
SEQ_PROPERTIES,
SEQ_DICTIONARY_SIZE,
SEQ_UNCOMPRESSED_SIZE,
SEQ_CODER_INIT,
SEQ_CODE,
} sequence;
/// If true, reject files that are unlikely to be .lzma files.
/// If false, more non-.lzma files get accepted and will give
/// LZMA_DATA_ERROR either immediately or after a few output bytes.
bool picky;
/// Position in the header fields
size_t pos;
/// Uncompressed size decoded from the header
lzma_vli uncompressed_size;
/// Memory usage limit
uint64_t memlimit;
/// Amount of memory actually needed (only an estimate)
uint64_t memusage;
/// Options decoded from the header needed to initialize
/// the LZMA decoder
lzma_options_lzma options;
} lzma_alone_coder;
static lzma_ret
alone_decode(void *coder_ptr,
const lzma_allocator *allocator lzma_attribute((__unused__)),
const uint8_t *restrict in, size_t *restrict in_pos,
size_t in_size, uint8_t *restrict out,
size_t *restrict out_pos, size_t out_size,
lzma_action action)
{
lzma_alone_coder *coder = coder_ptr;
while (*out_pos < out_size
&& (coder->sequence == SEQ_CODE || *in_pos < in_size))
switch (coder->sequence) {
case SEQ_PROPERTIES:
if (lzma_lzma_lclppb_decode(&coder->options, in[*in_pos]))
return LZMA_FORMAT_ERROR;
coder->sequence = SEQ_DICTIONARY_SIZE;
++*in_pos;
break;
case SEQ_DICTIONARY_SIZE:
coder->options.dict_size
|= (size_t)(in[*in_pos]) << (coder->pos * 8);
++*in_pos;
if (++coder->pos < 4)
break;
if (coder->picky && coder->options.dict_size
!= UINT32_MAX) {
// A hack to ditch tons of false positives:
// We allow only dictionary sizes that are
// 2^n or 2^n + 2^(n-1). LZMA_Alone created
// only files with 2^n, but accepts any
// dictionary size.
uint32_t d = coder->options.dict_size - 1;
d |= d >> 2;
d |= d >> 3;
d |= d >> 4;
d |= d >> 8;
d |= d >> 16;
++d;
if (d != coder->options.dict_size)
return LZMA_FORMAT_ERROR;
}
coder->uncompressed_size = LZMA_VLI_UNKNOWN;
// Calculate the memory usage so that it is ready
// for SEQ_CODER_INIT.
coder->memusage = lzma_lzma_decoder_memusage(&coder->options)
+ LZMA_MEMUSAGE_BASE;
coder->pos = 0;
coder->sequence = SEQ_CODER_INIT;
// Fall through
case SEQ_CODER_INIT: {
if (coder->memusage > coder->memlimit)
return LZMA_MEMLIMIT_ERROR;
lzma_filter_info filters[2] = {
{
.init = &lzma_lzma_decoder_init,
.options = &coder->options,
}, {
.init = NULL,
}
};
const lzma_ret ret = lzma_next_filter_init(&coder->next,
allocator, filters);
if (ret != LZMA_OK)
return ret;
// Use a hack to set the uncompressed size.
lzma_lz_decoder_uncompressed(coder->next.coder,
coder->uncompressed_size);
coder->sequence = SEQ_CODE;
break;
}
case SEQ_CODE: {
return coder->next.code(coder->next.coder,
allocator, in, in_pos, in_size,
out, out_pos, out_size, action);
}
default:
return LZMA_PROG_ERROR;
}
return LZMA_OK;
}
static void
alone_decoder_end(void *coder_ptr, const lzma_allocator *allocator)
{
lzma_alone_coder *coder = coder_ptr;
lzma_next_end(&coder->next, allocator);
lzma_free(coder, allocator);
return;
}
static lzma_ret
alone_decoder_memconfig(void *coder_ptr, uint64_t *memusage,
uint64_t *old_memlimit, uint64_t new_memlimit)
{
lzma_alone_coder *coder = coder_ptr;
*memusage = coder->memusage;
*old_memlimit = coder->memlimit;
if (new_memlimit != 0) {
if (new_memlimit < coder->memusage)
return LZMA_MEMLIMIT_ERROR;
coder->memlimit = new_memlimit;
}
return LZMA_OK;
}
extern lzma_ret
lzma_alone_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
uint64_t memlimit, bool picky)
{
lzma_next_coder_init(&lzma_alone_decoder_init, next, allocator);
if (memlimit == 0)
return LZMA_PROG_ERROR;
lzma_alone_coder *coder = next->coder;
if (coder == NULL) {
coder = lzma_alloc(sizeof(lzma_alone_coder), allocator);
if (coder == NULL)
return LZMA_MEM_ERROR;
next->coder = coder;
next->code = &alone_decode;
next->end = &alone_decoder_end;
next->memconfig = &alone_decoder_memconfig;
coder->next = LZMA_NEXT_CODER_INIT;
}
coder->sequence = SEQ_PROPERTIES;
coder->picky = picky;
coder->pos = 0;
coder->options.dict_size = 0;
coder->options.preset_dict = NULL;
coder->options.preset_dict_size = 0;
coder->uncompressed_size = 0;
coder->memlimit = memlimit;
coder->memusage = LZMA_MEMUSAGE_BASE;
return LZMA_OK;
}
extern LZMA_API(lzma_ret)
lzma_alone_decoder(lzma_stream *strm, uint64_t memlimit)
{
lzma_next_strm_init(lzma_alone_decoder_init, strm, memlimit, false);
strm->internal->supported_actions[LZMA_RUN] = true;
strm->internal->supported_actions[LZMA_FINISH] = true;
return LZMA_OK;
}
@@ -0,0 +1,23 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file alone_decoder.h
/// \brief Decoder for LZMA_Alone files
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_ALONE_DECODER_H
#define LZMA_ALONE_DECODER_H
#include "common.h"
extern lzma_ret lzma_alone_decoder_init(
lzma_next_coder *next, const lzma_allocator *allocator,
uint64_t memlimit, bool picky);
#endif
@@ -0,0 +1,160 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file alone_decoder.c
/// \brief Decoder for LZMA_Alone files
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
#include "lzma_encoder.h"
#define ALONE_HEADER_SIZE (1 + 4)
typedef struct {
lzma_next_coder next;
enum {
SEQ_HEADER,
SEQ_CODE,
} sequence;
size_t header_pos;
uint8_t header[ALONE_HEADER_SIZE];
} lzma_alone_coder;
static lzma_ret
alone_encode(void *coder_ptr,
const lzma_allocator *allocator lzma_attribute((__unused__)),
const uint8_t *restrict in, size_t *restrict in_pos,
size_t in_size, uint8_t *restrict out,
size_t *restrict out_pos, size_t out_size,
lzma_action action)
{
lzma_alone_coder *coder = coder_ptr;
while (*out_pos < out_size)
switch (coder->sequence) {
case SEQ_HEADER:
lzma_bufcpy(coder->header, &coder->header_pos,
ALONE_HEADER_SIZE,
out, out_pos, out_size);
if (coder->header_pos < ALONE_HEADER_SIZE)
return LZMA_OK;
coder->sequence = SEQ_CODE;
break;
case SEQ_CODE:
return coder->next.code(coder->next.coder,
allocator, in, in_pos, in_size,
out, out_pos, out_size, action);
default:
assert(0);
return LZMA_PROG_ERROR;
}
return LZMA_OK;
}
static void
alone_encoder_end(void *coder_ptr, const lzma_allocator *allocator)
{
lzma_alone_coder *coder = coder_ptr;
lzma_next_end(&coder->next, allocator);
lzma_free(coder, allocator);
return;
}
// At least for now, this is not used by any internal function.
static lzma_ret
alone_encoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_options_lzma *options)
{
lzma_next_coder_init(&alone_encoder_init, next, allocator);
lzma_alone_coder *coder = next->coder;
if (coder == NULL) {
coder = lzma_alloc(sizeof(lzma_alone_coder), allocator);
if (coder == NULL)
return LZMA_MEM_ERROR;
next->coder = coder;
next->code = &alone_encode;
next->end = &alone_encoder_end;
coder->next = LZMA_NEXT_CODER_INIT;
}
// Basic initializations
coder->sequence = SEQ_HEADER;
coder->header_pos = 0;
// Encode the header:
// - Properties (1 byte)
if (lzma_lzma_lclppb_encode(options, coder->header))
return LZMA_OPTIONS_ERROR;
// - Dictionary size (4 bytes)
if (options->dict_size < LZMA_DICT_SIZE_MIN)
return LZMA_OPTIONS_ERROR;
// Round up to the next 2^n or 2^n + 2^(n - 1) depending on which
// one is the next unless it is UINT32_MAX. While the header would
// allow any 32-bit integer, we do this to keep the decoder of liblzma
// accepting the resulting files.
uint32_t d = options->dict_size - 1;
d |= d >> 2;
d |= d >> 3;
d |= d >> 4;
d |= d >> 8;
d |= d >> 16;
if (d != UINT32_MAX)
++d;
unaligned_write32le(coder->header + 1, d);
// Initialize the LZMA encoder.
const lzma_filter_info filters[2] = {
{
.init = &lzma_lzma_encoder_init,
.options = (void *)(options),
}, {
.init = NULL,
}
};
return lzma_next_filter_init(&coder->next, allocator, filters);
}
/*
extern lzma_ret
lzma_alone_encoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_options_alone *options)
{
lzma_next_coder_init(&alone_encoder_init, next, allocator, options);
}
*/
extern LZMA_API(lzma_ret)
lzma_alone_encoder(lzma_stream *strm, const lzma_options_lzma *options)
{
lzma_next_strm_init(alone_encoder_init, strm, options);
strm->internal->supported_actions[LZMA_RUN] = true;
strm->internal->supported_actions[LZMA_FINISH] = true;
return LZMA_OK;
}
+443
View File
@@ -0,0 +1,443 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file common.h
/// \brief Common functions needed in many places in liblzma
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
/////////////
// Version //
/////////////
extern LZMA_API(uint32_t)
lzma_version_number(void)
{
return LZMA_VERSION;
}
extern LZMA_API(const char *)
lzma_version_string(void)
{
return LZMA_VERSION_STRING;
}
///////////////////////
// Memory allocation //
///////////////////////
extern void * lzma_attribute((__malloc__)) lzma_attr_alloc_size(1)
lzma_alloc(size_t size, const lzma_allocator *allocator)
{
// Some malloc() variants return NULL if called with size == 0.
if (size == 0)
size = 1;
void *ptr;
if (allocator != NULL && allocator->alloc != NULL)
ptr = allocator->alloc(allocator->opaque, 1, size);
else
ptr = malloc(size);
return ptr;
}
extern void * lzma_attribute((__malloc__)) lzma_attr_alloc_size(1)
lzma_alloc_zero(size_t size, const lzma_allocator *allocator)
{
// Some calloc() variants return NULL if called with size == 0.
if (size == 0)
size = 1;
void *ptr;
if (allocator != NULL && allocator->alloc != NULL) {
ptr = allocator->alloc(allocator->opaque, 1, size);
if (ptr != NULL)
memzero(ptr, size);
} else {
ptr = calloc(1, size);
}
return ptr;
}
extern void
lzma_free(void *ptr, const lzma_allocator *allocator)
{
if (allocator != NULL && allocator->free != NULL)
allocator->free(allocator->opaque, ptr);
else
free(ptr);
return;
}
//////////
// Misc //
//////////
extern size_t
lzma_bufcpy(const uint8_t *restrict in, size_t *restrict in_pos,
size_t in_size, uint8_t *restrict out,
size_t *restrict out_pos, size_t out_size)
{
const size_t in_avail = in_size - *in_pos;
const size_t out_avail = out_size - *out_pos;
const size_t copy_size = my_min(in_avail, out_avail);
memcpy(out + *out_pos, in + *in_pos, copy_size);
*in_pos += copy_size;
*out_pos += copy_size;
return copy_size;
}
extern lzma_ret
lzma_next_filter_init(lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_filter_info *filters)
{
lzma_next_coder_init(filters[0].init, next, allocator);
next->id = filters[0].id;
return filters[0].init == NULL
? LZMA_OK : filters[0].init(next, allocator, filters);
}
extern lzma_ret
lzma_next_filter_update(lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_filter *reversed_filters)
{
// Check that the application isn't trying to change the Filter ID.
// End of filters is indicated with LZMA_VLI_UNKNOWN in both
// reversed_filters[0].id and next->id.
if (reversed_filters[0].id != next->id)
return LZMA_PROG_ERROR;
if (reversed_filters[0].id == LZMA_VLI_UNKNOWN)
return LZMA_OK;
assert(next->update != NULL);
return next->update(next->coder, allocator, NULL, reversed_filters);
}
extern void
lzma_next_end(lzma_next_coder *next, const lzma_allocator *allocator)
{
if (next->init != (uintptr_t)(NULL)) {
// To avoid tiny end functions that simply call
// lzma_free(coder, allocator), we allow leaving next->end
// NULL and call lzma_free() here.
if (next->end != NULL)
next->end(next->coder, allocator);
else
lzma_free(next->coder, allocator);
// Reset the variables so the we don't accidentally think
// that it is an already initialized coder.
*next = LZMA_NEXT_CODER_INIT;
}
return;
}
//////////////////////////////////////
// External to internal API wrapper //
//////////////////////////////////////
extern lzma_ret
lzma_strm_init(lzma_stream *strm)
{
if (strm == NULL)
return LZMA_PROG_ERROR;
if (strm->internal == NULL) {
strm->internal = lzma_alloc(sizeof(lzma_internal),
strm->allocator);
if (strm->internal == NULL)
return LZMA_MEM_ERROR;
strm->internal->next = LZMA_NEXT_CODER_INIT;
}
memzero(strm->internal->supported_actions,
sizeof(strm->internal->supported_actions));
strm->internal->sequence = ISEQ_RUN;
strm->internal->allow_buf_error = false;
strm->total_in = 0;
strm->total_out = 0;
return LZMA_OK;
}
extern LZMA_API(lzma_ret)
lzma_code(lzma_stream *strm, lzma_action action)
{
// Sanity checks
if ((strm->next_in == NULL && strm->avail_in != 0)
|| (strm->next_out == NULL && strm->avail_out != 0)
|| strm->internal == NULL
|| strm->internal->next.code == NULL
|| (unsigned int)(action) > LZMA_ACTION_MAX
|| !strm->internal->supported_actions[action])
return LZMA_PROG_ERROR;
// Check if unsupported members have been set to non-zero or non-NULL,
// which would indicate that some new feature is wanted.
if (strm->reserved_ptr1 != NULL
|| strm->reserved_ptr2 != NULL
|| strm->reserved_ptr3 != NULL
|| strm->reserved_ptr4 != NULL
|| strm->reserved_int1 != 0
|| strm->reserved_int2 != 0
|| strm->reserved_int3 != 0
|| strm->reserved_int4 != 0
|| strm->reserved_enum1 != LZMA_RESERVED_ENUM
|| strm->reserved_enum2 != LZMA_RESERVED_ENUM)
return LZMA_OPTIONS_ERROR;
switch (strm->internal->sequence) {
case ISEQ_RUN:
switch (action) {
case LZMA_RUN:
break;
case LZMA_SYNC_FLUSH:
strm->internal->sequence = ISEQ_SYNC_FLUSH;
break;
case LZMA_FULL_FLUSH:
strm->internal->sequence = ISEQ_FULL_FLUSH;
break;
case LZMA_FINISH:
strm->internal->sequence = ISEQ_FINISH;
break;
case LZMA_FULL_BARRIER:
strm->internal->sequence = ISEQ_FULL_BARRIER;
break;
}
break;
case ISEQ_SYNC_FLUSH:
// The same action must be used until we return
// LZMA_STREAM_END, and the amount of input must not change.
if (action != LZMA_SYNC_FLUSH
|| strm->internal->avail_in != strm->avail_in)
return LZMA_PROG_ERROR;
break;
case ISEQ_FULL_FLUSH:
if (action != LZMA_FULL_FLUSH
|| strm->internal->avail_in != strm->avail_in)
return LZMA_PROG_ERROR;
break;
case ISEQ_FINISH:
if (action != LZMA_FINISH
|| strm->internal->avail_in != strm->avail_in)
return LZMA_PROG_ERROR;
break;
case ISEQ_FULL_BARRIER:
if (action != LZMA_FULL_BARRIER
|| strm->internal->avail_in != strm->avail_in)
return LZMA_PROG_ERROR;
break;
case ISEQ_END:
return LZMA_STREAM_END;
case ISEQ_ERROR:
default:
return LZMA_PROG_ERROR;
}
size_t in_pos = 0;
size_t out_pos = 0;
lzma_ret ret = strm->internal->next.code(
strm->internal->next.coder, strm->allocator,
strm->next_in, &in_pos, strm->avail_in,
strm->next_out, &out_pos, strm->avail_out, action);
strm->next_in += in_pos;
strm->avail_in -= in_pos;
strm->total_in += in_pos;
strm->next_out += out_pos;
strm->avail_out -= out_pos;
strm->total_out += out_pos;
strm->internal->avail_in = strm->avail_in;
// Cast is needed to silence a warning about LZMA_TIMED_OUT, which
// isn't part of lzma_ret enumeration.
switch ((unsigned int)(ret)) {
case LZMA_OK:
// Don't return LZMA_BUF_ERROR when it happens the first time.
// This is to avoid returning LZMA_BUF_ERROR when avail_out
// was zero but still there was no more data left to written
// to next_out.
if (out_pos == 0 && in_pos == 0) {
if (strm->internal->allow_buf_error)
ret = LZMA_BUF_ERROR;
else
strm->internal->allow_buf_error = true;
} else {
strm->internal->allow_buf_error = false;
}
break;
case LZMA_TIMED_OUT:
strm->internal->allow_buf_error = false;
ret = LZMA_OK;
break;
case LZMA_STREAM_END:
if (strm->internal->sequence == ISEQ_SYNC_FLUSH
|| strm->internal->sequence == ISEQ_FULL_FLUSH
|| strm->internal->sequence
== ISEQ_FULL_BARRIER)
strm->internal->sequence = ISEQ_RUN;
else
strm->internal->sequence = ISEQ_END;
// Fall through
case LZMA_NO_CHECK:
case LZMA_UNSUPPORTED_CHECK:
case LZMA_GET_CHECK:
case LZMA_MEMLIMIT_ERROR:
// Something else than LZMA_OK, but not a fatal error,
// that is, coding may be continued (except if ISEQ_END).
strm->internal->allow_buf_error = false;
break;
default:
// All the other errors are fatal; coding cannot be continued.
assert(ret != LZMA_BUF_ERROR);
strm->internal->sequence = ISEQ_ERROR;
break;
}
return ret;
}
extern LZMA_API(void)
lzma_end(lzma_stream *strm)
{
if (strm != NULL && strm->internal != NULL) {
lzma_next_end(&strm->internal->next, strm->allocator);
lzma_free(strm->internal, strm->allocator);
strm->internal = NULL;
}
return;
}
extern LZMA_API(void)
lzma_get_progress(lzma_stream *strm,
uint64_t *progress_in, uint64_t *progress_out)
{
if (strm->internal->next.get_progress != NULL) {
strm->internal->next.get_progress(strm->internal->next.coder,
progress_in, progress_out);
} else {
*progress_in = strm->total_in;
*progress_out = strm->total_out;
}
return;
}
extern LZMA_API(lzma_check)
lzma_get_check(const lzma_stream *strm)
{
// Return LZMA_CHECK_NONE if we cannot know the check type.
// It's a bug in the application if this happens.
if (strm->internal->next.get_check == NULL)
return LZMA_CHECK_NONE;
return strm->internal->next.get_check(strm->internal->next.coder);
}
extern LZMA_API(uint64_t)
lzma_memusage(const lzma_stream *strm)
{
uint64_t memusage;
uint64_t old_memlimit;
if (strm == NULL || strm->internal == NULL
|| strm->internal->next.memconfig == NULL
|| strm->internal->next.memconfig(
strm->internal->next.coder,
&memusage, &old_memlimit, 0) != LZMA_OK)
return 0;
return memusage;
}
extern LZMA_API(uint64_t)
lzma_memlimit_get(const lzma_stream *strm)
{
uint64_t old_memlimit;
uint64_t memusage;
if (strm == NULL || strm->internal == NULL
|| strm->internal->next.memconfig == NULL
|| strm->internal->next.memconfig(
strm->internal->next.coder,
&memusage, &old_memlimit, 0) != LZMA_OK)
return 0;
return old_memlimit;
}
extern LZMA_API(lzma_ret)
lzma_memlimit_set(lzma_stream *strm, uint64_t new_memlimit)
{
// Dummy variables to simplify memconfig functions
uint64_t old_memlimit;
uint64_t memusage;
if (strm == NULL || strm->internal == NULL
|| strm->internal->next.memconfig == NULL)
return LZMA_PROG_ERROR;
if (new_memlimit != 0 && new_memlimit < LZMA_MEMUSAGE_BASE)
return LZMA_MEMLIMIT_ERROR;
return strm->internal->next.memconfig(strm->internal->next.coder,
&memusage, &old_memlimit, new_memlimit);
}
+313
View File
@@ -0,0 +1,313 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file common.h
/// \brief Definitions common to the whole liblzma library
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_COMMON_H
#define LZMA_COMMON_H
#include "sysdefs.h"
#include "tuklib_integer.h"
#if defined(_WIN32) || defined(__CYGWIN__)
# ifdef DLL_EXPORT
# define LZMA_API_EXPORT __declspec(dllexport)
# else
# define LZMA_API_EXPORT
# endif
// Don't use ifdef or defined() below.
#elif HAVE_VISIBILITY
# define LZMA_API_EXPORT __attribute__((__visibility__("default")))
#else
# define LZMA_API_EXPORT
#endif
#define LZMA_API(type) LZMA_API_EXPORT type LZMA_API_CALL
#include "lzma.h"
// These allow helping the compiler in some often-executed branches, whose
// result is almost always the same.
#ifdef __GNUC__
# define likely(expr) __builtin_expect(expr, true)
# define unlikely(expr) __builtin_expect(expr, false)
#else
# define likely(expr) (expr)
# define unlikely(expr) (expr)
#endif
/// Size of temporary buffers needed in some filters
#define LZMA_BUFFER_SIZE 4096
/// Maximum number of worker threads within one multithreaded component.
/// The limit exists solely to make it simpler to prevent integer overflows
/// when allocating structures etc. This should be big enough for now...
/// the code won't scale anywhere close to this number anyway.
#define LZMA_THREADS_MAX 16384
/// Starting value for memory usage estimates. Instead of calculating size
/// of _every_ structure and taking into account malloc() overhead etc., we
/// add a base size to all memory usage estimates. It's not very accurate
/// but should be easily good enough.
#define LZMA_MEMUSAGE_BASE (UINT64_C(1) << 15)
/// Start of internal Filter ID space. These IDs must never be used
/// in Streams.
#define LZMA_FILTER_RESERVED_START (LZMA_VLI_C(1) << 62)
/// Supported flags that can be passed to lzma_stream_decoder()
/// or lzma_auto_decoder().
#define LZMA_SUPPORTED_FLAGS \
( LZMA_TELL_NO_CHECK \
| LZMA_TELL_UNSUPPORTED_CHECK \
| LZMA_TELL_ANY_CHECK \
| LZMA_IGNORE_CHECK \
| LZMA_CONCATENATED )
/// Largest valid lzma_action value as unsigned integer.
#define LZMA_ACTION_MAX ((unsigned int)(LZMA_FULL_BARRIER))
/// Special return value (lzma_ret) to indicate that a timeout was reached
/// and lzma_code() must not return LZMA_BUF_ERROR. This is converted to
/// LZMA_OK in lzma_code(). This is not in the lzma_ret enumeration because
/// there's no need to have it in the public API.
#define LZMA_TIMED_OUT 32
typedef struct lzma_next_coder_s lzma_next_coder;
typedef struct lzma_filter_info_s lzma_filter_info;
/// Type of a function used to initialize a filter encoder or decoder
typedef lzma_ret (*lzma_init_function)(
lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_filter_info *filters);
/// Type of a function to do some kind of coding work (filters, Stream,
/// Block encoders/decoders etc.). Some special coders use don't use both
/// input and output buffers, but for simplicity they still use this same
/// function prototype.
typedef lzma_ret (*lzma_code_function)(
void *coder, const lzma_allocator *allocator,
const uint8_t *restrict in, size_t *restrict in_pos,
size_t in_size, uint8_t *restrict out,
size_t *restrict out_pos, size_t out_size,
lzma_action action);
/// Type of a function to free the memory allocated for the coder
typedef void (*lzma_end_function)(
void *coder, const lzma_allocator *allocator);
/// Raw coder validates and converts an array of lzma_filter structures to
/// an array of lzma_filter_info structures. This array is used with
/// lzma_next_filter_init to initialize the filter chain.
struct lzma_filter_info_s {
/// Filter ID. This is used only by the encoder
/// with lzma_filters_update().
lzma_vli id;
/// Pointer to function used to initialize the filter.
/// This is NULL to indicate end of array.
lzma_init_function init;
/// Pointer to filter's options structure
void *options;
};
/// Hold data and function pointers of the next filter in the chain.
struct lzma_next_coder_s {
/// Pointer to coder-specific data
void *coder;
/// Filter ID. This is LZMA_VLI_UNKNOWN when this structure doesn't
/// point to a filter coder.
lzma_vli id;
/// "Pointer" to init function. This is never called here.
/// We need only to detect if we are initializing a coder
/// that was allocated earlier. See lzma_next_coder_init and
/// lzma_next_strm_init macros in this file.
uintptr_t init;
/// Pointer to function to do the actual coding
lzma_code_function code;
/// Pointer to function to free lzma_next_coder.coder. This can
/// be NULL; in that case, lzma_free is called to free
/// lzma_next_coder.coder.
lzma_end_function end;
/// Pointer to a function to get progress information. If this is NULL,
/// lzma_stream.total_in and .total_out are used instead.
void (*get_progress)(void *coder,
uint64_t *progress_in, uint64_t *progress_out);
/// Pointer to function to return the type of the integrity check.
/// Most coders won't support this.
lzma_check (*get_check)(const void *coder);
/// Pointer to function to get and/or change the memory usage limit.
/// If new_memlimit == 0, the limit is not changed.
lzma_ret (*memconfig)(void *coder, uint64_t *memusage,
uint64_t *old_memlimit, uint64_t new_memlimit);
/// Update the filter-specific options or the whole filter chain
/// in the encoder.
lzma_ret (*update)(void *coder, const lzma_allocator *allocator,
const lzma_filter *filters,
const lzma_filter *reversed_filters);
};
/// Macro to initialize lzma_next_coder structure
#define LZMA_NEXT_CODER_INIT \
(lzma_next_coder){ \
.coder = NULL, \
.init = (uintptr_t)(NULL), \
.id = LZMA_VLI_UNKNOWN, \
.code = NULL, \
.end = NULL, \
.get_progress = NULL, \
.get_check = NULL, \
.memconfig = NULL, \
.update = NULL, \
}
/// Internal data for lzma_strm_init, lzma_code, and lzma_end. A pointer to
/// this is stored in lzma_stream.
struct lzma_internal_s {
/// The actual coder that should do something useful
lzma_next_coder next;
/// Track the state of the coder. This is used to validate arguments
/// so that the actual coders can rely on e.g. that LZMA_SYNC_FLUSH
/// is used on every call to lzma_code until next.code has returned
/// LZMA_STREAM_END.
enum {
ISEQ_RUN,
ISEQ_SYNC_FLUSH,
ISEQ_FULL_FLUSH,
ISEQ_FINISH,
ISEQ_FULL_BARRIER,
ISEQ_END,
ISEQ_ERROR,
} sequence;
/// A copy of lzma_stream avail_in. This is used to verify that the
/// amount of input doesn't change once e.g. LZMA_FINISH has been
/// used.
size_t avail_in;
/// Indicates which lzma_action values are allowed by next.code.
bool supported_actions[LZMA_ACTION_MAX + 1];
/// If true, lzma_code will return LZMA_BUF_ERROR if no progress was
/// made (no input consumed and no output produced by next.code).
bool allow_buf_error;
};
/// Allocates memory
extern void *lzma_alloc(size_t size, const lzma_allocator *allocator)
lzma_attribute((__malloc__)) lzma_attr_alloc_size(1);
/// Allocates memory and zeroes it (like calloc()). This can be faster
/// than lzma_alloc() + memzero() while being backward compatible with
/// custom allocators.
extern void * lzma_attribute((__malloc__)) lzma_attr_alloc_size(1)
lzma_alloc_zero(size_t size, const lzma_allocator *allocator);
/// Frees memory
extern void lzma_free(void *ptr, const lzma_allocator *allocator);
/// Allocates strm->internal if it is NULL, and initializes *strm and
/// strm->internal. This function is only called via lzma_next_strm_init macro.
extern lzma_ret lzma_strm_init(lzma_stream *strm);
/// Initializes the next filter in the chain, if any. This takes care of
/// freeing the memory of previously initialized filter if it is different
/// than the filter being initialized now. This way the actual filter
/// initialization functions don't need to use lzma_next_coder_init macro.
extern lzma_ret lzma_next_filter_init(lzma_next_coder *next,
const lzma_allocator *allocator,
const lzma_filter_info *filters);
/// Update the next filter in the chain, if any. This checks that
/// the application is not trying to change the Filter IDs.
extern lzma_ret lzma_next_filter_update(
lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_filter *reversed_filters);
/// Frees the memory allocated for next->coder either using next->end or,
/// if next->end is NULL, using lzma_free.
extern void lzma_next_end(lzma_next_coder *next,
const lzma_allocator *allocator);
/// Copy as much data as possible from in[] to out[] and update *in_pos
/// and *out_pos accordingly. Returns the number of bytes copied.
extern size_t lzma_bufcpy(const uint8_t *restrict in, size_t *restrict in_pos,
size_t in_size, uint8_t *restrict out,
size_t *restrict out_pos, size_t out_size);
/// \brief Return if expression doesn't evaluate to LZMA_OK
///
/// There are several situations where we want to return immediately
/// with the value of expr if it isn't LZMA_OK. This macro shortens
/// the code a little.
#define return_if_error(expr) \
do { \
const lzma_ret ret_ = (expr); \
if (ret_ != LZMA_OK) \
return ret_; \
} while (0)
/// If next isn't already initialized, free the previous coder. Then mark
/// that next is _possibly_ initialized for the coder using this macro.
/// "Possibly" means that if e.g. allocation of next->coder fails, the
/// structure isn't actually initialized for this coder, but leaving
/// next->init to func is still OK.
#define lzma_next_coder_init(func, next, allocator) \
do { \
if ((uintptr_t)(func) != (next)->init) \
lzma_next_end(next, allocator); \
(next)->init = (uintptr_t)(func); \
} while (0)
/// Initializes lzma_strm and calls func() to initialize strm->internal->next.
/// (The function being called will use lzma_next_coder_init()). If
/// initialization fails, memory that wasn't freed by func() is freed
/// along strm->internal.
#define lzma_next_strm_init(func, strm, ...) \
do { \
return_if_error(lzma_strm_init(strm)); \
const lzma_ret ret_ = func(&(strm)->internal->next, \
(strm)->allocator, __VA_ARGS__); \
if (ret_ != LZMA_OK) { \
lzma_end(strm); \
return ret_; \
} \
} while (0)
#endif
@@ -0,0 +1,238 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_decoder.c
/// \brief Filter ID mapping to filter-specific functions
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#include "filter_encoder.h"
#include "lzma_encoder.h"
#ifdef HAVE_DECODER_LZMA2
#include "lzma2_encoder.h"
#endif
#if defined(HAVE_DECODER_X86) || \
defined(HAVE_DECODER_POWERPC) || \
defined(HAVE_DECODER_IA64) || \
defined(HAVE_DECODER_ARM) || \
defined(HAVE_DECODER_ARMTHUMB) || \
defined(HAVE_DECODER_SPARC)
#include "simple_encoder.h"
#endif
#ifdef HAVE_DECODER_DELTA
#include "delta_encoder.h"
#endif
typedef struct {
/// Filter ID
lzma_vli id;
/// Initializes the filter encoder and calls lzma_next_filter_init()
/// for filters + 1.
lzma_init_function init;
/// Calculates memory usage of the encoder. If the options are
/// invalid, UINT64_MAX is returned.
uint64_t (*memusage)(const void *options);
/// Calculates the recommended Uncompressed Size for .xz Blocks to
/// which the input data can be split to make multithreaded
/// encoding possible. If this is NULL, it is assumed that
/// the encoder is fast enough with single thread.
uint64_t (*block_size)(const void *options);
/// Tells the size of the Filter Properties field. If options are
/// invalid, UINT32_MAX is returned. If this is NULL, props_size_fixed
/// is used.
lzma_ret (*props_size_get)(uint32_t *size, const void *options);
uint32_t props_size_fixed;
/// Encodes Filter Properties.
///
/// \return - LZMA_OK: Properties encoded successfully.
/// - LZMA_OPTIONS_ERROR: Unsupported options
/// - LZMA_PROG_ERROR: Invalid options or not enough
/// output space
lzma_ret (*props_encode)(const void *options, uint8_t *out);
} lzma_filter_encoder;
static const lzma_filter_encoder encoders[] = {
#ifdef HAVE_ENCODER_LZMA1
{
.id = LZMA_FILTER_LZMA1,
.init = &lzma_lzma_encoder_init,
.memusage = &lzma_lzma_encoder_memusage,
.block_size = NULL, // FIXME
.props_size_get = NULL,
.props_size_fixed = 5,
.props_encode = &lzma_lzma_props_encode,
},
#endif
#ifdef HAVE_ENCODER_LZMA2
{
.id = LZMA_FILTER_LZMA2,
.init = &lzma_lzma2_encoder_init,
.memusage = &lzma_lzma2_encoder_memusage,
.block_size = &lzma_lzma2_block_size, // FIXME
.props_size_get = NULL,
.props_size_fixed = 1,
.props_encode = &lzma_lzma2_props_encode,
},
#endif
#ifdef HAVE_ENCODER_X86
{
.id = LZMA_FILTER_X86,
.init = &lzma_simple_x86_encoder_init,
.memusage = NULL,
.block_size = NULL,
.props_size_get = &lzma_simple_props_size,
.props_encode = &lzma_simple_props_encode,
},
#endif
#ifdef HAVE_ENCODER_POWERPC
{
.id = LZMA_FILTER_POWERPC,
.init = &lzma_simple_powerpc_encoder_init,
.memusage = NULL,
.block_size = NULL,
.props_size_get = &lzma_simple_props_size,
.props_encode = &lzma_simple_props_encode,
},
#endif
#ifdef HAVE_ENCODER_IA64
{
.id = LZMA_FILTER_IA64,
.init = &lzma_simple_ia64_encoder_init,
.memusage = NULL,
.block_size = NULL,
.props_size_get = &lzma_simple_props_size,
.props_encode = &lzma_simple_props_encode,
},
#endif
#ifdef HAVE_ENCODER_ARM
{
.id = LZMA_FILTER_ARM,
.init = &lzma_simple_arm_encoder_init,
.memusage = NULL,
.block_size = NULL,
.props_size_get = &lzma_simple_props_size,
.props_encode = &lzma_simple_props_encode,
},
#endif
#ifdef HAVE_ENCODER_ARMTHUMB
{
.id = LZMA_FILTER_ARMTHUMB,
.init = &lzma_simple_armthumb_encoder_init,
.memusage = NULL,
.block_size = NULL,
.props_size_get = &lzma_simple_props_size,
.props_encode = &lzma_simple_props_encode,
},
#endif
#ifdef HAVE_ENCODER_SPARC
{
.id = LZMA_FILTER_SPARC,
.init = &lzma_simple_sparc_encoder_init,
.memusage = NULL,
.block_size = NULL,
.props_size_get = &lzma_simple_props_size,
.props_encode = &lzma_simple_props_encode,
},
#endif
#ifdef HAVE_ENCODER_DELTA
{
.id = LZMA_FILTER_DELTA,
.init = &lzma_delta_encoder_init,
.memusage = &lzma_delta_coder_memusage,
.block_size = NULL,
.props_size_get = NULL,
.props_size_fixed = 1,
.props_encode = &lzma_delta_props_encode,
},
#endif
};
static const lzma_filter_encoder *
encoder_find(lzma_vli id)
{
for (size_t i = 0; i < ARRAY_SIZE(encoders); ++i)
if (encoders[i].id == id)
return encoders + i;
return NULL;
}
extern LZMA_API(lzma_bool)
lzma_filter_encoder_is_supported(lzma_vli id)
{
return encoder_find(id) != NULL;
}
extern uint64_t
lzma_mt_block_size(const lzma_filter *filters)
{
uint64_t max = 0;
for (size_t i = 0; filters[i].id != LZMA_VLI_UNKNOWN; ++i) {
const lzma_filter_encoder *const fe
= encoder_find(filters[i].id);
if (fe->block_size != NULL) {
const uint64_t size
= fe->block_size(filters[i].options);
if (size == 0)
return 0;
if (size > max)
max = size;
}
}
return max;
}
extern LZMA_API(lzma_ret)
lzma_properties_size(uint32_t *size, const lzma_filter *filter)
{
const lzma_filter_encoder *const fe = encoder_find(filter->id);
if (fe == NULL) {
// Unknown filter - if the Filter ID is a proper VLI,
// return LZMA_OPTIONS_ERROR instead of LZMA_PROG_ERROR,
// because it's possible that we just don't have support
// compiled in for the requested filter.
return filter->id <= LZMA_VLI_MAX
? LZMA_OPTIONS_ERROR : LZMA_PROG_ERROR;
}
if (fe->props_size_get == NULL) {
// No props_size_get() function, use props_size_fixed.
*size = fe->props_size_fixed;
return LZMA_OK;
}
return fe->props_size_get(size, filter->options);
}
extern LZMA_API(lzma_ret)
lzma_properties_encode(const lzma_filter *filter, uint8_t *props)
{
const lzma_filter_encoder *const fe = encoder_find(filter->id);
if (fe == NULL)
return LZMA_PROG_ERROR;
if (fe->props_encode == NULL)
return LZMA_OK;
return fe->props_encode(filter->options, props);
}
@@ -0,0 +1,27 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_encoder.c
/// \brief Filter ID mapping to filter-specific functions
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_FILTER_ENCODER_H
#define LZMA_FILTER_ENCODER_H
#include "common.h"
// FIXME: Might become a part of the public API.
extern uint64_t lzma_mt_block_size(const lzma_filter *filters);
extern lzma_ret lzma_raw_encoder_init(
lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_filter *filters);
#endif
+73
View File
@@ -0,0 +1,73 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file index.h
/// \brief Handling of Index
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_INDEX_H
#define LZMA_INDEX_H
#include "common.h"
/// Minimum Unpadded Size
#define UNPADDED_SIZE_MIN LZMA_VLI_C(5)
/// Maximum Unpadded Size
#define UNPADDED_SIZE_MAX (LZMA_VLI_MAX & ~LZMA_VLI_C(3))
/// Get the size of the Index Padding field. This is needed by Index encoder
/// and decoder, but applications should have no use for this.
extern uint32_t lzma_index_padding_size(const lzma_index *i);
/// Set for how many Records to allocate memory the next time
/// lzma_index_append() needs to allocate space for a new Record.
/// This is used only by the Index decoder.
extern void lzma_index_prealloc(lzma_index *i, lzma_vli records);
/// Round the variable-length integer to the next multiple of four.
static inline lzma_vli
vli_ceil4(lzma_vli vli)
{
assert(vli <= LZMA_VLI_MAX);
return (vli + 3) & ~LZMA_VLI_C(3);
}
/// Calculate the size of the Index field excluding Index Padding
static inline lzma_vli
index_size_unpadded(lzma_vli count, lzma_vli index_list_size)
{
// Index Indicator + Number of Records + List of Records + CRC32
return 1 + lzma_vli_size(count) + index_list_size + 4;
}
/// Calculate the size of the Index field including Index Padding
static inline lzma_vli
index_size(lzma_vli count, lzma_vli index_list_size)
{
return vli_ceil4(index_size_unpadded(count, index_list_size));
}
/// Calculate the total size of the Stream
static inline lzma_vli
index_stream_size(lzma_vli blocks_size,
lzma_vli count, lzma_vli index_list_size)
{
return LZMA_STREAM_HEADER_SIZE + blocks_size
+ index_size(count, index_list_size)
+ LZMA_STREAM_HEADER_SIZE;
}
#endif
+175
View File
@@ -0,0 +1,175 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file memcmplen.h
/// \brief Optimized comparison of two buffers
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_MEMCMPLEN_H
#define LZMA_MEMCMPLEN_H
#include "common.h"
#ifdef HAVE_IMMINTRIN_H
# include <immintrin.h>
#endif
/// Find out how many equal bytes the two buffers have.
///
/// \param buf1 First buffer
/// \param buf2 Second buffer
/// \param len How many bytes have already been compared and will
/// be assumed to match
/// \param limit How many bytes to compare at most, including the
/// already-compared bytes. This must be significantly
/// smaller than UINT32_MAX to avoid integer overflows.
/// Up to LZMA_MEMCMPLEN_EXTRA bytes may be read past
/// the specified limit from both buf1 and buf2.
///
/// \return Number of equal bytes in the buffers is returned.
/// This is always at least len and at most limit.
///
/// \note LZMA_MEMCMPLEN_EXTRA defines how many extra bytes may be read.
/// It's rounded up to 2^n. This extra amount needs to be
/// allocated in the buffers being used. It needs to be
/// initialized too to keep Valgrind quiet.
static inline uint32_t lzma_attribute((__always_inline__))
lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2,
uint32_t len, uint32_t limit)
{
assert(len <= limit);
assert(limit <= UINT32_MAX / 2);
#if defined(TUKLIB_FAST_UNALIGNED_ACCESS) \
&& ((TUKLIB_GNUC_REQ(3, 4) && defined(__x86_64__)) \
|| (defined(__INTEL_COMPILER) && defined(__x86_64__)) \
|| (defined(__INTEL_COMPILER) && defined(_M_X64)) \
|| (defined(_MSC_VER) && defined(_M_X64)))
// NOTE: This will use 64-bit unaligned access which
// TUKLIB_FAST_UNALIGNED_ACCESS wasn't meant to permit, but
// it's convenient here at least as long as it's x86-64 only.
//
// I keep this x86-64 only for now since that's where I know this
// to be a good method. This may be fine on other 64-bit CPUs too.
// On big endian one should use xor instead of subtraction and switch
// to __builtin_clzll().
#define LZMA_MEMCMPLEN_EXTRA 8
while (len < limit) {
const uint64_t x = *(const uint64_t *)(buf1 + len)
- *(const uint64_t *)(buf2 + len);
if (x != 0) {
# if defined(_M_X64) // MSVC or Intel C compiler on Windows
unsigned long tmp;
_BitScanForward64(&tmp, x);
len += (uint32_t)tmp >> 3;
# else // GCC, clang, or Intel C compiler
len += (uint32_t)__builtin_ctzll(x) >> 3;
# endif
return my_min(len, limit);
}
len += 8;
}
return limit;
#elif defined(TUKLIB_FAST_UNALIGNED_ACCESS) \
&& defined(HAVE__MM_MOVEMASK_EPI8) \
&& ((defined(__GNUC__) && defined(__SSE2_MATH__)) \
|| (defined(__INTEL_COMPILER) && defined(__SSE2__)) \
|| (defined(_MSC_VER) && defined(_M_IX86_FP) \
&& _M_IX86_FP >= 2))
// NOTE: Like above, this will use 128-bit unaligned access which
// TUKLIB_FAST_UNALIGNED_ACCESS wasn't meant to permit.
//
// SSE2 version for 32-bit and 64-bit x86. On x86-64 the above
// version is sometimes significantly faster and sometimes
// slightly slower than this SSE2 version, so this SSE2
// version isn't used on x86-64.
# define LZMA_MEMCMPLEN_EXTRA 16
while (len < limit) {
const uint32_t x = 0xFFFF ^ _mm_movemask_epi8(_mm_cmpeq_epi8(
_mm_loadu_si128((const __m128i *)(buf1 + len)),
_mm_loadu_si128((const __m128i *)(buf2 + len))));
if (x != 0) {
# if defined(__INTEL_COMPILER)
len += _bit_scan_forward(x);
# elif defined(_MSC_VER)
unsigned long tmp;
_BitScanForward(&tmp, x);
len += tmp;
# else
len += __builtin_ctz(x);
# endif
return my_min(len, limit);
}
len += 16;
}
return limit;
#elif defined(TUKLIB_FAST_UNALIGNED_ACCESS) && !defined(WORDS_BIGENDIAN)
// Generic 32-bit little endian method
# define LZMA_MEMCMPLEN_EXTRA 4
while (len < limit) {
uint32_t x = *(const uint32_t *)(buf1 + len)
- *(const uint32_t *)(buf2 + len);
if (x != 0) {
if ((x & 0xFFFF) == 0) {
len += 2;
x >>= 16;
}
if ((x & 0xFF) == 0)
++len;
return my_min(len, limit);
}
len += 4;
}
return limit;
#elif defined(TUKLIB_FAST_UNALIGNED_ACCESS) && defined(WORDS_BIGENDIAN)
// Generic 32-bit big endian method
# define LZMA_MEMCMPLEN_EXTRA 4
while (len < limit) {
uint32_t x = *(const uint32_t *)(buf1 + len)
^ *(const uint32_t *)(buf2 + len);
if (x != 0) {
if ((x & 0xFFFF0000) == 0) {
len += 2;
x <<= 16;
}
if ((x & 0xFF000000) == 0)
++len;
return my_min(len, limit);
}
len += 4;
}
return limit;
#else
// Simple portable version that doesn't use unaligned access.
# define LZMA_MEMCMPLEN_EXTRA 0
while (len < limit && buf1[len] == buf2[len])
++len;
return len;
#endif
}
#endif
+204
View File
@@ -0,0 +1,204 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file sysdefs.h
/// \brief Common includes, definitions, system-specific things etc.
///
/// This file is used also by the lzma command line tool, that's why this
/// file is separate from common.h.
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_SYSDEFS_H
#define LZMA_SYSDEFS_H
//////////////
// Includes //
//////////////
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
// Get standard-compliant stdio functions under MinGW and MinGW-w64.
#ifdef __MINGW32__
# define __USE_MINGW_ANSI_STDIO 1
#endif
// size_t and NULL
#include <stddef.h>
#ifdef HAVE_INTTYPES_H
# include <inttypes.h>
#endif
// C99 says that inttypes.h always includes stdint.h, but some systems
// don't do that, and require including stdint.h separately.
#ifdef HAVE_STDINT_H
# include <stdint.h>
#endif
// Some pre-C99 systems have SIZE_MAX in limits.h instead of stdint.h. The
// limits are also used to figure out some macros missing from pre-C99 systems.
#ifdef HAVE_LIMITS_H
# include <limits.h>
#endif
// Be more compatible with systems that have non-conforming inttypes.h.
// We assume that int is 32-bit and that long is either 32-bit or 64-bit.
// Full Autoconf test could be more correct, but this should work well enough.
// Note that this duplicates some code from lzma.h, but this is better since
// we can work without inttypes.h thanks to Autoconf tests.
#ifndef UINT32_C
# if UINT_MAX != 4294967295U
# error UINT32_C is not defined and unsigned int is not 32-bit.
# endif
# define UINT32_C(n) n ## U
#endif
#ifndef UINT32_MAX
# define UINT32_MAX UINT32_C(4294967295)
#endif
#ifndef PRIu32
# define PRIu32 "u"
#endif
#ifndef PRIx32
# define PRIx32 "x"
#endif
#ifndef PRIX32
# define PRIX32 "X"
#endif
#if ULONG_MAX == 4294967295UL
# ifndef UINT64_C
# define UINT64_C(n) n ## ULL
# endif
# ifndef PRIu64
# define PRIu64 "llu"
# endif
# ifndef PRIx64
# define PRIx64 "llx"
# endif
# ifndef PRIX64
# define PRIX64 "llX"
# endif
#else
# ifndef UINT64_C
# define UINT64_C(n) n ## UL
# endif
# ifndef PRIu64
# define PRIu64 "lu"
# endif
# ifndef PRIx64
# define PRIx64 "lx"
# endif
# ifndef PRIX64
# define PRIX64 "lX"
# endif
#endif
#ifndef UINT64_MAX
# define UINT64_MAX UINT64_C(18446744073709551615)
#endif
// Incorrect(?) SIZE_MAX:
// - Interix headers typedef size_t to unsigned long,
// but a few lines later define SIZE_MAX to INT32_MAX.
// - SCO OpenServer (x86) headers typedef size_t to unsigned int
// but define SIZE_MAX to INT32_MAX.
#if defined(__INTERIX) || defined(_SCO_DS)
# undef SIZE_MAX
#endif
// The code currently assumes that size_t is either 32-bit or 64-bit.
#ifndef SIZE_MAX
# if SIZEOF_SIZE_T == 4
# define SIZE_MAX UINT32_MAX
# elif SIZEOF_SIZE_T == 8
# define SIZE_MAX UINT64_MAX
# else
# error size_t is not 32-bit or 64-bit
# endif
#endif
#if SIZE_MAX != UINT32_MAX && SIZE_MAX != UINT64_MAX
# error size_t is not 32-bit or 64-bit
#endif
#include <stdlib.h>
#include <assert.h>
// Pre-C99 systems lack stdbool.h. All the code in LZMA Utils must be written
// so that it works with fake bool type, for example:
//
// bool foo = (flags & 0x100) != 0;
// bool bar = !!(flags & 0x100);
//
// This works with the real C99 bool but breaks with fake bool:
//
// bool baz = (flags & 0x100);
//
#ifdef HAVE_STDBOOL_H
# include <stdbool.h>
#else
# if ! HAVE__BOOL
typedef unsigned char _Bool;
# endif
# define bool _Bool
# define false 0
# define true 1
# define __bool_true_false_are_defined 1
#endif
// string.h should be enough but let's include strings.h and memory.h too if
// they exists, since that shouldn't do any harm, but may improve portability.
#ifdef HAVE_STRING_H
# include <string.h>
#endif
#ifdef HAVE_STRINGS_H
# include <strings.h>
#endif
#ifdef HAVE_MEMORY_H
# include <memory.h>
#endif
// As of MSVC 2013, inline and restrict are supported with
// non-standard keywords.
#if defined(_WIN32) && defined(_MSC_VER)
# ifndef inline
# define inline __inline
# endif
# ifndef restrict
# define restrict __restrict
# endif
#elif __STDC_VERSION__ < 199901L
# define restrict // nothing
#endif
////////////
// Macros //
////////////
#undef memzero
#define memzero(s, n) memset(s, 0, n)
// NOTE: Avoid using MIN() and MAX(), because even conditionally defining
// those macros can cause some portability trouble, since on some systems
// the system headers insist defining their own versions.
#define my_min(x, y) ((x) < (y) ? (x) : (y))
#define my_max(x, y) ((x) > (y) ? (x) : (y))
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(array) (sizeof(array) / sizeof((array)[0]))
#endif
#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
# define lzma_attr_alloc_size(x) __attribute__((__alloc_size__(x)))
#else
# define lzma_attr_alloc_size(x)
#endif
#endif
@@ -0,0 +1,71 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_common.h
/// \brief Common definitions for tuklib modules
//
// Author: Lasse Collin
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_COMMON_H
#define TUKLIB_COMMON_H
// The config file may be replaced by a package-specific file.
// It should include at least stddef.h, inttypes.h, and limits.h.
#include "tuklib_config.h"
// TUKLIB_SYMBOL_PREFIX is prefixed to all symbols exported by
// the tuklib modules. If you use a tuklib module in a library,
// you should use TUKLIB_SYMBOL_PREFIX to make sure that there
// are no symbol conflicts in case someone links your library
// into application that also uses the same tuklib module.
#ifndef TUKLIB_SYMBOL_PREFIX
# define TUKLIB_SYMBOL_PREFIX
#endif
#define TUKLIB_CAT_X(a, b) a ## b
#define TUKLIB_CAT(a, b) TUKLIB_CAT_X(a, b)
#ifndef TUKLIB_SYMBOL
# define TUKLIB_SYMBOL(sym) TUKLIB_CAT(TUKLIB_SYMBOL_PREFIX, sym)
#endif
#ifndef TUKLIB_DECLS_BEGIN
# ifdef __cplusplus
# define TUKLIB_DECLS_BEGIN extern "C" {
# else
# define TUKLIB_DECLS_BEGIN
# endif
#endif
#ifndef TUKLIB_DECLS_END
# ifdef __cplusplus
# define TUKLIB_DECLS_END }
# else
# define TUKLIB_DECLS_END
# endif
#endif
#if defined(__GNUC__) && defined(__GNUC_MINOR__)
# define TUKLIB_GNUC_REQ(major, minor) \
((__GNUC__ == (major) && __GNUC_MINOR__ >= (minor)) \
|| __GNUC__ > (major))
#else
# define TUKLIB_GNUC_REQ(major, minor) 0
#endif
#if TUKLIB_GNUC_REQ(2, 5)
# define tuklib_attr_noreturn __attribute__((__noreturn__))
#else
# define tuklib_attr_noreturn
#endif
#if (defined(_WIN32) && !defined(__CYGWIN__)) \
|| defined(__OS2__) || defined(__MSDOS__)
# define TUKLIB_DOSLIKE 1
#endif
#endif
@@ -0,0 +1,7 @@
#ifdef HAVE_CONFIG_H
# include "sysdefs.h"
#else
# include <stddef.h>
# include <inttypes.h>
# include <limits.h>
#endif
@@ -0,0 +1,523 @@
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_integer.h
/// \brief Various integer and bit operations
///
/// This file provides macros or functions to do some basic integer and bit
/// operations.
///
/// Endianness related integer operations (XX = 16, 32, or 64; Y = b or l):
/// - Byte swapping: bswapXX(num)
/// - Byte order conversions to/from native: convXXYe(num)
/// - Aligned reads: readXXYe(ptr)
/// - Aligned writes: writeXXYe(ptr, num)
/// - Unaligned reads (16/32-bit only): unaligned_readXXYe(ptr)
/// - Unaligned writes (16/32-bit only): unaligned_writeXXYe(ptr, num)
///
/// Since they can macros, the arguments should have no side effects since
/// they may be evaluated more than once.
///
/// \todo PowerPC and possibly some other architectures support
/// byte swapping load and store instructions. This file
/// doesn't take advantage of those instructions.
///
/// Bit scan operations for non-zero 32-bit integers:
/// - Bit scan reverse (find highest non-zero bit): bsr32(num)
/// - Count leading zeros: clz32(num)
/// - Count trailing zeros: ctz32(num)
/// - Bit scan forward (simply an alias for ctz32()): bsf32(num)
///
/// The above bit scan operations return 0-31. If num is zero,
/// the result is undefined.
//
// Authors: Lasse Collin
// Joachim Henke
//
// This file has been put into the public domain.
// You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_INTEGER_H
#define TUKLIB_INTEGER_H
#include "tuklib_common.h"
////////////////////////////////////////
// Operating system specific features //
////////////////////////////////////////
#if defined(HAVE_BYTESWAP_H)
// glibc, uClibc, dietlibc
# include <byteswap.h>
# ifdef HAVE_BSWAP_16
# define bswap16(num) bswap_16(num)
# endif
# ifdef HAVE_BSWAP_32
# define bswap32(num) bswap_32(num)
# endif
# ifdef HAVE_BSWAP_64
# define bswap64(num) bswap_64(num)
# endif
#elif defined(HAVE_SYS_ENDIAN_H)
// *BSDs and Darwin
# include <sys/endian.h>
#elif defined(HAVE_SYS_BYTEORDER_H)
// Solaris
# include <sys/byteorder.h>
# ifdef BSWAP_16
# define bswap16(num) BSWAP_16(num)
# endif
# ifdef BSWAP_32
# define bswap32(num) BSWAP_32(num)
# endif
# ifdef BSWAP_64
# define bswap64(num) BSWAP_64(num)
# endif
# ifdef BE_16
# define conv16be(num) BE_16(num)
# endif
# ifdef BE_32
# define conv32be(num) BE_32(num)
# endif
# ifdef BE_64
# define conv64be(num) BE_64(num)
# endif
# ifdef LE_16
# define conv16le(num) LE_16(num)
# endif
# ifdef LE_32
# define conv32le(num) LE_32(num)
# endif
# ifdef LE_64
# define conv64le(num) LE_64(num)
# endif
#endif
///////////////////
// Byte swapping //
///////////////////
#ifndef bswap16
# define bswap16(num) \
(((uint16_t)(num) << 8) | ((uint16_t)(num) >> 8))
#endif
#ifndef bswap32
# define bswap32(num) \
( (((uint32_t)(num) << 24) ) \
| (((uint32_t)(num) << 8) & UINT32_C(0x00FF0000)) \
| (((uint32_t)(num) >> 8) & UINT32_C(0x0000FF00)) \
| (((uint32_t)(num) >> 24) ) )
#endif
#ifndef bswap64
# define bswap64(num) \
( (((uint64_t)(num) << 56) ) \
| (((uint64_t)(num) << 40) & UINT64_C(0x00FF000000000000)) \
| (((uint64_t)(num) << 24) & UINT64_C(0x0000FF0000000000)) \
| (((uint64_t)(num) << 8) & UINT64_C(0x000000FF00000000)) \
| (((uint64_t)(num) >> 8) & UINT64_C(0x00000000FF000000)) \
| (((uint64_t)(num) >> 24) & UINT64_C(0x0000000000FF0000)) \
| (((uint64_t)(num) >> 40) & UINT64_C(0x000000000000FF00)) \
| (((uint64_t)(num) >> 56) ) )
#endif
// Define conversion macros using the basic byte swapping macros.
#ifdef WORDS_BIGENDIAN
# ifndef conv16be
# define conv16be(num) ((uint16_t)(num))
# endif
# ifndef conv32be
# define conv32be(num) ((uint32_t)(num))
# endif
# ifndef conv64be
# define conv64be(num) ((uint64_t)(num))
# endif
# ifndef conv16le
# define conv16le(num) bswap16(num)
# endif
# ifndef conv32le
# define conv32le(num) bswap32(num)
# endif
# ifndef conv64le
# define conv64le(num) bswap64(num)
# endif
#else
# ifndef conv16be
# define conv16be(num) bswap16(num)
# endif
# ifndef conv32be
# define conv32be(num) bswap32(num)
# endif
# ifndef conv64be
# define conv64be(num) bswap64(num)
# endif
# ifndef conv16le
# define conv16le(num) ((uint16_t)(num))
# endif
# ifndef conv32le
# define conv32le(num) ((uint32_t)(num))
# endif
# ifndef conv64le
# define conv64le(num) ((uint64_t)(num))
# endif
#endif
//////////////////////////////
// Aligned reads and writes //
//////////////////////////////
static inline uint16_t
read16be(const uint8_t *buf)
{
uint16_t num = *(const uint16_t *)buf;
return conv16be(num);
}
static inline uint16_t
read16le(const uint8_t *buf)
{
uint16_t num = *(const uint16_t *)buf;
return conv16le(num);
}
static inline uint32_t
read32be(const uint8_t *buf)
{
uint32_t num = *(const uint32_t *)buf;
return conv32be(num);
}
static inline uint32_t
read32le(const uint8_t *buf)
{
uint32_t num = *(const uint32_t *)buf;
return conv32le(num);
}
static inline uint64_t
read64be(const uint8_t *buf)
{
uint64_t num = *(const uint64_t *)buf;
return conv64be(num);
}
static inline uint64_t
read64le(const uint8_t *buf)
{
uint64_t num = *(const uint64_t *)buf;
return conv64le(num);
}
// NOTE: Possible byte swapping must be done in a macro to allow GCC
// to optimize byte swapping of constants when using glibc's or *BSD's
// byte swapping macros. The actual write is done in an inline function
// to make type checking of the buf pointer possible similarly to readXXYe()
// functions.
#define write16be(buf, num) write16ne((buf), conv16be(num))
#define write16le(buf, num) write16ne((buf), conv16le(num))
#define write32be(buf, num) write32ne((buf), conv32be(num))
#define write32le(buf, num) write32ne((buf), conv32le(num))
#define write64be(buf, num) write64ne((buf), conv64be(num))
#define write64le(buf, num) write64ne((buf), conv64le(num))
static inline void
write16ne(uint8_t *buf, uint16_t num)
{
*(uint16_t *)buf = num;
return;
}
static inline void
write32ne(uint8_t *buf, uint32_t num)
{
*(uint32_t *)buf = num;
return;
}
static inline void
write64ne(uint8_t *buf, uint64_t num)
{
*(uint64_t *)buf = num;
return;
}
////////////////////////////////
// Unaligned reads and writes //
////////////////////////////////
// NOTE: TUKLIB_FAST_UNALIGNED_ACCESS indicates only support for 16-bit and
// 32-bit unaligned integer loads and stores. It's possible that 64-bit
// unaligned access doesn't work or is slower than byte-by-byte access.
// Since unaligned 64-bit is probably not needed as often as 16-bit or
// 32-bit, we simply don't support 64-bit unaligned access for now.
#ifdef TUKLIB_FAST_UNALIGNED_ACCESS
# define unaligned_read16be read16be
# define unaligned_read16le read16le
# define unaligned_read32be read32be
# define unaligned_read32le read32le
# define unaligned_write16be write16be
# define unaligned_write16le write16le
# define unaligned_write32be write32be
# define unaligned_write32le write32le
#else
static inline uint16_t
unaligned_read16be(const uint8_t *buf)
{
uint16_t num = ((uint16_t)buf[0] << 8) | (uint16_t)buf[1];
return num;
}
static inline uint16_t
unaligned_read16le(const uint8_t *buf)
{
uint16_t num = ((uint16_t)buf[0]) | ((uint16_t)buf[1] << 8);
return num;
}
static inline uint32_t
unaligned_read32be(const uint8_t *buf)
{
uint32_t num = (uint32_t)buf[0] << 24;
num |= (uint32_t)buf[1] << 16;
num |= (uint32_t)buf[2] << 8;
num |= (uint32_t)buf[3];
return num;
}
static inline uint32_t
unaligned_read32le(const uint8_t *buf)
{
uint32_t num = (uint32_t)buf[0];
num |= (uint32_t)buf[1] << 8;
num |= (uint32_t)buf[2] << 16;
num |= (uint32_t)buf[3] << 24;
return num;
}
static inline void
unaligned_write16be(uint8_t *buf, uint16_t num)
{
buf[0] = (uint8_t)(num >> 8);
buf[1] = (uint8_t)num;
return;
}
static inline void
unaligned_write16le(uint8_t *buf, uint16_t num)
{
buf[0] = (uint8_t)num;
buf[1] = (uint8_t)(num >> 8);
return;
}
static inline void
unaligned_write32be(uint8_t *buf, uint32_t num)
{
buf[0] = (uint8_t)(num >> 24);
buf[1] = (uint8_t)(num >> 16);
buf[2] = (uint8_t)(num >> 8);
buf[3] = (uint8_t)num;
return;
}
static inline void
unaligned_write32le(uint8_t *buf, uint32_t num)
{
buf[0] = (uint8_t)num;
buf[1] = (uint8_t)(num >> 8);
buf[2] = (uint8_t)(num >> 16);
buf[3] = (uint8_t)(num >> 24);
return;
}
#endif
static inline uint32_t
bsr32(uint32_t n)
{
// Check for ICC first, since it tends to define __GNUC__ too.
#if defined(__INTEL_COMPILER)
return _bit_scan_reverse(n);
#elif TUKLIB_GNUC_REQ(3, 4) && UINT_MAX == UINT32_MAX
// GCC >= 3.4 has __builtin_clz(), which gives good results on
// multiple architectures. On x86, __builtin_clz() ^ 31U becomes
// either plain BSR (so the XOR gets optimized away) or LZCNT and
// XOR (if -march indicates that SSE4a instructions are supported).
return __builtin_clz(n) ^ 31U;
#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
uint32_t i;
__asm__("bsrl %1, %0" : "=r" (i) : "rm" (n));
return i;
#elif defined(_MSC_VER) && _MSC_VER >= 1400
// MSVC isn't supported by tuklib, but since this code exists,
// it doesn't hurt to have it here anyway.
uint32_t i;
_BitScanReverse(&i, n);
return i;
#else
uint32_t i = 31;
if ((n & UINT32_C(0xFFFF0000)) == 0) {
n <<= 16;
i = 15;
}
if ((n & UINT32_C(0xFF000000)) == 0) {
n <<= 8;
i -= 8;
}
if ((n & UINT32_C(0xF0000000)) == 0) {
n <<= 4;
i -= 4;
}
if ((n & UINT32_C(0xC0000000)) == 0) {
n <<= 2;
i -= 2;
}
if ((n & UINT32_C(0x80000000)) == 0)
--i;
return i;
#endif
}
static inline uint32_t
clz32(uint32_t n)
{
#if defined(__INTEL_COMPILER)
return _bit_scan_reverse(n) ^ 31U;
#elif TUKLIB_GNUC_REQ(3, 4) && UINT_MAX == UINT32_MAX
return __builtin_clz(n);
#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
uint32_t i;
__asm__("bsrl %1, %0\n\t"
"xorl $31, %0"
: "=r" (i) : "rm" (n));
return i;
#elif defined(_MSC_VER) && _MSC_VER >= 1400
uint32_t i;
_BitScanReverse(&i, n);
return i ^ 31U;
#else
uint32_t i = 0;
if ((n & UINT32_C(0xFFFF0000)) == 0) {
n <<= 16;
i = 16;
}
if ((n & UINT32_C(0xFF000000)) == 0) {
n <<= 8;
i += 8;
}
if ((n & UINT32_C(0xF0000000)) == 0) {
n <<= 4;
i += 4;
}
if ((n & UINT32_C(0xC0000000)) == 0) {
n <<= 2;
i += 2;
}
if ((n & UINT32_C(0x80000000)) == 0)
++i;
return i;
#endif
}
static inline uint32_t
ctz32(uint32_t n)
{
#if defined(__INTEL_COMPILER)
return _bit_scan_forward(n);
#elif TUKLIB_GNUC_REQ(3, 4) && UINT_MAX >= UINT32_MAX
return __builtin_ctz(n);
#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
uint32_t i;
__asm__("bsfl %1, %0" : "=r" (i) : "rm" (n));
return i;
#elif defined(_MSC_VER) && _MSC_VER >= 1400
uint32_t i;
_BitScanForward(&i, n);
return i;
#else
uint32_t i = 0;
if ((n & UINT32_C(0x0000FFFF)) == 0) {
n >>= 16;
i = 16;
}
if ((n & UINT32_C(0x000000FF)) == 0) {
n >>= 8;
i += 8;
}
if ((n & UINT32_C(0x0000000F)) == 0) {
n >>= 4;
i += 4;
}
if ((n & UINT32_C(0x00000003)) == 0) {
n >>= 2;
i += 2;
}
if ((n & UINT32_C(0x00000001)) == 0)
++i;
return i;
#endif
}
#define bsf32 ctz32
#endif