laag-xz 5.2.4.0

data/vendor/git.tukaani.org/xz/src/liblzma/liblzma.pc.in

@@ -0,0 +1,19 @@
+#
+# Author: Lasse Collin
+#
+# This file has been put into the public domain.
+# You can do whatever you want with this file.
+#
+
+prefix=@prefix@
+exec_prefix=@exec_prefix@
+libdir=@libdir@
+includedir=@includedir@
+
+Name: liblzma
+Description: General purpose data compression library
+URL: @PACKAGE_URL@
+Version: @PACKAGE_VERSION@
+Cflags: -I${includedir}
+Libs: -L${libdir} -llzma
+Libs.private: @PTHREAD_CFLAGS@ @LIBS@

data/vendor/git.tukaani.org/xz/src/liblzma/liblzma_w32res.rc

@@ -0,0 +1,12 @@
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#define MY_TYPE VFT_DLL
+#define MY_NAME "liblzma"
+#define MY_SUFFIX ".dll"
+#define MY_DESC "liblzma data compression library"
+#include "common_w32res.rc"

data/vendor/git.tukaani.org/xz/src/liblzma/lz/Makefile.inc

@@ -0,0 +1,22 @@
+##
+## Author: Lasse Collin
+##
+## This file has been put into the public domain.
+## You can do whatever you want with this file.
+##
+
+if COND_ENCODER_LZ
+liblzma_la_SOURCES += \
+	lz/lz_encoder.c \
+	lz/lz_encoder.h \
+	lz/lz_encoder_hash.h \
+	lz/lz_encoder_hash_table.h \
+	lz/lz_encoder_mf.c
+endif
+
+
+if COND_DECODER_LZ
+liblzma_la_SOURCES += \
+	lz/lz_decoder.c \
+	lz/lz_decoder.h
+endif

data/vendor/git.tukaani.org/xz/src/liblzma/lz/lz_decoder.c

@@ -0,0 +1,306 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       lz_decoder.c
+/// \brief      LZ out window
+///
+//  Authors:    Igor Pavlov
+//              Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+// liblzma supports multiple LZ77-based filters. The LZ part is shared
+// between these filters. The LZ code takes care of dictionary handling
+// and passing the data between filters in the chain. The filter-specific
+// part decodes from the input buffer to the dictionary.
+
+
+#include "lz_decoder.h"
+
+
+typedef struct {
+	/// Dictionary (history buffer)
+	lzma_dict dict;
+
+	/// The actual LZ-based decoder e.g. LZMA
+	lzma_lz_decoder lz;
+
+	/// Next filter in the chain, if any. Note that LZMA and LZMA2 are
+	/// only allowed as the last filter, but the long-range filter in
+	/// future can be in the middle of the chain.
+	lzma_next_coder next;
+
+	/// True if the next filter in the chain has returned LZMA_STREAM_END.
+	bool next_finished;
+
+	/// True if the LZ decoder (e.g. LZMA) has detected end of payload
+	/// marker. This may become true before next_finished becomes true.
+	bool this_finished;
+
+	/// Temporary buffer needed when the LZ-based filter is not the last
+	/// filter in the chain. The output of the next filter is first
+	/// decoded into buffer[], which is then used as input for the actual
+	/// LZ-based decoder.
+	struct {
+		size_t pos;
+		size_t size;
+		uint8_t buffer[LZMA_BUFFER_SIZE];
+	} temp;
+} lzma_coder;
+
+
+static void
+lz_decoder_reset(lzma_coder *coder)
+{
+	coder->dict.pos = 0;
+	coder->dict.full = 0;
+	coder->dict.buf[coder->dict.size - 1] = '\0';
+	coder->dict.need_reset = false;
+	return;
+}
+
+
+static lzma_ret
+decode_buffer(lzma_coder *coder,
+		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)
+{
+	while (true) {
+		// Wrap the dictionary if needed.
+		if (coder->dict.pos == coder->dict.size)
+			coder->dict.pos = 0;
+
+		// Store the current dictionary position. It is needed to know
+		// where to start copying to the out[] buffer.
+		const size_t dict_start = coder->dict.pos;
+
+		// Calculate how much we allow coder->lz.code() to decode.
+		// It must not decode past the end of the dictionary
+		// buffer, and we don't want it to decode more than is
+		// actually needed to fill the out[] buffer.
+		coder->dict.limit = coder->dict.pos
+				+ my_min(out_size - *out_pos,
+					coder->dict.size - coder->dict.pos);
+
+		// Call the coder->lz.code() to do the actual decoding.
+		const lzma_ret ret = coder->lz.code(
+				coder->lz.coder, &coder->dict,
+				in, in_pos, in_size);
+
+		// Copy the decoded data from the dictionary to the out[]
+		// buffer.
+		const size_t copy_size = coder->dict.pos - dict_start;
+		assert(copy_size <= out_size - *out_pos);
+		memcpy(out + *out_pos, coder->dict.buf + dict_start,
+				copy_size);
+		*out_pos += copy_size;
+
+		// Reset the dictionary if so requested by coder->lz.code().
+		if (coder->dict.need_reset) {
+			lz_decoder_reset(coder);
+
+			// Since we reset dictionary, we don't check if
+			// dictionary became full.
+			if (ret != LZMA_OK || *out_pos == out_size)
+				return ret;
+		} else {
+			// Return if everything got decoded or an error
+			// occurred, or if there's no more data to decode.
+			//
+			// Note that detecting if there's something to decode
+			// is done by looking if dictionary become full
+			// instead of looking if *in_pos == in_size. This
+			// is because it is possible that all the input was
+			// consumed already but some data is pending to be
+			// written to the dictionary.
+			if (ret != LZMA_OK || *out_pos == out_size
+					|| coder->dict.pos < coder->dict.size)
+				return ret;
+		}
+	}
+}
+
+
+static lzma_ret
+lz_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_coder *coder = coder_ptr;
+
+	if (coder->next.code == NULL)
+		return decode_buffer(coder, in, in_pos, in_size,
+				out, out_pos, out_size);
+
+	// We aren't the last coder in the chain, we need to decode
+	// our input to a temporary buffer.
+	while (*out_pos < out_size) {
+		// Fill the temporary buffer if it is empty.
+		if (!coder->next_finished
+				&& coder->temp.pos == coder->temp.size) {
+			coder->temp.pos = 0;
+			coder->temp.size = 0;
+
+			const lzma_ret ret = coder->next.code(
+					coder->next.coder,
+					allocator, in, in_pos, in_size,
+					coder->temp.buffer, &coder->temp.size,
+					LZMA_BUFFER_SIZE, action);
+
+			if (ret == LZMA_STREAM_END)
+				coder->next_finished = true;
+			else if (ret != LZMA_OK || coder->temp.size == 0)
+				return ret;
+		}
+
+		if (coder->this_finished) {
+			if (coder->temp.size != 0)
+				return LZMA_DATA_ERROR;
+
+			if (coder->next_finished)
+				return LZMA_STREAM_END;
+
+			return LZMA_OK;
+		}
+
+		const lzma_ret ret = decode_buffer(coder, coder->temp.buffer,
+				&coder->temp.pos, coder->temp.size,
+				out, out_pos, out_size);
+
+		if (ret == LZMA_STREAM_END)
+			coder->this_finished = true;
+		else if (ret != LZMA_OK)
+			return ret;
+		else if (coder->next_finished && *out_pos < out_size)
+			return LZMA_DATA_ERROR;
+	}
+
+	return LZMA_OK;
+}
+
+
+static void
+lz_decoder_end(void *coder_ptr, const lzma_allocator *allocator)
+{
+	lzma_coder *coder = coder_ptr;
+
+	lzma_next_end(&coder->next, allocator);
+	lzma_free(coder->dict.buf, allocator);
+
+	if (coder->lz.end != NULL)
+		coder->lz.end(coder->lz.coder, allocator);
+	else
+		lzma_free(coder->lz.coder, allocator);
+
+	lzma_free(coder, allocator);
+	return;
+}
+
+
+extern lzma_ret
+lzma_lz_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
+		const lzma_filter_info *filters,
+		lzma_ret (*lz_init)(lzma_lz_decoder *lz,
+			const lzma_allocator *allocator, const void *options,
+			lzma_lz_options *lz_options))
+{
+	// Allocate the base structure if it isn't already allocated.
+	lzma_coder *coder = next->coder;
+	if (coder == NULL) {
+		coder = lzma_alloc(sizeof(lzma_coder), allocator);
+		if (coder == NULL)
+			return LZMA_MEM_ERROR;
+
+		next->coder = coder;
+		next->code = &lz_decode;
+		next->end = &lz_decoder_end;
+
+		coder->dict.buf = NULL;
+		coder->dict.size = 0;
+		coder->lz = LZMA_LZ_DECODER_INIT;
+		coder->next = LZMA_NEXT_CODER_INIT;
+	}
+
+	// Allocate and initialize the LZ-based decoder. It will also give
+	// us the dictionary size.
+	lzma_lz_options lz_options;
+	return_if_error(lz_init(&coder->lz, allocator,
+			filters[0].options, &lz_options));
+
+	// If the dictionary size is very small, increase it to 4096 bytes.
+	// This is to prevent constant wrapping of the dictionary, which
+	// would slow things down. The downside is that since we don't check
+	// separately for the real dictionary size, we may happily accept
+	// corrupt files.
+	if (lz_options.dict_size < 4096)
+		lz_options.dict_size = 4096;
+
+	// Make dictionary size a multipe of 16. Some LZ-based decoders like
+	// LZMA use the lowest bits lzma_dict.pos to know the alignment of the
+	// data. Aligned buffer is also good when memcpying from the
+	// dictionary to the output buffer, since applications are
+	// recommended to give aligned buffers to liblzma.
+	//
+	// Avoid integer overflow.
+	if (lz_options.dict_size > SIZE_MAX - 15)
+		return LZMA_MEM_ERROR;
+
+	lz_options.dict_size = (lz_options.dict_size + 15) & ~((size_t)(15));
+
+	// Allocate and initialize the dictionary.
+	if (coder->dict.size != lz_options.dict_size) {
+		lzma_free(coder->dict.buf, allocator);
+		coder->dict.buf
+				= lzma_alloc(lz_options.dict_size, allocator);
+		if (coder->dict.buf == NULL)
+			return LZMA_MEM_ERROR;
+
+		coder->dict.size = lz_options.dict_size;
+	}
+
+	lz_decoder_reset(next->coder);
+
+	// Use the preset dictionary if it was given to us.
+	if (lz_options.preset_dict != NULL
+			&& lz_options.preset_dict_size > 0) {
+		// If the preset dictionary is bigger than the actual
+		// dictionary, copy only the tail.
+		const size_t copy_size = my_min(lz_options.preset_dict_size,
+				lz_options.dict_size);
+		const size_t offset = lz_options.preset_dict_size - copy_size;
+		memcpy(coder->dict.buf, lz_options.preset_dict + offset,
+				copy_size);
+		coder->dict.pos = copy_size;
+		coder->dict.full = copy_size;
+	}
+
+	// Miscellaneous initializations
+	coder->next_finished = false;
+	coder->this_finished = false;
+	coder->temp.pos = 0;
+	coder->temp.size = 0;
+
+	// Initialize the next filter in the chain, if any.
+	return lzma_next_filter_init(&coder->next, allocator, filters + 1);
+}
+
+
+extern uint64_t
+lzma_lz_decoder_memusage(size_t dictionary_size)
+{
+	return sizeof(lzma_coder) + (uint64_t)(dictionary_size);
+}
+
+
+extern void
+lzma_lz_decoder_uncompressed(void *coder_ptr, lzma_vli uncompressed_size)
+{
+	lzma_coder *coder = coder_ptr;
+	coder->lz.set_uncompressed(coder->lz.coder, uncompressed_size);
+}

data/vendor/git.tukaani.org/xz/src/liblzma/lz/lz_decoder.h

@@ -0,0 +1,234 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       lz_decoder.h
+/// \brief      LZ out window
+///
+//  Authors:    Igor Pavlov
+//              Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef LZMA_LZ_DECODER_H
+#define LZMA_LZ_DECODER_H
+
+#include "common.h"
+
+
+typedef struct {
+	/// Pointer to the dictionary buffer. It can be an allocated buffer
+	/// internal to liblzma, or it can a be a buffer given by the
+	/// application when in single-call mode (not implemented yet).
+	uint8_t *buf;
+
+	/// Write position in dictionary. The next byte will be written to
+	/// buf[pos].
+	size_t pos;
+
+	/// Indicates how full the dictionary is. This is used by
+	/// dict_is_distance_valid() to detect corrupt files that would
+	/// read beyond the beginning of the dictionary.
+	size_t full;
+
+	/// Write limit
+	size_t limit;
+
+	/// Size of the dictionary
+	size_t size;
+
+	/// True when dictionary should be reset before decoding more data.
+	bool need_reset;
+
+} lzma_dict;
+
+
+typedef struct {
+	size_t dict_size;
+	const uint8_t *preset_dict;
+	size_t preset_dict_size;
+} lzma_lz_options;
+
+
+typedef struct {
+	/// Data specific to the LZ-based decoder
+	void *coder;
+
+	/// Function to decode from in[] to *dict
+	lzma_ret (*code)(void *coder,
+			lzma_dict *restrict dict, const uint8_t *restrict in,
+			size_t *restrict in_pos, size_t in_size);
+
+	void (*reset)(void *coder, const void *options);
+
+	/// Set the uncompressed size
+	void (*set_uncompressed)(void *coder, lzma_vli uncompressed_size);
+
+	/// Free allocated resources
+	void (*end)(void *coder, const lzma_allocator *allocator);
+
+} lzma_lz_decoder;
+
+
+#define LZMA_LZ_DECODER_INIT \
+	(lzma_lz_decoder){ \
+		.coder = NULL, \
+		.code = NULL, \
+		.reset = NULL, \
+		.set_uncompressed = NULL, \
+		.end = NULL, \
+	}
+
+
+extern lzma_ret lzma_lz_decoder_init(lzma_next_coder *next,
+		const lzma_allocator *allocator,
+		const lzma_filter_info *filters,
+		lzma_ret (*lz_init)(lzma_lz_decoder *lz,
+			const lzma_allocator *allocator, const void *options,
+			lzma_lz_options *lz_options));
+
+extern uint64_t lzma_lz_decoder_memusage(size_t dictionary_size);
+
+extern void lzma_lz_decoder_uncompressed(
+		void *coder, lzma_vli uncompressed_size);
+
+
+//////////////////////
+// Inline functions //
+//////////////////////
+
+/// Get a byte from the history buffer.
+static inline uint8_t
+dict_get(const lzma_dict *const dict, const uint32_t distance)
+{
+	return dict->buf[dict->pos - distance - 1
+			+ (distance < dict->pos ? 0 : dict->size)];
+}
+
+
+/// Test if dictionary is empty.
+static inline bool
+dict_is_empty(const lzma_dict *const dict)
+{
+	return dict->full == 0;
+}
+
+
+/// Validate the match distance
+static inline bool
+dict_is_distance_valid(const lzma_dict *const dict, const size_t distance)
+{
+	return dict->full > distance;
+}
+
+
+/// Repeat *len bytes at distance.
+static inline bool
+dict_repeat(lzma_dict *dict, uint32_t distance, uint32_t *len)
+{
+	// Don't write past the end of the dictionary.
+	const size_t dict_avail = dict->limit - dict->pos;
+	uint32_t left = my_min(dict_avail, *len);
+	*len -= left;
+
+	// Repeat a block of data from the history. Because memcpy() is faster
+	// than copying byte by byte in a loop, the copying process gets split
+	// into three cases.
+	if (distance < left) {
+		// Source and target areas overlap, thus we can't use
+		// memcpy() nor even memmove() safely.
+		do {
+			dict->buf[dict->pos] = dict_get(dict, distance);
+			++dict->pos;
+		} while (--left > 0);
+
+	} else if (distance < dict->pos) {
+		// The easiest and fastest case
+		memcpy(dict->buf + dict->pos,
+				dict->buf + dict->pos - distance - 1,
+				left);
+		dict->pos += left;
+
+	} else {
+		// The bigger the dictionary, the more rare this
+		// case occurs. We need to "wrap" the dict, thus
+		// we might need two memcpy() to copy all the data.
+		assert(dict->full == dict->size);
+		const uint32_t copy_pos
+				= dict->pos - distance - 1 + dict->size;
+		uint32_t copy_size = dict->size - copy_pos;
+
+		if (copy_size < left) {
+			memmove(dict->buf + dict->pos, dict->buf + copy_pos,
+					copy_size);
+			dict->pos += copy_size;
+			copy_size = left - copy_size;
+			memcpy(dict->buf + dict->pos, dict->buf, copy_size);
+			dict->pos += copy_size;
+		} else {
+			memmove(dict->buf + dict->pos, dict->buf + copy_pos,
+					left);
+			dict->pos += left;
+		}
+	}
+
+	// Update how full the dictionary is.
+	if (dict->full < dict->pos)
+		dict->full = dict->pos;
+
+	return unlikely(*len != 0);
+}
+
+
+/// Puts one byte into the dictionary. Returns true if the dictionary was
+/// already full and the byte couldn't be added.
+static inline bool
+dict_put(lzma_dict *dict, uint8_t byte)
+{
+	if (unlikely(dict->pos == dict->limit))
+		return true;
+
+	dict->buf[dict->pos++] = byte;
+
+	if (dict->pos > dict->full)
+		dict->full = dict->pos;
+
+	return false;
+}
+
+
+/// Copies arbitrary amount of data into the dictionary.
+static inline void
+dict_write(lzma_dict *restrict dict, const uint8_t *restrict in,
+		size_t *restrict in_pos, size_t in_size,
+		size_t *restrict left)
+{
+	// NOTE: If we are being given more data than the size of the
+	// dictionary, it could be possible to optimize the LZ decoder
+	// so that not everything needs to go through the dictionary.
+	// This shouldn't be very common thing in practice though, and
+	// the slowdown of one extra memcpy() isn't bad compared to how
+	// much time it would have taken if the data were compressed.
+
+	if (in_size - *in_pos > *left)
+		in_size = *in_pos + *left;
+
+	*left -= lzma_bufcpy(in, in_pos, in_size,
+			dict->buf, &dict->pos, dict->limit);
+
+	if (dict->pos > dict->full)
+		dict->full = dict->pos;
+
+	return;
+}
+
+
+static inline void
+dict_reset(lzma_dict *dict)
+{
+	dict->need_reset = true;
+	return;
+}
+
+#endif