--- /dev/null
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <https://unlicense.org>
--- /dev/null
+#******************************************************************************
+# @file Makefile.unix
+#******************************************************************************
+SRCDIR ?= $(CURDIR)
+VPATH := $(SRCDIR)
+
+CC := gcc
+CFLAGS := -D_FILE_OFFSET_BITS=64 -I$(SRCDIR)/include -O2 -Wall -Werror -Wextra -std=c90
+
+CSRC := libxz/xz_crc32.c libxz/xz_crc64.c libxz/xz_dec_lzma2.c libxz/xz_dec_stream.c lib.c report.c unxz.c
+
+ifeq ($(OS), Windows_NT)
+all: unxz.exe
+
+unxz.exe: $(CSRC)
+ $(CC) $(CFLAGS) -o $@ $^
+else
+all: unxz
+
+unxz: $(CSRC)
+ $(CC) $(CFLAGS) -o $@ $^
+endif
+
+clean:
+
+ if [ -f unxz ]; then rm -rf unxz; fi
+ if [ -f unxz.exe ]; then rm -rf unxz.exe; fi
--- /dev/null
+#******************************************************************************
+# @file Makefile.w32
+#******************************************************************************
+SRCDIR ?= $(CURDIR)
+VPATH := $(SRCDIR)
+
+CC := gcc
+CFLAGS := -D_FILE_OFFSET_BITS=64 -I$(SRCDIR)/include -O2 -Wall -Werror -Wextra
+
+CSRC := libxz/xz_crc32.c libxz/xz_crc64.c libxz/xz_dec_lzma2.c libxz/xz_dec_stream.c lib.c report.c unxz.c
+
+all: unxz.exe
+
+clean:
+
+ if exist unxz ( del /q unxz )
+ if exist unxz.exe ( del /q unxz.exe )
+
+unxz.exe: $(CSRC)
+
+ $(CC) $(CFLAGS) -o $@ $^
--- /dev/null
+## License
+
+ All source code is Public Domain.
+
+## Obtain the source code
+
+ git clone https://git.candlhat.org/unxz.git
+
+## Building
+
+ BSD:
+
+ Make sure you have gcc and gmake installed then run gmake -f Makefile.unix.
+
+ Linux:
+
+ Make sure you have gcc and make installed then run make -f Makefile.unix.
+
+ macOS:
+
+ Make sure you have xcode command line tools installed then run
+ make -f Makefile.unix.
+
+ Windows:
+
+ Make sure you have mingw installed and the location within your PATH variable
+ then run mingw32-make.exe -f Makefile.w32.
--- /dev/null
+/******************************************************************************
+ * @file stdint.h
+ *****************************************************************************/
+#ifndef _STDINT_H_INCLUDED
+#ifndef _STDINT_H
+#ifndef _STDINT_H_
+
+#define _STDINT_H_INCLUDED
+#define _STDINT_H
+#define _STDINT_H_
+
+#include <limits.h>
+
+/* Add all data types (even though we don't use them) as the project seems to fail to build on some systems. */
+typedef signed char int8_t;
+typedef unsigned char uint8_t;
+
+typedef signed short int16_t;
+typedef unsigned short uint16_t;
+
+#if INT_MAX > 32767
+typedef signed int int32_t;
+typedef unsigned int uint32_t;
+#else
+typedef signed long int32_t;
+typedef unsigned long uint32_t;
+#endif
+
+#ifndef _INT64_T
+#define _INT64_T
+#if defined (NO_LONG_LONG) || ((ULONG_MAX >> 16) >> 16) == 0xffffffff
+typedef signed long int64_t;
+#else
+typedef signed long long int64_t;
+#endif
+#endif /* _INT64_T */
+
+#ifndef _UINT64_T
+#define _UINT64_T
+#if defined (NO_LONG_LONG) || ((ULONG_MAX >> 16) >> 16) == 0xffffffff
+typedef unsigned long uint64_t;
+#else
+typedef unsigned long long uint64_t;
+#endif
+#endif /* _UINT64_T */
+
+#endif /* _STDINT_H_ */
+#endif /* _STDINT_H */
+#endif /* _STDINT_H_INCLUDED */
--- /dev/null
+#ifndef _XZ_H
+#define _XZ_H
+
+/**
+ * enum xz_mode - Operation mode
+ *
+ * @XZ_SINGLE: Single-call mode. This uses less RAM than
+ * than multi-call modes, because the LZMA2
+ * dictionary doesn't need to be allocated as
+ * part of the decoder state. All required data
+ * structures are allocated at initialization,
+ * so xz_dec_run() cannot return XZ_MEM_ERROR.
+ * @XZ_PREALLOC: Multi-call mode with preallocated LZMA2
+ * dictionary buffer. All data structures are
+ * allocated at initialization, so xz_dec_run()
+ * cannot return XZ_MEM_ERROR.
+ * @XZ_DYNALLOC: Multi-call mode. The LZMA2 dictionary is
+ * allocated once the required size has been
+ * parsed from the stream headers. If the
+ * allocation fails, xz_dec_run() will return
+ * XZ_MEM_ERROR.
+ *
+ * It is possible to enable support only for a subset of the above
+ * modes at compile time by defining XZ_DEC_SINGLE, XZ_DEC_PREALLOC,
+ * or XZ_DEC_DYNALLOC. The xz_dec kernel module is always compiled
+ * with support for all operation modes, but the preboot code may
+ * be built with fewer features to minimize code size.
+ */
+enum xz_mode { XZ_SINGLE, XZ_PREALLOC, XZ_DYNALLOC };
+
+/**
+ * enum xz_ret - Return codes
+ * @XZ_OK: Everything is OK so far. More input or more
+ * output space is required to continue. This
+ * return code is possible only in multi-call mode
+ * (XZ_PREALLOC or XZ_DYNALLOC).
+ * @XZ_STREAM_END: Operation finished successfully.
+ * @XZ_UNSUPPORTED_CHECK: Integrity check type is not supported. Decoding
+ * is still possible in multi-call mode by simply
+ * calling xz_dec_run() again.
+ * Note that this return value is used only if
+ * XZ_DEC_ANY_CHECK was defined at build time,
+ * which is not used in the kernel. Unsupported
+ * check types return XZ_OPTIONS_ERROR if
+ * XZ_DEC_ANY_CHECK was not defined at build time.
+ * @XZ_MEM_ERROR: Allocating memory failed. This return code is
+ * possible only if the decoder was initialized
+ * with XZ_DYNALLOC. The amount of memory that was
+ * tried to be allocated was no more than the
+ * dict_max argument given to xz_dec_init().
+ * @XZ_MEMLIMIT_ERROR: A bigger LZMA2 dictionary would be needed than
+ * allowed by the dict_max argument given to
+ * xz_dec_init(). This return value is possible
+ * only in multi-call mode (XZ_PREALLOC or
+ * XZ_DYNALLOC); the single-call mode (XZ_SINGLE)
+ * ignores the dict_max argument.
+ * @XZ_FORMAT_ERROR: File format was not recognized (wrong magic
+ * bytes).
+ * @XZ_OPTIONS_ERROR: This implementation doesn't support the requested
+ * compression options. In the decoder this means
+ * that the header CRC32 matches, but the header
+ * itself specifies something that we don't support.
+ * @XZ_DATA_ERROR: Compressed data is corrupt.
+ * @XZ_BUF_ERROR: Cannot make any progress. Details are slightly
+ * different between multi-call and single-call
+ * mode; more information below.
+ *
+ * In multi-call mode, XZ_BUF_ERROR is returned when two consecutive calls
+ * to XZ code cannot consume any input and cannot produce any new output.
+ * This happens when there is no new input available, or the output buffer
+ * is full while at least one output byte is still pending. Assuming your
+ * code is not buggy, you can get this error only when decoding a compressed
+ * stream that is truncated or otherwise corrupt.
+ *
+ * In single-call mode, XZ_BUF_ERROR is returned only when the output buffer
+ * is too small or the compressed input is corrupt in a way that makes the
+ * decoder produce more output than the caller expected. When it is
+ * (relatively) clear that the compressed input is truncated, XZ_DATA_ERROR
+ * is used instead of XZ_BUF_ERROR.
+ */
+enum xz_ret {
+
+ XZ_OK,
+ XZ_STREAM_END,
+ XZ_UNSUPPORTED_CHECK,
+ XZ_MEM_ERROR,
+ XZ_MEMLIMIT_ERROR,
+ XZ_FORMAT_ERROR,
+ XZ_OPTIONS_ERROR,
+ XZ_DATA_ERROR,
+ XZ_BUF_ERROR
+
+};
+
+#include <stdint.h>
+
+/**
+ * struct xz_buf - Passing input and output buffers to XZ code
+ * @in: Beginning of the input buffer. This may be NULL if and only
+ * if in_pos is equal to in_size.
+ * @in_pos: Current position in the input buffer. This must not exceed
+ * in_size.
+ * @in_size: Size of the input buffer
+ * @out: Beginning of the output buffer. This may be NULL if and only
+ * if out_pos is equal to out_size.
+ * @out_pos: Current position in the output buffer. This must not exceed
+ * out_size.
+ * @out_size: Size of the output buffer
+ *
+ * Only the contents of the output buffer from out[out_pos] onward, and
+ * the variables in_pos and out_pos are modified by the XZ code.
+ */
+struct xz_buf {
+
+ uint8_t *in;
+ uint64_t in_pos;
+ uint64_t in_size;
+
+ uint8_t *out;
+ uint64_t out_pos;
+ uint64_t out_size;
+
+};
+
+
+/**
+ * struct xz_dec - Opaque type to hold the XZ decoder state
+ */
+struct xz_dec;
+
+/**
+ * xz_dec_init() - Allocate and initialize a XZ decoder state
+ * @mode: Operation mode
+ * @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for
+ * multi-call decoding. This is ignored in single-call mode
+ * (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes
+ * or 2^n + 2^(n-1) bytes (the latter sizes are less common
+ * in practice), so other values for dict_max don't make sense.
+ * In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB,
+ * 512 KiB, and 1 MiB are probably the only reasonable values,
+ * except for kernel and initramfs images where a bigger
+ * dictionary can be fine and useful.
+ *
+ * Single-call mode (XZ_SINGLE): xz_dec_run() decodes the whole stream at
+ * once. The caller must provide enough output space or the decoding will
+ * fail. The output space is used as the dictionary buffer, which is why
+ * there is no need to allocate the dictionary as part of the decoder's
+ * internal state.
+ *
+ * Because the output buffer is used as the workspace, streams encoded using
+ * a big dictionary are not a problem in single-call mode. It is enough that
+ * the output buffer is big enough to hold the actual uncompressed data; it
+ * can be smaller than the dictionary size stored in the stream headers.
+ *
+ * Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max bytes
+ * of memory is preallocated for the LZMA2 dictionary. This way there is no
+ * risk that xz_dec_run() could run out of memory, since xz_dec_run() will
+ * never allocate any memory. Instead, if the preallocated dictionary is too
+ * small for decoding the given input stream, xz_dec_run() will return
+ * XZ_MEMLIMIT_ERROR. Thus, it is important to know what kind of data will be
+ * decoded to avoid allocating excessive amount of memory for the dictionary.
+ *
+ * Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC):
+ * dict_max specifies the maximum allowed dictionary size that xz_dec_run()
+ * may allocate once it has parsed the dictionary size from the stream
+ * headers. This way excessive allocations can be avoided while still
+ * limiting the maximum memory usage to a sane value to prevent running the
+ * system out of memory when decompressing streams from untrusted sources.
+ *
+ * On success, xz_dec_init() returns a pointer to struct xz_dec, which is
+ * ready to be used with xz_dec_run(). If memory allocation fails,
+ * xz_dec_init() returns NULL.
+ */
+extern struct xz_dec *xz_dec_init (enum xz_mode mode, uint32_t dict_max);
+
+/**
+ * xz_dec_run() - Run the XZ decoder
+ * @s: Decoder state allocated using xz_dec_init()
+ * @b: Input and output buffers
+ *
+ * The possible return values depend on build options and operation mode.
+ * See enum xz_ret for details.
+ *
+ * Note that if an error occurs in single-call mode (return value is not
+ * XZ_STREAM_END), b->in_pos and b->out_pos are not modified and the
+ * contents of the output buffer from b->out[b->out_pos] onward are
+ * undefined. This is true even after XZ_BUF_ERROR, because with some filter
+ * chains, there may be a second pass over the output buffer, and this pass
+ * cannot be properly done if the output buffer is truncated. Thus, you
+ * cannot give the single-call decoder a too small buffer and then expect to
+ * get that amount valid data from the beginning of the stream. You must use
+ * the multi-call decoder if you don't want to uncompress the whole stream.
+ */
+extern enum xz_ret xz_dec_run (struct xz_dec *s, struct xz_buf *b);
+
+/**
+ * xz_dec_reset() - Reset an already allocated decoder state
+ * @s: Decoder state allocated using xz_dec_init()
+ *
+ * This function can be used to reset the multi-call decoder state without
+ * freeing and reallocating memory with xz_dec_end() and xz_dec_init().
+ *
+ * In single-call mode, xz_dec_reset() is always called in the beginning of
+ * xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in
+ * multi-call mode.
+ */
+extern void xz_dec_reset (struct xz_dec *s);
+
+/**
+ * xz_dec_end() - Free the memory allocated for the decoder state
+ * @s: Decoder state allocated using xz_dec_init(). If s is NULL,
+ * this function does nothing.
+ */
+extern void xz_dec_end (struct xz_dec *s);
+
+
+/**
+ * This must be called before any other xz_* function to initialize
+ * the CRC32 lookup table.
+ */
+extern void xz_crc32_init (void);
+
+/**
+ * Update CRC32 value using the polynomial from IEEE-802.3. To start a new
+ * calculation, the third argument must be zero. To continue the calculation,
+ * the previously returned value is passed as the third argument.
+ */
+extern uint32_t xz_crc32 (const uint8_t *buf, uint64_t size, uint32_t crc);
+
+
+/*
+ * This must be called before any other xz_* function (except xz_crc32_init())
+ * to initialize the CRC64 lookup table.
+ */
+extern void xz_crc64_init (void);
+
+/*
+ * Update CRC64 value using the polynomial from ECMA-182. To start a new
+ * calculation, the third argument must be zero. To continue the calculation,
+ * the previously returned value is passed as the third argument.
+ */
+extern uint64_t xz_crc64 (const uint8_t *buf, uint64_t size, uint64_t crc);
+
+#endif /* _XZ_H */
\ No newline at end of file
--- /dev/null
+#ifndef _XZ_LZMA2_H
+#define _XZ_LZMA2_H
+
+#include <stdint.h>
+
+/* Range coder constants */
+#define RC_TOP_BITS 24
+#define RC_BIT_MODEL_TOTAL_BITS 11
+
+#define RC_SHIFT_BITS 8
+#define RC_MOVE_BITS 5
+
+#define RC_TOP_VALUE (1 << RC_TOP_BITS)
+#define RC_BIT_MODEL_TOTAL (1 << RC_BIT_MODEL_TOTAL_BITS)
+
+/*
+ * Maximum number of position states. A position state is the lowest pb
+ * number of bits of the current uncompressed offset. In some places there
+ * are different sets of probabilities for different position states.
+ */
+#define POS_STATES_MAX (1 << 4)
+
+/*
+ * This enum is used to track which LZMA symbols have occurred most recently
+ * and in which order. This information is used to predict the next symbol.
+ *
+ * Symbols:
+ * - Literal: One 8-bit byte
+ * - Match: Repeat a chunk of data at some distance
+ * - Long repeat: Multi-byte match at a recently seen distance
+ * - Short repeat: One-byte repeat at a recently seen distance
+ *
+ * The symbol names are in from STATE_oldest_older_previous. REP means
+ * either short or long repeated match, and NONLIT means any non-literal.
+ */
+enum lzma_state {
+
+ STATE_LIT_LIT,
+ STATE_MATCH_LIT_LIT,
+ STATE_REP_LIT_LIT,
+ STATE_SHORTREP_LIT_LIT,
+ STATE_MATCH_LIT,
+ STATE_REP_LIT,
+ STATE_SHORTREP_LIT,
+ STATE_LIT_MATCH,
+ STATE_LIT_LONGREP,
+ STATE_LIT_SHORTREP,
+ STATE_NONLIT_MATCH,
+ STATE_NONLIT_REP
+
+};
+
+/* Total number of states */
+#define STATES 12
+
+/* The lowest 7 states indicate that the previous state was a literal. */
+#define LIT_STATES 7
+
+/* Indicate that the latest symbol was a literal. */
+/*static inline void lzma_state_literal (int *state) {
+
+ if (*state <= STATE_SHORTREP_LIT_LIT) {
+ *state = STATE_LIT_LIT;
+ } else if (*state <= STATE_LIT_SHORTREP) {
+ *state -= 3;
+ } else {
+ *state -= 6;
+ }
+
+}*/
+
+/* Indicate that the latest symbol was a match. */
+/*static inline void lzma_state_match (enum lzma_state *state) {
+ *state = *state < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH;
+}*/
+
+/* Indicate that the latest state was a long repeated match. */
+/*static inline void lzma_state_long_rep (enum lzma_state *state) {
+ *state = *state < LIT_STATES ? STATE_LIT_LONGREP : STATE_NONLIT_REP;
+}*/
+
+/* Indicate that the latest symbol was a short match. */
+/*static inline void lzma_state_short_rep (enum lzma_state *state) {
+ *state = *state < LIT_STATES ? STATE_LIT_SHORTREP : STATE_NONLIT_REP;
+}*/
+
+/* Test if the previous symbol was a literal. */
+/*static inline bool lzma_state_is_literal (enum lzma_state state) {
+ return state < LIT_STATES;
+}*/
+
+/**
+ * Each literal coder is divided in three sections:
+ * - 0x001-0x0FF: Without match byte
+ * - 0x101-0x1FF: With match byte; match bit is 0
+ * - 0x201-0x2FF: With match byte; match bit is 1
+ *
+ * Match byte is used when the previous LZMA symbol was something else than
+ * a literal (that is, it was some kind of match).
+ */
+#define LITERAL_CODER_SIZE 0x300
+
+/* Maximum number of literal coders */
+#define LITERAL_CODERS_MAX (1 << 4)
+
+/* Minimum length of a match is two bytes. */
+#define MATCH_LEN_MIN 2
+
+/**
+ * Match length is encoded with 4, 5, or 10 bits.
+ *
+ * Length Bits
+ * 2-9 4 = Choice=0 + 3 bits
+ * 10-17 5 = Choice=1 + Choice2=0 + 3 bits
+ * 18-273 10 = Choice=1 + Choice2=1 + 8 bits
+ */
+#define LEN_LOW_BITS 3
+#define LEN_MID_BITS 3
+#define LEN_HIGH_BITS 8
+
+#define LEN_LOW_SYMBOLS (1 << LEN_LOW_BITS)
+#define LEN_MID_SYMBOLS (1 << LEN_MID_BITS)
+#define LEN_HIGH_SYMBOLS (1 << LEN_HIGH_BITS)
+
+#define LEN_SYMBOLS (LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS + LEN_HIGH_SYMBOLS)
+
+/*
+ * Maximum length of a match is 273 which is a result of the encoding
+ * described above.
+ */
+#define MATCH_LEN_MAX (MATCH_LEN_MIN + LEN_SYMBOLS - 1)
+
+/*
+ * Different sets of probabilities are used for match distances that have
+ * very short match length: Lengths of 2, 3, and 4 bytes have a separate
+ * set of probabilities for each length. The matches with longer length
+ * use a shared set of probabilities.
+ */
+#define DIST_STATES 4
+
+/*
+ * Get the index of the appropriate probability array for decoding
+ * the distance slot.
+ */
+/*static inline uint32_t lzma_get_dist_state (uint32_t len) {
+ return len < DIST_STATES + MATCH_LEN_MIN ? len - MATCH_LEN_MIN : DIST_STATES - 1;
+}*/
+
+/**
+ * The highest two bits of a 32-bit match distance are encoded using six bits.
+ * This six-bit value is called a distance slot. This way encoding a 32-bit
+ * value takes 6-36 bits, larger values taking more bits.
+ */
+#define DIST_SLOT_BITS 6
+#define DIST_SLOTS (1 << DIST_SLOT_BITS)
+
+/**
+ * Match distances up to 127 are fully encoded using probabilities. Since
+ * the highest two bits (distance slot) are always encoded using six bits,
+ * the distances 0-3 don't need any additional bits to encode, since the
+ * distance slot itself is the same as the actual distance. DIST_MODEL_START
+ * indicates the first distance slot where at least one additional bit is
+ * needed.
+ */
+#define DIST_MODEL_START 4
+
+/**
+ * Match distances greater than 127 are encoded in three pieces:
+ * - distance slot: the highest two bits
+ * - direct bits: 2-26 bits below the highest two bits
+ * - alignment bits: four lowest bits
+ *
+ * Direct bits don't use any probabilities.
+ *
+ * The distance slot value of 14 is for distances 128-191.
+ */
+#define DIST_MODEL_END 14
+
+/* Distance slots that indicate a distance <= 127. */
+#define FULL_DISTANCES_BITS (DIST_MODEL_END / 2)
+#define FULL_DISTANCES (1 << FULL_DISTANCES_BITS)
+
+/*
+ * For match distances greater than 127, only the highest two bits and the
+ * lowest four bits (alignment) is encoded using probabilities.
+ */
+#define ALIGN_BITS 4
+
+#define ALIGN_SIZE (1 << ALIGN_BITS)
+#define ALIGN_MASK (ALIGN_SIZE - 1)
+
+/* Total number of all probability variables */
+#define PROBS_TOTAL (1846 + LITERAL_CODERS_MAX * LITERAL_CODER_SIZE)
+
+/*
+ * LZMA remembers the four most recent match distances. Reusing these
+ * distances tends to take less space than re-encoding the actual
+ * distance value.
+ */
+#define REPS 4
+
+#endif /* _XZ_LZMA2_H */
\ No newline at end of file
--- /dev/null
+/******************************************************************************
+ * @file lib.c
+ *****************************************************************************/
+#include <assert.h>
+#include <ctype.h>
+#include <limits.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "lib.h"
+#include "report.h"
+#include "unxz.h"
+
+#define OPTION_HELP 0x0001
+
+struct option {
+
+ const char *name;
+ int index, flags;
+
+};
+
+#define OPTION_NO_ARG 0x0001
+#define OPTION_HAS_ARG 0x0002
+
+static struct option opts[] = {
+
+ { "--help", OPTION_HELP, OPTION_NO_ARG },
+ { 0, 0, 0 }
+
+};
+
+static int strstart (const char *val, const char **str) {
+
+ const char *p = val;
+ const char *q = *str;
+
+ while (*p != '\0') {
+
+ if (*p != *q) {
+ return 0;
+ }
+
+ ++p;
+ ++q;
+
+ }
+
+ *str = q;
+ return 1;
+
+}
+
+static void print_help (void) {
+
+ if (program_name) {
+
+ fprintf (stderr, "Usage: %s [opts] file... [-x xlist]\n\n", program_name);
+ fprintf (stderr, "Options:\n\n");
+
+ fprintf (stderr, " --help Show this help information then exit.\n");
+
+ }
+
+ exit (EXIT_SUCCESS);
+
+}
+
+static void dynarray_add (void *ptab, long *nb_ptr, void *data) {
+
+ int nb, nb_alloc;
+ void **pp;
+
+ nb = *nb_ptr;
+ pp = *(void ***) ptab;
+
+ if ((nb & (nb - 1)) == 0) {
+
+ if (!nb) {
+ nb_alloc = 1;
+ } else {
+ nb_alloc = nb * 2;
+ }
+
+ pp = xrealloc (pp, nb_alloc * sizeof (void *));
+ *(void ***) ptab = pp;
+
+ }
+
+ pp[nb++] = data;
+ *nb_ptr = nb;
+
+}
+
+void parse_args (int argc, char **argv, int optind) {
+
+ struct option *popt;
+ const char *optarg, *r;
+
+ if (argc <= optind) {
+ print_help ();
+ }
+
+ while (optind < argc) {
+
+ r = argv[optind++];
+
+ if (r[0] != '-' || r[1] == '\0') {
+
+ dynarray_add (&state->files, &state->nb_files, xstrdup (r));
+ continue;
+
+ }
+
+ for (popt = opts; popt; popt++) {
+
+ const char *p1 = popt->name;
+ const char *r1 = r;
+
+ if (!p1) {
+
+ report_at (program_name, 0, REPORT_ERROR, "invalid option -- '%s'", r);
+ exit (EXIT_FAILURE);
+
+ }
+
+ if (!strstart (p1, &r1)) {
+ continue;
+ }
+
+ optarg = r1;
+
+ if (popt->flags & OPTION_HAS_ARG) {
+
+ if (*optarg == '\0') {
+
+ if (optind >= argc) {
+
+ report_at (program_name, 0, REPORT_ERROR, "argument to '%s' is missing", r);
+ exit (EXIT_FAILURE);
+
+ }
+
+ optarg = argv[optind++];
+
+ }
+
+ } else if (*optarg != '\0') {
+ continue;
+ }
+
+ break;
+
+ }
+
+ switch (popt->index) {
+
+ case OPTION_HELP: {
+
+ print_help ();
+ break;
+
+ }
+
+ default: {
+
+ report_at (program_name, 0, REPORT_ERROR, "unsupported option '%s'", r);
+ exit (EXIT_FAILURE);
+
+ }
+
+ }
+
+ }
+
+}
+
+char *xstrdup (const char *str) {
+
+ char *ptr = xmalloc (strlen (str) + 1);
+ strcpy (ptr, str);
+
+ return ptr;
+
+}
+
+char *xstrndup (const char *str, unsigned long len) {
+
+ char *p = xmalloc (len + 1);
+
+ memcpy (p, str, len);
+ return p;
+
+}
+
+void *xmalloc (unsigned long size) {
+
+ void *ptr = malloc (size);
+
+ if (ptr == NULL && size) {
+
+ report_at (program_name, 0, REPORT_ERROR, "memory full (malloc)");
+ exit (EXIT_FAILURE);
+
+ }
+
+ memset (ptr, 0, size);
+ return ptr;
+
+}
+
+void *xrealloc (void *ptr, unsigned long size) {
+
+ void *new_ptr = realloc (ptr, size);
+
+ if (new_ptr == NULL && size) {
+
+ report_at (program_name, 0, REPORT_ERROR, "memory full (realloc)");
+ exit (EXIT_FAILURE);
+
+ }
+
+ return new_ptr;
+
+}
--- /dev/null
+/******************************************************************************
+ * @file lib.h
+ *****************************************************************************/
+#ifndef _LIB_H
+#define _LIB_H
+
+char *xstrdup (const char *str);
+char *xstrndup (const char *str, unsigned long len);
+
+void *xmalloc (unsigned long size);
+void *xrealloc (void *ptr, unsigned long size);
+
+void parse_args (int argc, char **argv, int optind);
+
+#endif /* _LIB_H */
--- /dev/null
+/******************************************************************************
+ * @file xz_crc32.c
+ *****************************************************************************/
+#include <stdint.h>
+
+static uint32_t xz_crc32_table[256];
+
+uint32_t xz_crc32 (const uint8_t *buf, uint64_t size, uint32_t crc) {
+
+ crc = ~crc;
+
+ while (size != 0) {
+
+ crc = xz_crc32_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8);
+ size--;
+
+ }
+
+ return ~crc;
+
+}
+
+void xz_crc32_init (void) {
+
+ const uint32_t poly = 0xEDB88320;
+ uint32_t i, j, r;
+
+ for (i = 0; i < 256; i++) {
+
+ r = i;
+
+ for (j = 0; j < 8; j++) {
+ r = (r >> 1) ^ (poly & ~((r & 1) - 1));
+ }
+
+ xz_crc32_table[i] = r;
+
+ }
+
+}
--- /dev/null
+/******************************************************************************
+ * @file xz_crc64.c
+ *****************************************************************************/
+#include <stdint.h>
+
+static uint64_t xz_crc64_table[256];
+
+uint64_t xz_crc64 (const uint8_t *buf, uint64_t size, uint64_t crc) {
+
+ crc = ~crc;
+
+ while (size != 0) {
+
+ crc = xz_crc64_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8);
+ size--;
+
+ }
+
+ return ~crc;
+
+}
+
+void xz_crc64_init (void) {
+
+ const uint64_t poly = 0xC96C5795D7870F42ULL;
+ uint64_t i, j, r;
+
+ for (i = 0; i < 256; i++) {
+
+ r = i;
+
+ for (j = 0; j < 8; j++) {
+ r = (r >> 1) ^ (poly & ~((r & 1) - 1));
+ }
+
+ xz_crc64_table[i] = r;
+
+ }
+
+}
--- /dev/null
+/******************************************************************************
+ * @file xz_dec_bcj.c
+ *****************************************************************************/
+#include <stdint.h>
+#include <xz.h>
+
+struct xz_dec_bcj {
+
+ /* Type of the BCJ filter being used */
+ enum {
+
+ BCJ_X86 = 4, /* x86 or x86-64 */
+ BCJ_POWERPC = 5, /* Big endian only */
+ BCJ_IA64 = 6, /* Big or little endian */
+ BCJ_ARM = 7, /* Little endian only */
+ BCJ_ARMTHUMB = 8, /* Little endian only */
+ BCJ_SPARC = 9 /* Big or little endian */
+
+ } type;
+
+ /**
+ * Return value of the next filter in the chain. We need to preserve
+ * this information across calls, because we must not call the next
+ * filter anymore once it has returned XZ_STREAM_END.
+ */
+ enum xz_ret ret;
+
+ /* True if we are operating in single-call mode. */
+ int single_call;
+
+ /**
+ * Absolute position relative to the beginning of the uncompressed
+ * data (in a single .xz Block). We care only about the lowest 32
+ * bits so this doesn't need to be uint64_t even with big files.
+ */
+ uint32_t pos;
+
+ /* x86 filter state */
+ uint32_t x86_prev_mask;
+
+ /* Temporary space to hold the variables from struct xz_buf */
+ uint8_t *out;
+
+ uint64_t out_pos;
+ uint64_t out_size;
+
+ struct {
+
+ /* Amount of already filtered data in the beginning of buf */
+ uint64_t filtered;
+
+ /* Total amount of data currently stored in buf */
+ uint64_t size;
+
+ /*
+ * Buffer to hold a mix of filtered and unfiltered data. This
+ * needs to be big enough to hold Alignment + 2 * Look-ahead:
+ *
+ * Type Alignment Look-ahead
+ * ---------------------------------------
+ * x86 1 4
+ * PowerPC 4 0
+ * IA-64 16 0
+ * ARM 4 0
+ * ARM-Thumb 2 2
+ * SPARC 4 0
+ */
+ uint8_t buf[16];
+
+ } temp;
+
+};
+
+/**
+ * This is used to test the most significant byte of a memory address
+ * in an x86 instruction.
+ */
+static int bcj_x86_test_msbyte (uint8_t b) {
+ return (b == 0 || b == 8);
+}
+
+static uint64_t bcj_x86 (struct xz_dec_bcj *s, uint8_t *buf, uint64_t size) {
+
+ static const int mask_to_allowed_status[8] = { 1, 1, 1, 0, 1, 0, 0, 0 };
+ static const uint8_t mask_to_bit_num[8] = { 0, 1, 2, 2, 3, 3, 3, 3 };
+
+ uint32_t prev_mask = s->x86_prev_mask;
+ uint64_t prev_pos = -1, i;
+
+ uint32_t src, dest, j;
+ uint8_t b;
+
+ if (size <= 4) {
+ return 0;
+ }
+
+ size -= 4;
+
+ for (i = 0; i < size; i++) {
+
+ if ((buf[i] & 0xFE) != 0xE8) {
+ continue;
+ }
+
+ if ((prev_pos = i - prev_pos)) {
+ prev_mask = 0;
+ } else {
+
+ if ((prev_mask = (prev_mask << (prev_pos - 1)) & 7)) {
+
+ b = buf[i + 4 - mask_to_bit_num[prev_mask]];
+
+ if (!mask_to_allowed_status[prev_mask] || bcj_x86_test_msbyte (b)) {
+
+ prev_pos = i;
+
+ prev_mask = (prev_mask << 1) | 1;
+ continue;
+
+ }
+
+ }
+
+ }
+
+ prev_pos = i;
+
+ if (bcj_x86_test_msbyte (buf[i + 4])) {
+
+ src = get_unaligned_le32 (buf + i + 1);
+
+ for (;;) {
+
+ dest = src - (s->pos + (uint32_t) i + 5);
+
+ if (!prev_mask) {
+ break;
+ }
+
+ j = mask_to_bit_num[prev_mask] * 8;
+ b = (uint8_t) (dest >> 24 - j);
+
+ if (!bcj_x86_test_msbyte (b)) {
+ break;
+ }
+
+ src = dest ^ (((uint32_t) 1 << (32 - j)) - 1);
+
+ }
+
+ dest &= 0x01FFFFFF;
+
+ dest |= (uint32_t) 0 - (dest & 0x01000000);
+ put_unaligned_le32 (dest, buf + i + 1);
+
+ i += 4;
+
+ } else {
+ prev_mask = (prev_mask << 1) | 1;
+ }
+
+ }
+
+ prev_pos = i - prev_pos;
+
+ s->x86_prev_mask = (prev_pos > 3) ? 0 : (prev_mask << (prev_pos - 1));
+ return i;
+
+}
+
+static uint64_t bcj_arm (struct xz_dec_bcj *s, uint8_t *buf, uint64_t size) {
+
+ uint32_t addr;
+ uint64_t i;
+
+ for (i = 0; i + 4 <= size; i+= 4) {
+
+ if (buf[i + 3] == 0xEB) {
+
+ addr = (uint32_t) buf[i] | ((uint32_t) buf[i + 1] << 8) | ((uint32_t) buf[i + 2] << 16);
+ addr <<= 2;
+
+ addr -= s->pos + (uint32_t) i + 8;
+ addr >>= 2;
+
+ buf[i] = (uint8_t) addr;
+
+ buf[i + 1] = (uint8_t) (addr >> 8);
+ buf[i + 2] = (uint8_t) (addr >> 16);
+
+ }
+
+ }
+
+ return i;
+
+}
+
+static uint64_t bcj_armthumb (struct xz_dec_bcj *s, uint8_t *buf, uint64_t size) {
+
+ uint32_t addr;
+ uint64_t i;
+
+ for (i = 0; i + 4 <= size; i += 2) {
+
+ if ((buf[i + 1] & 0xF8) == 0xF0 && (buf[i + 3] & 0xF8) == 0xF8) {
+
+ addr = (((uint32_t) buf[i + 1] & 0x07) << 19) | ((uint32_t) buf[i] << 11) | (((uint32_t) buf[i + 3] & 0x07) << 8) | (uint32_t) buf[i + 2];
+ addr <<= 1;
+
+ addr -= s->pos + (uint32_t) i + 4;
+ addr >>= 1;
+
+ buf[i + 1] = (uint8_t) (0xF0 | ((addr >> 19) & 0x07));
+ buf[i] = (uint8_t) (addr >> 11);
+
+ buf[i + 3] = (uint8_t) (0xF8 | ((addr >> 8) & 0x07));
+ buf[i + 2] = (uint8_t) addr;
+
+ i += 2;
+
+ }
+
+ }
+
+ return i;
+
+}
+
+static uint64_t bcj_powerpc (struct xz_dec_bcj *s, uint8_t *buf, uint64_t size) {
+
+ uint32_t instr;
+ uint64_t i;
+
+ for (i = 0; i + 4 <= size; i += 4) {
+
+ instr = get_unaligned_be32 (buf + i);
+
+ if ((instr & 0xFC000003) == 0x48000001) {
+
+ instr &= 0x03FFFFFC;
+
+ instr -= s->pos + (uint32_t) i;
+ instr &= 0x03FFFFFC;
+
+ instr |= 0x48000001;
+ put_unaligned_be32 (instr, buf + i);
+
+ }
+
+ }
+
+ return i;
+
+}
+
+static uint64_t bcj_sparc (struct xz_dec_bcj *s, uint8_t *buf, uint64_t size) {
+
+ uint32_t instr;
+ uint64_t i;
+
+ for (i = 0; i + 4 <= size; i += 4) {
+
+ instr = get_unaligned_be32 (buf + i);
+
+ if ((instr >> 22) == 0x100 || (instr >> 22) == 0x1FF) {
+
+ instr <<= 2;
+
+ instr -= s->pos + (uint32_t) i;
+ instr >>= 2;
+
+ instr = ((uint32_t) 0x40000000 - (instr & 0x400000)) | 0x40000000 | (instr & 0x3FFFFF);
+ put_unaligned_be32 (instr, buf + i);
+
+ }
+
+ }
+
+ return i;
+
+}
+
+static uint64_t bcj_ia64 (struct xz_dec_bcj *s, uint8_t *buf, uint64_t size) {
+
+ static const uint8_t branch_table[32] = {
+
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 4, 4, 6, 6, 0, 0, 7, 7,
+ 4, 4, 0, 0, 4, 4, 0, 0
+
+ };
+
+ uint64_t i, j;
+
+ /* Instruction slot (0, 1 or 2) in the 128-bit instruction word. */
+ uint32_t slot;
+
+ /* Bitwise offset of the instruction indicated by slot. */
+ uint32_t bit_pos;
+
+ /* bit-pos split into byte and bit parts. */
+ uint32_t byte_pos, bit_res;
+
+ /* Address part of an instruction. */
+ uint32_t addr;
+
+ /* Mask used to detect which instruction to convert. */
+ uint32_t mask;
+
+ /* 41-bit instruction stored somewhere in the lowest 48 bits. */
+ uint64_t instr;
+
+ /* Instruction normalized with bit_res for easier manipulation. */
+ uint64_t norm;
+
+ for (i = 0; i + 16 <= size; i += 16) {
+
+ mask = branch_table[buf[i] & 0x3F];
+
+ for (slot = 0, bit_pos = 5; slot < 3; slot++, bit_pos += 41) {
+
+ if (((mask >> slot) & 1) == 0) {
+ continue;
+ }
+
+ byte_pos = bit_pos >> 3;
+ bit_res = bit_pos & 7;
+
+ instr = 0;
+
+ for (j = 0; j < 6; j++) {
+ instr |= (uint64_t) (buf[i + j + byte_pos]) << (8 * j);
+ }
+
+ norm = instr >> bit_res;
+
+ if (((norm >> 37) & 0x0F) == 0x05 && ((norm >> 9) & 0x07) == 0) {
+
+ addr = (norm >> 13) & 0x0FFFFF;
+
+ addr |= ((uint32_t)(norm >> 36) & 1) << 20;
+ addr <<= 4;
+
+ addr -= s->pos + (uint32_t)i;
+ addr >>= 4;
+
+ norm &= ~((uint64_t)0x8FFFFF << 13);
+ norm |= (uint64_t)(addr & 0x0FFFFF) << 13;
+ norm |= (uint64_t)(addr & 0x100000) << (36 - 20);
+
+ instr &= (1 << bit_res) - 1;
+ instr |= norm << bit_res;
+
+ for (j = 0; j < 6; j++) {
+ buf[i + j + byte_pos] = (uint8_t) (instr >> (8 * j));
+ }
+
+ }
+
+ }
+
+ }
+
+ return i;
+
+}
+
+/**
+ * Apply the selected BCJ filter. Update *pos and s->pos to match the amount
+ * of data that got filtered.
+ *
+ * NOTE: This is implemented as a switch statement to avoid using function
+ * pointers, which could be problematic in the kernel boot code, which must
+ * avoid pointers to static data (at least on x86).
+ */
+static void bcj_apply (struct xz_dec_bcj *s, uint8_t *buf, uint64_t *pos, uint64_t size) {
+
+ uint64_t filtered;
+
+ buf += *pos;
+ size -= *pos;
+
+ switch (s->type) {
+
+ case BCJ_X86:
+
+ filtered = bcj_x86 (s, buf, size);
+ break;
+
+ case BCJ_POWERPC:
+
+ filtered = bcj_powerpc (s, buf, size);
+ break;
+
+ case BCJ_IA64:
+
+ filtered = bcj_ia64 (s, buf, size);
+ break;
+
+ case BCJ_ARM:
+
+ filtered = bcj_arm (s, buf, size);
+ break;
+
+ case BCJ_ARMTHUMB:
+
+ filtered = bcj_armthumb (s, buf, size);
+ break;
+
+ case BCJ_SPARC:
+
+ filtered = bcj_sparc (s, buf, size);
+ break;
+
+ default:
+
+ /* Never reached but silence compiler warnings. */
+ filtered = 0;
+ break;
+
+ }
+
+ *pos += filtered;
+ s->pos += filtered;
+
+}
+
+#ifndef MIN
+# define MIN(x, y) ((x) < (y) ? (x) : (y))
+#endif
+
+/**
+ * Flush pending filtered data from temp to the output buffer.
+ * Move the remaining mixture of possibly filtered and unfiltered
+ * data to the beginning of temp.
+ */
+static void bcj_flush (struct xz_dec_bcj *s, struct xz_buf *b) {
+
+ uint64_t copy_size;
+
+ copy_size = MIN (s->temp.filtered, b->out_size - b->out_pos);
+ memcpy (b->out + b->out_pos, s->temp.buf, copy_size);
+
+ b->out_pos += copy_size;
+
+ s->temp.filtered -= copy_size;
+ s->temp.size -= copy_size;
+ memmove (s->temp.buf, s->temp.buf + copy_size, s->temp.size);
+
+}
+
+/**
+ * The BCJ filter functions are primitive in sense that they process the
+ * data in chunks of 1-16 bytes. To hide this issue, this function does
+ * some buffering.
+ */
+enum xz_ret xz_dec_bcj_run (struct xz_dec_bcj *s, struct xz_dec_lzma2 *lzma2, struct xz_buf *b) {
+
+ uint64_t out_start;
+
+ /*
+ * Flush pending already filtered data to the output buffer. Return
+ * immediatelly if we couldn't flush everything, or if the next
+ * filter in the chain had already returned XZ_STREAM_END.
+ */
+ if (s->temp.filtered > 0) {
+
+ bcj_flush (s, b);
+
+ if (s->temp.filtered > 0) {
+ return XZ_OK;
+ }
+
+ if (s->ret == XZ_STREAM_END) {
+ return XZ_STREAM_END;
+ }
+
+ }
+
+ /*
+ * If we have more output space than what is currently pending in
+ * temp, copy the unfiltered data from temp to the output buffer
+ * and try to fill the output buffer by decoding more data from the
+ * next filter in the chain. Apply the BCJ filter on the new data
+ * in the output buffer. If everything cannot be filtered, copy it
+ * to temp and rewind the output buffer position accordingly.
+ */
+ if (s->temp.size < b->out_size - b->out_pos) {
+
+ out_start = b->out_pos;
+
+ memcpy (b->out + b->out_pos, s->temp.buf, s->temp.size);
+ b->out_pos += s->temp.size;
+
+ s->ret = xz_dec_lzma2_run (lzma2, b);
+
+ if (s->ret != XZ_STREAM_END && (s->ret != XZ_OK || s->single_call)) {
+ return s->ret;
+ }
+
+ bcj_apply (s, b->out, &out_start, b->out_pos);
+
+ /*
+ * As an exception, if the next filter returned XZ_STREAM_END,
+ * we can do that too, since the last few bytes that remain
+ * unfiltered are meant to remain unfiltered.
+ */
+ if (s->ret == XZ_STREAM_END) {
+ return XZ_STREAM_END;
+ }
+
+ s->temp.size = b->out_pos - out_start;
+ b->out_pos -= s->temp.size;
+
+ memcpy (s->temp.buf, b->out + b->out_pos, s->temp.size);
+
+ }
+
+ /*
+ * If we have unfiltered data in temp, try to fill by decoding more
+ * data from the next filter. Apply the BCJ filter on temp. Then we
+ * hopefully can fill the actual output buffer by copying filtered
+ * data from temp. A mix of filtered and unfiltered data may be left
+ * in temp; it will be taken care on the next call to this function.
+ */
+ if (s->temp.size > 0) {
+
+ /* Make b->out{,_pos,_size} temporarily point to s->temp. */
+ s->out = b->out;
+ s->out_pos = b->out_pos;
+ s->out_size = b->out_size;
+ b->out = s->temp.buf;
+ b->out_pos = s->temp.size;
+ b->out_size = sizeof(s->temp.buf);
+
+ s->ret = xz_dec_lzma2_run (lzma2, b);
+
+ s->temp.size = b->out_pos;
+ b->out = s->out;
+ b->out_pos = s->out_pos;
+ b->out_size = s->out_size;
+
+ if (s->ret != XZ_OK && s->ret != XZ_STREAM_END) {
+ return s->ret;
+ }
+
+ bcj_apply (s, s->temp.buf, &s->temp.filtered, s->temp.size);
+
+ /*
+ * If the next filter returned XZ_STREAM_END, we mark that
+ * everything is filtered, since the last unfiltered bytes
+ * of the stream are meant to be left as is.
+ */
+ if (s->ret == XZ_STREAM_END) {
+ s->temp.filtered = s->temp.size;
+ }
+
+ bcj_flush (s, b);
+
+ if (s->temp.filtered > 0) {
+ return XZ_OK;
+ }
+
+ }
+
+ return s->ret;
+
+}
+
+struct xz_dec_bcj *xz_dec_bcj_create (int single_call) {
+
+ struct xz_dec_bcj *s;
+
+ if ((s = malloc (sizeof (*s)))) {
+ s->single_call = single_call;
+ }
+
+ return s;
+
+}
+
+enum xz_ret xz_dec_bcj_reset (struct xz_dec_bcj *s, uint8_t id) {
+
+ switch (id) {
+
+ case BCJ_X86: case BCJ_POWERPC:
+ case BCJ_IA64: case BCJ_ARM:
+ case BCJ_ARMTHUMB: case BCJ_SPARC:
+
+ break;
+
+ default:
+
+ /* Unsupported Filter ID */
+ return XZ_OPTIONS_ERROR;
+
+ }
+
+ s->type = id;
+ s->ret = XZ_OK;
+ s->pos = 0;
+
+ s->x86_prev_mask = 0;
+ s->temp.filtered = 0;
+ s->temp.size = 0;
+
+ return XZ_OK;
+
+}
--- /dev/null
+/******************************************************************************
+ * @file xz_dec_lzma2.c
+ *****************************************************************************/
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <xz_lzma2.h>
+#include <xz.h>
+
+#ifndef MIN
+# define MIN(x, y) ((x) < (y) ? (x) : (y))
+#endif
+
+#define DEC_IS_SINGLE(mode) ((mode) == XZ_SINGLE)
+#define DEC_IS_MULTI(mode) ((mode) != XZ_SINGLE)
+#define DEC_IS_PREALLOC(mode) ((mode) == XZ_PREALLOC)
+#define DEC_IS_DYNALLOC(mode) ((mode) == XZ_DYNALLOC)
+
+/* Indicate that the latest symbol was a literal. */
+static void lzma_state_literal (int *state) {
+
+ if (*state <= STATE_SHORTREP_LIT_LIT) {
+ *state = STATE_LIT_LIT;
+ } else if (*state <= STATE_LIT_SHORTREP) {
+ *state -= 3;
+ } else {
+ *state -= 6;
+ }
+
+}
+
+/* Indicate that the latest symbol was a match. */
+static void lzma_state_match (enum lzma_state *state) {
+ *state = *state < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH;
+}
+
+/* Indicate that the latest state was a long repeated match. */
+static void lzma_state_long_rep (enum lzma_state *state) {
+ *state = *state < LIT_STATES ? STATE_LIT_LONGREP : STATE_NONLIT_REP;
+}
+
+/* Indicate that the latest symbol was a short match. */
+static void lzma_state_short_rep (enum lzma_state *state) {
+ *state = *state < LIT_STATES ? STATE_LIT_SHORTREP : STATE_NONLIT_REP;
+}
+
+/* Test if the previous symbol was a literal. */
+static int lzma_state_is_literal (enum lzma_state state) {
+ return state < LIT_STATES;
+}
+
+/**
+ * Get the index of the appropriate probability array for decoding
+ * the distance slot.
+ */
+static uint32_t lzma_get_dist_state (uint32_t len) {
+ return len < DIST_STATES + MATCH_LEN_MIN ? len - MATCH_LEN_MIN : DIST_STATES - 1;
+}
+
+/* Range decoder initialization eats the first five bytes of each LZMA chunk. */
+#define RC_INIT_BYTES 5
+
+/*
+ * Minimum number of usable input buffer to safely decode one LZMA symbol.
+ * The worst case is that we decode 22 bits using probabilities and 26
+ * direct bits. This may decode at maximum of 20 bytes of input. However,
+ * lzma_main() does an extra normalization before returning, thus we
+ * need to put 21 here.
+ */
+#define LZMA_IN_REQUIRED 21
+
+/*
+ * Dictionary (history buffer)
+ *
+ * These are always true:
+ * start <= pos <= full <= end
+ * pos <= limit <= end
+ *
+ * In multi-call mode, also these are true:
+ * end == size
+ * size <= size_max
+ * allocated <= size
+ *
+ * Most of these variables are size_t to support single-call mode,
+ * in which the dictionary variables address the actual output
+ * buffer directly.
+ */
+struct dictionary {
+
+ /* Beginning of the history buffer */
+ uint8_t *buf;
+
+ /* Old position in buf (before decoding more data) */
+ uint64_t start;
+
+ /* Position in buf */
+ uint64_t pos;
+
+ /*
+ * How full dictionary is. This is used to detect corrupt input that
+ * would read beyond the beginning of the uncompressed stream.
+ */
+ uint64_t full;
+
+ /* Write limit; we don't write to buf[limit] or later bytes. */
+ uint64_t limit;
+
+ /*
+ * End of the dictionary buffer. In multi-call mode, this is
+ * the same as the dictionary size. In single-call mode, this
+ * indicates the size of the output buffer.
+ */
+ uint64_t end;
+
+ /*
+ * Size of the dictionary as specified in Block Header. This is used
+ * together with "full" to detect corrupt input that would make us
+ * read beyond the beginning of the uncompressed stream.
+ */
+ uint32_t size;
+
+ /*
+ * Maximum allowed dictionary size in multi-call mode.
+ * This is ignored in single-call mode.
+ */
+ uint32_t size_max;
+
+ /*
+ * Amount of memory currently allocated for the dictionary.
+ * This is used only with XZ_DYNALLOC. (With XZ_PREALLOC,
+ * size_max is always the same as the allocated size.)
+ */
+ uint32_t allocated;
+
+ /* Operation mode */
+ enum xz_mode mode;
+
+};
+
+/* Range decoder */
+struct rc_dec {
+
+ uint32_t range;
+ uint32_t code;
+
+ /*
+ * Number of initializing bytes remaining to be read
+ * by rc_read_init().
+ */
+ uint32_t init_bytes_left;
+
+ /*
+ * Buffer from which we read our input. It can be either
+ * temp.buf or the caller-provided input buffer.
+ */
+ const uint8_t *in;
+ uint64_t in_pos;
+ uint64_t in_limit;
+
+};
+
+/* Probabilities for a length decoder. */
+struct lzma_len_dec {
+
+ /* Probability of match length being at least 10 */
+ uint16_t choice;
+
+ /* Probability of match length being at least 18 */
+ uint16_t choice2;
+
+ /* Probabilities for match lengths 2-9 */
+ uint16_t low[POS_STATES_MAX][LEN_LOW_SYMBOLS];
+
+ /* Probabilities for match lengths 10-17 */
+ uint16_t mid[POS_STATES_MAX][LEN_MID_SYMBOLS];
+
+ /* Probabilities for match lengths 18-273 */
+ uint16_t high[LEN_HIGH_SYMBOLS];
+
+};
+
+struct lzma_dec {
+
+ /* Distances of latest four matches */
+ uint32_t rep0;
+ uint32_t rep1;
+ uint32_t rep2;
+ uint32_t rep3;
+
+ /* Types of the most recently seen LZMA symbols */
+ enum lzma_state state;
+
+ /*
+ * Length of a match. This is updated so that dict_repeat can
+ * be called again to finish repeating the whole match.
+ */
+ uint32_t len;
+
+ /*
+ * LZMA properties or related bit masks (number of literal
+ * context bits, a mask dervied from the number of literal
+ * position bits, and a mask dervied from the number
+ * position bits)
+ */
+ uint32_t lc;
+ uint32_t literal_pos_mask; /* (1 << lp) - 1 */
+ uint32_t pos_mask; /* (1 << pb) - 1 */
+
+ /* If 1, it's a match. Otherwise it's a single 8-bit literal. */
+ uint16_t is_match[STATES][POS_STATES_MAX];
+
+ /* If 1, it's a repeated match. The distance is one of rep0 .. rep3. */
+ uint16_t is_rep[STATES];
+
+ /*
+ * If 0, distance of a repeated match is rep0.
+ * Otherwise check is_rep1.
+ */
+ uint16_t is_rep0[STATES];
+
+ /*
+ * If 0, distance of a repeated match is rep1.
+ * Otherwise check is_rep2.
+ */
+ uint16_t is_rep1[STATES];
+
+ /* If 0, distance of a repeated match is rep2. Otherwise it is rep3. */
+ uint16_t is_rep2[STATES];
+
+ /*
+ * If 1, the repeated match has length of one byte. Otherwise
+ * the length is decoded from rep_len_decoder.
+ */
+ uint16_t is_rep0_long[STATES][POS_STATES_MAX];
+
+ /*
+ * Probability tree for the highest two bits of the match
+ * distance. There is a separate probability tree for match
+ * lengths of 2 (i.e. MATCH_LEN_MIN), 3, 4, and [5, 273].
+ */
+ uint16_t dist_slot[DIST_STATES][DIST_SLOTS];
+
+ /*
+ * Probility trees for additional bits for match distance
+ * when the distance is in the range [4, 127].
+ */
+ uint16_t dist_special[FULL_DISTANCES - DIST_MODEL_END];
+
+ /*
+ * Probability tree for the lowest four bits of a match
+ * distance that is equal to or greater than 128.
+ */
+ uint16_t dist_align[ALIGN_SIZE];
+
+ /* Length of a normal match */
+ struct lzma_len_dec match_len_dec;
+
+ /* Length of a repeated match */
+ struct lzma_len_dec rep_len_dec;
+
+ /* Probabilities of literals */
+ uint16_t literal[LITERAL_CODERS_MAX][LITERAL_CODER_SIZE];
+
+};
+
+struct lzma2_dec {
+
+ /* Position in xz_dec_lzma2_run(). */
+ enum lzma2_seq {
+
+ SEQ_CONTROL,
+ SEQ_UNCOMPRESSED_1,
+ SEQ_UNCOMPRESSED_2,
+ SEQ_COMPRESSED_0,
+ SEQ_COMPRESSED_1,
+ SEQ_PROPERTIES,
+ SEQ_LZMA_PREPARE,
+ SEQ_LZMA_RUN,
+ SEQ_COPY
+
+ } sequence;
+
+ /* Next position after decoding the compressed size of the chunk. */
+ enum lzma2_seq next_sequence;
+
+ /* Uncompressed size of LZMA chunk (2 MiB at maximum) */
+ uint32_t uncompressed;
+
+ /*
+ * Compressed size of LZMA chunk or compressed/uncompressed
+ * size of uncompressed chunk (64 KiB at maximum)
+ */
+ uint32_t compressed;
+
+ /*
+ * True if dictionary reset is needed. This is false before
+ * the first chunk (LZMA or uncompressed).
+ */
+ int need_dict_reset;
+
+ /*
+ * True if new LZMA properties are needed. This is false
+ * before the first LZMA chunk.
+ */
+ int need_props;
+
+};
+
+struct xz_dec_lzma2 {
+
+ /*
+ * The order below is important on x86 to reduce code size and
+ * it shouldn't hurt on other platforms. Everything up to and
+ * including lzma.pos_mask are in the first 128 bytes on x86-32,
+ * which allows using smaller instructions to access those
+ * variables. On x86-64, fewer variables fit into the first 128
+ * bytes, but this is still the best order without sacrificing
+ * the readability by splitting the structures.
+ */
+ struct rc_dec rc;
+ struct dictionary dict;
+ struct lzma2_dec lzma2;
+ struct lzma_dec lzma;
+
+ /*
+ * Temporary buffer which holds small number of input bytes between
+ * decoder calls. See lzma2_lzma() for details.
+ */
+ struct {
+
+ uint32_t size;
+ uint8_t buf[3 * LZMA_IN_REQUIRED];
+
+ } temp;
+
+};
+
+/*
+ * Reset the dictionary state. When in single-call mode, set up the beginning
+ * of the dictionary to point to the actual output buffer.
+ */
+static void dict_reset(struct dictionary *dict, struct xz_buf *b) {
+
+ if (DEC_IS_SINGLE (dict->mode)) {
+
+ dict->buf = b->out + b->out_pos;
+ dict->end = b->out_size - b->out_pos;
+
+ }
+
+ dict->start = 0;
+ dict->pos = 0;
+ dict->limit = 0;
+ dict->full = 0;
+
+}
+
+/* Set dictionary write limit */
+static void dict_limit (struct dictionary *dict, uint64_t out_max)
+{
+
+ if (dict->end - dict->pos <= out_max) {
+ dict->limit = dict->end;
+ } else {
+ dict->limit = dict->pos + out_max;
+ }
+
+}
+
+/* Return true if at least one byte can be written into the dictionary. */
+static int dict_has_space (const struct dictionary *dict) {
+ return dict->pos < dict->limit;
+}
+
+/**
+ * Get a byte from the dictionary at the given distance. The distance is
+ * assumed to valid, or as a special case, zero when the dictionary is
+ * still empty. This special case is needed for single-call decoding to
+ * avoid writing a '\0' to the end of the destination buffer.
+ */
+static uint32_t dict_get (const struct dictionary *dict, uint32_t dist) {
+
+ uint64_t offset = dict->pos - dist - 1;
+
+ if (dist >= dict->pos) {
+ offset += dict->end;
+ }
+
+ return dict->full > 0 ? dict->buf[offset] : 0;
+
+}
+
+/**
+ * Put one byte into the dictionary. It is assumed that there is space
+ * for it.
+ */
+static void dict_put (struct dictionary *dict, uint8_t byte) {
+
+ dict->buf[dict->pos++] = byte;
+
+ if (dict->full < dict->pos) {
+ dict->full = dict->pos;
+ }
+
+}
+
+/**
+ * Repeat given number of bytes from the given distance. If the distance is
+ * invalid, false is returned. On success, true is returned and *len is
+ * updated to indicate how many bytes were left to be repeated.
+ */
+static int dict_repeat (struct dictionary *dict, uint32_t *len, uint32_t dist) {
+
+ uint64_t back;
+ uint32_t left;
+
+ if (dist >= dict->full || dist >= dict->size) {
+ return 0;
+ }
+
+ left = MIN (dict->limit - dict->pos, *len);
+ *len -= left;
+
+ back = dict->pos - dist - 1;
+
+ if (dist >= dict->pos) {
+ back += dict->end;
+ }
+
+ do {
+
+ dict->buf[dict->pos++] = dict->buf[back++];
+
+ if (back == dict->end) {
+ back = 0;
+ }
+
+ } while (--left > 0);
+
+ if (dict->full < dict->pos) {
+ dict->full = dict->pos;
+ }
+
+ return 1;
+
+}
+
+/* Copy uncompressed data as is from input to dictionary and output buffers. */
+static void dict_uncompressed (struct dictionary *dict, struct xz_buf *b, uint32_t *left) {
+
+ uint64_t copy_size;
+
+ while (*left > 0 && b->in_pos < b->in_size && b->out_pos < b->out_size) {
+
+ copy_size = MIN (b->in_size - b->in_pos, b->out_size - b->out_pos);
+
+ if (copy_size > dict->end - dict->pos) {
+ copy_size = dict->end - dict->pos;
+ }
+
+ if (copy_size > *left) {
+ copy_size = *left;
+ }
+
+ *left -= copy_size;
+
+ memmove (dict->buf + dict->pos, b->in + b->in_pos, copy_size);
+ dict->pos += copy_size;
+
+ if (dict->full < dict->pos) {
+ dict->full = dict->pos;
+ }
+
+ if (DEC_IS_MULTI (dict->mode)) {
+
+ if (dict->pos == dict->end) {
+ dict->pos = 0;
+ }
+
+ memmove (b->out + b->out_pos, b->in + b->in_pos, copy_size);
+
+ }
+
+ dict->start = dict->pos;
+
+ b->out_pos += copy_size;
+ b->in_pos += copy_size;
+
+ }
+
+}
+
+/*
+ * Flush pending data from dictionary to b->out. It is assumed that there is
+ * enough space in b->out. This is guaranteed because caller uses dict_limit()
+ * before decoding data into the dictionary.
+ */
+static uint32_t dict_flush (struct dictionary *dict, struct xz_buf *b) {
+
+ uint32_t copy_size = dict->pos - dict->start;
+
+ if (DEC_IS_MULTI (dict->mode)) {
+
+ if (dict->pos == dict->end) {
+ dict->pos = 0;
+ }
+
+ memcpy (b->out + b->out_pos, dict->buf + dict->start, copy_size);
+
+ }
+
+ dict->start = dict->pos;
+ b->out_pos += copy_size;
+
+ return copy_size;
+
+}
+
+/* Reset the range decoder. */
+static void rc_reset (struct rc_dec *rc) {
+
+ rc->range = (uint32_t)-1;
+ rc->code = 0;
+ rc->init_bytes_left = RC_INIT_BYTES;
+
+}
+
+/*
+ * Read the first five initial bytes into rc->code if they haven't been
+ * read already. (Yes, the first byte gets completely ignored.)
+ */
+static int rc_read_init (struct rc_dec *rc, struct xz_buf *b) {
+
+ while (rc->init_bytes_left > 0) {
+
+ if (b->in_pos == b->in_size) {
+ return 0;
+ }
+
+ rc->code = (rc->code << 8) + b->in[b->in_pos++];
+ --rc->init_bytes_left;
+
+ }
+
+ return 1;
+
+}
+
+/* Return true if there may not be enough input for the next decoding loop. */
+static int rc_limit_exceeded (const struct rc_dec *rc) {
+ return rc->in_pos > rc->in_limit;
+}
+
+/*
+ * Return true if it is possible (from point of view of range decoder) that
+ * we have reached the end of the LZMA chunk.
+ */
+static int rc_is_finished (const struct rc_dec *rc) {
+ return rc->code == 0;
+}
+
+/* Read the next input byte if needed. */
+static void rc_normalize (struct rc_dec *rc) {
+
+ if (rc->range < RC_TOP_VALUE) {
+
+ rc->range <<= RC_SHIFT_BITS;
+ rc->code = (rc->code << RC_SHIFT_BITS) + rc->in[rc->in_pos++];
+
+ }
+
+}
+
+/*
+ * Decode one bit. In some versions, this function has been splitted in three
+ * functions so that the compiler is supposed to be able to more easily avoid
+ * an extra branch. In this particular version of the LZMA decoder, this
+ * doesn't seem to be a good idea (tested with GCC 3.3.6, 3.4.6, and 4.3.3
+ * on x86). Using a non-splitted version results in nicer looking code too.
+ *
+ * NOTE: This must return an int. Do not make it return a bool or the speed
+ * of the code generated by GCC 3.x decreases 10-15 %. (GCC 4.3 doesn't care,
+ * and it generates 10-20 % faster code than GCC 3.x from this file anyway.)
+ */
+static int rc_bit (struct rc_dec *rc, uint16_t *prob) {
+
+ uint32_t bound;
+ int bit;
+
+ rc_normalize (rc);
+ bound = (rc->range >> RC_BIT_MODEL_TOTAL_BITS) * *prob;
+
+ if (rc->code < bound) {
+
+ rc->range = bound;
+
+ *prob += (RC_BIT_MODEL_TOTAL - *prob) >> RC_MOVE_BITS;
+ bit = 0;
+
+ } else {
+
+ rc->range -= bound;
+ rc->code -= bound;
+
+ *prob -= *prob >> RC_MOVE_BITS;
+ bit = 1;
+
+ }
+
+ return bit;
+
+}
+
+/* Decode a bittree starting from the most significant bit. */
+static uint32_t rc_bittree (struct rc_dec *rc, uint16_t *probs, uint32_t limit) {
+
+ uint32_t symbol = 1;
+
+ do {
+
+ if (rc_bit (rc, &probs[symbol])) {
+ symbol = (symbol << 1) + 1;
+ } else {
+ symbol <<= 1;
+ }
+
+ } while (symbol < limit);
+
+ return symbol;
+
+}
+
+/* Decode a bittree starting from the least significant bit. */
+static void rc_bittree_reverse (struct rc_dec *rc, uint16_t *probs, uint32_t *dest, uint32_t limit) {
+
+ uint32_t symbol = 1;
+ uint32_t i = 0;
+
+ do {
+
+ if (rc_bit (rc, &probs[symbol])) {
+
+ symbol = (symbol << 1) + 1;
+ *dest += 1 << i;
+
+ } else {
+ symbol <<= 1;
+ }
+
+ } while (++i < limit);
+
+}
+
+/* Decode direct bits (fixed fifty-fifty probability) */
+static void rc_direct (struct rc_dec *rc, uint32_t *dest, uint32_t limit) {
+
+ uint32_t mask;
+
+ do {
+
+ rc_normalize(rc);
+
+ rc->range >>= 1;
+ rc->code -= rc->range;
+
+ mask = (uint32_t) 0 - (rc->code >> 31);
+ rc->code += rc->range & mask;
+
+ *dest = (*dest << 1) + (mask + 1);
+
+ } while (--limit > 0);
+
+}
+
+/* Get pointer to literal coder probability array. */
+static uint16_t *lzma_literal_probs (struct xz_dec_lzma2 *s) {
+
+ uint32_t prev_byte = dict_get(&s->dict, 0);
+
+ uint32_t low = prev_byte >> (8 - s->lzma.lc);
+ uint32_t high = (s->dict.pos & s->lzma.literal_pos_mask) << s->lzma.lc;
+
+ return s->lzma.literal[low + high];
+
+}
+
+/* Decode a literal (one 8-bit byte) */
+static void lzma_literal (struct xz_dec_lzma2 *s) {
+
+ uint16_t *probs;
+
+ uint32_t symbol, offset, i;
+ uint32_t match_byte, match_bit;
+
+ probs = lzma_literal_probs (s);
+
+ if (lzma_state_is_literal (s->lzma.state)) {
+ symbol = rc_bittree (&s->rc, probs, 0x100);
+ } else {
+
+ symbol = 1;
+
+ match_byte = dict_get (&s->dict, s->lzma.rep0) << 1;
+ offset = 0x100;
+
+ do {
+
+ match_bit = match_byte & offset;
+ match_byte <<= 1;
+
+ i = offset + match_bit + symbol;
+
+ if (rc_bit (&s->rc, &probs[i])) {
+
+ symbol = (symbol << 1) + 1;
+ offset &= match_bit;
+
+ } else {
+
+ symbol <<= 1;
+ offset &= ~match_bit;
+
+ }
+
+ } while (symbol < 0x100);
+
+ }
+
+ dict_put (&s->dict, (uint8_t) symbol);
+ lzma_state_literal ((int *) &s->lzma.state);
+
+}
+
+/* Decode the length of the match into s->lzma.len. */
+static void lzma_len (struct xz_dec_lzma2 *s, struct lzma_len_dec *l, uint32_t pos_state) {
+
+ uint16_t *probs;
+ uint32_t limit;
+
+ if (!rc_bit (&s->rc, &l->choice)) {
+
+ probs = l->low[pos_state];
+ limit = LEN_LOW_SYMBOLS;
+ s->lzma.len = MATCH_LEN_MIN;
+
+ } else {
+
+ if (!rc_bit (&s->rc, &l->choice2)) {
+
+ probs = l->mid[pos_state];
+ limit = LEN_MID_SYMBOLS;
+
+ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS;
+
+ } else {
+
+ probs = l->high;
+ limit = LEN_HIGH_SYMBOLS;
+
+ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS;
+
+ }
+
+ }
+
+ s->lzma.len += rc_bittree (&s->rc, probs, limit) - limit;
+
+}
+
+/* Decode a match. The distance will be stored in s->lzma.rep0. */
+static void lzma_match (struct xz_dec_lzma2 *s, uint32_t pos_state) {
+
+ uint32_t dist_slot, limit;
+ uint16_t *probs;
+
+ lzma_state_match (&s->lzma.state);
+
+ s->lzma.rep3 = s->lzma.rep2;
+ s->lzma.rep2 = s->lzma.rep1;
+ s->lzma.rep1 = s->lzma.rep0;
+
+ lzma_len (s, &s->lzma.match_len_dec, pos_state);
+
+ probs = s->lzma.dist_slot[lzma_get_dist_state (s->lzma.len)];
+ dist_slot = rc_bittree (&s->rc, probs, DIST_SLOTS) - DIST_SLOTS;
+
+ if (dist_slot < DIST_MODEL_START) {
+ s->lzma.rep0 = dist_slot;
+ } else {
+
+ limit = (dist_slot >> 1) - 1;
+ s->lzma.rep0 = 2 + (dist_slot & 1);
+
+ if (dist_slot < DIST_MODEL_END) {
+
+ s->lzma.rep0 <<= limit;
+
+ probs = s->lzma.dist_special + s->lzma.rep0 - dist_slot - 1;
+ rc_bittree_reverse (&s->rc, probs, &s->lzma.rep0, limit);
+
+ } else {
+
+ rc_direct (&s->rc, &s->lzma.rep0, limit - ALIGN_BITS);
+
+ s->lzma.rep0 <<= ALIGN_BITS;
+ rc_bittree_reverse (&s->rc, s->lzma.dist_align, &s->lzma.rep0, ALIGN_BITS);
+
+ }
+
+ }
+
+}
+
+/**
+ * Decode a repeated match. The distance is one of the four most recently
+ * seen matches. The distance will be stored in s->lzma.rep0.
+ */
+static void lzma_rep_match (struct xz_dec_lzma2 *s, uint32_t pos_state) {
+
+ uint32_t tmp;
+
+ if (!rc_bit (&s->rc, &s->lzma.is_rep0[s->lzma.state])) {
+
+ if (!rc_bit (&s->rc, &s->lzma.is_rep0_long[s->lzma.state][pos_state])) {
+
+ lzma_state_short_rep (&s->lzma.state);
+
+ s->lzma.len = 1;
+ return;
+
+ }
+
+ } else {
+
+ if (!rc_bit (&s->rc, &s->lzma.is_rep1[s->lzma.state])) {
+ tmp = s->lzma.rep1;
+ } else {
+
+ if (!rc_bit (&s->rc, &s->lzma.is_rep2[s->lzma.state])) {
+ tmp = s->lzma.rep2;
+ } else {
+
+ tmp = s->lzma.rep3;
+ s->lzma.rep3 = s->lzma.rep2;
+
+ }
+
+ s->lzma.rep2 = s->lzma.rep1;
+
+ }
+
+ s->lzma.rep1 = s->lzma.rep0;
+ s->lzma.rep0 = tmp;
+
+ }
+
+ lzma_state_long_rep (&s->lzma.state);
+ lzma_len (s, &s->lzma.rep_len_dec, pos_state);
+
+}
+
+/* LZMA decoder core */
+static int lzma_main (struct xz_dec_lzma2 *s) {
+
+ uint32_t pos_state;
+
+ /*
+ * If the dictionary was reached during the previous call, try to
+ * finish the possibly pending repeat in the dictionary.
+ */
+ if (dict_has_space (&s->dict) && s->lzma.len > 0) {
+ dict_repeat (&s->dict, &s->lzma.len, s->lzma.rep0);
+ }
+
+ /*
+ * Decode more LZMA symbols. One iteration may consume up to
+ * LZMA_IN_REQUIRED - 1 bytes.
+ */
+ while (dict_has_space (&s->dict) && !rc_limit_exceeded (&s->rc)) {
+
+ pos_state = s->dict.pos & s->lzma.pos_mask;
+
+ if (!rc_bit (&s->rc, &s->lzma.is_match[
+
+ s->lzma.state][pos_state])) {
+ lzma_literal (s);
+
+ } else {
+
+ if (rc_bit (&s->rc, &s->lzma.is_rep[s->lzma.state])) {
+ lzma_rep_match (s, pos_state);
+ } else {
+ lzma_match (s, pos_state);
+ }
+
+ if (!dict_repeat (&s->dict, &s->lzma.len, s->lzma.rep0)) {
+ return 0;
+ }
+
+ }
+
+ }
+
+ /*
+ * Having the range decoder always normalized when we are outside
+ * this function makes it easier to correctly handle end of the chunk.
+ */
+ rc_normalize (&s->rc);
+
+ /* Return */
+ return 1;
+
+}
+
+/**
+ * Reset the LZMA decoder and range decoder state. Dictionary is nore reset
+ * here, because LZMA state may be reset without resetting the dictionary.
+ */
+static void lzma_reset (struct xz_dec_lzma2 *s) {
+
+ uint16_t *probs;
+ uint64_t i;
+
+ s->lzma.state = STATE_LIT_LIT;
+ s->lzma.rep0 = 0;
+ s->lzma.rep1 = 0;
+ s->lzma.rep2 = 0;
+ s->lzma.rep3 = 0;
+
+ /*
+ * All probabilities are initialized to the same value. This hack
+ * makes the code smaller by avoiding a separate loop for each
+ * probability array.
+ *
+ * This could be optimized so that only that part of literal
+ * probabilities that are actually required. In the common case
+ * we would write 12 KiB less.
+ */
+ probs = s->lzma.is_match[0];
+
+ for (i = 0; i < PROBS_TOTAL; ++i) {
+ probs[i] = RC_BIT_MODEL_TOTAL / 2;
+ }
+
+ rc_reset (&s->rc);
+
+}
+
+/**
+ * Decode and validate LZMA properties (lc/lp/pb) and calculate the bit masks
+ * from the decoded lp and pb values. On success, the LZMA decoder state is
+ * reset and true is returned.
+ */
+static int lzma_props (struct xz_dec_lzma2 *s, uint8_t props) {
+
+ if (props > (4 * 5 + 4) * 9 + 8) {
+ return 0;
+ }
+
+ s->lzma.pos_mask = 0;
+
+ while (props >= 9 * 5) {
+
+ props -= 9 * 5;
+ ++s->lzma.pos_mask;
+
+ }
+
+ s->lzma.pos_mask = (1 << s->lzma.pos_mask) - 1;
+ s->lzma.literal_pos_mask = 0;
+
+ while (props >= 9) {
+
+ props -= 9;
+ ++s->lzma.literal_pos_mask;
+
+ }
+
+ s->lzma.lc = props;
+
+ if (s->lzma.lc + s->lzma.literal_pos_mask > 4) {
+ return 0;
+ }
+
+ s->lzma.literal_pos_mask = (1 << s->lzma.literal_pos_mask) - 1;
+ lzma_reset (s);
+
+ return 1;
+
+}
+
+static void memzero (void *buf, uint64_t size) {
+
+ uint8_t *b = buf;
+ uint8_t *e = b + size;
+
+ while (b != e) {
+ *b++ = '\0';
+ }
+
+}
+
+/*
+ * The LZMA decoder assumes that if the input limit (s->rc.in_limit) hasn't
+ * been exceeded, it is safe to read up to LZMA_IN_REQUIRED bytes. This
+ * wrapper function takes care of making the LZMA decoder's assumption safe.
+ *
+ * As long as there is plenty of input left to be decoded in the current LZMA
+ * chunk, we decode directly from the caller-supplied input buffer until
+ * there's LZMA_IN_REQUIRED bytes left. Those remaining bytes are copied into
+ * s->temp.buf, which (hopefully) gets filled on the next call to this
+ * function. We decode a few bytes from the temporary buffer so that we can
+ * continue decoding from the caller-supplied input buffer again.
+ */
+static int lzma2_lzma (struct xz_dec_lzma2 *s, struct xz_buf *b) {
+
+ uint64_t in_avail;
+ uint32_t tmp;
+
+ in_avail = b->in_size - b->in_pos;
+
+ if (s->temp.size > 0 || s->lzma2.compressed == 0) {
+
+ tmp = 2 * LZMA_IN_REQUIRED - s->temp.size;
+
+ if (tmp > s->lzma2.compressed - s->temp.size) {
+ tmp = s->lzma2.compressed - s->temp.size;
+ }
+
+ if (tmp > in_avail) {
+ tmp = in_avail;
+ }
+
+ memcpy (s->temp.buf + s->temp.size, b->in + b->in_pos, tmp);
+
+ if (s->temp.size + tmp == s->lzma2.compressed) {
+
+ memzero (s->temp.buf + s->temp.size + tmp, sizeof (s->temp.buf) - s->temp.size - tmp);
+ s->rc.in_limit = s->temp.size + tmp;
+
+ } else if (s->temp.size + tmp < LZMA_IN_REQUIRED) {
+
+ s->temp.size += tmp;
+ b->in_pos += tmp;
+
+ return 1;
+
+ } else {
+ s->rc.in_limit = s->temp.size + tmp - LZMA_IN_REQUIRED;
+ }
+
+ s->rc.in = s->temp.buf;
+ s->rc.in_pos = 0;
+
+ if (!lzma_main (s) || s->rc.in_pos > s->temp.size + tmp) {
+ return 0;
+ }
+
+ s->lzma2.compressed -= s->rc.in_pos;
+
+ if (s->rc.in_pos < s->temp.size) {
+
+ s->temp.size -= s->rc.in_pos;
+
+ memmove (s->temp.buf, s->temp.buf + s->rc.in_pos,
+ s->temp.size);
+
+ return 1;
+
+ }
+
+ b->in_pos += s->rc.in_pos - s->temp.size;
+ s->temp.size = 0;
+
+ }
+
+ in_avail = b->in_size - b->in_pos;
+
+ if (in_avail >= LZMA_IN_REQUIRED) {
+
+ s->rc.in = b->in;
+ s->rc.in_pos = b->in_pos;
+
+ if (in_avail >= s->lzma2.compressed + LZMA_IN_REQUIRED) {
+ s->rc.in_limit = b->in_pos + s->lzma2.compressed;
+ } else {
+ s->rc.in_limit = b->in_size - LZMA_IN_REQUIRED;
+ }
+
+ if (!lzma_main (s)) {
+ return 0;
+ }
+
+ in_avail = s->rc.in_pos - b->in_pos;
+
+ if (in_avail > s->lzma2.compressed) {
+ return 0;
+ }
+
+ s->lzma2.compressed -= in_avail;
+ b->in_pos = s->rc.in_pos;
+
+ }
+
+ in_avail = b->in_size - b->in_pos;
+
+ if (in_avail < LZMA_IN_REQUIRED) {
+
+ if (in_avail > s->lzma2.compressed) {
+ in_avail = s->lzma2.compressed;
+ }
+
+ memcpy (s->temp.buf, b->in + b->in_pos, in_avail);
+ s->temp.size = in_avail;
+
+ b->in_pos += in_avail;
+
+ }
+
+ return 1;
+
+}
+
+/*
+ * Take care of the LZMA2 control layer, and forward the job of actual LZMA
+ * decoding or copying of uncompressed chunks to other functions.
+ */
+enum xz_ret xz_dec_lzma2_run (struct xz_dec_lzma2 *s, struct xz_buf *b) {
+
+ uint32_t tmp;
+
+ while (b->in_pos < b->in_size || s->lzma2.sequence == SEQ_LZMA_RUN) {
+
+ switch (s->lzma2.sequence) {
+
+ case SEQ_CONTROL:
+
+ /*
+ * LZMA2 control byte
+ *
+ * Exact values:
+ * 0x00 End marker
+ * 0x01 Dictionary reset followed by
+ * an uncompressed chunk
+ * 0x02 Uncompressed chunk (no dictionary reset)
+ *
+ * Highest three bits (s->control & 0xE0):
+ * 0xE0 Dictionary reset, new properties and state
+ * reset, followed by LZMA compressed chunk
+ * 0xC0 New properties and state reset, followed
+ * by LZMA compressed chunk (no dictionary
+ * reset)
+ * 0xA0 State reset using old properties,
+ * followed by LZMA compressed chunk (no
+ * dictionary reset)
+ * 0x80 LZMA chunk (no dictionary or state reset)
+ *
+ * For LZMA compressed chunks, the lowest five bits
+ * (s->control & 1F) are the highest bits of the
+ * uncompressed size (bits 16-20).
+ *
+ * A new LZMA2 stream must begin with a dictionary
+ * reset. The first LZMA chunk must set new
+ * properties and reset the LZMA state.
+ *
+ * Values that don't match anything described above
+ * are invalid and we return XZ_DATA_ERROR.
+ */
+ tmp = b->in[b->in_pos++];
+
+ if (tmp == 0x00) {
+ return XZ_STREAM_END;
+ }
+
+ if (tmp >= 0xE0 || tmp == 0x01) {
+
+ s->lzma2.need_props = 1;
+ s->lzma2.need_dict_reset = 0;
+
+ dict_reset (&s->dict, b);
+
+ } else if (s->lzma2.need_dict_reset) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (tmp >= 0x80) {
+
+ s->lzma2.uncompressed = (tmp & 0x1F) << 16;
+ s->lzma2.sequence = SEQ_UNCOMPRESSED_1;
+
+ if (tmp >= 0xC0) {
+
+ /*
+ * When there are new properties,
+ * state reset is done at
+ * SEQ_PROPERTIES.
+ */
+ s->lzma2.need_props = 0;
+ s->lzma2.next_sequence = SEQ_PROPERTIES;
+
+ } else if (s->lzma2.need_props) {
+ return XZ_DATA_ERROR;
+ } else {
+
+ s->lzma2.next_sequence = SEQ_LZMA_PREPARE;
+
+ if (tmp >= 0xA0) {
+ lzma_reset (s);
+ }
+
+ }
+
+ } else {
+
+ if (tmp > 0x02) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->lzma2.sequence = SEQ_COMPRESSED_0;
+ s->lzma2.next_sequence = SEQ_COPY;
+
+ }
+
+ break;
+
+ case SEQ_UNCOMPRESSED_1:
+
+ s->lzma2.uncompressed += (uint32_t )b->in[b->in_pos++] << 8;
+ s->lzma2.sequence = SEQ_UNCOMPRESSED_2;
+ break;
+
+ case SEQ_UNCOMPRESSED_2:
+
+ s->lzma2.uncompressed += (uint32_t) b->in[b->in_pos++] + 1;
+ s->lzma2.sequence = SEQ_COMPRESSED_0;
+ break;
+
+ case SEQ_COMPRESSED_0:
+
+ s->lzma2.compressed = (uint32_t) b->in[b->in_pos++] << 8;
+ s->lzma2.sequence = SEQ_COMPRESSED_1;
+ break;
+
+ case SEQ_COMPRESSED_1:
+
+ s->lzma2.compressed += (uint32_t) b->in[b->in_pos++] + 1;
+ s->lzma2.sequence = s->lzma2.next_sequence;
+ break;
+
+ case SEQ_PROPERTIES:
+
+ if (!lzma_props (s, b->in[b->in_pos++])) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->lzma2.sequence = SEQ_LZMA_PREPARE;
+ /* fall through */
+
+ case SEQ_LZMA_PREPARE:
+
+ if (s->lzma2.compressed < RC_INIT_BYTES) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (!rc_read_init (&s->rc, b)) {
+ return XZ_OK;
+ }
+
+ s->lzma2.compressed -= RC_INIT_BYTES;
+ s->lzma2.sequence = SEQ_LZMA_RUN;
+
+ /* fall through */
+
+ case SEQ_LZMA_RUN:
+
+ /*
+ * Set dictionary limit to indicate how much we want
+ * to be encoded at maximum. Decode new data into the
+ * dictionary. Flush the new data from dictionary to
+ * b->out. Check if we finished decoding this chunk.
+ * In case the dictionary got full but we didn't fill
+ * the output buffer yet, we may run this loop
+ * multiple times without changing s->lzma2.sequence.
+ */
+ dict_limit (&s->dict, MIN (b->out_size - b->out_pos, s->lzma2.uncompressed));
+
+ if (!lzma2_lzma (s, b)) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->lzma2.uncompressed -= dict_flush (&s->dict, b);
+
+ if (s->lzma2.uncompressed == 0) {
+
+ if (s->lzma2.compressed > 0 || s->lzma.len > 0 || !rc_is_finished (&s->rc)) {
+ return XZ_DATA_ERROR;
+ }
+
+ rc_reset (&s->rc);
+ s->lzma2.sequence = SEQ_CONTROL;
+
+ } else if (b->out_pos == b->out_size || (b->in_pos == b->in_size && s->temp.size < s->lzma2.compressed)) {
+ return XZ_OK;
+ }
+
+ break;
+
+ case SEQ_COPY:
+
+ dict_uncompressed (&s->dict, b, &s->lzma2.compressed);
+
+ if (s->lzma2.compressed > 0) {
+ return XZ_OK;
+ }
+
+ s->lzma2.sequence = SEQ_CONTROL;
+ break;
+
+ }
+
+ }
+
+ return XZ_OK;
+
+}
+
+struct xz_dec_lzma2 *xz_dec_lzma2_create (enum xz_mode mode, uint32_t dict_max) {
+
+ struct xz_dec_lzma2 *s;
+
+ if (!(s = malloc (sizeof (*s)))) {
+ return 0;
+ }
+
+ memzero (s, sizeof (*s));
+
+ s->dict.mode = mode;
+ s->dict.size_max = dict_max;
+
+ if (DEC_IS_PREALLOC (mode)) {
+
+ if (!(s->dict.buf = malloc (dict_max))) {
+
+ free (s);
+ return 0;
+
+ }
+
+ memzero (s->dict.buf, sizeof (dict_max));
+
+ } else if (DEC_IS_DYNALLOC (mode)) {
+
+ s->dict.buf = 0;
+ s->dict.allocated = 0;
+
+ }
+
+ return s;
+
+}
+
+enum xz_ret xz_dec_lzma2_reset (struct xz_dec_lzma2 *s, uint8_t props) {
+
+ /* This limits dictionary size to 3 GiB to keep parsing simpler. */
+ if (props > 39) {
+ return XZ_OPTIONS_ERROR;
+ }
+
+ s->dict.size = 2 + (props & 1);
+ s->dict.size <<= (props >> 1) + 11;
+
+ if (DEC_IS_MULTI (s->dict.mode)) {
+
+ if (s->dict.size > s->dict.size_max) {
+ return XZ_MEMLIMIT_ERROR;
+ }
+
+ s->dict.end = s->dict.size;
+
+ if (DEC_IS_DYNALLOC (s->dict.mode)) {
+
+ if (s->dict.allocated < s->dict.size) {
+
+ free (s->dict.buf);
+
+ if (!(s->dict.buf = malloc (s->dict.size))) {
+
+ s->dict.allocated = 0;
+ return XZ_MEM_ERROR;
+
+ }
+
+ memzero (s->dict.buf, sizeof (s->dict.size));
+
+ }
+
+ }
+
+ }
+
+ s->lzma.len = 0;
+
+ s->lzma2.sequence = SEQ_CONTROL;
+ s->lzma2.need_dict_reset = 1;
+
+ s->temp.size = 0;
+ return XZ_OK;
+
+}
+
+void xz_dec_lzma2_end (struct xz_dec_lzma2 *s) {
+
+ if (DEC_IS_MULTI (s->dict.mode)) {
+ free (s->dict.buf);
+ }
+
+ free (s);
+
+}
--- /dev/null
+/******************************************************************************
+ * @file xz_dec_stream.c
+ *****************************************************************************/
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <xz.h>
+
+static uint32_t get_le32 (const uint8_t *buf) {
+ return (uint32_t) buf[0]| ((uint32_t) buf[1] << 8) | ((uint32_t) buf[2] << 16) | ((uint32_t) buf[3] << 24);
+}
+
+#define DEC_IS_SINGLE(mode) ((mode) == XZ_SINGLE)
+
+#ifndef MIN
+# define MIN(x, y) ((x) < (y) ? (x) : (y))
+#endif
+
+/**
+ * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used
+ * before calling xz_dec_lzma2_run().
+ */
+extern struct xz_dec_lzma2 *xz_dec_lzma2_create (enum xz_mode mode, uint32_t dict_max);
+
+/**
+ * Decode the LZMA2 properties (one byte) and reset the decoder. Return
+ * XZ_OK on success, XZ_MEMLIMIT_ERROR if the preallocated dictionary is not
+ * big enough, and XZ_OPTIONS_ERROR if props indicates something that this
+ * decoder doesn't support.
+ */
+extern enum xz_ret xz_dec_lzma2_reset (struct xz_dec_lzma2 *s, uint8_t props);
+
+/* Decode raw LZMA2 stream from b->in to b->out. */
+extern enum xz_ret xz_dec_lzma2_run (struct xz_dec_lzma2 *s, struct xz_buf *b);
+
+/* Free the memory allocated for the LZMA2 decoder. */
+extern void xz_dec_lzma2_end (struct xz_dec_lzma2 *s);
+
+#define memeq(a, b, size) (memcmp (a, b, size) == 0)
+#define memzero(buf, size) memset (buf, 0, size)
+
+/* Hash used to validate the Index field */
+struct xz_dec_hash {
+
+ uint64_t unpadded, uncompressed;
+ uint64_t crc32;
+
+};
+
+/* Integrity Check types */
+enum xz_check {
+
+ XZ_CHECK_NONE = 0,
+ XZ_CHECK_CRC32 = 1,
+ XZ_CHECK_CRC64 = 4,
+ XZ_CHECK_SHA256 = 10
+
+};
+
+struct xz_dec {
+
+ /* Position in dec_main() */
+ enum {
+
+ SEQ_STREAM_HEADER,
+ SEQ_BLOCK_START,
+ SEQ_BLOCK_HEADER,
+ SEQ_BLOCK_UNCOMPRESS,
+ SEQ_BLOCK_PADDING,
+ SEQ_BLOCK_CHECK,
+ SEQ_INDEX,
+ SEQ_INDEX_PADDING,
+ SEQ_INDEX_CRC32,
+ SEQ_STREAM_FOOTER
+
+ } sequence;
+
+ /* Position in variable-length integers and Check fields */
+ uint32_t pos;
+
+ /* Variable-length integer decoded by dec_vli() */
+ uint64_t vli;
+
+ /* Saved in_pos and out_pos */
+ uint64_t in_start;
+ uint64_t out_start;
+
+ /* CRC32 value in Block or Index */
+ uint64_t crc;
+
+ /* Type of the integrity check calculated from uncompressed data */
+ enum xz_check check_type;
+
+ /* Operation mode */
+ enum xz_mode mode;
+
+ /*
+ * True if the next call to xz_dec_run() is allowed to return
+ * XZ_BUF_ERROR.
+ */
+ int allow_buf_error;
+
+ /* Information stored in Block Header */
+ struct {
+
+ /*
+ * Value stored in the Compressed Size field, or
+ * VLI_UNKNOWN if Compressed Size is not present.
+ */
+ uint64_t compressed;
+
+ /*
+ * Value stored in the Uncompressed Size field, or
+ * VLI_UNKNOWN if Uncompressed Size is not present.
+ */
+ uint64_t uncompressed;
+
+ /* Size of the Block Header field */
+ uint32_t size;
+
+ } block_header;
+
+ /* Information collected when decoding Blocks */
+ struct {
+
+ /* Observed compressed size of the current Block */
+ uint64_t compressed;
+
+ /* Observed uncompressed size of the current Block */
+ uint64_t uncompressed;
+
+ /* Number of Blocks decoded so far */
+ uint64_t count;
+
+ /*
+ * Hash calculated from the Block sizes. This is used to
+ * validate the Index field.
+ */
+ struct xz_dec_hash hash;
+
+ } block;
+
+ /* Variables needed when verifying the Index field */
+ struct {
+
+ /* Position in dec_index() */
+ enum {
+
+ SEQ_INDEX_COUNT,
+ SEQ_INDEX_UNPADDED,
+ SEQ_INDEX_UNCOMPRESSED
+
+ } sequence;
+
+ /* Size of the Index in bytes */
+ uint64_t size;
+
+ /* Number of Records (matches block.count in valid files) */
+ uint64_t count;
+
+ /*
+ * Hash calculated from the Records (matches block.hash in
+ * valid files).
+ */
+ struct xz_dec_hash hash;
+
+ } index;
+
+ /*
+ * Temporary buffer needed to hold Stream Header, Block Header,
+ * and Stream Footer. The Block Header is the biggest (1 KiB)
+ * so we reserve space according to that. buf[] has to be aligned
+ * to a multiple of four bytes; the uint64_t variables before it
+ * should guarantee this.
+ */
+ struct {
+
+ uint64_t pos;
+ uint64_t size;
+ uint8_t buf[1024];
+
+ } temp;
+
+ struct xz_dec_lzma2 *lzma2;
+
+#ifdef XZ_DEC_BCJ
+ struct xz_dec_bcj *bcj;
+ bool bcj_active;
+#endif
+
+};
+
+/*
+ * Fill s->temp by copying data starting from b->in[b->in_pos]. Caller
+ * must have set s->temp.pos to indicate how much data we are supposed
+ * to copy into s->temp.buf. Return true once s->temp.pos has reached
+ * s->temp.size.
+ */
+static int fill_temp (struct xz_dec *s, struct xz_buf *b) {
+
+ uint64_t copy_size = MIN (b->in_size - b->in_pos, s->temp.size - s->temp.pos);
+ memcpy (s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size);
+
+ b->in_pos += copy_size;
+ s->temp.pos += copy_size;
+
+ if (s->temp.pos == s->temp.size) {
+
+ s->temp.pos = 0;
+ return 1;
+
+ }
+
+ return 0;
+
+}
+
+#define VLI_BYTES_MAX (sizeof (uint64_t) * 8 / 7)
+
+/* Decode a variable-length integer (little-endian base-128 encoding) */
+static enum xz_ret dec_vli (struct xz_dec *s, const uint8_t *in, uint64_t *in_pos, uint64_t in_size) {
+
+ uint8_t byte;
+
+ if (s->pos == 0) {
+ s->vli = 0;
+ }
+
+ while (*in_pos < in_size) {
+
+ byte = in[*in_pos];
+ ++*in_pos;
+
+ s->vli |= (uint64_t) (byte & 0x7F) << s->pos;
+
+ if ((byte & 0x80) == 0) {
+
+ /* Don't allow non-minimal encodings. */
+ if (byte == 0 && s->pos != 0) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->pos = 0;
+ return XZ_STREAM_END;
+
+ }
+
+ s->pos += 7;
+
+ if (s->pos == 7 * VLI_BYTES_MAX) {
+ return XZ_DATA_ERROR;
+ }
+
+ }
+
+ return XZ_OK;
+
+}
+
+/*
+ * Decode the Compressed Data field from a Block. Update and validate
+ * the observed compressed and uncompressed sizes of the Block so that
+ * they don't exceed the values possibly stored in the Block Header
+ * (validation assumes that no integer overflow occurs, since vli_type
+ * is normally uint64_t). Update the CRC32 if presence of the CRC32
+ * field was indicated in Stream Header.
+ *
+ * Once the decoding is finished, validate that the observed sizes match
+ * the sizes possibly stored in the Block Header. Update the hash and
+ * Block count, which are later used to validate the Index field.
+ */
+static enum xz_ret dec_block (struct xz_dec *s, struct xz_buf *b) {
+
+ enum xz_ret ret;
+
+ s->in_start = b->in_pos;
+ s->out_start = b->out_pos;
+
+ ret = xz_dec_lzma2_run (s->lzma2, b);
+
+ s->block.compressed += b->in_pos - s->in_start;
+ s->block.uncompressed += b->out_pos - s->out_start;
+
+ /*
+ * There is no need to separately check for VLI_UNKNOWN, since
+ * the observed sizes are always smaller than VLI_UNKNOWN.
+ */
+ if (s->block.compressed > s->block_header.compressed || s->block.uncompressed > s->block_header.uncompressed) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (s->check_type == XZ_CHECK_CRC32) {
+ s->crc = xz_crc32 (b->out + s->out_start, b->out_pos - s->out_start, s->crc);
+ } else if (s->check_type == XZ_CHECK_CRC64) {
+ s->crc = xz_crc64 (b->out + s->out_start, b->out_pos - s->out_start, s->crc);
+ }
+
+ if (ret == XZ_STREAM_END) {
+
+ if (s->block_header.compressed != (uint64_t) -1 && s->block_header.compressed != s->block.compressed) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (s->block_header.uncompressed != (uint64_t) -1 && s->block_header.uncompressed != s->block.uncompressed) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->block.hash.unpadded += s->block_header.size + s->block.compressed;
+
+ if (s->check_type == XZ_CHECK_CRC32) {
+ s->block.hash.unpadded += 4;
+ } else if (s->check_type == XZ_CHECK_CRC64) {
+ s->block.hash.unpadded += 8;
+ }
+
+ s->block.hash.uncompressed += s->block.uncompressed;
+ s->block.hash.crc32 = xz_crc32 ((const uint8_t *) &s->block.hash, sizeof (s->block.hash), s->block.hash.crc32);
+
+ ++s->block.count;
+
+ }
+
+ return ret;
+
+}
+
+/* Update the Index size and the CRC32 value. */
+static void index_update (struct xz_dec *s, const struct xz_buf *b) {
+
+ uint64_t in_used = b->in_pos - s->in_start;
+ s->index.size += in_used;
+
+ s->crc = xz_crc32 (b->in + s->in_start, in_used, s->crc);
+
+}
+
+/*
+ * Decode the Number of Records, Unpadded Size, and Uncompressed Size
+ * fields from the Index field. That is, Index Padding and CRC32 are not
+ * decoded by this function.
+ *
+ * This can return XZ_OK (more input needed), XZ_STREAM_END (everything
+ * successfully decoded), or XZ_DATA_ERROR (input is corrupt).
+ */
+static enum xz_ret dec_index (struct xz_dec *s, struct xz_buf *b) {
+
+ enum xz_ret ret;
+
+ do {
+
+ ret = dec_vli (s, b->in, &b->in_pos, b->in_size);
+
+ if (ret != XZ_STREAM_END) {
+
+ index_update (s, b);
+ return ret;
+
+ }
+
+ switch (s->index.sequence) {
+
+ case SEQ_INDEX_COUNT:
+
+ s->index.count = s->vli;
+
+ /*
+ * Validate that the Number of Records field
+ * indicates the same number of Records as
+ * there were Blocks in the Stream.
+ */
+ if (s->index.count != s->block.count) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->index.sequence = SEQ_INDEX_UNPADDED;
+ break;
+
+ case SEQ_INDEX_UNPADDED:
+
+ s->index.hash.unpadded += s->vli;
+ s->index.sequence = SEQ_INDEX_UNCOMPRESSED;
+ break;
+
+ case SEQ_INDEX_UNCOMPRESSED:
+
+ s->index.hash.uncompressed += s->vli;
+ s->index.hash.crc32 = xz_crc32 ((const uint8_t *)&s->index.hash, sizeof(s->index.hash), s->index.hash.crc32);
+
+ --s->index.count;
+
+ s->index.sequence = SEQ_INDEX_UNPADDED;
+ break;
+
+ }
+
+ } while (s->index.count > 0);
+
+ return XZ_STREAM_END;
+
+}
+
+/*
+ * Validate that the next four input bytes match the value of s->crc32.
+ * s->pos must be zero when starting to validate the first byte.
+ */
+static enum xz_ret crc_validate (struct xz_dec *s, struct xz_buf *b, uint32_t bits) {
+
+ do {
+
+ if (b->in_pos == b->in_size) {
+ return XZ_OK;
+ }
+
+ if (((s->crc >> s->pos) & 0xFF) != b->in[b->in_pos++]) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->pos += 8;
+
+ } while (s->pos < bits);
+
+ s->crc = 0;
+ s->pos = 0;
+
+ return XZ_STREAM_END;
+
+}
+
+#define HEADER_MAGIC "\3757zXZ"
+#define HEADER_MAGIC_SIZE 6
+
+/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */
+static enum xz_ret dec_stream_header (struct xz_dec *s) {
+
+ if (!memeq (s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE)) {
+ return XZ_FORMAT_ERROR;
+ }
+
+ if (xz_crc32 (s->temp.buf + HEADER_MAGIC_SIZE, 2, 0) != get_le32 (s->temp.buf + HEADER_MAGIC_SIZE + 2)) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (s->temp.buf[HEADER_MAGIC_SIZE] != 0) {
+ return XZ_OPTIONS_ERROR;
+ }
+
+ /**
+ * * Of integrity checks, we support only none (Check ID = 0) and
+ * CRC32 (Check ID = 1). However, if XZ_DEC_ANY_CHECK is defined,
+ * we will accept other check types too, but then the check won't
+ * be verified and a warning (XZ_UNSUPPORTED_CHECK) will be given.
+ * Of integrity checks, we support none (Check ID = 0),
+ * CRC32 (Check ID = 1), and optionally CRC64 (Check ID = 4).
+ * However, if XZ_DEC_ANY_CHECK is defined, we will accept other
+ * check types too, but then the check won't be verified and
+ * a warning (XZ_UNSUPPORTED_CHECK) will be given.
+ */
+ s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1];
+
+ if (s->check_type > XZ_CHECK_CRC32 && s->check_type != XZ_CHECK_CRC64) {
+ return XZ_OPTIONS_ERROR;
+ }
+
+ return XZ_OK;
+
+}
+
+#define FOOTER_MAGIC "YZ"
+#define FOOTER_MAGIC_SIZE 2
+
+/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */
+static enum xz_ret dec_stream_footer (struct xz_dec *s) {
+
+ if (!memeq (s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE)) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (xz_crc32 (s->temp.buf + 4, 6, 0) != get_le32 (s->temp.buf)) {
+ return XZ_DATA_ERROR;
+ }
+
+ /*
+ * Validate Backward Size. Note that we never added the size of the
+ * Index CRC32 field to s->index.size, thus we use s->index.size / 4
+ * instead of s->index.size / 4 - 1.
+ */
+ if ((s->index.size >> 2) != get_le32 (s->temp.buf + 4)) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (s->temp.buf[8] != 0 || s->temp.buf[9] != s->check_type) {
+ return XZ_DATA_ERROR;
+ }
+
+ /*
+ * Use XZ_STREAM_END instead of XZ_OK to be more convenient
+ * for the caller.
+ */
+ return XZ_STREAM_END;
+
+}
+
+/* Decode the Block Header and initialize the filter chain. */
+static enum xz_ret dec_block_header (struct xz_dec *s)
+{
+
+ enum xz_ret ret;
+
+ /*
+ * Validate the CRC32. We know that the temp buffer is at least
+ * eight bytes so this is safe.
+ */
+ s->temp.size -= 4;
+
+ if (xz_crc32 (s->temp.buf, s->temp.size, 0) != get_le32 (s->temp.buf + s->temp.size)) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->temp.pos = 2;
+
+ /*
+ * Catch unsupported Block Flags. We support only one or two filters
+ * in the chain, so we catch that with the same test.
+ */
+#ifdef XZ_DEC_BCJ
+ if (s->temp.buf[1] & 0x3E)
+#else
+ if (s->temp.buf[1] & 0x3F)
+#endif
+ return XZ_OPTIONS_ERROR;
+
+ /* Compressed Size */
+ if (s->temp.buf[1] & 0x40) {
+
+ if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) != XZ_STREAM_END) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->block_header.compressed = s->vli;
+
+ } else {
+ s->block_header.compressed = (uint64_t) -1;
+ }
+
+ /* Uncompressed Size */
+ if (s->temp.buf[1] & 0x80) {
+
+ if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) != XZ_STREAM_END) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->block_header.uncompressed = s->vli;
+
+ } else {
+ s->block_header.uncompressed = (uint64_t) -1;
+ }
+
+#ifdef XZ_DEC_BCJ
+ /* If there are two filters, the first one must be a BCJ filter. */
+ s->bcj_active = s->temp.buf[1] & 0x01;
+ if (s->bcj_active) {
+ if (s->temp.size - s->temp.pos < 2)
+ return XZ_OPTIONS_ERROR;
+
+ ret = xz_dec_bcj_reset(s->bcj, s->temp.buf[s->temp.pos++]);
+ if (ret != XZ_OK)
+ return ret;
+
+ /*
+ * We don't support custom start offset,
+ * so Size of Properties must be zero.
+ */
+ if (s->temp.buf[s->temp.pos++] != 0x00)
+ return XZ_OPTIONS_ERROR;
+ }
+#endif
+
+ /* Valid Filter Flags always take at least two bytes. */
+ if (s->temp.size - s->temp.pos < 2) {
+ return XZ_DATA_ERROR;
+ }
+
+ /* Filter ID = LZMA2 */
+ if (s->temp.buf[s->temp.pos++] != 0x21) {
+ return XZ_OPTIONS_ERROR;
+ }
+
+ /* Size of Properties = 1-byte Filter Properties */
+ if (s->temp.buf[s->temp.pos++] != 0x01) {
+ return XZ_OPTIONS_ERROR;
+ }
+
+ /* Filter Properties contains LZMA2 dictionary size. */
+ if (s->temp.size - s->temp.pos < 1) {
+ return XZ_DATA_ERROR;
+ }
+
+ ret = xz_dec_lzma2_reset (s->lzma2, s->temp.buf[s->temp.pos++]);
+
+ if (ret != XZ_OK) {
+ return ret;
+ }
+
+ /* The rest must be Header Padding. */
+ while (s->temp.pos < s->temp.size) {
+
+ if (s->temp.buf[s->temp.pos++] != 0x00) {
+ return XZ_OPTIONS_ERROR;
+ }
+
+ }
+
+ s->temp.pos = 0;
+
+ s->block.compressed = 0;
+ s->block.uncompressed = 0;
+
+ return XZ_OK;
+
+}
+
+#define STREAM_HEADER_SIZE 12
+
+static enum xz_ret dec_main (struct xz_dec *s, struct xz_buf *b) {
+
+ enum xz_ret ret;
+
+ /*
+ * Store the start position for the case when we are in the middle
+ * of the Index field.
+ */
+ s->in_start = b->in_pos;
+
+ for (;;) {
+
+ switch (s->sequence) {
+
+ case SEQ_STREAM_HEADER:
+
+ /*
+ * Stream Header is copied to s->temp, and then
+ * decoded from there. This way if the caller
+ * gives us only little input at a time, we can
+ * still keep the Stream Header decoding code
+ * simple. Similar approach is used in many places
+ * in this file.
+ */
+ if (!fill_temp (s, b)) {
+ return XZ_OK;
+ }
+
+ /*
+ * If dec_stream_header() returns
+ * XZ_UNSUPPORTED_CHECK, it is still possible
+ * to continue decoding if working in multi-call
+ * mode. Thus, update s->sequence before calling
+ * dec_stream_header().
+ */
+ s->sequence = SEQ_BLOCK_START;
+
+ ret = dec_stream_header (s);
+
+ if (ret != XZ_OK) {
+ return ret;
+ }
+
+ /* fall through */
+
+ case SEQ_BLOCK_START:
+
+ /* We need one byte of input to continue. */
+ if (b->in_pos == b->in_size) {
+ return XZ_OK;
+ }
+
+ /* See if this is the beginning of the Index field. */
+ if (b->in[b->in_pos] == 0) {
+
+ s->in_start = b->in_pos++;
+ s->sequence = SEQ_INDEX;
+
+ break;
+
+ }
+
+ /*
+ * Calculate the size of the Block Header and
+ * prepare to decode it.
+ */
+ s->block_header.size = ((uint32_t) b->in[b->in_pos] + 1) * 4;
+
+ s->temp.size = s->block_header.size;
+ s->temp.pos = 0;
+ s->sequence = SEQ_BLOCK_HEADER;
+
+ /* fall through */
+
+ case SEQ_BLOCK_HEADER:
+
+ if (!fill_temp (s, b)) {
+ return XZ_OK;
+ }
+
+ ret = dec_block_header (s);
+
+ if (ret != XZ_OK) {
+ return ret;
+ }
+
+ s->sequence = SEQ_BLOCK_UNCOMPRESS;
+ /* fall through */
+
+ case SEQ_BLOCK_UNCOMPRESS:
+
+ ret = dec_block (s, b);
+
+ if (ret != XZ_STREAM_END) {
+ return ret;
+ }
+
+ s->sequence = SEQ_BLOCK_PADDING;
+ /* fall through */
+
+ case SEQ_BLOCK_PADDING:
+
+ /*
+ * Size of Compressed Data + Block Padding
+ * must be a multiple of four. We don't need
+ * s->block.compressed for anything else
+ * anymore, so we use it here to test the size
+ * of the Block Padding field.
+ */
+ while (s->block.compressed & 3) {
+
+ if (b->in_pos == b->in_size) {
+ return XZ_OK;
+ }
+
+ if (b->in[b->in_pos++] != 0) {
+ return XZ_DATA_ERROR;
+ }
+
+ ++s->block.compressed;
+
+ }
+
+ s->sequence = SEQ_BLOCK_CHECK;
+ /* fall through */
+
+ case SEQ_BLOCK_CHECK:
+
+ if (s->check_type == XZ_CHECK_CRC32) {
+
+ ret = crc_validate (s, b, 32);
+
+ if (ret != XZ_STREAM_END) {
+ return ret;
+ }
+
+ } else if (s->check_type == XZ_CHECK_CRC64) {
+
+ ret = crc_validate (s, b, 64);
+
+ if (ret != XZ_STREAM_END) {
+ return ret;
+ }
+
+ }
+
+#ifdef XZ_DEC_ANY_CHECK
+ else if (!check_skip(s, b)) {
+ return XZ_OK;
+ }
+#endif
+
+ s->sequence = SEQ_BLOCK_START;
+ break;
+
+ case SEQ_INDEX:
+
+ ret = dec_index (s, b);
+
+ if (ret != XZ_STREAM_END) {
+ return ret;
+ }
+
+ s->sequence = SEQ_INDEX_PADDING;
+ /* fall through */
+
+ case SEQ_INDEX_PADDING:
+
+ while ((s->index.size + (b->in_pos - s->in_start)) & 3) {
+
+ if (b->in_pos == b->in_size) {
+
+ index_update (s, b);
+ return XZ_OK;
+
+ }
+
+ if (b->in[b->in_pos++] != 0) {
+ return XZ_DATA_ERROR;
+ }
+
+ }
+
+ /* Finish the CRC32 value and Index size. */
+ index_update (s, b);
+
+ /* Compare the hashes to validate the Index field. */
+ if (!memeq (&s->block.hash, &s->index.hash, sizeof(s->block.hash))) {
+ return XZ_DATA_ERROR;
+ }
+
+ s->sequence = SEQ_INDEX_CRC32;
+ /* fall through */
+
+ case SEQ_INDEX_CRC32:
+
+ ret = crc_validate (s, b, 32);
+
+ if (ret != XZ_STREAM_END) {
+ return ret;
+ }
+
+ s->temp.size = STREAM_HEADER_SIZE;
+ s->sequence = SEQ_STREAM_FOOTER;
+
+ /* fall through */
+
+ case SEQ_STREAM_FOOTER:
+
+ if (!fill_temp (s, b)) {
+ return XZ_OK;
+ }
+
+ return dec_stream_footer (s);
+
+ }
+
+ }
+
+ /* Never reached */
+
+}
+
+/*
+ * xz_dec_run() is a wrapper for dec_main() to handle some special cases in
+ * multi-call and single-call decoding.
+ *
+ * In multi-call mode, we must return XZ_BUF_ERROR when it seems clear that we
+ * are not going to make any progress anymore. This is to prevent the caller
+ * from calling us infinitely when the input file is truncated or otherwise
+ * corrupt. Since zlib-style API allows that the caller fills the input buffer
+ * only when the decoder doesn't produce any new output, we have to be careful
+ * to avoid returning XZ_BUF_ERROR too easily: XZ_BUF_ERROR is returned only
+ * after the second consecutive call to xz_dec_run() that makes no progress.
+ *
+ * In single-call mode, if we couldn't decode everything and no error
+ * occurred, either the input is truncated or the output buffer is too small.
+ * Since we know that the last input byte never produces any output, we know
+ * that if all the input was consumed and decoding wasn't finished, the file
+ * must be corrupt. Otherwise the output buffer has to be too small or the
+ * file is corrupt in a way that decoding it produces too big output.
+ *
+ * If single-call decoding fails, we reset b->in_pos and b->out_pos back to
+ * their original values. This is because with some filter chains there won't
+ * be any valid uncompressed data in the output buffer unless the decoding
+ * actually succeeds (that's the price to pay of using the output buffer as
+ * the workspace).
+ */
+enum xz_ret xz_dec_run (struct xz_dec *s, struct xz_buf *b) {
+
+ uint64_t in_start;
+ uint64_t out_start;
+
+ enum xz_ret ret;
+
+ if (DEC_IS_SINGLE (s->mode)) {
+ xz_dec_reset (s);
+ }
+
+ in_start = b->in_pos;
+ out_start = b->out_pos;
+
+ ret = dec_main (s, b);
+
+ if (DEC_IS_SINGLE (s->mode)) {
+
+ if (ret == XZ_OK) {
+ ret = b->in_pos == b->in_size ? XZ_DATA_ERROR : XZ_BUF_ERROR;
+ }
+
+ if (ret != XZ_STREAM_END) {
+
+ b->in_pos = in_start;
+ b->out_pos = out_start;
+
+ }
+
+ } else if (ret == XZ_OK && in_start == b->in_pos && out_start == b->out_pos) {
+
+ if (s->allow_buf_error) {
+ ret = XZ_BUF_ERROR;
+ }
+
+ s->allow_buf_error = 1;
+
+ } else {
+ s->allow_buf_error = 0;
+ }
+
+ return ret;
+
+}
+
+struct xz_dec *xz_dec_init (enum xz_mode mode, uint32_t dict_max) {
+
+ struct xz_dec *s;
+
+ if (!(s = malloc (sizeof (*s)))) {
+ return 0;
+ }
+
+ memzero (s, sizeof (*s));
+ s->mode = mode;
+
+#ifdef XZ_DEC_BCJ
+ s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode));
+ if (s->bcj == NULL)
+ goto error_bcj;
+#endif
+
+ if (!(s->lzma2 = xz_dec_lzma2_create (mode, dict_max))) {
+ goto error_lzma2;
+ }
+
+ xz_dec_reset (s);
+ return s;
+
+error_lzma2:
+
+#ifdef XZ_DEC_BCJ
+ xz_dec_bcj_end(s->bcj);
+ error_bcj:
+#endif
+
+ free (s);
+ return 0;
+
+}
+
+void xz_dec_reset (struct xz_dec *s) {
+
+ s->sequence = SEQ_STREAM_HEADER;
+ s->allow_buf_error = 0;
+
+ s->pos = 0;
+ s->crc = 0;
+
+ memzero (&s->block, sizeof (s->block));
+ memzero (&s->index, sizeof (s->index));
+
+ s->temp.pos = 0;
+ s->temp.size = STREAM_HEADER_SIZE;
+
+}
+
+void xz_dec_end (struct xz_dec *s) {
+
+ if (s) {
+
+ xz_dec_lzma2_end (s->lzma2);
+#ifdef XZ_DEC_BCJ
+ xz_dec_bcj_end (s->bcj);
+#endif
+
+ free (s);
+
+ }
+
+}
--- /dev/null
+/******************************************************************************
+ * @file report.c
+ *****************************************************************************/
+#include <stdarg.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "report.h"
+
+unsigned long errors = 0;
+
+#ifndef __PDOS__
+#if defined (_WIN32)
+# include <windows.h>
+static int OriginalConsoleColor = -1;
+#endif
+
+static void reset_console_color (void) {
+
+#if defined (_WIN32)
+
+ HANDLE hStdError = GetStdHandle (STD_ERROR_HANDLE);
+
+ if (OriginalConsoleColor == -1) { return; }
+
+ SetConsoleTextAttribute (hStdError, OriginalConsoleColor);
+ OriginalConsoleColor = -1;
+
+#else
+
+ fprintf (stderr, "\033[0m");
+
+#endif
+
+}
+
+static void set_console_color (int color) {
+
+#if defined (_WIN32)
+
+ HANDLE hStdError = GetStdHandle (STD_ERROR_HANDLE);
+ WORD wColor;
+
+ if (OriginalConsoleColor == -1) {
+
+ CONSOLE_SCREEN_BUFFER_INFO csbi;
+
+ if (!GetConsoleScreenBufferInfo (hStdError, &csbi)) {
+ return;
+ }
+
+ OriginalConsoleColor = csbi.wAttributes;
+
+ }
+
+ wColor = (OriginalConsoleColor & 0xF0) + (color & 0xF);
+ SetConsoleTextAttribute (hStdError, wColor);
+
+#else
+
+ fprintf (stderr, "\033[%dm", color);
+
+#endif
+
+}
+#endif
+
+static void output_message (const char *filename, unsigned long lineno, unsigned long idx, enum report_type type, const char *fmt, va_list ap) {
+
+ if (filename) {
+
+ if (lineno == 0 && idx == 0) {
+ fprintf (stderr, "%s: ", filename);
+ } else {
+ fprintf (stderr, "%s:", filename);
+ }
+
+ }
+
+ if (lineno > 0) {
+
+ if (idx == 0) {
+ fprintf (stderr, "%lu: ", lineno);
+ } else {
+ fprintf (stderr, "%lu:", lineno);
+ }
+
+ }
+
+ if (idx > 0) {
+ fprintf (stderr, "%lu: ", idx);
+ }
+
+ if (type == REPORT_ERROR || type == REPORT_FATAL_ERROR) {
+
+#ifndef __PDOS__
+ set_console_color (COLOR_ERROR);
+#endif
+
+ if (type == REPORT_ERROR) {
+ fprintf (stderr, "error:");
+ } else {
+ fprintf (stderr, "fatal error:");
+ }
+
+ } else if (type == REPORT_INTERNAL_ERROR) {
+
+#ifndef __PDOS__
+ set_console_color (COLOR_INTERNAL_ERROR);
+#endif
+
+ fprintf (stderr, "internal error:");
+
+ } else if (type == REPORT_WARNING) {
+
+#ifndef __PDOS__
+ set_console_color (COLOR_WARNING);
+#endif
+
+ fprintf (stderr, "warning:");
+
+ }
+
+#ifndef __PDOS__
+ reset_console_color ();
+#endif
+
+ fprintf (stderr, " ");
+ vfprintf (stderr, fmt, ap);
+ fprintf (stderr, "\n");
+
+ if (type != REPORT_WARNING) {
+ ++errors;
+ }
+
+}
+
+unsigned long get_error_count (void) {
+ return errors;
+}
+
+void report_at (const char *filename, unsigned long lineno, enum report_type type, const char *fmt, ...) {
+
+ va_list ap;
+
+ va_start (ap, fmt);
+ output_message (filename, lineno, 0, type, fmt, ap);
+ va_end (ap);
+
+}
--- /dev/null
+/******************************************************************************
+ * @file report.h
+ *****************************************************************************/
+#ifndef _REPORT_H
+#define _REPORT_H
+
+enum report_type {
+
+ REPORT_ERROR = 0,
+ REPORT_FATAL_ERROR,
+ REPORT_INTERNAL_ERROR,
+ REPORT_WARNING
+
+};
+
+#if defined (_WIN32)
+# define COLOR_ERROR 12
+# define COLOR_WARNING 13
+# define COLOR_INTERNAL_ERROR 19
+#else
+# define COLOR_ERROR 91
+# define COLOR_INTERNAL_ERROR 94
+# define COLOR_WARNING 95
+#endif
+
+unsigned long get_error_count (void);
+void report_at (const char *filename, unsigned long line_number, enum report_type type, const char *fmt, ...);
+
+#endif /* _REPORT_H */
--- /dev/null
+/******************************************************************************
+ * @file unxz.c
+ *****************************************************************************/
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <xz.h>
+#include "lib.h"
+#include "report.h"
+#include "unxz.h"
+
+#define XZ_IOBUF_SIZE 4096
+
+struct unxz_state *state = 0;
+const char *program_name = 0;
+
+int main (int argc, char **argv) {
+
+ struct xz_buf b = { 0 };
+ struct xz_dec *s;
+
+ enum xz_ret ret;
+ int i;
+
+ FILE *ifp, *ofp;
+
+ const char *ipath;
+ char *opath = 0, *p;
+
+ if (argc && *argv) {
+
+ program_name = *argv;
+
+ if ((p = strrchr (program_name, '/')) || (p == strrchr (program_name, '\\'))) {
+ program_name = (p + 1);
+ }
+
+ }
+
+ state = xmalloc (sizeof (*state));
+ parse_args (argc, argv, 1);
+
+ if (state->nb_files == 0) {
+
+ report_at (program_name, 0, REPORT_ERROR, "no input files provided");
+ return EXIT_FAILURE;
+
+ }
+
+ xz_crc32_init ();
+ xz_crc64_init ();
+
+ if (!(s = xz_dec_init (XZ_DYNALLOC, (uint32_t) -1))) {
+ return -1;
+ }
+
+ b.out_size = XZ_IOBUF_SIZE;
+
+ if (!(b.out = malloc (b.out_size))) {
+ return -1;
+ }
+
+ if (!(b.in = malloc (XZ_IOBUF_SIZE))) {
+ return -1;
+ }
+
+ for (i = 0; i < state->nb_files; i++) {
+
+ b.out_pos = 0;
+
+ b.in_pos = 0;
+ b.in_size = 0;
+
+ ipath = state->files[i];
+
+ if (!(ifp = fopen (ipath, "r+b"))) {
+
+ report_at (program_name, 0, REPORT_ERROR, "failed to open '%s' for reading", ipath);
+ continue;
+
+ }
+
+ if ((p = strrchr (ipath, '.'))) {
+
+ if (strcmp (p, ".xz")) {
+
+ report_at (program_name, 0, REPORT_ERROR, "skipping %s", ipath);
+
+ fclose (ifp);
+ continue;
+
+ }
+
+ opath = xstrndup (ipath, p - ipath);
+
+ }
+
+ if (!(ofp = fopen (opath, "w+b"))) {
+
+ report_at (program_name, 0, REPORT_ERROR, "failed to open '%s' for writing", opath);
+ free (opath);
+
+ fclose (ifp);
+ continue;
+
+ }
+
+ do {
+
+ if (b.in_pos == b.in_size) {
+
+ b.in_size = fread (b.in, 1, XZ_IOBUF_SIZE, ifp);
+ b.in_pos = 0;
+
+ }
+
+ ret = xz_dec_run (s, &b);
+
+ if (b.out_pos == b.out_size || (ret != XZ_OK && b.out_pos > 0)) {
+
+ if (fwrite (b.out, 1, b.out_pos, ofp) != (uint64_t) b.out_pos) {
+ ret = XZ_BUF_ERROR;
+ }
+
+ b.out_pos = 0;
+
+ }
+
+ } while (ret == XZ_OK);
+
+ switch (ret) {
+
+ case XZ_STREAM_END:
+
+ break;
+
+ case XZ_MEM_ERROR:
+
+ /* This can occur only in multi-call mode. */
+ report_at (program_name, 0, REPORT_ERROR, "XZ decompressor ran out of memory\n");
+ break;
+
+ case XZ_FORMAT_ERROR:
+
+ report_at (program_name, 0, REPORT_ERROR, "Input is not in the XZ format (wrong magic bytes)\n");
+ break;
+
+ case XZ_OPTIONS_ERROR:
+
+ report_at (program_name, 0, REPORT_ERROR, "Input was encoded with settings that are not supported by this XZ decoder\n");
+ break;
+
+ case XZ_DATA_ERROR: case XZ_BUF_ERROR:
+
+ report_at (program_name, 0, REPORT_ERROR, "XZ-compressed data is corrupt\n");
+ break;
+
+ default:
+
+ report_at (program_name, 0, REPORT_INTERNAL_ERROR, "Bug in the XZ decompressor\n");
+ break;
+
+ }
+
+ fclose (ifp);
+ fclose (ofp);
+
+ free (opath);
+
+ }
+
+ xz_dec_end (s);
+ free (b.in);
+
+ return (get_error_count () ? EXIT_FAILURE : EXIT_SUCCESS);
+
+}
--- /dev/null
+/******************************************************************************
+ * @file unxz.h
+ *****************************************************************************/
+#ifndef _UNXZ_H
+#define _UNXZ_H
+
+struct unxz_state {
+
+ const char **files;
+ long nb_files;
+
+};
+
+extern struct unxz_state *state;
+extern const char *program_name;
+
+#endif /* _UNXZ_H */
projects / unxz.git / commitdiff