xzless: Rename unused variables to silence static analysers.

In this particular case I don't see this affecting readability
of the code.

Thanks to Pavel Raiskup.

INSTALL

@@ -400,12 +400,6 @@ XZ Utils Installation
                                 one thread, something bad may happen.
 
     --enable-sandbox=METHOD
-                This feature is EXPERIMENTAL in the XZ Utils 5.2.x and
-                disabled by default. If you test this, look especially
-                if message translations and locale-specific decimal and
-                thousand separators (e.g. xz --list foo.xz) work the
-                same way as they do without sandboxing.
-
                 There is limited sandboxing support in the xz tool. If
                 built with sandbox support, it's used automatically when
                 (de)compressing exactly one file to standard output and
@@ -419,6 +413,7 @@ XZ Utils Installation
                         auto    Look for a supported sandboxing method
                                 and use it if found. If no method is
                                 found, then sandboxing isn't used.
+                                This is the default.
 
                         no      Disable sandboxing support.
 

NEWS

@@ -2,6 +2,17 @@
 XZ Utils Release Notes
 ======================
 
+5.3.1alpha (2018-04-29)
+
+    * All fixes from 5.2.4.
+
+    * Add lzma_file_info_decoder() into liblzma and use it in xz to
+      implement the --list feature.
+
+    * Capsicum sandbox support is enabled by default where available
+      (FreeBSD >= 10).
+
+
 5.2.4 (2018-04-29)
 
     * liblzma:

THANKS

@@ -103,6 +103,7 @@ has been important. :-) In alphabetical order:
   - Paul Townsend
   - Mohammed Adnène Trojette
   - Alexey Tourbin
+  - Loganaden Velvindron
   - Patrick J. Volkerding
   - Martin Väth
   - Adam Walling

configure.ac

@@ -498,10 +498,10 @@ AM_CONDITIONAL([COND_SYMVERS], [test "x$enable_symbol_versions" = xyes])
 
 AC_MSG_CHECKING([if sandboxing should be used])
 AC_ARG_ENABLE([sandbox], [AS_HELP_STRING([--enable-sandbox=METHOD],
-		[This is an experimental feature.
-		Sandboxing METHOD can be `auto', `no', or `capsicum'.
-		The default is `no'.])],
-	[], [enable_sandbox=no])
+		[Sandboxing METHOD can be `auto', `no', or `capsicum'.
+		The default is `auto' which enables sandboxing if
+		a supported sandboxing method is found.])],
+	[], [enable_sandbox=auto])
 case $enable_sandbox in
 	auto)
 		AC_MSG_RESULT([maybe (autodetect)])

doc/examples/11_file_info.c

@@ -0,0 +1,206 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       11_file_info.c
+/// \brief      Get uncmopressed size of .xz file(s)
+///
+/// Usage:      ./11_file_info INFILE1.xz [INFILEn.xz]...
+///
+/// Example:    ./11_file_info foo.xz
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include <stdbool.h>
+#include <inttypes.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <lzma.h>
+
+
+static bool
+print_file_size(lzma_stream *strm, FILE *infile, const char *filename)
+{
+	// Get the file size. In standard C it can be done by seeking to
+	// the end of the file and then getting the file position.
+	// In POSIX one can use fstat() and then st_size from struct stat.
+	// Also note that fseek() and ftell() use long and thus don't support
+	// large files on 32-bit systems (POSIX versions fseeko() and
+	// ftello() can support large files).
+	if (fseek(infile, 0, SEEK_END)) {
+		fprintf(stderr, "Error seeking the file `%s': %s\n",
+				filename, strerror(errno));
+		return false;
+	}
+
+	const long file_size = ftell(infile);
+
+	// The decoder wants to start from the beginning of the .xz file.
+	rewind(infile);
+
+	// Initialize the decoder.
+	lzma_index *i;
+	lzma_ret ret = lzma_file_info_decoder(strm, &i, UINT64_MAX,
+			(uint64_t)file_size);
+	switch (ret) {
+	case LZMA_OK:
+		// Initialization succeeded.
+		break;
+
+	case LZMA_MEM_ERROR:
+		fprintf(stderr, "Out of memory when initializing "
+				"the .xz file info decoder\n");
+		return false;
+
+	case LZMA_PROG_ERROR:
+	default:
+		fprintf(stderr, "Unknown error, possibly a bug\n");
+		return false;
+	}
+
+	// This example program reuses the same lzma_stream structure
+	// for multiple files, so we need to reset this when starting
+	// a new file.
+	strm->avail_in = 0;
+
+	// Buffer for input data.
+	uint8_t inbuf[BUFSIZ];
+
+	// Pass data to the decoder and seek when needed.
+	while (true) {
+		if (strm->avail_in == 0) {
+			strm->next_in = inbuf;
+			strm->avail_in = fread(inbuf, 1, sizeof(inbuf),
+					infile);
+
+			if (ferror(infile)) {
+				fprintf(stderr,
+					"Error reading from `%s': %s\n",
+					filename, strerror(errno));
+				return false;
+			}
+
+			// We don't need to care about hitting the end of
+			// the file so no need to check for feof().
+		}
+
+		ret = lzma_code(strm, LZMA_RUN);
+
+		switch (ret) {
+		case LZMA_OK:
+			break;
+
+		case LZMA_SEEK_NEEDED:
+			// The cast is safe because liblzma won't ask us to
+			// seek past the known size of the input file which
+			// did fit into a long.
+			//
+			// NOTE: Remember to change these to off_t if you
+			// switch fseeko() or lseek().
+			if (fseek(infile, (long)(strm->seek_pos), SEEK_SET)) {
+				fprintf(stderr, "Error seeking the "
+						"file `%s': %s\n",
+						filename, strerror(errno));
+				return false;
+			}
+
+			// The old data in the inbuf is useless now. Set
+			// avail_in to zero so that we will read new input
+			// from the new file position on the next iteration
+			// of this loop.
+			strm->avail_in = 0;
+			break;
+
+		case LZMA_STREAM_END:
+			// File information was successfully decoded.
+			// See <lzma/index.h> for functions that can be
+			// used on it. In this example we just print
+			// the uncompressed size (in bytes) of
+			// the .xz file followed by its file name.
+			printf("%10" PRIu64 " %s\n",
+					lzma_index_uncompressed_size(i),
+					filename);
+
+			// Free the memory of the lzma_index structure.
+			lzma_index_end(i, NULL);
+
+			return true;
+
+		case LZMA_FORMAT_ERROR:
+			// .xz magic bytes weren't found.
+			fprintf(stderr, "The file `%s' is not "
+					"in the .xz format\n", filename);
+			return false;
+
+		case LZMA_OPTIONS_ERROR:
+			fprintf(stderr, "The file `%s' has .xz headers that "
+					"are not supported by this liblzma "
+					"version\n", filename);
+			return false;
+
+		case LZMA_DATA_ERROR:
+			fprintf(stderr, "The file `%s' is corrupt\n",
+					filename);
+			return false;
+
+		case LZMA_MEM_ERROR:
+			fprintf(stderr, "Memory allocation failed when "
+					"decoding the file `%s'\n", filename);
+			return false;
+
+		// LZMA_MEMLIMIT_ERROR shouldn't happen because we used
+		// UINT64_MAX as the limit.
+		//
+		// LZMA_BUF_ERROR shouldn't happen because we always provide
+		// new input when the input buffer is empty. The decoder
+		// knows the input file size and thus won't try to read past
+		// the end of the file.
+		case LZMA_MEMLIMIT_ERROR:
+		case LZMA_BUF_ERROR:
+		case LZMA_PROG_ERROR:
+		default:
+			fprintf(stderr, "Unknown error, possibly a bug\n");
+			return false;
+		}
+	}
+
+	// This line is never reached.
+}
+
+
+extern int
+main(int argc, char **argv)
+{
+	bool success = true;
+	lzma_stream strm = LZMA_STREAM_INIT;
+
+	for (int i = 1; i < argc; ++i) {
+		FILE *infile = fopen(argv[i], "rb");
+
+		if (infile == NULL) {
+			fprintf(stderr, "Cannot open the file `%s': %s\n",
+					argv[i], strerror(errno));
+			success = false;
+		}
+
+		success &= print_file_size(&strm, infile, argv[i]);
+
+		(void)fclose(infile);
+	}
+
+	lzma_end(&strm);
+
+	// Close stdout to catch possible write errors that can occur
+	// when pending data is flushed from the stdio buffers.
+	if (fclose(stdout)) {
+		fprintf(stderr, "Write error: %s\n", strerror(errno));
+		success = false;
+	}
+
+	return success ? EXIT_SUCCESS : EXIT_FAILURE;
+}

doc/examples/Makefile

@@ -13,7 +13,8 @@ PROGS = \
 	01_compress_easy \
 	02_decompress \
 	03_compress_custom \
-	04_compress_easy_mt
+	04_compress_easy_mt \
+	11_file_info
 
 all: $(PROGS)
 

dos/Makefile

@@ -64,6 +64,7 @@ SRCS_C = \
 	../src/liblzma/common/block_header_encoder.c \
 	../src/liblzma/common/block_util.c \
 	../src/liblzma/common/common.c \
+	../src/liblzma/common/file_info.c \
 	../src/liblzma/common/filter_common.c \
 	../src/liblzma/common/filter_decoder.c \
 	../src/liblzma/common/filter_encoder.c \

src/liblzma/Makefile.am

@@ -24,7 +24,7 @@ liblzma_la_CPPFLAGS = \
 	-I$(top_srcdir)/src/liblzma/simple \
 	-I$(top_srcdir)/src/common \
 	-DTUKLIB_SYMBOL_PREFIX=lzma_
-liblzma_la_LDFLAGS = -no-undefined -version-info 7:4:2
+liblzma_la_LDFLAGS = -no-undefined -version-info 8:99:3
 
 EXTRA_DIST += liblzma.map validate_map.sh
 if COND_SYMVERS

src/liblzma/api/lzma/base.h

@@ -234,6 +234,23 @@ typedef enum {
 		 * can be a sign of a bug in liblzma. See the documentation
 		 * how to report bugs.
 		 */
+
+	LZMA_SEEK_NEEDED        = 12
+		/**<
+		 * \brief       Request to change the input file position
+		 *
+		 * Some coders can do random access in the input file. The
+		 * initialization functions of these coders take the file size
+		 * as an argument. No other coders can return LZMA_SEEK_NEEDED.
+		 *
+		 * When this value is returned, the application must seek to
+		 * the file position given in lzma_stream.seek_pos. This value
+		 * is guaranteed to never exceed the file size that was
+		 * specified at the coder initialization.
+		 *
+		 * After seeking the application should read new input and
+		 * pass it normally via lzma_stream.next_in and .avail_in.
+		 */
 } lzma_ret;
 
 
@@ -514,7 +531,19 @@ typedef struct {
 	void *reserved_ptr2;
 	void *reserved_ptr3;
 	void *reserved_ptr4;
-	uint64_t reserved_int1;
+
+	/**
+	 * \brief       New seek input position for LZMA_SEEK_NEEDED
+	 *
+	 * When lzma_code() returns LZMA_SEEK_NEEDED, the new input position
+	 * needed by liblzma will be available seek_pos. The value is
+	 * guaranteed to not exceed the file size that was specified when
+	 * this lzma_stream was initialized.
+	 *
+	 * In all other situations the value of this variable is undefined.
+	 */
+	uint64_t seek_pos;
+
 	uint64_t reserved_int2;
 	size_t reserved_int3;
 	size_t reserved_int4;

src/liblzma/api/lzma/filter.h

@@ -341,9 +341,10 @@ extern LZMA_API(lzma_ret) lzma_properties_encode(
  * \param       filter      filter->id must have been set to the correct
  *                          Filter ID. filter->options doesn't need to be
  *                          initialized (it's not freed by this function). The
- *                          decoded options will be stored to filter->options.
- *                          filter->options is set to NULL if there are no
- *                          properties or if an error occurs.
+ *                          decoded options will be stored in filter->options;
+ *                          it's application's responsibility to free it when
+ *                          appropriate. filter->options is set to NULL if
+ *                          there are no properties or if an error occurs.
  * \param       allocator   Custom memory allocator used to allocate the
  *                          options. Set to NULL to use the default malloc(),
  *                          and in case of an error, also free().

src/liblzma/api/lzma/index.h

@@ -684,3 +684,69 @@ extern LZMA_API(lzma_ret) lzma_index_buffer_decode(lzma_index **i,
 		uint64_t *memlimit, const lzma_allocator *allocator,
 		const uint8_t *in, size_t *in_pos, size_t in_size)
 		lzma_nothrow;
+
+
+/**
+ * \brief       Initialize a .xz file information decoder
+ *
+ * \param       strm        Pointer to a properly prepared lzma_stream
+ * \param       dest_index  Pointer to a pointer where the decoder will put
+ *                          the decoded lzma_index. The old value
+ *                          of *dest_index is ignored (not freed).
+ * \param       memlimit    How much memory the resulting lzma_index is
+ *                          allowed to require. Use UINT64_MAX to
+ *                          effectively disable the limiter.
+ * \param       file_size   Size of the input .xz file
+ *
+ * This decoder decodes the Stream Header, Stream Footer, Index, and
+ * Stream Padding field(s) from the input .xz file and stores the resulting
+ * combined index in *dest_index. This information can be used to get the
+ * uncompressed file size with lzma_index_uncompressed_size(*dest_index) or,
+ * for example, to implement random access reading by locating the Blocks
+ * in the Streams.
+ *
+ * To get the required information from the .xz file, lzma_code() may ask
+ * the application to seek in the input file by returning LZMA_SEEK_NEEDED
+ * and having the target file position specified in lzma_stream.seek_pos.
+ * The number of seeks required depends on the input file and how big buffers
+ * the application provides. When possible, the decoder will seek backward
+ * and forward in the given buffer to avoid useless seek requests. Thus, if
+ * the application provides the whole file at once, no external seeking will
+ * be required (that is, lzma_code() won't return LZMA_SEEK_NEEDED).
+ *
+ * The value in lzma_stream.total_in can be used to estimate how much data
+ * liblzma had to read to get the file information. However, due to seeking
+ * and the way total_in is updated, the value of total_in will be somewhat
+ * inaccurate (a little too big). Thus, total_in is a good estimate but don't
+ * expect to see the same exact value for the same file if you change the
+ * input buffer size or switch to a different liblzma version.
+ *
+ * Valid `action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * You only need to use LZMA_RUN; LZMA_FINISH is only supported because it
+ * might be convenient for some applications. If you use LZMA_FINISH and if
+ * lzma_code() asks the application to seek, remember to reset `action' back
+ * to LZMA_RUN unless you hit the end of the file again.
+ *
+ * Possible return values from lzma_code():
+ *   - LZMA_OK: All OK so far, more input needed
+ *   - LZMA_SEEK_NEEDED: Provide more input starting from the absolute
+ *     file position strm->seek_pos
+ *   - LZMA_STREAM_END: Decoding was successful, *dest_index has been set
+ *   - LZMA_FORMAT_ERROR: The input file is not in the .xz format (the
+ *     expected magic bytes were not found from the beginning of the file)
+ *   - LZMA_OPTIONS_ERROR: File looks valid but contains headers that aren't
+ *     supported by this version of liblzma
+ *   - LZMA_DATA_ERROR: File is corrupt
+ *   - LZMA_BUF_ERROR
+ *   - LZMA_MEM_ERROR
+ *   - LZMA_MEMLIMIT_ERROR
+ *   - LZMA_PROG_ERROR
+ *
+ * \return      - LZMA_OK
+ *              - LZMA_MEM_ERROR
+ *              - LZMA_PROG_ERROR
+ */
+extern LZMA_API(lzma_ret) lzma_file_info_decoder(
+		lzma_stream *strm, lzma_index **dest_index,
+		uint64_t memlimit, uint64_t file_size)
+		lzma_nothrow;

src/liblzma/api/lzma/version.h

@@ -21,9 +21,9 @@
  * Version number split into components
  */
 #define LZMA_VERSION_MAJOR 5
-#define LZMA_VERSION_MINOR 2
-#define LZMA_VERSION_PATCH 4
-#define LZMA_VERSION_STABILITY LZMA_VERSION_STABILITY_STABLE
+#define LZMA_VERSION_MINOR 3
+#define LZMA_VERSION_PATCH 1
+#define LZMA_VERSION_STABILITY LZMA_VERSION_STABILITY_ALPHA
 
 #ifndef LZMA_VERSION_COMMIT
 #	define LZMA_VERSION_COMMIT ""

src/liblzma/common/Makefile.inc

@@ -65,11 +65,13 @@ liblzma_la_SOURCES += \
 	common/block_decoder.h \
 	common/block_header_decoder.c \
 	common/easy_decoder_memusage.c \
+	common/file_info.c \
 	common/filter_buffer_decoder.c \
 	common/filter_decoder.c \
 	common/filter_decoder.h \
 	common/filter_flags_decoder.c \
 	common/index_decoder.c \
+	common/index_decoder.h \
 	common/index_hash.c \
 	common/stream_buffer_decoder.c \
 	common/stream_decoder.c \

src/liblzma/common/common.c

@@ -207,7 +207,6 @@ lzma_code(lzma_stream *strm, lzma_action action)
 			|| strm->reserved_ptr2 != NULL
 			|| strm->reserved_ptr3 != NULL
 			|| strm->reserved_ptr4 != NULL
-			|| strm->reserved_int1 != 0
 			|| strm->reserved_int2 != 0
 			|| strm->reserved_int3 != 0
 			|| strm->reserved_int4 != 0
@@ -318,6 +317,17 @@ lzma_code(lzma_stream *strm, lzma_action action)
 		ret = LZMA_OK;
 		break;
 
+	case LZMA_SEEK_NEEDED:
+		strm->internal->allow_buf_error = false;
+
+		// If LZMA_FINISH was used, reset it back to the
+		// LZMA_RUN-based state so that new input can be supplied
+		// by the application.
+		if (strm->internal->sequence == ISEQ_FINISH)
+			strm->internal->sequence = ISEQ_RUN;
+
+		break;
+
 	case LZMA_STREAM_END:
 		if (strm->internal->sequence == ISEQ_SYNC_FLUSH
 				|| strm->internal->sequence == ISEQ_FULL_FLUSH

src/liblzma/common/file_info.c

@@ -0,0 +1,855 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       file_info.c
+/// \brief      Decode .xz file information into a lzma_index structure
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "index_decoder.h"
+
+
+typedef struct {
+	enum {
+		SEQ_MAGIC_BYTES,
+		SEQ_PADDING_SEEK,
+		SEQ_PADDING_DECODE,
+		SEQ_FOOTER,
+		SEQ_INDEX_INIT,
+		SEQ_INDEX_DECODE,
+		SEQ_HEADER_DECODE,
+		SEQ_HEADER_COMPARE,
+	} sequence;
+
+	/// Absolute position of in[*in_pos] in the file. All code that
+	/// modifies *in_pos also updates this. seek_to_pos() needs this
+	/// to determine if we need to request the application to seek for
+	/// us or if we can do the seeking internally by adjusting *in_pos.
+	uint64_t file_cur_pos;
+
+	/// This refers to absolute positions of interesting parts of the
+	/// input file. Sometimes it points to the *beginning* of a specific
+	/// field and sometimes to the *end* of a field. The current target
+	/// position at each moment is explained in the comments.
+	uint64_t file_target_pos;
+
+	/// Size of the .xz file (from the application).
+	uint64_t file_size;
+
+	/// Index decoder
+	lzma_next_coder index_decoder;
+
+	/// Number of bytes remaining in the Index field that is currently
+	/// being decoded.
+	lzma_vli index_remaining;
+
+	/// The Index decoder will store the decoded Index in this pointer.
+	lzma_index *this_index;
+
+	/// Amount of Stream Padding in the current Stream.
+	lzma_vli stream_padding;
+
+	/// The final combined index is collected here.
+	lzma_index *combined_index;
+
+	/// Pointer from the application where to store the index information
+	/// after successful decoding.
+	lzma_index **dest_index;
+
+	/// Pointer to lzma_stream.seek_pos to be used when returning
+	/// LZMA_SEEK_NEEDED. This is set by seek_to_pos() when needed.
+	uint64_t *external_seek_pos;
+
+	/// Memory usage limit
+	uint64_t memlimit;
+
+	/// Stream Flags from the very beginning of the file.
+	lzma_stream_flags first_header_flags;
+
+	/// Stream Flags from Stream Header of the current Stream.
+	lzma_stream_flags header_flags;
+
+	/// Stream Flags from Stream Footer of the current Stream.
+	lzma_stream_flags footer_flags;
+
+	size_t temp_pos;
+	size_t temp_size;
+	uint8_t temp[8192];
+
+} lzma_file_info_coder;
+
+
+/// Copies data from in[*in_pos] into coder->temp until
+/// coder->temp_pos == coder->temp_size. This also keeps coder->file_cur_pos
+/// in sync with *in_pos. Returns true if more input is needed.
+static bool
+fill_temp(lzma_file_info_coder *coder, const uint8_t *restrict in,
+		size_t *restrict in_pos, size_t in_size)
+{
+	coder->file_cur_pos += lzma_bufcpy(in, in_pos, in_size,
+			coder->temp, &coder->temp_pos, coder->temp_size);
+	return coder->temp_pos < coder->temp_size;
+}
+
+
+/// Seeks to the absolute file position specified by target_pos.
+/// This tries to do the seeking by only modifying *in_pos, if possible.
+/// The main benefit of this is that if one passes the whole file at once
+/// to lzma_code(), the decoder will never need to return LZMA_SEEK_NEEDED
+/// as all the seeking can be done by adjusting *in_pos in this function.
+///
+/// Returns true if an external seek is needed and the caller must return
+/// LZMA_SEEK_NEEDED.
+static bool
+seek_to_pos(lzma_file_info_coder *coder, uint64_t target_pos,
+		size_t in_start, size_t *in_pos, size_t in_size)
+{
+	// The input buffer doesn't extend beyond the end of the file.
+	// This has been checked by file_info_decode() already.
+	assert(coder->file_size - coder->file_cur_pos >= in_size - *in_pos);
+
+	const uint64_t pos_min = coder->file_cur_pos - (*in_pos - in_start);
+	const uint64_t pos_max = coder->file_cur_pos + (in_size - *in_pos);
+
+	bool external_seek_needed;
+
+	if (target_pos >= pos_min && target_pos <= pos_max) {
+		// The requested position is available in the current input
+		// buffer or right after it. That is, in a corner case we
+		// end up setting *in_pos == in_size and thus will immediately
+		// need new input bytes from the application.
+		*in_pos += (size_t)(target_pos - coder->file_cur_pos);
+		external_seek_needed = false;
+	} else {
+		// Ask the application to seek the input file.
+		*coder->external_seek_pos = target_pos;
+		external_seek_needed = true;
+
+		// Mark the whole input buffer as used. This way
+		// lzma_stream.total_in will have a better estimate
+		// of the amount of data read. It still won't be perfect
+		// as the value will depend on the input buffer size that
+		// the application uses, but it should be good enough for
+		// those few who want an estimate.
+		*in_pos = in_size;
+	}
+
+	// After seeking (internal or external) the current position
+	// will match the requested target position.
+	coder->file_cur_pos = target_pos;
+
+	return external_seek_needed;
+}
+
+
+/// The caller sets coder->file_target_pos so that it points to the *end*
+/// of the desired file position. This function then determines how far
+/// backwards from that position we can seek. After seeking fill_temp()
+/// can be used to read data into coder->temp. When fill_temp() has finished,
+/// coder->temp[coder->temp_size] will match coder->file_target_pos.
+///
+/// This also validates that coder->target_file_pos is sane in sense that
+/// we aren't trying to seek too far backwards (too close or beyond the
+/// beginning of the file).
+static lzma_ret
+reverse_seek(lzma_file_info_coder *coder,
+		size_t in_start, size_t *in_pos, size_t in_size)
+{
+	// Check that there is enough data before the target position
+	// to contain at least Stream Header and Stream Footer. If there
+	// isn't, the file cannot be valid.
+	if (coder->file_target_pos < 2 * LZMA_STREAM_HEADER_SIZE)
+		return LZMA_DATA_ERROR;
+
+	coder->temp_pos = 0;
+
+	// The Stream Header at the very beginning of the file gets handled
+	// specially in SEQ_MAGIC_BYTES and thus we will never need to seek
+	// there. By not seeking to the first LZMA_STREAM_HEADER_SIZE bytes
+	// we avoid a useless external seek after SEQ_MAGIC_BYTES if the
+	// application uses an extremely small input buffer and the input
+	// file is very small.
+	if (coder->file_target_pos - LZMA_STREAM_HEADER_SIZE
+			< sizeof(coder->temp))
+		coder->temp_size = (size_t)(coder->file_target_pos
+				- LZMA_STREAM_HEADER_SIZE);
+	else
+		coder->temp_size = sizeof(coder->temp);
+
+	// The above if-statements guarantee this. This is important because
+	// the Stream Header/Footer decoders assume that there's at least
+	// LZMA_STREAM_HEADER_SIZE bytes in coder->temp.
+	assert(coder->temp_size >= LZMA_STREAM_HEADER_SIZE);
+
+	if (seek_to_pos(coder, coder->file_target_pos - coder->temp_size,
+			in_start, in_pos, in_size))
+		return LZMA_SEEK_NEEDED;
+
+	return LZMA_OK;
+}
+
+
+/// Gets the number of zero-bytes at the end of the buffer.
+static size_t
+get_padding_size(const uint8_t *buf, size_t buf_size)
+{
+	size_t padding = 0;
+	while (buf_size > 0 && buf[--buf_size] == 0x00)
+		++padding;
+
+	return padding;
+}
+
+
+/// With the Stream Header at the very beginning of the file, LZMA_FORMAT_ERROR
+/// is used to tell the application that Magic Bytes didn't match. In other
+/// Stream Header/Footer fields (in the middle/end of the file) it could be
+/// a bit confusing to return LZMA_FORMAT_ERROR as we already know that there
+/// is a valid Stream Header at the beginning of the file. For those cases
+/// this function is used to convert LZMA_FORMAT_ERROR to LZMA_DATA_ERROR.
+static lzma_ret
+hide_format_error(lzma_ret ret)
+{
+	if (ret == LZMA_FORMAT_ERROR)
+		ret = LZMA_DATA_ERROR;
+
+	return ret;
+}
+
+
+/// Calls the Index decoder and updates coder->index_remaining.
+/// This is a separate function because the input can be either directly
+/// from the application or from coder->temp.
+static lzma_ret
+decode_index(lzma_file_info_coder *coder, const lzma_allocator *allocator,
+		const uint8_t *restrict in, size_t *restrict in_pos,
+		size_t in_size, bool update_file_cur_pos)
+{
+	const size_t in_start = *in_pos;
+
+	const lzma_ret ret = coder->index_decoder.code(
+			coder->index_decoder.coder,
+			allocator, in, in_pos, in_size,
+			NULL, NULL, 0, LZMA_RUN);
+
+	coder->index_remaining -= *in_pos - in_start;
+
+	if (update_file_cur_pos)
+		coder->file_cur_pos += *in_pos - in_start;
+
+	return ret;
+}
+
+
+static lzma_ret
+file_info_decode(void *coder_ptr, const lzma_allocator *allocator,
+		const uint8_t *restrict in, size_t *restrict in_pos,
+		size_t in_size,
+		uint8_t *restrict out lzma_attribute((__unused__)),
+		size_t *restrict out_pos lzma_attribute((__unused__)),
+		size_t out_size lzma_attribute((__unused__)),
+		lzma_action action lzma_attribute((__unused__)))
+{
+	lzma_file_info_coder *coder = coder_ptr;
+	const size_t in_start = *in_pos;
+
+	// If the caller provides input past the end of the file, trim
+	// the extra bytes from the buffer so that we won't read too far.
+	assert(coder->file_size >= coder->file_cur_pos);
+	if (coder->file_size - coder->file_cur_pos < in_size - in_start)
+		in_size = in_start
+			+ (size_t)(coder->file_size - coder->file_cur_pos);
+
+	while (true)
+	switch (coder->sequence) {
+	case SEQ_MAGIC_BYTES:
+		// Decode the Stream Header at the beginning of the file
+		// first to check if the Magic Bytes match. The flags
+		// are stored in coder->first_header_flags so that we
+		// don't need to seek to it again.
+		//
+		// Check that the file is big enough to contain at least
+		// Stream Header.
+		if (coder->file_size < LZMA_STREAM_HEADER_SIZE)
+			return LZMA_FORMAT_ERROR;
+
+		// Read the Stream Header field into coder->temp.
+		if (fill_temp(coder, in, in_pos, in_size))
+			return LZMA_OK;
+
+		// This is the only Stream Header/Footer decoding where we
+		// want to return LZMA_FORMAT_ERROR if the Magic Bytes don't
+		// match. Elsewehere it will be converted to LZMA_DATA_ERROR.
+		return_if_error(lzma_stream_header_decode(
+				&coder->first_header_flags, coder->temp));
+
+		// Now that we know that the Magic Bytes match, check the
+		// file size. It's better to do this here after checking the
+		// Magic Bytes since this way we can give LZMA_FORMAT_ERROR
+		// instead of LZMA_DATA_ERROR when the Magic Bytes don't
+		// match in a file that is too big or isn't a multiple of
+		// four bytes.
+		if (coder->file_size > LZMA_VLI_MAX || (coder->file_size & 3))
+			return LZMA_DATA_ERROR;
+
+		// Start looking for Stream Padding and Stream Footer
+		// at the end of the file.
+		coder->file_target_pos = coder->file_size;
+
+	// Fall through
+
+	case SEQ_PADDING_SEEK:
+		coder->sequence = SEQ_PADDING_DECODE;
+		return_if_error(reverse_seek(
+				coder, in_start, in_pos, in_size));
+
+	// Fall through
+
+	case SEQ_PADDING_DECODE: {
+		// Copy to coder->temp first. This keeps the code simpler if
+		// the application only provides input a few bytes at a time.
+		if (fill_temp(coder, in, in_pos, in_size))
+			return LZMA_OK;
+
+		// Scan the buffer backwards to get the size of the
+		// Stream Padding field (if any).
+		const size_t new_padding = get_padding_size(
+				coder->temp, coder->temp_size);
+		coder->stream_padding += new_padding;
+
+		// Set the target position to the beginning of Stream Padding
+		// that has been observed so far. If all Stream Padding has
+		// been seen, then the target position will be at the end
+		// of the Stream Footer field.
+		coder->file_target_pos -= new_padding;
+
+		if (new_padding == coder->temp_size) {
+			// The whole buffer was padding. Seek backwards in
+			// the file to get more input.
+			coder->sequence = SEQ_PADDING_SEEK;
+			break;
+		}
+
+		// Size of Stream Padding must be a multiple of 4 bytes.
+		if (coder->stream_padding & 3)
+			return LZMA_DATA_ERROR;
+
+		coder->sequence = SEQ_FOOTER;
+
+		// Calculate the amount of non-padding data in coder->temp.
+		coder->temp_size -= new_padding;
+		coder->temp_pos = coder->temp_size;
+
+		// We can avoid an external seek if the whole Stream Footer
+		// is already in coder->temp. In that case SEQ_FOOTER won't
+		// read more input and will find the Stream Footer from
+		// coder->temp[coder->temp_size - LZMA_STREAM_HEADER_SIZE].
+		//
+		// Otherwise we will need to seek. The seeking is done so
+		// that Stream Footer wil be at the end of coder->temp.
+		// This way it's likely that we also get a complete Index
+		// field into coder->temp without needing a separate seek
+		// for that (unless the Index field is big).
+		if (coder->temp_size < LZMA_STREAM_HEADER_SIZE)
+			return_if_error(reverse_seek(
+					coder, in_start, in_pos, in_size));
+	}
+
+	// Fall through
+
+	case SEQ_FOOTER:
+		// Copy the Stream Footer field into coder->temp.
+		// If Stream Footer was already available in coder->temp
+		// in SEQ_PADDING_DECODE, then this does nothing.
+		if (fill_temp(coder, in, in_pos, in_size))
+			return LZMA_OK;
+
+		// Make coder->file_target_pos and coder->temp_size point
+		// to the beginning of Stream Footer and thus to the end
+		// of the Index field. coder->temp_pos will be updated
+		// a bit later.
+		coder->file_target_pos -= LZMA_STREAM_HEADER_SIZE;
+		coder->temp_size -= LZMA_STREAM_HEADER_SIZE;
+
+		// Decode Stream Footer.
+		return_if_error(hide_format_error(lzma_stream_footer_decode(
+				&coder->footer_flags,
+				coder->temp + coder->temp_size)));
+
+		// Check that we won't seek past the beginning of the file.
+		//
+		// LZMA_STREAM_HEADER_SIZE is added because there must be
+		// space for Stream Header too even though we won't seek
+		// there before decoding the Index field.
+		//
+		// There's no risk of integer overflow here because
+		// Backward Size cannot be greater than 2^34.
+		if (coder->file_target_pos < coder->footer_flags.backward_size
+				+ LZMA_STREAM_HEADER_SIZE)
+			return LZMA_DATA_ERROR;
+
+		// Set the target position to the beginning of the Index field.
+		coder->file_target_pos -= coder->footer_flags.backward_size;
+		coder->sequence = SEQ_INDEX_INIT;
+
+		// We can avoid an external seek if the whole Index field is
+		// already available in coder->temp.
+		if (coder->temp_size >= coder->footer_flags.backward_size) {
+			// Set coder->temp_pos to point to the beginning
+			// of the Index.
+			coder->temp_pos = coder->temp_size
+					- coder->footer_flags.backward_size;
+		} else {
+			// These are set to zero to indicate that there's no
+			// useful data (Index or anything else) in coder->temp.
+			coder->temp_pos = 0;
+			coder->temp_size = 0;
+
+			// Seek to the beginning of the Index field.
+			if (seek_to_pos(coder, coder->file_target_pos,
+					in_start, in_pos, in_size))
+				return LZMA_SEEK_NEEDED;
+		}
+
+	// Fall through
+
+	case SEQ_INDEX_INIT: {
+		// Calculate the amount of memory already used by the earlier
+		// Indexes so that we know how big memory limit to pass to
+		// the Index decoder.
+		//
+		// NOTE: When there are multiple Streams, the separate
+		// lzma_index structures can use more RAM (as measured by
+		// lzma_index_memused()) than the final combined lzma_index.
+		// Thus memlimit may need to be slightly higher than the final
+		// calculated memory usage will be. This is perhaps a bit
+		// confusing to the application, but I think it shouldn't
+		// cause problems in practice.
+		uint64_t memused = 0;
+		if (coder->combined_index != NULL) {
+			memused = lzma_index_memused(coder->combined_index);
+			assert(memused <= coder->memlimit);
+			if (memused > coder->memlimit) // Extra sanity check
+				return LZMA_PROG_ERROR;
+		}
+
+		// Initialize the Index decoder.
+		return_if_error(lzma_index_decoder_init(
+				&coder->index_decoder, allocator,
+				&coder->this_index,
+				coder->memlimit - memused));
+
+		coder->index_remaining = coder->footer_flags.backward_size;
+		coder->sequence = SEQ_INDEX_DECODE;
+	}
+
+	// Fall through
+
+	case SEQ_INDEX_DECODE: {
+		// Decode (a part of) the Index. If the whole Index is already
+		// in coder->temp, read it from there. Otherwise read from
+		// in[*in_pos] onwards. Note that index_decode() updates
+		// coder->index_remaining and optionally coder->file_cur_pos.
+		lzma_ret ret;
+		if (coder->temp_size != 0) {
+			assert(coder->temp_size - coder->temp_pos
+					== coder->index_remaining);
+			ret = decode_index(coder, allocator, coder->temp,
+					&coder->temp_pos, coder->temp_size,
+					false);
+		} else {
+			// Don't give the decoder more input than the known
+			// remaining size of the Index field.
+			size_t in_stop = in_size;
+			if (in_size - *in_pos > coder->index_remaining)
+				in_stop = *in_pos
+					+ (size_t)(coder->index_remaining);
+
+			ret = decode_index(coder, allocator,
+					in, in_pos, in_stop, true);
+		}
+
+		switch (ret) {
+		case LZMA_OK:
+			// If the Index docoder asks for more input when we
+			// have already given it as much input as Backward Size
+			// indicated, the file is invalid.
+			if (coder->index_remaining == 0)
+				return LZMA_DATA_ERROR;
+
+			// We cannot get here if we were reading Index from
+			// coder->temp because when reading from coder->temp
+			// we give the Index decoder exactly
+			// coder->index_remaining bytes of input.
+			assert(coder->temp_size == 0);
+
+			return LZMA_OK;
+
+		case LZMA_STREAM_END:
+			// If the decoding seems to be successful, check also
+			// that the Index decoder consumed as much input as
+			// indicated by the Backward Size field.
+			if (coder->index_remaining != 0)
+				return LZMA_DATA_ERROR;
+
+			break;
+
+		default:
+			return ret;
+		}
+
+		// Calculate how much the Index tells us to seek backwards
+		// (relative to the beginning of the Index): Total size of
+		// all Blocks plus the size of the Stream Header field.
+		// No integer overflow here because lzma_index_total_size()
+		// cannot return a value greater than LZMA_VLI_MAX.
+		const uint64_t seek_amount
+				= lzma_index_total_size(coder->this_index)
+					+ LZMA_STREAM_HEADER_SIZE;
+
+		// Check that Index is sane in sense that seek_amount won't
+		// make us seek past the beginning of the file when locating
+		// the Stream Header.
+		//
+		// coder->file_target_pos still points to the beginning of
+		// the Index field.
+		if (coder->file_target_pos < seek_amount)
+			return LZMA_DATA_ERROR;
+
+		// Set the target to the beginning of Stream Header.
+		coder->file_target_pos -= seek_amount;
+
+		if (coder->file_target_pos == 0) {
+			// We would seek to the beginning of the file, but
+			// since we already decoded that Stream Header in
+			// SEQ_MAGIC_BYTES, we can use the cached value from
+			// coder->first_header_flags to avoid the seek.
+			coder->header_flags = coder->first_header_flags;
+			coder->sequence = SEQ_HEADER_COMPARE;
+			break;
+		}
+
+		coder->sequence = SEQ_HEADER_DECODE;
+
+		// Make coder->file_target_pos point to the end of
+		// the Stream Header field.
+		coder->file_target_pos += LZMA_STREAM_HEADER_SIZE;
+
+		// If coder->temp_size is non-zero, it points to the end
+		// of the Index field. Then the beginning of the Index
+		// field is at coder->temp[coder->temp_size
+		// - coder->footer_flags.backward_size].
+		assert(coder->temp_size == 0 || coder->temp_size
+				>= coder->footer_flags.backward_size);
+
+		// If coder->temp contained the whole Index, see if it has
+		// enough data to contain also the Stream Header. If so,
+		// we avoid an external seek.
+		//
+		// NOTE: This can happen only with small .xz files and only
+		// for the non-first Stream as the Stream Flags of the first
+		// Stream are cached and already handled a few lines above.
+		// So this isn't as useful as the other seek-avoidance cases.
+		if (coder->temp_size != 0 && coder->temp_size
+				- coder->footer_flags.backward_size
+				>= seek_amount) {
+			// Make temp_pos and temp_size point to the *end* of
+			// Stream Header so that SEQ_HEADER_DECODE will find
+			// the start of Stream Header from coder->temp[
+			// coder->temp_size - LZMA_STREAM_HEADER_SIZE].
+			coder->temp_pos = coder->temp_size
+					- coder->footer_flags.backward_size
+					- seek_amount
+					+ LZMA_STREAM_HEADER_SIZE;
+			coder->temp_size = coder->temp_pos;
+		} else {
+			// Seek so that Stream Header will be at the end of
+			// coder->temp. With typical multi-Stream files we
+			// will usually also get the Stream Footer and Index
+			// of the *previous* Stream in coder->temp and thus
+			// won't need a separate seek for them.
+			return_if_error(reverse_seek(coder,
+					in_start, in_pos, in_size));
+		}
+	}
+
+	// Fall through
+
+	case SEQ_HEADER_DECODE:
+		// Copy the Stream Header field into coder->temp.
+		// If Stream Header was already available in coder->temp
+		// in SEQ_INDEX_DECODE, then this does nothing.
+		if (fill_temp(coder, in, in_pos, in_size))
+			return LZMA_OK;
+
+		// Make all these point to the beginning of Stream Header.
+		coder->file_target_pos -= LZMA_STREAM_HEADER_SIZE;
+		coder->temp_size -= LZMA_STREAM_HEADER_SIZE;
+		coder->temp_pos = coder->temp_size;
+
+		// Decode the Stream Header.
+		return_if_error(hide_format_error(lzma_stream_header_decode(
+				&coder->header_flags,
+				coder->temp + coder->temp_size)));
+
+		coder->sequence = SEQ_HEADER_COMPARE;
+
+	// Fall through
+
+	case SEQ_HEADER_COMPARE:
+		// Compare Stream Header against Stream Footer. They must
+		// match.
+		return_if_error(lzma_stream_flags_compare(
+				&coder->header_flags, &coder->footer_flags));
+
+		// Store the decoded Stream Flags into the Index. Use the
+		// Footer Flags because it contains Backward Size, although
+		// it shouldn't matter in practice.
+		if (lzma_index_stream_flags(coder->this_index,
+				&coder->footer_flags) != LZMA_OK)
+			return LZMA_PROG_ERROR;
+
+		// Store also the size of the Stream Padding field. It is
+		// needed to calculate the offsets of the Streams correctly.
+		if (lzma_index_stream_padding(coder->this_index,
+				coder->stream_padding) != LZMA_OK)
+			return LZMA_PROG_ERROR;
+
+		// Reset it so that it's ready for the next Stream.
+		coder->stream_padding = 0;
+
+		// Append the earlier decoded Indexes after this_index.
+		if (coder->combined_index != NULL)
+			return_if_error(lzma_index_cat(coder->this_index,
+					coder->combined_index, allocator));
+
+		coder->combined_index = coder->this_index;
+		coder->this_index = NULL;
+
+		// If the whole file was decoded, tell the caller that we
+		// are finished.
+		if (coder->file_target_pos == 0) {
+			// The combined index must indicate the same file
+			// size as was told to us at initialization.
+			assert(lzma_index_file_size(coder->combined_index)
+					== coder->file_size);
+
+			// Make the combined index available to
+			// the application.
+			*coder->dest_index = coder->combined_index;
+			coder->combined_index = NULL;
+
+			// Mark the input buffer as used since we may have
+			// done internal seeking and thus don't know how
+			// many input bytes were actually used. This way
+			// lzma_stream.total_in gets a slightly better
+			// estimate of the amount of input used.
+			*in_pos = in_size;
+			return LZMA_STREAM_END;
+		}
+
+		// We didn't hit the beginning of the file yet, so continue
+		// reading backwards in the file. If we have unprocessed
+		// data in coder->temp, use it before requesting more data
+		// from the application.
+		//
+		// coder->file_target_pos, coder->temp_size, and
+		// coder->temp_pos all point to the beginning of Stream Header
+		// and thus the end of the previous Stream in the file.
+		coder->sequence = coder->temp_size > 0
+				? SEQ_PADDING_DECODE : SEQ_PADDING_SEEK;
+		break;
+
+	default:
+		assert(0);
+		return LZMA_PROG_ERROR;
+	}
+}
+
+
+static lzma_ret
+file_info_decoder_memconfig(void *coder_ptr, uint64_t *memusage,
+		uint64_t *old_memlimit, uint64_t new_memlimit)
+{
+	lzma_file_info_coder *coder = coder_ptr;
+
+	// The memory usage calculation comes from three things:
+	//
+	// (1) The Indexes that have already been decoded and processed into
+	//     coder->combined_index.
+	//
+	// (2) The latest Index in coder->this_index that has been decoded but
+	//     not yet put into coder->combined_index.
+	//
+	// (3) The latest Index that we have started decoding but haven't
+	//     finished and thus isn't available in coder->this_index yet.
+	//     Memory usage and limit information needs to be communicated
+	//     from/to coder->index_decoder.
+	//
+	// Care has to be taken to not do both (2) and (3) when calculating
+	// the memory usage.
+	uint64_t combined_index_memusage = 0;
+	uint64_t this_index_memusage = 0;
+
+	// (1) If we have already successfully decoded one or more Indexes,
+	// get their memory usage.
+	if (coder->combined_index != NULL)
+		combined_index_memusage = lzma_index_memused(
+				coder->combined_index);
+
+	// Choose between (2), (3), or neither.
+	if (coder->this_index != NULL) {
+		// (2) The latest Index is available. Use its memory usage.
+		this_index_memusage = lzma_index_memused(coder->this_index);
+
+	} else if (coder->sequence == SEQ_INDEX_DECODE) {
+		// (3) The Index decoder is activate and hasn't yet stored
+		// the new index in coder->this_index. Get the memory usage
+		// information from the Index decoder.
+		//
+		// NOTE: If the Index decoder doesn't yet know how much memory
+		// it will eventually need, it will return a tiny value here.
+		uint64_t dummy;
+		if (coder->index_decoder.memconfig(coder->index_decoder.coder,
+					&this_index_memusage, &dummy, 0)
+				!= LZMA_OK) {
+			assert(0);
+			return LZMA_PROG_ERROR;
+		}
+	}
+
+	// Now we know the total memory usage/requirement. If we had neither
+	// old Indexes nor a new Index, this will be zero which isn't
+	// acceptable as lzma_memusage() has to return non-zero on success
+	// and even with an empty .xz file we will end up with a lzma_index
+	// that takes some memory.
+	*memusage = combined_index_memusage + this_index_memusage;
+	if (*memusage == 0)
+		*memusage = lzma_index_memusage(1, 0);
+
+	*old_memlimit = coder->memlimit;
+
+	// If requested, set a new memory usage limit.
+	if (new_memlimit != 0) {
+		if (new_memlimit < *memusage)
+			return LZMA_MEMLIMIT_ERROR;
+
+		// In the condition (3) we need to tell the Index decoder
+		// its new memory usage limit.
+		if (coder->this_index == NULL
+				&& coder->sequence == SEQ_INDEX_DECODE) {
+			const uint64_t idec_new_memlimit = new_memlimit
+					- combined_index_memusage;
+
+			assert(this_index_memusage > 0);
+			assert(idec_new_memlimit > 0);
+
+			uint64_t dummy1;
+			uint64_t dummy2;
+
+			if (coder->index_decoder.memconfig(
+					coder->index_decoder.coder,
+					&dummy1, &dummy2, idec_new_memlimit)
+					!= LZMA_OK) {
+				assert(0);
+				return LZMA_PROG_ERROR;
+			}
+		}
+
+		coder->memlimit = new_memlimit;
+	}
+
+	return LZMA_OK;
+}
+
+
+static void
+file_info_decoder_end(void *coder_ptr, const lzma_allocator *allocator)
+{
+	lzma_file_info_coder *coder = coder_ptr;
+
+	lzma_next_end(&coder->index_decoder, allocator);
+	lzma_index_end(coder->this_index, allocator);
+	lzma_index_end(coder->combined_index, allocator);
+
+	lzma_free(coder, allocator);
+	return;
+}
+
+
+static lzma_ret
+lzma_file_info_decoder_init(lzma_next_coder *next,
+		const lzma_allocator *allocator, uint64_t *seek_pos,
+		lzma_index **dest_index,
+		uint64_t memlimit, uint64_t file_size)
+{
+	lzma_next_coder_init(&lzma_file_info_decoder_init, next, allocator);
+
+	if (dest_index == NULL)
+		return LZMA_PROG_ERROR;
+
+	lzma_file_info_coder *coder = next->coder;
+	if (coder == NULL) {
+		coder = lzma_alloc(sizeof(lzma_file_info_coder), allocator);
+		if (coder == NULL)
+			return LZMA_MEM_ERROR;
+
+		next->coder = coder;
+		next->code = &file_info_decode;
+		next->end = &file_info_decoder_end;
+		next->memconfig = &file_info_decoder_memconfig;
+
+		coder->index_decoder = LZMA_NEXT_CODER_INIT;
+		coder->this_index = NULL;
+		coder->combined_index = NULL;
+	}
+
+	coder->sequence = SEQ_MAGIC_BYTES;
+	coder->file_cur_pos = 0;
+	coder->file_target_pos = 0;
+	coder->file_size = file_size;
+
+	lzma_index_end(coder->this_index, allocator);
+	coder->this_index = NULL;
+
+	lzma_index_end(coder->combined_index, allocator);
+	coder->combined_index = NULL;
+
+	coder->stream_padding = 0;
+
+	coder->dest_index = dest_index;
+	coder->external_seek_pos = seek_pos;
+
+	// If memlimit is 0, make it 1 to ensure that lzma_memlimit_get()
+	// won't return 0 (which would indicate an error).
+	coder->memlimit = my_max(1, memlimit);
+
+	// Preprare thse for reading the first Stream Header into coder->temp.
+	coder->temp_pos = 0;
+	coder->temp_size = LZMA_STREAM_HEADER_SIZE;
+
+	return LZMA_OK;
+}
+
+
+extern LZMA_API(lzma_ret)
+lzma_file_info_decoder(lzma_stream *strm, lzma_index **dest_index,
+		uint64_t memlimit, uint64_t file_size)
+{
+	lzma_next_strm_init(lzma_file_info_decoder_init, strm, &strm->seek_pos,
+			dest_index, memlimit, file_size);
+
+	// We allow LZMA_FINISH in addition to LZMA_RUN for convenience.
+	// lzma_code() is able to handle the LZMA_FINISH + LZMA_SEEK_NEEDED
+	// combination in a sane way. Applications still need to be careful
+	// if they use LZMA_FINISH so that they remember to reset it back
+	// to LZMA_RUN after seeking if needed.
+	strm->internal->supported_actions[LZMA_RUN] = true;
+	strm->internal->supported_actions[LZMA_FINISH] = true;
+
+	return LZMA_OK;
+}

src/liblzma/common/index.c

@@ -825,8 +825,8 @@ lzma_index_cat(lzma_index *restrict dest, lzma_index *restrict src,
 				s->groups.root = &newg->node;
 			}
 
-			if (s->groups.rightmost == &g->node)
-				s->groups.rightmost = &newg->node;
+			assert(s->groups.rightmost == &g->node);
+			s->groups.rightmost = &newg->node;
 
 			lzma_free(g, allocator);
 

src/liblzma/common/index_decoder.c

@@ -10,7 +10,7 @@
 //
 ///////////////////////////////////////////////////////////////////////////////
 
-#include "index.h"
+#include "index_decoder.h"
 #include "check.h"
 
 
@@ -265,11 +265,11 @@ index_decoder_reset(lzma_index_coder *coder, const lzma_allocator *allocator,
 }
 
 
-static lzma_ret
-index_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
+extern lzma_ret
+lzma_index_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
 		lzma_index **i, uint64_t memlimit)
 {
-	lzma_next_coder_init(&index_decoder_init, next, allocator);
+	lzma_next_coder_init(&lzma_index_decoder_init, next, allocator);
 
 	if (i == NULL)
 		return LZMA_PROG_ERROR;
@@ -296,7 +296,7 @@ index_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
 extern LZMA_API(lzma_ret)
 lzma_index_decoder(lzma_stream *strm, lzma_index **i, uint64_t memlimit)
 {
-	lzma_next_strm_init(index_decoder_init, strm, i, memlimit);
+	lzma_next_strm_init(lzma_index_decoder_init, strm, i, memlimit);
 
 	strm->internal->supported_actions[LZMA_RUN] = true;
 	strm->internal->supported_actions[LZMA_FINISH] = true;

src/liblzma/common/index_decoder.h

@@ -0,0 +1,24 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       index_decoder.h
+/// \brief      Decodes the Index field
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef LZMA_INDEX_DECODER_H
+#define LZMA_INDEX_DECODER_H
+
+#include "index.h"
+
+
+extern lzma_ret lzma_index_decoder_init(lzma_next_coder *next,
+		const lzma_allocator *allocator,
+		lzma_index **i, uint64_t memlimit);
+
+
+#endif

src/liblzma/liblzma.map

@@ -102,7 +102,12 @@ global:
 	lzma_get_progress;
 	lzma_stream_encoder_mt;
 	lzma_stream_encoder_mt_memusage;
+} XZ_5.0;
+
+XZ_5.3.1alpha {
+global:
+	lzma_file_info_decoder;
 
 local:
 	*;
-} XZ_5.0;
+} XZ_5.2;

src/scripts/xzless.in

@@ -46,7 +46,7 @@ if test "${LESSMETACHARS+set}" != set; then
 	LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
 fi
 
-if test "$(less -V | { read less ver re && echo ${ver}; })" -ge 429; then
+if test "$(less -V | { read _ ver _ && echo ${ver}; })" -ge 429; then
 	# less 429 or later: LESSOPEN pipe will be used on
 	# standard input if $LESSOPEN begins with |-.
 	LESSOPEN="|-$xz -cdfq -- %s"

src/xz/file_io.c

@@ -1169,16 +1169,30 @@ io_read(file_pair *pair, io_buf *buf_union, size_t size)
 
 
 extern bool
-io_pread(file_pair *pair, io_buf *buf, size_t size, off_t pos)
+io_seek_src(file_pair *pair, off_t pos)
 {
-	// Using lseek() and read() is more portable than pread() and
-	// for us it is as good as real pread().
+	assert(pos >= 0);
+
 	if (lseek(pair->src_fd, pos, SEEK_SET) != pos) {
 		message_error(_("%s: Error seeking the file: %s"),
 				pair->src_name, strerror(errno));
 		return true;
 	}
 
+	pair->src_eof = false;
+
+	return false;
+}
+
+
+extern bool
+io_pread(file_pair *pair, io_buf *buf, size_t size, off_t pos)
+{
+	// Using lseek() and read() is more portable than pread() and
+	// for us it is as good as real pread().
+	if (io_seek_src(pair, pos))
+		return true;
+
 	const size_t amount = io_read(pair, buf, size);
 	if (amount == SIZE_MAX)
 		return true;

src/xz/file_io.h

@@ -129,6 +129,19 @@ extern size_t io_read(file_pair *pair, io_buf *buf, size_t size);
 extern void io_fix_src_pos(file_pair *pair, size_t rewind_size);
 
 
+/// \brief      Seek to the given absolute position in the source file
+///
+/// This calls lseek() and also clears pair->src_eof.
+///
+/// \param      pair    Seekable source file
+/// \param      pos     Offset relative to the beginning of the file,
+///                     from which the data should be read.
+///
+/// \return     On success, false is returned. On error, error message
+///             is printed and true is returned.
+extern bool io_seek_src(file_pair *pair, off_t pos);
+
+
 /// \brief      Read from source file from given offset to a buffer
 ///
 /// This is remotely similar to standard pread(). This uses lseek() though,

src/xz/list.c

@@ -143,9 +143,6 @@ xz_ver_to_str(uint32_t ver)
 ///
 /// \return     On success, false is returned. On error, true is returned.
 ///
-// TODO: This function is pretty big. liblzma should have a function that
-// takes a callback function to parse the Index(es) from a .xz file to make
-// it easy for applications.
 static bool
 parse_indexes(xz_file_info *xfi, file_pair *pair)
 {
@@ -161,238 +158,75 @@ parse_indexes(xz_file_info *xfi, file_pair *pair)
 	}
 
 	io_buf buf;
-	lzma_stream_flags header_flags;
-	lzma_stream_flags footer_flags;
-	lzma_ret ret;
-
-	// lzma_stream for the Index decoder
 	lzma_stream strm = LZMA_STREAM_INIT;
+	lzma_index *idx = NULL;
 
-	// All Indexes decoded so far
-	lzma_index *combined_index = NULL;
-
-	// The Index currently being decoded
-	lzma_index *this_index = NULL;
-
-	// Current position in the file. We parse the file backwards so
-	// initialize it to point to the end of the file.
-	off_t pos = pair->src_st.st_size;
-
-	// Each loop iteration decodes one Index.
-	do {
-		// Check that there is enough data left to contain at least
-		// the Stream Header and Stream Footer. This check cannot
-		// fail in the first pass of this loop.
-		if (pos < 2 * LZMA_STREAM_HEADER_SIZE) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(LZMA_DATA_ERROR));
-			goto error;
-		}
-
-		pos -= LZMA_STREAM_HEADER_SIZE;
-		lzma_vli stream_padding = 0;
-
-		// Locate the Stream Footer. There may be Stream Padding which
-		// we must skip when reading backwards.
-		while (true) {
-			if (pos < LZMA_STREAM_HEADER_SIZE) {
-				message_error("%s: %s", pair->src_name,
-						message_strm(
-							LZMA_DATA_ERROR));
-				goto error;
-			}
-
-			if (io_pread(pair, &buf,
-					LZMA_STREAM_HEADER_SIZE, pos))
-				goto error;
-
-			// Stream Padding is always a multiple of four bytes.
-			int i = 2;
-			if (buf.u32[i] != 0)
-				break;
-
-			// To avoid calling io_pread() for every four bytes
-			// of Stream Padding, take advantage that we read
-			// 12 bytes (LZMA_STREAM_HEADER_SIZE) already and
-			// check them too before calling io_pread() again.
-			do {
-				stream_padding += 4;
-				pos -= 4;
-				--i;
-			} while (i >= 0 && buf.u32[i] == 0);
-		}
-
-		// Decode the Stream Footer.
-		ret = lzma_stream_footer_decode(&footer_flags, buf.u8);
-		if (ret != LZMA_OK) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(ret));
-			goto error;
-		}
-
-		// Check that the Stream Footer doesn't specify something
-		// that we don't support. This can only happen if the xz
-		// version is older than liblzma and liblzma supports
-		// something new.
-		//
-		// It is enough to check Stream Footer. Stream Header must
-		// match when it is compared against Stream Footer with
-		// lzma_stream_flags_compare().
-		if (footer_flags.version != 0) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(LZMA_OPTIONS_ERROR));
-			goto error;
-		}
-
-		// Check that the size of the Index field looks sane.
-		lzma_vli index_size = footer_flags.backward_size;
-		if ((lzma_vli)(pos) < index_size + LZMA_STREAM_HEADER_SIZE) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(LZMA_DATA_ERROR));
-			goto error;
-		}
-
-		// Set pos to the beginning of the Index.
-		pos -= index_size;
-
-		// See how much memory we can use for decoding this Index.
-		uint64_t memlimit = hardware_memlimit_get(MODE_LIST);
-		uint64_t memused = 0;
-		if (combined_index != NULL) {
-			memused = lzma_index_memused(combined_index);
-			if (memused > memlimit)
-				message_bug();
-
-			memlimit -= memused;
-		}
-
-		// Decode the Index.
-		ret = lzma_index_decoder(&strm, &this_index, memlimit);
-		if (ret != LZMA_OK) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(ret));
-			goto error;
-		}
-
-		do {
-			// Don't give the decoder more input than the
-			// Index size.
-			strm.avail_in = my_min(IO_BUFFER_SIZE, index_size);
-			if (io_pread(pair, &buf, strm.avail_in, pos))
-				goto error;
-
-			pos += strm.avail_in;
-			index_size -= strm.avail_in;
+	lzma_ret ret = lzma_file_info_decoder(&strm, &idx,
+			hardware_memlimit_get(MODE_LIST),
+			(uint64_t)(pair->src_st.st_size));
+	if (ret != LZMA_OK) {
+		message_error("%s: %s", pair->src_name, message_strm(ret));
+		return true;
+	}
 
+	while (true) {
+		if (strm.avail_in == 0) {
 			strm.next_in = buf.u8;
-			ret = lzma_code(&strm, LZMA_RUN);
+			strm.avail_in = io_read(pair, &buf, IO_BUFFER_SIZE);
+			if (strm.avail_in == SIZE_MAX)
+				goto error;
+		}
 
-		} while (ret == LZMA_OK);
+		ret = lzma_code(&strm, LZMA_RUN);
 
-		// If the decoding seems to be successful, check also that
-		// the Index decoder consumed as much input as indicated
-		// by the Backward Size field.
-		if (ret == LZMA_STREAM_END)
-			if (index_size != 0 || strm.avail_in != 0)
-				ret = LZMA_DATA_ERROR;
+		switch (ret) {
+		case LZMA_OK:
+			break;
 
-		if (ret != LZMA_STREAM_END) {
-			// LZMA_BUFFER_ERROR means that the Index decoder
-			// would have liked more input than what the Index
-			// size should be according to Stream Footer.
-			// The message for LZMA_DATA_ERROR makes more
-			// sense in that case.
-			if (ret == LZMA_BUF_ERROR)
-				ret = LZMA_DATA_ERROR;
+		case LZMA_SEEK_NEEDED:
+			// The cast is safe because liblzma won't ask us to
+			// seek past the known size of the input file which
+			// did fit into off_t.
+			assert(strm.seek_pos
+					<= (uint64_t)(pair->src_st.st_size));
+			if (io_seek_src(pair, (off_t)(strm.seek_pos)))
+				goto error;
 
+			// avail_in must be zero so that we will read new
+			// input.
+			strm.avail_in = 0;
+			break;
+
+		case LZMA_STREAM_END: {
+			lzma_end(&strm);
+			xfi->idx = idx;
+
+			// Calculate xfi->stream_padding.
+			lzma_index_iter iter;
+			lzma_index_iter_init(&iter, xfi->idx);
+			while (!lzma_index_iter_next(&iter,
+					LZMA_INDEX_ITER_STREAM))
+				xfi->stream_padding += iter.stream.padding;
+
+			return false;
+		}
+
+		default:
 			message_error("%s: %s", pair->src_name,
 					message_strm(ret));
 
 			// If the error was too low memory usage limit,
 			// show also how much memory would have been needed.
-			if (ret == LZMA_MEMLIMIT_ERROR) {
-				uint64_t needed = lzma_memusage(&strm);
-				if (UINT64_MAX - needed < memused)
-					needed = UINT64_MAX;
-				else
-					needed += memused;
-
-				message_mem_needed(V_ERROR, needed);
-			}
+			if (ret == LZMA_MEMLIMIT_ERROR)
+				message_mem_needed(V_ERROR,
+						lzma_memusage(&strm));
 
 			goto error;
 		}
-
-		// Decode the Stream Header and check that its Stream Flags
-		// match the Stream Footer.
-		pos -= footer_flags.backward_size + LZMA_STREAM_HEADER_SIZE;
-		if ((lzma_vli)(pos) < lzma_index_total_size(this_index)) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(LZMA_DATA_ERROR));
-			goto error;
-		}
-
-		pos -= lzma_index_total_size(this_index);
-		if (io_pread(pair, &buf, LZMA_STREAM_HEADER_SIZE, pos))
-			goto error;
-
-		ret = lzma_stream_header_decode(&header_flags, buf.u8);
-		if (ret != LZMA_OK) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(ret));
-			goto error;
-		}
-
-		ret = lzma_stream_flags_compare(&header_flags, &footer_flags);
-		if (ret != LZMA_OK) {
-			message_error("%s: %s", pair->src_name,
-					message_strm(ret));
-			goto error;
-		}
-
-		// Store the decoded Stream Flags into this_index. This is
-		// needed so that we can print which Check is used in each
-		// Stream.
-		ret = lzma_index_stream_flags(this_index, &footer_flags);
-		if (ret != LZMA_OK)
-			message_bug();
-
-		// Store also the size of the Stream Padding field. It is
-		// needed to show the offsets of the Streams correctly.
-		ret = lzma_index_stream_padding(this_index, stream_padding);
-		if (ret != LZMA_OK)
-			message_bug();
-
-		if (combined_index != NULL) {
-			// Append the earlier decoded Indexes
-			// after this_index.
-			ret = lzma_index_cat(
-					this_index, combined_index, NULL);
-			if (ret != LZMA_OK) {
-				message_error("%s: %s", pair->src_name,
-						message_strm(ret));
-				goto error;
-			}
-		}
-
-		combined_index = this_index;
-		this_index = NULL;
-
-		xfi->stream_padding += stream_padding;
-
-	} while (pos > 0);
-
-	lzma_end(&strm);
-
-	// All OK. Make combined_index available to the caller.
-	xfi->idx = combined_index;
-	return false;
+	}
 
 error:
-	// Something went wrong, free the allocated memory.
 	lzma_end(&strm);
-	lzma_index_end(combined_index, NULL);
-	lzma_index_end(this_index, NULL);
 	return true;
 }
 

src/xz/message.c

@@ -818,6 +818,7 @@ message_strm(lzma_ret code)
 	case LZMA_STREAM_END:
 	case LZMA_GET_CHECK:
 	case LZMA_PROG_ERROR:
+	case LZMA_SEEK_NEEDED:
 		// Without "default", compiler will warn if new constants
 		// are added to lzma_ret, it is not too easy to forget to
 		// add the new constants to this function.

windows/vs2013/liblzma.vcxproj

@@ -229,6 +229,7 @@
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder_memusage.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_preset.c" />
+    <ClCompile Include="..\..\src\liblzma\common\file_info.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_decoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_common.c" />
@@ -318,6 +319,7 @@
     <ClInclude Include="..\..\src\liblzma\common\filter_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\filter_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index.h" />
+    <ClInclude Include="..\..\src\liblzma\common\index_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\memcmplen.h" />
     <ClInclude Include="..\..\src\liblzma\common\outqueue.h" />

windows/vs2013/liblzma_dll.vcxproj

@@ -255,6 +255,7 @@
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder_memusage.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_preset.c" />
+    <ClCompile Include="..\..\src\liblzma\common\file_info.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_decoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_common.c" />
@@ -344,6 +345,7 @@
     <ClInclude Include="..\..\src\liblzma\common\filter_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\filter_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index.h" />
+    <ClInclude Include="..\..\src\liblzma\common\index_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\memcmplen.h" />
     <ClInclude Include="..\..\src\liblzma\common\outqueue.h" />

windows/vs2017/liblzma.vcxproj

@@ -230,6 +230,7 @@
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder_memusage.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_preset.c" />
+    <ClCompile Include="..\..\src\liblzma\common\file_info.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_decoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_common.c" />
@@ -319,6 +320,7 @@
     <ClInclude Include="..\..\src\liblzma\common\filter_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\filter_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index.h" />
+    <ClInclude Include="..\..\src\liblzma\common\index_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\memcmplen.h" />
     <ClInclude Include="..\..\src\liblzma\common\outqueue.h" />

windows/vs2017/liblzma_dll.vcxproj

@@ -256,6 +256,7 @@
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_encoder_memusage.c" />
     <ClCompile Include="..\..\src\liblzma\common\easy_preset.c" />
+    <ClCompile Include="..\..\src\liblzma\common\file_info.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_decoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_buffer_encoder.c" />
     <ClCompile Include="..\..\src\liblzma\common\filter_common.c" />
@@ -345,6 +346,7 @@
     <ClInclude Include="..\..\src\liblzma\common\filter_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\filter_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index.h" />
+    <ClInclude Include="..\..\src\liblzma\common\index_decoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\index_encoder.h" />
     <ClInclude Include="..\..\src\liblzma\common\memcmplen.h" />
     <ClInclude Include="..\..\src\liblzma\common\outqueue.h" />