linux/lib/xz/xz_dec_stream.c

/*
 * .xz Stream decoder
 *
 * Author: Lasse Collin <[email protected]>
 *
 * This file has been put into the public domain.
 * You can do whatever you want with this file.
 */

#include "xz_private.h"
#include "xz_stream.h"

/* Hash used to validate the Index field */
struct xz_dec_hash { … };

struct xz_dec { … };

#ifdef XZ_DEC_ANY_CHECK
/* Sizes of the Check field with different Check IDs */
static const uint8_t check_sizes[16] = {
	0,
	4, 4, 4,
	8, 8, 8,
	16, 16, 16,
	32, 32, 32,
	64, 64, 64
};
#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 bool fill_temp(struct xz_dec *s, struct xz_buf *b)
{ … }

/* Decode a variable-length integer (little-endian base-128 encoding) */
static enum xz_ret dec_vli(struct xz_dec *s, const uint8_t *in,
			   size_t *in_pos, size_t in_size)
{ … }

/*
 * 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)
{ … }

/* Update the Index size and the CRC32 value. */
static void index_update(struct xz_dec *s, const struct xz_buf *b)
{ … }

/*
 * 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)
{ … }

/*
 * 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 crc32_validate(struct xz_dec *s, struct xz_buf *b)
{ … }

#ifdef XZ_DEC_ANY_CHECK
/*
 * Skip over the Check field when the Check ID is not supported.
 * Returns true once the whole Check field has been skipped over.
 */
static bool check_skip(struct xz_dec *s, struct xz_buf *b)
{
	while (s->pos < check_sizes[s->check_type]) {
		if (b->in_pos == b->in_size)
			return false;

		++b->in_pos;
		++s->pos;
	}

	s->pos = 0;

	return true;
}
#endif

/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */
static enum xz_ret dec_stream_header(struct xz_dec *s)
{ … }

/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */
static enum xz_ret dec_stream_footer(struct xz_dec *s)
{ … }

/* Decode the Block Header and initialize the filter chain. */
static enum xz_ret dec_block_header(struct xz_dec *s)
{ … }

static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
{ … }

/*
 * 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).
 */
XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b)
{ … }

XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max)
{ … }

XZ_EXTERN void xz_dec_reset(struct xz_dec *s)
{ … }

XZ_EXTERN void xz_dec_end(struct xz_dec *s)
{ … }