*
* The "slow" algorithm to generate LZX-compressed data is roughly as follows:
*
- * 1. Preprocess the input data to translate the targets of x86 call instructions
- * to absolute offsets.
+ * 1. Preprocess the input data to translate the targets of x86 call
+ * instructions to absolute offsets.
*
* 2. Build the suffix array and inverse suffix array for the input data. The
* suffix array contains the indices of all suffixes of the input data,
*
* 3. Build the longest common prefix array corresponding to the suffix array.
*
- * 4. For each suffix, find the highest lower ranked suffix that has a
- * lower position, the lowest higher ranked suffix that has a lower position,
- * and the length of the common prefix shared between each. This
- * information is later used to link suffix ranks into a doubly-linked list
- * for searching the suffix array.
+ * 4. For each suffix, find the highest lower ranked suffix that has a lower
+ * position, the lowest higher ranked suffix that has a lower position, and
+ * the length of the common prefix shared between each. This information is
+ * later used to link suffix ranks into a doubly-linked list for searching
+ * the suffix array.
*
* 5. Set a default cost model for matches/literals.
*
- * 6. Determine the lowest cost sequence of LZ77 matches ((offset, length) pairs)
- * and literal bytes to divide the input into. Raw match-finding is done by
- * searching the suffix array using a linked list to avoid considering any
- * suffixes that start after the current position. Each run of the
- * match-finder returns the approximate lowest-cost longest match as well as
- * any shorter matches that have even lower approximate costs. Each such run
- * also adds the suffix rank of the current position into the linked list
- * being used to search the suffix array. Parsing, or match-choosing, is
- * solved as a minimum-cost path problem using a forward "optimal parsing"
+ * 6. Determine the lowest cost sequence of LZ77 matches ((offset, length)
+ * pairs) and literal bytes to divide the input into. Raw match-finding is
+ * done by searching the suffix array using a linked list to avoid
+ * considering any suffixes that start after the current position. Each run
+ * of the match-finder returns the approximate lowest-cost longest match as
+ * well as any shorter matches that have even lower approximate costs. Each
+ * such run also adds the suffix rank of the current position into the linked
+ * list being used to search the suffix array. Parsing, or match-choosing,
+ * is solved as a minimum-cost path problem using a forward "optimal parsing"
* algorithm based on the Deflate encoder from 7-Zip. This algorithm moves
* forward calculating the minimum cost to reach each byte until either a
* very long match is found or until a position is found at which no matches
* Huffman codes that were computed for the block.
*
* Note: the algorithm does not yet attempt to split the input into multiple LZX
- * blocks.
+ * blocks, instead using a series of blocks of LZX_DIV_BLOCK_SIZE bytes.
*
* Fast algorithm
* --------------
* block splitting is done; only compressing the full input into an aligned
* offset block is considered.
*
- * API
- * ===
- *
- * The old API (retained for backward compatibility) consists of just one function:
- *
- * wimlib_lzx_compress()
- *
- * The new compressor has more potential parameters and needs more memory, so
- * the new API ties up memory allocations and compression parameters into a
- * context:
- *
- * wimlib_lzx_alloc_context()
- * wimlib_lzx_compress2()
- * wimlib_lzx_free_context()
- * wimlib_lzx_set_default_params()
- *
- * Both wimlib_lzx_compress() and wimlib_lzx_compress2() are designed to
- * compress an in-memory buffer of up to 32768 bytes. There is no sliding
- * window. This is suitable for the WIM format, which uses fixed-size chunks
- * that are seemingly always 32768 bytes. If needed, the compressor potentially
- * could be extended to support a larger and/or sliding window.
- *
- * Both wimlib_lzx_compress() and wimlib_lzx_compress2() return 0 if the data
- * could not be compressed to less than the size of the uncompressed data.
- * Again, this is suitable for the WIM format, which stores such data chunks
- * uncompressed.
- *
- * The functions in this LZX compression API are exported from the library,
- * although with the possible exception of wimlib_lzx_set_default_params(), this
- * is only in case other programs happen to have uses for it other than WIM
- * reading/writing as already handled through the rest of the library.
- *
* Acknowledgments
* ===============
*
#endif
#include "wimlib.h"
-#include "wimlib/compress.h"
+#include "wimlib/compressor_ops.h"
+#include "wimlib/compress_common.h"
+#include "wimlib/endianness.h"
#include "wimlib/error.h"
+#include "wimlib/lz_hash.h"
+#include "wimlib/lz_sarray.h"
#include "wimlib/lzx.h"
#include "wimlib/util.h"
#include <pthread.h>
#include <string.h>
#ifdef ENABLE_LZX_DEBUG
-# include "wimlib/decompress.h"
+# include "wimlib/decompress_common.h"
#endif
-#include "divsufsort/divsufsort.h"
-
typedef u32 block_cost_t;
#define INFINITE_BLOCK_COST ((block_cost_t)~0U)
#define LZX_OPTIM_ARRAY_SIZE 4096
-/* Currently, this constant can't simply be changed because the code currently
- * uses a static number of position slots (and may make other assumptions as
- * well). */
-#define LZX_MAX_WINDOW_SIZE 32768
-
-/* This may be WIM-specific */
-#define LZX_DEFAULT_BLOCK_SIZE 32768
+#define LZX_DIV_BLOCK_SIZE 32768
#define LZX_MAX_CACHE_PER_POS 10
/* Codewords for the LZX main, length, and aligned offset Huffman codes */
struct lzx_codewords {
- u16 main[LZX_MAINCODE_NUM_SYMBOLS];
+ u16 main[LZX_MAINCODE_MAX_NUM_SYMBOLS];
u16 len[LZX_LENCODE_NUM_SYMBOLS];
u16 aligned[LZX_ALIGNEDCODE_NUM_SYMBOLS];
};
* A 0 length means the codeword has zero frequency.
*/
struct lzx_lens {
- u8 main[LZX_MAINCODE_NUM_SYMBOLS];
+ u8 main[LZX_MAINCODE_MAX_NUM_SYMBOLS];
u8 len[LZX_LENCODE_NUM_SYMBOLS];
u8 aligned[LZX_ALIGNEDCODE_NUM_SYMBOLS];
};
* --- generally a high cost, since even if it gets used in the next iteration,
* it probably will not be used very times. */
struct lzx_costs {
- u8 main[LZX_MAINCODE_NUM_SYMBOLS];
+ u8 main[LZX_MAINCODE_MAX_NUM_SYMBOLS];
u8 len[LZX_LENCODE_NUM_SYMBOLS];
u8 aligned[LZX_ALIGNEDCODE_NUM_SYMBOLS];
};
/* Tables for tallying symbol frequencies in the three LZX alphabets */
struct lzx_freqs {
- freq_t main[LZX_MAINCODE_NUM_SYMBOLS];
- freq_t len[LZX_LENCODE_NUM_SYMBOLS];
- freq_t aligned[LZX_ALIGNEDCODE_NUM_SYMBOLS];
+ input_idx_t main[LZX_MAINCODE_MAX_NUM_SYMBOLS];
+ input_idx_t len[LZX_LENCODE_NUM_SYMBOLS];
+ input_idx_t aligned[LZX_ALIGNEDCODE_NUM_SYMBOLS];
};
/* LZX intermediate match/literal format */
*
* 8-24 position footer. This is the offset of the real formatted
* offset from the position base. This can be at most 17 bits
- * (since lzx_extra_bits[LZX_NUM_POSITION_SLOTS - 1] is 17).
+ * (since lzx_extra_bits[LZX_MAX_POSITION_SLOTS - 1] is 17).
*
* 0-7 length of match, minus 2. This can be at most
* (LZX_MAX_MATCH_LEN - 2) == 255, so it will fit in 8 bits. */
u32 data;
};
-/* Raw LZ match/literal format: just a length and offset.
- *
- * The length is the number of bytes of the match, and the offset is the number
- * of bytes back in the input the match is from the current position.
- *
- * If @len < LZX_MIN_MATCH_LEN, then it's really just a literal byte and @offset is
- * meaningless. */
-struct raw_match {
- u16 len;
- input_idx_t offset;
-};
-
/* Specification for an LZX block. */
struct lzx_block_spec {
struct lzx_lru_queue queue;
};
-/* Suffix array link */
-struct salink {
- /* Rank of highest ranked suffix that has rank lower than the suffix
- * corresponding to this structure and either has a lower position
- * (initially) or has a position lower than the highest position at
- * which matches have been searched for so far, or -1 if there is no
- * such suffix. */
- input_idx_t prev;
-
- /* Rank of lowest ranked suffix that has rank greater than the suffix
- * corresponding to this structure and either has a lower position
- * (intially) or has a position lower than the highest position at which
- * matches have been searched for so far, or -1 if there is no such
- * suffix. */
- input_idx_t next;
-
- /* Length of longest common prefix between the suffix corresponding to
- * this structure and the suffix with rank @prev, or 0 if @prev is -1.
- */
- input_idx_t lcpprev;
-
- /* Length of longest common prefix between the suffix corresponding to
- * this structure and the suffix with rank @next, or 0 if @next is -1.
- */
- input_idx_t lcpnext;
-};
-
/* State of the LZX compressor. */
struct lzx_compressor {
/* The parameters that were used to create the compressor. */
- struct wimlib_lzx_params params;
+ struct wimlib_lzx_compressor_params params;
/* The buffer of data to be compressed.
*
* 0xe8 byte preprocessing is done directly on the data here before
* further compression.
*
- * Note that this compressor does *not* use a sliding window!!!! It's
- * not needed in the WIM format, since every chunk is compressed
+ * Note that this compressor does *not* use a real sliding window!!!!
+ * It's not needed in the WIM format, since every chunk is compressed
* independently. This is by design, to allow random access to the
* chunks.
*
* We reserve a few extra bytes to potentially allow reading off the end
* of the array in the match-finding code for optimization purposes.
*/
- u8 window[LZX_MAX_WINDOW_SIZE + 12];
+ u8 *window;
/* Number of bytes of data to be compressed, which is the number of
* bytes of data in @window that are actually valid. */
input_idx_t window_size;
+ /* Allocated size of the @window. */
+ input_idx_t max_window_size;
+
+ /* Number of symbols in the main alphabet (depends on the
+ * @max_window_size since it determines the maximum allowed offset). */
+ unsigned num_main_syms;
+
/* The current match offset LRU queue. */
struct lzx_lru_queue queue;
/* The current cost model. */
struct lzx_costs costs;
- /* Suffix array for window.
- * This is a mapping from suffix rank to suffix position. */
- input_idx_t *SA;
+ /* Fast algorithm only: Array of hash table links. */
+ input_idx_t *prev_tab;
- /* Inverse suffix array for window.
- * This is a mapping from suffix position to suffix rank.
- * If 0 <= r < window_size, then ISA[SA[r]] == r. */
- input_idx_t *ISA;
+ /* Slow algorithm only: Suffix array match-finder. */
+ struct lz_sarray lz_sarray;
- /* Suffix array links.
- *
- * During a linear scan of the input string to find matches, this array
- * used to keep track of which rank suffixes in the suffix array appear
- * before the current position. Instead of searching in the original
- * suffix array, scans for matches at a given position traverse a linked
- * list containing only suffixes that appear before that position. */
- struct salink *salink;
-
- /* Position in window of next match to return.
- * Note: This cannot simply be modified, as the match-finder must still
- * be synchronized on the same position. To seek forwards or backwards,
- * use lzx_lz_skip_bytes() or lzx_lz_rewind_matchfinder(), respectively.
- */
+ /* Position in window of next match to return. */
input_idx_t match_window_pos;
/* The match-finder shall ensure the length of matches does not exceed
u32 optimum_end_idx;
};
-/* Returns the LZX position slot that corresponds to a given formatted offset.
- *
- * Logically, this returns the smallest i such that
- * formatted_offset >= lzx_position_base[i].
- *
- * The actual implementation below takes advantage of the regularity of the
- * numbers in the lzx_position_base array to calculate the slot directly from
- * the formatted offset without actually looking at the array.
- */
-static unsigned
-lzx_get_position_slot_raw(unsigned formatted_offset)
-{
-#if 0
- /*
- * Slots 36-49 (formatted_offset >= 262144) can be found by
- * (formatted_offset/131072) + 34 == (formatted_offset >> 17) + 34;
- * however, this check for formatted_offset >= 262144 is commented out
- * because WIM chunks cannot be that large.
- */
- if (formatted_offset >= 262144) {
- return (formatted_offset >> 17) + 34;
- } else
-#endif
- {
- /* Note: this part here only works if:
- *
- * 2 <= formatted_offset < 655360
- *
- * It is < 655360 because the frequency of the position bases
- * increases starting at the 655360 entry, and it is >= 2
- * because the below calculation fails if the most significant
- * bit is lower than the 2's place. */
- LZX_ASSERT(2 <= formatted_offset && formatted_offset < 655360);
- unsigned mssb_idx = bsr32(formatted_offset);
- return (mssb_idx << 1) |
- ((formatted_offset >> (mssb_idx - 1)) & 1);
- }
-}
-
-
/* Returns the LZX position slot that corresponds to a given match offset,
* taking into account the recent offset queue and updating it if the offset is
* found in it. */
* a set of tables that map symbols to codewords and codeword lengths. */
static void
lzx_make_huffman_codes(const struct lzx_freqs *freqs,
- struct lzx_codes *codes)
+ struct lzx_codes *codes,
+ unsigned num_main_syms)
{
- make_canonical_huffman_code(LZX_MAINCODE_NUM_SYMBOLS,
+ make_canonical_huffman_code(num_main_syms,
LZX_MAX_MAIN_CODEWORD_LEN,
freqs->main,
codes->lens.main,
}
/* Combine the position slot with the length header into a single symbol
- * that will be encoded with the main tree.
+ * that will be encoded with the main code.
*
* The actual main symbol is offset by LZX_NUM_CHARS because values
* under LZX_NUM_CHARS are used to indicate a literal byte rather than a
/* For aligned offset blocks with at least 3 extra bits, output the
* verbatim bits literally, then the aligned bits encoded using the
- * aligned offset tree. Otherwise, only the verbatim bits need to be
+ * aligned offset code. Otherwise, only the verbatim bits need to be
* output. */
if ((block_type == LZX_BLOCKTYPE_ALIGNED) && (num_extra_bits >= 3)) {
lzx_build_precode(const u8 lens[restrict],
const u8 prev_lens[restrict],
const unsigned num_syms,
- freq_t precode_freqs[restrict LZX_PRECODE_NUM_SYMBOLS],
+ input_idx_t precode_freqs[restrict LZX_PRECODE_NUM_SYMBOLS],
u8 output_syms[restrict num_syms],
u8 precode_lens[restrict LZX_PRECODE_NUM_SYMBOLS],
u16 precode_codewords[restrict LZX_PRECODE_NUM_SYMBOLS],
* literally.
*
* output_syms[] will be filled in with the length symbols that will be
- * output, including RLE codes, not yet encoded using the pre-tree.
+ * output, including RLE codes, not yet encoded using the precode.
*
* cur_run_len keeps track of how many code word lengths are in the
* current run of identical lengths. */
*
* The extra length symbol is encoded as a difference
* from the length of the codeword for the first symbol
- * in the run in the previous tree.
+ * in the run in the previous code.
* */
while (cur_run_len >= 4) {
unsigned additional_bits;
/* Any remaining lengths in the run are outputted without RLE,
* as a difference from the length of that codeword in the
- * previous tree. */
+ * previous code. */
while (cur_run_len > 0) {
signed char delta;
const u8 prev_lens[restrict],
unsigned num_syms)
{
- freq_t precode_freqs[LZX_PRECODE_NUM_SYMBOLS];
+ input_idx_t precode_freqs[LZX_PRECODE_NUM_SYMBOLS];
u8 output_syms[num_syms];
u8 precode_lens[LZX_PRECODE_NUM_SYMBOLS];
u16 precode_codewords[LZX_PRECODE_NUM_SYMBOLS];
}
static void
-lzx_assert_codes_valid(const struct lzx_codes * codes)
+lzx_assert_codes_valid(const struct lzx_codes * codes, unsigned num_main_syms)
{
#ifdef ENABLE_LZX_DEBUG
unsigned i;
- for (i = 0; i < LZX_MAINCODE_NUM_SYMBOLS; i++)
+ for (i = 0; i < num_main_syms; i++)
LZX_ASSERT(codes->lens.main[i] <= LZX_MAX_MAIN_CODEWORD_LEN);
for (i = 0; i < LZX_LENCODE_NUM_SYMBOLS; i++)
const unsigned tablebits = 10;
u16 decode_table[(1 << tablebits) +
- (2 * max(LZX_MAINCODE_NUM_SYMBOLS, LZX_LENCODE_NUM_SYMBOLS))]
+ (2 * max(num_main_syms, LZX_LENCODE_NUM_SYMBOLS))]
_aligned_attribute(DECODE_TABLE_ALIGNMENT);
LZX_ASSERT(0 == make_huffman_decode_table(decode_table,
- LZX_MAINCODE_NUM_SYMBOLS,
+ num_main_syms,
min(tablebits, LZX_MAINCODE_TABLEBITS),
codes->lens.main,
LZX_MAX_MAIN_CODEWORD_LEN));
static void
lzx_write_compressed_block(int block_type,
unsigned block_size,
+ unsigned max_window_size,
+ unsigned num_main_syms,
struct lzx_match * chosen_matches,
unsigned num_chosen_matches,
const struct lzx_codes * codes,
LZX_ASSERT(block_type == LZX_BLOCKTYPE_ALIGNED ||
block_type == LZX_BLOCKTYPE_VERBATIM);
- LZX_ASSERT(block_size <= LZX_MAX_WINDOW_SIZE);
- LZX_ASSERT(num_chosen_matches <= LZX_MAX_WINDOW_SIZE);
- lzx_assert_codes_valid(codes);
+ lzx_assert_codes_valid(codes, num_main_syms);
/* The first three bits indicate the type of block and are one of the
* LZX_BLOCKTYPE_* constants. */
- bitstream_put_bits(ostream, block_type, LZX_BLOCKTYPE_NBITS);
+ bitstream_put_bits(ostream, block_type, 3);
- /* The next bit indicates whether the block size is the default (32768),
- * indicated by a 1 bit, or whether the block size is given by the next
- * 16 bits, indicated by a 0 bit. */
+ /* Output the block size.
+ *
+ * The original LZX format seemed to always encode the block size in 3
+ * bytes. However, the implementation in WIMGAPI, as used in WIM files,
+ * uses the first bit to indicate whether the block is the default size
+ * (32768) or a different size given explicitly by the next 16 bits.
+ *
+ * By default, this compressor uses a window size of 32768 and therefore
+ * follows the WIMGAPI behavior. However, this compressor also supports
+ * window sizes greater than 32768 bytes, which do not appear to be
+ * supported by WIMGAPI. In such cases, we retain the default size bit
+ * to mean a size of 32768 bytes but output non-default block size in 24
+ * bits rather than 16. The compatibility of this behavior is unknown
+ * because WIMs created with chunk size greater than 32768 can seemingly
+ * only be opened by wimlib anyway. */
if (block_size == LZX_DEFAULT_BLOCK_SIZE) {
bitstream_put_bits(ostream, 1, 1);
} else {
bitstream_put_bits(ostream, 0, 1);
- bitstream_put_bits(ostream, block_size, LZX_BLOCKSIZE_NBITS);
+
+ if (max_window_size >= 65536)
+ bitstream_put_bits(ostream, block_size >> 16, 8);
+
+ bitstream_put_bits(ostream, block_size, 16);
}
/* Write out lengths of the main code. Note that the LZX specification
* incorrectly states that the aligned offset code comes after the
- * length code, but in fact it is the very first tree to be written
+ * length code, but in fact it is the very first code to be written
* (before the main code). */
if (block_type == LZX_BLOCKTYPE_ALIGNED)
for (i = 0; i < LZX_ALIGNEDCODE_NUM_SYMBOLS; i++)
LZX_DEBUG("Writing main code...");
- /* Write the pre-tree and lengths for the first LZX_NUM_CHARS symbols in
+ /* Write the precode and lengths for the first LZX_NUM_CHARS symbols in
* the main code, which are the codewords for literal bytes. */
lzx_write_compressed_code(ostream,
codes->lens.main,
prev_codes->lens.main,
LZX_NUM_CHARS);
- /* Write the pre-tree and lengths for the rest of the main code, which
+ /* Write the precode and lengths for the rest of the main code, which
* are the codewords for match headers. */
lzx_write_compressed_code(ostream,
codes->lens.main + LZX_NUM_CHARS,
prev_codes->lens.main + LZX_NUM_CHARS,
- LZX_MAINCODE_NUM_SYMBOLS - LZX_NUM_CHARS);
+ num_main_syms - LZX_NUM_CHARS);
LZX_DEBUG("Writing length code...");
- /* Write the pre-tree and lengths for the length code. */
+ /* Write the precode and lengths for the length code. */
lzx_write_compressed_code(ostream,
codes->lens.len,
prev_codes->lens.len,
static void
lzx_write_all_blocks(struct lzx_compressor *ctx, struct output_bitstream *ostream)
{
+
const struct lzx_codes *prev_codes = &ctx->zero_codes;
for (unsigned i = 0; i < ctx->num_blocks; i++) {
const struct lzx_block_spec *spec = &ctx->block_specs[i];
lzx_write_compressed_block(spec->block_type,
spec->block_size,
+ ctx->max_window_size,
+ ctx->num_main_syms,
&ctx->chosen_matches[spec->chosen_matches_start_pos],
spec->num_chosen_matches,
&spec->codes,
prev_codes,
ostream);
+
prev_codes = &spec->codes;
}
}
freqs->aligned[position_footer & 7]++;
/* Pack the position slot, position footer, and match length into an
- * intermediate representation.
- *
- * bits description
- * ---- -----------------------------------------------------------
- *
- * 31 1 if a match, 0 if a literal.
- *
- * 30-25 position slot. This can be at most 50, so it will fit in 6
- * bits.
- *
- * 8-24 position footer. This is the offset of the real formatted
- * offset from the position base. This can be at most 17 bits
- * (since lzx_extra_bits[LZX_NUM_POSITION_SLOTS - 1] is 17).
- *
- * 0-7 length of match, offset by 2. This can be at most
- * (LZX_MAX_MATCH_LEN - 2) == 255, so it will fit in 8 bits. */
- BUILD_BUG_ON(LZX_NUM_POSITION_SLOTS > 64);
- LZX_ASSERT(lzx_get_num_extra_bits(LZX_NUM_POSITION_SLOTS - 1) <= 17);
- BUILD_BUG_ON(LZX_MAX_MATCH_LEN - LZX_MIN_MATCH_LEN + 1 > 256);
+ * intermediate representation. See `struct lzx_match' for details.
+ */
+ LZX_ASSERT(LZX_MAX_POSITION_SLOTS <= 64);
+ LZX_ASSERT(lzx_get_num_extra_bits(LZX_MAX_POSITION_SLOTS - 1) <= 17);
+ LZX_ASSERT(LZX_MAX_MATCH_LEN - LZX_MIN_MATCH_LEN + 1 <= 256);
+
+ LZX_ASSERT(position_slot <= (1U << (31 - 25)) - 1);
+ LZX_ASSERT(position_footer <= (1U << (25 - 8)) - 1);
+ LZX_ASSERT(adjusted_match_len <= (1U << (8 - 0)) - 1);
return 0x80000000 |
(position_slot << 25) |
(position_footer << 8) |
/* Fast heuristic cost evaluation to use in the inner loop of the match-finder.
* Unlike lzx_match_cost() which does a true cost evaluation, this simply
* prioritize matches based on their offset. */
-static block_cost_t
-lzx_match_cost_fast(unsigned offset, const struct lzx_lru_queue *queue)
+static input_idx_t
+lzx_match_cost_fast(input_idx_t length, input_idx_t offset, const void *_queue)
{
+ const struct lzx_lru_queue *queue = _queue;
+
/* It seems well worth it to take the time to give priority to recently
* used offsets. */
- for (unsigned i = 0; i < LZX_NUM_RECENT_OFFSETS; i++)
+ for (input_idx_t i = 0; i < LZX_NUM_RECENT_OFFSETS; i++)
if (offset == queue->R[i])
return i;
- BUILD_BUG_ON(LZX_MAX_WINDOW_SIZE >= (block_cost_t)~0U);
return offset;
}
lzx_set_costs(struct lzx_compressor * ctx, const struct lzx_lens * lens)
{
unsigned i;
+ unsigned num_main_syms = ctx->num_main_syms;
/* Main code */
- for (i = 0; i < LZX_MAINCODE_NUM_SYMBOLS; i++) {
+ for (i = 0; i < num_main_syms; i++) {
ctx->costs.main[i] = lens->main[i];
if (ctx->costs.main[i] == 0)
ctx->costs.main[i] = ctx->params.alg_params.slow.main_nostat_cost;
}
}
-/* Advance the suffix array match-finder to the next position. */
-static void
-lzx_lz_update_salink(input_idx_t i,
- const input_idx_t SA[restrict],
- const input_idx_t ISA[restrict],
- struct salink link[restrict])
-{
- /* r = Rank of the suffix at the current position. */
- const input_idx_t r = ISA[i];
-
- /* next = rank of LOWEST ranked suffix that is ranked HIGHER than the
- * current suffix AND has a LOWER position, or -1 if none exists. */
- const input_idx_t next = link[r].next;
-
- /* prev = rank of HIGHEST ranked suffix that is ranked LOWER than the
- * current suffix AND has a LOWER position, or -1 if none exists. */
- const input_idx_t prev = link[r].prev;
-
- /* Link the suffix at the current position into the linked list that
- * contains all suffixes in the suffix array that are appear at or
- * before the current position, sorted by rank.
- *
- * Save the values of all fields we overwrite so that rollback is
- * possible. */
- if (next != (input_idx_t)~0U) {
-
- link[next].prev = r;
- link[next].lcpprev = link[r].lcpnext;
- }
-
- if (prev != (input_idx_t)~0U) {
-
- link[prev].next = r;
- link[prev].lcpnext = link[r].lcpprev;
- }
-}
-
-/* Rewind the suffix array match-finder to the specified position.
- *
- * This undoes a series of updates by lzx_lz_update_salink(). */
-static void
-lzx_lz_rewind_matchfinder(struct lzx_compressor *ctx,
- const unsigned orig_pos)
-{
- LZX_DEBUG("Rewind match-finder %u => %u", ctx->match_window_pos, orig_pos);
-
- if (ctx->match_window_pos == orig_pos)
- return;
-
- /* NOTE: this has been optimized for the current algorithm where no
- * block-splitting is done and matches are cached, so that the suffix
- * array match-finder only runs through the input one time. Generalized
- * rewinds of the suffix array match-finder are possible, but require
- * incrementally saving fields being overwritten in
- * lzx_lz_update_salink(), then restoring them here in reverse order.
- */
-
- LZX_ASSERT(ctx->match_window_pos > orig_pos);
- LZX_ASSERT(orig_pos == 0);
- ctx->matches_cached = true;
- ctx->cached_matches_pos = 0;
- ctx->match_window_pos = orig_pos;
-}
-
-/*
- * Use the suffix array match-finder to retrieve a list of LZ matches at the
- * current position.
- *
- * [in] @i Current position in the window.
- * [in] @SA Suffix array for the window.
- * [in] @ISA Inverse suffix array for the window.
- * [inout] @link Suffix array links used internally by the match-finder.
- * [out] @matches The (length, offset) pairs of the resulting matches will
- * be written here, sorted in decreasing order by
- * length. All returned lengths will be unique.
- * [in] @queue Recently used match offsets, used when evaluating the
- * cost of matches.
- * [in] @min_match_len Minimum match length to return.
- * [in] @max_matches_to_consider Maximum number of matches to consider at
- * the position.
- * [in] @max_matches_to_return Maximum number of matches to return.
- *
- * The return value is the number of matches found and written to @matches.
- */
-static unsigned
-lzx_lz_get_matches(const input_idx_t i,
- const input_idx_t SA[const restrict],
- const input_idx_t ISA[const restrict],
- struct salink link[const restrict],
- struct raw_match matches[const restrict],
- const struct lzx_lru_queue * const restrict queue,
- const unsigned min_match_len,
- const uint32_t max_matches_to_consider,
- const uint32_t max_matches_to_return)
-{
- /* r = Rank of the suffix at the current position. */
- const input_idx_t r = ISA[i];
-
- /* Prepare for searching the current position. */
- lzx_lz_update_salink(i, SA, ISA, link);
-
- /* L = rank of next suffix to the left;
- * R = rank of next suffix to the right;
- * lenL = length of match between current position and the suffix with rank L;
- * lenR = length of match between current position and the suffix with rank R.
- *
- * This is left and right relative to the rank of the current suffix.
- * Since the suffixes in the suffix array are sorted, the longest
- * matches are immediately to the left and right (using the linked list
- * to ignore all suffixes that occur later in the window). The match
- * length decreases the farther left and right we go. We shall keep the
- * length on both sides in sync in order to choose the lowest-cost match
- * of each length.
- */
- input_idx_t L = link[r].prev;
- input_idx_t R = link[r].next;
- input_idx_t lenL = link[r].lcpprev;
- input_idx_t lenR = link[r].lcpnext;
-
- /* nmatches = number of matches found so far. */
- unsigned nmatches = 0;
-
- /* best_cost = cost of lowest-cost match found so far.
- *
- * We keep track of this so that we can ignore shorter matches that do
- * not have lower costs than a longer matches already found.
- */
- block_cost_t best_cost = INFINITE_BLOCK_COST;
-
- /* count_remaining = maximum number of possible matches remaining to be
- * considered. */
- uint32_t count_remaining = max_matches_to_consider;
-
- /* pending = match currently being considered for a specific length. */
- struct raw_match pending;
- block_cost_t pending_cost;
-
- while (lenL >= min_match_len || lenR >= min_match_len)
- {
- pending.len = lenL;
- pending_cost = INFINITE_BLOCK_COST;
- block_cost_t cost;
-
- /* Extend left. */
- if (lenL >= min_match_len && lenL >= lenR) {
- for (;;) {
-
- if (--count_remaining == 0)
- goto out_save_pending;
-
- input_idx_t offset = i - SA[L];
-
- /* Save match if it has smaller cost. */
- cost = lzx_match_cost_fast(offset, queue);
- if (cost < pending_cost) {
- pending.offset = offset;
- pending_cost = cost;
- }
-
- if (link[L].lcpprev < lenL) {
- /* Match length decreased. */
-
- lenL = link[L].lcpprev;
-
- /* Save the pending match unless the
- * right side still may have matches of
- * this length to be scanned, or if a
- * previous (longer) match had lower
- * cost. */
- if (pending.len > lenR) {
- if (pending_cost < best_cost) {
- best_cost = pending_cost;
- matches[nmatches++] = pending;
- if (nmatches == max_matches_to_return)
- return nmatches;
- }
- pending.len = lenL;
- pending_cost = INFINITE_BLOCK_COST;
- }
- if (lenL < min_match_len || lenL < lenR)
- break;
- }
- L = link[L].prev;
- }
- }
-
- pending.len = lenR;
-
- /* Extend right. */
- if (lenR >= min_match_len && lenR > lenL) {
- for (;;) {
-
- if (--count_remaining == 0)
- goto out_save_pending;
-
- input_idx_t offset = i - SA[R];
-
- /* Save match if it has smaller cost. */
- cost = lzx_match_cost_fast(offset, queue);
- if (cost < pending_cost) {
- pending.offset = offset;
- pending_cost = cost;
- }
-
- if (link[R].lcpnext < lenR) {
- /* Match length decreased. */
-
- lenR = link[R].lcpnext;
-
- /* Save the pending match unless a
- * previous (longer) match had lower
- * cost. */
- if (pending_cost < best_cost) {
- matches[nmatches++] = pending;
- best_cost = pending_cost;
- if (nmatches == max_matches_to_return)
- return nmatches;
- }
-
- if (lenR < min_match_len || lenR <= lenL)
- break;
-
- pending.len = lenR;
- pending_cost = INFINITE_BLOCK_COST;
- }
- R = link[R].next;
- }
- }
- }
- goto out;
-
-out_save_pending:
- if (pending_cost != INFINITE_BLOCK_COST)
- matches[nmatches++] = pending;
-
-out:
- return nmatches;
-}
-
-
/* Tell the match-finder to skip the specified number of bytes (@n) in the
* input. */
static void
} else {
while (n--) {
ctx->cached_matches[ctx->cached_matches_pos++].len = 0;
- lzx_lz_update_salink(ctx->match_window_pos++, ctx->SA,
- ctx->ISA, ctx->salink);
+ lz_sarray_skip_position(&ctx->lz_sarray);
+ ctx->match_window_pos++;
}
+ LZX_ASSERT(lz_sarray_get_pos(&ctx->lz_sarray) == ctx->match_window_pos);
}
}
if (ctx->matches_cached) {
num_matches = matches[-1].len;
} else {
- unsigned min_match_len = LZX_MIN_MATCH_LEN;
- if (!ctx->params.alg_params.slow.use_len2_matches)
- min_match_len = max(min_match_len, 3);
- const uint32_t max_search_depth = ctx->params.alg_params.slow.max_search_depth;
- const uint32_t max_matches_per_pos = ctx->params.alg_params.slow.max_matches_per_pos;
-
- if (unlikely(max_search_depth == 0 || max_matches_per_pos == 0))
- num_matches = 0;
- else
- num_matches = lzx_lz_get_matches(ctx->match_window_pos,
- ctx->SA,
- ctx->ISA,
- ctx->salink,
- matches,
- queue,
- min_match_len,
- max_search_depth,
- max_matches_per_pos);
+ LZX_ASSERT(lz_sarray_get_pos(&ctx->lz_sarray) == ctx->match_window_pos);
+ num_matches = lz_sarray_get_matches(&ctx->lz_sarray,
+ matches,
+ lzx_match_cost_fast,
+ queue);
matches[-1].len = num_matches;
}
ctx->cached_matches_pos += num_matches + 1;
* Set default symbol costs.
*/
static void
-lzx_set_default_costs(struct lzx_costs * costs)
+lzx_set_default_costs(struct lzx_costs * costs, unsigned num_main_syms)
{
unsigned i;
costs->main[i] = 8;
/* Match header symbols */
- for (; i < LZX_MAINCODE_NUM_SYMBOLS; i++)
+ for (; i < num_main_syms; i++)
costs->main[i] = 10;
/* Length symbols */
const struct lzx_lru_queue orig_queue = ctx->queue;
struct lzx_freqs freqs;
+ unsigned orig_window_pos = spec->window_pos;
+ unsigned orig_cached_pos = ctx->cached_matches_pos;
+
+ LZX_ASSERT(ctx->match_window_pos == spec->window_pos);
+
ctx->match_window_end = spec->window_pos + spec->block_size;
spec->chosen_matches_start_pos = spec->window_pos;
* computed from the previous pass. */
for (unsigned pass = 0; pass < num_passes; pass++) {
- lzx_lz_rewind_matchfinder(ctx, spec->window_pos);
+ ctx->match_window_pos = orig_window_pos;
+ ctx->cached_matches_pos = orig_cached_pos;
ctx->queue = orig_queue;
spec->num_chosen_matches = 0;
memset(&freqs, 0, sizeof(freqs));
spec->num_chosen_matches++] = lzx_match;
}
- lzx_make_huffman_codes(&freqs, &spec->codes);
+ lzx_make_huffman_codes(&freqs, &spec->codes,
+ ctx->num_main_syms);
if (pass < num_passes - 1)
lzx_set_costs(ctx, &spec->codes.lens);
+ ctx->matches_cached = true;
}
spec->block_type = lzx_choose_verbatim_or_aligned(&freqs, &spec->codes);
+ ctx->matches_cached = false;
}
static void
lzx_optimize_block(ctx, &ctx->block_specs[i], num_passes);
}
-/* Initialize the suffix array match-finder for the specified input. */
-static void
-lzx_lz_init_matchfinder(const u8 T[const restrict],
- const input_idx_t n,
- input_idx_t SA[const restrict],
- input_idx_t ISA[const restrict],
- struct salink link[const restrict],
- const unsigned max_match_len)
-{
- /* Compute SA (Suffix Array). */
-
- {
- saidx_t sa[n];
- /* ISA and link are used as temporary space. */
- BUILD_BUG_ON(LZX_MAX_WINDOW_SIZE * sizeof(ISA[0]) < 256 * sizeof(saidx_t));
- BUILD_BUG_ON(LZX_MAX_WINDOW_SIZE * 2 * sizeof(link[0]) < 256 * 256 * sizeof(saidx_t));
- divsufsort(T, sa, n, (saidx_t*)ISA, (saidx_t*)link);
- for (input_idx_t i = 0; i < n; i++)
- SA[i] = sa[i];
- }
-
-#ifdef ENABLE_LZX_DEBUG
-
- LZX_ASSERT(n > 0);
-
- /* Verify suffix array. */
- {
- bool found[n];
- ZERO_ARRAY(found);
- for (input_idx_t r = 0; r < n; r++) {
- input_idx_t i = SA[r];
- LZX_ASSERT(i < n);
- LZX_ASSERT(!found[i]);
- found[i] = true;
- }
- }
-
- for (input_idx_t r = 0; r < n - 1; r++) {
-
- input_idx_t i1 = SA[r];
- input_idx_t i2 = SA[r + 1];
-
- input_idx_t n1 = n - i1;
- input_idx_t n2 = n - i2;
-
- LZX_ASSERT(memcmp(&T[i1], &T[i2], min(n1, n2)) <= 0);
- }
- LZX_DEBUG("Verified SA (len %u)", n);
-#endif /* ENABLE_LZX_DEBUG */
-
- /* Compute ISA (Inverse Suffix Array) */
- for (input_idx_t r = 0; r < n; r++)
- ISA[SA[r]] = r;
-
- {
- input_idx_t LCP[n];
- /* Compute LCP (longest common prefix) array.
- *
- * Algorithm adapted from Kasai et al. 2001: "Linear-Time
- * Longest-Common-Prefix Computation in Suffix Arrays and Its
- * Applications". */
- {
- input_idx_t h = 0;
- for (input_idx_t i = 0; i < n; i++) {
- input_idx_t r = ISA[i];
- if (r > 0) {
- input_idx_t j = SA[r - 1];
-
- input_idx_t lim = min(n - i, n - j);
-
- while (h < lim && T[i + h] == T[j + h])
- h++;
- LCP[r] = h;
- if (h > 0)
- h--;
- }
- }
- }
-
- #ifdef ENABLE_LZX_DEBUG
- /* Verify LCP array. */
- for (input_idx_t r = 0; r < n - 1; r++) {
- LZX_ASSERT(ISA[SA[r]] == r);
- LZX_ASSERT(ISA[SA[r + 1]] == r + 1);
-
- input_idx_t i1 = SA[r];
- input_idx_t i2 = SA[r + 1];
- input_idx_t lcp = LCP[r + 1];
-
- input_idx_t n1 = n - i1;
- input_idx_t n2 = n - i2;
-
- LZX_ASSERT(lcp <= min(n1, n2));
-
- LZX_ASSERT(memcmp(&T[i1], &T[i2], lcp) == 0);
- if (lcp < min(n1, n2))
- LZX_ASSERT(T[i1 + lcp] != T[i2 + lcp]);
- }
- #endif /* ENABLE_LZX_DEBUG */
-
- /* Compute salink.next and salink.lcpnext.
- *
- * Algorithm adapted from Crochemore et al. 2009:
- * "LPF computation revisited".
- *
- * Note: we cap lcpnext to the maximum match length so that the
- * match-finder need not worry about it later. */
- link[n - 1].next = (input_idx_t)~0U;
- link[n - 1].prev = (input_idx_t)~0U;
- link[n - 1].lcpnext = 0;
- link[n - 1].lcpprev = 0;
- for (input_idx_t r = n - 2; r != (input_idx_t)~0U; r--) {
- input_idx_t t = r + 1;
- input_idx_t l = LCP[t];
- while (t != (input_idx_t)~0 && SA[t] > SA[r]) {
- l = min(l, link[t].lcpnext);
- t = link[t].next;
- }
- link[r].next = t;
- link[r].lcpnext = min(l, max_match_len);
- LZX_ASSERT(t == (input_idx_t)~0U || l <= n - SA[t]);
- LZX_ASSERT(l <= n - SA[r]);
- LZX_ASSERT(memcmp(&T[SA[r]], &T[SA[t]], l) == 0);
- }
-
- /* Compute salink.prev and salink.lcpprev.
- *
- * Algorithm adapted from Crochemore et al. 2009:
- * "LPF computation revisited".
- *
- * Note: we cap lcpprev to the maximum match length so that the
- * match-finder need not worry about it later. */
- link[0].prev = (input_idx_t)~0;
- link[0].next = (input_idx_t)~0;
- link[0].lcpprev = 0;
- link[0].lcpnext = 0;
- for (input_idx_t r = 1; r < n; r++) {
- input_idx_t t = r - 1;
- input_idx_t l = LCP[r];
- while (t != (input_idx_t)~0 && SA[t] > SA[r]) {
- l = min(l, link[t].lcpprev);
- t = link[t].prev;
- }
- link[r].prev = t;
- link[r].lcpprev = min(l, max_match_len);
- LZX_ASSERT(t == (input_idx_t)~0 || l <= n - SA[t]);
- LZX_ASSERT(l <= n - SA[r]);
- LZX_ASSERT(memcmp(&T[SA[r]], &T[SA[t]], l) == 0);
- }
- }
-}
-
/* Prepare the input window into one or more LZX blocks ready to be output. */
static void
lzx_prepare_blocks(struct lzx_compressor * ctx)
{
/* Initialize the match-finder. */
- lzx_lz_init_matchfinder(ctx->window, ctx->window_size,
- ctx->SA, ctx->ISA, ctx->salink,
- LZX_MAX_MATCH_LEN);
+ lz_sarray_load_window(&ctx->lz_sarray, ctx->window, ctx->window_size);
ctx->cached_matches_pos = 0;
ctx->matches_cached = false;
ctx->match_window_pos = 0;
/* Set up a default cost model. */
- lzx_set_default_costs(&ctx->costs);
+ lzx_set_default_costs(&ctx->costs, ctx->num_main_syms);
- /* Assume that the entire input will be one LZX block. */
- ctx->block_specs[0].window_pos = 0;
- ctx->block_specs[0].block_size = ctx->window_size;
- ctx->num_blocks = 1;
+ ctx->num_blocks = DIV_ROUND_UP(ctx->window_size, LZX_DIV_BLOCK_SIZE);
+ for (unsigned i = 0; i < ctx->num_blocks; i++) {
+ unsigned pos = LZX_DIV_BLOCK_SIZE * i;
+ ctx->block_specs[i].window_pos = pos;
+ ctx->block_specs[i].block_size = min(ctx->window_size - pos, LZX_DIV_BLOCK_SIZE);
+ }
/* Determine sequence of matches/literals to output for each block. */
lzx_optimize_blocks(ctx);
* aren't worth choosing when using greedy or lazy parsing. */
.min_match = 3,
.max_match = LZX_MAX_MATCH_LEN,
+ .max_offset = LZX_MAX_WINDOW_SIZE,
.good_match = LZX_MAX_MATCH_LEN,
.nice_match = LZX_MAX_MATCH_LEN,
.max_chain_len = LZX_MAX_MATCH_LEN,
lzx_record_match,
lzx_record_literal,
&record_ctx,
- &lzx_lz_params);
-
+ &lzx_lz_params,
+ ctx->prev_tab);
/* Set up block specification. */
spec = &ctx->block_specs[0];
spec->block_size = ctx->window_size;
spec->num_chosen_matches = (record_ctx.matches - ctx->chosen_matches);
spec->chosen_matches_start_pos = 0;
- lzx_make_huffman_codes(&record_ctx.freqs, &spec->codes);
+ lzx_make_huffman_codes(&record_ctx.freqs, &spec->codes,
+ ctx->num_main_syms);
ctx->num_blocks = 1;
}
}
}
-/* API function documented in wimlib.h */
-WIMLIBAPI unsigned
-wimlib_lzx_compress2(const void * const restrict uncompressed_data,
- unsigned const uncompressed_len,
- void * const restrict compressed_data,
- struct wimlib_lzx_context * const restrict lzx_ctx)
+static size_t
+lzx_compress(const void *uncompressed_data, size_t uncompressed_size,
+ void *compressed_data, size_t compressed_size_avail, void *_ctx)
{
- struct lzx_compressor *ctx = (struct lzx_compressor*)lzx_ctx;
+ struct lzx_compressor *ctx = _ctx;
struct output_bitstream ostream;
- input_idx_t compressed_len;
+ size_t compressed_size;
- if (uncompressed_len < 100) {
+ if (uncompressed_size < 100) {
LZX_DEBUG("Too small to bother compressing.");
return 0;
}
- if (uncompressed_len > 32768) {
- LZX_DEBUG("Only up to 32768 bytes of uncompressed data are supported.");
+ if (uncompressed_size > ctx->max_window_size) {
+ LZX_DEBUG("Can't compress %zu bytes using window of %u bytes!",
+ uncompressed_size, ctx->max_window_size);
return 0;
}
- wimlib_assert(lzx_ctx != NULL);
-
- LZX_DEBUG("Attempting to compress %u bytes...", uncompressed_len);
+ LZX_DEBUG("Attempting to compress %zu bytes...",
+ uncompressed_size);
/* The input data must be preprocessed. To avoid changing the original
* input, copy it to a temporary buffer. */
- memcpy(ctx->window, uncompressed_data, uncompressed_len);
- ctx->window_size = uncompressed_len;
+ memcpy(ctx->window, uncompressed_data, uncompressed_size);
+ ctx->window_size = uncompressed_size;
/* This line is unnecessary; it just avoids inconsequential accesses of
* uninitialized memory that would show up in memory-checking tools such
LZX_DEBUG("Writing compressed blocks...");
/* Generate the compressed data. */
- init_output_bitstream(&ostream, compressed_data, ctx->window_size - 1);
+ init_output_bitstream(&ostream, compressed_data, compressed_size_avail);
lzx_write_all_blocks(ctx, &ostream);
LZX_DEBUG("Flushing bitstream...");
- compressed_len = flush_output_bitstream(&ostream);
- if (compressed_len == ~(input_idx_t)0) {
- LZX_DEBUG("Data did not compress to less than original length!");
+ compressed_size = flush_output_bitstream(&ostream);
+ if (compressed_size == ~(input_idx_t)0) {
+ LZX_DEBUG("Data did not compress to %zu bytes or less!",
+ compressed_size_avail);
return 0;
}
- LZX_DEBUG("Done: compressed %u => %u bytes.",
- uncompressed_len, compressed_len);
+ LZX_DEBUG("Done: compressed %zu => %zu bytes.",
+ uncompressed_size, compressed_size);
/* Verify that we really get the same thing back when decompressing.
* Although this could be disabled by default in all cases, it only
#endif
)
{
- u8 buf[uncompressed_len];
+ struct wimlib_decompressor *decompressor;
- if (wimlib_lzx_decompress(compressed_data, compressed_len,
- buf, uncompressed_len))
+ if (0 == wimlib_create_decompressor(WIMLIB_COMPRESSION_TYPE_LZX,
+ ctx->max_window_size,
+ NULL,
+ &decompressor))
{
- ERROR("Failed to decompress data we "
- "compressed using LZX algorithm");
- wimlib_assert(0);
- return 0;
- }
-
- if (memcmp(uncompressed_data, buf, uncompressed_len)) {
- ERROR("Data we compressed using LZX algorithm "
- "didn't decompress to original");
- wimlib_assert(0);
- return 0;
+ int ret;
+ ret = wimlib_decompress(compressed_data,
+ compressed_size,
+ ctx->window,
+ uncompressed_size,
+ decompressor);
+ wimlib_free_decompressor(decompressor);
+
+ if (ret) {
+ ERROR("Failed to decompress data we "
+ "compressed using LZX algorithm");
+ wimlib_assert(0);
+ return 0;
+ }
+ if (memcmp(uncompressed_data, ctx->window, uncompressed_size)) {
+ ERROR("Data we compressed using LZX algorithm "
+ "didn't decompress to original");
+ wimlib_assert(0);
+ return 0;
+ }
+ } else {
+ WARNING("Failed to create decompressor for "
+ "data verification!");
}
}
- return compressed_len;
-}
-
-static bool
-lzx_params_compatible(const struct wimlib_lzx_params *oldparams,
- const struct wimlib_lzx_params *newparams)
-{
- return 0 == memcmp(oldparams, newparams, sizeof(struct wimlib_lzx_params));
+ return compressed_size;
}
-static struct wimlib_lzx_params lzx_user_default_params;
-static struct wimlib_lzx_params *lzx_user_default_params_ptr;
-
static bool
-lzx_params_valid(const struct wimlib_lzx_params *params)
+lzx_params_valid(const struct wimlib_lzx_compressor_params *params)
{
/* Validate parameters. */
- if (params->size_of_this != sizeof(struct wimlib_lzx_params)) {
+ if (params->hdr.size != sizeof(struct wimlib_lzx_compressor_params)) {
LZX_DEBUG("Invalid parameter structure size!");
return false;
}
return true;
}
-/* API function documented in wimlib.h */
-WIMLIBAPI int
-wimlib_lzx_set_default_params(const struct wimlib_lzx_params * params)
+static void
+lzx_free_compressor(void *_ctx)
{
- if (params) {
- if (!lzx_params_valid(params))
- return WIMLIB_ERR_INVALID_PARAM;
- lzx_user_default_params = *params;
- lzx_user_default_params_ptr = &lzx_user_default_params;
- } else {
- lzx_user_default_params_ptr = NULL;
+ struct lzx_compressor *ctx = _ctx;
+
+ if (ctx) {
+ FREE(ctx->chosen_matches);
+ FREE(ctx->cached_matches);
+ FREE(ctx->optimum);
+ lz_sarray_destroy(&ctx->lz_sarray);
+ FREE(ctx->block_specs);
+ FREE(ctx->prev_tab);
+ FREE(ctx->window);
+ FREE(ctx);
}
- return 0;
}
-/* API function documented in wimlib.h */
-WIMLIBAPI int
-wimlib_lzx_alloc_context(const struct wimlib_lzx_params *params,
- struct wimlib_lzx_context **ctx_pp)
+static int
+lzx_create_compressor(size_t window_size,
+ const struct wimlib_compressor_params_header *_params,
+ void **ctx_ret)
{
+ const struct wimlib_lzx_compressor_params *params =
+ (const struct wimlib_lzx_compressor_params*)_params;
+ struct lzx_compressor *ctx;
LZX_DEBUG("Allocating LZX context...");
- struct lzx_compressor *ctx;
+ if (!lzx_window_size_valid(window_size))
+ return WIMLIB_ERR_INVALID_PARAM;
- static const struct wimlib_lzx_params fast_default = {
- .size_of_this = sizeof(struct wimlib_lzx_params),
+ static const struct wimlib_lzx_compressor_params fast_default = {
+ .hdr = {
+ .size = sizeof(struct wimlib_lzx_compressor_params),
+ },
.algorithm = WIMLIB_LZX_ALGORITHM_FAST,
.use_defaults = 0,
.alg_params = {
},
},
};
- static const struct wimlib_lzx_params slow_default = {
- .size_of_this = sizeof(struct wimlib_lzx_params),
+ static const struct wimlib_lzx_compressor_params slow_default = {
+ .hdr = {
+ .size = sizeof(struct wimlib_lzx_compressor_params),
+ },
.algorithm = WIMLIB_LZX_ALGORITHM_SLOW,
.use_defaults = 0,
.alg_params = {
return WIMLIB_ERR_INVALID_PARAM;
} else {
LZX_DEBUG("Using default algorithm and parameters.");
- if (lzx_user_default_params_ptr)
- params = lzx_user_default_params_ptr;
- else
- params = &slow_default;
+ params = &slow_default;
}
if (params->use_defaults) {
params = &fast_default;
}
- if (ctx_pp) {
- ctx = *(struct lzx_compressor**)ctx_pp;
-
- if (ctx && lzx_params_compatible(&ctx->params, params))
- return 0;
- } else {
- LZX_DEBUG("Check parameters only.");
- return 0;
- }
-
LZX_DEBUG("Allocating memory.");
- ctx = MALLOC(sizeof(struct lzx_compressor));
+ ctx = CALLOC(1, sizeof(struct lzx_compressor));
if (ctx == NULL)
- goto err;
-
- size_t block_specs_length;
+ goto oom;
+
+ ctx->num_main_syms = lzx_get_num_main_syms(window_size);
+ ctx->max_window_size = window_size;
+ ctx->window = MALLOC(window_size + 12);
+ if (ctx->window == NULL)
+ goto oom;
+
+ if (params->algorithm == WIMLIB_LZX_ALGORITHM_FAST) {
+ ctx->prev_tab = MALLOC(window_size * sizeof(ctx->prev_tab[0]));
+ if (ctx->prev_tab == NULL)
+ goto oom;
+ }
-#if 0
- if (params->algorithm == WIMLIB_LZX_ALGORITHM_SLOW)
- block_specs_length = 1U << params->alg_params.slow.num_split_passes;
- else
-#endif
- block_specs_length = 1U;
+ size_t block_specs_length = DIV_ROUND_UP(window_size, LZX_DIV_BLOCK_SIZE);
ctx->block_specs = MALLOC(block_specs_length * sizeof(ctx->block_specs[0]));
if (ctx->block_specs == NULL)
- goto err_free_ctx;
+ goto oom;
if (params->algorithm == WIMLIB_LZX_ALGORITHM_SLOW) {
- ctx->SA = MALLOC(3U * LZX_MAX_WINDOW_SIZE * sizeof(ctx->SA[0]));
- if (ctx->SA == NULL)
- goto err_free_block_specs;
- ctx->ISA = ctx->SA + LZX_MAX_WINDOW_SIZE;
- ctx->salink = MALLOC(LZX_MAX_WINDOW_SIZE * sizeof(ctx->salink[0]));
- if (ctx->salink == NULL)
- goto err_free_SA;
- } else {
- ctx->SA = NULL;
- ctx->ISA = NULL;
- ctx->salink = NULL;
+ unsigned min_match_len = LZX_MIN_MATCH_LEN;
+ if (!params->alg_params.slow.use_len2_matches)
+ min_match_len = max(min_match_len, 3);
+
+ if (!lz_sarray_init(&ctx->lz_sarray,
+ window_size,
+ min_match_len,
+ LZX_MAX_MATCH_LEN,
+ params->alg_params.slow.max_search_depth,
+ params->alg_params.slow.max_matches_per_pos))
+ goto oom;
}
if (params->algorithm == WIMLIB_LZX_ALGORITHM_SLOW) {
ctx->optimum = MALLOC((LZX_OPTIM_ARRAY_SIZE + LZX_MAX_MATCH_LEN) *
sizeof(ctx->optimum[0]));
if (ctx->optimum == NULL)
- goto err_free_salink;
- } else {
- ctx->optimum = NULL;
+ goto oom;
}
if (params->algorithm == WIMLIB_LZX_ALGORITHM_SLOW) {
- uint32_t cache_per_pos;
+ u32 cache_per_pos;
cache_per_pos = params->alg_params.slow.max_matches_per_pos;
if (cache_per_pos > LZX_MAX_CACHE_PER_POS)
cache_per_pos = LZX_MAX_CACHE_PER_POS;
- ctx->cached_matches = MALLOC(LZX_MAX_WINDOW_SIZE * (cache_per_pos + 1) *
+ ctx->cached_matches = MALLOC(window_size * (cache_per_pos + 1) *
sizeof(ctx->cached_matches[0]));
if (ctx->cached_matches == NULL)
- goto err_free_optimum;
- } else {
- ctx->cached_matches = NULL;
+ goto oom;
}
- ctx->chosen_matches = MALLOC(LZX_MAX_WINDOW_SIZE *
- sizeof(ctx->chosen_matches[0]));
+ ctx->chosen_matches = MALLOC(window_size * sizeof(ctx->chosen_matches[0]));
if (ctx->chosen_matches == NULL)
- goto err_free_cached_matches;
+ goto oom;
- memcpy(&ctx->params, params, sizeof(struct wimlib_lzx_params));
+ memcpy(&ctx->params, params, sizeof(struct wimlib_lzx_compressor_params));
memset(&ctx->zero_codes, 0, sizeof(ctx->zero_codes));
LZX_DEBUG("Successfully allocated new LZX context.");
- wimlib_lzx_free_context(*ctx_pp);
- *ctx_pp = (struct wimlib_lzx_context*)ctx;
+ *ctx_ret = ctx;
return 0;
-err_free_cached_matches:
- FREE(ctx->cached_matches);
-err_free_optimum:
- FREE(ctx->optimum);
-err_free_salink:
- FREE(ctx->salink);
-err_free_SA:
- FREE(ctx->SA);
-err_free_block_specs:
- FREE(ctx->block_specs);
-err_free_ctx:
- FREE(ctx);
-err:
- LZX_DEBUG("Ran out of memory.");
+oom:
+ lzx_free_compressor(ctx);
return WIMLIB_ERR_NOMEM;
}
-/* API function documented in wimlib.h */
-WIMLIBAPI void
-wimlib_lzx_free_context(struct wimlib_lzx_context *_ctx)
-{
- struct lzx_compressor *ctx = (struct lzx_compressor*)_ctx;
-
- if (ctx) {
- FREE(ctx->chosen_matches);
- FREE(ctx->cached_matches);
- FREE(ctx->optimum);
- FREE(ctx->salink);
- FREE(ctx->SA);
- FREE(ctx->block_specs);
- FREE(ctx);
- }
-}
-
-/* API function documented in wimlib.h */
-WIMLIBAPI unsigned
-wimlib_lzx_compress(const void * const restrict uncompressed_data,
- unsigned const uncompressed_len,
- void * const restrict compressed_data)
-{
- int ret;
- struct wimlib_lzx_context *ctx = NULL;
- unsigned compressed_len;
-
- ret = wimlib_lzx_alloc_context(NULL, &ctx);
- if (ret) {
- wimlib_assert(ret != WIMLIB_ERR_INVALID_PARAM);
- WARNING("Couldn't allocate LZX compression context: %"TS"",
- wimlib_get_error_string(ret));
- return 0;
- }
-
- compressed_len = wimlib_lzx_compress2(uncompressed_data,
- uncompressed_len,
- compressed_data,
- ctx);
-
- wimlib_lzx_free_context(ctx);
-
- return compressed_len;
-}
+const struct compressor_ops lzx_compressor_ops = {
+ .create_compressor = lzx_create_compressor,
+ .compress = lzx_compress,
+ .free_compressor = lzx_free_compressor,
+};