From 602ce69afb7c825a5aeed16d0bdb5a6a213d1cb1 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Sun, 30 May 2010 03:35:18 +0200 Subject: unxz: new applet, complete with xzcat and xz -d aliases function old new delta unpack_xz_stream_stdin - 3953 +3953 lzma_main - 2601 +2601 lzma_len - 516 +516 dec_vli - 165 +165 dict_repeat - 103 +103 lzma_reset - 98 +98 fill_temp - 98 +98 crc32_validate - 93 +93 xz_dec_reset - 77 +77 unxz_main - 77 +77 index_update - 47 +47 xz_crc32 - 40 +40 packed_usage 27044 27060 +16 make_new_name_unxz - 14 +14 applet_names 2240 2254 +14 applet_main 1312 1324 +12 applet_nameofs 656 662 +6 unpack_unxz - 5 +5 send_tree 355 360 +5 applet_install_loc 164 166 +2 ------------------------------------------------------------------------------ (add/remove: 15/0 grow/shrink: 6/0 up/down: 7942/0) Total: 7942 bytes text data bss dec hex filename 844032 453 6812 851297 cfd61 busybox_old 852063 453 6812 859328 d1cc0 busybox_unstripped Signed-off-by: Denys Vlasenko --- archival/libunarchive/unxz/xz_lzma2.h | 204 ++++++++++++++++++++++++++++++++++ 1 file changed, 204 insertions(+) create mode 100644 archival/libunarchive/unxz/xz_lzma2.h (limited to 'archival/libunarchive/unxz/xz_lzma2.h') diff --git a/archival/libunarchive/unxz/xz_lzma2.h b/archival/libunarchive/unxz/xz_lzma2.h new file mode 100644 index 000000000..47f21afbc --- /dev/null +++ b/archival/libunarchive/unxz/xz_lzma2.h @@ -0,0 +1,204 @@ +/* + * LZMA2 definitions + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_LZMA2_H +#define XZ_LZMA2_H + +/* Range coder constants */ +#define RC_SHIFT_BITS 8 +#define RC_TOP_BITS 24 +#define RC_TOP_VALUE (1 << RC_TOP_BITS) +#define RC_BIT_MODEL_TOTAL_BITS 11 +#define RC_BIT_MODEL_TOTAL (1 << RC_BIT_MODEL_TOTAL_BITS) +#define RC_MOVE_BITS 5 + +/* + * Maximum number of position states. A position state is the lowest pb + * number of bits of the current uncompressed offset. In some places there + * are different sets of probabilities for different position states. + */ +#define POS_STATES_MAX (1 << 4) + +/* + * This enum is used to track which LZMA symbols have occurred most recently + * and in which order. This information is used to predict the next symbol. + * + * Symbols: + * - Literal: One 8-bit byte + * - Match: Repeat a chunk of data at some distance + * - Long repeat: Multi-byte match at a recently seen distance + * - Short repeat: One-byte repeat at a recently seen distance + * + * The symbol names are in from STATE_oldest_older_previous. REP means + * either short or long repeated match, and NONLIT means any non-literal. + */ +enum lzma_state { + STATE_LIT_LIT, + STATE_MATCH_LIT_LIT, + STATE_REP_LIT_LIT, + STATE_SHORTREP_LIT_LIT, + STATE_MATCH_LIT, + STATE_REP_LIT, + STATE_SHORTREP_LIT, + STATE_LIT_MATCH, + STATE_LIT_LONGREP, + STATE_LIT_SHORTREP, + STATE_NONLIT_MATCH, + STATE_NONLIT_REP +}; + +/* Total number of states */ +#define STATES 12 + +/* The lowest 7 states indicate that the previous state was a literal. */ +#define LIT_STATES 7 + +/* Indicate that the latest symbol was a literal. */ +static inline void XZ_FUNC lzma_state_literal(enum lzma_state *state) +{ + if (*state <= STATE_SHORTREP_LIT_LIT) + *state = STATE_LIT_LIT; + else if (*state <= STATE_LIT_SHORTREP) + *state -= 3; + else + *state -= 6; +} + +/* Indicate that the latest symbol was a match. */ +static inline void XZ_FUNC lzma_state_match(enum lzma_state *state) +{ + *state = *state < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH; +} + +/* Indicate that the latest state was a long repeated match. */ +static inline void XZ_FUNC lzma_state_long_rep(enum lzma_state *state) +{ + *state = *state < LIT_STATES ? STATE_LIT_LONGREP : STATE_NONLIT_REP; +} + +/* Indicate that the latest symbol was a short match. */ +static inline void XZ_FUNC lzma_state_short_rep(enum lzma_state *state) +{ + *state = *state < LIT_STATES ? STATE_LIT_SHORTREP : STATE_NONLIT_REP; +} + +/* Test if the previous symbol was a literal. */ +static inline bool XZ_FUNC lzma_state_is_literal(enum lzma_state state) +{ + return state < LIT_STATES; +} + +/* Each literal coder is divided in three sections: + * - 0x001-0x0FF: Without match byte + * - 0x101-0x1FF: With match byte; match bit is 0 + * - 0x201-0x2FF: With match byte; match bit is 1 + * + * Match byte is used when the previous LZMA symbol was something else than + * a literal (that is, it was some kind of match). + */ +#define LITERAL_CODER_SIZE 0x300 + +/* Maximum number of literal coders */ +#define LITERAL_CODERS_MAX (1 << 4) + +/* Minimum length of a match is two bytes. */ +#define MATCH_LEN_MIN 2 + +/* Match length is encoded with 4, 5, or 10 bits. + * + * Length Bits + * 2-9 4 = Choice=0 + 3 bits + * 10-17 5 = Choice=1 + Choice2=0 + 3 bits + * 18-273 10 = Choice=1 + Choice2=1 + 8 bits + */ +#define LEN_LOW_BITS 3 +#define LEN_LOW_SYMBOLS (1 << LEN_LOW_BITS) +#define LEN_MID_BITS 3 +#define LEN_MID_SYMBOLS (1 << LEN_MID_BITS) +#define LEN_HIGH_BITS 8 +#define LEN_HIGH_SYMBOLS (1 << LEN_HIGH_BITS) +#define LEN_SYMBOLS (LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS + LEN_HIGH_SYMBOLS) + +/* + * Maximum length of a match is 273 which is a result of the encoding + * described above. + */ +#define MATCH_LEN_MAX (MATCH_LEN_MIN + LEN_SYMBOLS - 1) + +/* + * Different sets of probabilities are used for match distances that have + * very short match length: Lengths of 2, 3, and 4 bytes have a separate + * set of probabilities for each length. The matches with longer length + * use a shared set of probabilities. + */ +#define DIST_STATES 4 + +/* + * Get the index of the appropriate probability array for decoding + * the distance slot. + */ +static inline uint32_t XZ_FUNC lzma_get_dist_state(uint32_t len) +{ + return len < DIST_STATES + MATCH_LEN_MIN + ? len - MATCH_LEN_MIN : DIST_STATES - 1; +} + +/* + * The highest two bits of a 32-bit match distance are encoded using six bits. + * This six-bit value is called a distance slot. This way encoding a 32-bit + * value takes 6-36 bits, larger values taking more bits. + */ +#define DIST_SLOT_BITS 6 +#define DIST_SLOTS (1 << DIST_SLOT_BITS) + +/* Match distances up to 127 are fully encoded using probabilities. Since + * the highest two bits (distance slot) are always encoded using six bits, + * the distances 0-3 don't need any additional bits to encode, since the + * distance slot itself is the same as the actual distance. DIST_MODEL_START + * indicates the first distance slot where at least one additional bit is + * needed. + */ +#define DIST_MODEL_START 4 + +/* + * Match distances greater than 127 are encoded in three pieces: + * - distance slot: the highest two bits + * - direct bits: 2-26 bits below the highest two bits + * - alignment bits: four lowest bits + * + * Direct bits don't use any probabilities. + * + * The distance slot value of 14 is for distances 128-191. + */ +#define DIST_MODEL_END 14 + +/* Distance slots that indicate a distance <= 127. */ +#define FULL_DISTANCES_BITS (DIST_MODEL_END / 2) +#define FULL_DISTANCES (1 << FULL_DISTANCES_BITS) + +/* + * For match distances greater than 127, only the highest two bits and the + * lowest four bits (alignment) is encoded using probabilities. + */ +#define ALIGN_BITS 4 +#define ALIGN_SIZE (1 << ALIGN_BITS) +#define ALIGN_MASK (ALIGN_SIZE - 1) + +/* Total number of all probability variables */ +#define PROBS_TOTAL (1846 + LITERAL_CODERS_MAX * LITERAL_CODER_SIZE) + +/* + * LZMA remembers the four most recent match distances. Reusing these + * distances tends to take less space than re-encoding the actual + * distance value. + */ +#define REPS 4 + +#endif -- cgit v1.2.3