lzma.h | lzma.h | |||
---|---|---|---|---|
skipping to change at line 47 | skipping to change at line 47 | |||
* lc/lp/pb in the middle of encoding, and some other internal improvements . | * lc/lp/pb in the middle of encoding, and some other internal improvements . | |||
*/ | */ | |||
#define LZMA_FILTER_LZMA2 LZMA_VLI_C(0x21) | #define LZMA_FILTER_LZMA2 LZMA_VLI_C(0x21) | |||
/** | /** | |||
* \brief Match finders | * \brief Match finders | |||
* | * | |||
* Match finder has major effect on both speed and compression ratio. | * Match finder has major effect on both speed and compression ratio. | |||
* Usually hash chains are faster than binary trees. | * Usually hash chains are faster than binary trees. | |||
* | * | |||
* If you will use LZMA_SYNC_FLUSH often, the hash chains may be a better | ||||
* choice, because binary trees get much higher compression ratio penalty | ||||
* with LZMA_SYNC_FLUSH. | ||||
* | ||||
* The memory usage formulas are only rough estimates, which are closest to | * The memory usage formulas are only rough estimates, which are closest to | |||
* reality when dict_size is a power of two. The formulas are more complex | * reality when dict_size is a power of two. The formulas are more complex | |||
* in reality, and can also change a little between liblzma versions. Use | * in reality, and can also change a little between liblzma versions. Use | |||
* lzma_raw_encoder_memusage() to get more accurate estimate of memory usag e. | * lzma_memusage_encoder() to get more accurate estimate of memory usage. | |||
*/ | */ | |||
typedef enum { | typedef enum { | |||
LZMA_MF_HC3 = 0x03, | LZMA_MF_HC3 = 0x03, | |||
/**< | /**< | |||
* \brief Hash Chain with 2- and 3-byte hashing | * \brief Hash Chain with 2- and 3-byte hashing | |||
* | * | |||
* Minimum nice_len: 3 | * Minimum nice_len: 3 | |||
* | * | |||
* Memory usage: | * Memory usage: | |||
* - dict_size <= 16 MiB: dict_size * 7.5 | * - dict_size <= 16 MiB: dict_size * 7.5 | |||
* - dict_size > 16 MiB: dict_size * 5.5 + 64 MiB | * - dict_size > 16 MiB: dict_size * 5.5 + 64 MiB | |||
*/ | */ | |||
LZMA_MF_HC4 = 0x04, | LZMA_MF_HC4 = 0x04, | |||
/**< | /**< | |||
* \brief Hash Chain with 2-, 3-, and 4-byte hashing | * \brief Hash Chain with 2-, 3-, and 4-byte hashing | |||
* | * | |||
* Minimum nice_len: 4 | * Minimum nice_len: 4 | |||
* | * | |||
* Memory usage: | * Memory usage: dict_size * 7.5 | |||
* - dict_size <= 32 MiB: dict_size * 7.5 | ||||
* - dict_size > 32 MiB: dict_size * 6.5 | ||||
*/ | */ | |||
LZMA_MF_BT2 = 0x12, | LZMA_MF_BT2 = 0x12, | |||
/**< | /**< | |||
* \brief Binary Tree with 2-byte hashing | * \brief Binary Tree with 2-byte hashing | |||
* | * | |||
* Minimum nice_len: 2 | * Minimum nice_len: 2 | |||
* | * | |||
* Memory usage: dict_size * 9.5 | * Memory usage: dict_size * 9.5 | |||
*/ | */ | |||
skipping to change at line 105 | skipping to change at line 99 | |||
* - dict_size <= 16 MiB: dict_size * 11.5 | * - dict_size <= 16 MiB: dict_size * 11.5 | |||
* - dict_size > 16 MiB: dict_size * 9.5 + 64 MiB | * - dict_size > 16 MiB: dict_size * 9.5 + 64 MiB | |||
*/ | */ | |||
LZMA_MF_BT4 = 0x14 | LZMA_MF_BT4 = 0x14 | |||
/**< | /**< | |||
* \brief Binary Tree with 2-, 3-, and 4-byte hashing | * \brief Binary Tree with 2-, 3-, and 4-byte hashing | |||
* | * | |||
* Minimum nice_len: 4 | * Minimum nice_len: 4 | |||
* | * | |||
* Memory usage: | * Memory usage: dict_size * 11.5 | |||
* - dict_size <= 32 MiB: dict_size * 11.5 | ||||
* - dict_size > 32 MiB: dict_size * 10.5 | ||||
*/ | */ | |||
} lzma_match_finder; | } lzma_match_finder; | |||
/** | /** | |||
* \brief Test if given match finder is supported | * \brief Test if given match finder is supported | |||
* | * | |||
* Return true if the given match finder is supported by this liblzma build . | * Return true if the given match finder is supported by this liblzma build . | |||
* Otherwise false is returned. It is safe to call this with a value that | * Otherwise false is returned. It is safe to call this with a value that | |||
* isn't listed in lzma_match_finder enumeration; the return value will be | * isn't listed in lzma_match_finder enumeration; the return value will be | |||
* false. | * false. | |||
skipping to change at line 174 | skipping to change at line 166 | |||
*/ | */ | |||
extern LZMA_API(lzma_bool) lzma_mode_is_supported(lzma_mode mode) | extern LZMA_API(lzma_bool) lzma_mode_is_supported(lzma_mode mode) | |||
lzma_nothrow lzma_attr_const; | lzma_nothrow lzma_attr_const; | |||
/** | /** | |||
* \brief Options specific to the LZMA1 and LZMA2 filters | * \brief Options specific to the LZMA1 and LZMA2 filters | |||
* | * | |||
* Since LZMA1 and LZMA2 share most of the code, it's simplest to share | * Since LZMA1 and LZMA2 share most of the code, it's simplest to share | |||
* the options structure too. For encoding, all but the reserved variables | * the options structure too. For encoding, all but the reserved variables | |||
* need to be initialized unless specifically mentioned otherwise. | * need to be initialized unless specifically mentioned otherwise. | |||
* lzma_lzma_preset() can be used to get a good starting point. | ||||
* | * | |||
* For raw decoding, both LZMA1 and LZMA2 need dict_size, preset_dict, and | * For raw decoding, both LZMA1 and LZMA2 need dict_size, preset_dict, and | |||
* preset_dict_size (if preset_dict != NULL). LZMA1 needs also lc, lp, and pb. | * preset_dict_size (if preset_dict != NULL). LZMA1 needs also lc, lp, and pb. | |||
*/ | */ | |||
typedef struct { | typedef struct { | |||
/** | /** | |||
* \brief Dictionary size in bytes | * \brief Dictionary size in bytes | |||
* | * | |||
* Dictionary size indicates how many bytes of the recently processe d | * Dictionary size indicates how many bytes of the recently processe d | |||
* uncompressed data is kept in memory. One method to reduce size of | * uncompressed data is kept in memory. One method to reduce size of | |||
skipping to change at line 257 | skipping to change at line 248 | |||
*/ | */ | |||
uint32_t preset_dict_size; | uint32_t preset_dict_size; | |||
/** | /** | |||
* \brief Number of literal context bits | * \brief Number of literal context bits | |||
* | * | |||
* How many of the highest bits of the previous uncompressed | * How many of the highest bits of the previous uncompressed | |||
* eight-bit byte (also known as `literal') are taken into | * eight-bit byte (also known as `literal') are taken into | |||
* account when predicting the bits of the next literal. | * account when predicting the bits of the next literal. | |||
* | * | |||
* E.g. in typical English text, an upper-case letter is | * \todo Example | |||
* often followed by a lower-case letter, and a lower-case | ||||
* letter is usually followed by another lower-case letter. | ||||
* In the US-ASCII character set, the highest three bits are 010 | ||||
* for upper-case letters and 011 for lower-case letters. | ||||
* When lc is at least 3, the literal coding can take advantage of | ||||
* this property in the uncompressed data. | ||||
* | * | |||
* There is a limit that applies to literal context bits and literal | * There is a limit that applies to literal context bits and literal | |||
* position bits together: lc + lp <= 4. Without this limit the | * position bits together: lc + lp <= 4. Without this limit the | |||
* decoding could become very slow, which could have security relate d | * decoding could become very slow, which could have security relate d | |||
* results in some cases like email servers doing virus scanning. | * results in some cases like email servers doing virus scanning. | |||
* This limit also simplifies the internal implementation in liblzma . | * This limit also simplifies the internal implementation in liblzma . | |||
* | * | |||
* There may be LZMA1 streams that have lc + lp > 4 (maximum possibl e | * There may be LZMA1 streams that have lc + lp > 4 (maximum possibl e | |||
* lc would be 8). It is not possible to decode such streams with | * lc would be 8). It is not possible to decode such streams with | |||
* liblzma. | * liblzma. | |||
*/ | */ | |||
uint32_t lc; | uint32_t lc; | |||
# define LZMA_LCLP_MIN 0 | # define LZMA_LCLP_MIN 0 | |||
# define LZMA_LCLP_MAX 4 | # define LZMA_LCLP_MAX 4 | |||
# define LZMA_LC_DEFAULT 3 | # define LZMA_LC_DEFAULT 3 | |||
/** | /** | |||
* \brief Number of literal position bits | * \brief Number of literal position bits | |||
* | * | |||
* lp affects what kind of alignment in the uncompressed data is | * How many of the lowest bits of the current position (number | |||
* assumed when encoding literals. A literal is a single 8-bit byte. | * of bytes from the beginning of the uncompressed data) in the | |||
* See pb below for more information about alignment. | * uncompressed data is taken into account when predicting the | |||
* bits of the next literal (a single eight-bit byte). | ||||
* | ||||
* \todo Example | ||||
*/ | */ | |||
uint32_t lp; | uint32_t lp; | |||
# define LZMA_LP_DEFAULT 0 | # define LZMA_LP_DEFAULT 0 | |||
/** | /** | |||
* \brief Number of position bits | * \brief Number of position bits | |||
* | * | |||
* pb affects what kind of alignment in the uncompressed data is | * How many of the lowest bits of the current position in the | |||
* assumed in general. The default means four-byte alignment | * uncompressed data is taken into account when estimating | |||
* (2^ pb =2^2=4), which is often a good choice when there's | * probabilities of matches. A match is a sequence of bytes for | |||
* no better guess. | * which a matching sequence is found from the dictionary and | |||
* | * thus can be stored as distance-length pair. | |||
* When the aligment is known, setting pb accordingly may reduce | * | |||
* the file size a little. E.g. with text files having one-byte | * Example: If most of the matches occur at byte positions of | |||
* alignment (US-ASCII, ISO-8859-*, UTF-8), setting pb=0 can | * 8 * n + 3, that is, 3, 11, 19, ... set pb to 3, because 2**3 == 8 | |||
* improve compression slightly. For UTF-16 text, pb=1 is a good | . | |||
* choice. If the alignment is an odd number like 3 bytes, pb=0 | ||||
* might be the best choice. | ||||
* | ||||
* Even though the assumed alignment can be adjusted with pb and | ||||
* lp, LZMA1 and LZMA2 still slightly favor 16-byte alignment. | ||||
* It might be worth taking into account when designing file formats | ||||
* that are likely to be often compressed with LZMA1 or LZMA2. | ||||
*/ | */ | |||
uint32_t pb; | uint32_t pb; | |||
# define LZMA_PB_MIN 0 | # define LZMA_PB_MIN 0 | |||
# define LZMA_PB_MAX 4 | # define LZMA_PB_MAX 4 | |||
# define LZMA_PB_DEFAULT 2 | # define LZMA_PB_DEFAULT 2 | |||
/** Compression mode */ | /** Compression mode */ | |||
lzma_mode mode; | lzma_mode mode; | |||
/** | /** | |||
skipping to change at line 359 | skipping to change at line 339 | |||
* been checked; or | * been checked; or | |||
* - maximum search depth is reached. | * - maximum search depth is reached. | |||
* | * | |||
* Maximum search depth is needed to prevent the match finder from | * Maximum search depth is needed to prevent the match finder from | |||
* wasting too much time in case there are lots of short match | * wasting too much time in case there are lots of short match | |||
* candidates. On the other hand, stopping the search before all | * candidates. On the other hand, stopping the search before all | |||
* candidates have been checked can reduce compression ratio. | * candidates have been checked can reduce compression ratio. | |||
* | * | |||
* Setting depth to zero tells liblzma to use an automatic default | * Setting depth to zero tells liblzma to use an automatic default | |||
* value, that depends on the selected match finder and nice_len. | * value, that depends on the selected match finder and nice_len. | |||
* The default is in the range [4, 200] or so (it may vary between | * The default is in the range [10, 200] or so (it may vary between | |||
* liblzma versions). | * liblzma versions). | |||
* | * | |||
* Using a bigger depth value than the default can increase | * Using a bigger depth value than the default can increase | |||
* compression ratio in some cases. There is no strict maximum value , | * compression ratio in some cases. There is no strict maximum value , | |||
* but high values (thousands or millions) should be used with care: | * but high values (thousands or millions) should be used with care: | |||
* the encoder could remain fast enough with typical input, but | * the encoder could remain fast enough with typical input, but | |||
* malicious input could cause the match finder to slow down | * malicious input could cause the match finder to slow down | |||
* dramatically, possibly creating a denial of service attack. | * dramatically, possibly creating a denial of service attack. | |||
*/ | */ | |||
uint32_t depth; | uint32_t depth; | |||
/* | /* | |||
* Reserved space to allow possible future extensions without | * Reserved space to allow possible future extensions without | |||
* breaking the ABI. You should not touch these, because the names | * breaking the ABI. You should not touch these, because the names | |||
* of these variables may change. These are and will never be used | * of these variables may change. These are and will never be used | |||
* with the currently supported options, so it is safe to leave thes e | * with the currently supported options, so it is safe to leave thes e | |||
* uninitialized. | * uninitialized. | |||
*/ | */ | |||
void *reserved_ptr1; | ||||
void *reserved_ptr2; | ||||
uint32_t reserved_int1; | uint32_t reserved_int1; | |||
uint32_t reserved_int2; | uint32_t reserved_int2; | |||
uint32_t reserved_int3; | uint32_t reserved_int3; | |||
uint32_t reserved_int4; | uint32_t reserved_int4; | |||
uint32_t reserved_int5; | uint32_t reserved_int5; | |||
uint32_t reserved_int6; | uint32_t reserved_int6; | |||
uint32_t reserved_int7; | uint32_t reserved_int7; | |||
uint32_t reserved_int8; | uint32_t reserved_int8; | |||
lzma_reserved_enum reserved_enum1; | lzma_reserved_enum reserved_enum1; | |||
lzma_reserved_enum reserved_enum2; | lzma_reserved_enum reserved_enum2; | |||
lzma_reserved_enum reserved_enum3; | lzma_reserved_enum reserved_enum3; | |||
lzma_reserved_enum reserved_enum4; | lzma_reserved_enum reserved_enum4; | |||
void *reserved_ptr1; | ||||
void *reserved_ptr2; | ||||
} lzma_options_lzma; | } lzma_options_lzma; | |||
/** | /** | |||
* \brief Set a compression preset to lzma_options_lzma structure | * \brief Set a compression preset to lzma_options_lzma structure | |||
* | * | |||
* 0 is the fastest and 9 is the slowest. These match the switches -0 .. -9 | * 0 is the fastest and 9 is the slowest. These match the switches -0 .. -9 | |||
* of the xz command line tool. In addition, it is possible to bitwise-or | * of the xz command line tool. In addition, it is possible to bitwise-or | |||
* flags to the preset. Currently only LZMA_PRESET_EXTREME is supported. | * flags to the preset. Currently only LZMA_PRESET_EXTREME is supported. | |||
* The flags are defined in container.h, because the flags are used also | * The flags are defined in container.h, because the flags are used also | |||
* with lzma_easy_encoder(). | * with lzma_easy_encoder(). | |||
* | * | |||
* The preset values are subject to changes between liblzma versions. | * The preset values are subject to changes between liblzma versions. | |||
* | * | |||
* This function is available only if LZMA1 or LZMA2 encoder has been enabl ed | * This function is available only if LZMA1 or LZMA2 encoder has been enabl ed | |||
* when building liblzma. | * when building liblzma. | |||
* | ||||
* \return On success, false is returned. If the preset is not | ||||
* supported, true is returned. | ||||
*/ | */ | |||
extern LZMA_API(lzma_bool) lzma_lzma_preset( | extern LZMA_API(lzma_bool) lzma_lzma_preset( | |||
lzma_options_lzma *options, uint32_t preset) lzma_nothrow; | lzma_options_lzma *options, uint32_t preset) lzma_nothrow; | |||
End of changes. 12 change blocks. | ||||
44 lines changed or deleted | 22 lines changed or added | |||
This html diff was produced by rfcdiff 1.41. The latest version is available from http://tools.ietf.org/tools/rfcdiff/ |