#include "postgres.h"
#include <limits.h>
#include "common/pg_lzcompress.h"

Include dependency graph for pg_lzcompress.c:

Data Structures
struct	PGLZ_HistEntry

Macros
#define	PGLZ_MAX_HISTORY_LISTS 8192 /* must be power of 2 */

#define	PGLZ_HISTORY_SIZE 4096

#define	PGLZ_MAX_MATCH 273

#define	INVALID_ENTRY 0

#define	INVALID_ENTRY_PTR (&hist_entries[INVALID_ENTRY])

#define	pglz_hist_idx(_s, _e, _mask)

#define	pglz_hist_add(_hs, _he, _hn, _recycle, _s, _e, _mask)

#define	pglz_out_ctrl(__ctrlp, __ctrlb, __ctrl, __buf)

#define	pglz_out_literal(_ctrlp, _ctrlb, _ctrl, _buf, _byte)

#define	pglz_out_tag(_ctrlp, _ctrlb, _ctrl, _buf, _len, _off)

Typedefs
typedef struct PGLZ_HistEntry	PGLZ_HistEntry

Functions
static int	pglz_find_match (int16 hstart, const char input, const char end, int lenp, int *offp, int good_match, int good_drop, int mask)

int32	pglz_compress (const char source, int32 slen, char dest, const PGLZ_Strategy *strategy)

int32	pglz_decompress (const char source, int32 slen, char dest, int32 rawsize, bool check_complete)

int32	pglz_maximum_compressed_size (int32 rawsize, int32 total_compressed_size)

Variables
static const PGLZ_Strategy	strategy_default_data

const PGLZ_Strategy *const	PGLZ_strategy_default = &strategy_default_data

static const PGLZ_Strategy	strategy_always_data

const PGLZ_Strategy *const	PGLZ_strategy_always = &strategy_always_data

static int16	hist_start [PGLZ_MAX_HISTORY_LISTS]

static PGLZ_HistEntry	hist_entries [PGLZ_HISTORY_SIZE+1]

Macro Definition Documentation

◆ INVALID_ENTRY

#define INVALID_ENTRY 0

Definition at line 262 of file pg_lzcompress.c.

◆ INVALID_ENTRY_PTR

#define INVALID_ENTRY_PTR (&hist_entries[INVALID_ENTRY])

Definition at line 263 of file pg_lzcompress.c.

◆ pglz_hist_add

#define pglz_hist_add	(	_hs,
		_he,
		_hn,
		_recycle,
		_s,
		_e,
		_mask
	)

Definition at line 296 of file pg_lzcompress.c.

◆ pglz_hist_idx

#define pglz_hist_idx	(	_s,
		_e,
		_mask
	)

Value:

            (                                       \
            ((((_e) - (_s)) < 4) ? (int) (_s)[0] :                          \
             (((_s)[0] << 6) ^ ((_s)[1] << 4) ^                             \
              ((_s)[2] << 2) ^ (_s)[3])) & (_mask)              \
        )

Definition at line 277 of file pg_lzcompress.c.

◆ PGLZ_HISTORY_SIZE

#define PGLZ_HISTORY_SIZE 4096

Definition at line 196 of file pg_lzcompress.c.

◆ PGLZ_MAX_HISTORY_LISTS

#define PGLZ_MAX_HISTORY_LISTS 8192 /* must be power of 2 */

Definition at line 195 of file pg_lzcompress.c.

◆ PGLZ_MAX_MATCH

#define PGLZ_MAX_MATCH 273

Definition at line 197 of file pg_lzcompress.c.

◆ pglz_out_ctrl

#define pglz_out_ctrl	(	__ctrlp,
		__ctrlb,
		__ctrl,
		__buf
	)

Value:

do { \
    if ((__ctrl & 0xff) == 0)                                               \
    {                                                                       \
        *(__ctrlp) = __ctrlb;                                               \
        __ctrlp = (__buf)++;                                                \
        __ctrlb = 0;                                                        \
        __ctrl = 1;                                                         \
    }                                                                       \
} while (0)

Definition at line 336 of file pg_lzcompress.c.

◆ pglz_out_literal

#define pglz_out_literal	(	_ctrlp,
		_ctrlb,
		_ctrl,
		_buf,
		_byte
	)

Value:

do { \
    pglz_out_ctrl(_ctrlp,_ctrlb,_ctrl,_buf);                                \
    *(_buf)++ = (unsigned char)(_byte);                                     \
    _ctrl <<= 1;                                                            \
} while (0)

Definition at line 355 of file pg_lzcompress.c.

◆ pglz_out_tag

#define pglz_out_tag	(	_ctrlp,
		_ctrlb,
		_ctrl,
		_buf,
		_len,
		_off
	)

Value:

do { \
    pglz_out_ctrl(_ctrlp,_ctrlb,_ctrl,_buf);                                \
    _ctrlb |= _ctrl;                                                        \
    _ctrl <<= 1;                                                            \
    if (_len > 17)                                                          \
    {                                                                       \
        (_buf)[0] = (unsigned char)((((_off) & 0xf00) >> 4) | 0x0f);        \
        (_buf)[1] = (unsigned char)(((_off) & 0xff));                       \
        (_buf)[2] = (unsigned char)((_len) - 18);                           \
        (_buf) += 3;                                                        \
    } else {                                                                \
        (_buf)[0] = (unsigned char)((((_off) & 0xf00) >> 4) | ((_len) - 3)); \
        (_buf)[1] = (unsigned char)((_off) & 0xff);                         \
        (_buf) += 2;                                                        \
    }                                                                       \
} while (0)

Definition at line 371 of file pg_lzcompress.c.

Typedef Documentation

◆ PGLZ_HistEntry

typedef struct PGLZ_HistEntry PGLZ_HistEntry

Function Documentation

◆ pglz_compress()

int32 pglz_compress	(	const char *	source,
		int32	slen,
		char *	dest,
		const PGLZ_Strategy *	strategy
	)

Definition at line 509 of file pg_lzcompress.c.

{
    unsigned char *bp = (unsigned char *) dest;
    unsigned char *bstart = bp;
    int         hist_next = 1;
    bool        hist_recycle = false;
    const char *dp = source;
    const char *dend = source + slen;
    unsigned char ctrl_dummy = 0;
    unsigned char *ctrlp = &ctrl_dummy;
    unsigned char ctrlb = 0;
    unsigned char ctrl = 0;
    bool        found_match = false;
    int32       match_len;
    int32       match_off;
    int32       good_match;
    int32       good_drop;
    int32       result_size;
    int32       result_max;
    int32       need_rate;
    int         hashsz;
    int         mask;
 
    /*
     * Our fallback strategy is the default.
     */
    if (strategy == NULL)
        strategy = PGLZ_strategy_default;
 
    /*
     * If the strategy forbids compression (at all or if source chunk size out
     * of range), fail.
     */
    if (strategy->match_size_good <= 0 ||
        slen < strategy->min_input_size ||
        slen > strategy->max_input_size)
        return -1;
 
    /*
     * Limit the match parameters to the supported range.
     */
    good_match = strategy->match_size_good;
    if (good_match > PGLZ_MAX_MATCH)
        good_match = PGLZ_MAX_MATCH;
    else if (good_match < 17)
        good_match = 17;
 
    good_drop = strategy->match_size_drop;
    if (good_drop < 0)
        good_drop = 0;
    else if (good_drop > 100)
        good_drop = 100;
 
    need_rate = strategy->min_comp_rate;
    if (need_rate < 0)
        need_rate = 0;
    else if (need_rate > 99)
        need_rate = 99;
 
    /*
     * Compute the maximum result size allowed by the strategy, namely the
     * input size minus the minimum wanted compression rate.  This had better
     * be <= slen, else we might overrun the provided output buffer.
     */
    if (slen > (INT_MAX / 100))
    {
        /* Approximate to avoid overflow */
        result_max = (slen / 100) * (100 - need_rate);
    }
    else
        result_max = (slen * (100 - need_rate)) / 100;
 
    /*
     * Experiments suggest that these hash sizes work pretty well. A large
     * hash table minimizes collision, but has a higher startup cost. For a
     * small input, the startup cost dominates. The table size must be a power
     * of two.
     */
    if (slen < 128)
        hashsz = 512;
    else if (slen < 256)
        hashsz = 1024;
    else if (slen < 512)
        hashsz = 2048;
    else if (slen < 1024)
        hashsz = 4096;
    else
        hashsz = 8192;
    mask = hashsz - 1;
 
    /*
     * Initialize the history lists to empty.  We do not need to zero the
     * hist_entries[] array; its entries are initialized as they are used.
     */
    memset(hist_start, 0, hashsz * sizeof(int16));
 
    /*
     * Compress the source directly into the output buffer.
     */
    while (dp < dend)
    {
        /*
         * If we already exceeded the maximum result size, fail.
         *
         * We check once per loop; since the loop body could emit as many as 4
         * bytes (a control byte and 3-byte tag), PGLZ_MAX_OUTPUT() had better
         * allow 4 slop bytes.
         */
        if (bp - bstart >= result_max)
            return -1;
 
        /*
         * If we've emitted more than first_success_by bytes without finding
         * anything compressible at all, fail.  This lets us fall out
         * reasonably quickly when looking at incompressible input (such as
         * pre-compressed data).
         */
        if (!found_match && bp - bstart >= strategy->first_success_by)
            return -1;
 
        /*
         * Try to find a match in the history
         */
        if (pglz_find_match(hist_start, dp, dend, &match_len,
                            &match_off, good_match, good_drop, mask))
        {
            /*
             * Create the tag and add history entries for all matched
             * characters.
             */
            pglz_out_tag(ctrlp, ctrlb, ctrl, bp, match_len, match_off);
            while (match_len--)
            {
                pglz_hist_add(hist_start, hist_entries,
                              hist_next, hist_recycle,
                              dp, dend, mask);
                dp++;           /* Do not do this ++ in the line above! */
                /* The macro would do it four times - Jan.  */
            }
            found_match = true;
        }
        else
        {
            /*
             * No match found. Copy one literal byte.
             */
            pglz_out_literal(ctrlp, ctrlb, ctrl, bp, *dp);
            pglz_hist_add(hist_start, hist_entries,
                          hist_next, hist_recycle,
                          dp, dend, mask);
            dp++;               /* Do not do this ++ in the line above! */
            /* The macro would do it four times - Jan.  */
        }
    }
 
    /*
     * Write out the last control byte and check that we haven't overrun the
     * output size allowed by the strategy.
     */
    *ctrlp = ctrlb;
    result_size = bp - bstart;
    if (result_size >= result_max)
        return -1;
 
    /* success */
    return result_size;
}

References generate_unaccent_rules::dest, PGLZ_Strategy::first_success_by, hist_entries, hist_start, PGLZ_Strategy::match_size_drop, PGLZ_Strategy::match_size_good, PGLZ_Strategy::max_input_size, PGLZ_Strategy::min_comp_rate, pglz_find_match(), pglz_hist_add, PGLZ_MAX_MATCH, pglz_out_literal, pglz_out_tag, PGLZ_strategy_default, and source.

Referenced by pglz_compress_datum(), and XLogCompressBackupBlock().

◆ pglz_decompress()

int32 pglz_decompress	(	const char *	source,
		int32	slen,
		char *	dest,
		int32	rawsize,
		bool	check_complete
	)

Definition at line 692 of file pg_lzcompress.c.

{
    const unsigned char *sp;
    const unsigned char *srcend;
    unsigned char *dp;
    unsigned char *destend;
 
    sp = (const unsigned char *) source;
    srcend = ((const unsigned char *) source) + slen;
    dp = (unsigned char *) dest;
    destend = dp + rawsize;
 
    while (sp < srcend && dp < destend)
    {
        /*
         * Read one control byte and process the next 8 items (or as many as
         * remain in the compressed input).
         */
        unsigned char ctrl = *sp++;
        int         ctrlc;
 
        for (ctrlc = 0; ctrlc < 8 && sp < srcend && dp < destend; ctrlc++)
        {
            if (ctrl & 1)
            {
                /*
                 * Set control bit means we must read a match tag. The match
                 * is coded with two bytes. First byte uses lower nibble to
                 * code length - 3. Higher nibble contains upper 4 bits of the
                 * offset. The next following byte contains the lower 8 bits
                 * of the offset. If the length is coded as 18, another
                 * extension tag byte tells how much longer the match really
                 * was (0-255).
                 */
                int32       len;
                int32       off;
 
                len = (sp[0] & 0x0f) + 3;
                off = ((sp[0] & 0xf0) << 4) | sp[1];
                sp += 2;
                if (len == 18)
                    len += *sp++;
 
                /*
                 * Check for corrupt data: if we fell off the end of the
                 * source, or if we obtained off = 0, or if off is more than
                 * the distance back to the buffer start, we have problems.
                 * (We must check for off = 0, else we risk an infinite loop
                 * below in the face of corrupt data.  Likewise, the upper
                 * limit on off prevents accessing outside the buffer
                 * boundaries.)
                 */
                if (unlikely(sp > srcend || off == 0 ||
                             off > (dp - (unsigned char *) dest)))
                    return -1;
 
                /*
                 * Don't emit more data than requested.
                 */
                len = Min(len, destend - dp);
 
                /*
                 * Now we copy the bytes specified by the tag from OUTPUT to
                 * OUTPUT (copy len bytes from dp - off to dp).  The copied
                 * areas could overlap, so to avoid undefined behavior in
                 * memcpy(), be careful to copy only non-overlapping regions.
                 *
                 * Note that we cannot use memmove() instead, since while its
                 * behavior is well-defined, it's also not what we want.
                 */
                while (off < len)
                {
                    /*
                     * We can safely copy "off" bytes since that clearly
                     * results in non-overlapping source and destination.
                     */
                    memcpy(dp, dp - off, off);
                    len -= off;
                    dp += off;
 
                    /*----------
                     * This bit is less obvious: we can double "off" after
                     * each such step.  Consider this raw input:
                     *      112341234123412341234
                     * This will be encoded as 5 literal bytes "11234" and
                     * then a match tag with length 16 and offset 4.  After
                     * memcpy'ing the first 4 bytes, we will have emitted
                     *      112341234
                     * so we can double "off" to 8, then after the next step
                     * we have emitted
                     *      11234123412341234
                     * Then we can double "off" again, after which it is more
                     * than the remaining "len" so we fall out of this loop
                     * and finish with a non-overlapping copy of the
                     * remainder.  In general, a match tag with off < len
                     * implies that the decoded data has a repeat length of
                     * "off".  We can handle 1, 2, 4, etc repetitions of the
                     * repeated string per memcpy until we get to a situation
                     * where the final copy step is non-overlapping.
                     *
                     * (Another way to understand this is that we are keeping
                     * the copy source point dp - off the same throughout.)
                     *----------
                     */
                    off += off;
                }
                memcpy(dp, dp - off, len);
                dp += len;
            }
            else
            {
                /*
                 * An unset control bit means LITERAL BYTE. So we just copy
                 * one from INPUT to OUTPUT.
                 */
                *dp++ = *sp++;
            }
 
            /*
             * Advance the control bit
             */
            ctrl >>= 1;
        }
    }
 
    /*
     * If requested, check we decompressed the right amount.
     */
    if (check_complete && (dp != destend || sp != srcend))
        return -1;
 
    /*
     * That's it.
     */
    return (char *) dp - dest;
}

References generate_unaccent_rules::dest, len, Min, source, and unlikely.

Referenced by pglz_decompress_datum(), pglz_decompress_datum_slice(), and RestoreBlockImage().

◆ pglz_find_match()

static int pglz_find_match	(	int16 *	hstart,
		const char *	input,
		const char *	end,
		int *	lenp,
		int *	offp,
		int	good_match,
		int	good_drop,
		int	mask
	)

inlinestatic

Definition at line 399 of file pg_lzcompress.c.

{
    PGLZ_HistEntry *hent;
    int16       hentno;
    int32       len = 0;
    int32       off = 0;
 
    /*
     * Traverse the linked history list until a good enough match is found.
     */
    hentno = hstart[pglz_hist_idx(input, end, mask)];
    hent = &hist_entries[hentno];
    while (hent != INVALID_ENTRY_PTR)
    {
        const char *ip = input;
        const char *hp = hent->pos;
        int32       thisoff;
        int32       thislen;
 
        /*
         * Stop if the offset does not fit into our tag anymore.
         */
        thisoff = ip - hp;
        if (thisoff >= 0x0fff)
            break;
 
        /*
         * Determine length of match. A better match must be larger than the
         * best so far. And if we already have a match of 16 or more bytes,
         * it's worth the call overhead to use memcmp() to check if this match
         * is equal for the same size. After that we must fallback to
         * character by character comparison to know the exact position where
         * the diff occurred.
         */
        thislen = 0;
        if (len >= 16)
        {
            if (memcmp(ip, hp, len) == 0)
            {
                thislen = len;
                ip += len;
                hp += len;
                while (ip < end && *ip == *hp && thislen < PGLZ_MAX_MATCH)
                {
                    thislen++;
                    ip++;
                    hp++;
                }
            }
        }
        else
        {
            while (ip < end && *ip == *hp && thislen < PGLZ_MAX_MATCH)
            {
                thislen++;
                ip++;
                hp++;
            }
        }
 
        /*
         * Remember this match as the best (if it is)
         */
        if (thislen > len)
        {
            len = thislen;
            off = thisoff;
        }
 
        /*
         * Advance to the next history entry
         */
        hent = hent->next;
 
        /*
         * Be happy with lesser good matches the more entries we visited. But
         * no point in doing calculation if we're at end of list.
         */
        if (hent != INVALID_ENTRY_PTR)
        {
            if (len >= good_match)
                break;
            good_match -= (good_match * good_drop) / 100;
        }
    }
 
    /*
     * Return match information only if it results at least in one byte
     * reduction.
     */
    if (len > 2)
    {
        *lenp = len;
        *offp = off;
        return 1;
    }
 
    return 0;
}

References hist_entries, input, INVALID_ENTRY_PTR, len, PGLZ_HistEntry::next, pglz_hist_idx, PGLZ_MAX_MATCH, and PGLZ_HistEntry::pos.

Referenced by pglz_compress().

◆ pglz_maximum_compressed_size()

int32 pglz_maximum_compressed_size	(	int32	rawsize,
		int32	total_compressed_size
	)

Definition at line 846 of file pg_lzcompress.c.

{
    int64       compressed_size;
 
    /*
     * pglz uses one control bit per byte, so if the entire desired prefix is
     * represented as literal bytes, we'll need (rawsize * 9) bits.  We care
     * about bytes though, so be sure to round up not down.
     *
     * Use int64 here to prevent overflow during calculation.
     */
    compressed_size = ((int64) rawsize * 9 + 7) / 8;
 
    /*
     * The above fails to account for a corner case: we could have compressed
     * data that starts with N-1 or N-2 literal bytes and then has a match tag
     * of 2 or 3 bytes.  It's therefore possible that we need to fetch 1 or 2
     * more bytes in order to have the whole match tag.  (Match tags earlier
     * in the compressed data don't cause a problem, since they should
     * represent more decompressed bytes than they occupy themselves.)
     */
    compressed_size += 2;
 
    /*
     * Maximum compressed size can't be larger than total compressed size.
     * (This also ensures that our result fits in int32.)
     */
    compressed_size = Min(compressed_size, total_compressed_size);
 
    return (int32) compressed_size;
}

References Min.

Referenced by detoast_attr_slice().

Variable Documentation

◆ hist_entries

PGLZ_HistEntry hist_entries[PGLZ_HISTORY_SIZE+1]

static

Definition at line 256 of file pg_lzcompress.c.

Referenced by pglz_compress(), and pglz_find_match().

◆ hist_start

int16 hist_start[PGLZ_MAX_HISTORY_LISTS]

static

Definition at line 255 of file pg_lzcompress.c.

Referenced by pglz_compress().

◆ PGLZ_strategy_always

const PGLZ_Strategy* const PGLZ_strategy_always = &strategy_always_data

Definition at line 248 of file pg_lzcompress.c.

◆ PGLZ_strategy_default

const PGLZ_Strategy* const PGLZ_strategy_default = &strategy_default_data

Definition at line 236 of file pg_lzcompress.c.

Referenced by pglz_compress(), pglz_compress_datum(), and XLogCompressBackupBlock().

◆ strategy_always_data

const PGLZ_Strategy strategy_always_data

static

Initial value:

Definition at line 239 of file pg_lzcompress.c.

◆ strategy_default_data

const PGLZ_Strategy strategy_default_data

static

Initial value:

Definition at line 223 of file pg_lzcompress.c.

Data Structures

Macros

Typedefs

Functions

Variables

Macro Definition Documentation

◆ INVALID_ENTRY

◆ INVALID_ENTRY_PTR

◆ pglz_hist_add

◆ pglz_hist_idx

◆ PGLZ_HISTORY_SIZE

◆ PGLZ_MAX_HISTORY_LISTS

◆ PGLZ_MAX_MATCH

◆ pglz_out_ctrl

◆ pglz_out_literal

◆ pglz_out_tag

Typedef Documentation

◆ PGLZ_HistEntry

Function Documentation

◆ pglz_compress()

◆ pglz_decompress()

◆ pglz_find_match()

◆ pglz_maximum_compressed_size()

Variable Documentation

◆ hist_entries

◆ hist_start

◆ PGLZ_strategy_always

◆ PGLZ_strategy_default

◆ strategy_always_data

◆ strategy_default_data