trgm_gist.c File Reference

#include "postgres.h"
#include "access/reloptions.h"
#include "access/stratnum.h"
#include "fmgr.h"
#include "port/pg_bitutils.h"
#include "trgm.h"
#include "varatt.h"

Include dependency graph for trgm_gist.c:

Go to the source code of this file.

Data Structures
struct	TrgmGistOptions
struct	gtrgm_consistent_cache
struct	CACHESIGN
struct	SPLITCOST

Macros
#define	GET_SIGLEN()
#define	GETENTRY(vec, pos)   ((TRGM *) DatumGetPointer((vec)->vector[(pos)].key))
#define	WISH_F(a, b, c)   (double)( -(double)(((a)-(b))*((a)-(b))*((a)-(b)))*(c) )

Functions
	PG_FUNCTION_INFO_V1 (gtrgm_in)
	PG_FUNCTION_INFO_V1 (gtrgm_out)
	PG_FUNCTION_INFO_V1 (gtrgm_compress)
	PG_FUNCTION_INFO_V1 (gtrgm_decompress)
	PG_FUNCTION_INFO_V1 (gtrgm_consistent)
	PG_FUNCTION_INFO_V1 (gtrgm_distance)
	PG_FUNCTION_INFO_V1 (gtrgm_union)
	PG_FUNCTION_INFO_V1 (gtrgm_same)
	PG_FUNCTION_INFO_V1 (gtrgm_penalty)
	PG_FUNCTION_INFO_V1 (gtrgm_picksplit)
	PG_FUNCTION_INFO_V1 (gtrgm_options)
Datum	gtrgm_in (PG_FUNCTION_ARGS)
Datum	gtrgm_out (PG_FUNCTION_ARGS)
static TRGM *	gtrgm_alloc (bool isalltrue, int siglen, BITVECP sign)
static void	makesign (BITVECP sign, TRGM *a, int siglen)
Datum	gtrgm_compress (PG_FUNCTION_ARGS)
Datum	gtrgm_decompress (PG_FUNCTION_ARGS)
static int32	cnt_sml_sign_common (TRGM *qtrg, BITVECP sign, int siglen)
Datum	gtrgm_consistent (PG_FUNCTION_ARGS)
Datum	gtrgm_distance (PG_FUNCTION_ARGS)
static int32	unionkey (BITVECP sbase, TRGM *add, int siglen)
Datum	gtrgm_union (PG_FUNCTION_ARGS)
Datum	gtrgm_same (PG_FUNCTION_ARGS)
static int32	sizebitvec (BITVECP sign, int siglen)
static int	hemdistsign (BITVECP a, BITVECP b, int siglen)
static int	hemdist (TRGM *a, TRGM *b, int siglen)
Datum	gtrgm_penalty (PG_FUNCTION_ARGS)
static void	fillcache (CACHESIGN *item, TRGM *key, BITVECP sign, int siglen)
static int	comparecost (const void *a, const void *b)
static int	hemdistcache (CACHESIGN *a, CACHESIGN *b, int siglen)
Datum	gtrgm_picksplit (PG_FUNCTION_ARGS)
Datum	gtrgm_options (PG_FUNCTION_ARGS)

Macro Definition Documentation

GET_SIGLEN

#define GET_SIGLEN

(

)

Value:

                                 (PG_HAS_OPCLASS_OPTIONS() ? \
                                 ((TrgmGistOptions *) PG_GET_OPCLASS_OPTIONS())->siglen : \
                                 SIGLEN_DEFAULT)

Definition at line 20 of file trgm_gist.c.

                                                                                        : \
                                 SIGLEN_DEFAULT)

GETENTRY

#define GETENTRY	(		vec,
			pos
	)		((TRGM *) DatumGetPointer((vec)->vector[(pos)].key))

Definition at line 40 of file trgm_gist.c.

WISH_F

#define WISH_F	(		a,
			b,
			c
	)		(double)( -(double)(((a)-(b))*((a)-(b))*((a)-(b)))*(c) )

Definition at line 763 of file trgm_gist.c.

Function Documentation

cnt_sml_sign_common()

static int32 cnt_sml_sign_common ( TRGM *  qtrg, BITVECP  sign, int  siglen  )

static

Definition at line 179 of file trgm_gist.c.

{
    int32       count = 0;
    int32       k,
                len = ARRNELEM(qtrg);
    trgm       *ptr = GETARR(qtrg);
    int32       tmp = 0;
 
    for (k = 0; k < len; k++)
    {
        CPTRGM(&tmp, ptr + k);
        count += GETBIT(sign, HASHVAL(tmp, siglen));
    }
 
    return count;
}

References ARRNELEM, CPTRGM, fb(), GETARR, GETBIT, HASHVAL, len, and sign.

Referenced by gtrgm_consistent(), and gtrgm_distance().

comparecost()

static int comparecost ( const void *  a, const void *  b  )

static

Definition at line 771 of file trgm_gist.c.

{
    if (((const SPLITCOST *) a)->cost == ((const SPLITCOST *) b)->cost)
        return 0;
    else
        return (((const SPLITCOST *) a)->cost > ((const SPLITCOST *) b)->cost) ? 1 : -1;
}

References a, and b.

Referenced by gtrgm_picksplit().

fillcache()

static void fillcache ( CACHESIGN *  item, TRGM *  key, BITVECP  sign, int  siglen  )

static

Definition at line 751 of file trgm_gist.c.

{
    item->allistrue = false;
    item->sign = sign;
    if (ISARRKEY(key))
        makesign(item->sign, key, siglen);
    else if (ISALLTRUE(key))
        item->allistrue = true;
    else
        memcpy(item->sign, GETSIGN(key), siglen);
}

References CACHESIGN::allistrue, fb(), GETSIGN, ISALLTRUE, ISARRKEY, makesign(), CACHESIGN::sign, and sign.

Referenced by gtrgm_picksplit().

gtrgm_alloc()

static TRGM * gtrgm_alloc ( bool  isalltrue, int  siglen, BITVECP  sign  )

static

Definition at line 77 of file trgm_gist.c.

{
    int         flag = SIGNKEY | (isalltrue ? ALLISTRUE : 0);
    int         size = CALCGTSIZE(flag, siglen);
    TRGM       *res = palloc(size);
 
    SET_VARSIZE(res, size);
    res->flag = flag;
 
    if (!isalltrue)
    {
        if (sign)
            memcpy(GETSIGN(res), sign, siglen);
        else
            memset(GETSIGN(res), 0, siglen);
    }
 
    return res;
}

References ALLISTRUE, CALCGTSIZE, fb(), TRGM::flag, flag(), GETSIGN, palloc(), SET_VARSIZE(), sign, and SIGNKEY.

Referenced by gtrgm_compress(), gtrgm_picksplit(), and gtrgm_union().

gtrgm_compress()

Datum gtrgm_compress

(

PG_FUNCTION_ARGS

)

Definition at line 115 of file trgm_gist.c.

{
    GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
    int         siglen = GET_SIGLEN();
    GISTENTRY  *retval = entry;
 
    if (entry->leafkey)
    {                           /* trgm */
        TRGM       *res;
        text       *val = DatumGetTextPP(entry->key);
 
        res = generate_trgm(VARDATA_ANY(val), VARSIZE_ANY_EXHDR(val));
        retval = palloc_object(GISTENTRY);
        gistentryinit(*retval, PointerGetDatum(res),
                      entry->rel, entry->page,
                      entry->offset, false);
    }
    else if (ISSIGNKEY(DatumGetPointer(entry->key)) &&
             !ISALLTRUE(DatumGetPointer(entry->key)))
    {
        int32       i;
        TRGM       *res;
        BITVECP     sign = GETSIGN(DatumGetPointer(entry->key));
 
        LOOPBYTE(siglen)
        {
            if ((sign[i] & 0xff) != 0xff)
                PG_RETURN_POINTER(retval);
        }
 
        res = gtrgm_alloc(true, siglen, sign);
        retval = palloc_object(GISTENTRY);
        gistentryinit(*retval, PointerGetDatum(res),
                      entry->rel, entry->page,
                      entry->offset, false);
    }
    PG_RETURN_POINTER(retval);
}

References DatumGetPointer(), DatumGetTextPP, generate_trgm(), GET_SIGLEN, GETSIGN, gistentryinit, gtrgm_alloc(), i, ISALLTRUE, ISSIGNKEY, GISTENTRY::key, GISTENTRY::leafkey, LOOPBYTE, GISTENTRY::offset, GISTENTRY::page, palloc_object, PG_GETARG_POINTER, PG_RETURN_POINTER, PointerGetDatum(), GISTENTRY::rel, sign, val, VARDATA_ANY(), and VARSIZE_ANY_EXHDR().

gtrgm_consistent()

Datum gtrgm_consistent

(

PG_FUNCTION_ARGS

)

Definition at line 197 of file trgm_gist.c.

{
    GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
    text       *query = PG_GETARG_TEXT_P(1);
    StrategyNumber strategy = (StrategyNumber) PG_GETARG_UINT16(2);
#ifdef NOT_USED
    Oid         subtype = PG_GETARG_OID(3);
#endif
    bool       *recheck = (bool *) PG_GETARG_POINTER(4);
    int         siglen = GET_SIGLEN();
    TRGM       *key = (TRGM *) DatumGetPointer(entry->key);
    TRGM       *qtrg;
    bool        res;
    Size        querysize = VARSIZE(query);
    gtrgm_consistent_cache *cache;
    double      nlimit;
 
    /*
     * We keep the extracted trigrams in cache, because trigram extraction is
     * relatively CPU-expensive.  When trying to reuse a cached value, check
     * strategy number not just query itself, because trigram extraction
     * depends on strategy.
     *
     * The cached structure is a single palloc chunk containing the
     * gtrgm_consistent_cache header, then the input query (4-byte length
     * word, uncompressed, starting at a MAXALIGN boundary), then the TRGM
     * value (also starting at a MAXALIGN boundary).  However we don't try to
     * include the regex graph (if any) in that struct.  (XXX currently, this
     * approach can leak regex graphs across index rescans.  Not clear if
     * that's worth fixing.)
     */
    cache = (gtrgm_consistent_cache *) fcinfo->flinfo->fn_extra;
    if (cache == NULL ||
        cache->strategy != strategy ||
        VARSIZE(cache->query) != querysize ||
        memcmp(cache->query, query, querysize) != 0)
    {
        gtrgm_consistent_cache *newcache;
        TrgmPackedGraph *graph = NULL;
        Size        qtrgsize;
 
        switch (strategy)
        {
            case SimilarityStrategyNumber:
            case WordSimilarityStrategyNumber:
            case StrictWordSimilarityStrategyNumber:
            case EqualStrategyNumber:
                qtrg = generate_trgm(VARDATA(query),
                                     querysize - VARHDRSZ);
                break;
            case ILikeStrategyNumber:
#ifndef IGNORECASE
                elog(ERROR, "cannot handle ~~* with case-sensitive trigrams");
#endif
                /* FALL THRU */
            case LikeStrategyNumber:
                qtrg = generate_wildcard_trgm(VARDATA(query),
                                              querysize - VARHDRSZ);
                break;
            case RegExpICaseStrategyNumber:
#ifndef IGNORECASE
                elog(ERROR, "cannot handle ~* with case-sensitive trigrams");
#endif
                /* FALL THRU */
            case RegExpStrategyNumber:
                qtrg = createTrgmNFA(query, PG_GET_COLLATION(),
                                     &graph, fcinfo->flinfo->fn_mcxt);
                /* just in case an empty array is returned ... */
                if (qtrg && ARRNELEM(qtrg) <= 0)
                {
                    pfree(qtrg);
                    qtrg = NULL;
                }
                break;
            default:
                elog(ERROR, "unrecognized strategy number: %d", strategy);
                qtrg = NULL;    /* keep compiler quiet */
                break;
        }
 
        qtrgsize = qtrg ? VARSIZE(qtrg) : 0;
 
        newcache = (gtrgm_consistent_cache *)
            MemoryContextAlloc(fcinfo->flinfo->fn_mcxt,
                               MAXALIGN(sizeof(gtrgm_consistent_cache)) +
                               MAXALIGN(querysize) +
                               qtrgsize);
 
        newcache->strategy = strategy;
        newcache->query = (text *)
            ((char *) newcache + MAXALIGN(sizeof(gtrgm_consistent_cache)));
        memcpy(newcache->query, query, querysize);
        if (qtrg)
        {
            newcache->trigrams = (TRGM *)
                ((char *) newcache->query + MAXALIGN(querysize));
            memcpy((char *) newcache->trigrams, qtrg, qtrgsize);
            /* release qtrg in case it was made in fn_mcxt */
            pfree(qtrg);
        }
        else
            newcache->trigrams = NULL;
        newcache->graph = graph;
 
        if (cache)
            pfree(cache);
        fcinfo->flinfo->fn_extra = newcache;
        cache = newcache;
    }
 
    qtrg = cache->trigrams;
 
    switch (strategy)
    {
        case SimilarityStrategyNumber:
        case WordSimilarityStrategyNumber:
        case StrictWordSimilarityStrategyNumber:
 
            /*
             * Similarity search is exact. (Strict) word similarity search is
             * inexact
             */
            *recheck = (strategy != SimilarityStrategyNumber);
 
            nlimit = index_strategy_get_limit(strategy);
 
            if (GIST_LEAF(entry))
            {                   /* all leafs contains orig trgm */
                double      tmpsml = cnt_sml(qtrg, key, *recheck);
 
                res = (tmpsml >= nlimit);
            }
            else if (ISALLTRUE(key))
            {                   /* non-leaf contains signature */
                res = true;
            }
            else
            {                   /* non-leaf contains signature */
                int32       count = cnt_sml_sign_common(qtrg, GETSIGN(key), siglen);
                int32       len = ARRNELEM(qtrg);
 
                if (len == 0)
                    res = false;
                else
                    res = (((((float8) count) / ((float8) len))) >= nlimit);
            }
            break;
        case ILikeStrategyNumber:
#ifndef IGNORECASE
            elog(ERROR, "cannot handle ~~* with case-sensitive trigrams");
#endif
            /* FALL THRU */
        case LikeStrategyNumber:
        case EqualStrategyNumber:
            /* Wildcard and equal search are inexact */
            *recheck = true;
 
            /*
             * Check if all the extracted trigrams can be present in child
             * nodes.
             */
            if (GIST_LEAF(entry))
            {                   /* all leafs contains orig trgm */
                res = trgm_contained_by(qtrg, key);
            }
            else if (ISALLTRUE(key))
            {                   /* non-leaf contains signature */
                res = true;
            }
            else
            {                   /* non-leaf contains signature */
                int32       k,
                            tmp = 0,
                            len = ARRNELEM(qtrg);
                trgm       *ptr = GETARR(qtrg);
                BITVECP     sign = GETSIGN(key);
 
                res = true;
                for (k = 0; k < len; k++)
                {
                    CPTRGM(&tmp, ptr + k);
                    if (!GETBIT(sign, HASHVAL(tmp, siglen)))
                    {
                        res = false;
                        break;
                    }
                }
            }
            break;
        case RegExpICaseStrategyNumber:
#ifndef IGNORECASE
            elog(ERROR, "cannot handle ~* with case-sensitive trigrams");
#endif
            /* FALL THRU */
        case RegExpStrategyNumber:
            /* Regexp search is inexact */
            *recheck = true;
 
            /* Check regex match as much as we can with available info */
            if (qtrg)
            {
                if (GIST_LEAF(entry))
                {               /* all leafs contains orig trgm */
                    bool       *check;
 
                    check = trgm_presence_map(qtrg, key);
                    res = trigramsMatchGraph(cache->graph, check);
                    pfree(check);
                }
                else if (ISALLTRUE(key))
                {               /* non-leaf contains signature */
                    res = true;
                }
                else
                {               /* non-leaf contains signature */
                    int32       k,
                                tmp = 0,
                                len = ARRNELEM(qtrg);
                    trgm       *ptr = GETARR(qtrg);
                    BITVECP     sign = GETSIGN(key);
                    bool       *check;
 
                    /*
                     * GETBIT() tests may give false positives, due to limited
                     * size of the sign array.  But since trigramsMatchGraph()
                     * implements a monotone boolean function, false positives
                     * in the check array can't lead to false negative answer.
                     * So we can apply trigramsMatchGraph despite uncertainty,
                     * and that usefully improves the quality of the search.
                     */
                    check = (bool *) palloc(len * sizeof(bool));
                    for (k = 0; k < len; k++)
                    {
                        CPTRGM(&tmp, ptr + k);
                        check[k] = GETBIT(sign, HASHVAL(tmp, siglen));
                    }
                    res = trigramsMatchGraph(cache->graph, check);
                    pfree(check);
                }
            }
            else
            {
                /* trigram-free query must be rechecked everywhere */
                res = true;
            }
            break;
        default:
            elog(ERROR, "unrecognized strategy number: %d", strategy);
            res = false;        /* keep compiler quiet */
            break;
    }
 
    PG_RETURN_BOOL(res);
}

References ARRNELEM, cnt_sml(), cnt_sml_sign_common(), CPTRGM, createTrgmNFA(), DatumGetPointer(), elog, EqualStrategyNumber, ERROR, fb(), generate_trgm(), generate_wildcard_trgm(), GET_SIGLEN, GETARR, GETBIT, GETSIGN, GIST_LEAF, gtrgm_consistent_cache::graph, HASHVAL, ILikeStrategyNumber, index_strategy_get_limit(), ISALLTRUE, GISTENTRY::key, len, LikeStrategyNumber, MAXALIGN, MemoryContextAlloc(), palloc(), pfree(), PG_GET_COLLATION, PG_GETARG_OID, PG_GETARG_POINTER, PG_GETARG_TEXT_P, PG_GETARG_UINT16, PG_RETURN_BOOL, gtrgm_consistent_cache::query, RegExpICaseStrategyNumber, RegExpStrategyNumber, sign, SimilarityStrategyNumber, gtrgm_consistent_cache::strategy, StrictWordSimilarityStrategyNumber, trgm_contained_by(), trgm_presence_map(), gtrgm_consistent_cache::trigrams, trigramsMatchGraph(), VARDATA(), VARHDRSZ, VARSIZE(), and WordSimilarityStrategyNumber.

gtrgm_decompress()

Datum gtrgm_decompress

(

PG_FUNCTION_ARGS

)

Definition at line 155 of file trgm_gist.c.

{
    GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
    GISTENTRY  *retval;
    text       *key;
 
    key = DatumGetTextPP(entry->key);
 
    if (key != (text *) DatumGetPointer(entry->key))
    {
        /* need to pass back the decompressed item */
        retval = palloc_object(GISTENTRY);
        gistentryinit(*retval, PointerGetDatum(key),
                      entry->rel, entry->page, entry->offset, entry->leafkey);
        PG_RETURN_POINTER(retval);
    }
    else
    {
        /* we can return the entry as-is */
        PG_RETURN_POINTER(entry);
    }
}

References DatumGetPointer(), DatumGetTextPP, gistentryinit, GISTENTRY::key, GISTENTRY::leafkey, GISTENTRY::offset, GISTENTRY::page, palloc_object, PG_GETARG_POINTER, PG_RETURN_POINTER, PointerGetDatum(), and GISTENTRY::rel.

gtrgm_distance()

Datum gtrgm_distance

(

PG_FUNCTION_ARGS

)

Definition at line 453 of file trgm_gist.c.

{
    GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
    text       *query = PG_GETARG_TEXT_P(1);
    StrategyNumber strategy = (StrategyNumber) PG_GETARG_UINT16(2);
#ifdef NOT_USED
    Oid         subtype = PG_GETARG_OID(3);
#endif
    bool       *recheck = (bool *) PG_GETARG_POINTER(4);
    int         siglen = GET_SIGLEN();
    TRGM       *key = (TRGM *) DatumGetPointer(entry->key);
    TRGM       *qtrg;
    float8      res;
    Size        querysize = VARSIZE(query);
    char       *cache = (char *) fcinfo->flinfo->fn_extra;
 
    /*
     * Cache the generated trigrams across multiple calls with the same query.
     */
    if (cache == NULL ||
        VARSIZE(cache) != querysize ||
        memcmp(cache, query, querysize) != 0)
    {
        char       *newcache;
 
        qtrg = generate_trgm(VARDATA(query), querysize - VARHDRSZ);
 
        newcache = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt,
                                      MAXALIGN(querysize) +
                                      VARSIZE(qtrg));
 
        memcpy(newcache, query, querysize);
        memcpy(newcache + MAXALIGN(querysize), qtrg, VARSIZE(qtrg));
 
        if (cache)
            pfree(cache);
        fcinfo->flinfo->fn_extra = newcache;
        cache = newcache;
    }
 
    qtrg = (TRGM *) (cache + MAXALIGN(querysize));
 
    switch (strategy)
    {
        case DistanceStrategyNumber:
        case WordDistanceStrategyNumber:
        case StrictWordDistanceStrategyNumber:
            /* Only plain trigram distance is exact */
            *recheck = (strategy != DistanceStrategyNumber);
            if (GIST_LEAF(entry))
            {                   /* all leafs contains orig trgm */
 
                /*
                 * Prevent gcc optimizing the sml variable using volatile
                 * keyword. Otherwise res can differ from the
                 * word_similarity_dist_op() function.
                 */
                float4 volatile sml = cnt_sml(qtrg, key, *recheck);
 
                res = 1.0 - sml;
            }
            else if (ISALLTRUE(key))
            {                   /* all leafs contains orig trgm */
                res = 0.0;
            }
            else
            {                   /* non-leaf contains signature */
                int32       count = cnt_sml_sign_common(qtrg, GETSIGN(key), siglen);
                int32       len = ARRNELEM(qtrg);
 
                res = (len == 0) ? -1.0 : 1.0 - ((float8) count) / ((float8) len);
            }
            break;
        default:
            elog(ERROR, "unrecognized strategy number: %d", strategy);
            res = 0;            /* keep compiler quiet */
            break;
    }
 
    PG_RETURN_FLOAT8(res);
}

References ARRNELEM, cnt_sml(), cnt_sml_sign_common(), DatumGetPointer(), DistanceStrategyNumber, elog, ERROR, fb(), generate_trgm(), GET_SIGLEN, GETSIGN, GIST_LEAF, ISALLTRUE, GISTENTRY::key, len, MAXALIGN, MemoryContextAlloc(), pfree(), PG_GETARG_OID, PG_GETARG_POINTER, PG_GETARG_TEXT_P, PG_GETARG_UINT16, PG_RETURN_FLOAT8, StrictWordDistanceStrategyNumber, VARDATA(), VARHDRSZ, VARSIZE(), and WordDistanceStrategyNumber.

gtrgm_in()

Datum gtrgm_in

(

PG_FUNCTION_ARGS

)

Definition at line 57 of file trgm_gist.c.

{
    ereport(ERROR,
            (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
             errmsg("cannot accept a value of type %s", "gtrgm")));
 
    PG_RETURN_VOID();           /* keep compiler quiet */
}

References ereport, errcode(), errmsg(), ERROR, fb(), and PG_RETURN_VOID.

gtrgm_options()

Datum gtrgm_options

(

PG_FUNCTION_ARGS

)

Definition at line 962 of file trgm_gist.c.

{
    local_relopts *relopts = (local_relopts *) PG_GETARG_POINTER(0);
 
    init_local_reloptions(relopts, sizeof(TrgmGistOptions));
    add_local_int_reloption(relopts, "siglen",
                            "signature length in bytes",
                            SIGLEN_DEFAULT, 1, SIGLEN_MAX,
                            offsetof(TrgmGistOptions, siglen));
 
    PG_RETURN_VOID();
}

References add_local_int_reloption(), fb(), init_local_reloptions(), PG_GETARG_POINTER, PG_RETURN_VOID, SIGLEN_DEFAULT, and SIGLEN_MAX.

gtrgm_out()

Datum gtrgm_out

(

PG_FUNCTION_ARGS

)

Definition at line 67 of file trgm_gist.c.

{
    ereport(ERROR,
            (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
             errmsg("cannot display a value of type %s", "gtrgm")));
 
    PG_RETURN_VOID();           /* keep compiler quiet */
}

References ereport, errcode(), errmsg(), ERROR, fb(), and PG_RETURN_VOID.

gtrgm_penalty()

Datum gtrgm_penalty

(

PG_FUNCTION_ARGS

)

Definition at line 689 of file trgm_gist.c.

{
    GISTENTRY  *origentry = (GISTENTRY *) PG_GETARG_POINTER(0); /* always ISSIGNKEY */
    GISTENTRY  *newentry = (GISTENTRY *) PG_GETARG_POINTER(1);
    float      *penalty = (float *) PG_GETARG_POINTER(2);
    int         siglen = GET_SIGLEN();
    TRGM       *origval = (TRGM *) DatumGetPointer(origentry->key);
    TRGM       *newval = (TRGM *) DatumGetPointer(newentry->key);
    BITVECP     orig = GETSIGN(origval);
 
    *penalty = 0.0;
 
    if (ISARRKEY(newval))
    {
        char       *cache = (char *) fcinfo->flinfo->fn_extra;
        TRGM       *cachedVal = (TRGM *) (cache + MAXALIGN(siglen));
        Size        newvalsize = VARSIZE(newval);
        BITVECP     sign;
 
        /*
         * Cache the sign data across multiple calls with the same newval.
         */
        if (cache == NULL ||
            VARSIZE(cachedVal) != newvalsize ||
            memcmp(cachedVal, newval, newvalsize) != 0)
        {
            char       *newcache;
 
            newcache = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt,
                                          MAXALIGN(siglen) +
                                          newvalsize);
 
            makesign((BITVECP) newcache, newval, siglen);
 
            cachedVal = (TRGM *) (newcache + MAXALIGN(siglen));
            memcpy(cachedVal, newval, newvalsize);
 
            if (cache)
                pfree(cache);
            fcinfo->flinfo->fn_extra = newcache;
            cache = newcache;
        }
 
        sign = (BITVECP) cache;
 
        if (ISALLTRUE(origval))
            *penalty = ((float) (SIGLENBIT(siglen) - sizebitvec(sign, siglen))) / (float) (SIGLENBIT(siglen) + 1);
        else
            *penalty = hemdistsign(sign, orig, siglen);
    }
    else
        *penalty = hemdist(origval, newval, siglen);
    PG_RETURN_POINTER(penalty);
}

References DatumGetPointer(), fb(), GET_SIGLEN, GETSIGN, hemdist(), hemdistsign(), ISALLTRUE, ISARRKEY, makesign(), MAXALIGN, MemoryContextAlloc(), newval, pfree(), PG_GETARG_POINTER, PG_RETURN_POINTER, SIGLENBIT, sign, sizebitvec(), and VARSIZE().

gtrgm_picksplit()

Datum gtrgm_picksplit

(

PG_FUNCTION_ARGS

)

Definition at line 797 of file trgm_gist.c.

{
    GistEntryVector *entryvec = (GistEntryVector *) PG_GETARG_POINTER(0);
    OffsetNumber maxoff = entryvec->n - 1;
    GIST_SPLITVEC *v = (GIST_SPLITVEC *) PG_GETARG_POINTER(1);
    int         siglen = GET_SIGLEN();
    OffsetNumber k,
                j;
    TRGM       *datum_l,
               *datum_r;
    BITVECP     union_l,
                union_r;
    int32       size_alpha,
                size_beta;
    int32       size_waste,
                waste = -1;
    int32       nbytes;
    OffsetNumber seed_1 = 0,
                seed_2 = 0;
    OffsetNumber *left,
               *right;
    BITVECP     ptr;
    int         i;
    CACHESIGN  *cache;
    char       *cache_sign;
    SPLITCOST  *costvector;
 
    /* cache the sign data for each existing item */
    cache = palloc_array(CACHESIGN, maxoff + 1);
    cache_sign = palloc(siglen * (maxoff + 1));
 
    for (k = FirstOffsetNumber; k <= maxoff; k = OffsetNumberNext(k))
        fillcache(&cache[k], GETENTRY(entryvec, k), &cache_sign[siglen * k],
                  siglen);
 
    /* now find the two furthest-apart items */
    for (k = FirstOffsetNumber; k < maxoff; k = OffsetNumberNext(k))
    {
        for (j = OffsetNumberNext(k); j <= maxoff; j = OffsetNumberNext(j))
        {
            size_waste = hemdistcache(&(cache[j]), &(cache[k]), siglen);
            if (size_waste > waste)
            {
                waste = size_waste;
                seed_1 = k;
                seed_2 = j;
            }
        }
    }
 
    /* just in case we didn't make a selection ... */
    if (seed_1 == 0 || seed_2 == 0)
    {
        seed_1 = 1;
        seed_2 = 2;
    }
 
    /* initialize the result vectors */
    nbytes = maxoff * sizeof(OffsetNumber);
    v->spl_left = left = (OffsetNumber *) palloc(nbytes);
    v->spl_right = right = (OffsetNumber *) palloc(nbytes);
    v->spl_nleft = 0;
    v->spl_nright = 0;
 
    /* form initial .. */
    datum_l = gtrgm_alloc(cache[seed_1].allistrue, siglen, cache[seed_1].sign);
    datum_r = gtrgm_alloc(cache[seed_2].allistrue, siglen, cache[seed_2].sign);
 
    union_l = GETSIGN(datum_l);
    union_r = GETSIGN(datum_r);
 
    /* sort before ... */
    costvector = palloc_array(SPLITCOST, maxoff);
    for (j = FirstOffsetNumber; j <= maxoff; j = OffsetNumberNext(j))
    {
        costvector[j - 1].pos = j;
        size_alpha = hemdistcache(&(cache[seed_1]), &(cache[j]), siglen);
        size_beta = hemdistcache(&(cache[seed_2]), &(cache[j]), siglen);
        costvector[j - 1].cost = abs(size_alpha - size_beta);
    }
    qsort(costvector, maxoff, sizeof(SPLITCOST), comparecost);
 
    for (k = 0; k < maxoff; k++)
    {
        j = costvector[k].pos;
        if (j == seed_1)
        {
            *left++ = j;
            v->spl_nleft++;
            continue;
        }
        else if (j == seed_2)
        {
            *right++ = j;
            v->spl_nright++;
            continue;
        }
 
        if (ISALLTRUE(datum_l) || cache[j].allistrue)
        {
            if (ISALLTRUE(datum_l) && cache[j].allistrue)
                size_alpha = 0;
            else
                size_alpha = SIGLENBIT(siglen) -
                    sizebitvec((cache[j].allistrue) ? GETSIGN(datum_l) :
                               GETSIGN(cache[j].sign),
                               siglen);
        }
        else
            size_alpha = hemdistsign(cache[j].sign, GETSIGN(datum_l), siglen);
 
        if (ISALLTRUE(datum_r) || cache[j].allistrue)
        {
            if (ISALLTRUE(datum_r) && cache[j].allistrue)
                size_beta = 0;
            else
                size_beta = SIGLENBIT(siglen) -
                    sizebitvec((cache[j].allistrue) ? GETSIGN(datum_r) :
                               GETSIGN(cache[j].sign),
                               siglen);
        }
        else
            size_beta = hemdistsign(cache[j].sign, GETSIGN(datum_r), siglen);
 
        if (size_alpha < size_beta + WISH_F(v->spl_nleft, v->spl_nright, 0.1))
        {
            if (ISALLTRUE(datum_l) || cache[j].allistrue)
            {
                if (!ISALLTRUE(datum_l))
                    memset(GETSIGN(datum_l), 0xff, siglen);
            }
            else
            {
                ptr = cache[j].sign;
                LOOPBYTE(siglen)
                    union_l[i] |= ptr[i];
            }
            *left++ = j;
            v->spl_nleft++;
        }
        else
        {
            if (ISALLTRUE(datum_r) || cache[j].allistrue)
            {
                if (!ISALLTRUE(datum_r))
                    memset(GETSIGN(datum_r), 0xff, siglen);
            }
            else
            {
                ptr = cache[j].sign;
                LOOPBYTE(siglen)
                    union_r[i] |= ptr[i];
            }
            *right++ = j;
            v->spl_nright++;
        }
    }
 
    v->spl_ldatum = PointerGetDatum(datum_l);
    v->spl_rdatum = PointerGetDatum(datum_r);
 
    PG_RETURN_POINTER(v);
}

References comparecost(), fb(), fillcache(), FirstOffsetNumber, GET_SIGLEN, GETENTRY, GETSIGN, gtrgm_alloc(), hemdistcache(), hemdistsign(), i, ISALLTRUE, j, LOOPBYTE, GistEntryVector::n, OffsetNumberNext, palloc(), palloc_array, PG_GETARG_POINTER, PG_RETURN_POINTER, PointerGetDatum(), qsort, SIGLENBIT, CACHESIGN::sign, sign, sizebitvec(), GIST_SPLITVEC::spl_ldatum, GIST_SPLITVEC::spl_left, GIST_SPLITVEC::spl_nleft, GIST_SPLITVEC::spl_nright, GIST_SPLITVEC::spl_rdatum, GIST_SPLITVEC::spl_right, and WISH_F.

gtrgm_same()

Datum gtrgm_same

(

PG_FUNCTION_ARGS

)

Definition at line 592 of file trgm_gist.c.

{
    TRGM       *a = (TRGM *) PG_GETARG_POINTER(0);
    TRGM       *b = (TRGM *) PG_GETARG_POINTER(1);
    bool       *result = (bool *) PG_GETARG_POINTER(2);
    int         siglen = GET_SIGLEN();
 
    if (ISSIGNKEY(a))
    {                           /* then b also ISSIGNKEY */
        if (ISALLTRUE(a) && ISALLTRUE(b))
            *result = true;
        else if (ISALLTRUE(a))
            *result = false;
        else if (ISALLTRUE(b))
            *result = false;
        else
        {
            int32       i;
            BITVECP     sa = GETSIGN(a),
                        sb = GETSIGN(b);
 
            *result = true;
            LOOPBYTE(siglen)
            {
                if (sa[i] != sb[i])
                {
                    *result = false;
                    break;
                }
            }
        }
    }
    else
    {                           /* a and b ISARRKEY */
        int32       lena = ARRNELEM(a),
                    lenb = ARRNELEM(b);
 
        if (lena != lenb)
            *result = false;
        else
        {
            trgm       *ptra = GETARR(a),
                       *ptrb = GETARR(b);
            int32       i;
 
            *result = true;
            for (i = 0; i < lena; i++)
                if (CMPTRGM(ptra + i, ptrb + i))
                {
                    *result = false;
                    break;
                }
        }
    }
 
    PG_RETURN_POINTER(result);
}

References a, ARRNELEM, b, CMPTRGM, fb(), GET_SIGLEN, GETARR, GETSIGN, i, ISALLTRUE, ISSIGNKEY, LOOPBYTE, PG_GETARG_POINTER, and PG_RETURN_POINTER.

gtrgm_union()

Datum gtrgm_union

(

PG_FUNCTION_ARGS

)

Definition at line 566 of file trgm_gist.c.

{
    GistEntryVector *entryvec = (GistEntryVector *) PG_GETARG_POINTER(0);
    int32       len = entryvec->n;
    int        *size = (int *) PG_GETARG_POINTER(1);
    int         siglen = GET_SIGLEN();
    int32       i;
    TRGM       *result = gtrgm_alloc(false, siglen, NULL);
    BITVECP     base = GETSIGN(result);
 
    for (i = 0; i < len; i++)
    {
        if (unionkey(base, GETENTRY(entryvec, i), siglen))
        {
            result->flag = ALLISTRUE;
            SET_VARSIZE(result, CALCGTSIZE(ALLISTRUE, siglen));
            break;
        }
    }
 
    *size = VARSIZE(result);
 
    PG_RETURN_POINTER(result);
}

References ALLISTRUE, CALCGTSIZE, fb(), TRGM::flag, GET_SIGLEN, GETENTRY, GETSIGN, gtrgm_alloc(), i, len, GistEntryVector::n, PG_GETARG_POINTER, PG_RETURN_POINTER, SET_VARSIZE(), unionkey(), and VARSIZE().

hemdist()

static int hemdist ( TRGM *  a, TRGM *  b, int  siglen  )

static

Definition at line 673 of file trgm_gist.c.

{
    if (ISALLTRUE(a))
    {
        if (ISALLTRUE(b))
            return 0;
        else
            return SIGLENBIT(siglen) - sizebitvec(GETSIGN(b), siglen);
    }
    else if (ISALLTRUE(b))
        return SIGLENBIT(siglen) - sizebitvec(GETSIGN(a), siglen);
 
    return hemdistsign(GETSIGN(a), GETSIGN(b), siglen);
}

References a, b, GETSIGN, hemdistsign(), ISALLTRUE, SIGLENBIT, and sizebitvec().

Referenced by gtrgm_penalty().

hemdistcache()

static int hemdistcache ( CACHESIGN *  a, CACHESIGN *  b, int  siglen  )

static

Definition at line 781 of file trgm_gist.c.

{
    if (a->allistrue)
    {
        if (b->allistrue)
            return 0;
        else
            return SIGLENBIT(siglen) - sizebitvec(b->sign, siglen);
    }
    else if (b->allistrue)
        return SIGLENBIT(siglen) - sizebitvec(a->sign, siglen);
 
    return hemdistsign(a->sign, b->sign, siglen);
}

References a, b, hemdistsign(), SIGLENBIT, and sizebitvec().

Referenced by gtrgm_picksplit().

hemdistsign()

static int hemdistsign ( BITVECP  a, BITVECP  b, int  siglen  )

static

Definition at line 657 of file trgm_gist.c.

{
    int         i,
                diff,
                dist = 0;
 
    LOOPBYTE(siglen)
    {
        diff = (unsigned char) (a[i] ^ b[i]);
        /* Using the popcount functions here isn't likely to win */
        dist += pg_number_of_ones[diff];
    }
    return dist;
}

References a, b, fb(), i, LOOPBYTE, and pg_number_of_ones.

Referenced by gtrgm_penalty(), gtrgm_picksplit(), hemdist(), and hemdistcache().

makesign()

static void makesign ( BITVECP  sign, TRGM *  a, int  siglen  )

static

Definition at line 98 of file trgm_gist.c.

{
    int32       k,
                len = ARRNELEM(a);
    trgm       *ptr = GETARR(a);
    int32       tmp = 0;
 
    MemSet(sign, 0, siglen);
    SETBIT(sign, SIGLENBIT(siglen));    /* set last unused bit */
    for (k = 0; k < len; k++)
    {
        CPTRGM(&tmp, ptr + k);
        HASH(sign, tmp, siglen);
    }
}

References a, ARRNELEM, CPTRGM, GETARR, HASH, len, MemSet, SETBIT, SIGLENBIT, and sign.

Referenced by fillcache(), and gtrgm_penalty().

PG_FUNCTION_INFO_V1() [1/11]

PG_FUNCTION_INFO_V1

(

gtrgm_compress

)

PG_FUNCTION_INFO_V1() [2/11]

PG_FUNCTION_INFO_V1

(

gtrgm_consistent

)

PG_FUNCTION_INFO_V1() [3/11]

PG_FUNCTION_INFO_V1

(

gtrgm_decompress

)

PG_FUNCTION_INFO_V1() [4/11]

PG_FUNCTION_INFO_V1

(

gtrgm_distance

)

PG_FUNCTION_INFO_V1() [5/11]

PG_FUNCTION_INFO_V1

(

gtrgm_in

)

PG_FUNCTION_INFO_V1() [6/11]

PG_FUNCTION_INFO_V1

(

gtrgm_options

)

PG_FUNCTION_INFO_V1() [7/11]

PG_FUNCTION_INFO_V1

(

gtrgm_out

)

PG_FUNCTION_INFO_V1() [8/11]

PG_FUNCTION_INFO_V1

(

gtrgm_penalty

)

PG_FUNCTION_INFO_V1() [9/11]

PG_FUNCTION_INFO_V1

(

gtrgm_picksplit

)

PG_FUNCTION_INFO_V1() [10/11]

PG_FUNCTION_INFO_V1

(

gtrgm_same

)

PG_FUNCTION_INFO_V1() [11/11]

PG_FUNCTION_INFO_V1

(

gtrgm_union

)

sizebitvec()

static int32 sizebitvec ( BITVECP  sign, int  siglen  )

static

Definition at line 651 of file trgm_gist.c.

{
    return pg_popcount(sign, siglen);
}

References pg_popcount(), and sign.

Referenced by gtrgm_penalty(), gtrgm_picksplit(), hemdist(), and hemdistcache().

unionkey()

static int32 unionkey ( BITVECP  sbase, TRGM *  add, int  siglen  )

static

Definition at line 536 of file trgm_gist.c.

{
    int32       i;
 
    if (ISSIGNKEY(add))
    {
        BITVECP     sadd = GETSIGN(add);
 
        if (ISALLTRUE(add))
            return 1;
 
        LOOPBYTE(siglen)
            sbase[i] |= sadd[i];
    }
    else
    {
        trgm       *ptr = GETARR(add);
        int32       tmp = 0;
 
        for (i = 0; i < ARRNELEM(add); i++)
        {
            CPTRGM(&tmp, ptr + i);
            HASH(sbase, tmp, siglen);
        }
    }
    return 0;
}

References ARRNELEM, CPTRGM, fb(), GETARR, GETSIGN, HASH, i, ISALLTRUE, ISSIGNKEY, and LOOPBYTE.

Referenced by gtrgm_union().