Change

typedef struct {} WordEntryPos; to typedef uint16 WordEntryPos according to http://www.pgsql.ru/db/mw/msg.html?mid=2035188 Require re-fill all tsvector fields and reindex tsvector indexes.
21 years ago · fe30edbab8
parent 4405e74355
commit fe30edbab8
6 changed files with 57 additions and 44 deletions
--- a/contrib/tsearch2/query.c
+++ b/contrib/tsearch2/query.c
@ -396,7 +396,7 @@ checkclass_str(CHKVAL * chkval, WordEntry * val, ITEM * item)

 	while (len--)
 	{
-		if (item->weight & (1 << ptr->weight))
+		if (item->weight & (1 << WEP_GETWEIGHT(*ptr)))
 			return true;
 		ptr++;
 	}
--- a/contrib/tsearch2/rank.c
+++ b/contrib/tsearch2/rank.c
@ -39,7 +39,7 @@ Datum		get_covers(PG_FUNCTION_ARGS);

 static float weights[] = {0.1, 0.2, 0.4, 1.0};

-#define wpos(wep)	( w[ ((WordEntryPos*)(wep))->weight ] )
+#define wpos(wep)	( w[ WEP_GETWEIGHT(wep) ] )

 #define DEF_NORM_METHOD 0

@ -113,8 +113,8 @@ find_wordentry(tsvector * t, QUERYTYPE * q, ITEM * item)
 }

 static WordEntryPos POSNULL[] = {
-	{0, 0},
-	{0, MAXENTRYPOS - 1}
+	0,
+	0
 };

 static float
@ -136,6 +136,7 @@ calc_rank_and(float *w, tsvector * t, QUERYTYPE * q)

 	memset(pos, 0, sizeof(uint16 **) * q->size);
 	*(uint16 *) POSNULL = lengthof(POSNULL) - 1;
+	WEP_SETPOS(POSNULL[1], MAXENTRYPOS-1); 

 	for (i = 0; i < q->size; i++)
 	{
@ -165,14 +166,14 @@ calc_rank_and(float *w, tsvector * t, QUERYTYPE * q)
 			{
 				for (p = 0; p < lenct; p++)
 				{
-					dist = Abs(post[l].pos - ct[p].pos);
+					dist = Abs((int)WEP_GETPOS(post[l]) - (int)WEP_GETPOS(ct[p]));
 					if (dist || (dist == 0 && (pos[i] == (uint16 *) POSNULL || pos[k] == (uint16 *) POSNULL)))
 					{
 						float		curw;

 						if (!dist)
 							dist = MAXENTRYPOS;
-						curw = sqrt(wpos(&(post[l])) * wpos(&(ct[p])) * word_distance(dist));
+						curw = sqrt(wpos(post[l]) * wpos(ct[p]) * word_distance(dist));
 						res = (res < 0) ? curw : 1.0 - (1.0 - res) * (1.0 - curw);
 					}
 				}
@ -219,9 +220,9 @@ calc_rank_or(float *w, tsvector * t, QUERYTYPE * q)
 		for (j = 0; j < dimt; j++)
 		{
 			if (res < 0)
-				res = wpos(&(post[j]));
+				res = wpos(post[j]);
 			else
-				res = 1.0 - (1.0 - res) * (1.0 - wpos(&(post[j])));
+				res = 1.0 - (1.0 - res) * (1.0 - wpos(post[j]));
 		}
 	}
 	return res;
@ -497,7 +498,7 @@ get_docrep(tsvector * txt, QUERYTYPE * query, int *doclen)
 		for (j = 0; j < dimt; j++)
 		{
 			doc[cur].item = &(item[i]);
-			doc[cur].pos = post[j].pos;
+			doc[cur].pos = WEP_GETPOS(post[j]);
 			cur++;
 		}
 	}
@ -656,7 +657,7 @@ get_covers(PG_FUNCTION_ARGS)
 		{
 			dw[cur].w = STRPTR(txt) + pptr[i].pos;
 			dw[cur].len = pptr[i].len;
-			dw[cur].pos = posdata[j].pos;
+			dw[cur].pos = WEP_GETPOS(posdata[j]);
 			cur++;
 		}
 		len += (pptr[i].len + 1) * (int) POSDATALEN(txt, &(pptr[i]));
--- a/contrib/tsearch2/ts_stat.c
+++ b/contrib/tsearch2/ts_stat.c
@ -42,7 +42,7 @@ check_weight(tsvector * txt, WordEntry * wptr, int8 weight)

 	while (len--)
 	{
-		if (weight & (1 << ptr->weight))
+		if (weight & (1 << WEP_GETWEIGHT(*ptr)))
 			num++;
 		ptr++;
 	}
--- a/contrib/tsearch2/tsvector.c
+++ b/contrib/tsearch2/tsvector.c
@ -50,9 +50,9 @@ Datum		tsvector_length(PG_FUNCTION_ARGS);
 static int
 comparePos(const void *a, const void *b)
 {
-	if (((WordEntryPos *) a)->pos == ((WordEntryPos *) b)->pos)
+	if (WEP_GETPOS(*(WordEntryPos *) a) == WEP_GETPOS(*(WordEntryPos *) b))
 		return 1;
-	return (((WordEntryPos *) a)->pos > ((WordEntryPos *) b)->pos) ? 1 : -1;
+	return (WEP_GETPOS(*(WordEntryPos *) a)> WEP_GETPOS(*(WordEntryPos *) b)) ? 1 : -1;
 }

 static int
@ -70,16 +70,15 @@ uniquePos(WordEntryPos * a, int4 l)
 	ptr = a + 1;
 	while (ptr - a < l)
 	{
-		if (ptr->pos != res->pos)
+		if (WEP_GETPOS(*ptr) != WEP_GETPOS(*res))
 		{
 			res++;
-			res->pos = ptr->pos;
-			res->weight = ptr->weight;
-			if (res - a >= MAXNUMPOS - 1 || res->pos == MAXENTRYPOS - 1)
+			*res = *ptr;
+			if (res - a >= MAXNUMPOS - 1 || WEP_GETPOS(*res) == MAXENTRYPOS - 1)
 				break;
 		}
-		else if (ptr->weight > res->weight)
-			res->weight = ptr->weight;
+		else if (WEP_GETWEIGHT(*ptr) > WEP_GETWEIGHT(*res))
+			WEP_SETWEIGHT(*res, WEP_GETWEIGHT(*ptr));
 		ptr++;
 	}
 	return res + 1 - a;
@ -324,12 +323,12 @@ gettoken_tsvector(TI_IN_STATE * state)
 					state->pos = (WordEntryPos *) repalloc(state->pos, sizeof(WordEntryPos) * state->alen);
 				}
 				(*(uint16 *) (state->pos))++;
-				state->pos[*(uint16 *) (state->pos)].pos = LIMITPOS(atoi(state->prsbuf));
-				if (state->pos[*(uint16 *) (state->pos)].pos == 0)
+				WEP_SETPOS(state->pos[*(uint16 *) (state->pos)], LIMITPOS(atoi(state->prsbuf)));
+				if (WEP_GETPOS(state->pos[*(uint16 *) (state->pos)]) == 0)
 					ereport(ERROR,
 							(errcode(ERRCODE_SYNTAX_ERROR),
 							 errmsg("wrong position info")));
-				state->pos[*(uint16 *) (state->pos)].weight = 0;
+				WEP_SETWEIGHT( state->pos[*(uint16 *) (state->pos)], 0 );
 				state->state = WAITPOSDELIM;
 			}
 			else
@ -343,35 +342,35 @@ gettoken_tsvector(TI_IN_STATE * state)
 				state->state = INPOSINFO;
 			else if (tolower(*(state->prsbuf)) == 'a' || *(state->prsbuf) == '*')
 			{
-				if (state->pos[*(uint16 *) (state->pos)].weight)
+				if ( WEP_GETWEIGHT(state->pos[*(uint16 *) (state->pos)]) )
 					ereport(ERROR,
 							(errcode(ERRCODE_SYNTAX_ERROR),
 							 errmsg("syntax error")));
-				state->pos[*(uint16 *) (state->pos)].weight = 3;
+				WEP_SETWEIGHT( state->pos[*(uint16 *) (state->pos)], 3 );
 			}
 			else if (tolower(*(state->prsbuf)) == 'b')
 			{
-				if (state->pos[*(uint16 *) (state->pos)].weight)
+				if ( WEP_GETWEIGHT(state->pos[*(uint16 *) (state->pos)]) )
 					ereport(ERROR,
 							(errcode(ERRCODE_SYNTAX_ERROR),
 							 errmsg("syntax error")));
-				state->pos[*(uint16 *) (state->pos)].weight = 2;
+				WEP_SETWEIGHT( state->pos[*(uint16 *) (state->pos)], 2 );
 			}
 			else if (tolower(*(state->prsbuf)) == 'c')
 			{
-				if (state->pos[*(uint16 *) (state->pos)].weight)
+				if ( WEP_GETWEIGHT(state->pos[*(uint16 *) (state->pos)]) )
 					ereport(ERROR,
 							(errcode(ERRCODE_SYNTAX_ERROR),
 							 errmsg("syntax error")));
-				state->pos[*(uint16 *) (state->pos)].weight = 1;
+				WEP_SETWEIGHT( state->pos[*(uint16 *) (state->pos)], 1 );
 			}
 			else if (tolower(*(state->prsbuf)) == 'd')
 			{
-				if (state->pos[*(uint16 *) (state->pos)].weight)
+				if ( WEP_GETWEIGHT(state->pos[*(uint16 *) (state->pos)]) )
 					ereport(ERROR,
 							(errcode(ERRCODE_SYNTAX_ERROR),
 							 errmsg("syntax error")));
-				state->pos[*(uint16 *) (state->pos)].weight = 0;
+				WEP_SETWEIGHT( state->pos[*(uint16 *) (state->pos)], 0 );
 			}
 			else if (isspace((unsigned char) *(state->prsbuf)) ||
 					 *(state->prsbuf) == '\0')
@ -540,9 +539,9 @@ tsvector_out(PG_FUNCTION_ARGS)
 			wptr = POSDATAPTR(out, ptr);
 			while (pp)
 			{
-				sprintf(curout, "%d", wptr->pos);
+				sprintf(curout, "%d", WEP_GETPOS(*wptr));
 				curout = strchr(curout, '\0');
-				switch (wptr->weight)
+				switch (WEP_GETWEIGHT(*wptr))
 				{
 					case 3:
 						*curout++ = 'A';
@ -704,8 +703,8 @@ makevalue(PRSTEXT * prs)
 			wptr = POSDATAPTR(in, ptr);
 			for (j = 0; j < *(uint16 *) cur; j++)
 			{
-				wptr[j].weight = 0;
-				wptr[j].pos = prs->words[i].pos.apos[j + 1];
+				WEP_SETWEIGHT(wptr[j], 0);
+				WEP_SETPOS(wptr[j], prs->words[i].pos.apos[j + 1]);
 			}
 			cur += sizeof(uint16) + prs->words[i].pos.apos[0] * sizeof(WordEntryPos);
 			pfree(prs->words[i].pos.apos);
--- a/contrib/tsearch2/tsvector.h
+++ b/contrib/tsearch2/tsvector.h
@ -23,12 +23,25 @@ typedef struct
 #define MAXSTRLEN ( 1<<11 )
 #define MAXSTRPOS ( 1<<20 )

+/*
+Equivalent to 
 typedef struct
 {
-	uint16
-				weight:2,
-				pos:14;
-}	WordEntryPos;
+       uint16
+                                weight:2,
+                                pos:14;
+}       WordEntryPos;
+
+*/
+
+typedef uint16 WordEntryPos;
+
+#define  WEP_GETWEIGHT(x)	( (x) >> 14 )
+#define  WEP_GETPOS(x)	( (x) & 0x3fff )
+
+#define  WEP_SETWEIGHT(x,v)  (x) = ( (v) << 14 ) | ( (x) & 0x3fff ) 
+#define  WEP_SETPOS(x,v)	(x) = ( (x) & 0xc000 ) | ( (v) & 0x3fff ) 
+

 #define MAXENTRYPOS (1<<14)
 #define MAXNUMPOS	256
--- a/contrib/tsearch2/tsvector_op.c
+++ b/contrib/tsearch2/tsvector_op.c
@ -106,7 +106,7 @@ setweight(PG_FUNCTION_ARGS)
 			p = POSDATAPTR(out, entry);
 			while (j--)
 			{
-				p->weight = w;
+				WEP_SETWEIGHT(*p,w);
 				p++;
 			}
 		}
@ -144,10 +144,10 @@ add_pos(tsvector * src, WordEntry * srcptr, tsvector * dest, WordEntry * destptr
 		*clen = 0;

 	startlen = *clen;
-	for (i = 0; i < slen && *clen < MAXNUMPOS && (*clen == 0 || dpos[*clen - 1].pos != MAXENTRYPOS - 1); i++)
+	for (i = 0; i < slen && *clen < MAXNUMPOS && (*clen == 0 || WEP_GETPOS(dpos[*clen - 1]) != MAXENTRYPOS - 1); i++)
 	{
-		dpos[*clen].weight = spos[i].weight;
-		dpos[*clen].pos = LIMITPOS(spos[i].pos + maxpos);
+		WEP_SETWEIGHT(dpos[*clen], WEP_GETWEIGHT(spos[i]));
+		WEP_SETPOS(dpos[*clen], LIMITPOS(WEP_GETPOS(spos[i]) + maxpos));
 		(*clen)++;
 	}

@ -186,8 +186,8 @@ concat(PG_FUNCTION_ARGS)
 			p = POSDATAPTR(in1, ptr);
 			while (j--)
 			{
-				if (p->pos > maxpos)
-					maxpos = p->pos;
+				if (WEP_GETPOS(*p) > maxpos)
+					maxpos = WEP_GETPOS(*p);
 				p++;
 			}
 		}