/*
* Add positions from src to dest after offsetting them by maxpos.
* Return the number added (might be less than expected due to overflow)
*/
static int32
add_pos(TSVector src, WordEntry *srcptr,
TSVector dest, WordEntry *destptr,
int32 maxpos)
{
uint16 *clen = &_POSVECPTR(dest, destptr)->npos;
int i;
uint16 slen = POSDATALEN(src, srcptr),
startlen;
WordEntryPos *spos = POSDATAPTR(src, srcptr),
*dpos = POSDATAPTR(dest, destptr);
if (!destptr->haspos)
*clen = 0;
startlen = *clen;
for (i = 0;
i < slen && *clen < MAXNUMPOS &&
(*clen == 0 || WEP_GETPOS(dpos[*clen - 1]) != MAXENTRYPOS - 1);
i++)
{
WEP_SETWEIGHT(dpos[*clen], WEP_GETWEIGHT(spos[i]));
WEP_SETPOS(dpos[*clen], LIMITPOS(WEP_GETPOS(spos[i]) + maxpos));
(*clen)++;
}
if (*clen != startlen)
destptr->haspos = 1;
return *clen - startlen;
}
/*
* Removes duplicate pos entries. If there's two entries with same pos
* but different weight, the higher weight is retained.
*
* Returns new___ length.
*/
static int
uniquePos(WordEntryPos *a, int l)
{
WordEntryPos *ptr,
*res;
if (l <= 1)
return l;
qsort((void *) a, l, sizeof(WordEntryPos), comparePos);
res = a;
ptr = a + 1;
while (ptr - a < l)
{
if (WEP_GETPOS(*ptr) != WEP_GETPOS(*res))
{
res++;
*res = *ptr;
if (res - a >= MAXNUMPOS - 1 ||
WEP_GETPOS(*res) == MAXENTRYPOS - 1)
break;
}
else if (WEP_GETWEIGHT(*ptr) > WEP_GETWEIGHT(*res))
WEP_SETWEIGHT(*res, WEP_GETWEIGHT(*ptr));
ptr++;
}
return res + 1 - a;
}
Datum
tsvector_setweight(PG_FUNCTION_ARGS)
{
TSVector in = PG_GETARG_TSVECTOR(0);
char cw = PG_GETARG_CHAR(1);
TSVector out;
int i,
j;
WordEntry *entry;
WordEntryPos *p;
int w = 0;
switch (cw)
{
case 'A':
case 'a':
w = 3;
break;
case 'B':
case 'b':
w = 2;
break;
case 'C':
case 'c':
w = 1;
break;
case 'D':
case 'd':
w = 0;
break;
default:
/* internal error */
elog(ERROR, "unrecognized weight: %d", cw);
}
out = (TSVector) palloc(VARSIZE(in));
memcpy(out, in, VARSIZE(in));
entry = ARRPTR(out);
i = out->size;
while (i--)
{
if ((j = POSDATALEN(out, entry)) != 0)
{
p = POSDATAPTR(out, entry);
while (j--)
{
WEP_SETWEIGHT(*p, w);
p++;
}
}
entry++;
}
PG_FREE_IF_COPY(in, 0);
PG_RETURN_POINTER(out);
}
/*
* make value of tsvector, given parsed text
*/
TSVector
make_tsvector(ParsedText *prs)
{
int i,
j,
lenstr = 0,
totallen;
TSVector in;
WordEntry *ptr;
char *str;
int stroff;
prs->curwords = uniqueWORD(prs->words, prs->curwords);
for (i = 0; i < prs->curwords; i++)
{
lenstr += prs->words[i].len;
if (prs->words[i].alen)
{
lenstr = SHORTALIGN(lenstr);
lenstr += sizeof(uint16) + prs->words[i].pos.apos[0] * sizeof(WordEntryPos);
}
}
if (lenstr > MAXSTRPOS)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("string is too long for tsvector (%d bytes, max %d bytes)", lenstr, MAXSTRPOS)));
totallen = CALCDATASIZE(prs->curwords, lenstr);
in = (TSVector) palloc0(totallen);
SET_VARSIZE(in, totallen);
in->size = prs->curwords;
ptr = ARRPTR(in);
str = STRPTR(in);
stroff = 0;
for (i = 0; i < prs->curwords; i++)
{
ptr->len = prs->words[i].len;
ptr->pos = stroff;
memcpy(str + stroff, prs->words[i].word, prs->words[i].len);
stroff += prs->words[i].len;
pfree(prs->words[i].word);
if (prs->words[i].alen)
{
int k = prs->words[i].pos.apos[0];
WordEntryPos *wptr;
if (k > 0xFFFF)
elog(ERROR, "positions array too long");
ptr->haspos = 1;
stroff = SHORTALIGN(stroff);
*(uint16 *) (str + stroff) = (uint16) k;
wptr = POSDATAPTR(in, ptr);
for (j = 0; j < k; j++)
{
WEP_SETWEIGHT(wptr[j], 0);
WEP_SETPOS(wptr[j], prs->words[i].pos.apos[j + 1]);
}
stroff += sizeof(uint16) + k * sizeof(WordEntryPos);
pfree(prs->words[i].pos.apos);
}
else
ptr->haspos = 0;
ptr++;
}
pfree(prs->words);
return in;
}
/*
* Get next token from string being parsed. Returns true if successful,
* false if end of input string is reached. On success, these output
* parameters are filled in:
*
* *strval pointer to token
* *lenval length of *strval
* *pos_ptr pointer to a palloc'd array of positions and weights
* associated with the token. If the caller is not interested
* in the information, NULL can be supplied. Otherwise
* the caller is responsible for pfreeing the array.
* *poslen number of elements in *pos_ptr
* *endptr scan resumption point
*
* Pass NULL for unwanted output parameters.
*/
bool
gettoken_tsvector(TSVectorParseState state,
char **strval, int *lenval,
WordEntryPos **pos_ptr, int *poslen,
char **endptr)
{
int oldstate = 0;
char *curpos = state->word;
int statecode = WAITWORD;
/*
* pos is for collecting the comma delimited list of positions followed by
* the actual token.
*/
WordEntryPos *pos = NULL;
int npos = 0; /* elements of pos used */
int posalen = 0; /* allocated size of pos */
while (1)
{
if (statecode == WAITWORD)
{
if (*(state->prsbuf) == '\0')
return false;
else if (t_iseq(state->prsbuf, '\''))
statecode = WAITENDCMPLX;
else if (t_iseq(state->prsbuf, '\\'))
{
statecode = WAITNEXTCHAR;
oldstate = WAITENDWORD;
}
else if (state->oprisdelim && ISOPERATOR(state->prsbuf))
PRSSYNTAXERROR;
else if (!t_isspace(state->prsbuf))
{
COPYCHAR(curpos, state->prsbuf);
curpos += pg_mblen(state->prsbuf);
statecode = WAITENDWORD;
}
}
else if (statecode == WAITNEXTCHAR)
{
if (*(state->prsbuf) == '\0')
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("there is no escaped character: \"%s\"",
state->bufstart)));
else
{
RESIZEPRSBUF;
COPYCHAR(curpos, state->prsbuf);
curpos += pg_mblen(state->prsbuf);
Assert(oldstate != 0);
statecode = oldstate;
}
}
else if (statecode == WAITENDWORD)
{
if (t_iseq(state->prsbuf, '\\'))
{
statecode = WAITNEXTCHAR;
oldstate = WAITENDWORD;
}
else if (t_isspace(state->prsbuf) || *(state->prsbuf) == '\0' ||
(state->oprisdelim && ISOPERATOR(state->prsbuf)))
{
RESIZEPRSBUF;
if (curpos == state->word)
PRSSYNTAXERROR;
*(curpos) = '\0';
RETURN_TOKEN;
}
else if (t_iseq(state->prsbuf, ':'))
{
if (curpos == state->word)
PRSSYNTAXERROR;
*(curpos) = '\0';
if (state->oprisdelim)
RETURN_TOKEN;
else
statecode = INPOSINFO;
}
else
{
RESIZEPRSBUF;
COPYCHAR(curpos, state->prsbuf);
curpos += pg_mblen(state->prsbuf);
}
}
else if (statecode == WAITENDCMPLX)
{
if (t_iseq(state->prsbuf, '\''))
{
statecode = WAITCHARCMPLX;
}
else if (t_iseq(state->prsbuf, '\\'))
{
statecode = WAITNEXTCHAR;
oldstate = WAITENDCMPLX;
}
else if (*(state->prsbuf) == '\0')
PRSSYNTAXERROR;
else
{
RESIZEPRSBUF;
COPYCHAR(curpos, state->prsbuf);
curpos += pg_mblen(state->prsbuf);
}
}
else if (statecode == WAITCHARCMPLX)
{
if (t_iseq(state->prsbuf, '\''))
{
RESIZEPRSBUF;
COPYCHAR(curpos, state->prsbuf);
curpos += pg_mblen(state->prsbuf);
statecode = WAITENDCMPLX;
}
else
{
RESIZEPRSBUF;
*(curpos) = '\0';
if (curpos == state->word)
PRSSYNTAXERROR;
if (state->oprisdelim)
{
/* state->prsbuf+=pg_mblen(state->prsbuf); */
RETURN_TOKEN;
}
else
statecode = WAITPOSINFO;
continue; /* recheck current character */
}
}
else if (statecode == WAITPOSINFO)
{
if (t_iseq(state->prsbuf, ':'))
statecode = INPOSINFO;
else
RETURN_TOKEN;
}
else if (statecode == INPOSINFO)
{
if (t_isdigit(state->prsbuf))
{
if (posalen == 0)
{
posalen = 4;
pos = (WordEntryPos *) palloc(sizeof(WordEntryPos) * posalen);
npos = 0;
}
else if (npos + 1 >= posalen)
{
posalen *= 2;
pos = (WordEntryPos *) repalloc(pos, sizeof(WordEntryPos) * posalen);
}
npos++;
WEP_SETPOS(pos[npos - 1], LIMITPOS(atoi(state->prsbuf)));
/* we cannot get here in tsquery, so no need for 2 errmsgs */
if (WEP_GETPOS(pos[npos - 1]) == 0)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("wrong position info in tsvector: \"%s\"",
state->bufstart)));
WEP_SETWEIGHT(pos[npos - 1], 0);
statecode = WAITPOSDELIM;
}
else
PRSSYNTAXERROR;
}
else if (statecode == WAITPOSDELIM)
{
if (t_iseq(state->prsbuf, ','))
statecode = INPOSINFO;
else if (t_iseq(state->prsbuf, 'a') || t_iseq(state->prsbuf, 'A') || t_iseq(state->prsbuf, '*'))
{
if (WEP_GETWEIGHT(pos[npos - 1]))
PRSSYNTAXERROR;
WEP_SETWEIGHT(pos[npos - 1], 3);
}
else if (t_iseq(state->prsbuf, 'b') || t_iseq(state->prsbuf, 'B'))
{
if (WEP_GETWEIGHT(pos[npos - 1]))
PRSSYNTAXERROR;
WEP_SETWEIGHT(pos[npos - 1], 2);
}
else if (t_iseq(state->prsbuf, 'c') || t_iseq(state->prsbuf, 'C'))
{
if (WEP_GETWEIGHT(pos[npos - 1]))
PRSSYNTAXERROR;
WEP_SETWEIGHT(pos[npos - 1], 1);
}
else if (t_iseq(state->prsbuf, 'd') || t_iseq(state->prsbuf, 'D'))
{
if (WEP_GETWEIGHT(pos[npos - 1]))
PRSSYNTAXERROR;
WEP_SETWEIGHT(pos[npos - 1], 0);
}
else if (t_isspace(state->prsbuf) ||
*(state->prsbuf) == '\0')
RETURN_TOKEN;
else if (!t_isdigit(state->prsbuf))
PRSSYNTAXERROR;
}
else /* internal error */
elog(ERROR, "unrecognized state in gettoken_tsvector: %d",
statecode);
/* get next char */
state->prsbuf += pg_mblen(state->prsbuf);
}
}
