Datum
tsvectorin(PG_FUNCTION_ARGS)
{
char *buf = PG_GETARG_CSTRING(0);
TSVectorParseState state;
WordEntryIN *arr;
int totallen;
int arrlen; /* allocated size of arr */
WordEntry *inarr;
int len = 0;
TSVector in;
int i;
char *token;
int toklen;
WordEntryPos *pos;
int poslen;
char *strbuf;
int stroff;
/*
* Tokens are appended to tmpbuf, cur is a pointer to the end of used
* space in tmpbuf.
*/
char *tmpbuf;
char *cur;
int buflen = 256; /* allocated size of tmpbuf */
state = init_tsvector_parser(buf, false, false);
arrlen = 64;
arr = (WordEntryIN *) palloc(sizeof(WordEntryIN) * arrlen);
cur = tmpbuf = (char *) palloc(buflen);
while (gettoken_tsvector(state, &token, &toklen, &pos, &poslen, NULL))
{
if (toklen >= MAXSTRLEN)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("word is too long (%ld bytes, max %ld bytes)",
(long) toklen,
(long) (MAXSTRLEN - 1))));
if (cur - tmpbuf > MAXSTRPOS)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("string is too long for tsvector (%ld bytes, max %ld bytes)",
(long) (cur - tmpbuf), (long) MAXSTRPOS)));
/*
* Enlarge buffers if needed
*/
if (len >= arrlen)
{
arrlen *= 2;
arr = (WordEntryIN *)
repalloc((void *) arr, sizeof(WordEntryIN) * arrlen);
}
while ((cur - tmpbuf) + toklen >= buflen)
{
int dist = cur - tmpbuf;
buflen *= 2;
tmpbuf = (char *) repalloc((void *) tmpbuf, buflen);
cur = tmpbuf + dist;
}
arr[len].entry.len = toklen;
arr[len].entry.pos = cur - tmpbuf;
memcpy((void *) cur, (void *) token, toklen);
cur += toklen;
if (poslen != 0)
{
arr[len].entry.haspos = 1;
arr[len].pos = pos;
arr[len].poslen = poslen;
}
else
{
arr[len].entry.haspos = 0;
arr[len].pos = NULL;
arr[len].poslen = 0;
}
len++;
}
close_tsvector_parser(state);
if (len > 0)
len = uniqueentry(arr, len, tmpbuf, &buflen);
else
buflen = 0;
if (buflen > MAXSTRPOS)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("string is too long for tsvector (%d bytes, max %d bytes)", buflen, MAXSTRPOS)));
totallen = CALCDATASIZE(len, buflen);
in = (TSVector) palloc0(totallen);
SET_VARSIZE(in, totallen);
in->size = len;
inarr = ARRPTR(in);
strbuf = STRPTR(in);
stroff = 0;
for (i = 0; i < len; i++)
{
memcpy(strbuf + stroff, &tmpbuf[arr[i].entry.pos], arr[i].entry.len);
arr[i].entry.pos = stroff;
stroff += arr[i].entry.len;
if (arr[i].entry.haspos)
{
if (arr[i].poslen > 0xFFFF)
elog(ERROR, "positions array too long");
/* Copy number of positions */
stroff = SHORTALIGN(stroff);
*(uint16 *) (strbuf + stroff) = (uint16) arr[i].poslen;
stroff += sizeof(uint16);
/* Copy positions */
memcpy(strbuf + stroff, arr[i].pos, arr[i].poslen * sizeof(WordEntryPos));
stroff += arr[i].poslen * sizeof(WordEntryPos);
pfree(arr[i].pos);
}
inarr[i] = arr[i].entry;
}
Assert((strbuf + stroff - (char *) in) == totallen);
PG_RETURN_TSVECTOR(in);
}
/*
* get token from query string
*/
static int4
gettoken_query(QPRS_STATE * state, int4 *val, int4 *lenval, char **strval, int2 *weight)
{
while (1)
{
switch (state->state)
{
case WAITOPERAND:
if (*(state->buf) == '!')
{
(state->buf)++;
*val = (int4) '!';
return OPR;
}
else if (*(state->buf) == '(')
{
state->count++;
(state->buf)++;
return OPEN;
}
else if (*(state->buf) == ':')
{
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("error at start of operand")));
}
else if (*(state->buf) != ' ')
{
state->valstate.prsbuf = state->buf;
state->state = WAITOPERATOR;
if (gettoken_tsvector(&(state->valstate)))
{
*strval = state->valstate.word;
*lenval = state->valstate.curpos - state->valstate.word;
state->buf = get_weight(state->valstate.prsbuf, weight);
return VAL;
}
else
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("no operand")));
}
break;
case WAITOPERATOR:
if (*(state->buf) == '&' || *(state->buf) == '|')
{
state->state = WAITOPERAND;
*val = (int4) *(state->buf);
(state->buf)++;
return OPR;
}
else if (*(state->buf) == ')')
{
(state->buf)++;
state->count--;
return (state->count < 0) ? ERR : CLOSE;
}
else if (*(state->buf) == '\0')
return (state->count) ? ERR : END;
else if (*(state->buf) != ' ')
return ERR;
break;
default:
return ERR;
break;
}
(state->buf)++;
}
return END;
}
Datum
tsvector_in(PG_FUNCTION_ARGS)
{
char *buf = PG_GETARG_CSTRING(0);
TI_IN_STATE state;
WordEntryIN *arr;
WordEntry *inarr;
int4 len = 0,
totallen = 64;
tsvector *in;
char *tmpbuf,
*cur;
int4 i,
buflen = 256;
state.prsbuf = buf;
state.len = 32;
state.word = (char *) palloc(state.len);
state.oprisdelim = false;
arr = (WordEntryIN *) palloc(sizeof(WordEntryIN) * totallen);
cur = tmpbuf = (char *) palloc(buflen);
while (gettoken_tsvector(&state))
{
if (len >= totallen)
{
totallen *= 2;
arr = (WordEntryIN *) repalloc((void *) arr, sizeof(WordEntryIN) * totallen);
}
while ((cur - tmpbuf) + (state.curpos - state.word) >= buflen)
{
int4 dist = cur - tmpbuf;
buflen *= 2;
tmpbuf = (char *) repalloc((void *) tmpbuf, buflen);
cur = tmpbuf + dist;
}
if (state.curpos - state.word >= MAXSTRLEN)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("word is too long")));
arr[len].entry.len = state.curpos - state.word;
if (cur - tmpbuf > MAXSTRPOS)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("too long value")));
arr[len].entry.pos = cur - tmpbuf;
memcpy((void *) cur, (void *) state.word, arr[len].entry.len);
cur += arr[len].entry.len;
if (state.alen)
{
arr[len].entry.haspos = 1;
arr[len].pos = state.pos;
}
else
arr[len].entry.haspos = 0;
len++;
}
pfree(state.word);
if (len > 0)
len = uniqueentry(arr, len, tmpbuf, &buflen);
else
buflen=0;
totallen = CALCDATASIZE(len, buflen);
in = (tsvector *) palloc(totallen);
memset(in, 0, totallen);
in->len = totallen;
in->size = len;
cur = STRPTR(in);
inarr = ARRPTR(in);
for (i = 0; i < len; i++)
{
memcpy((void *) cur, (void *) &tmpbuf[arr[i].entry.pos], arr[i].entry.len);
arr[i].entry.pos = cur - STRPTR(in);
cur += SHORTALIGN(arr[i].entry.len);
if (arr[i].entry.haspos)
{
memcpy(cur, arr[i].pos, (*(uint16 *) arr[i].pos + 1) * sizeof(WordEntryPos));
cur += (*(uint16 *) arr[i].pos + 1) * sizeof(WordEntryPos);
pfree(arr[i].pos);
}
memcpy(&(inarr[i]), &(arr[i].entry), sizeof(WordEntry));
}
pfree(tmpbuf);
pfree(arr);
PG_RETURN_POINTER(in);
}
