/*
* 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);
}
}
int4
gettoken_tsvector(TI_IN_STATE * state)
{
int4 oldstate = 0;
state->curpos = state->word;
state->state = WAITWORD;
state->alen = 0;
while (1)
{
if (state->state == WAITWORD)
{
if (*(state->prsbuf) == '\0')
return 0;
else if (*(state->prsbuf) == '\'')
state->state = WAITENDCMPLX;
else if (*(state->prsbuf) == '\\')
{
state->state = WAITNEXTCHAR;
oldstate = WAITENDWORD;
}
else if (state->oprisdelim && ISOPERATOR(*(state->prsbuf)))
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
else if (*(state->prsbuf) != ' ')
{
*(state->curpos) = *(state->prsbuf);
state->curpos++;
state->state = WAITENDWORD;
}
}
else if (state->state == WAITNEXTCHAR)
{
if (*(state->prsbuf) == '\0')
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("there is no escaped character")));
else
{
RESIZEPRSBUF;
*(state->curpos) = *(state->prsbuf);
state->curpos++;
state->state = oldstate;
}
}
else if (state->state == WAITENDWORD)
{
if (*(state->prsbuf) == '\\')
{
state->state = WAITNEXTCHAR;
oldstate = WAITENDWORD;
}
else if (*(state->prsbuf) == ' ' || *(state->prsbuf) == '\0' ||
(state->oprisdelim && ISOPERATOR(*(state->prsbuf))))
{
RESIZEPRSBUF;
if (state->curpos == state->word)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
*(state->curpos) = '\0';
return 1;
}
else if (*(state->prsbuf) == ':')
{
if (state->curpos == state->word)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
*(state->curpos) = '\0';
if (state->oprisdelim)
return 1;
else
state->state = INPOSINFO;
}
else
{
RESIZEPRSBUF;
*(state->curpos) = *(state->prsbuf);
state->curpos++;
}
}
else if (state->state == WAITENDCMPLX)
{
if (*(state->prsbuf) == '\'')
{
RESIZEPRSBUF;
*(state->curpos) = '\0';
if (state->curpos == state->word)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
if (state->oprisdelim)
{
state->prsbuf++;
return 1;
}
else
state->state = WAITPOSINFO;
}
else if (*(state->prsbuf) == '\\')
{
state->state = WAITNEXTCHAR;
oldstate = WAITENDCMPLX;
}
else if (*(state->prsbuf) == '\0')
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
else
{
RESIZEPRSBUF;
*(state->curpos) = *(state->prsbuf);
state->curpos++;
}
}
else if (state->state == WAITPOSINFO)
{
if (*(state->prsbuf) == ':')
state->state = INPOSINFO;
else
return 1;
}
else if (state->state == INPOSINFO)
{
if (isdigit(*(state->prsbuf)))
{
if (state->alen == 0)
{
state->alen = 4;
state->pos = (WordEntryPos *) palloc(sizeof(WordEntryPos) * state->alen);
*(uint16 *) (state->pos) = 0;
}
else if (*(uint16 *) (state->pos) + 1 >= state->alen)
{
state->alen *= 2;
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)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("wrong position info")));
state->pos[*(uint16 *) (state->pos)].weight = 0;
state->state = WAITPOSDELIM;
}
else
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
}
else if (state->state == WAITPOSDELIM)
{
if (*(state->prsbuf) == ',')
state->state = INPOSINFO;
else if (tolower(*(state->prsbuf)) == 'a' || *(state->prsbuf) == '*')
{
if (state->pos[*(uint16 *) (state->pos)].weight)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
state->pos[*(uint16 *) (state->pos)].weight = 3;
}
else if (tolower(*(state->prsbuf)) == 'b')
{
if (state->pos[*(uint16 *) (state->pos)].weight)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
state->pos[*(uint16 *) (state->pos)].weight = 2;
}
else if (tolower(*(state->prsbuf)) == 'c')
{
if (state->pos[*(uint16 *) (state->pos)].weight)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
state->pos[*(uint16 *) (state->pos)].weight = 1;
}
else if (tolower(*(state->prsbuf)) == 'd')
{
if (state->pos[*(uint16 *) (state->pos)].weight)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
state->pos[*(uint16 *) (state->pos)].weight = 0;
}
else if (isspace(*(state->prsbuf)) || *(state->prsbuf) == '\0')
return 1;
else if (!isdigit(*(state->prsbuf)))
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error")));
}
else
/* internal error */
elog(ERROR, "internal error");
state->prsbuf++;
}
return 0;
}
