Datum
dabs_int_lexize(PG_FUNCTION_ARGS)
{
char *in = (char *) PG_GETARG_POINTER(1);
char *out = pnstrdup(in, PG_GETARG_INT32(2));
char *start;
char *end;
TSLexeme *res = palloc0(sizeof(TSLexeme) * 2);
res[1].lexeme = NULL;
while (*out && t_iseq(out, '-'))
out += pg_mblen(out);
start = out;
while (*out)
out += pg_mblen(out);
end = out;
out = pnstrdup(start, end - start);
res[0].lexeme = out;
PG_RETURN_POINTER(res);
}
static char *
getlexeme(char *start, char *end, int *len)
{
char *ptr;
int charlen;
while (start < end && (charlen = pg_mblen(start)) == 1 && t_iseq(start, '_'))
start += charlen;
ptr = start;
if (ptr >= end)
return NULL;
while (ptr < end && !((charlen = pg_mblen(ptr)) == 1 && t_iseq(ptr, '_')))
ptr += charlen;
*len = ptr - start;
return start;
}
/*
* Test whether a regex is of the subset supported here.
* Keep this in sync with RS_compile!
*/
bool
RS_isRegis(const char *str)
{
int state = RS_IN_WAIT;
const char *c = str;
while (*c)
{
if (state == RS_IN_WAIT)
{
if (t_isalpha(c))
/* okay */ ;
else if (t_iseq(c, '['))
state = RS_IN_ONEOF;
else
return false;
}
else if (state == RS_IN_ONEOF)
{
if (t_iseq(c, '^'))
state = RS_IN_NONEOF;
else if (t_isalpha(c))
state = RS_IN_ONEOF_IN;
else
return false;
}
else if (state == RS_IN_ONEOF_IN || state == RS_IN_NONEOF)
{
if (t_isalpha(c))
/* okay */ ;
else if (t_iseq(c, ']'))
state = RS_IN_WAIT;
else
return false;
}
else
elog(ERROR, "internal error in RS_isRegis: state %d", state);
c += pg_mblen(c);
}
return (state == RS_IN_WAIT);
}
/*
* Finds the next whitespace-delimited word within the 'in' string.
* Returns a pointer to the first character of the word, and a pointer
* to the next byte after the last character in the word (in *end).
* Character '*' at the end of word will not be threated as word
* charater if flags is not null.
*/
static char *
findwrd(char *in, char **end, uint16 *flags)
{
char *start;
char *lastchar;
/* Skip leading spaces */
while (*in && t_isspace(in))
in += pg_mblen(in);
/* Return NULL on empty lines */
if (*in == '\0')
{
*end = NULL;
return NULL;
}
lastchar = start = in;
/* Find end of word */
while (*in && !t_isspace(in))
{
lastchar = in;
in += pg_mblen(in);
}
if (in - lastchar == 1 && t_iseq(lastchar, '*') && flags)
{
*flags = TSL_PREFIX;
*end = lastchar;
}
else
{
if (flags)
*flags = 0;
*end = in;
}
return start;
}
static void
thesaurusRead(char *filename, DictThesaurus *d)
{
tsearch_readline_state trst;
uint16 idsubst = 0;
bool useasis = false;
char *line;
filename = get_tsearch_config_filename(filename, "ths");
if (!tsearch_readline_begin(&trst, filename))
ereport(ERROR,
(errcode(ERRCODE_CONFIG_FILE_ERROR),
errmsg("could not open thesaurus file \"%s\": %m",
filename)));
while ((line = tsearch_readline(&trst)) != NULL)
{
char *ptr;
int state = TR_WAITLEX;
char *beginwrd = NULL;
uint16 posinsubst = 0;
uint16 nwrd = 0;
ptr = line;
/* is it a comment? */
while (*ptr && t_isspace(ptr))
ptr += pg_mblen(ptr);
if (t_iseq(ptr, '#') || *ptr == '\0' ||
t_iseq(ptr, '\n') || t_iseq(ptr, '\r'))
{
pfree(line);
continue;
}
while (*ptr)
{
if (state == TR_WAITLEX)
{
if (t_iseq(ptr, ':'))
{
if (posinsubst == 0)
ereport(ERROR,
(errcode(ERRCODE_CONFIG_FILE_ERROR),
errmsg("unexpected delimiter")));
state = TR_WAITSUBS;
}
else if (!t_isspace(ptr))
{
beginwrd = ptr;
state = TR_INLEX;
}
}
else if (state == TR_INLEX)
{
if (t_iseq(ptr, ':'))
{
newLexeme(d, beginwrd, ptr, idsubst, posinsubst++);
state = TR_WAITSUBS;
}
else if (t_isspace(ptr))
{
newLexeme(d, beginwrd, ptr, idsubst, posinsubst++);
state = TR_WAITLEX;
}
}
else if (state == TR_WAITSUBS)
{
if (t_iseq(ptr, '*'))
{
useasis = true;
state = TR_INSUBS;
beginwrd = ptr + pg_mblen(ptr);
}
else if (t_iseq(ptr, '\\'))
{
useasis = false;
state = TR_INSUBS;
beginwrd = ptr + pg_mblen(ptr);
}
else if (!t_isspace(ptr))
{
useasis = false;
beginwrd = ptr;
state = TR_INSUBS;
}
}
else if (state == TR_INSUBS)
{
if (t_isspace(ptr))
{
if (ptr == beginwrd)
ereport(ERROR,
(errcode(ERRCODE_CONFIG_FILE_ERROR),
errmsg("unexpected end of line or lexeme")));
addWrd(d, beginwrd, ptr, idsubst, nwrd++, posinsubst, useasis);
state = TR_WAITSUBS;
}
}
else
elog(ERROR, "unrecognized thesaurus state: %d", state);
ptr += pg_mblen(ptr);
}
if (state == TR_INSUBS)
{
if (ptr == beginwrd)
ereport(ERROR,
(errcode(ERRCODE_CONFIG_FILE_ERROR),
errmsg("unexpected end of line or lexeme")));
addWrd(d, beginwrd, ptr, idsubst, nwrd++, posinsubst, useasis);
}
idsubst++;
if (!(nwrd && posinsubst))
ereport(ERROR,
(errcode(ERRCODE_CONFIG_FILE_ERROR),
errmsg("unexpected end of line")));
pfree(line);
}
d->nsubst = idsubst;
tsearch_readline_end(&trst);
}
void
RS_compile(Regis *r, bool issuffix, const char *str)
{
int len = strlen(str);
int state = RS_IN_WAIT;
const char *c = str;
RegisNode *ptr = NULL;
memset(r, 0, sizeof(Regis));
r->issuffix = (issuffix) ? 1 : 0;
while (*c)
{
if (state == RS_IN_WAIT)
{
if (t_isalpha(c))
{
if (ptr)
ptr = newRegisNode(ptr, len);
else
ptr = r->node = newRegisNode(NULL, len);
COPYCHAR(ptr->data, c);
ptr->type = RSF_ONEOF;
ptr->len = pg_mblen(c);
}
else if (t_iseq(c, '['))
{
if (ptr)
ptr = newRegisNode(ptr, len);
else
ptr = r->node = newRegisNode(NULL, len);
ptr->type = RSF_ONEOF;
state = RS_IN_ONEOF;
}
else /* shouldn't get here */
elog(ERROR, "invalid regis pattern: \"%s\"", str);
}
else if (state == RS_IN_ONEOF)
{
if (t_iseq(c, '^'))
{
ptr->type = RSF_NONEOF;
state = RS_IN_NONEOF;
}
else if (t_isalpha(c))
{
COPYCHAR(ptr->data, c);
ptr->len = pg_mblen(c);
state = RS_IN_ONEOF_IN;
}
else /* shouldn't get here */
elog(ERROR, "invalid regis pattern: \"%s\"", str);
}
else if (state == RS_IN_ONEOF_IN || state == RS_IN_NONEOF)
{
if (t_isalpha(c))
{
COPYCHAR(ptr->data + ptr->len, c);
ptr->len += pg_mblen(c);
}
else if (t_iseq(c, ']'))
state = RS_IN_WAIT;
else /* shouldn't get here */
elog(ERROR, "invalid regis pattern: \"%s\"", str);
}
else
elog(ERROR, "internal error in RS_compile: state %d", state);
c += pg_mblen(c);
}
if (state != RS_IN_WAIT) /* shouldn't get here */
elog(ERROR, "invalid regis pattern: \"%s\"", str);
ptr = r->node;
while (ptr)
{
r->nchar++;
ptr = ptr->next;
}
}
Datum
ltree_in(PG_FUNCTION_ARGS)
{
char *buf = (char *) PG_GETARG_POINTER(0);
char *ptr;
nodeitem *list,
*lptr;
int num = 0,
totallen = 0;
int state = LTPRS_WAITNAME;
ltree *result;
ltree_level *curlevel;
int charlen;
int pos = 0;
ptr = buf;
while (*ptr)
{
charlen = pg_mblen(ptr);
if (charlen == 1 && t_iseq(ptr, '.'))
num++;
ptr += charlen;
}
if (num + 1 > MaxAllocSize / sizeof(nodeitem))
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("number of levels (%d) exceeds the maximum allowed (%d)",
num + 1, (int) (MaxAllocSize / sizeof(nodeitem)))));
list = lptr = (nodeitem *) palloc(sizeof(nodeitem) * (num + 1));
ptr = buf;
while (*ptr)
{
charlen = pg_mblen(ptr);
if (state == LTPRS_WAITNAME)
{
if (ISALNUM(ptr))
{
lptr->start = ptr;
lptr->wlen = 0;
state = LTPRS_WAITDELIM;
}
else
UNCHAR;
}
else if (state == LTPRS_WAITDELIM)
{
if (charlen == 1 && t_iseq(ptr, '.'))
{
lptr->len = ptr - lptr->start;
if (lptr->wlen > 255)
ereport(ERROR,
(errcode(ERRCODE_NAME_TOO_LONG),
errmsg("name of level is too long"),
errdetail("Name length is %d, must "
"be < 256, in position %d.",
lptr->wlen, pos)));
totallen += MAXALIGN(lptr->len + LEVEL_HDRSIZE);
lptr++;
state = LTPRS_WAITNAME;
}
else if (!ISALNUM(ptr))
UNCHAR;
}
else
/* internal error */
elog(ERROR, "internal error in parser");
ptr += charlen;
lptr->wlen++;
pos++;
}
if (state == LTPRS_WAITDELIM)
{
lptr->len = ptr - lptr->start;
if (lptr->wlen > 255)
ereport(ERROR,
(errcode(ERRCODE_NAME_TOO_LONG),
errmsg("name of level is too long"),
errdetail("Name length is %d, must "
"be < 256, in position %d.",
lptr->wlen, pos)));
totallen += MAXALIGN(lptr->len + LEVEL_HDRSIZE);
lptr++;
}
else if (!(state == LTPRS_WAITNAME && lptr == list))
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error"),
errdetail("Unexpected end of line.")));
result = (ltree *) palloc0(LTREE_HDRSIZE + totallen);
SET_VARSIZE(result, LTREE_HDRSIZE + totallen);
result->numlevel = lptr - list;
curlevel = LTREE_FIRST(result);
lptr = list;
while (lptr - list < result->numlevel)
{
curlevel->len = (uint16) lptr->len;
memcpy(curlevel->name, lptr->start, lptr->len);
curlevel = LEVEL_NEXT(curlevel);
lptr++;
}
pfree(list);
PG_RETURN_POINTER(result);
}
Datum
lquery_in(PG_FUNCTION_ARGS)
{
char *buf = (char *) PG_GETARG_POINTER(0);
char *ptr;
int num = 0,
totallen = 0,
numOR = 0;
int state = LQPRS_WAITLEVEL;
lquery *result;
nodeitem *lptr = NULL;
lquery_level *cur,
*curqlevel,
*tmpql;
lquery_variant *lrptr = NULL;
bool hasnot = false;
bool wasbad = false;
int charlen;
int pos = 0;
ptr = buf;
while (*ptr)
{
charlen = pg_mblen(ptr);
if (charlen == 1)
{
if (t_iseq(ptr, '.'))
num++;
else if (t_iseq(ptr, '|'))
numOR++;
}
ptr += charlen;
}
num++;
if (num > MaxAllocSize / ITEMSIZE)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("number of levels (%d) exceeds the maximum allowed (%d)",
num, (int) (MaxAllocSize / ITEMSIZE))));
curqlevel = tmpql = (lquery_level *) palloc0(ITEMSIZE * num);
ptr = buf;
while (*ptr)
{
charlen = pg_mblen(ptr);
if (state == LQPRS_WAITLEVEL)
{
if (ISALNUM(ptr))
{
GETVAR(curqlevel) = lptr = (nodeitem *) palloc0(sizeof(nodeitem) * (numOR + 1));
lptr->start = ptr;
state = LQPRS_WAITDELIM;
curqlevel->numvar = 1;
}
else if (charlen == 1 && t_iseq(ptr, '!'))
{
GETVAR(curqlevel) = lptr = (nodeitem *) palloc0(sizeof(nodeitem) * (numOR + 1));
lptr->start = ptr + 1;
state = LQPRS_WAITDELIM;
curqlevel->numvar = 1;
curqlevel->flag |= LQL_NOT;
hasnot = true;
}
else if (charlen == 1 && t_iseq(ptr, '*'))
state = LQPRS_WAITOPEN;
else
UNCHAR;
}
else if (state == LQPRS_WAITVAR)
{
if (ISALNUM(ptr))
{
lptr++;
lptr->start = ptr;
state = LQPRS_WAITDELIM;
curqlevel->numvar++;
}
else
UNCHAR;
}
else if (state == LQPRS_WAITDELIM)
{
if (charlen == 1 && t_iseq(ptr, '@'))
{
if (lptr->start == ptr)
UNCHAR;
lptr->flag |= LVAR_INCASE;
curqlevel->flag |= LVAR_INCASE;
}
else if (charlen == 1 && t_iseq(ptr, '*'))
{
if (lptr->start == ptr)
UNCHAR;
lptr->flag |= LVAR_ANYEND;
curqlevel->flag |= LVAR_ANYEND;
}
else if (charlen == 1 && t_iseq(ptr, '%'))
{
if (lptr->start == ptr)
UNCHAR;
lptr->flag |= LVAR_SUBLEXEME;
curqlevel->flag |= LVAR_SUBLEXEME;
}
else if (charlen == 1 && t_iseq(ptr, '|'))
{
lptr->len = ptr - lptr->start -
((lptr->flag & LVAR_SUBLEXEME) ? 1 : 0) -
((lptr->flag & LVAR_INCASE) ? 1 : 0) -
((lptr->flag & LVAR_ANYEND) ? 1 : 0);
if (lptr->wlen > 255)
ereport(ERROR,
(errcode(ERRCODE_NAME_TOO_LONG),
errmsg("name of level is too long"),
errdetail("Name length is %d, must "
"be < 256, in position %d.",
lptr->wlen, pos)));
state = LQPRS_WAITVAR;
}
else if (charlen == 1 && t_iseq(ptr, '.'))
{
lptr->len = ptr - lptr->start -
((lptr->flag & LVAR_SUBLEXEME) ? 1 : 0) -
((lptr->flag & LVAR_INCASE) ? 1 : 0) -
((lptr->flag & LVAR_ANYEND) ? 1 : 0);
if (lptr->wlen > 255)
ereport(ERROR,
(errcode(ERRCODE_NAME_TOO_LONG),
errmsg("name of level is too long"),
errdetail("Name length is %d, must "
"be < 256, in position %d.",
lptr->wlen, pos)));
state = LQPRS_WAITLEVEL;
curqlevel = NEXTLEV(curqlevel);
}
else if (ISALNUM(ptr))
{
if (lptr->flag)
UNCHAR;
}
else
UNCHAR;
}
else if (state == LQPRS_WAITOPEN)
{
if (charlen == 1 && t_iseq(ptr, '{'))
state = LQPRS_WAITFNUM;
else if (charlen == 1 && t_iseq(ptr, '.'))
{
curqlevel->low = 0;
curqlevel->high = 0xffff;
curqlevel = NEXTLEV(curqlevel);
state = LQPRS_WAITLEVEL;
}
else
UNCHAR;
}
else if (state == LQPRS_WAITFNUM)
{
if (charlen == 1 && t_iseq(ptr, ','))
state = LQPRS_WAITSNUM;
else if (t_isdigit(ptr))
{
curqlevel->low = atoi(ptr);
state = LQPRS_WAITND;
}
else
UNCHAR;
}
else if (state == LQPRS_WAITSNUM)
{
if (t_isdigit(ptr))
{
curqlevel->high = atoi(ptr);
state = LQPRS_WAITCLOSE;
}
else if (charlen == 1 && t_iseq(ptr, '}'))
{
curqlevel->high = 0xffff;
state = LQPRS_WAITEND;
}
else
UNCHAR;
}
else if (state == LQPRS_WAITCLOSE)
{
if (charlen == 1 && t_iseq(ptr, '}'))
state = LQPRS_WAITEND;
else if (!t_isdigit(ptr))
UNCHAR;
}
else if (state == LQPRS_WAITND)
{
if (charlen == 1 && t_iseq(ptr, '}'))
{
curqlevel->high = curqlevel->low;
state = LQPRS_WAITEND;
}
else if (charlen == 1 && t_iseq(ptr, ','))
state = LQPRS_WAITSNUM;
else if (!t_isdigit(ptr))
UNCHAR;
}
else if (state == LQPRS_WAITEND)
{
if (charlen == 1 && t_iseq(ptr, '.'))
{
state = LQPRS_WAITLEVEL;
curqlevel = NEXTLEV(curqlevel);
}
else
UNCHAR;
}
else
/* internal error */
elog(ERROR, "internal error in parser");
ptr += charlen;
if (state == LQPRS_WAITDELIM)
lptr->wlen++;
pos++;
}
if (state == LQPRS_WAITDELIM)
{
if (lptr->start == ptr)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error"),
errdetail("Unexpected end of line.")));
lptr->len = ptr - lptr->start -
((lptr->flag & LVAR_SUBLEXEME) ? 1 : 0) -
((lptr->flag & LVAR_INCASE) ? 1 : 0) -
((lptr->flag & LVAR_ANYEND) ? 1 : 0);
if (lptr->len == 0)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error"),
errdetail("Unexpected end of line.")));
if (lptr->wlen > 255)
ereport(ERROR,
(errcode(ERRCODE_NAME_TOO_LONG),
errmsg("name of level is too long"),
errdetail("Name length is %d, must "
"be < 256, in position %d.",
lptr->wlen, pos)));
}
else if (state == LQPRS_WAITOPEN)
curqlevel->high = 0xffff;
else if (state != LQPRS_WAITEND)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error"),
errdetail("Unexpected end of line.")));
curqlevel = tmpql;
totallen = LQUERY_HDRSIZE;
while ((char *) curqlevel - (char *) tmpql < num * ITEMSIZE)
{
totallen += LQL_HDRSIZE;
if (curqlevel->numvar)
{
lptr = GETVAR(curqlevel);
while (lptr - GETVAR(curqlevel) < curqlevel->numvar)
{
totallen += MAXALIGN(LVAR_HDRSIZE + lptr->len);
lptr++;
}
}
else if (curqlevel->low > curqlevel->high)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("syntax error"),
errdetail("Low limit(%d) is greater than upper(%d).",
curqlevel->low, curqlevel->high)));
curqlevel = NEXTLEV(curqlevel);
}
result = (lquery *) palloc0(totallen);
SET_VARSIZE(result, totallen);
result->numlevel = num;
result->firstgood = 0;
result->flag = 0;
if (hasnot)
result->flag |= LQUERY_HASNOT;
cur = LQUERY_FIRST(result);
curqlevel = tmpql;
while ((char *) curqlevel - (char *) tmpql < num * ITEMSIZE)
{
memcpy(cur, curqlevel, LQL_HDRSIZE);
cur->totallen = LQL_HDRSIZE;
if (curqlevel->numvar)
{
lrptr = LQL_FIRST(cur);
lptr = GETVAR(curqlevel);
while (lptr - GETVAR(curqlevel) < curqlevel->numvar)
{
cur->totallen += MAXALIGN(LVAR_HDRSIZE + lptr->len);
lrptr->len = lptr->len;
lrptr->flag = lptr->flag;
lrptr->val = ltree_crc32_sz(lptr->start, lptr->len);
memcpy(lrptr->name, lptr->start, lptr->len);
lptr++;
lrptr = LVAR_NEXT(lrptr);
}
pfree(GETVAR(curqlevel));
if (cur->numvar > 1 || cur->flag != 0)
wasbad = true;
else if (wasbad == false)
(result->firstgood)++;
}
else
wasbad = true;
curqlevel = NEXTLEV(curqlevel);
cur = LQL_NEXT(cur);
}
pfree(tmpql);
PG_RETURN_POINTER(result);
}
Datum
tsvectorout(PG_FUNCTION_ARGS)
{
TSVector out = PG_GETARG_TSVECTOR(0);
char *outbuf;
int32 i,
lenbuf = 0,
pp;
WordEntry *ptr = ARRPTR(out);
char *curbegin,
*curin,
*curout;
lenbuf = out->size * 2 /* '' */ + out->size - 1 /* space */ + 2 /* \0 */ ;
for (i = 0; i < out->size; i++)
{
lenbuf += ptr[i].len * 2 * pg_database_encoding_max_length() /* for escape */ ;
if (ptr[i].haspos)
lenbuf += 1 /* : */ + 7 /* int2 + , + weight */ * POSDATALEN(out, &(ptr[i]));
}
curout = outbuf = (char *) palloc(lenbuf);
for (i = 0; i < out->size; i++)
{
curbegin = curin = STRPTR(out) + ptr->pos;
if (i != 0)
*curout++ = ' ';
*curout++ = '\'';
while (curin - curbegin < ptr->len)
{
int len = pg_mblen(curin);
if (t_iseq(curin, '\''))
*curout++ = '\'';
else if (t_iseq(curin, '\\'))
*curout++ = '\\';
while (len--)
*curout++ = *curin++;
}
*curout++ = '\'';
if ((pp = POSDATALEN(out, ptr)) != 0)
{
WordEntryPos *wptr;
*curout++ = ':';
wptr = POSDATAPTR(out, ptr);
while (pp)
{
curout += sprintf(curout, "%d", WEP_GETPOS(*wptr));
switch (WEP_GETWEIGHT(*wptr))
{
case 3:
*curout++ = 'A';
break;
case 2:
*curout++ = 'B';
break;
case 1:
*curout++ = 'C';
break;
case 0:
default:
break;
}
if (pp > 1)
*curout++ = ',';
pp--;
wptr++;
}
}
ptr++;
}
*curout = '\0';
PG_FREE_IF_COPY(out, 0);
PG_RETURN_CSTRING(outbuf);
}
/*
* get token from query string
*/
static int4
gettoken_query(QPRS_STATE *state, int4 *val, int4 *lenval, char **strval, uint16 *flag)
{
int charlen;
for (;;)
{
charlen = pg_mblen(state->buf);
switch (state->state)
{
case WAITOPERAND:
if (charlen == 1 && t_iseq(state->buf, '!'))
{
(state->buf)++;
*val = (int4) '!';
return OPR;
}
else if (charlen == 1 && t_iseq(state->buf, '('))
{
state->count++;
(state->buf)++;
return OPEN;
}
else if (ISALNUM(state->buf))
{
state->state = INOPERAND;
*strval = state->buf;
*lenval = charlen;
*flag = 0;
}
else if (!t_isspace(state->buf))
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("operand syntax error")));
break;
case INOPERAND:
if (ISALNUM(state->buf))
{
if (*flag)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("modificators syntax error")));
*lenval += charlen;
}
else if (charlen == 1 && t_iseq(state->buf, '%'))
*flag |= LVAR_SUBLEXEME;
else if (charlen == 1 && t_iseq(state->buf, '@'))
*flag |= LVAR_INCASE;
else if (charlen == 1 && t_iseq(state->buf, '*'))
*flag |= LVAR_ANYEND;
else
{
state->state = WAITOPERATOR;
return VAL;
}
break;
case WAITOPERATOR:
if (charlen == 1 && (t_iseq(state->buf, '&') || t_iseq(state->buf, '|')))
{
state->state = WAITOPERAND;
*val = (int4) *(state->buf);
(state->buf)++;
return OPR;
}
else if (charlen == 1 && t_iseq(state->buf, ')'))
{
(state->buf)++;
state->count--;
return (state->count < 0) ? ERR : CLOSE;
}
else if (*(state->buf) == '\0')
return (state->count) ? ERR : END;
else if (charlen == 1 && !t_iseq(state->buf, ' '))
return ERR;
break;
default:
return ERR;
break;
}
state->buf += charlen;
}
return END;
}
/*
* 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);
}
}
