-
+
Full Text Search
dictionary can be used to overcome linguistic problems, for example, to
prevent an English stemmer dictionary from reducing the word 'Paris' to
'pari'. It is enough to have a Paris paris line in the
- synonym dictionary and put it before the english_stem> dictionary:
+ synonym dictionary and put it before the english_stem>
+ dictionary. For example:
SELECT * FROM ts_debug('english', 'Paris');
PostgreSQL> installation's shared-data directory).
The file format is just one line
per word to be substituted, with the word followed by its synonym,
- separated by white space. Blank lines and trailing spaces are ignored,
- and upper case is folded to lower case.
+ separated by white space. Blank lines and trailing spaces are ignored.
+ The synonym> template also has an optional parameter
+ CaseSensitive>, which defaults to false>. When
+ CaseSensitive> is false>, words in the synonym file
+ are folded to lower case, as are input tokens. When it is
+ true>, words and tokens are not folded to lower case,
+ but are compared as-is.
+
*
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/tsearch/dict_synonym.c,v 1.7 2008/01/01 19:45:52 momjian Exp $
+ * $PostgreSQL: pgsql/src/backend/tsearch/dict_synonym.c,v 1.8 2008/03/10 03:01:28 tgl Exp $
*
*-------------------------------------------------------------------------
*/
{
int len; /* length of syn array */
Syn *syn;
+ bool case_sensitive;
} DictSyn;
/*
DictSyn *d;
ListCell *l;
char *filename = NULL;
+ bool case_sensitive = false;
FILE *fin;
char *starti,
*starto,
if (pg_strcasecmp("Synonyms", defel->defname) == 0)
filename = defGetString(defel);
+ else if (pg_strcasecmp("CaseSensitive", defel->defname) == 0)
+ case_sensitive = defGetBoolean(defel);
else
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
}
}
- d->syn[cur].in = lowerstr(starti);
- d->syn[cur].out = lowerstr(starto);
+ if (case_sensitive)
+ {
+ d->syn[cur].in = pstrdup(starti);
+ d->syn[cur].out = pstrdup(starto);
+ }
+ else
+ {
+ d->syn[cur].in = lowerstr(starti);
+ d->syn[cur].out = lowerstr(starto);
+ }
cur++;
d->len = cur;
qsort(d->syn, d->len, sizeof(Syn), compareSyn);
+ d->case_sensitive = case_sensitive;
+
PG_RETURN_POINTER(d);
}
if (len <= 0 || d->len <= 0)
PG_RETURN_POINTER(NULL);
- key.in = lowerstr_with_len(in, len);
+ if (d->case_sensitive)
+ key.in = pnstrdup(in, len);
+ else
+ key.in = lowerstr_with_len(in, len);
+
key.out = NULL;
found = (Syn *) bsearch(&key, d->syn, d->len, sizeof(Syn), compareSyn);