Add an Accept parameter to "simple" dictionaries. The default of true

tglsfdc · tglsfdc · commit ca450a07eeee · 2007-11-14T18:36:37.000Z
gives the old behavior; selecting false allows the dictionary to be used
as a filter ahead of other dictionaries, because it will pass on rather
than accept words that aren't in its stopword list.
Jan Urbanski
diff --git a/doc/src/sgml/textsearch.sgml b/doc/src/sgml/textsearch.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.32 2007/11/14 03:26:24 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.33 2007/11/14 18:36:37 tgl Exp $ -->
 
 <chapter id="textsearch">
  <title id="textsearch-title">Full Text Search</title>
@@ -2093,9 +2093,11 @@ SELECT ts_rank_cd (to_tsvector('english','list stop words'), to_tsquery('list &a
    <para>
     The <literal>simple</> dictionary template operates by converting the
     input token to lower case and checking it against a file of stop words.
-    If it is found in the file then <literal>NULL</> is returned, causing
+    If it is found in the file then an empty array is returned, causing
     the token to be discarded.  If not, the lower-cased form of the word
-    is returned as the normalized lexeme.
+    is returned as the normalized lexeme.  Alternatively, the dictionary
+    can be configured to report non-stop-words as unrecognized, allowing
+    them to be passed on to the next dictionary in the list.
    </para>
 
    <para>
@@ -2138,6 +2140,35 @@ SELECT ts_lexize('public.simple_dict','The');
 </programlisting>
    </para>
 
+   <para>
+    We can also choose to return <literal>NULL</>, instead of the lower-cased
+    word, if it is not found in the stop words file.  This behavior is
+    selected by setting the dictionary's <literal>Accept</> parameter to
+    <literal>false</>.  Continuing the example:
+
+<programlisting>
+ALTER TEXT SEARCH DICTIONARY public.simple_dict ( Accept = false );
+
+SELECT ts_lexize('public.simple_dict','YeS');
+ ts_lexize
+-----------
+
+
+SELECT ts_lexize('public.simple_dict','The');
+ ts_lexize
+-----------
+ {}
+</programlisting>
+   </para>
+
+   <para>
+    With the default setting of <literal>Accept</> = <literal>true</>,
+    it is only useful to place a <literal>simple</> dictionary at the end
+    of a list of dictionaries, since it will never pass on any token to
+    a following dictionary.  Conversely, <literal>Accept</> = <literal>false</>
+    is only useful when there is at least one following dictionary.
+   </para>
+
    <caution>
     <para>
      Most types of dictionaries rely on configuration files, such as files of
diff --git a/src/backend/tsearch/dict_simple.c b/src/backend/tsearch/dict_simple.c
@@ -7,7 +7,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/tsearch/dict_simple.c,v 1.3 2007/08/25 00:03:59 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/tsearch/dict_simple.c,v 1.4 2007/11/14 18:36:37 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -23,6 +23,7 @@
 typedef struct
 {
 	StopList	stoplist;
+	bool		accept;
 } DictSimple;
 
 
@@ -31,9 +32,12 @@ dsimple_init(PG_FUNCTION_ARGS)
 {
 	List	   *dictoptions = (List *) PG_GETARG_POINTER(0);
 	DictSimple *d = (DictSimple *) palloc0(sizeof(DictSimple));
-	bool		stoploaded = false;
+	bool		stoploaded = false,
+				acceptloaded = false;
 	ListCell   *l;
 
+	d->accept = true;			/* default */
+
 	foreach(l, dictoptions)
 	{
 		DefElem    *defel = (DefElem *) lfirst(l);
@@ -47,6 +51,15 @@ dsimple_init(PG_FUNCTION_ARGS)
 			readstoplist(defGetString(defel), &d->stoplist, lowerstr);
 			stoploaded = true;
 		}
+		else if (pg_strcasecmp("Accept", defel->defname) == 0)
+		{
+			if (acceptloaded)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+						 errmsg("multiple Accept parameters")));
+			d->accept = defGetBoolean(defel);
+			acceptloaded = true;
+		}
 		else
 		{
 			ereport(ERROR,
@@ -66,14 +79,28 @@ dsimple_lexize(PG_FUNCTION_ARGS)
 	char	   *in = (char *) PG_GETARG_POINTER(1);
 	int32	   len = PG_GETARG_INT32(2);
 	char	   *txt;
-	TSLexeme   *res = palloc0(sizeof(TSLexeme) * 2);
+	TSLexeme   *res;
 
 	txt = lowerstr_with_len(in, len);
 
 	if (*txt == '\0' || searchstoplist(&(d->stoplist), txt))
+	{
+		/* reject as stopword */
 		pfree(txt);
-	else
+		res = palloc0(sizeof(TSLexeme) * 2);
+		PG_RETURN_POINTER(res);
+	}
+	else if (d->accept)
+	{
+		/* accept */
+		res = palloc0(sizeof(TSLexeme) * 2);
 		res[0].lexeme = txt;
-
-	PG_RETURN_POINTER(res);
+		PG_RETURN_POINTER(res);
+	}
+	else
+	{
+		/* report as unrecognized */
+		pfree(txt);
+		PG_RETURN_POINTER(NULL);
+	}
 }
