Add a CaseSensitive parameter to synonym dictionaries.

tglsfdc · tglsfdc · commit 7953fdcd9ecf · 2008-03-10T03:01:28.000Z
Simon Riggs
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 1.41 2008/03/04 03:17:18 momjian Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.42 2008/03/10 03:01:28 tgl Exp $ -->
 
 <chapter id="textsearch">
  <title id="textsearch-title">Full Text Search</title>
@@ -2209,7 +2209,8 @@ SELECT ts_lexize('public.simple_dict','The');
     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 <literal>Paris paris</literal> line in the
-    synonym dictionary and put it before the <literal>english_stem</> dictionary:
+    synonym dictionary and put it before the <literal>english_stem</>
+    dictionary.  For example:
 
 <programlisting>
 SELECT * FROM ts_debug('english', 'Paris');
@@ -2242,10 +2243,17 @@ SELECT * FROM ts_debug('english', 'Paris');
     <productname>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.
    </para>
 
+   <para>
+    The <literal>synonym</> template also has an optional parameter
+    <literal>CaseSensitive</>, which defaults to <literal>false</>.  When
+    <literal>CaseSensitive</> is <literal>false</>, words in the synonym file
+    are folded to lower case, as are input tokens.  When it is
+    <literal>true</>, words and tokens are not folded to lower case,
+    but are compared as-is.
+   </para>
   </sect2>
 
   <sect2 id="textsearch-thesaurus">
diff --git a/src/backend/tsearch/dict_synonym.c b/src/backend/tsearch/dict_synonym.c
@@ -7,7 +7,7 @@
  *
  *
  * 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 $
  *
  *-------------------------------------------------------------------------
  */
@@ -30,6 +30,7 @@ typedef struct
 {
 	int			len;			/* length of syn array */
 	Syn		   *syn;
+	bool		case_sensitive;
 } DictSyn;
 
 /*
@@ -77,6 +78,7 @@ dsynonym_init(PG_FUNCTION_ARGS)
 	DictSyn    *d;
 	ListCell   *l;
 	char	   *filename = NULL;
+	bool		case_sensitive = false;
 	FILE	   *fin;
 	char	   *starti,
 			   *starto,
@@ -90,6 +92,8 @@ dsynonym_init(PG_FUNCTION_ARGS)
 
 		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),
@@ -154,8 +158,16 @@ dsynonym_init(PG_FUNCTION_ARGS)
 			}
 		}
 
-		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++;
 
@@ -168,6 +180,8 @@ dsynonym_init(PG_FUNCTION_ARGS)
 	d->len = cur;
 	qsort(d->syn, d->len, sizeof(Syn), compareSyn);
 
+	d->case_sensitive = case_sensitive;
+
 	PG_RETURN_POINTER(d);
 }
 
@@ -185,7 +199,11 @@ dsynonym_lexize(PG_FUNCTION_ARGS)
 	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);
