Rename and slightly redefine the default text search parser's "word"

categories, as per discussion.  asciiword (formerly lword) is still
ASCII-letters-only, and numword (formerly word) is still the most general
mixed-alpha-and-digits case.  But word (formerly nlword) is now
any-group-of-letters-with-at-least-one-non-ASCII, rather than all-non-ASCII as
before.  This is no worse than before for parsing mixed Russian/English text,
which seems to have been the design center for the original coding; and it
should simplify matters for parsing most European languages.  In particular
it will not be necessary for any language to accept strings containing digits
as being regular "words".  The hyphenated-word categories are adjusted
similarly.

1 files changed, 7 insertions, 6 deletions

diff --git a/src/backend/snowball/snowball.sql.in b/src/backend/snowball/snowball.sql.in
index 8b6328a083..7a32c85edb 100644
--- a/src/backend/snowball/snowball.sql.in
+++ b/src/backend/snowball/snowball.sql.in
@@ -1,4 +1,4 @@
--- $PostgreSQL: pgsql/src/backend/snowball/snowball.sql.in,v 1.4 2007/09/03 02:30:43 tgl Exp $$
+-- $PostgreSQL: pgsql/src/backend/snowball/snowball.sql.in,v 1.5 2007/10/23 20:46:12 tgl Exp $$
 
 -- text search configuration for _LANGNAME_ language
 CREATE TEXT SEARCH DICTIONARY _DICTNAME_
@@ -12,14 +12,15 @@ CREATE TEXT SEARCH CONFIGURATION _CFGNAME_
 COMMENT ON TEXT SEARCH CONFIGURATION _CFGNAME_ IS 'configuration for _LANGNAME_ language';
 
 ALTER TEXT SEARCH CONFIGURATION _CFGNAME_ ADD MAPPING
-	FOR email, url, host, sfloat, version, uri, file, float, int, uint
+	FOR email, url, host, sfloat, version, uri, file, float, int, uint,
+            numword, hword_numpart, numhword
 	WITH simple;
 
 ALTER TEXT SEARCH CONFIGURATION _CFGNAME_ ADD MAPPING
-    FOR lhword, lpart_hword, lword
-	WITH _LATDICTNAME_;
+    FOR asciiword, hword_asciipart, asciihword
+	WITH _ASCDICTNAME_;
 
 ALTER TEXT SEARCH CONFIGURATION _CFGNAME_ ADD MAPPING
-    FOR hword, nlhword, nlpart_hword, nlword, word, part_hword
-	WITH _NONLATDICTNAME_;
+    FOR word, hword_part, hword
+	WITH _NONASCDICTNAME_;