Add regression tests for ispell, synonym and thesaurus dictionaries.

Rename synonym.syn.sample and thesaurs.ths.sample to
synonym_sample.syn and thesaurs_sample.ths accordingly to be able to use they
in regression test.

Ispell dictionary uses synthetic simple dictionary files.

1 files changed, 121 insertions, 0 deletions

diff --git a/src/test/regress/sql/tsdicts.sql b/src/test/regress/sql/tsdicts.sql
new file mode 100644
index 0000000000..2e6cf791d8
--- /dev/null
+++ b/src/test/regress/sql/tsdicts.sql
@@ -0,0 +1,121 @@
+--Test text search dictionaries and configurations
+
+-- Test ISpell dictionary with ispell affix file
+CREATE TEXT SEARCH DICTIONARY ispell (
+                        Template=ispell,
+                        DictFile=ispell_sample,
+                        AffFile=ispell_sample
+);
+
+SELECT ts_lexize('ispell', 'skies');
+SELECT ts_lexize('ispell', 'bookings');
+SELECT ts_lexize('ispell', 'booking');
+SELECT ts_lexize('ispell', 'foot');
+SELECT ts_lexize('ispell', 'foots');
+SELECT ts_lexize('ispell', 'rebookings');
+SELECT ts_lexize('ispell', 'rebooking');
+SELECT ts_lexize('ispell', 'rebook');
+SELECT ts_lexize('ispell', 'unbookings');
+SELECT ts_lexize('ispell', 'unbooking');
+SELECT ts_lexize('ispell', 'unbook');
+
+SELECT ts_lexize('ispell', 'footklubber');
+SELECT ts_lexize('ispell', 'footballklubber');
+SELECT ts_lexize('ispell', 'ballyklubber');
+SELECT ts_lexize('ispell', 'footballyklubber');
+
+-- Test ISpell dictionary with hunspell affix file
+CREATE TEXT SEARCH DICTIONARY hunspell (
+                        Template=ispell,
+                        DictFile=ispell_sample,
+                        AffFile=hunspell_sample
+);
+
+SELECT ts_lexize('hunspell', 'skies');
+SELECT ts_lexize('hunspell', 'bookings');
+SELECT ts_lexize('hunspell', 'booking');
+SELECT ts_lexize('hunspell', 'foot');
+SELECT ts_lexize('hunspell', 'foots');
+SELECT ts_lexize('hunspell', 'rebookings');
+SELECT ts_lexize('hunspell', 'rebooking');
+SELECT ts_lexize('hunspell', 'rebook');
+SELECT ts_lexize('hunspell', 'unbookings');
+SELECT ts_lexize('hunspell', 'unbooking');
+SELECT ts_lexize('hunspell', 'unbook');
+
+SELECT ts_lexize('hunspell', 'footklubber');
+SELECT ts_lexize('hunspell', 'footballklubber');
+SELECT ts_lexize('hunspell', 'ballyklubber');
+SELECT ts_lexize('hunspell', 'footballyklubber');
+
+-- Synonim dictionary
+CREATE TEXT SEARCH DICTIONARY synonym (
+						Template=synonym, 
+						Synonyms=synonym_sample
+);
+
+SELECT ts_lexize('synonym', 'PoStGrEs');
+SELECT ts_lexize('synonym', 'Gogle');
+
+-- Create and simple test thesaurus dictionary
+-- More test in configuration checks because of ts_lexize
+-- can not give more tat one word as it may wish thesaurus.
+CREATE TEXT SEARCH DICTIONARY thesaurus (
+                        Template=thesaurus,
+						DictFile=thesaurus_sample, 
+						Dictionary=english_stem
+);
+
+SELECT ts_lexize('thesaurus', 'one');
+
+-- Test ispell dictionary in configuration
+CREATE TEXT SEARCH CONFIGURATION ispell_tst (
+						COPY=english
+);
+
+ALTER TEXT SEARCH CONFIGURATION ispell_tst ALTER MAPPING FOR
+	hword, lhword, lpart_hword, lword, nlhword, nlpart_hword, nlword, part_hword, word 
+	WITH ispell, english_stem;
+
+SELECT to_tsvector('ispell_tst', 'Booking the skies after rebookings for footballklubber from a foot');
+SELECT to_tsquery('ispell_tst', 'footballklubber');
+SELECT to_tsquery('ispell_tst', 'footballyklubber:b & rebookings:A & sky');
+
+-- Test ispell dictionary with hunspell affix in configuration
+CREATE TEXT SEARCH CONFIGURATION hunspell_tst (
+						COPY=ispell_tst
+);
+
+ALTER TEXT SEARCH CONFIGURATION hunspell_tst ALTER MAPPING
+	REPLACE ispell WITH hunspell;
+
+SELECT to_tsvector('hunspell_tst', 'Booking the skies after rebookings for footballklubber from a foot');
+SELECT to_tsquery('hunspell_tst', 'footballklubber');
+SELECT to_tsquery('hunspell_tst', 'footballyklubber:b & rebookings:A & sky');
+
+-- Test synonym dictionary in configuration
+CREATE TEXT SEARCH CONFIGURATION synonym_tst (
+						COPY=english
+);
+
+ALTER TEXT SEARCH CONFIGURATION synonym_tst ALTER MAPPING FOR 
+	lword, lpart_hword, lhword 
+	WITH synonym, english_stem;
+
+SELECT to_tsvector('synonym_tst', 'Postgresql is often called as postgres or pgsql and pronounced as postgre');
+SELECT to_tsvector('synonym_tst', 'Most common mistake is to write Gogle instead of Google');
+
+-- test thesaurus in configuration
+-- see thesaurus_sample.ths to understand 'odd' resulting tsvector
+CREATE TEXT SEARCH CONFIGURATION thesaurus_tst (
+						COPY=synonym_tst
+);
+
+ALTER TEXT SEARCH CONFIGURATION thesaurus_tst ALTER MAPPING FOR 
+	lword, lpart_hword, lhword 
+	WITH synonym, thesaurus, english_stem;
+
+SELECT to_tsvector('thesaurus_tst', 'one postgres one two one two three one');
+SELECT to_tsvector('thesaurus_tst', 'Supernovae star is very new star and usually called supernovae (abbrevation SN)');
+SELECT to_tsvector('thesaurus_tst', 'Booking tickets is looking like a booking a tickets');
+