adapt tests to extended results

diff --git a/test/python/tokenizer/test_icu.py b/test/python/tokenizer/test_icu.py
index ce00281cff7e09e850fb4d5ee957fb687f65d809..12cef894f863cb2336b1be26240e28fb4a8ba28e 100644 (file)
--- a/test/python/tokenizer/test_icu.py
+++ b/test/python/tokenizer/test_icu.py
@@ -230,19 +230,20 @@ def test_update_statistics(word_table, table_factory, temp_db_cursor,
                            tokenizer_factory, test_config):
     word_table.add_full_word(1000, 'hello')
     word_table.add_full_word(1001, 'bye')
                            tokenizer_factory, test_config):
     word_table.add_full_word(1000, 'hello')
     word_table.add_full_word(1001, 'bye')

+    word_table.add_full_word(1002, 'town')

     table_factory('search_name',
                   'place_id BIGINT, name_vector INT[], nameaddress_vector INT[]',
     table_factory('search_name',
                   'place_id BIGINT, name_vector INT[], nameaddress_vector INT[]',

-                  [(12, [1000], [1001])])
+                  [(12, [1000], [1001]), (13, [1001], [1002]), (14, [1000, 1001], [1002])])

     tok = tokenizer_factory()
 
     tok.update_statistics(test_config)
 
     tok = tokenizer_factory()
 
     tok.update_statistics(test_config)
 

-    assert temp_db_cursor.scalar("""SELECT count(*) FROM word
-                                    WHERE type = 'W' and word_id = 1000 and
-                                          (info->>'count')::int > 0""") == 1
-    assert temp_db_cursor.scalar("""SELECT count(*) FROM word
-                                    WHERE type = 'W' and word_id = 1001 and
-                                          (info->>'addr_count')::int > 0""") == 1
+    assert temp_db_cursor.row_set("""SELECT word_id,
+                                            (info->>'count')::int,
+                                            (info->>'addr_count')::int
+                                     FROM word
+                                     WHERE type = 'W'""") == \
+        {(1000, 2, None), (1001, 2, None), (1002, None, 2)}

 
 
 def test_normalize_postcode(analyzer):
 
 
 def test_normalize_postcode(analyzer):

diff --git a/test/python/tokenizer/token_analysis/test_generic.py b/test/python/tokenizer/token_analysis/test_generic.py
index 02870f2445e7b798a7bc29ffa5aa794d2dd1a9a1..48f2483bc8e54cfe2a6ceed3d89a2efe14c5561e 100644 (file)
--- a/test/python/tokenizer/token_analysis/test_generic.py
+++ b/test/python/tokenizer/token_analysis/test_generic.py
@@ -40,7 +40,7 @@ def make_analyser(*variants, variant_only=False):
 
 def get_normalized_variants(proc, name):
     norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
 
 def get_normalized_variants(proc, name):
     norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)

-    return proc.compute_variants(norm.transliterate(name).strip())
+    return proc.compute_variants(norm.transliterate(name).strip())[0]

 
 
 def test_no_variants():
 
 
 def test_no_variants():

diff --git a/test/python/tokenizer/token_analysis/test_generic_mutation.py b/test/python/tokenizer/token_analysis/test_generic_mutation.py
index 2ce2236a3c490762c965c42a75cdcc4344661c54..e0507e4c30ace40f5d4ead0c0889b10cb8eddb6b 100644 (file)
--- a/test/python/tokenizer/token_analysis/test_generic_mutation.py
+++ b/test/python/tokenizer/token_analysis/test_generic_mutation.py
@@ -40,7 +40,7 @@ class TestMutationNoVariants:
 
     def variants(self, name):
         norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
 
     def variants(self, name):
         norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)

-        return set(self.analysis.compute_variants(norm.transliterate(name).strip()))
+        return set(self.analysis.compute_variants(norm.transliterate(name).strip())[0])

 
     @pytest.mark.parametrize('pattern', ('(capture)', ['a list']))
     def test_bad_pattern(self, pattern):
 
     @pytest.mark.parametrize('pattern', ('(capture)', ['a list']))
     def test_bad_pattern(self, pattern):