indexing: precompute row counts

[nominatim.git] / test / python / tokenizer / test_icu.py

diff --git a/test/python/tokenizer/test_icu.py b/test/python/tokenizer/test_icu.py
index d85a5b65e565d83187b2688839afe72c1f175fcb..a2bf676699ec9a326f59957740740899da8340dc 100644 (file)
--- a/test/python/tokenizer/test_icu.py
+++ b/test/python/tokenizer/test_icu.py
@@ -1,23 +1,22 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later

 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #

-# Copyright (C) 2022 by the Nominatim developer community.
+# Copyright (C) 2024 by the Nominatim developer community.

 # For a full list of authors see the git log.
 """
 Tests for ICU tokenizer.
 """
 # For a full list of authors see the git log.
 """
 Tests for ICU tokenizer.
 """

-import shutil

 import yaml
 import itertools
 
 import pytest
 
 import yaml
 import itertools
 
 import pytest
 

-from nominatim.tokenizer import icu_tokenizer
-import nominatim.tokenizer.icu_rule_loader
-from nominatim.db import properties
-from nominatim.db.sql_preprocessor import SQLPreprocessor
-from nominatim.indexer.place_info import PlaceInfo
+from nominatim_db.tokenizer import icu_tokenizer
+import nominatim_db.tokenizer.icu_rule_loader
+from nominatim_db.db import properties
+from nominatim_db.db.sql_preprocessor import SQLPreprocessor
+from nominatim_db.data.place_info import PlaceInfo

 
 from mock_icu_word_table import MockIcuWordTable
 
 
 from mock_icu_word_table import MockIcuWordTable
 


@@ -32,8 +31,6 @@ def test_config(project_env, tmp_path):
     sqldir.mkdir()
     (sqldir / 'tokenizer').mkdir()
     (sqldir / 'tokenizer' / 'icu_tokenizer.sql').write_text("SELECT 'a'")
     sqldir.mkdir()
     (sqldir / 'tokenizer').mkdir()
     (sqldir / 'tokenizer' / 'icu_tokenizer.sql').write_text("SELECT 'a'")

-    shutil.copy(str(project_env.lib_dir.sql / 'tokenizer' / 'icu_tokenizer_tables.sql'),
-                str(sqldir / 'tokenizer' / 'icu_tokenizer_tables.sql'))

 
     project_env.lib_dir.sql = sqldir
 
 
     project_env.lib_dir.sql = sqldir
 


@@ -72,7 +69,8 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
 
     def _mk_analyser(norm=("[[:Punctuation:][:Space:]]+ > ' '",), trans=(':: upper()',),
                      variants=('~gasse -> gasse', 'street => st', ),
 
     def _mk_analyser(norm=("[[:Punctuation:][:Space:]]+ > ' '",), trans=(':: upper()',),
                      variants=('~gasse -> gasse', 'street => st', ),

-                     sanitizers=[], with_housenumber=False):
+                     sanitizers=[], with_housenumber=False,
+                     with_postcode=False):

         cfgstr = {'normalization': list(norm),
                   'sanitizers': sanitizers,
                   'transliteration': list(trans),
         cfgstr = {'normalization': list(norm),
                   'sanitizers': sanitizers,
                   'transliteration': list(trans),


@@ -81,8 +79,11 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
         if with_housenumber:
             cfgstr['token-analysis'].append({'id': '@housenumber',
                                              'analyzer': 'housenumbers'})
         if with_housenumber:
             cfgstr['token-analysis'].append({'id': '@housenumber',
                                              'analyzer': 'housenumbers'})

+        if with_postcode:
+            cfgstr['token-analysis'].append({'id': '@postcode',
+                                             'analyzer': 'postcodes'})

         (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr))
         (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr))

-        tok.loader = nominatim.tokenizer.icu_rule_loader.ICURuleLoader(test_config)
+        tok.loader = nominatim_db.tokenizer.icu_rule_loader.ICURuleLoader(test_config)

 
         return tok.name_analyzer()
 
 
         return tok.name_analyzer()
 


@@ -156,7 +157,7 @@ def test_init_new(tokenizer_factory, test_config, db_prop):
     tok = tokenizer_factory()
     tok.init_new_db(test_config)
 
     tok = tokenizer_factory()
     tok.init_new_db(test_config)
 

-    assert db_prop(nominatim.tokenizer.icu_rule_loader.DBCFG_IMPORT_NORM_RULES) \
+    assert db_prop(nominatim_db.tokenizer.icu_rule_loader.DBCFG_IMPORT_NORM_RULES) \

             .startswith(':: lower ();')
 
 
             .startswith(':: lower ();')
 
 


@@ -198,18 +199,16 @@ def test_update_sql_functions(db_prop, temp_db_cursor,
     assert test_content == set((('1133', ), ))
 
 
     assert test_content == set((('1133', ), ))
 
 

-def test_finalize_import(tokenizer_factory, temp_db_conn,
-                         temp_db_cursor, test_config, sql_preprocessor_cfg):
-    func_file = test_config.lib_dir.sql / 'tokenizer' / 'legacy_tokenizer_indices.sql'
-    func_file.write_text("""CREATE FUNCTION test() RETURNS TEXT
-                            AS $$ SELECT 'b'::text $$ LANGUAGE SQL""")
-
+def test_finalize_import(tokenizer_factory, temp_db_cursor,
+                         test_config, sql_preprocessor_cfg):

     tok = tokenizer_factory()
     tok.init_new_db(test_config)
 
     tok = tokenizer_factory()
     tok.init_new_db(test_config)
 

+    assert not temp_db_cursor.index_exists('word', 'idx_word_word_id')
+

     tok.finalize_import(test_config)
 
     tok.finalize_import(test_config)
 

-    temp_db_cursor.scalar('SELECT test()') == 'b'
+    assert temp_db_cursor.index_exists('word', 'idx_word_word_id')

 
 
 def test_check_database(test_config, tokenizer_factory,
 
 
 def test_check_database(test_config, tokenizer_factory,


@@ -220,23 +219,28 @@ def test_check_database(test_config, tokenizer_factory,
     assert tok.check_database(test_config) is None
 
 
     assert tok.check_database(test_config) is None
 
 

-def test_update_statistics_reverse_only(word_table, tokenizer_factory):
+def test_update_statistics_reverse_only(word_table, tokenizer_factory, test_config):

     tok = tokenizer_factory()
     tok = tokenizer_factory()

-    tok.update_statistics()
+    tok.update_statistics(test_config)

 
 
 
 

-def test_update_statistics(word_table, table_factory, temp_db_cursor, tokenizer_factory):
+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(1000, 'hello')

+    word_table.add_full_word(1001, 'bye')

     table_factory('search_name',
     table_factory('search_name',

-                  'place_id BIGINT, name_vector INT[]',
-                  [(12, [1000])])
+                  'place_id BIGINT, name_vector INT[], nameaddress_vector INT[]',
+                  [(12, [1000], [1001])])

     tok = tokenizer_factory()
 
     tok = tokenizer_factory()
 

-    tok.update_statistics()
+    tok.update_statistics(test_config)

 
     assert temp_db_cursor.scalar("""SELECT count(*) FROM word
 
     assert temp_db_cursor.scalar("""SELECT count(*) FROM word

-                                    WHERE type = 'W' and
-                                          (info->>'count')::int > 0""") > 0
+                                    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

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


@@ -246,28 +250,69 @@ def test_normalize_postcode(analyzer):
         anl.normalize_postcode('38 Б') == '38 Б'
 
 
         anl.normalize_postcode('38 Б') == '38 Б'
 
 

-def test_update_postcodes_from_db_empty(analyzer, table_factory, word_table):
-    table_factory('location_postcode', 'postcode TEXT',
-                  content=(('1234',), ('12 34',), ('AB23',), ('1234',)))
+class TestPostcodes:

 
 

-    with analyzer() as anl:
-        anl.update_postcodes_from_db()
+    @pytest.fixture(autouse=True)
+    def setup(self, analyzer, sql_functions):
+        sanitizers = [{'step': 'clean-postcodes'}]
+        with analyzer(sanitizers=sanitizers, with_postcode=True) as anl:
+            self.analyzer = anl
+            yield anl

 
 

-    assert word_table.count() == 3
-    assert word_table.get_postcodes() == {'1234', '12 34', 'AB23'}

 
 

+    def process_postcode(self, cc, postcode):
+        return self.analyzer.process_place(PlaceInfo({'country_code': cc,
+                                                      'address': {'postcode': postcode}}))

 
 

-def test_update_postcodes_from_db_add_and_remove(analyzer, table_factory, word_table):
-    table_factory('location_postcode', 'postcode TEXT',
-                  content=(('1234',), ('45BC', ), ('XX45', )))
-    word_table.add_postcode(' 1234', '1234')
-    word_table.add_postcode(' 5678', '5678')

 
 

-    with analyzer() as anl:
-        anl.update_postcodes_from_db()
+    def test_update_postcodes_from_db_empty(self, table_factory, word_table):
+        table_factory('location_postcode', 'country_code TEXT, postcode TEXT',
+                      content=(('de', '12345'), ('se', '132 34'),
+                               ('bm', 'AB23'), ('fr', '12345')))
+
+        self.analyzer.update_postcodes_from_db()
+
+        assert word_table.count() == 5
+        assert word_table.get_postcodes() == {'12345', '132 34@132 34', 'AB 23@AB 23'}
+
+
+    def test_update_postcodes_from_db_ambigious(self, table_factory, word_table):
+        table_factory('location_postcode', 'country_code TEXT, postcode TEXT',
+                      content=(('in', '123456'), ('sg', '123456')))
+
+        self.analyzer.update_postcodes_from_db()
+
+        assert word_table.count() == 3
+        assert word_table.get_postcodes() == {'123456', '123456@123 456'}
+
+
+    def test_update_postcodes_from_db_add_and_remove(self, table_factory, word_table):
+        table_factory('location_postcode', 'country_code TEXT, postcode TEXT',
+                      content=(('ch', '1234'), ('bm', 'BC 45'), ('bm', 'XX45')))
+        word_table.add_postcode(' 1234', '1234')
+        word_table.add_postcode(' 5678', '5678')
+
+        self.analyzer.update_postcodes_from_db()
+
+        assert word_table.count() == 5
+        assert word_table.get_postcodes() == {'1234', 'BC 45@BC 45', 'XX 45@XX 45'}
+
+
+    def test_process_place_postcode_simple(self, word_table):
+        info = self.process_postcode('de', '12345')
+
+        assert info['postcode'] == '12345'
+
+        assert word_table.get_postcodes() == {'12345', }
+
+
+    def test_process_place_postcode_with_space(self, word_table):
+        info = self.process_postcode('in', '123 567')
+
+        assert info['postcode'] == '123567'
+
+        assert word_table.get_postcodes() == {'123567@123 567', }

 
 

-    assert word_table.count() == 3
-    assert word_table.get_postcodes() == {'1234', '45BC', 'XX45'}

 
 
 def test_update_special_phrase_empty_table(analyzer, word_table):
 
 
 def test_update_special_phrase_empty_table(analyzer, word_table):


@@ -437,13 +482,6 @@ class TestPlaceAddress:
         assert word_table.get_postcodes() == {pcode, }
 
 
         assert word_table.get_postcodes() == {pcode, }
 
 

-    @pytest.mark.parametrize('pcode', ['12:23', 'ab;cd;f', '123;836'])
-    def test_process_place_bad_postcode(self, word_table, pcode):
-        self.process_address(postcode=pcode)
-
-        assert not word_table.get_postcodes()
-
-

     @pytest.mark.parametrize('hnr', ['123a', '1', '101'])
     def test_process_place_housenumbers_simple(self, hnr, getorcreate_hnr_id):
         info = self.process_address(housenumber=hnr)
     @pytest.mark.parametrize('hnr', ['123a', '1', '101'])
     def test_process_place_housenumbers_simple(self, hnr, getorcreate_hnr_id):
         info = self.process_address(housenumber=hnr)


@@ -485,7 +523,7 @@ class TestPlaceAddress:
     def test_process_place_nonexisting_street(self):
         info = self.process_address(street='Grand Road')
 
     def test_process_place_nonexisting_street(self):
         info = self.process_address(street='Grand Road')
 

-        assert 'street' not in info
+        assert info['street'] == '{}'

 
 
     def test_process_place_multiple_street_tags(self):
 
 
     def test_process_place_multiple_street_tags(self):


@@ -500,7 +538,7 @@ class TestPlaceAddress:
     def test_process_place_street_empty(self):
         info = self.process_address(street='🜵')
 
     def test_process_place_street_empty(self):
         info = self.process_address(street='🜵')
 

-        assert 'street' not in info
+        assert info['street'] == '{}'

 
 
     def test_process_place_street_from_cache(self):
 
 
     def test_process_place_street_from_cache(self):


@@ -516,7 +554,7 @@ class TestPlaceAddress:
     def test_process_place_place(self):
         info = self.process_address(place='Honu Lulu')
 
     def test_process_place_place(self):
         info = self.process_address(place='Honu Lulu')
 

-        assert eval(info['place']) == self.name_token_set('HONU', 'LULU')
+        assert eval(info['place']) == self.name_token_set('HONU', 'LULU', '#HONU LULU')

 
 
     def test_process_place_place_extra(self):
 
 
     def test_process_place_place_extra(self):


@@ -536,8 +574,8 @@ class TestPlaceAddress:
                                     suburb='Zwickau', street='Hauptstr',
                                     full='right behind the church')
 
                                     suburb='Zwickau', street='Hauptstr',
                                     full='right behind the church')
 

-        city = self.name_token_set('ZWICKAU')
-        state = self.name_token_set('SACHSEN')
+        city = self.name_token_set('ZWICKAU', '#ZWICKAU')
+        state = self.name_token_set('SACHSEN', '#SACHSEN')

 
         result = {k: eval(v) for k,v in info['addr'].items()}
 
 
         result = {k: eval(v) for k,v in info['addr'].items()}
 


@@ -549,7 +587,7 @@ class TestPlaceAddress:
 
         result = {k: eval(v) for k,v in info['addr'].items()}
 
 
         result = {k: eval(v) for k,v in info['addr'].items()}
 

-        assert result == {'city': self.name_token_set('Bruxelles')}
+        assert result == {'city': self.name_token_set('Bruxelles', '#Bruxelles')}

 
 
     def test_process_place_address_terms_empty(self):
 
 
     def test_process_place_address_terms_empty(self):