port unit tests to new python package layout

test/python/tokenizer/sanitizers/test_clean_housenumbers.py

@@ -1,16 +1,16 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 the sanitizer that normalizes housenumbers.
 """
 import pytest
 
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.data.place_info import PlaceInfo
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
+from nominatim_db.data.place_info import PlaceInfo
 
 @pytest.fixture
 def sanitize(request, def_config):

test/python/tokenizer/sanitizers/test_clean_postcodes.py

@@ -1,17 +1,17 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 the sanitizer that normalizes postcodes.
 """
 import pytest
 
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.data.place_info import PlaceInfo
-from nominatim.data import country_info
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
+from nominatim_db.data.place_info import PlaceInfo
+from nominatim_db.data import country_info
 
 @pytest.fixture
 def sanitize(def_config, request):

test/python/tokenizer/sanitizers/test_clean_tiger_tags.py

@@ -1,16 +1,16 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 sanitizer that clean up TIGER tags.
 """
 import pytest
 
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.data.place_info import PlaceInfo
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
+from nominatim_db.data.place_info import PlaceInfo
 
 class TestCleanTigerTags:
 

test/python/tokenizer/sanitizers/test_delete_tags.py

@@ -1,17 +1,16 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2023 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 the sanitizer that normalizes housenumbers.
 """
 import pytest
 
-
-from nominatim.data.place_info import PlaceInfo
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
+from nominatim_db.data.place_info import PlaceInfo
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
 
 
 class TestWithDefault:
@@ -324,4 +323,4 @@ class TestAllParameters:
                                     name='foo', ref='foo', name_pqr='bar', ref_pqr='baz')
 
         assert res == [('bar', 'name', 'pqr'), ('baz', 'ref', 'pqr'),
-                       ('foo', 'name', ''), ('foo', 'ref', '')]
+                       ('foo', 'name', ''), ('foo', 'ref', '')]

test/python/tokenizer/sanitizers/test_sanitizer_config.py

@@ -1,16 +1,16 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 sanitizer configuration helper functions.
 """
 import pytest
 
-from nominatim.errors import UsageError
-from nominatim.tokenizer.sanitizers.config import SanitizerConfig
+from nominatim_core.errors import UsageError
+from nominatim_db.tokenizer.sanitizers.config import SanitizerConfig
 
 def test_string_list_default_empty():
     assert SanitizerConfig().get_string_list('op') == []

test/python/tokenizer/sanitizers/test_split_name_list.py

@@ -1,18 +1,18 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 the sanitizer that splits multivalue lists.
 """
 import pytest
 
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.data.place_info import PlaceInfo
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
+from nominatim_db.data.place_info import PlaceInfo
 
-from nominatim.errors import UsageError
+from nominatim_core.errors import UsageError
 
 class TestSplitName:
 

test/python/tokenizer/sanitizers/test_strip_brace_terms.py

@@ -1,16 +1,16 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 the sanitizer that handles braced suffixes.
 """
 import pytest
 
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.data.place_info import PlaceInfo
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
+from nominatim_db.data.place_info import PlaceInfo
 
 class TestStripBrace:
 

test/python/tokenizer/sanitizers/test_tag_analyzer_by_language.py

@@ -1,17 +1,17 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 the sanitizer that enables language-dependent analyzers.
 """
 import pytest
 
-from nominatim.data.place_info import PlaceInfo
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.data.country_info import setup_country_config
+from nominatim_db.data.place_info import PlaceInfo
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
+from nominatim_db.data.country_info import setup_country_config
 
 class TestWithDefaults:
 

test/python/tokenizer/sanitizers/test_tag_japanese.py

@@ -1,9 +1,16 @@
-from nominatim.data.place_info import PlaceInfo
-from nominatim.data.place_name import PlaceName
-from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
+# SPDX-License-Identifier: GPL-3.0-or-later
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2024 by the Nominatim developer community.
+# For a full list of authors see the git log.
 from typing import Mapping, Optional, List
 import pytest
 
+from nominatim_db.data.place_info import PlaceInfo
+from nominatim_db.data.place_name import PlaceName
+from nominatim_db.tokenizer.place_sanitizer import PlaceSanitizer
+
 class TestTagJapanese:
     @pytest.fixture(autouse=True)
     def setup_country(self, def_config):

test/python/tokenizer/test_factory.py

@@ -1,17 +1,17 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 creating new tokenizers.
 """
 import pytest
 
-from nominatim.db import properties
-from nominatim.tokenizer import factory
-from nominatim.errors import UsageError
+from nominatim_core.db import properties
+from nominatim_db.tokenizer import factory
+from nominatim_core.errors import UsageError
 from dummy_tokenizer import DummyTokenizer
 
 

test/python/tokenizer/test_icu.py

@@ -1,8 +1,8 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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.
@@ -12,11 +12,11 @@ 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.data.place_info import PlaceInfo
+from nominatim_db.tokenizer import icu_tokenizer
+import nominatim_db.tokenizer.icu_rule_loader
+from nominatim_core.db import properties
+from nominatim_core.db.sql_preprocessor import SQLPreprocessor
+from nominatim_db.data.place_info import PlaceInfo
 
 from mock_icu_word_table import MockIcuWordTable
 
@@ -83,7 +83,7 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
             cfgstr['token-analysis'].append({'id': '@postcode',
                                              'analyzer': 'postcodes'})
         (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()
 
@@ -157,7 +157,7 @@ def test_init_new(tokenizer_factory, test_config, db_prop):
     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 ();')
 
 

test/python/tokenizer/test_icu_rule_loader.py

@@ -1,8 +1,8 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 converting a config file to ICU rules.
@@ -12,8 +12,8 @@ from textwrap import dedent
 import pytest
 import yaml
 
-from nominatim.tokenizer.icu_rule_loader import ICURuleLoader
-from nominatim.errors import UsageError
+from nominatim_db.tokenizer.icu_rule_loader import ICURuleLoader
+from nominatim_core.errors import UsageError
 
 from icu import Transliterator
 

test/python/tokenizer/test_legacy.py

@@ -1,8 +1,8 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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.
 """
 Test for legacy tokenizer.
@@ -12,10 +12,10 @@ import re
 
 import pytest
 
-from nominatim.data.place_info import PlaceInfo
-from nominatim.tokenizer import legacy_tokenizer
-from nominatim.db import properties
-from nominatim.errors import UsageError
+from nominatim_db.data.place_info import PlaceInfo
+from nominatim_db.tokenizer import legacy_tokenizer
+from nominatim_core.db import properties
+from nominatim_core.errors import UsageError
 
 from mock_legacy_word_table import MockLegacyWordTable
 

test/python/tokenizer/test_place_sanitizer.py

@@ -1,17 +1,17 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 execution of the sanitztion step.
 """
 import pytest
 
-from nominatim.errors import UsageError
-import nominatim.tokenizer.place_sanitizer as sanitizer
-from nominatim.data.place_info import PlaceInfo
+from nominatim_core.errors import UsageError
+import nominatim_db.tokenizer.place_sanitizer as sanitizer
+from nominatim_db.data.place_info import PlaceInfo
 
 
 def test_placeinfo_clone_new_name():

test/python/tokenizer/token_analysis/test_analysis_postcodes.py

@@ -1,8 +1,8 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 special postcode analysis and variant generation.
@@ -11,9 +11,9 @@ import pytest
 
 from icu import Transliterator
 
-import nominatim.tokenizer.token_analysis.postcodes as module
-from nominatim.data.place_name import PlaceName
-from nominatim.errors import UsageError
+import nominatim_db.tokenizer.token_analysis.postcodes as module
+from nominatim_db.data.place_name import PlaceName
+from nominatim_core.errors import UsageError
 
 DEFAULT_NORMALIZATION = """ :: NFD ();
                             '🜳' > ' ';

test/python/tokenizer/token_analysis/test_generic.py

@@ -1,8 +1,8 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 import name normalisation and variant generation.
@@ -11,8 +11,8 @@ import pytest
 
 from icu import Transliterator
 
-import nominatim.tokenizer.token_analysis.generic as module
-from nominatim.errors import UsageError
+import nominatim_db.tokenizer.token_analysis.generic as module
+from nominatim_core.errors import UsageError
 
 DEFAULT_NORMALIZATION = """ :: NFD ();
                             '🜳' > ' ';

test/python/tokenizer/token_analysis/test_generic_mutation.py

@@ -1,8 +1,8 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # 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 generic token analysis, mutation part.
@@ -11,8 +11,8 @@ import pytest
 
 from icu import Transliterator
 
-import nominatim.tokenizer.token_analysis.generic as module
-from nominatim.errors import UsageError
+import nominatim_db.tokenizer.token_analysis.generic as module
+from nominatim_core.errors import UsageError
 
 DEFAULT_NORMALIZATION = """ '🜳' > ' ';
                             [[:Nonspacing Mark:] [:Cf:]] >;