X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/c3788d765ed4e7ddf00794085af757714bc102cf..cd08956c610f224096ae831a59eb0412faaaeaad:/test/python/tokenizer/token_analysis/test_generic.py diff --git a/test/python/tokenizer/token_analysis/test_generic.py b/test/python/tokenizer/token_analysis/test_generic.py index 9b008cc5..02870f24 100644 --- a/test/python/tokenizer/token_analysis/test_generic.py +++ b/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) 2025 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_db.errors import UsageError DEFAULT_NORMALIZATION = """ :: NFD (); '🜳' > ' '; @@ -26,27 +26,30 @@ DEFAULT_TRANSLITERATION = """ :: Latin (); '🜵' > ' '; """ + def make_analyser(*variants, variant_only=False): - rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]} + rules = {'analyzer': 'generic', 'variants': [{'words': variants}]} if variant_only: rules['mode'] = 'variant-only' - config = module.configure(rules, DEFAULT_NORMALIZATION) trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION) + norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION) + config = module.configure(rules, norm, trans) - return module.create(trans, config) + return module.create(norm, trans, config) def get_normalized_variants(proc, name): norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION) - return proc.get_variants_ascii(norm.transliterate(name).strip()) + return proc.compute_variants(norm.transliterate(name).strip()) def test_no_variants(): - rules = { 'analyzer': 'generic' } - config = module.configure(rules, DEFAULT_NORMALIZATION) + rules = {'analyzer': 'generic'} trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION) + norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION) + config = module.configure(rules, norm, trans) - proc = module.create(trans, config) + proc = module.create(norm, trans, config) assert get_normalized_variants(proc, '大德!') == ['dà dé'] @@ -60,35 +63,36 @@ def test_variants_empty(): VARIANT_TESTS = [ -(('~strasse,~straße -> str', '~weg => weg'), "hallo", {'hallo'}), -(('weg => wg',), "holzweg", {'holzweg'}), -(('weg -> wg',), "holzweg", {'holzweg'}), -(('~weg => weg',), "holzweg", {'holz weg', 'holzweg'}), -(('~weg -> weg',), "holzweg", {'holz weg', 'holzweg'}), -(('~weg => w',), "holzweg", {'holz w', 'holzw'}), -(('~weg -> w',), "holzweg", {'holz weg', 'holzweg', 'holz w', 'holzw'}), -(('~weg => weg',), "Meier Weg", {'meier weg', 'meierweg'}), -(('~weg -> weg',), "Meier Weg", {'meier weg', 'meierweg'}), -(('~weg => w',), "Meier Weg", {'meier w', 'meierw'}), -(('~weg -> w',), "Meier Weg", {'meier weg', 'meierweg', 'meier w', 'meierw'}), -(('weg => wg',), "Meier Weg", {'meier wg'}), -(('weg -> wg',), "Meier Weg", {'meier weg', 'meier wg'}), -(('~strasse,~straße -> str', '~weg => weg'), "Bauwegstraße", + (('~strasse,~straße -> str', '~weg => weg'), "hallo", {'hallo'}), + (('weg => wg',), "holzweg", {'holzweg'}), + (('weg -> wg',), "holzweg", {'holzweg'}), + (('~weg => weg',), "holzweg", {'holz weg', 'holzweg'}), + (('~weg -> weg',), "holzweg", {'holz weg', 'holzweg'}), + (('~weg => w',), "holzweg", {'holz w', 'holzw'}), + (('~weg -> w',), "holzweg", {'holz weg', 'holzweg', 'holz w', 'holzw'}), + (('~weg => weg',), "Meier Weg", {'meier weg', 'meierweg'}), + (('~weg -> weg',), "Meier Weg", {'meier weg', 'meierweg'}), + (('~weg => w',), "Meier Weg", {'meier w', 'meierw'}), + (('~weg -> w',), "Meier Weg", {'meier weg', 'meierweg', 'meier w', 'meierw'}), + (('weg => wg',), "Meier Weg", {'meier wg'}), + (('weg -> wg',), "Meier Weg", {'meier weg', 'meier wg'}), + (('~strasse,~straße -> str', '~weg => weg'), "Bauwegstraße", {'bauweg straße', 'bauweg str', 'bauwegstraße', 'bauwegstr'}), -(('am => a', 'bach => b'), "am bach", {'a b'}), -(('am => a', '~bach => b'), "am bach", {'a b'}), -(('am -> a', '~bach -> b'), "am bach", {'am bach', 'a bach', 'am b', 'a b'}), -(('am -> a', '~bach -> b'), "ambach", {'ambach', 'am bach', 'amb', 'am b'}), -(('saint -> s,st', 'street -> st'), "Saint Johns Street", + (('am => a', 'bach => b'), "am bach", {'a b'}), + (('am => a', '~bach => b'), "am bach", {'a b'}), + (('am -> a', '~bach -> b'), "am bach", {'am bach', 'a bach', 'am b', 'a b'}), + (('am -> a', '~bach -> b'), "ambach", {'ambach', 'am bach', 'amb', 'am b'}), + (('saint -> s,st', 'street -> st'), "Saint Johns Street", {'saint johns street', 's johns street', 'st johns street', 'saint johns st', 's johns st', 'st johns st'}), -(('river$ -> r',), "River Bend Road", {'river bend road'}), -(('river$ -> r',), "Bent River", {'bent river', 'bent r'}), -(('^north => n',), "North 2nd Street", {'n 2nd street'}), -(('^north => n',), "Airport North", {'airport north'}), -(('am -> a',), "am am am am am am am am", {'am am am am am am am am'}), -(('am => a',), "am am am am am am am am", {'a a a a a a a a'}) -] + (('river$ -> r',), "River Bend Road", {'river bend road'}), + (('river$ -> r',), "Bent River", {'bent river', 'bent r'}), + (('^north => n',), "North 2nd Street", {'n 2nd street'}), + (('^north => n',), "Airport North", {'airport north'}), + (('am -> a',), "am am am am am am am am", {'am am am am am am am am'}), + (('am => a',), "am am am am am am am am", {'a a a a a a a a'}) + ] + @pytest.mark.parametrize("rules,name,variants", VARIANT_TESTS) def test_variants(rules, name, variants): @@ -101,10 +105,11 @@ def test_variants(rules, name, variants): VARIANT_ONLY_TESTS = [ -(('weg => wg',), "hallo", set()), -(('weg => wg',), "Meier Weg", {'meier wg'}), -(('weg -> wg',), "Meier Weg", {'meier wg'}), -] + (('weg => wg',), "hallo", set()), + (('weg => wg',), "Meier Weg", {'meier wg'}), + (('weg -> wg',), "Meier Weg", {'meier wg'}), + ] + @pytest.mark.parametrize("rules,name,variants", VARIANT_ONLY_TESTS) def test_variants_only(rules, name, variants): @@ -120,15 +125,15 @@ class TestGetReplacements: @staticmethod def configure_rules(*variants): - rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]} - return module.configure(rules, DEFAULT_NORMALIZATION) - + rules = {'analyzer': 'generic', 'variants': [{'words': variants}]} + trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION) + norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION) + return module.configure(rules, norm, trans) def get_replacements(self, *variants): config = self.configure_rules(*variants) - return sorted((k, sorted(v)) for k,v in config['replacements']) - + return sorted((k, sorted(v)) for k, v in config['replacements']) @pytest.mark.parametrize("variant", ['foo > bar', 'foo -> bar -> bar', '~foo~ -> bar', 'fo~ o -> bar']) @@ -136,38 +141,32 @@ class TestGetReplacements: with pytest.raises(UsageError): self.configure_rules(variant) - @pytest.mark.parametrize("rule", ["!!! -> bar", "bar => !!!"]) def test_ignore_unnormalizable_terms(self, rule): repl = self.get_replacements(rule) assert repl == [] - def test_add_full(self): repl = self.get_replacements("foo -> bar") assert repl == [(' foo ', [' bar', ' foo'])] - def test_replace_full(self): repl = self.get_replacements("foo => bar") assert repl == [(' foo ', [' bar'])] - def test_add_suffix_no_decompose(self): repl = self.get_replacements("~berg |-> bg") assert repl == [(' berg ', [' berg', ' bg']), ('berg ', ['berg', 'bg'])] - def test_replace_suffix_no_decompose(self): repl = self.get_replacements("~berg |=> bg") - assert repl == [(' berg ', [' bg']),('berg ', ['bg'])] - + assert repl == [(' berg ', [' bg']), ('berg ', ['bg'])] def test_add_suffix_decompose(self): repl = self.get_replacements("~berg -> bg") @@ -175,26 +174,22 @@ class TestGetReplacements: assert repl == [(' berg ', [' berg', ' bg', 'berg', 'bg']), ('berg ', [' berg', ' bg', 'berg', 'bg'])] - def test_replace_suffix_decompose(self): repl = self.get_replacements("~berg => bg") assert repl == [(' berg ', [' bg', 'bg']), ('berg ', [' bg', 'bg'])] - def test_add_prefix_no_compose(self): repl = self.get_replacements("hinter~ |-> hnt") assert repl == [(' hinter', [' hinter', ' hnt']), (' hinter ', [' hinter', ' hnt'])] - def test_replace_prefix_no_compose(self): repl = self.get_replacements("hinter~ |=> hnt") - assert repl == [(' hinter', [' hnt']), (' hinter ', [' hnt'])] - + assert repl == [(' hinter', [' hnt']), (' hinter ', [' hnt'])] def test_add_prefix_compose(self): repl = self.get_replacements("hinter~-> h") @@ -202,45 +197,38 @@ class TestGetReplacements: assert repl == [(' hinter', [' h', ' h ', ' hinter', ' hinter ']), (' hinter ', [' h', ' h', ' hinter', ' hinter'])] - def test_replace_prefix_compose(self): repl = self.get_replacements("hinter~=> h") assert repl == [(' hinter', [' h', ' h ']), (' hinter ', [' h', ' h'])] - def test_add_beginning_only(self): repl = self.get_replacements("^Premier -> Pr") assert repl == [('^ premier ', ['^ pr', '^ premier'])] - def test_replace_beginning_only(self): repl = self.get_replacements("^Premier => Pr") assert repl == [('^ premier ', ['^ pr'])] - def test_add_final_only(self): repl = self.get_replacements("road$ -> rd") assert repl == [(' road ^', [' rd ^', ' road ^'])] - def test_replace_final_only(self): repl = self.get_replacements("road$ => rd") assert repl == [(' road ^', [' rd ^'])] - def test_decompose_only(self): repl = self.get_replacements("~foo -> foo") assert repl == [(' foo ', [' foo', 'foo']), ('foo ', [' foo', 'foo'])] - def test_add_suffix_decompose_end_only(self): repl = self.get_replacements("~berg |-> bg", "~berg$ -> bg") @@ -249,7 +237,6 @@ class TestGetReplacements: ('berg ', ['berg', 'bg']), ('berg ^', [' berg ^', ' bg ^', 'berg ^', 'bg ^'])] - def test_replace_suffix_decompose_end_only(self): repl = self.get_replacements("~berg |=> bg", "~berg$ => bg") @@ -258,7 +245,6 @@ class TestGetReplacements: ('berg ', ['bg']), ('berg ^', [' bg ^', 'bg ^'])] - @pytest.mark.parametrize('rule', ["~berg,~burg -> bg", "~berg, ~burg -> bg", "~berg,,~burg -> bg"])