+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.
"""
Tests for import name normalisation and variant generation.
"""
-from textwrap import dedent
-
import pytest
-from nominatim.tokenizer.icu_rule_loader import ICURuleLoader
+from icu import Transliterator
+import nominatim.tokenizer.token_analysis.generic as module
from nominatim.errors import UsageError
-@pytest.fixture
-def cfgfile(def_config, tmp_path):
- project_dir = tmp_path / 'project_dir'
- project_dir.mkdir()
- def_config.project_dir = project_dir
-
- def _create_config(*variants, **kwargs):
- content = dedent("""\
- normalization:
- - ":: NFD ()"
- - "'π³' > ' '"
- - "[[:Nonspacing Mark:] [:Cf:]] >"
- - ":: lower ()"
- - "[[:Punctuation:][:Space:]]+ > ' '"
- - ":: NFC ()"
- transliteration:
- - ":: Latin ()"
- - "'π΅' > ' '"
- """)
- content += "token-analysis:\n - analyzer: generic\n variants:\n - words:\n"
- content += '\n'.join((" - " + s for s in variants)) + '\n'
- for k, v in kwargs:
- content += " {}: {}\n".format(k, v)
- (project_dir / 'icu_tokenizer.yaml').write_text(content)
-
- return def_config
-
- return _create_config
+DEFAULT_NORMALIZATION = """ :: NFD ();
+ 'π³' > ' ';
+ [[:Nonspacing Mark:] [:Cf:]] >;
+ :: lower ();
+ [[:Punctuation:][:Space:]]+ > ' ';
+ :: NFC ();
+ """
+
+DEFAULT_TRANSLITERATION = """ :: Latin ();
+ 'π΅' > ' ';
+ """
+
+def make_analyser(*variants, variant_only=False):
+ rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]}
+ if variant_only:
+ rules['mode'] = 'variant-only'
+ trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)
+ norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
+ config = module.configure(rules, norm, trans)
+
+ return module.create(norm, trans, config)
def get_normalized_variants(proc, name):
- return proc.get_variants_ascii(proc.get_normalized(name))
+ norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
+ return proc.compute_variants(norm.transliterate(name).strip())
+
+def test_no_variants():
+ rules = { 'analyzer': 'generic' }
+ trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)
+ norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
+ config = module.configure(rules, norm, trans)
-def test_variants_empty(cfgfile):
- config = cfgfile('saint -> π΅', 'street -> st')
+ proc = module.create(norm, trans, config)
- proc = ICURuleLoader(config).make_token_analysis()
+ assert get_normalized_variants(proc, '倧德!') == ['dà dé']
+
+
+def test_variants_empty():
+ proc = make_analyser('saint -> π΅', 'street -> st')
assert get_normalized_variants(proc, 'π΅') == []
assert get_normalized_variants(proc, 'π³') == []
]
@pytest.mark.parametrize("rules,name,variants", VARIANT_TESTS)
-def test_variants(cfgfile, rules, name, variants):
- config = cfgfile(*rules)
- proc = ICURuleLoader(config).make_token_analysis()
+def test_variants(rules, name, variants):
+ proc = make_analyser(*rules)
+
+ result = get_normalized_variants(proc, name)
+
+ assert len(result) == len(set(result))
+ assert set(get_normalized_variants(proc, name)) == variants
+
+
+VARIANT_ONLY_TESTS = [
+(('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):
+ proc = make_analyser(*rules, variant_only=True)
result = get_normalized_variants(proc, name)
assert set(get_normalized_variants(proc, name)) == variants
-def test_search_normalized(cfgfile):
- config = cfgfile('~street => s,st', 'master => mstr')
- proc = ICURuleLoader(config).make_token_analysis()
+class TestGetReplacements:
+
+ @staticmethod
+ def configure_rules(*variants):
+ 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'])
+
+
+ @pytest.mark.parametrize("variant", ['foo > bar', 'foo -> bar -> bar',
+ '~foo~ -> bar', 'fo~ o -> bar'])
+ def test_invalid_variant_description(self, variant):
+ 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'])]
+
+
+ def test_add_suffix_decompose(self):
+ repl = self.get_replacements("~berg -> bg")
+
+ 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'])]
+
+
+ def test_add_prefix_compose(self):
+ repl = self.get_replacements("hinter~-> h")
+
+ 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")
+
+ assert repl == [(' berg ', [' berg', ' bg']),
+ (' berg ^', [' berg ^', ' bg ^', 'berg ^', 'bg ^']),
+ ('berg ', ['berg', 'bg']),
+ ('berg ^', [' berg ^', ' bg ^', 'berg ^', 'bg ^'])]
+
+
+ def test_replace_suffix_decompose_end_only(self):
+ repl = self.get_replacements("~berg |=> bg", "~berg$ => bg")
+
+ assert repl == [(' berg ', [' bg']),
+ (' berg ^', [' bg ^', 'bg ^']),
+ ('berg ', ['bg']),
+ ('berg ^', [' bg ^', 'bg ^'])]
+
+
+ @pytest.mark.parametrize('rule', ["~berg,~burg -> bg",
+ "~berg, ~burg -> bg",
+ "~berg,,~burg -> bg"])
+ def test_add_multiple_suffix(self, rule):
+ repl = self.get_replacements(rule)
- assert proc.get_search_normalized('Master Street') == 'master street'
- assert proc.get_search_normalized('Earnes St') == 'earnes st'
- assert proc.get_search_normalized('Nostreet') == 'nostreet'
+ assert repl == [(' berg ', [' berg', ' bg', 'berg', 'bg']),
+ (' burg ', [' bg', ' burg', 'bg', 'burg']),
+ ('berg ', [' berg', ' bg', 'berg', 'bg']),
+ ('burg ', [' bg', ' burg', 'bg', 'burg'])]
projects / nominatim.git / blobdiff