X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/336258ecf82548a46715b7165b0547dacc161e07..109af0ef1c55421a166fd2d45586d04fe7f6f969:/test/python/test_tokenizer_icu_rule_loader.py diff --git a/test/python/test_tokenizer_icu_rule_loader.py b/test/python/test_tokenizer_icu_rule_loader.py index c3480de8..e22ccd4b 100644 --- a/test/python/test_tokenizer_icu_rule_loader.py +++ b/test/python/test_tokenizer_icu_rule_loader.py @@ -12,7 +12,16 @@ from nominatim.errors import UsageError from icu import Transliterator @pytest.fixture -def cfgrules(): +def test_config(def_config, tmp_path): + project_dir = tmp_path / 'project_dir' + project_dir.mkdir() + def_config.project_dir = project_dir + + return def_config + + +@pytest.fixture +def cfgrules(test_config): def _create_config(*variants, **kwargs): content = dedent("""\ normalization: @@ -25,36 +34,40 @@ def cfgrules(): - ":: Latin ()" - "[[:Punctuation:][:Space:]]+ > ' '" """) - content += "variants:\n - words:\n" - content += '\n'.join((" - " + s for s in variants)) + '\n' + 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) - return yaml.safe_load(content) + (test_config.project_dir / 'icu_tokenizer.yaml').write_text(content) + + return test_config return _create_config -def test_empty_rule_set(): - rule_cfg = yaml.safe_load(dedent("""\ +def test_empty_rule_set(test_config): + (test_config.project_dir / 'icu_tokenizer.yaml').write_text(dedent("""\ normalization: transliteration: - variants: + token-analysis: + - analyzer: generic + variants: """)) - rules = ICURuleLoader(rule_cfg) + rules = ICURuleLoader(test_config) assert rules.get_search_rules() == '' assert rules.get_normalization_rules() == '' assert rules.get_transliteration_rules() == '' - assert list(rules.get_replacement_pairs()) == [] -CONFIG_SECTIONS = ('normalization', 'transliteration', 'variants') +CONFIG_SECTIONS = ('normalization', 'transliteration', 'token-analysis') @pytest.mark.parametrize("section", CONFIG_SECTIONS) -def test_missing_section(section): - rule_cfg = { s: {} for s in CONFIG_SECTIONS if s != section} +def test_missing_section(section, test_config): + rule_cfg = { s: [] for s in CONFIG_SECTIONS if s != section} + (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(rule_cfg)) with pytest.raises(UsageError): - ICURuleLoader(rule_cfg) + ICURuleLoader(test_config) def test_get_search_rules(cfgrules): @@ -88,26 +101,36 @@ def test_get_transliteration_rules(cfgrules): assert trans.transliterate(" проспект-Prospekt ") == " prospekt Prospekt " -def test_transliteration_rules_from_file(def_config, tmp_path): - def_config.project_dir = tmp_path - cfgpath = tmp_path / ('test_config.yaml') +def test_transliteration_rules_from_file(test_config): + cfgpath = test_config.project_dir / ('icu_tokenizer.yaml') cfgpath.write_text(dedent("""\ normalization: transliteration: - "'ax' > 'b'" - !include transliteration.yaml - variants: + token-analysis: + - analyzer: generic + variants: """)) - transpath = tmp_path / ('transliteration.yaml') + transpath = test_config.project_dir / ('transliteration.yaml') transpath.write_text('- "x > y"') - loader = ICURuleLoader(def_config.load_sub_configuration('test_config.yaml')) + loader = ICURuleLoader(test_config) rules = loader.get_transliteration_rules() trans = Transliterator.createFromRules("test", rules) assert trans.transliterate(" axxt ") == " byt " +def test_search_rules(cfgrules): + config = cfgrules('~street => s,st', 'master => mstr') + proc = ICURuleLoader(config).make_token_analysis() + + assert proc.search.transliterate('Master Street').strip() == 'master street' + assert proc.search.transliterate('Earnes St').strip() == 'earnes st' + assert proc.search.transliterate('Nostreet').strip() == 'nostreet' + + class TestGetReplacements: @pytest.fixture(autouse=True) @@ -116,9 +139,9 @@ class TestGetReplacements: def get_replacements(self, *variants): loader = ICURuleLoader(self.cfgrules(*variants)) - rules = loader.get_replacement_pairs() + rules = loader.analysis[None].config['replacements'] - return set((v.source, v.replacement) for v in rules) + return sorted((k, sorted(v)) for k,v in rules) @pytest.mark.parametrize("variant", ['foo > bar', 'foo -> bar -> bar', @@ -130,131 +153,122 @@ class TestGetReplacements: def test_add_full(self): repl = self.get_replacements("foo -> bar") - assert repl == {(' foo ', ' bar '), (' foo ', ' foo ')} + assert repl == [(' foo ', [' bar', ' foo'])] def test_replace_full(self): repl = self.get_replacements("foo => bar") - assert repl == {(' foo ', ' bar ')} + assert repl == [(' foo ', [' bar'])] def test_add_suffix_no_decompose(self): repl = self.get_replacements("~berg |-> bg") - assert repl == {('berg ', 'berg '), ('berg ', 'bg '), - (' berg ', ' berg '), (' 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") - assert repl == {('berg ', 'berg '), ('berg ', ' berg '), - (' berg ', ' berg '), (' berg ', 'berg '), - ('berg ', 'bg '), ('berg ', ' bg '), - (' berg ', 'bg '), (' 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 '), ('berg ', ' bg '), - (' berg ', 'bg '), (' 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'), (' hinter ', ' hinter '), - (' hinter', ' hnt'), (' 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") - assert repl == {(' hinter', ' hinter'), (' hinter', ' hinter '), - (' hinter', ' h'), (' hinter', ' h '), - (' hinter ', ' hinter '), (' hinter ', ' hinter'), - (' hinter ', ' h '), (' 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'), (' hinter', ' h '), - (' hinter ', ' h '), (' 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 ', '^ premier '), ('^ premier ', '^ pr ')} + assert repl == [('^ premier ', ['^ pr', '^ premier'])] def test_replace_beginning_only(self): repl = self.get_replacements("^Premier => Pr") - assert repl == {('^ premier ', '^ pr ')} + assert repl == [('^ premier ', ['^ pr'])] def test_add_final_only(self): repl = self.get_replacements("road$ -> rd") - assert repl == {(' road ^', ' road ^'), (' road ^', ' rd ^')} + assert repl == [(' road ^', [' rd ^', ' road ^'])] def test_replace_final_only(self): repl = self.get_replacements("road$ => rd") - assert repl == {(' 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 '), (' 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 '), ('berg ', 'bg '), - (' berg ', ' berg '), (' berg ', ' bg '), - ('berg ^', 'berg ^'), ('berg ^', ' berg ^'), - ('berg ^', 'bg ^'), ('berg ^', ' bg ^'), - (' berg ^', 'berg ^'), (' berg ^', 'bg ^'), - (' berg ^', ' berg ^'), (' 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 '), - ('berg ^', 'bg ^'), ('berg ^', ' bg ^'), - (' berg ^', 'bg ^'), (' berg ^', ' bg ^')} + assert repl == [(' berg ', [' bg']), + (' berg ^', [' bg ^', 'bg ^']), + ('berg ', ['bg']), + ('berg ^', [' bg ^', 'bg ^'])] def test_add_multiple_suffix(self): repl = self.get_replacements("~berg,~burg -> bg") - assert repl == {('berg ', 'berg '), ('berg ', ' berg '), - (' berg ', ' berg '), (' berg ', 'berg '), - ('berg ', 'bg '), ('berg ', ' bg '), - (' berg ', 'bg '), (' berg ', ' bg '), - ('burg ', 'burg '), ('burg ', ' burg '), - (' burg ', ' burg '), (' burg ', 'burg '), - ('burg ', 'bg '), ('burg ', ' bg '), - (' burg ', 'bg '), (' burg ', ' bg ')} + assert repl == [(' berg ', [' berg', ' bg', 'berg', 'bg']), + (' burg ', [' bg', ' burg', 'bg', 'burg']), + ('berg ', [' berg', ' bg', 'berg', 'bg']), + ('burg ', [' bg', ' burg', 'bg', 'burg'])]