Merge remote-tracking branch 'upstream/master'

[nominatim.git] / 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 bb30dc6eae2133b9c3fdb42cf95dab5620657aa6..e22ccd4b054f1a73d3e9bc99b25ba3715356ca38 100644 (file)
--- a/test/python/test_tokenizer_icu_rule_loader.py
+++ b/test/python/test_tokenizer_icu_rule_loader.py
@@ -1,16 +1,27 @@
 """
 Tests for converting a config file to ICU rules.
 """
 """
 Tests for converting a config file to ICU rules.
 """

-import pytest

 from textwrap import dedent
 
 from textwrap import dedent
 

+import pytest
+import yaml
+

 from nominatim.tokenizer.icu_rule_loader import ICURuleLoader
 from nominatim.errors import UsageError
 
 from icu import Transliterator
 
 @pytest.fixture
 from nominatim.tokenizer.icu_rule_loader import ICURuleLoader
 from nominatim.errors import UsageError
 
 from icu import Transliterator
 
 @pytest.fixture

-def cfgfile(tmp_path, suffix='.yaml'):
+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:
     def _create_config(*variants, **kwargs):
         content = dedent("""\
         normalization:


@@ -23,47 +34,44 @@ def cfgfile(tmp_path, suffix='.yaml'):
             - "::  Latin ()"
             - "[[:Punctuation:][:Space:]]+ > ' '"
         """)
             - "::  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)
         for k, v in kwargs:
             content += "    {}: {}\n".format(k, v)

-        fpath = tmp_path / ('test_config' + suffix)
-        fpath.write_text(dedent(content))
-        return fpath
+        (test_config.project_dir / 'icu_tokenizer.yaml').write_text(content)
+
+        return test_config

 
     return _create_config
 
 
 
     return _create_config
 
 

-def test_empty_rule_file(tmp_path):
-    fpath = tmp_path / ('test_config.yaml')
-    fpath.write_text(dedent("""\
+def test_empty_rule_set(test_config):
+    (test_config.project_dir / 'icu_tokenizer.yaml').write_text(dedent("""\

         normalization:
         transliteration:
         normalization:
         transliteration:

-        variants:
+        token-analysis:
+          - analyzer: generic
+            variants:

         """))
 
         """))
 

-    rules = ICURuleLoader(fpath)
+    rules = ICURuleLoader(test_config)

     assert rules.get_search_rules() == ''
     assert rules.get_normalization_rules() == ''
     assert rules.get_transliteration_rules() == ''
     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)
 
 @pytest.mark.parametrize("section", CONFIG_SECTIONS)

-def test_missing_normalization(tmp_path, section):
-    fpath = tmp_path / ('test_config.yaml')
-    with fpath.open('w') as fd:
-        for name in CONFIG_SECTIONS:
-            if name != section:
-                fd.write(name + ':\n')
+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):
 
     with pytest.raises(UsageError):

-        ICURuleLoader(fpath)
+        ICURuleLoader(test_config)

 
 
 
 

-def test_get_search_rules(cfgfile):
-    loader = ICURuleLoader(cfgfile())
+def test_get_search_rules(cfgrules):
+    loader = ICURuleLoader(cfgrules())

 
     rules = loader.get_search_rules()
     trans = Transliterator.createFromRules("test", rules)
 
     rules = loader.get_search_rules()
     trans = Transliterator.createFromRules("test", rules)


@@ -77,188 +85,190 @@ def test_get_search_rules(cfgfile):
     assert trans.transliterate(" проспект ") == " prospekt "
 
 
     assert trans.transliterate(" проспект ") == " prospekt "
 
 

-def test_get_normalization_rules(cfgfile):
-    loader = ICURuleLoader(cfgfile())
+def test_get_normalization_rules(cfgrules):
+    loader = ICURuleLoader(cfgrules())

     rules = loader.get_normalization_rules()
     trans = Transliterator.createFromRules("test", rules)
 
     assert trans.transliterate(" проспект-Prospekt ") == " проспект prospekt "
 
 
     rules = loader.get_normalization_rules()
     trans = Transliterator.createFromRules("test", rules)
 
     assert trans.transliterate(" проспект-Prospekt ") == " проспект prospekt "
 
 

-def test_get_transliteration_rules(cfgfile):
-    loader = ICURuleLoader(cfgfile())
+def test_get_transliteration_rules(cfgrules):
+    loader = ICURuleLoader(cfgrules())

     rules = loader.get_transliteration_rules()
     trans = Transliterator.createFromRules("test", rules)
 
     assert trans.transliterate(" проспект-Prospekt ") == " prospekt Prospekt "
 
 
     rules = loader.get_transliteration_rules()
     trans = Transliterator.createFromRules("test", rules)
 
     assert trans.transliterate(" проспект-Prospekt ") == " prospekt Prospekt "
 
 

-def test_transliteration_rules_from_file(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
     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"')
 
     transpath.write_text('- "x > y"')
 

-    loader = ICURuleLoader(cfgpath)
+    loader = ICURuleLoader(test_config)

     rules = loader.get_transliteration_rules()
     trans = Transliterator.createFromRules("test", rules)
 
     assert trans.transliterate(" axxt ") == " byt "
 
 
     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)
 class TestGetReplacements:
 
     @pytest.fixture(autouse=True)

-    def setup_cfg(self, cfgfile):
-        self.cfgfile = cfgfile
+    def setup_cfg(self, cfgrules):
+        self.cfgrules = cfgrules

 
     def get_replacements(self, *variants):
 
     def get_replacements(self, *variants):

-        loader = ICURuleLoader(self.cfgfile(*variants))
-        rules = loader.get_replacement_pairs()
+        loader = ICURuleLoader(self.cfgrules(*variants))
+        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',
                                          '~foo~ -> bar', 'fo~ o -> bar'])
     def test_invalid_variant_description(self, variant):
         with pytest.raises(UsageError):
 
 
     @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):

-            ICURuleLoader(self.cfgfile(variant))
+            ICURuleLoader(self.cfgrules(variant))

 
     def test_add_full(self):
         repl = self.get_replacements("foo -> bar")
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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")
 
 
 
     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'])]