make token analyzers configurable modules

[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 d89e13b519d196de4422650e011dbcd103397866..b76eee75c9a5660cc6fd590a7a4fc3cd088eeac6 100644 (file)
--- a/test/python/test_tokenizer_icu_rule_loader.py
+++ b/test/python/test_tokenizer_icu_rule_loader.py
@@ -1,17 +1,28 @@
 """
 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 _create_config(suffixes, abbr):
+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:
             - ":: NFD ()"
         content = dedent("""\
         normalization:
             - ":: NFD ()"


@@ -21,55 +32,243 @@ def cfgfile(tmp_path, suffix='.yaml'):
             - ":: NFC ()"
         transliteration:
             - "::  Latin ()"
             - ":: NFC ()"
         transliteration:
             - "::  Latin ()"

+            - "[[:Punctuation:][:Space:]]+ > ' '"

         """)
         """)

-        content += "compound_suffixes:\n"
-        content += '\n'.join(("    - " + s for s in suffixes)) + '\n'
-        content += "abbreviations:\n"
-        content += '\n'.join(("    - " + s for s in abbr)) + '\n'
-        fpath = tmp_path / ('test_config' + suffix)
-        fpath.write_text(dedent(content))
-        return fpath
+        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)
+        (test_config.project_dir / 'icu_tokenizer.yaml').write_text(content)
+
+        return test_config

 
     return _create_config
 
 
     return _create_config
 

-def test_missing_normalization(tmp_path):
-    fpath = tmp_path / ('test_config.yaml')
-    fpath.write_text(dedent("""\
-        normalizatio:
-            - ":: NFD ()"
+
+def test_empty_rule_set(test_config):
+    (test_config.project_dir / 'icu_tokenizer.yaml').write_text(dedent("""\
+        normalization:
+        transliteration:
+        token-analysis:
+          - analyzer: generic
+            variants:

         """))
 
         """))
 

-    with pytest.raises(UsageError):
-        ICURuleLoader(fpath)
+    rules = ICURuleLoader(test_config)
+    assert rules.get_search_rules() == ''
+    assert rules.get_normalization_rules() == ''
+    assert rules.get_transliteration_rules() == ''

 
 

+CONFIG_SECTIONS = ('normalization', 'transliteration', 'token-analysis')
+
+@pytest.mark.parametrize("section", CONFIG_SECTIONS)
+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(test_config)

 
 

-def test_get_search_rules(cfgfile):
-    fpath = cfgfile(['strasse', 'straße', 'weg'],
-                    ['strasse,straße => str',
-                     'prospekt => pr'])

 
 

-    loader = ICURuleLoader(fpath)
+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)
 

-    assert trans.transliterate(" Baumstraße ") == " baum straße "
-    assert trans.transliterate(" Baumstrasse ") == " baum strasse "
-    assert trans.transliterate(" Baumstr ") == " baum str "
-    assert trans.transliterate(" Baumwegstr ") == " baumweg str "
+    assert trans.transliterate(" Baum straße ") == " baum straße "
+    assert trans.transliterate(" Baumstraße ") == " baumstraße "
+    assert trans.transliterate(" Baumstrasse ") == " baumstrasse "
+    assert trans.transliterate(" Baumstr ") == " baumstr "
+    assert trans.transliterate(" Baumwegstr ") == " baumwegstr "

     assert trans.transliterate(" Αθήνα ") == " athēna "
     assert trans.transliterate(" проспект ") == " prospekt "
 
 
     assert trans.transliterate(" Αθήνα ") == " athēna "
     assert trans.transliterate(" проспект ") == " prospekt "
 
 

-def test_get_synonym_pairs(cfgfile):
-    fpath = cfgfile(['Weg', 'Strasse'],
-                    ['Strasse => str,st'])
+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 "
+
+
+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 "
+
+
+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
+        token-analysis:
+            - analyzer: generic
+              variants:
+        """))
+    transpath = test_config.project_dir / ('transliteration.yaml')
+    transpath.write_text('- "x > y"')
+
+    loader = ICURuleLoader(test_config)
+    rules = loader.get_transliteration_rules()
+    trans = Transliterator.createFromRules("test", rules)
+
+    assert trans.transliterate(" axxt ") == " byt "
+
+
+class TestGetReplacements:
+
+    @pytest.fixture(autouse=True)
+    def setup_cfg(self, cfgrules):
+        self.cfgrules = cfgrules
+
+    def get_replacements(self, *variants):
+        loader = ICURuleLoader(self.cfgrules(*variants))
+        rules = loader.analysis[None].config['variants']
+
+        return set((v.source, v.replacement) for 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):
+            ICURuleLoader(self.cfgrules(variant))
+
+    def test_add_full(self):
+        repl = self.get_replacements("foo -> bar")
+
+        assert repl == {(' foo ', ' bar '), (' foo ', ' 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 '), ('berg ', 'bg '),
+                        (' berg ', ' 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 '), ('berg ', ' berg '),
+                        (' berg ', ' berg '), (' berg ', 'berg '),
+                        ('berg ', 'bg '), ('berg ', ' bg '),
+                        (' 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 ')}
+
+
+    def test_add_prefix_no_compose(self):
+        repl = self.get_replacements("hinter~ |-> hnt")
+
+        assert repl == {(' hinter', ' hinter'), (' hinter ', ' hinter '),
+                        (' hinter', ' hnt'), (' 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', ' hinter'), (' hinter', ' hinter '),
+                        (' hinter', ' h'), (' hinter', ' h '),
+                        (' hinter ', ' hinter '), (' hinter ', ' hinter'),
+                        (' hinter ', ' h '), (' hinter ', ' h')}
+
+
+    def test_replace_prefix_compose(self):
+        repl = self.get_replacements("hinter~=> h")
+
+        assert repl == {(' hinter', ' h'), (' hinter', ' h '),
+                        (' hinter ', ' h '), (' hinter ', ' h')}
+
+
+    def test_add_beginning_only(self):
+        repl = self.get_replacements("^Premier -> Pr")
+
+        assert repl == {('^ premier ', '^ premier '), ('^ premier ', '^ pr ')}
+
+
+    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 ^', ' road ^'), (' road ^', ' rd ^')}
+
+
+    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 '), (' 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 ^')}
+
+
+    def test_replace_suffix_decompose_end_only(self):
+        repl = self.get_replacements("~berg |=> bg", "~berg$ => bg")

 
 

-    loader = ICURuleLoader(fpath)
+        assert repl == {('berg ', 'bg '), (' berg ', ' bg '),
+                        ('berg ^', 'bg ^'), ('berg ^', ' bg ^'),
+                        (' berg ^', 'bg ^'), (' berg ^', ' bg ^')}

 
 

-    repl = loader.get_replacement_pairs()

 
 

-    assert repl == [(' strasse ', {' strasse ', ' str ', ' st '}),
-                    ('strasse ', {' strasse ', ' str ', ' st '}),
-                    ('weg ', {' weg '})]
+    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 ')}