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 161dff94e9ce8b6a3007f3655df64f783229db93..e22ccd4b054f1a73d3e9bc99b25ba3715356ca38 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 ()"


@@ -23,69 +34,44 @@ def cfgfile(tmp_path, suffix='.yaml'):
             - "::  Latin ()"
             - "[[:Punctuation:][:Space:]]+ > ' '"
         """)
             - "::  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_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:

-        compound_suffixes:
-        abbreviations:
+        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 rules.get_replacement_pairs() == []

 
 

-CONFIG_SECTIONS = ('normalization', 'transliteration',
-                   'compound_suffixes', 'abbreviations')
+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)
-
-@pytest.mark.parametrize("abbr", ["simple",
-                                  "double => arrow => bad",
-                                  "bad = > arrow"])
-def test_bad_abbreviation_syntax(tmp_path, abbr):
-    fpath = tmp_path / ('test_config.yaml')
-    fpath.write_text(dedent("""\
-        normalization:
-        transliteration:
-        compound_suffixes:
-        abbreviations:
-         - {}
-        """.format(abbr)))
-
-    with pytest.raises(UsageError):
-        rules = ICURuleLoader(fpath)
+        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)


@@ -99,95 +85,190 @@ def test_get_search_rules(cfgfile):
     assert trans.transliterate(" проспект ") == " prospekt "
 
 
     assert trans.transliterate(" проспект ") == " prospekt "
 
 

-def test_get_normalization_rules(cfgfile):
-    fpath = cfgfile(['strasse', 'straße', 'weg'],
-                    ['strasse,straße => str'])
-
-    loader = ICURuleLoader(fpath)
+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):
-    fpath = cfgfile(['strasse', 'straße', 'weg'],
-                    ['strasse,straße => str'])
-
-    loader = ICURuleLoader(fpath)
+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

-        compound_suffixes:
-        abbreviations:
+        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_get_replacement_pairs_multi_to(cfgfile):
-    fpath = cfgfile(['Pfad', 'Strasse'],
-                    ['Strasse => str,st'])
+def test_search_rules(cfgrules):
+    config = cfgrules('~street => s,st', 'master => mstr')
+    proc = ICURuleLoader(config).make_token_analysis()

 
 

-    repl = ICURuleLoader(fpath).get_replacement_pairs()
+    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'

 
 

-    assert [(a, sorted(b)) for a, b in repl] == \
-             [(' strasse ', [' st ', ' str ', ' strasse ', 'st ', 'str ', 'strasse ']),
-              ('strasse ', [' st ', ' str ', ' strasse ', 'st ', 'str ', 'strasse ']),
-              (' pfad ', [' pfad ', 'pfad ']),
-              ('pfad ', [' pfad ', 'pfad '])]

 
 

+class TestGetReplacements:

 
 

-def test_get_replacement_pairs_multi_from(cfgfile):
-    fpath = cfgfile([], ['saint,Sainte => st'])
+    @pytest.fixture(autouse=True)
+    def setup_cfg(self, cfgrules):
+        self.cfgrules = cfgrules

 
 

-    repl = ICURuleLoader(fpath).get_replacement_pairs()
+    def get_replacements(self, *variants):
+        loader = ICURuleLoader(self.cfgrules(*variants))
+        rules = loader.analysis[None].config['replacements']

 
 

-    assert [(a, sorted(b)) for a, b in repl] == \
-             [(' sainte ', [' sainte ', ' st ']),
-              (' saint ', [' saint ', ' st '])]
+        return sorted((k, sorted(v)) for k,v in rules)

 
 
 
 

-def test_get_replacement_pairs_cross_abbreviations(cfgfile):
-    fpath = cfgfile([], ['saint,Sainte => st',
-                         'sainte => ste'])
+    @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))

 
 

-    repl = ICURuleLoader(fpath).get_replacement_pairs()
+    def test_add_full(self):
+        repl = self.get_replacements("foo -> bar")

 
 

-    assert [(a, sorted(b)) for a, b in repl] == \
-             [(' sainte ', [' sainte ', ' st ', ' ste ']),
-              (' saint ', [' saint ', ' st '])]
+        assert repl == [(' foo ', [' bar', ' foo'])]

 
 
 
 

-@pytest.mark.parametrize("abbr", ["missing to =>",
-                                  "  => missing from",
-                                  "=>"])
-def test_bad_abbreviation_syntax(tmp_path, abbr):
-    fpath = tmp_path / ('test_config.yaml')
-    fpath.write_text(dedent("""\
-        normalization:
-        transliteration:
-        compound_suffixes:
-        abbreviations:
-         - {}
-        """.format(abbr)))
+    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 ^'])]
+

 
 

-    repl = ICURuleLoader(fpath).get_replacement_pairs()
+    def test_add_multiple_suffix(self):
+        repl = self.get_replacements("~berg,~burg -> bg")

 
 

-    assert repl == []
+        assert repl == [(' berg ', [' berg', ' bg', 'berg', 'bg']),
+                        (' burg ', [' bg', ' burg', 'bg', 'burg']),
+                        ('berg ', [' berg', ' bg', 'berg', 'bg']),
+                        ('burg ', [' bg', ' burg', 'bg', 'burg'])]