Merge remote-tracking branch 'upstream/master'

[nominatim.git] / test / python / tokenizer / token_analysis / test_generic.py

diff --git a/test/python/tokenizer/token_analysis/test_generic.py b/test/python/tokenizer/token_analysis/test_generic.py
index 02a95f25b15d9403ba567e867f2e541731be9c06..191f551f86debcef7d011a102b5adf60803030f6 100644 (file)
--- a/test/python/tokenizer/token_analysis/test_generic.py
+++ b/test/python/tokenizer/token_analysis/test_generic.py
@@ -1,3 +1,9 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2024 by the Nominatim developer community.
+# For a full list of authors see the git log.

 """
 Tests for import name normalisation and variant generation.
 """
 """
 Tests for import name normalisation and variant generation.
 """


@@ -5,8 +11,8 @@ import pytest
 
 from icu import Transliterator
 
 
 from icu import Transliterator
 

-import nominatim.tokenizer.token_analysis.generic as module
-from nominatim.errors import UsageError
+import nominatim_db.tokenizer.token_analysis.generic as module
+from nominatim_db.errors import UsageError

 
 DEFAULT_NORMALIZATION = """ :: NFD ();
                             '🜳' > ' ';
 
 DEFAULT_NORMALIZATION = """ :: NFD ();
                             '🜳' > ' ';


@@ -24,23 +30,25 @@ def make_analyser(*variants, variant_only=False):
     rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]}
     if variant_only:
         rules['mode'] = 'variant-only'
     rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]}
     if variant_only:
         rules['mode'] = 'variant-only'

-    config = module.configure(rules, DEFAULT_NORMALIZATION)

     trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)
     trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)

+    norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
+    config = module.configure(rules, norm, trans)

 
 

-    return module.create(trans, config)
+    return module.create(norm, trans, config)

 
 
 def get_normalized_variants(proc, name):
     norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
 
 
 def get_normalized_variants(proc, name):
     norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)

-    return proc.get_variants_ascii(norm.transliterate(name).strip())
+    return proc.compute_variants(norm.transliterate(name).strip())

 
 
 def test_no_variants():
     rules = { 'analyzer': 'generic' }
 
 
 def test_no_variants():
     rules = { 'analyzer': 'generic' }

-    config = module.configure(rules, DEFAULT_NORMALIZATION)

     trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)
     trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)

+    norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
+    config = module.configure(rules, norm, trans)

 
 

-    proc = module.create(trans, config)
+    proc = module.create(norm, trans, config)

 
     assert get_normalized_variants(proc, '大德!') == ['dà dé']
 
 
     assert get_normalized_variants(proc, '大德!') == ['dà dé']
 


@@ -115,7 +123,9 @@ class TestGetReplacements:
     @staticmethod
     def configure_rules(*variants):
         rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]}
     @staticmethod
     def configure_rules(*variants):
         rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]}

-        return module.configure(rules, DEFAULT_NORMALIZATION)
+        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):
 
 
     def get_replacements(self, *variants):