-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later
#
# This file is part of Nominatim. (https://nominatim.org)
#
-# Copyright (C) 2022 by the Nominatim developer community.
+# 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.
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 ();
'🜳' > ' ';
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)
+ 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)
- return proc.get_variants_ascii(norm.transliterate(name).strip())
+ return proc.compute_variants(norm.transliterate(name).strip())
def test_no_variants():
rules = { 'analyzer': 'generic' }
- config = module.configure(rules, DEFAULT_NORMALIZATION)
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']
@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):