safety-screen/Nominatim
1
0
Fork 0
forked from hans/Nominatim
Code Pull Requests Activity

enable flake for Python tests

Browse Source
This commit is contained in:
Sarah Hoffmann
2025-03-09 15:33:24 +01:00
parent 5a245e33e0
commit 4cc788f69e
93 changed files with 949 additions and 1191 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
test/python/tokenizer/token_analysis/test_analysis_postcodes.py
View File

@@ -2,7 +2,7 @@
#
# This file is part of Nominatim. (https://nominatim.org)
#
# Copyright (C) 2024 by the Nominatim developer community.
# Copyright (C) 2025 by the Nominatim developer community.
# For a full list of authors see the git log.
"""
Tests for special postcode analysis and variant generation.
@@ -13,7 +13,6 @@ from icu import Transliterator
import nominatim_db.tokenizer.token_analysis.postcodes as module
from nominatim_db.data.place_name import PlaceName
from nominatim_db.errors import UsageError
DEFAULT_NORMALIZATION = """ :: NFD ();
'🜳' > ' ';
@@ -27,9 +26,10 @@ DEFAULT_TRANSLITERATION = """ :: Latin ();
'🜵' > ' ';
"""
@pytest.fixture
def analyser():
rules = { 'analyzer': 'postcodes'}
rules = {'analyzer': 'postcodes'}
config = module.configure(rules, DEFAULT_NORMALIZATION)
trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)

98
test/python/tokenizer/token_analysis/test_generic.py
View File

@@ -2,7 +2,7 @@
#
# This file is part of Nominatim. (https://nominatim.org)
#
# Copyright (C) 2024 by the Nominatim developer community.
# Copyright (C) 2025 by the Nominatim developer community.
# For a full list of authors see the git log.
"""
Tests for import name normalisation and variant generation.
@@ -26,8 +26,9 @@ DEFAULT_TRANSLITERATION = """ :: Latin ();
'🜵' > ' ';
"""
def make_analyser(*variants, variant_only=False):
rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]}
rules = {'analyzer': 'generic', 'variants': [{'words': variants}]}
if variant_only:
rules['mode'] = 'variant-only'
trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)
@@ -43,7 +44,7 @@ def get_normalized_variants(proc, name):
def test_no_variants():
rules = { 'analyzer': 'generic' }
rules = {'analyzer': 'generic'}
trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)
norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
config = module.configure(rules, norm, trans)
@@ -62,35 +63,36 @@ def test_variants_empty():
VARIANT_TESTS = [
(('~strasse,~straße -> str', '~weg => weg'), "hallo", {'hallo'}),
(('weg => wg',), "holzweg", {'holzweg'}),
(('weg -> wg',), "holzweg", {'holzweg'}),
(('~weg => weg',), "holzweg", {'holz weg', 'holzweg'}),
(('~weg -> weg',), "holzweg", {'holz weg', 'holzweg'}),
(('~weg => w',), "holzweg", {'holz w', 'holzw'}),
(('~weg -> w',), "holzweg", {'holz weg', 'holzweg', 'holz w', 'holzw'}),
(('~weg => weg',), "Meier Weg", {'meier weg', 'meierweg'}),
(('~weg -> weg',), "Meier Weg", {'meier weg', 'meierweg'}),
(('~weg => w',), "Meier Weg", {'meier w', 'meierw'}),
(('~weg -> w',), "Meier Weg", {'meier weg', 'meierweg', 'meier w', 'meierw'}),
(('weg => wg',), "Meier Weg", {'meier wg'}),
(('weg -> wg',), "Meier Weg", {'meier weg', 'meier wg'}),
(('~strasse,~straße -> str', '~weg => weg'), "Bauwegstraße",
(('~strasse,~straße -> str', '~weg => weg'), "hallo", {'hallo'}),
(('weg => wg',), "holzweg", {'holzweg'}),
(('weg -> wg',), "holzweg", {'holzweg'}),
(('~weg => weg',), "holzweg", {'holz weg', 'holzweg'}),
(('~weg -> weg',), "holzweg", {'holz weg', 'holzweg'}),
(('~weg => w',), "holzweg", {'holz w', 'holzw'}),
(('~weg -> w',), "holzweg", {'holz weg', 'holzweg', 'holz w', 'holzw'}),
(('~weg => weg',), "Meier Weg", {'meier weg', 'meierweg'}),
(('~weg -> weg',), "Meier Weg", {'meier weg', 'meierweg'}),
(('~weg => w',), "Meier Weg", {'meier w', 'meierw'}),
(('~weg -> w',), "Meier Weg", {'meier weg', 'meierweg', 'meier w', 'meierw'}),
(('weg => wg',), "Meier Weg", {'meier wg'}),
(('weg -> wg',), "Meier Weg", {'meier weg', 'meier wg'}),
(('~strasse,~straße -> str', '~weg => weg'), "Bauwegstraße",
{'bauweg straße', 'bauweg str', 'bauwegstraße', 'bauwegstr'}),
(('am => a', 'bach => b'), "am bach", {'a b'}),
(('am => a', '~bach => b'), "am bach", {'a b'}),
(('am -> a', '~bach -> b'), "am bach", {'am bach', 'a bach', 'am b', 'a b'}),
(('am -> a', '~bach -> b'), "ambach", {'ambach', 'am bach', 'amb', 'am b'}),
(('saint -> s,st', 'street -> st'), "Saint Johns Street",
(('am => a', 'bach => b'), "am bach", {'a b'}),
(('am => a', '~bach => b'), "am bach", {'a b'}),
(('am -> a', '~bach -> b'), "am bach", {'am bach', 'a bach', 'am b', 'a b'}),
(('am -> a', '~bach -> b'), "ambach", {'ambach', 'am bach', 'amb', 'am b'}),
(('saint -> s,st', 'street -> st'), "Saint Johns Street",
{'saint johns street', 's johns street', 'st johns street',
'saint johns st', 's johns st', 'st johns st'}),
(('river$ -> r',), "River Bend Road", {'river bend road'}),
(('river$ -> r',), "Bent River", {'bent river', 'bent r'}),
(('^north => n',), "North 2nd Street", {'n 2nd street'}),
(('^north => n',), "Airport North", {'airport north'}),
(('am -> a',), "am am am am am am am am", {'am am am am am am am am'}),
(('am => a',), "am am am am am am am am", {'a a a a a a a a'})
]
(('river$ -> r',), "River Bend Road", {'river bend road'}),
(('river$ -> r',), "Bent River", {'bent river', 'bent r'}),
(('^north => n',), "North 2nd Street", {'n 2nd street'}),
(('^north => n',), "Airport North", {'airport north'}),
(('am -> a',), "am am am am am am am am", {'am am am am am am am am'}),
(('am => a',), "am am am am am am am am", {'a a a a a a a a'})
]
@pytest.mark.parametrize("rules,name,variants", VARIANT_TESTS)
def test_variants(rules, name, variants):
@@ -103,10 +105,11 @@ def test_variants(rules, name, variants):
VARIANT_ONLY_TESTS = [
(('weg => wg',), "hallo", set()),
(('weg => wg',), "Meier Weg", {'meier wg'}),
(('weg -> wg',), "Meier Weg", {'meier wg'}),
]
(('weg => wg',), "hallo", set()),
(('weg => wg',), "Meier Weg", {'meier wg'}),
(('weg -> wg',), "Meier Weg", {'meier wg'}),
]
@pytest.mark.parametrize("rules,name,variants", VARIANT_ONLY_TESTS)
def test_variants_only(rules, name, variants):
@@ -122,17 +125,15 @@ class TestGetReplacements:
@staticmethod
def configure_rules(*variants):
rules = { 'analyzer': 'generic', 'variants': [{'words': variants}]}
rules = {'analyzer': 'generic', 'variants': [{'words': variants}]}
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):
config = self.configure_rules(*variants)
return sorted((k, sorted(v)) for k,v in config['replacements'])
return sorted((k, sorted(v)) for k, v in config['replacements'])
@pytest.mark.parametrize("variant", ['foo > bar', 'foo -> bar -> bar',
'~foo~ -> bar', 'fo~ o -> bar'])
@@ -140,38 +141,32 @@ class TestGetReplacements:
with pytest.raises(UsageError):
self.configure_rules(variant)
@pytest.mark.parametrize("rule", ["!!! -> bar", "bar => !!!"])
def test_ignore_unnormalizable_terms(self, rule):
repl = self.get_replacements(rule)
assert repl == []
def test_add_full(self):
repl = self.get_replacements("foo -> bar")
assert repl == [(' foo ', [' bar', ' 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', ' bg']),
('berg ', ['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")
@@ -179,26 +174,22 @@ class TestGetReplacements:
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'])]
assert repl == [(' hinter', [' hnt']), (' hinter ', [' hnt'])]
def test_add_prefix_compose(self):
repl = self.get_replacements("hinter~-> h")
@@ -206,45 +197,38 @@ class TestGetReplacements:
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")
@@ -253,7 +237,6 @@ class TestGetReplacements:
('berg ', ['berg', 'bg']),
('berg ^', [' berg ^', ' bg ^', 'berg ^', 'bg ^'])]
def test_replace_suffix_decompose_end_only(self):
repl = self.get_replacements("~berg |=> bg", "~berg$ => bg")
@@ -262,7 +245,6 @@ class TestGetReplacements:
('berg ', ['bg']),
('berg ^', [' bg ^', 'bg ^'])]
@pytest.mark.parametrize('rule', ["~berg,~burg -> bg",
"~berg, ~burg -> bg",
"~berg,,~burg -> bg"])

19
test/python/tokenizer/token_analysis/test_generic_mutation.py
View File

@@ -2,7 +2,7 @@
#
# This file is part of Nominatim. (https://nominatim.org)
#
# Copyright (C) 2024 by the Nominatim developer community.
# Copyright (C) 2025 by the Nominatim developer community.
# For a full list of authors see the git log.
"""
Tests for generic token analysis, mutation part.
@@ -24,37 +24,34 @@ DEFAULT_TRANSLITERATION = """ :: Latin ();
'🜵' > ' ';
"""
class TestMutationNoVariants:
def make_analyser(self, *mutations):
rules = { 'analyzer': 'generic',
'mutations': [ {'pattern': m[0], 'replacements': m[1]}
for m in mutations]
}
rules = {'analyzer': 'generic',
'mutations': [{'pattern': m[0], 'replacements': m[1]}
for m in mutations]
}
trans = Transliterator.createFromRules("test_trans", DEFAULT_TRANSLITERATION)
norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
config = module.configure(rules, norm, trans)
self.analysis = module.create(norm, trans, config)
def variants(self, name):
norm = Transliterator.createFromRules("test_norm", DEFAULT_NORMALIZATION)
return set(self.analysis.compute_variants(norm.transliterate(name).strip()))
@pytest.mark.parametrize('pattern', ('(capture)', ['a list']))
def test_bad_pattern(self, pattern):
with pytest.raises(UsageError):
self.make_analyser((pattern, ['b']))
@pytest.mark.parametrize('replacements', (None, 'a string'))
def test_bad_replacement(self, replacements):
with pytest.raises(UsageError):
self.make_analyser(('a', replacements))
def test_simple_replacement(self):
self.make_analyser(('a', ['b']))
@@ -62,27 +59,23 @@ class TestMutationNoVariants:
assert self.variants('abba') == {'bbbb'}
assert self.variants('2 aar') == {'2 bbr'}
def test_multichar_replacement(self):
self.make_analyser(('1 1', ['1 1 1']))
assert self.variants('1 1456') == {'1 1 1456'}
assert self.variants('1 1 1') == {'1 1 1 1'}
def test_removement_replacement(self):
self.make_analyser((' ', [' ', '']))
assert self.variants('A 345') == {'a 345', 'a345'}
assert self.variants('a g b') == {'a g b', 'ag b', 'a gb', 'agb'}
def test_regex_pattern(self):
self.make_analyser(('[^a-z]+', ['XXX', ' ']))
assert self.variants('a-34n12') == {'aXXXnXXX', 'aXXXn', 'a nXXX', 'a n'}
def test_multiple_mutations(self):
self.make_analyser(('ä', ['ä', 'ae']), ('ö', ['ö', 'oe']))

2
test/python/tokenizer/token_analysis/test_simple_trie.py
View File

@@ -10,6 +10,7 @@ Tests for simplified trie structure.
from nominatim_db.tokenizer.token_analysis.simple_trie import SimpleTrie
def test_single_item_trie():
t = SimpleTrie([('foob', 42)])
@@ -18,6 +19,7 @@ def test_single_item_trie():
assert t.longest_prefix('foob') == (42, 4)
assert t.longest_prefix('123foofoo', 3) == (None, 3)
def test_complex_item_tree():
t = SimpleTrie([('a', 1),
('b', 2),