1
0
mirror of https://github.com/arsenetar/dupeguru.git synced 2026-01-22 14:41:39 +00:00

Format files with black

- Format all files with black
- Update tox.ini flake8 arguments to be compatible
- Add black to requirements-extra.txt
- Reduce ignored flake8 rules and fix a few violations
This commit is contained in:
2019-12-31 20:16:27 -06:00
parent 359d6498f7
commit 7ba8aa3514
141 changed files with 5241 additions and 3648 deletions

View File

@@ -13,13 +13,28 @@ from hscommon.testutil import eq_, log_calls
from .base import NamedObject
from .. import engine
from ..engine import (
get_match, getwords, Group, getfields, unpack_fields, compare_fields, compare, WEIGHT_WORDS,
MATCH_SIMILAR_WORDS, NO_FIELD_ORDER, build_word_dict, get_groups, getmatches, Match,
getmatches_by_contents, merge_similar_words, reduce_common_words
get_match,
getwords,
Group,
getfields,
unpack_fields,
compare_fields,
compare,
WEIGHT_WORDS,
MATCH_SIMILAR_WORDS,
NO_FIELD_ORDER,
build_word_dict,
get_groups,
getmatches,
Match,
getmatches_by_contents,
merge_similar_words,
reduce_common_words,
)
no = NamedObject
def get_match_triangle():
o1 = NamedObject(with_words=True)
o2 = NamedObject(with_words=True)
@@ -29,6 +44,7 @@ def get_match_triangle():
m3 = get_match(o2, o3)
return [m1, m2, m3]
def get_test_group():
m1, m2, m3 = get_match_triangle()
result = Group()
@@ -37,6 +53,7 @@ def get_test_group():
result.add_match(m3)
return result
def assert_match(m, name1, name2):
# When testing matches, whether objects are in first or second position very often doesn't
# matter. This function makes this test more convenient.
@@ -46,53 +63,54 @@ def assert_match(m, name1, name2):
eq_(m.first.name, name2)
eq_(m.second.name, name1)
class TestCasegetwords:
def test_spaces(self):
eq_(['a', 'b', 'c', 'd'], getwords("a b c d"))
eq_(['a', 'b', 'c', 'd'], getwords(" a b c d "))
eq_(["a", "b", "c", "d"], getwords("a b c d"))
eq_(["a", "b", "c", "d"], getwords(" a b c d "))
def test_splitter_chars(self):
eq_(
[chr(i) for i in range(ord('a'), ord('z')+1)],
getwords("a-b_c&d+e(f)g;h\\i[j]k{l}m:n.o,p<q>r/s?t~u!v@w#x$y*z")
[chr(i) for i in range(ord("a"), ord("z") + 1)],
getwords("a-b_c&d+e(f)g;h\\i[j]k{l}m:n.o,p<q>r/s?t~u!v@w#x$y*z"),
)
def test_joiner_chars(self):
eq_(["aec"], getwords("a'e\u0301c"))
def test_empty(self):
eq_([], getwords(''))
eq_([], getwords(""))
def test_returns_lowercase(self):
eq_(['foo', 'bar'], getwords('FOO BAR'))
eq_(["foo", "bar"], getwords("FOO BAR"))
def test_decompose_unicode(self):
eq_(getwords('foo\xe9bar'), ['fooebar'])
eq_(getwords("foo\xe9bar"), ["fooebar"])
class TestCasegetfields:
def test_simple(self):
eq_([['a', 'b'], ['c', 'd', 'e']], getfields('a b - c d e'))
eq_([["a", "b"], ["c", "d", "e"]], getfields("a b - c d e"))
def test_empty(self):
eq_([], getfields(''))
eq_([], getfields(""))
def test_cleans_empty_fields(self):
expected = [['a', 'bc', 'def']]
actual = getfields(' - a bc def')
expected = [["a", "bc", "def"]]
actual = getfields(" - a bc def")
eq_(expected, actual)
expected = [['bc', 'def']]
expected = [["bc", "def"]]
class TestCaseunpack_fields:
def test_with_fields(self):
expected = ['a', 'b', 'c', 'd', 'e', 'f']
actual = unpack_fields([['a'], ['b', 'c'], ['d', 'e', 'f']])
expected = ["a", "b", "c", "d", "e", "f"]
actual = unpack_fields([["a"], ["b", "c"], ["d", "e", "f"]])
eq_(expected, actual)
def test_without_fields(self):
expected = ['a', 'b', 'c', 'd', 'e', 'f']
actual = unpack_fields(['a', 'b', 'c', 'd', 'e', 'f'])
expected = ["a", "b", "c", "d", "e", "f"]
actual = unpack_fields(["a", "b", "c", "d", "e", "f"])
eq_(expected, actual)
def test_empty(self):
@@ -101,134 +119,151 @@ class TestCaseunpack_fields:
class TestCaseWordCompare:
def test_list(self):
eq_(100, compare(['a', 'b', 'c', 'd'], ['a', 'b', 'c', 'd']))
eq_(86, compare(['a', 'b', 'c', 'd'], ['a', 'b', 'c']))
eq_(100, compare(["a", "b", "c", "d"], ["a", "b", "c", "d"]))
eq_(86, compare(["a", "b", "c", "d"], ["a", "b", "c"]))
def test_unordered(self):
#Sometimes, users don't want fuzzy matching too much When they set the slider
#to 100, they don't expect a filename with the same words, but not the same order, to match.
#Thus, we want to return 99 in that case.
eq_(99, compare(['a', 'b', 'c', 'd'], ['d', 'b', 'c', 'a']))
# Sometimes, users don't want fuzzy matching too much When they set the slider
# to 100, they don't expect a filename with the same words, but not the same order, to match.
# Thus, we want to return 99 in that case.
eq_(99, compare(["a", "b", "c", "d"], ["d", "b", "c", "a"]))
def test_word_occurs_twice(self):
#if a word occurs twice in first, but once in second, we want the word to be only counted once
eq_(89, compare(['a', 'b', 'c', 'd', 'a'], ['d', 'b', 'c', 'a']))
# if a word occurs twice in first, but once in second, we want the word to be only counted once
eq_(89, compare(["a", "b", "c", "d", "a"], ["d", "b", "c", "a"]))
def test_uses_copy_of_lists(self):
first = ['foo', 'bar']
second = ['bar', 'bleh']
first = ["foo", "bar"]
second = ["bar", "bleh"]
compare(first, second)
eq_(['foo', 'bar'], first)
eq_(['bar', 'bleh'], second)
eq_(["foo", "bar"], first)
eq_(["bar", "bleh"], second)
def test_word_weight(self):
eq_(int((6.0 / 13.0) * 100), compare(['foo', 'bar'], ['bar', 'bleh'], (WEIGHT_WORDS, )))
eq_(
int((6.0 / 13.0) * 100),
compare(["foo", "bar"], ["bar", "bleh"], (WEIGHT_WORDS,)),
)
def test_similar_words(self):
eq_(100, compare(['the', 'white', 'stripes'], ['the', 'whites', 'stripe'], (MATCH_SIMILAR_WORDS, )))
eq_(
100,
compare(
["the", "white", "stripes"],
["the", "whites", "stripe"],
(MATCH_SIMILAR_WORDS,),
),
)
def test_empty(self):
eq_(0, compare([], []))
def test_with_fields(self):
eq_(67, compare([['a', 'b'], ['c', 'd', 'e']], [['a', 'b'], ['c', 'd', 'f']]))
eq_(67, compare([["a", "b"], ["c", "d", "e"]], [["a", "b"], ["c", "d", "f"]]))
def test_propagate_flags_with_fields(self, monkeypatch):
def mock_compare(first, second, flags):
eq_((0, 1, 2, 3, 5), flags)
monkeypatch.setattr(engine, 'compare_fields', mock_compare)
compare([['a']], [['a']], (0, 1, 2, 3, 5))
monkeypatch.setattr(engine, "compare_fields", mock_compare)
compare([["a"]], [["a"]], (0, 1, 2, 3, 5))
class TestCaseWordCompareWithFields:
def test_simple(self):
eq_(67, compare_fields([['a', 'b'], ['c', 'd', 'e']], [['a', 'b'], ['c', 'd', 'f']]))
eq_(
67,
compare_fields(
[["a", "b"], ["c", "d", "e"]], [["a", "b"], ["c", "d", "f"]]
),
)
def test_empty(self):
eq_(0, compare_fields([], []))
def test_different_length(self):
eq_(0, compare_fields([['a'], ['b']], [['a'], ['b'], ['c']]))
eq_(0, compare_fields([["a"], ["b"]], [["a"], ["b"], ["c"]]))
def test_propagates_flags(self, monkeypatch):
def mock_compare(first, second, flags):
eq_((0, 1, 2, 3, 5), flags)
monkeypatch.setattr(engine, 'compare_fields', mock_compare)
compare_fields([['a']], [['a']], (0, 1, 2, 3, 5))
monkeypatch.setattr(engine, "compare_fields", mock_compare)
compare_fields([["a"]], [["a"]], (0, 1, 2, 3, 5))
def test_order(self):
first = [['a', 'b'], ['c', 'd', 'e']]
second = [['c', 'd', 'f'], ['a', 'b']]
first = [["a", "b"], ["c", "d", "e"]]
second = [["c", "d", "f"], ["a", "b"]]
eq_(0, compare_fields(first, second))
def test_no_order(self):
first = [['a', 'b'], ['c', 'd', 'e']]
second = [['c', 'd', 'f'], ['a', 'b']]
eq_(67, compare_fields(first, second, (NO_FIELD_ORDER, )))
first = [['a', 'b'], ['a', 'b']] #a field can only be matched once.
second = [['c', 'd', 'f'], ['a', 'b']]
eq_(0, compare_fields(first, second, (NO_FIELD_ORDER, )))
first = [['a', 'b'], ['a', 'b', 'c']]
second = [['c', 'd', 'f'], ['a', 'b']]
eq_(33, compare_fields(first, second, (NO_FIELD_ORDER, )))
first = [["a", "b"], ["c", "d", "e"]]
second = [["c", "d", "f"], ["a", "b"]]
eq_(67, compare_fields(first, second, (NO_FIELD_ORDER,)))
first = [["a", "b"], ["a", "b"]] # a field can only be matched once.
second = [["c", "d", "f"], ["a", "b"]]
eq_(0, compare_fields(first, second, (NO_FIELD_ORDER,)))
first = [["a", "b"], ["a", "b", "c"]]
second = [["c", "d", "f"], ["a", "b"]]
eq_(33, compare_fields(first, second, (NO_FIELD_ORDER,)))
def test_compare_fields_without_order_doesnt_alter_fields(self):
#The NO_ORDER comp type altered the fields!
first = [['a', 'b'], ['c', 'd', 'e']]
second = [['c', 'd', 'f'], ['a', 'b']]
eq_(67, compare_fields(first, second, (NO_FIELD_ORDER, )))
eq_([['a', 'b'], ['c', 'd', 'e']], first)
eq_([['c', 'd', 'f'], ['a', 'b']], second)
# The NO_ORDER comp type altered the fields!
first = [["a", "b"], ["c", "d", "e"]]
second = [["c", "d", "f"], ["a", "b"]]
eq_(67, compare_fields(first, second, (NO_FIELD_ORDER,)))
eq_([["a", "b"], ["c", "d", "e"]], first)
eq_([["c", "d", "f"], ["a", "b"]], second)
class TestCasebuild_word_dict:
def test_with_standard_words(self):
l = [NamedObject('foo bar', True)]
l.append(NamedObject('bar baz', True))
l.append(NamedObject('baz bleh foo', True))
d = build_word_dict(l)
itemList = [NamedObject("foo bar", True)]
itemList.append(NamedObject("bar baz", True))
itemList.append(NamedObject("baz bleh foo", True))
d = build_word_dict(itemList)
eq_(4, len(d))
eq_(2, len(d['foo']))
assert l[0] in d['foo']
assert l[2] in d['foo']
eq_(2, len(d['bar']))
assert l[0] in d['bar']
assert l[1] in d['bar']
eq_(2, len(d['baz']))
assert l[1] in d['baz']
assert l[2] in d['baz']
eq_(1, len(d['bleh']))
assert l[2] in d['bleh']
eq_(2, len(d["foo"]))
assert itemList[0] in d["foo"]
assert itemList[2] in d["foo"]
eq_(2, len(d["bar"]))
assert itemList[0] in d["bar"]
assert itemList[1] in d["bar"]
eq_(2, len(d["baz"]))
assert itemList[1] in d["baz"]
assert itemList[2] in d["baz"]
eq_(1, len(d["bleh"]))
assert itemList[2] in d["bleh"]
def test_unpack_fields(self):
o = NamedObject('')
o.words = [['foo', 'bar'], ['baz']]
o = NamedObject("")
o.words = [["foo", "bar"], ["baz"]]
d = build_word_dict([o])
eq_(3, len(d))
eq_(1, len(d['foo']))
eq_(1, len(d["foo"]))
def test_words_are_unaltered(self):
o = NamedObject('')
o.words = [['foo', 'bar'], ['baz']]
o = NamedObject("")
o.words = [["foo", "bar"], ["baz"]]
build_word_dict([o])
eq_([['foo', 'bar'], ['baz']], o.words)
eq_([["foo", "bar"], ["baz"]], o.words)
def test_object_instances_can_only_be_once_in_words_object_list(self):
o = NamedObject('foo foo', True)
o = NamedObject("foo foo", True)
d = build_word_dict([o])
eq_(1, len(d['foo']))
eq_(1, len(d["foo"]))
def test_job(self):
def do_progress(p, d=''):
def do_progress(p, d=""):
self.log.append(p)
return True
j = job.Job(1, do_progress)
self.log = []
s = "foo bar"
build_word_dict([NamedObject(s, True), NamedObject(s, True), NamedObject(s, True)], j)
build_word_dict(
[NamedObject(s, True), NamedObject(s, True), NamedObject(s, True)], j
)
# We don't have intermediate log because iter_with_progress is called with every > 1
eq_(0, self.log[0])
eq_(100, self.log[1])
@@ -237,51 +272,56 @@ class TestCasebuild_word_dict:
class TestCasemerge_similar_words:
def test_some_similar_words(self):
d = {
'foobar': set([1]),
'foobar1': set([2]),
'foobar2': set([3]),
"foobar": set([1]),
"foobar1": set([2]),
"foobar2": set([3]),
}
merge_similar_words(d)
eq_(1, len(d))
eq_(3, len(d['foobar']))
eq_(3, len(d["foobar"]))
class TestCasereduce_common_words:
def test_typical(self):
d = {
'foo': set([NamedObject('foo bar', True) for i in range(50)]),
'bar': set([NamedObject('foo bar', True) for i in range(49)])
"foo": set([NamedObject("foo bar", True) for i in range(50)]),
"bar": set([NamedObject("foo bar", True) for i in range(49)]),
}
reduce_common_words(d, 50)
assert 'foo' not in d
eq_(49, len(d['bar']))
assert "foo" not in d
eq_(49, len(d["bar"]))
def test_dont_remove_objects_with_only_common_words(self):
d = {
'common': set([NamedObject("common uncommon", True) for i in range(50)] + [NamedObject("common", True)]),
'uncommon': set([NamedObject("common uncommon", True)])
"common": set(
[NamedObject("common uncommon", True) for i in range(50)]
+ [NamedObject("common", True)]
),
"uncommon": set([NamedObject("common uncommon", True)]),
}
reduce_common_words(d, 50)
eq_(1, len(d['common']))
eq_(1, len(d['uncommon']))
eq_(1, len(d["common"]))
eq_(1, len(d["uncommon"]))
def test_values_still_are_set_instances(self):
d = {
'common': set([NamedObject("common uncommon", True) for i in range(50)] + [NamedObject("common", True)]),
'uncommon': set([NamedObject("common uncommon", True)])
"common": set(
[NamedObject("common uncommon", True) for i in range(50)]
+ [NamedObject("common", True)]
),
"uncommon": set([NamedObject("common uncommon", True)]),
}
reduce_common_words(d, 50)
assert isinstance(d['common'], set)
assert isinstance(d['uncommon'], set)
assert isinstance(d["common"], set)
assert isinstance(d["uncommon"], set)
def test_dont_raise_KeyError_when_a_word_has_been_removed(self):
#If a word has been removed by the reduce, an object in a subsequent common word that
#contains the word that has been removed would cause a KeyError.
# If a word has been removed by the reduce, an object in a subsequent common word that
# contains the word that has been removed would cause a KeyError.
d = {
'foo': set([NamedObject('foo bar baz', True) for i in range(50)]),
'bar': set([NamedObject('foo bar baz', True) for i in range(50)]),
'baz': set([NamedObject('foo bar baz', True) for i in range(49)])
"foo": set([NamedObject("foo bar baz", True) for i in range(50)]),
"bar": set([NamedObject("foo bar baz", True) for i in range(50)]),
"baz": set([NamedObject("foo bar baz", True) for i in range(49)]),
}
try:
reduce_common_words(d, 50)
@@ -289,35 +329,37 @@ class TestCasereduce_common_words:
self.fail()
def test_unpack_fields(self):
#object.words may be fields.
# object.words may be fields.
def create_it():
o = NamedObject('')
o.words = [['foo', 'bar'], ['baz']]
o = NamedObject("")
o.words = [["foo", "bar"], ["baz"]]
return o
d = {
'foo': set([create_it() for i in range(50)])
}
d = {"foo": set([create_it() for i in range(50)])}
try:
reduce_common_words(d, 50)
except TypeError:
self.fail("must support fields.")
def test_consider_a_reduced_common_word_common_even_after_reduction(self):
#There was a bug in the code that causeda word that has already been reduced not to
#be counted as a common word for subsequent words. For example, if 'foo' is processed
#as a common word, keeping a "foo bar" file in it, and the 'bar' is processed, "foo bar"
#would not stay in 'bar' because 'foo' is not a common word anymore.
only_common = NamedObject('foo bar', True)
# There was a bug in the code that causeda word that has already been reduced not to
# be counted as a common word for subsequent words. For example, if 'foo' is processed
# as a common word, keeping a "foo bar" file in it, and the 'bar' is processed, "foo bar"
# would not stay in 'bar' because 'foo' is not a common word anymore.
only_common = NamedObject("foo bar", True)
d = {
'foo': set([NamedObject('foo bar baz', True) for i in range(49)] + [only_common]),
'bar': set([NamedObject('foo bar baz', True) for i in range(49)] + [only_common]),
'baz': set([NamedObject('foo bar baz', True) for i in range(49)])
"foo": set(
[NamedObject("foo bar baz", True) for i in range(49)] + [only_common]
),
"bar": set(
[NamedObject("foo bar baz", True) for i in range(49)] + [only_common]
),
"baz": set([NamedObject("foo bar baz", True) for i in range(49)]),
}
reduce_common_words(d, 50)
eq_(1, len(d['foo']))
eq_(1, len(d['bar']))
eq_(49, len(d['baz']))
eq_(1, len(d["foo"]))
eq_(1, len(d["bar"]))
eq_(49, len(d["baz"]))
class TestCaseget_match:
@@ -326,8 +368,8 @@ class TestCaseget_match:
o2 = NamedObject("bar bleh", True)
m = get_match(o1, o2)
eq_(50, m.percentage)
eq_(['foo', 'bar'], m.first.words)
eq_(['bar', 'bleh'], m.second.words)
eq_(["foo", "bar"], m.first.words)
eq_(["bar", "bleh"], m.second.words)
assert m.first is o1
assert m.second is o2
@@ -340,7 +382,9 @@ class TestCaseget_match:
assert object() not in m
def test_word_weight(self):
m = get_match(NamedObject("foo bar", True), NamedObject("bar bleh", True), (WEIGHT_WORDS, ))
m = get_match(
NamedObject("foo bar", True), NamedObject("bar bleh", True), (WEIGHT_WORDS,)
)
eq_(m.percentage, int((6.0 / 13.0) * 100))
@@ -349,54 +393,59 @@ class TestCaseGetMatches:
eq_(getmatches([]), [])
def test_simple(self):
l = [NamedObject("foo bar"), NamedObject("bar bleh"), NamedObject("a b c foo")]
r = getmatches(l)
itemList = [NamedObject("foo bar"), NamedObject("bar bleh"), NamedObject("a b c foo")]
r = getmatches(itemList)
eq_(2, len(r))
m = first(m for m in r if m.percentage == 50) #"foo bar" and "bar bleh"
assert_match(m, 'foo bar', 'bar bleh')
m = first(m for m in r if m.percentage == 33) #"foo bar" and "a b c foo"
assert_match(m, 'foo bar', 'a b c foo')
m = first(m for m in r if m.percentage == 50) # "foo bar" and "bar bleh"
assert_match(m, "foo bar", "bar bleh")
m = first(m for m in r if m.percentage == 33) # "foo bar" and "a b c foo"
assert_match(m, "foo bar", "a b c foo")
def test_null_and_unrelated_objects(self):
l = [NamedObject("foo bar"), NamedObject("bar bleh"), NamedObject(""), NamedObject("unrelated object")]
r = getmatches(l)
itemList = [
NamedObject("foo bar"),
NamedObject("bar bleh"),
NamedObject(""),
NamedObject("unrelated object"),
]
r = getmatches(itemList)
eq_(len(r), 1)
m = r[0]
eq_(m.percentage, 50)
assert_match(m, 'foo bar', 'bar bleh')
assert_match(m, "foo bar", "bar bleh")
def test_twice_the_same_word(self):
l = [NamedObject("foo foo bar"), NamedObject("bar bleh")]
r = getmatches(l)
itemList = [NamedObject("foo foo bar"), NamedObject("bar bleh")]
r = getmatches(itemList)
eq_(1, len(r))
def test_twice_the_same_word_when_preworded(self):
l = [NamedObject("foo foo bar", True), NamedObject("bar bleh", True)]
r = getmatches(l)
itemList = [NamedObject("foo foo bar", True), NamedObject("bar bleh", True)]
r = getmatches(itemList)
eq_(1, len(r))
def test_two_words_match(self):
l = [NamedObject("foo bar"), NamedObject("foo bar bleh")]
r = getmatches(l)
itemList = [NamedObject("foo bar"), NamedObject("foo bar bleh")]
r = getmatches(itemList)
eq_(1, len(r))
def test_match_files_with_only_common_words(self):
#If a word occurs more than 50 times, it is excluded from the matching process
#The problem with the common_word_threshold is that the files containing only common
#words will never be matched together. We *should* match them.
# If a word occurs more than 50 times, it is excluded from the matching process
# The problem with the common_word_threshold is that the files containing only common
# words will never be matched together. We *should* match them.
# This test assumes that the common word threashold const is 50
l = [NamedObject("foo") for i in range(50)]
r = getmatches(l)
itemList = [NamedObject("foo") for i in range(50)]
r = getmatches(itemList)
eq_(1225, len(r))
def test_use_words_already_there_if_there(self):
o1 = NamedObject('foo')
o2 = NamedObject('bar')
o2.words = ['foo']
o1 = NamedObject("foo")
o2 = NamedObject("bar")
o2.words = ["foo"]
eq_(1, len(getmatches([o1, o2])))
def test_job(self):
def do_progress(p, d=''):
def do_progress(p, d=""):
self.log.append(p)
return True
@@ -409,28 +458,28 @@ class TestCaseGetMatches:
eq_(100, self.log[-1])
def test_weight_words(self):
l = [NamedObject("foo bar"), NamedObject("bar bleh")]
m = getmatches(l, weight_words=True)[0]
itemList = [NamedObject("foo bar"), NamedObject("bar bleh")]
m = getmatches(itemList, weight_words=True)[0]
eq_(int((6.0 / 13.0) * 100), m.percentage)
def test_similar_word(self):
l = [NamedObject("foobar"), NamedObject("foobars")]
eq_(len(getmatches(l, match_similar_words=True)), 1)
eq_(getmatches(l, match_similar_words=True)[0].percentage, 100)
l = [NamedObject("foobar"), NamedObject("foo")]
eq_(len(getmatches(l, match_similar_words=True)), 0) #too far
l = [NamedObject("bizkit"), NamedObject("bizket")]
eq_(len(getmatches(l, match_similar_words=True)), 1)
l = [NamedObject("foobar"), NamedObject("foosbar")]
eq_(len(getmatches(l, match_similar_words=True)), 1)
itemList = [NamedObject("foobar"), NamedObject("foobars")]
eq_(len(getmatches(itemList, match_similar_words=True)), 1)
eq_(getmatches(itemList, match_similar_words=True)[0].percentage, 100)
itemList = [NamedObject("foobar"), NamedObject("foo")]
eq_(len(getmatches(itemList, match_similar_words=True)), 0) # too far
itemList = [NamedObject("bizkit"), NamedObject("bizket")]
eq_(len(getmatches(itemList, match_similar_words=True)), 1)
itemList = [NamedObject("foobar"), NamedObject("foosbar")]
eq_(len(getmatches(itemList, match_similar_words=True)), 1)
def test_single_object_with_similar_words(self):
l = [NamedObject("foo foos")]
eq_(len(getmatches(l, match_similar_words=True)), 0)
itemList = [NamedObject("foo foos")]
eq_(len(getmatches(itemList, match_similar_words=True)), 0)
def test_double_words_get_counted_only_once(self):
l = [NamedObject("foo bar foo bleh"), NamedObject("foo bar bleh bar")]
m = getmatches(l)[0]
itemList = [NamedObject("foo bar foo bleh"), NamedObject("foo bar bleh bar")]
m = getmatches(itemList)[0]
eq_(75, m.percentage)
def test_with_fields(self):
@@ -450,13 +499,13 @@ class TestCaseGetMatches:
eq_(m.percentage, 50)
def test_only_match_similar_when_the_option_is_set(self):
l = [NamedObject("foobar"), NamedObject("foobars")]
eq_(len(getmatches(l, match_similar_words=False)), 0)
itemList = [NamedObject("foobar"), NamedObject("foobars")]
eq_(len(getmatches(itemList, match_similar_words=False)), 0)
def test_dont_recurse_do_match(self):
# with nosetests, the stack is increased. The number has to be high enough not to be failing falsely
sys.setrecursionlimit(200)
files = [NamedObject('foo bar') for i in range(201)]
files = [NamedObject("foo bar") for i in range(201)]
try:
getmatches(files)
except RuntimeError:
@@ -465,9 +514,9 @@ class TestCaseGetMatches:
sys.setrecursionlimit(1000)
def test_min_match_percentage(self):
l = [NamedObject("foo bar"), NamedObject("bar bleh"), NamedObject("a b c foo")]
r = getmatches(l, min_match_percentage=50)
eq_(1, len(r)) #Only "foo bar" / "bar bleh" should match
itemList = [NamedObject("foo bar"), NamedObject("bar bleh"), NamedObject("a b c foo")]
r = getmatches(itemList, min_match_percentage=50)
eq_(1, len(r)) # Only "foo bar" / "bar bleh" should match
def test_MemoryError(self, monkeypatch):
@log_calls
@@ -476,12 +525,12 @@ class TestCaseGetMatches:
raise MemoryError()
return Match(first, second, 0)
objects = [NamedObject() for i in range(10)] # results in 45 matches
monkeypatch.setattr(engine, 'get_match', mocked_match)
objects = [NamedObject() for i in range(10)] # results in 45 matches
monkeypatch.setattr(engine, "get_match", mocked_match)
try:
r = getmatches(objects)
except MemoryError:
self.fail('MemorryError must be handled')
self.fail("MemorryError must be handled")
eq_(42, len(r))
@@ -599,7 +648,7 @@ class TestCaseGroup:
eq_([o1], g.dupes)
g.switch_ref(o2)
assert o2 is g.ref
g.switch_ref(NamedObject('', True))
g.switch_ref(NamedObject("", True))
assert o2 is g.ref
def test_switch_ref_from_ref_dir(self):
@@ -620,11 +669,11 @@ class TestCaseGroup:
m = g.get_match_of(o)
assert g.ref in m
assert o in m
assert g.get_match_of(NamedObject('', True)) is None
assert g.get_match_of(NamedObject("", True)) is None
assert g.get_match_of(g.ref) is None
def test_percentage(self):
#percentage should return the avg percentage in relation to the ref
# percentage should return the avg percentage in relation to the ref
m1, m2, m3 = get_match_triangle()
m1 = Match(m1[0], m1[1], 100)
m2 = Match(m2[0], m2[1], 50)
@@ -651,9 +700,9 @@ class TestCaseGroup:
o1 = m1.first
o2 = m1.second
o3 = m2.second
o1.name = 'c'
o2.name = 'b'
o3.name = 'a'
o1.name = "c"
o2.name = "b"
o3.name = "a"
g = Group()
g.add_match(m1)
g.add_match(m2)
@@ -709,9 +758,9 @@ class TestCaseGroup:
def test_prioritize_nothing_changes(self):
# prioritize() returns False when nothing changes in the group.
g = get_test_group()
g[0].name = 'a'
g[1].name = 'b'
g[2].name = 'c'
g[0].name = "a"
g[1].name = "b"
g[2].name = "c"
assert not g.prioritize(lambda x: x.name)
def test_list_like(self):
@@ -723,7 +772,11 @@ class TestCaseGroup:
def test_discard_matches(self):
g = Group()
o1, o2, o3 = (NamedObject("foo", True), NamedObject("bar", True), NamedObject("baz", True))
o1, o2, o3 = (
NamedObject("foo", True),
NamedObject("bar", True),
NamedObject("baz", True),
)
g.add_match(get_match(o1, o2))
g.add_match(get_match(o1, o3))
g.discard_matches()
@@ -737,8 +790,8 @@ class TestCaseget_groups:
eq_([], r)
def test_simple(self):
l = [NamedObject("foo bar"), NamedObject("bar bleh")]
matches = getmatches(l)
itemList = [NamedObject("foo bar"), NamedObject("bar bleh")]
matches = getmatches(itemList)
m = matches[0]
r = get_groups(matches)
eq_(1, len(r))
@@ -747,28 +800,39 @@ class TestCaseget_groups:
eq_([m.second], g.dupes)
def test_group_with_multiple_matches(self):
#This results in 3 matches
l = [NamedObject("foo"), NamedObject("foo"), NamedObject("foo")]
matches = getmatches(l)
# This results in 3 matches
itemList = [NamedObject("foo"), NamedObject("foo"), NamedObject("foo")]
matches = getmatches(itemList)
r = get_groups(matches)
eq_(1, len(r))
g = r[0]
eq_(3, len(g))
def test_must_choose_a_group(self):
l = [NamedObject("a b"), NamedObject("a b"), NamedObject("b c"), NamedObject("c d"), NamedObject("c d")]
#There will be 2 groups here: group "a b" and group "c d"
#"b c" can go either of them, but not both.
matches = getmatches(l)
itemList = [
NamedObject("a b"),
NamedObject("a b"),
NamedObject("b c"),
NamedObject("c d"),
NamedObject("c d"),
]
# There will be 2 groups here: group "a b" and group "c d"
# "b c" can go either of them, but not both.
matches = getmatches(itemList)
r = get_groups(matches)
eq_(2, len(r))
eq_(5, len(r[0])+len(r[1]))
eq_(5, len(r[0]) + len(r[1]))
def test_should_all_go_in_the_same_group(self):
l = [NamedObject("a b"), NamedObject("a b"), NamedObject("a b"), NamedObject("a b")]
#There will be 2 groups here: group "a b" and group "c d"
#"b c" can fit in both, but it must be in only one of them
matches = getmatches(l)
itemList = [
NamedObject("a b"),
NamedObject("a b"),
NamedObject("a b"),
NamedObject("a b"),
]
# There will be 2 groups here: group "a b" and group "c d"
# "b c" can fit in both, but it must be in only one of them
matches = getmatches(itemList)
r = get_groups(matches)
eq_(1, len(r))
@@ -787,8 +851,8 @@ class TestCaseget_groups:
assert o3 in g
def test_four_sized_group(self):
l = [NamedObject("foobar") for i in range(4)]
m = getmatches(l)
itemList = [NamedObject("foobar") for i in range(4)]
m = getmatches(itemList)
r = get_groups(m)
eq_(1, len(r))
eq_(4, len(r[0]))
@@ -808,10 +872,12 @@ class TestCaseget_groups:
# (A, B) match is the highest (thus resulting in an (A, B) group), still match C and D
# in a separate group instead of discarding them.
A, B, C, D = [NamedObject() for _ in range(4)]
m1 = Match(A, B, 90) # This is the strongest "A" match
m2 = Match(A, C, 80) # Because C doesn't match with B, it won't be in the group
m3 = Match(A, D, 80) # Same thing for D
m4 = Match(C, D, 70) # However, because C and D match, they should have their own group.
m1 = Match(A, B, 90) # This is the strongest "A" match
m2 = Match(A, C, 80) # Because C doesn't match with B, it won't be in the group
m3 = Match(A, D, 80) # Same thing for D
m4 = Match(
C, D, 70
) # However, because C and D match, they should have their own group.
groups = get_groups([m1, m2, m3, m4])
eq_(len(groups), 2)
g1, g2 = groups
@@ -819,4 +885,3 @@ class TestCaseget_groups:
assert B in g1
assert C in g2
assert D in g2