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

Apply pyupgrade changes

Browse Source
This commit is contained in:
Andrew Senetar
2022-04-27 20:53:12 -05:00
parent e0061d7bc1
commit 63dd4d4561
36 changed files with 89 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
core/app.py
View File

@@ -264,7 +264,7 @@ class DupeGuru(Broadcaster):
try:
f._read_all_info(attrnames=self.METADATA_TO_READ)
return f
except EnvironmentError:
except OSError:
return None
def _get_export_data(self):

9
core/directories.py
View File

@@ -120,7 +120,7 @@ class Directories:
file.is_ref = state == DirectoryState.REFERENCE
count += 1
yield file
except (EnvironmentError, OSError, fs.InvalidPath):
except (OSError, fs.InvalidPath):
pass
logging.debug(
"Collected %d files in folder %s",
@@ -134,14 +134,13 @@ class Directories:
j.check_if_cancelled()
try:
for subfolder in from_folder.subfolders:
for folder in self._get_folders(subfolder, j):
yield folder
yield from self._get_folders(subfolder, j)
state = self.get_state(from_folder.path)
if state != DirectoryState.EXCLUDED:
from_folder.is_ref = state == DirectoryState.REFERENCE
logging.debug("Yielding Folder %r state: %d", from_folder, state)
yield from_folder
except (EnvironmentError, fs.InvalidPath):
except (OSError, fs.InvalidPath):
pass
# ---Public
@@ -173,7 +172,7 @@ class Directories:
subpaths = [p for p in path.glob("*") if p.is_dir()]
subpaths.sort(key=lambda x: x.name.lower())
return subpaths
except EnvironmentError:
except OSError:
return []
def get_files(self, fileclasses=None, j=job.nulljob):

8
core/engine.py
View File

@@ -166,7 +166,7 @@ def reduce_common_words(word_dict, threshold):
The exception to this removal are the objects where all the words of the object are common.
Because if we remove them, we will miss some duplicates!
"""
uncommon_words = set(word for word, objects in word_dict.items() if len(objects) < threshold)
uncommon_words = {word for word, objects in word_dict.items() if len(objects) < threshold}
for word, objects in list(word_dict.items()):
if len(objects) < threshold:
continue
@@ -409,7 +409,7 @@ class Group:
You can call this after the duplicate scanning process to free a bit of memory.
"""
discarded = set(m for m in self.matches if not all(obj in self.unordered for obj in [m.first, m.second]))
discarded = {m for m in self.matches if not all(obj in self.unordered for obj in [m.first, m.second])}
self.matches -= discarded
self.candidates = defaultdict(set)
return discarded
@@ -456,7 +456,7 @@ class Group:
self._matches_for_ref = None
if (len(self) > 1) and any(not getattr(item, "is_ref", False) for item in self):
if discard_matches:
self.matches = set(m for m in self.matches if item not in m)
self.matches = {m for m in self.matches if item not in m}
else:
self._clear()
except ValueError:
@@ -529,7 +529,7 @@ def get_groups(matches):
del dupe2group
del matches
# should free enough memory to continue
logging.warning("Memory Overflow. Groups: {0}".format(len(groups)))
logging.warning(f"Memory Overflow. Groups: {len(groups)}")
# Now that we have a group, we have to discard groups' matches and see if there're any "orphan"
# matches, that is, matches that were candidate in a group but that none of their 2 files were
# accepted in the group. With these orphan groups, it's safe to build additional groups

6
core/fs.py
View File

@@ -197,7 +197,7 @@ class File:
self.path = path
def __repr__(self):
return "<{} {}>".format(self.__class__.__name__, str(self.path))
return f"<{self.__class__.__name__} {str(self.path)}>"
def __getattribute__(self, attrname):
result = object.__getattribute__(self, attrname)
@@ -317,7 +317,7 @@ class File:
raise AlreadyExistsError(newname, self.path.parent)
try:
self.path.rename(destpath)
except EnvironmentError:
except OSError:
raise OperationError(self)
if not destpath.exists():
raise OperationError(self)
@@ -421,5 +421,5 @@ def get_files(path, fileclasses=[File]):
if file is not None:
result.append(file)
return result
except EnvironmentError:
except OSError:
raise InvalidPath(path)

2
core/pe/cache.py
View File

@@ -13,7 +13,7 @@ def colors_to_string(colors):
[(0,100,255)] --> 0064ff
[(1,2,3),(4,5,6)] --> 010203040506
"""
return "".join("%02x%02x%02x" % (r, g, b) for r, g, b in colors)
return "".join("{:02x}{:02x}{:02x}".format(r, g, b) for r, g, b in colors)
# This function is an important bottleneck of dupeGuru PE. It has been converted to C.

4
core/pe/cache_shelve.py
View File

@@ -14,7 +14,7 @@ from .cache import string_to_colors, colors_to_string
def wrap_path(path):
return "path:{}".format(path)
return f"path:{path}"
def unwrap_path(key):
@@ -22,7 +22,7 @@ def unwrap_path(key):
def wrap_id(path):
return "id:{}".format(path)
return f"id:{path}"
def unwrap_id(key):

2
core/pe/matchblock.py
View File

@@ -87,7 +87,7 @@ def prepare_pictures(pictures, cache_path, with_dimensions, j=job.nulljob):
blocks = picture.get_blocks(BLOCK_COUNT_PER_SIDE)
cache[picture.unicode_path] = blocks
prepared.append(picture)
except (IOError, ValueError) as e:
except (OSError, ValueError) as e:
logging.warning(str(e))
except MemoryError:
logging.warning(

2
core/prioritize.py
View File

@@ -43,7 +43,7 @@ class Criterion:
@property
def display(self):
return "{} ({})".format(self.category.NAME, self.display_value)
return f"{self.category.NAME} ({self.display_value})"
class ValueListCategory(CriterionCategory):

8
core/results.py
View File

@@ -191,7 +191,7 @@ class Results(Markable):
self.__filters.append(filter_str)
if self.__filtered_dupes is None:
self.__filtered_dupes = flatten(g[:] for g in self.groups)
self.__filtered_dupes = set(dupe for dupe in self.__filtered_dupes if filter_re.search(str(dupe.path)))
self.__filtered_dupes = {dupe for dupe in self.__filtered_dupes if filter_re.search(str(dupe.path))}
filtered_groups = set()
for dupe in self.__filtered_dupes:
filtered_groups.add(self.get_group_of_duplicate(dupe))
@@ -301,7 +301,7 @@ class Results(Markable):
try:
func(dupe)
to_remove.append(dupe)
except (EnvironmentError, UnicodeEncodeError) as e:
except (OSError, UnicodeEncodeError) as e:
self.problems.append((dupe, str(e)))
if remove_from_results:
self.remove_duplicates(to_remove)
@@ -374,8 +374,8 @@ class Results(Markable):
try:
do_write(outfile)
except IOError as e:
# If our IOError is because dest is already a directory, we want to handle that. 21 is
except OSError as e:
# If our OSError is because dest is already a directory, we want to handle that. 21 is
# the code we get on OS X and Linux, 13 is what we get on Windows.
if e.errno in {21, 13}:
p = str(outfile)

2
core/tests/app_test.py
View File

@@ -95,7 +95,7 @@ class TestCaseDupeGuru:
# At some point, any() was used in a wrong way that made Scan() wrongly return 1
app = TestApp().app
f1, f2 = [FakeFile("foo") for _ in range(2)]
f1, f2 = (FakeFile("foo") for _ in range(2))
f1.is_ref, f2.is_ref = (False, False)
assert not (bool(f1) and bool(f2))
add_fake_files_to_directories(app.directories, [f1, f2])

26
core/tests/engine_test.py
View File

@@ -271,9 +271,9 @@ class TestCaseBuildWordDict:
class TestCaseMergeSimilarWords:
def test_some_similar_words(self):
d = {
"foobar": set([1]),
"foobar1": set([2]),
"foobar2": set([3]),
"foobar": {1},
"foobar1": {2},
"foobar2": {3},
}
merge_similar_words(d)
eq_(1, len(d))
@@ -283,8 +283,8 @@ class TestCaseMergeSimilarWords:
class TestCaseReduceCommonWords:
def test_typical(self):
d = {
"foo": set([NamedObject("foo bar", True) for _ in range(50)]),
"bar": set([NamedObject("foo bar", True) for _ in range(49)]),
"foo": {NamedObject("foo bar", True) for _ in range(50)},
"bar": {NamedObject("foo bar", True) for _ in range(49)},
}
reduce_common_words(d, 50)
assert "foo" not in d
@@ -293,7 +293,7 @@ class TestCaseReduceCommonWords:
def test_dont_remove_objects_with_only_common_words(self):
d = {
"common": set([NamedObject("common uncommon", True) for _ in range(50)] + [NamedObject("common", True)]),
"uncommon": set([NamedObject("common uncommon", True)]),
"uncommon": {NamedObject("common uncommon", True)},
}
reduce_common_words(d, 50)
eq_(1, len(d["common"]))
@@ -302,7 +302,7 @@ class TestCaseReduceCommonWords:
def test_values_still_are_set_instances(self):
d = {
"common": set([NamedObject("common uncommon", True) for _ in range(50)] + [NamedObject("common", True)]),
"uncommon": set([NamedObject("common uncommon", True)]),
"uncommon": {NamedObject("common uncommon", True)},
}
reduce_common_words(d, 50)
assert isinstance(d["common"], set)
@@ -312,9 +312,9 @@ class TestCaseReduceCommonWords:
# 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 _ in range(50)]),
"bar": set([NamedObject("foo bar baz", True) for _ in range(50)]),
"baz": set([NamedObject("foo bar baz", True) for _ in range(49)]),
"foo": {NamedObject("foo bar baz", True) for _ in range(50)},
"bar": {NamedObject("foo bar baz", True) for _ in range(50)},
"baz": {NamedObject("foo bar baz", True) for _ in range(49)},
}
try:
reduce_common_words(d, 50)
@@ -328,7 +328,7 @@ class TestCaseReduceCommonWords:
o.words = [["foo", "bar"], ["baz"]]
return o
d = {"foo": set([create_it() for _ in range(50)])}
d = {"foo": {create_it() for _ in range(50)}}
try:
reduce_common_words(d, 50)
except TypeError:
@@ -343,7 +343,7 @@ class TestCaseReduceCommonWords:
d = {
"foo": set([NamedObject("foo bar baz", True) for _ in range(49)] + [only_common]),
"bar": set([NamedObject("foo bar baz", True) for _ in range(49)] + [only_common]),
"baz": set([NamedObject("foo bar baz", True) for _ in range(49)]),
"baz": {NamedObject("foo bar baz", True) for _ in range(49)},
}
reduce_common_words(d, 50)
eq_(1, len(d["foo"]))
@@ -884,7 +884,7 @@ class TestCaseGetGroups:
# If, with a (A, B, C, D) set, all match with A, but C and D don't match with B and that the
# (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)]
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

8
core/tests/exclude_test.py
View File

@@ -289,8 +289,8 @@ class TestCaseListEmptyUnion(TestCaseListEmpty):
compiled = [x for x in self.exclude_list.compiled]
assert regex not in compiled
# Need to escape both to get the same strings after compilation
compiled_escaped = set([x.encode("unicode-escape").decode() for x in compiled[0].pattern.split("|")])
default_escaped = set([x.encode("unicode-escape").decode() for x in default_regexes])
compiled_escaped = {x.encode("unicode-escape").decode() for x in compiled[0].pattern.split("|")}
default_escaped = {x.encode("unicode-escape").decode() for x in default_regexes}
assert compiled_escaped == default_escaped
eq_(len(default_regexes), len(compiled[0].pattern.split("|")))
@@ -366,8 +366,8 @@ class TestCaseDictEmptyUnion(TestCaseDictEmpty):
compiled = [x for x in self.exclude_list.compiled]
assert regex not in compiled
# Need to escape both to get the same strings after compilation
compiled_escaped = set([x.encode("unicode-escape").decode() for x in compiled[0].pattern.split("|")])
default_escaped = set([x.encode("unicode-escape").decode() for x in default_regexes])
compiled_escaped = {x.encode("unicode-escape").decode() for x in compiled[0].pattern.split("|")}
default_escaped = {x.encode("unicode-escape").decode() for x in default_regexes}
assert compiled_escaped == default_escaped
eq_(len(default_regexes), len(compiled[0].pattern.split("|")))

6
core/tests/results_test.py
View File

@@ -337,7 +337,7 @@ class TestCaseResultsMarkings:
def log_object(o):
log.append(o)
if o is self.objects[1]:
raise EnvironmentError("foobar")
raise OSError("foobar")
log = []
self.results.mark_all()
@@ -464,7 +464,7 @@ class TestCaseResultsXML:
eq_(6, len(g1))
eq_(3, len([c for c in g1 if c.tag == "file"]))
eq_(3, len([c for c in g1 if c.tag == "match"]))
d1, d2, d3 = [c for c in g1 if c.tag == "file"]
d1, d2, d3 = (c for c in g1 if c.tag == "file")
eq_(op.join("basepath", "foo bar"), d1.get("path"))
eq_(op.join("basepath", "bar bleh"), d2.get("path"))
eq_(op.join("basepath", "foo bleh"), d3.get("path"))
@@ -477,7 +477,7 @@ class TestCaseResultsXML:
eq_(3, len(g2))
eq_(2, len([c for c in g2 if c.tag == "file"]))
eq_(1, len([c for c in g2 if c.tag == "match"]))
d1, d2 = [c for c in g2 if c.tag == "file"]
d1, d2 = (c for c in g2 if c.tag == "file")
eq_(op.join("basepath", "ibabtu"), d1.get("path"))
eq_(op.join("basepath", "ibabtu"), d2.get("path"))
eq_("n", d1.get("is_ref"))

14
core/tests/scanner_test.py
View File

@@ -29,7 +29,7 @@ class NamedObject:
self.words = getwords(name)
def __repr__(self):
return "<NamedObject %r %r>" % (self.name, self.path)
return "<NamedObject {!r} {!r}>".format(self.name, self.path)
no = NamedObject
@@ -336,7 +336,7 @@ def test_tag_scan(fake_fileexists):
def test_tag_with_album_scan(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.TAG
s.scanned_tags = set(["artist", "album", "title"])
s.scanned_tags = {"artist", "album", "title"}
o1 = no("foo")
o2 = no("bar")
o3 = no("bleh")
@@ -356,7 +356,7 @@ def test_tag_with_album_scan(fake_fileexists):
def test_that_dash_in_tags_dont_create_new_fields(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.TAG
s.scanned_tags = set(["artist", "album", "title"])
s.scanned_tags = {"artist", "album", "title"}
s.min_match_percentage = 50
o1 = no("foo")
o2 = no("bar")
@@ -373,7 +373,7 @@ def test_that_dash_in_tags_dont_create_new_fields(fake_fileexists):
def test_tag_scan_with_different_scanned(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.TAG
s.scanned_tags = set(["track", "year"])
s.scanned_tags = {"track", "year"}
o1 = no("foo")
o2 = no("bar")
o1.artist = "The White Stripes"
@@ -391,7 +391,7 @@ def test_tag_scan_with_different_scanned(fake_fileexists):
def test_tag_scan_only_scans_existing_tags(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.TAG
s.scanned_tags = set(["artist", "foo"])
s.scanned_tags = {"artist", "foo"}
o1 = no("foo")
o2 = no("bar")
o1.artist = "The White Stripes"
@@ -405,7 +405,7 @@ def test_tag_scan_only_scans_existing_tags(fake_fileexists):
def test_tag_scan_converts_to_str(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.TAG
s.scanned_tags = set(["track"])
s.scanned_tags = {"track"}
o1 = no("foo")
o2 = no("bar")
o1.track = 42
@@ -420,7 +420,7 @@ def test_tag_scan_converts_to_str(fake_fileexists):
def test_tag_scan_non_ascii(fake_fileexists):
s = Scanner()
s.scan_type = ScanType.TAG
s.scanned_tags = set(["title"])
s.scanned_tags = {"title"}
o1 = no("foo")
o2 = no("bar")
o1.title = "foobar\u00e9"