arsenetar/dupeguru
1
0
Fork 0
mirror of https://github.com/arsenetar/dupeguru.git synced 2025-03-10 05:34:36 +00:00
Code Releases Wiki Activity

Simplify getmatches_by_contents() signature

Browse Source 
partial and sizeattr attributes are not needed anymore.
This commit is contained in:
Virgil Dupras 2016-06-08 12:06:08 -04:00
parent 64e86c9ff9
commit fbdd1d866e
2 changed files with 10 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
core/engine.py
View File

@ -246,21 +246,15 @@ def getmatches(
return result
return result
def getmatches_by_contents(files, sizeattr='size', partial=False, j=job.nulljob):
def getmatches_by_contents(files, j=job.nulljob):
"""Returns a list of :class:`Match` within ``files`` if their contents is the same.
:param str sizeattr: attibute name of the :class:`~core.fs.file` that returns the size of the
file to use for comparison.
:param bool partial: if true, will use the "md5partial" attribute instead of "md5" to compute
contents hash.
:param j: A :ref:`job progress instance <jobs>`.
"""
j = j.start_subjob([2, 8])
size2files = defaultdict(set)
for file in j.iter_with_progress(files, tr("Read size of %d/%d files")):
filesize = getattr(file, sizeattr)
if filesize:
size2files[filesize].add(file)
for f in files:
if f.size:
size2files[f.size].add(f)
del files
possible_matches = [files for files in size2files.values() if len(files) > 1]
del size2files
@ -271,7 +265,7 @@ def getmatches_by_contents(files, sizeattr='size', partial=False, j=job.nulljob)
if first.is_ref and second.is_ref:
continue # Don't spend time comparing two ref pics together.
if first.md5partial == second.md5partial:
if partial or first.md5 == second.md5:
if first.md5 == second.md5:
result.append(Match(first, second, 100))
j.add_progress(desc=tr("%d matches found") % len(result))
return result

7
core/scanner.py
View File

@ -72,13 +72,14 @@ class Scanner:
self.discarded_file_count = 0
def _getmatches(self, files, j):
if self.size_threshold:
if self.size_threshold or self.scan_type in {ScanType.Contents, ScanType.Folders}:
j = j.start_subjob([2, 8])
for f in j.iter_with_progress(files, tr("Read size of %d/%d files")):
f.size # pre-read, makes a smoother progress if read here (especially for bundles)
if self.size_threshold:
files = [f for f in files if f.size >= self.size_threshold]
if self.scan_type in {ScanType.Contents, ScanType.Folders}:
return engine.getmatches_by_contents(files, sizeattr='size', partial=False, j=j)
return engine.getmatches_by_contents(files, j=j)
else:
j = j.start_subjob([2, 8])
kw = {}
@ -98,7 +99,7 @@ class Scanner:
],
}[self.scan_type]
for f in j.iter_with_progress(files, tr("Read metadata of %d/%d files")):
logging.debug("Reading metadata of {}".format(str(f.path)))
logging.debug("Reading metadata of %s", f.path)
f.words = func(f)
return engine.getmatches(files, j=j, **kw)