def get_dupe_groups(self, files, j=job.nulljob):
j = j.start_subjob([8, 2])
for f in (f for f in files if not hasattr(f, 'is_ref')):
f.is_ref = False
files = remove_dupe_paths(files)
logging.info("Getting matches. Scan type: %d", self.scan_type)
matches = self._getmatches(files, j)
logging.info('Found %d matches' % len(matches))
j.set_progress(100, tr("Removing false matches"))
# In removing what we call here "false matches", we first want to remove, if we scan by
# folders, we want to remove folder matches for which the parent is also in a match (they're
# "duplicated duplicates if you will). Then, we also don't want mixed file kinds if the
# option isn't enabled, we want matches for which both files exist and, lastly, we don't
# want matches with both files as ref.
if self.scan_type == ScanType.Folders and matches:
allpath = {m.first.path for m in matches}
allpath |= {m.second.path for m in matches}
sortedpaths = sorted(allpath)
toremove = set()
last_parent_path = sortedpaths[0]
for p in sortedpaths[1:]:
if p in last_parent_path:
toremove.add(p)
else:
last_parent_path = p
matches = [m for m in matches if m.first.path not in toremove or m.second.path not in toremove]
if not self.mix_file_kind:
matches = [m for m in matches if get_file_ext(m.first.name) == get_file_ext(m.second.name)]
matches = [m for m in matches if m.first.path.exists() and m.second.path.exists()]
matches = [m for m in matches if not (m.first.is_ref and m.second.is_ref)]
if self.ignore_list:
j = j.start_subjob(2)
iter_matches = j.iter_with_progress(matches, tr("Processed %d/%d matches against the ignore list"))
matches = [
m for m in iter_matches
if not self.ignore_list.AreIgnored(str(m.first.path), str(m.second.path))
]
logging.info('Grouping matches')
groups = engine.get_groups(matches, j)
matched_files = dedupe([m.first for m in matches] + [m.second for m in matches])
if self.scan_type in {ScanType.Filename, ScanType.Fields, ScanType.FieldsNoOrder, ScanType.Tag}:
self.discarded_file_count = len(matched_files) - sum(len(g) for g in groups)
else:
# Ticket #195
# To speed up the scan, we don't bother comparing contents of files that are both ref
# files. However, this messes up "discarded" counting because there's a missing match
# in cases where we end up with a dupe group anyway (with a non-ref file). Because it's
# impossible to have discarded matches in exact dupe scans, we simply set it at 0, thus
# bypassing our tricky problem.
# Also, although ScanType.FuzzyBlock is not always doing exact comparisons, we also
# bypass ref comparison, thus messing up with our "discarded" count. So we're
# effectively disabling the "discarded" feature in PE, but it's better than falsely
# reporting discarded matches.
self.discarded_file_count = 0
groups = [g for g in groups if any(not f.is_ref for f in g)]
logging.info('Created %d groups' % len(groups))
j.set_progress(100, tr("Doing group prioritization"))
for g in groups:
g.prioritize(self._key_func, self._tie_breaker)
return groups
def get_dupe_groups(self, files, ignore_list=None, j=job.nulljob):
for f in (f for f in files if not hasattr(f, "is_ref")):
f.is_ref = False
files = remove_dupe_paths(files)
logging.info("Getting matches. Scan type: %d", self.scan_type)
matches = self._getmatches(files, j)
logging.info("Found %d matches" % len(matches))
j.set_progress(100, tr("Almost done! Fiddling with results..."))
# In removing what we call here "false matches", we first want to remove, if we scan by
# folders, we want to remove folder matches for which the parent is also in a match (they're
# "duplicated duplicates if you will). Then, we also don't want mixed file kinds if the
# option isn't enabled, we want matches for which both files exist and, lastly, we don't
# want matches with both files as ref.
if self.scan_type == ScanType.FOLDERS and matches:
allpath = {m.first.path for m in matches}
allpath |= {m.second.path for m in matches}
sortedpaths = sorted(allpath)
toremove = set()
last_parent_path = sortedpaths[0]
for p in sortedpaths[1:]:
if p in last_parent_path:
toremove.add(p)
else:
last_parent_path = p
matches = [m for m in matches if m.first.path not in toremove or m.second.path not in toremove]
if not self.mix_file_kind:
matches = [m for m in matches if get_file_ext(m.first.name) == get_file_ext(m.second.name)]
matches = [m for m in matches if m.first.path.exists() and m.second.path.exists()]
matches = [m for m in matches if not (m.first.is_ref and m.second.is_ref)]
if ignore_list:
matches = [m for m in matches if not ignore_list.are_ignored(str(m.first.path), str(m.second.path))]
logging.info("Grouping matches")
groups = engine.get_groups(matches)
if self.scan_type in {
ScanType.FILENAME,
ScanType.FIELDS,
ScanType.FIELDSNOORDER,
ScanType.TAG,
}:
matched_files = dedupe([m.first for m in matches] + [m.second for m in matches])
self.discarded_file_count = len(matched_files) - sum(len(g) for g in groups)
else:
# Ticket #195
# To speed up the scan, we don't bother comparing contents of files that are both ref
# files. However, this messes up "discarded" counting because there's a missing match
# in cases where we end up with a dupe group anyway (with a non-ref file). Because it's
# impossible to have discarded matches in exact dupe scans, we simply set it at 0, thus
# bypassing our tricky problem.
# Also, although ScanType.FuzzyBlock is not always doing exact comparisons, we also
# bypass ref comparison, thus messing up with our "discarded" count. So we're
# effectively disabling the "discarded" feature in PE, but it's better than falsely
# reporting discarded matches.
self.discarded_file_count = 0
groups = [g for g in groups if any(not f.is_ref for f in g)]
logging.info("Created %d groups" % len(groups))
for g in groups:
g.prioritize(self._key_func, self._tie_breaker)
return groups
def can_handle(cls, path):
return fs.File.can_handle(path) and get_file_ext(
path.name) in cls.HANDLED_EXTS
def extension(self):
return get_file_ext(self.name)
def extension(self):
return get_file_ext(self.name)
def can_handle(cls, path):
if not fs.File.can_handle(path):
return False
return get_file_ext(path.name) in auto.EXT2CLASS
def can_handle(cls, path):
return fs.File.can_handle(path) and get_file_ext(path.name) in cls.HANDLED_EXTS
def can_handle(cls, path):
if not fs.File.can_handle(path):
return False
return get_file_ext(path.name) in SUPPORTED_EXTS
def can_handle(cls, path):
if not fs.File.can_handle(path):
return False
return get_file_ext(path.name) in auto.EXT2CLASS
def _create_sub_file(self, name, with_parent=True):
parent = self if with_parent else None
ext = get_file_ext(name)
if ext in ASSOC:
return ASSOC[ext](parent, name)
