arsenetar/dupeguru
1
0
Fork 0
mirror of https://github.com/arsenetar/dupeguru.git synced 2025-09-11 17:58:17 +00:00
Code Releases Wiki Activity

Fixed a bug causing groups with more than one ref file in it to appear (which looks weird and messes with selection).

Browse Source 
Contents scans already weeded them out, bu t they were still possible with name-based scans. Now, the Scanner removes them all.
This commit is contained in:
Virgil Dupras 2012-08-09 11:16:06 -04:00
parent df30a31782
commit 111edc3ce5
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
core/scanner.py
View File

@ -11,7 +11,6 @@ import re
import os.path as op import os.path as op
from jobprogress import job from jobprogress import job
from hscommon import io
from hscommon.util import dedupe, rem_file_ext, get_file_ext from hscommon.util import dedupe, rem_file_ext, get_file_ext
from hscommon.trans import tr from hscommon.trans import tr
@ -129,6 +128,11 @@ class Scanner:
matches = self._getmatches(files, j) matches = self._getmatches(files, j)
logging.info('Found %d matches' % len(matches)) logging.info('Found %d matches' % len(matches))
j.set_progress(100, tr("Removing false 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: if self.scan_type == ScanType.Folders and matches:
allpath = {m.first.path for m in matches} allpath = {m.first.path for m in matches}
allpath |= {m.second.path for m in matches} allpath |= {m.second.path for m in matches}
@ -143,7 +147,8 @@ class Scanner:
matches = [m for m in matches if m.first.path not in toremove or m.second.path not in toremove] 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: 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 get_file_ext(m.first.name) == get_file_ext(m.second.name)]
matches = [m for m in matches if io.exists(m.first.path) and io.exists(m.second.path)] 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: if self.ignore_list:
j = j.start_subjob(2) j = j.start_subjob(2)
iter_matches = j.iter_with_progress(matches, tr("Processed %d/%d matches against the ignore list")) iter_matches = j.iter_with_progress(matches, tr("Processed %d/%d matches against the ignore list"))