feat(images): duplicate cleanup keeps images' own categories (#332)

The kept copy's own category wins; a kept copy without one receives the
removed copy's, keyed by the deepest output source holding each file.
The removed copy's row is never deleted, so a give-back or a failed
delete loses nothing. The job log reports how many were kept.
This commit is contained in:
Vito Sansevero
2026-10-27 18:17:28 -07:00
parent cd573ccf1a
commit 0237fba77a
4 changed files with 177 additions and 3 deletions
+4
View File
@@ -589,6 +589,7 @@ class DuplicateFilesMixin:
spellings = await self._run_in_executor(self._source_spellings)
removed, failure, keepers = 0, None, {}
totals = dict.fromkeys(("moved", "merged", "favorites", "tags", "review"), 0)
totals["categories"] = 0 # image categories kept on the kept copies (#332)
for done, target in enumerate(targets, start=1):
if failure is not None:
self._record_target(job, "kept", target, NOT_ATTEMPTED)
@@ -635,6 +636,9 @@ class DuplicateFilesMixin:
job.log_line(
f"Added {_plural(totals['tags'], 'image tag')} to the kept copies"
)
if totals.get("categories"):
kept = _plural(totals["categories"], "image category", "image categories")
job.log_line(f"Kept {kept} on the kept copies")
if totals["review"]:
job.log_line(
f"Settled {_plural(totals['review'], 'Needs review item')} "
+24 -1
View File
@@ -18,7 +18,7 @@ Blocking: each lookup stats the file's folders once (cached).
import os
from pathlib import Path
from .images import _favorite_relative_key, _favorite_root_key
from .images import _favorite_relative_key, _favorite_root_key, image_category_key
def _identity(path):
@@ -78,6 +78,15 @@ class Spellings:
)
return spelled
@property
def listed_roots(self):
"""The listed roots (the output sources), in order."""
return [root for root, _identity in self._listed]
def category_key(self, path):
"""*path*'s image category file key (#332), or None outside every source."""
return image_category_key(self.listed_roots, path)
def favorites(self, path):
"""``{listed root: path below it (POSIX)}`` for each listed root holding it."""
path = os.path.abspath(str(path))
@@ -125,9 +134,23 @@ def copy_move(target, kept_stat, spellings):
"targets": targets,
"kept_path": target["keeper_abs"],
"favorites": favorites,
"categories": _category_pairs(target, spellings),
"removed_locator": target["locator"],
"kept_locator": target["keeper_locator"],
"sha256": target["hash"],
"kept_size": kept_stat.st_size,
"kept_mtime_ns": kept_stat.st_mtime_ns,
}
def _category_pairs(target, spellings):
"""``[(removed file key, kept file key)]`` for the image category (#332).
From the two absolute paths, not the favorites tuples: those follow the
listed root, which differs from the file key when sources nest.
"""
removed = spellings.category_key(target["abs"])
kept = spellings.category_key(target["keeper_abs"])
if removed is None or kept is None:
return []
return [(removed, kept)]