Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improve relink performance #614

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Improve relink performance #614

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e5e7b47
feat: avoid superfluous calls to os.walk when relinking missing files…
Toby222 Nov 29, 2024
211e89f
fix(fmt): split line to make ruff happy
Toby222 Nov 29, 2024
2b3edff
fix: remove changes to legacy JSON library
Toby222 Dec 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions tagstudio/src/core/utils/missing_files.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ class MissingRegistry:
library: Library
files_fixed_count: int = 0
missing_files: list[Entry] = field(default_factory=list)
library_file_cache: set[Path] = None
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

#608 already added a library file cache here. Could you leverage that one instead of adding a new one?


@property
def missing_files_count(self) -> int:
Expand All @@ -40,15 +41,18 @@ def match_missing_file(self, match_item: Entry) -> list[Path]:
Works if files were just moved to different subfolders and don't have duplicate names.
"""
matches = []
for item in self.library.library_dir.glob(f"**/{match_item.path.name}"):
if item.name == match_item.path.name: # TODO - implement IGNORE_ITEMS
new_path = Path(item).relative_to(self.library.library_dir)
matches.append(new_path)
# TODO - implement IGNORE_ITEMS
item_name = match_item.path.name
for matched_path in filter(lambda file: file.name == item_name, self.library_file_cache):
logger.info("match_missing_files", matched_path=matched_path)
new_path = Path(matched_path).relative_to(self.library.library_dir)
matches.append(new_path)

return matches

def fix_missing_files(self) -> Iterator[int]:
"""Attempt to fix missing files by finding a match in the library directory."""
self.library_file_cache = set(self.library.library_dir.rglob("*"))
self.files_fixed_count = 0
for i, entry in enumerate(self.missing_files, start=1):
item_matches = self.match_missing_file(entry)
Expand All @@ -59,6 +63,7 @@ def fix_missing_files(self) -> Iterator[int]:
# remove fixed file
self.missing_files.remove(entry)
yield i
self.library_file_cache = None

def execute_deletion(self) -> Iterator[int]:
for i, missing in enumerate(self.missing_files, start=1):
Expand Down
Loading