amorfo77/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-07-31 08:05:59 +00:00
Code Issues Projects Releases Wiki Activity

Refactor: de-duplicate BLAKE2b compare and simplify zip dir-marker loop

Browse Source 
DirectoryExportSink.add_json and _commit_streamed_file each inlined the
same hash-and-compare logic; extracted _content_unchanged(). Replaced
ZipExportSink._ensure_dirs's repeated slice/join with a prefix
accumulator and hoisted the _zip-is-open assertion out of the loop. No
behavioral change.
This commit is contained in:
stumpylog
2026-07-23 12:27:15 -07:00
parent 5e21ba891d
commit 7044d8ae5f
1 changed files with 23 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/documents/export/sinks.py
+23 -15
View File
@@ -164,17 +164,25 @@ class DirectoryExportSink(ExportSink):
target.parent.mkdir(parents=True, exist_ok=True)
copy_file_with_basic_stats(source, target)
@staticmethod
def _content_unchanged(target: Path, new_bytes: bytes) -> bool:
"""True if ``target`` already holds byte-identical content (BLAKE2b)."""
return (
hashlib.blake2b(target.read_bytes()).hexdigest()
== hashlib.blake2b(new_bytes).hexdigest()
)
def add_json(self, content: list | dict, arcname: str) -> None:
target = (self._target / arcname).resolve()
json_str = _dumps(content)
perform_write = True
if target in self._snapshot:
self._snapshot.discard(target)
if self._compare_json:
target_checksum = hashlib.blake2b(target.read_bytes()).hexdigest()
src_checksum = hashlib.blake2b(json_str.encode("utf-8")).hexdigest()
if src_checksum == target_checksum:
perform_write = False
if self._compare_json and self._content_unchanged(
target,
json_str.encode("utf-8"),
):
perform_write = False
if perform_write:
target.parent.mkdir(parents=True, exist_ok=True)
target.write_text(json_str, encoding="utf-8")
@@ -203,12 +211,12 @@ class DirectoryExportSink(ExportSink):
def _commit_streamed_file(self, target: Path, tmp: Path) -> None:
if target in self._snapshot:
self._snapshot.discard(target)
if self._compare_json:
existing = hashlib.blake2b(target.read_bytes()).hexdigest()
new = hashlib.blake2b(tmp.read_bytes()).hexdigest()
if existing == new:
tmp.unlink()
return
if self._compare_json and self._content_unchanged(
target,
tmp.read_bytes(),
):
tmp.unlink()
return
tmp.rename(target)
def _finalize(self) -> None:
@@ -251,12 +259,12 @@ class ZipExportSink(ExportSink):
)
def _ensure_dirs(self, arcname: str) -> None:
parts = PurePosixPath(arcname).parts[:-1]
for i in range(len(parts)):
dir_arc = "/".join(parts[: i + 1]) + "/"
assert self._zip is not None
dir_arc = ""
for part in PurePosixPath(arcname).parts[:-1]:
dir_arc += f"{part}/"
if dir_arc not in self._dirs:
self._dirs.add(dir_arc)
assert self._zip is not None
self._zip.mkdir(dir_arc)
def add_file(