Enhancement: support import of zipped export (#10073)

This commit is contained in:
Kilian 2025-06-13 19:06:37 +02:00 committed by GitHub
parent 4313635b01
commit 246f17c6c8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 53 additions and 8 deletions

View File

@ -333,7 +333,7 @@ must be provided to import. If this value is lost, the export cannot be imported
The document importer takes the export produced by the [Document
exporter](#exporter) and imports it into paperless.
The importer works just like the exporter. You point it at a directory,
The importer works just like the exporter. You point it at a directory or the generated .zip file,
and the script does the rest of the work:
```shell
@ -351,9 +351,6 @@ When you use the provided docker compose script, put the export inside
the `export` folder in your paperless source directory. Specify
`../export` as the `source`.
Note that .zip files (as can be generated from the exporter) are not supported. You must unzip them into
the target directory first.
!!! note
Importing from a previous version of Paperless may work, but for best

View File

@ -1,9 +1,12 @@
import json
import logging
import os
import tempfile
from collections.abc import Generator
from contextlib import contextmanager
from pathlib import Path
from zipfile import ZipFile
from zipfile import is_zipfile
import tqdm
from django.conf import settings
@ -234,14 +237,19 @@ class Command(CryptMixin, BaseCommand):
self.manifest_paths = []
self.manifest = []
# Create a temporary directory for extracting a zip file into it, even if supplied source is no zip file to keep code cleaner.
with tempfile.TemporaryDirectory() as tmp_dir:
if is_zipfile(self.source):
with ZipFile(self.source) as zf:
zf.extractall(tmp_dir)
self.source = Path(tmp_dir)
self._run_import()
def _run_import(self):
self.pre_check()
self.load_metadata()
self.load_manifest_files()
self.check_manifest_validity()
self.decrypt_secret_fields()
# see /src/documents/signals/handlers.py

View File

@ -2,6 +2,7 @@ import json
import tempfile
from io import StringIO
from pathlib import Path
from zipfile import ZipFile
from django.contrib.auth.models import User
from django.core.management import call_command
@ -335,3 +336,42 @@ class TestCommandImport(
self.assertIn("Version mismatch:", stdout_str)
self.assertIn("importing 2.8.1", stdout_str)
def test_import_zipped_export(self):
"""
GIVEN:
- A zip file with correct content (manifest.json and version.json inside)
WHEN:
- An import is attempted using the zip file as the source
THEN:
- The command reads from the zip without warnings or errors
"""
stdout = StringIO()
zip_path = self.dirs.scratch_dir / "export.zip"
# Create manifest.json and version.json in a temp dir
with tempfile.TemporaryDirectory() as temp_dir:
temp_dir_path = Path(temp_dir)
(temp_dir_path / "manifest.json").touch()
(temp_dir_path / "version.json").touch()
# Create the zip file
with ZipFile(zip_path, "w") as zf:
zf.write(temp_dir_path / "manifest.json", arcname="manifest.json")
zf.write(temp_dir_path / "version.json", arcname="version.json")
# Try to import from the zip file
with self.assertRaises(json.decoder.JSONDecodeError):
call_command(
"document_importer",
"--no-progress-bar",
str(zip_path),
stdout=stdout,
)
stdout.seek(0)
stdout_str = str(stdout.read())
# There should be no error or warnings. Therefore the output should be empty.
self.assertEqual(stdout_str, "")