paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-02-09 23:49:29 -06:00
Code Issues Packages Projects Releases Wiki Activity

Wrong indentation level

Browse Source
This commit is contained in:
Trenton H
2026-02-09 16:11:36 -08:00
parent 914362224c
commit 40ff58ad39
3 changed files with 86 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
src/documents/management/commands/document_exporter.py
View File

@@ -327,48 +327,50 @@ class Command(CryptMixin, BaseCommand):
for index, document_dict in enumerate(document_manifest): for index, document_dict in enumerate(document_manifest):
document = document_map[document_dict["pk"]] document = document_map[document_dict["pk"]]
# 3.1. generate a unique filename # 3.1. generate a unique filename
base_name = self.generate_base_name(document) base_name = self.generate_base_name(document)
# 3.2. write filenames into manifest # 3.2. write filenames into manifest
original_target, thumbnail_target, archive_target = ( original_target, thumbnail_target, archive_target = (
self.generate_document_targets(document, base_name, document_dict) self.generate_document_targets(document, base_name, document_dict)
)
# 3.3. write files to target folder
if not self.data_only:
self.copy_document_files(
document,
original_target,
thumbnail_target,
archive_target,
) )
if self.split_manifest: # 3.3. write files to target folder
manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json") if not self.data_only:
if self.use_folder_prefix: self.copy_document_files(
manifest_name = Path("json") / manifest_name document,
manifest_name = (self.target / manifest_name).resolve() original_target,
manifest_name.parent.mkdir(parents=True, exist_ok=True) thumbnail_target,
content = [document_manifest[index]] archive_target,
content += list( )
filter(
lambda d: d["fields"]["document"] == document_dict["pk"],
manifest_dict["notes"],
),
)
content += list(
filter(
lambda d: d["fields"]["document"] == document_dict["pk"],
manifest_dict["custom_field_instances"],
),
)
self.check_and_write_json( if self.split_manifest:
content, manifest_name = base_name.with_name(
manifest_name, f"{base_name.stem}-manifest.json",
) )
progress.update(task, advance=1) if self.use_folder_prefix:
manifest_name = Path("json") / manifest_name
manifest_name = (self.target / manifest_name).resolve()
manifest_name.parent.mkdir(parents=True, exist_ok=True)
content = [document_manifest[index]]
content += list(
filter(
lambda d: d["fields"]["document"] == document_dict["pk"],
manifest_dict["notes"],
),
)
content += list(
filter(
lambda d: d["fields"]["document"] == document_dict["pk"],
manifest_dict["custom_field_instances"],
),
)
self.check_and_write_json(
content,
manifest_name,
)
progress.update(task, advance=1)
# These were exported already # These were exported already
if self.split_manifest: if self.split_manifest:

84
src/documents/management/commands/document_importer.py
View File

@@ -383,56 +383,56 @@ class Command(CryptMixin, BaseCommand):
for record in manifest_documents: for record in manifest_documents:
document = Document.objects.get(pk=record["pk"]) document = Document.objects.get(pk=record["pk"])
doc_file = record[EXPORTER_FILE_NAME] doc_file = record[EXPORTER_FILE_NAME]
document_path = self.source / doc_file document_path = self.source / doc_file
if EXPORTER_THUMBNAIL_NAME in record: if EXPORTER_THUMBNAIL_NAME in record:
thumb_file = record[EXPORTER_THUMBNAIL_NAME] thumb_file = record[EXPORTER_THUMBNAIL_NAME]
thumbnail_path = (self.source / thumb_file).resolve() thumbnail_path = (self.source / thumb_file).resolve()
else: else:
thumbnail_path = None thumbnail_path = None
if EXPORTER_ARCHIVE_NAME in record: if EXPORTER_ARCHIVE_NAME in record:
archive_file = record[EXPORTER_ARCHIVE_NAME] archive_file = record[EXPORTER_ARCHIVE_NAME]
archive_path = self.source / archive_file archive_path = self.source / archive_file
else: else:
archive_path = None archive_path = None
with FileLock(settings.MEDIA_LOCK): with FileLock(settings.MEDIA_LOCK):
if Path(document.source_path).is_file(): if Path(document.source_path).is_file():
raise FileExistsError(document.source_path) raise FileExistsError(document.source_path)
create_source_path_directory(document.source_path) create_source_path_directory(document.source_path)
copy_file_with_basic_stats(document_path, document.source_path) copy_file_with_basic_stats(document_path, document.source_path)
if thumbnail_path: if thumbnail_path:
if thumbnail_path.suffix in {".png", ".PNG"}: if thumbnail_path.suffix in {".png", ".PNG"}:
run_convert( run_convert(
density=300, density=300,
scale="500x5000>", scale="500x5000>",
alpha="remove", alpha="remove",
strip=True, strip=True,
trim=False, trim=False,
auto_orient=True, auto_orient=True,
input_file=f"{thumbnail_path}[0]", input_file=f"{thumbnail_path}[0]",
output_file=str(document.thumbnail_path), output_file=str(document.thumbnail_path),
) )
else: else:
copy_file_with_basic_stats( copy_file_with_basic_stats(
thumbnail_path, thumbnail_path,
document.thumbnail_path, document.thumbnail_path,
) )
if archive_path: if archive_path:
create_source_path_directory(document.archive_path) create_source_path_directory(document.archive_path)
# TODO: this assumes that the export is valid and # TODO: this assumes that the export is valid and
# archive_filename is present on all documents with # archive_filename is present on all documents with
# archived files # archived files
copy_file_with_basic_stats(archive_path, document.archive_path) copy_file_with_basic_stats(archive_path, document.archive_path)
document.save() document.save()
progress.update(task, advance=1) progress.update(task, advance=1)
def decrypt_secret_fields(self) -> None: def decrypt_secret_fields(self) -> None:
""" """

4
src/paperless_ai/tests/test_ai_indexing.py
View File

@@ -76,6 +76,7 @@ def test_update_llm_index(
mock_queryset = MagicMock() mock_queryset = MagicMock()
mock_queryset.exists.return_value = True mock_queryset.exists.return_value = True
mock_queryset.__iter__.return_value = iter([real_document]) mock_queryset.__iter__.return_value = iter([real_document])
mock_queryset.count.return_value = 1
mock_all.return_value = mock_queryset mock_all.return_value = mock_queryset
indexing.update_llm_index(rebuild=True) indexing.update_llm_index(rebuild=True)
@@ -97,6 +98,7 @@ def test_update_llm_index_removes_meta(
mock_queryset = MagicMock() mock_queryset = MagicMock()
mock_queryset.exists.return_value = True mock_queryset.exists.return_value = True
mock_queryset.__iter__.return_value = iter([real_document]) mock_queryset.__iter__.return_value = iter([real_document])
mock_queryset.count.return_value = 1
mock_all.return_value = mock_queryset mock_all.return_value = mock_queryset
indexing.update_llm_index(rebuild=True) indexing.update_llm_index(rebuild=True)
@@ -129,6 +131,7 @@ def test_update_llm_index_partial_update(
mock_queryset = MagicMock() mock_queryset = MagicMock()
mock_queryset.exists.return_value = True mock_queryset.exists.return_value = True
mock_queryset.__iter__.return_value = iter([real_document, doc2]) mock_queryset.__iter__.return_value = iter([real_document, doc2])
mock_queryset.count.return_value = 2
mock_all.return_value = mock_queryset mock_all.return_value = mock_queryset
indexing.update_llm_index(rebuild=True) indexing.update_llm_index(rebuild=True)
@@ -149,6 +152,7 @@ def test_update_llm_index_partial_update(
mock_queryset = MagicMock() mock_queryset = MagicMock()
mock_queryset.exists.return_value = True mock_queryset.exists.return_value = True
mock_queryset.__iter__.return_value = iter([updated_document, doc2, doc3]) mock_queryset.__iter__.return_value = iter([updated_document, doc2, doc3])
mock_queryset.count.return_value = 3
mock_all.return_value = mock_queryset mock_all.return_value = mock_queryset
# assert logs "Updating LLM index with %d new nodes and removing %d old nodes." # assert logs "Updating LLM index with %d new nodes and removing %d old nodes."