mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-08-28 13:37:32 +00:00
Compare commits
19
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
6b47534841 | ||
|
|
c6e3f7a0c4 | ||
|
|
dc7b649625 | ||
|
|
a4075c49b2 | ||
|
|
70b1c86ad3 | ||
|
|
8f5f577634 | ||
|
|
65b6db7b63 | ||
|
|
6f843bda8d | ||
|
|
b7267815e3 | ||
|
|
c9bf18646a | ||
|
|
8d1af73dc4 | ||
|
|
515866a381 | ||
|
|
a91a2ab7e6 | ||
|
|
6d49f6e283 | ||
|
|
ccd39118c2 | ||
|
|
9c9771b5fc | ||
|
|
73e872d5f7 | ||
|
|
d3e6ef8c02 | ||
|
|
18af45959f |
+105
-23
@@ -186,29 +186,110 @@ line-ending = "lf"
|
|||||||
# https://docs.astral.sh/ruff/rules/
|
# https://docs.astral.sh/ruff/rules/
|
||||||
select = [ "E4", "E7", "E9", "F" ]
|
select = [ "E4", "E7", "E9", "F" ]
|
||||||
extend-select = [
|
extend-select = [
|
||||||
"COM", # https://docs.astral.sh/ruff/rules/#flake8-commas-com
|
"ASYNC", # https://docs.astral.sh/ruff/rules/#flake8-async-async
|
||||||
"DJ", # https://docs.astral.sh/ruff/rules/#flake8-django-dj
|
"B002", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"EXE", # https://docs.astral.sh/ruff/rules/#flake8-executable-exe
|
"B003", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"FBT", # https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt
|
"B004", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"FLY", # https://docs.astral.sh/ruff/rules/#flynt-fly
|
"B005", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"G201", # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
|
"B006", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"I", # https://docs.astral.sh/ruff/rules/#isort-i
|
"B008", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"ICN", # https://docs.astral.sh/ruff/rules/#flake8-import-conventions-icn
|
"B009", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"INP", # https://docs.astral.sh/ruff/rules/#flake8-no-pep420-inp
|
"B010", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"ISC", # https://docs.astral.sh/ruff/rules/#flake8-implicit-str-concat-isc
|
"B012", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"PIE", # https://docs.astral.sh/ruff/rules/#flake8-pie-pie
|
"B013", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"PLC", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
"B014", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"PLE", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
"B015", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"PTH", # https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
|
"B016", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"Q", # https://docs.astral.sh/ruff/rules/#flake8-quotes-q
|
"B017", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"RSE", # https://docs.astral.sh/ruff/rules/#flake8-raise-rse
|
"B018", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"RUF", # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
|
"B019", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"SIM", # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
|
"B020", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"T20", # https://docs.astral.sh/ruff/rules/#flake8-print-t20
|
"B021", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"TC", # https://docs.astral.sh/ruff/rules/#flake8-type-checking-tc
|
"B022", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"TID", # https://docs.astral.sh/ruff/rules/#flake8-tidy-imports-tid
|
"B023", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"UP", # https://docs.astral.sh/ruff/rules/#pyupgrade-up
|
"B025", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
"W", # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
|
"B026", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"B029", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"B030", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"B031", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"B032", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"B033", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"B035", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"B039", # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
|
||||||
|
"C4", # https://docs.astral.sh/ruff/rules/#flake8-comprehensions-c4
|
||||||
|
"COM", # https://docs.astral.sh/ruff/rules/#flake8-commas-com
|
||||||
|
"D419", # https://docs.astral.sh/ruff/rules/#pydocstyle-d
|
||||||
|
"DJ", # https://docs.astral.sh/ruff/rules/#flake8-django-dj
|
||||||
|
"DTZ", # https://docs.astral.sh/ruff/rules/#flake8-datetimez-dtz
|
||||||
|
"EXE", # https://docs.astral.sh/ruff/rules/#flake8-executable-exe
|
||||||
|
"FA", # https://docs.astral.sh/ruff/rules/#flake8-future-annotations-fa
|
||||||
|
"FBT", # https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt
|
||||||
|
"FLY", # https://docs.astral.sh/ruff/rules/#flynt-fly
|
||||||
|
"FURB", # https://docs.astral.sh/ruff/rules/#refurb-furb
|
||||||
|
"G010", # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
|
||||||
|
"G101", # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
|
||||||
|
"G201", # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
|
||||||
|
"G202", # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
|
||||||
|
"I", # https://docs.astral.sh/ruff/rules/#isort-i
|
||||||
|
"ICN", # https://docs.astral.sh/ruff/rules/#flake8-import-conventions-icn
|
||||||
|
"INP", # https://docs.astral.sh/ruff/rules/#flake8-no-pep420-inp
|
||||||
|
"INT001", # https://docs.astral.sh/ruff/rules/#flake8-gettext-int
|
||||||
|
"INT002", # https://docs.astral.sh/ruff/rules/#flake8-gettext-int
|
||||||
|
"INT003", # https://docs.astral.sh/ruff/rules/#flake8-gettext-int
|
||||||
|
"ISC", # https://docs.astral.sh/ruff/rules/#flake8-implicit-str-concat-isc
|
||||||
|
"LOG001", # https://docs.astral.sh/ruff/rules/#flake8-logging-log
|
||||||
|
"LOG002", # https://docs.astral.sh/ruff/rules/#flake8-logging-log
|
||||||
|
"LOG009", # https://docs.astral.sh/ruff/rules/#flake8-logging-log
|
||||||
|
"LOG014", # https://docs.astral.sh/ruff/rules/#flake8-logging-log
|
||||||
|
"LOG015", # https://docs.astral.sh/ruff/rules/#flake8-logging-log
|
||||||
|
"N999", # https://docs.astral.sh/ruff/rules/#pep8-naming-n
|
||||||
|
"PERF101", # https://docs.astral.sh/ruff/rules/#perflint-perf
|
||||||
|
"PERF102", # https://docs.astral.sh/ruff/rules/#perflint-perf
|
||||||
|
"PERF402", # https://docs.astral.sh/ruff/rules/#perflint-perf
|
||||||
|
"PGH005", # https://docs.astral.sh/ruff/rules/#pygrep-hooks-pgh
|
||||||
|
"PIE", # https://docs.astral.sh/ruff/rules/#flake8-pie-pie
|
||||||
|
"PLC", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLE", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR0124", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR0133", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR0206", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR0402", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1704", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1708", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1711", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1716", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1722", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1730", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1733", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR1736", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLR2044", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PLW", # https://docs.astral.sh/ruff/rules/#pylint-pl
|
||||||
|
"PT010", # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
|
||||||
|
"PT014", # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
|
||||||
|
"PT020", # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
|
||||||
|
"PT025", # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
|
||||||
|
"PT026", # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
|
||||||
|
"PT031", # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
|
||||||
|
"PTH", # https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
|
||||||
|
"Q", # https://docs.astral.sh/ruff/rules/#flake8-quotes-q
|
||||||
|
"RSE", # https://docs.astral.sh/ruff/rules/#flake8-raise-rse
|
||||||
|
"RUF", # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
|
||||||
|
"S102", # https://docs.astral.sh/ruff/rules/#flake8-bandit-s
|
||||||
|
"S110", # https://docs.astral.sh/ruff/rules/#flake8-bandit-s
|
||||||
|
"S112", # https://docs.astral.sh/ruff/rules/#flake8-bandit-s
|
||||||
|
"SIM", # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
|
||||||
|
"T100", # https://docs.astral.sh/ruff/rules/#flake8-debugger-t10
|
||||||
|
"T20", # https://docs.astral.sh/ruff/rules/#flake8-print-t20
|
||||||
|
"TC", # https://docs.astral.sh/ruff/rules/#flake8-type-checking-tc
|
||||||
|
"TID", # https://docs.astral.sh/ruff/rules/#flake8-tidy-imports-tid
|
||||||
|
"TRY002", # https://docs.astral.sh/ruff/rules/#tryceratops-try
|
||||||
|
"TRY004", # https://docs.astral.sh/ruff/rules/#tryceratops-try
|
||||||
|
"TRY201", # https://docs.astral.sh/ruff/rules/#tryceratops-try
|
||||||
|
"TRY203", # https://docs.astral.sh/ruff/rules/#tryceratops-try
|
||||||
|
"TRY401", # https://docs.astral.sh/ruff/rules/#tryceratops-try
|
||||||
|
"UP", # https://docs.astral.sh/ruff/rules/#pyupgrade-up
|
||||||
|
"W", # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
|
||||||
|
"YTT", # https://docs.astral.sh/ruff/rules/#flake8-2020-ytt
|
||||||
]
|
]
|
||||||
ignore = [
|
ignore = [
|
||||||
"DJ001",
|
"DJ001",
|
||||||
@@ -224,6 +305,7 @@ per-file-ignores."*/migrations/*.py" = [
|
|||||||
]
|
]
|
||||||
# Testing
|
# Testing
|
||||||
per-file-ignores."*/tests/*.py" = [
|
per-file-ignores."*/tests/*.py" = [
|
||||||
|
"DTZ",
|
||||||
"E501",
|
"E501",
|
||||||
"SIM117",
|
"SIM117",
|
||||||
]
|
]
|
||||||
|
|||||||
+14
-17
@@ -27,7 +27,7 @@ from documents.models import DocumentType
|
|||||||
from documents.models import PaperlessTask
|
from documents.models import PaperlessTask
|
||||||
from documents.models import StoragePath
|
from documents.models import StoragePath
|
||||||
from documents.models import Tag
|
from documents.models import Tag
|
||||||
from documents.permissions import set_permissions_for_objects
|
from documents.permissions import set_permissions_for_object
|
||||||
from documents.plugins.helpers import DocumentsStatusManager
|
from documents.plugins.helpers import DocumentsStatusManager
|
||||||
from documents.tasks import bulk_update_documents
|
from documents.tasks import bulk_update_documents
|
||||||
from documents.tasks import consume_file
|
from documents.tasks import consume_file
|
||||||
@@ -430,13 +430,10 @@ def set_permissions(
|
|||||||
else:
|
else:
|
||||||
qs.update(owner=owner)
|
qs.update(owner=owner)
|
||||||
|
|
||||||
|
for doc in qs:
|
||||||
|
set_permissions_for_object(permissions=set_permissions, object=doc, merge=merge)
|
||||||
|
|
||||||
affected_docs = list(qs.values_list("pk", flat=True))
|
affected_docs = list(qs.values_list("pk", flat=True))
|
||||||
set_permissions_for_objects(
|
|
||||||
permissions=set_permissions,
|
|
||||||
model=Document,
|
|
||||||
pks=affected_docs,
|
|
||||||
merge=merge,
|
|
||||||
)
|
|
||||||
|
|
||||||
bulk_update_documents.apply_async(
|
bulk_update_documents.apply_async(
|
||||||
kwargs={"document_ids": affected_docs},
|
kwargs={"document_ids": affected_docs},
|
||||||
@@ -510,8 +507,8 @@ def rotate(
|
|||||||
logger.info(
|
logger.info(
|
||||||
f"Queued new rotated version for document {pair.root_doc.id} by {degrees} degrees",
|
f"Queued new rotated version for document {pair.root_doc.id} by {degrees} degrees",
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(f"Error rotating document {pair.root_doc.id}: {e}")
|
logger.exception(f"Error rotating document {pair.root_doc.id}")
|
||||||
|
|
||||||
return "OK"
|
return "OK"
|
||||||
|
|
||||||
@@ -557,9 +554,9 @@ def merge(
|
|||||||
affected_docs.append(doc.id)
|
affected_docs.append(doc.id)
|
||||||
if handoff_asn is None and doc.archive_serial_number is not None:
|
if handoff_asn is None and doc.archive_serial_number is not None:
|
||||||
handoff_asn = doc.archive_serial_number
|
handoff_asn = doc.archive_serial_number
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"Error merging document {doc.id}, it will not be included in the merge: {e}",
|
f"Error merging document {doc.id}, it will not be included in the merge",
|
||||||
)
|
)
|
||||||
if len(affected_docs) == 0:
|
if len(affected_docs) == 0:
|
||||||
logger.warning("No documents were merged")
|
logger.warning("No documents were merged")
|
||||||
@@ -808,8 +805,8 @@ def split(
|
|||||||
else:
|
else:
|
||||||
group(consume_tasks).delay()
|
group(consume_tasks).delay()
|
||||||
|
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(f"Error splitting document {doc.id}: {e}")
|
logger.exception(f"Error splitting document {doc.id}")
|
||||||
|
|
||||||
return "OK"
|
return "OK"
|
||||||
|
|
||||||
@@ -861,8 +858,8 @@ def delete_pages(
|
|||||||
logger.info(
|
logger.info(
|
||||||
f"Queued new version for document {pair.root_doc.id} after deleting pages {pages}",
|
f"Queued new version for document {pair.root_doc.id} after deleting pages {pages}",
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(f"Error deleting pages from document {pair.root_doc.id}: {e}")
|
logger.exception(f"Error deleting pages from document {pair.root_doc.id}")
|
||||||
|
|
||||||
return "OK"
|
return "OK"
|
||||||
|
|
||||||
@@ -989,7 +986,7 @@ def edit_pdf(
|
|||||||
group(consume_tasks).delay()
|
group(consume_tasks).delay()
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.exception(f"Error editing document {pair.root_doc.id}: {e}")
|
logger.exception(f"Error editing document {pair.root_doc.id}")
|
||||||
raise ValueError(
|
raise ValueError(
|
||||||
f"An error occurred while editing the document: {e}",
|
f"An error occurred while editing the document: {e}",
|
||||||
) from e
|
) from e
|
||||||
@@ -1100,7 +1097,7 @@ def remove_password(
|
|||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"Error removing password from document {pair.root_doc.id}: {e}",
|
f"Error removing password from document {pair.root_doc.id}",
|
||||||
)
|
)
|
||||||
raise ValueError(
|
raise ValueError(
|
||||||
f"An error occurred while removing the password: {e}",
|
f"An error occurred while removing the password: {e}",
|
||||||
|
|||||||
@@ -69,8 +69,8 @@ def load_classifier(*, raise_exception: bool = False) -> DocumentClassifier | No
|
|||||||
Path(settings.MODEL_FILE).unlink()
|
Path(settings.MODEL_FILE).unlink()
|
||||||
classifier = None
|
classifier = None
|
||||||
if raise_exception:
|
if raise_exception:
|
||||||
raise e
|
raise
|
||||||
except ClassifierModelCorruptError as e:
|
except ClassifierModelCorruptError:
|
||||||
# there's something wrong with the model file.
|
# there's something wrong with the model file.
|
||||||
logger.exception(
|
logger.exception(
|
||||||
"Unrecoverable error while loading document "
|
"Unrecoverable error while loading document "
|
||||||
@@ -79,17 +79,17 @@ def load_classifier(*, raise_exception: bool = False) -> DocumentClassifier | No
|
|||||||
Path(settings.MODEL_FILE).unlink()
|
Path(settings.MODEL_FILE).unlink()
|
||||||
classifier = None
|
classifier = None
|
||||||
if raise_exception:
|
if raise_exception:
|
||||||
raise e
|
raise
|
||||||
except OSError as e:
|
except OSError:
|
||||||
logger.exception("IO error while loading document classification model")
|
logger.exception("IO error while loading document classification model")
|
||||||
classifier = None
|
classifier = None
|
||||||
if raise_exception:
|
if raise_exception:
|
||||||
raise e
|
raise
|
||||||
except Exception as e: # pragma: no cover
|
except Exception: # pragma: no cover
|
||||||
logger.exception("Unknown error while loading document classification model")
|
logger.exception("Unknown error while loading document classification model")
|
||||||
classifier = None
|
classifier = None
|
||||||
if raise_exception:
|
if raise_exception:
|
||||||
raise e
|
raise
|
||||||
|
|
||||||
return classifier
|
return classifier
|
||||||
|
|
||||||
|
|||||||
@@ -216,7 +216,7 @@ class ConsumerPluginMixin:
|
|||||||
current_progress,
|
current_progress,
|
||||||
max_progress,
|
max_progress,
|
||||||
document_id=document_id,
|
document_id=document_id,
|
||||||
owner_id=self.metadata.owner_id if self.metadata.owner_id else None,
|
owner_id=self.metadata.owner_id or None,
|
||||||
users_can_view=(self.metadata.view_users or [])
|
users_can_view=(self.metadata.view_users or [])
|
||||||
+ (self.metadata.change_users or []),
|
+ (self.metadata.change_users or []),
|
||||||
groups_can_view=(self.metadata.view_groups or [])
|
groups_can_view=(self.metadata.view_groups or [])
|
||||||
@@ -674,9 +674,7 @@ class ConsumerPlugin(
|
|||||||
document=document,
|
document=document,
|
||||||
logging_group=self.logging_group,
|
logging_group=self.logging_group,
|
||||||
classifier=classifier,
|
classifier=classifier,
|
||||||
original_file=self.unmodified_original
|
original_file=self.unmodified_original or self.working_copy,
|
||||||
if self.unmodified_original
|
|
||||||
else self.working_copy,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
# After everything is in the database, copy the files into
|
# After everything is in the database, copy the files into
|
||||||
@@ -849,7 +847,7 @@ class ConsumerPlugin(
|
|||||||
else:
|
else:
|
||||||
stats = Path(self.input_doc.original_file).stat()
|
stats = Path(self.input_doc.original_file).stat()
|
||||||
create_date = timezone.make_aware(
|
create_date = timezone.make_aware(
|
||||||
datetime.datetime.fromtimestamp(stats.st_mtime),
|
datetime.datetime.fromtimestamp(stats.st_mtime), # noqa: DTZ006 - make_aware() requires a naive datetime
|
||||||
)
|
)
|
||||||
self.log.debug(f"Creation date from st_mtime: {create_date}")
|
self.log.debug(f"Creation date from st_mtime: {create_date}")
|
||||||
|
|
||||||
@@ -963,7 +961,7 @@ class ConsumerPlugin(
|
|||||||
try:
|
try:
|
||||||
copy_basic_file_stats(source, target)
|
copy_basic_file_stats(source, target)
|
||||||
except Exception: # pragma: no cover
|
except Exception: # pragma: no cover
|
||||||
pass
|
self.log.debug("Unable to copy file stats from %s to %s", source, target)
|
||||||
|
|
||||||
|
|
||||||
class ConsumerPreflightPlugin(
|
class ConsumerPreflightPlugin(
|
||||||
|
|||||||
@@ -78,7 +78,9 @@ class CollatePlugin(NoCleanupPluginMixin, NoSetupPluginMixin, ConsumeTaskPlugin)
|
|||||||
stats = staging.stat()
|
stats = staging.stat()
|
||||||
# if the file is older than the timeout, we don't consider
|
# if the file is older than the timeout, we don't consider
|
||||||
# it valid
|
# it valid
|
||||||
if (dt.datetime.now().timestamp() - stats.st_mtime) > TIMEOUT_SECONDS:
|
if (
|
||||||
|
dt.datetime.now(tz=dt.UTC).timestamp() - stats.st_mtime
|
||||||
|
) > TIMEOUT_SECONDS:
|
||||||
logger.warning("Outdated double sided staging file exists, deleting it")
|
logger.warning("Outdated double sided staging file exists, deleting it")
|
||||||
staging.unlink()
|
staging.unlink()
|
||||||
else:
|
else:
|
||||||
@@ -134,7 +136,7 @@ class CollatePlugin(NoCleanupPluginMixin, NoSetupPluginMixin, ConsumeTaskPlugin)
|
|||||||
shutil.move(pdf_file, staging)
|
shutil.move(pdf_file, staging)
|
||||||
# update access to modification time so we know if the file
|
# update access to modification time so we know if the file
|
||||||
# is outdated when another file gets uploaded
|
# is outdated when another file gets uploaded
|
||||||
timestamp = dt.datetime.now().timestamp()
|
timestamp = dt.datetime.now(tz=dt.UTC).timestamp()
|
||||||
os.utime(staging, (timestamp, timestamp))
|
os.utime(staging, (timestamp, timestamp))
|
||||||
logger.info(
|
logger.info(
|
||||||
"Got scan with odd numbered pages of double-sided scan, moved it to %s",
|
"Got scan with odd numbered pages of double-sided scan, moved it to %s",
|
||||||
|
|||||||
@@ -734,7 +734,7 @@ class CustomFieldQueryParser:
|
|||||||
)
|
)
|
||||||
|
|
||||||
# Check if any of the requested IDs are missing.
|
# Check if any of the requested IDs are missing.
|
||||||
missing_ids = set(value) - set(link.document_id for link in links)
|
missing_ids = set(value) - {link.document_id for link in links}
|
||||||
if missing_ids:
|
if missing_ids:
|
||||||
# The result should be an empty set in this case.
|
# The result should be an empty set in this case.
|
||||||
return Q(id__in=[])
|
return Q(id__in=[])
|
||||||
|
|||||||
@@ -631,23 +631,25 @@ class Command(BaseCommand):
|
|||||||
):
|
):
|
||||||
# Process each change
|
# Process each change
|
||||||
for change_type, path in changes:
|
for change_type, path in changes:
|
||||||
path = Path(path).resolve()
|
resolved_path = Path(path).resolve()
|
||||||
if change_type == Change.deleted:
|
if change_type == Change.deleted:
|
||||||
# Consumed (or otherwise removed); a later file
|
# Consumed (or otherwise removed); a later file
|
||||||
# reusing this name must not be skipped as
|
# reusing this name must not be skipped as
|
||||||
# already-queued.
|
# already-queued.
|
||||||
queued.discard(path)
|
queued.discard(resolved_path)
|
||||||
if not path.is_file():
|
if not resolved_path.is_file():
|
||||||
continue
|
continue
|
||||||
if path in queued:
|
if resolved_path in queued:
|
||||||
# Already queued and awaiting consumption; a stray
|
# Already queued and awaiting consumption; a stray
|
||||||
# event (NAS metadata touch, AV scan, etc.) while
|
# event (NAS metadata touch, AV scan, etc.) while
|
||||||
# the file sits on disk mid-consumption must not
|
# the file sits on disk mid-consumption must not
|
||||||
# cause it to be queued a second time (GH #13511).
|
# cause it to be queued a second time (GH #13511).
|
||||||
logger.debug(f"Ignoring event for queued file: {path}")
|
logger.debug(
|
||||||
|
f"Ignoring event for queued file: {resolved_path}",
|
||||||
|
)
|
||||||
continue
|
continue
|
||||||
logger.debug(f"Event: {change_type.name} for {path}")
|
logger.debug(f"Event: {change_type.name} for {resolved_path}")
|
||||||
tracker.track(path, change_type)
|
tracker.track(resolved_path, change_type)
|
||||||
|
|
||||||
# Check for stable files
|
# Check for stable files
|
||||||
for stable_path in tracker.get_stable_files():
|
for stable_path in tracker.get_stable_files():
|
||||||
|
|||||||
@@ -30,6 +30,10 @@ if TYPE_CHECKING:
|
|||||||
logger = logging.getLogger("paperless.matching")
|
logger = logging.getLogger("paperless.matching")
|
||||||
|
|
||||||
|
|
||||||
|
class UnsupportedWorkflowTriggerTypeError(Exception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
def log_reason(
|
def log_reason(
|
||||||
matching_model: MatchingModel | WorkflowTrigger,
|
matching_model: MatchingModel | WorkflowTrigger,
|
||||||
document: Document,
|
document: Document,
|
||||||
@@ -691,7 +695,9 @@ def document_matches_workflow(
|
|||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
# New trigger types need to be explicitly checked above
|
# New trigger types need to be explicitly checked above
|
||||||
raise Exception(f"Trigger type {trigger_type} not yet supported")
|
raise UnsupportedWorkflowTriggerTypeError(
|
||||||
|
f"Trigger type {trigger_type} not yet supported",
|
||||||
|
)
|
||||||
|
|
||||||
if trigger_matched:
|
if trigger_matched:
|
||||||
logger.info(f"Document matched {trigger} from {workflow}")
|
logger.info(f"Document matched {trigger} from {workflow}")
|
||||||
|
|||||||
@@ -377,7 +377,7 @@ class Document(SoftDeleteModel, ModelWithOwner): # type: ignore[django-manager-
|
|||||||
from documents.versioning import versions_newest_first
|
from documents.versioning import versions_newest_first
|
||||||
|
|
||||||
if hasattr(self, "effective_content"):
|
if hasattr(self, "effective_content"):
|
||||||
return getattr(self, "effective_content")
|
return self.effective_content
|
||||||
|
|
||||||
if self.root_document_id is not None or self.pk is None:
|
if self.root_document_id is not None or self.pk is None:
|
||||||
return self.content
|
return self.content
|
||||||
|
|||||||
@@ -41,7 +41,7 @@ def get_default_file_extension(mime_type: str) -> str:
|
|||||||
return supported[mime_type]
|
return supported[mime_type]
|
||||||
|
|
||||||
ext = mimetypes.guess_extension(mime_type)
|
ext = mimetypes.guess_extension(mime_type)
|
||||||
return ext if ext else ""
|
return ext or ""
|
||||||
|
|
||||||
|
|
||||||
def is_file_ext_supported(ext: str) -> bool:
|
def is_file_ext_supported(ext: str) -> bool:
|
||||||
|
|||||||
@@ -173,184 +173,6 @@ def set_permissions_for_object(
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
def _resolve_permissions(codenames: set[str], ctype: ContentType) -> list[Permission]:
|
|
||||||
"""
|
|
||||||
Resolves `codenames` to Permission rows, raising like the single-object
|
|
||||||
assign_perm() this bulk path replaces does (via a `.get()` internally)
|
|
||||||
if any codename doesn't exist -- e.g. a client-supplied action name that
|
|
||||||
was never validated (BulkEditObjectsSerializer._validate_permissions
|
|
||||||
calls validate_set_permissions() only for its side-effecting id checks
|
|
||||||
and discards the filtered dict it returns, so an unrecognized action key
|
|
||||||
reaches this function as-is). A plain `.filter()` with no existence
|
|
||||||
check would otherwise silently build zero rows and no-op instead of
|
|
||||||
reporting the bad input.
|
|
||||||
"""
|
|
||||||
permission_objs = list(
|
|
||||||
Permission.objects.filter(content_type=ctype, codename__in=codenames),
|
|
||||||
)
|
|
||||||
missing = codenames - {p.codename for p in permission_objs}
|
|
||||||
if missing:
|
|
||||||
raise Permission.DoesNotExist(
|
|
||||||
f"Permission matching query does not exist for codename(s): "
|
|
||||||
f"{', '.join(sorted(missing))}",
|
|
||||||
)
|
|
||||||
return permission_objs
|
|
||||||
|
|
||||||
|
|
||||||
# Target number of permission rows to build in Python before handing them to
|
|
||||||
# bulk_create -- keeps peak memory bounded for a large "apply to all" call,
|
|
||||||
# independent of bulk_create's own batch_size (which only caps the size of
|
|
||||||
# each INSERT statement, not how many row objects exist in memory at once).
|
|
||||||
_PERMISSION_ROW_CHUNK_SIZE = 5000
|
|
||||||
|
|
||||||
|
|
||||||
def _apply_bulk_permission_entry(
|
|
||||||
*,
|
|
||||||
perm_model: type[UserObjectPermission] | type[GroupObjectPermission],
|
|
||||||
identity_model: type[User] | type[Group],
|
|
||||||
identity_field: str,
|
|
||||||
ids: list[int],
|
|
||||||
codename: str,
|
|
||||||
permission_objs: list[Permission],
|
|
||||||
ctype: ContentType,
|
|
||||||
object_pks: list[str],
|
|
||||||
merge: bool,
|
|
||||||
) -> None:
|
|
||||||
# Only the ids are needed to build permission rows (via `<field>_id=`),
|
|
||||||
# so avoid fetching full User/Group rows for identities that may not
|
|
||||||
# even end up being granted anything new.
|
|
||||||
add_ids = set(
|
|
||||||
identity_model.objects.filter(id__in=ids).values_list("id", flat=True),
|
|
||||||
)
|
|
||||||
|
|
||||||
if not merge:
|
|
||||||
existing_ids = set(
|
|
||||||
perm_model.objects.filter(
|
|
||||||
content_type=ctype,
|
|
||||||
object_pk__in=object_pks,
|
|
||||||
permission__codename=codename,
|
|
||||||
)
|
|
||||||
.values_list(f"{identity_field}_id", flat=True)
|
|
||||||
.distinct(),
|
|
||||||
)
|
|
||||||
remove_ids = existing_ids - add_ids
|
|
||||||
if remove_ids:
|
|
||||||
perm_model.objects.filter(
|
|
||||||
content_type=ctype,
|
|
||||||
object_pk__in=object_pks,
|
|
||||||
permission__codename=codename,
|
|
||||||
**{f"{identity_field}_id__in": remove_ids},
|
|
||||||
).delete()
|
|
||||||
|
|
||||||
if not add_ids:
|
|
||||||
return
|
|
||||||
|
|
||||||
rows_per_pk = len(permission_objs) * len(add_ids)
|
|
||||||
pks_per_chunk = max(1, _PERMISSION_ROW_CHUNK_SIZE // rows_per_pk)
|
|
||||||
for start in range(0, len(object_pks), pks_per_chunk):
|
|
||||||
pk_chunk = object_pks[start : start + pks_per_chunk]
|
|
||||||
rows = [
|
|
||||||
perm_model(
|
|
||||||
content_type=ctype,
|
|
||||||
object_pk=pk,
|
|
||||||
permission=permission_obj,
|
|
||||||
**{f"{identity_field}_id": identity_id},
|
|
||||||
)
|
|
||||||
for permission_obj in permission_objs
|
|
||||||
for pk in pk_chunk
|
|
||||||
for identity_id in add_ids
|
|
||||||
]
|
|
||||||
# ignore_conflicts skips only rows that already exist as an exact
|
|
||||||
# (identity, permission, object) match -- the same de-dup the
|
|
||||||
# underlying (user|group, permission, object_pk) unique constraint
|
|
||||||
# already enforces for the single-object assign_perm() this
|
|
||||||
# replaces, so it doesn't change what counts as "already granted".
|
|
||||||
# batch_size caps how many rows go into a single INSERT so a huge
|
|
||||||
# chunk doesn't build one enormous statement.
|
|
||||||
perm_model.objects.bulk_create(rows, ignore_conflicts=True, batch_size=1000)
|
|
||||||
|
|
||||||
|
|
||||||
def set_permissions_for_objects(
|
|
||||||
permissions: dict,
|
|
||||||
model: type[Model],
|
|
||||||
pks: QuerySet | list,
|
|
||||||
*,
|
|
||||||
merge: bool = False,
|
|
||||||
) -> None:
|
|
||||||
"""
|
|
||||||
Bulk equivalent of set_permissions_for_object: applies the same
|
|
||||||
permission changes to every object identified by `pks` at once.
|
|
||||||
|
|
||||||
Takes a model + pks (rather than model instances) deliberately -- the
|
|
||||||
permission rows built below only ever need `pk`, `content_type`, and
|
|
||||||
identity ids, so callers shouldn't have to fetch full rows (with every
|
|
||||||
other field) just to hand them to this function.
|
|
||||||
|
|
||||||
Deliberately does not use guardian's queryset/list-aware assign_perm:
|
|
||||||
passing a list as the object routes to bulk_assign_perm, which skips
|
|
||||||
creating a direct permission row for anyone who already has the
|
|
||||||
permission via ANY group membership (it checks
|
|
||||||
ObjectPermissionChecker.has_perm, which is group-inheritance-aware) --
|
|
||||||
unlike the single-object assign_perm this replaces, which always
|
|
||||||
ensures a direct row via get_or_create regardless of group-derived
|
|
||||||
access. Losing that guarantee would mean a later revocation of the
|
|
||||||
group's grant silently strips access an admin explicitly asked to be
|
|
||||||
direct. Bulk-creating rows straight against the permission models
|
|
||||||
instead (see _apply_bulk_permission_entry) preserves the original
|
|
||||||
always-create-a-direct-row semantics while still batching every object
|
|
||||||
and every identity into one query per action, rather than one query per
|
|
||||||
(object, user) pair.
|
|
||||||
"""
|
|
||||||
object_pks = [str(pk) for pk in pks]
|
|
||||||
if not object_pks: # pragma: no cover
|
|
||||||
return
|
|
||||||
|
|
||||||
model_name = model.__name__.lower()
|
|
||||||
ctype = ContentType.objects.get_for_model(model)
|
|
||||||
|
|
||||||
for action, entry in permissions.items():
|
|
||||||
codename = f"{action}_{model_name}"
|
|
||||||
implied_codenames = {codename}
|
|
||||||
if action == "change":
|
|
||||||
# change gives view too
|
|
||||||
implied_codenames.add(f"view_{model_name}")
|
|
||||||
|
|
||||||
# Resolved once per action (not once per users/groups branch) and
|
|
||||||
# shared between both below -- also where an unrecognized action
|
|
||||||
# name (see _resolve_permissions) is caught.
|
|
||||||
permission_objs = (
|
|
||||||
_resolve_permissions(implied_codenames, ctype)
|
|
||||||
if "users" in entry or "groups" in entry
|
|
||||||
else []
|
|
||||||
)
|
|
||||||
|
|
||||||
if "users" in entry:
|
|
||||||
_apply_bulk_permission_entry(
|
|
||||||
perm_model=UserObjectPermission,
|
|
||||||
identity_model=User,
|
|
||||||
identity_field="user",
|
|
||||||
ids=entry["users"],
|
|
||||||
codename=codename,
|
|
||||||
permission_objs=permission_objs,
|
|
||||||
ctype=ctype,
|
|
||||||
object_pks=object_pks,
|
|
||||||
merge=merge,
|
|
||||||
)
|
|
||||||
|
|
||||||
if "groups" in entry:
|
|
||||||
_apply_bulk_permission_entry(
|
|
||||||
perm_model=GroupObjectPermission,
|
|
||||||
identity_model=Group,
|
|
||||||
identity_field="group",
|
|
||||||
ids=entry["groups"],
|
|
||||||
codename=codename,
|
|
||||||
permission_objs=permission_objs,
|
|
||||||
ctype=ctype,
|
|
||||||
object_pks=object_pks,
|
|
||||||
merge=merge,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def permitted_object_ids(
|
def permitted_object_ids(
|
||||||
user: User | None,
|
user: User | None,
|
||||||
model: type[Model],
|
model: type[Model],
|
||||||
|
|||||||
@@ -43,8 +43,8 @@ def _discover_parser_class() -> type[DateParserPluginBase]:
|
|||||||
valid_plugins.append(ep)
|
valid_plugins.append(ep)
|
||||||
else:
|
else:
|
||||||
logger.warning(f"Plugin {ep.name} does not subclass DateParser.")
|
logger.warning(f"Plugin {ep.name} does not subclass DateParser.")
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(f"Unable to load date parser plugin {ep.name}: {e}")
|
logger.exception(f"Unable to load date parser plugin {ep.name}")
|
||||||
|
|
||||||
if not valid_plugins:
|
if not valid_plugins:
|
||||||
return RegexDateParserPlugin
|
return RegexDateParserPlugin
|
||||||
|
|||||||
@@ -91,8 +91,8 @@ class DateParserPluginBase(ABC):
|
|||||||
},
|
},
|
||||||
locales=self.config.languages,
|
locales=self.config.languages,
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(f"Error while parsing date string '{date_string}': {e}")
|
logger.exception(f"Error while parsing date string '{date_string}'")
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def _filter_date(
|
def _filter_date(
|
||||||
|
|||||||
@@ -59,11 +59,10 @@ def safe_regex_match(pattern: str, text: str, *, flags: int = 0):
|
|||||||
try:
|
try:
|
||||||
validate_regex_pattern(pattern)
|
validate_regex_pattern(pattern)
|
||||||
compiled = regex.compile(pattern, flags=flags)
|
compiled = regex.compile(pattern, flags=flags)
|
||||||
except (regex.error, ValueError) as exc:
|
except (regex.error, ValueError):
|
||||||
logger.exception(
|
logger.exception(
|
||||||
"Error while processing regular expression %s: %s",
|
"Error while processing regular expression %s",
|
||||||
textwrap.shorten(pattern, width=80, placeholder="…"),
|
textwrap.shorten(pattern, width=80, placeholder="…"),
|
||||||
exc,
|
|
||||||
)
|
)
|
||||||
return None
|
return None
|
||||||
|
|
||||||
@@ -86,11 +85,10 @@ def safe_regex_sub(pattern: str, repl: str, text: str, *, flags: int = 0) -> str
|
|||||||
try:
|
try:
|
||||||
validate_regex_pattern(pattern)
|
validate_regex_pattern(pattern)
|
||||||
compiled = regex.compile(pattern, flags=flags)
|
compiled = regex.compile(pattern, flags=flags)
|
||||||
except (regex.error, ValueError) as exc:
|
except (regex.error, ValueError):
|
||||||
logger.exception(
|
logger.exception(
|
||||||
"Error while processing regular expression %s: %s",
|
"Error while processing regular expression %s",
|
||||||
textwrap.shorten(pattern, width=80, placeholder="…"),
|
textwrap.shorten(pattern, width=80, placeholder="…"),
|
||||||
exc,
|
|
||||||
)
|
)
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
|||||||
@@ -1142,7 +1142,7 @@ def get_backend() -> TantivyBackend:
|
|||||||
Returns:
|
Returns:
|
||||||
Thread-safe singleton TantivyBackend instance
|
Thread-safe singleton TantivyBackend instance
|
||||||
"""
|
"""
|
||||||
global _backend, _backend_path
|
global _backend, _backend_path # noqa: PLW0603 - module-level singleton, no class to hold this state
|
||||||
|
|
||||||
current_path: Path = settings.INDEX_DIR
|
current_path: Path = settings.INDEX_DIR
|
||||||
|
|
||||||
@@ -1173,7 +1173,7 @@ def reset_backend() -> None:
|
|||||||
Forces creation of a new backend instance on the next get_backend() call.
|
Forces creation of a new backend instance on the next get_backend() call.
|
||||||
Used for test isolation and when switching between different index directories.
|
Used for test isolation and when switching between different index directories.
|
||||||
"""
|
"""
|
||||||
global _backend, _backend_path
|
global _backend, _backend_path # noqa: PLW0603 - module-level singleton, no class to hold this state
|
||||||
|
|
||||||
with _backend_lock:
|
with _backend_lock:
|
||||||
if _backend is not None:
|
if _backend is not None:
|
||||||
|
|||||||
@@ -240,7 +240,7 @@ def parse_user_query(
|
|||||||
DEFAULT_SEARCH_FIELDS,
|
DEFAULT_SEARCH_FIELDS,
|
||||||
field_boosts=_FIELD_BOOSTS,
|
field_boosts=_FIELD_BOOSTS,
|
||||||
# (prefix=True, distance=1, transposition_cost_one=True) — edit-distance fuzziness
|
# (prefix=True, distance=1, transposition_cost_one=True) — edit-distance fuzziness
|
||||||
fuzzy_fields={f: (True, 1, True) for f in DEFAULT_SEARCH_FIELDS},
|
fuzzy_fields=dict.fromkeys(DEFAULT_SEARCH_FIELDS, (True, 1, True)),
|
||||||
)
|
)
|
||||||
# 0.1 boost keeps fuzzy hits ranked below exact matches (intentional)
|
# 0.1 boost keeps fuzzy hits ranked below exact matches (intentional)
|
||||||
clauses.append((tantivy.Occur.Should, tantivy.Query.boost_query(fuzzy, 0.1)))
|
clauses.append((tantivy.Occur.Should, tantivy.Query.boost_query(fuzzy, 0.1)))
|
||||||
|
|||||||
@@ -433,7 +433,7 @@ class OwnedObjectSerializer(
|
|||||||
return set()
|
return set()
|
||||||
|
|
||||||
ctype = ContentType.objects.get_for_model(first_obj)
|
ctype = ContentType.objects.get_for_model(first_obj)
|
||||||
object_pks = list(obj.pk for obj in objects)
|
object_pks = [obj.pk for obj in objects]
|
||||||
pk_type = type(first_obj.pk)
|
pk_type = type(first_obj.pk)
|
||||||
|
|
||||||
def get_pks_for_permission_type(model):
|
def get_pks_for_permission_type(model):
|
||||||
@@ -727,7 +727,7 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
|
|||||||
self.instance.clean()
|
self.instance.clean()
|
||||||
except ValidationError as e:
|
except ValidationError as e:
|
||||||
logger.debug("Tag parent validation failed: %s", e)
|
logger.debug("Tag parent validation failed: %s", e)
|
||||||
raise e
|
raise
|
||||||
finally:
|
finally:
|
||||||
self.instance.tn_parent = original_parent
|
self.instance.tn_parent = original_parent
|
||||||
else:
|
else:
|
||||||
@@ -737,7 +737,7 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
|
|||||||
temp.clean()
|
temp.clean()
|
||||||
except ValidationError as e:
|
except ValidationError as e:
|
||||||
logger.debug("Tag parent validation failed: %s", e)
|
logger.debug("Tag parent validation failed: %s", e)
|
||||||
raise e
|
raise
|
||||||
|
|
||||||
return super().validate(attrs)
|
return super().validate(attrs)
|
||||||
|
|
||||||
@@ -1147,7 +1147,7 @@ class DocumentSerializer(
|
|||||||
def to_representation(self, instance):
|
def to_representation(self, instance):
|
||||||
doc = super().to_representation(instance)
|
doc = super().to_representation(instance)
|
||||||
if "content" in self.fields and hasattr(instance, "effective_content"):
|
if "content" in self.fields and hasattr(instance, "effective_content"):
|
||||||
doc["content"] = getattr(instance, "effective_content") or ""
|
doc["content"] = instance.effective_content or ""
|
||||||
if self.truncate_content and "content" in self.fields:
|
if self.truncate_content and "content" in self.fields:
|
||||||
doc["content"] = doc.get("content")[0:550]
|
doc["content"] = doc.get("content")[0:550]
|
||||||
return doc
|
return doc
|
||||||
@@ -1857,8 +1857,8 @@ class BulkEditSerializer(
|
|||||||
if isinstance(custom_fields, dict):
|
if isinstance(custom_fields, dict):
|
||||||
try:
|
try:
|
||||||
ids = [int(i[0]) for i in custom_fields.items()]
|
ids = [int(i[0]) for i in custom_fields.items()]
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(f"Error validating custom fields: {e}")
|
logger.exception("Error validating custom fields")
|
||||||
raise serializers.ValidationError(
|
raise serializers.ValidationError(
|
||||||
f"{name} must be a list of integers or a dict of id:value pairs, see the log for details",
|
f"{name} must be a list of integers or a dict of id:value pairs, see the log for details",
|
||||||
)
|
)
|
||||||
@@ -2056,13 +2056,12 @@ class BulkEditSerializer(
|
|||||||
for doc in docs:
|
for doc in docs:
|
||||||
if "-" in doc:
|
if "-" in doc:
|
||||||
pages.append(
|
pages.append(
|
||||||
[
|
list(
|
||||||
x
|
range(
|
||||||
for x in range(
|
|
||||||
int(doc.split("-")[0]),
|
int(doc.split("-")[0]),
|
||||||
int(doc.split("-")[1]) + 1,
|
int(doc.split("-")[1]) + 1,
|
||||||
)
|
),
|
||||||
],
|
),
|
||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
pages.append([int(doc)])
|
pages.append([int(doc)])
|
||||||
@@ -2923,7 +2922,7 @@ class ShareLinkBundleSerializer(OwnedObjectSerializer):
|
|||||||
return share_link_bundle
|
return share_link_bundle
|
||||||
|
|
||||||
def get_document_count(self, obj: ShareLinkBundle) -> int:
|
def get_document_count(self, obj: ShareLinkBundle) -> int:
|
||||||
return getattr(obj, "document_total") or obj.documents.count()
|
return obj.document_total or obj.documents.count()
|
||||||
|
|
||||||
|
|
||||||
class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):
|
class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):
|
||||||
|
|||||||
@@ -636,7 +636,7 @@ def update_filename_and_move_files(
|
|||||||
# so this is not the end of the world.
|
# so this is not the end of the world.
|
||||||
# B: if moving the original file failed, nothing has changed
|
# B: if moving the original file failed, nothing has changed
|
||||||
# anyway.
|
# anyway.
|
||||||
pass
|
logger.exception("Error reverting document changes")
|
||||||
|
|
||||||
# restore old values on the instance
|
# restore old values on the instance
|
||||||
instance.filename = old_filename
|
instance.filename = old_filename
|
||||||
@@ -1101,10 +1101,11 @@ def _extract_input_data(
|
|||||||
if v is None or k.startswith("_"):
|
if v is None or k.startswith("_"):
|
||||||
continue
|
continue
|
||||||
if isinstance(v, datetime.date):
|
if isinstance(v, datetime.date):
|
||||||
v = v.isoformat()
|
override_dict[k] = v.isoformat()
|
||||||
elif isinstance(v, Path):
|
elif isinstance(v, Path):
|
||||||
v = str(v)
|
override_dict[k] = str(v)
|
||||||
override_dict[k] = v
|
else:
|
||||||
|
override_dict[k] = v
|
||||||
if override_dict:
|
if override_dict:
|
||||||
data["overrides"] = override_dict
|
data["overrides"] = override_dict
|
||||||
return data
|
return data
|
||||||
|
|||||||
@@ -217,9 +217,9 @@ def consume_file(
|
|||||||
overrides.filename or input_doc.original_file.name,
|
overrides.filename or input_doc.original_file.name,
|
||||||
self.request.id,
|
self.request.id,
|
||||||
) as status_mgr,
|
) as status_mgr,
|
||||||
TemporaryDirectory(dir=settings.SCRATCH_DIR) as tmp_dir,
|
TemporaryDirectory(dir=settings.SCRATCH_DIR) as tmp_dir_name,
|
||||||
):
|
):
|
||||||
tmp_dir = Path(tmp_dir)
|
tmp_dir = Path(tmp_dir_name)
|
||||||
msg = None
|
msg = None
|
||||||
for plugin_class in plugins:
|
for plugin_class in plugins:
|
||||||
plugin_name = plugin_class.NAME
|
plugin_name = plugin_class.NAME
|
||||||
@@ -261,7 +261,7 @@ def consume_file(
|
|||||||
)
|
)
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.exception(f"{plugin_name} failed: {e}")
|
logger.exception(f"{plugin_name} failed")
|
||||||
status_mgr.send_progress(
|
status_mgr.send_progress(
|
||||||
ProgressStatusOptions.FAILED,
|
ProgressStatusOptions.FAILED,
|
||||||
f"{e}",
|
f"{e}",
|
||||||
@@ -495,8 +495,8 @@ def empty_trash(doc_ids=None) -> None:
|
|||||||
content_type=ContentType.objects.get_for_model(Document),
|
content_type=ContentType.objects.get_for_model(Document),
|
||||||
object_id__in=deleted_document_ids,
|
object_id__in=deleted_document_ids,
|
||||||
).delete()
|
).delete()
|
||||||
except Exception as e: # pragma: no cover
|
except Exception: # pragma: no cover
|
||||||
logger.exception(f"Error while emptying trash: {e}")
|
logger.exception("Error while emptying trash")
|
||||||
finally:
|
finally:
|
||||||
models.signals.post_delete.disconnect(
|
models.signals.post_delete.disconnect(
|
||||||
cleanup_document_deletion,
|
cleanup_document_deletion,
|
||||||
@@ -832,9 +832,8 @@ def build_share_link_bundle(bundle_id: int) -> None:
|
|||||||
logger.info("Built share link bundle %s", bundle.pk)
|
logger.info("Built share link bundle %s", bundle.pk)
|
||||||
except Exception as exc:
|
except Exception as exc:
|
||||||
logger.exception(
|
logger.exception(
|
||||||
"Failed to build share link bundle %s: %s",
|
"Failed to build share link bundle %s",
|
||||||
bundle_id,
|
bundle_id,
|
||||||
exc,
|
|
||||||
)
|
)
|
||||||
bundle.status = ShareLinkBundle.Status.FAILED
|
bundle.status = ShareLinkBundle.Status.FAILED
|
||||||
bundle.last_error = {
|
bundle.last_error = {
|
||||||
|
|||||||
@@ -78,6 +78,10 @@ class PlaceholderString(str):
|
|||||||
def __ne__(self, other) -> bool:
|
def __ne__(self, other) -> bool:
|
||||||
return not self.__eq__(other)
|
return not self.__eq__(other)
|
||||||
|
|
||||||
|
def __hash__(self) -> int:
|
||||||
|
# Equal to both "-none-" and "none", so hash to a single canonical value
|
||||||
|
return hash("-none-")
|
||||||
|
|
||||||
|
|
||||||
NO_VALUE_PLACEHOLDER = PlaceholderString("-none-")
|
NO_VALUE_PLACEHOLDER = PlaceholderString("-none-")
|
||||||
|
|
||||||
|
|||||||
@@ -138,9 +138,9 @@ def parse_w_workflow_placeholders(
|
|||||||
|
|
||||||
# We're good!
|
# We're good!
|
||||||
return rendered_template
|
return rendered_template
|
||||||
except UndefinedError as e:
|
except UndefinedError:
|
||||||
# The undefined class logs this already for us
|
# The undefined class logs this already for us
|
||||||
raise e
|
raise
|
||||||
except TemplateSyntaxError as e:
|
except TemplateSyntaxError as e:
|
||||||
logger.warning(f"Template syntax error in title generation: {e}")
|
logger.warning(f"Template syntax error in title generation: {e}")
|
||||||
except SecurityError as e:
|
except SecurityError as e:
|
||||||
@@ -150,5 +150,5 @@ def parse_w_workflow_placeholders(
|
|||||||
logger.warning(
|
logger.warning(
|
||||||
f"Invalid title format '{text}', workflow not applied: {e}",
|
f"Invalid title format '{text}', workflow not applied: {e}",
|
||||||
)
|
)
|
||||||
raise e
|
raise
|
||||||
return None
|
return None
|
||||||
|
|||||||
@@ -296,7 +296,7 @@ class TestRegexDateParser:
|
|||||||
|
|
||||||
# simulate parse failure for malformed input
|
# simulate parse failure for malformed input
|
||||||
if "99/99/9999" in date_string or "bad date" in date_string:
|
if "99/99/9999" in date_string or "bad date" in date_string:
|
||||||
raise Exception("parse failed for malformed date")
|
raise Exception("parse failed for malformed date") # noqa: TRY002 - simulates a generic parser failure
|
||||||
|
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
|||||||
@@ -57,13 +57,13 @@ class MultiprocessCommand(PaperlessCommand):
|
|||||||
|
|
||||||
def handle(self, *args, **options):
|
def handle(self, *args, **options):
|
||||||
items = list(range(5))
|
items = list(range(5))
|
||||||
results = []
|
results = list(
|
||||||
for result in self.process_parallel(
|
self.process_parallel(
|
||||||
_double_value,
|
_double_value,
|
||||||
items,
|
items,
|
||||||
description="Processing...",
|
description="Processing...",
|
||||||
):
|
),
|
||||||
results.append(result)
|
)
|
||||||
successes = sum(1 for r in results if r.success)
|
successes = sum(1 for r in results if r.success)
|
||||||
self.stdout.write(f"Successes: {successes}")
|
self.stdout.write(f"Successes: {successes}")
|
||||||
|
|
||||||
|
|||||||
@@ -66,7 +66,7 @@ class TestWriteBatchLockRetry:
|
|||||||
)
|
)
|
||||||
mock_sleep = mocker.patch(
|
mock_sleep = mocker.patch(
|
||||||
"documents.search._backend.time.sleep",
|
"documents.search._backend.time.sleep",
|
||||||
side_effect=lambda s: sleep_values.append(s),
|
side_effect=sleep_values.append,
|
||||||
)
|
)
|
||||||
|
|
||||||
# Should not raise — 4th attempt succeeds
|
# Should not raise — 4th attempt succeeds
|
||||||
@@ -111,7 +111,7 @@ class TestWriteBatchLockRetry:
|
|||||||
sleep_values: list[float] = []
|
sleep_values: list[float] = []
|
||||||
mocker.patch(
|
mocker.patch(
|
||||||
"documents.search._backend.time.sleep",
|
"documents.search._backend.time.sleep",
|
||||||
side_effect=lambda s: sleep_values.append(s),
|
side_effect=sleep_values.append,
|
||||||
)
|
)
|
||||||
for _ in range(50):
|
for _ in range(50):
|
||||||
sleep_values.clear()
|
sleep_values.clear()
|
||||||
|
|||||||
@@ -1003,8 +1003,8 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
|||||||
for correspondent in response.data[field]:
|
for correspondent in response.data[field]:
|
||||||
self.assertEqual(correspondent["document_count"], 0)
|
self.assertEqual(correspondent["document_count"], 0)
|
||||||
self.assertCountEqual(
|
self.assertCountEqual(
|
||||||
map(lambda c: c["id"], response.data[field]),
|
(c["id"] for c in response.data[field]),
|
||||||
map(lambda c: c["id"], Entity.objects.values("id")),
|
(c["id"] for c in Entity.objects.values("id")),
|
||||||
)
|
)
|
||||||
|
|
||||||
def test_api_selection_data(self) -> None:
|
def test_api_selection_data(self) -> None:
|
||||||
|
|||||||
@@ -2,13 +2,10 @@ import datetime
|
|||||||
import json
|
import json
|
||||||
from unittest import mock
|
from unittest import mock
|
||||||
|
|
||||||
from django.contrib.auth.models import Group
|
|
||||||
from django.contrib.auth.models import Permission
|
from django.contrib.auth.models import Permission
|
||||||
from django.contrib.auth.models import User
|
from django.contrib.auth.models import User
|
||||||
from django.test import override_settings
|
from django.test import override_settings
|
||||||
from guardian.shortcuts import assign_perm
|
from guardian.shortcuts import assign_perm
|
||||||
from guardian.shortcuts import get_groups_with_perms
|
|
||||||
from guardian.shortcuts import get_users_with_perms
|
|
||||||
from rest_framework import status
|
from rest_framework import status
|
||||||
from rest_framework.test import APITestCase
|
from rest_framework.test import APITestCase
|
||||||
|
|
||||||
@@ -818,47 +815,6 @@ class TestBulkEditObjects(APITestCase):
|
|||||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||||
self.assertEqual(StoragePath.objects.count(), 0)
|
self.assertEqual(StoragePath.objects.count(), 0)
|
||||||
|
|
||||||
def test_bulk_objects_set_permissions_batched_across_object_count(
|
|
||||||
self,
|
|
||||||
) -> None:
|
|
||||||
"""
|
|
||||||
GIVEN:
|
|
||||||
- Many tags are being bulk-edited to set permissions at once
|
|
||||||
WHEN:
|
|
||||||
- bulk_edit_objects API endpoint is called with set_permissions
|
|
||||||
operation over a small batch vs. a much larger one
|
|
||||||
THEN:
|
|
||||||
- Permissions are applied correctly at both scales
|
|
||||||
"""
|
|
||||||
group1 = Group.objects.create(name="perm-group")
|
|
||||||
permissions = {
|
|
||||||
"view": {"users": [self.user1.id, self.user2.id], "groups": [group1.id]},
|
|
||||||
"change": {"users": [self.user1.id], "groups": [group1.id]},
|
|
||||||
}
|
|
||||||
|
|
||||||
def run_with_n_tags(n: int) -> None:
|
|
||||||
tags = [Tag.objects.create(name=f"perm-tag-{n}-{i}") for i in range(n)]
|
|
||||||
response = self.client.post(
|
|
||||||
"/api/bulk_edit_objects/",
|
|
||||||
json.dumps(
|
|
||||||
{
|
|
||||||
"objects": [t.id for t in tags],
|
|
||||||
"object_type": "tags",
|
|
||||||
"operation": "set_permissions",
|
|
||||||
"permissions": permissions,
|
|
||||||
"merge": False,
|
|
||||||
},
|
|
||||||
),
|
|
||||||
content_type="application/json",
|
|
||||||
)
|
|
||||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
|
||||||
for tag in tags:
|
|
||||||
self.assertEqual(get_users_with_perms(tag).count(), 2)
|
|
||||||
self.assertEqual(get_groups_with_perms(tag).count(), 1)
|
|
||||||
|
|
||||||
run_with_n_tags(5)
|
|
||||||
run_with_n_tags(50)
|
|
||||||
|
|
||||||
def test_bulk_objects_delete_all_filtered(self) -> None:
|
def test_bulk_objects_delete_all_filtered(self) -> None:
|
||||||
"""
|
"""
|
||||||
GIVEN:
|
GIVEN:
|
||||||
|
|||||||
@@ -18,8 +18,8 @@ class MockOpenIDProvider:
|
|||||||
|
|
||||||
def get_brands(self):
|
def get_brands(self):
|
||||||
default_servers = [
|
default_servers = [
|
||||||
dict(id="yahoo", name="Yahoo", openid_url="http://me.yahoo.com"),
|
{"id": "yahoo", "name": "Yahoo", "openid_url": "http://me.yahoo.com"},
|
||||||
dict(id="hyves", name="Hyves", openid_url="http://hyves.nl"),
|
{"id": "hyves", "name": "Hyves", "openid_url": "http://hyves.nl"},
|
||||||
]
|
]
|
||||||
return default_servers
|
return default_servers
|
||||||
|
|
||||||
|
|||||||
@@ -205,12 +205,12 @@ class TestBarcode(
|
|||||||
- Barcode is detected on page 1 (zero indexed)
|
- Barcode is detected on page 1 (zero indexed)
|
||||||
"""
|
"""
|
||||||
|
|
||||||
for test_file in [
|
for test_filename in [
|
||||||
"patch-code-t-middle-reverse.pdf",
|
"patch-code-t-middle-reverse.pdf",
|
||||||
"patch-code-t-middle-distorted.pdf",
|
"patch-code-t-middle-distorted.pdf",
|
||||||
"patch-code-t-middle-fuzzy.pdf",
|
"patch-code-t-middle-fuzzy.pdf",
|
||||||
]:
|
]:
|
||||||
test_file = self.BARCODE_SAMPLE_DIR / test_file
|
test_file = self.BARCODE_SAMPLE_DIR / test_filename
|
||||||
|
|
||||||
with self.get_reader(test_file) as reader:
|
with self.get_reader(test_file) as reader:
|
||||||
reader.detect()
|
reader.detect()
|
||||||
|
|||||||
@@ -5,7 +5,6 @@ from unittest import mock
|
|||||||
|
|
||||||
import pikepdf
|
import pikepdf
|
||||||
from django.contrib.auth.models import Group
|
from django.contrib.auth.models import Group
|
||||||
from django.contrib.auth.models import Permission
|
|
||||||
from django.contrib.auth.models import User
|
from django.contrib.auth.models import User
|
||||||
from django.test import TestCase
|
from django.test import TestCase
|
||||||
from guardian.shortcuts import assign_perm
|
from guardian.shortcuts import assign_perm
|
||||||
@@ -20,7 +19,6 @@ from documents.models import Document
|
|||||||
from documents.models import DocumentType
|
from documents.models import DocumentType
|
||||||
from documents.models import StoragePath
|
from documents.models import StoragePath
|
||||||
from documents.models import Tag
|
from documents.models import Tag
|
||||||
from documents.permissions import set_permissions_for_objects
|
|
||||||
from documents.tests.utils import DirectoriesMixin
|
from documents.tests.utils import DirectoriesMixin
|
||||||
|
|
||||||
|
|
||||||
@@ -512,120 +510,6 @@ class TestBulkEdit(DirectoriesMixin, TestCase):
|
|||||||
)
|
)
|
||||||
self.assertEqual(groups_with_perms.count(), 2)
|
self.assertEqual(groups_with_perms.count(), 2)
|
||||||
|
|
||||||
@mock.patch("documents.tasks.bulk_update_documents.apply_async")
|
|
||||||
def test_set_permissions_batched_across_document_count(
|
|
||||||
self,
|
|
||||||
m,
|
|
||||||
) -> None:
|
|
||||||
"""
|
|
||||||
GIVEN:
|
|
||||||
- Many documents are being bulk-edited to set permissions at once
|
|
||||||
WHEN:
|
|
||||||
- set_permissions runs over a small batch vs. a much larger one
|
|
||||||
THEN:
|
|
||||||
- Permissions are applied correctly at both scales
|
|
||||||
"""
|
|
||||||
permissions = {
|
|
||||||
"view": {
|
|
||||||
"users": [self.user1.id, self.user2.id],
|
|
||||||
"groups": [self.group2.id],
|
|
||||||
},
|
|
||||||
"change": {
|
|
||||||
"users": [self.user1.id],
|
|
||||||
"groups": [self.group2.id],
|
|
||||||
},
|
|
||||||
}
|
|
||||||
|
|
||||||
def run_with_n_documents(n: int) -> None:
|
|
||||||
docs = [
|
|
||||||
Document.objects.create(checksum=f"perm-{n}-{i}", title=f"perm-{n}-{i}")
|
|
||||||
for i in range(n)
|
|
||||||
]
|
|
||||||
bulk_edit.set_permissions(
|
|
||||||
[doc.id for doc in docs],
|
|
||||||
set_permissions=permissions,
|
|
||||||
owner=self.owner,
|
|
||||||
merge=False,
|
|
||||||
)
|
|
||||||
for doc in docs:
|
|
||||||
self.assertEqual(get_users_with_perms(doc).count(), 2)
|
|
||||||
self.assertEqual(get_groups_with_perms(doc).count(), 1)
|
|
||||||
|
|
||||||
run_with_n_documents(5)
|
|
||||||
run_with_n_documents(50)
|
|
||||||
|
|
||||||
@mock.patch("documents.tasks.bulk_update_documents.apply_async")
|
|
||||||
def test_set_permissions_grants_direct_perm_even_if_already_granted_via_group(
|
|
||||||
self,
|
|
||||||
m,
|
|
||||||
) -> None:
|
|
||||||
"""
|
|
||||||
GIVEN:
|
|
||||||
- A user already has view access to a document via group
|
|
||||||
membership, with no direct grant of their own
|
|
||||||
WHEN:
|
|
||||||
- set_permissions explicitly grants that same user direct view
|
|
||||||
access via bulk_edit
|
|
||||||
THEN:
|
|
||||||
- A direct permission grant is created for the user, not skipped
|
|
||||||
because they already have equivalent access via the group
|
|
||||||
|
|
||||||
Regression test: guardian's queryset-aware assign_perm() (routed to
|
|
||||||
when the target is a list/queryset) skips creating a direct row for
|
|
||||||
anyone whose ObjectPermissionChecker.has_perm() already returns True
|
|
||||||
-- which includes group-derived access. The single-object assign_perm
|
|
||||||
this bulk path replaces has no such check; it always ensures a
|
|
||||||
direct row via get_or_create. Losing that guarantee would mean
|
|
||||||
revoking the group's grant later silently strips access that was
|
|
||||||
supposed to be explicit.
|
|
||||||
"""
|
|
||||||
self.doc1.owner = self.user1
|
|
||||||
self.doc1.save()
|
|
||||||
self.user1.groups.add(self.group1)
|
|
||||||
assign_perm("view_document", self.group1, self.doc1)
|
|
||||||
|
|
||||||
bulk_edit.set_permissions(
|
|
||||||
[self.doc1.id],
|
|
||||||
set_permissions={
|
|
||||||
"view": {"users": [self.user1.id], "groups": []},
|
|
||||||
},
|
|
||||||
merge=True,
|
|
||||||
)
|
|
||||||
|
|
||||||
direct_users = get_users_with_perms(
|
|
||||||
self.doc1,
|
|
||||||
only_with_perms_in=["view_document"],
|
|
||||||
with_group_users=False,
|
|
||||||
)
|
|
||||||
self.assertIn(self.user1, direct_users)
|
|
||||||
|
|
||||||
def test_set_permissions_for_objects_raises_for_unknown_action(self) -> None:
|
|
||||||
"""
|
|
||||||
GIVEN:
|
|
||||||
- An unrecognized permission action name with users to grant it
|
|
||||||
to
|
|
||||||
WHEN:
|
|
||||||
- set_permissions_for_objects is called
|
|
||||||
THEN:
|
|
||||||
- Permission.DoesNotExist is raised, not a silent no-op
|
|
||||||
|
|
||||||
Regression test: the endpoint that calls this
|
|
||||||
(BulkEditObjectPermissionsView) never actually validates action
|
|
||||||
names against the raw client-supplied permissions dict --
|
|
||||||
BulkEditObjectsSerializer._validate_permissions calls
|
|
||||||
validate_set_permissions() only for its side-effecting user/group id
|
|
||||||
checks and discards the filtered dict it returns -- so a bogus
|
|
||||||
action key reaches this function as-is. Resolving the Permission via
|
|
||||||
a bare `.filter()` (which returns empty instead of raising) would
|
|
||||||
silently drop the grant and report success.
|
|
||||||
"""
|
|
||||||
with self.assertRaises(Permission.DoesNotExist):
|
|
||||||
set_permissions_for_objects(
|
|
||||||
{"not_a_real_action": {"users": [self.user1.id], "groups": []}},
|
|
||||||
Document,
|
|
||||||
[self.doc1.pk],
|
|
||||||
)
|
|
||||||
|
|
||||||
@mock.patch("documents.models.Document.delete")
|
@mock.patch("documents.models.Document.delete")
|
||||||
def test_delete_documents_old_uuid_field(self, m) -> None:
|
def test_delete_documents_old_uuid_field(self, m) -> None:
|
||||||
m.side_effect = Exception("Data too long for column 'transaction_id' at row 1")
|
m.side_effect = Exception("Data too long for column 'transaction_id' at row 1")
|
||||||
@@ -893,7 +777,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
|
|||||||
sig.set.return_value.apply_async.side_effect = Exception("boom")
|
sig.set.return_value.apply_async.side_effect = Exception("boom")
|
||||||
mock_consume_file.return_value = sig
|
mock_consume_file.return_value = sig
|
||||||
|
|
||||||
with self.assertRaises(Exception):
|
with self.assertRaises(Exception): # noqa: B017 - mock injects a bare Exception
|
||||||
bulk_edit.merge(doc_ids, delete_originals=True)
|
bulk_edit.merge(doc_ids, delete_originals=True)
|
||||||
|
|
||||||
self.doc1.refresh_from_db()
|
self.doc1.refresh_from_db()
|
||||||
@@ -1434,7 +1318,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
|
|||||||
sig.apply_async.side_effect = Exception("boom")
|
sig.apply_async.side_effect = Exception("boom")
|
||||||
mock_chord.return_value = sig
|
mock_chord.return_value = sig
|
||||||
|
|
||||||
with self.assertRaises(Exception):
|
with self.assertRaises(Exception): # noqa: B017 - mock injects a bare Exception
|
||||||
bulk_edit.edit_pdf(doc_ids, operations, delete_original=True)
|
bulk_edit.edit_pdf(doc_ids, operations, delete_original=True)
|
||||||
|
|
||||||
self.doc2.refresh_from_db()
|
self.doc2.refresh_from_db()
|
||||||
@@ -1546,7 +1430,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
|
|||||||
{"page": 9999}, # invalid page, forces error during PDF load
|
{"page": 9999}, # invalid page, forces error during PDF load
|
||||||
]
|
]
|
||||||
with self.assertLogs("paperless.bulk_edit", level="ERROR"):
|
with self.assertLogs("paperless.bulk_edit", level="ERROR"):
|
||||||
with self.assertRaises(Exception):
|
with self.assertRaises(ValueError):
|
||||||
bulk_edit.edit_pdf(doc_ids, operations)
|
bulk_edit.edit_pdf(doc_ids, operations)
|
||||||
mock_group.assert_not_called()
|
mock_group.assert_not_called()
|
||||||
mock_consume_file.assert_not_called()
|
mock_consume_file.assert_not_called()
|
||||||
|
|||||||
@@ -783,7 +783,7 @@ class TestClassifier(DirectoriesMixin, TestCase):
|
|||||||
|
|
||||||
Path(settings.MODEL_FILE).touch()
|
Path(settings.MODEL_FILE).touch()
|
||||||
mock_load.side_effect = Exception()
|
mock_load.side_effect = Exception()
|
||||||
with self.assertRaises(Exception):
|
with self.assertRaises(Exception): # noqa: B017 - mock injects a bare Exception
|
||||||
load_classifier(raise_exception=True)
|
load_classifier(raise_exception=True)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -137,7 +137,7 @@ class FaultyParser(_BaseNewStyleParser):
|
|||||||
|
|
||||||
class FaultyGenericExceptionParser(_BaseNewStyleParser):
|
class FaultyGenericExceptionParser(_BaseNewStyleParser):
|
||||||
def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
|
def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
|
||||||
raise Exception("Generic exception.")
|
raise Exception("Generic exception.") # noqa: TRY002 - deliberately not a ParseError
|
||||||
|
|
||||||
|
|
||||||
def fake_magic_from_file(file, *, mime=False): # NOSONAR
|
def fake_magic_from_file(file, *, mime=False): # NOSONAR
|
||||||
@@ -1333,7 +1333,7 @@ class PreConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
|
|||||||
script_calls = [
|
script_calls = [
|
||||||
call
|
call
|
||||||
for call in m.call_args_list
|
for call in m.call_args_list
|
||||||
if call.args and call.args[0] and call.args[0][0] not in ("pdftotext",)
|
if call.args and call.args[0] and call.args[0][0] != "pdftotext"
|
||||||
]
|
]
|
||||||
self.assertEqual(script_calls, [])
|
self.assertEqual(script_calls, [])
|
||||||
|
|
||||||
|
|||||||
@@ -44,6 +44,7 @@ from documents import tasks
|
|||||||
from documents.data_models import ConsumableDocument
|
from documents.data_models import ConsumableDocument
|
||||||
from documents.data_models import DocumentMetadataOverrides
|
from documents.data_models import DocumentMetadataOverrides
|
||||||
from documents.data_models import DocumentSource
|
from documents.data_models import DocumentSource
|
||||||
|
from documents.matching import UnsupportedWorkflowTriggerTypeError
|
||||||
from documents.matching import document_matches_workflow
|
from documents.matching import document_matches_workflow
|
||||||
from documents.matching import existing_document_matches_workflow
|
from documents.matching import existing_document_matches_workflow
|
||||||
from documents.matching import prefilter_documents_by_workflowtrigger
|
from documents.matching import prefilter_documents_by_workflowtrigger
|
||||||
@@ -2851,7 +2852,13 @@ class TestWorkflows(
|
|||||||
doc = Document.objects.create(
|
doc = Document.objects.create(
|
||||||
title="test",
|
title="test",
|
||||||
)
|
)
|
||||||
self.assertRaises(Exception, document_matches_workflow, doc, w, 99)
|
self.assertRaises(
|
||||||
|
UnsupportedWorkflowTriggerTypeError,
|
||||||
|
document_matches_workflow,
|
||||||
|
doc,
|
||||||
|
w,
|
||||||
|
99,
|
||||||
|
)
|
||||||
|
|
||||||
def test_removal_action_document_updated_workflow(self) -> None:
|
def test_removal_action_document_updated_workflow(self) -> None:
|
||||||
"""
|
"""
|
||||||
|
|||||||
@@ -21,28 +21,32 @@ def uri_validator(value: str, allowed_schemes: set[str] | None = None) -> None:
|
|||||||
parts = urlparse(value)
|
parts = urlparse(value)
|
||||||
if not parts.scheme:
|
if not parts.scheme:
|
||||||
raise ValidationError(
|
raise ValidationError(
|
||||||
_(f"Unable to parse URI {value}, missing scheme"),
|
_("Unable to parse URI %(value)s, missing scheme"),
|
||||||
params={"value": value},
|
params={"value": value},
|
||||||
)
|
)
|
||||||
elif not parts.netloc and not parts.path:
|
elif not parts.netloc and not parts.path:
|
||||||
raise ValidationError(
|
raise ValidationError(
|
||||||
_(f"Unable to parse URI {value}, missing net location or path"),
|
_("Unable to parse URI %(value)s, missing net location or path"),
|
||||||
params={"value": value},
|
params={"value": value},
|
||||||
)
|
)
|
||||||
|
|
||||||
if allowed_schemes and parts.scheme not in allowed_schemes:
|
if allowed_schemes and parts.scheme not in allowed_schemes:
|
||||||
raise ValidationError(
|
raise ValidationError(
|
||||||
_(
|
_(
|
||||||
f"URI scheme '{parts.scheme}' is not allowed. Allowed schemes: {', '.join(allowed_schemes)}",
|
"URI scheme '%(scheme)s' is not allowed. Allowed schemes: %(allowed_schemes)s",
|
||||||
),
|
),
|
||||||
params={"value": value, "scheme": parts.scheme},
|
params={
|
||||||
|
"value": value,
|
||||||
|
"scheme": parts.scheme,
|
||||||
|
"allowed_schemes": ", ".join(allowed_schemes),
|
||||||
|
},
|
||||||
)
|
)
|
||||||
|
|
||||||
except ValidationError:
|
except ValidationError:
|
||||||
raise
|
raise
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
raise ValidationError(
|
raise ValidationError(
|
||||||
_(f"Unable to parse URI {value}"),
|
_("Unable to parse URI %(value)s"),
|
||||||
params={"value": value},
|
params={"value": value},
|
||||||
) from e
|
) from e
|
||||||
|
|
||||||
|
|||||||
+29
-33
@@ -178,7 +178,7 @@ from documents.permissions import has_perms_owner_aware
|
|||||||
from documents.permissions import has_system_status_permission
|
from documents.permissions import has_system_status_permission
|
||||||
from documents.permissions import permitted_document_ids
|
from documents.permissions import permitted_document_ids
|
||||||
from documents.permissions import permitted_object_ids
|
from documents.permissions import permitted_object_ids
|
||||||
from documents.permissions import set_permissions_for_objects
|
from documents.permissions import set_permissions_for_object
|
||||||
from documents.plugins.date_parsing import get_date_parser
|
from documents.plugins.date_parsing import get_date_parser
|
||||||
from documents.schema import generate_object_with_permissions_schema
|
from documents.schema import generate_object_with_permissions_schema
|
||||||
from documents.search import SearchHit
|
from documents.search import SearchHit
|
||||||
@@ -1440,7 +1440,7 @@ class DocumentViewSet(
|
|||||||
try:
|
try:
|
||||||
lang = detect(doc.content)
|
lang = detect(doc.content)
|
||||||
except Exception:
|
except Exception:
|
||||||
pass
|
logger.debug("Unable to detect language for document %s", doc.pk)
|
||||||
meta["lang"] = lang
|
meta["lang"] = lang
|
||||||
|
|
||||||
return Response(meta)
|
return Response(meta)
|
||||||
@@ -1478,13 +1478,12 @@ class DocumentViewSet(
|
|||||||
with get_date_parser() as date_parser:
|
with get_date_parser() as date_parser:
|
||||||
gen = date_parser.parse(doc.filename, doc.content)
|
gen = date_parser.parse(doc.filename, doc.content)
|
||||||
dates = sorted(
|
dates = sorted(
|
||||||
{
|
set(
|
||||||
i
|
itertools.islice(
|
||||||
for i in itertools.islice(
|
|
||||||
gen,
|
gen,
|
||||||
settings.NUMBER_OF_SUGGESTED_DATES,
|
settings.NUMBER_OF_SUGGESTED_DATES,
|
||||||
)
|
),
|
||||||
},
|
),
|
||||||
)
|
)
|
||||||
|
|
||||||
resp_data = {
|
resp_data = {
|
||||||
@@ -1568,21 +1567,16 @@ class DocumentViewSet(
|
|||||||
except ValueError as exc:
|
except ValueError as exc:
|
||||||
logger.exception(
|
logger.exception(
|
||||||
"Invalid AI configuration while generating suggestions for "
|
"Invalid AI configuration while generating suggestions for "
|
||||||
"document %s: %s",
|
"document %s",
|
||||||
doc.pk,
|
doc.pk,
|
||||||
exc,
|
|
||||||
exc_info=True,
|
|
||||||
)
|
)
|
||||||
raise ValidationError(
|
raise ValidationError(
|
||||||
{"ai": [_("Invalid AI configuration.")]},
|
{"ai": [_("Invalid AI configuration.")]},
|
||||||
) from exc
|
) from exc
|
||||||
except LLMTimeoutError as exc:
|
except LLMTimeoutError:
|
||||||
logger.exception(
|
logger.exception(
|
||||||
"AI backend timed out while generating suggestions for "
|
"AI backend timed out while generating suggestions for document %s",
|
||||||
"document %s: %s",
|
|
||||||
doc.pk,
|
doc.pk,
|
||||||
exc,
|
|
||||||
exc_info=True,
|
|
||||||
)
|
)
|
||||||
return Response(
|
return Response(
|
||||||
{"ai": [_("AI backend request timed out.")]},
|
{"ai": [_("AI backend request timed out.")]},
|
||||||
@@ -2055,7 +2049,7 @@ class DocumentViewSet(
|
|||||||
doc_name, doc_data = serializer.validated_data.get("document")
|
doc_name, doc_data = serializer.validated_data.get("document")
|
||||||
version_label = serializer.validated_data.get("version_label")
|
version_label = serializer.validated_data.get("version_label")
|
||||||
|
|
||||||
t = int(mktime(datetime.now().timetuple()))
|
t = int(mktime(datetime.now().timetuple())) # noqa: DTZ005 - mktime() requires a local time tuple
|
||||||
|
|
||||||
settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
|
settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
@@ -3325,7 +3319,7 @@ class PostDocumentView(GenericAPIView[Any]):
|
|||||||
cf = serializer.validated_data.get("custom_fields")
|
cf = serializer.validated_data.get("custom_fields")
|
||||||
from_webui = serializer.validated_data.get("from_webui")
|
from_webui = serializer.validated_data.get("from_webui")
|
||||||
|
|
||||||
t = int(mktime(datetime.now().timetuple()))
|
t = int(mktime(datetime.now().timetuple())) # noqa: DTZ005 - mktime() requires a local time tuple
|
||||||
|
|
||||||
settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
|
settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
@@ -4135,7 +4129,7 @@ class UiSettingsView(GenericAPIView[Any]):
|
|||||||
user_resp["last_name"] = user.last_name
|
user_resp["last_name"] = user.last_name
|
||||||
|
|
||||||
# strip <app_label>.
|
# strip <app_label>.
|
||||||
roles = map(lambda perm: re.sub(r"^\w+.", "", perm), user.get_all_permissions())
|
roles = (re.sub(r"^\w+.", "", perm) for perm in user.get_all_permissions())
|
||||||
return Response(
|
return Response(
|
||||||
{
|
{
|
||||||
"user": user_resp,
|
"user": user_resp,
|
||||||
@@ -4914,12 +4908,12 @@ class BulkEditObjectsView(PassUserMixin):
|
|||||||
qs_owner_update.update(owner=owner)
|
qs_owner_update.update(owner=owner)
|
||||||
|
|
||||||
if "permissions" in serializer.validated_data:
|
if "permissions" in serializer.validated_data:
|
||||||
set_permissions_for_objects(
|
for obj in qs:
|
||||||
permissions=permissions,
|
set_permissions_for_object(
|
||||||
model=object_class,
|
permissions=permissions,
|
||||||
pks=qs.values_list("pk", flat=True),
|
object=obj,
|
||||||
merge=merge,
|
merge=merge,
|
||||||
)
|
)
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.warning(
|
logger.warning(
|
||||||
@@ -5162,11 +5156,11 @@ class SystemStatusView(PassUserMixin):
|
|||||||
f"{m.app}.{m.name}"
|
f"{m.app}.{m.name}"
|
||||||
for m in MigrationRecorder.Migration.objects.all().order_by("id")
|
for m in MigrationRecorder.Migration.objects.all().order_by("id")
|
||||||
]
|
]
|
||||||
except Exception as e: # pragma: no cover
|
except Exception: # pragma: no cover
|
||||||
applied_migrations = []
|
applied_migrations = []
|
||||||
db_status = "ERROR"
|
db_status = "ERROR"
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"System status detected a possible problem while connecting to the database: {e}",
|
"System status detected a possible problem while connecting to the database",
|
||||||
)
|
)
|
||||||
db_error = "Error connecting to database, check logs for more detail."
|
db_error = "Error connecting to database, check logs for more detail."
|
||||||
|
|
||||||
@@ -5182,10 +5176,10 @@ class SystemStatusView(PassUserMixin):
|
|||||||
try:
|
try:
|
||||||
client.ping()
|
client.ping()
|
||||||
redis_status = "OK"
|
redis_status = "OK"
|
||||||
except Exception as e:
|
except Exception:
|
||||||
redis_status = "ERROR"
|
redis_status = "ERROR"
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"System status detected a possible problem while connecting to redis: {e}",
|
"System status detected a possible problem while connecting to redis",
|
||||||
)
|
)
|
||||||
redis_error = "Error connecting to redis, check logs for more detail."
|
redis_error = "Error connecting to redis, check logs for more detail."
|
||||||
|
|
||||||
@@ -5215,10 +5209,10 @@ class SystemStatusView(PassUserMixin):
|
|||||||
else:
|
else:
|
||||||
celery_active = "WARNING"
|
celery_active = "WARNING"
|
||||||
celery_error = "Celery worker responded unexpectedly."
|
celery_error = "Celery worker responded unexpectedly."
|
||||||
except Exception as e:
|
except Exception:
|
||||||
celery_active = "ERROR"
|
celery_active = "ERROR"
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"System status detected a possible problem while connecting to celery: {e}",
|
"System status detected a possible problem while connecting to celery",
|
||||||
)
|
)
|
||||||
celery_error = "Error connecting to celery, check logs for more detail."
|
celery_error = "Error connecting to celery, check logs for more detail."
|
||||||
|
|
||||||
@@ -5233,13 +5227,15 @@ class SystemStatusView(PassUserMixin):
|
|||||||
index_dir = settings.INDEX_DIR
|
index_dir = settings.INDEX_DIR
|
||||||
mtimes = [p.stat().st_mtime for p in index_dir.iterdir() if p.is_file()]
|
mtimes = [p.stat().st_mtime for p in index_dir.iterdir() if p.is_file()]
|
||||||
index_last_modified = (
|
index_last_modified = (
|
||||||
make_aware(datetime.fromtimestamp(max(mtimes))) if mtimes else None
|
make_aware(datetime.fromtimestamp(max(mtimes))) # noqa: DTZ006 - make_aware() requires a naive datetime
|
||||||
|
if mtimes
|
||||||
|
else None
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception:
|
||||||
index_status = "ERROR"
|
index_status = "ERROR"
|
||||||
index_error = "Error opening index, check logs for more detail."
|
index_error = "Error opening index, check logs for more detail."
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"System status detected a possible problem while opening the index: {e}",
|
"System status detected a possible problem while opening the index",
|
||||||
)
|
)
|
||||||
index_last_modified = None
|
index_last_modified = None
|
||||||
|
|
||||||
|
|||||||
@@ -66,7 +66,7 @@ def build_workflow_action_context(
|
|||||||
else None
|
else None
|
||||||
)
|
)
|
||||||
|
|
||||||
filename = document.original_file if document.original_file else ""
|
filename = document.original_file or ""
|
||||||
return {
|
return {
|
||||||
"title": overrides.title
|
"title": overrides.title
|
||||||
if overrides and overrides.title
|
if overrides and overrides.title
|
||||||
@@ -179,9 +179,9 @@ def execute_email_action(
|
|||||||
f"Sent {n_messages} notification email(s) to {action.email.to}",
|
f"Sent {n_messages} notification email(s) to {action.email.to}",
|
||||||
extra={"group": logging_group},
|
extra={"group": logging_group},
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"Error occurred sending notification email: {e}",
|
"Error occurred sending notification email",
|
||||||
extra={"group": logging_group},
|
extra={"group": logging_group},
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -265,9 +265,9 @@ def execute_webhook_action(
|
|||||||
f"Webhook to {action.webhook.url} queued",
|
f"Webhook to {action.webhook.url} queued",
|
||||||
extra={"group": logging_group},
|
extra={"group": logging_group},
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception(
|
logger.exception(
|
||||||
f"Error occurred sending webhook: {e}",
|
"Error occurred sending webhook",
|
||||||
extra={"group": logging_group},
|
extra={"group": logging_group},
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|||||||
@@ -47,7 +47,7 @@ def resolve_date(dates: list[str]) -> date | None:
|
|||||||
"""
|
"""
|
||||||
for value in dates:
|
for value in dates:
|
||||||
try:
|
try:
|
||||||
return datetime.strptime(value, "%Y-%m-%d").date()
|
return datetime.strptime(value, "%Y-%m-%d").date() # noqa: DTZ007 - only the calendar date is used, time/tz is discarded
|
||||||
except (TypeError, ValueError):
|
except (TypeError, ValueError):
|
||||||
logger.debug("Ignoring unparsable suggested date %s", value)
|
logger.debug("Ignoring unparsable suggested date %s", value)
|
||||||
return None
|
return None
|
||||||
|
|||||||
@@ -70,6 +70,6 @@ def send_webhook(
|
|||||||
logger.error(
|
logger.error(
|
||||||
f"Failed attempt sending webhook to {url}: {e}",
|
f"Failed attempt sending webhook to {url}: {e}",
|
||||||
)
|
)
|
||||||
raise e
|
raise
|
||||||
finally:
|
finally:
|
||||||
transport.close()
|
transport.close()
|
||||||
|
|||||||
@@ -241,7 +241,7 @@ def check_v3_minimum_upgrade_version(
|
|||||||
return []
|
return []
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
last_applied = sorted(applied)[-1] if applied else "(none)"
|
last_applied = max(applied) if applied else "(none)"
|
||||||
logger.error(
|
logger.error(
|
||||||
"V3 upgrade check failed: last applied documents migration is %r. "
|
"V3 upgrade check failed: last applied documents migration is %r. "
|
||||||
"Expected '1075_workflowaction_order' (v2.20.15). "
|
"Expected '1075_workflowaction_order' (v2.20.15). "
|
||||||
@@ -341,6 +341,7 @@ def get_tesseract_langs():
|
|||||||
proc = subprocess.run(
|
proc = subprocess.run(
|
||||||
[shutil.which("tesseract"), "--list-langs"],
|
[shutil.which("tesseract"), "--list-langs"],
|
||||||
capture_output=True,
|
capture_output=True,
|
||||||
|
check=False,
|
||||||
)
|
)
|
||||||
|
|
||||||
# Decode bytes to string, split on newlines, trim out the header
|
# Decode bytes to string, split on newlines, trim out the header
|
||||||
|
|||||||
@@ -84,7 +84,7 @@ def get_parser_registry() -> ParserRegistry:
|
|||||||
ParserRegistry
|
ParserRegistry
|
||||||
The shared registry singleton.
|
The shared registry singleton.
|
||||||
"""
|
"""
|
||||||
global _registry, _discovery_complete
|
global _registry, _discovery_complete # noqa: PLW0603 - module-level singleton, no class to hold this state
|
||||||
|
|
||||||
with _lock:
|
with _lock:
|
||||||
if _registry is None:
|
if _registry is None:
|
||||||
@@ -113,7 +113,7 @@ def init_builtin_parsers() -> None:
|
|||||||
-------
|
-------
|
||||||
None
|
None
|
||||||
"""
|
"""
|
||||||
global _registry
|
global _registry # noqa: PLW0603 - module-level singleton, no class to hold this state
|
||||||
|
|
||||||
with _lock:
|
with _lock:
|
||||||
if _registry is None:
|
if _registry is None:
|
||||||
@@ -137,7 +137,7 @@ def reset_parser_registry() -> None:
|
|||||||
-------
|
-------
|
||||||
None
|
None
|
||||||
"""
|
"""
|
||||||
global _registry, _discovery_complete
|
global _registry, _discovery_complete # noqa: PLW0603 - module-level singleton, no class to hold this state
|
||||||
|
|
||||||
_registry = None
|
_registry = None
|
||||||
_discovery_complete = False
|
_discovery_complete = False
|
||||||
|
|||||||
@@ -76,7 +76,7 @@ class RemoteEngineConfig:
|
|||||||
def engine_is_valid(self) -> bool:
|
def engine_is_valid(self) -> bool:
|
||||||
"""Return True when the engine is known and fully configured."""
|
"""Return True when the engine is known and fully configured."""
|
||||||
return (
|
return (
|
||||||
self.engine in ("azureai",)
|
self.engine == "azureai"
|
||||||
and self.api_key is not None
|
and self.api_key is not None
|
||||||
and not (self.engine == "azureai" and self.endpoint is None)
|
and not (self.engine == "azureai" and self.endpoint is None)
|
||||||
)
|
)
|
||||||
@@ -467,7 +467,7 @@ class RemoteDocumentParser:
|
|||||||
return result.content
|
return result.content
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.exception("Azure AI Vision parsing failed: %s", e)
|
logger.exception("Azure AI Vision parsing failed")
|
||||||
raise ParseError(f"Azure AI Vision parsing failed: {e}") from e
|
raise ParseError(f"Azure AI Vision parsing failed: {e}") from e
|
||||||
|
|
||||||
finally:
|
finally:
|
||||||
|
|||||||
@@ -306,8 +306,9 @@ def extract_pdf_metadata(
|
|||||||
|
|
||||||
for key, value in meta.items():
|
for key, value in meta.items():
|
||||||
if isinstance(value, list):
|
if isinstance(value, list):
|
||||||
value = " ".join(str(e) for e in value)
|
str_value = " ".join(str(e) for e in value)
|
||||||
value = str(value)
|
else:
|
||||||
|
str_value = str(value)
|
||||||
|
|
||||||
try:
|
try:
|
||||||
m = namespace_pattern.match(key)
|
m = namespace_pattern.match(key)
|
||||||
@@ -329,7 +330,7 @@ def extract_pdf_metadata(
|
|||||||
namespace=namespace,
|
namespace=namespace,
|
||||||
prefix=meta.REVERSE_NS[namespace],
|
prefix=meta.REVERSE_NS[namespace],
|
||||||
key=key_value,
|
key=key_value,
|
||||||
value=value,
|
value=str_value,
|
||||||
),
|
),
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
|
|||||||
@@ -294,7 +294,7 @@ if _CHANNELS_BACKEND.startswith("channels_redis."):
|
|||||||
###############################################################################
|
###############################################################################
|
||||||
|
|
||||||
EMAIL_HOST: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST", "localhost")
|
EMAIL_HOST: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST", "localhost")
|
||||||
EMAIL_PORT: Final[int] = int(os.getenv("PAPERLESS_EMAIL_PORT", 25))
|
EMAIL_PORT: Final[int] = get_int_from_env("PAPERLESS_EMAIL_PORT", 25)
|
||||||
EMAIL_HOST_USER: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_USER", "")
|
EMAIL_HOST_USER: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_USER", "")
|
||||||
EMAIL_HOST_PASSWORD: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_PASSWORD", "")
|
EMAIL_HOST_PASSWORD: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_PASSWORD", "")
|
||||||
DEFAULT_FROM_EMAIL: Final[str] = os.getenv("PAPERLESS_EMAIL_FROM", EMAIL_HOST_USER)
|
DEFAULT_FROM_EMAIL: Final[str] = os.getenv("PAPERLESS_EMAIL_FROM", EMAIL_HOST_USER)
|
||||||
@@ -381,8 +381,9 @@ ACCOUNT_SESSION_REMEMBER = get_bool_from_env(
|
|||||||
"True",
|
"True",
|
||||||
)
|
)
|
||||||
SESSION_EXPIRE_AT_BROWSER_CLOSE = not ACCOUNT_SESSION_REMEMBER
|
SESSION_EXPIRE_AT_BROWSER_CLOSE = not ACCOUNT_SESSION_REMEMBER
|
||||||
SESSION_COOKIE_AGE = int(
|
SESSION_COOKIE_AGE = get_int_from_env(
|
||||||
os.getenv("PAPERLESS_SESSION_COOKIE_AGE", 60 * 60 * 24 * 7 * 3),
|
"PAPERLESS_SESSION_COOKIE_AGE",
|
||||||
|
60 * 60 * 24 * 7 * 3,
|
||||||
)
|
)
|
||||||
# https://docs.djangoproject.com/en/5.1/ref/settings/#std-setting-SESSION_ENGINE
|
# https://docs.djangoproject.com/en/5.1/ref/settings/#std-setting-SESSION_ENGINE
|
||||||
SESSION_ENGINE = "django.contrib.sessions.backends.cached_db"
|
SESSION_ENGINE = "django.contrib.sessions.backends.cached_db"
|
||||||
@@ -395,7 +396,6 @@ if AUTO_LOGIN_USERNAME:
|
|||||||
|
|
||||||
|
|
||||||
def _parse_remote_user_settings() -> str:
|
def _parse_remote_user_settings() -> str:
|
||||||
global MIDDLEWARE, AUTHENTICATION_BACKENDS, REST_FRAMEWORK
|
|
||||||
enable = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER")
|
enable = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER")
|
||||||
enable_api = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER_API")
|
enable_api = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER_API")
|
||||||
if enable or enable_api:
|
if enable or enable_api:
|
||||||
@@ -454,7 +454,6 @@ if ALLOWED_HOSTS != ["*"]:
|
|||||||
|
|
||||||
|
|
||||||
def _parse_paperless_url():
|
def _parse_paperless_url():
|
||||||
global CSRF_TRUSTED_ORIGINS, CORS_ALLOWED_ORIGINS, ALLOWED_HOSTS
|
|
||||||
url = os.getenv("PAPERLESS_URL")
|
url = os.getenv("PAPERLESS_URL")
|
||||||
if url:
|
if url:
|
||||||
CSRF_TRUSTED_ORIGINS.append(url)
|
CSRF_TRUSTED_ORIGINS.append(url)
|
||||||
@@ -614,8 +613,8 @@ USE_TZ = True
|
|||||||
|
|
||||||
LOGGING_DIR.mkdir(parents=True, exist_ok=True)
|
LOGGING_DIR.mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
LOGROTATE_MAX_SIZE = os.getenv("PAPERLESS_LOGROTATE_MAX_SIZE", 1024 * 1024)
|
LOGROTATE_MAX_SIZE = get_int_from_env("PAPERLESS_LOGROTATE_MAX_SIZE", 1024 * 1024)
|
||||||
LOGROTATE_MAX_BACKUPS = os.getenv("PAPERLESS_LOGROTATE_MAX_BACKUPS", 20)
|
LOGROTATE_MAX_BACKUPS = get_int_from_env("PAPERLESS_LOGROTATE_MAX_BACKUPS", 20)
|
||||||
|
|
||||||
LOGGING = {
|
LOGGING = {
|
||||||
"version": 1,
|
"version": 1,
|
||||||
@@ -811,9 +810,15 @@ IGNORABLE_FILES: Final[list[str]] = [
|
|||||||
"Thumbs.db",
|
"Thumbs.db",
|
||||||
]
|
]
|
||||||
|
|
||||||
CONSUMER_POLLING_INTERVAL = float(os.getenv("PAPERLESS_CONSUMER_POLLING_INTERVAL", 0))
|
CONSUMER_POLLING_INTERVAL = get_float_from_env(
|
||||||
|
"PAPERLESS_CONSUMER_POLLING_INTERVAL",
|
||||||
|
0.0,
|
||||||
|
)
|
||||||
|
|
||||||
CONSUMER_STABILITY_DELAY = float(os.getenv("PAPERLESS_CONSUMER_STABILITY_DELAY", 5))
|
CONSUMER_STABILITY_DELAY = get_float_from_env(
|
||||||
|
"PAPERLESS_CONSUMER_STABILITY_DELAY",
|
||||||
|
5.0,
|
||||||
|
)
|
||||||
|
|
||||||
CONSUMER_DELETE_DUPLICATES = get_bool_from_env("PAPERLESS_CONSUMER_DELETE_DUPLICATES")
|
CONSUMER_DELETE_DUPLICATES = get_bool_from_env("PAPERLESS_CONSUMER_DELETE_DUPLICATES")
|
||||||
|
|
||||||
|
|||||||
@@ -111,7 +111,7 @@ def parse_dict_from_str(
|
|||||||
return False
|
return False
|
||||||
|
|
||||||
settings: dict[str, Any] = copy.deepcopy(defaults) if defaults else {}
|
settings: dict[str, Any] = copy.deepcopy(defaults) if defaults else {}
|
||||||
_type_map = type_map if type_map else {}
|
_type_map = type_map or {}
|
||||||
|
|
||||||
if not env_str:
|
if not env_str:
|
||||||
return settings
|
return settings
|
||||||
|
|||||||
@@ -114,17 +114,17 @@ def test_cache_hit_when_enabled() -> None:
|
|||||||
assert settings.CACHALOT_TIMEOUT == 1
|
assert settings.CACHALOT_TIMEOUT == 1
|
||||||
|
|
||||||
# Read a table to populate the cache
|
# Read a table to populate the cache
|
||||||
list(list(Tag.objects.values_list("id", flat=True)))
|
list(Tag.objects.values_list("id", flat=True))
|
||||||
|
|
||||||
# Invalidate the cache then read the database, there should be DB hit
|
# Invalidate the cache then read the database, there should be DB hit
|
||||||
invalidate_db_cache()
|
invalidate_db_cache()
|
||||||
with CaptureQueriesContext(connection) as ctx:
|
with CaptureQueriesContext(connection) as ctx:
|
||||||
list(list(Tag.objects.values_list("id", flat=True)))
|
list(Tag.objects.values_list("id", flat=True))
|
||||||
assert len(ctx)
|
assert len(ctx)
|
||||||
|
|
||||||
# Doing the same request again should hit the cache, not the DB
|
# Doing the same request again should hit the cache, not the DB
|
||||||
with CaptureQueriesContext(connection) as ctx:
|
with CaptureQueriesContext(connection) as ctx:
|
||||||
list(list(Tag.objects.values_list("id", flat=True)))
|
list(Tag.objects.values_list("id", flat=True))
|
||||||
assert not len(ctx)
|
assert not len(ctx)
|
||||||
|
|
||||||
# Wait the end of TTL
|
# Wait the end of TTL
|
||||||
@@ -133,7 +133,7 @@ def test_cache_hit_when_enabled() -> None:
|
|||||||
|
|
||||||
# Read the DB again. The DB should be hit because the cache has expired
|
# Read the DB again. The DB should be hit because the cache has expired
|
||||||
with CaptureQueriesContext(connection) as ctx:
|
with CaptureQueriesContext(connection) as ctx:
|
||||||
list(list(Tag.objects.values_list("id", flat=True)))
|
list(Tag.objects.values_list("id", flat=True))
|
||||||
assert len(ctx)
|
assert len(ctx)
|
||||||
|
|
||||||
# Invalidate the cache at the end of test
|
# Invalidate the cache at the end of test
|
||||||
@@ -149,7 +149,7 @@ def test_cache_is_disabled_by_default() -> None:
|
|||||||
# Read the table multiple times: the DB should always be hit without cache
|
# Read the table multiple times: the DB should always be hit without cache
|
||||||
for _ in range(3):
|
for _ in range(3):
|
||||||
with CaptureQueriesContext(connection) as ctx:
|
with CaptureQueriesContext(connection) as ctx:
|
||||||
list(list(Tag.objects.values_list("id", flat=True)))
|
list(Tag.objects.values_list("id", flat=True))
|
||||||
assert len(ctx)
|
assert len(ctx)
|
||||||
|
|
||||||
# Invalidate the cache at the end of test
|
# Invalidate the cache at the end of test
|
||||||
|
|||||||
@@ -59,7 +59,7 @@ def test_ocr_to_dateparser_languages_exception(
|
|||||||
raise RuntimeError("Simulated error")
|
raise RuntimeError("Simulated error")
|
||||||
|
|
||||||
with caplog.at_level(logging.WARNING):
|
with caplog.at_level(logging.WARNING):
|
||||||
monkeypatch.setattr(utils, "LocaleDataLoader", lambda: DummyLoader())
|
monkeypatch.setattr(utils, "LocaleDataLoader", DummyLoader)
|
||||||
result = utils.ocr_to_dateparser_languages("eng+fra")
|
result = utils.ocr_to_dateparser_languages("eng+fra")
|
||||||
assert result == []
|
assert result == []
|
||||||
assert (
|
assert (
|
||||||
|
|||||||
@@ -103,8 +103,8 @@ def stream_chat_with_documents(
|
|||||||
documents,
|
documents,
|
||||||
output_language=output_language,
|
output_language=output_language,
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception:
|
||||||
logger.exception("Failed to stream document chat response: %s", e)
|
logger.exception("Failed to stream document chat response")
|
||||||
yield CHAT_ERROR_MESSAGE
|
yield CHAT_ERROR_MESSAGE
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -167,7 +167,7 @@ def test_get_ai_document_classification_failure(mock_run_llm_query, mock_documen
|
|||||||
"""
|
"""
|
||||||
mock_run_llm_query.side_effect = Exception("LLM query failed")
|
mock_run_llm_query.side_effect = Exception("LLM query failed")
|
||||||
|
|
||||||
with pytest.raises(Exception):
|
with pytest.raises(Exception): # noqa: B017 - mock injects a bare Exception
|
||||||
get_ai_document_classification(mock_document)
|
get_ai_document_classification(mock_document)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -21,5 +21,6 @@ class TestLazyAiImports:
|
|||||||
capture_output=True,
|
capture_output=True,
|
||||||
text=True,
|
text=True,
|
||||||
cwd=_SRC_DIR,
|
cwd=_SRC_DIR,
|
||||||
|
check=False,
|
||||||
)
|
)
|
||||||
assert result.returncode == 0, result.stdout + result.stderr
|
assert result.returncode == 0, result.stdout + result.stderr
|
||||||
|
|||||||
@@ -7,7 +7,6 @@ import ssl
|
|||||||
import tempfile
|
import tempfile
|
||||||
import traceback
|
import traceback
|
||||||
import unicodedata
|
import unicodedata
|
||||||
from datetime import date
|
|
||||||
from datetime import timedelta
|
from datetime import timedelta
|
||||||
from fnmatch import fnmatch
|
from fnmatch import fnmatch
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
@@ -406,7 +405,7 @@ def make_criterias(rule: MailRule, *, supports_gmail_labels: bool):
|
|||||||
Returns criteria to be applied to MailBox.fetch for the given rule.
|
Returns criteria to be applied to MailBox.fetch for the given rule.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
maximum_age = date.today() - timedelta(days=rule.maximum_age)
|
maximum_age = timezone.localdate() - timedelta(days=rule.maximum_age)
|
||||||
criterias = {}
|
criterias = {}
|
||||||
if rule.maximum_age > 0:
|
if rule.maximum_age > 0:
|
||||||
criterias["date_gte"] = maximum_age
|
criterias["date_gte"] = maximum_age
|
||||||
@@ -723,9 +722,9 @@ class MailAccountHandler(LoggingMixin):
|
|||||||
f"Rule {rule}: Stopping processing rules due to stop_processing flag",
|
f"Rule {rule}: Stopping processing rules due to stop_processing flag",
|
||||||
)
|
)
|
||||||
break
|
break
|
||||||
except Exception as e:
|
except Exception:
|
||||||
self.log.exception(
|
self.log.exception(
|
||||||
f"Rule {rule}: Error while processing rule: {e}",
|
f"Rule {rule}: Error while processing rule",
|
||||||
)
|
)
|
||||||
except MailError:
|
except MailError:
|
||||||
raise
|
raise
|
||||||
@@ -874,9 +873,9 @@ class MailAccountHandler(LoggingMixin):
|
|||||||
|
|
||||||
total_processed_files += processed_files
|
total_processed_files += processed_files
|
||||||
mails_processed += 1
|
mails_processed += 1
|
||||||
except Exception as e:
|
except Exception:
|
||||||
self.log.exception(
|
self.log.exception(
|
||||||
f"Rule {rule}: Error while processing mail {message.uid}: {e}",
|
f"Rule {rule}: Error while processing mail {message.uid}",
|
||||||
)
|
)
|
||||||
|
|
||||||
self.log.debug(f"Rule {rule}: Processed {mails_processed} matching mail(s)")
|
self.log.debug(f"Rule {rule}: Processed {mails_processed} matching mail(s)")
|
||||||
|
|||||||
@@ -11,6 +11,10 @@ from imap_tools import MailMessage
|
|||||||
from documents.loggers import LoggingMixin
|
from documents.loggers import LoggingMixin
|
||||||
|
|
||||||
|
|
||||||
|
class MailDecryptionError(Exception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
class MailMessagePreprocessor(abc.ABC):
|
class MailMessagePreprocessor(abc.ABC):
|
||||||
"""
|
"""
|
||||||
Defines the interface for preprocessors that alter messages before they are handled in MailAccountHandler
|
Defines the interface for preprocessors that alter messages before they are handled in MailAccountHandler
|
||||||
@@ -69,7 +73,7 @@ class MailMessageDecryptor(MailMessagePreprocessor, LoggingMixin):
|
|||||||
f"Message decryption failed with status message "
|
f"Message decryption failed with status message "
|
||||||
f"{decrypted_raw_message.status}",
|
f"{decrypted_raw_message.status}",
|
||||||
)
|
)
|
||||||
raise Exception(
|
raise MailDecryptionError(
|
||||||
f"Decryption failed: {decrypted_raw_message.status}, {decrypted_raw_message.stderr}",
|
f"Decryption failed: {decrypted_raw_message.status}, {decrypted_raw_message.stderr}",
|
||||||
)
|
)
|
||||||
self.log.debug("Message decrypted successfully.")
|
self.log.debug("Message decrypted successfully.")
|
||||||
|
|||||||
@@ -50,7 +50,7 @@ class ProcessedMailFactory(DjangoModelFactory[ProcessedMail]):
|
|||||||
|
|
||||||
rule = factory.SubFactory(MailRuleFactory)
|
rule = factory.SubFactory(MailRuleFactory)
|
||||||
folder = "INBOX"
|
folder = "INBOX"
|
||||||
uid = factory.Sequence(lambda n: str(n))
|
uid = factory.Sequence(str)
|
||||||
subject = factory.Faker("sentence", nb_words=4)
|
subject = factory.Faker("sentence", nb_words=4)
|
||||||
received = factory.LazyFunction(timezone.now)
|
received = factory.LazyFunction(timezone.now)
|
||||||
processed = factory.LazyFunction(timezone.now)
|
processed = factory.LazyFunction(timezone.now)
|
||||||
|
|||||||
@@ -214,7 +214,7 @@ class BogusMailBox(AbstractContextManager):
|
|||||||
)
|
)
|
||||||
self.messages = list(filter(lambda m: m.uid not in uid_list, self.messages))
|
self.messages = list(filter(lambda m: m.uid not in uid_list, self.messages))
|
||||||
else:
|
else:
|
||||||
raise Exception
|
raise Exception # noqa: TRY002 - test double simulating a generic mailbox failure
|
||||||
|
|
||||||
|
|
||||||
def fake_magic_from_buffer(buffer, *, mime=False):
|
def fake_magic_from_buffer(buffer, *, mime=False):
|
||||||
|
|||||||
@@ -14,6 +14,7 @@ from imap_tools import MailMessage
|
|||||||
|
|
||||||
from paperless_mail.mail import MailAccountHandler
|
from paperless_mail.mail import MailAccountHandler
|
||||||
from paperless_mail.models import MailRule
|
from paperless_mail.models import MailRule
|
||||||
|
from paperless_mail.preprocessor import MailDecryptionError
|
||||||
from paperless_mail.preprocessor import MailMessageDecryptor
|
from paperless_mail.preprocessor import MailMessageDecryptor
|
||||||
from paperless_mail.tests.factories import MailAccountFactory
|
from paperless_mail.tests.factories import MailAccountFactory
|
||||||
from paperless_mail.tests.test_mail import TestMail
|
from paperless_mail.tests.test_mail import TestMail
|
||||||
@@ -82,7 +83,9 @@ class MessageEncryptor:
|
|||||||
armor=True,
|
armor=True,
|
||||||
)
|
)
|
||||||
if not encrypted_data.ok:
|
if not encrypted_data.ok:
|
||||||
raise Exception(f"Encryption failed: {encrypted_data.stderr}")
|
raise Exception( # noqa: TRY002 - test fixture setup, not production code
|
||||||
|
f"Encryption failed: {encrypted_data.stderr}",
|
||||||
|
)
|
||||||
encrypted_email_content = encrypted_data.data
|
encrypted_email_content = encrypted_data.data
|
||||||
|
|
||||||
new_email = MIMEMultipart("encrypted", protocol="application/pgp-encrypted")
|
new_email = MIMEMultipart("encrypted", protocol="application/pgp-encrypted")
|
||||||
@@ -184,7 +187,11 @@ class TestMailMessageGpgDecryptor(TestMail):
|
|||||||
EMAIL_GNUPG_HOME=empty_gpg_home,
|
EMAIL_GNUPG_HOME=empty_gpg_home,
|
||||||
):
|
):
|
||||||
message_decryptor = MailMessageDecryptor()
|
message_decryptor = MailMessageDecryptor()
|
||||||
self.assertRaises(Exception, message_decryptor.run, encrypted_message)
|
self.assertRaises(
|
||||||
|
MailDecryptionError,
|
||||||
|
message_decryptor.run,
|
||||||
|
encrypted_message,
|
||||||
|
)
|
||||||
finally:
|
finally:
|
||||||
# Clean up the temporary GPG home used only by this test
|
# Clean up the temporary GPG home used only by this test
|
||||||
try:
|
try:
|
||||||
|
|||||||
@@ -1,4 +1,3 @@
|
|||||||
import datetime
|
|
||||||
import logging
|
import logging
|
||||||
from datetime import timedelta
|
from datetime import timedelta
|
||||||
from http import HTTPStatus
|
from http import HTTPStatus
|
||||||
@@ -87,7 +86,7 @@ class MailAccountViewSet(PassUserMixin, ModelViewSet[MailAccount]):
|
|||||||
@action(methods=["post"], detail=False)
|
@action(methods=["post"], detail=False)
|
||||||
def test(self, request):
|
def test(self, request):
|
||||||
logger = logging.getLogger("paperless_mail")
|
logger = logging.getLogger("paperless_mail")
|
||||||
request.data["name"] = datetime.datetime.now().isoformat()
|
request.data["name"] = timezone.now().isoformat()
|
||||||
serializer = self.get_serializer(data=request.data)
|
serializer = self.get_serializer(data=request.data)
|
||||||
serializer.is_valid(raise_exception=True)
|
serializer.is_valid(raise_exception=True)
|
||||||
existing_account = None
|
existing_account = None
|
||||||
|
|||||||
Reference in New Issue
Block a user