Compare commits

...
Author SHA1 Message Date
stumpylog cdda191f91 Feature: Allow configuring the compression type and compression levels during export
Building on the zip export improvements, this now allows users to further configure the
zip to fit their needs.  A simple stored zip for speed, or a high compression zstd for
the smallest archive.  Full validation of the method and levels at the command line
2026-08-09 15:27:10 -07:00
Trenton HandGitHub c28c532bef Fix: check bulk mail delete permissions for the whole batch up front (#13620)
ProcessedMailViewSet.bulk_delete checked permissions inside the delete loop, so an unpermitted id returned 403 only after the mails ahead of it had already been deleted. Resolve the permitted set once via permitted_object_ids and reject before deleting anything, which also drops the per-mail permission queries.
2026-08-09 13:55:49 +00:00
GitHub Actions 1d61f7fc62 Auto translate strings 2026-08-09 07:16:59 +00:00
shamoonandGitHub aa67fd3aef Tweak: improve no ML suggestions UX (#13621) 2026-08-09 00:15:27 -07:00
Trenton HandGitHub 17dc482872 Fix: Allow DRF to validate the maximum API key length (#13614) 2026-08-08 19:51:27 +00:00
GitHub Actions b0e0e8a353 Auto translate strings 2026-08-08 14:29:01 +00:00
17 changed files with 777 additions and 34 deletions
+15
View File
@@ -299,6 +299,8 @@ optional arguments:
-sm, --split-manifest -sm, --split-manifest
-z, --zip -z, --zip
-zn, --zip-name -zn, --zip-name
--zip-compression
--zip-compression-level
--data-only --data-only
--no-progress-bar --no-progress-bar
--passphrase --passphrase
@@ -361,6 +363,19 @@ If `-z` or `--zip` is provided, the export will be a zip file
in the target directory, named according to the current local date or the in the target directory, named according to the current local date or the
value set in `-zn` or `--zip-name`. value set in `-zn` or `--zip-name`.
The compression method for the zip can be set with `--zip-compression`
(`stored`, `deflated` (default), `bzip2`, `lzma`, or `zstd`) and tuned with
`--zip-compression-level` (deflated: 09, bzip2: 19, zstd: -2222; ignored
for `stored` and `lzma`). Both options require `--zip`.
!!! warning
`zstd` compression requires Python 3.14 or newer on **both** the machine
creating the export and any machine importing it. An archive compressed with
`zstd` (or `lzma`/`bzip2` where those modules are unavailable) cannot be
imported on a runtime that lacks the codec; the importer will refuse it with
a clear error. The default `deflated` is universally readable.
If `--data-only` is provided, only the database will be exported. This option is intended If `--data-only` is provided, only the database will be exported. This option is intended
to facilitate database upgrades without needing to clean documents and thumbnails from the media directory. to facilitate database upgrades without needing to clean documents and thumbnails from the media directory.
+13 -6
View File
@@ -1703,7 +1703,7 @@
</context-group> </context-group>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context> <context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">28</context> <context context-type="linenumber">34</context>
</context-group> </context-group>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context> <context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
@@ -3279,7 +3279,7 @@
</context-group> </context-group>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context> <context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">40</context> <context context-type="linenumber">46</context>
</context-group> </context-group>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context> <context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
@@ -7070,32 +7070,39 @@
<context context-type="linenumber">143</context> <context context-type="linenumber">143</context>
</context-group> </context-group>
</trans-unit> </trans-unit>
<trans-unit id="8336346011691074629" datatype="html">
<source>No suggestions</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">11,12</context>
</context-group>
</trans-unit>
<trans-unit id="5320136382998259826" datatype="html"> <trans-unit id="5320136382998259826" datatype="html">
<source>Suggest</source> <source>Suggest</source>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context> <context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">8,9</context> <context context-type="linenumber">13,14</context>
</context-group> </context-group>
</trans-unit> </trans-unit>
<trans-unit id="6934085657687954669" datatype="html"> <trans-unit id="6934085657687954669" datatype="html">
<source>Show suggestions</source> <source>Show suggestions</source>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context> <context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">17,18</context> <context context-type="linenumber">23,24</context>
</context-group> </context-group>
</trans-unit> </trans-unit>
<trans-unit id="3834115140127576673" datatype="html"> <trans-unit id="3834115140127576673" datatype="html">
<source>No novel suggestions</source> <source>No novel suggestions</source>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context> <context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">24,25</context> <context context-type="linenumber">30,31</context>
</context-group> </context-group>
</trans-unit> </trans-unit>
<trans-unit id="4369111787961525769" datatype="html"> <trans-unit id="4369111787961525769" datatype="html">
<source>Document Types</source> <source>Document Types</source>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context> <context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
<context context-type="linenumber">34</context> <context context-type="linenumber">40</context>
</context-group> </context-group>
<context-group purpose="location"> <context-group purpose="location">
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context> <context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
@@ -2,10 +2,16 @@
<button type="button" class="btn btn-sm btn-outline-primary" (click)="clickSuggest()" [disabled]="disabled() || loading() || (suggestions() && !aiEnabled())"> <button type="button" class="btn btn-sm btn-outline-primary" (click)="clickSuggest()" [disabled]="disabled() || loading() || (suggestions() && !aiEnabled())">
@if (loading()) { @if (loading()) {
<div class="spinner-border spinner-border-sm" role="status"></div> <div class="spinner-border spinner-border-sm" role="status"></div>
} @else if (noSuggestions) {
<i-bs width="1.2em" height="1.2em" name="check-circle"></i-bs>
} @else { } @else {
<i-bs width="1.2em" height="1.2em" name="stars"></i-bs> <i-bs width="1.2em" height="1.2em" name="stars"></i-bs>
} }
<span class="d-none d-lg-inline ps-1" i18n>Suggest</span> @if (noSuggestions) {
<span class="d-none d-lg-inline ps-1" i18n>No suggestions</span>
} @else {
<span class="d-none d-lg-inline ps-1" i18n>Suggest</span>
}
@if (totalSuggestions > 0) { @if (totalSuggestions > 0) {
<span class="badge bg-primary ms-2">{{ totalSuggestions }}</span> <span class="badge bg-primary ms-2">{{ totalSuggestions }}</span>
} }
@@ -19,7 +25,7 @@
<div ngbDropdownMenu aria-labelledby="suggestionsDropdown" class="shadow suggestions-dropdown"> <div ngbDropdownMenu aria-labelledby="suggestionsDropdown" class="shadow suggestions-dropdown">
<div class="list-group list-group-flush small pb-0"> <div class="list-group list-group-flush small pb-0">
@if (!suggestions()?.suggested_tags && !suggestions()?.suggested_document_types && !suggestions()?.suggested_correspondents) { @if (totalSuggestions === 0) {
<div class="list-group-item text-muted fst-italic"> <div class="list-group-item text-muted fst-italic">
<small class="text-muted small fst-italic" i18n>No novel suggestions</small> <small class="text-muted small fst-italic" i18n>No novel suggestions</small>
</div> </div>
@@ -30,6 +30,34 @@ describe('SuggestionsDropdownComponent', () => {
expect(component.totalSuggestions).toBe(4) expect(component.totalSuggestions).toBe(4)
}) })
it('should show when a completed request returned no suggestions', () => {
fixture.componentRef.setInput('suggestions', {
correspondents: [],
tags: [],
document_types: [],
storage_paths: [],
dates: [],
})
fixture.detectChanges()
expect(component.noSuggestions).toBeTruthy()
expect(fixture.nativeElement.textContent).toContain('No suggestions')
})
it('should not show the empty state before a request or with suggestions', () => {
expect(component.noSuggestions).toBeFalsy()
fixture.componentRef.setInput('suggestions', {
correspondents: [],
tags: [42],
document_types: [],
storage_paths: [],
dates: [],
})
expect(component.noSuggestions).toBeFalsy()
})
it('should emit getSuggestions when clickSuggest is called and suggestions are null', () => { it('should emit getSuggestions when clickSuggest is called and suggestions are null', () => {
jest.spyOn(component.getSuggestions, 'emit') jest.spyOn(component.getSuggestions, 'emit')
fixture.componentRef.setInput('suggestions', null) fixture.componentRef.setInput('suggestions', null)
@@ -59,5 +87,6 @@ describe('SuggestionsDropdownComponent', () => {
}) })
component.clickSuggest() component.clickSuggest()
expect(component.dropdown.open).toBeTruthy() expect(component.dropdown.open).toBeTruthy()
expect(fixture.nativeElement.textContent).toContain('No novel suggestions')
}) })
}) })
@@ -61,4 +61,21 @@ export class SuggestionsDropdownComponent {
this.suggestions()?.suggested_document_types?.length || 0 this.suggestions()?.suggested_document_types?.length || 0
) )
} }
get noSuggestions(): boolean {
const suggestions = this.suggestions()
return (
suggestions != null &&
!suggestions.title &&
!suggestions.tags?.length &&
!suggestions.suggested_tags?.length &&
!suggestions.correspondents?.length &&
!suggestions.suggested_correspondents?.length &&
!suggestions.document_types?.length &&
!suggestions.suggested_document_types?.length &&
!suggestions.storage_paths?.length &&
!suggestions.suggested_storage_paths?.length &&
!suggestions.dates?.length
)
}
} }
+108
View File
@@ -0,0 +1,108 @@
from __future__ import annotations
import importlib
import zipfile
# ZIP_ZSTANDARD exists only on Python 3.14+ (PEP 784). None elsewhere.
ZSTD: int | None = getattr(zipfile, "ZIP_ZSTANDARD", None)
# CLI choices are fixed across runtimes so argparse never hides zstd; runtime
# availability is enforced separately in compression_available().
COMPRESSION_CHOICES: tuple[str, ...] = (
"stored",
"deflated",
"bzip2",
"lzma",
"zstd",
)
# Method name -> zipfile compression constant (zstd only when supported).
COMPRESSION_METHODS: dict[str, int] = {
"stored": zipfile.ZIP_STORED,
"deflated": zipfile.ZIP_DEFLATED,
"bzip2": zipfile.ZIP_BZIP2,
"lzma": zipfile.ZIP_LZMA,
}
if ZSTD is not None:
COMPRESSION_METHODS["zstd"] = ZSTD
# Inclusive (min, max) level bounds per method; None => level not applicable.
# Verified on CPython 3.14.3.
#
# zstd's raw library bounds are (-131072, 22)
# (compression.zstd.CompressionParameter.compression_level.bounds()) — the
# minimum is an internal implementation constant (-ZSTD_TARGETLENGTH_MAX),
# not a meaningful distinct "level"; deeper negative values than -22 buy
# nothing over -22 in practice. We expose the conventional zstd CLI range
# instead of the raw library bounds.
LEVEL_BOUNDS: dict[str, tuple[int, int] | None] = {
"stored": None,
"deflated": (0, 9),
"bzip2": (1, 9),
"lzma": None,
"zstd": (-22, 22),
}
# zipfile compress_type id -> method name. 93 = current zstd id, 20 = legacy
# zstd id that zipfile can still read.
_COMPRESS_TYPE_TO_METHOD: dict[int, str] = {
zipfile.ZIP_STORED: "stored",
zipfile.ZIP_DEFLATED: "deflated",
zipfile.ZIP_BZIP2: "bzip2",
zipfile.ZIP_LZMA: "lzma",
93: "zstd",
20: "zstd",
}
def compression_available(method: str) -> bool:
"""Whether the running interpreter can actually use the given method."""
if method in ("stored", "deflated"):
# zlib is a hard CPython dependency; stored needs nothing.
return True
if method == "bzip2":
return _module_importable("bz2")
if method == "lzma":
return _module_importable("lzma")
if method == "zstd":
return ZSTD is not None and _module_importable("compression.zstd")
return False
def _module_importable(name: str) -> bool:
try:
importlib.import_module(name)
except ImportError:
return False
return True
def level_error(method: str, level: int | None) -> str | None:
"""Return a human message if (method, level) is invalid, else None."""
if level is None:
return None
bounds = LEVEL_BOUNDS[method]
if bounds is None:
return f"--zip-compression-level has no effect for '{method}'"
low, high = bounds
if not (low <= level <= high):
return (
f"--zip-compression-level for '{method}' must be between {low} and {high}"
)
return None
def compress_type_readable(compress_type: int) -> bool:
"""Whether this interpreter can decompress an entry of the given type."""
method = _COMPRESS_TYPE_TO_METHOD.get(compress_type)
if method is None:
return False
return compression_available(method)
def unreadable_method_names(compress_types: set[int]) -> set[str]:
"""Map a set of compress_type ids to human method names for error messages."""
names: set[str] = set()
for ct in compress_types:
names.add(_COMPRESS_TYPE_TO_METHOD.get(ct, f"method {ct}"))
return names
+13 -2
View File
@@ -243,11 +243,21 @@ class ZipExportSink(ExportSink):
added as an entry at finalize (a zip entry cannot be interleaved with others). added as an entry at finalize (a zip entry cannot be interleaved with others).
""" """
def __init__(self, target: Path, zip_name: str, *, delete: bool = False) -> None: def __init__(
self,
target: Path,
zip_name: str,
*,
delete: bool = False,
compression: int = zipfile.ZIP_DEFLATED,
compresslevel: int | None = None,
) -> None:
self._target = target.resolve() self._target = target.resolve()
self._zip_path = (self._target / zip_name).with_suffix(".zip") self._zip_path = (self._target / zip_name).with_suffix(".zip")
self._tmp_path = self._zip_path.with_name(self._zip_path.name + ".tmp") self._tmp_path = self._zip_path.with_name(self._zip_path.name + ".tmp")
self._delete = delete self._delete = delete
self._compression = compression
self._compresslevel = compresslevel
self._zip: zipfile.ZipFile | None = None self._zip: zipfile.ZipFile | None = None
self._dirs: set[str] = set() self._dirs: set[str] = set()
self._pending_manifest: tuple[Path, str] | None = None self._pending_manifest: tuple[Path, str] | None = None
@@ -258,7 +268,8 @@ class ZipExportSink(ExportSink):
self._zip = zipfile.ZipFile( self._zip = zipfile.ZipFile(
self._tmp_path, self._tmp_path,
"w", "w",
compression=zipfile.ZIP_DEFLATED, compression=self._compression,
compresslevel=self._compresslevel,
allowZip64=True, allowZip64=True,
) )
@@ -29,6 +29,11 @@ if TYPE_CHECKING:
if settings.AUDIT_LOG_ENABLED: if settings.AUDIT_LOG_ENABLED:
from auditlog.models import LogEntry from auditlog.models import LogEntry
from documents.export.compression import COMPRESSION_CHOICES
from documents.export.compression import COMPRESSION_METHODS
from documents.export.compression import ZSTD
from documents.export.compression import compression_available
from documents.export.compression import level_error
from documents.export.sinks import DirectoryExportSink from documents.export.sinks import DirectoryExportSink
from documents.export.sinks import ExportSink from documents.export.sinks import ExportSink
from documents.export.sinks import StreamingManifestWriter from documents.export.sinks import StreamingManifestWriter
@@ -192,6 +197,28 @@ class Command(CryptMixin, PaperlessCommand):
help="Sets the export zip file name", help="Sets the export zip file name",
) )
parser.add_argument(
"--zip-compression",
choices=COMPRESSION_CHOICES,
default=None,
help=(
"Compression method for the export zip (requires --zip). "
"Default: deflated. 'zstd' requires Python 3.14+ on both the "
"exporting and importing machine."
),
)
parser.add_argument(
"--zip-compression-level",
type=int,
default=None,
help=(
"Compression level for the export zip (requires --zip). "
"deflated: 0-9, bzip2: 1-9, zstd: -22..22; ignored for "
"stored/lzma."
),
)
parser.add_argument( parser.add_argument(
"--data-only", "--data-only",
default=False, default=False,
@@ -247,12 +274,39 @@ class Command(CryptMixin, PaperlessCommand):
if not os.access(self.target, os.W_OK): if not os.access(self.target, os.W_OK):
raise CommandError("That path doesn't appear to be writable") raise CommandError("That path doesn't appear to be writable")
zip_compression: str | None = options["zip_compression"]
zip_compression_level: int | None = options["zip_compression_level"]
if not self.zip_export and (
zip_compression is not None or zip_compression_level is not None
):
raise CommandError(
"--zip-compression and --zip-compression-level require --zip",
)
compression_method = zip_compression or "deflated"
if self.zip_export:
if not compression_available(compression_method):
if compression_method == "zstd" and ZSTD is None:
raise CommandError(
"zstd compression requires Python 3.14 or newer",
)
raise CommandError(
f"Compression method '{compression_method}' is not "
f"available on this Python runtime",
)
level_msg = level_error(compression_method, zip_compression_level)
if level_msg is not None:
raise CommandError(level_msg)
sink: ExportSink sink: ExportSink
if self.zip_export: if self.zip_export:
sink = ZipExportSink( sink = ZipExportSink(
self.target, self.target,
options["zip_name"], options["zip_name"],
delete=self.delete, delete=self.delete,
compression=COMPRESSION_METHODS[compression_method],
compresslevel=zip_compression_level,
) )
else: else:
sink = DirectoryExportSink( sink = DirectoryExportSink(
@@ -32,6 +32,8 @@ from django.db.models.signals import post_save
from filelock import FileLock from filelock import FileLock
from guardian.shortcuts import clear_ct_cache from guardian.shortcuts import clear_ct_cache
from documents.export.compression import compress_type_readable
from documents.export.compression import unreadable_method_names
from documents.file_handling import create_source_path_directory from documents.file_handling import create_source_path_directory
from documents.management.commands.base import PaperlessCommand from documents.management.commands.base import PaperlessCommand
from documents.management.commands.mixins import CryptMixin from documents.management.commands.mixins import CryptMixin
@@ -460,6 +462,20 @@ class Command(CryptMixin, PaperlessCommand):
with tempfile.TemporaryDirectory() as tmp_dir: with tempfile.TemporaryDirectory() as tmp_dir:
if is_zipfile(self.source): if is_zipfile(self.source):
with ZipFile(self.source) as zf: with ZipFile(self.source) as zf:
unsupported = {
info.compress_type
for info in zf.infolist()
if not compress_type_readable(info.compress_type)
}
if unsupported:
names = sorted(unreadable_method_names(unsupported))
message = (
f"This archive uses compression this Python cannot "
f"read ({', '.join(names)})."
)
if "zstd" in names:
message += " zstd archives require Python 3.14+."
raise CommandError(message)
zf.extractall(tmp_dir) zf.extractall(tmp_dir)
self.source = Path(tmp_dir) self.source = Path(tmp_dir)
self._run_import() self._run_import()
@@ -0,0 +1,190 @@
import sys
import zipfile
import pytest
from documents.export import compression
class TestCompressionMethods:
def test_choices_always_include_zstd(self) -> None:
"""
GIVEN:
- The compression policy module's CLI choices list
WHEN:
- Read on any runtime
THEN:
- zstd is always present; availability is checked separately so
argparse never hides it based on the current Python version
"""
assert compression.COMPRESSION_CHOICES == (
"stored",
"deflated",
"bzip2",
"lzma",
"zstd",
)
@pytest.mark.parametrize(
("name", "constant"),
[
("stored", zipfile.ZIP_STORED),
("deflated", zipfile.ZIP_DEFLATED),
("bzip2", zipfile.ZIP_BZIP2),
("lzma", zipfile.ZIP_LZMA),
],
)
def test_method_maps_to_zipfile_constant(self, name: str, constant: int) -> None:
"""
GIVEN:
- A compression method name
WHEN:
- Looked up in COMPRESSION_METHODS
THEN:
- It maps to the matching zipfile compression constant
"""
assert compression.COMPRESSION_METHODS[name] == constant
def test_stored_and_deflated_always_available(self) -> None:
"""
GIVEN:
- The stored and deflated compression methods
WHEN:
- Checked with compression_available()
THEN:
- Both are always available (zlib is a hard CPython dependency)
"""
assert compression.compression_available("stored")
assert compression.compression_available("deflated")
def test_zstd_availability_tracks_runtime(self) -> None:
"""
GIVEN:
- The zstd compression method
WHEN:
- Checked with compression_available() on this runtime
THEN:
- Availability matches whether Python is 3.14+
"""
expected: bool = sys.version_info >= (3, 14)
assert compression.compression_available("zstd") == expected
class TestLevelError:
@pytest.mark.parametrize(
("method", "level"),
[
("deflated", 0),
("deflated", 9),
("bzip2", 1),
("bzip2", 9),
("zstd", -22),
("zstd", 22),
("deflated", None),
("stored", None),
],
)
def test_valid_levels_return_none(self, method: str, level: int | None) -> None:
"""
GIVEN:
- A method and a level within its valid bounds (or no level)
WHEN:
- Checked with level_error()
THEN:
- No error message is returned
"""
assert compression.level_error(method, level) is None
@pytest.mark.parametrize(
("method", "level"),
[
("deflated", 10),
("deflated", -1),
("bzip2", 0),
("bzip2", 10),
("zstd", -23),
("zstd", 23),
],
)
def test_out_of_range_levels_return_message(
self,
method: str,
level: int,
) -> None:
"""
GIVEN:
- A method and a level outside its valid bounds
WHEN:
- Checked with level_error()
THEN:
- An error message naming the valid range is returned
"""
msg: str | None = compression.level_error(method, level)
assert msg is not None
assert "between" in msg
@pytest.mark.parametrize("method", ["stored", "lzma"])
def test_level_on_levelless_method_is_rejected(self, method: str) -> None:
"""
GIVEN:
- A method that ignores compression level (stored, lzma)
WHEN:
- A level is passed to level_error() anyway
THEN:
- An error message noting the level has no effect is returned
"""
msg: str | None = compression.level_error(method, 5)
assert msg is not None
assert "no effect" in msg
class TestCompressTypeReadable:
@pytest.mark.parametrize("ct", [zipfile.ZIP_STORED, zipfile.ZIP_DEFLATED])
def test_stored_and_deflated_always_readable(self, ct: int) -> None:
"""
GIVEN:
- A stored or deflated compress_type id
WHEN:
- Checked with compress_type_readable()
THEN:
- It is always readable
"""
assert compression.compress_type_readable(ct)
def test_zstd_compress_type_readability_tracks_runtime(self) -> None:
"""
GIVEN:
- The current (93) and legacy (20) zstd compress_type ids
WHEN:
- Checked with compress_type_readable() on this runtime
THEN:
- Readability matches whether Python is 3.14+
"""
# 93 = ZIP_ZSTANDARD; 20 = legacy zstd method id (read-only)
expected: bool = sys.version_info >= (3, 14)
assert compression.compress_type_readable(93) == expected
assert compression.compress_type_readable(20) == expected
def test_unknown_compress_type_is_unreadable(self) -> None:
"""
GIVEN:
- An unrecognized compress_type id
WHEN:
- Checked with compress_type_readable()
THEN:
- It is reported as unreadable
"""
assert not compression.compress_type_readable(9999)
def test_unreadable_method_names_lists_methods(self) -> None:
"""
GIVEN:
- A set containing an unknown compress_type id
WHEN:
- Passed to unreadable_method_names()
THEN:
- It is reported generically as "method <id>"
"""
# An unknown method id maps to no name and is reported generically.
names: set[str] = compression.unreadable_method_names({9999})
assert names == {"method 9999"}
+43
View File
@@ -5,6 +5,7 @@ import zipfile
from pathlib import Path from pathlib import Path
import pytest import pytest
import pytest_mock
from pytest_django.fixtures import SettingsWrapper from pytest_django.fixtures import SettingsWrapper
from documents.export.sinks import DirectoryExportSink from documents.export.sinks import DirectoryExportSink
@@ -305,6 +306,48 @@ class TestZipExportSink:
assert not (target / "export.zip").exists() assert not (target / "export.zip").exists()
class TestZipExportSinkCompression:
@pytest.mark.parametrize(
("method", "constant"),
[
("stored", zipfile.ZIP_STORED),
("deflated", zipfile.ZIP_DEFLATED),
("bzip2", zipfile.ZIP_BZIP2),
("lzma", zipfile.ZIP_LZMA),
],
)
def test_compression_and_level_forwarded_to_zipfile(
self,
mocker: pytest_mock.MockerFixture,
tmp_path: Path,
method: str,
constant: int,
) -> None:
"""
GIVEN:
- A ZipExportSink constructed with a compression method and level
WHEN:
- The sink is opened
THEN:
- zipfile.ZipFile is constructed with those values forwarded
unchanged (whether ZipFile actually compresses is Python's own
contract, not ours, so this checks the call args, not a real
archive)
"""
target: Path = tmp_path / "out"
target.mkdir()
zip_cls = mocker.patch("documents.export.sinks.zipfile.ZipFile")
sink = ZipExportSink(target, "export", compression=constant, compresslevel=5)
sink._open()
zip_cls.assert_called_once_with(
mocker.ANY,
"w",
compression=constant,
compresslevel=5,
allowZip64=True,
)
class TestStreamContract: class TestStreamContract:
@pytest.fixture(params=["dir", "zip"]) @pytest.fixture(params=["dir", "zip"])
def sink(self, request: pytest.FixtureRequest, tmp_path: Path) -> ExportSink: def sink(self, request: pytest.FixtureRequest, tmp_path: Path) -> ExportSink:
@@ -6,6 +6,8 @@ from datetime import timedelta
from io import StringIO from io import StringIO
from pathlib import Path from pathlib import Path
from unittest import mock from unittest import mock
from zipfile import ZIP_DEFLATED
from zipfile import ZIP_LZMA
from zipfile import ZipFile from zipfile import ZipFile
import pytest import pytest
@@ -1078,6 +1080,186 @@ class TestExportImport(
skip_checks=True, skip_checks=True,
) )
def test_compression_flags_require_zip(self) -> None:
"""
GIVEN:
- A request to export without --zip
WHEN:
- --zip-compression or --zip-compression-level is passed anyway
THEN:
- A CommandError is raised (the flags are meaningless without --zip)
"""
for args in (
["--zip-compression", "lzma"],
["--zip-compression-level", "5"],
):
with self.assertRaises(CommandError):
call_command(
"document_exporter",
self.target,
*args,
skip_checks=True,
)
def test_zip_compression_level_out_of_range_raises(self) -> None:
"""
GIVEN:
- A request to export to a zip file
WHEN:
- --zip-compression-level is outside the chosen method's valid range
THEN:
- A CommandError is raised
"""
with self.assertRaises(CommandError):
call_command(
"document_exporter",
self.target,
"--zip",
"--zip-compression",
"deflated",
"--zip-compression-level",
"99",
skip_checks=True,
)
def test_zip_compression_level_rejected_for_stored(self) -> None:
"""
GIVEN:
- A request to export to a zip file with --zip-compression stored
WHEN:
- --zip-compression-level is also passed
THEN:
- A CommandError is raised (stored ignores level entirely)
"""
with self.assertRaises(CommandError):
call_command(
"document_exporter",
self.target,
"--zip",
"--zip-compression",
"stored",
"--zip-compression-level",
"5",
skip_checks=True,
)
def test_zip_compression_level_rejected_for_lzma(self) -> None:
"""
GIVEN:
- A request to export to a zip file with --zip-compression lzma
WHEN:
- --zip-compression-level is also passed
THEN:
- A CommandError is raised (lzma ignores level entirely)
"""
with self.assertRaises(CommandError):
call_command(
"document_exporter",
self.target,
"--zip",
"--zip-compression",
"lzma",
"--zip-compression-level",
"5",
skip_checks=True,
)
def test_zstd_unavailable_raises_friendly_error(self) -> None:
"""
GIVEN:
- A Python runtime without zstd support (< 3.14)
WHEN:
- --zip-compression zstd is requested
THEN:
- A CommandError naming the Python version requirement is raised
zstd availability is mocked rather than relying on the actual
runtime: on a Python 3.14+ CI leg, ZSTD is not None, so without the
mock this check is skipped and the command falls through into the
real export, which fails on missing document files instead of
raising the expected CommandError.
"""
with (
mock.patch(
"documents.management.commands.document_exporter.ZSTD",
None,
),
mock.patch(
"documents.management.commands.document_exporter.compression_available",
return_value=False,
),
self.assertRaises(CommandError) as e,
):
call_command(
"document_exporter",
self.target,
"--zip",
"--zip-compression",
"zstd",
skip_checks=True,
)
self.assertIn("3.14", str(e.exception))
def test_zip_compression_flag_resolves_to_sink_constant(self) -> None:
"""
GIVEN:
- A request to export to a zip file with --zip-compression lzma
WHEN:
- The export runs
THEN:
- ZipExportSink is constructed with the resolved ZIP_LZMA constant
(whether zipfile actually compresses with the chosen method is
Python's own contract, and ZipExportSink's own tests already
cover the forwarding; what this command owns is resolving the
CLI string to the right constant, so assert that resolution
directly)
"""
with mock.patch(
"documents.management.commands.document_exporter.ZipExportSink",
) as sink_cls:
call_command(
"document_exporter",
self.target,
"--zip",
"--zip-compression",
"lzma",
skip_checks=True,
)
sink_cls.assert_called_once_with(
mock.ANY,
mock.ANY,
delete=False,
compression=ZIP_LZMA,
compresslevel=None,
)
def test_default_zip_compression_resolves_to_deflate(self) -> None:
"""
GIVEN:
- A request to export to a zip file with no --zip-compression flag
WHEN:
- The export runs
THEN:
- ZipExportSink is constructed with the default ZIP_DEFLATED
constant and compresslevel=None, matching pre-existing behavior
"""
with mock.patch(
"documents.management.commands.document_exporter.ZipExportSink",
) as sink_cls:
call_command(
"document_exporter",
self.target,
"--zip",
skip_checks=True,
)
sink_cls.assert_called_once_with(
mock.ANY,
mock.ANY,
delete=False,
compression=ZIP_DEFLATED,
compresslevel=None,
)
@pytest.mark.management @pytest.mark.management
class TestCryptExportImport( class TestCryptExportImport(
@@ -525,6 +525,35 @@ class TestCommandImport(
self.assertEqual(doc.tags.count(), 1) self.assertEqual(doc.tags.count(), 1)
self.assertEqual(doc.tags.first().name, "batch-flush-tag") self.assertEqual(doc.tags.first().name, "batch-flush-tag")
def test_import_rejects_unreadable_compression(self) -> None:
"""
GIVEN:
- A zip archive with an entry whose compression this Python can't read
WHEN:
- Import is attempted
THEN:
- A CommandError naming the issue is raised, before extraction
"""
import zipfile
from unittest import mock
archive = Path(self.dirs.scratch_dir) / "export.zip"
with zipfile.ZipFile(archive, "w") as zf:
zf.writestr("manifest.json", "[]")
with mock.patch(
"documents.management.commands.document_importer.compress_type_readable",
return_value=False,
):
with self.assertRaises(CommandError) as e:
call_command(
"document_importer",
str(archive),
"--no-progress-bar",
skip_checks=True,
)
self.assertIn("compression", str(e.exception))
@pytest.mark.management @pytest.mark.management
@pytest.mark.django_db @pytest.mark.django_db
+20 -20
View File
@@ -2,7 +2,7 @@ msgid ""
msgstr "" msgstr ""
"Project-Id-Version: paperless-ngx\n" "Project-Id-Version: paperless-ngx\n"
"Report-Msgid-Bugs-To: \n" "Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2026-08-07 20:00+0000\n" "POT-Creation-Date: 2026-08-08 14:28+0000\n"
"PO-Revision-Date: 2022-02-17 04:17\n" "PO-Revision-Date: 2022-02-17 04:17\n"
"Last-Translator: \n" "Last-Translator: \n"
"Language-Team: English\n" "Language-Team: English\n"
@@ -21,39 +21,39 @@ msgstr ""
msgid "Documents" msgid "Documents"
msgstr "" msgstr ""
#: documents/filters.py:472 #: documents/filters.py:471
msgid "Value must be valid JSON." msgid "Value must be valid JSON."
msgstr "" msgstr ""
#: documents/filters.py:491 #: documents/filters.py:490
msgid "Invalid custom field query expression" msgid "Invalid custom field query expression"
msgstr "" msgstr ""
#: documents/filters.py:501 #: documents/filters.py:500
msgid "Invalid expression list. Must be nonempty." msgid "Invalid expression list. Must be nonempty."
msgstr "" msgstr ""
#: documents/filters.py:522 #: documents/filters.py:521
msgid "Invalid logical operator {op!r}" msgid "Invalid logical operator {op!r}"
msgstr "" msgstr ""
#: documents/filters.py:536 #: documents/filters.py:535
msgid "Maximum number of query conditions exceeded." msgid "Maximum number of query conditions exceeded."
msgstr "" msgstr ""
#: documents/filters.py:600 #: documents/filters.py:599
msgid "{name!r} is not a valid custom field." msgid "{name!r} is not a valid custom field."
msgstr "" msgstr ""
#: documents/filters.py:637 #: documents/filters.py:636
msgid "{data_type} does not support query expr {expr!r}." msgid "{data_type} does not support query expr {expr!r}."
msgstr "" msgstr ""
#: documents/filters.py:756 documents/models.py:136 #: documents/filters.py:755 documents/models.py:136
msgid "Maximum nesting depth exceeded." msgid "Maximum nesting depth exceeded."
msgstr "" msgstr ""
#: documents/filters.py:1098 #: documents/filters.py:1073
msgid "Custom field not found" msgid "Custom field not found"
msgstr "" msgstr ""
@@ -1352,7 +1352,7 @@ msgid "workflow runs"
msgstr "" msgstr ""
#: documents/serialisers.py:521 documents/serialisers.py:873 #: documents/serialisers.py:521 documents/serialisers.py:873
#: documents/serialisers.py:2767 documents/views.py:300 documents/views.py:2556 #: documents/serialisers.py:2767 documents/views.py:299 documents/views.py:2555
#: paperless_mail/serialisers.py:155 #: paperless_mail/serialisers.py:155
msgid "Insufficient permissions." msgid "Insufficient permissions."
msgstr "" msgstr ""
@@ -1393,7 +1393,7 @@ msgstr ""
msgid "Duplicate document identifiers are not allowed." msgid "Duplicate document identifiers are not allowed."
msgstr "" msgstr ""
#: documents/serialisers.py:2853 documents/views.py:4510 #: documents/serialisers.py:2853 documents/views.py:4509
#, python-format #, python-format
msgid "Documents not found: %(ids)s" msgid "Documents not found: %(ids)s"
msgstr "" msgstr ""
@@ -1661,36 +1661,36 @@ msgstr ""
msgid "Unable to parse URI {value}" msgid "Unable to parse URI {value}"
msgstr "" msgstr ""
#: documents/views.py:293 documents/views.py:2553 #: documents/views.py:292 documents/views.py:2552
msgid "Invalid more_like_id" msgid "Invalid more_like_id"
msgstr "" msgstr ""
#: documents/views.py:1567 #: documents/views.py:1566
msgid "Invalid AI configuration." msgid "Invalid AI configuration."
msgstr "" msgstr ""
#: documents/views.py:1576 #: documents/views.py:1575
msgid "AI backend request timed out." msgid "AI backend request timed out."
msgstr "" msgstr ""
#: documents/views.py:2378 documents/views.py:2699 #: documents/views.py:2377 documents/views.py:2698
msgid "Specify only one of text, title_search, query, or more_like_id." msgid "Specify only one of text, title_search, query, or more_like_id."
msgstr "" msgstr ""
#: documents/views.py:4523 #: documents/views.py:4522
#, python-format #, python-format
msgid "Insufficient permissions to share document %(id)s." msgid "Insufficient permissions to share document %(id)s."
msgstr "" msgstr ""
#: documents/views.py:4569 #: documents/views.py:4568
msgid "Bundle is already being processed." msgid "Bundle is already being processed."
msgstr "" msgstr ""
#: documents/views.py:4630 #: documents/views.py:4629
msgid "The share link bundle is still being prepared. Please try again later." msgid "The share link bundle is still being prepared. Please try again later."
msgstr "" msgstr ""
#: documents/views.py:4640 #: documents/views.py:4639
msgid "The share link bundle is unavailable." msgid "The share link bundle is unavailable."
msgstr "" msgstr ""
+1
View File
@@ -217,6 +217,7 @@ class ApplicationConfigurationSerializer(
llm_api_key = ObfuscatedPasswordField( llm_api_key = ObfuscatedPasswordField(
required=False, required=False,
allow_null=True, allow_null=True,
max_length=1024,
) )
def run_validation(self, data): def run_validation(self, data):
+27
View File
@@ -757,3 +757,30 @@ class TestAPIProcessedMails(DirectoriesMixin, APITestCase):
format="json", format="json",
) )
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
def test_bulk_delete_processed_mails_rejects_mixed_batch_atomically(self) -> None:
"""
GIVEN:
- A permitted processed mail and one the user may not delete
WHEN:
- API call bulk deletes both in a single request
THEN:
- The request is rejected and neither mail is deleted
"""
user2 = User.objects.create_user(username="temp_admin2")
rule = MailRuleFactory()
# Created first so it sorts ahead of the forbidden mail, i.e. the
# permission check has to cover the whole batch before deleting rather
# than rejecting only once it reaches the forbidden one.
pm_owned = ProcessedMailFactory(rule=rule, owner=self.user)
pm_forbidden = ProcessedMailFactory(rule=rule, owner=user2)
response = self.client.post(
f"{self.ENDPOINT}bulk_delete/",
data={"mail_ids": [pm_owned.id, pm_forbidden.id]},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
self.assertTrue(ProcessedMail.objects.filter(id=pm_owned.id).exists())
self.assertTrue(ProcessedMail.objects.filter(id=pm_forbidden.id).exists())
+12 -4
View File
@@ -27,6 +27,7 @@ from documents.filters import PermittedObjectsFilter
from documents.models import PaperlessTask from documents.models import PaperlessTask
from documents.permissions import PaperlessObjectPermissions from documents.permissions import PaperlessObjectPermissions
from documents.permissions import has_perms_owner_aware from documents.permissions import has_perms_owner_aware
from documents.permissions import permitted_object_ids
from documents.views import PassUserMixin from documents.views import PassUserMixin
from paperless.views import StandardPagination from paperless.views import StandardPagination
from paperless_mail.filters import ProcessedMailFilterSet from paperless_mail.filters import ProcessedMailFilterSet
@@ -211,10 +212,17 @@ class ProcessedMailViewSet(PassUserMixin, ReadOnlyModelViewSet[ProcessedMail]):
): ):
return HttpResponseBadRequest("mail_ids must be a list of integers") return HttpResponseBadRequest("mail_ids must be a list of integers")
mails = ProcessedMail.objects.filter(id__in=mail_ids) mails = ProcessedMail.objects.filter(id__in=mail_ids)
for mail in mails: # Check every id up front so an unpermitted one rejects the whole
if not has_perms_owner_aware(request.user, "delete_processedmail", mail): # request rather than deleting the mails ahead of it first.
return HttpResponseForbidden("Insufficient permissions") if mails.exclude(
mail.delete() pk__in=permitted_object_ids(
request.user,
ProcessedMail,
"delete_processedmail",
),
).exists():
return HttpResponseForbidden("Insufficient permissions")
mails.delete()
return Response({"result": "OK", "deleted_mail_ids": mail_ids}) return Response({"result": "OK", "deleted_mail_ids": mail_ids})