amorfo77/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-08-15 07:13:18 +00:00
Code Issues Projects Releases Wiki Activity
Files
c094e91567c9e496c4ad4afe203b4d65528f4d83
paperless-ngx/pyproject.toml
T
Trenton HGitHubClaude Sonnet 4.6
 a9756f9462 Chore: Convert Tesseract parser to plugin style (#12403) 
* Move tesseract parser, tests, and samples to paperless.parsers

Relocates files in preparation for the Phase 3 Protocol-based parser
refactor, preserving full git history via rename.

- src/paperless_tesseract/parsers.py -> src/paperless/parsers/tesseract.py
- src/paperless_tesseract/tests/test_parser.py -> src/paperless/tests/parsers/test_tesseract_parser.py
- src/paperless_tesseract/tests/test_parser_custom_settings.py -> src/paperless/tests/parsers/test_tesseract_custom_settings.py
- src/paperless_tesseract/tests/samples/* -> src/paperless/tests/samples/tesseract/
- Moves RUF001 suppression from broad per-file pyproject.toml ignore to inline noqa comments on the two affected lines

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Refactor RasterisedDocumentParser to ParserProtocol interface

- Add RasterisedDocumentParser to registry.register_defaults()
- Update parser class: remove DocumentParser inheritance, add Protocol
  class attrs/classmethods/properties, context-manager lifecycle
- Add read_file_handle_unicode_errors() to shared parsers/utils.py
- Replace inline unicode-error-handling with shared utility call

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Update tesseract signals.py to import from new parser location

RasterisedDocumentParser moved to paperless.parsers.tesseract; update
the lazy import in signals.get_parser so the signal-based consumer
declaration continues to work during the registry transition. Pop
logging_group and progress_callback kwargs for constructor compatibility.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* tests: rewrite test_tesseract_parser to pytest style with typed fixtures

- Converts all tests from Django TestCase to pytest-style classes
- Adds tesseract_samples_dir, null_app_config, tesseract_parser, and
  make_tesseract_parser fixtures in conftest.py; all DB-free except
  TestOcrmypdfParameters which uses @pytest.mark.django_db
- Defines MakeTesseractParser type alias in conftest.py for autocomplete
- Fixes FBT001 (boolean positional args) by making bool params
  keyword-only with * separator in parametrize test signatures
- Adds type annotations to all fixture parameters for IDE support
- Uses pytest.param(..., id="...") throughout; pytest-mock for patching

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(types): fully annotate paperless/parsers/tesseract.py

Fixes all mypy and pyrefly errors in the new parser file:

- Add missing type annotations to is_image, has_alpha, get_dpi,
  calculate_a4_dpi, construct_ocrmypdf_parameters, post_process_text
- Narrow Path-only (no str) for image helper args; convert to str when
  building list[str] args for run_subprocess
- Annotate ocrmypdf_args as dict[str, Any] so operator expressions on
  its values type-check and ocrmypdf.ocr(**args) resolves cleanly
- Declare text: str | None = None at top of extract_text to unify
  all assignments to the same type across both branches
- Import Any from typing

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Fixes isort

* fix: add RasterisedDocumentParser to new-style parser shim checks

The new RasterisedDocumentParser uses __enter__/__exit__ for resource
management instead of cleanup(). Update all existing new-style shims to
include it in the isinstance checks:

- documents/consumer.py: _parser_cleanup(), parser_is_new_style
- documents/tasks.py: parser_is_new_style, finally cleanup branch
  (also adds RemoteDocumentParser which was missing from the latter)
- documents/management/commands/document_thumbnails.py: adds new-style
  handling from scratch (enter/exit + 2-arg get_thumbnail signature)

Fix stale import paths in three test files that were still importing
from paperless_tesseract.parsers instead of paperless.parsers.tesseract.

Fix two registry tests that used application/pdf as a proxy for "no
handler" — now that RasterisedDocumentParser is registered, PDF always
has a handler, so switch to a truly unsupported MIME type.

Signal infrastructure and shims remain intact; this is plumbing only.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* One missed import (cherry pick?)

* Adds a no cover for a special case of handling unicode errors in PDF metadata

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-20 12:46:07 -07:00

356 lines
9.4 KiB
TOML
Raw Blame History

[project]
name = "paperless-ngx"
version = "2.20.11"
description = "A community-supported supercharged document management system: scan, index and archive all your physical documents"
readme = "README.md"
requires-python = ">=3.11"
classifiers = [
"Programming Language :: Python :: 3 :: Only",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Programming Language :: Python :: 3.14",
]
# TODO: Move certain things to groups and then utilize that further
# This will allow testing to not install a webserver, mysql, etc
dependencies = [
"azure-ai-documentintelligence>=1.0.2",
"babel>=2.17",
"bleach~=6.3.0",
"celery[redis]~=5.6.2",
"channels~=4.2",
"channels-redis~=4.2",
"concurrent-log-handler~=0.9.25",
"dateparser~=1.2",
# WARNING: django does not use semver.
# Only patch versions are guaranteed to not introduce breaking changes.
"django~=5.2.10",
"django-allauth[mfa,socialaccount]~=65.15.0",
"django-auditlog~=3.4.1",
"django-cachalot~=2.9.0",
"django-celery-results~=2.6.0",
"django-compression-middleware~=0.5.0",
"django-cors-headers~=4.9.0",
"django-extensions~=4.1",
"django-filter~=25.1",
"django-guardian~=3.3.0",
"django-multiselectfield~=1.0.1",
"django-rich~=2.2.0",
"django-soft-delete~=1.0.18",
"django-treenode>=0.23.2",
"djangorestframework~=3.16",
"djangorestframework-guardian~=0.4.0",
"drf-spectacular~=0.28",
"drf-spectacular-sidecar~=2026.3.1",
"drf-writable-nested~=0.7.1",
"faiss-cpu>=1.10",
"filelock~=3.25.2",
"flower~=2.0.1",
"gotenberg-client~=0.13.1",
"httpx-oauth~=0.16",
"ijson>=3.2",
"imap-tools~=1.11.0",
"jinja2~=3.1.5",
"langdetect~=1.0.9",
"llama-index-core>=0.14.12",
"llama-index-embeddings-huggingface>=0.6.1",
"llama-index-embeddings-openai>=0.5.1",
"llama-index-llms-ollama>=0.9.1",
"llama-index-llms-openai>=0.6.13",
"llama-index-vector-stores-faiss>=0.5.2",
"nltk~=3.9.1",
"ocrmypdf~=17.3.0",
"openai>=1.76",
"pathvalidate~=3.3.1",
"pdf2image~=1.17.0",
"python-dateutil~=2.9.0",
"python-dotenv~=1.2.1",
"python-gnupg~=0.5.4",
"python-ipware~=3.0.0",
"python-magic~=0.4.27",
"rapidfuzz~=3.14.0",
"redis[hiredis]~=5.2.1",
"regex>=2025.9.18",
"scikit-learn~=1.8.0",
"sentence-transformers>=4.1",
"setproctitle~=1.3.4",
"tika-client~=0.10.0",
"torch~=2.10.0",
"watchfiles>=1.1.1",
"whitenoise~=6.11",
"whoosh-reloaded>=2.7.5",
"zxing-cpp~=3.0.0",
]
optional-dependencies.mariadb = [
"mysqlclient~=2.2.7",
]
optional-dependencies.postgres = [
"psycopg[c,pool]==3.3",
# Direct dependency for proper resolution of the pre-built wheels
"psycopg-c==3.3",
"psycopg-pool==3.3",
]
optional-dependencies.webserver = [
"granian[uvloop]~=2.7.0",
]
[dependency-groups]
dev = [
{ "include-group" = "docs" },
{ "include-group" = "testing" },
{ "include-group" = "lint" },
]
docs = [
"zensical>=0.0.21",
]
testing = [
"daphne",
"factory-boy~=3.3.1",
"faker~=40.8.0",
"imagehash",
"pytest~=9.0.0",
"pytest-cov~=7.0.0",
"pytest-django~=4.12.0",
"pytest-env~=1.5.0",
"pytest-httpx",
"pytest-mock~=3.15.1",
#"pytest-randomly~=4.0.1",
"pytest-rerunfailures~=16.1",
"pytest-sugar",
"pytest-xdist~=3.8.0",
]
lint = [
"prek~=0.3.0",
"ruff~=0.15.0",
]
typing = [
"celery-types",
"django-filter-stubs",
"django-stubs[compatible-mypy]",
"djangorestframework-stubs[compatible-mypy]",
"lxml-stubs",
"microsoft-python-type-stubs @ git+https://github.com/microsoft/python-type-stubs.git",
"mypy",
"mypy-baseline",
"pyrefly",
"types-bleach",
"types-channels",
"types-colorama",
"types-dateparser",
"types-markdown",
"types-pygments",
"types-python-dateutil",
"types-pytz",
"types-redis",
"types-setuptools",
]
[tool.uv]
required-version = ">=0.9.0"
package = false
environments = [
"sys_platform == 'darwin'",
"sys_platform == 'linux'",
]
[[tool.uv.index]]
name = "pytorch-cpu"
url = "https://download.pytorch.org/whl/cpu"
explicit = true
[tool.uv.sources]
# Markers are chosen to select these almost exclusively when building the Docker image
psycopg-c = [
{ url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
{ url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },
]
torch = [
{ index = "pytorch-cpu" },
]
[tool.ruff]
target-version = "py311"
line-length = 88
src = [
"src",
]
respect-gitignore = true
# https://docs.astral.sh/ruff/settings/
fix = true
show-fixes = true
output-format = "grouped"
# https://docs.astral.sh/ruff/rules/
lint.extend-select = [
"COM", # https://docs.astral.sh/ruff/rules/#flake8-commas-com
"DJ", # https://docs.astral.sh/ruff/rules/#flake8-django-dj
"EXE", # https://docs.astral.sh/ruff/rules/#flake8-executable-exe
"FBT", # https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt
"FLY", # https://docs.astral.sh/ruff/rules/#flynt-fly
"G201", # 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
"ISC", # https://docs.astral.sh/ruff/rules/#flake8-implicit-str-concat-isc
"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
"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
"SIM", # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
"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
"UP", # https://docs.astral.sh/ruff/rules/#pyupgrade-up
"W", # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
]
lint.ignore = [
"DJ001",
"PLC0415",
"RUF012",
"SIM105",
]
# Migrations
lint.per-file-ignores."*/migrations/*.py" = [
"E501",
"SIM",
"T201",
]
# Testing
lint.per-file-ignores."*/tests/*.py" = [
"E501",
"SIM117",
]
lint.per-file-ignores.".github/scripts/*.py" = [
"E501",
"INP001",
"SIM117",
]
# Docker specific
lint.per-file-ignores."docker/rootfs/usr/local/bin/wait-for-redis.py" = [
"INP001",
"T201",
]
lint.per-file-ignores."docker/wait-for-redis.py" = [
"INP001",
"T201",
]
lint.per-file-ignores."src/documents/models.py" = [
"SIM115",
]
lint.isort.force-single-line = true
[tool.codespell]
write-changes = true
ignore-words-list = "criterias,afterall,valeu,ureue,equest,ure,assertIn,Oktober,commitish"
skip = "src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless_mail/tests/samples/*,src/paperless/tests/samples/mail/*,src/documents/tests/samples/*,*.po,*.json"
[tool.pytest]
minversion = "9.0"
pythonpath = [ "src" ]
strict_config = true
strict_markers = true
strict_parametrization_ids = true
strict_xfail = true
testpaths = [
"src/documents/tests/",
"src/paperless/tests/",
"src/paperless_mail/tests/",
"src/paperless_tesseract/tests/",
"src/paperless_tika/tests",
"src/paperless_text/tests/",
"src/paperless_remote/tests/",
"src/paperless_ai/tests",
]
addopts = [
"--pythonwarnings=all",
"--cov",
"--cov-report=html",
"--cov-report=xml",
"--numprocesses=auto",
"--maxprocesses=16",
"--dist=loadscope",
"--durations=50",
"--durations-min=0.5",
"--junitxml=junit.xml",
"-o",
"junit_family=legacy",
]
norecursedirs = [ "src/locale/", ".venv/", "src-ui/" ]
DJANGO_SETTINGS_MODULE = "paperless.settings"
markers = [
"live: Integration tests requiring external services (Gotenberg, Tika, nginx, etc)",
"nginx: Tests that make HTTP requests to the local nginx service",
"gotenberg: Tests requiring Gotenberg service",
"tika: Tests requiring Tika service",
"greenmail: Tests requiring Greenmail service",
"date_parsing: Tests which cover date parsing from content or filename",
"management: Tests which cover management commands/functionality",
]
[tool.pytest_env]
PAPERLESS_DISABLE_DBHANDLER = "true"
PAPERLESS_CACHE_BACKEND = "django.core.cache.backends.locmem.LocMemCache"
PAPERLESS_CHANNELS_BACKEND = "channels.layers.InMemoryChannelLayer"
[tool.coverage.report]
exclude_also = [
"if settings.AUDIT_LOG_ENABLED:",
"if AUDIT_LOG_ENABLED:",
"if TYPE_CHECKING:",
]
[tool.coverage.run]
source = [
"src/",
]
omit = [
"*/tests/*",
"manage.py",
"paperless/wsgi.py",
"paperless/auth.py",
]
[tool.mypy]
mypy_path = "src"
plugins = [
"mypy_django_plugin.main",
"mypy_drf_plugin.main",
]
check_untyped_defs = true
disallow_any_generics = true
disallow_incomplete_defs = true
disallow_untyped_defs = true
warn_redundant_casts = true
warn_unused_ignores = true
[tool.pyrefly]
search-path = [ "src" ]
baseline = ".pyrefly-baseline.json"
python-platform = "linux"
[tool.django-stubs]
django_settings_module = "paperless.settings"
[tool.mypy-baseline]
baseline_path = ".mypy-baseline.txt"
sort_baseline = true
ignore_categories = [ "note" ]
Reference in New Issue View Git Blame Copy Permalink