mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-08-10 12:53:20 +00:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Trenton Holmes
|
b5e2aae0e8 |
@@ -173,6 +173,10 @@ RUN set -eux \
|
||||
&& rm --force --verbose *.deb \
|
||||
&& rm --recursive --force --verbose /var/lib/apt/lists/*
|
||||
|
||||
# Ensure interactive shells (docker exec bash) see resolved *_FILE secrets,
|
||||
# mirroring what with-contenv already does for s6 services.
|
||||
RUN echo '. /etc/profile.d/contenv.sh' >> /etc/bash.bashrc
|
||||
|
||||
WORKDIR /usr/src/paperless/src/
|
||||
|
||||
# Python dependencies
|
||||
|
||||
Executable
+18
@@ -0,0 +1,18 @@
|
||||
#!/bin/sh
|
||||
# Source s6 container environment for interactive shells.
|
||||
# Ensures variables resolved from *_FILE secret injection are visible
|
||||
# when using 'docker exec bash'. Does not affect s6 services (those
|
||||
# use with-contenv directly). Has no effect in non-container contexts
|
||||
# because the directory will not exist.
|
||||
# Note: sh/dash shells opened via 'docker exec sh' are not covered;
|
||||
# only bash-based sessions benefit from this file.
|
||||
_pngx_contenv="/run/s6/container_environment"
|
||||
if [ -d "${_pngx_contenv}" ]; then
|
||||
for _pngx_f in "${_pngx_contenv}"/*; do
|
||||
[ -f "${_pngx_f}" ] || continue
|
||||
_pngx_name=$(basename "${_pngx_f}")
|
||||
_pngx_val=$(cat "${_pngx_f}")
|
||||
export "${_pngx_name}=${_pngx_val}"
|
||||
done
|
||||
fi
|
||||
unset _pngx_contenv _pngx_f _pngx_name _pngx_val
|
||||
@@ -948,11 +948,10 @@ for display in the web interface.
|
||||
|
||||
!!! note
|
||||
|
||||
The **remote OCR parser** (Azure AI) also honors this setting: when
|
||||
no archive is requested (`never`, or `auto` with a born-digital PDF),
|
||||
the remote engine is skipped entirely and locally-extracted text is
|
||||
used instead, avoiding an unnecessary API call and a duplicate text
|
||||
layer.
|
||||
The **remote OCR parser** (Azure AI) always produces a searchable
|
||||
PDF and stores it as the archive copy, regardless of this setting.
|
||||
`ARCHIVE_FILE_GENERATION=never` has no effect when the remote
|
||||
parser handles a document.
|
||||
|
||||
#### [`PAPERLESS_OCR_CLEAN=<mode>`](#PAPERLESS_OCR_CLEAN) {#PAPERLESS_OCR_CLEAN}
|
||||
|
||||
|
||||
@@ -187,11 +187,10 @@ PAPERLESS_ARCHIVE_FILE_GENERATION=auto
|
||||
|
||||
### Remote OCR parser
|
||||
|
||||
If you use the **remote OCR parser** (Azure AI), `ARCHIVE_FILE_GENERATION` is
|
||||
honored the same way as for the local engine: when no archive is requested
|
||||
(`never`, or `auto` with a born-digital PDF), the remote engine is skipped
|
||||
entirely and locally-extracted text is used instead, avoiding an unnecessary
|
||||
API call and a duplicate text layer.
|
||||
If you use the **remote OCR parser** (Azure AI), note that it always produces a
|
||||
searchable PDF and stores it as the archive copy. `ARCHIVE_FILE_GENERATION=never`
|
||||
has no effect for documents handled by the remote parser - the archive is produced
|
||||
unconditionally by the remote engine.
|
||||
|
||||
## Search Index (Whoosh -> Tantivy)
|
||||
|
||||
|
||||
+1
-1
@@ -66,5 +66,5 @@
|
||||
"ts-node": "~10.9.1",
|
||||
"typescript": "^6.0.3"
|
||||
},
|
||||
"packageManager": "pnpm@11.15.1"
|
||||
"packageManager": "pnpm@10.26.0"
|
||||
}
|
||||
|
||||
@@ -5,7 +5,6 @@ trustPolicy: no-downgrade
|
||||
trustPolicyExclude:
|
||||
- "chokidar@4.0.3"
|
||||
- "semver@6.3.1 || 5.7.2"
|
||||
blockExoticSubdeps: true
|
||||
allowBuilds:
|
||||
"@parcel/watcher": true
|
||||
canvas: true
|
||||
|
||||
@@ -3,9 +3,7 @@ Built-in remote-OCR document parser.
|
||||
|
||||
Handles documents by sending them to a configured remote OCR engine
|
||||
(currently Azure AI Vision / Document Intelligence) and retrieving both
|
||||
the extracted text and a searchable PDF with an embedded text layer. For
|
||||
born-digital PDFs that need no archive copy, the remote call is skipped
|
||||
entirely in favor of locally-extracted text (see ``RemoteDocumentParser.parse``).
|
||||
the extracted text and a searchable PDF with an embedded text layer.
|
||||
|
||||
When no engine is configured, ``score()`` returns ``None`` so the parser
|
||||
is effectively invisible to the registry — the tesseract parser handles
|
||||
@@ -24,8 +22,6 @@ from typing import Self
|
||||
from django.conf import settings
|
||||
|
||||
from documents.parsers import ParseError
|
||||
from paperless.parsers.utils import extract_pdf_text
|
||||
from paperless.parsers.utils import post_process_text
|
||||
from paperless.version import __full_version_str__
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -74,11 +70,8 @@ class RemoteDocumentParser:
|
||||
"""Parse documents via a remote OCR API (currently Azure AI Vision).
|
||||
|
||||
This parser sends documents to a remote engine that returns both
|
||||
extracted text and a searchable PDF with an embedded text layer,
|
||||
except when ``parse()`` is called with ``produce_archive=False`` for
|
||||
a PDF, in which case the remote call is skipped and only locally
|
||||
extracted text is returned (no archive). It does not depend on
|
||||
Tesseract or ocrmypdf.
|
||||
extracted text and a searchable PDF with an embedded text layer.
|
||||
It does not depend on Tesseract or ocrmypdf.
|
||||
|
||||
Class attributes
|
||||
----------------
|
||||
@@ -167,11 +160,8 @@ class RemoteDocumentParser:
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
Always True — the remote engine is capable of returning a PDF
|
||||
with an embedded text layer to serve as the archive copy.
|
||||
Whether it actually does so for a given document depends on
|
||||
``produce_archive`` passed to :meth:`parse` (see there for when
|
||||
the remote engine call, and thus archive generation, is skipped).
|
||||
Always True — the remote engine always returns a PDF with an
|
||||
embedded text layer that serves as the archive copy.
|
||||
"""
|
||||
return True
|
||||
|
||||
@@ -228,12 +218,6 @@ class RemoteDocumentParser:
|
||||
) -> None:
|
||||
"""Send the document to the remote engine and store results.
|
||||
|
||||
When *produce_archive* is False for a PDF, the caller (via
|
||||
``documents.consumer.should_produce_archive``) has already determined
|
||||
that the document is born-digital and needs no archive — skip the
|
||||
remote engine entirely rather than re-OCRing it and creating a
|
||||
duplicate text layer.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
document_path:
|
||||
@@ -241,8 +225,8 @@ class RemoteDocumentParser:
|
||||
mime_type:
|
||||
Detected MIME type of the document.
|
||||
produce_archive:
|
||||
Whether an archive copy is wanted. For PDFs, False skips the
|
||||
remote engine and uses locally-extracted text instead.
|
||||
Ignored — the remote engine always returns a searchable PDF,
|
||||
which is stored as the archive copy regardless of this flag.
|
||||
"""
|
||||
config = RemoteEngineConfig(
|
||||
engine=settings.REMOTE_OCR_ENGINE,
|
||||
@@ -257,16 +241,6 @@ class RemoteDocumentParser:
|
||||
self._text = ""
|
||||
return
|
||||
|
||||
if not produce_archive and mime_type == "application/pdf":
|
||||
logger.debug(
|
||||
"Remote OCR: skipped — no archive requested, "
|
||||
"using locally-extracted text",
|
||||
)
|
||||
self._text = (
|
||||
post_process_text(extract_pdf_text(document_path, log=logger)) or ""
|
||||
)
|
||||
return
|
||||
|
||||
if config.engine == "azureai":
|
||||
self._text = self._azure_ai_vision_parse(document_path, config)
|
||||
|
||||
|
||||
@@ -337,117 +337,6 @@ class TestRemoteParserParse:
|
||||
assert remote_parser.get_date() is None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# parse() — produce_archive=False skips the remote engine (PDFs only)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestRemoteParserSkipsWhenNoArchiveWanted:
|
||||
"""When the caller has already decided no archive is needed for a PDF
|
||||
(documents.consumer.should_produce_archive), the remote engine call is
|
||||
skipped entirely in favor of locally-extracted text.
|
||||
"""
|
||||
|
||||
def test_pdf_skips_azure_when_no_archive_requested(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: produce_archive=False for a PDF
|
||||
WHEN: parse() is called
|
||||
THEN: Azure is never invoked, no archive is produced, and text
|
||||
comes from local pdftotext extraction
|
||||
"""
|
||||
remote_parser.parse(
|
||||
simple_digital_pdf_file,
|
||||
"application/pdf",
|
||||
produce_archive=False,
|
||||
)
|
||||
|
||||
azure_client.begin_analyze_document.assert_not_called()
|
||||
assert remote_parser.get_archive_path() is None
|
||||
assert remote_parser.get_text() != ""
|
||||
|
||||
def test_pdf_no_archive_requested_text_matches_local_extraction(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
mocker: MockerFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: produce_archive=False for a PDF
|
||||
WHEN: parse() is called
|
||||
THEN: the returned text is exactly the locally-extracted text,
|
||||
not anything from the (unused) Azure mock
|
||||
"""
|
||||
mocker.patch(
|
||||
"paperless.parsers.remote.extract_pdf_text",
|
||||
return_value="Local digital text.",
|
||||
)
|
||||
|
||||
remote_parser.parse(
|
||||
simple_digital_pdf_file,
|
||||
"application/pdf",
|
||||
produce_archive=False,
|
||||
)
|
||||
|
||||
assert remote_parser.get_text() == "Local digital text."
|
||||
|
||||
def test_pdf_no_archive_requested_closes_no_client(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
) -> None:
|
||||
remote_parser.parse(
|
||||
simple_digital_pdf_file,
|
||||
"application/pdf",
|
||||
produce_archive=False,
|
||||
)
|
||||
|
||||
azure_client.close.assert_not_called()
|
||||
|
||||
def test_non_pdf_still_calls_azure_when_no_archive_requested(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
) -> None:
|
||||
"""
|
||||
Images have no local-text fallback, so produce_archive=False does
|
||||
not skip the remote engine for non-PDF MIME types.
|
||||
"""
|
||||
remote_parser.parse(
|
||||
simple_digital_pdf_file,
|
||||
"image/png",
|
||||
produce_archive=False,
|
||||
)
|
||||
|
||||
azure_client.begin_analyze_document.assert_called_once()
|
||||
assert remote_parser.get_text() == _DEFAULT_TEXT
|
||||
|
||||
@pytest.mark.usefixtures("no_engine_settings")
|
||||
def test_unconfigured_engine_takes_precedence_over_skip(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
"""An unconfigured engine still short-circuits before the
|
||||
produce_archive check, returning empty text as before.
|
||||
"""
|
||||
remote_parser.parse(
|
||||
simple_digital_pdf_file,
|
||||
"application/pdf",
|
||||
produce_archive=False,
|
||||
)
|
||||
|
||||
assert remote_parser.get_text() == ""
|
||||
assert remote_parser.get_archive_path() is None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# parse() — Azure failure path
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@@ -1298,16 +1298,16 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "fpdf2"
|
||||
version = "2.8.8"
|
||||
version = "2.8.7"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "defusedxml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/1e/bc/8fd4321aed40cadadddc8f311c65b6082346b252bca048f7b476d8f35d72/fpdf2-2.8.8.tar.gz", hash = "sha256:9e94e155e85e8053329a9a1fce8b566fd7a7c5bb79e98a1a3952d379b947c5b9", size = 374689, upload-time = "2026-08-09T23:32:45.334Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/27/f2/72feae0b2827ed38013e4307b14f95bf0b3d124adfef4d38a7d57533f7be/fpdf2-2.8.7.tar.gz", hash = "sha256:7060ccee5a9c7ab0a271fb765a36a23639f83ef8996c34e3d46af0a17ede57f9", size = 362351, upload-time = "2026-02-28T05:39:16.456Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f5/be/af012eda9507494f28b99b077423806c43a11573eb6225dd46f19ae2d263/fpdf2-2.8.8-py3-none-any.whl", hash = "sha256:3557a478fc577a929c94aace9666aed4dcc432b5ab6764232e6a59f1ccd75f17", size = 337000, upload-time = "2026-08-09T23:32:43.728Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/66/0a/cf50ecffa1e3747ed9380a3adfc829259f1f86b3fdbd9e505af789003141/fpdf2-2.8.7-py3-none-any.whl", hash = "sha256:d391fc508a3ce02fc43a577c830cda4fe6f37646f2d143d489839940932fbc19", size = 327056, upload-time = "2026-02-28T05:39:14.619Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -2927,8 +2927,8 @@ dependencies = [
|
||||
{ name = "sqlite-vec", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "tantivy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "tika-client", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
|
||||
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'linux'" },
|
||||
{ name = "watchfiles", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "whitenoise", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "zxing-cpp", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
@@ -4511,8 +4511,8 @@ dependencies = [
|
||||
{ name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "scikit-learn", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "scipy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "torch", version = "2.13.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
|
||||
{ name = "torch", version = "2.13.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'linux'" },
|
||||
{ name = "tqdm", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "transformers", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
@@ -4957,17 +4957,18 @@ name = "torch"
|
||||
version = "2.13.0"
|
||||
source = { registry = "https://download.pytorch.org/whl/cpu" }
|
||||
resolution-markers = [
|
||||
"python_full_version >= '3.15' and sys_platform == 'darwin'",
|
||||
"python_full_version >= '3.12' and python_full_version < '3.15' and sys_platform == 'darwin'",
|
||||
"python_full_version < '3.12' and sys_platform == 'darwin'",
|
||||
]
|
||||
dependencies = [
|
||||
{ name = "filelock", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "fsspec", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "jinja2", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "networkx", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "setuptools", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "sympy", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "typing-extensions", marker = "python_full_version < '3.15' and sys_platform == 'darwin'" },
|
||||
{ name = "filelock", marker = "sys_platform == 'darwin'" },
|
||||
{ name = "fsspec", marker = "sys_platform == 'darwin'" },
|
||||
{ name = "jinja2", marker = "sys_platform == 'darwin'" },
|
||||
{ name = "networkx", marker = "sys_platform == 'darwin'" },
|
||||
{ name = "setuptools", marker = "sys_platform == 'darwin'" },
|
||||
{ name = "sympy", marker = "sys_platform == 'darwin'" },
|
||||
{ name = "typing-extensions", marker = "sys_platform == 'darwin'" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.13.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:e76f9bcecc52b8ff711239a2f7547d5353df95878ab232f0773c1d95928b92f8", upload-time = "2026-07-08T12:26:13Z" },
|
||||
@@ -4982,7 +4983,6 @@ name = "torch"
|
||||
version = "2.13.0+cpu"
|
||||
source = { registry = "https://download.pytorch.org/whl/cpu" }
|
||||
resolution-markers = [
|
||||
"python_full_version >= '3.15' and sys_platform == 'darwin'",
|
||||
"python_full_version == '3.12.*' and platform_machine == 'x86_64' and sys_platform == 'linux'",
|
||||
"python_full_version == '3.12.*' and platform_machine == 'aarch64' and sys_platform == 'linux'",
|
||||
"python_full_version >= '3.15' and sys_platform == 'linux'",
|
||||
@@ -4990,13 +4990,13 @@ resolution-markers = [
|
||||
"python_full_version < '3.12' and sys_platform == 'linux'",
|
||||
]
|
||||
dependencies = [
|
||||
{ name = "filelock", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "fsspec", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "jinja2", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "networkx", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "setuptools", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "sympy", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "typing-extensions", marker = "(python_full_version >= '3.15' and sys_platform == 'darwin') or sys_platform == 'linux'" },
|
||||
{ name = "filelock", marker = "sys_platform == 'linux'" },
|
||||
{ name = "fsspec", marker = "sys_platform == 'linux'" },
|
||||
{ name = "jinja2", marker = "sys_platform == 'linux'" },
|
||||
{ name = "networkx", marker = "sys_platform == 'linux'" },
|
||||
{ name = "setuptools", marker = "sys_platform == 'linux'" },
|
||||
{ name = "sympy", marker = "sys_platform == 'linux'" },
|
||||
{ name = "typing-extensions", marker = "sys_platform == 'linux'" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.13.0%2Bcpu-cp311-cp311-linux_s390x.whl", hash = "sha256:6e9817dbdf5ea76789babd46e457eac5bf14ff566cf85f8addbfdff2d56601ce", upload-time = "2026-07-08T19:27:52Z" },
|
||||
|
||||
Reference in New Issue
Block a user