Won't build yet, but saves what should be correct and work later. Also saves the current dev package list for later diff

Dockerfile

@@ -5,7 +5,7 @@
 # Purpose: Compiles the frontend
 # Notes:
 #  - Does PNPM stuff with Typescript and such
-FROM --platform=$BUILDPLATFORM docker.io/node:20-bookworm-slim AS compile-frontend
+FROM --platform=$BUILDPLATFORM docker.io/node:20-trixie-slim AS compile-frontend
 
 COPY ./src-ui /src/src-ui
 
@@ -32,7 +32,7 @@ RUN set -eux \
 # Purpose: Installs s6-overlay and rootfs
 # Comments:
 #  - Don't leave anything extra in here either
-FROM ghcr.io/astral-sh/uv:0.8.4-python3.12-bookworm-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.8.4-python3.12-trixie-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 
@@ -170,20 +170,8 @@ RUN set -eux \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES} \
     && echo "Installing pre-built updates" \
-      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all --parallel --parallel-max 4 \
+      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all \
-        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
         https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
-      && echo "Installing qpdf ${QPDF_VERSION}" \
-        && dpkg --install ./libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        && dpkg --install ./qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-      && echo "Installing Ghostscript ${GS_VERSION}" \
-        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
-        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
       && echo "Installing jbig2enc" \
         && dpkg --install ./jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
       && echo "Configuring imagemagick" \

dev.txt

@@ -0,0 +1,319 @@
+adduser 3.134
+apt 2.6.1
+base-files 12.4+deb12u11
+base-passwd 3.6.1
+bash 5.2.15-2+b8
+bsdutils 1:2.38.1-5+deb12u3
+ca-certificates 20230311+deb12u1
+coreutils 9.1-1
+curl 7.88.1-10+deb12u12
+dash 0.5.12-2
+debconf 1.5.82
+debian-archive-keyring 2023.3+deb12u2
+debianutils 5.7-0.5~deb12u1
+diffutils 1:3.8-4
+dirmngr 2.2.40-1.1
+dpkg 1.21.22
+e2fsprogs 1.47.0-2
+file 1:5.44-3
+findutils 4.9.0-4
+fontconfig 2.14.1-4
+fontconfig-config 2.14.1-4
+fonts-liberation 1:1.07.4-11
+fonts-urw-base35 20200910-7
+gcc-12-base 12.2.0-14+deb12u1
+gettext 0.21-12
+gettext-base 0.21-12
+ghostscript 10.03.1~dfsg-1
+gnupg 2.2.40-1.1
+gnupg-l10n 2.2.40-1.1
+gnupg-utils 2.2.40-1.1
+gosu 1.14-1+b10
+gpg 2.2.40-1.1
+gpg-agent 2.2.40-1.1
+gpg-wks-client 2.2.40-1.1
+gpg-wks-server 2.2.40-1.1
+gpgconf 2.2.40-1.1
+gpgsm 2.2.40-1.1
+gpgv 2.2.40-1.1
+grep 3.8-5
+gzip 1.12-1
+hicolor-icon-theme 0.17-2
+hostname 3.23+nmu1
+icc-profiles-free 2.0.1+dfsg-1.1
+imagemagick 8:6.9.11.60+dfsg-1.6+deb12u3
+imagemagick-6-common 8:6.9.11.60+dfsg-1.6+deb12u3
+imagemagick-6.q16 8:6.9.11.60+dfsg-1.6+deb12u3
+init-system-helpers 1.65.2
+jbig2dec 0.19-3
+jbig2enc 0.30-1
+libacl1 2.3.1-3
+libaom3 3.6.0-1+deb12u1
+libapt-pkg6.0 2.6.1
+libarchive13 3.6.2-1+deb12u2
+libassuan0 2.5.5-5
+libattr1 1:2.5.1-4
+libaudit-common 1:3.0.9-1
+libaudit1 1:3.0.9-1
+libavahi-client3 0.8-10+deb12u1
+libavahi-common-data 0.8-10+deb12u1
+libavahi-common3 0.8-10+deb12u1
+libavcodec59 7:5.1.6-0+deb12u1
+libavformat59 7:5.1.6-0+deb12u1
+libavutil57 7:5.1.6-0+deb12u1
+libblkid1 2.38.1-5+deb12u3
+libbluray2 1:1.3.4-1
+libbrotli1 1.0.9-2+b6
+libbsd0 0.11.7-2
+libbz2-1.0 1.0.8-5+b1
+libc-bin 2.36-9+deb12u10
+libc6 2.36-9+deb12u10
+libcairo-gobject2 1.16.0-7
+libcairo2 1.16.0-7
+libcap-ng0 0.8.3-1+b3
+libcap2 1:2.66-4+deb12u1
+libchromaprint1 1.5.1-2+b1
+libcjson1 1.7.15-1+deb12u2
+libcodec2-1.0 1.0.5-1
+libcom-err2 1.47.0-2
+libconfig-inifiles-perl 3.000003-2
+libcrypt1 1:4.4.33-2
+libcups2 2.4.2-3+deb12u8
+libcurl4 7.88.1-10+deb12u12
+libdatrie1 0.2.13-2+b1
+libdav1d6 1.0.0-2+deb12u1
+libdb5.3 5.3.28+dfsg2-1
+libdbus-1-3 1.14.10-1~deb12u1
+libde265-0 1.0.11-1+deb12u2
+libdebconfclient0 0.270
+libdeflate0 1.14-1
+libdrm-common 2.4.114-1
+libdrm2 2.4.114-1+b1
+libedit2 3.1-20221030-2
+libexpat1 2.5.0-1+deb12u1
+libext2fs2 1.47.0-2
+libffi8 3.4.4-1
+libfftw3-double3 3.3.10-1
+libfontconfig1 2.14.1-4
+libfontenc1 1:1.1.4-1
+libfreetype6 2.12.1+dfsg-5+deb12u4
+libfribidi0 1.0.8-2.1
+libgcc-s1 12.2.0-14+deb12u1
+libgcrypt20 1.10.1-3
+libgdbm-compat4 1.23-3
+libgdbm6 1.23-3
+libgdk-pixbuf-2.0-0 2.42.10+dfsg-1+deb12u2
+libgdk-pixbuf2.0-common 2.42.10+dfsg-1+deb12u2
+libgif7 5.2.1-2.5
+libglib2.0-0 2.74.6-2+deb12u6
+libgme0 0.6.3-6
+libgmp10 2:6.2.1+dfsg1-1.1
+libgnutls30 3.7.9-2+deb12u5
+libgomp1 12.2.0-14+deb12u1
+libgpg-error0 1.46-1
+libgraphite2-3 1.3.14-1
+libgs-common 10.0.0~dfsg-11+deb12u7
+libgs10 10.03.1~dfsg-1
+libgs10-common 10.03.1~dfsg-1
+libgsm1 1.0.22-1
+libgssapi-krb5-2 1.20.1-2+deb12u3
+libharfbuzz0b 6.0.0+dfsg-3
+libheif1 1.15.1-1+deb12u1
+libhogweed6 3.8.1-2
+libhwy1 1.0.3-3+deb12u1
+libice6 2:1.0.10-1
+libicu72 72.1-3+deb12u1
+libidn12 1.41-1
+libidn2-0 2.3.3-1+b1
+libijs-0.35 0.35-15
+libimagequant0 2.17.0-1
+libjbig0 2.1-6.1
+libjbig2dec0 0.19-3
+libjpeg62-turbo 1:2.1.5-2
+libjxl0.7 0.7.0-10+deb12u1
+libk5crypto3 1.20.1-2+deb12u3
+libkeyutils1 1.6.3-2
+libkrb5-3 1.20.1-2+deb12u3
+libkrb5support0 1.20.1-2+deb12u3
+libksba8 1.6.3-2
+liblcms2-2 2.14-2
+libldap-2.5-0 2.5.13+dfsg-5
+liblept5 1.82.0-3+b3
+liblerc4 4.0.0+ds-2
+liblqr-1-0 0.4.2-2.1
+libltdl7 2.4.7-7~deb12u1
+liblz4-1 1.9.4-1
+liblzma5 5.4.1-1
+libmagic-mgc 1:5.44-3
+libmagic1 1:5.44-3
+libmagickcore-6.q16-6 8:6.9.11.60+dfsg-1.6+deb12u3
+libmagickwand-6.q16-6 8:6.9.11.60+dfsg-1.6+deb12u3
+libmariadb3 1:10.11.11-0+deb12u1
+libmbedcrypto7 2.28.3-1
+libmd0 1.0.4-2
+libmfx1 22.5.4-1
+libmount1 2.38.1-5+deb12u3
+libmp3lame0 3.100-6
+libmpg123-0 1.31.2-1+deb12u1
+libncurses6 6.4-4
+libncursesw6 6.4-4
+libnettle8 3.8.1-2
+libnghttp2-14 1.52.0-1+deb12u2
+libnorm1 1.5.9+dfsg-2
+libnpth0 1.6-3
+libnsl2 1.3.0-2
+libnspr4 2:4.35-1
+libnss3 2:3.87.1-1+deb12u1
+libnuma1 2.0.16-1
+libogg0 1.3.5-3
+libopenjp2-7 2.5.0-2+deb12u1
+libopenmpt0 0.6.9-1
+libopus0 1.3.1-3
+libp11-kit0 0.24.1-2
+libpam-modules 1.5.2-6+deb12u1
+libpam-modules-bin 1.5.2-6+deb12u1
+libpam-runtime 1.5.2-6+deb12u1
+libpam0g 1.5.2-6+deb12u1
+libpango-1.0-0 1.50.12+ds-1
+libpangocairo-1.0-0 1.50.12+ds-1
+libpangoft2-1.0-0 1.50.12+ds-1
+libpaper1 1.1.29
+libpcre2-8-0 10.42-1
+libperl5.36 5.36.0-7+deb12u2
+libpgm-5.3-0 5.3.128~dfsg-2
+libpixman-1-0 0.42.2-1
+libpng16-16 1.6.39-2
+libpoppler126 22.12.0-2+deb12u1
+libpq5 15.13-0+deb12u1
+libpsl5 0.21.2-1
+libqpdf29 11.9.0-1
+librabbitmq4 0.11.0-1+deb12u1
+librav1e0 0.5.1-6
+libreadline8 8.2-1.3
+librist4 0.2.7+dfsg-1
+librsvg2-2 2.54.7+dfsg-1~deb12u1
+librtmp1 2.4+20151223.gitfa8646d.1-2+b2
+libsasl2-2 2.1.28+dfsg-10
+libsasl2-modules-db 2.1.28+dfsg-10
+libseccomp2 2.5.4-1+deb12u1
+libselinux1 3.4-1+b6
+libsemanage-common 3.4-1
+libsemanage2 3.4-1+b5
+libsepol2 3.4-2.1
+libshine3 3.1.1-2
+libsm6 2:1.2.3-1
+libsmartcols1 2.38.1-5+deb12u3
+libsnappy1v5 1.1.9-3
+libsodium23 1.0.18-1
+libsoxr0 0.1.3-4
+libspeex1 1.2.1-2
+libsqlite3-0 3.40.1-2+deb12u1
+libsrt1.5-gnutls 1.5.1-1+deb12u1
+libss2 1.47.0-2
+libssh-gcrypt-4 0.10.6-0+deb12u1
+libssh2-1 1.10.0-3+b1
+libssl3 3.0.17-1~deb12u1
+libstdc++6 12.2.0-14+deb12u1
+libsvtav1enc1 1.4.1+dfsg-1
+libswresample4 7:5.1.6-0+deb12u1
+libsystemd0 252.38-1~deb12u1
+libtasn1-6 4.19.0-2+deb12u1
+libtesseract5 5.3.0-2
+libthai-data 0.1.29-1
+libthai0 0.1.29-1
+libtheora0 1.1.1+dfsg.1-16.1+b1
+libtiff6 4.5.0-6+deb12u2
+libtinfo6 6.4-4
+libtirpc-common 1.3.3+ds-1
+libtirpc3 1.3.3+ds-1
+libtwolame0 0.4.0-2
+libudev1 252.38-1~deb12u1
+libudfread0 1.1.2-1
+libunistring2 1.0-2
+libuuid1 2.38.1-5+deb12u3
+libv4l-0 1.22.1-5+b2
+libv4lconvert0 1.22.1-5+b2
+libva-drm2 2.17.0-1
+libva-x11-2 2.17.0-1
+libva2 2.17.0-1
+libvdpau1 1.5-2
+libvorbis0a 1.3.7-1
+libvorbisenc2 1.3.7-1
+libvorbisfile3 1.3.7-1
+libvpx7 1.12.0-1+deb12u4
+libwebp7 1.2.4-0.2+deb12u1
+libwebpdemux2 1.2.4-0.2+deb12u1
+libwebpmux3 1.2.4-0.2+deb12u1
+libx11-6 2:1.8.4-2+deb12u2
+libx11-data 2:1.8.4-2+deb12u2
+libx11-xcb1 2:1.8.4-2+deb12u2
+libx264-164 2:0.164.3095+gitbaee400-3
+libx265-199 3.5-2+b1
+libxau6 1:1.0.9-1
+libxcb-dri3-0 1.15-1
+libxcb-render0 1.15-1
+libxcb-shm0 1.15-1
+libxcb1 1.15-1
+libxdmcp6 1:1.1.2-3
+libxext6 2:1.3.4-1+b1
+libxfixes3 1:6.0.0-2
+libxml2 2.9.14+dfsg-1.3~deb12u2
+libxrender1 1:0.9.10-1.1
+libxslt1.1 1.1.35-1+deb12u1
+libxt6 1:1.2.1-1.1
+libxvidcore4 2:1.3.7-1
+libxxhash0 0.8.1-1
+libzbar0 0.23.92-7+deb12u1
+libzmq5 4.3.4-6
+libzstd1 1.5.4+dfsg2-5
+libzvbi-common 0.2.41-1
+libzvbi0 0.2.41-1
+login 1:4.13+dfsg1-1+deb12u1
+logsave 1.47.0-2
+mariadb-client 1:10.11.11-0+deb12u1
+mariadb-client-core 1:10.11.11-0+deb12u1
+mariadb-common 1:10.11.11-0+deb12u1
+mawk 1.3.4.20200120-3.1
+media-types 10.0.0
+mount 2.38.1-5+deb12u3
+mysql-common 5.8+1.1.0
+ncurses-base 6.4-4
+ncurses-bin 6.4-4
+netbase 6.4
+ocl-icd-libopencl1 2.3.1-1
+openssl 3.0.17-1~deb12u1
+passwd 1:4.13+dfsg1-1+deb12u1
+perl 5.36.0-7+deb12u2
+perl-base 5.36.0-7+deb12u2
+perl-modules-5.36 5.36.0-7+deb12u2
+pinentry-curses 1.2.1-1
+pngquant 2.17.0-1
+poppler-data 0.4.12-1
+poppler-utils 22.12.0-2+deb12u1
+postgresql-client 15+248
+postgresql-client-15 15.13-0+deb12u1
+postgresql-client-common 248
+qpdf 11.9.0-1
+readline-common 8.2-1.3
+sed 4.9-1
+sensible-utils 0.0.17+nmu1
+shared-mime-info 2.2-1
+sysvinit-utils 3.06-4
+tar 1.34+dfsg-1.2+deb12u1
+tesseract-ocr 5.3.0-2
+tesseract-ocr-deu 1:4.1.0-2
+tesseract-ocr-eng 1:4.1.0-2
+tesseract-ocr-fra 1:4.1.0-2
+tesseract-ocr-ita 1:4.1.0-2
+tesseract-ocr-osd 1:4.1.0-2
+tesseract-ocr-spa 1:4.1.0-2
+tzdata 2025b-0+deb12u1
+ucf 3.0043+nmu1+deb12u1
+unpaper 7.0.0-0.1
+usr-is-merged 37~deb12u1
+util-linux 2.38.1-5+deb12u3
+util-linux-extra 2.38.1-5+deb12u3
+x11-common 1:7.7+23
+xfonts-encodings 1:1.0.4-2.2
+xfonts-utils 1:7.7+6
+zlib1g 1:1.2.13.dfsg-1

docs/configuration.md

@@ -1800,23 +1800,3 @@ password. All of these options come from their similarly-named [Django settings]
 #### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
 
 : Defaults to false.
-
-## Remote OCR
-
-#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
-
-: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
-
-    Defaults to None, which disables remote OCR.
-
-#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
-
-: The API key to use for the remote OCR engine.
-
-    Defaults to None.
-
-#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
-
-: The endpoint to use for the remote OCR engine. This is required for Azure AI.
-
-    Defaults to None.

docs/index.md

@@ -25,10 +25,9 @@ physical documents into a searchable online archive so you can keep, well, _less
 ## Features
 
 -   **Organize and index** your scanned documents with tags, correspondents, types, and more.
--   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
 -   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
-    -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+-   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
-    -   _New!_ Supports remote OCR with Azure AI (opt-in).
 -   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
 -   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
 -   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.

docs/usage.md

@@ -850,18 +850,6 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
-## Remote OCR
-
-!!! important
-
-    This feature is disabled by default and will always remain strictly "opt-in".
-
-Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
-[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
-This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
-Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
-the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
-
 ## Architecture
 
 Paperless-ngx consists of the following components:

pyproject.toml

@@ -15,7 +15,6 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
-  "azure-ai-documentintelligence>=1.0.2",
   "bleach~=6.2.0",
   "celery[redis]~=5.5.1",
   "channels~=4.2",
@@ -234,7 +233,6 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
-  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src/paperless/settings.py

@@ -324,7 +324,6 @@ INSTALLED_APPS = [
     "paperless_tesseract.apps.PaperlessTesseractConfig",
     "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
-    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -1444,10 +1443,3 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
     "PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
     "true",
 )
-
-###############################################################################
-# Remote Parser                                                               #
-###############################################################################
-REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
-REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
-REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")

src/paperless_remote/__init__.py

@@ -1,4 +0,0 @@
-# this is here so that django finds the checks.
-from paperless_remote.checks import check_remote_parser_configured
-
-__all__ = ["check_remote_parser_configured"]

src/paperless_remote/apps.py

@@ -1,14 +0,0 @@
-from django.apps import AppConfig
-
-from paperless_remote.signals import remote_consumer_declaration
-
-
-class PaperlessRemoteParserConfig(AppConfig):
-    name = "paperless_remote"
-
-    def ready(self):
-        from documents.signals import document_consumer_declaration
-
-        document_consumer_declaration.connect(remote_consumer_declaration)
-
-        AppConfig.ready(self)

src/paperless_remote/checks.py

@@ -1,15 +0,0 @@
-from django.conf import settings
-from django.core.checks import Error
-from django.core.checks import register
-
-
-@register()
-def check_remote_parser_configured(app_configs, **kwargs):
-    if settings.REMOTE_OCR_ENGINE == "azureai" and not settings.REMOTE_OCR_ENDPOINT:
-        return [
-            Error(
-                "Azure AI remote parser requires endpoint to be configured.",
-            ),
-        ]
-
-    return []

src/paperless_remote/parsers.py

@@ -1,113 +0,0 @@
-from pathlib import Path
-
-from django.conf import settings
-
-from paperless_tesseract.parsers import RasterisedDocumentParser
-
-
-class RemoteEngineConfig:
-    def __init__(
-        self,
-        engine: str,
-        api_key: str | None = None,
-        endpoint: str | None = None,
-    ):
-        self.engine = engine
-        self.api_key = api_key
-        self.endpoint = endpoint
-
-    def engine_is_valid(self):
-        valid = self.engine in ["azureai"] and self.api_key is not None
-        if self.engine == "azureai":
-            valid = valid and self.endpoint is not None
-        return valid
-
-
-class RemoteDocumentParser(RasterisedDocumentParser):
-    """
-    This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
-    as this is the only service that provides a remote OCR API with text-embedded PDF output.
-    """
-
-    logging_name = "paperless.parsing.remote"
-
-    def get_settings(self) -> RemoteEngineConfig:
-        """
-        Returns the configuration for the remote OCR engine, loaded from Django settings.
-        """
-        return RemoteEngineConfig(
-            engine=settings.REMOTE_OCR_ENGINE,
-            api_key=settings.REMOTE_OCR_API_KEY,
-            endpoint=settings.REMOTE_OCR_ENDPOINT,
-        )
-
-    def supported_mime_types(self):
-        if self.settings.engine_is_valid():
-            return {
-                "application/pdf": ".pdf",
-                "image/png": ".png",
-                "image/jpeg": ".jpg",
-                "image/tiff": ".tiff",
-                "image/bmp": ".bmp",
-                "image/gif": ".gif",
-                "image/webp": ".webp",
-            }
-        else:
-            return {}
-
-    def azure_ai_vision_parse(
-        self,
-        file: Path,
-    ) -> str | None:
-        """
-        Uses Azure AI Vision to parse the document and return the text content.
-        It requests a searchable PDF output with embedded text.
-        The PDF is saved to the archive_path attribute.
-        Returns the text content extracted from the document.
-        If the parsing fails, it returns None.
-        """
-        from azure.ai.documentintelligence import DocumentIntelligenceClient
-        from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
-        from azure.ai.documentintelligence.models import AnalyzeOutputOption
-        from azure.ai.documentintelligence.models import DocumentContentFormat
-        from azure.core.credentials import AzureKeyCredential
-
-        client = DocumentIntelligenceClient(
-            endpoint=self.settings.endpoint,
-            credential=AzureKeyCredential(self.settings.api_key),
-        )
-
-        with file.open("rb") as f:
-            analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
-            poller = client.begin_analyze_document(
-                model_id="prebuilt-read",
-                body=analyze_request,
-                output_content_format=DocumentContentFormat.TEXT,
-                output=[AnalyzeOutputOption.PDF],  # request searchable PDF output
-                content_type="application/json",
-            )
-
-        poller.wait()
-        result_id = poller.details["operation_id"]
-        result = poller.result()
-
-        # Download the PDF with embedded text
-        self.archive_path = Path(self.tempdir) / "archive.pdf"
-        with self.archive_path.open("wb") as f:
-            for chunk in client.get_analyze_result_pdf(
-                model_id="prebuilt-read",
-                result_id=result_id,
-            ):
-                f.write(chunk)
-
-        return result.content
-
-    def parse(self, document_path: Path, mime_type, file_name=None):
-        if not self.settings.engine_is_valid():
-            self.log.warning(
-                "No valid remote parser engine is configured, content will be empty.",
-            )
-            self.text = ""
-            return
-        elif self.settings.engine == "azureai":
-            self.text = self.azure_ai_vision_parse(document_path)

src/paperless_remote/signals.py

@@ -1,18 +0,0 @@
-def get_parser(*args, **kwargs):
-    from paperless_remote.parsers import RemoteDocumentParser
-
-    return RemoteDocumentParser(*args, **kwargs)
-
-
-def get_supported_mime_types():
-    from paperless_remote.parsers import RemoteDocumentParser
-
-    return RemoteDocumentParser(None).supported_mime_types()
-
-
-def remote_consumer_declaration(sender, **kwargs):
-    return {
-        "parser": get_parser,
-        "weight": 5,
-        "mime_types": get_supported_mime_types(),
-    }

src/paperless_remote/tests/test_checks.py

@@ -1,29 +0,0 @@
-from django.test import TestCase
-from django.test import override_settings
-
-from paperless_remote import check_remote_parser_configured
-
-
-class TestChecks(TestCase):
-    @override_settings(REMOTE_OCR_ENGINE=None)
-    def test_no_engine(self):
-        msgs = check_remote_parser_configured(None)
-        self.assertEqual(len(msgs), 0)
-
-    @override_settings(REMOTE_OCR_ENGINE="azureai")
-    @override_settings(REMOTE_OCR_API_KEY="somekey")
-    @override_settings(REMOTE_OCR_ENDPOINT=None)
-    def test_azure_no_endpoint(self):
-        msgs = check_remote_parser_configured(None)
-        self.assertEqual(len(msgs), 1)
-        self.assertTrue(
-            msgs[0].msg.startswith(
-                "Azure AI remote parser requires endpoint to be configured.",
-            ),
-        )
-
-    @override_settings(REMOTE_OCR_ENGINE="something")
-    @override_settings(REMOTE_OCR_API_KEY="somekey")
-    def test_valid_configuration(self):
-        msgs = check_remote_parser_configured(None)
-        self.assertEqual(len(msgs), 0)

src/paperless_remote/tests/test_parser.py

@@ -1,101 +0,0 @@
-import uuid
-from pathlib import Path
-from unittest import mock
-
-from django.test import TestCase
-from django.test import override_settings
-
-from documents.tests.utils import DirectoriesMixin
-from documents.tests.utils import FileSystemAssertsMixin
-from paperless_remote.parsers import RemoteDocumentParser
-from paperless_remote.signals import get_parser
-
-
-class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
-    SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
-
-    def assertContainsStrings(self, content, strings):
-        # Asserts that all strings appear in content, in the given order.
-        indices = []
-        for s in strings:
-            if s in content:
-                indices.append(content.index(s))
-            else:
-                self.fail(f"'{s}' is not in '{content}'")
-        self.assertListEqual(indices, sorted(indices))
-
-    @mock.patch("paperless_tesseract.parsers.run_subprocess")
-    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
-    def test_get_text_with_azure(self, mock_client_cls, mock_subprocess):
-        # Arrange mock Azure client
-        mock_client = mock.Mock()
-        mock_client_cls.return_value = mock_client
-
-        # Simulate poller result and its `.details`
-        mock_poller = mock.Mock()
-        mock_poller.wait.return_value = None
-        mock_poller.details = {"operation_id": "fake-op-id"}
-        mock_client.begin_analyze_document.return_value = mock_poller
-        mock_poller.result.return_value.content = "This is a test document."
-
-        # Return dummy PDF bytes
-        mock_client.get_analyze_result_pdf.return_value = [
-            b"%PDF-",
-            b"1.7 ",
-            b"FAKEPDF",
-        ]
-
-        # Simulate pdftotext by writing dummy text to sidecar file
-        def fake_run(cmd, *args, **kwargs):
-            with Path(cmd[-1]).open("w", encoding="utf-8") as f:
-                f.write("This is a test document.")
-
-        mock_subprocess.side_effect = fake_run
-
-        with override_settings(
-            REMOTE_OCR_ENGINE="azureai",
-            REMOTE_OCR_API_KEY="somekey",
-            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
-        ):
-            parser = get_parser(uuid.uuid4())
-            parser.parse(
-                self.SAMPLE_FILES / "simple-digital.pdf",
-                "application/pdf",
-            )
-
-            self.assertContainsStrings(
-                parser.text.strip(),
-                ["This is a test document."],
-            )
-
-    @override_settings(
-        REMOTE_OCR_ENGINE="azureai",
-        REMOTE_OCR_API_KEY="key",
-        REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
-    )
-    def test_supported_mime_types_valid_config(self):
-        parser = RemoteDocumentParser(uuid.uuid4())
-        expected_types = {
-            "application/pdf": ".pdf",
-            "image/png": ".png",
-            "image/jpeg": ".jpg",
-            "image/tiff": ".tiff",
-            "image/bmp": ".bmp",
-            "image/gif": ".gif",
-            "image/webp": ".webp",
-        }
-        self.assertEqual(parser.supported_mime_types(), expected_types)
-
-    def test_supported_mime_types_invalid_config(self):
-        parser = get_parser(uuid.uuid4())
-        self.assertEqual(parser.supported_mime_types(), {})
-
-    @override_settings(
-        REMOTE_OCR_ENGINE=None,
-        REMOTE_OCR_API_KEY=None,
-        REMOTE_OCR_ENDPOINT=None,
-    )
-    def test_parse_with_invalid_config(self):
-        parser = get_parser(uuid.uuid4())
-        parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
-        self.assertEqual(parser.text, "")

uv.lock

@@ -93,34 +93,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/af/cc/55a32a2c98022d88812b5986d2a92c4ff3ee087e83b712ebc703bba452bf/Automat-24.8.1-py3-none-any.whl", hash = "sha256:bf029a7bc3da1e2c24da2343e7598affaa9f10bf0ab63ff808566ce90551e02a", size = 42585, upload-time = "2024-08-19T17:31:56.729Z" },
 ]
 
-[[package]]
-name = "azure-ai-documentintelligence"
-version = "1.0.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "azure-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
-]
-
-[[package]]
-name = "azure-core"
-version = "1.33.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "requests", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
-]
-
 [[package]]
 name = "babel"
 version = "2.17.0"
@@ -1411,15 +1383,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/fc/4e5a141c3f7c7bed550ac1f69e599e92b6be449dd4677ec09f325cad0955/inotifyrecursive-0.3.5-py3-none-any.whl", hash = "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f", size = 8009, upload-time = "2020-11-20T12:38:46.981Z" },
 ]
 
-[[package]]
-name = "isodate"
-version = "0.7.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
-]
-
 [[package]]
 name = "jinja2"
 version = "3.1.6"
@@ -1948,7 +1911,6 @@ name = "paperless-ngx"
 version = "2.17.1"
 source = { virtual = "." }
 dependencies = [
-    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "bleach", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "celery", extra = ["redis"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "channels", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2082,7 +2044,6 @@ typing = [
 
 [package.metadata]
 requires-dist = [
-    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "bleach", specifier = "~=6.2.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },
     { name = "channels", specifier = "~=4.2" },