Merge branch 'dev' into feature-remote-ocr-2

---------

Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>

Dockerfile

@@ -5,7 +5,7 @@
 # Purpose: Compiles the frontend
 # Notes:
 #  - Does PNPM stuff with Typescript and such
-FROM --platform=$BUILDPLATFORM docker.io/node:20-trixie-slim AS compile-frontend
+FROM --platform=$BUILDPLATFORM docker.io/node:20-bookworm-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:0.8.16-python3.12-trixie-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.8.15-python3.12-bookworm-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 
@@ -170,8 +170,20 @@ RUN set -eux \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES} \
     && echo "Installing pre-built updates" \
-      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all \
-        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-v${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all --parallel --parallel-max 4 \
+        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

@@ -1,319 +0,0 @@
-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/advanced_usage.md

@@ -506,6 +506,7 @@ for the possible codes and their meanings.
 The `localize_date` filter formats a date or datetime object into a localized string using Babel internationalization.
 This takes into account the provided locale for translation. Since this must be used on a date or datetime object,
 you must access the field directly, i.e. `document.created`.
+An ISO string can also be provided to control the output format.
 
 ###### Syntax
 
@@ -516,7 +517,7 @@ you must access the field directly, i.e. `document.created`.
 
 ###### Parameters
 
--   `value` (date | datetime): Date or datetime object to format (datetime should be timezone-aware)
+-   `value` (date | datetime | str): Date, datetime object or ISO string to format (datetime should be timezone-aware)
 -   `format` (str): Format type - either a Babel preset ('short', 'medium', 'long', 'full') or custom pattern
 -   `locale` (str): Locale code for localization (e.g., 'en_US', 'fr_FR', 'de_DE')
 

docs/configuration.md

@@ -1800,3 +1800,23 @@ 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

@@ -25,9 +25,10 @@ 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.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
 -   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

@@ -408,7 +408,7 @@ Currently, there are three events that correspond to workflow trigger 'types':
    but the document content has been extracted and metadata such as document type, tags, etc. have been set, so these can now
    be used for filtering.
 3. **Document Updated**: when a document is updated. Similar to 'added' events, triggers can include filtering by content matching,
-   tags, doc type, or correspondent.
+   tags, doc type, correspondent or storage path.
 4. **Scheduled**: a scheduled trigger that can be used to run workflows at a specific time. The date used can be either the document
    added, created, updated date or you can specify a (date) custom field. You can also specify a day offset from the date (positive
    offsets will trigger after the date, negative offsets will trigger before).
@@ -452,10 +452,11 @@ Workflows allow you to filter by:
 -   File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
     example, automatically assigning documents to different owners based on the upload directory.
 -   Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
--   Content matching (`Added` and `Updated` triggers only). Filter document content using the matching settings.
--   Tags (`Added` and `Updated` triggers only). Filter for documents with any of the specified tags
--   Document type (`Added` and `Updated` triggers only). Filter documents with this doc type
--   Correspondent (`Added` and `Updated` triggers only). Filter documents with this correspondent
+-   Content matching (`Added`, `Updated` and `Scheduled` triggers only). Filter document content using the matching settings.
+-   Tags (`Added`, `Updated` and `Scheduled` triggers only). Filter for documents with any of the specified tags
+-   Document type (`Added`, `Updated` and `Scheduled` triggers only). Filter documents with this doc type
+-   Correspondent (`Added`, `Updated` and `Scheduled` triggers only). Filter documents with this correspondent
+-   Storage path (`Added`, `Updated` and `Scheduled` triggers only). Filter documents with this storage path
 
 ### Workflow Actions
 
@@ -505,35 +506,52 @@ you may want to adjust these settings to prevent abuse.
 
 #### Workflow placeholders
 
-Some workflow text can include placeholders but the available options differ depending on the type of
-workflow trigger. This is because at the time of consumption (when the text is to be set), no automatic tags etc. have been
-applied. You can use the following placeholders with any trigger type:
+Titles can be assigned by workflows using [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/).
+This allows for complex logic to be used to generate the title, including [logical structures](https://jinja.palletsprojects.com/en/3.1.x/templates/#list-of-control-structures)
+and [filters](https://jinja.palletsprojects.com/en/3.1.x/templates/#id11).
+The template is provided as a string.
 
--   `{correspondent}`: assigned correspondent name
--   `{document_type}`: assigned document type name
--   `{owner_username}`: assigned owner username
--   `{added}`: added datetime
--   `{added_year}`: added year
--   `{added_year_short}`: added year
--   `{added_month}`: added month
--   `{added_month_name}`: added month name
--   `{added_month_name_short}`: added month short name
--   `{added_day}`: added day
--   `{added_time}`: added time in HH:MM format
--   `{original_filename}`: original file name without extension
--   `{filename}`: current file name without extension
+Using Jinja2 Templates is also useful for [Date localization](advanced_usage.md#Date-Localization) in the title.
+
+The available inputs differ depending on the type of workflow trigger.
+This is because at the time of consumption (when the text is to be set), no automatic tags etc. have been
+applied. You can use the following placeholders in the template with any trigger type:
+
+-   `{{correspondent}}`: assigned correspondent name
+-   `{{document_type}}`: assigned document type name
+-   `{{owner_username}}`: assigned owner username
+-   `{{added}}`: added datetime
+-   `{{added_year}}`: added year
+-   `{{added_year_short}}`: added year
+-   `{{added_month}}`: added month
+-   `{{added_month_name}}`: added month name
+-   `{{added_month_name_short}}`: added month short name
+-   `{{added_day}}`: added day
+-   `{{added_time}}`: added time in HH:MM format
+-   `{{original_filename}}`: original file name without extension
+-   `{{filename}}`: current file name without extension
 
 The following placeholders are only available for "added" or "updated" triggers
 
--   `{created}`: created datetime
--   `{created_year}`: created year
--   `{created_year_short}`: created year
--   `{created_month}`: created month
--   `{created_month_name}`: created month name
--   `{created_month_name_short}`: created month short name
--   `{created_day}`: created day
--   `{created_time}`: created time in HH:MM format
--   `{doc_url}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
+-   `{{created}}`: created datetime
+-   `{{created_year}}`: created year
+-   `{{created_year_short}}`: created year
+-   `{{created_month}}`: created month
+-   `{{created_month_name}}`: created month name
+-   `{created_month_name_short}}`: created month short name
+-   `{{created_day}}`: created day
+-   `{{created_time}}`: created time in HH:MM format
+-   `{{doc_url}}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
+
+##### Examples
+
+```jinja2
+{{ created | localize_date('MMMM', 'en_US') }}
+<!-- Output: "January" -->
+
+{{ added | localize_date('MMMM', 'de_DE') }}
+<!-- Output: "Juni" --> # codespell:ignore
+```
 
 ### Workflow permissions
 
@@ -850,6 +868,21 @@ 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.
+
+Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
+or page limitations (e.g. with a free tier).
+
 ## Architecture
 
 Paperless-ngx consists of the following components:

pyproject.toml

@@ -15,6 +15,7 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
+  "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.2.0",
   "celery[redis]~=5.5.1",
@@ -232,6 +233,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/src/app/components/common/custom-field-display/custom-field-display.component.html

@@ -35,6 +35,9 @@
             @case (CustomFieldDataType.Select) {
                 <span [ngbTooltip]="nameTooltip">{{getSelectValue(field, value)}}</span>
             }
+            @case (CustomFieldDataType.LongText) {
+                <p class="mb-0" [ngbTooltip]="nameTooltip">{{value | slice:0:20}}{{value.length > 20 ? '...' : ''}}</p>
+            }
             @default {
               <span [ngbTooltip]="nameTooltip">{{value}}</span>
             }

src-ui/src/app/components/common/custom-field-display/custom-field-display.component.ts

@@ -1,5 +1,5 @@
-import { CurrencyPipe, getLocaleCurrencyCode } from '@angular/common'
-import { Component, Input, LOCALE_ID, OnInit, inject } from '@angular/core'
+import { CurrencyPipe, getLocaleCurrencyCode, SlicePipe } from '@angular/common'
+import { Component, inject, Input, LOCALE_ID, OnInit } from '@angular/core'
 import { NgbTooltipModule } from '@ng-bootstrap/ng-bootstrap'
 import { takeUntil } from 'rxjs'
 import { CustomField, CustomFieldDataType } from 'src/app/data/custom-field'
@@ -14,7 +14,7 @@ import { LoadingComponentWithPermissions } from '../../loading-component/loading
   selector: 'pngx-custom-field-display',
   templateUrl: './custom-field-display.component.html',
   styleUrl: './custom-field-display.component.scss',
-  imports: [CustomDatePipe, CurrencyPipe, NgbTooltipModule],
+  imports: [CustomDatePipe, CurrencyPipe, NgbTooltipModule, SlicePipe],
 })
 export class CustomFieldDisplayComponent
   extends LoadingComponentWithPermissions

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.html

@@ -177,6 +177,7 @@
           <pngx-input-tags [allowCreate]="false" i18n-title title="Has any of tags" formControlName="filter_has_tags"></pngx-input-tags>
           <pngx-input-select i18n-title title="Has correspondent" [items]="correspondents" [allowNull]="true" formControlName="filter_has_correspondent"></pngx-input-select>
           <pngx-input-select i18n-title title="Has document type" [items]="documentTypes" [allowNull]="true" formControlName="filter_has_document_type"></pngx-input-select>
+          <pngx-input-select i18n-title title="Has storage path" [items]="storagePaths" [allowNull]="true" formControlName="filter_has_storage_path"></pngx-input-select>
         </div>
       }
     </div>

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts

@@ -412,6 +412,9 @@ export class WorkflowEditDialogComponent
         filter_has_document_type: new FormControl(
           trigger.filter_has_document_type
         ),
+        filter_has_storage_path: new FormControl(
+          trigger.filter_has_storage_path
+        ),
         schedule_offset_days: new FormControl(trigger.schedule_offset_days),
         schedule_is_recurring: new FormControl(trigger.schedule_is_recurring),
         schedule_recurring_interval_days: new FormControl(
@@ -536,6 +539,7 @@ export class WorkflowEditDialogComponent
       filter_has_tags: [],
       filter_has_correspondent: null,
       filter_has_document_type: null,
+      filter_has_storage_path: null,
       matching_algorithm: MATCH_NONE,
       match: '',
       is_insensitive: true,

src-ui/src/app/components/common/input/custom-fields-values/custom-fields-values.component.html

@@ -68,6 +68,11 @@
           [allowNull]="true"
           [horizontal]="true"></pngx-input-select>
         }
+        @case (CustomFieldDataType.LongText) {
+          <pngx-input-textarea [(ngModel)]="value[fieldId]" (ngModelChange)="onChange(value)"
+          [title]="getCustomField(fieldId)?.name"
+          class="flex-grow-1"></pngx-input-textarea>
+        }
       }
       <button type="button" class="btn btn-link text-danger" (click)="removeSelectedField.next(fieldId)">
         <i-bs name="trash"></i-bs>

src-ui/src/app/components/common/input/custom-fields-values/custom-fields-values.component.ts

@@ -24,6 +24,7 @@ import { MonetaryComponent } from '../monetary/monetary.component'
 import { NumberComponent } from '../number/number.component'
 import { SelectComponent } from '../select/select.component'
 import { TextComponent } from '../text/text.component'
+import { TextAreaComponent } from '../textarea/textarea.component'
 import { UrlComponent } from '../url/url.component'
 
 @Component({
@@ -51,6 +52,7 @@ import { UrlComponent } from '../url/url.component'
     ReactiveFormsModule,
     RouterModule,
     NgxBootstrapIconsModule,
+    TextAreaComponent,
   ],
 })
 export class CustomFieldsValuesComponent extends AbstractInputComponent<Object> {

src-ui/src/app/components/common/input/textarea/textarea.component.ts

@@ -4,6 +4,7 @@ import {
   NG_VALUE_ACCESSOR,
   ReactiveFormsModule,
 } from '@angular/forms'
+import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { SafeHtmlPipe } from 'src/app/pipes/safehtml.pipe'
 import { AbstractInputComponent } from '../abstract-input'
 
@@ -18,7 +19,12 @@ import { AbstractInputComponent } from '../abstract-input'
   selector: 'pngx-input-textarea',
   templateUrl: './textarea.component.html',
   styleUrls: ['./textarea.component.scss'],
-  imports: [FormsModule, ReactiveFormsModule, SafeHtmlPipe],
+  imports: [
+    FormsModule,
+    ReactiveFormsModule,
+    SafeHtmlPipe,
+    NgxBootstrapIconsModule,
+  ],
 })
 export class TextAreaComponent extends AbstractInputComponent<string> {
   @Input()

src-ui/src/app/components/common/pdf-editor/pdf-editor.component.html

@@ -30,7 +30,7 @@
       <div class="page-item rounded p-2" cdkDrag (click)="toggleSelection(i)" [class.selected]="p.selected">
         <div class="btn-toolbar hover-actions z-10">
           <div class="btn-group me-2">
-            <button class="btn btn-sm btn-dark" (click)="rotate(i); $event.stopPropagation()" title="Rotate page counter-clockwise" i18n-title>
+            <button class="btn btn-sm btn-dark" (click)="rotate(i, true); $event.stopPropagation()" title="Rotate page counter-clockwise" i18n-title>
               <i-bs name="arrow-counterclockwise"></i-bs>
             </button>
             <button class="btn btn-sm btn-dark" (click)="rotate(i); $event.stopPropagation()" title="Rotate page clockwise" i18n-title>

src-ui/src/app/components/common/pdf-editor/pdf-editor.component.ts

@@ -67,8 +67,9 @@ export class PDFEditorComponent extends ConfirmDialogComponent {
     this.pages[i].selected = !this.pages[i].selected
   }
 
-  rotate(i: number) {
-    this.pages[i].rotate = (this.pages[i].rotate + 90) % 360
+  rotate(i: number, counterclockwise: boolean = false) {
+    this.pages[i].rotate =
+      (this.pages[i].rotate + (counterclockwise ? -90 : 90) + 360) % 360
   }
 
   rotateSelected(dir: number) {

src-ui/src/app/components/common/toast/toast.component.html

@@ -17,7 +17,7 @@
             <i-bs width="0.9em" height="0.9em" name="exclamation-triangle"></i-bs>
         }
         <div>
-            <p class="ms-2 mb-0">{{toast.content}}</p>
+            <p class="ms-2 mb-0 text-break">{{toast.content}}</p>
             @if (toast.error) {
             <details class="ms-2">
                 <div class="mt-2 ms-n4 me-n2 small">

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -54,6 +54,10 @@
         <i-bs width="1em" height="1em" name="arrow-counterclockwise"></i-bs>&nbsp;<span i18n>Reprocess</span>
       </button>
 
+      <button ngbDropdownItem (click)="printDocument()" [hidden]="useNativePdfViewer || isMobile">
+        <i-bs width="1em" height="1em" name="printer"></i-bs>&nbsp;<span i18n>Print</span>
+      </button>
+
       <button ngbDropdownItem (click)="moreLike()">
         <i-bs width="1em" height="1em" name="diagram-3"></i-bs>&nbsp;<span i18n>More like this</span>
       </button>
@@ -212,6 +216,14 @@
                       (removed)="removeField(fieldInstance)"
                       [error]="getCustomFieldError(i)"></pngx-input-select>
                     }
+                    @case (CustomFieldDataType.LongText) {
+                      <pngx-input-textarea formControlName="value"
+                      [title]="getCustomFieldFromInstance(fieldInstance)?.name"
+                      [removable]="userCanEdit"
+                      (removed)="removeField(fieldInstance)"
+                      [horizontal]="true"
+                      [error]="getCustomFieldError(i)"></pngx-input-textarea>
+                    }
                   }
                 </div>
               }

src-ui/src/app/components/document-detail/document-detail.component.spec.ts

@@ -1415,4 +1415,151 @@ describe('DocumentDetailComponent', () => {
       .flush('fail', { status: 500, statusText: 'Server Error' })
     expect(component.previewText).toContain('An error occurred loading content')
   })
+
+  it('should print document successfully', fakeAsync(() => {
+    initNormally()
+
+    const appendChildSpy = jest
+      .spyOn(document.body, 'appendChild')
+      .mockImplementation((node: Node) => node)
+    const removeChildSpy = jest
+      .spyOn(document.body, 'removeChild')
+      .mockImplementation((node: Node) => node)
+    const createObjectURLSpy = jest
+      .spyOn(URL, 'createObjectURL')
+      .mockReturnValue('blob:mock-url')
+    const revokeObjectURLSpy = jest
+      .spyOn(URL, 'revokeObjectURL')
+      .mockImplementation(() => {})
+
+    const mockContentWindow = {
+      focus: jest.fn(),
+      print: jest.fn(),
+      onafterprint: null,
+    }
+
+    const mockIframe = {
+      style: {},
+      src: '',
+      onload: null,
+      contentWindow: mockContentWindow,
+    }
+
+    const createElementSpy = jest
+      .spyOn(document, 'createElement')
+      .mockReturnValue(mockIframe as any)
+
+    const blob = new Blob(['test'], { type: 'application/pdf' })
+    component.printDocument()
+
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/${doc.id}/download/`
+    )
+    req.flush(blob)
+
+    tick()
+
+    expect(createElementSpy).toHaveBeenCalledWith('iframe')
+    expect(appendChildSpy).toHaveBeenCalledWith(mockIframe)
+    expect(createObjectURLSpy).toHaveBeenCalledWith(blob)
+
+    if (mockIframe.onload) {
+      mockIframe.onload({} as any)
+    }
+
+    expect(mockContentWindow.focus).toHaveBeenCalled()
+    expect(mockContentWindow.print).toHaveBeenCalled()
+
+    if (mockIframe.onload) {
+      mockIframe.onload(new Event('load'))
+    }
+
+    if (mockContentWindow.onafterprint) {
+      mockContentWindow.onafterprint(new Event('afterprint'))
+    }
+
+    expect(removeChildSpy).toHaveBeenCalledWith(mockIframe)
+    expect(revokeObjectURLSpy).toHaveBeenCalledWith('blob:mock-url')
+
+    createElementSpy.mockRestore()
+    appendChildSpy.mockRestore()
+    removeChildSpy.mockRestore()
+    createObjectURLSpy.mockRestore()
+    revokeObjectURLSpy.mockRestore()
+  }))
+
+  it('should show error toast if print document fails', () => {
+    initNormally()
+    const toastSpy = jest.spyOn(toastService, 'showError')
+    component.printDocument()
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/${doc.id}/download/`
+    )
+    req.error(new ErrorEvent('failed'))
+    expect(toastSpy).toHaveBeenCalledWith(
+      'Error loading document for printing.'
+    )
+  })
+
+  it('should show error toast if printing throws inside iframe', fakeAsync(() => {
+    initNormally()
+
+    const appendChildSpy = jest
+      .spyOn(document.body, 'appendChild')
+      .mockImplementation((node: Node) => node)
+    const removeChildSpy = jest
+      .spyOn(document.body, 'removeChild')
+      .mockImplementation((node: Node) => node)
+    const createObjectURLSpy = jest
+      .spyOn(URL, 'createObjectURL')
+      .mockReturnValue('blob:mock-url')
+    const revokeObjectURLSpy = jest
+      .spyOn(URL, 'revokeObjectURL')
+      .mockImplementation(() => {})
+
+    const toastSpy = jest.spyOn(toastService, 'showError')
+
+    const mockContentWindow = {
+      focus: jest.fn().mockImplementation(() => {
+        throw new Error('focus failed')
+      }),
+      print: jest.fn(),
+      onafterprint: null,
+    }
+
+    const mockIframe: any = {
+      style: {},
+      src: '',
+      onload: null,
+      contentWindow: mockContentWindow,
+    }
+
+    const createElementSpy = jest
+      .spyOn(document, 'createElement')
+      .mockReturnValue(mockIframe as any)
+
+    const blob = new Blob(['test'], { type: 'application/pdf' })
+    component.printDocument()
+
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/${doc.id}/download/`
+    )
+    req.flush(blob)
+
+    tick()
+
+    if (mockIframe.onload) {
+      mockIframe.onload(new Event('load'))
+    }
+
+    expect(toastSpy).toHaveBeenCalled()
+    expect(removeChildSpy).toHaveBeenCalledWith(mockIframe)
+    expect(revokeObjectURLSpy).toHaveBeenCalledWith('blob:mock-url')
+
+    createElementSpy.mockRestore()
+    appendChildSpy.mockRestore()
+    removeChildSpy.mockRestore()
+    createObjectURLSpy.mockRestore()
+    revokeObjectURLSpy.mockRestore()
+  }))
 })

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -98,6 +98,7 @@ import { PermissionsFormComponent } from '../common/input/permissions/permission
 import { SelectComponent } from '../common/input/select/select.component'
 import { TagsComponent } from '../common/input/tags/tags.component'
 import { TextComponent } from '../common/input/text/text.component'
+import { TextAreaComponent } from '../common/input/textarea/textarea.component'
 import { UrlComponent } from '../common/input/url/url.component'
 import { PageHeaderComponent } from '../common/page-header/page-header.component'
 import {
@@ -173,6 +174,7 @@ export enum ZoomSetting {
     NgbDropdownModule,
     NgxBootstrapIconsModule,
     PdfViewerModule,
+    TextAreaComponent,
   ],
 })
 export class DocumentDetailComponent
@@ -291,6 +293,10 @@ export class DocumentDetailComponent
     return this.settings.get(SETTINGS_KEYS.USE_NATIVE_PDF_VIEWER)
   }
 
+  get isMobile(): boolean {
+    return this.deviceDetectorService.isMobile()
+  }
+
   get archiveContentRenderType(): ContentRenderType {
     return this.document?.archived_file_name
       ? this.getRenderType('application/pdf')
@@ -1419,6 +1425,44 @@ export class DocumentDetailComponent
       })
   }
 
+  printDocument() {
+    const printUrl = this.documentsService.getDownloadUrl(
+      this.document.id,
+      false
+    )
+    this.http
+      .get(printUrl, { responseType: 'blob' })
+      .pipe(takeUntil(this.unsubscribeNotifier))
+      .subscribe({
+        next: (blob) => {
+          const blobUrl = URL.createObjectURL(blob)
+          const iframe = document.createElement('iframe')
+          iframe.style.display = 'none'
+          iframe.src = blobUrl
+          document.body.appendChild(iframe)
+          iframe.onload = () => {
+            try {
+              iframe.contentWindow.focus()
+              iframe.contentWindow.print()
+              iframe.contentWindow.onafterprint = () => {
+                document.body.removeChild(iframe)
+                URL.revokeObjectURL(blobUrl)
+              }
+            } catch (err) {
+              this.toastService.showError($localize`Print failed.`, err)
+              document.body.removeChild(iframe)
+              URL.revokeObjectURL(blobUrl)
+            }
+          }
+        },
+        error: () => {
+          this.toastService.showError(
+            $localize`Error loading document for printing.`
+          )
+        },
+      })
+  }
+
   public openShareLinks() {
     const modal = this.modalService.open(ShareLinksDialogComponent)
     modal.componentInstance.documentId = this.document.id

src-ui/src/app/components/document-list/bulk-editor/custom-fields-bulk-edit-dialog/custom-fields-bulk-edit-dialog.component.html

@@ -56,6 +56,10 @@
                 [items]="field.extra_data.select_options" bindLabel="label" [allowNull]="true" [horizontal]="true">
               </pngx-input-select>
             }
+            @case (CustomFieldDataType.LongText) {
+              <pngx-input-textarea formControlName="{{field.id}}" class="w-100" [title]="field.name" [horizontal]="true">
+              </pngx-input-textarea>
+            }
           }
           <button type="button" class="btn btn-outline-danger mb-3" (click)="removeField(field.id)">
             <i-bs name="x"></i-bs>

src-ui/src/app/components/document-list/bulk-editor/custom-fields-bulk-edit-dialog/custom-fields-bulk-edit-dialog.component.ts

@@ -18,6 +18,7 @@ import { TextComponent } from 'src/app/components/common/input/text/text.compone
 import { UrlComponent } from 'src/app/components/common/input/url/url.component'
 import { CustomField, CustomFieldDataType } from 'src/app/data/custom-field'
 import { DocumentService } from 'src/app/services/rest/document.service'
+import { TextAreaComponent } from '../../../common/input/textarea/textarea.component'
 
 @Component({
   selector: 'pngx-custom-fields-bulk-edit-dialog',
@@ -35,6 +36,7 @@ import { DocumentService } from 'src/app/services/rest/document.service'
     FormsModule,
     ReactiveFormsModule,
     NgxBootstrapIconsModule,
+    TextAreaComponent,
   ],
 })
 export class CustomFieldsBulkEditDialogComponent {

src-ui/src/app/data/custom-field-query.ts

@@ -114,6 +114,10 @@ export const CUSTOM_FIELD_QUERY_OPERATOR_GROUPS_BY_TYPE = {
     CustomFieldQueryOperatorGroups.Exact,
     CustomFieldQueryOperatorGroups.Subset,
   ],
+  [CustomFieldDataType.LongText]: [
+    CustomFieldQueryOperatorGroups.Basic,
+    CustomFieldQueryOperatorGroups.String,
+  ],
 }
 
 export const CUSTOM_FIELD_QUERY_VALUE_TYPES_BY_OPERATOR = {

src-ui/src/app/data/custom-field.ts

@@ -10,6 +10,7 @@ export enum CustomFieldDataType {
   Monetary = 'monetary',
   DocumentLink = 'documentlink',
   Select = 'select',
+  LongText = 'longtext',
 }
 
 export const DATA_TYPE_LABELS = [
@@ -49,6 +50,10 @@ export const DATA_TYPE_LABELS = [
     id: CustomFieldDataType.Select,
     name: $localize`Select`,
   },
+  {
+    id: CustomFieldDataType.LongText,
+    name: $localize`Long Text`,
+  },
 ]
 
 export interface CustomField extends ObjectWithId {

src-ui/src/app/data/workflow-trigger.ts

@@ -44,6 +44,8 @@ export interface WorkflowTrigger extends ObjectWithId {
 
   filter_has_document_type?: number // DocumentType.id
 
+  filter_has_storage_path?: number // StoragePath.id
+
   schedule_offset_days?: number
 
   schedule_is_recurring?: boolean

src-ui/src/main.ts

@@ -110,6 +110,7 @@ import {
   playFill,
   plus,
   plusCircle,
+  printer,
   questionCircle,
   scissors,
   search,
@@ -319,6 +320,7 @@ const icons = {
   playFill,
   plus,
   plusCircle,
+  printer,
   questionCircle,
   scissors,
   search,

src/documents/bulk_edit.py

@@ -181,6 +181,7 @@ def modify_custom_fields(
                 defaults[value_field] = value
                 if (
                     custom_field.data_type == CustomField.FieldDataType.DOCUMENTLINK
+                    and value
                     and doc_id in value
                 ):
                     # Prevent self-linking

src/documents/filters.py

@@ -230,6 +230,7 @@ class CustomFieldsFilter(Filter):
                 | qs.filter(custom_fields__value_monetary__icontains=value)
                 | qs.filter(custom_fields__value_document_ids__icontains=value)
                 | qs.filter(custom_fields__value_select__in=option_ids)
+                | qs.filter(custom_fields__value_long_text__icontains=value)
             )
         else:
             return qs
@@ -314,6 +315,7 @@ class CustomFieldQueryParser:
         CustomField.FieldDataType.MONETARY: ("basic", "string", "arithmetic"),
         CustomField.FieldDataType.DOCUMENTLINK: ("basic", "containment"),
         CustomField.FieldDataType.SELECT: ("basic",),
+        CustomField.FieldDataType.LONG_TEXT: ("basic", "string"),
     }
 
     DATE_COMPONENTS = [
@@ -845,7 +847,10 @@ class DocumentsOrderingFilter(OrderingFilter):
 
             annotation = None
             match field.data_type:
-                case CustomField.FieldDataType.STRING:
+                case (
+                    CustomField.FieldDataType.STRING
+                    | CustomField.FieldDataType.LONG_TEXT
+                ):
                     annotation = Subquery(
                         CustomFieldInstance.objects.filter(
                             document_id=OuterRef("id"),

src/documents/matching.py

@@ -386,6 +386,16 @@ def existing_document_matches_workflow(
         )
         trigger_matched = False
 
+    # Document storage_path vs trigger has_storage_path
+    if (
+        trigger.filter_has_storage_path is not None
+        and document.storage_path != trigger.filter_has_storage_path
+    ):
+        reason = (
+            f"Document storage path {document.storage_path} does not match {trigger.filter_has_storage_path}",
+        )
+        trigger_matched = False
+
     # Document original_filename vs trigger filename
     if (
         trigger.filter_filename is not None
@@ -430,6 +440,11 @@ def prefilter_documents_by_workflowtrigger(
             document_type=trigger.filter_has_document_type,
         )
 
+    if trigger.filter_has_storage_path is not None:
+        documents = documents.filter(
+            storage_path=trigger.filter_has_storage_path,
+        )
+
     if trigger.filter_filename is not None and len(trigger.filter_filename) > 0:
         # the true fnmatch will actually run later so we just want a loose filter here
         regex = fnmatch_translate(trigger.filter_filename).lstrip("^").rstrip("$")

src/documents/migrations/1069_workflowtrigger_filter_has_storage_path_and_more.py

@@ -0,0 +1,35 @@
+# Generated by Django 5.2.6 on 2025-09-11 17:29
+
+import django.db.models.deletion
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1068_alter_document_created"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="workflowtrigger",
+            name="filter_has_storage_path",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                to="documents.storagepath",
+                verbose_name="has this storage path",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="workflowaction",
+            name="assign_title",
+            field=models.TextField(
+                blank=True,
+                help_text="Assign a document title, must  be a Jinja2 template, see documentation.",
+                null=True,
+                verbose_name="assign title",
+            ),
+        ),
+    ]

src/documents/migrations/1070_customfieldinstance_value_long_text_and_more.py

@@ -0,0 +1,39 @@
+# Generated by Django 5.2.6 on 2025-09-13 17:11
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1069_workflowtrigger_filter_has_storage_path_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="customfieldinstance",
+            name="value_long_text",
+            field=models.TextField(null=True),
+        ),
+        migrations.AlterField(
+            model_name="customfield",
+            name="data_type",
+            field=models.CharField(
+                choices=[
+                    ("string", "String"),
+                    ("url", "URL"),
+                    ("date", "Date"),
+                    ("boolean", "Boolean"),
+                    ("integer", "Integer"),
+                    ("float", "Float"),
+                    ("monetary", "Monetary"),
+                    ("documentlink", "Document Link"),
+                    ("select", "Select"),
+                    ("longtext", "Long Text"),
+                ],
+                editable=False,
+                max_length=50,
+                verbose_name="data type",
+            ),
+        ),
+    ]

src/documents/models.py

@@ -759,6 +759,7 @@ class CustomField(models.Model):
         MONETARY = ("monetary", _("Monetary"))
         DOCUMENTLINK = ("documentlink", _("Document Link"))
         SELECT = ("select", _("Select"))
+        LONG_TEXT = ("longtext", _("Long Text"))
 
     created = models.DateTimeField(
         _("created"),
@@ -816,6 +817,7 @@ class CustomFieldInstance(SoftDeleteModel):
         CustomField.FieldDataType.MONETARY: "value_monetary",
         CustomField.FieldDataType.DOCUMENTLINK: "value_document_ids",
         CustomField.FieldDataType.SELECT: "value_select",
+        CustomField.FieldDataType.LONG_TEXT: "value_long_text",
     }
 
     created = models.DateTimeField(
@@ -883,6 +885,8 @@ class CustomFieldInstance(SoftDeleteModel):
 
     value_select = models.CharField(null=True, max_length=16)
 
+    value_long_text = models.TextField(null=True)
+
     class Meta:
         ordering = ("created",)
         verbose_name = _("custom field instance")
@@ -1044,6 +1048,14 @@ class WorkflowTrigger(models.Model):
         verbose_name=_("has this correspondent"),
     )
 
+    filter_has_storage_path = models.ForeignKey(
+        StoragePath,
+        null=True,
+        blank=True,
+        on_delete=models.SET_NULL,
+        verbose_name=_("has this storage path"),
+    )
+
     schedule_offset_days = models.IntegerField(
         _("schedule offset days"),
         default=0,
@@ -1207,14 +1219,12 @@ class WorkflowAction(models.Model):
         default=WorkflowActionType.ASSIGNMENT,
     )
 
-    assign_title = models.CharField(
+    assign_title = models.TextField(
         _("assign title"),
-        max_length=256,
         null=True,
         blank=True,
         help_text=_(
-            "Assign a document title, can include some placeholders, "
-            "see documentation.",
+            "Assign a document title, must  be a Jinja2 template, see documentation.",
         ),
     )
 

src/documents/serialisers.py

@@ -2054,6 +2054,7 @@ class WorkflowTriggerSerializer(serializers.ModelSerializer):
             "filter_has_tags",
             "filter_has_correspondent",
             "filter_has_document_type",
+            "filter_has_storage_path",
             "schedule_offset_days",
             "schedule_is_recurring",
             "schedule_recurring_interval_days",

src/documents/templating/environment.py

@@ -0,0 +1,27 @@
+from jinja2.sandbox import SandboxedEnvironment
+
+
+class JinjaEnvironment(SandboxedEnvironment):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.undefined_tracker = None
+
+    def is_safe_callable(self, obj):
+        # Block access to .save() and .delete() methods
+        if callable(obj) and getattr(obj, "__name__", None) in (
+            "save",
+            "delete",
+            "update",
+        ):
+            return False
+        # Call the parent method for other cases
+        return super().is_safe_callable(obj)
+
+
+_template_environment = JinjaEnvironment(
+    trim_blocks=True,
+    lstrip_blocks=True,
+    keep_trailing_newline=False,
+    autoescape=False,
+    extensions=["jinja2.ext.loopcontrols"],
+)

src/documents/templating/filepath.py

@@ -2,22 +2,16 @@ import logging
 import os
 import re
 from collections.abc import Iterable
-from datetime import date
-from datetime import datetime
 from pathlib import PurePath
 
 import pathvalidate
-from babel import Locale
-from babel import dates
 from django.utils import timezone
-from django.utils.dateparse import parse_date
 from django.utils.text import slugify as django_slugify
 from jinja2 import StrictUndefined
 from jinja2 import Template
 from jinja2 import TemplateSyntaxError
 from jinja2 import UndefinedError
 from jinja2 import make_logging_undefined
-from jinja2.sandbox import SandboxedEnvironment
 from jinja2.sandbox import SecurityError
 
 from documents.models import Correspondent
@@ -27,39 +21,16 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
+from documents.templating.environment import _template_environment
+from documents.templating.filters import format_datetime
+from documents.templating.filters import get_cf_value
+from documents.templating.filters import localize_date
 
 logger = logging.getLogger("paperless.templating")
 
 _LogStrictUndefined = make_logging_undefined(logger, StrictUndefined)
 
 
-class FilePathEnvironment(SandboxedEnvironment):
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.undefined_tracker = None
-
-    def is_safe_callable(self, obj):
-        # Block access to .save() and .delete() methods
-        if callable(obj) and getattr(obj, "__name__", None) in (
-            "save",
-            "delete",
-            "update",
-        ):
-            return False
-        # Call the parent method for other cases
-        return super().is_safe_callable(obj)
-
-
-_template_environment = FilePathEnvironment(
-    trim_blocks=True,
-    lstrip_blocks=True,
-    keep_trailing_newline=False,
-    autoescape=False,
-    extensions=["jinja2.ext.loopcontrols"],
-    undefined=_LogStrictUndefined,
-)
-
-
 class FilePathTemplate(Template):
     def render(self, *args, **kwargs) -> str:
         def clean_filepath(value: str) -> str:
@@ -81,54 +52,7 @@ class FilePathTemplate(Template):
         return clean_filepath(original_render)
 
 
-def get_cf_value(
-    custom_field_data: dict[str, dict[str, str]],
-    name: str,
-    default: str | None = None,
-) -> str | None:
-    if name in custom_field_data and custom_field_data[name]["value"] is not None:
-        return custom_field_data[name]["value"]
-    elif default is not None:
-        return default
-    return None
-
-
-def format_datetime(value: str | datetime, format: str) -> str:
-    if isinstance(value, str):
-        value = parse_date(value)
-    return value.strftime(format=format)
-
-
-def localize_date(value: date | datetime, format: str, locale: str) -> str:
-    """
-    Format a date or datetime object into a localized string using Babel.
-
-    Args:
-        value (date | datetime): The date or datetime to format. If a datetime
-            is provided, it should be timezone-aware (e.g., UTC from a Django DB object).
-        format (str): The format to use. Can be one of Babel's preset formats
-            ('short', 'medium', 'long', 'full') or a custom pattern string.
-        locale (str): The locale code (e.g., 'en_US', 'fr_FR') to use for
-            localization.
-
-    Returns:
-        str: The localized, formatted date string.
-
-    Raises:
-        TypeError: If `value` is not a date or datetime instance.
-    """
-    try:
-        Locale.parse(locale)
-    except Exception as e:
-        raise ValueError(f"Invalid locale identifier: {locale}") from e
-
-    if isinstance(value, datetime):
-        return dates.format_datetime(value, format=format, locale=locale)
-    elif isinstance(value, date):
-        return dates.format_date(value, format=format, locale=locale)
-    else:
-        raise TypeError(f"Unsupported type {type(value)} for localize_date")
-
+_template_environment.undefined = _LogStrictUndefined
 
 _template_environment.filters["get_cf_value"] = get_cf_value
 
@@ -278,6 +202,7 @@ def get_custom_fields_context(
             CustomField.FieldDataType.MONETARY,
             CustomField.FieldDataType.STRING,
             CustomField.FieldDataType.URL,
+            CustomField.FieldDataType.LONG_TEXT,
         }:
             value = pathvalidate.sanitize_filename(
                 field_instance.value,

src/documents/templating/filters.py

@@ -0,0 +1,60 @@
+from datetime import date
+from datetime import datetime
+
+from babel import Locale
+from babel import dates
+from django.utils.dateparse import parse_date
+from django.utils.dateparse import parse_datetime
+
+
+def localize_date(value: date | datetime | str, format: str, locale: str) -> str:
+    """
+    Format a date, datetime or str object into a localized string using Babel.
+
+    Args:
+        value (date | datetime | str): The date or datetime to format. If a datetime
+            is provided, it should be timezone-aware (e.g., UTC from a Django DB object).
+            if str is provided is is parsed as date.
+        format (str): The format to use. Can be one of Babel's preset formats
+            ('short', 'medium', 'long', 'full') or a custom pattern string.
+        locale (str): The locale code (e.g., 'en_US', 'fr_FR') to use for
+            localization.
+
+    Returns:
+        str: The localized, formatted date string.
+
+    Raises:
+        TypeError: If `value` is not a date, datetime or str instance.
+    """
+    if isinstance(value, str):
+        value = parse_datetime(value)
+
+    try:
+        Locale.parse(locale)
+    except Exception as e:
+        raise ValueError(f"Invalid locale identifier: {locale}") from e
+
+    if isinstance(value, datetime):
+        return dates.format_datetime(value, format=format, locale=locale)
+    elif isinstance(value, date):
+        return dates.format_date(value, format=format, locale=locale)
+    else:
+        raise TypeError(f"Unsupported type {type(value)} for localize_date")
+
+
+def format_datetime(value: str | datetime, format: str) -> str:
+    if isinstance(value, str):
+        value = parse_date(value)
+    return value.strftime(format=format)
+
+
+def get_cf_value(
+    custom_field_data: dict[str, dict[str, str]],
+    name: str,
+    default: str | None = None,
+) -> str | None:
+    if name in custom_field_data and custom_field_data[name]["value"] is not None:
+        return custom_field_data[name]["value"]
+    elif default is not None:
+        return default
+    return None

src/documents/templating/workflows.py

@@ -1,7 +1,33 @@
+import logging
 from datetime import date
 from datetime import datetime
 from pathlib import Path
 
+from django.utils.text import slugify as django_slugify
+from jinja2 import StrictUndefined
+from jinja2 import Template
+from jinja2 import TemplateSyntaxError
+from jinja2 import UndefinedError
+from jinja2 import make_logging_undefined
+from jinja2.sandbox import SecurityError
+
+from documents.templating.environment import _template_environment
+from documents.templating.filters import format_datetime
+from documents.templating.filters import localize_date
+
+logger = logging.getLogger("paperless.templating")
+
+_LogStrictUndefined = make_logging_undefined(logger, StrictUndefined)
+
+
+_template_environment.undefined = _LogStrictUndefined
+
+_template_environment.filters["datetime"] = format_datetime
+
+_template_environment.filters["slugify"] = django_slugify
+
+_template_environment.filters["localize_date"] = localize_date
+
 
 def parse_w_workflow_placeholders(
     text: str,
@@ -20,6 +46,7 @@ def parse_w_workflow_placeholders(
     e.g. for pre-consumption triggers created will not have been parsed yet, but it will
     for added / updated triggers
     """
+
     formatting = {
         "correspondent": correspondent_name,
         "document_type": doc_type_name,
@@ -52,4 +79,28 @@ def parse_w_workflow_placeholders(
         formatting.update({"doc_title": doc_title})
     if doc_url is not None:
         formatting.update({"doc_url": doc_url})
-    return text.format(**formatting).strip()
+
+    logger.debug(f"Jinja Template is : {text}")
+    try:
+        template = _template_environment.from_string(
+            text,
+            template_class=Template,
+        )
+        rendered_template = template.render(formatting)
+
+        # We're good!
+        return rendered_template
+    except UndefinedError as e:
+        # The undefined class logs this already for us
+        raise e
+    except TemplateSyntaxError as e:
+        logger.warning(f"Template syntax error in title generation: {e}")
+    except SecurityError as e:
+        logger.warning(f"Template attempted restricted operation: {e}")
+    except Exception as e:
+        logger.warning(f"Unknown error in title generation: {e}")
+        logger.warning(
+            f"Invalid title format '{text}', workflow not applied: {e}",
+        )
+        raise e
+    return None

src/documents/tests/test_api_workflows.py

@@ -186,6 +186,7 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
                             "filter_has_tags": [self.t1.id],
                             "filter_has_document_type": self.dt.id,
                             "filter_has_correspondent": self.c.id,
+                            "filter_has_storage_path": self.sp.id,
                         },
                     ],
                     "actions": [

src/documents/tests/test_consumer.py

@@ -304,22 +304,6 @@ class TestConsumer(
         self.assertEqual(document.title, "Override Title")
         self._assert_first_last_send_progress()
 
-    def testOverrideTitleInvalidPlaceholders(self):
-        with self.assertLogs("paperless.consumer", level="ERROR") as cm:
-            with self.get_consumer(
-                self.get_test_file(),
-                DocumentMetadataOverrides(title="Override {correspondent]"),
-            ) as consumer:
-                consumer.run()
-
-                document = Document.objects.first()
-
-            self.assertIsNotNone(document)
-
-            self.assertEqual(document.title, "sample")
-            expected_str = "Error occurred parsing title override 'Override {correspondent]', falling back to original"
-            self.assertIn(expected_str, cm.output[0])
-
     def testOverrideCorrespondent(self):
         c = Correspondent.objects.create(name="test")
 
@@ -437,7 +421,7 @@ class TestConsumer(
             DocumentMetadataOverrides(
                 correspondent_id=c.pk,
                 document_type_id=dt.pk,
-                title="{correspondent}{document_type} {added_month}-{added_year_short}",
+                title="{{correspondent}}{{document_type}} {{added_month}}-{{added_year_short}}",
             ),
         ) as consumer:
             consumer.run()

src/documents/tests/test_document_model.py

@@ -18,14 +18,17 @@ class TestDocument(TestCase):
         self.originals_dir = tempfile.mkdtemp()
         self.thumb_dir = tempfile.mkdtemp()
 
-        override_settings(
+        self.overrides = override_settings(
             ORIGINALS_DIR=self.originals_dir,
             THUMBNAIL_DIR=self.thumb_dir,
-        ).enable()
+        )
+
+        self.overrides.enable()
 
     def tearDown(self) -> None:
         shutil.rmtree(self.originals_dir)
         shutil.rmtree(self.thumb_dir)
+        self.overrides.disable()
 
     def test_file_deletion(self):
         document = Document.objects.create(

src/documents/tests/test_file_handling.py

@@ -23,7 +23,6 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.tasks import empty_trash
-from documents.templating.filepath import localize_date
 from documents.tests.factories import DocumentFactory
 from documents.tests.utils import DirectoriesMixin
 from documents.tests.utils import FileSystemAssertsMixin
@@ -1591,166 +1590,13 @@ class TestFilenameGeneration(DirectoriesMixin, TestCase):
             )
 
 
-class TestDateLocalization:
+class TestPathDateLocalization:
     """
     Groups all tests related to the `localize_date` function.
     """
 
     TEST_DATE = datetime.date(2023, 10, 26)
 
-    TEST_DATETIME = datetime.datetime(
-        2023,
-        10,
-        26,
-        14,
-        30,
-        5,
-        tzinfo=datetime.timezone.utc,
-    )
-
-    @pytest.mark.parametrize(
-        "value, format_style, locale_str, expected_output",
-        [
-            pytest.param(
-                TEST_DATE,
-                "EEEE, MMM d, yyyy",
-                "en_US",
-                "Thursday, Oct 26, 2023",
-                id="date-en_US-custom",
-            ),
-            pytest.param(
-                TEST_DATE,
-                "dd.MM.yyyy",
-                "de_DE",
-                "26.10.2023",
-                id="date-de_DE-custom",
-            ),
-            # German weekday and month name translation
-            pytest.param(
-                TEST_DATE,
-                "EEEE",
-                "de_DE",
-                "Donnerstag",
-                id="weekday-de_DE",
-            ),
-            pytest.param(
-                TEST_DATE,
-                "MMMM",
-                "de_DE",
-                "Oktober",
-                id="month-de_DE",
-            ),
-            # French weekday and month name translation
-            pytest.param(
-                TEST_DATE,
-                "EEEE",
-                "fr_FR",
-                "jeudi",
-                id="weekday-fr_FR",
-            ),
-            pytest.param(
-                TEST_DATE,
-                "MMMM",
-                "fr_FR",
-                "octobre",
-                id="month-fr_FR",
-            ),
-        ],
-    )
-    def test_localize_date_with_date_objects(
-        self,
-        value: datetime.date,
-        format_style: str,
-        locale_str: str,
-        expected_output: str,
-    ):
-        """
-        Tests `localize_date` with `date` objects across different locales and formats.
-        """
-        assert localize_date(value, format_style, locale_str) == expected_output
-
-    @pytest.mark.parametrize(
-        "value, format_style, locale_str, expected_output",
-        [
-            pytest.param(
-                TEST_DATETIME,
-                "yyyy.MM.dd G 'at' HH:mm:ss zzz",
-                "en_US",
-                "2023.10.26 AD at 14:30:05 UTC",
-                id="datetime-en_US-custom",
-            ),
-            pytest.param(
-                TEST_DATETIME,
-                "dd.MM.yyyy",
-                "fr_FR",
-                "26.10.2023",
-                id="date-fr_FR-custom",
-            ),
-            # Spanish weekday and month translation
-            pytest.param(
-                TEST_DATETIME,
-                "EEEE",
-                "es_ES",
-                "jueves",
-                id="weekday-es_ES",
-            ),
-            pytest.param(
-                TEST_DATETIME,
-                "MMMM",
-                "es_ES",
-                "octubre",
-                id="month-es_ES",
-            ),
-            # Italian weekday and month translation
-            pytest.param(
-                TEST_DATETIME,
-                "EEEE",
-                "it_IT",
-                "giovedì",
-                id="weekday-it_IT",
-            ),
-            pytest.param(
-                TEST_DATETIME,
-                "MMMM",
-                "it_IT",
-                "ottobre",
-                id="month-it_IT",
-            ),
-        ],
-    )
-    def test_localize_date_with_datetime_objects(
-        self,
-        value: datetime.datetime,
-        format_style: str,
-        locale_str: str,
-        expected_output: str,
-    ):
-        # To handle the non-breaking space in French and other locales
-        result = localize_date(value, format_style, locale_str)
-        assert result.replace("\u202f", " ") == expected_output.replace("\u202f", " ")
-
-    @pytest.mark.parametrize(
-        "invalid_value",
-        [
-            "2023-10-26",
-            1698330605,
-            None,
-            [],
-            {},
-        ],
-    )
-    def test_localize_date_raises_type_error_for_invalid_input(self, invalid_value):
-        with pytest.raises(TypeError) as excinfo:
-            localize_date(invalid_value, "medium", "en_US")
-
-        assert f"Unsupported type {type(invalid_value)}" in str(excinfo.value)
-
-    def test_localize_date_raises_error_for_invalid_locale(self):
-        with pytest.raises(ValueError) as excinfo:
-            localize_date(self.TEST_DATE, "medium", "invalid_locale_code")
-
-        assert "Invalid locale identifier" in str(excinfo.value)
-
     @pytest.mark.django_db
     @pytest.mark.parametrize(
         "filename_format,expected_filename",

src/documents/tests/test_filters.py

@@ -0,0 +1,296 @@
+import datetime
+from typing import Any
+from typing import Literal
+
+import pytest
+
+from documents.templating.filters import localize_date
+
+
+class TestDateLocalization:
+    """
+    Groups all tests related to the `localize_date` function.
+    """
+
+    TEST_DATE = datetime.date(2023, 10, 26)
+
+    TEST_DATETIME = datetime.datetime(
+        2023,
+        10,
+        26,
+        14,
+        30,
+        5,
+        tzinfo=datetime.timezone.utc,
+    )
+
+    TEST_DATETIME_STRING: str = "2023-10-26T14:30:05+00:00"
+
+    TEST_DATE_STRING: str = "2023-10-26"
+
+    @pytest.mark.parametrize(
+        "value, format_style, locale_str, expected_output",
+        [
+            pytest.param(
+                TEST_DATE,
+                "EEEE, MMM d, yyyy",
+                "en_US",
+                "Thursday, Oct 26, 2023",
+                id="date-en_US-custom",
+            ),
+            pytest.param(
+                TEST_DATE,
+                "dd.MM.yyyy",
+                "de_DE",
+                "26.10.2023",
+                id="date-de_DE-custom",
+            ),
+            # German weekday and month name translation
+            pytest.param(
+                TEST_DATE,
+                "EEEE",
+                "de_DE",
+                "Donnerstag",
+                id="weekday-de_DE",
+            ),
+            pytest.param(
+                TEST_DATE,
+                "MMMM",
+                "de_DE",
+                "Oktober",
+                id="month-de_DE",
+            ),
+            # French weekday and month name translation
+            pytest.param(
+                TEST_DATE,
+                "EEEE",
+                "fr_FR",
+                "jeudi",
+                id="weekday-fr_FR",
+            ),
+            pytest.param(
+                TEST_DATE,
+                "MMMM",
+                "fr_FR",
+                "octobre",
+                id="month-fr_FR",
+            ),
+        ],
+    )
+    def test_localize_date_with_date_objects(
+        self,
+        value: datetime.date,
+        format_style: str,
+        locale_str: str,
+        expected_output: str,
+    ):
+        """
+        Tests `localize_date` with `date` objects across different locales and formats.
+        """
+        assert localize_date(value, format_style, locale_str) == expected_output
+
+    @pytest.mark.parametrize(
+        "value, format_style, locale_str, expected_output",
+        [
+            pytest.param(
+                TEST_DATETIME,
+                "yyyy.MM.dd G 'at' HH:mm:ss zzz",
+                "en_US",
+                "2023.10.26 AD at 14:30:05 UTC",
+                id="datetime-en_US-custom",
+            ),
+            pytest.param(
+                TEST_DATETIME,
+                "dd.MM.yyyy",
+                "fr_FR",
+                "26.10.2023",
+                id="date-fr_FR-custom",
+            ),
+            # Spanish weekday and month translation
+            pytest.param(
+                TEST_DATETIME,
+                "EEEE",
+                "es_ES",
+                "jueves",
+                id="weekday-es_ES",
+            ),
+            pytest.param(
+                TEST_DATETIME,
+                "MMMM",
+                "es_ES",
+                "octubre",
+                id="month-es_ES",
+            ),
+            # Italian weekday and month translation
+            pytest.param(
+                TEST_DATETIME,
+                "EEEE",
+                "it_IT",
+                "giovedì",
+                id="weekday-it_IT",
+            ),
+            pytest.param(
+                TEST_DATETIME,
+                "MMMM",
+                "it_IT",
+                "ottobre",
+                id="month-it_IT",
+            ),
+        ],
+    )
+    def test_localize_date_with_datetime_objects(
+        self,
+        value: datetime.datetime,
+        format_style: str,
+        locale_str: str,
+        expected_output: str,
+    ):
+        # To handle the non-breaking space in French and other locales
+        result = localize_date(value, format_style, locale_str)
+        assert result.replace("\u202f", " ") == expected_output.replace("\u202f", " ")
+
+    @pytest.mark.parametrize(
+        "invalid_value",
+        [
+            1698330605,
+            None,
+            [],
+            {},
+        ],
+    )
+    def test_localize_date_raises_type_error_for_invalid_input(
+        self,
+        invalid_value: None | list[object] | dict[Any, Any] | Literal[1698330605],
+    ):
+        with pytest.raises(TypeError) as excinfo:
+            localize_date(invalid_value, "medium", "en_US")
+
+        assert f"Unsupported type {type(invalid_value)}" in str(excinfo.value)
+
+    def test_localize_date_raises_error_for_invalid_locale(self):
+        with pytest.raises(ValueError) as excinfo:
+            localize_date(self.TEST_DATE, "medium", "invalid_locale_code")
+
+        assert "Invalid locale identifier" in str(excinfo.value)
+
+    @pytest.mark.parametrize(
+        "value, format_style, locale_str, expected_output",
+        [
+            pytest.param(
+                TEST_DATETIME_STRING,
+                "EEEE, MMM d, yyyy",
+                "en_US",
+                "Thursday, Oct 26, 2023",
+                id="date-en_US-custom",
+            ),
+            pytest.param(
+                TEST_DATETIME_STRING,
+                "dd.MM.yyyy",
+                "de_DE",
+                "26.10.2023",
+                id="date-de_DE-custom",
+            ),
+            # German weekday and month name translation
+            pytest.param(
+                TEST_DATETIME_STRING,
+                "EEEE",
+                "de_DE",
+                "Donnerstag",
+                id="weekday-de_DE",
+            ),
+            pytest.param(
+                TEST_DATETIME_STRING,
+                "MMMM",
+                "de_DE",
+                "Oktober",
+                id="month-de_DE",
+            ),
+            # French weekday and month name translation
+            pytest.param(
+                TEST_DATETIME_STRING,
+                "EEEE",
+                "fr_FR",
+                "jeudi",
+                id="weekday-fr_FR",
+            ),
+            pytest.param(
+                TEST_DATETIME_STRING,
+                "MMMM",
+                "fr_FR",
+                "octobre",
+                id="month-fr_FR",
+            ),
+        ],
+    )
+    def test_localize_date_with_datetime_string(
+        self,
+        value: str,
+        format_style: str,
+        locale_str: str,
+        expected_output: str,
+    ):
+        """
+        Tests `localize_date` with `date` string across different locales and formats.
+        """
+        assert localize_date(value, format_style, locale_str) == expected_output
+
+    @pytest.mark.parametrize(
+        "value, format_style, locale_str, expected_output",
+        [
+            pytest.param(
+                TEST_DATE_STRING,
+                "EEEE, MMM d, yyyy",
+                "en_US",
+                "Thursday, Oct 26, 2023",
+                id="date-en_US-custom",
+            ),
+            pytest.param(
+                TEST_DATE_STRING,
+                "dd.MM.yyyy",
+                "de_DE",
+                "26.10.2023",
+                id="date-de_DE-custom",
+            ),
+            # German weekday and month name translation
+            pytest.param(
+                TEST_DATE_STRING,
+                "EEEE",
+                "de_DE",
+                "Donnerstag",
+                id="weekday-de_DE",
+            ),
+            pytest.param(
+                TEST_DATE_STRING,
+                "MMMM",
+                "de_DE",
+                "Oktober",
+                id="month-de_DE",
+            ),
+            # French weekday and month name translation
+            pytest.param(
+                TEST_DATE_STRING,
+                "EEEE",
+                "fr_FR",
+                "jeudi",
+                id="weekday-fr_FR",
+            ),
+            pytest.param(
+                TEST_DATE_STRING,
+                "MMMM",
+                "fr_FR",
+                "octobre",
+                id="month-fr_FR",
+            ),
+        ],
+    )
+    def test_localize_date_with_date_string(
+        self,
+        value: str,
+        format_style: str,
+        locale_str: str,
+        expected_output: str,
+    ):
+        """
+        Tests `localize_date` with `date` string across different locales and formats.
+        """
+        assert localize_date(value, format_style, locale_str) == expected_output

src/documents/tests/test_management.py

@@ -97,12 +97,6 @@ class TestArchiver(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
 
 class TestDecryptDocuments(FileSystemAssertsMixin, TestCase):
-    @override_settings(
-        ORIGINALS_DIR=(Path(__file__).parent / "samples" / "originals"),
-        THUMBNAIL_DIR=(Path(__file__).parent / "samples" / "thumb"),
-        PASSPHRASE="test",
-        FILENAME_FORMAT=None,
-    )
     @mock.patch("documents.management.commands.decrypt_documents.input")
     def test_decrypt(self, m):
         media_dir = tempfile.mkdtemp()
@@ -111,55 +105,55 @@ class TestDecryptDocuments(FileSystemAssertsMixin, TestCase):
         originals_dir.mkdir(parents=True, exist_ok=True)
         thumb_dir.mkdir(parents=True, exist_ok=True)
 
-        override_settings(
+        with override_settings(
             ORIGINALS_DIR=originals_dir,
             THUMBNAIL_DIR=thumb_dir,
             PASSPHRASE="test",
-        ).enable()
+            FILENAME_FORMAT=None,
+        ):
+            doc = Document.objects.create(
+                checksum="82186aaa94f0b98697d704b90fd1c072",
+                title="wow",
+                filename="0000004.pdf.gpg",
+                mime_type="application/pdf",
+                storage_type=Document.STORAGE_TYPE_GPG,
+            )
 
-        doc = Document.objects.create(
-            checksum="82186aaa94f0b98697d704b90fd1c072",
-            title="wow",
-            filename="0000004.pdf.gpg",
-            mime_type="application/pdf",
-            storage_type=Document.STORAGE_TYPE_GPG,
-        )
+            shutil.copy(
+                (
+                    Path(__file__).parent
+                    / "samples"
+                    / "documents"
+                    / "originals"
+                    / "0000004.pdf.gpg"
+                ),
+                originals_dir / "0000004.pdf.gpg",
+            )
+            shutil.copy(
+                (
+                    Path(__file__).parent
+                    / "samples"
+                    / "documents"
+                    / "thumbnails"
+                    / "0000004.webp.gpg"
+                ),
+                thumb_dir / f"{doc.id:07}.webp.gpg",
+            )
 
-        shutil.copy(
-            (
-                Path(__file__).parent
-                / "samples"
-                / "documents"
-                / "originals"
-                / "0000004.pdf.gpg"
-            ),
-            originals_dir / "0000004.pdf.gpg",
-        )
-        shutil.copy(
-            (
-                Path(__file__).parent
-                / "samples"
-                / "documents"
-                / "thumbnails"
-                / "0000004.webp.gpg"
-            ),
-            thumb_dir / f"{doc.id:07}.webp.gpg",
-        )
+            call_command("decrypt_documents")
 
-        call_command("decrypt_documents")
+            doc.refresh_from_db()
 
-        doc.refresh_from_db()
+            self.assertEqual(doc.storage_type, Document.STORAGE_TYPE_UNENCRYPTED)
+            self.assertEqual(doc.filename, "0000004.pdf")
+            self.assertIsFile(Path(originals_dir) / "0000004.pdf")
+            self.assertIsFile(doc.source_path)
+            self.assertIsFile(Path(thumb_dir) / f"{doc.id:07}.webp")
+            self.assertIsFile(doc.thumbnail_path)
 
-        self.assertEqual(doc.storage_type, Document.STORAGE_TYPE_UNENCRYPTED)
-        self.assertEqual(doc.filename, "0000004.pdf")
-        self.assertIsFile(Path(originals_dir) / "0000004.pdf")
-        self.assertIsFile(doc.source_path)
-        self.assertIsFile(Path(thumb_dir) / f"{doc.id:07}.webp")
-        self.assertIsFile(doc.thumbnail_path)
-
-        with doc.source_file as f:
-            checksum: str = hashlib.md5(f.read()).hexdigest()
-            self.assertEqual(checksum, doc.checksum)
+            with doc.source_file as f:
+                checksum: str = hashlib.md5(f.read()).hexdigest()
+                self.assertEqual(checksum, doc.checksum)
 
 
 class TestMakeIndex(TestCase):

src/documents/tests/test_workflows.py

@@ -1,6 +1,8 @@
+import datetime
 import shutil
 import socket
 from datetime import timedelta
+from pathlib import Path
 from typing import TYPE_CHECKING
 from unittest import mock
 
@@ -15,6 +17,7 @@ from guardian.shortcuts import get_users_with_perms
 from httpx import HTTPError
 from httpx import HTTPStatusError
 from pytest_httpx import HTTPXMock
+from rest_framework.test import APIClient
 from rest_framework.test import APITestCase
 
 from documents.signals.handlers import run_workflows
@@ -22,7 +25,7 @@ from documents.signals.handlers import send_webhook
 
 if TYPE_CHECKING:
     from django.db.models import QuerySet
-
+from pytest_django.fixtures import SettingsWrapper
 
 from documents import tasks
 from documents.data_models import ConsumableDocument
@@ -122,7 +125,7 @@ class TestWorkflows(
             filter_path=f"*/{self.dirs.scratch_dir.parts[-1]}/*",
         )
         action = WorkflowAction.objects.create(
-            assign_title="Doc from {correspondent}",
+            assign_title="Doc from {{correspondent}}",
             assign_correspondent=self.c,
             assign_document_type=self.dt,
             assign_storage_path=self.sp,
@@ -241,7 +244,7 @@ class TestWorkflows(
         )
 
         action = WorkflowAction.objects.create(
-            assign_title="Doc from {correspondent}",
+            assign_title="Doc from {{correspondent}}",
             assign_correspondent=self.c,
             assign_document_type=self.dt,
             assign_storage_path=self.sp,
@@ -892,7 +895,7 @@ class TestWorkflows(
             filter_filename="*sample*",
         )
         action = WorkflowAction.objects.create(
-            assign_title="Doc created in {created_year}",
+            assign_title="Doc created in {{created_year}}",
             assign_correspondent=self.c2,
             assign_document_type=self.dt,
             assign_storage_path=self.sp,
@@ -1147,6 +1150,38 @@ class TestWorkflows(
             expected_str = f"Document correspondent {doc.correspondent} does not match {trigger.filter_has_correspondent}"
             self.assertIn(expected_str, cm.output[1])
 
+    def test_document_added_no_match_storage_path(self):
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+            filter_has_storage_path=self.sp,
+        )
+        action = WorkflowAction.objects.create(
+            assign_title="Doc assign owner",
+            assign_owner=self.user2,
+        )
+        w = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            original_filename="sample.pdf",
+        )
+
+        with self.assertLogs("paperless.matching", level="DEBUG") as cm:
+            document_consumption_finished.send(
+                sender=self.__class__,
+                document=doc,
+            )
+            expected_str = f"Document did not match {w}"
+            self.assertIn(expected_str, cm.output[0])
+            expected_str = f"Document storage path {doc.storage_path} does not match {trigger.filter_has_storage_path}"
+            self.assertIn(expected_str, cm.output[1])
+
     def test_document_added_invalid_title_placeholders(self):
         """
         GIVEN:
@@ -1155,7 +1190,7 @@ class TestWorkflows(
         WHEN:
             - File that matches is added
         THEN:
-            - Title is not updated, error is output
+            - Title is updated but the placeholder isn't replaced
         """
         trigger = WorkflowTrigger.objects.create(
             type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
@@ -1181,15 +1216,12 @@ class TestWorkflows(
             created=created,
         )
 
-        with self.assertLogs("paperless.handlers", level="ERROR") as cm:
-            document_consumption_finished.send(
-                sender=self.__class__,
-                document=doc,
-            )
-            expected_str = f"Error occurred parsing title assignment '{action.assign_title}', falling back to original"
-            self.assertIn(expected_str, cm.output[0])
+        document_consumption_finished.send(
+            sender=self.__class__,
+            document=doc,
+        )
 
-        self.assertEqual(doc.title, "sample test")
+        self.assertEqual(doc.title, "Doc {created_year]")
 
     def test_document_updated_workflow(self):
         trigger = WorkflowTrigger.objects.create(
@@ -1223,6 +1255,45 @@ class TestWorkflows(
 
         self.assertEqual(doc.custom_fields.all().count(), 1)
 
+    def test_document_consumption_workflow_month_placeholder_addded(self):
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+            sources=f"{DocumentSource.ApiUpload}",
+            filter_filename="simple*",
+        )
+
+        action = WorkflowAction.objects.create(
+            assign_title="Doc added in {{added_month_name_short}}",
+        )
+
+        w = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+        superuser = User.objects.create_superuser("superuser")
+        self.client.force_authenticate(user=superuser)
+        test_file = shutil.copy(
+            self.SAMPLE_DIR / "simple.pdf",
+            self.dirs.scratch_dir / "simple.pdf",
+        )
+        with mock.patch("documents.tasks.ProgressManager", DummyProgressManager):
+            tasks.consume_file(
+                ConsumableDocument(
+                    source=DocumentSource.ApiUpload,
+                    original_file=test_file,
+                ),
+                None,
+            )
+            document = Document.objects.first()
+            self.assertRegex(
+                document.title,
+                r"Doc added in \w{3,}",
+            )  # Match any 3-letter month name
+
     def test_document_updated_workflow_existing_custom_field(self):
         """
         GIVEN:
@@ -1777,6 +1848,7 @@ class TestWorkflows(
             filter_filename="*sample*",
             filter_has_document_type=self.dt,
             filter_has_correspondent=self.c,
+            filter_has_storage_path=self.sp,
         )
         trigger.filter_has_tags.set([self.t1])
         trigger.save()
@@ -1797,6 +1869,7 @@ class TestWorkflows(
                 title=f"sample test {i}",
                 checksum=f"checksum{i}",
                 correspondent=self.c,
+                storage_path=self.sp,
                 original_filename=f"sample_{i}.pdf",
                 document_type=self.dt if i % 2 == 0 else None,
             )
@@ -2035,7 +2108,7 @@ class TestWorkflows(
             filter_filename="*simple*",
         )
         action = WorkflowAction.objects.create(
-            assign_title="Doc from {correspondent}",
+            assign_title="Doc from {{correspondent}}",
             assign_correspondent=self.c,
             assign_document_type=self.dt,
             assign_storage_path=self.sp,
@@ -2614,7 +2687,7 @@ class TestWorkflows(
         )
         webhook_action = WorkflowActionWebhook.objects.create(
             use_params=False,
-            body="Test message: {doc_url}",
+            body="Test message: {{doc_url}}",
             url="http://paperless-ngx.com",
             include_document=False,
         )
@@ -2673,7 +2746,7 @@ class TestWorkflows(
         )
         webhook_action = WorkflowActionWebhook.objects.create(
             use_params=False,
-            body="Test message: {doc_url}",
+            body="Test message: {{doc_url}}",
             url="http://paperless-ngx.com",
             include_document=True,
         )
@@ -3130,3 +3203,238 @@ class TestWebhookSecurity:
         req = httpx_mock.get_request()
         assert req.headers["Host"] == "paperless-ngx.com"
         assert "evil.test" not in req.headers.get("Host", "")
+
+
+@pytest.mark.django_db
+class TestDateWorkflowLocalization(
+    SampleDirMixin,
+):
+    """Test cases for workflows that use date localization in templates."""
+
+    TEST_DATETIME = datetime.datetime(
+        2023,
+        6,
+        26,
+        14,
+        30,
+        5,
+        tzinfo=datetime.timezone.utc,
+    )
+
+    @pytest.mark.parametrize(
+        "title_template,expected_title",
+        [
+            pytest.param(
+                "Created at {{ created | localize_date('MMMM', 'es_ES') }}",
+                "Created at junio",
+                id="spanish_month",
+            ),
+            pytest.param(
+                "Created at {{ created | localize_date('MMMM', 'de_DE') }}",
+                "Created at Juni",  # codespell:ignore
+                id="german_month",
+            ),
+            pytest.param(
+                "Created at {{ created | localize_date('dd/MM/yyyy', 'en_GB') }}",
+                "Created at 26/06/2023",
+                id="british_date_format",
+            ),
+        ],
+    )
+    def test_document_added_workflow_localization(
+        self,
+        title_template: str,
+        expected_title: str,
+    ):
+        """
+        GIVEN:
+            - Document added workflow with title template using localize_date filter
+        WHEN:
+            - Document is consumed
+        THEN:
+            - Document title is set with localized date
+        """
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+            filter_filename="*sample*",
+        )
+
+        action = WorkflowAction.objects.create(
+            assign_title=title_template,
+        )
+
+        workflow = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        workflow.triggers.add(trigger)
+        workflow.actions.add(action)
+        workflow.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            correspondent=None,
+            original_filename="sample.pdf",
+            created=self.TEST_DATETIME,
+        )
+
+        document_consumption_finished.send(
+            sender=self.__class__,
+            document=doc,
+        )
+
+        doc.refresh_from_db()
+        assert doc.title == expected_title
+
+    @pytest.mark.parametrize(
+        "title_template,expected_title",
+        [
+            pytest.param(
+                "Created at {{ created | localize_date('MMMM', 'es_ES') }}",
+                "Created at junio",
+                id="spanish_month",
+            ),
+            pytest.param(
+                "Created at {{ created | localize_date('MMMM', 'de_DE') }}",
+                "Created at Juni",  # codespell:ignore
+                id="german_month",
+            ),
+            pytest.param(
+                "Created at {{ created | localize_date('dd/MM/yyyy', 'en_GB') }}",
+                "Created at 26/06/2023",
+                id="british_date_format",
+            ),
+        ],
+    )
+    def test_document_updated_workflow_localization(
+        self,
+        title_template: str,
+        expected_title: str,
+    ):
+        """
+        GIVEN:
+            - Document updated workflow with title template using localize_date filter
+        WHEN:
+            - Document is updated via API
+        THEN:
+            - Document title is set with localized date
+        """
+        # Setup test data
+        dt = DocumentType.objects.create(name="DocType Name")
+        c = Correspondent.objects.create(name="Correspondent Name")
+
+        client = APIClient()
+        superuser = User.objects.create_superuser("superuser")
+        client.force_authenticate(user=superuser)
+
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+            filter_has_document_type=dt,
+        )
+
+        doc = Document.objects.create(
+            title="sample test",
+            correspondent=c,
+            original_filename="sample.pdf",
+            created=self.TEST_DATETIME,
+        )
+
+        action = WorkflowAction.objects.create(
+            assign_title=title_template,
+        )
+
+        workflow = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        workflow.triggers.add(trigger)
+        workflow.actions.add(action)
+        workflow.save()
+
+        client.patch(
+            f"/api/documents/{doc.id}/",
+            {"document_type": dt.id},
+            format="json",
+        )
+
+        doc.refresh_from_db()
+        assert doc.title == expected_title
+
+    @pytest.mark.parametrize(
+        "title_template,expected_title",
+        [
+            pytest.param(
+                "Added at {{ added | localize_date('MMMM', 'es_ES') }}",
+                "Added at junio",
+                id="spanish_month",
+            ),
+            pytest.param(
+                "Added at {{ added | localize_date('MMMM', 'de_DE') }}",
+                "Added at Juni",  # codespell:ignore
+                id="german_month",
+            ),
+            pytest.param(
+                "Added at {{ added | localize_date('dd/MM/yyyy', 'en_GB') }}",
+                "Added at 26/06/2023",
+                id="british_date_format",
+            ),
+        ],
+    )
+    def test_document_consumption_workflow_localization(
+        self,
+        tmp_path: Path,
+        settings: SettingsWrapper,
+        title_template: str,
+        expected_title: str,
+    ):
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+            sources=f"{DocumentSource.ApiUpload}",
+            filter_filename="simple*",
+        )
+
+        test_file = shutil.copy(
+            self.SAMPLE_DIR / "simple.pdf",
+            tmp_path / "simple.pdf",
+        )
+
+        action = WorkflowAction.objects.create(
+            assign_title=title_template,
+        )
+
+        w = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+        (tmp_path / "scratch").mkdir(parents=True, exist_ok=True)
+        (tmp_path / "thumbnails").mkdir(parents=True, exist_ok=True)
+
+        # Temporarily override "now" for the environment so templates using
+        # added/created placeholders behave as if it's a different system date.
+        with (
+            mock.patch(
+                "documents.tasks.ProgressManager",
+                DummyProgressManager,
+            ),
+            mock.patch(
+                "django.utils.timezone.now",
+                return_value=self.TEST_DATETIME,
+            ),
+            override_settings(
+                SCRATCH_DIR=tmp_path / "scratch",
+                THUMBNAIL_DIR=tmp_path / "thumbnails",
+            ),
+        ):
+            tasks.consume_file(
+                ConsumableDocument(
+                    source=DocumentSource.ApiUpload,
+                    original_file=test_file,
+                ),
+                None,
+            )
+            document = Document.objects.first()
+            assert document.title == expected_title

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-09-09 20:04+0000\n"
+"POT-Creation-Date: 2025-09-14 03:21+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -21,39 +21,39 @@ msgstr ""
 msgid "Documents"
 msgstr ""
 
-#: documents/filters.py:384
+#: documents/filters.py:386
 msgid "Value must be valid JSON."
 msgstr ""
 
-#: documents/filters.py:403
+#: documents/filters.py:405
 msgid "Invalid custom field query expression"
 msgstr ""
 
-#: documents/filters.py:413
+#: documents/filters.py:415
 msgid "Invalid expression list. Must be nonempty."
 msgstr ""
 
-#: documents/filters.py:434
+#: documents/filters.py:436
 msgid "Invalid logical operator {op!r}"
 msgstr ""
 
-#: documents/filters.py:448
+#: documents/filters.py:450
 msgid "Maximum number of query conditions exceeded."
 msgstr ""
 
-#: documents/filters.py:513
+#: documents/filters.py:515
 msgid "{name!r} is not a valid custom field."
 msgstr ""
 
-#: documents/filters.py:550
+#: documents/filters.py:552
 msgid "{data_type} does not support query expr {expr!r}."
 msgstr ""
 
-#: documents/filters.py:658
+#: documents/filters.py:660
 msgid "Maximum nesting depth exceeded."
 msgstr ""
 
-#: documents/filters.py:843
+#: documents/filters.py:845
 msgid "Custom field not found"
 msgstr ""
 
@@ -61,27 +61,27 @@ msgstr ""
 msgid "owner"
 msgstr ""
 
-#: documents/models.py:53 documents/models.py:946
+#: documents/models.py:53 documents/models.py:950
 msgid "None"
 msgstr ""
 
-#: documents/models.py:54 documents/models.py:947
+#: documents/models.py:54 documents/models.py:951
 msgid "Any word"
 msgstr ""
 
-#: documents/models.py:55 documents/models.py:948
+#: documents/models.py:55 documents/models.py:952
 msgid "All words"
 msgstr ""
 
-#: documents/models.py:56 documents/models.py:949
+#: documents/models.py:56 documents/models.py:953
 msgid "Exact match"
 msgstr ""
 
-#: documents/models.py:57 documents/models.py:950
+#: documents/models.py:57 documents/models.py:954
 msgid "Regular expression"
 msgstr ""
 
-#: documents/models.py:58 documents/models.py:951
+#: documents/models.py:58 documents/models.py:955
 msgid "Fuzzy word"
 msgstr ""
 
@@ -89,20 +89,20 @@ msgstr ""
 msgid "Automatic"
 msgstr ""
 
-#: documents/models.py:62 documents/models.py:423 documents/models.py:1441
+#: documents/models.py:62 documents/models.py:423 documents/models.py:1451
 #: paperless_mail/models.py:23 paperless_mail/models.py:143
 msgid "name"
 msgstr ""
 
-#: documents/models.py:64 documents/models.py:1015
+#: documents/models.py:64 documents/models.py:1019
 msgid "match"
 msgstr ""
 
-#: documents/models.py:67 documents/models.py:1018
+#: documents/models.py:67 documents/models.py:1022
 msgid "matching algorithm"
 msgstr ""
 
-#: documents/models.py:72 documents/models.py:1023
+#: documents/models.py:72 documents/models.py:1027
 msgid "is insensitive"
 msgstr ""
 
@@ -207,7 +207,7 @@ msgid "The number of pages of the document."
 msgstr ""
 
 #: documents/models.py:217 documents/models.py:655 documents/models.py:693
-#: documents/models.py:764 documents/models.py:822
+#: documents/models.py:765 documents/models.py:824
 msgid "created"
 msgstr ""
 
@@ -256,7 +256,7 @@ msgid "The position of this document in your physical document archive."
 msgstr ""
 
 #: documents/models.py:294 documents/models.py:666 documents/models.py:720
-#: documents/models.py:1484
+#: documents/models.py:1494
 msgid "document"
 msgstr ""
 
@@ -280,11 +280,11 @@ msgstr ""
 msgid "Title"
 msgstr ""
 
-#: documents/models.py:410 documents/models.py:967
+#: documents/models.py:410 documents/models.py:971
 msgid "Created"
 msgstr ""
 
-#: documents/models.py:411 documents/models.py:966
+#: documents/models.py:411 documents/models.py:970
 msgid "Added"
 msgstr ""
 
@@ -752,427 +752,434 @@ msgstr ""
 msgid "Select"
 msgstr ""
 
-#: documents/models.py:773
+#: documents/models.py:762
+msgid "Long Text"
+msgstr ""
+
+#: documents/models.py:774
 msgid "data type"
 msgstr ""
 
-#: documents/models.py:780
+#: documents/models.py:781
 msgid "extra data"
 msgstr ""
 
-#: documents/models.py:784
+#: documents/models.py:785
 msgid "Extra data for the custom field, such as select options"
 msgstr ""
 
-#: documents/models.py:790
+#: documents/models.py:791
 msgid "custom field"
 msgstr ""
 
-#: documents/models.py:791
+#: documents/models.py:792
 msgid "custom fields"
 msgstr ""
 
-#: documents/models.py:888
+#: documents/models.py:892
 msgid "custom field instance"
 msgstr ""
 
-#: documents/models.py:889
+#: documents/models.py:893
 msgid "custom field instances"
 msgstr ""
 
-#: documents/models.py:954
+#: documents/models.py:958
 msgid "Consumption Started"
 msgstr ""
 
-#: documents/models.py:955
+#: documents/models.py:959
 msgid "Document Added"
 msgstr ""
 
-#: documents/models.py:956
+#: documents/models.py:960
 msgid "Document Updated"
 msgstr ""
 
-#: documents/models.py:957
+#: documents/models.py:961
 msgid "Scheduled"
 msgstr ""
 
-#: documents/models.py:960
+#: documents/models.py:964
 msgid "Consume Folder"
 msgstr ""
 
-#: documents/models.py:961
+#: documents/models.py:965
 msgid "Api Upload"
 msgstr ""
 
-#: documents/models.py:962
+#: documents/models.py:966
 msgid "Mail Fetch"
 msgstr ""
 
-#: documents/models.py:963
+#: documents/models.py:967
 msgid "Web UI"
 msgstr ""
 
-#: documents/models.py:968
+#: documents/models.py:972
 msgid "Modified"
 msgstr ""
 
-#: documents/models.py:969
+#: documents/models.py:973
 msgid "Custom Field"
 msgstr ""
 
-#: documents/models.py:972
+#: documents/models.py:976
 msgid "Workflow Trigger Type"
 msgstr ""
 
-#: documents/models.py:984
+#: documents/models.py:988
 msgid "filter path"
 msgstr ""
 
-#: documents/models.py:989
+#: documents/models.py:993
 msgid ""
 "Only consume documents with a path that matches this if specified. Wildcards "
 "specified as * are allowed. Case insensitive."
 msgstr ""
 
-#: documents/models.py:996
+#: documents/models.py:1000
 msgid "filter filename"
 msgstr ""
 
-#: documents/models.py:1001 paperless_mail/models.py:200
+#: documents/models.py:1005 paperless_mail/models.py:200
 msgid ""
 "Only consume documents which entirely match this filename if specified. "
 "Wildcards such as *.pdf or *invoice* are allowed. Case insensitive."
 msgstr ""
 
-#: documents/models.py:1012
+#: documents/models.py:1016
 msgid "filter documents from this mail rule"
 msgstr ""
 
-#: documents/models.py:1028
+#: documents/models.py:1032
 msgid "has these tag(s)"
 msgstr ""
 
-#: documents/models.py:1036
+#: documents/models.py:1040
 msgid "has this document type"
 msgstr ""
 
-#: documents/models.py:1044
+#: documents/models.py:1048
 msgid "has this correspondent"
 msgstr ""
 
-#: documents/models.py:1048
+#: documents/models.py:1056
+msgid "has this storage path"
+msgstr ""
+
+#: documents/models.py:1060
 msgid "schedule offset days"
 msgstr ""
 
-#: documents/models.py:1051
+#: documents/models.py:1063
 msgid "The number of days to offset the schedule trigger by."
 msgstr ""
 
-#: documents/models.py:1056
+#: documents/models.py:1068
 msgid "schedule is recurring"
 msgstr ""
 
-#: documents/models.py:1059
+#: documents/models.py:1071
 msgid "If the schedule should be recurring."
 msgstr ""
 
-#: documents/models.py:1064
+#: documents/models.py:1076
 msgid "schedule recurring delay in days"
 msgstr ""
 
-#: documents/models.py:1068
+#: documents/models.py:1080
 msgid "The number of days between recurring schedule triggers."
 msgstr ""
 
-#: documents/models.py:1073
+#: documents/models.py:1085
 msgid "schedule date field"
 msgstr ""
 
-#: documents/models.py:1078
+#: documents/models.py:1090
 msgid "The field to check for a schedule trigger."
 msgstr ""
 
-#: documents/models.py:1087
+#: documents/models.py:1099
 msgid "schedule date custom field"
 msgstr ""
 
-#: documents/models.py:1091
+#: documents/models.py:1103
 msgid "workflow trigger"
 msgstr ""
 
-#: documents/models.py:1092
+#: documents/models.py:1104
 msgid "workflow triggers"
 msgstr ""
 
-#: documents/models.py:1100
+#: documents/models.py:1112
 msgid "email subject"
 msgstr ""
 
-#: documents/models.py:1104
+#: documents/models.py:1116
 msgid ""
 "The subject of the email, can include some placeholders, see documentation."
 msgstr ""
 
-#: documents/models.py:1110
+#: documents/models.py:1122
 msgid "email body"
 msgstr ""
 
-#: documents/models.py:1113
+#: documents/models.py:1125
 msgid ""
 "The body (message) of the email, can include some placeholders, see "
 "documentation."
 msgstr ""
 
-#: documents/models.py:1119
+#: documents/models.py:1131
 msgid "emails to"
 msgstr ""
 
-#: documents/models.py:1122
+#: documents/models.py:1134
 msgid "The destination email addresses, comma separated."
 msgstr ""
 
-#: documents/models.py:1128
+#: documents/models.py:1140
 msgid "include document in email"
 msgstr ""
 
-#: documents/models.py:1139
+#: documents/models.py:1151
 msgid "webhook url"
 msgstr ""
 
-#: documents/models.py:1142
+#: documents/models.py:1154
 msgid "The destination URL for the notification."
 msgstr ""
 
-#: documents/models.py:1147
+#: documents/models.py:1159
 msgid "use parameters"
 msgstr ""
 
-#: documents/models.py:1152
+#: documents/models.py:1164
 msgid "send as JSON"
 msgstr ""
 
-#: documents/models.py:1156
+#: documents/models.py:1168
 msgid "webhook parameters"
 msgstr ""
 
-#: documents/models.py:1159
+#: documents/models.py:1171
 msgid "The parameters to send with the webhook URL if body not used."
 msgstr ""
 
-#: documents/models.py:1163
+#: documents/models.py:1175
 msgid "webhook body"
 msgstr ""
 
-#: documents/models.py:1166
+#: documents/models.py:1178
 msgid "The body to send with the webhook URL if parameters not used."
 msgstr ""
 
-#: documents/models.py:1170
+#: documents/models.py:1182
 msgid "webhook headers"
 msgstr ""
 
-#: documents/models.py:1173
+#: documents/models.py:1185
 msgid "The headers to send with the webhook URL."
 msgstr ""
 
-#: documents/models.py:1178
+#: documents/models.py:1190
 msgid "include document in webhook"
 msgstr ""
 
-#: documents/models.py:1189
+#: documents/models.py:1201
 msgid "Assignment"
 msgstr ""
 
-#: documents/models.py:1193
+#: documents/models.py:1205
 msgid "Removal"
 msgstr ""
 
-#: documents/models.py:1197 documents/templates/account/password_reset.html:15
+#: documents/models.py:1209 documents/templates/account/password_reset.html:15
 msgid "Email"
 msgstr ""
 
-#: documents/models.py:1201
+#: documents/models.py:1213
 msgid "Webhook"
 msgstr ""
 
-#: documents/models.py:1205
+#: documents/models.py:1217
 msgid "Workflow Action Type"
 msgstr ""
 
-#: documents/models.py:1211
+#: documents/models.py:1223
 msgid "assign title"
 msgstr ""
 
-#: documents/models.py:1216
-msgid ""
-"Assign a document title, can include some placeholders, see documentation."
+#: documents/models.py:1227
+msgid "Assign a document title, must  be a Jinja2 template, see documentation."
 msgstr ""
 
-#: documents/models.py:1225 paperless_mail/models.py:274
+#: documents/models.py:1235 paperless_mail/models.py:274
 msgid "assign this tag"
 msgstr ""
 
-#: documents/models.py:1234 paperless_mail/models.py:282
+#: documents/models.py:1244 paperless_mail/models.py:282
 msgid "assign this document type"
 msgstr ""
 
-#: documents/models.py:1243 paperless_mail/models.py:296
+#: documents/models.py:1253 paperless_mail/models.py:296
 msgid "assign this correspondent"
 msgstr ""
 
-#: documents/models.py:1252
+#: documents/models.py:1262
 msgid "assign this storage path"
 msgstr ""
 
-#: documents/models.py:1261
+#: documents/models.py:1271
 msgid "assign this owner"
 msgstr ""
 
-#: documents/models.py:1268
+#: documents/models.py:1278
 msgid "grant view permissions to these users"
 msgstr ""
 
-#: documents/models.py:1275
+#: documents/models.py:1285
 msgid "grant view permissions to these groups"
 msgstr ""
 
-#: documents/models.py:1282
+#: documents/models.py:1292
 msgid "grant change permissions to these users"
 msgstr ""
 
-#: documents/models.py:1289
+#: documents/models.py:1299
 msgid "grant change permissions to these groups"
 msgstr ""
 
-#: documents/models.py:1296
+#: documents/models.py:1306
 msgid "assign these custom fields"
 msgstr ""
 
-#: documents/models.py:1300
+#: documents/models.py:1310
 msgid "custom field values"
 msgstr ""
 
-#: documents/models.py:1304
+#: documents/models.py:1314
 msgid "Optional values to assign to the custom fields."
 msgstr ""
 
-#: documents/models.py:1313
+#: documents/models.py:1323
 msgid "remove these tag(s)"
 msgstr ""
 
-#: documents/models.py:1318
+#: documents/models.py:1328
 msgid "remove all tags"
 msgstr ""
 
-#: documents/models.py:1325
+#: documents/models.py:1335
 msgid "remove these document type(s)"
 msgstr ""
 
-#: documents/models.py:1330
+#: documents/models.py:1340
 msgid "remove all document types"
 msgstr ""
 
-#: documents/models.py:1337
+#: documents/models.py:1347
 msgid "remove these correspondent(s)"
 msgstr ""
 
-#: documents/models.py:1342
+#: documents/models.py:1352
 msgid "remove all correspondents"
 msgstr ""
 
-#: documents/models.py:1349
+#: documents/models.py:1359
 msgid "remove these storage path(s)"
 msgstr ""
 
-#: documents/models.py:1354
+#: documents/models.py:1364
 msgid "remove all storage paths"
 msgstr ""
 
-#: documents/models.py:1361
+#: documents/models.py:1371
 msgid "remove these owner(s)"
 msgstr ""
 
-#: documents/models.py:1366
+#: documents/models.py:1376
 msgid "remove all owners"
 msgstr ""
 
-#: documents/models.py:1373
+#: documents/models.py:1383
 msgid "remove view permissions for these users"
 msgstr ""
 
-#: documents/models.py:1380
+#: documents/models.py:1390
 msgid "remove view permissions for these groups"
 msgstr ""
 
-#: documents/models.py:1387
+#: documents/models.py:1397
 msgid "remove change permissions for these users"
 msgstr ""
 
-#: documents/models.py:1394
+#: documents/models.py:1404
 msgid "remove change permissions for these groups"
 msgstr ""
 
-#: documents/models.py:1399
+#: documents/models.py:1409
 msgid "remove all permissions"
 msgstr ""
 
-#: documents/models.py:1406
+#: documents/models.py:1416
 msgid "remove these custom fields"
 msgstr ""
 
-#: documents/models.py:1411
+#: documents/models.py:1421
 msgid "remove all custom fields"
 msgstr ""
 
-#: documents/models.py:1420
+#: documents/models.py:1430
 msgid "email"
 msgstr ""
 
-#: documents/models.py:1429
+#: documents/models.py:1439
 msgid "webhook"
 msgstr ""
 
-#: documents/models.py:1433
+#: documents/models.py:1443
 msgid "workflow action"
 msgstr ""
 
-#: documents/models.py:1434
+#: documents/models.py:1444
 msgid "workflow actions"
 msgstr ""
 
-#: documents/models.py:1443 paperless_mail/models.py:145
+#: documents/models.py:1453 paperless_mail/models.py:145
 msgid "order"
 msgstr ""
 
-#: documents/models.py:1449
+#: documents/models.py:1459
 msgid "triggers"
 msgstr ""
 
-#: documents/models.py:1456
+#: documents/models.py:1466
 msgid "actions"
 msgstr ""
 
-#: documents/models.py:1459 paperless_mail/models.py:154
+#: documents/models.py:1469 paperless_mail/models.py:154
 msgid "enabled"
 msgstr ""
 
-#: documents/models.py:1470
+#: documents/models.py:1480
 msgid "workflow"
 msgstr ""
 
-#: documents/models.py:1474
+#: documents/models.py:1484
 msgid "workflow trigger type"
 msgstr ""
 
-#: documents/models.py:1488
+#: documents/models.py:1498
 msgid "date run"
 msgstr ""
 
-#: documents/models.py:1494
+#: documents/models.py:1504
 msgid "workflow run"
 msgstr ""
 
-#: documents/models.py:1495
+#: documents/models.py:1505
 msgid "workflow runs"
 msgstr ""
 

src/paperless/settings.py

@@ -322,6 +322,7 @@ 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",
@@ -1388,3 +1389,10 @@ 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

@@ -0,0 +1,4 @@
+# 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

@@ -0,0 +1,14 @@
+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

@@ -0,0 +1,17 @@
+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 and settings.REMOTE_OCR_API_KEY
+    ):
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        ]
+
+    return []

src/paperless_remote/parsers.py

@@ -0,0 +1,114 @@
+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 = 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)
+
+        client.close()
+        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

@@ -0,0 +1,18 @@
+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

@@ -0,0 +1,30 @@
+from unittest 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 and API key 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

@@ -0,0 +1,101 @@
+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: str, strings: list[str]):
+        # 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

@@ -95,6 +95,34 @@ 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"
@@ -1403,6 +1431,15 @@ 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"
@@ -2023,6 +2060,7 @@ name = "paperless-ngx"
 version = "2.18.4"
 source = { virtual = "." }
 dependencies = [
+    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "babel", 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'" },
@@ -2159,6 +2197,7 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.2.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },