Merge branch 'Stirling-Tools:main' into main

.github/FUNDING.yml

@@ -10,4 +10,4 @@ liberapay: # Replace with a single Liberapay username
 issuehunt: # Replace with a single IssueHunt username
 otechie: # Replace with a single Otechie username
 lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
-custom: ['https://paypal.me/froodleplex?country.x=GB&locale.x=en_GB'] # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
+custom: ['https://www.paypal.com/donate/?hosted_button_id=MN7JPG5G6G3JL'] # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/workflows/build.yml

@@ -3,14 +3,8 @@ name: "Build repo"
 on:
   push:
     branches: ["main"]
-    paths-ignore:
-      - ".github/**"
-      - "**/*.md"
   pull_request:
     branches: ["main"]
-    paths-ignore:
-      - ".github/**"
-      - "**/*.md"
 
 jobs:
   build:
@@ -36,7 +30,7 @@ jobs:
 
       - uses: gradle/actions/setup-gradle@v3
         with:
-          gradle-version: 7.6
+          gradle-version: 8.7
 
       - name: Build with Gradle
         run: ./gradlew build --no-build-cache

.github/workflows/push-docker.yml

@@ -24,7 +24,7 @@ jobs:
 
       - uses: gradle/actions/setup-gradle@v3
         with:
-          gradle-version: 7.6
+          gradle-version: 8.7
 
       - name: Run Gradle Command
         run: ./gradlew clean build

.github/workflows/releaseArtifacts.yml

@@ -29,7 +29,7 @@ jobs:
 
       - uses: gradle/actions/setup-gradle@v3
         with:
-          gradle-version: 7.6
+          gradle-version: 8.7
 
       - name: Generate jar (With Security=${{ matrix.enable_security }})
         run: ./gradlew clean createExe

.github/workflows/test.yml

@@ -32,6 +32,15 @@ jobs:
           sudo curl -SL "https://github.com/docker/compose/releases/download/v2.26.1/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
           # sudo chmod +x /usr/local/bin/docker-compose
 
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.7"
+
+      - name: Pip requirements
+        run: |
+           pip install -r ./cucumber/requirements.txt
+              
       - name: Run Docker Compose Tests
         run: |
           chmod +x ./test.sh

.gitignore

@@ -124,4 +124,7 @@ watchedFolders/
 
 # Ignore Mac DS_Store files
 .DS_Store
-**/.DS_Store
+**/.DS_Store
+
+#cucumber
+/cucumber/reports/**

CONTRIBUTING.md

@@ -29,7 +29,7 @@ If you would like to add or modify a translation, please see [How to add new lan
 
 ## Docs
 
-Documentation for Stirling-PDF is handled in a seperate repository. Please see [Docs repository](https://github.com/Stirling-Tools/Stirling-Tools.github.io) or use "edit this page"-button at the bottom of each page at [https://stirlingtools.com/docs/](https://stirlingtools.com/docs/).
+Documentation for Stirling-PDF is handled in a separate repository. Please see [Docs repository](https://github.com/Stirling-Tools/Stirling-Tools.github.io) or use "edit this page"-button at the bottom of each page at [https://stirlingtools.com/docs/](https://stirlingtools.com/docs/).
 
 ## Fixing Bugs or Adding a New Feature
 

Dockerfile

@@ -1,44 +1,42 @@
 # Main stage
-FROM alpine:20240329
+FROM alpine:3.20.0
 
 # Copy necessary files
 COPY scripts /scripts
 COPY pipeline /pipeline
 COPY src/main/resources/static/fonts/*.ttf /usr/share/fonts/opentype/noto/
-COPY src/main/resources/static/fonts/*.otf /usr/share/fonts/opentype/noto/
+#COPY src/main/resources/static/fonts/*.otf /usr/share/fonts/opentype/noto/
 COPY build/libs/*.jar app.jar
 
 ARG VERSION_TAG
 
-
 # Set Environment Variables
 ENV DOCKER_ENABLE_SECURITY=false \
     VERSION_TAG=$VERSION_TAG \
     JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS -XX:MaxRAMPercentage=75" \
-	HOME=/home/stirlingpdfuser \
-	PUID=1000 \
+    HOME=/home/stirlingpdfuser \
+    PUID=1000 \
     PGID=1000 \
     UMASK=022
 
-
 # JDK for app
 RUN echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/main" | tee -a /etc/apk/repositories && \
     echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/community" | tee -a /etc/apk/repositories && \
     echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/testing" | tee -a /etc/apk/repositories && \
-    apk update && \
+    apk upgrade --no-cache -a && \
     apk add --no-cache \
         ca-certificates \
         tzdata \
         tini \
-        openssl \
-openssl-dev \
         bash \
         curl \
-        openjdk17-jre \
-        su-exec \
         shadow \
+        su-exec \
+        openssl \
+        openssl-dev \
+        openjdk21-jre \
 # Doc conversion
-        libreoffice@testing \
+        libreoffice \
 # pdftohtml
         poppler-utils \
 # OCR MY PDF (unpaper for descew and other advanced featues)
@@ -60,10 +58,9 @@ openssl-dev \
     addgroup -S stirlingpdfgroup && adduser -S stirlingpdfuser -G stirlingpdfgroup && \
     chown -R stirlingpdfuser:stirlingpdfgroup $HOME /scripts /usr/share/fonts/opentype/noto /configs /customFiles /pipeline && \
     chown stirlingpdfuser:stirlingpdfgroup /app.jar && \
-    tesseract --list-langs && \
-    rm -rf /var/cache/apk/*
+    tesseract --list-langs
 
-EXPOSE 8080
+EXPOSE 8080/tcp
 
 # Set user and run command
 ENTRYPOINT ["tini", "--", "/scripts/init.sh"]

Dockerfile-ultra-lite

@@ -1,5 +1,5 @@
 # use alpine
-FROM alpine:3.19.1
+FROM alpine:3.20.0
 
 ARG VERSION_TAG
 
@@ -8,7 +8,7 @@ ENV DOCKER_ENABLE_SECURITY=false \
     HOME=/home/stirlingpdfuser \
     VERSION_TAG=$VERSION_TAG \
     JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS -XX:MaxRAMPercentage=75" \
-	PUID=1000 \
+    PUID=1000 \
     PGID=1000 \
     UMASK=022
 
@@ -18,34 +18,32 @@ COPY scripts/init-without-ocr.sh /scripts/init-without-ocr.sh
 COPY pipeline /pipeline
 COPY build/libs/*.jar app.jar
 
-
 # Set up necessary directories and permissions
-
-RUN mkdir /configs /logs /customFiles && \
-    chmod +x /scripts/*.sh && \
+RUN echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/main" | tee -a /etc/apk/repositories && \
+    echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/community" | tee -a /etc/apk/repositories && \
+    echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/testing" | tee -a /etc/apk/repositories && \
+    apk upgrade --no-cache -a && \
     apk add --no-cache \
         ca-certificates \
         tzdata \
         tini \
         bash \
         curl \
-        su-exec \
         shadow \
-        openjdk17-jre && \
-    echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/main" | tee -a /etc/apk/repositories && \
-    echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/community" | tee -a /etc/apk/repositories && \
-    echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/testing" | tee -a /etc/apk/repositories && \
+        su-exec \
+        openjdk21-jre && \
     # User permissions
+    mkdir /configs /logs /customFiles && \
+    chmod +x /scripts/*.sh && \
     addgroup -S stirlingpdfgroup && adduser -S stirlingpdfuser -G stirlingpdfgroup && \
     chown -R stirlingpdfuser:stirlingpdfgroup $HOME /scripts  /configs /customFiles /pipeline && \
     chown stirlingpdfuser:stirlingpdfgroup /app.jar    
 
 # Set environment variables
 ENV ENDPOINTS_GROUPS_TO_REMOVE=CLI
 
-EXPOSE 8080
-
-ENTRYPOINT ["tini", "--", "/scripts/init-without-ocr.sh"]
+EXPOSE 8080/tcp
 
 # Run the application
+ENTRYPOINT ["tini", "--", "/scripts/init-without-ocr.sh"]
 CMD ["java", "-Dfile.encoding=UTF-8", "-jar", "/app.jar"]

LocalRunGuide.md

@@ -14,7 +14,7 @@ You could theoretically use a Distrobox/Toolbox, if your Distribution has old or
 
 Install the following software, if not already installed:
 
-- Java 17 or later
+- Java 17 or later (21 recommended)
 
 - Gradle 7.0 or later (included within repo so not needed on server)
 
@@ -42,17 +42,25 @@ For Debian-based systems, you can use the following command:
 
 ```bash
 sudo apt-get update
-sudo apt-get install -y git  automake  autoconf  libtool  libleptonica-dev  pkg-config zlib1g-dev make g++ openjdk-17-jdk python3 python3-pip
+sudo apt-get install -y git  automake  autoconf  libtool  libleptonica-dev  pkg-config zlib1g-dev make g++ openjdk-21-jdk python3 python3-pip
 ```
 
 For Fedora-based systems use this command:
 
 ```bash
-sudo dnf install -y git automake autoconf libtool leptonica-devel pkg-config zlib-devel make gcc-c++ java-17-openjdk python3 python3-pip
+sudo dnf install -y git automake autoconf libtool leptonica-devel pkg-config zlib-devel make gcc-c++ java-21-openjdk python3 python3-pip
+```
+
+For non-root users with Nix Package Manager, use the following command:
+```bash
+nix-channel --update
+nix-env -iA nixpkgs.jdk21 nixpkgs.git nixpkgs.python38 nixpkgs.gnumake nixpkgs.libgcc nixpkgs.automake nixpkgs.autoconf nixpkgs.libtool nixpkgs.pkg-config nixpkgs.zlib nixpkgs.leptonica
 ```
 
 ### Step 2: Clone and Build jbig2enc (Only required for certain OCR functionality)
 
+For Debian and Fedora, you can build it from source using the following commands:
+
 ```bash
 mkdir ~/.git
 cd ~/.git &&\
@@ -64,6 +72,11 @@ make &&\
 sudo make install
 ```
 
+For Nix, you will face `Leptonica not detected`. Bypass this by installing it directly using the following command:
+```bash
+nix-env -iA nixpkgs.jbig2enc
+```
+
 ### Step 3: Install Additional Software
 Next we need to install LibreOffice for conversions, ocrmypdf for OCR, and opencv for pattern recognition functionality.
 
@@ -105,6 +118,13 @@ sudo dnf install -y libreoffice-writer libreoffice-calc libreoffice-impress unpa
 pip3 install uno opencv-python-headless unoconv pngquant WeasyPrint
 ```
 
+For Nix:
+
+```bash
+nix-env -iA nixpkgs.unpaper nixpkgs.libreoffice nixpkgs.ocrmypdf nixpkgs.poppler_utils
+pip3 install uno opencv-python-headless unoconv pngquant WeasyPrint
+```
+
 ### Step 4: Clone and Build Stirling-PDF
 
 ```bash
@@ -115,33 +135,38 @@ chmod +x ./gradlew &&\
 ./gradlew build
 ```
 
-
 ### Step 5: Move jar to desired location
 
 After the build process, a `.jar` file will be generated in the `build/libs` directory.
 You can move this file to a desired location, for example, `/opt/Stirling-PDF/`.
 You must also move the Script folder within the Stirling-PDF repo that you have downloaded to this directory.
-This folder is required for the python scripts using OpenCV
+This folder is required for the python scripts using OpenCV.
 
 ```bash
 sudo mkdir /opt/Stirling-PDF &&\
 sudo mv ./build/libs/Stirling-PDF-*.jar /opt/Stirling-PDF/ &&\
 sudo mv scripts /opt/Stirling-PDF/ &&\
 echo "Scripts installed."
 ```
+
+For non-root users, you can just keep the jar in the main directory of Stirling-PDF using the following command:
+```bash
+mv ./build/libs/Stirling-PDF-*.jar ./Stirling-PDF-*.jar
+```
+
 ### Step 6: Other files
 #### OCR
 If you plan to use the OCR (Optical Character Recognition) functionality, you might need to install language packs for Tesseract if running non-english scanning.
 
 ##### Installing Language Packs
-Easiest is to use the langpacks provided by your repositories. Skip the other steps
+Easiest is to use the langpacks provided by your repositories. Skip the other steps.
 
 Manual:
 
 1. Download the desired language pack(s) by selecting the `.traineddata` file(s) for the language(s) you need.
 2. Place the `.traineddata` files in the Tesseract tessdata directory: `/usr/share/tessdata`
-3.
-Please view  [OCRmyPDF install guide](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for more info.
+3. Please view  [OCRmyPDF install guide](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for more info.
+
 **IMPORTANT:** DO NOT REMOVE EXISTING `eng.traineddata`, IT'S REQUIRED.
 
 Debian based systems, install languages with this command:
@@ -171,14 +196,38 @@ dnf search -C tesseract-langpack-
 rpm -qa | grep tesseract-langpack | sed 's/tesseract-langpack-//g'
 ```
 
+Nix:
+
+```bash
+nix-env -iA nixpkgs.tesseract
+```
+
+**Note:** Nix Package Manager pre-installs almost all the language packs when tesseract is installed.
+
 ### Step 7: Run Stirling-PDF
 
+Those who have pushed to the root directory, run the following commands:
+
 ```bash
 ./gradlew bootRun
 or
 java -jar /opt/Stirling-PDF/Stirling-PDF-*.jar
 ```
 
+Since libreoffice, soffice, and conversion tools have their dbus_tmp_dir set as `dbus_tmp_dir="/run/user/$(id -u)/libreoffice-dbus"`, you might get the following error when using their endpoints:
+```
+[Thread-7] INFO  s.s.SPDF.utils.ProcessExecutor - mkdir: cannot create directory ‘/run/user/1501’: Permission denied
+```
+To resolve this, before starting the Stirling-PDF, you have to set the environment variable to a directory you have write access to by using the following commands:
+
+```bash
+mkdir temp
+export DBUS_SESSION_BUS_ADDRESS="unix:path=./temp"
+./gradlew bootRun
+or
+java -jar ./Stirling-PDF-*.jar
+```
+
 ### Step 8: Adding a Desktop icon
 
 This will add a modified Appstarter to your Appmenu.
@@ -202,7 +251,19 @@ EOF
 
 Note: Currently the app will run in the background until manually closed.
 
-### Optional: Run Stirling-PDF as a service
+### Optional: Changing the host and port of the application:
+
+To override the default configuration, you can add the following to `/.git/Stirling-PDF/configs/custom_settings.yml` file:
+
+```bash
+server:
+  host: 0.0.0.0
+  port: 3000
+```
+
+**Note:** This file is created after the first application launch. To have it before that, you can create the directory and add the file yourself.
+
+### Optional: Run Stirling-PDF as a service (requires root).
 
 First create a .env file, where you can store environment variables:
 ```
@@ -239,6 +300,7 @@ WantedBy=multi-user.target
 ```
 
 Notify systemd that it has to rebuild its internal service database (you have to run this command every time you make a change in the service file):
+
 ```
 sudo systemctl daemon-reload
 ```