print (WIP), fake scan (WIP) and text conversion for ultra-lite

Dockerfile

@@ -25,15 +25,17 @@ ENV DOCKER_ENABLE_SECURITY=false \
 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 add --no-cache \
         ca-certificates \
         tzdata \
         tini \
+        openssl \
+openssl-dev \
         bash \
         curl \
         openjdk17-jre \
         su-exec \
-        font-noto-cjk \
         shadow \
 # Doc conversion
         libreoffice@testing \
@@ -58,7 +60,8 @@ RUN echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/main" | tee -a /et
     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
+    tesseract --list-langs && \
+    rm -rf /var/cache/apk/*
 
 EXPOSE 8080
 

README.md

@@ -121,6 +121,7 @@ docker run -d \
   -v /location/of/logs:/logs \
   -e DOCKER_ENABLE_SECURITY=false \
   -e INSTALL_BOOK_AND_ADVANCED_HTML_OPS=false \
+  -e LANGS=en_GB \
   --name stirling-pdf \
   frooodle/s-pdf:latest
 
@@ -147,6 +148,7 @@ services:
     environment:
       - DOCKER_ENABLE_SECURITY=false
       - INSTALL_BOOK_AND_ADVANCED_HTML_OPS=false
+      - LANGS=en_GB
 ```
 
 Note: Podman is CLI-compatible with Docker, so simply replace "docker" with "podman".
@@ -252,13 +254,13 @@ metrics:
 - ``SYSTEM_CONNECTIONTIMEOUTMINUTES`` to set custom connection timeout values
 - ``DOCKER_ENABLE_SECURITY`` to tell docker to download security jar (required as true for auth login)
 - ``INSTALL_BOOK_AND_ADVANCED_HTML_OPS`` to download calibre onto stirling-pdf enabling pdf to/from book and advanced html conversion
+- ``LANGS`` to define custom font libraries to install for use for document conversions
 
 ## API
 
 For those wanting to use Stirling-PDFs backend API to link with their own custom scripting to edit PDFs you can view all existing API documentation
 [here](https://app.swaggerhub.com/apis-docs/Stirling-Tools/Stirling-PDF/) or navigate to /swagger-ui/index.html of your stirling-pdf instance for your versions documentation (Or by following the API button in your settings of Stirling-PDF)
 
-
 ## Login authentication
 
 ![stirling-login](images/login-light.png)

build.gradle

@@ -12,7 +12,7 @@ plugins {
 import com.github.jk1.license.render.*
 
 group = 'stirling.software'
-version = '0.22.8'
+version = '0.23.0'
 sourceCompatibility = '17'
 
 repositories {

exampleYmlFiles/docker-compose-latest.yml

@@ -21,6 +21,8 @@ services:
     environment:
       DOCKER_ENABLE_SECURITY: "false"
       SECURITY_ENABLELOGIN: "false"
+      LANGS: "en_GB,en_US,ar_AR,de_DE,fr_FR,es_ES,zh_CN,zh_TW,ca_CA,it_IT,sv_SE,pl_PL,ro_RO,ko_KR,pt_BR,ru_RU,el_GR,hi_IN,hu_HU,tr_TR,id_ID"
+      INSTALL_BOOK_AND_ADVANCED_HTML_OPS: "true"
       SYSTEM_DEFAULTLOCALE: en-US
       UI_APPNAME: Stirling-PDF
       UI_HOMEDESCRIPTION: Demo site for Stirling-PDF Latest

scripts/init-without-ocr.sh

@@ -1,26 +1,31 @@
-#!/bin/sh
+#!/bin/bash
 
 # Update the user and group IDs as per environment variables
 if [ ! -z "$PUID" ] && [ "$PUID" != "$(id -u stirlingpdfuser)" ]; then
     usermod -o -u "$PUID" stirlingpdfuser || true
 fi
 
+
 if [ ! -z "$PGID" ] && [ "$PGID" != "$(getent group stirlingpdfgroup | cut -d: -f3)" ]; then
     groupmod -o -g "$PGID" stirlingpdfgroup || true
 fi
 umask "$UMASK" || true
 
-
 if [[ "$INSTALL_BOOK_AND_ADVANCED_HTML_OPS" == "true" ]]; then
   apk add --no-cache calibre@testing
 fi
 
 /scripts/download-security-jar.sh
 
+if [[ -n "$LANGS" ]]; then
+	/scripts/installFonts.sh $LANGS
+fi
+
 echo "Setting permissions and ownership for necessary directories..."
-if chown -R stirlingpdfuser:stirlingpdfgroup $HOME /logs /scripts /usr/share/fonts/opentype/noto /usr/share/tessdata /configs /customFiles /pipeline /app.jar; then
-	chmod -R 755 /logs /scripts /usr/share/fonts/opentype/noto /usr/share/tessdata /configs /customFiles /pipeline /app.jar || true
-	# If chown succeeds, execute the command as stirlingpdfuser
+# Attempt to change ownership of directories and files
+if chown -R stirlingpdfuser:stirlingpdfgroup $HOME /logs /scripts /usr/share/fonts/opentype/noto /configs /customFiles /pipeline /app.jar; then
+	chmod -R 755 /logs /scripts /usr/share/fonts/opentype/noto /configs /customFiles /pipeline /app.jar || true
+    # If chown succeeds, execute the command as stirlingpdfuser
     exec su-exec stirlingpdfuser "$@"
 else
     # If chown fails, execute the command without changing the user context

scripts/init.sh

@@ -13,18 +13,6 @@ if [ -d /usr/share/tesseract-ocr/5/tessdata ]; then
         cp -r /usr/share/tesseract-ocr/5/tessdata/* /usr/share/tessdata || true;
 fi
 
-# Update the user and group IDs as per environment variables
-if [ ! -z "$PUID" ] && [ "$PUID" != "$(id -u stirlingpdfuser)" ]; then
-    usermod -o -u "$PUID" stirlingpdfuser || true
-fi
-
-
-if [ ! -z "$PGID" ] && [ "$PGID" != "$(getent group stirlingpdfgroup | cut -d: -f3)" ]; then
-    groupmod -o -g "$PGID" stirlingpdfgroup || true
-fi
-umask "$UMASK" || true
-
-
 # Check if TESSERACT_LANGS environment variable is set and is not empty
 if [[ -n "$TESSERACT_LANGS" ]]; then
   # Convert comma-separated values to a space-separated list
@@ -40,20 +28,4 @@ if [[ -n "$TESSERACT_LANGS" ]]; then
   done
 fi
 
-if [[ "$INSTALL_BOOK_AND_ADVANCED_HTML_OPS" == "true" ]]; then
-  apk add --no-cache calibre@testing
-fi
-
-/scripts/download-security-jar.sh
-
-echo "Setting permissions and ownership for necessary directories..."
-# Attempt to change ownership of directories and files
-if chown -R stirlingpdfuser:stirlingpdfgroup $HOME /logs /scripts /usr/share/fonts/opentype/noto /usr/share/tessdata /configs /customFiles /pipeline /app.jar; then
-	chmod -R 755 /logs /scripts /usr/share/fonts/opentype/noto /usr/share/tessdata /configs /customFiles /pipeline /app.jar || true
-    # If chown succeeds, execute the command as stirlingpdfuser
-    exec su-exec stirlingpdfuser "$@"
-else
-    # If chown fails, execute the command without changing the user context
-    echo "[WARN] Chown failed, running as host user"
-    exec "$@"
-fi
+/scripts/init-without-ocr.sh "$@"

scripts/installFonts.sh

@@ -0,0 +1,67 @@
+#!/bin/bash
+
+LANGS=$1
+
+# Function to install a font package
+install_font() {
+    echo "Installing font package: $1"
+    if ! apk add "$1" --no-cache; then
+        echo "Failed to install $1"
+    fi
+}
+
+# Install common fonts used across many languages
+#common_fonts=(
+#    font-terminus
+#    font-dejavu
+#    font-noto
+#    font-noto-cjk
+#    font-awesome
+#    font-noto-extra
+#)
+#
+#for font in "${common_fonts[@]}"; do
+#    install_font $font
+#done
+
+# Map languages to specific font packages
+declare -A language_fonts=(
+    ["ar_AR"]="font-noto-arabic"
+    ["zh_CN"]="font-isas-misc"
+    ["zh_TW"]="font-isas-misc"
+    ["ja_JP"]="font-noto font-noto-thai font-noto-tibetan font-ipa font-sony-misc font-jis-misc"
+    ["ru_RU"]="font-vollkorn font-misc-cyrillic font-mutt-misc font-screen-cyrillic font-winitzki-cyrillic font-cronyx-cyrillic"
+    ["sr_LATN_RS"]="font-vollkorn font-misc-cyrillic font-mutt-misc font-screen-cyrillic font-winitzki-cyrillic font-cronyx-cyrillic"
+    ["uk_UA"]="font-vollkorn font-misc-cyrillic font-mutt-misc font-screen-cyrillic font-winitzki-cyrillic font-cronyx-cyrillic"
+    ["ko_KR"]="font-noto font-noto-thai font-noto-tibetan"
+    ["el_GR"]="font-noto"
+    ["hi_IN"]="font-noto-devanagari"
+    ["bg_BG"]="font-vollkorn font-misc-cyrillic"
+    ["GENERAL"]="font-terminus font-dejavu font-noto font-noto-cjk font-awesome font-noto-extra"
+)
+
+# Install fonts for other languages which generally do not need special packages beyond 'font-noto'
+other_langs=("en_GB" "en_US" "de_DE" "fr_FR" "es_ES" "ca_CA" "it_IT" "pt_BR" "nl_NL" "sv_SE" "pl_PL" "ro_RO" "hu_HU" "tr_TR" "id_ID" "eu_ES")
+if [[ $LANGS == "ALL" ]]; then
+    # Install all fonts from the language_fonts map
+    for fonts in "${language_fonts[@]}"; do
+        for font in $fonts; do
+            install_font $font
+        done
+    done
+else
+    # Split comma-separated languages and install necessary fonts
+    IFS=',' read -ra LANG_CODES <<< "$LANGS"
+    for code in "${LANG_CODES[@]}"; do
+        if [[ " ${other_langs[@]} " =~ " ${code} " ]]; then
+            install_font font-noto
+        else
+            fonts_to_install=${language_fonts[$code]}
+            if [ ! -z "$fonts_to_install" ]; then
+                for font in $fonts_to_install; do
+                    install_font $font
+                done
+            fi
+        fi
+    done
+fi

src/main/java/stirling/software/SPDF/SPdfApplication.java

@@ -62,6 +62,7 @@ public void init() {
     }
 
     public static void main(String[] args) throws IOException, InterruptedException {
+
         SpringApplication app = new SpringApplication(SPdfApplication.class);
         app.addInitializers(new ConfigInitializer());
         if (Files.exists(Paths.get("configs/settings.yml"))) {

src/main/java/stirling/software/SPDF/config/EndpointConfiguration.java

@@ -146,14 +146,14 @@ public void init() {
         addEndpointToGroup("CLI", "xlsx-to-pdf");
         addEndpointToGroup("CLI", "pdf-to-word");
         addEndpointToGroup("CLI", "pdf-to-presentation");
-        addEndpointToGroup("CLI", "pdf-to-text");
         addEndpointToGroup("CLI", "pdf-to-html");
         addEndpointToGroup("CLI", "pdf-to-xml");
         addEndpointToGroup("CLI", "ocr-pdf");
         addEndpointToGroup("CLI", "html-to-pdf");
         addEndpointToGroup("CLI", "url-to-pdf");
         addEndpointToGroup("CLI", "book-to-pdf");
         addEndpointToGroup("CLI", "pdf-to-book");
+        addEndpointToGroup("CLI", "pdf-to-rtf");
 
         // Calibre
         addEndpointToGroup("Calibre", "book-to-pdf");
@@ -175,7 +175,7 @@ public void init() {
         addEndpointToGroup("LibreOffice", "xlsx-to-pdf");
         addEndpointToGroup("LibreOffice", "pdf-to-word");
         addEndpointToGroup("LibreOffice", "pdf-to-presentation");
-        addEndpointToGroup("LibreOffice", "pdf-to-text");
+        addEndpointToGroup("LibreOffice", "pdf-to-rtf");
         addEndpointToGroup("LibreOffice", "pdf-to-html");
         addEndpointToGroup("LibreOffice", "pdf-to-xml");
 
@@ -218,6 +218,7 @@ public void init() {
         addEndpointToGroup("Java", "overlay-pdf");
         addEndpointToGroup("Java", "split-pdf-by-sections");
         addEndpointToGroup("Java", REMOVE_BLANKS);
+        addEndpointToGroup("Java", "pdf-to-text");
 
         // Javascript
         addEndpointToGroup("Javascript", "pdf-organizer");

src/main/java/stirling/software/SPDF/controller/api/converters/ConvertPDFToPDFA.java

@@ -31,7 +31,8 @@ public class ConvertPDFToPDFA {
             summary = "Convert a PDF to a PDF/A",
             description =
                     "This endpoint converts a PDF file to a PDF/A file. PDF/A is a format designed for long-term archiving of digital documents. Input:PDF Output:PDF Type:SISO")
-    public ResponseEntity<byte[]> pdfToPdfA(@ModelAttribute PdfToPdfARequest request) throws Exception {
+    public ResponseEntity<byte[]> pdfToPdfA(@ModelAttribute PdfToPdfARequest request)
+            throws Exception {
         MultipartFile inputFile = request.getFileInput();
         String outputFormat = request.getOutputFormat();