print (WIP), fake scan (WIP) and text conversion for ultra-lite (#1098)

* Changes!

* lang

* fake scan init, print init and pdf to text for exe

* Hardening suggestions for Stirling-PDF / changes (#1099)

* Switch order of literals to prevent NullPointerException

* Introduced protections against predictable RNG abuse

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>

* Update README.md

* install custom fonts

* Formats etc

* version bump

* disable WIP work

* remove chinese font

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
Co-authored-by: systo <systo@host.docker.internal>

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