Merge pull request #331 from ifad/feature/tesseract-5

Update to Tesseract 5

Gemfile.lock

@@ -5,7 +5,7 @@ GEM
     byebug (11.1.3)
     concurrent-ruby (1.3.4)
     connection_pool (2.4.1)
-    csv (3.3.0)
+    csv (3.3.2)
     daemons (1.4.1)
     date (3.4.1)
     diff-lcs (1.5.1)
@@ -29,7 +29,7 @@ GEM
       csv
     json (2.7.6)
     kgio (2.11.4)
-    logger (1.6.2)
+    logger (1.6.4)
     mail (2.8.1)
       mini_mime (>= 0.1.1)
       net-imap
@@ -62,7 +62,7 @@ GEM
     rack-protection (3.2.0)
       base64 (>= 0.1.0)
       rack (~> 2.2, >= 2.2.4)
-    rack-test (2.1.0)
+    rack-test (2.2.0)
       rack (>= 1.3)
     raindrops (0.20.1)
     rake (13.2.1)
@@ -113,9 +113,9 @@ GEM
       eventmachine (~> 1.0, >= 1.0.4)
       rack (>= 1, < 3)
     thor (1.3.2)
-    tilt (2.4.0)
+    tilt (2.5.0)
     timecop (0.9.10)
-    timeout (0.4.2)
+    timeout (0.4.3)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
     unf (0.2.0)

docker/colore/Dockerfile

@@ -4,16 +4,23 @@ RUN apt-get update && apt-get -yq install --no-install-suggests --no-install-rec
   build-essential \
   imagemagick \
   libmagic-dev \
-  tesseract-ocr \
-  tesseract-ocr-ara \
-  tesseract-ocr-fra \
-  tesseract-ocr-spa \
   wkhtmltopdf
 
 # Needed to get the latest libreoffice
 # Ref: https://wiki.debian.org/LibreOffice#Using_Debian_backports
-RUN echo 'deb http://deb.debian.org/debian bullseye-backports main contrib non-free' >> /etc/apt/sources.list
-RUN apt-get update && apt-get -yq -t bullseye-backports install libreoffice
+RUN echo 'deb https://deb.debian.org/debian bullseye-backports main contrib non-free' >> /etc/apt/sources.list
+
+# Needed for Tesseract 5
+# Ref: https://notesalexp.org/tesseract-ocr/html/
+RUN echo 'deb https://notesalexp.org/tesseract-ocr5/bullseye bullseye main' >> /etc/apt/sources.list
+RUN wget -qO /etc/apt/trusted.gpg.d/alexp_key.asc https://notesalexp.org/debian/alexp_key.asc
+
+RUN apt-get update && apt-get -yq -t bullseye-backports install \
+  libreoffice \
+  tesseract-ocr \
+  tesseract-ocr-ara \
+  tesseract-ocr-fra \
+  tesseract-ocr-spa
 
 ARG TIKA_VERSION=3.0.0