Refactor and add tesseract

tesseract/Dockerfile

@@ -0,0 +1,16 @@
+FROM ubuntu:18.04
+
+ENV LANG C.UTF-8  
+ENV LC_ALL C.UTF-8 
+
+RUN apt-get update && apt-get install -y software-properties-common && add-apt-repository -y ppa:alex-p/tesseract-ocr
+RUN apt-get update && apt-get install -y \
+    imagemagick \
+    tesseract-ocr \
+    tesseract-ocr-eng \
+    tesseract-ocr-nor
+
+COPY ocr.sh /bin/ocr.sh
+RUN chmod +x /bin/ocr.sh
+
+ENTRYPOINT ["tesseract"]

tesseract/ocr.sh

@@ -0,0 +1,5 @@
+#!/bin/sh
+
+convert -colorspace gray -fill white -resize 5000x -sharpen 0x1 $1 /tmp/image.jpg
+tesseract -l nor /tmp/image.jpg /tmp/out
+cat /tmp/out*