From 0e80410ea10db5ef5a4e34b7097e566ca4454ae4 Mon Sep 17 00:00:00 2001
From: Alan Casagrande <alancasagrande@gmail.com>
Date: Mon, 18 Feb 2019 11:32:06 -0300
Subject: [PATCH] docker image with ocr enabled

---
 docd/debian_ocr.sh         | 23 +++++++++++++++++++++++
 docd/debian_ocr/Dockerfile | 27 +++++++++++++++++++++++++++
 2 files changed, 50 insertions(+)
 create mode 100755 docd/debian_ocr.sh
 create mode 100644 docd/debian_ocr/Dockerfile

diff --git a/docd/debian_ocr.sh b/docd/debian_ocr.sh
new file mode 100755
index 0000000..9ca8d1d
--- /dev/null
+++ b/docd/debian_ocr.sh
@@ -0,0 +1,23 @@
+#!/usr/bin/env sh
+
+# Debian alternative build with OCR enabled.
+
+# Build context must be the GOPATH where docconv and gosseract are contained. 
+
+# Build runs on the Docker image, which is more reliable when working from other 
+# OS than Linux.
+
+export NAME=docd
+export VERSION=debian
+export DOCKERFILE=$GOPATH/src/code.sajari.com/docconv/docd/debian_ocr/Dockerfile
+
+echo "Building ${NAME} for ${VERSION} with OCR enabled..."
+
+echo "GOPATH: ${GOPATH}"
+
+echo "Dockerfile: ${DOCKERFILE}"
+
+docker build \
+    -t $NAME:ocr \
+    -f $DOCKERFILE \
+    $GOPATH
diff --git a/docd/debian_ocr/Dockerfile b/docd/debian_ocr/Dockerfile
new file mode 100644
index 0000000..c177c53
--- /dev/null
+++ b/docd/debian_ocr/Dockerfile
@@ -0,0 +1,27 @@
+FROM debian
+
+RUN apt-get update 
+RUN apt-get install -y zip
+RUN apt-get install -y poppler-utils
+RUN apt-get install -y wv
+RUN apt-get install -y unrtf
+RUN apt-get install -y tidy
+RUN apt-get install -y lynx
+RUN apt-get install -y libtesseract-dev
+RUN apt-get install -y libleptonica-dev
+RUN apt-get install -y tesseract-ocr-eng
+RUN apt-get install -y git
+RUN apt-get install -y golang
+
+# Build context must be the host GOPATH
+COPY . /goworkspace
+
+WORKDIR /goworkspace/src/code.sajari.com/docconv/docd
+
+ENV GOPATH=/goworkspace
+
+RUN GOOS=linux GOARCH=amd64 go build -tags ocr -o /docd
+
+EXPOSE 8888
+
+CMD ["/docd"]