From 3f366339ad1628855458f000748265039242b054 Mon Sep 17 00:00:00 2001
From: "Gerber, Mike" <mike.gerber@sbb.spk-berlin.de>
Date: Mon, 24 Jun 2019 16:36:19 +0200
Subject: [PATCH] Add container setup

---
 Dockerfile       | 25 +++++++++++++++++++++++++
 build            |  2 ++
 requirements.txt |  4 ++++
 run              |  2 ++
 4 files changed, 33 insertions(+)
 create mode 100644 Dockerfile
 create mode 100755 build
 create mode 100644 requirements.txt
 create mode 100755 run

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..2843a21
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,25 @@
+FROM ubuntu:18.04
+
+ENV LC_ALL=C.UTF-8 LANG=C.UTF-8
+
+RUN apt-get update && \
+    apt-get install -y \
+      git \
+      libleptonica-dev \
+      libtesseract-dev \
+      libxml2-utils \
+      python3-pip \
+      tesseract-ocr-all \
+      xmlstarlet \
+    && \
+    apt-get clean
+
+COPY requirements.txt /tmp
+RUN pip3 install --no-cache-dir -r /tmp/requirements.txt
+
+COPY my_ocrd_workflow /usr/bin
+COPY xsd              /usr/bin/xsd
+
+
+WORKDIR /data
+CMD ["/usr/bin/my_ocrd_workflow"]
diff --git a/build b/build
new file mode 100755
index 0000000..2297810
--- /dev/null
+++ b/build
@@ -0,0 +1,2 @@
+#!/bin/sh
+podman build -t my_ocrd_workflow .
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..d0bd925
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,4 @@
+git+https://github.com/seuretm/ocrd_typegroups_classifier.git
+ocrd_kraken
+tesserocr == 2.3.1  # 2.4.0 fails with Ubuntu 18.04's tesseract
+ocrd_tesserocr
diff --git a/run b/run
new file mode 100755
index 0000000..996578b
--- /dev/null
+++ b/run
@@ -0,0 +1,2 @@
+#!/bin/sh
+podman run -it --mount type=bind,src="$(pwd)",target=/data --privileged=true my_ocrd_workflow