From aa6cfb6c30bb47be1aa29aa99ce131717b420154 Mon Sep 17 00:00:00 2001
From: Narate Ketram <rate@tel.co.th>
Date: Tue, 23 Oct 2018 22:53:41 +0700
Subject: [PATCH 1/2] Add docker support

---
 .dockerignore       |  1 +
 Dockerfile          | 11 +++++++++++
 README.md           | 19 +++++++++++++++++++
 docker-compose.yaml |  6 ++++++
 requirements.txt    |  1 -
 5 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100644 .dockerignore
 create mode 100644 Dockerfile
 create mode 100644 docker-compose.yaml

diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..8fa5b33
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1 @@
+env
\ No newline at end of file
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..334789f
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,11 @@
+FROM python
+LABEL maintainer="Narate Ketram <koonnarate@gmail.com>"
+WORKDIR /app
+RUN apt-get update && \
+    apt-get install -y tesseract-ocr libtesseract-dev
+ADD requirements.txt .
+RUN pip install -r requirements.txt
+
+ADD . .
+EXPOSE 5000
+CMD ["python", "main.py"]
diff --git a/README.md b/README.md
index ebf51b7..4bed5d4 100644
--- a/README.md
+++ b/README.md
@@ -14,5 +14,24 @@ Run the respective python scripts for respective use-cases.
 * Pillow (For Image Processing)
 * [ImageMagick](https://legacy.imagemagick.org/script/binary-releases.php#windows)
 * wand(Python binding for ImageMagick)
+
+## Run in Docker
+
+First build docker image
+```
+docker build -t ocr .
+```
+
+Run Docker container
+```
+docker run -it --rm -p 5000:5000 ocr
+```
+
+Or run using docker-compose
+
+```
+docker-compose up
+```
+
 ***
 **[Tesseract](https://github.com/tesseract-ocr/tesseract)** was originally written in C++ and uses an LSTM Network behind the scenes, for more reading and installation guide, you can check out this very helpful [blog post](https://appliedmachinelearning.blog/2018/06/30/performing-ocr-by-running-parallel-instances-of-tesseract-4-0-python/). This will explain you the essential stuff. I have also extended this for PDFs to make it more useful for real-world use-case.
diff --git a/docker-compose.yaml b/docker-compose.yaml
new file mode 100644
index 0000000..9e46718
--- /dev/null
+++ b/docker-compose.yaml
@@ -0,0 +1,6 @@
+version: '3.7'
+services: 
+  ocr:
+    build: .
+    ports: 
+      - 5000:5000
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
index 8e15f17..daac1ba 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,7 +4,6 @@ ItsDangerous==1.0.0
 Jinja2==2.10
 MarkupSafe==1.0
 Pillow==5.3.0
-pkg-resources==0.0.0
 pytesseract==0.2.5
 Wand==0.4.4
 Werkzeug==0.14.1

From cd35ccd7ef2833e4b3ed4a56cd9f7001531f5f3e Mon Sep 17 00:00:00 2001
From: Narate Ketram <rate@tel.co.th>
Date: Tue, 23 Oct 2018 23:42:25 +0700
Subject: [PATCH 2/2] Fixed ValueError: 'jpeg' is unsupported format

---
 Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index 334789f..4a4ceb3 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -2,7 +2,7 @@ FROM python
 LABEL maintainer="Narate Ketram <koonnarate@gmail.com>"
 WORKDIR /app
 RUN apt-get update && \
-    apt-get install -y tesseract-ocr libtesseract-dev
+    apt-get install -y tesseract-ocr libtesseract-dev imagemagick ghostscript
 ADD requirements.txt .
 RUN pip install -r requirements.txt