feat: added dockerfiles

.dockerignore

@@ -0,0 +1,56 @@
+.metadata
+bin/
+tmp/
+*.tmp
+*.bak
+*.swp
+*~.nib
+local.properties
+.settings/
+.loadpath
+.recommenders
+
+# Eclipse Core
+.project
+
+# External tool builders
+.externalToolBuilders/
+
+# Locally stored "Eclipse launch configurations"
+*.launch
+
+# PyDev specific (Python IDE for Eclipse)
+*.pydevproject
+
+# CDT-specific (C/C++ Development Tooling)
+.cproject
+
+# JDT-specific (Eclipse Java Development Tools)
+.classpath
+
+# Java annotation processor (APT)
+.factorypath
+
+# PDT-specific (PHP Development Tools)
+.buildpath
+
+# sbteclipse plugin
+.target
+
+# Tern plugin
+.tern-project
+
+# TeXlipse plugin
+.texlipse
+
+# STS (Spring Tool Suite)
+.springBeans
+
+# Code Recommenders
+.recommenders/
+
+# Maven
+target/
+
+# Baleen specific
+testing.log

BUILD.md

@@ -10,4 +10,11 @@
 2. Run `mvn package` from the Baleen project directory
 3. Optionally run `mvn javadoc:aggregate-jar` to build Javadoc
 4. The Baleen JAR will be built and saved in the target directory under the top level project directory
-5. Run Baleen by running `java -jar baleen-2.4.0.jar` and then navigating to <http://localhost:6413>
+5. Run Baleen by running `java -jar baleen-2.4.1.jar` and then navigating to <http://localhost:6413>
+
+## Docker Instructions
+
+1. Download the Baleen source from GitHub
+2. Run `docker build -t baleen:2.4.1-SNAPSHOT .` from the root of the project
+5. Run Baleen by running `docker run --name baleen -p 6413:6413 baleen:2.4.1-SNAPSHOT` and then navigating to <http://localhost:6413>
+

Dockerfile

@@ -0,0 +1,31 @@
+
+###############################################################################
+# BUILD
+###############################################################################
+FROM maven:3.5-jdk-8 AS build
+
+# we need to create a new user as some of the
+# tests rely on files being readonly and fail
+# when run as root
+RUN useradd -ms /bin/bash baleen
+WORKDIR /home/baleen
+
+COPY . .
+
+RUN chown -R baleen *
+USER baleen
+
+RUN mvn package
+
+###############################################################################
+# RELEASE
+###############################################################################
+FROM java:8-jdk-alpine AS release
+
+ARG baleen_version=2.4.1-SNAPSHOT
+
+COPY --from=build /home/baleen/target/baleen-${baleen_version}.jar ./baleen.jar
+
+EXPOSE 6413
+
+ENTRYPOINT [ "java", "-jar", "baleen.jar" ]

README.md

@@ -16,9 +16,11 @@ Baleen 2.4 contains a number of changes that may make it incompatible with older
 
 Baleen includes an in-built server, which hosts full documentation and guides on how to use Baleen.
 To get started, you will need to launch this server and read this documentation.
-To launch the server, run the following command.
+To launch the server, run one of the following commands.
 
-> java -jar baleen-2.4.0.jar
+> `java -jar baleen-2.4.0.jar`
+
+> `docker-compose -f example/docker-compose.yml up`
 
 Once running, the server can be accessed at [http://localhost:6413](http://localhost:6413).
 
@@ -28,10 +30,15 @@ If you require the Javadoc to be available through the in-built server, then you
 
 ## Running
 
-To run Baleen, you will need:
+To run Baleen, you will need either;
 
 * A sensible amount of RAM. Start with 4GB and alter according to the number of annotators being employed. 
 * Java 8
+
+or
+
+* [Docker](https://www.docker.com/) v17+
+* [Docker Compose](https://docs.docker.com/compose/) v1.17+
 
 ## Developing
 

example/config/example_config.yml

@@ -0,0 +1,9 @@
+---
+logging:
+  loggers:
+    - name: console
+      minLevel: INFO
+
+pipelines:
+  - name: Example Pipeline
+    file: /config/example_pipeline.yml

example/config/example_pipeline.yml

@@ -0,0 +1,17 @@
+---
+mongo:
+  db: baleen
+  host: mongo
+
+collectionreader:
+  class: FolderReader
+  folders:
+   - /data
+
+annotators:
+  - regex.Url
+  - language.OpenNLP
+  - gazetteer.Country
+
+consumers:
+  - Mongo

example/data/example_doc.txt

@@ -0,0 +1,13 @@
+Syria has accused Israel of bombarding an area west of Damascus, with reports of a military airport being hit.
+State television quoted the army as saying several rockets landed in the airport compound in Mezzeh, Reuters news agency reports.
+It remains unclear if the alleged bombardment, which caused fires, has caused any casualties.
+The Israeli government has previously neither confirmed nor denied that it carries out strikes in Syria.
+It is thought to have bombed weapons shipments intended for Lebanon's Hezbollah movement several times since Syria's civil war began in 2011.
+Hezbollah, which fought a month-long war with Israel in 2006, has sent thousands of fighters to Syria to support President Bashar al-Assad's forces.
+State-run Syrian news agency Sana reported explosions at the Mezzeh military airport and said ambulances were rushing to the scene.
+"The army was quoted as warning Israel ""of the repercussions of the flagrant attack"", according to Reuters."
+In December, Syrian state media said an Israeli missile strike had targeted the airport in Mezzeh, causing fires but no casualties.
+Days earlier, on 30 November, Israeli jets were reported to have fired missiles from Lebanese airspace into Syria, striking Sabboura, an area outside Damascus.
+The target was unclear but the highway from Lebanon to Damascus runs through the town.
+
+source: https://github.com/dstl/re3d

example/docker-compose.yml

@@ -0,0 +1,21 @@
+---
+version: '3'
+services:
+  baleen:
+    image: baleen:2.4.1-SNAPSHOT
+    build:
+      context: ../
+      args:
+        baleen_version: 2.4.1-SNAPSHOT
+    ports:
+      - 6413:6413
+    command: /config/example_config.yml
+    volumes:
+      - ./config/:/config
+      - ./data/:/data
+    depends_on:
+      - mongo
+  mongo:
+    image: mongo:3.0
+    ports:
+      - 27017:27017