Google openrefine role.

google-openrefine/defaults/main.yml

@@ -0,0 +1,17 @@
+---
+openrefine_enabled: True
+openrefine_major_version: 3
+openrefine_minor_version: 0
+openrefine_file_extension: 'tar.gz'
+openrefine_distribution_prefix: 'openrefine'
+openrefine_dist_file: '{{ openrefine_distribution_prefix }}-linux-{{ openrefine_version }}.{{ openrefine_file_extension }}'
+openrefine_version: '{{ openrefine_major_version }}.{{ openrefine_minor_version }}'
+openrefine_download_url: 'https://github.com/OpenRefine/OpenRefine/releases/download/{{ openrefine_version }}/{{ openrefine_dist_file }}'
+openrefine_user: openrefine
+openrefine_user_home: /srv/google-openrefine
+openrefine_data_dir: '{{ openrefine_user_home }}/data'
+openrefine_log_dir: '{{ openrefine_user_home }}/logs'
+openrefine_base_dir: '{{ openrefine_user_home }}/{{ openrefine_distribution_prefix }}-{{ openrefine_version }}'
+openrefine_http_port: 3333
+openrefine_java_heap: 2048m
+

google-openrefine/handlers/main.yml

@@ -0,0 +1,4 @@
+---
+- name: Restart openrefine
+  service: name=openrefine state=restarted
+

google-openrefine/tasks/main.yml

@@ -0,0 +1,40 @@
+---
+- block:
+  - name: Create the openrefine user
+    user: name={{ openrefine_user }} home={{ openrefine_user_home }} createhome=no shell=/usr/sbin/nologin system=yes
+
+  - name: Create the openrefine home, if it does not already exist.
+    file: dest={{ openrefine_user_home }} owner=root group=root state=directory recurse=yes
+
+  - name: Create the openrefine data and logs directories
+    file: dest={{ item }} owner={{ openrefine_user }} group={{ openrefine_user }} state=directory recurse=yes
+    with_items:
+      - '{{ openrefine_data_dir }}'
+      - '{{ openrefine_log_dir }}'
+
+  - name: Download openrefine
+    unarchive: remote_src=yes src={{ openrefine_download_url }} dest={{ openrefine_user_home }}
+    args:
+      creates: '{{ openrefine_user_home }}/{{ openrefine_distribution_prefix }}-{{ openrefine_version }}'
+
+  - name: Install the openrefine configuration
+    template: src=refine.ini dest={{ openrefine_user_home }}/{{ openrefine_distribution_prefix }}-{{ openrefine_version }}/refine.ini owner=root group=root mode=0644
+    notify: Restart openrefine
+
+  - name: Install the openrefine upstart init script
+    template: src=openrefine.conf.j2 dest=/etc/init/openrefine.conf owner=root group=root mode=0644
+    when: ansible_service_mgr != 'systemd'
+
+  - name: Ensure that the service is running and enabled
+    service: name=openrefine state=started enabled=yes
+
+  when: openrefine_enabled
+  tags: [ 'openrefine', 'google_openrefine' ]
+
+- block:
+
+  - name: Ensure that the service is running and enabled
+    service: name=openrefine state=stopped enabled=no
+
+  when: not openrefine_enabled
+  tags: [ 'openrefine', 'google_openrefine' ]

google-openrefine/templates/openrefine.conf.j2

@@ -0,0 +1,13 @@
+description "Google OpenRefine server"
+start on (local-filesystems and net-device-up IFACE!=lo)
+stop on runlevel [016]
+
+respawn
+respawn limit 10 5
+setuid {{ openrefine_user }}
+setgid {{ openrefine_user }}
+
+script
+  chdir {{ openrefine_base_dir }}
+  exec ./refine > {{ openrefine_log_dir }}/openrefine.log 2>&1
+end script

google-openrefine/templates/refine.ini

@@ -0,0 +1,25 @@
+# NOTE: This file is not read if you run the Refine executable directly
+# It is only read of you use the refine shell script or refine.bat
+
+no_proxy="localhost,127.0.0.1"
+REFINE_PORT={{ openrefine_http_port }}
+#REFINE_HOST=127.0.0.1
+#REFINE_WEBAPP=main\webapp
+
+# Memory and max form size allocations
+#REFINE_MAX_FORM_CONTENT_SIZE=1048576
+REFINE_MEMORY=1400M
+
+# Set initial java heap space (default: 256M) for better performance with large datasets
+REFINE_MIN_MEMORY=1400M
+
+# Some sample configurations. These have no defaults.
+#ANT_HOME=C:\grefine\tools\apache-ant-1.8.1
+#JAVA_HOME=C:\Program Files\Java\jdk1.8.0_151
+#JAVA_OPTIONS=-XX:+UseParallelGC -verbose:gc -Drefine.headless=true
+#JAVA_OPTIONS=-Drefine.data_dir=C:\Users\user\AppData\Roaming\OpenRefine
+JAVA_HOME={{ jdk_java_home }}
+JAVA_OPTIONS="-server -Djava.awt.headless=true -Dfile.encoding=UTF-8 -Xms{{ openrefine_java_heap }} -Xmx{{ openrefine_java_heap }} -Drefine.data_dir={{ openrefine_data_dir }}"
+
+# Uncomment to increase autosave period to 60 mins (default: 5 minutes) for better performance of long-lasting transformations
+#REFINE_AUTOSAVE_PERIOD=60