add datax

README.md

@@ -45,6 +45,7 @@ A collection of delicious docker recipes.
 - [x] airflow
 - [x] ambari
 - [x] cmak (~kafka-manager~)
+- [x] datax :cn:
 - [x] kafka-arm
 - [x] luigi
 - [x] nifi

datax/Dockerfile

@@ -0,0 +1,19 @@
+#
+# Dockerfile for datax
+#
+
+FROM openjdk:8-alpine
+MAINTAINER EasyPi Software Foundation
+
+WORKDIR /opt/datax
+
+RUN set -xe \
+    && apk add --no-cache curl python2 tar \
+    && curl -sSL http://datax-opensource.oss-cn-hangzhou.aliyuncs.com/datax.tar.gz | tar xz --strip 1 \
+    && bin/datax.py --help \
+    && apk del curl tar
+
+ENV PATH=/opt/datax/bin:$PATH
+
+ENTRYPOINT ["datax.py"]
+CMD ["--help"]

datax/README.md

@@ -0,0 +1,14 @@
+datax
+=====
+
+[DataX][1] is a data migration tool written by alibaba.
+
+## up and running
+
+```bash
+$ alias datax='docker run --rm -v $PWD:/data vimagick/datax'
+$ wget https://github.com/alibaba/DataX/raw/master/core/src/main/job/job.json
+$ datax job.json
+```
+
+[1]: https://github.com/alibaba/DataX

datax/data/job.json

@@ -0,0 +1,52 @@
+{
+    "job": {
+        "setting": {
+            "speed": {
+                "byte":10485760
+            },
+            "errorLimit": {
+                "record": 0,
+                "percentage": 0.02
+            }
+        },
+        "content": [
+            {
+                "reader": {
+                    "name": "streamreader",
+                    "parameter": {
+                        "column" : [
+                            {
+                                "value": "DataX",
+                                "type": "string"
+                            },
+                            {
+                                "value": 19890604,
+                                "type": "long"
+                            },
+                            {
+                                "value": "1989-06-04 00:00:00",
+                                "type": "date"
+                            },
+                            {
+                                "value": true,
+                                "type": "bool"
+                            },
+                            {
+                                "value": "test",
+                                "type": "bytes"
+                            }
+                        ],
+                        "sliceRecordCount": 100000
+                    }
+                },
+                "writer": {
+                    "name": "streamwriter",
+                    "parameter": {
+                        "print": false,
+                        "encoding": "UTF-8"
+                    }
+                }
+            }
+        ]
+    }
+}

datax/docker-compose.yml

@@ -0,0 +1,5 @@
+datax:
+  image: vimagick/datax
+  command: /data/job.json
+  volumes:
+  - ./data:/data