hbase_inputformat.py
2.6 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import sys
from common import *
from dependencies import *
from pyspark import SparkConf, SparkContext
if __name__ == "__main__":
load_env()
host = 'HPC-server'
table = 'test'
conf = SparkConf().setAppName("HBaseInputFormat")
print conf.getAll()
sc = SparkContext(conf=conf)
hparams = dict(
inputFormatClass="org.apache.hadoop.hbase.mapreduce.TableInputFormat",
readKeyClass="org.apache.hadoop.hbase.io.ImmutableBytesWritable",
readValueClass="org.apache.hadoop.hbase.client.Result",
readKeyConverter="org.apache.spark.examples.pythonconverters.ImmutableBytesWritableToStringConverter",
readValueConverter="org.apache.spark.examples.pythonconverters.CustomHBaseResultToStringConverter",
outputFormatClass="org.apache.hadoop.hbase.mapreduce.TableOutputFormat",
writeKeyClass="org.apache.hadoop.hbase.io.ImmutableBytesWritable",
# writeValueClass="org.apache.hadoop.io.Writable",
writeValueClass="org.apache.hadoop.hbase.client.Put",
writeKeyConverter="org.apache.spark.examples.pythonconverters.StringToImmutableBytesWritableConverter",
writeValueConverter="org.apache.spark.examples.pythonconverters.StringListToPutConverter",
)
hconf = {"hbase.zookeeper.quorum": host,
"hbase.mapreduce.inputtable": table,
}
hbase_rdd = sc.newAPIHadoopRDD(inputFormatClass=hparams["inputFormatClass"],
keyClass=hparams["readKeyClass"],
valueClass=hparams["readValueClass"],
keyConverter=hparams["readKeyConverter"],
valueConverter=hparams["readValueConverter"],
conf=hconf)
output = hbase_rdd.collect()
for (k, v) in output:
print (k, v)
sc.stop()