From 4583cf4be17155c68178155acf6866d7cc8f7df0 Mon Sep 17 00:00:00 2001 From: GenTang Date: Fri, 22 May 2015 23:37:03 -0700 Subject: [SPARK-5090] [EXAMPLES] The improvement of python converter for hbase Hi, Following the discussion in http://apache-spark-developers-list.1001551.n3.nabble.com/python-converter-in-HBaseConverter-scala-spark-examples-td10001.html. I made some modification in three files in package examples: 1. HBaseConverters.scala: the new converter will converts all the records in an hbase results into a single string 2. hbase_input.py: as the value string may contain several records, we can use ast package to convert the string into dict 3. HBaseTest.scala: as the package examples use hbase 0.98.7 the original constructor HTableDescriptor is deprecated. The updation to new constructor is made Author: GenTang Closes #3920 from GenTang/master and squashes the following commits: d2153df [GenTang] import JSONObject precisely 4802481 [GenTang] dump the result into a singl String 62df7f0 [GenTang] remove the comment 21de653 [GenTang] return the string in json format 15b1fe3 [GenTang] the modification of comments 5cbbcfc [GenTang] the improvement of pythonconverter ceb31c5 [GenTang] the modification for adapting updation of hbase 3253b61 [GenTang] the modification accompanying the improvement of pythonconverter --- .../examples/pythonconverters/HBaseConverters.scala | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'examples/src/main/scala') diff --git a/examples/src/main/scala/org/apache/spark/examples/pythonconverters/HBaseConverters.scala b/examples/src/main/scala/org/apache/spark/examples/pythonconverters/HBaseConverters.scala index 273bee0a8b..90d48a6410 100644 --- a/examples/src/main/scala/org/apache/spark/examples/pythonconverters/HBaseConverters.scala +++ b/examples/src/main/scala/org/apache/spark/examples/pythonconverters/HBaseConverters.scala @@ -18,20 +18,34 @@ package org.apache.spark.examples.pythonconverters import scala.collection.JavaConversions._ +import scala.util.parsing.json.JSONObject import org.apache.spark.api.python.Converter import org.apache.hadoop.hbase.client.{Put, Result} import org.apache.hadoop.hbase.io.ImmutableBytesWritable import org.apache.hadoop.hbase.util.Bytes +import org.apache.hadoop.hbase.KeyValue.Type +import org.apache.hadoop.hbase.CellUtil /** - * Implementation of [[org.apache.spark.api.python.Converter]] that converts an - * HBase Result to a String + * Implementation of [[org.apache.spark.api.python.Converter]] that converts all + * the records in an HBase Result to a String */ class HBaseResultToStringConverter extends Converter[Any, String] { override def convert(obj: Any): String = { + import collection.JavaConverters._ val result = obj.asInstanceOf[Result] - Bytes.toStringBinary(result.value()) + val output = result.listCells.asScala.map(cell => + Map( + "row" -> Bytes.toStringBinary(CellUtil.cloneRow(cell)), + "columnFamily" -> Bytes.toStringBinary(CellUtil.cloneFamily(cell)), + "qualifier" -> Bytes.toStringBinary(CellUtil.cloneQualifier(cell)), + "timestamp" -> cell.getTimestamp.toString, + "type" -> Type.codeToType(cell.getTypeByte).toString, + "value" -> Bytes.toStringBinary(CellUtil.cloneValue(cell)) + ) + ) + output.map(JSONObject(_).toString()).mkString("\n") } } -- cgit v1.2.3