├── project
    ├── build.properties
    └── plugins.sbt
├── .gitignore
├── hbase_input.py
├── src
    ├── main
    │   └── scala
    │   │   └── examples
    │   │       ├── pythonConverters.scala
    │   │       └── HBaseInput.scala
    └── test
    │   └── scala
    │       └── examples
    │           └── pythonConverterTest.scala
├── README.md
├── sbt
    ├── sbt-launch-lib.bash
    └── sbt
└── LICENSE


/project/build.properties:
--------------------------------------------------------------------------------
1 | // This file should only contain the version of sbt to use.
2 | sbt.version=0.13.7
3 | 


--------------------------------------------------------------------------------
/project/plugins.sbt:
--------------------------------------------------------------------------------
1 | // Use sbt-spark-package plugin to assembly package
2 | // You may use this file to add plugin dependencies for sbt.
3 | resolvers += "Spark Packages repo" at "https://dl.bintray.com/spark-packages/maven/"
4 | 
5 | addSbtPlugin("org.spark-packages" %% "sbt-spark-package" % "0.2.1")
6 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | *.class
 2 | *.log
 3 | *.swp
 4 | 
 5 | # sbt specific
 6 | .cache/
 7 | .history/
 8 | .lib/
 9 | dist/*
10 | target/
11 | lib_managed/
12 | src_managed/
13 | project/boot/
14 | project/plugins/project/
15 | 
16 | # Scala-IDE specific
17 | .scala_dependencies
18 | .worksheet
19 | 
20 | # IntelliJ
21 | *.iml
22 | .idea/
23 | 


--------------------------------------------------------------------------------
/hbase_input.py:
--------------------------------------------------------------------------------
 1 | import sys
 2 | import json
 3 | 
 4 | from pyspark import SparkContext
 5 | 
 6 | """
 7 | Create test data in HBase first:
 8 | hbase(main):016:0> create 'test', 'c1'
 9 | hbase(main):017:0> put 'test', 'r1', 'c1:a', 'a1'
10 | hbase(main):018:0> put 'test', 'r1', 'c1:b', 'b1'
11 | hbase(main):019:0> put 'test', 'r2', 'c1:a', 'a2'
12 | hbase(main):020:0> put 'test', 'r3', 'c1', '3'
13 | hbase(main):028:0> scan "test"
14 | ROW                          COLUMN+CELL
15 |  r1                          column=c1:a, timestamp=1420329575846, value=a1
16 |  r1                          column=c1:b, timestamp=1420329640962, value=b1
17 |  r2                          column=c1:a, timestamp=1420329683843, value=a2
18 |  r3                          column=c1:,  timestamp=1420329810504, value=3
19 | """
20 | if __name__ == "__main__":
21 |   if len(sys.argv) != 4:
22 |     print >> sys.stderr, """
23 |       Usage: hbase_inputformat <host> <table> <column>
24 |       Run with example jar:
25 |       ./bin/spark-submit --driver-class-path <the path to spark_hbase.jar> \
26 |       /path/to/examples/hbase_inputformat.py <host> <table> <column>
27 |       Assumes you have some data in HBase already, running on <host>, in <table> at <column>
28 |       More information is available at https://github.com/GenTang/spark_hbase
29 |         """
30 |     exit(-1)
31 |   host = sys.argv[1]
32 |   table = sys.argv[2]
33 |   column = sys.argv[3]
34 |   sc = SparkContext(appName="HBaseInputFormat")
35 | 
36 |   # Other options for configuring scan behavior are available. More information available at
37 |   # https://github.com/apache/hbase/blob/master/hbase-server/src/main/java/org/apache/hadoop/hbase/mapreduce/TableInputFormat.java 
38 |   conf = {
39 |       "hbase.zookeeper.quorum": host, 
40 |       "hbase.mapreduce.inputtable": table,
41 |       "hbase.mapreduce.scan.columns": column}
42 |   keyConv = "examples.pythonconverters.ImmutableBytesWritableToStringConverter"
43 |   valueConv = "examples.pythonconverters.HBaseResultToStringConverter"
44 | 
45 |   hbase_rdd = sc.newAPIHadoopRDD(
46 |       "org.apache.hadoop.hbase.mapreduce.TableInputFormat",
47 |       "org.apache.hadoop.hbase.io.ImmutableBytesWritable",
48 |       "org.apache.hadoop.hbase.client.Result",
49 |       keyConverter=keyConv,
50 |       valueConverter=valueConv,
51 |       conf=conf)
52 | 
53 |   
54 |   hbase_rdd = hbase_rdd.flatMapValues(lambda v: v.split("\n")).mapValues(json.loads)
55 |   # hbase_rdd is a RDD[dict]
56 | 
57 |   output = hbase_rdd.collect()
58 |   for (k, v) in output:
59 |     print (k, v)
60 | 
61 |   sc.stop()
62 | 


--------------------------------------------------------------------------------
/src/main/scala/examples/pythonConverters.scala:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *    http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | 
18 | package examples.pythonconverters
19 | 
20 | import scala.collection.JavaConversions._
21 | import scala.util.parsing.json.JSONObject
22 | 
23 | import org.apache.spark.api.python.Converter
24 | import org.apache.hadoop.hbase.client.{Put, Result}
25 | import org.apache.hadoop.hbase.io.ImmutableBytesWritable
26 | import org.apache.hadoop.hbase.util.Bytes
27 | import org.apache.hadoop.hbase.KeyValue.Type
28 | import org.apache.hadoop.hbase.CellUtil
29 | 
30 | 
31 | /**
32 |  * Implementation of [[org.apache.spark.api.python.Converter]] that converts all 
33 |  * the records in an HBase Result to a String. In the String, it contains row, column,
34 |  * qualifier, timesstamp, type and value
35 |  */
36 | 
37 | class HBaseResultToStringConverter extends Converter[Any, String]{
38 |   override def convert(obj: Any): String = {
39 |     import collection.JavaConverters._
40 |     val result = obj.asInstanceOf[Result]                      
41 |     val output = result.listCells.asScala.map(cell =>
42 |         Map(
43 |           "row" -> Bytes.toStringBinary(CellUtil.cloneFamily(cell)),
44 |           "columnFamily" -> Bytes.toStringBinary(CellUtil.cloneFamily(cell)),
45 |           "qualifier" -> Bytes.toStringBinary(CellUtil.cloneQualifier(cell)),
46 |           "timestamp" -> cell.getTimestamp.toString,
47 |           "type" -> Type.codeToType(cell.getTypeByte).toString,
48 |           "value" -> Bytes.toStringBinary(CellUtil.cloneValue(cell))
49 |         )
50 |       )
51 |     // output is an instance of Map which will be translated to json String
52 |     // Hbase will escape "\n", so it is safe to use "\n" to join json.
53 |     output.map(JSONObject(_).toString()).mkString("\n")                                           
54 |   }
55 | }
56 | 
57 | /**
58 |  * Implementation of [[org.apache.spark.api.python.Converter]] that converts an
59 |  * ImmutableBytesWritable to a String
60 |  */
61 | 
62 | class ImmutableBytesWritableToStringConverter extends Converter[Any, String] {
63 |   override def convert(obj: Any): String = {
64 |     val key = obj.asInstanceOf[ImmutableBytesWritable]
65 |     Bytes.toStringBinary(key.get())
66 |   }
67 | }
68 | 


--------------------------------------------------------------------------------
/src/test/scala/examples/pythonConverterTest.scala:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *    http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | 
18 | package examples.pythonconverters
19 | 
20 | import org.apache.hadoop.hbase.client.HBaseAdmin
21 | import org.apache.hadoop.hbase.{HBaseConfiguration, HTableDescriptor}
22 | import org.apache.hadoop.hbase.mapreduce.TableInputFormat
23 | import org.apache.hadoop.hbase.HConstants
24 | 
25 | import org.apache.spark._
26 | import org.apache.spark.rdd.RDD
27 | import org.apache.spark.api.python.Converter 
28 | 
29 | object HBaseTest {
30 |   def main(args: Array[String]) {
31 |     val sparkConf = new SparkConf().setAppName("HBaseTest").setMaster("localhost")
32 |     val sc = new SparkContext(sparkConf)
33 |     val conf = HBaseConfiguration.create()
34 |     // Other options for hbase configuration are available, please check 
35 |     // http://hbase.apache.org/apidocs/org/apache/hadoop/hbase/HConstants.html
36 |     conf.set(HConstants.ZOOKEEPER_QUORUM, args(0))
37 |     // Other options for configuring scan behavior are available. More information available at
38 |     // http://hbase.apache.org/apidocs/org/apache/hadoop/hbase/mapreduce/TableInputFormat.html
39 |     conf.set(TableInputFormat.INPUT_TABLE, args(1))
40 | 
41 |     // Initialize hBase table if necessary
42 |     val admin = new HBaseAdmin(conf)
43 |     if (!admin.isTableAvailable(args(1))) {
44 |       val tableDesc = new HTableDescriptor(args(1))
45 |       admin.createTable(tableDesc)
46 |     }
47 | 
48 |     val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat],
49 |       classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
50 |       classOf[org.apache.hadoop.hbase.client.Result])
51 |     val keyConverter = new ImmutableBytesWritableToStringConverter().asInstanceOf[Converter[Any,Any]]
52 |     val valueConverter = new HBaseResultToStringConverter().asInstanceOf[Converter[Any, Any]]
53 |     
54 |     val hrdd = convertRDD(hBaseRDD, keyConverter, valueConverter)
55 |     hrdd.map(_._2).foreach(println)
56 | 
57 |     sc.stop()
58 |   }
59 | 
60 |  
61 |    // This function is copied from org.apache.spark.api.python.PythonHadoopUtils.convertRDD.
62 |   def convertRDD[K, V](rdd: RDD[(K, V)],
63 |                        keyConverter: Converter[Any, Any],
64 |                        valueConverter: Converter[Any, Any]): RDD[(Any, Any)] = {
65 |     rdd.map { case (k, v) => (keyConverter.convert(k), valueConverter.convert(v)) }
66 |   }
67 | 
68 | }
69 | 


--------------------------------------------------------------------------------
/src/main/scala/examples/HBaseInput.scala:
--------------------------------------------------------------------------------
 1 | /*
 2 |  * Licensed to the Apache Software Foundation (ASF) under one or more
 3 |  * contributor license agreements.  See the NOTICE file distributed with
 4 |  * this work for additional information regarding copyright ownership.
 5 |  * The ASF licenses this file to You under the Apache License, Version 2.0
 6 |  * (the "License"); you may not use this file except in compliance with
 7 |  * the License.  You may obtain a copy of the License at
 8 |  *
 9 |  *    http://www.apache.org/licenses/LICENSE-2.0
10 |  *
11 |  * Unless required by applicable law or agreed to in writing, software
12 |  * distributed under the License is distributed on an "AS IS" BASIS,
13 |  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 |  * See the License for the specific language governing permissions and
15 |  * limitations under the License.
16 |  */
17 | 
18 | package examples
19 | 
20 | import org.apache.hadoop.hbase.client.HBaseAdmin
21 | import org.apache.hadoop.hbase.{HBaseConfiguration, HTableDescriptor, TableName}
22 | import org.apache.hadoop.hbase.mapreduce.TableInputFormat
23 | import org.apache.hadoop.hbase.KeyValue.Type
24 | import org.apache.hadoop.hbase.HConstants
25 | import org.apache.hadoop.hbase.util.Bytes
26 | import org.apache.hadoop.hbase.CellUtil
27 | 
28 | 
29 | import org.apache.spark._
30 | 
31 | import scala.collection.JavaConverters._
32 | 
33 | 
34 | object HBaseInput {
35 |   def main(args: Array[String]) {
36 |     val sparkConf = new SparkConf().setAppName("HBaseTest")
37 |     val sc = new SparkContext(sparkConf)
38 |     val conf = HBaseConfiguration.create()
39 |     // Other options for hbase configuration are available, please check 
40 |     // http://hbase.apache.org/apidocs/org/apache/hadoop/hbase/HConstants.html
41 |     conf.set(HConstants.ZOOKEEPER_QUORUM, args(0))
42 |     // Other options for configuring scan behavior are available. More information available at
43 |     // http://hbase.apache.org/apidocs/org/apache/hadoop/hbase/mapreduce/TableInputFormat.html
44 |     conf.set(TableInputFormat.INPUT_TABLE, args(1))
45 | 
46 |     // Initialize hBase table if necessary
47 |     val admin = new HBaseAdmin(conf)
48 |     if (!admin.isTableAvailable(args(1))) {
49 |       val tableDesc = new HTableDescriptor(TableName.valueOf(args(1)))
50 |       admin.createTable(tableDesc)
51 |     }
52 | 
53 |     val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat],
54 |       classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
55 |       classOf[org.apache.hadoop.hbase.client.Result])
56 | 
57 |     //keyValue is a RDD[java.util.list[hbase.KeyValue]]
58 |     val keyValue = hBaseRDD.map(x => x._2).map(_.list)
59 | 
60 |     //outPut is a RDD[String], in which each line represents a record in HBase
61 |     val outPut = keyValue.flatMap(x =>  x.asScala.map(cell =>
62 |         "columnFamily=%s,qualifier=%s,timestamp=%s,type=%s,value=%s".format(
63 |           Bytes.toStringBinary(CellUtil.cloneFamily(cell)),
64 |           Bytes.toStringBinary(CellUtil.cloneQualifier(cell)),
65 |           cell.getTimestamp.toString,
66 |           Type.codeToType(cell.getTypeByte),
67 |           Bytes.toStringBinary(CellUtil.cloneValue(cell))
68 |         )
69 |       )
70 |     )
71 | 
72 |     outPut.foreach(println)
73 | 
74 |     sc.stop()
75 |   }
76 | }
77 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | spark_hbase
 2 | ===========
 3 | 
 4 | Spark has their own example about integrating HBase and Spark in scala [HBaseTest.scala](https://github.com/apache/spark/blob/master/examples/src/main/scala/org/apache/spark/examples/HBaseTest.scala) and python converter [HBaseConverters.scala](https://github.com/apache/spark/blob/master/examples/src/main/scala/org/apache/spark/examples/pythonconverters/HBaseConverters.scala). 
 5 | 
 6 | However, the python converter `HBaseResultToStringConverter` in  [HBaseConverters.scala](https://github.com/apache/spark/blob/master/examples/src/main/scala/org/apache/spark/examples/pythonconverters/HBaseConverters.scala) return only the value of first column in the result. And [HBaseTest.scala](https://github.com/apache/spark/blob/master/examples/src/main/scala/org/apache/spark/examples/HBaseTest.scala) stops just at returning *org.apache.hadoop.hbase.client.Result* and doing .count() call.
 7 | 
 8 | Here we provide a new example in Scala about transferring data saved in hbase into `String` by Spark and a new example of python converter.
 9 | 
10 | The example in scala [HBaseInput.scala](/src/main/scala/examples/HBaseInput.scala) transfers the data saved in hbase into `RDD[String]` which contains *columnFamily, qualifier, timestamp, type, value*. 
11 | 
12 | The example of converter for python [pythonConverters.scala](/src/main/scala/examples//pythonConverters.scala) transfer the data saved in hbase into string which contains the same information as the example above. We can use `ast` package to easily transfer this string to dictionary
13 | 
14 | How to run
15 | =========
16 | 1. Make sure that you well set up [git](https://help.github.com/articles/set-up-git/#platform-linux)
17 | 2. Download this application by 
18 | 
19 |   ```bash
20 |    $ git clone https://github.com/GenTang/spark_hbase.git
21 |   ```
22 | 
23 | 3. Build the assembly by using SBT `assembly`
24 | 
25 |   ```bash
26 |   $ <the path to spark_hbase>/sbt/sbt clean assembly
27 |   ```
28 | 
29 | * Run example python script [hbase_input.py](hbase_input.py) which use pythonConverter `ImmutableBytesWritableToStringConverter` and `HBaseResultToStringConverter` to convert the data in hbase to dictionary
30 | 
31 |   * If you are using `SPARK_CLASSPATH`:
32 |      1. Add `export SPARK_CLASSPATH=$SPARK_CLASSPATH":<the path to hbase>/lib/*:<the path to spark_hbase>/target/scala-2.10/spark_hbase-assembly-1.0.jar` to `./conf/spark-env.sh`.
33 |   
34 |     2. Launch the script by 
35 |       ```bash
36 |       $ ./bin/spark-submit <the path to hbase_input.py> \
37 |          <host> <table> <column>
38 |       ```
39 | 
40 |   * You can also use `spark.executor.extraClassPath` and `--driver-class-path` (recommended):
41 |      1. Add `spark.executor.extraClassPath <the path to hbase>/lib/*` to `spark-defaults.conf`.
42 | 
43 |      2. Launch the script by
44 |        ```bash
45 |         $ ./bin/spark-submit \
46 |            --driver-class-path <the path to spark_hbase>/target/scala-2.10/spark_hbase-assembly-1.0.jar \
47 |            <the path to hbase_input.py> \
48 |            <host> <table> <column>
49 |        ```
50 | 
51 | * Run example scala script [HBaseInput.scala](/src/main/scala/examples/HBaseInput.scala)
52 |   * If you are using `SPARK_CLASSPATH`:
53 |      1. Add `export SPARK_CLASSPATH=$SPARK_CLASSPATH":<the path to hbase>/lib/*` to `./conf/spark-env.sh`.
54 | 
55 |      2. Launch the script by 
56 |       ```bash
57 |       $ ./bin/spark-submit \
58 |          --class examples.HBaseInput \
59 |          <the path to spark_hbase>/target/scala-2.10/spark_hbase-assembly-1.0.jar \
60 |          <host> <table> 
61 |       ```
62 |       
63 |   * You can also use `spark.executor.extraClassPath` and `--driver-class-path` (recommended):
64 |      1. The same configuration as above
65 |  
66 |      2. Launch the script by
67 |       ```bash
68 |       $ ./bin/spark-submit \
69 |          --driver-class-path <the path to hbase>/lib/*: \
70 |          --class examples.HBaseInput \
71 |          <the path to spark_hbase>/target/scala-2.10/spark_hbase-assembly-1.0.jar \
72 |          <host> <table> 
73 |       ```
74 | 
75 | Example of results
76 | ==================
77 | Assume that you have already some data in hbase as follow:
78 | 
79 |     hbase(main):028:0> scan "test"
80 |     ROW                          COLUMN+CELL
81 |      r1                          column=c1:a, timestamp=1420329575846, value=a1
82 |      r1                          column=c1:b, timestamp=1420329640962, value=b1
83 |      r2                          column=c1:a, timestamp=1420329683843, value=a2
84 |      r3                          column=c1:,  timestamp=1420329810504, value=3
85 | 
86 | By launching `$ ./bin/spark-submit --driver-class-path <the path to spark_hbase>/target/scala-2.10/spark_hbase-assembly-1.0.jar <the path to hbase_input.py> localhost test c1`, you will get 
87 | 
88 |      (u'r1', {'columnFamliy': 'c1', 'timestamp': '1420329575846', 'type': 'Put', 'qualifier': 'a', 'value': 'a1'}) 
89 |      (u'r1', {'columnFamliy': 'c1', 'timestamp': '1420329640962', 'type': 'Put', 'qualifier': 'b', 'value': 'b1'}) 
90 |      (u'r2', {'columnFamliy': 'c1', 'timestamp': '1420329683843', 'type': 'Put', 'qualifier': 'a', 'value': 'a2'}) 
91 |      (u'r3', {'columnFamliy': 'c1', 'timestamp': '1420329810504', 'type': 'Put', 'qualifier': '', 'value': '3'})
92 | 


--------------------------------------------------------------------------------
/sbt/sbt-launch-lib.bash:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/env bash
  2 | #
  3 | 
  4 | # A library to simplify using the SBT launcher from other packages.
  5 | # Note: This should be used by tools like giter8/conscript etc.
  6 | 
  7 | # TODO - Should we merge the main SBT script with this library?
  8 | 
  9 | if test -z "$HOME"; then
 10 |   declare -r script_dir="$(dirname "$script_path")"
 11 | else
 12 |   declare -r script_dir="$HOME/.sbt"
 13 | fi
 14 | 
 15 | declare -a residual_args
 16 | declare -a java_args
 17 | declare -a scalac_args
 18 | declare -a sbt_commands
 19 | declare -a maven_profiles
 20 | 
 21 | if test -x "$JAVA_HOME/bin/java"; then
 22 |     echo -e "Using $JAVA_HOME as default JAVA_HOME."
 23 |     echo "Note, this will be overridden by -java-home if it is set."
 24 |     declare java_cmd="$JAVA_HOME/bin/java"
 25 | else
 26 |     declare java_cmd=java
 27 | fi
 28 | 
 29 | echoerr () {
 30 |   echo 1>&2 "$@"
 31 | }
 32 | vlog () {
 33 |   [[ $verbose || $debug ]] && echoerr "$@"
 34 | }
 35 | dlog () {
 36 |   [[ $debug ]] && echoerr "$@"
 37 | }
 38 | 
 39 | acquire_sbt_jar () {
 40 |   SBT_VERSION=`awk -F "=" '/sbt\.version/ {print $2}' ./project/build.properties`
 41 |   URL1=https://dl.bintray.com/typesafe/ivy-releases/org.scala-sbt/sbt-launch/${SBT_VERSION}/sbt-launch.jar
 42 |   JAR=sbt/sbt-launch-${SBT_VERSION}.jar
 43 | 
 44 |   sbt_jar=$JAR
 45 | 
 46 |   if [[ ! -f "$sbt_jar" ]]; then
 47 |     # Download sbt launch jar if it hasn't been downloaded yet
 48 |     if [ ! -f "${JAR}" ]; then
 49 |     # Download
 50 |     printf "Attempting to fetch sbt\n"
 51 |     JAR_DL="${JAR}.part"
 52 |     if [ $(command -v curl) ]; then
 53 |       curl --fail --location --silent ${URL1} > "${JAR_DL}" &&\
 54 |         mv "${JAR_DL}" "${JAR}"
 55 |     elif [ $(command -v wget) ]; then
 56 |       wget --quiet ${URL1} -O "${JAR_DL}" &&\
 57 |         mv "${JAR_DL}" "${JAR}"
 58 |     else
 59 |       printf "You do not have curl or wget installed, please install sbt manually from http://www.scala-sbt.org/\n"
 60 |       exit -1
 61 |     fi
 62 |     fi
 63 |     if [ ! -f "${JAR}" ]; then
 64 |     # We failed to download
 65 |     printf "Our attempt to download sbt locally to ${JAR} failed. Please install sbt manually from http://www.scala-sbt.org/\n"
 66 |     exit -1
 67 |     fi
 68 |     printf "Launching sbt from ${JAR}\n"
 69 |   fi
 70 | }
 71 | 
 72 | execRunner () {
 73 |   # print the arguments one to a line, quoting any containing spaces
 74 |   [[ $verbose || $debug ]] && echo "# Executing command line:" && {
 75 |     for arg; do
 76 |       if printf "%s\n" "$arg" | grep -q ' '; then
 77 |         printf "\"%s\"\n" "$arg"
 78 |       else
 79 |         printf "%s\n" "$arg"
 80 |       fi
 81 |     done
 82 |     echo ""
 83 |   }
 84 | 
 85 |   "$@"
 86 | }
 87 | 
 88 | addJava () {
 89 |   dlog "[addJava] arg = '$1'"
 90 |   java_args=( "${java_args[@]}" "$1" )
 91 | }
 92 | 
 93 | enableProfile () {
 94 |   dlog "[enableProfile] arg = '$1'"
 95 |   maven_profiles=( "${maven_profiles[@]}" "$1" )
 96 |   export SBT_MAVEN_PROFILES="${maven_profiles[@]}"
 97 | }
 98 | 
 99 | addSbt () {
100 |   dlog "[addSbt] arg = '$1'"
101 |   sbt_commands=( "${sbt_commands[@]}" "$1" )
102 | }
103 | addResidual () {
104 |   dlog "[residual] arg = '$1'"
105 |   residual_args=( "${residual_args[@]}" "$1" )
106 | }
107 | addDebugger () {
108 |   addJava "-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=$1"
109 | }
110 | 
111 | # a ham-fisted attempt to move some memory settings in concert
112 | # so they need not be dicked around with individually.
113 | get_mem_opts () {
114 |   local mem=${1:-2048}
115 |   local perm=$(( $mem / 4 ))
116 |   (( $perm > 256 )) || perm=256
117 |   (( $perm < 4096 )) || perm=4096
118 |   local codecache=$(( $perm / 2 ))
119 | 
120 |   echo "-Xms${mem}m -Xmx${mem}m -XX:MaxPermSize=${perm}m -XX:ReservedCodeCacheSize=${codecache}m"
121 | }
122 | 
123 | require_arg () {
124 |   local type="$1"
125 |   local opt="$2"
126 |   local arg="$3"
127 |   if [[ -z "$arg" ]] || [[ "${arg:0:1}" == "-" ]]; then
128 |     echo "$opt requires <$type> argument" 1>&2
129 |     exit 1
130 |   fi
131 | }
132 | 
133 | is_function_defined() {
134 |   declare -f "$1" > /dev/null
135 | }
136 | 
137 | process_args () {
138 |   while [[ $# -gt 0 ]]; do
139 |     case "$1" in
140 |        -h|-help) usage; exit 1 ;;
141 |     -v|-verbose) verbose=1 && shift ;;
142 |       -d|-debug) debug=1 && shift ;;
143 | 
144 |            -ivy) require_arg path "$1" "$2" && addJava "-Dsbt.ivy.home=$2" && shift 2 ;;
145 |            -mem) require_arg integer "$1" "$2" && sbt_mem="$2" && shift 2 ;;
146 |      -jvm-debug) require_arg port "$1" "$2" && addDebugger $2 && shift 2 ;;
147 |          -batch) exec </dev/null && shift ;;
148 | 
149 |        -sbt-jar) require_arg path "$1" "$2" && sbt_jar="$2" && shift 2 ;;
150 |    -sbt-version) require_arg version "$1" "$2" && sbt_version="$2" && shift 2 ;;
151 |      -java-home) require_arg path "$1" "$2" && java_cmd="$2/bin/java" && export JAVA_HOME=$2 && shift 2 ;;
152 | 
153 |             -D*) addJava "$1" && shift ;;
154 |             -J*) addJava "${1:2}" && shift ;;
155 |             -P*) enableProfile "$1" && shift ;;
156 |               *) addResidual "$1" && shift ;;
157 |     esac
158 |   done
159 | 
160 |   is_function_defined process_my_args && {
161 |     myargs=("${residual_args[@]}")
162 |     residual_args=()
163 |     process_my_args "${myargs[@]}"
164 |   }
165 | }
166 | 
167 | run() {
168 |   # no jar? download it.
169 |   [[ -f "$sbt_jar" ]] || acquire_sbt_jar "$sbt_version" || {
170 |     # still no jar? uh-oh.
171 |     echo "Download failed. Obtain the sbt-launch.jar manually and place it at $sbt_jar"
172 |     exit 1
173 |   }
174 | 
175 |   # process the combined args, then reset "$@" to the residuals
176 |   process_args "$@"
177 |   set -- "${residual_args[@]}"
178 |   argumentCount=$#
179 | 
180 |   # run sbt
181 |   execRunner "$java_cmd" \
182 |     ${SBT_OPTS:-$default_sbt_opts} \
183 |     $(get_mem_opts $sbt_mem) \
184 |     ${java_opts} \
185 |     ${java_args[@]} \
186 |     -jar "$sbt_jar" \
187 |     "${sbt_commands[@]}" \
188 |     "${residual_args[@]}"
189 | }
190 | 


--------------------------------------------------------------------------------
/sbt/sbt:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/env bash
  2 | 
  3 | #
  4 | # Licensed to the Apache Software Foundation (ASF) under one or more
  5 | # contributor license agreements.  See the NOTICE file distributed with
  6 | # this work for additional information regarding copyright ownership.
  7 | # The ASF licenses this file to You under the Apache License, Version 2.0
  8 | # (the "License"); you may not use this file except in compliance with
  9 | # the License.  You may obtain a copy of the License at
 10 | #
 11 | #    http://www.apache.org/licenses/LICENSE-2.0
 12 | #
 13 | # Unless required by applicable law or agreed to in writing, software
 14 | # distributed under the License is distributed on an "AS IS" BASIS,
 15 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 16 | # See the License for the specific language governing permissions and
 17 | # limitations under the License.
 18 | #
 19 | 
 20 | # When creating new tests for Spark SQL Hive, the HADOOP_CLASSPATH must contain the hive jars so
 21 | # that we can run Hive to generate the golden answer.  This is not required for normal development
 22 | # or testing.
 23 | if [ -n "$HIVE_HOME" ]; then
 24 |     for i in "$HIVE_HOME"/lib/*
 25 |     do HADOOP_CLASSPATH="$HADOOP_CLASSPATH:$i"
 26 |     done
 27 |     export HADOOP_CLASSPATH
 28 | fi
 29 | 
 30 | realpath () {
 31 | (
 32 |   TARGET_FILE="$1"
 33 | 
 34 |   cd "$(dirname "$TARGET_FILE")"
 35 |   TARGET_FILE="$(basename "$TARGET_FILE")"
 36 | 
 37 |   COUNT=0
 38 |   while [ -L "$TARGET_FILE" -a $COUNT -lt 100 ]
 39 |   do
 40 |       TARGET_FILE="$(readlink "$TARGET_FILE")"
 41 |       cd $(dirname "$TARGET_FILE")
 42 |       TARGET_FILE="$(basename $TARGET_FILE)"
 43 |       COUNT=$(($COUNT + 1))
 44 |   done
 45 | 
 46 |   echo "$(pwd -P)/"$TARGET_FILE""
 47 | )
 48 | }
 49 | 
 50 | . "$(dirname "$(realpath "$0")")"/sbt-launch-lib.bash
 51 | 
 52 | 
 53 | declare -r noshare_opts="-Dsbt.global.base=project/.sbtboot -Dsbt.boot.directory=project/.boot -Dsbt.ivy.home=project/.ivy"
 54 | declare -r sbt_opts_file=".sbtopts"
 55 | declare -r etc_sbt_opts_file="/etc/sbt/sbtopts"
 56 | 
 57 | usage() {
 58 |  cat <<EOM
 59 | Usage: $script_name [options]
 60 | 
 61 |   -h | -help         print this message
 62 |   -v | -verbose      this runner is chattier
 63 |   -d | -debug        set sbt log level to debug
 64 |   -no-colors         disable ANSI color codes
 65 |   -sbt-create        start sbt even if current directory contains no sbt project
 66 |   -sbt-dir   <path>  path to global settings/plugins directory (default: ~/.sbt)
 67 |   -sbt-boot  <path>  path to shared boot directory (default: ~/.sbt/boot in 0.11 series)
 68 |   -ivy       <path>  path to local Ivy repository (default: ~/.ivy2)
 69 |   -mem    <integer>  set memory options (default: $sbt_mem, which is $(get_mem_opts $sbt_mem))
 70 |   -no-share          use all local caches; no sharing
 71 |   -no-global         uses global caches, but does not use global ~/.sbt directory.
 72 |   -jvm-debug <port>  Turn on JVM debugging, open at the given port.
 73 |   -batch             Disable interactive mode
 74 | 
 75 |   # sbt version (default: from project/build.properties if present, else latest release)
 76 |   -sbt-version  <version>   use the specified version of sbt
 77 |   -sbt-jar      <path>      use the specified jar as the sbt launcher
 78 |   -sbt-rc                   use an RC version of sbt
 79 |   -sbt-snapshot             use a snapshot version of sbt
 80 | 
 81 |   # java version (default: java from PATH, currently $(java -version 2>&1 | grep version))
 82 |   -java-home <path>         alternate JAVA_HOME
 83 | 
 84 |   # jvm options and output control
 85 |   JAVA_OPTS          environment variable, if unset uses "$java_opts"
 86 |   SBT_OPTS           environment variable, if unset uses "$default_sbt_opts"
 87 |   .sbtopts           if this file exists in the current directory, it is
 88 |                      prepended to the runner args
 89 |   /etc/sbt/sbtopts   if this file exists, it is prepended to the runner args
 90 |   -Dkey=val          pass -Dkey=val directly to the java runtime
 91 |   -J-X               pass option -X directly to the java runtime
 92 |                      (-J is stripped)
 93 |   -S-X               add -X to sbt's scalacOptions (-S is stripped)
 94 |   -PmavenProfiles    Enable a maven profile for the build.
 95 | 
 96 | In the case of duplicated or conflicting options, the order above
 97 | shows precedence: JAVA_OPTS lowest, command line options highest.
 98 | EOM
 99 | }
100 | 
101 | process_my_args () {
102 |   while [[ $# -gt 0 ]]; do
103 |     case "$1" in
104 |      -no-colors) addJava "-Dsbt.log.noformat=true" && shift ;;
105 |       -no-share) addJava "$noshare_opts" && shift ;;
106 |      -no-global) addJava "-Dsbt.global.base=$(pwd)/project/.sbtboot" && shift ;;
107 |       -sbt-boot) require_arg path "$1" "$2" && addJava "-Dsbt.boot.directory=$2" && shift 2 ;;
108 |        -sbt-dir) require_arg path "$1" "$2" && addJava "-Dsbt.global.base=$2" && shift 2 ;;
109 |      -debug-inc) addJava "-Dxsbt.inc.debug=true" && shift ;;
110 |          -batch) exec </dev/null && shift ;;
111 | 
112 |     -sbt-create) sbt_create=true && shift ;;
113 | 
114 |               *) addResidual "$1" && shift ;;
115 |     esac
116 |   done
117 | 
118 |   # Now, ensure sbt version is used.
119 |   [[ "${sbt_version}XXX" != "XXX" ]] && addJava "-Dsbt.version=$sbt_version"
120 | }
121 | 
122 | loadConfigFile() {
123 |   cat "$1" | sed '/^\#/d'
124 | }
125 | 
126 | # if sbtopts files exist, prepend their contents to $@ so it can be processed by this runner
127 | [[ -f "$etc_sbt_opts_file" ]] && set -- $(loadConfigFile "$etc_sbt_opts_file") "$@"
128 | [[ -f "$sbt_opts_file" ]] && set -- $(loadConfigFile "$sbt_opts_file") "$@"
129 | 
130 | exit_status=127
131 | saved_stty=""
132 | 
133 | restoreSttySettings() {
134 |   stty $saved_stty
135 |   saved_stty=""
136 | }
137 | 
138 | onExit() {
139 |   if [[ "$saved_stty" != "" ]]; then
140 |     restoreSttySettings
141 |   fi
142 |   exit $exit_status
143 | }
144 | 
145 | saveSttySettings() {
146 |   saved_stty=$(stty -g 2>/dev/null)
147 |   if [[ ! $? ]]; then
148 |     saved_stty=""
149 |   fi
150 | }
151 | 
152 | saveSttySettings
153 | trap onExit INT
154 | 
155 | run "$@"
156 | 
157 | exit_status=$?
158 | onExit
159 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 | Apache License
  2 |                            Version 2.0, January 2004
  3 |                         http://www.apache.org/licenses/
  4 | 
  5 |    TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
  6 | 
  7 |    1. Definitions.
  8 | 
  9 |       "License" shall mean the terms and conditions for use, reproduction,
 10 |       and distribution as defined by Sections 1 through 9 of this document.
 11 | 
 12 |       "Licensor" shall mean the copyright owner or entity authorized by
 13 |       the copyright owner that is granting the License.
 14 | 
 15 |       "Legal Entity" shall mean the union of the acting entity and all
 16 |       other entities that control, are controlled by, or are under common
 17 |       control with that entity. For the purposes of this definition,
 18 |       "control" means (i) the power, direct or indirect, to cause the
 19 |       direction or management of such entity, whether by contract or
 20 |       otherwise, or (ii) ownership of fifty percent (50%) or more of the
 21 |       outstanding shares, or (iii) beneficial ownership of such entity.
 22 | 
 23 |       "You" (or "Your") shall mean an individual or Legal Entity
 24 |       exercising permissions granted by this License.
 25 | 
 26 |       "Source" form shall mean the preferred form for making modifications,
 27 |       including but not limited to software source code, documentation
 28 |       source, and configuration files.
 29 | 
 30 |       "Object" form shall mean any form resulting from mechanical
 31 |       transformation or translation of a Source form, including but
 32 |       not limited to compiled object code, generated documentation,
 33 |       and conversions to other media types.
 34 | 
 35 |       "Work" shall mean the work of authorship, whether in Source or
 36 |       Object form, made available under the License, as indicated by a
 37 |       copyright notice that is included in or attached to the work
 38 |       (an example is provided in the Appendix below).
 39 | 
 40 |       "Derivative Works" shall mean any work, whether in Source or Object
 41 |       form, that is based on (or derived from) the Work and for which the
 42 |       editorial revisions, annotations, elaborations, or other modifications
 43 |       represent, as a whole, an original work of authorship. For the purposes
 44 |       of this License, Derivative Works shall not include works that remain
 45 |       separable from, or merely link (or bind by name) to the interfaces of,
 46 |       the Work and Derivative Works thereof.
 47 | 
 48 |       "Contribution" shall mean any work of authorship, including
 49 |       the original version of the Work and any modifications or additions
 50 |       to that Work or Derivative Works thereof, that is intentionally
 51 |       submitted to Licensor for inclusion in the Work by the copyright owner
 52 |       or by an individual or Legal Entity authorized to submit on behalf of
 53 |       the copyright owner. For the purposes of this definition, "submitted"
 54 |       means any form of electronic, verbal, or written communication sent
 55 |       to the Licensor or its representatives, including but not limited to
 56 |       communication on electronic mailing lists, source code control systems,
 57 |       and issue tracking systems that are managed by, or on behalf of, the
 58 |       Licensor for the purpose of discussing and improving the Work, but
 59 |       excluding communication that is conspicuously marked or otherwise
 60 |       designated in writing by the copyright owner as "Not a Contribution."
 61 | 
 62 |       "Contributor" shall mean Licensor and any individual or Legal Entity
 63 |       on behalf of whom a Contribution has been received by Licensor and
 64 |       subsequently incorporated within the Work.
 65 | 
 66 |    2. Grant of Copyright License. Subject to the terms and conditions of
 67 |       this License, each Contributor hereby grants to You a perpetual,
 68 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 69 |       copyright license to reproduce, prepare Derivative Works of,
 70 |       publicly display, publicly perform, sublicense, and distribute the
 71 |       Work and such Derivative Works in Source or Object form.
 72 | 
 73 |    3. Grant of Patent License. Subject to the terms and conditions of
 74 |       this License, each Contributor hereby grants to You a perpetual,
 75 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 76 |       (except as stated in this section) patent license to make, have made,
 77 |       use, offer to sell, sell, import, and otherwise transfer the Work,
 78 |       where such license applies only to those patent claims licensable
 79 |       by such Contributor that are necessarily infringed by their
 80 |       Contribution(s) alone or by combination of their Contribution(s)
 81 |       with the Work to which such Contribution(s) was submitted. If You
 82 |       institute patent litigation against any entity (including a
 83 |       cross-claim or counterclaim in a lawsuit) alleging that the Work
 84 |       or a Contribution incorporated within the Work constitutes direct
 85 |       or contributory patent infringement, then any patent licenses
 86 |       granted to You under this License for that Work shall terminate
 87 |       as of the date such litigation is filed.
 88 | 
 89 |    4. Redistribution. You may reproduce and distribute copies of the
 90 |       Work or Derivative Works thereof in any medium, with or without
 91 |       modifications, and in Source or Object form, provided that You
 92 |       meet the following conditions:
 93 | 
 94 |       (a) You must give any other recipients of the Work or
 95 |           Derivative Works a copy of this License; and
 96 | 
 97 |       (b) You must cause any modified files to carry prominent notices
 98 |           stating that You changed the files; and
 99 | 
100 |       (c) You must retain, in the Source form of any Derivative Works
101 |           that You distribute, all copyright, patent, trademark, and
102 |           attribution notices from the Source form of the Work,
103 |           excluding those notices that do not pertain to any part of
104 |           the Derivative Works; and
105 | 
106 |       (d) If the Work includes a "NOTICE" text file as part of its
107 |           distribution, then any Derivative Works that You distribute must
108 |           include a readable copy of the attribution notices contained
109 |           within such NOTICE file, excluding those notices that do not
110 |           pertain to any part of the Derivative Works, in at least one
111 |           of the following places: within a NOTICE text file distributed
112 |           as part of the Derivative Works; within the Source form or
113 |           documentation, if provided along with the Derivative Works; or,
114 |           within a display generated by the Derivative Works, if and
115 |           wherever such third-party notices normally appear. The contents
116 |           of the NOTICE file are for informational purposes only and
117 |           do not modify the License. You may add Your own attribution
118 |           notices within Derivative Works that You distribute, alongside
119 |           or as an addendum to the NOTICE text from the Work, provided
120 |           that such additional attribution notices cannot be construed
121 |           as modifying the License.
122 | 
123 |       You may add Your own copyright statement to Your modifications and
124 |       may provide additional or different license terms and conditions
125 |       for use, reproduction, or distribution of Your modifications, or
126 |       for any such Derivative Works as a whole, provided Your use,
127 |       reproduction, and distribution of the Work otherwise complies with
128 |       the conditions stated in this License.
129 | 
130 |    5. Submission of Contributions. Unless You explicitly state otherwise,
131 |       any Contribution intentionally submitted for inclusion in the Work
132 |       by You to the Licensor shall be under the terms and conditions of
133 |       this License, without any additional terms or conditions.
134 |       Notwithstanding the above, nothing herein shall supersede or modify
135 |       the terms of any separate license agreement you may have executed
136 |       with Licensor regarding such Contributions.
137 | 
138 |    6. Trademarks. This License does not grant permission to use the trade
139 |       names, trademarks, service marks, or product names of the Licensor,
140 |       except as required for reasonable and customary use in describing the
141 |       origin of the Work and reproducing the content of the NOTICE file.
142 | 
143 |    7. Disclaimer of Warranty. Unless required by applicable law or
144 |       agreed to in writing, Licensor provides the Work (and each
145 |       Contributor provides its Contributions) on an "AS IS" BASIS,
146 |       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 |       implied, including, without limitation, any warranties or conditions
148 |       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 |       PARTICULAR PURPOSE. You are solely responsible for determining the
150 |       appropriateness of using or redistributing the Work and assume any
151 |       risks associated with Your exercise of permissions under this License.
152 | 
153 |    8. Limitation of Liability. In no event and under no legal theory,
154 |       whether in tort (including negligence), contract, or otherwise,
155 |       unless required by applicable law (such as deliberate and grossly
156 |       negligent acts) or agreed to in writing, shall any Contributor be
157 |       liable to You for damages, including any direct, indirect, special,
158 |       incidental, or consequential damages of any character arising as a
159 |       result of this License or out of the use or inability to use the
160 |       Work (including but not limited to damages for loss of goodwill,
161 |       work stoppage, computer failure or malfunction, or any and all
162 |       other commercial damages or losses), even if such Contributor
163 |       has been advised of the possibility of such damages.
164 | 
165 |    9. Accepting Warranty or Additional Liability. While redistributing
166 |       the Work or Derivative Works thereof, You may choose to offer,
167 |       and charge a fee for, acceptance of support, warranty, indemnity,
168 |       or other liability obligations and/or rights consistent with this
169 |       License. However, in accepting such obligations, You may act only
170 |       on Your own behalf and on Your sole responsibility, not on behalf
171 |       of any other Contributor, and only if You agree to indemnify,
172 |       defend, and hold each Contributor harmless for any liability
173 |       incurred by, or claims asserted against, such Contributor by reason
174 |       of your accepting any such warranty or additional liability.
175 | 
176 |    END OF TERMS AND CONDITIONS
177 | 
178 |    APPENDIX: How to apply the Apache License to your work.
179 | 
180 |       To apply the Apache License to your work, attach the following
181 |       boilerplate notice, with the fields enclosed by brackets "{}"
182 |       replaced with your own identifying information. (Don't include
183 |       the brackets!)  The text should be enclosed in the appropriate
184 |       comment syntax for the file format. We also recommend that a
185 |       file or class name and description of purpose be included on the
186 |       same "printed page" as the copyright notice for easier
187 |       identification within third-party archives.
188 | 
189 |    Copyright {yyyy} {name of copyright owner}
190 | 
191 |    Licensed under the Apache License, Version 2.0 (the "License");
192 |    you may not use this file except in compliance with the License.
193 |    You may obtain a copy of the License at
194 | 
195 |        http://www.apache.org/licenses/LICENSE-2.0
196 | 
197 |    Unless required by applicable law or agreed to in writing, software
198 |    distributed under the License is distributed on an "AS IS" BASIS,
199 |    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 |    See the License for the specific language governing permissions and
201 |    limitations under the License.
202 | 
203 | 


--------------------------------------------------------------------------------