diff options
author | cra14 <chandan.rajah2@bskyb.com> | 2013-04-26 13:01:17 +0100 |
---|---|---|
committer | cra14 <chandan.rajah2@bskyb.com> | 2013-04-26 13:01:17 +0100 |
commit | ea9c80374da846edf2a1634a42ccb932838ebd5b (patch) | |
tree | 553c1b8f3df86e3d0e73491464e70cba11c02d1f | |
parent | a9bf735c35b00f81e8bb036735813ff793b46666 (diff) | |
download | SpyGlass-ea9c80374da846edf2a1634a42ccb932838ebd5b.tar.gz SpyGlass-ea9c80374da846edf2a1634a42ccb932838ebd5b.zip |
Updated README file with instructions
-rw-r--r-- | README.md | 205 |
1 files changed, 106 insertions, 99 deletions
@@ -3,107 +3,114 @@ SpyGlass Cascading and Scalding wrapper for HBase with advanced read features +Building +======== -Example -======= - -package parallelai.spyglass.hbase.example - -import org.apache.hadoop.conf.Configuration -import org.apache.hadoop.hbase.HBaseConfiguration -import org.apache.hadoop.hbase.client.HConnectionManager -import org.apache.hadoop.hbase.client.HTable -import org.apache.hadoop.hbase.util.Bytes -import org.apache.log4j.Level -import org.apache.log4j.Logger - -import com.twitter.scalding._ -import com.twitter.scalding.Args - -import parallelai.spyglass.base.JobBase -import parallelai.spyglass.hbase.HBaseSource -import parallelai.spyglass.hbase.HBaseConstants.SourceMode - -class HBaseExample(args: Args) extends JobBase(args) { - - val isDebug: Boolean = args("debug").toBoolean - - if (isDebug) Logger.getRootLogger().setLevel(Level.DEBUG) - - val output = args("output") - - println(output) - - val jobConf = getJobConf - - val quorumNames = "cldmgr.prod.bigdata.bskyb.com:2181" - - case class HBaseTableStore( - conf: Configuration, - quorum: String, - tableName: String) { - - val tableBytes = Bytes.toBytes(tableName) - val connection = HConnectionManager.getConnection(conf) - val maxThreads = conf.getInt("hbase.htable.threads.max", 1) - - conf.set("hbase.zookeeper.quorum", quorumNames); - - val htable = new HTable(HBaseConfiguration.create(conf), tableName) - - } - - val hTableStore = HBaseTableStore(getJobConf, quorumNames, "skybet.test.tbet") - - val hbs2 = new HBaseSource( - "table_name", - "quorum_name:2181", - 'key, - Array("column_family"), - Array('column_name), - sourceMode = SourceMode.GET_LIST, keyList = List("5003914", "5000687", "5004897")) - .read - .write(Tsv(output.format("get_list"))) - - val hbs3 = new HBaseSource( - "table_name", - "quorum_name:2181", - 'key, - Array("column_family"), - Array('column_name), - sourceMode = SourceMode.SCAN_ALL) //, stopKey = "99460693") - .read - .write(Tsv(output.format("scan_all"))) - - val hbs4 = new HBaseSource( - "table_name", - "quorum_name:2181", - 'key, - Array("column_family"), - Array('column_name), - sourceMode = SourceMode.SCAN_RANGE, stopKey = "5003914") - .read - .write(Tsv(output.format("scan_range_to_end"))) + $ mvn clean install -U + + Requires Maven 3.x.x - val hbs5 = new HBaseSource( - "table_name", - "quorum_name:2181", - 'key, - Array("column_family"), - Array('column_name), - sourceMode = SourceMode.SCAN_RANGE, startKey = "5003914") - .read - .write(Tsv(output.format("scan_range_from_start"))) - val hbs6 = new HBaseSource( - "table_name", - "quorum_name:2181", - 'key, - Array("column_family"), - Array('column_name), - sourceMode = SourceMode.SCAN_RANGE, startKey = "5003914", stopKey = "5004897") - .read - .write(Tsv(output.format("scan_range_between"))) +Example +======= -} + package parallelai.spyglass.hbase.example + + import org.apache.hadoop.conf.Configuration + import org.apache.hadoop.hbase.HBaseConfiguration + import org.apache.hadoop.hbase.client.HConnectionManager + import org.apache.hadoop.hbase.client.HTable + import org.apache.hadoop.hbase.util.Bytes + import org.apache.log4j.Level + import org.apache.log4j.Logger + + import com.twitter.scalding._ + import com.twitter.scalding.Args + + import parallelai.spyglass.base.JobBase + import parallelai.spyglass.hbase.HBaseSource + import parallelai.spyglass.hbase.HBaseConstants.SourceMode + + class HBaseExample(args: Args) extends JobBase(args) { + + val isDebug: Boolean = args("debug").toBoolean + + if (isDebug) Logger.getRootLogger().setLevel(Level.DEBUG) + + val output = args("output") + + println(output) + + val jobConf = getJobConf + + val quorumNames = "cldmgr.prod.bigdata.bskyb.com:2181" + + case class HBaseTableStore( + conf: Configuration, + quorum: String, + tableName: String) { + + val tableBytes = Bytes.toBytes(tableName) + val connection = HConnectionManager.getConnection(conf) + val maxThreads = conf.getInt("hbase.htable.threads.max", 1) + + conf.set("hbase.zookeeper.quorum", quorumNames); + + val htable = new HTable(HBaseConfiguration.create(conf), tableName) + + } + + val hTableStore = HBaseTableStore(getJobConf, quorumNames, "skybet.test.tbet") + + val hbs2 = new HBaseSource( + "table_name", + "quorum_name:2181", + 'key, + Array("column_family"), + Array('column_name), + sourceMode = SourceMode.GET_LIST, keyList = List("5003914", "5000687", "5004897")) + .read + .write(Tsv(output.format("get_list"))) + + val hbs3 = new HBaseSource( + "table_name", + "quorum_name:2181", + 'key, + Array("column_family"), + Array('column_name), + sourceMode = SourceMode.SCAN_ALL) //, stopKey = "99460693") + .read + .write(Tsv(output.format("scan_all"))) + + val hbs4 = new HBaseSource( + "table_name", + "quorum_name:2181", + 'key, + Array("column_family"), + Array('column_name), + sourceMode = SourceMode.SCAN_RANGE, stopKey = "5003914") + .read + .write(Tsv(output.format("scan_range_to_end"))) + + val hbs5 = new HBaseSource( + "table_name", + "quorum_name:2181", + 'key, + Array("column_family"), + Array('column_name), + sourceMode = SourceMode.SCAN_RANGE, startKey = "5003914") + .read + .write(Tsv(output.format("scan_range_from_start"))) + + val hbs6 = new HBaseSource( + "table_name", + "quorum_name:2181", + 'key, + Array("column_family"), + Array('column_name), + sourceMode = SourceMode.SCAN_RANGE, startKey = "5003914", stopKey = "5004897") + .read + .write(Tsv(output.format("scan_range_between"))) + + } |