diff options
author | Antonios Chalkiopoulos <Antwnis@gmail.com> | 2014-05-22 22:04:44 +0100 |
---|---|---|
committer | Antonios Chalkiopoulos <Antwnis@gmail.com> | 2014-05-22 22:04:44 +0100 |
commit | 08e00dfce43244ec1edb0e2363a977fea985b454 (patch) | |
tree | 3ef8c08587edd2826c272c1277389bb7427aad66 /src/main/java/parallelai/spyglass/hbase/HBaseInputFormatGranular.java | |
parent | ba87c17eed4e6f2d1e1b1d4644193485aae0bb4e (diff) | |
download | SpyGlass-08e00dfce43244ec1edb0e2363a977fea985b454.tar.gz SpyGlass-08e00dfce43244ec1edb0e2363a977fea985b454.zip |
Releasing 4.3 Spyglass for Scalding (0.9.1) and Scala (2.10)
Diffstat (limited to 'src/main/java/parallelai/spyglass/hbase/HBaseInputFormatGranular.java')
-rw-r--r-- | src/main/java/parallelai/spyglass/hbase/HBaseInputFormatGranular.java | 23 |
1 files changed, 11 insertions, 12 deletions
diff --git a/src/main/java/parallelai/spyglass/hbase/HBaseInputFormatGranular.java b/src/main/java/parallelai/spyglass/hbase/HBaseInputFormatGranular.java index 64effc9..332bbd7 100644 --- a/src/main/java/parallelai/spyglass/hbase/HBaseInputFormatGranular.java +++ b/src/main/java/parallelai/spyglass/hbase/HBaseInputFormatGranular.java @@ -3,52 +3,51 @@ package parallelai.spyglass.hbase; import java.io.IOException; import java.net.InetAddress; import java.util.ArrayList; -import java.util.Collection; import java.util.HashMap; import java.util.List; import java.util.Set; import java.util.TreeSet; -import java.util.UUID; import javax.naming.NamingException; import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; -import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.HConstants; import org.apache.hadoop.hbase.HRegionLocation; import org.apache.hadoop.hbase.HServerAddress; -import org.apache.hadoop.hbase.client.HTable; import org.apache.hadoop.hbase.client.Result; -import org.apache.hadoop.hbase.filter.Filter; import org.apache.hadoop.hbase.io.ImmutableBytesWritable; import org.apache.hadoop.hbase.util.Addressing; import org.apache.hadoop.hbase.util.Bytes; import org.apache.hadoop.hbase.util.Pair; import org.apache.hadoop.hbase.util.Strings; -import org.apache.hadoop.mapred.InputFormat; import org.apache.hadoop.mapred.InputSplit; import org.apache.hadoop.mapred.JobConf; -import org.apache.hadoop.mapred.JobConfigurable; import org.apache.hadoop.mapred.RecordReader; import org.apache.hadoop.mapred.Reporter; import org.apache.hadoop.net.DNS; -import org.apache.hadoop.util.StringUtils; import parallelai.spyglass.hbase.HBaseConstants.SourceMode; +/** + * See HBaseInputFormatRegional first (!) + * + * Now that we know which splits we are interested reading from, we will proceed + * with iterating over the region servers & splits and depending on our Read strategy + * i.e. SCAN_RANGE, GET_LIST , SCAN_ALL we initiate <class>HBaseTableSplitGranular</class> per + * region and split with all the correct parameters. + * + * So all the different <u>strategies</u> are implemented here at a high level + * + */ public class HBaseInputFormatGranular extends HBaseInputFormatBase { private final Log LOG = LogFactory.getLog(HBaseInputFormatGranular.class); - // private String tableName = ""; - private HashMap<InetAddress, String> reverseDNSCacheMap = new HashMap<InetAddress, String>(); private String nameServer = null; - // private Scan scan = null; - @SuppressWarnings("deprecation") @Override public HBaseTableSplitGranular[] getSplits(JobConf job, int numSplits) throws IOException { |