Changeset 31361

Timestamp:

2017-01-27T10:26:16+13:00 (7 years ago)

Author:

davidb

Message:

Change from String to Text

File:

• other-projects/hathitrust/wcsa/extracted-features-solr/trunk/solr-ingest/src/main/java/org/hathitrust/extractedfeatures/ProcessForCatalogLangCount.java (modified) (2 diffs)

other-projects/hathitrust/wcsa/extracted-features-solr/trunk/solr-ingest/src/main/java/org/hathitrust/extractedfeatures/ProcessForCatalogLangCount.java

@@ -7 +7 @@
 import java.io.Serializable;
 import org.apache.commons.cli.*;
-
+import org.apache.hadoop.io.Text;
 import org.apache.spark.api.java.*;
 import org.apache.spark.api.java.function.Function2;
@@ -122 +122 @@
         String packed_sequence_path = "hdfs:///user/capitanu/data/packed-ef";
 
-        JavaPairRDD<String, String> inputRdd = jsc.sequenceFile(packed_sequence_path, String.class, String.class);
-        JavaRDD<String> jsonTextRdd = inputRdd.map(Tuple2::_2);
+        JavaPairRDD<String, Text> inputRdd = jsc.sequenceFile(packed_sequence_path, String.class, Text.class);
+        JavaRDD<Text> jsonTextRdd = inputRdd.map(Tuple2::_2);
 
         /*