Changeset 31360 for other-projects/hathitrust/wcsa

Timestamp:

2017-01-26T23:50:19+13:00 (7 years ago)

Author:

davidb

Message:

Seems to be Text class not a String class coming out of the seuquenceFiles

File:

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

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

@@ -2 +2 @@
 
 import java.io.IOException;
+
+import org.apache.hadoop.io.Text;
 import org.apache.spark.api.java.function.Function;
 import org.json.JSONObject;
 
-class PerVolumeCatalogLangSequenceFileMap implements Function<String, String>
+class PerVolumeCatalogLangSequenceFileMap implements Function<Text, String>
 {
     private static final long serialVersionUID = 1L;
@@ -22 +24 @@
     }
     
-    public String call(String json_text) throws IOException
+    public String call(Text json_text) throws IOException
     {
         String catalog_lang = null;
          
         try {
-            JSONObject extracted_feature_record  = new JSONObject(json_text);
+            JSONObject extracted_feature_record  = new JSONObject(json_text.toString());
 
             String volume_id = extracted_feature_record.getString("id");