Merge pull request #59 from data-integrations/feature_release/CDAP-14442-remove-format-dependencies

CDAP-14442 remove avro, parquet, and orc dependencies

Author: albertshau

pom.xml

@@ -57,7 +57,7 @@
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
     <cdap.version>5.1.0</cdap.version>
-    <hydrator.version>2.1.0</hydrator.version>
+    <hydrator.version>2.1.1-SNAPSHOT</hydrator.version>
     <guava.version>20.0</guava.version>
     <slf4j.version>1.7.5</slf4j.version>
     <junit.version>4.12</junit.version>
@@ -67,11 +67,9 @@
     <google.cloud.spanner.version>0.53.0-beta</google.cloud.spanner.version>
     <spark.version>1.6.1</spark.version>
     <google.cloud.speech.version>0.54.0-beta</google.cloud.speech.version>
-    <parquet.avro.version>1.8.1</parquet.avro.version>
     <google.protobuf.java.version>3.4.0</google.protobuf.java.version>
     <google.cloud.pubsub.version>1.36.0</google.cloud.pubsub.version>
-    <orc.mapreduce.version>1.1.0</orc.mapreduce.version>
-    <avro.mapred.version>1.7.7</avro.mapred.version>
+    <avro.version>1.7.7</avro.version>
     <jackson.core.version>2.8.11.1</jackson.core.version>
   </properties>
 
@@ -97,7 +95,7 @@
     <dependency>
       <groupId>org.apache.avro</groupId>
       <artifactId>avro</artifactId>
-      <version>1.7.7</version>
+      <version>${avro.version}</version>
     </dependency>
     <dependency>
       <groupId>co.cask.cdap</groupId>
@@ -265,17 +263,6 @@
       <artifactId>google-cloud-speech</artifactId>
       <version>${google.cloud.speech.version}</version>
     </dependency>
-    <dependency>
-      <groupId>org.apache.parquet</groupId>
-      <artifactId>parquet-avro</artifactId>
-      <version>${parquet.avro.version}</version>
-      <exclusions>
-        <exclusion>
-          <groupId>org.apache.avro</groupId>
-          <artifactId>avro</artifactId>
-        </exclusion>
-      </exclusions>
-    </dependency>
     <dependency>
       <groupId>com.google.protobuf</groupId>
       <artifactId>protobuf-java</artifactId>
@@ -286,34 +273,11 @@
       <artifactId>google-cloud-pubsub</artifactId>
       <version>${google.cloud.pubsub.version}</version>
     </dependency>
-    <dependency>
-      <groupId>org.apache.orc</groupId>
-      <artifactId>orc-mapreduce</artifactId>
-      <version>${orc.mapreduce.version}</version>
-      <exclusions>
-        <exclusion>
-          <groupId>org.apache.hadoop</groupId>
-          <artifactId>hadoop-hdfs</artifactId>
-        </exclusion>
-        <exclusion>
-          <groupId>org.apache.hadoop</groupId>
-          <artifactId>hadoop-common</artifactId>
-        </exclusion>
-        <exclusion>
-          <groupId>org.apache.hadoop</groupId>
-          <artifactId>hadoop-mapreduce-client-core</artifactId>
-        </exclusion>
-        <exclusion>
-          <groupId>org.apache.hive</groupId>
-          <artifactId>hive-storage-api</artifactId>
-        </exclusion>
-      </exclusions>
-    </dependency>
     <dependency>
       <groupId>org.apache.avro</groupId>
       <artifactId>avro-mapred</artifactId>
       <classifier>hadoop2</classifier>
-      <version>${avro.mapred.version}</version>
+      <version>${avro.version}</version>
     </dependency>
     <dependency>
       <groupId>com.fasterxml.jackson.core</groupId>
@@ -524,12 +488,7 @@
             <!--Only @Plugin classes in the export packages will be included as plugin-->
             <_exportcontents>
               co.cask.gcp.*;
-              co.cask.hydrator.format.*;
               com.google.cloud.hadoop.*;
-              org.apache.avro.mapred.*;
-              org.apache.avro.mapreduce;
-              org.apache.parquet.avro.*;
-              org.apache.parquet.hadoop.*;
               org.apache.spark.streaming.pubsub*;
             </_exportcontents>
           </instructions>

src/main/java/co/cask/gcp/bigquery/BigQuerySource.java

@@ -165,16 +165,16 @@ public void onRunFinish(boolean succeeded, BatchSourceContext context) {
   @Path("getSchema")
   public Schema getSchema(BigQuerySourceConfig request) throws Exception {
     String dataset = request.getDataset();
-    String table = request.getTable();
+    String tableName = request.getTable();
     String project = request.getDatasetProject();
-    Table bqTable = BigQueryUtils.getBigQueryTable(request.getServiceAccountFilePath(), project, dataset, table);
+    Table table = BigQueryUtils.getBigQueryTable(request.getServiceAccountFilePath(), project, dataset, tableName);
     if (table == null) {
       // Table does not exist
       throw new IllegalArgumentException(String.format("BigQuery table '%s:%s.%s' does not exist",
-                                                       project, dataset, table));
+                                                       project, dataset, tableName));
     }
 
-    com.google.cloud.bigquery.Schema bgSchema = bqTable.getDefinition().getSchema();
+    com.google.cloud.bigquery.Schema bgSchema = table.getDefinition().getSchema();
     if (bgSchema == null) {
       throw new IllegalArgumentException(String.format("Cannot read from table '%s:%s.%s' because it has no schema.",
                                                        project, dataset, table));
@@ -195,7 +195,7 @@ private void validateOutputSchema() throws IOException {
     if (table == null) {
       // Table does not exist
       throw new IllegalArgumentException(String.format("BigQuery table '%s:%s.%s' does not exist.",
-                                                       project, dataset, table));
+                                                       project, dataset, tableName));
     }
 
     com.google.cloud.bigquery.Schema bgSchema = table.getDefinition().getSchema();

src/main/java/co/cask/gcp/spanner/sink/SpannerSink.java

@@ -42,11 +42,11 @@
 import com.google.cloud.spanner.Spanner;
 import com.google.cloud.spanner.SpannerException;
 import com.google.cloud.spanner.Statement;
+import com.google.common.base.Strings;
 import com.google.spanner.admin.database.v1.CreateDatabaseMetadata;
 import com.google.spanner.admin.database.v1.UpdateDatabaseDdlMetadata;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.io.NullWritable;
-import org.apache.parquet.Strings;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;