Merge pull request #46 from data-integrations/feature_release/CDAP-14481-add-get-schema-button

CDAP-14481 add get schema button for gcs file source

Author: albertshau

docs/BigQueryTable-batchsource.md

@@ -21,7 +21,7 @@ must be readable by all users running the job.
 
 Properties
 ----------
-**Reference Name:** Name used to uniquely identify this sink for lineage, annotating metadata, etc.
+**Reference Name:** Name used to uniquely identify this source for lineage, annotating metadata, etc.
 
 **Project ID**: Google Cloud Project ID, which uniquely identifies a project.
 It can be found on the Dashboard in the Google Cloud Platform Console.

docs/GCSFile-batchsource.md

@@ -23,7 +23,7 @@ must be readable by all users running the job.
 
 Properties
 ----------
-**Reference Name:** Name used to uniquely identify this sink for lineage, annotating metadata, etc.
+**Reference Name:** Name used to uniquely identify this source for lineage, annotating metadata, etc.
 
 **Project ID**: Google Cloud Project ID, which uniquely identifies a project.
 It can be found on the Dashboard in the Google Cloud Platform Console.

docs/Spanner-batchsource.md

@@ -21,7 +21,7 @@ must be readable by all users running the job.
 
 Properties
 ----------
-**Reference Name:** Name used to uniquely identify this sink for lineage, annotating metadata, etc.
+**Reference Name:** Name used to uniquely identify this source for lineage, annotating metadata, etc.
 
 **Project ID**: Google Cloud Project ID, which uniquely identifies a project.
 It can be found on the Dashboard in the Google Cloud Platform Console.

src/main/java/co/cask/gcp/gcs/source/GCSSource.java

@@ -21,6 +21,7 @@
 import co.cask.cdap.api.annotation.Name;
 import co.cask.cdap.api.annotation.Plugin;
 import co.cask.cdap.api.data.schema.Schema;
+import co.cask.cdap.api.plugin.EndpointPluginContext;
 import co.cask.cdap.etl.api.PipelineConfigurer;
 import co.cask.cdap.etl.api.batch.BatchSource;
 import co.cask.cdap.etl.api.batch.BatchSourceContext;
@@ -41,6 +42,7 @@
 import java.util.Map;
 import java.util.regex.Pattern;
 import javax.annotation.Nullable;
+import javax.ws.rs.Path;
 
 /**
  * Class description here.
@@ -87,6 +89,23 @@ protected void recordLineage(LineageRecorder lineageRecorder, List<String> outpu
     lineageRecorder.recordRead("Read", "Read from Google Cloud Storage.", outputFields);
   }
 
+  /**
+   * Endpoint method to get the output schema of a source.
+   *
+   * @param config configuration for the source
+   * @param pluginContext context to create plugins
+   * @return schema of fields
+   */
+  @Path("getSchema")
+  public Schema getSchema(GCSSourceConfig config, EndpointPluginContext pluginContext) {
+    FileFormat fileFormat = config.getFormat();
+    if (fileFormat == null) {
+      return config.getSchema();
+    }
+    Schema schema = fileFormat.getSchema(config.getPathField());
+    return schema == null ? config.getSchema() : schema;
+  }
+
   /**
    * Config for the plugin.
    */

widgets/GCSFile-batchsource.json

@@ -47,6 +47,12 @@
               "tsv"
             ],
             "default": "text"
+          },
+          "plugin-function": {
+            "method": "POST",
+            "widget": "outputSchema",
+            "output-property": "schema",
+            "plugin-method": "getSchema"
           }
         },
         {