BigQuery: Add 'QueryJob.estimated_bytes_processed' property

bigquery/google/cloud/bigquery/job.py

@@ -500,6 +500,10 @@ def _get_resource_config(cls, resource):
                            '["configuration"]["%s"]' % cls._JOB_TYPE)
         return job_id, resource['configuration']
 
+    def _build_resource(self):
+        """Helper:  Generate a resource for :meth:`_begin`."""
+        raise NotImplementedError("Abstract")
+
     def _begin(self, client=None, retry=DEFAULT_RETRY):
         """API call:  begin the job via a POST request
 
@@ -1237,7 +1241,7 @@ def output_rows(self):
             return int(statistics['load']['outputRows'])
 
     def _build_resource(self):
-        """Generate a resource for :meth:`begin`."""
+        """Generate a resource for :meth:`_begin`."""
         configuration = self._configuration.to_api_repr()
         if self.source_uris is not None:
             _helpers._set_sub_prop(
@@ -1413,7 +1417,7 @@ def destination_encryption_configuration(self):
         return self._configuration.destination_encryption_configuration
 
     def _build_resource(self):
-        """Generate a resource for :meth:`begin`."""
+        """Generate a resource for :meth:`_begin`."""
 
         source_refs = [{
             'projectId': table.project,
@@ -1631,7 +1635,7 @@ def destination_uri_file_counts(self):
         return None
 
     def _build_resource(self):
-        """Generate a resource for :meth:`begin`."""
+        """Generate a resource for :meth:`_begin`."""
 
         source_ref = {
             'projectId': self.source.project,
@@ -2202,7 +2206,7 @@ def schema_update_options(self):
         return self._configuration.schema_update_options
 
     def _build_resource(self):
-        """Generate a resource for :meth:`begin`."""
+        """Generate a resource for :meth:`_begin`."""
         configuration = self._configuration.to_api_repr()
 
         resource = {
@@ -2437,6 +2441,22 @@ def undeclared_query_parameters(self):
 
         return parameters
 
+    @property
+    def estimated_bytes_processed(self):
+        """Return the estimated number of bytes processed by the query.
+
+        See:
+        https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#statistics.query.estimatedBytesProcessed
+
+        :rtype: int or None
+        :returns: number of DML rows affected by the job, or None if job is not
+                  yet complete.
+        """
+        result = self._job_statistics().get('estimatedBytesProcessed')
+        if result is not None:
+            result = int(result)
+        return result
+
     def done(self, retry=DEFAULT_RETRY):
         """Refresh the job and checks if it is complete.