airflow-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] Fokko closed pull request #3898: [AIRFLOW-3059] PostgresToGCS Log the number of rows read
Date Sat, 15 Sep 2018 21:06:43 GMT
Fokko closed pull request #3898: [AIRFLOW-3059] PostgresToGCS Log the number of rows read
URL: https://github.com/apache/incubator-airflow/pull/3898
 
 
   

This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:

As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):

diff --git a/airflow/contrib/operators/postgres_to_gcs_operator.py b/airflow/contrib/operators/postgres_to_gcs_operator.py
index 850d858f94..78da78ee2f 100644
--- a/airflow/contrib/operators/postgres_to_gcs_operator.py
+++ b/airflow/contrib/operators/postgres_to_gcs_operator.py
@@ -133,28 +133,38 @@ def _write_local_data_files(self, cursor):
             contain the data for the GCS objects.
         """
         schema = list(map(lambda schema_tuple: schema_tuple[0], cursor.description))
-        file_no = 0
-        tmp_file_handle = NamedTemporaryFile(delete=True)
-        tmp_file_handles = {self.filename.format(file_no): tmp_file_handle}
-
-        for row in cursor:
-            # Convert datetime objects to utc seconds, and decimals to floats
-            row = map(self.convert_types, row)
-            row_dict = dict(zip(schema, row))
-
-            s = json.dumps(row_dict, sort_keys=True)
-            if PY3:
-                s = s.encode('utf-8')
-            tmp_file_handle.write(s)
-
-            # Append newline to make dumps BigQuery compatible.
-            tmp_file_handle.write(b'\n')
-
-            # Stop if the file exceeds the file size limit.
-            if tmp_file_handle.tell() >= self.approx_max_file_size_bytes:
-                file_no += 1
-                tmp_file_handle = NamedTemporaryFile(delete=True)
-                tmp_file_handles[self.filename.format(file_no)] = tmp_file_handle
+        tmp_file_handles = {}
+        row_no = 0
+
+        def _create_new_file():
+            handle = NamedTemporaryFile(delete=True)
+            filename = self.filename.format(len(tmp_file_handles))
+            tmp_file_handles[filename] = handle
+            return handle
+
+        # Don't create a file if there is nothing to write
+        if cursor.rowcount > 0:
+            tmp_file_handle = _create_new_file()
+
+            for row in cursor:
+                # Convert datetime objects to utc seconds, and decimals to floats
+                row = map(self.convert_types, row)
+                row_dict = dict(zip(schema, row))
+
+                s = json.dumps(row_dict, sort_keys=True)
+                if PY3:
+                    s = s.encode('utf-8')
+                tmp_file_handle.write(s)
+
+                # Append newline to make dumps BigQuery compatible.
+                tmp_file_handle.write(b'\n')
+
+                # Stop if the file exceeds the file size limit.
+                if tmp_file_handle.tell() >= self.approx_max_file_size_bytes:
+                    tmp_file_handle = _create_new_file()
+                row_no += 1
+
+        self.log.info('Received %s rows over %s files', row_no, len(tmp_file_handles))
 
         return tmp_file_handles
 


 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

Mime
View raw message