docs-archive/1.10.3/_sources/_api/airflow/contrib/operators/mysql_to_gcs/index.rst.txt

:mod:`airflow.contrib.operators.mysql_to_gcs`
=============================================

.. py:module:: airflow.contrib.operators.mysql_to_gcs







Module Contents
---------------






.. data:: PY3
   

   









.. py:class:: MySqlToGoogleCloudStorageOperator(sql, bucket, filename, schema_filename=None, approx_max_file_size_bytes=1900000000, mysql_conn_id='mysql_default', google_cloud_storage_conn_id='google_cloud_default', schema=None, delegate_to=None, export_format='json', field_delimiter=',', *args, **kwargs)

   Bases::class:`airflow.models.BaseOperator`

   

   Copy data from MySQL to Google cloud storage in JSON or CSV format.

   The JSON data files generated are newline-delimited to enable them to be
   loaded into BigQuery.
   Reference: https://cloud.google.com/bigquery/docs/
   loading-data-cloud-storage-json#limitations

   :param sql: The SQL to execute on the MySQL table.
   :type sql: str
   :param bucket: The bucket to upload to.
   :type bucket: str
   :param filename: The filename to use as the object name when uploading
       to Google cloud storage. A {} should be specified in the filename
       to allow the operator to inject file numbers in cases where the
       file is split due to size.
   :type filename: str
   :param schema_filename: If set, the filename to use as the object name
       when uploading a .json file containing the BigQuery schema fields
       for the table that was dumped from MySQL.
   :type schema_filename: str
   :param approx_max_file_size_bytes: This operator supports the ability
       to split large table dumps into multiple files (see notes in the
       filenamed param docs above). Google cloud storage allows for files
       to be a maximum of 4GB. This param allows developers to specify the
       file size of the splits.
   :type approx_max_file_size_bytes: long
   :param mysql_conn_id: Reference to a specific MySQL hook.
   :type mysql_conn_id: str
   :param google_cloud_storage_conn_id: Reference to a specific Google
       cloud storage hook.
   :type google_cloud_storage_conn_id: str
   :param schema: The schema to use, if any. Should be a list of dict or
       a str. Pass a string if using Jinja template, otherwise, pass a list of
       dict. Examples could be seen: https://cloud.google.com/bigquery/docs
       /schemas#specifying_a_json_schema_file
   :type schema: str or list
   :param delegate_to: The account to impersonate, if any. For this to
       work, the service account making the request must have domain-wide
       delegation enabled.
   :type delegate_to: str
   :param export_format: Desired format of files to be exported.
   :type export_format: str
   :param field_delimiter: The delimiter to be used for CSV files.
   :type field_delimiter: str


   

   

   .. attribute:: template_fields
      :annotation: = ['sql', 'bucket', 'filename', 'schema_filename', 'schema'] 

      



   

   

   .. attribute:: template_ext
      :annotation: = ['.sql'] 

      



   

   

   .. attribute:: ui_color
      :annotation: = #a0e08c 

      



   

   

   

   .. method:: execute(self, context)

      



   

   .. method:: _query_mysql(self)

      
      Queries mysql and returns a cursor to the results.

      



   

   .. method:: _write_local_data_files(self, cursor)

      
      Takes a cursor, and writes results to a local file.

      :return: A dictionary where keys are filenames to be used as object
          names in GCS, and values are file handles to local files that
          contain the data for the GCS objects.

      



   

   .. method:: _configure_csv_file(self, file_handle, schema)

      
      Configure a csv writer with the file_handle and write schema
      as headers for the new file.

      



   

   .. method:: _write_local_schema_file(self, cursor)

      
      Takes a cursor, and writes the BigQuery schema in .json format for the
      results to a local file system.

      :return: A dictionary where key is a filename to be used as an object
          name in GCS, and values are file handles to local files that
          contains the BigQuery schema fields in .json format.

      



   

   .. method:: _upload_to_gcs(self, files_to_upload)

      
      Upload all of the file splits (and optionally the schema .json file) to
      Google cloud storage.

      



   

   .. staticmethod:: _convert_types(schema, col_type_dict, row)

      
      Takes a value from MySQLdb, and converts it to a value that's safe for
      JSON/Google cloud storage/BigQuery. Dates are converted to UTC seconds.
      Decimals are converted to floats. Binary type fields are encoded with base64,
      as imported BYTES data must be base64-encoded according to Bigquery SQL
      date type documentation: https://cloud.google.com/bigquery/data-types

      



   

   .. method:: _get_col_type_dict(self)

      
      Return a dict of column name and column type based on self.schema if not None.

      



   

   .. classmethod:: type_map(cls, mysql_type)

      
      Helper function that maps from MySQL fields to BigQuery fields. Used
      when a schema_filename is set.