apache-airflow-providers-sftp 4.4.0__py3-none-any.whl → 4.5.0__py3-none-any.whl

airflow/providers/sftp/__init__.py

@@ -28,14 +28,16 @@ import packaging.version
 
 __all__ = ["__version__"]
 
-__version__ = "4.4.0"
+__version__ = "4.5.0"
 
 try:
     from airflow import __version__ as airflow_version
 except ImportError:
     from airflow.version import version as airflow_version
 
-if packaging.version.parse(airflow_version) < packaging.version.parse("2.4.0"):
+if packaging.version.parse(packaging.version.parse(airflow_version).base_version) < packaging.version.parse(
+    "2.4.0"
+):
     raise RuntimeError(
         f"The package `apache-airflow-providers-sftp:{__version__}` requires Apache Airflow 2.4.0+"  # NOQA: E501
     )

airflow/providers/sftp/get_provider_info.py

@@ -29,6 +29,7 @@ def get_provider_info():
         "description": "`SSH File Transfer Protocol (SFTP) <https://tools.ietf.org/wg/secsh/draft-ietf-secsh-filexfer/>`__\n",
         "suspended": False,
         "versions": [
+            "4.5.0",
             "4.4.0",
             "4.3.1",
             "4.3.0",

airflow/providers/sftp/operators/sftp.py

@@ -19,10 +19,13 @@
 from __future__ import annotations
 
 import os
+import socket
 import warnings
 from pathlib import Path
 from typing import Any, Sequence
 
+import paramiko
+
 from airflow.exceptions import AirflowException, AirflowProviderDeprecationWarning
 from airflow.models import BaseOperator
 from airflow.providers.sftp.hooks.sftp import SFTPHook
@@ -188,3 +191,82 @@ class SFTPOperator(BaseOperator):
             raise AirflowException(f"Error while transferring {file_msg}, error: {str(e)}")
 
         return self.local_filepath
+
+    def get_openlineage_facets_on_start(self):
+        """
+        This returns OpenLineage datasets in format:
+            input: file://<local_host>/path
+            output: file://<remote_host>:<remote_port>/path.
+        """
+        from openlineage.client.run import Dataset
+
+        from airflow.providers.openlineage.extractors import OperatorLineage
+
+        scheme = "file"
+        local_host = socket.gethostname()
+        try:
+            local_host = socket.gethostbyname(local_host)
+        except Exception as e:
+            self.log.warning(
+                f"Failed to resolve local hostname. Using the hostname got by socket.gethostbyname() without resolution. {e}",  # noqa: E501
+                exc_info=True,
+            )
+
+        hook = self.sftp_hook or self.ssh_hook or SFTPHook(ssh_conn_id=self.ssh_conn_id)
+
+        if self.remote_host is not None:
+            remote_host = self.remote_host
+        else:
+            remote_host = hook.get_connection(hook.ssh_conn_id).host
+
+        try:
+            remote_host = socket.gethostbyname(remote_host)
+        except OSError as e:
+            self.log.warning(
+                f"Failed to resolve remote hostname. Using the provided hostname without resolution. {e}",  # noqa: E501
+                exc_info=True,
+            )
+
+        if hasattr(hook, "port"):
+            remote_port = hook.port
+        elif hasattr(hook, "ssh_hook"):
+            remote_port = hook.ssh_hook.port
+
+        # Since v4.1.0, SFTPOperator accepts both a string (single file) and a list of
+        # strings (multiple files) as local_filepath and remote_filepath, and internally
+        # keeps them as list in both cases. But before 4.1.0, only single string is
+        # allowed. So we consider both cases here for backward compatibility.
+        if isinstance(self.local_filepath, str):
+            local_filepath = [self.local_filepath]
+        else:
+            local_filepath = self.local_filepath
+        if isinstance(self.remote_filepath, str):
+            remote_filepath = [self.remote_filepath]
+        else:
+            remote_filepath = self.remote_filepath
+
+        local_datasets = [
+            Dataset(namespace=self._get_namespace(scheme, local_host, None, path), name=path)
+            for path in local_filepath
+        ]
+        remote_datasets = [
+            Dataset(namespace=self._get_namespace(scheme, remote_host, remote_port, path), name=path)
+            for path in remote_filepath
+        ]
+
+        if self.operation.lower() == SFTPOperation.GET:
+            inputs = remote_datasets
+            outputs = local_datasets
+        else:
+            inputs = local_datasets
+            outputs = remote_datasets
+
+        return OperatorLineage(
+            inputs=inputs,
+            outputs=outputs,
+        )
+
+    def _get_namespace(self, scheme, host, port, path) -> str:
+        port = port or paramiko.config.SSH_PORT
+        authority = f"{host}:{port}"
+        return f"{scheme}://{authority}"

{apache_airflow_providers_sftp-4.4.0.dist-info → apache_airflow_providers_sftp-4.5.0.dist-info}/METADATA

@@ -1,14 +1,14 @@
 Metadata-Version: 2.1
 Name: apache-airflow-providers-sftp
-Version: 4.4.0
+Version: 4.5.0
 Summary: Provider for Apache Airflow. Implements apache-airflow-providers-sftp package
 Home-page: https://airflow.apache.org/
 Download-URL: https://archive.apache.org/dist/airflow/providers
 Author: Apache Software Foundation
 Author-email: dev@airflow.apache.org
 License: Apache License 2.0
-Project-URL: Documentation, https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.4.0/
-Project-URL: Changelog, https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.4.0/changelog.html
+Project-URL: Documentation, https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.5.0/
+Project-URL: Changelog, https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.5.0/changelog.html
 Project-URL: Bug Tracker, https://github.com/apache/airflow/issues
 Project-URL: Source Code, https://github.com/apache/airflow
 Project-URL: Slack Chat, https://s.apache.org/airflow-slack
@@ -33,6 +33,8 @@ License-File: LICENSE
 License-File: NOTICE
 Requires-Dist: apache-airflow-providers-ssh (>=2.1.0)
 Requires-Dist: apache-airflow (>=2.4.0)
+Provides-Extra: openlineage
+Requires-Dist: apache-airflow-providers-openlineage ; extra == 'openlineage'
 Provides-Extra: ssh
 Requires-Dist: apache-airflow-providers-ssh ; extra == 'ssh'
 
@@ -74,7 +76,7 @@ Requires-Dist: apache-airflow-providers-ssh ; extra == 'ssh'
 
 Package ``apache-airflow-providers-sftp``
 
-Release: ``4.4.0``
+Release: ``4.5.0``
 
 
 `SSH File Transfer Protocol (SFTP) <https://tools.ietf.org/wg/secsh/draft-ietf-secsh-filexfer/>`__
@@ -87,7 +89,7 @@ This is a provider package for ``sftp`` provider. All classes for this provider
 are in ``airflow.providers.sftp`` python package.
 
 You can find package information and changelog for the provider
-in the `documentation <https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.4.0/>`_.
+in the `documentation <https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.5.0/>`_.
 
 
 Installation
@@ -119,14 +121,15 @@ You can install such cross-provider dependencies when installing from PyPI. For
 
 .. code-block:: bash
 
-    pip install apache-airflow-providers-sftp[ssh]
+    pip install apache-airflow-providers-sftp[openlineage]
 
 
-==============================================================================================  =======
-Dependent package                                                                               Extra
-==============================================================================================  =======
-`apache-airflow-providers-ssh <https://airflow.apache.org/docs/apache-airflow-providers-ssh>`_  ``ssh``
-==============================================================================================  =======
+==============================================================================================================  ===============
+Dependent package                                                                                               Extra
+==============================================================================================================  ===============
+`apache-airflow-providers-openlineage <https://airflow.apache.org/docs/apache-airflow-providers-openlineage>`_  ``openlineage``
+`apache-airflow-providers-ssh <https://airflow.apache.org/docs/apache-airflow-providers-ssh>`_                  ``ssh``
+==============================================================================================================  ===============
 
 The changelog for the provider package can be found in the
-`changelog <https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.4.0/changelog.html>`_.
+`changelog <https://airflow.apache.org/docs/apache-airflow-providers-sftp/4.5.0/changelog.html>`_.

{apache_airflow_providers_sftp-4.4.0.dist-info → apache_airflow_providers_sftp-4.5.0.dist-info}/RECORD

@@ -1,18 +1,18 @@
-airflow/providers/sftp/__init__.py,sha256=qxVlMGng2CgYmbRMB_cIdyMsIEXZ2Qfvt_7gR6c6WPU,1529
-airflow/providers/sftp/get_provider_info.py,sha256=qz_B4aZUVtA0lubmQjGBLMwShbqXKuxSDlxSnRBmxak,3389
+airflow/providers/sftp/__init__.py,sha256=mXow8LvnjpNw3VDueC-e8n8bgQz2PUD-x-9WmvEw3Ss,1573
+airflow/providers/sftp/get_provider_info.py,sha256=kVwrdxtNsJvmNDcdx2y8PmboiiyGXFB9dO14NY2HY28,3410
 airflow/providers/sftp/decorators/__init__.py,sha256=9hdXHABrVpkbpjZgUft39kOFL2xSGeG4GEua0Hmelus,785
 airflow/providers/sftp/decorators/sensors/__init__.py,sha256=9hdXHABrVpkbpjZgUft39kOFL2xSGeG4GEua0Hmelus,785
 airflow/providers/sftp/decorators/sensors/sftp.py,sha256=dRzXMgWf5SgGCQ2gOSvpzfJx8V9t98EorB0QZYccb94,2862
 airflow/providers/sftp/hooks/__init__.py,sha256=9hdXHABrVpkbpjZgUft39kOFL2xSGeG4GEua0Hmelus,785
 airflow/providers/sftp/hooks/sftp.py,sha256=CHKPBzMr7oSW9nBQ8sExdD9zi50aUGpjdnebiW10rzU,14745
 airflow/providers/sftp/operators/__init__.py,sha256=9hdXHABrVpkbpjZgUft39kOFL2xSGeG4GEua0Hmelus,785
-airflow/providers/sftp/operators/sftp.py,sha256=qmKGkba70_kll05RSkeSL_Dyo1fWFaPvpsQBX38N4H4,8458
+airflow/providers/sftp/operators/sftp.py,sha256=Mp5nWEZa9SdLCO-QahaDJ0CnT9y_t3zRlGBAkrblFrA,11475
 airflow/providers/sftp/sensors/__init__.py,sha256=9hdXHABrVpkbpjZgUft39kOFL2xSGeG4GEua0Hmelus,785
 airflow/providers/sftp/sensors/sftp.py,sha256=tSN0e8cRtIuTxHDce9DaBVs2qadKLSl49dwpo-qcfUw,4410
-apache_airflow_providers_sftp-4.4.0.dist-info/LICENSE,sha256=gXPVwptPlW1TJ4HSuG5OMPg-a3h43OGMkZRR1rpwfJA,10850
-apache_airflow_providers_sftp-4.4.0.dist-info/METADATA,sha256=Rh15DlgYywdQg_4GLpV9vBph45I5n-RTEUD3h917O70,5621
-apache_airflow_providers_sftp-4.4.0.dist-info/NOTICE,sha256=m-6s2XynUxVSUIxO4rVablAZCvFq-wmLrqV91DotRBw,240
-apache_airflow_providers_sftp-4.4.0.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
-apache_airflow_providers_sftp-4.4.0.dist-info/entry_points.txt,sha256=aiWTzXS-mN60ugZ7sL3xJpUvaMjF5dXfF65JUMVaBcs,101
-apache_airflow_providers_sftp-4.4.0.dist-info/top_level.txt,sha256=OeMVH5md7fr2QQWpnZoOWWxWO-0WH1IP70lpTVwopPg,8
-apache_airflow_providers_sftp-4.4.0.dist-info/RECORD,,
+apache_airflow_providers_sftp-4.5.0.dist-info/LICENSE,sha256=gXPVwptPlW1TJ4HSuG5OMPg-a3h43OGMkZRR1rpwfJA,10850
+apache_airflow_providers_sftp-4.5.0.dist-info/METADATA,sha256=U6wt--5ZRLaKaoJAgW04GcQQk3cqJ5E3MwxX2B3KeYc,5966
+apache_airflow_providers_sftp-4.5.0.dist-info/NOTICE,sha256=m-6s2XynUxVSUIxO4rVablAZCvFq-wmLrqV91DotRBw,240
+apache_airflow_providers_sftp-4.5.0.dist-info/WHEEL,sha256=AtBG6SXL3KF_v0NxLf0ehyVOh0cold-JbJYXNGorC6Q,92
+apache_airflow_providers_sftp-4.5.0.dist-info/entry_points.txt,sha256=aiWTzXS-mN60ugZ7sL3xJpUvaMjF5dXfF65JUMVaBcs,101
+apache_airflow_providers_sftp-4.5.0.dist-info/top_level.txt,sha256=OeMVH5md7fr2QQWpnZoOWWxWO-0WH1IP70lpTVwopPg,8
+apache_airflow_providers_sftp-4.5.0.dist-info/RECORD,,

{apache_airflow_providers_sftp-4.4.0.dist-info → apache_airflow_providers_sftp-4.5.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.40.0)
+Generator: bdist_wheel (0.41.0)
 Root-Is-Purelib: true
 Tag: py3-none-any