apache-airflow-providers-http 4.13.3__tar.gz → 5.0.0__tar.gz

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: apache-airflow-providers-http
-Version: 4.13.3
+Version: 5.0.0
 Summary: Provider package apache-airflow-providers-http for Apache Airflow
 Keywords: airflow-provider,http,airflow,integration
 Author-email: Apache Software Foundation <dev@airflow.apache.org>
@@ -20,17 +20,17 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: System :: Monitoring
-Requires-Dist: aiohttp>=3.9.2,<3.11.0
-Requires-Dist: apache-airflow>=2.8.0
+Requires-Dist: aiohttp>=3.9.2,!=3.11.0
+Requires-Dist: apache-airflow>=2.9.0
 Requires-Dist: asgiref>=2.3.0
 Requires-Dist: requests-toolbelt>=0.4.0
 Requires-Dist: requests>=2.27.0,<3
 Project-URL: Bug Tracker, https://github.com/apache/airflow/issues
-Project-URL: Changelog, https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3/changelog.html
-Project-URL: Documentation, https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3
+Project-URL: Changelog, https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0/changelog.html
+Project-URL: Documentation, https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0
 Project-URL: Slack Chat, https://s.apache.org/airflow-slack
 Project-URL: Source Code, https://github.com/apache/airflow
-Project-URL: Twitter, https://twitter.com/ApacheAirflow
+Project-URL: Twitter, https://x.com/ApacheAirflow
 Project-URL: YouTube, https://www.youtube.com/channel/UCSXwxpWZQ7XZ1WL3wqevChA/
 
 
@@ -77,7 +77,7 @@ Project-URL: YouTube, https://www.youtube.com/channel/UCSXwxpWZQ7XZ1WL3wqevChA/
 
 Package ``apache-airflow-providers-http``
 
-Release: ``4.13.3``
+Release: ``5.0.0``
 
 
 `Hypertext Transfer Protocol (HTTP) <https://www.w3.org/Protocols/>`__
@@ -90,7 +90,7 @@ This is a provider package for ``http`` provider. All classes for this provider
 are in ``airflow.providers.http`` python package.
 
 You can find package information and changelog for the provider
-in the `documentation <https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3/>`_.
+in the `documentation <https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0/>`_.
 
 Installation
 ------------
@@ -104,15 +104,15 @@ The package supports the following python versions: 3.9,3.10,3.11,3.12
 Requirements
 ------------
 
-=====================  ===================
+=====================  ====================
 PIP package            Version required
-=====================  ===================
-``apache-airflow``     ``>=2.8.0``
+=====================  ====================
+``apache-airflow``     ``>=2.9.0``
 ``requests``           ``>=2.27.0,<3``
 ``requests-toolbelt``  ``>=0.4.0``
-``aiohttp``            ``<3.11.0,>=3.9.2``
+``aiohttp``            ``!=3.11.0,>=3.9.2``
 ``asgiref``            ``>=2.3.0``
-=====================  ===================
+=====================  ====================
 
 The changelog for the provider package can be found in the
-`changelog <https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3/changelog.html>`_.
+`changelog <https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0/changelog.html>`_.

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/README.rst

@@ -42,7 +42,7 @@
 
 Package ``apache-airflow-providers-http``
 
-Release: ``4.13.3``
+Release: ``5.0.0``
 
 
 `Hypertext Transfer Protocol (HTTP) <https://www.w3.org/Protocols/>`__
@@ -55,7 +55,7 @@ This is a provider package for ``http`` provider. All classes for this provider
 are in ``airflow.providers.http`` python package.
 
 You can find package information and changelog for the provider
-in the `documentation <https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3/>`_.
+in the `documentation <https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0/>`_.
 
 Installation
 ------------
@@ -69,15 +69,15 @@ The package supports the following python versions: 3.9,3.10,3.11,3.12
 Requirements
 ------------
 
-=====================  ===================
+=====================  ====================
 PIP package            Version required
-=====================  ===================
-``apache-airflow``     ``>=2.8.0``
+=====================  ====================
+``apache-airflow``     ``>=2.9.0``
 ``requests``           ``>=2.27.0,<3``
 ``requests-toolbelt``  ``>=0.4.0``
-``aiohttp``            ``<3.11.0,>=3.9.2``
+``aiohttp``            ``!=3.11.0,>=3.9.2``
 ``asgiref``            ``>=2.3.0``
-=====================  ===================
+=====================  ====================
 
 The changelog for the provider package can be found in the
-`changelog <https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3/changelog.html>`_.
+`changelog <https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0/changelog.html>`_.

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/airflow/providers/http/__init__.py

@@ -29,11 +29,11 @@ from airflow import __version__ as airflow_version
 
 __all__ = ["__version__"]
 
-__version__ = "4.13.3"
+__version__ = "5.0.0"
 
 if packaging.version.parse(packaging.version.parse(airflow_version).base_version) < packaging.version.parse(
-    "2.8.0"
+    "2.9.0"
 ):
     raise RuntimeError(
-        f"The package `apache-airflow-providers-http:{__version__}` needs Apache Airflow 2.8.0+"
+        f"The package `apache-airflow-providers-http:{__version__}` needs Apache Airflow 2.9.0+"
     )

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/airflow/providers/http/get_provider_info.py

@@ -28,8 +28,9 @@ def get_provider_info():
         "name": "Hypertext Transfer Protocol (HTTP)",
         "description": "`Hypertext Transfer Protocol (HTTP) <https://www.w3.org/Protocols/>`__\n",
         "state": "ready",
-        "source-date-epoch": 1731570291,
+        "source-date-epoch": 1734534857,
         "versions": [
+            "5.0.0",
             "4.13.3",
             "4.13.2",
             "4.13.1",
@@ -68,10 +69,10 @@ def get_provider_info():
             "1.0.0",
         ],
         "dependencies": [
-            "apache-airflow>=2.8.0",
+            "apache-airflow>=2.9.0",
             "requests>=2.27.0,<3",
             "requests-toolbelt>=0.4.0",
-            "aiohttp>=3.9.2,<3.11.0",
+            "aiohttp>=3.9.2,!=3.11.0",
             "asgiref>=2.3.0",
         ],
         "integrations": [

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/airflow/providers/http/hooks/http.py

@@ -19,6 +19,7 @@ from __future__ import annotations
 
 import asyncio
 from typing import TYPE_CHECKING, Any, Callable
+from urllib.parse import urlparse
 
 import aiohttp
 import requests
@@ -34,6 +35,7 @@ from airflow.hooks.base import BaseHook
 
 if TYPE_CHECKING:
     from aiohttp.client_reqrep import ClientResponse
+    from requests.adapters import HTTPAdapter
 
     from airflow.models import Connection
 
@@ -54,6 +56,7 @@ class HttpHook(BaseHook):
         API url i.e https://www.google.com/ and optional authentication credentials. Default
         headers can also be specified in the Extra field in json format.
     :param auth_type: The auth type for the service
+    :param adapter: An optional instance of `requests.adapters.HTTPAdapter` to mount for the session.
     :param tcp_keep_alive: Enable TCP Keep Alive for the connection.
     :param tcp_keep_alive_idle: The TCP Keep Alive Idle parameter (corresponds to ``socket.TCP_KEEPIDLE``).
     :param tcp_keep_alive_count: The TCP Keep Alive count parameter (corresponds to ``socket.TCP_KEEPCNT``)
@@ -76,6 +79,7 @@ class HttpHook(BaseHook):
         tcp_keep_alive_idle: int = 120,
         tcp_keep_alive_count: int = 20,
         tcp_keep_alive_interval: int = 30,
+        adapter: HTTPAdapter | None = None,
     ) -> None:
         super().__init__()
         self.http_conn_id = http_conn_id
@@ -83,10 +87,17 @@ class HttpHook(BaseHook):
         self.base_url: str = ""
         self._retry_obj: Callable[..., Any]
         self._auth_type: Any = auth_type
-        self.tcp_keep_alive = tcp_keep_alive
-        self.keep_alive_idle = tcp_keep_alive_idle
-        self.keep_alive_count = tcp_keep_alive_count
-        self.keep_alive_interval = tcp_keep_alive_interval
+
+        # If no adapter is provided, use TCPKeepAliveAdapter (default behavior)
+        self.adapter = adapter
+        if tcp_keep_alive and adapter is None:
+            self.keep_alive_adapter = TCPKeepAliveAdapter(
+                idle=tcp_keep_alive_idle,
+                count=tcp_keep_alive_count,
+                interval=tcp_keep_alive_interval,
+            )
+        else:
+            self.keep_alive_adapter = None
 
     @property
     def auth_type(self):
@@ -102,47 +113,76 @@ class HttpHook(BaseHook):
         """
         Create a Requests HTTP session.
 
-        :param headers: additional headers to be passed through as a dictionary
+        :param headers: Additional headers to be passed through as a dictionary.
+        :return: A configured requests.Session object.
         """
         session = requests.Session()
-
-        if self.http_conn_id:
-            conn = self.get_connection(self.http_conn_id)
-
-            if conn.host and "://" in conn.host:
-                self.base_url = conn.host
-            else:
-                # schema defaults to HTTP
-                schema = conn.schema if conn.schema else "http"
-                host = conn.host if conn.host else ""
-                self.base_url = f"{schema}://{host}"
-
-            if conn.port:
-                self.base_url += f":{conn.port}"
-            if conn.login:
-                session.auth = self.auth_type(conn.login, conn.password)
-            elif self._auth_type:
-                session.auth = self.auth_type()
-            if conn.extra:
-                extra = conn.extra_dejson
-                extra.pop(
-                    "timeout", None
-                )  # ignore this as timeout is only accepted in request method of Session
-                extra.pop("allow_redirects", None)  # ignore this as only max_redirects is accepted in Session
-                session.proxies = extra.pop("proxies", extra.pop("proxy", {}))
-                session.stream = extra.pop("stream", False)
-                session.verify = extra.pop("verify", extra.pop("verify_ssl", True))
-                session.cert = extra.pop("cert", None)
-                session.max_redirects = extra.pop("max_redirects", DEFAULT_REDIRECT_LIMIT)
-                session.trust_env = extra.pop("trust_env", True)
-
-                try:
-                    session.headers.update(extra)
-                except TypeError:
-                    self.log.warning("Connection to %s has invalid extra field.", conn.host)
+        connection = self.get_connection(self.http_conn_id)
+        self._set_base_url(connection)
+        session = self._configure_session_from_auth(session, connection)
+        if connection.extra:
+            session = self._configure_session_from_extra(session, connection)
+        session = self._configure_session_from_mount_adapters(session)
         if headers:
             session.headers.update(headers)
+        return session
+
+    def _set_base_url(self, connection: Connection) -> None:
+        host = connection.host or ""
+        schema = connection.schema or "http"
+        # RFC 3986 (https://www.rfc-editor.org/rfc/rfc3986.html#page-16)
+        if "://" in host:
+            self.base_url = host
+        else:
+            self.base_url = f"{schema}://{host}" if host else f"{schema}://"
+            if connection.port:
+                self.base_url = f"{self.base_url}:{connection.port}"
+        parsed = urlparse(self.base_url)
+        if not parsed.scheme:
+            raise ValueError(f"Invalid base URL: Missing scheme in {self.base_url}")
+
+    def _configure_session_from_auth(
+        self, session: requests.Session, connection: Connection
+    ) -> requests.Session:
+        session.auth = self._extract_auth(connection)
+        return session
+
+    def _extract_auth(self, connection: Connection) -> Any | None:
+        if connection.login:
+            return self.auth_type(connection.login, connection.password)
+        elif self._auth_type:
+            return self.auth_type()
+        return None
+
+    def _configure_session_from_extra(
+        self, session: requests.Session, connection: Connection
+    ) -> requests.Session:
+        extra = connection.extra_dejson
+        extra.pop("timeout", None)
+        extra.pop("allow_redirects", None)
+        session.proxies = extra.pop("proxies", extra.pop("proxy", {}))
+        session.stream = extra.pop("stream", False)
+        session.verify = extra.pop("verify", extra.pop("verify_ssl", True))
+        session.cert = extra.pop("cert", None)
+        session.max_redirects = extra.pop("max_redirects", DEFAULT_REDIRECT_LIMIT)
+        session.trust_env = extra.pop("trust_env", True)
+        try:
+            session.headers.update(extra)
+        except TypeError:
+            self.log.warning("Connection to %s has invalid extra field.", connection.host)
+        return session
 
+    def _configure_session_from_mount_adapters(self, session: requests.Session) -> requests.Session:
+        scheme = urlparse(self.base_url).scheme
+        if not scheme:
+            raise ValueError(
+                f"Cannot mount adapters: {self.base_url} does not include a valid scheme (http or https)."
+            )
+        if self.adapter:
+            session.mount(f"{scheme}://", self.adapter)
+        elif self.keep_alive_adapter:
+            session.mount("http://", self.keep_alive_adapter)
+            session.mount("https://", self.keep_alive_adapter)
         return session
 
     def run(
@@ -171,11 +211,6 @@ class HttpHook(BaseHook):
 
         url = self.url_from_endpoint(endpoint)
 
-        if self.tcp_keep_alive:
-            keep_alive_adapter = TCPKeepAliveAdapter(
-                idle=self.keep_alive_idle, count=self.keep_alive_count, interval=self.keep_alive_interval
-            )
-            session.mount(url, keep_alive_adapter)
         if self.method == "GET":
             # GET uses params
             req = requests.Request(self.method, url, params=data, headers=headers, **request_kwargs)
@@ -467,5 +502,4 @@ class HttpAsyncHook(BaseHook):
         if exception.status == 413:
             # don't retry for payload Too Large
             return False
-
         return exception.status >= 500

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/airflow/providers/http/operators/http.py

@@ -19,13 +19,13 @@ from __future__ import annotations
 
 import base64
 import pickle
-from typing import TYPE_CHECKING, Any, Callable, Sequence
+from collections.abc import Sequence
+from typing import TYPE_CHECKING, Any, Callable
 
-from deprecated import deprecated
 from requests import Response
 
 from airflow.configuration import conf
-from airflow.exceptions import AirflowException, AirflowProviderDeprecationWarning
+from airflow.exceptions import AirflowException
 from airflow.hooks.base import BaseHook
 from airflow.models import BaseOperator
 from airflow.providers.http.triggers.http import HttpTrigger
@@ -320,67 +320,3 @@ class HttpOperator(BaseOperator):
             extra_options=merge_dicts(self.extra_options, next_page_params.get("extra_options", {})),
             **self.request_kwargs,
         )
-
-
-@deprecated(
-    reason=(
-        "Class `SimpleHttpOperator` is deprecated and "
-        "will be removed in a future release. Please use `HttpOperator` instead."
-    ),
-    category=AirflowProviderDeprecationWarning,
-)
-class SimpleHttpOperator(HttpOperator):
-    """
-    Calls an endpoint on an HTTP system to execute an action.
-
-    .. seealso::
-        For more information on how to use this operator, take a look at the guide:
-        :ref:`howto/operator:HttpOperator`
-
-    :param http_conn_id: The :ref:`http connection<howto/connection:http>` to run
-        the operator against
-    :param endpoint: The relative part of the full url. (templated)
-    :param method: The HTTP method to use, default = "POST"
-    :param data: The data to pass. POST-data in POST/PUT and params
-        in the URL for a GET request. (templated)
-    :param headers: The HTTP headers to be added to the GET request
-    :param pagination_function: A callable that generates the parameters used to call the API again,
-        based on the previous response. Typically used when the API is paginated and returns for e.g a
-        cursor, a 'next page id', or a 'next page URL'. When provided, the Operator will call the API
-        repeatedly until this callable returns None. The result of the Operator will become by default a
-        list of Response.text objects (instead of a single response object). Same with the other injected
-        functions (like response_check, response_filter, ...) which will also receive a list of Response
-        objects. This function receives a Response object form previous call, and should return a nested
-        dictionary with the following optional keys: `endpoint`, `data`, `headers` and `extra_options.
-        Those keys will be merged and/or override the parameters provided into the HttpOperator declaration.
-        Parameters are merged when they are both a dictionary (e.g.: HttpOperator.headers will be merged
-        with the `headers` dict provided by this function). When merging, dict items returned by this
-        function will override initial ones (e.g: if both HttpOperator.headers and `headers` have a 'cookie'
-        item, the one provided by `headers` is kept). Parameters are simply overridden when any of them are
-        string (e.g.: HttpOperator.endpoint is overridden by `endpoint`).
-    :param response_check: A check against the 'requests' response object.
-        The callable takes the response object as the first positional argument
-        and optionally any number of keyword arguments available in the context dictionary.
-        It should return True for 'pass' and False otherwise. If a pagination_function
-        is provided, this function will receive a list of response objects instead of a
-        single response object.
-    :param response_filter: A function allowing you to manipulate the response
-        text. e.g response_filter=lambda response: json.loads(response.text).
-        The callable takes the response object as the first positional argument
-        and optionally any number of keyword arguments available in the context dictionary.
-        If a pagination_function is provided, this function will receive a list of response
-        object instead of a single response object.
-    :param extra_options: Extra options for the 'requests' library, see the
-        'requests' documentation (options to modify timeout, ssl, etc.)
-    :param log_response: Log the response (default: False)
-    :param auth_type: The auth type for the service
-    :param tcp_keep_alive: Enable TCP Keep Alive for the connection.
-    :param tcp_keep_alive_idle: The TCP Keep Alive Idle parameter (corresponds to ``socket.TCP_KEEPIDLE``).
-    :param tcp_keep_alive_count: The TCP Keep Alive count parameter (corresponds to ``socket.TCP_KEEPCNT``)
-    :param tcp_keep_alive_interval: The TCP Keep Alive interval parameter (corresponds to
-        ``socket.TCP_KEEPINTVL``)
-    :param deferrable: Run operator in the deferrable mode
-    """
-
-    def __init__(self, **kwargs: Any):
-        super().__init__(**kwargs)

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/airflow/providers/http/sensors/http.py

@@ -17,8 +17,9 @@
 # under the License.
 from __future__ import annotations
 
+from collections.abc import Sequence
 from datetime import timedelta
-from typing import TYPE_CHECKING, Any, Callable, Sequence
+from typing import TYPE_CHECKING, Any, Callable
 
 from airflow.configuration import conf
 from airflow.exceptions import AirflowException
@@ -48,7 +49,7 @@ class HttpSensor(BaseSensorOperator):
 
         def response_check(response, task_instance):
             # The task_instance is injected, so you can pull data form xcom
-            # Other context variables such as dag, ds, execution_date are also available.
+            # Other context variables such as dag, ds, logical_date are also available.
             xcom_data = task_instance.xcom_pull(task_ids="pushing_task")
             # In practice you would do something more sensible with this data..
             print(xcom_data)

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/airflow/providers/http/triggers/http.py

@@ -19,7 +19,8 @@ from __future__ import annotations
 import asyncio
 import base64
 import pickle
-from typing import TYPE_CHECKING, Any, AsyncIterator
+from collections.abc import AsyncIterator
+from typing import TYPE_CHECKING, Any
 
 import requests
 from requests.cookies import RequestsCookieJar

{apache_airflow_providers_http-4.13.3 → apache_airflow_providers_http-5.0.0}/pyproject.toml

@@ -27,7 +27,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "apache-airflow-providers-http"
-version = "4.13.3"
+version = "5.0.0"
 description = "Provider package apache-airflow-providers-http for Apache Airflow"
 readme = "README.rst"
 authors = [
@@ -54,20 +54,20 @@ classifiers = [
 ]
 requires-python = "~=3.9"
 dependencies = [
-    "aiohttp>=3.9.2,<3.11.0",
-    "apache-airflow>=2.8.0",
+    "aiohttp>=3.9.2,!=3.11.0",
+    "apache-airflow>=2.9.0",
     "asgiref>=2.3.0",
     "requests-toolbelt>=0.4.0",
     "requests>=2.27.0,<3",
 ]
 
 [project.urls]
-"Documentation" = "https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3"
-"Changelog" = "https://airflow.apache.org/docs/apache-airflow-providers-http/4.13.3/changelog.html"
+"Documentation" = "https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0"
+"Changelog" = "https://airflow.apache.org/docs/apache-airflow-providers-http/5.0.0/changelog.html"
 "Bug Tracker" = "https://github.com/apache/airflow/issues"
 "Source Code" = "https://github.com/apache/airflow"
 "Slack Chat" = "https://s.apache.org/airflow-slack"
-"Twitter" = "https://twitter.com/ApacheAirflow"
+"Twitter" = "https://x.com/ApacheAirflow"
 "YouTube" = "https://www.youtube.com/channel/UCSXwxpWZQ7XZ1WL3wqevChA/"
 
 [project.entry-points."apache_airflow_provider"]