[GitHub] [airflow] uranusjr commented on a diff in pull request #31749: S3 Key sensor deferrable

["uranusjr (via GitHub)" <gi...@apache.org>]

uranusjr commented on code in PR #31749:
URL: https://github.com/apache/airflow/pull/31749#discussion_r1221063235


##########
airflow/providers/amazon/aws/sensors/s3.py:
##########
@@ -93,54 +95,102 @@ def __init__(
         self.check_fn = check_fn
         self.aws_conn_id = aws_conn_id
         self.verify = verify
-
-    def _check_key(self, key):
-        bucket_name, key = S3Hook.get_s3_bucket_key(self.bucket_name, key, "bucket_name", "bucket_key")
-        self.log.info("Poking for key : s3://%s/%s", bucket_name, key)
-
-        """
-        Set variable `files` which contains a list of dict which contains only the size
-        If needed we might want to add other attributes later
-        Format: [{
-            'Size': int
-        }]
-        """
-        if self.wildcard_match:
-            prefix = re.split(r"[\[\*\?]", key, 1)[0]
-            keys = self.hook.get_file_metadata(prefix, bucket_name)
-            key_matches = [k for k in keys if fnmatch.fnmatch(k["Key"], key)]
-            if len(key_matches) == 0:
-                return False
-
-            # Reduce the set of metadata to size only
-            files = list(map(lambda f: {"Size": f["Size"]}, key_matches))
+        self.deferrable = deferrable
+
+    def execute(self, context: Context) -> Any:
+        if self.deferrable:
+            from airflow.providers.amazon.aws.triggers.s3 import S3KeyTrigger
+
+            self.defer(
+                trigger=S3KeyTrigger(
+                    bucket_name=self.bucket_name,
+                    bucket_key=self.bucket_key,
+                    wildcard_match=self.wildcard_match,
+                    aws_conn_id=self.aws_conn_id,
+                    verify=self.verify,
+                ),
+                method_name="execute_complete",
+            )
         else:
-            obj = self.hook.head_object(key, bucket_name)
-            if obj is None:
-                return False
-            files = [{"Size": obj["ContentLength"]}]
-
-        if self.check_fn is not None:
-            return self.check_fn(files)
-
-        return True
+            super().execute(context=context)
 
     def poke(self, context: Context):
         if isinstance(self.bucket_key, str):
-            return self._check_key(self.bucket_key)
+            self.bucket_keys = [self.bucket_key]
         else:
-            return all(self._check_key(key) for key in self.bucket_key)
+            self.bucket_keys = self.bucket_key
+        wildcard_keys = []
+        objs = []
+        bucket_key_names = []
+        for i in range(len(self.bucket_keys)):
+            bucket_key_names.append(
+                S3Hook.get_s3_bucket_key(self.bucket_name, self.bucket_keys[i], "bucket_name", "bucket_key")
+            )
+            bucket_name = bucket_key_names[i][0]
+            key = bucket_key_names[i][1]

Review Comment:
   This can use a rewrite with `enumerate`



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@airflow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org