Truncate Wasb storage account name if it's more than 24 characters (#33851)

* Truncate Wasb storage account name if it's more than 24 characters

Storage account names must be between 3 and 24 characters in length but for some
reasons that I can't explain, we saw a situation where the storage name is more than 24 characters
and had to be truncated before it could work. Maybe it was possible in the past to have more than 24 characters or
it could come from cluster but whichever way, the solution that worked was truncating the account name to
24 characters.

* Apply suggestions from code review

Co-authored-by: Jed Cunningham <[email protected]>

* Also add the change to the async part

---------

Co-authored-by: Jed Cunningham <[email protected]>

Author: ephraimbuddy

airflow/providers/microsoft/azure/hooks/wasb.py

@@ -163,10 +163,18 @@ def get_conn(self) -> BlobServiceClient:
         account_url = conn.host if conn.host else f"https://{conn.login}.blob.core.windows.net/"
         parsed_url = urlparse(account_url)
 
-        if not parsed_url.netloc and "." not in parsed_url.path:
-            # if there's no netloc and no dots in the path, then user only
-            # provided the Active Directory ID, not the full URL or DNS name
-            account_url = f"https://{conn.login}.blob.core.windows.net/"
+        if not parsed_url.netloc:
+            if "." not in parsed_url.path:
+                # if there's no netloc and no dots in the path, then user only
+                # provided the Active Directory ID, not the full URL or DNS name
+                account_url = f"https://{conn.login}.blob.core.windows.net/"
+            else:
+                # if there's no netloc but there are dots in the path, then user
+                # provided the DNS name without the https:// prefix.
+                # Azure storage account name can only be 3 to 24 characters in length
+                # https://learn.microsoft.com/en-us/azure/storage/common/storage-account-overview#storage-account-name
+                acc_name = account_url.split(".")[0][:24]
+                account_url = f"https://{acc_name}." + ".".join(account_url.split(".")[1:])
 
         tenant = self._get_field(extra, "tenant_id")
         if tenant:
@@ -568,10 +576,18 @@ async def get_async_conn(self) -> AsyncBlobServiceClient:
         account_url = conn.host if conn.host else f"https://{conn.login}.blob.core.windows.net/"
         parsed_url = urlparse(account_url)
 
-        if not parsed_url.netloc and "." not in parsed_url.path:
-            # if there's no netloc and no dots in the path, then user only
-            # provided the Active Directory ID, not the full URL or DNS name
-            account_url = f"https://{conn.login}.blob.core.windows.net/"
+        if not parsed_url.netloc:
+            if "." not in parsed_url.path:
+                # if there's no netloc and no dots in the path, then user only
+                # provided the Active Directory ID, not the full URL or DNS name
+                account_url = f"https://{conn.login}.blob.core.windows.net/"
+            else:
+                # if there's no netloc but there are dots in the path, then user
+                # provided the DNS name without the https:// prefix.
+                # Azure storage account name can only be 3 to 24 characters in length
+                # https://learn.microsoft.com/en-us/azure/storage/common/storage-account-overview#storage-account-name
+                acc_name = account_url.split(".")[0][:24]
+                account_url = f"https://{acc_name}." + ".".join(account_url.split(".")[1:])
 
         tenant = self._get_field(extra, "tenant_id")
         if tenant:

tests/providers/microsoft/azure/hooks/test_wasb.py

@@ -346,8 +346,12 @@ def test_extra_client_secret_auth_config_ad_connection(self):
                 "https://testaccountname.blob.core.windows.net",
             ),
             ("testhost", "https://accountlogin.blob.core.windows.net/"),
-            ("testhost.dns", "testhost.dns"),
-            ("testhost.blob.net", "testhost.blob.net"),
+            ("testhost.dns", "https://testhost.dns"),
+            ("testhost.blob.net", "https://testhost.blob.net"),
+            (
+                "testhostakjhdisdfbearioyo.blob.core.windows.net",
+                "https://testhostakjhdisdfbearioy.blob.core.windows.net",
+            ),  # more than 24 characters
         ],
     )
     def test_proper_account_url_update(