kevinjqliu commented on code in PR #2244:
URL: https://github.com/apache/iceberg-python/pull/2244#discussion_r2278046031
##########
pyiceberg/catalog/rest/auth.py:
##########
@@ -121,6 +125,98 @@ def auth_header(self) -> str:
return f"Bearer {self._token}"
+class OAuth2TokenProvider:
+ """Thread-safe OAuth2 token provider with token refresh support."""
+
+ client_id: str
+ client_secret: str
+ token_url: str
+ scope: Optional[str]
+ refresh_margin: int
+ expires_in: Optional[int]
+
+ _token: Optional[str]
+ _expires_at: int
+ _lock: threading.Lock
+
+ def __init__(
+ self,
+ client_id: str,
+ client_secret: str,
+ token_url: str,
+ scope: Optional[str] = None,
+ refresh_margin: int = 60,
+ expires_in: Optional[int] = None,
+ ):
+ self.client_id = client_id
+ self.client_secret = client_secret
+ self.token_url = token_url
+ self.scope = scope
+ self.refresh_margin = refresh_margin
+ self.expires_in = expires_in
+
+ self._token = None
+ self._expires_at = 0
+ self._lock = threading.Lock()
+
+ @cached_property
+ def _client_secret_header(self) -> str:
+ creds = f"{self.client_id}:{self.client_secret}"
+ creds_bytes = creds.encode("utf-8")
+ b64_creds = base64.b64encode(creds_bytes).decode("utf-8")
+ return f"Basic {b64_creds}"
+
+ def _refresh_token(self) -> None:
+ data = {}
Review Comment:
```suggestion
data = {
"grant_type": "client_credentials"
}
```
need to add grant_type for oauth2 to work
https://www.oauth.com/oauth2-servers/access-tokens/client-credentials/
the legacyoauth implementation had it
https://github.com/apache/iceberg-python/blob/640c592b705db01199020db8e5f2b6e2c67f06bf/pyiceberg/catalog/rest/auth.py#L98
##########
pyiceberg/catalog/rest/auth.py:
##########
@@ -109,6 +122,95 @@ def auth_header(self) -> str:
return f"Bearer {self._token}"
+class OAuth2TokenProvider:
+ """Thread-safe OAuth2 token provider with token refresh support."""
+
+ client_id: str
+ client_secret: str
+ token_url: str
+ scope: Optional[str]
+ refresh_margin: int
+ expires_in: Optional[int]
+
+ _token: Optional[str]
+ _expires_at: int
+ _lock: threading.Lock
+
+ def __init__(
+ self,
+ client_id: str,
+ client_secret: str,
+ token_url: str,
+ scope: Optional[str] = None,
+ refresh_margin: int = 60,
+ expires_in: Optional[int] = None,
+ ):
+ self.client_id = client_id
+ self.client_secret = client_secret
+ self.token_url = token_url
+ self.scope = scope
+ self.refresh_margin = refresh_margin
+ self.expires_in = expires_in
+
+ self._token = None
+ self._expires_at = 0
+ self._lock = threading.Lock()
+
+ def _refresh_token(self) -> None:
+ data = {
+ "grant_type": "client_credentials",
+ "client_id": self.client_id,
+ "client_secret": self.client_secret,
+ }
+ if self.scope:
+ data["scope"] = self.scope
+
+ response = requests.post(self.token_url, data=data)
+ response.raise_for_status()
+ result = response.json()
+
+ self._token = result["access_token"]
+ expires_in = result.get("expires_in", self.expires_in)
+ if expires_in is None:
+ raise ValueError(
+ "The expiration time of the Token must be provided by the
Server in the Access Token Response in `expired_in` field, or by the PyIceberg
Client."
+ )
+ self._expires_at = time.time() + expires_in - self.refresh_margin
+
+ def get_token(self) -> str:
+ with self._lock:
+ if not self._token or time.time() >= self._expires_at:
+ self._refresh_token()
+ if self._token is None:
+ raise ValueError("Authorization token is None after refresh")
+ return self._token
+
+
+class OAuth2AuthManager(AuthManager):
Review Comment:
make sense! thanks for looking into it
##########
mkdocs/docs/configuration.md:
##########
@@ -374,6 +374,94 @@ Specific headers defined by the RESTCatalog spec include:
| ------------------------------------ | -------------------------------------
| -------------------- |
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|
| `header.X-Iceberg-Access-Delegation` | `{vended-credentials,remote-signing}`
| `vended-credentials` | Signal to the server that the client supports
delegated access via a comma-separated list of access mechanisms. The server
may choose to supply access via any or none of the requested mechanisms |
+#### Authentication in RESTCatalog
+
+The RESTCatalog supports pluggable authentication via the `auth` configuration
block. This allows you to specify which how the access token will be fetched
and managed for use with the HTTP requests to the RESTCatalog server. The
authentication method is selected by setting the `auth.type` property, and
additional configuration can be provided as needed for each method.
+
+##### Supported Authentication Types
+
+- `noop`: No authentication (no Authorization header sent).
+- `basic`: HTTP Basic authentication.
+- `oauth2`: OAuth2 client credentials flow.
+- `legacyoauth2`: Legacy OAuth2 client credentials flow (Deprecated and will
be removed in PyIceberg 1.0.0)
Review Comment:
```suggestion
```
should we remove this then?
"Legacy OAuth 2" is also documented in the section above
https://github.com/apache/iceberg-python/blob/977842bc42c8f9ace24e2f0e0cbd66222ccc74a9/mkdocs/docs/configuration.md#legacy-oauth2
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
