Add per-Connection ssl_verify / ssl_ca_bundle plus global defaults so CDH 5 / on-prem clusters with self-signed certs or custom CA bundles can be queried without patching code. - Connection gets ssl_verify (bool|None) and ssl_ca_bundle (str|None) - Settings gets ssl_verify_default and ssl_ca_bundle_default - New YarnClientConfig dataclass carries the resolved verify= value - _request passes verify= through to httpx.request - All public yarn_client functions now take YarnClientConfig instead of a bare yarn_rm_url string; tool call sites resolve the Connection - SaveConnectionRequest exposes the two new fields Tests cover per-connection CA bundle, per-connection verify=False, global default fallback, and connection-not-found error.
88 lines
2.3 KiB
Python
88 lines
2.3 KiB
Python
# coding=utf-8
|
|
"""
|
|
@Time :2026/6/24
|
|
@Author :tao.chen
|
|
"""
|
|
from datetime import datetime
|
|
|
|
from pydantic import BaseModel, Field, field_validator
|
|
|
|
|
|
class Job(BaseModel):
|
|
job_id: str
|
|
application_id: str
|
|
script_path: str
|
|
queue: str
|
|
submit_time: datetime
|
|
connection: str
|
|
yarn_rm_url: str | None = None
|
|
|
|
|
|
class JobStatus(BaseModel):
|
|
application_id: str
|
|
state: str
|
|
raw: str = Field(default="")
|
|
|
|
|
|
class JobResult(BaseModel):
|
|
application_id: str
|
|
state: str
|
|
final_status: str | None = None
|
|
diagnostics: str | None = None
|
|
tracking_url: str | None = None
|
|
started_time: int | None = None
|
|
finished_time: int | None = None
|
|
|
|
|
|
class SubmitResult(BaseModel):
|
|
job_id: str
|
|
application_id: str
|
|
tracking_url: str | None = None
|
|
|
|
|
|
class Connection(BaseModel):
|
|
name: str
|
|
# Defaults to "yarn" because that's the literal string spark-submit wants
|
|
# for --master when targeting YARN. Override for Standalone (spark://...),
|
|
# Kubernetes (k8s://...), or local mode.
|
|
master: str = "yarn"
|
|
deploy_mode: str = "cluster"
|
|
yarn_rm_url: str | None = None
|
|
spark_conf: dict[str, str] = Field(default_factory=dict)
|
|
# None means "fall back to Settings.ssl_verify_default". Explicit True/False
|
|
# overrides the global default for this connection.
|
|
ssl_verify: bool | None = None
|
|
ssl_ca_bundle: str | None = None
|
|
|
|
@field_validator("master")
|
|
@classmethod
|
|
def _check_master(cls, v: str) -> str:
|
|
"""Catch common typos like 'yarn-cluster' or 'http://...'. """
|
|
if v == "yarn":
|
|
return v
|
|
if v.startswith(("spark://", "k8s://", "mesos://", "local")):
|
|
return v
|
|
raise ValueError(
|
|
f"master must be 'yarn', 'spark://...', 'k8s://...', 'mesos://...', "
|
|
f"or 'local[/N]'; got {v!r}"
|
|
)
|
|
|
|
|
|
class PendingSubmission(BaseModel):
|
|
pending_id: str
|
|
connection: str
|
|
master: str
|
|
deploy_mode: str
|
|
yarn_rm_url: str | None = None
|
|
script_path: str
|
|
queue: str
|
|
executor_memory: str
|
|
executor_cores: int
|
|
num_executors: int
|
|
spark_conf: dict[str, str] = Field(default_factory=dict)
|
|
created_at: datetime
|
|
status: str = "PENDING" # PENDING | SUBMITTED | CANCELLED | FAILED
|
|
error: str | None = None
|
|
job_id: str | None = None
|
|
application_id: str | None = None
|