Claude
516541a4df
YARN is the dominant use case, and the value of master for YARN is the
literal string 'yarn' (not a URL) — there is no useful variation. Making
it a default saves every YARN user from typing the same value every time:
save_connection(name='prod') # master defaults to 'yarn'
save_connection(name='dev', master='spark://10.0.0.5:7077') # override
Added a field_validator on master that catches common typos
('yarn-cluster', 'http://...', empty string) at save time with a clear
error message instead of letting them reach spark-submit.
Backward compatible: existing Connection records without an explicit
master field default to 'yarn' on load (Pydantic applies defaults on
deserialization), so already-saved data still works.
3 new tests cover the default, the validator, and that other cluster
managers (spark://, k8s://, local[N]) still pass.
74 lines
1.9 KiB
Python
74 lines
1.9 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 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)
|
|
|
|
@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
|