dolphinscheduler可以通过shell节点校验数据是否符合要求
PT_DATE=${system.biz.date}
PT_PATH=/user/hive/warehouse/default.db/test/pt_d=${PT_DATE}| module.exports = async (params) => { | |
| const { quickAddApi: { inputPrompt }, app } = params; | |
| const adapter = app.vault.adapter; | |
| // 配置常量 | |
| const CONFIG = { | |
| SOURCE_FOLDER: "未归档/MyBrain", | |
| IMPORT_BASE: "未归档/已导入", | |
| SUB_FOLDERS: { | |
| NOTES: "notes", |
| // Updated: Aug. 20, 2024 | |
| // Run: node testRegex.js whatever.txt | |
| // Live demo: https://jina.ai/tokenizer | |
| // LICENSE: Apache-2.0 (https://www.apache.org/licenses/LICENSE-2.0) | |
| // COPYRIGHT: Jina AI | |
| const fs = require('fs'); | |
| const util = require('util'); | |
| // Define variables for magic numbers | |
| const MAX_HEADING_LENGTH = 7; |
| import time | |
| import logging | |
| # 位数 | |
| WORKER_ID_BITS = 5 | |
| DATA_CENTER_ID_BITS = 5 | |
| SEQUENCE_BITS = 12 | |
| TIMESTAMP_EPOCH = 1288834974657 | |
| # 0-31 |
| 2021-10-09 09:06:10.974 [flink-akka.actor.default-dispatcher-4] INFO org.apache.flink.kubernetes.KubernetesResourceManagerDriver - Recovered 0 pods from previous attempts, current attempt id is 1. | |
| 2021-10-09 09:06:10.975 [flink-akka.actor.default-dispatcher-4] INFO o.a.f.runtime.resourcemanager.active.ActiveResourceManager - Recovered 0 workers from previous attempt. | |
| 2021-10-09 09:06:10.977 [flink-akka.actor.default-dispatcher-4] INFO o.a.f.runtime.resourcemanager.active.ActiveResourceManager - ResourceManager akka.tcp://flink@flinkx-demo.dboard:6123/user/rpc/resourcemanager_0 was granted leadership with fencing token 00000000000000000000000000000000 | |
| 2021-10-09 09:06:10.981 [flink-akka.actor.default-dispatcher-4] INFO o.a.f.runtime.resourcemanager.slotmanager.SlotManagerImpl - Starting the SlotManager. | |
| 2021-10-09 09:06:11.181 [flink-akka.actor.default-dispatcher-5] INFO com.dtstack.flinkx.util.DataSyncFactoryUtil - load flinkx plugin hdfsreader:com.dtstack.flinkx.connector.hd |
| library(optparse) | |
| # Rscript test.r --in.csv1 data/mock.csv --in.csv2 data/mock.csv --out.csv1 data/out.csv | |
| # read param | |
| option_list <- list( | |
| make_option(c("-i", "--in.csv1"), type = "character", default = "", action = "store", help = "This is first!"), | |
| make_option(c("-f", "--in.csv2"), type = "character", default = "", action = "store", help = "This is first!"), | |
| make_option(c("-t", "--out.csv1"), type = "character", default = "", action = "store", help = "This is first!") | |
| ) |
| print("do klist") | |
| os.system("klist") | |
| krb5 = os.getenv("KRB5_CONFIG") | |
| print("get krb5: {}".format(krb5)) | |
| if os.getenv("KRB5_CONFIG") is not None: | |
| keytab = os.getenv("KEYTAB") | |
| principal = os.getenv("PRINCIPAL") | |
| kinit_cmd = "env KRB5_CONFIG={} kinit -kt {} {}".format(krb5, keytab, principal) | |
| print("do kinit: {}".format(kinit_cmd)) | |
| os.system(kinit_cmd) |
| def _test_spark_udtf(self): | |
| """ | |
| # source | |
| root | |
| |-- id: long (nullable = true) | |
| |-- title: string (nullable = true) | |
| |-- abstract: string (nullable = true) | |
| |-- content: string (nullable = true) | |
| |-- else: string (nullable = true) |
| package cn.lite.flow.executor.plugin.sql.hive; | |
| import org.apache.hive.jdbc.HiveStatement; | |
| import org.slf4j.Logger; | |
| import org.slf4j.LoggerFactory; | |
| import java.util.List; | |
| /** | |
| * @description: hive日志搜集 |