Dagu-一个带有Web UI的cron替代品

curl -L https://raw.githubusercontent.com/yohamta/dagu/main/scripts/downloader.sh | bash

brew install yohamta/tap/dagu

brew upgrade yohamta/tap/dagu

docker run \
--rm \
-p 8080:8080 \
-v $HOME/.dagu/dags:/home/dagu/.dagu/dags \
-v $HOME/.dagu/data:/home/dagu/.dagu/data \
-v $HOME/.dagu/logs:/home/dagu/.dagu/logs \
ghcr.io/dagu-dev/dagu:latest dagu start-all

schedule: "* * * * *" # Run the DAG every minute
steps:
  - name: s1
    command: echo Hello Dagu
  - name: s2
    command: echo done!
    depends:
      - s1

# Runs the DAG
dagu start [--params=<params>] <file>

# Displays the current status of the DAG
dagu status <file>

# Re-runs the specified DAG run
dagu retry --req=<request-id> <file>

# Stops the DAG execution
dagu stop <file>

# Restarts the current running DAG
dagu restart <file>

# Dry-runs the DAG
dagu dry [--params=<params>] <file>

# Launches both the web UI server and scheduler process
dagu start-all [--host=<host>] [--port=<port>] [--dags=<path to directory>]

# Launches the Dagu web UI server
dagu server [--host=<host>] [--port=<port>] [--dags=<path to directory>]

# Starts the scheduler process
dagu scheduler [--dags=<path to directory>]

# Shows the current binary version
dagu version

#!/bin/bash
process="dagu start-all"
command="/usr/bin/dagu start-all"

if ps ax | grep -v grep | grep "$process" > /dev/null
then
    exit
else
    $command &
fi

exit

# Environment variables used throughout the pipeline
env:
  - DATA_DIR: /data
  - SCRIPT_DIR: /scripts
  - LOG_DIR: /log
  # ... other variables can be added here

# Handlers to manage errors and cleanup after execution
handlerOn:
  failure:
    command: "echo error"
  exit:
    command: "echo clean up"

# The schedule for the workflow execution in cron format
# This schedule runs the workflow daily at 12:00 AM
schedule: "0 0 * * *"

steps:
  # Step 1: Pull the latest data from a data source
  - name: pull_data
    command: "sh"
    script: |
      echo `date '+%Y-%m-%d'`
    output: DATE

 # Step 2: Cleanse and prepare the data
  - name: cleanse_data
    command: echo cleansing ${DATA_DIR}/${DATE}.csv
    depends:
      - pull_data

  # Step 3: Transform the data
  - name: transform_data
    command: echo transforming ${DATA_DIR}/${DATE}_clean.csv
    depends:
      - cleanse_data

  # Parallel Step 1: Load the data into a database
  - name: load_data
    command: echo loading ${DATA_DIR}/${DATE}_transformed.csv
    depends:
      - transform_data

  # Parallel Step 2: Generate a statistical report
  - name: generate_report
    command: echo generating report ${DATA_DIR}/${DATE}_transformed.csv
    depends:
      - transform_data

  # Step 4: Run some analytics
  - name: run_analytics
    command: echo running analytics ${DATA_DIR}/${DATE}_transformed.csv
    depends:
      - load_data

  # Step 5: Send an email report
  - name: send_report
    command: echo sending email ${DATA_DIR}/${DATE}_analytics.csv
    depends:
      - run_analytics
      - generate_report

  # Step 6: Cleanup temporary files
  - name: cleanup
    command: echo removing ${DATE}*.csv
    depends:
      - send_report