Russell Jurney rjurney

Click Conversion Guide for Abzu CLI

This document serves as a guide for converting the existing argparse-based CLI to use Click.

Decorator-based Command Pattern
- Use @click.command() and @click.group() decorators
- Replace manual subparser creation with nested command groups

	from collections import defaultdict
	from pprint import pprint


	class Solution:
	def longestCommonPrefix(self, strs: List[str]) -> str:
	str_count = len(strs)
	min_len = min([len(s) for s in strs])
	print(f"Minimum string length: {min_len:,}")

	from graphframes.lib import AggregateMessages as AM
	from graphframes.examples import Graphs
	from pyspark.sql.functions import sum as sqlsum


	g = Graphs(spark).friends() # Get example graph

	# For each user, sum the ages of the adjacent users
	msgToSrc = AM.dst["age"]
	msgToDst = AM.src["age"]

	import os
	import glob
	import shutil
	import uuid
	from pyspark.sql.readwriter import DataFrameWriter


	def csv_single(self, path, **options):
	"""
	Write the DataFrame as a single CSV file at the specified path.

	"""Script that tests and times Relik's relation extraction and entity linking on the GraphFrames Paper: https://people.eecs.berkeley.edu/~matei/papers/2016/grades_graphframes.pdf"""

	import timeit
	import warnings
	from pprint import pprint
	from relik import Relik # type: ignore
	from relik.inference.data.objects import RelikOutput # type: ignore

	# Squash Relik's warnings for prettier screenshots
	warnings.simplefilter("ignore")

	from pypdf import PdfReader

	# Load the PDF. The GraphFrames paper normally resides at
	# https://people.eecs.berkeley.edu/~matei/papers/2016/grades_graphframes.pdf
	reader = PdfReader("data/grades_graphframes.pdf")

	# Extract text from all pages
	text = "\n".join([page.extract_text() for page in reader.pages if page.extract_text()])

	# Write it to a text file