mallamanis

import json
import multiprocessing as mp
import re
from collections import defaultdict
from typing import List, Optional, Set

from datasets import load_dataset
from datasketch import MinHash, MinHashLSH, minhash
from dpu_utils.utils.iterators import ThreadedIterator
from tqdm import tqdm

mallamanis

[
    "https://github.com/minimaxir/big-list-of-naughty-strings.git",
    "https://github.com/shadowsocks/shadowsocks.git",
    "https://github.com/littlecodersh/ItChat.git",
    "https://github.com/google-research/bert.git",
    "https://github.com/0voice/interview_internal_reference.git",
    "https://github.com/keon/algorithms.git",
    "https://github.com/satwikkansal/wtfpython.git",
    "https://github.com/drduh/macOS-Security-and-Privacy-Guide.git",
    "https://github.com/google/python-fire.git",

mallamanis

/**
 * @name Use with open() as
 * @description Consider using a context manager
 * @kind problem
 * @tags maintainability
 * @problem.severity recommendation
 * @sub-severity low
 * @precision medium
 * @id py/use-context-manager
 */

mallamanis

/**
 * @name Join paths correctly
 * @description use os.path.join or an alternative to correctly join paths.
 * @kind path-problem
 * @tags maintainability
 * @problem.severity recommendation
 * @sub-severity low
 * @precision medium
 * @tags speed
 * @sub-severity low

mallamanis

/**
 * @name Iterate of the items of a dictionary using `.items()`.
 * @description instead of iterating over the keys of a dictionary and the indexing the dictionary,
		use `.items()` to retrieve the key-value pairs.
 * @kind problem
 * @tags maintainability
 * @problem.severity recommendation
 * @sub-severity low
 * @precision medium
 * @tags speed

mallamanis

/**
 * @name Use islice() to slice an iterable.
 * @description instead of converting an iterable to a list and then slicing it
	use `islice` for efficiency.
 * @kind problem
 * @tags maintainability
 * @problem.severity recommendation
 * @sub-severity low
 * @precision high
 * @tags speed

mallamanis

/**
 * @name Use hash()
 * @description use hash() instead of __hash__
 * @kind problem
 * @tags maintainability
 * @problem.severity recommendation
 * @sub-severity low
 * @precision high
 * @tags style
 * @sub-severity low

mallamanis

/**
 * @name Prefer iglob
 * @description Use iglob instead of glob
 * @kind problem
 * @tags speed
 * @problem.severity recommendation
 * @sub-severity low
 * @precision high
 * @id py/use-iglob
 */

mallamanis

/**
 * @name Do not check leap year using modulo
 * @description Use the system functions to check for leap years instead of modulo. Very low precision.
 * @kind problem
 * @tags reliability
 *       maintainability
 * @problem.severity recommendation
 * @sub-severity low
 * @precision low
 * @id py/no-leap-check-with-modulo

mallamanis

/**
 * @name Use math.inf or math.nan
 * @description Prefer using math.inf instead of parsing infinity
	from a string
 * @kind problem
 * @tags maintainability
 * @problem.severity recommendation
 * @sub-severity low
 * @precision high
 * @id py/no-float-inf