upstream-zulip/tools/build-demo-organization-wordlist

#!/usr/bin/env python3
import re

import orjson
import requests

EXCLUDED_NOUNS = [
    "Fightings",
    "Followings",
    "Harassments",
    "Injustices",
    "Insults",
    "Outrages",
    "Pleas",
    "Poisons",
    "Prejudices",
    "Punishments",
    "Robberies",
    "Sins",
    "Softwares",
    "Steams",
    "Theses",
]

EXCLUDED_ADVERBS = [
    "Obnoxiously",
    "Rudely",
    "Ruthlessly",
    "Scornfully",
    "Selfishly",
]

EXCLUDED_ADJECTIVES = [
    "Cruel",
    "Destructive",
    "Dishonest",
    "Illegal",
    "Infamous",
    "Shocking",
]


def clean_word(word: str) -> str:
    return word.replace("\\n", "").replace("'", "").replace("]", "").replace("[", "").strip()


def run() -> None:
    url = "https://raw.githubusercontent.com/jitsi/js-utils/refs/heads/master/random/roomNameGenerator.ts"
    response = requests.get(url)
    content = str(response.content)

    raw_plural_nouns = re.findall(r"const _PLURALNOUN_.*?=\s*(.*?);", content)
    plural_nouns = raw_plural_nouns[0].split(",")
    cleaned_nouns: list[str] = [
        clean_word(noun).lower() for noun in plural_nouns if clean_word(noun) not in EXCLUDED_NOUNS
    ]

    raw_adverbs = re.findall(r"const _ADVERB_.*?=\s*(.*?);", content)
    adverbs = raw_adverbs[0].split(",")
    cleaned_adverbs: list[str] = [
        clean_word(adverb).lower()
        for adverb in adverbs
        if clean_word(adverb) not in EXCLUDED_ADVERBS
    ]

    raw_adjectives = re.findall(r"const _ADJECTIVE_.*?=\s*(.*?);", content)
    adjectives = raw_adjectives[0].split(",")
    cleaned_adjectives: list[str] = [
        clean_word(adjective).lower()
        for adjective in adjectives
        if clean_word(adjective) not in EXCLUDED_ADJECTIVES
    ]

    word_map = {
        "nouns": cleaned_nouns,
        "adverbs": cleaned_adverbs,
        "adjectives": cleaned_adjectives,
    }

    file_path = "zerver/lib/demo_organization_words.json"
    with open(file_path, "wb+") as f:
        f.write(
            orjson.dumps(
                word_map,
                option=orjson.OPT_APPEND_NEWLINE | orjson.OPT_INDENT_2 | orjson.OPT_SORT_KEYS,
            )
        )


if __name__ == "__main__":
    run()