Japanese translation checker for minikube

jtchecker.py

import codecs
import json
import re
import string

CHO_ON_PATTERN = re.compile(r"[ア-ンー・]+[アカガサザタダナハバパマヤラワァィゥェォ][^ア-ン]")

ILLEGAL_CHARACTERS = re.compile("[　（｛【『［）｝】』］”’，．・０１２３４５６７８９：／－]")
ILLEGAL_KANJI_PATTERN = re.compile("(下さい|無し|為|する事)")

QUOTED_PATTERN = re.compile(r"'[^']+'")
DOUBLE_QUOTED_PATTERN = re.compile(r'"[^"]+"')

LETTERS = string.ascii_letters + string.punctuation
HANKAKU_SPACE_PATTERN1 = re.compile(f"[{LETTERS}][^{string.printable}]")
HANKAKU_SPACE_PATTERN2 = re.compile(f"[^{string.printable}][{LETTERS}]")


# 末尾に長音記号がないかどうか
def cho_on(source: str) -> str:
    result = CHO_ON_PATTERN.findall(source)
    if result is None:
        return []
    return [x[:-1] for x in result if x[-1] != "ー"]


# 強調・引用部分がないかどうか
def quoted(source: str) -> str:
    result = QUOTED_PATTERN.findall(source)
    result += DOUBLE_QUOTED_PATTERN.findall(source)
    if result is None:
        return []
    return [x[:-1] for x in result if x[-1] != "ー"]


# 不正文字をつかっているかどうか
def illegal_characters(source: str) -> str:
    result = ILLEGAL_CHARACTERS.findall(source)
    if len(result) > 0:
        return result


# 制限漢字表記があるかどうか
def illegal_kanji(source: str) -> str:
    result = ILLEGAL_KANJI_PATTERN.findall(source)
    if len(result) > 0:
        return result


# 半角単語と全角単語の間に半角空白があるかどうか
def hankaku_space(source: str) -> str:
    result = HANKAKU_SPACE_PATTERN1.findall(source)
    result = [x for x in result if x[0] not in ["("]]
    result = [x for x in result if x[1] not in ["」", "。", "、"]]
    result2 = HANKAKU_SPACE_PATTERN2.findall(source)
    result2 = [x for x in result2 if x[0] not in ["。", "、", "「"]]
    result2 = [x for x in result2 if x[1] not in [":", ")"]]
    if len(result) > 0:
        return result


with open("ja.json", encoding="utf8") as f:
    data = json.load(f)
    sorted(data)
    _count = 1
    for english, japanese in data.items():
        # 行数カウンタ
        _count += 1
        japanese2 = codecs.escape_decode(bytes(japanese, "utf-8"))[0]\
            .decode("utf-8")
        result = cho_on(japanese2)
        if result:
            print(f"{_count} {japanese}: 長音注意 ({str(result)[1:-1]})")
        result = quoted(japanese2)
        if result:
            print(f"{_count} {japanese}: 強調・引用注意 ({str(result)[1:-1]})")
        result = illegal_characters(japanese2)
        if result:
            print(f"{_count} {japanese}: 使用禁止文字あり ({str(result)[1:-1]})")
        result = illegal_kanji(japanese2)
        if result:
            print(f"{_count} {japanese}: 使用禁止フレーズあり ({str(result)[1:-1]})")
        result = hankaku_space(japanese2)
        if result:
            print(f"{_count} {japanese}: 半角スペース注意 ({str(result)[1:-1]})")