character_counter.py

# Generated by GPT 4
# Modified by RisingInIris2017
# Licensed under Public Domain
import os
import re


# 是否清除空行。如果设为 True，需先备份文件
REMOVE_BLANK_LINES = True


def remove_blank_lines(root_folder):
    for root, dirs, files in os.walk(root_folder):
        for file in files:
            if file.endswith('.txt'):
                file_path = os.path.join(root, file)
                with open(file_path, 'r', encoding='utf-8') as f:
                    lines = f.readlines()
                with open(file_path, 'w', encoding='utf-8') as f:
                    for line in lines:
                        if not line.strip():
                            continue
                        f.write(line)


def count_chinese_characters_and_lines(root_folder):
    total_lines = 0
    total_chinese_characters = 0
    
    # 假定文件以 UTF-8 编码，Minecraft 语言文件基本满足这个假设
    chinese_regex = re.compile(r'[\u4e00-\u9fff]')

    for root, dirs, files in os.walk(root_folder):
        for file in files:
            if file.endswith('.txt'):
                file_path = os.path.join(root, file)
                with open(file_path, 'r', encoding='utf-8') as f:
                    for line in f:
                        total_lines += 1
                        total_chinese_characters += len(chinese_regex.findall(line))

    return total_lines, total_chinese_characters


# 将待计数的文件所在的顶层目录填写在此处
folder_path = r''
if REMOVE_BLANK_LINES:
    remove_blank_lines(folder_path)
lines, characters = count_chinese_characters_and_lines(folder_path)
print(f'总行数: {lines}')
print(f'汉字总数: {characters}')