AIStoryBoard/python/check_dict.py

# -*- coding: utf-8 -*-
import sys
from pathlib import Path

dict_path = Path(__file__).parent / 'OnnxOCR-main' / 'OnnxOCR-main' / 'onnxocr' / 'models' / 'ppocrv5' / 'ppocrv5_dict.txt'

with open(dict_path, 'r', encoding='utf-8') as f:
    content = f.read()

# 检查日文字符
hiragana = [c for c in content if '\u3040' <= c <= '\u309F']  # 平假名
katakana = [c for c in content if '\u30A0' <= c <= '\u30FF']  # 片假名
kanji = [c for c in content if '\u4E00' <= c <= '\u9FAF']  # 汉字

print(f'字典总字符数: {len(content)}')
print(f'平假名数量: {len(hiragana)}')
print(f'片假名数量: {len(katakana)}')
print(f'汉字数量: {len(kanji)}')

if hiragana:
    print(f'平假名示例: {hiragana[:20]}')
else:
    print('平假名: 无')

if katakana:
    print(f'片假名示例: {katakana[:20]}')
else:
    print('片假名: 无')

print(f'汉字示例: {kanji[:20]}')