import re def count_chars_words(sentence): # 使用正则表达式分割句子,其中中文按字分割,英文按词分割 segments = re.findall(r'[\u4e00-\u9fa5]+|\w+', sentence) # 统计字符数和词数 char_count = 0 word_count = 0 for segment in segments: # print(segment) if re.match(r'[\u4e00-\u9fa5]+', segment): # 中文部分,每个汉字算一个字符 char_count += len(segment) else: # 英文部分,每个单词算一个词 word_count += len(segment.split()) return char_count + word_count sentence = "如果您 want to deploy the 模型并进行推理" count = count_chars_words(sentence) print(f"字符数:{count}") sentence = "今天天气真好,我们一起出去吃饭吧。" count = count_chars_words(sentence) print(f"字符数:{count}") sentence = "我最近在学习machine learning,希望能够在未来的artificial intelligence领域有所建树。" count = count_chars_words(sentence) print(f"字符数:{count}") sentence = "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante。" count = count_chars_words(sentence) print(f"字符数:{count}")