“wangquan” 57fdf656b9 add_xiaozhi
2025-07-18 13:12:09 +08:00

47 lines
1.4 KiB
Python
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

def get_string_no_punctuation_or_emoji(s):
"""去除字符串首尾的空格、标点符号和表情符号"""
chars = list(s)
# 处理开头的字符
start = 0
while start < len(chars) and is_punctuation_or_emoji(chars[start]):
start += 1
# 处理结尾的字符
end = len(chars) - 1
while end >= start and is_punctuation_or_emoji(chars[end]):
end -= 1
return "".join(chars[start : end + 1])
def is_punctuation_or_emoji(char):
"""检查字符是否为空格、指定标点或表情符号"""
# 定义需要去除的中英文标点(包括全角/半角)
punctuation_set = {
"",
",", # 中文逗号 + 英文逗号
"",
".", # 中文句号 + 英文句号
"",
"!", # 中文感叹号 + 英文感叹号
"-",
"", # 英文连字符 + 中文全角横线
"", # 中文顿号
"[",
"]", # 方括号
"",
"", # 中文方括号
}
if char.isspace() or char in punctuation_set:
return True
# 检查表情符号(保留原有逻辑)
code_point = ord(char)
emoji_ranges = [
(0x1F600, 0x1F64F),
(0x1F300, 0x1F5FF),
(0x1F680, 0x1F6FF),
(0x1F900, 0x1F9FF),
(0x1FA70, 0x1FAFF),
(0x2600, 0x26FF),
(0x2700, 0x27BF),
]
return any(start <= code_point <= end for start, end in emoji_ranges)