Files
xiaozhi-esp32-server/main/xiaozhi-server/core/utils/textUtils.py
T

114 lines
2.9 KiB
Python
Raw Normal View History

import json
TAG = __name__
EMOJI_MAP = {
"😂": "laughing",
"😭": "crying",
"😠": "angry",
"😔": "sad",
"😍": "loving",
"😲": "surprised",
"😱": "shocked",
"🤔": "thinking",
"😌": "relaxed",
"😴": "sleepy",
"😜": "silly",
"🙄": "confused",
"😶": "neutral",
"🙂": "happy",
"😆": "laughing",
"😳": "embarrassed",
"😉": "winking",
"😎": "cool",
"🤤": "delicious",
"😘": "kissy",
"😏": "confident",
}
2025-07-23 14:35:59 +08:00
EMOJI_RANGES = [
(0x1F600, 0x1F64F),
(0x1F300, 0x1F5FF),
(0x1F680, 0x1F6FF),
(0x1F900, 0x1F9FF),
(0x1FA70, 0x1FAFF),
(0x2600, 0x26FF),
(0x2700, 0x27BF),
]
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
"“",
"”",
'"', # 中文双引号 + 英文引号
"",
":", # 中文冒号 + 英文冒号
"-",
"", # 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
2025-07-23 14:35:59 +08:00
return is_emoji(char)
async def get_emotion(conn, text):
"""获取文本内的情绪消息"""
emoji = "🙂"
emotion = "happy"
for char in text:
if char in EMOJI_MAP:
emoji = char
emotion = EMOJI_MAP[char]
break
try:
await conn.websocket.send(
json.dumps(
{
"type": "llm",
"text": emoji,
"emotion": emotion,
"session_id": conn.session_id,
}
)
)
except Exception as e:
conn.logger.bind(tag=TAG).warning(f"发送情绪表情失败,错误:{e}")
return
2025-07-23 14:35:59 +08:00
def is_emoji(char):
"""检查字符是否为emoji表情"""
code_point = ord(char)
return any(start <= code_point <= end for start, end in EMOJI_RANGES)
def check_emoji(text):
"""去除文本中的所有emoji表情"""
return ''.join(char for char in text if not is_emoji(char) and char != "\n")