[播报文本净化]：完成TTS表情包过滤，包含emoji清理、上下文净化和回归测试

src/owner_voice_pet/tts.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import math
 import base64
 import json
+import re
 import socket
 import struct
 import subprocess
@@ -18,6 +19,131 @@ from .config import AppConfig
 from .models import AudioSegment, ErrorCode, ProviderError
 
 
+_MARKDOWN_IMAGE_RE = re.compile(r"!\[[^\]]*]\([^)]*\)")
+_SHORTCODE_EMOJI_RE = re.compile(r":(?:[A-Za-z][A-Za-z0-9_+\-]{1,31}):")
+_ASCII_KAOMOJI_RE = re.compile(r"(?:\^_?\^|T_T|QAQ|QwQ|qwq|orz)")
+_SYMBOL_KAOMOJI_RE = re.compile(r"[\(（][^()（）]{0,20}[\u00b0\u2500-\u2bff][^()（）]{0,20}[\)）][^\s，。！？,.!?]{0,10}")
+_EMOJI_RANGES = (
+    (0x1F000, 0x1FAFF),
+    (0x2600, 0x27BF),
+    (0x2300, 0x23FF),
+)
+_EMOJI_JOINERS = {0x200D, 0x20E3}
+_BRACKET_PAIRS = {"[": "]", "【": "】", "(": ")", "（": "）"}
+_BRACKET_EMOTE_WORDS = {
+    "ok",
+    "doge",
+    "emoji",
+    "一笑",
+    "偷笑",
+    "傻笑",
+    "加油",
+    "发呆",
+    "吐舌",
+    "呲牙",
+    "哭",
+    "哭泣",
+    "困",
+    "大哭",
+    "大笑",
+    "委屈",
+    "害羞",
+    "尴尬",
+    "开心",
+    "微笑",
+    "怒",
+    "惊讶",
+    "惊喜",
+    "惊恐",
+    "捂脸",
+    "抱拳",
+    "擦汗",
+    "晕",
+    "汗",
+    "流汗",
+    "流泪",
+    "滑稽",
+    "爱心",
+    "玫瑰",
+    "生气",
+    "白眼",
+    "点赞",
+    "破涕为笑",
+    "笑",
+    "笑哭",
+    "鼓掌",
+    "比心",
+    "亲亲",
+    "调皮",
+    "难过",
+    "高兴",
+    "鼓励",
+    "狗头",
+}
+
+
+def sanitize_tts_text(text: str) -> str:
+    clean = text.strip()
+    if not clean:
+        return ""
+    clean = _MARKDOWN_IMAGE_RE.sub("", clean)
+    clean = _SHORTCODE_EMOJI_RE.sub("", clean)
+    clean = _strip_bracket_emotes(clean)
+    clean = _SYMBOL_KAOMOJI_RE.sub("", clean)
+    clean = _ASCII_KAOMOJI_RE.sub("", clean)
+    clean = "".join(ch for ch in clean if not _is_emoji_char(ch))
+    return _normalize_spoken_text(clean)
+
+
+def _strip_bracket_emotes(text: str) -> str:
+    result: list[str] = []
+    index = 0
+    while index < len(text):
+        ch = text[index]
+        close = _BRACKET_PAIRS.get(ch)
+        if close is None:
+            result.append(ch)
+            index += 1
+            continue
+        close_index = text.find(close, index + 1)
+        if close_index == -1 or close_index - index > 12:
+            result.append(ch)
+            index += 1
+            continue
+        content = text[index + 1 : close_index]
+        if _is_bracket_emote(content):
+            index = close_index + 1
+            continue
+        result.append(ch)
+        index += 1
+    return "".join(result)
+
+
+def _is_bracket_emote(content: str) -> bool:
+    token = re.sub(r"\s+", "", content.strip()).lower()
+    if not token or len(token) > 8:
+        return False
+    if token in _BRACKET_EMOTE_WORDS or token.endswith("表情"):
+        return True
+    return all(_is_emoji_char(ch) for ch in token)
+
+
+def _is_emoji_char(ch: str) -> bool:
+    codepoint = ord(ch)
+    if codepoint in _EMOJI_JOINERS or 0xFE00 <= codepoint <= 0xFE0F:
+        return True
+    return any(start <= codepoint <= end for start, end in _EMOJI_RANGES)
+
+
+def _normalize_spoken_text(text: str) -> str:
+    clean = re.sub(r"[ \t]+", " ", text)
+    clean = re.sub(r"\s+([，。！？,.!?；;：:])", r"\1", clean)
+    clean = re.sub(r"([，,])\s*([。！？!?])", r"\2", clean)
+    clean = re.sub(r"([。！？!?]){2,}", r"\1", clean)
+    clean = re.sub(r"\s{2,}", " ", clean)
+    return clean.strip(" \t\r\n，,；;：:")
+
+
 class SentenceBuffer:
     def __init__(self, max_chars: int = 80) -> None:
         self.max_chars = max_chars