feat: CCA v6 腾讯云部署 + 审稿台（含查找替换）

- deploy/cca_route.py: Flask 蓝图（6个API端点），WAV自动转MP3
- deploy/cca.html: 4步单页流程（上传→处理→审稿→下载），查找替换(Ctrl+H)
- src/term_normalizer.py: 新增正则层（同音字/引号/书名号/小数点/波浪号）
- src/ai_proofreader.py: speaker角色识别+专家段增强Prompt+的地得加强
- src/ai_line_breaker.py: 引号不跨屏+极短行合并+短句合并间隔放宽
- cca_pipeline.py: Step 2.5 校对后二次正则兜底
- 已部署至 http://101.42.29.217/cca.html

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

cca/cca_pipeline.py

@@ -34,6 +34,7 @@ from srt_writer import write_srt, ms_to_srt_time
 from segment_splitter import split_into_segments
 from hotword_extractor import extract_hotwords
 from ai_proofreader import proofread_batch
+from term_normalizer import normalize_terms
 
 
 def main():
@@ -104,6 +105,11 @@ def main():
 
     print(f"[流水线] ASR 共 {len(sentences)} 句")
 
+    # ====== Step 1.5: 术语格式化（正则后处理，不耗 token）======
+    if script_text:
+        print("[流水线] 术语格式化（型号短横线/武器昵称引号/中文数字）...")
+        sentences = normalize_terms(sentences, script_text)
+
     # ====== Step 2: AI 校对 ======
     if use_ai and not args.no_proofread and script_text:
         print("[流水线] AI 校对中 (DeepSeek)...")
@@ -111,6 +117,12 @@ def main():
     elif not script_text and not args.no_proofread and use_ai:
         print("[流水线] 未提供A稿(--script)，跳过AI校对")
 
+    # ====== Step 2.5: 校对后二次正则修复（兜住AI校对引入的新问题）======
+    if script_text:
+        from term_normalizer import normalize_terms as post_normalize
+        print("[流水线] 校对后二次正则修复...")
+        sentences = post_normalize(sentences, script_text)
+
     # ====== Step 3: 节目结构切分 ======
     print("[流水线] 切分节目结构...")
     segments = split_into_segments(sentences)