doco: v2说话人分段模式 — ASR说话人分离+大block拆分+三维动画解说识别

- asr_adapter: 新增roleType=1说话人分离参数，新增parse_order_result_with_speaker()，write_asr_result自动输出asr_v2_timed_spk.txt - fusion_align: 新增speaker-aware alignment v2流程（_annotate_b_lines_with_speakers区间匹配、_detect_speaker_blocks、SYSTEM_PROMPT_SPEAKER_ALIGN大block拆分prompt、_build_broadcast_segments支持block内多段拆分） - cli: 兼容v1/v2 stats字典 - 新增convert_to_md.py（20期融合A稿docx转md+YAML frontmatter） - backup_before_spk/: 修改前代码备份
2026-06-24 16:26:05 +08:00
parent a87f453326
commit 1c3963d17c
14 changed files with 13069 additions and 266 deletions
@@ -0,0 +1,176 @@
+"""
+将 20 期融合A稿 (.docx) 转为带 YAML frontmatter 的 .md 文件，
+供 TPS 主项目知识库 /api/knowledge/upload 批量导入。
+
+用法：
+    cd E:\tps-dashboard\doco
+    python convert_to_md.py
+
+产物落在 doco/deliverables/ 目录下，每期一个 .md 文件。
+"""
+
+import glob
+import os
+import re
+import sys
+from datetime import datetime
+from pathlib import Path
+
+from docx import Document
+
+PROGRAMS_DIR = Path(__file__).parent / "programs"
+OUTPUT_DIR = Path(__file__).parent / "deliverables"
+
+# ep001 文件名没有编导和标题信息，需要手工补
+EP001_OVERRIDE = {
+    "title": "现代防空反导大对决",
+    "author": "",  # ← 通哥填
+    "date": "2026-06-12",
+}
+
+
+def find_fusion_docx(episode_dir: Path) -> Path | None:
+    """在 episode 目录里找融合A稿 docx（排除批改稿）。"""
+    candidates = []
+    for f in episode_dir.iterdir():
+        if f.suffix == ".docx" and "融合A稿" in f.name and "批改" not in f.name:
+            candidates.append(f)
+    if not candidates:
+        return None
+    if len(candidates) == 1:
+        return candidates[0]
+    # 优先选带日期前缀的（ep002+ 格式）
+    for c in candidates:
+        if re.match(r"\d{8}", c.stem):
+            return c
+    return candidates[0]
+
+
+def parse_metadata_from_filename(docx_path: Path, episode_dir_name: str) -> dict:
+    """
+    从文件名提取元数据。
+    ep002+ 文件名格式：{YYYYMMDD}{标题}_{编导}_融合A稿.docx
+    ep001 特殊处理。
+    """
+    if episode_dir_name.startswith("ep001"):
+        return EP001_OVERRIDE.copy()
+
+    stem = docx_path.stem  # e.g. "20260127潜艇的仿生之路_穆佩弦_融合A稿"
+
+    # 去掉 "_融合A稿" 后缀
+    stem = re.sub(r"_融合A稿$", "", stem)
+
+    # 提取日期 (前8位)
+    date_str = stem[:8]
+    try:
+        dt = datetime.strptime(date_str, "%Y%m%d")
+        date_iso = dt.strftime("%Y-%m-%d")
+    except ValueError:
+        date_iso = ""
+
+    rest = stem[8:]  # e.g. "潜艇的仿生之路_穆佩弦"
+
+    # 最后一个 _ 分隔编导
+    parts = rest.rsplit("_", 1)
+    if len(parts) == 2:
+        title, author = parts
+    else:
+        title = rest
+        author = ""
+
+    return {"title": title, "date": date_iso, "author": author}
+
+
+def docx_to_markdown(docx_path: Path) -> str:
+    """将融合A稿 docx 转为 markdown 正文。"""
+    doc = Document(str(docx_path))
+    lines = []
+
+    for para in doc.paragraphs:
+        text = para.text.strip()
+        if not text:
+            continue
+
+        # 大标题（第一段，通常带书名号）
+        if not lines and (text.startswith("《") or text.startswith("【") is False):
+            lines.append(f"# {text}")
+            lines.append("")
+            continue
+
+        # 段头标签：【主持人1】【解说3】【专家2】【导视】隔断：【...】
+        if re.match(r"^【.+?】$", text) or re.match(r"^隔断\d*[：:]【.+?】", text):
+            lines.append("")
+            lines.append(f"## {text}")
+            lines.append("")
+            continue
+
+        # 普通正文段落
+        lines.append(text)
+        lines.append("")
+
+    return "\n".join(lines).strip() + "\n"
+
+
+def build_frontmatter(meta: dict, episode_id: str) -> str:
+    """生成 YAML frontmatter。"""
+    fm_lines = ["---"]
+    fm_lines.append(f"标题: {meta['title']}")
+    if meta["author"]:
+        fm_lines.append(f"编导: {meta['author']}")
+    if meta["date"]:
+        fm_lines.append(f"播出日期: {meta['date']}")
+    fm_lines.append("类型: 节目文稿")
+    fm_lines.append(f"期号: {episode_id}")
+    fm_lines.append("---")
+    return "\n".join(fm_lines)
+
+
+def main():
+    OUTPUT_DIR.mkdir(exist_ok=True)
+
+    # 找所有 ep??? 目录（排除 ep002_004 这种非标准的）
+    episode_dirs = sorted(
+        d
+        for d in PROGRAMS_DIR.iterdir()
+        if d.is_dir() and re.match(r"^ep\d{3}_\d{8}_", d.name)
+    )
+
+    print(f"找到 {len(episode_dirs)} 个期目录")
+    success = 0
+    errors = []
+
+    for ep_dir in episode_dirs:
+        episode_id = ep_dir.name.split("_")[0]  # ep001, ep002, ...
+        docx_path = find_fusion_docx(ep_dir)
+
+        if docx_path is None:
+            errors.append(f"{ep_dir.name}: 未找到融合A稿")
+            continue
+
+        print(f"  {episode_id}: {docx_path.name}")
+
+        meta = parse_metadata_from_filename(docx_path, ep_dir.name)
+        frontmatter = build_frontmatter(meta, episode_id)
+        body = docx_to_markdown(docx_path)
+
+        # 输出文件名：ep001_现代防空反导大对决.md
+        safe_title = meta["title"].replace(":", "：").replace("/", "_")
+        out_name = f"{episode_id}_{safe_title}.md"
+        out_path = OUTPUT_DIR / out_name
+
+        with open(out_path, "w", encoding="utf-8") as f:
+            f.write(frontmatter + "\n\n" + body)
+
+        success += 1
+
+    print(f"\n完成：{success}/{len(episode_dirs)} 期转换成功")
+    if errors:
+        print("失败：")
+        for e in errors:
+            print(f"  {e}")
+
+    print(f"\n产物目录：{OUTPUT_DIR}")
+
+
+if __name__ == "__main__":
+    main()