From 6cd1288b181dd4338c091a81c42c38bc3cd2a218 Mon Sep 17 00:00:00 2001
From: Codex <codex@localhost>
Date: Mon, 15 Jun 2026 14:53:01 +0800
Subject: [PATCH] fix: preserve source body for missing summaries

---
 scripts/import_course_summaries.py | 65 ++++++++++++++++++++++++++++--
 1 file changed, 62 insertions(+), 3 deletions(-)

diff --git a/scripts/import_course_summaries.py b/scripts/import_course_summaries.py
index e5a847d..2041402 100644
--- a/scripts/import_course_summaries.py
+++ b/scripts/import_course_summaries.py
@@ -13,6 +13,7 @@ sys.path.insert(0, str(ROOT))
 
 from app.data import (  # noqa: E402
     append_operation_log,
+    course_summary_to_class_record_line,
     course_summary_semantic_key,
     create_course_summary_review_task,
     normalize_course_summary,
@@ -192,7 +193,59 @@ def parse_missing_table(path: Path) -> list[dict]:
     return rows
 
 
-def import_missing_tasks(missing_table: Path, tasks_path: Path, dry_run: bool) -> int:
+def time_range_from_text(text: str) -> str:
+    match = re.search(r"(\d{1,2})[:：](\d{2})\s*[-－–—]\s*(\d{1,2})[:：](\d{2})", text)
+    if not match:
+        return ""
+    start_hour, start_minute, end_hour, end_minute = map(int, match.groups())
+    start = start_hour * 60 + start_minute
+    end = end_hour * 60 + end_minute
+    if end <= start:
+        return ""
+    return f"{start_hour:02d}:{start_minute:02d}-{end_hour:02d}:{end_minute:02d}"
+
+
+def duration_from_time_range(time_range: str) -> tuple[str, int | None]:
+    match = re.fullmatch(r"(\d{2}):(\d{2})-(\d{2}):(\d{2})", time_range)
+    if not match:
+        return "", None
+    start_hour, start_minute, end_hour, end_minute = map(int, match.groups())
+    minutes = end_hour * 60 + end_minute - (start_hour * 60 + start_minute)
+    if minutes <= 0:
+        return "", None
+    return f"{minutes // 60}小时{minutes % 60}分", minutes
+
+
+def source_summary_for_missing_row(source: Path, row: dict) -> dict:
+    relative_path = str(row.get("来源文件") or "").strip()
+    if not relative_path:
+        return {}
+    source_path = source / relative_path
+    if not source_path.exists():
+        return {}
+
+    target_date = str(row.get("日期") or "").replace(".", "-")
+    best: dict = {}
+    for entry in iter_markdown_entries(source_path):
+        if entry.get("date_iso") != target_date:
+            continue
+        time_range = str(entry.get("time_range") or "") or time_range_from_text(str(entry.get("body") or ""))
+        duration, minutes = duration_from_time_range(time_range)
+        candidate = {
+            "title": entry.get("title", ""),
+            "body": entry.get("body", ""),
+            "time_range": time_range,
+            "duration": duration,
+            "duration_minutes": minutes,
+        }
+        if time_range:
+            return candidate
+        if not best:
+            best = candidate
+    return best
+
+
+def import_missing_tasks(source: Path, missing_table: Path, tasks_path: Path, dry_run: bool) -> int:
     rows = parse_missing_table(missing_table)
     if not rows:
         return 0
@@ -220,12 +273,18 @@ def import_missing_tasks(missing_table: Path, tasks_path: Path, dry_run: bool) -
             "teacher_trusted": False,
             "remark": row.get("备注", ""),
         }
+        summary.update({key: value for key, value in source_summary_for_missing_row(source, row).items() if value not in ("", None)})
+        proposed_line = ""
+        try:
+            proposed_line = course_summary_to_class_record_line(summary)
+        except ValueError:
+            pass
         created += 1
         if not dry_run:
             create_course_summary_review_task(
                 tasks_path,
                 summary,
-                "",
+                proposed_line,
                 ["历史 classnotes缺失导入，默认只进入审核，不自动扣课时"],
                 saved_path=row.get("来源文件", ""),
             )
@@ -240,7 +299,7 @@ def main() -> None:
     missing_table = args.missing_table or (source / "classnotes缺失.txt")
     scanned, copied = copy_markdown_files(source, target, args.dry_run)
     imported, skipped = rebuild_state_from_markdown(target if target.exists() else source, args.state, args.dry_run)
-    review_tasks = import_missing_tasks(missing_table, args.tasks, args.dry_run)
+    review_tasks = import_missing_tasks(source, missing_table, args.tasks, args.dry_run)
     if not args.dry_run:
         append_operation_log(
             args.operation_logs,