改造为 SQLite 原生读写

app/scripts/import_course_summaries.py

@@ -11,17 +11,13 @@ from pathlib import Path
 ROOT = Path(__file__).resolve().parents[1]
 sys.path.insert(0, str(ROOT))
 
+from app import repository  # noqa: E402
 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,
-    read_admin_tasks,
-    read_course_summary_state,
     safe_filename_part,
     sha1_text,
-    write_course_summary_state,
 )
 
 
@@ -41,12 +37,13 @@ EXCLUDE_PREFIXES = (
 
 
 def parse_args() -> argparse.Namespace:
-    parser = argparse.ArgumentParser(description="导入历史课程小结 Markdown 到 VPS 数据目录")
+    parser = argparse.ArgumentParser(description="导入历史课程小结 Markdown 到 SQLite")
     parser.add_argument("--source", required=True, type=Path, help="本机历史课程小结采集目录")
-    parser.add_argument("--target", default=Path("/data/course_summaries"), type=Path, help="VPS 课程小结正式目录")
-    parser.add_argument("--state", default=Path("/data/course_summary_state.json"), type=Path, help="课程小结状态文件")
-    parser.add_argument("--tasks", default=Path("/data/admin_tasks.json"), type=Path, help="管理任务文件")
-    parser.add_argument("--operation-logs", default=Path("/data/operation_logs.jsonl"), type=Path, help="操作日志文件")
+    parser.add_argument("--db-path", default=Path("/data/xsk_education.db"), type=Path, help="SQLite 数据库路径")
+    parser.add_argument("--target", type=Path, help=argparse.SUPPRESS)
+    parser.add_argument("--state", type=Path, help=argparse.SUPPRESS)
+    parser.add_argument("--tasks", type=Path, help=argparse.SUPPRESS)
+    parser.add_argument("--operation-logs", type=Path, help=argparse.SUPPRESS)
     parser.add_argument("--missing-table", type=Path, help="历史 classnotes缺失.txt；不传则尝试 source/classnotes缺失.txt")
     parser.add_argument("--dry-run", action="store_true", help="只统计，不写入")
     return parser.parse_args()
@@ -292,30 +289,123 @@ def import_missing_tasks(source: Path, missing_table: Path, tasks_path: Path, dr
     return created
 
 
+def collect_history_entries(source: Path) -> tuple[int, list[dict], int]:
+    scanned = 0
+    skipped = 0
+    entries: list[dict] = []
+    for path in sorted(source.rglob("*.md")):
+        if not should_import_markdown(path, source):
+            continue
+        scanned += 1
+        for entry in iter_markdown_entries(path):
+            try:
+                entries.append(normalize_course_summary(entry))
+            except ValueError:
+                skipped += 1
+    return scanned, entries, skipped
+
+
+def collect_missing_review_tasks(source: Path, missing_table: Path) -> list[tuple[dict, str]]:
+    rows = parse_missing_table(missing_table)
+    tasks: list[tuple[dict, str]] = []
+    for row in rows:
+        source_seed = "|".join(str(row.get(key, "")) for key in ("日期", "学生", "老师", "科目", "来源文件", "备注"))
+        source_id = f"history-missing:{sha1_text(source_seed, 20)}"
+        summary = {
+            "source_id": source_id,
+            "student": row.get("学生", ""),
+            "date_iso": str(row.get("日期", "")).replace(".", "-"),
+            "time_range": row.get("时间段", ""),
+            "duration": row.get("时长", ""),
+            "teacher": row.get("老师", ""),
+            "subject": row.get("科目", ""),
+            "group": row.get("群聊", ""),
+            "title": "历史 classnotes 缺失",
+            "body": f"历史 classnotes 缺失项：{source_seed}",
+            "recognition_source": "history_missing_table",
+            "confidence": "review",
+            "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
+        tasks.append((summary, proposed_line))
+    return tasks
+
+
 def main() -> None:
     args = parse_args()
     source = args.source.resolve()
-    target = args.target.resolve()
+    repository.SQLITE_DB_PATH = args.db_path.resolve()
     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(source, missing_table, args.tasks, args.dry_run)
+    scanned, entries, skipped = collect_history_entries(source)
+    missing_tasks = collect_missing_review_tasks(source, missing_table)
+    batch_id = f"history-import-{datetime.now().strftime('%Y%m%d%H%M%S')}"
     if not args.dry_run:
-        append_operation_log(
-            args.operation_logs,
-            "history_course_summary_import",
-            "completed",
-            source=str(source),
-            target=str(target),
-            scanned_files=scanned,
-            copied_files=copied,
-            indexed_summaries=imported,
-            skipped_summaries=skipped,
-            review_tasks=review_tasks,
-        )
+        def work(conn, backup_id):
+            imported = 0
+            duplicates = 0
+            for summary in entries:
+                saved = repository._save_course_summary(conn, summary)
+                repository._add_summary_seen(conn, summary["source_id"], course_summary_semantic_key(summary))
+                imported += 1 if saved.get("added") else 0
+                duplicates += 0 if saved.get("added") else 1
+            created_tasks = 0
+            for summary, proposed_line in missing_tasks:
+                repository._create_course_summary_review_task(
+                    conn,
+                    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=str(summary.get("remark") or ""),
+                )
+                created_tasks += 1
+            repository._add_ingest_batch(
+                conn,
+                {
+                    "batch_id": batch_id,
+                    "received_at": datetime.now().isoformat(timespec="seconds"),
+                    "window": {"mode": "历史导入", "source": str(source)},
+                    "students": [],
+                    "result": {
+                        "received": len(entries),
+                        "saved": imported,
+                        "auto_registered": 0,
+                        "review_pending": created_tasks,
+                        "duplicates": duplicates,
+                        "rejected": skipped,
+                    },
+                },
+            )
+            repository._append_operation_log(
+                conn,
+                "历史课程小结导入",
+                "完成",
+                source=str(source),
+                scanned_files=scanned,
+                indexed_summaries=imported,
+                skipped_summaries=skipped,
+                review_tasks=created_tasks,
+                backup_id=backup_id,
+            )
+            return {"imported": imported, "duplicates": duplicates, "review_tasks": created_tasks}
+
+        result = repository._write_transaction("history-course-summary-import", [str(source), batch_id], work)
+        imported = int(result.get("imported") or 0)
+        duplicates = int(result.get("duplicates") or 0)
+        review_tasks = int(result.get("review_tasks") or 0)
+    else:
+        imported = len(entries)
+        duplicates = 0
+        review_tasks = len(missing_tasks)
     print(
-        f"历史小结导入完成：扫描 Markdown {scanned} 个，复制 {copied} 个，"
-        f"索引小结 {imported} 条，跳过 {skipped} 条，生成审核任务 {review_tasks} 条。"
+        f"历史小结导入完成：扫描 Markdown {scanned} 个，"
+        f"写入/待写入小结 {imported} 条，重复 {duplicates} 条，"
+        f"跳过 {skipped} 条，生成审核任务 {review_tasks} 条。"
     )