feat: add course summary search

2026-06-15 12:08:04 +08:00
parent 8832a52310
commit df076f6951
7 changed files with 317 additions and 2 deletions
@@ -42,6 +42,8 @@ CLASSNOTE_RE = re.compile(
 )
 PAYMENT_LINE_RE = re.compile(r"^(?P<student>.+?)-(?P<date>\d{4}-\d{2}-\d{2}):(?P<hours>\d+(?:\.\d+)?)$")
 TIME_RANGE_RE = re.compile(r"^(?P<sh>\d{1,2}):(?P<sm>\d{2})-(?P<eh>\d{1,2}):(?P<em>\d{2})$")
+COURSE_SUMMARY_HEADING_RE = re.compile(r"^###\s+(?P<title>.+)$", re.M)
+COURSE_SUMMARY_DATE_RE = re.compile(r"(?P<date>\d{4}[.-]\d{1,2}[.-]\d{1,2})")
 BACKUP_DIR_RE = re.compile(r"^\d{8}-\d{6}-\d{6}-")
 BACKUP_KEEP_COUNT = 50
 ACCOUNT_STATUSES = {"正常", "预警", "欠费", "结课", "退费"}
@@ -1059,6 +1061,169 @@ def list_operation_logs(path: Path, limit: int = 100, operation: str = "", statu
    return {"count": len(rows), "items": rows}


+def normalize_filter_date(value: str) -> str:
+    text = value.strip().replace(".", "-")
+    if not text:
+        return ""
+    parts = text.split("-")
+    if len(parts) == 3:
+        text = f"{int(parts[0]):04d}-{int(parts[1]):02d}-{int(parts[2]):02d}"
+    return date.fromisoformat(text).isoformat()
+
+
+def parse_course_summary_file_identity(root: Path, path: Path) -> dict:
+    relative = path.relative_to(root)
+    student = canonical_name(relative.parts[0]) if relative.parts else ""
+    stem = path.stem
+    parts = stem.split("_")
+    teacher = ""
+    subject = ""
+    if len(parts) >= 3:
+        student = canonical_name(parts[0])
+        teacher = canonical_name("_".join(parts[1:-1]))
+        subject = parts[-1]
+    return {
+        "student": student,
+        "teacher": teacher,
+        "subject": normalize_subject(subject),
+        "source_path": str(path),
+        "relative_path": str(relative),
+    }
+
+
+def parse_course_summary_title_date(title: str) -> str:
+    match = COURSE_SUMMARY_DATE_RE.search(title)
+    if not match:
+        return ""
+    raw = match.group("date").replace(".", "-")
+    parts = raw.split("-")
+    if len(parts) != 3:
+        return ""
+    normalized = f"{int(parts[0]):04d}-{int(parts[1]):02d}-{int(parts[2]):02d}"
+    try:
+        return date.fromisoformat(normalized).isoformat()
+    except ValueError:
+        return ""
+
+
+def iter_course_summary_markdown(root: Path) -> Iterable[dict]:
+    if not root.exists():
+        return
+    for path in sorted(root.rglob("*.md")):
+        if not path.is_file():
+            continue
+        text = path.read_text(encoding="utf-8")
+        matches = list(COURSE_SUMMARY_HEADING_RE.finditer(text))
+        if not matches:
+            continue
+        identity = parse_course_summary_file_identity(root, path)
+        group = ""
+        group_match = re.search(r"^##\s+(.+)$", text[: matches[0].start()], flags=re.M)
+        if group_match:
+            group = group_match.group(1).strip()
+        for index, match in enumerate(matches):
+            title = match.group("title").strip()
+            start = match.end()
+            end = matches[index + 1].start() if index + 1 < len(matches) else len(text)
+            body = text[start:end].strip()
+            body_without_meta = re.sub(r"^(?:>\s+.*\n)+\s*", "", body).strip()
+            body_text = body_without_meta or body
+            item_id = sha1_text(f"{identity['relative_path']}|{title}|{index}|{body_text[:200]}", 20)
+            yield {
+                **identity,
+                "id": item_id,
+                "title": title,
+                "date_iso": parse_course_summary_title_date(title),
+                "group": group,
+                "body": body_text,
+                "body_preview": body_text[:260] + ("..." if len(body_text) > 260 else ""),
+            }
+
+
+def course_summary_matches(item: dict, q: str, student: str, teacher: str, subject: str, date_from: str, date_to: str) -> bool:
+    if student and student not in str(item.get("student", "")):
+        return False
+    if teacher and teacher not in str(item.get("teacher", "")):
+        return False
+    if subject and normalize_subject(subject) not in str(item.get("subject", "")):
+        return False
+    item_date = str(item.get("date_iso") or "")
+    if date_from and (not item_date or item_date < date_from):
+        return False
+    if date_to and (not item_date or item_date > date_to):
+        return False
+    if q:
+        haystack = "\n".join(
+            str(item.get(key, ""))
+            for key in ("student", "teacher", "subject", "title", "group", "body", "relative_path")
+        )
+        return q in haystack
+    return True
+
+
+def course_summary_matched_fields(item: dict, q: str) -> list[str]:
+    if not q:
+        return []
+    labels = {
+        "student": "学生",
+        "teacher": "老师",
+        "subject": "科目",
+        "title": "标题",
+        "group": "群名",
+        "body": "正文",
+        "relative_path": "来源",
+    }
+    return [label for key, label in labels.items() if q in str(item.get(key, ""))]
+
+
+def query_course_summaries(
+    root: Path,
+    q: str = "",
+    student: str = "",
+    teacher: str = "",
+    subject: str = "",
+    date_from: str = "",
+    date_to: str = "",
+    limit: int = 200,
+) -> dict:
+    normalized_from = normalize_filter_date(date_from)
+    normalized_to = normalize_filter_date(date_to)
+    if normalized_from and normalized_to and normalized_from > normalized_to:
+        raise ValueError("开始日期不能晚于结束日期")
+    keyword = q.strip()
+    matched = [
+        item
+        for item in iter_course_summary_markdown(root)
+        if course_summary_matches(
+            item,
+            keyword,
+            canonical_name(student.strip()),
+            canonical_name(teacher.strip()),
+            subject.strip(),
+            normalized_from,
+            normalized_to,
+        )
+    ]
+    for item in matched:
+        item["matched_fields"] = course_summary_matched_fields(item, keyword)
+    matched.sort(
+        key=lambda item: (
+            str(item.get("date_iso") or "0000-00-00"),
+            str(item.get("student") or ""),
+            str(item.get("teacher") or ""),
+            str(item.get("subject") or ""),
+            str(item.get("title") or ""),
+        ),
+        reverse=True,
+    )
+    limited = matched[:limit]
+    return {
+        "count": len(matched),
+        "returned": len(limited),
+        "items": limited,
+    }
+
+
 def course_summary_path(root: Path, summary: dict) -> Path:
    student = safe_filename_part(summary["student"])
    teacher = safe_filename_part(summary["teacher"] or "待核对老师")