From: studyhill <studyhill@local>
Date: Sat, 29 Aug 2026 11:37:15 +0000 (+0800)
Subject: 新增词汇表导出脚本
X-Git-Url: http://acesimba.cloud/gitweb/?a=commitdiff_plain;h=36e637aca03348e44bb8a69b1119bfe3184f18c2;p=study-mountion.git

新增词汇表导出脚本

导出 74 组切分结果与重点词标记到 Excel（章节/课时号/组标识/单词/词性/词义/
重点词等 11 列），便于线下核对与手工改标重点词。支持 --out 指定路径。
---

diff --git a/backend/imports/export_vocab.py b/backend/imports/export_vocab.py
new file mode 100644
index 0000000..36e9c95
--- /dev/null
+++ b/backend/imports/export_vocab.py
@@ -0,0 +1,119 @@
+"""导出分组后的词汇表到 Excel。
+
+用法：
+    python3 imports/export_vocab.py                       # 默认输出到 /home/tools
+    python3 imports/export_vocab.py --out /path/to.xlsx   # 指定路径
+
+用途：把 74 组的切分结果与重点词标记导出，便于线下核对、手工改标重点词。
+"""
+
+import argparse
+import json
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import db  # noqa: E402
+from openpyxl import Workbook  # noqa: E402
+from openpyxl.styles import Alignment, Font, PatternFill  # noqa: E402
+from openpyxl.utils import get_column_letter  # noqa: E402
+
+DEFAULT_OUT = "/home/tools/雅思词汇真经-分组词汇表.xlsx"
+
+# (表头, 数据键, 列宽)
+COLUMNS = [
+    ("章节", "chapter", 7),
+    ("章节标题", "chapter_title", 12),
+    ("课时号", "lesson_no", 8),
+    ("组号", "group_no", 6),
+    ("组标识", "group_code", 11),
+    ("单词ID", "wid", 10),
+    ("单词", "word", 22),
+    ("音标", "phonetic", 16),
+    ("词性", "pos", 9),
+    ("词义", "meaning", 46),
+    ("重点词", "is_key", 8),
+]
+
+
+def export(out_path):
+    conn = db.get_conn()
+    lessons = conn.execute(
+        "SELECT lesson_no, title, payload FROM lessons ORDER BY lesson_no"
+    ).fetchall()
+    course = conn.execute("SELECT name, code FROM courses LIMIT 1").fetchone()
+    conn.close()
+
+    wb = Workbook()
+    ws = wb.active
+    ws.title = "分组词汇表"
+
+    head_fill = PatternFill("solid", fgColor="4A90C8")
+    for i, (name, _, width) in enumerate(COLUMNS, start=1):
+        cell = ws.cell(row=1, column=i, value=name)
+        cell.font = Font(bold=True, color="FFFFFF")
+        cell.fill = head_fill
+        cell.alignment = Alignment(horizontal="center", vertical="center")
+        ws.column_dimensions[get_column_letter(i)].width = width
+    ws.freeze_panes = "A2"  # 冻结表头，滚动时始终可见
+    ws.auto_filter.ref = f"A1:{get_column_letter(len(COLUMNS))}1"
+
+    row_no = 2
+    for lesson in lessons:
+        payload = json.loads(lesson["payload"])
+        meta = payload.get("meta", {})
+        chapter = meta.get("chapter")
+        group_no = meta.get("group_no")
+        for w in payload.get("words", []):
+            values = {
+                "chapter": chapter,
+                "chapter_title": meta.get("chapter_title"),
+                "lesson_no": lesson["lesson_no"],
+                "group_no": group_no,
+                "group_code": f"Ch{chapter}-G{group_no}",
+                "wid": w.get("wid"),
+                "word": w.get("word"),
+                "phonetic": w.get("phonetic"),
+                "pos": w.get("pos"),
+                "meaning": w.get("meaning"),
+                "is_key": "是" if w.get("is_key") else "否",
+            }
+            for i, (_, key, _) in enumerate(COLUMNS, start=1):
+                ws.cell(row=row_no, column=i, value=values.get(key))
+            row_no += 1
+
+    os.makedirs(os.path.dirname(out_path), exist_ok=True)
+    wb.save(out_path)
+
+    total = row_no - 2
+    key_count = sum(
+        1
+        for lesson in lessons
+        for w in json.loads(lesson["payload"]).get("words", [])
+        if w.get("is_key")
+    )
+    return {
+        "course": f"{course['name']}（{course['code']}）" if course else "—",
+        "lessons": len(lessons),
+        "words": total,
+        "key_words": key_count,
+        "path": out_path,
+    }
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--out", default=DEFAULT_OUT)
+    args = ap.parse_args()
+
+    db.init_db()
+    info = export(args.out)
+    print(f"课程：{info['course']}")
+    print(f"课时：{info['lessons']} 组")
+    print(f"词条：{info['words']} 条（其中重点词 {info['key_words']}）")
+    print(f"已导出：{info['path']}")
+
+
+if __name__ == "__main__":
+    main()