更新谚语搜索，调整搜索函数

README.md

@@ -334,16 +334,19 @@ Authorization: Bearer <your_jwt_token>
 #### 2.2 法语谚语详情
 
 - **接口**: `POST /search/proverb`
-- **描述**: 通过谚语ID获取法语谚语原文与中文解释。
+- **描述**: 根据谚语ID返回法语谚语全文与中文释义。
 - **需要认证**: 是
-- **查询参数**:
-  - `proverb_id`: 谚语ID (integer)
+- **请求类型**: `application/x-www-form-urlencoded`
+- **表单字段**:
+  - `proverb_id`: 谚语ID (integer，必填)
 - **响应**:
 
 ```json
 {
-  "proverb_text": "Petit à petit, l'oiseau fait son nid.",
-  "chi_exp": "循序渐进才能取得成功。"
+  "result": {
+    "proverb_text": "Petit à petit, l'oiseau fait son nid.",
+    "chi_exp": "循序渐进才能取得成功。"
+  }
 }
 ```
 
@@ -380,14 +383,13 @@ Authorization: Bearer <your_jwt_token>
 #### 2.4 谚语联想建议
 
 - **接口**: `POST /search/proverb/list`
-- **描述**: 按输入内容（自动识别法语或中文）返回谚语候选列表。
+- **描述**: 按输入内容返回谚语候选列表，后端会自动检测输入语言（中文/日文假名/拉丁字母），无法识别时退回法语字段搜索。
 - **需要认证**: 是
 - **请求体**:
 
 ```json
 {
-  "query": "慢",
-  "language": "fr"
+  "query": "慢"
 }
 ```
 
@@ -405,6 +407,9 @@ Authorization: Bearer <your_jwt_token>
 }
 ```
 
+- **状态码**:
+  - `200`: 查询成功
+
 ---
 
 ### 3. 翻译模块 (`/translate`)
@@ -437,6 +442,7 @@ Authorization: Bearer <your_jwt_token>
 }
 ```
 
+- **限制**: 依赖 Redis 计数器做限流，同一用户每秒最多 2 次请求（超出返回 `429`）
 - **状态码**:
   - `200`: 翻译成功
   - `401`: 未授权
@@ -452,7 +458,7 @@ Authorization: Bearer <your_jwt_token>
   - `from_lang`: 源语言，默认为 `auto`
   - `to_lang`: 目标语言，默认为 `zh`
 
-- **限制**: 每秒最多2次请求
+- **限制**: 与标准翻译接口共享限流计数，同一用户每秒最多2次请求
 - **状态码**:
   - `200`: 翻译成功
   - `429`: 请求频率过高
@@ -770,7 +776,8 @@ Authorization: Bearer <your_jwt_token>
 - **需要认证**: 是
 - **查询参数**:
   - `count`: 抽题数量 (integer，默认 `20`)
-  - `lang`: 语种代码，支持 `fr-FR`（法语）、`ja-JP`（日语），默认 `fr-FR`
+- **表单字段**:
+  - `lang`: 语种代码（`fr-FR` 或 `ja-JP`，默认 `fr-FR`）。由于实现方式，FastAPI 将其视为 form-data 字段，GET 请求需通过 form 提交或在调试文档中直接填写。
 - **响应**:
 
 ```json

app/api/search_dict/routes.py

@@ -1,6 +1,6 @@
 from typing import Literal, List
 
-from fastapi import APIRouter, Depends, HTTPException, Request
+from fastapi import APIRouter, Depends, HTTPException, Request, Form
 
 from app.api.search_dict import service
 from app.api.search_dict.search_schemas import SearchRequest, WordSearchResponse, SearchItemFr, SearchItemJp, \
@@ -8,7 +8,7 @@ from app.api.search_dict.search_schemas import SearchRequest, WordSearchResponse
 from app.api.search_dict.service import suggest_autocomplete
 from app.api.word_comment.word_comment_schemas import CommentSet
 from app.models import DefinitionJp, CommentFr, CommentJp
-from app.models.fr import DefinitionFr
+from app.models.fr import DefinitionFr, ProverbFr
 from app.utils.all_kana import all_in_kana
 from app.utils.security import get_current_user
 from app.utils.textnorm import normalize_text
@@ -165,7 +165,19 @@ async def search_word_list(query_word: SearchRequest, user=Depends(get_current_u
 
 
 @dict_search.post("/search/proverb/list")
-async def search_proverb_list(query_word: ProverbSearchRequest, user=Depends(get_current_user)):
-    lang: Literal['fr', 'zh'] = 'zh' if service.contains_chinese(query_word.query) else 'fr'
-    suggest_proverbs = await service.suggest_proverb(query=query_word, lang=lang)
+async def search_proverb_list(query_word: ProverbSearchRequest):
+    lang = service.detect_language(text=query_word.query)
+    query = normalize_text(query_word.query) if lang == "fr" else query_word.query
+    suggest_proverbs = await service.suggest_proverb(
+        query=query_word.query,
+        lang=lang,
+        model=ProverbFr,
+        search_field="search_text",
+    )
+    # TODO 使用法语词典时是否存在用英语输入的情况
     return {"list": suggest_proverbs}
+
+@dict_search.post("/search/proverb")
+async def search_proverb(proverb_id:int = Form(...), user=Depends(get_current_user)):
+    result = await service.accurate_proverb(proverb_id=proverb_id)
+    return {"result": result}

app/api/search_dict/search_schemas.py

@@ -13,7 +13,7 @@ class SearchRequest(BaseModel):
 
 class ProverbSearchRequest(BaseModel):
     query: str
-    language: Literal['fr', 'jp'] = "fr"
+    dict_language: Literal['fr', 'jp'] = "fr"
 
 
 class SearchItemJp(BaseModel):

app/api/search_dict/service.py

@@ -1,9 +1,8 @@
-import asyncio
 import re
-from typing import List, Tuple, Dict, Literal
+from typing import List, Tuple, Dict, Literal, Type
 
 from fastapi import HTTPException
-from tortoise import Tortoise
+from tortoise import Tortoise, Model
 from tortoise.expressions import Q
 
 from app.api.search_dict.search_schemas import SearchRequest, ProverbSearchResponse, ProverbSearchRequest
@@ -14,75 +13,97 @@ from app.utils.textnorm import normalize_text
 from settings import TORTOISE_ORM
 
 
-def contains_chinese(text: str) -> bool:
-    """判断字符串中是否包含至少一个中文字符"""
-    return bool(re.search(r'[\u4e00-\u9fff]', text))
+def detect_language(text: str) -> Literal["fr", "zh", "jp", "other"]:
+    """
+    自动检测输入语言:
+        返回 'zh' / 'jp' / 'fr' / 'other'
+    """
+    if re.search(r"[\u4e00-\u9fff]", text):
+        return "zh"
+    elif re.search(r"[\u3040-\u30ff\u31f0-\u31ff]", text):  # 日文假名范围
+        return "jp"
+    elif re.search(r"[a-zA-ZÀ-ÿ]", text):
+        return "fr"
+    return "other"
 
 
 async def accurate_proverb(proverb_id: int) -> ProverbSearchResponse:
+    """对于查询法语谚语的精准查询，返回详细信息"""
     proverb = await ProverbFr.get_or_none(id=proverb_id)
     if not proverb:
         raise HTTPException(status_code=404, detail="Proverb not found")
     return ProverbSearchResponse(
-        proverb_text=proverb.proverb,
+        proverb_text=proverb.text,
         chi_exp=proverb.chi_exp,
     )
 
 
-async def suggest_proverb(query: ProverbSearchRequest, lang: Literal['fr', 'zh']) -> List[Dict[str, str]]:
+async def suggest_proverb(
+        query: str,
+        lang: Literal["fr", "zh", "jp"],
+        model: Type[Model],
+        search_field: str = "search_text",
+        target_field: str = "text",
+        chi_exp_field: str = "chi_exp",
+        limit: int = 10,
+) -> List[Dict[str, str]]:
     """
-     对法语谚语表进行搜索建议。
+    通用搜索建议函数，用于多语言谚语表。
     参数:
-        query.query: 搜索关键词
+        query: 搜索关键词
         lang: 'fr' 或 'zh'
-    逻辑:
-        1. 若 lang='fr'，按谚语字段 (proverb) 搜索；
-        2. 若 lang='zh'，按中文释义字段 (chi_exp) 搜索；
-        3. 优先以输入开头的匹配；
-        4. 其次为包含输入但不以其开头的匹配（按 freq 排序）。
-    :return: [{'id': 1, 'proverb': 'xxx'}, ...]
+        model: Tortoise ORM 模型类，例如 ProverbFr
+        proverb_field: 外语谚语字段名
+        chi_exp_field: 中文释义字段名
+        limit: 每类匹配的最大返回数量
+
+    搜索逻辑:
+        1. 根据语言选择搜索字段；
+        2. 优先匹配以输入开头的结果；
+        3. 其次匹配包含输入但非开头的结果；
+        4. 合并去重后返回。
     """
-    keyword = query.query.strip()
-    results: List[Dict[str, str]] = []
-
+    keyword = query.strip()
     if not keyword:
-        return results
+        return []
 
-    # ✅ 根据语言决定搜索字段
+    # ✅ 根据语言选择搜索字段
     if lang == "zh":
-        startswith_field = "chi_exp__istartswith"
-        contains_field = "chi_exp__icontains"
-    else:  # 默认法语
-        startswith_field = "proverb__istartswith"
-        contains_field = "proverb__icontains"
+        startswith_field = f"{chi_exp_field}__istartswith"
+        contains_field = f"{chi_exp_field}__icontains"
+    else:
+        startswith_field = f"{search_field}__istartswith"
+        contains_field = f"{search_field}__icontains"
 
     # ✅ 1. 开头匹配
     start_matches = await (
-        ProverbFr.filter(**{startswith_field: keyword})
+        model.filter(**{startswith_field: keyword})
         .order_by("-freq")
-        .limit(10)
-        .values("id", "proverb", "chi_exp")
+        .limit(limit)
+        .values("id", target_field, search_field, chi_exp_field)
     )
 
-    # ✅ 2. 包含匹配（但不是开头）
+    # ✅ 2. 包含匹配（非开头）
     contain_matches = await (
-        ProverbFr.filter(
+        model.filter(
             Q(**{contains_field: keyword}) & ~Q(**{startswith_field: keyword})
         )
         .order_by("-freq")
-        .limit(10)
-        .values("id", "proverb", "chi_exp")
+        .limit(limit)
+        .values("id", target_field, search_field, chi_exp_field)
     )
 
-    # ✅ 合并结果（去重并保持顺序）
+    # ✅ 3. 合并去重并保持顺序
+    results: List[Dict[str, str]] = []
     seen_ids = set()
     for row in start_matches + contain_matches:
         if row["id"] not in seen_ids:
             seen_ids.add(row["id"])
             results.append({
                 "id": row["id"],
-                "proverb": row["proverb"],
-                "chi_exp": row["chi_exp"]
+                "proverb": row[target_field],
+                "search_text": row[search_field],
+                "chi_exp": row[chi_exp_field]
             })
 
     return results
@@ -205,4 +226,5 @@ async def __main():
 
 
 if __name__ == '__main__':
-    asyncio.run(__main())
+    # asyncio.run(__main())
+    print(detect_language(text="ahsjdasd"))

app/api/translator.py

@@ -8,8 +8,8 @@ from fastapi import APIRouter, Depends, HTTPException
 
 from app.models import User
 from app.schemas.trans_schemas import TransResponse, TransRequest
+from app.utils.md5 import make_md5
 from app.utils.security import is_admin_user, get_current_user
-from scripts.md5 import make_md5
 from settings import settings
 
 translator_router = APIRouter()

app/models/fr.py

@@ -45,11 +45,11 @@ class DefinitionFr(Model):
 
 class ProverbFr(Model):
     id = fields.IntField(pk=True)
-    proverb = fields.TextField(description="法语谚语及常用表达")
+    text = fields.TextField(description="法语谚语及常用表达")
     chi_exp = fields.TextField(description="中文释义")
     freq = fields.IntField(default=0)
+    search_text = fields.TextField()
     created_at = fields.DatetimeField(auto_now_add=True)
-    updated_at = fields.DatetimeField(auto_now=True)
 
     class Meta:
         table = "proverb_fr"

app/models/jp.py

@@ -87,3 +87,14 @@ class PronunciationTestJp(Model):
 
     class Meta:
         table = "pronunciationtest_jp"
+
+class IdiomJp(Model):
+    id = fields.IntField(pk=True)
+    text = fields.TextField(null=False)
+    chi_exp = fields.TextField(null=False)
+    example = fields.TextField(null=False)
+    search_text = fields.TextField(null=False)
+    created_at = fields.DatetimeField(auto_now_add=True)
+
+    class Meta:
+        table = "idiom_jp"

main.py

@@ -18,7 +18,7 @@ from app.api.user.routes import users_router
 from app.api.word_comment.routes import word_comment_router
 from app.core.redis import init_redis, close_redis
 from app.utils.phone_encrypt import PhoneEncrypt
-from settings import ONLINE_SETTINGS
+from settings import TORTOISE_ORM
 
 
 @asynccontextmanager
@@ -46,7 +46,7 @@ app.add_middleware(
 
 register_tortoise(
     app=app,
-    config=ONLINE_SETTINGS,
+    config=TORTOISE_ORM,
 )
 
 app.include_router(users_router, tags=["User API"], prefix="/users")

scripts/update_fr.py

@@ -2,7 +2,7 @@ import asyncio
 from pathlib import Path
 
 import pandas as pd
-from tortoise import Tortoise, connections
+from tortoise import Tortoise
 from tortoise.exceptions import MultipleObjectsReturned
 
 from app.models.fr import DefinitionFr, WordlistFr
@@ -101,14 +101,13 @@ async def varification_eg():
 
 async def main():
     await Tortoise.init(config=TORTOISE_ORM)
-    await DefinitionFr.all().delete()   # TRUNCATE TABLE definitions_fr;
-    conn = connections.get("default")
-    await conn.execute_script("""
-        ALTER TABLE definitions_fr AUTO_INCREMENT = 1;
-    """)
-    await import_def_fr()
-    # await import_wordlist_fr()
-
+    #     await DefinitionFr.all().delete()   # TRUNCATE TABLE definitions_fr;
+    #     conn = connections.get("default")
+    #     await conn.execute_script("""
+    #         ALTER TABLE definitions_fr AUTO_INCREMENT = 1;
+    #     """)
+    #     await import_def_fr()
+    #     # await import_wordlist_fr()
 
 if __name__ == "__main__":
     asyncio.run(main())

scripts/update_jp.py

@@ -1,21 +1,21 @@
 import asyncio
 import re
 import unicodedata
-import jaconv
+from importlib import resources
 from pathlib import Path
 
+import jaconv
 import pandas as pd
 from fugashi import Tagger
-import unidic_lite
-from importlib import resources
 from pykakasi import kakasi
 from tortoise import Tortoise
 from tortoise.exceptions import MultipleObjectsReturned
 
 from app.models import WordlistJp, DefinitionJp, AttachmentJp, PosType
+from app.models.jp import IdiomJp
 from settings import TORTOISE_ORM
 
-xlsx_name = "./DictTable-20250823.xlsx"
+xlsx_name = "./DictTable_20251029.xlsx"
 xlsx_path = Path(xlsx_name)
 
 
@@ -228,6 +228,24 @@ async def set_hiragana(xlsx_path: Path = xlsx_path, sheet_name : str="日汉释
 
         await WordlistJp.filter(text=word).update(hiragana=hiragana)
 
+async def import_idiom():
+    path = xlsx_path
+    df = pd.read_excel(path, sheet_name="日语惯用语")
+    df.columns = [col.strip() for col in df.columns]
+
+    for row in df.itertuples():
+        sentence = str(row[1]).strip()
+        search_text = str(row[2]).strip()
+        chi_exp = str(row[3]).strip()
+        example = str(row[4]).strip()
+
+        await IdiomJp.create(
+            text=sentence,
+            chi_exp=chi_exp,
+            example=example,
+            search_text=search_text,
+        )
+
 
 async def main():
     await Tortoise.init(config=TORTOISE_ORM)
@@ -237,8 +255,8 @@ async def main():
     # await import_wordlist_jp()
     # await import_def_jp()
     # await import_attachment()
-    await set_hiragana()
-
+    # await set_hiragana()
+    await import_idiom()
 
 if __name__ == '__main__':
     asyncio.run(main())