更新谚语搜索，调整搜索函数

README.md

@@ -344,8 +344,9 @@ Authorization: Bearer <your_jwt_token>
 ```json
 {
   "result": {
-    "proverb_text": "Petit à petit, l'oiseau fait son nid.",
-    "chi_exp": "循序渐进才能取得成功。"
+    "text": "Petit à petit, l'oiseau fait son nid.",
+    "chi_exp": "循序渐进才能取得成功。",
+    "freq": 128
   }
 }
 ```
@@ -356,7 +357,7 @@ Authorization: Bearer <your_jwt_token>
 
 #### 2.3 单词联想建议
 
-- **接口**: `POST /search/word/list`
+- **接口**: `POST /search/list/word`
 - **描述**: 根据用户输入返回单词联想列表，含前缀匹配与包含匹配。
 - **需要认证**: 是
 - **请求体**:
@@ -380,16 +381,20 @@ Authorization: Bearer <your_jwt_token>
 
 > **说明**: `language = "jp"` 时返回形如 `[["愛", "あい"], ["愛する", "あいする"]]` 的二维数组，第二列为假名读音。
 
+- **状态码**:
+  - `200`: 查询成功
+
 #### 2.4 谚语联想建议
 
-- **接口**: `POST /search/proverb/list`
+- **接口**: `POST /search/list/proverb`
 - **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"
+  "query": "慢",
+  "dict_language": "fr"
 }
 ```
 
@@ -410,6 +415,64 @@ Authorization: Bearer <your_jwt_token>
 - **状态码**:
   - `200`: 查询成功
 
+#### 2.5 日语惯用语联想建议
+
+- **接口**: `POST /search/list/idiom`
+- **描述**: 针对日语惯用语返回联想候选，支持输入日文假名或中文汉字；若输入匹配汉字映射表，会并发查询假名结果并合并输出。
+- **需要认证**: 是
+- **请求体**:
+
+```json
+{
+  "query": "愛してる",
+  "dict_language": "jp"
+}
+```
+
+- **响应示例**:
+
+```json
+{
+  "list": [
+    {
+      "id": 21,
+      "proverb": "愛してる",
+      "chi_exp": "我爱你"
+    }
+  ]
+}
+```
+
+- **状态码**:
+  - `200`: 查询成功
+  - `400`: 当 `dict_language` 不是 `jp` 时返回错误信息
+
+#### 2.6 日语惯用语详情
+
+- **接口**: `POST /search/idiom`
+- **描述**: 根据惯用语 ID 返回详细信息并增加访问频次。
+- **需要认证**: 是
+- **查询参数**:
+  - `query_id`: 惯用语 ID (integer)
+- **响应示例**:
+
+```json
+{
+  "result": {
+    "id": 21,
+    "text": "愛してる",
+    "search_text": "あいしてる",
+    "chi_exp": "我爱你",
+    "example": "私はあなたを愛してる。",
+    "freq": 57
+  }
+}
+```
+
+- **状态码**:
+  - `200`: 查询成功
+  - `404`: 惯用语不存在
+
 ---
 
 ### 3. 翻译模块 (`/translate`)
@@ -1061,7 +1124,7 @@ curl -X POST "http://127.0.0.1:8000/search/word" \
   }'
 
 # 4. 获取单词联想列表
-curl -X POST "http://127.0.0.1:8000/search/word/list" \
+curl -X POST "http://127.0.0.1:8000/search/list/word" \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer <your_token_here>" \
   -d '{

app/api/search_dict/routes.py

@@ -1,3 +1,4 @@
+import asyncio
 from typing import Literal, List
 
 from fastapi import APIRouter, Depends, HTTPException, Request, Form
@@ -5,7 +6,7 @@ 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, \
     ProverbSearchRequest
-from app.api.search_dict.service import suggest_autocomplete, accurate_proverb
+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, ProverbFr
@@ -136,23 +137,10 @@ async def search(request: Request, body: SearchRequest, user=Depends(get_current
         )
 
 
-@dict_search.post("/search/proverb")
-async def proverb(request: Request, proverb_id: int, user=Depends(get_current_user)):
-    """
-    用于法语谚语搜索
-    :param request:
-    :param body: 要求用户输入的内容必须为法语
-    :param user:
-    :return:
-    """
-    content = await service.accurate_proverb(proverb_id=proverb_id)
-    return content
-
-
 # TODO 相关度排序（转换为模糊匹配）
 # TODO 输入搜索框时反馈内容
 
-@dict_search.post("/search/word/list")
+@dict_search.post("/search/list/word")
 async def search_word_list(query_word: SearchRequest, user=Depends(get_current_user)):
     """
     检索时的提示接口
@@ -165,9 +153,9 @@ async def search_word_list(query_word: SearchRequest, user=Depends(get_current_u
     return {"list": word_contents}
 
 
-@dict_search.post("/search/proverb/list")
+@dict_search.post("/search/list/proverb")
 async def search_proverb_list(query_word: ProverbSearchRequest, user=Depends(get_current_user)):
-    lang = service.detect_language(text=query_word.query)[1]
+    query, 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,
@@ -180,35 +168,53 @@ async def search_proverb_list(query_word: ProverbSearchRequest, user=Depends(get
 
 @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)
+    result = await service.accurate_idiom_proverb(search_id=proverb_id, model=ProverbFr, only_fields=["text", "chi_exp"])
 
     return {"result": result}
 
 
-@dict_search.post("/search/idiom/list")
-async def search_idiom_list(query_idiom: ProverbSearchRequest):
+@dict_search.post("/search/list/idiom")
+async def search_idiom_list(query_idiom: ProverbSearchRequest, user=Depends(get_current_user)):
     if query_idiom.dict_language == "fr":
         raise HTTPException(status_code=400, detail="Dict language Error")
-    trad_query, lang = service.detect_language(text=query_idiom.query)
+
+    mapping_query, lang, is_kangji = await service.detect_language(text=query_idiom.query)
     query = all_in_kana(text=query_idiom.query) if lang == "jp" else query_idiom.query
-    result = await service.suggest_proverb(
+
+    # ✅ 并发任务列表
+    tasks = [
+        service.suggest_proverb(
             query=query,
             lang=lang,
             model=IdiomJp,
             search_field="search_text",
             target_field="text",
         )
-    if lang == "zh":
-        trad_query = all_in_kana(text=query_idiom.query)
-        search_idioms_from_chi = await service.suggest_proverb(
-            query=trad_query,
+    ]
+
+    if lang == "zh" and is_kangji:
+        # jp_query = all_in_kana(text=query_idiom.query)
+        tasks.append(
+            service.suggest_proverb(
+                query=mapping_query,
                 lang="jp",
                 model=IdiomJp,
+                search_field="text",
             )
-        result[:0] = search_idioms_from_chi
+        )
+
+    # ✅ 并发执行（返回结果顺序与任务顺序一致）
+    results = await asyncio.gather(*tasks)
+
+    # ✅ 合并结果
+    result = results[0]
+    if len(results) > 1:
+        result[:0] = results[1]  # 将中文映射查询结果插到最前面
+
     return {"list": result}
 
+
 @dict_search.post("/search/idiom")
-async def search_idiom(query_id: int):
-    result = await accurate_proverb(proverb_id=query_id)
+async def search_idiom(query_id: int, user=Depends(get_current_user)):
+    result = await service.accurate_idiom_proverb(search_id=query_id, model=IdiomJp, only_fields=["id", "text", "search_text", "chi_exp", "example"])
     return {"result": result}

app/api/search_dict/service.py

@@ -2,83 +2,70 @@ import re
 from typing import List, Tuple, Dict, Literal, Type
 
 from fastapi import HTTPException
-from opencc import OpenCC
 from tortoise import Tortoise, Model
 from tortoise.expressions import Q
 
-from app.api.search_dict.search_schemas import SearchRequest, ProverbSearchResponse, ProverbSearchRequest
-from app.models import WordlistFr, WordlistJp
-from app.models.fr import ProverbFr
+from app.api.search_dict.search_schemas import SearchRequest, ProverbSearchRequest
+from app.models import WordlistFr, WordlistJp, KangjiMapping
 from app.utils.all_kana import all_in_kana
 from app.utils.textnorm import normalize_text
 from settings import TORTOISE_ORM
 
 
-def detect_language(text: str) -> Tuple[str, Literal["fr", "zh", "jp", "other"]]:
+async def detect_language(text: str) -> Tuple[str, str, bool]:
     """
     自动检测输入语言:
         - zh: 简体中文
-        - jp: 日语（含假名或繁体/旧体字）
+        - jp: 日语（含假名或旧字体）
         - fr: 拉丁字母（法语等）
         - other: 其他
-    """
-    cc_s2t = OpenCC('s2t')  # 简体 → 繁体
-    cc_t2s = OpenCC('t2s')  # 繁体 → 简体
 
+    返回:
+        (映射或原文本, 语言代码, 是否为“含汉字且命中映射表”的情况)
+    """
     JAPANESE_HIRAGANA = r"[\u3040-\u309F]"
     JAPANESE_KATAKANA = r"[\u30A0-\u30FF\u31F0-\u31FF]"
 
     text = text.strip()
     if not text:
-        return "", "other"
+        return "", "other", False
 
-    # ✅ Step 1: 假名检测
-    if re.search(JAPANESE_HIRAGANA, text) or re.search(JAPANESE_KATAKANA, text):
-        return text, "jp"
+    # ✅ Step 1: 全部假名（无汉字）
+    if re.fullmatch(f"(?:{JAPANESE_HIRAGANA}|{JAPANESE_KATAKANA})+", text):
+        return text, "jp", False
 
     # ✅ Step 2: 汉字检测
     if re.search(r"[\u4e00-\u9fff]", text):
-        # 简繁互转对比
-        to_trad = cc_s2t.convert(text)
-        to_simp = cc_t2s.convert(text)
+        # 优先判断是否为日语汉字
+        jp_match = await KangjiMapping.get_or_none(kangji=text).only("kangji")
+        if jp_match:
+            return text, "jp", True  # 含汉字且命中日语列
 
-        # 如果输入等于繁体转换结果 → 繁体或日文汉字
-        if text == to_trad and text != to_simp:
-            return text, "jp"
-        # 如果输入等于简体转换结果 → 简体中文
-        elif text == to_simp and text != to_trad:
-            return to_trad, "zh"  # 注意返回的是繁体形式用于补充搜索
-        # 否则混合（既有简体又有繁体）
-        else:
-            # 混合时可优先认定为繁体（日语）
-            return to_trad, "jp"
+        # 再检查是否为中文汉字
+        zh_match = await KangjiMapping.get_or_none(hanzi=text).only("hanzi", "kangji")
+        if zh_match:
+            return zh_match.kangji, "zh", True  # 含汉字且命中中文列
 
-    # ✅ Step 3: 拉丁字母检测
+        # 若都不在映射表中，则为未映射的中文
+        return text, "zh", False
+
+    # ✅ Step 3: 拉丁字母检测（如法语）
     if re.search(r"[a-zA-ZÀ-ÿ]", text):
-        return text, "fr"
+        return text, "fr", False
 
-    return text, "other"
+    # ✅ Step 4: 其他情况（符号、空格等）
+    return text, "other", False
 
 
-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")
-    proverb.freq = proverb.freq + 1
-    await proverb.save()
-    return ProverbSearchResponse(
-        proverb_text=proverb.text,
-        chi_exp=proverb.chi_exp,
-    )
-
-async def accurate_idiom(idiom_id: int):
-    proverb = await ProverbFr.get_or_none(id=idiom_id)
-    if not proverb:
-        raise HTTPException(status_code=404, detail="Proverb not found")
-    proverb.freq = proverb.freq + 1
-    await proverb.save()
-    return proverb
+async def accurate_idiom_proverb(search_id: int, model: Type[Model], only_fields: List[str] = None):
+    if "freq" not in only_fields:
+        only_fields.append("freq")
+    result = await model.get_or_none(id=search_id).only(*only_fields)
+    if not result:
+        raise HTTPException(status_code=404, detail="Target not found")
+    result.freq = result.freq + 1
+    await result.save(update_fields=["freq"])
+    return result
 
 
 async def suggest_proverb(
@@ -90,54 +77,37 @@ async def suggest_proverb(
         chi_exp_field: str = "chi_exp",
         limit: int = 10,
 ) -> List[Dict[str, str]]:
-    """
-    通用搜索建议函数，用于多语言谚语表。
-    参数:
-        query: 搜索关键词
-        lang: 'fr' 或 'zh'
-        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.strip()
     if not keyword:
         return []
 
-    # ✅ 根据语言选择搜索字段
+    # ✅ 搜索条件：中文时双字段联合匹配
     if lang == "zh":
-        startswith_field = f"{chi_exp_field}__istartswith"
-        contains_field = f"{chi_exp_field}__icontains"
+        start_condition = Q(**{f"{chi_exp_field}__istartswith": keyword}) | Q(
+            **{f"{search_field}__istartswith": keyword})
+        contain_condition = Q(**{f"{chi_exp_field}__icontains": keyword}) | Q(**{f"{search_field}__icontains": keyword})
     else:
-        startswith_field = f"{search_field}__istartswith"
-        contains_field = f"{search_field}__icontains"
+        start_condition = Q(**{f"{search_field}__istartswith": keyword})
+        contain_condition = Q(**{f"{search_field}__icontains": keyword})
 
     # ✅ 1. 开头匹配
     start_matches = await (
-        model.filter(**{startswith_field: keyword})
-        .order_by("-freq")
+        model.filter(start_condition)
+        .order_by("-freq", "id")
         .limit(limit)
-        .values("id", target_field, search_field, chi_exp_field)
+        .values("id", target_field, chi_exp_field, "search_text")
     )
 
-    # ✅ 2. 包含匹配（非开头）
+    # ✅ 2. 包含匹配（但不是开头）
     contain_matches = await (
-        model.filter(
-            Q(**{contains_field: keyword}) & ~Q(**{startswith_field: keyword})
-        )
-        .order_by("-freq")
+        model.filter(contain_condition & ~start_condition)
+        .order_by("-freq", "id")
         .limit(limit)
-        .values("id", target_field, search_field, chi_exp_field)
+        .values("id", target_field, chi_exp_field, "search_text")
     )
 
-    # ✅ 3. 合并去重并保持顺序
-    results: List[Dict[str, str]] = []
+    # ✅ 3. 合并去重保持顺序
+    results = []
     seen_ids = set()
     for row in start_matches + contain_matches:
         if row["id"] not in seen_ids:
@@ -145,11 +115,12 @@ async def suggest_proverb(
             results.append({
                 "id": row["id"],
                 "proverb": row[target_field],
-                "search_text": row[search_field],
-                "chi_exp": row[chi_exp_field]
+                "search_text": row["search_text"],
+                "chi_exp": row[chi_exp_field],
             })
 
-    return results
+    # ✅ 截断最终返回数量
+    return results[:limit]
 
 
 async def suggest_autocomplete(query: SearchRequest, limit: int = 10):

app/models/jp.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Tuple, TypeVar
+from typing import Tuple, TypeVar, Optional
 
 import pandas as pd
 from tortoise import fields
@@ -74,6 +74,7 @@ class DefinitionJp(Model):
     class Meta:
         table = "definitions_jp"
 
+
 class PosType(Model):
     id = fields.IntField(pk=True)
     pos_type = fields.CharEnumField(PosEnumJp, max_length=30, null=False)
@@ -81,6 +82,7 @@ class PosType(Model):
     class Meta:
         table = "pos_type"
 
+
 class PronunciationTestJp(Model):
     id = fields.IntField(pk=True)
     text = fields.TextField(description="朗读文段")
@@ -88,6 +90,7 @@ class PronunciationTestJp(Model):
     class Meta:
         table = "pronunciationtest_jp"
 
+
 class IdiomJp(Model):
     id = fields.IntField(pk=True)
     text = fields.TextField(null=False)
@@ -100,6 +103,7 @@ class IdiomJp(Model):
     class Meta:
         table = "idiom_jp"
 
+
 class KangjiMapping(Model):
     id = fields.IntField(pk=True)
     hanzi = fields.TextField(null=False)
@@ -107,5 +111,12 @@ class KangjiMapping(Model):
     note = fields.TextField(null=False)
     created_at = fields.DatetimeField(auto_now_add=True)
 
+    @classmethod
+    async def chi2kangji(text_chi: str) -> Optional[str]:
+        mapping = await KangjiMapping.get_or_none(hanzi=text_chi)
+        if not mapping:
+            return None
+        return mapping.kangji
+
     class Meta:
         table = "kangji_mapping_zh_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 TORTOISE_ORM
+from settings import ONLINE_SETTINGS
 
 
 @asynccontextmanager
@@ -46,7 +46,7 @@ app.add_middleware(
 
 register_tortoise(
     app=app,
-    config=TORTOISE_ORM,
+    config=ONLINE_SETTINGS,
 )
 
 app.include_router(users_router, tags=["User API"], prefix="/users")