rquote 0.4.1__py3-none-any.whl → 0.4.3__py3-none-any.whl

rquote/cache/persistent.py

@@ -232,7 +232,7 @@ class PersistentCache(Cache):
                     freq: str, fq: str) -> Optional[Tuple[str, str, pd.DataFrame]]:
         """从 duckdb 获取数据"""
         result = self.conn.execute("""
-            SELECT name, data, earliest_date, latest_date, expire_at
+            SELECT name, data, expire_at
             FROM cache_data
             WHERE cache_key = ?
         """, [base_key]).fetchone()
@@ -240,7 +240,7 @@ class PersistentCache(Cache):
         if not result:
             return None
         
-        name, data_blob, earliest_date, latest_date, expire_at = result
+        name, data_blob, expire_at = result
         
         # 检查过期
         if self.ttl and expire_at:
@@ -253,44 +253,44 @@ class PersistentCache(Cache):
         import pickle
         df = pickle.loads(data_blob)
         
-        # 获取缓存数据的日期范围
-        cached_earliest = self._parse_date(earliest_date)
-        cached_latest = self._parse_date(latest_date)
+        # 确保索引是 DatetimeIndex
+        if not isinstance(df.index, pd.DatetimeIndex):
+            try:
+                df.index = pd.to_datetime(df.index)
+            except (ValueError, TypeError):
+                return None
+        
+        if df.empty:
+            return None
         
-        # 如果请求的日期范围完全在缓存范围内，直接返回过滤后的数据
+        # 直接从 DataFrame 索引获取实际的日期范围
+        cached_earliest = df.index.min()
+        cached_latest = df.index.max()
+        
+        # 解析请求的日期范围
         request_sdate = self._parse_date(sdate) if sdate else None
         request_edate = self._parse_date(edate) if edate else None
         
-        # 检查是否有重叠
-        if request_edate and cached_earliest and request_edate < cached_earliest:
+        # 检查是否有重叠：如果请求的日期范围与缓存数据有重叠，就返回过滤后的数据
+        # 注意：即使缓存中有部分数据，也应该返回（让上层决定是否需要扩展）
+        has_overlap = True
+        if request_edate and request_edate < cached_earliest:
             # 请求的结束日期早于缓存的最早日期，无重叠
-            return None
-        if request_sdate and cached_latest and request_sdate > cached_latest:
+            has_overlap = False
+        if request_sdate and request_sdate > cached_latest:
             # 请求的开始日期晚于缓存的最晚日期，无重叠
-            return None
+            has_overlap = False
         
-        # 有重叠，返回缓存中可用的部分数据
-        # 计算实际可用的日期范围
-        actual_sdate = max(request_sdate, cached_earliest) if request_sdate and cached_earliest else (request_sdate or cached_earliest)
-        actual_edate = min(request_edate, cached_latest) if request_edate and cached_latest else (request_edate or cached_latest)
+        if not has_overlap:
+            return None
         
-        # 过滤数据
-        filtered_df = self._filter_dataframe_by_date(
-            df, 
-            actual_sdate.strftime('%Y-%m-%d') if actual_sdate else None,
-            actual_edate.strftime('%Y-%m-%d') if actual_edate else None
-        )
+        # 按照请求的日期范围过滤数据（即使缓存中有更多数据，也只返回请求范围内的）
+        # 重要：必须按照 edate 截取，和从网络获取的行为一致
+        filtered_df = self._filter_dataframe_by_date(df, sdate, edate)
         
         if filtered_df.empty:
             return None
         
-        # 确保索引是 DatetimeIndex
-        if not isinstance(filtered_df.index, pd.DatetimeIndex):
-            try:
-                filtered_df.index = pd.to_datetime(filtered_df.index)
-            except (ValueError, TypeError):
-                pass  # 如果转换失败，保持原样
-        
         return (symbol, name, filtered_df)
     
     def _get_pickle(self, base_key: str, symbol: str, sdate: str, edate: str,
@@ -311,47 +311,45 @@ class PersistentCache(Cache):
         
         df = cache_entry['data']
         name = cache_entry.get('name', '')
-        earliest_date = cache_entry.get('earliest_date')
-        latest_date = cache_entry.get('latest_date')
         
-        # 获取缓存数据的日期范围
-        cached_earliest = self._parse_date(earliest_date)
-        cached_latest = self._parse_date(latest_date)
+        # 确保索引是 DatetimeIndex
+        if not isinstance(df.index, pd.DatetimeIndex):
+            try:
+                df.index = pd.to_datetime(df.index)
+            except (ValueError, TypeError):
+                return None
+        
+        if df.empty:
+            return None
+        
+        # 直接从 DataFrame 索引获取实际的日期范围
+        cached_earliest = df.index.min()
+        cached_latest = df.index.max()
         
-        # 如果请求的日期范围完全在缓存范围内，直接返回过滤后的数据
+        # 解析请求的日期范围
         request_sdate = self._parse_date(sdate) if sdate else None
         request_edate = self._parse_date(edate) if edate else None
         
-        # 检查是否有重叠
-        if request_edate and cached_earliest and request_edate < cached_earliest:
+        # 检查是否有重叠：如果请求的日期范围与缓存数据有重叠，就返回过滤后的数据
+        # 注意：即使缓存中有部分数据，也应该返回（让上层决定是否需要扩展）
+        has_overlap = True
+        if request_edate and request_edate < cached_earliest:
             # 请求的结束日期早于缓存的最早日期，无重叠
-            return None
-        if request_sdate and cached_latest and request_sdate > cached_latest:
+            has_overlap = False
+        if request_sdate and request_sdate > cached_latest:
             # 请求的开始日期晚于缓存的最晚日期，无重叠
-            return None
+            has_overlap = False
         
-        # 有重叠，返回缓存中可用的部分数据
-        # 计算实际可用的日期范围
-        actual_sdate = max(request_sdate, cached_earliest) if request_sdate and cached_earliest else (request_sdate or cached_earliest)
-        actual_edate = min(request_edate, cached_latest) if request_edate and cached_latest else (request_edate or cached_latest)
+        if not has_overlap:
+            return None
         
-        # 过滤数据
-        filtered_df = self._filter_dataframe_by_date(
-            df,
-            actual_sdate.strftime('%Y-%m-%d') if actual_sdate else None,
-            actual_edate.strftime('%Y-%m-%d') if actual_edate else None
-        )
+        # 按照请求的日期范围过滤数据（即使缓存中有更多数据，也只返回请求范围内的）
+        # 重要：必须按照 edate 截取，和从网络获取的行为一致
+        filtered_df = self._filter_dataframe_by_date(df, sdate, edate)
         
         if filtered_df.empty:
             return None
         
-        # 确保索引是 DatetimeIndex
-        if not isinstance(filtered_df.index, pd.DatetimeIndex):
-            try:
-                filtered_df.index = pd.to_datetime(filtered_df.index)
-            except (ValueError, TypeError):
-                pass  # 如果转换失败，保持原样
-        
         return (symbol, name, filtered_df)
     
     def put(self, key: str, value: Any, ttl: Optional[int] = None) -> None:
@@ -449,7 +447,10 @@ class PersistentCache(Cache):
     def _put_duckdb(self, base_key: str, symbol: str, name: str, df: pd.DataFrame,
                      earliest_date: Optional[str], latest_date: Optional[str],
                      freq: str, fq: str, expire_at: Optional[pd.Timestamp]):
-        """存储到 duckdb"""
+        """存储到 duckdb
+        
+        注意：earliest_date 和 latest_date 仅用于记录，实际查询时从 DataFrame 索引获取
+        """
         import pickle
         data_blob = pickle.dumps(df)
         

rquote/utils/logging.py

@@ -3,20 +3,40 @@
 日志工具
 """
 import logging
+import os
 
 
 def setup_logger():
     """设置日志记录器"""
     logger = logging.getLogger('rquote')
     if not logger.handlers:
-        logger.setLevel(logging.INFO)
-        file_handler = logging.FileHandler('/tmp/rquote.log')
+        # 默认关闭日志，通过环境变量 RQUOTE_LOG_LEVEL 控制
+        log_level = os.getenv('RQUOTE_LOG_LEVEL', '').upper()
+        log_file = os.getenv('RQUOTE_LOG_FILE', '/tmp/rquote.log')
         
-        formatter = logging.Formatter('%(asctime)-15s:%(lineno)s %(message)s')
-        file_handler.setFormatter(formatter)
-        
-        logger.addHandler(file_handler)
-        logger.addHandler(logging.StreamHandler())
+        # 如果设置了有效的日志级别，则启用日志
+        if log_level in ('DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'):
+            # 将字符串级别转换为logging级别
+            level_map = {
+                'DEBUG': logging.DEBUG,
+                'INFO': logging.INFO,
+                'WARNING': logging.WARNING,
+                'ERROR': logging.ERROR,
+                'CRITICAL': logging.CRITICAL,
+            }
+            logger.setLevel(level_map[log_level])
+            
+            # 添加文件handler
+            file_handler = logging.FileHandler(log_file)
+            formatter = logging.Formatter('%(asctime)-15s:%(lineno)s %(message)s')
+            file_handler.setFormatter(formatter)
+            logger.addHandler(file_handler)
+            
+            # 添加控制台handler
+            logger.addHandler(logging.StreamHandler())
+        else:
+            # 默认关闭日志：设置为CRITICAL级别，不添加handler
+            logger.setLevel(logging.CRITICAL)
     
     return logger
 

{rquote-0.4.1.dist-info → rquote-0.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rquote
-Version: 0.4.1
+Version: 0.4.3
 Summary: Mostly day quotes of cn/hk/us/fund/future markets, side with quote list fetch
 Requires-Python: >=3.9.0
 Description-Content-Type: text/markdown
@@ -18,7 +18,7 @@ Requires-Dist: duckdb>=0.9.0; extra == "persistent"
 
 ## 版本信息
 
-当前版本：**0.4.1**
+当前版本：**0.4.3**
 
 ## 主要特性
 
@@ -346,6 +346,50 @@ os.environ['RQUOTE_HTTP_TIMEOUT'] = '20'
 config_from_env = config.Config.from_env()
 ```
 
+### 日志配置
+
+**默认情况下，日志功能是关闭的。** 如果需要启用日志，可以通过环境变量手动开启：
+
+#### 通过环境变量开启日志
+
+```bash
+# 设置日志级别为 INFO（会同时输出到文件和控制台）
+export RQUOTE_LOG_LEVEL=INFO
+
+# 可选：自定义日志文件路径（默认为 /tmp/rquote.log）
+export RQUOTE_LOG_FILE=/path/to/your/logfile.log
+
+# 然后运行你的Python脚本
+python your_script.py
+```
+
+#### 支持的日志级别
+
+- `DEBUG`: 详细的调试信息
+- `INFO`: 一般信息（推荐）
+- `WARNING`: 警告信息
+- `ERROR`: 错误信息
+- `CRITICAL`: 严重错误
+
+#### 在Python代码中开启日志
+
+```python
+import os
+
+# 在导入 rquote 之前设置环境变量
+os.environ['RQUOTE_LOG_LEVEL'] = 'INFO'
+os.environ['RQUOTE_LOG_FILE'] = '/tmp/rquote.log'  # 可选
+
+from rquote import get_price
+
+# 现在日志已启用
+sid, name, df = get_price('sh000001')
+```
+
+#### 关闭日志
+
+如果不设置 `RQUOTE_LOG_LEVEL` 环境变量，或者设置为空值，日志功能将保持关闭状态（默认行为）。
+
 ### 使用改进的HTTP客户端
 
 ```python

{rquote-0.4.1.dist-info → rquote-0.4.3.dist-info}/RECORD

@@ -11,7 +11,7 @@ rquote/api/tick.py,sha256=nEcjuAjtBHUaD8KPRLg643piVa21PhKDQvkVWNwvvME,1431
 rquote/cache/__init__.py,sha256=S393I5Wmp0QooaRka9n7bvDUdEbg3jUhm6u815T86rM,317
 rquote/cache/base.py,sha256=orzG4Yo-6gzVG027j1-LTZPT718JohnCdLDnOLoLUQ4,515
 rquote/cache/memory.py,sha256=7z4keb3q91pzI4ASQWy1MU8T5nbWLCEUjJcStv_3hvk,1933
-rquote/cache/persistent.py,sha256=ZffpM1a_ngRTjvHvPwk3XoorH87TSCBwtrXtvO0yqBo,19751
+rquote/cache/persistent.py,sha256=dgzH_rKVwUzuYTxsIWEHX2orixFesWd-sIUJ7TwbS7Y,19369
 rquote/data_sources/__init__.py,sha256=WCe1aam4677jM5G6wP4a-dQFTeBzcU5PJqsKieAVMBo,215
 rquote/data_sources/base.py,sha256=JuKsTMxH7y8yRxHg3JbLzQwXPr43rS4pnwc5625u2U4,443
 rquote/data_sources/sina.py,sha256=T_3Dl0Mwlhx8CKRJll_UKobYecRWltGaIOiGkpHS43Q,3300
@@ -31,9 +31,9 @@ rquote/utils/__init__.py,sha256=-ZHABqFHQeJrCCsgnqEYWR57jl7GduCKn2V3hpFi-pE,348
 rquote/utils/date.py,sha256=nhK3xQ2kFvKhdkPw-2HR2V0PSzBfXmX8L7laG7VmG2E,913
 rquote/utils/helpers.py,sha256=V07n9BtRS8bEJH023Kca78-unk7iD3B9hn2UjELetYs,354
 rquote/utils/http.py,sha256=X0Alhnu0CNqyQeOt6ivUWmh2XwrWxXd2lSpQOKDdnzw,3249
-rquote/utils/logging.py,sha256=cbeRH4ODazn7iyQmGoEBT2lH5LX4Ca3zDfs_20J1T28,566
+rquote/utils/logging.py,sha256=fs2YF1Srux4LLTdk_Grjm5g1f4mzewI38VVSAI82goA,1471
 rquote/utils/web.py,sha256=I8_pcThW6VUvahuRHdtp32iZwr85hEt1hB6TgznMy_U,3854
-rquote-0.4.1.dist-info/METADATA,sha256=Cp9oRn7ohg_2XmhczYDNR2JJMX0MK2aDFjqhP5kJWVA,13259
-rquote-0.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rquote-0.4.1.dist-info/top_level.txt,sha256=CehAiaZx7Fo8HGoV2zd5GhILUW1jQEN8YS-cWMlrK9Y,7
-rquote-0.4.1.dist-info/RECORD,,
+rquote-0.4.3.dist-info/METADATA,sha256=R9zS71G3lxp8C43qrY67DBn2Y2t_1P7rTtCztfj7Kq8,14344
+rquote-0.4.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rquote-0.4.3.dist-info/top_level.txt,sha256=CehAiaZx7Fo8HGoV2zd5GhILUW1jQEN8YS-cWMlrK9Y,7
+rquote-0.4.3.dist-info/RECORD,,