re-common 10.0.42__py3-none-any.whl → 10.0.43__py3-none-any.whl

re_common/v2/baselibrary/s3object/baseaioboto3.py

@@ -1,8 +1,17 @@
+import gzip
+import io
+from typing import Protocol
+
 import aioboto3
 import aiofiles
 from aiobotocore.config import AioConfig
 
 
+class AsyncReadable(Protocol):
+    async def read(self, n: int = -1) -> bytes:
+        ...
+
+
 # config = AioConfig(connect_timeout=600000, read_timeout=600000, retries={'max_attempts': 3},
 #                    max_pool_connections=10)
 
@@ -10,6 +19,15 @@ class BaseAioBoto3(object):
 
     def __init__(self, aws_access_key_id, aws_secret_access_key, endpoint_url,
                  config=AioConfig(max_pool_connections=10)):
+        """
+          初始化华为云 OBS 客户端
+
+          Args:
+              access_key: 华为云 Access Key
+              secret_key: 华为云 Secret Key
+              region: 区域，如 'cn-north-4'
+              endpoint: 华为云 OBS 端点，可选
+          """
         self.aws_access_key_id = aws_access_key_id
         self.aws_secret_access_key = aws_secret_access_key
         self.endpoint_url = endpoint_url
@@ -20,7 +38,7 @@ class BaseAioBoto3(object):
         if self.boto_session is None:
             self.boto_session = aioboto3.Session(
                 aws_access_key_id=self.aws_access_key_id,
-                aws_secret_access_key=self.aws_secret_access_key,
+                aws_secret_access_key=self.aws_secret_access_key
             )
 
     async def read_minio_data(self, bucket, key):
@@ -30,6 +48,10 @@ class BaseAioBoto3(object):
             result = await s3_ob["Body"].read()
             return result
 
+    def ungzip(self, raw_bytes, encoding="utf-8"):
+        with gzip.GzipFile(fileobj=io.BytesIO(raw_bytes)) as gz:
+            return gz.read().decode(encoding)
+
     # 异步下载大文件
     async def download_file(self, bucket: str, key: str, local_path: str):
         await self.initialize_class_variable()
@@ -46,3 +68,55 @@ class BaseAioBoto3(object):
                     await f.write(chunk)
 
         return local_path
+
+    async def list_files(self, bucket: str, prefix: str, recursive: bool = True):
+        """
+        获取 bucket 下某个“目录”(prefix) 的文件列表
+
+        单文件返回样例 ['server_data/api-title-roc/py_full_organ_dic/', 'server_data/api-title-roc/py_full_organ_dic/part-00000.gz']
+
+        :param bucket: bucket 名
+        :param prefix: 目录前缀，如 'server_data/api-title-roc/'
+        :param recursive: 是否递归子目录
+        :return: List[str] 文件 key 列表
+        """
+        await self.initialize_class_variable()
+        keys = []
+
+        # 非递归时，用 delimiter 模拟目录
+        extra_args = {}
+        if not recursive:
+            extra_args["Delimiter"] = "/"
+
+        async with self.boto_session.client(
+                "s3",
+                endpoint_url=self.endpoint_url,
+                config=self.config
+        ) as s3:
+
+            continuation_token = None
+
+            while True:
+                kwargs = {
+                    "Bucket": bucket,
+                    "Prefix": prefix,
+                    **extra_args
+                }
+                # 下一页的“游标”
+                if continuation_token:
+                    kwargs["ContinuationToken"] = continuation_token
+
+                resp = await s3.list_objects_v2(**kwargs)
+
+                # 文件
+                for obj in resp.get("Contents", []):
+                    keys.append(obj["Key"])
+
+                # 是否还有下一页
+                if resp.get("IsTruncated"):  # 说明还有下一页
+                    # 下一页从哪里继续查
+                    continuation_token = resp.get("NextContinuationToken")
+                else:
+                    break
+
+        return keys

re_common/v2/baselibrary/s3object/huaweiobs.py

@@ -0,0 +1,80 @@
+# pip install pycryptodome==3.10.1
+# pip install esdk-obs-python
+# 引入模块
+import os
+
+from obs import ObsClient, GetObjectHeader
+
+
+class BaseObsClient(object):
+
+    def __init__(self, aws_access_key_id="", aws_secret_access_key="", endpoint_url=""):
+        self.aws_access_key_id = aws_access_key_id
+        self.aws_secret_access_key = aws_secret_access_key
+        self.endpoint_url = endpoint_url
+        self.client = None
+        if self.aws_access_key_id and self.aws_secret_access_key and self.endpoint_url:
+            self.get_client()
+
+    def get_client(self):
+        self.client = ObsClient(access_key_id=self.aws_access_key_id,
+                                secret_access_key=self.aws_secret_access_key,
+                                server=self.endpoint_url)
+        return self
+
+    def close(self):
+        self.client.close()
+
+    def put_object(self, bucket_name, objectKey, body):
+        """
+        直接写内容到文件
+        Args:
+            bucket_name:
+            key:
+            body: 需要
+
+        Returns:
+        """
+        # 上传文本对象
+        resp = self.client.putContent(bucket_name, objectKey, body)
+        # 返回码为2xx时，接口调用成功，否则接口调用失败
+        if resp.status < 300:
+            return True, resp
+        else:
+            return False, resp
+
+
+    def download_memobj(self, bucket_name, objectKey):
+        """
+        return: None
+        """
+        # 指定loadStreamInMemory为True忽略downloadpath路径，将文件的二进制流下载到内存
+        # 二进制下载对象
+        resp = self.client.getObject(bucketName=bucket_name, objectKey=objectKey, loadStreamInMemory=True)
+        # 返回码为2xx时，接口调用成功，否则接口调用失败
+        if resp.status < 300:
+            return True, resp
+        else:
+            return False, resp
+
+    def download_file(self, bucket_name, objectKey,downloadPath):
+        """
+        return: None
+        """
+        headers = GetObjectHeader()
+        resp = self.client.getObject(bucket_name, objectKey, downloadPath, headers=headers)
+        # 返回码为2xx时，接口调用成功，否则接口调用失败
+        if resp.status < 300:
+            return True, resp
+        else:
+            return False, resp
+
+
+    def list_prefixes(self,bucket_name,prefix, max_keys = 100):
+        # 列举桶内对象
+        resp = self.client.listObjects(bucket_name, prefix, max_keys=max_keys, encoding_type='url')
+        # 返回码为2xx时，接口调用成功，否则接口调用失败
+        if resp.status < 300:
+            return True, resp
+        else:
+            return False, resp

re_common/v2/baselibrary/utils/string_bool.py

@@ -15,6 +15,20 @@ def is_all_english_chars(s):
 
 
 def contains_chinese_chars(s):
+    """
+    判断字符串中是否包含中文（汉字）字符
+
+    使用 regex 库（不是内置 re），通过 Unicode 属性 IsHan
+    来匹配任意一个汉字。
+
+    参数:
+        s (str): 待检测的字符串
+
+    返回:
+        bool:
+            True  - 字符串中至少包含一个中文字符
+            False - 字符串中不包含任何中文字符
+    """
     return bool(regex.search(r"[\p{IsHan}]", s))
 
 
@@ -108,56 +122,49 @@ def is_all_symbols(text):
     # 检查每个字符是否属于符号类别
     return all(unicodedata.category(char).startswith(('P', 'S')) for char in text)
 
-
-def is_whole_word_en(sub_str: str, long_str: str) -> bool:
+def is_whole_word_en_re(organ: str, ele_organ: str) -> bool:
     """
-    判断 sub_str 是否作为 long_str 中的一个完整英文单词（不被其他单词嵌套）。
+    与 is_whole_word_en 效果一致
+    """
+    if not organ or not ele_organ:
+        return False
 
-    参数:
-        sub_str: 要搜索的英文子串
-        long_str: 被搜索的字符串
+    pattern = rf"(^|[^a-z0-9-]){re.escape(organ)}([^a-z0-9-]|$)"
+    return re.search(pattern, ele_organ) is not None
 
-    返回:
-        True 表示 sub_str 是一个完整单词；False 表示是部分单词或不匹配。
-    """
-    # 用于 忽略大小写 进行匹配
-    regex_pattern = re.compile(r"[^a-z0-9]", re.IGNORECASE)  # 用于判断非字母数字字符
+def is_whole_word_en(sub_str: str, long_str: str) -> bool:
+    regex_pattern = re.compile(r"[^a-z0-9-]", re.IGNORECASE)
 
     if not sub_str or not long_str:
         return False
 
-    # 检查整段是否完全等于 sub_str
-    if long_str == sub_str:
+    # 使用 startsWith 和 endsWith 检查边界
+    if long_str.startswith(sub_str) and long_str.endswith(sub_str) and len(sub_str) == len(long_str):
         return True
 
-    # 遍历所有 sub_str 的出现位置
-    index = 0
-    while index < len(long_str):
-        # 从字符串 long_str 的第 index 个位置开始，查找子串 sub_str 第一次出现的位置，并把它赋值给 index。
-        index = long_str.find(sub_str, index)
-        if index == -1:
-            break
-
-        # 检查 sub_str 前一个字符（如果有）是否为非字母数字
-        if index == 0:
-            is_start = True
+    # 检查是否在中间位置，且前后有非字母数字字符
+    # index = long_str.find(sub_str)
+    index_list = [m.start() for m in re.finditer(re.escape(sub_str), long_str)]
+
+    def get_bools(index):
+        if index >= 0:
+            is_start = False
+            is_end = False
+            if index == 0:
+                is_start = True
+            else:
+                is_start = bool(regex_pattern.match(long_str[index - 1]))
+
+            if len(long_str) == len(sub_str) + index:
+                is_end = True
+            else:
+                is_end = bool(regex_pattern.match(long_str[index + len(sub_str)]))
+
+            return is_start and is_end
         else:
-            is_start = bool(regex_pattern.match(long_str[index - 1]))
+            return False
 
-        # 检查 sub_str 后一个字符（如果有）是否为非字母数字
-        end_index = index + len(sub_str)
-        if end_index == len(long_str):
-            is_end = True
-        else:
-            is_end = bool(regex_pattern.match(long_str[end_index]))
-
-        if is_start and is_end:
-            return True
-
-        # 移动索引继续查找
-        index += 1
-
-    return False
+    return any([get_bools(index) for index in index_list])
 
 
 def is_whole_word(sub_str: str, long_str: str) -> bool:
@@ -178,10 +185,10 @@ def is_whole_word(sub_str: str, long_str: str) -> bool:
         # 是否是字母数字
         if is_ascii_alnum(sub_str[0]) or is_ascii_alnum(sub_str[-1]):
             # 表示中英文混合 看是否是截断单词即可
-            return is_whole_word_en(sub_str, long_str)
+            return is_whole_word_en_re(sub_str, long_str)
         else:
             # 中文子串只要被包含即可视为“完整词”
             return is_contain
     else:
         # 英文使用完整单词判断逻辑
-        return is_whole_word_en(sub_str, long_str)
+        return is_whole_word_en_re(sub_str, long_str)

{re_common-10.0.42.dist-info → re_common-10.0.43.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: re_common
-Version: 10.0.42
+Version: 10.0.43
 Summary: a library about all python projects
 Home-page: https://gitee.com/xujiangios/re-common
 Author: vic
@@ -11,6 +11,15 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+Dynamic: summary
 
 
     这是一个基础类，依赖很多的第三方包，是一个用得到的第三方库的封装，可以在此基础上迅速构建项目

{re_common-10.0.42.dist-info → re_common-10.0.43.dist-info}/RECORD

@@ -177,8 +177,9 @@ re_common/v2/baselibrary/helpers/search_packge/fit_text_match.py,sha256=cMN4W7xu
 re_common/v2/baselibrary/helpers/search_packge/scikit_learn_text_matcher.py,sha256=Ri8Ul2_URq1TVvlXwG0OvqBo9_LSpivvdvjQM7xr01I,9947
 re_common/v2/baselibrary/helpers/search_packge/test.py,sha256=jYDa6s66jqiz6xEhXMPLqmONFbmfv-EgxaVpdHbGk4U,52
 re_common/v2/baselibrary/s3object/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-re_common/v2/baselibrary/s3object/baseaioboto3.py,sha256=3WVgcBdohPJut-1MB2QCCuYKf9ynjohMKL3prMjHt94,1973
+re_common/v2/baselibrary/s3object/baseaioboto3.py,sha256=Xqk1z0DyNM127EBH1sstftGSkRNkm6eKlbNRXby38rI,4383
 re_common/v2/baselibrary/s3object/baseboto3.py,sha256=mXuIFx99pnrPGQ4LJCZwlN1HLbaU-OWLwck0cVzW6hc,11203
+re_common/v2/baselibrary/s3object/huaweiobs.py,sha256=rUXm7S5yZ4T4a_CK0ggsEX4k_Th2jZW2oygGb6xhtW8,2754
 re_common/v2/baselibrary/tools/WeChatRobot.py,sha256=sKBt2gPsfj0gzV6KaLSAhIhL-j3qNfHfqE-lII1LVwM,3537
 re_common/v2/baselibrary/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 re_common/v2/baselibrary/tools/ac_ahocorasick.py,sha256=c63y5RtKVLD37nyPCnBqfNygwRj4gTQqyIdDOrC65G0,2847
@@ -218,7 +219,7 @@ re_common/v2/baselibrary/utils/json_cls.py,sha256=M93piYtmgm_wP8E57culTrd_AhHLoG
 re_common/v2/baselibrary/utils/mq.py,sha256=UHpO8iNIHs91Tgp-BgnSUpZwjWquxrGLdpr3FMMv2zw,2858
 re_common/v2/baselibrary/utils/n_ary_expression_tree.py,sha256=-05kO6G2Rth7CEK-5lfFrthFZ1Q0-0a7cni7mWZ-2gg,9172
 re_common/v2/baselibrary/utils/pinyin_utils.py,sha256=OXZfVvMjKfCvEbJ6PIwpwWbupU1CSBXJNDnf3jMhC10,7141
-re_common/v2/baselibrary/utils/string_bool.py,sha256=no7fdxe2iYUaxQBRA8kkyRhmJGaxxQa3JHQ_5LZLyi8,6210
+re_common/v2/baselibrary/utils/string_bool.py,sha256=FsmrUZw1CCUXrfC9ZejdgKO35320wWffiduAGhl_bFQ,6412
 re_common/v2/baselibrary/utils/string_clear.py,sha256=Ympa0Cs2y_72QeeyMS8de8y_QgtEFJJQ0AgHnylbMUc,7861
 re_common/v2/baselibrary/utils/string_smi.py,sha256=cU0WAWHRGnGoVQx3eCEKeM_q_olFNzRTJe7rSe586SY,741
 re_common/v2/baselibrary/utils/stringutils.py,sha256=hH0pHNvgR_TgulmBPRax9U_sp6bwYG5ksDbdqHRCFvk,10083
@@ -248,8 +249,8 @@ re_common/vip/title/transform/TransformRegulationTitleToZt.py,sha256=LKRdIsWKues
 re_common/vip/title/transform/TransformStandardTitleToZt.py,sha256=-fCKAbSBzXVyQDCE61CalvR9E_QzQMA08QOO_NePFNI,5563
 re_common/vip/title/transform/TransformThesisTitleToZt.py,sha256=QS-uV0cQrpUFAcKucuJQ9Ue2VRQH-inmfn_X3IplfRo,5488
 re_common/vip/title/transform/__init__.py,sha256=m83-CWyRq_VHPYHaALEQlmXrkTdrZ3e4B_kCfBYE-uc,239
-re_common-10.0.42.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
-re_common-10.0.42.dist-info/METADATA,sha256=OHWLXAG4NpAA8WfEywa-GJlin-KBZ6kQWCaICOrdyA0,582
-re_common-10.0.42.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-re_common-10.0.42.dist-info/top_level.txt,sha256=_H9H23zoLIalm1AIY_KYTVh_H0ZnmjxQIxsvXtLv45o,10
-re_common-10.0.42.dist-info/RECORD,,
+re_common-10.0.43.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
+re_common-10.0.43.dist-info/METADATA,sha256=wLSvL6sw37eaQmsTV3OYThFy_oqzN4Bx1qcXw36SbNQ,787
+re_common-10.0.43.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+re_common-10.0.43.dist-info/top_level.txt,sha256=_H9H23zoLIalm1AIY_KYTVh_H0ZnmjxQIxsvXtLv45o,10
+re_common-10.0.43.dist-info/RECORD,,

{re_common-10.0.42.dist-info → re_common-10.0.43.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any