orbitkit 0.8.46__tar.gz → 0.8.48__tar.gz

{orbitkit-0.8.46/orbitkit.egg-info → orbitkit-0.8.48}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: orbitkit
-Version: 0.8.46
+Version: 0.8.48
 Summary: This project is only for Orbit Tech internal use.
 Home-page: https://github.com/clown-0726/orbitkit
 Author: Lilu Cao
@@ -19,15 +19,37 @@ Classifier: Programming Language :: Python :: 3.4
 Classifier: Programming Language :: Python :: 3.5
 Classifier: Programming Language :: Python :: 3.6
 Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Software Development :: Libraries
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: boto3>=1.16.0
-Requires-Dist: requests>=2.12.1
-Requires-Dist: prettytable>=3.0.0
-Requires-Dist: pytz>=2022.1
+Requires-Dist: boto3>=1.40.46
+Requires-Dist: aioboto3>=15.5.0
+Requires-Dist: aiofiles>=25.1.0
+Requires-Dist: requests>=2.32.5
+Requires-Dist: prettytable>=3.17.0
+Requires-Dist: pytz>=2025.2
 Requires-Dist: Deprecated
 Requires-Dist: func_timeout
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: maintainer
+Dynamic: maintainer-email
+Dynamic: platform
+Dynamic: requires-dist
+Dynamic: summary
 
 # orbitkit
 

orbitkit-0.8.48/orbitkit/VERSION

@@ -0,0 +1 @@
+0.8.48

{orbitkit-0.8.46 → orbitkit-0.8.48}/orbitkit/audio_transcoder/netmind_extract_v1.py

@@ -74,11 +74,11 @@ class Translate:
 #      "start": 0.031, "end": 2.921},
 #     {"speaker": "SPEAKER_01", "text": "We just wanted to take a minute to thank you.", "start": 3.507, "end": 4.962}],
 #  "id": "0ca63ef01e224adca4865b3cec94c1a2", "model": "WhisperX"}
-def text_processing(netmind_data, lang):
+def text_processing(netmind_data, lang, translate_model='gpt-4.1-mini'):
     import fasttext
     from urllib.request import urlretrieve
     model_path = "lid.176.bin"
-    tran = Translate()
+    tran = Translate(model=translate_model)
     # 如果模型不存在，则下载
     if not os.path.exists(model_path):
         logger.info("Downloading fasttext language detection model...")
@@ -145,6 +145,7 @@ def send_request_to_stream(file_steam, **kwargs):
 def request_wav_from_netmind(s3_client, s3_path=None, file_steam=None, **kwargs):
     lang = kwargs.get('lang', 'en')
     folder = kwargs.get('folder', '')
+    translate_model = kwargs.get('translate_model', 'gpt-4.1-mini')
     if s3_path:
         s3_path_obj = s3_split_path(s3_path)
         # 开始尝试提取...
@@ -165,10 +166,10 @@ def request_wav_from_netmind(s3_client, s3_path=None, file_steam=None, **kwargs)
     with open(json_netmind_wav_path, 'w', encoding='utf-8') as json_file:
         json.dump(data, json_file, ensure_ascii=False, indent=4)
 
-    net_process = text_processing(data, lang)
+    net_process = text_processing(data, lang, translate_model=translate_model)
 
     # 翻译接口处理
     json_netmind_lang_wav_path = os.path.join(folder, 'netmind_lang_wav.json')
     with open(json_netmind_lang_wav_path, 'w', encoding='utf-8') as json_file:
         json.dump(net_process, json_file, ensure_ascii=False, indent=4)
-    return json_netmind_wav_path, json_netmind_lang_wav_path
+    return json_netmind_wav_path, json_netmind_lang_wav_path

orbitkit-0.8.48/orbitkit/orbit_type/__init__.py

@@ -0,0 +1 @@
+from .orbit_type_simple import OrbitTypeMatcher, OrbitTypeMatcherAsync

{orbitkit-0.8.46 → orbitkit-0.8.48}/orbitkit/orbit_type/orbit_type_simple.py

@@ -2,9 +2,10 @@ import abc
 import json
 import logging
 import re
-from typing import List, Literal
+from typing import List, Literal, Optional
 from botocore.exceptions import ClientError
 import boto3
+import aioboto3
 
 logger = logging.getLogger(__name__)
 
@@ -459,6 +460,281 @@ class OrbitTypeMatcher:
             }
 
 
+class OrbitTypeMatcherAsync:
+    """
+    OrbitTypeMatcher 的异步版本
+    使用 aioboto3 进行异步 S3 操作，提升性能
+    """
+
+    def __init__(
+        self,
+        aws_access_key_id: Optional[str] = None,
+        aws_secret_access_key: Optional[str] = None,
+        file_bucket: str = 'ot-cdn',
+        key_prefix: str = 'orbit-typing/typing-prod'
+    ):
+        """
+        初始化异步类型匹配器
+        
+        :param aws_access_key_id: AWS access key ID（可选，不提供则使用默认凭证链）
+        :param aws_secret_access_key: AWS secret access key（可选）
+        :param file_bucket: S3 bucket 名称
+        :param key_prefix: S3 key 前缀
+        """
+        # 创建 aioboto3 session
+        if aws_access_key_id and aws_secret_access_key:
+            self.session = aioboto3.Session(
+                aws_access_key_id=aws_access_key_id,
+                aws_secret_access_key=aws_secret_access_key
+            )
+        else:
+            # 使用默认凭证链（环境变量、AWS CLI 配置、IAM 角色等）
+            self.session = aioboto3.Session()
+        
+        self.file_bucket = file_bucket
+        self.key_prefix = key_prefix
+        self.matcher = None
+        self.json_file = None
+        self.version = None
+
+    @classmethod
+    async def create(
+        cls,
+        aws_access_key_id: Optional[str] = None,
+        aws_secret_access_key: Optional[str] = None,
+        file_bucket: str = 'ot-cdn',
+        key_prefix: str = 'orbit-typing/typing-prod',
+        version: Optional[str] = None
+    ):
+        """
+        异步工厂方法，用于创建已初始化的 OrbitTypeMatcherAsync 实例
+        
+        :param aws_access_key_id: AWS access key ID（可选）
+        :param aws_secret_access_key: AWS secret access key（可选）
+        :param file_bucket: S3 bucket 名称
+        :param key_prefix: S3 key 前缀
+        :param version: 类型版本号（可选，不提供则使用最新版本）
+        :return: 已初始化的 OrbitTypeMatcherAsync 实例
+        
+        示例：
+            matcher = await OrbitTypeMatcherAsync.create(version='0.3.4')
+            result = matcher.match_type(title='Press Release')
+        """
+        instance = cls(
+            aws_access_key_id=aws_access_key_id,
+            aws_secret_access_key=aws_secret_access_key,
+            file_bucket=file_bucket,
+            key_prefix=key_prefix
+        )
+        
+        # 异步加载版本和配置文件
+        if not version:
+            version = await instance.get_newest_version()
+        
+        source_key = f'{key_prefix}/{version}.json'
+        json_file = await instance.read_s3_file(
+            bucket_name=file_bucket,
+            file_name=source_key
+        )
+        
+        if not json_file:
+            raise Exception(f'该 S3 文件不存在: {source_key}')
+        
+        instance.json_file = json_file
+        instance.matcher = L3RuleListMatcher(json_file)
+        instance.version = version
+        
+        return instance
+
+    async def read_s3_file(self, bucket_name: str, file_name: str):
+        """
+        异步读取 S3 中的 JSON 文件
+        
+        :param bucket_name: S3 bucket 名称
+        :param file_name: 文件路径
+        :return: JSON 数据或 None
+        """
+        try:
+            async with self.session.client('s3') as s3_client:
+                file_obj = await s3_client.get_object(Bucket=bucket_name, Key=file_name)
+                content = await file_obj['Body'].read()
+                lines = content.decode('utf-8')
+                json_data = json.loads(lines)
+                return json_data
+        except ClientError as e:
+            logger.error(f"读取 S3 文件失败: {bucket_name}/{file_name}, 错误: {e}")
+            return None
+
+    async def get_newest_version(self):
+        """
+        异步获取最新的类型版本号
+        
+        :return: 最新版本号字符串
+        """
+        async with self.session.client('s3') as s3_client:
+            response = await s3_client.list_objects_v2(
+                Bucket=self.file_bucket,
+                Prefix=self.key_prefix
+            )
+
+            # 遍历存储桶中的对象，获取文件名
+            file_names = []
+            for obj in response.get('Contents', []):
+                key = obj['Key']
+                if key.endswith('/'):  # 排除文件夹本身
+                    continue
+                file_names.append(key.split('/')[-1])  # 获取文件名部分
+
+            result = []
+            for key in file_names:
+                if 'tmp.json' in key:
+                    continue
+                if '.json' not in key:
+                    continue
+                result.append(key.replace('.json', ''))
+
+            def sort_vision_json_file(filename):
+                parts = filename.replace('.json', '').split('.')
+                return tuple(int(part) for part in parts)
+
+            sorted_versions = sorted(result, key=sort_vision_json_file, reverse=True)
+            return sorted_versions[0]
+
+    def get_full_type_list(self):
+        """
+        获取完整包含 1、2、3 级类型的列表
+        注意：此方法是同步的，因为它只进行内存操作
+        
+        :return: 完整类型列表
+        """
+        lv1_list = self.json_file['lv1_list']
+        lv1_dict = {}
+        for row in lv1_list:
+            lv1_id = row['lv1_id']
+            name = row['lv1_name']
+            lv1_dict[lv1_id] = name
+
+        lv2_list = self.json_file['lv2_list']
+        lv2_dict = {}
+        for row in lv2_list:
+            lv1_id = row['lv1_id']
+            lv2_id = row['lv2_id']
+            name = row['lv2_name']
+            lv2_dict[lv2_id] = {
+                'lv2_id': lv2_id,
+                'lv2_name': name,
+                'lv1_id': lv1_id,
+                'lv1_name': lv1_dict[lv1_id]
+            }
+
+        lv3_list = self.json_file['lv3_list']
+        lv3_data = []
+        for row in lv3_list:
+            lv2_id = row['level_2_id']
+            this_dict = {
+                'lv3_id': row['lv3_id'],
+                'lv3_name': row['lv3_name']
+            }
+            this_dict.update(lv2_dict[lv2_id])
+            lv3_data.append(this_dict)
+
+        sorted_list = sorted(
+            lv3_data,
+            key=lambda x: (int(x['lv3_id']), int(x['lv2_id']), int(x['lv1_id']))
+        )
+        return sorted_list
+
+    def match_type(self, match_flag: Literal['in_order', 'match_all'] = 'in_order', **match_kwargs):
+        """
+        用于匹配的函数，可以传入 n 个匹配参数
+        注意：此方法是同步的，因为匹配操作只涉及内存操作，不需要 I/O
+        
+        :param match_flag: 匹配模式
+            - 'in_order': 按顺序依次匹配，匹配到结果就停止
+            - 'match_all': 匹配全部的项，并将结果合并
+        :param match_kwargs: 匹配参数（如 title='...', url='...', description='...'）
+        :return: 匹配结果
+        
+        示例：
+            # 按顺序匹配
+            key, result = matcher.match_type(
+                match_flag='in_order',
+                title='Press Release',
+                description='Company news'
+            )
+            
+            # 匹配所有
+            result = matcher.match_type(
+                match_flag='match_all',
+                title='Press Release',
+                url='https://example.com/news/press-release'
+            )
+        """
+        if match_flag not in ['in_order', 'match_all']:
+            raise ValueError('match_flag 参数必须是 "in_order" 或 "match_all"')
+        if not match_kwargs:
+            raise ValueError('必须传入匹配关键词！')
+
+        default_result = [{'lv3_id': '19999', 'lv3_name': 'Miscellaneous'}]
+
+        def match_url(url: str):
+            split_url = url.replace('http://', '').replace('https://', '').split('/')
+            split_url = [x.strip().replace('%20', ' ') for x in split_url if len(x.strip()) > 4]
+            for part in reversed(split_url):
+                match_result = self.matcher.start_match_all(part)
+                if match_result:
+                    match_key = f'url#{part}'
+                    return match_key, match_result
+            return None, None
+
+        if match_flag == 'in_order':
+            for key, value in match_kwargs.items():
+                if key == 'url':
+                    url_key, match_result = match_url(value)
+                    if match_result:
+                        return url_key, match_result
+                else:
+                    match_result = self.matcher.start_match_all(value)
+                    if match_result:
+                        return key, match_result
+            return None, default_result
+
+        elif match_flag == 'match_all':
+            overall_results = []
+            match_detail = {}
+            for key, value in match_kwargs.items():
+                if key == 'url':
+                    url_key, match_result = match_url(value)
+                    if match_result:
+                        overall_results += match_result
+                        match_detail[url_key] = match_result
+                else:
+                    match_result = self.matcher.start_match_all(value)
+                    if match_result:
+                        overall_results += match_result
+                        match_detail[key] = match_result
+
+            if not overall_results:
+                overall_results = default_result
+
+            unique_dict = {d['lv3_id']: d for d in overall_results}
+            sorted_results = sorted(unique_dict.values(), key=lambda x: int(x['lv3_id']))
+
+            return {
+                'results': sorted_results,
+                'match_detail': match_detail
+            }
+
+
 if __name__ == '__main__':
+    # 同步版本示例
     matcher = OrbitTypeMatcher(version='0.2.1')
     matcher.match_type(title='asdf')
+    
+    # 异步版本示例
+    # import asyncio
+    # async def test_async():
+    #     matcher = await OrbitTypeMatcherAsync.create(version='0.3.4')
+    #     result = matcher.match_type(match_flag='in_order', title='Press Release')
+    #     print(result)
+    # asyncio.run(test_async())

{orbitkit-0.8.46 → orbitkit-0.8.48}/orbitkit/util/__init__.py

@@ -49,6 +49,7 @@ from .util_html import (
 )
 from .util_aws_s3_wrapper import (
     AwsS3Wrapper,
+    AwsS3WrapperAsync,
 )
 from .util_aliyun import (
     oss_split_path,

orbitkit-0.8.48/orbitkit/util/util_aws_s3_wrapper.py

@@ -0,0 +1,369 @@
+import logging
+import os.path
+from typing import Optional
+import boto3
+from orbitkit.util import get_from_dict_or_env, s3_split_path, get_content_type_4_filename
+import botocore
+from botocore.exceptions import ClientError
+import aioboto3
+import aiofiles
+
+logger = logging.getLogger(__name__)
+
+
+class AwsS3Wrapper:
+    """Encapsulates Amazon s3 actions for Orbitfin"""
+
+    def __init__(self, s3_resource, s3_client):
+        """
+        :param s3_resource: boto3.resource('s3')
+        :param s3_client: boto3.client('s3')
+        """
+        self.s3_resource = s3_resource
+        self.s3_client = s3_client
+
+    @classmethod
+    def from_s3(cls, *args, **kwargs):
+        # Try to get key aws pair
+        aws_access_key_id = get_from_dict_or_env(
+            kwargs, "aws_access_key_id", "AWS_ACCESS_KEY_ID",
+        )
+
+        aws_secret_access_key = get_from_dict_or_env(
+            kwargs, "aws_secret_access_key", "AWS_SECRET_ACCESS_KEY",
+        )
+
+        s3_resource = boto3.resource('s3', aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key)
+        s3_client = boto3.client('s3', aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key)
+
+        return cls(s3_resource, s3_client)
+
+    def get_s3_resource(self):
+        return self.s3_resource
+
+    def get_s3_client(self):
+        return self.s3_client
+
+    def check_file_exist(self, s3_path: str) -> bool:
+        """
+        :param s3_path: Target store path for s3.
+        :return:
+        """
+
+        s3_path_obj = s3_split_path(s3_path)
+        try:
+            self.s3_resource.Object(s3_path_obj["bucket"], s3_path_obj["store_path"]).load()
+        except botocore.exceptions.ClientError as e:
+            if e.response['Error']['Code'] == "404":
+                # The object does not exist.
+                return False
+            else:
+                # Something else has gone wrong.
+                raise Exception("Check s3 file exist unknown error...")
+        else:
+            # The object does exist.
+            return True
+
+    def copy_file(self, source_path: str, target_path: str):
+        """
+        :param source_path: Source s3 path location
+        :param target_path: Target s3 path location
+        :return:
+        """
+        source_path_obj = s3_split_path(source_path)
+        target_path_obj = s3_split_path(target_path)
+
+        self.s3_resource.Object(target_path_obj["bucket"], target_path_obj["store_path"]).copy_from(
+            CopySource=source_path_obj["bucket"] + '/' + source_path_obj["store_path"],
+        )
+
+    def delete_file(self, s3_path: str):
+        """
+        :param s3_path: Target store path for s3.
+        :return:
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        self.s3_resource.Object(s3_path_obj["bucket"], s3_path_obj["store_path"]).delete()
+
+    def download_file(self, s3_path: str, local_path: str, filename: str):
+        """
+        :param s3_path: Target store path for s3.
+        :param local_path: Local path
+        :param filename: File name
+        :return:
+        """
+        if not os.path.exists(local_path):
+            os.makedirs(local_path)
+
+        s3_path_obj = s3_split_path(s3_path)
+        self.s3_resource.Bucket(s3_path_obj["bucket"]).download_file(s3_path_obj["store_path"], os.path.join(local_path, filename))
+
+    def upload_by_local_path(self, s3_path: str, local_path: str, text_with_utf8: bool = True):
+        """
+        :param s3_path: Target store path for s3.
+        :param local_path: Local file path.
+        :param text_with_utf8: If content-type start with "text/" then put ;charset=utf-8 after.
+        :return:
+        """
+        if not os.path.exists(local_path):
+            raise Exception("Local file doesn't exist!")
+
+        content_type = get_content_type_4_filename(s3_path, text_with_utf8)
+        s3_path_obj = s3_split_path(s3_path)
+
+        self.s3_client.upload_file(local_path,
+                                   s3_path_obj["bucket"],
+                                   s3_path_obj["store_path"],
+                                   ExtraArgs={'ContentType': content_type})
+
+    def upload_file(self, s3_path: str, content: bytes, metadata: Optional[dict] = None, text_with_utf8: bool = True):
+        """
+        :param s3_path: Target store path for s3.
+        :param content: The content of file, if text-like use content.encode("utf-8"), if binary then put directly.
+        :param metadata: Custom metadata for file.
+        :param text_with_utf8: If content-type start with "text/" then put ;charset=utf-8 after.
+        :return:
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        content_type = get_content_type_4_filename(s3_path, text_with_utf8)
+
+        object_put = self.s3_resource.Object(s3_path_obj["bucket"], s3_path_obj["store_path"])
+        if metadata:
+            object_put.put(Body=content, ContentType=content_type, Metadata=metadata)
+        else:
+            object_put.put(Body=content, ContentType=content_type)
+
+    def get_file_meta_info(self, s3_path: str) -> dict:
+        """
+        :param s3_path: Target store path for s3.
+        :return:
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        response = self.s3_client.head_object(Bucket=s3_path_obj["bucket"], Key=s3_path_obj["store_path"])
+        return {
+            "content_type": response['ContentType'],
+            "metadata": response['Metadata'],
+        }
+
+    def read_text_like_file(self, s3_path: str, decoding: str = "utf-8") -> str:
+        """
+        :param s3_path: Target store path for s3.
+        :param decoding: decoding, default is "utf-8".
+        :return:
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        obj = self.s3_client.get_object(Bucket=s3_path_obj["bucket"], Key=s3_path_obj["store_path"])
+        return obj['Body'].read().decode(decoding)
+
+
+class AwsS3WrapperAsync:
+    """Encapsulates Amazon S3 async actions for Orbitfin using aioboto3"""
+
+    def __init__(self, aws_access_key_id: Optional[str] = None, aws_secret_access_key: Optional[str] = None):
+        """
+        初始化异步 S3 包装器
+        
+        :param aws_access_key_id: AWS access key ID（可选，不提供则使用 AWS CLI 配置或环境变量）
+        :param aws_secret_access_key: AWS secret access key（可选）
+        
+        凭证获取顺序：
+        1. 直接传入的参数
+        2. 环境变量（AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY）
+        3. AWS CLI 配置文件（~/.aws/credentials）
+        4. IAM 角色（如果在 EC2/ECS 上运行）
+        """
+        self.aws_access_key_id = aws_access_key_id
+        self.aws_secret_access_key = aws_secret_access_key
+        
+        # 如果提供了凭证，使用指定凭证；否则使用默认凭证链
+        if aws_access_key_id and aws_secret_access_key:
+            self.session = aioboto3.Session(
+                aws_access_key_id=aws_access_key_id,
+                aws_secret_access_key=aws_secret_access_key
+            )
+        else:
+            # 使用默认凭证链（环境变量、AWS CLI 配置、IAM 角色等）
+            self.session = aioboto3.Session()
+
+    @classmethod
+    def from_s3(cls, *args, **kwargs):
+        """
+        创建 AwsS3WrapperAsync 实例
+        
+        支持从以下来源获取 AWS 凭证（按优先级）：
+        1. kwargs 参数（aws_access_key_id, aws_secret_access_key）
+        2. 环境变量（AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY）
+        3. AWS CLI 配置文件（~/.aws/credentials）
+        4. IAM 角色
+        
+        示例：
+            # 使用默认凭证链（推荐）
+            wrapper = AwsS3WrapperAsync.from_s3()
+            
+            # 显式指定凭证
+            wrapper = AwsS3WrapperAsync.from_s3(
+                aws_access_key_id="xxx",
+                aws_secret_access_key="yyy"
+            )
+        """
+        # 尝试从 kwargs 或环境变量获取凭证（可选）
+        aws_access_key_id = kwargs.get("aws_access_key_id") or os.environ.get("AWS_ACCESS_KEY_ID")
+        aws_secret_access_key = kwargs.get("aws_secret_access_key") or os.environ.get("AWS_SECRET_ACCESS_KEY")
+        
+        return cls(aws_access_key_id, aws_secret_access_key)
+
+    async def check_file_exist(self, s3_path: str) -> bool:
+        """
+        检查 S3 文件是否存在
+        :param s3_path: S3 路径
+        :return: 文件是否存在
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        
+        async with self.session.client('s3') as s3_client:
+            try:
+                await s3_client.head_object(
+                    Bucket=s3_path_obj["bucket"],
+                    Key=s3_path_obj["store_path"]
+                )
+                return True
+            except ClientError as e:
+                if e.response['Error']['Code'] == "404":
+                    return False
+                else:
+                    raise Exception("Check s3 file exist unknown error...")
+
+    async def copy_file(self, source_path: str, target_path: str):
+        """
+        复制 S3 文件
+        :param source_path: 源 S3 路径
+        :param target_path: 目标 S3 路径
+        """
+        source_path_obj = s3_split_path(source_path)
+        target_path_obj = s3_split_path(target_path)
+
+        async with self.session.client('s3') as s3_client:
+            copy_source = {
+                'Bucket': source_path_obj["bucket"],
+                'Key': source_path_obj["store_path"]
+            }
+            await s3_client.copy_object(
+                CopySource=copy_source,
+                Bucket=target_path_obj["bucket"],
+                Key=target_path_obj["store_path"]
+            )
+
+    async def delete_file(self, s3_path: str):
+        """
+        删除 S3 文件
+        :param s3_path: S3 路径
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        
+        async with self.session.client('s3') as s3_client:
+            await s3_client.delete_object(
+                Bucket=s3_path_obj["bucket"],
+                Key=s3_path_obj["store_path"]
+            )
+
+    async def download_file(self, s3_path: str, local_path: str, filename: str):
+        """
+        从 S3 下载文件到本地
+        :param s3_path: S3 路径
+        :param local_path: 本地目录路径
+        :param filename: 文件名
+        """
+        if not os.path.exists(local_path):
+            os.makedirs(local_path)
+
+        s3_path_obj = s3_split_path(s3_path)
+        local_file_path = os.path.join(local_path, filename)
+
+        async with self.session.client('s3') as s3_client:
+            response = await s3_client.get_object(
+                Bucket=s3_path_obj["bucket"],
+                Key=s3_path_obj["store_path"]
+            )
+            async with aiofiles.open(local_file_path, 'wb') as f:
+                await f.write(await response['Body'].read())
+
+    async def upload_by_local_path(self, s3_path: str, local_path: str, text_with_utf8: bool = True):
+        """
+        从本地路径上传文件到 S3
+        :param s3_path: S3 目标路径
+        :param local_path: 本地文件路径
+        :param text_with_utf8: 如果是文本文件，是否添加 utf-8 编码标识
+        """
+        if not os.path.exists(local_path):
+            raise Exception("Local file doesn't exist!")
+
+        content_type = get_content_type_4_filename(s3_path, text_with_utf8)
+        s3_path_obj = s3_split_path(s3_path)
+
+        async with self.session.client('s3') as s3_client:
+            async with aiofiles.open(local_path, 'rb') as f:
+                content = await f.read()
+                await s3_client.put_object(
+                    Bucket=s3_path_obj["bucket"],
+                    Key=s3_path_obj["store_path"],
+                    Body=content,
+                    ContentType=content_type
+                )
+
+    async def upload_file(self, s3_path: str, content: bytes, metadata: Optional[dict] = None, text_with_utf8: bool = True):
+        """
+        上传文件内容到 S3
+        :param s3_path: S3 目标路径
+        :param content: 文件内容（字节）
+        :param metadata: 自定义元数据
+        :param text_with_utf8: 如果是文本文件，是否添加 utf-8 编码标识
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        content_type = get_content_type_4_filename(s3_path, text_with_utf8)
+
+        async with self.session.client('s3') as s3_client:
+            put_args = {
+                'Bucket': s3_path_obj["bucket"],
+                'Key': s3_path_obj["store_path"],
+                'Body': content,
+                'ContentType': content_type
+            }
+            if metadata:
+                put_args['Metadata'] = metadata
+            
+            await s3_client.put_object(**put_args)
+
+    async def get_file_meta_info(self, s3_path: str) -> dict:
+        """
+        获取 S3 文件的元信息
+        :param s3_path: S3 路径
+        :return: 包含 content_type 和 metadata 的字典
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        
+        async with self.session.client('s3') as s3_client:
+            response = await s3_client.head_object(
+                Bucket=s3_path_obj["bucket"],
+                Key=s3_path_obj["store_path"]
+            )
+            return {
+                "content_type": response['ContentType'],
+                "metadata": response['Metadata'],
+            }
+
+    async def read_text_like_file(self, s3_path: str, decoding: str = "utf-8") -> str:
+        """
+        读取 S3 文本文件内容
+        :param s3_path: S3 路径
+        :param decoding: 解码方式，默认 utf-8
+        :return: 文件文本内容
+        """
+        s3_path_obj = s3_split_path(s3_path)
+        
+        async with self.session.client('s3') as s3_client:
+            response = await s3_client.get_object(
+                Bucket=s3_path_obj["bucket"],
+                Key=s3_path_obj["store_path"]
+            )
+            content = await response['Body'].read()
+            return content.decode(decoding)

{orbitkit-0.8.46 → orbitkit-0.8.48/orbitkit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: orbitkit
-Version: 0.8.46
+Version: 0.8.48
 Summary: This project is only for Orbit Tech internal use.
 Home-page: https://github.com/clown-0726/orbitkit
 Author: Lilu Cao
@@ -19,15 +19,37 @@ Classifier: Programming Language :: Python :: 3.4
 Classifier: Programming Language :: Python :: 3.5
 Classifier: Programming Language :: Python :: 3.6
 Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Software Development :: Libraries
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: boto3>=1.16.0
-Requires-Dist: requests>=2.12.1
-Requires-Dist: prettytable>=3.0.0
-Requires-Dist: pytz>=2022.1
+Requires-Dist: boto3>=1.40.46
+Requires-Dist: aioboto3>=15.5.0
+Requires-Dist: aiofiles>=25.1.0
+Requires-Dist: requests>=2.32.5
+Requires-Dist: prettytable>=3.17.0
+Requires-Dist: pytz>=2025.2
 Requires-Dist: Deprecated
 Requires-Dist: func_timeout
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: maintainer
+Dynamic: maintainer-email
+Dynamic: platform
+Dynamic: requires-dist
+Dynamic: summary
 
 # orbitkit
 

orbitkit-0.8.48/orbitkit.egg-info/requires.txt

@@ -0,0 +1,8 @@
+boto3>=1.40.46
+aioboto3>=15.5.0
+aiofiles>=25.1.0
+requests>=2.32.5
+prettytable>=3.17.0
+pytz>=2025.2
+Deprecated
+func_timeout

{orbitkit-0.8.46 → orbitkit-0.8.48}/setup.py

@@ -32,15 +32,24 @@ setup(
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
         'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: 3.9',
+        'Programming Language :: Python :: 3.10',
+        'Programming Language :: Python :: 3.11',
+        'Programming Language :: Python :: 3.12',
+        'Programming Language :: Python :: 3.13',
+        'Programming Language :: Python :: 3.14',
         'Topic :: Software Development :: Libraries'
     ],
     include_package_data=True,
     zip_safe=False,
     install_requires=[
-        "boto3 >= 1.16.0",
-        "requests >= 2.12.1",
-        "prettytable >= 3.0.0",
-        "pytz >= 2022.1",
+        "boto3 >= 1.40.46",
+        "aioboto3 >= 15.5.0",
+        "aiofiles >= 25.1.0",
+        "requests >= 2.32.5",
+        "prettytable >= 3.17.0",
+        "pytz >= 2025.2",
         "Deprecated",
         "func_timeout",
     ]

orbitkit-0.8.46/orbitkit/VERSION

@@ -1 +0,0 @@
-0.8.46

orbitkit-0.8.46/orbitkit/orbit_type/__init__.py

@@ -1 +0,0 @@
-from .orbit_type_simple import OrbitTypeMatcher

orbitkit-0.8.46/orbitkit/util/util_aws_s3_wrapper.py

@@ -1,154 +0,0 @@
-import logging
-import os.path
-from typing import Optional
-import boto3
-from orbitkit.util import get_from_dict_or_env, s3_split_path, get_content_type_4_filename
-import botocore
-from botocore.exceptions import ClientError
-
-logger = logging.getLogger(__name__)
-
-
-class AwsS3Wrapper:
-    """Encapsulates Amazon s3 actions for Orbitfin"""
-
-    def __init__(self, s3_resource, s3_client):
-        """
-        :param s3_resource: boto3.resource('s3')
-        :param s3_client: boto3.client('s3')
-        """
-        self.s3_resource = s3_resource
-        self.s3_client = s3_client
-
-    @classmethod
-    def from_s3(cls, *args, **kwargs):
-        # Try to get key aws pair
-        aws_access_key_id = get_from_dict_or_env(
-            kwargs, "aws_access_key_id", "AWS_ACCESS_KEY_ID",
-        )
-
-        aws_secret_access_key = get_from_dict_or_env(
-            kwargs, "aws_secret_access_key", "AWS_SECRET_ACCESS_KEY",
-        )
-
-        s3_resource = boto3.resource('s3', aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key)
-        s3_client = boto3.client('s3', aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key)
-
-        return cls(s3_resource, s3_client)
-
-    def get_s3_resource(self):
-        return self.s3_resource
-
-    def get_s3_client(self):
-        return self.s3_client
-
-    def check_file_exist(self, s3_path: str) -> bool:
-        """
-        :param s3_path: Target store path for s3.
-        :return:
-        """
-
-        s3_path_obj = s3_split_path(s3_path)
-        try:
-            self.s3_resource.Object(s3_path_obj["bucket"], s3_path_obj["store_path"]).load()
-        except botocore.exceptions.ClientError as e:
-            if e.response['Error']['Code'] == "404":
-                # The object does not exist.
-                return False
-            else:
-                # Something else has gone wrong.
-                raise Exception("Check s3 file exist unknown error...")
-        else:
-            # The object does exist.
-            return True
-
-    def copy_file(self, source_path: str, target_path: str):
-        """
-        :param source_path: Source s3 path location
-        :param target_path: Target s3 path location
-        :return:
-        """
-        source_path_obj = s3_split_path(source_path)
-        target_path_obj = s3_split_path(target_path)
-
-        self.s3_resource.Object(target_path_obj["bucket"], target_path_obj["store_path"]).copy_from(
-            CopySource=source_path_obj["bucket"] + '/' + source_path_obj["store_path"],
-        )
-
-    def delete_file(self, s3_path: str):
-        """
-        :param s3_path: Target store path for s3.
-        :return:
-        """
-        s3_path_obj = s3_split_path(s3_path)
-        self.s3_resource.Object(s3_path_obj["bucket"], s3_path_obj["store_path"]).delete()
-
-    def download_file(self, s3_path: str, local_path: str, filename: str):
-        """
-        :param s3_path: Target store path for s3.
-        :param local_path: Local path
-        :param filename: File name
-        :return:
-        """
-        if not os.path.exists(local_path):
-            os.makedirs(local_path)
-
-        s3_path_obj = s3_split_path(s3_path)
-        self.s3_resource.Bucket(s3_path_obj["bucket"]).download_file(s3_path_obj["store_path"], os.path.join(local_path, filename))
-
-    def upload_by_local_path(self, s3_path: str, local_path: str, text_with_utf8: bool = True):
-        """
-        :param s3_path: Target store path for s3.
-        :param local_path: Local file path.
-        :param text_with_utf8: If content-type start with "text/" then put ;charset=utf-8 after.
-        :return:
-        """
-        if not os.path.exists(local_path):
-            raise Exception("Local file doesn't exist!")
-
-        content_type = get_content_type_4_filename(s3_path, text_with_utf8)
-        s3_path_obj = s3_split_path(s3_path)
-
-        self.s3_client.upload_file(local_path,
-                                   s3_path_obj["bucket"],
-                                   s3_path_obj["store_path"],
-                                   ExtraArgs={'ContentType': content_type})
-
-    def upload_file(self, s3_path: str, content: bytes, metadata: Optional[dict] = None, text_with_utf8: bool = True):
-        """
-        :param s3_path: Target store path for s3.
-        :param content: The content of file, if text-like use content.encode("utf-8"), if binary then put directly.
-        :param metadata: Custom metadata for file.
-        :param text_with_utf8: If content-type start with "text/" then put ;charset=utf-8 after.
-        :return:
-        """
-        s3_path_obj = s3_split_path(s3_path)
-        content_type = get_content_type_4_filename(s3_path, text_with_utf8)
-
-        object_put = self.s3_resource.Object(s3_path_obj["bucket"], s3_path_obj["store_path"])
-        if metadata:
-            object_put.put(Body=content, ContentType=content_type, Metadata=metadata)
-        else:
-            object_put.put(Body=content, ContentType=content_type)
-
-    def get_file_meta_info(self, s3_path: str) -> dict:
-        """
-        :param s3_path: Target store path for s3.
-        :return:
-        """
-        s3_path_obj = s3_split_path(s3_path)
-        response = self.s3_client.head_object(Bucket=s3_path_obj["bucket"], Key=s3_path_obj["store_path"])
-        return {
-            "content_type": response['ContentType'],
-            "metadata": response['Metadata'],
-        }
-
-    def read_text_like_file(self, s3_path: str, decoding: str = "utf-8") -> str:
-        """
-        :param s3_path: Target store path for s3.
-        :param decoding: decoding, default is "utf-8".
-        :return:
-        """
-        s3_path_obj = s3_split_path(s3_path)
-        obj = self.s3_client.get_object(Bucket=s3_path_obj["bucket"], Key=s3_path_obj["store_path"])
-        return obj['Body'].read().decode(decoding)

orbitkit-0.8.46/orbitkit.egg-info/requires.txt

@@ -1,6 +0,0 @@
-boto3>=1.16.0
-requests>=2.12.1
-prettytable>=3.0.0
-pytz>=2022.1
-Deprecated
-func_timeout