orbitkit 0.8.36__tar.gz → 0.8.37__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (78) hide show
  1. {orbitkit-0.8.36/orbitkit.egg-info → orbitkit-0.8.37}/PKG-INFO +2 -14
  2. orbitkit-0.8.37/orbitkit/VERSION +1 -0
  3. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/__init__.py +3 -0
  4. orbitkit-0.8.37/orbitkit/util/cache_asset_downloader.py +132 -0
  5. {orbitkit-0.8.36 → orbitkit-0.8.37/orbitkit.egg-info}/PKG-INFO +2 -14
  6. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit.egg-info/SOURCES.txt +1 -0
  7. orbitkit-0.8.36/orbitkit/VERSION +0 -1
  8. {orbitkit-0.8.36 → orbitkit-0.8.37}/LICENSE +0 -0
  9. {orbitkit-0.8.36 → orbitkit-0.8.37}/MANIFEST.in +0 -0
  10. {orbitkit-0.8.36 → orbitkit-0.8.37}/README.md +0 -0
  11. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/__init__.py +0 -0
  12. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/airflow_handler/__init__.py +0 -0
  13. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/airflow_handler/data_preprocessing.py +0 -0
  14. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/airflow_handler/file_flow_entry_process.py +0 -0
  15. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/airflow_handler/file_flow_exit_process.py +0 -0
  16. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/airflow_handler/file_handler.py +0 -0
  17. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/airflow_handler/file_handler_v2.py +0 -0
  18. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/audio_transcoder/__init__.py +0 -0
  19. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
  20. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/constant/__init__.py +0 -0
  21. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/constant/report_schema.py +0 -0
  22. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/id_srv/__init__.py +0 -0
  23. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/id_srv/id_gen.py +0 -0
  24. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/id_srv/id_perm_like.py +0 -0
  25. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/lark_send/__init__.py +0 -0
  26. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/lark_send/lark.py +0 -0
  27. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/llm_tools/__init__.py +0 -0
  28. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
  29. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/orbit_type/__init__.py +0 -0
  30. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
  31. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
  32. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/orbit_type/tools.py +0 -0
  33. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_embedding/__init__.py +0 -0
  34. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
  35. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
  36. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/__init__.py +0 -0
  37. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
  38. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/exceptions.py +0 -0
  39. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
  40. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
  41. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
  42. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
  43. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
  44. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
  45. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
  46. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +0 -0
  47. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
  48. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
  49. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor_simple/base.py +0 -0
  50. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
  51. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor_simple/core.py +0 -0
  52. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
  53. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
  54. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_extractor_simple/utils.py +0 -0
  55. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_writer/__init__.py +0 -0
  56. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
  57. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/common.py +0 -0
  58. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/customize_regix_manager.py +0 -0
  59. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/secret_manager.py +0 -0
  60. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_aliyun.py +0 -0
  61. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
  62. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_aws.py +0 -0
  63. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
  64. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_date.py +0 -0
  65. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_html.py +0 -0
  66. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_kafka.py +0 -0
  67. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_md5.py +0 -0
  68. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_selenium.py +0 -0
  69. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_simple_timer.py +0 -0
  70. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_str.py +0 -0
  71. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_type_mapping.py +0 -0
  72. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit/util/util_url.py +0 -0
  73. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit.egg-info/dependency_links.txt +0 -0
  74. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit.egg-info/not-zip-safe +0 -0
  75. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit.egg-info/requires.txt +0 -0
  76. {orbitkit-0.8.36 → orbitkit-0.8.37}/orbitkit.egg-info/top_level.txt +0 -0
  77. {orbitkit-0.8.36 → orbitkit-0.8.37}/setup.cfg +0 -0
  78. {orbitkit-0.8.36 → orbitkit-0.8.37}/setup.py +0 -0
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.1
2
2
  Name: orbitkit
3
- Version: 0.8.36
3
+ Version: 0.8.37
4
4
  Summary: This project is only for Orbit Tech internal use.
5
5
  Home-page: https://github.com/clown-0726/orbitkit
6
6
  Author: Lilu Cao
@@ -28,18 +28,6 @@ Requires-Dist: prettytable>=3.0.0
28
28
  Requires-Dist: pytz>=2022.1
29
29
  Requires-Dist: Deprecated
30
30
  Requires-Dist: func_timeout
31
- Dynamic: author
32
- Dynamic: author-email
33
- Dynamic: classifier
34
- Dynamic: description
35
- Dynamic: description-content-type
36
- Dynamic: home-page
37
- Dynamic: license
38
- Dynamic: maintainer
39
- Dynamic: maintainer-email
40
- Dynamic: platform
41
- Dynamic: requires-dist
42
- Dynamic: summary
43
31
 
44
32
  # orbitkit
45
33
 
@@ -0,0 +1 @@
1
+ 0.8.37
@@ -67,3 +67,6 @@ from .util_url import (
67
67
  website_url_standardize,
68
68
  website_url_compare,
69
69
  )
70
+ from .cache_asset_downloader import (
71
+ CacheAssetDownloader,
72
+ )
@@ -0,0 +1,132 @@
1
+ import os
2
+ import platform
3
+ import hashlib
4
+ import requests
5
+ from pathlib import Path
6
+ from typing import Optional
7
+ from urllib.parse import urlparse
8
+
9
+ """
10
+ 功能描述
11
+ CacheAssetDownloader 是一个智能的资源下载器,主要用于管理大型文件(如机器学习模型、数据集等)的下载和本地缓存。
12
+
13
+ 跨平台缓存管理:
14
+ Windows:使用 %LOCALAPPDATA% 或 用户目录/AppData/Local
15
+ macOS:使用 ~/Library/Caches
16
+ Linux/Docker:使用 $XDG_CACHE_HOME 或 ~/.cache
17
+
18
+ 智能缓存机制:
19
+ 自动检查本地缓存是否存在
20
+ 支持 MD5 哈希验证确保文件完整性
21
+ 避免重复下载,节省带宽和时间
22
+
23
+ 安全下载:
24
+ 流式下载,适合大文件
25
+ 异常处理和错误恢复
26
+ 文件验证失败时自动清理
27
+ """
28
+
29
+
30
+ class CacheAssetDownloader:
31
+ def __init__(self, asset_sub_folder: str, download_url: str, expected_hash: Optional[str] = None):
32
+ self.asset_sub_folder = asset_sub_folder
33
+ self.download_url = download_url
34
+ self.expected_hash = expected_hash
35
+
36
+ # 设置缓存目录
37
+ self.cache_dir = self._get_cache_dir()
38
+ self.asset_path = None
39
+
40
+ # 自动下载资源
41
+ self._download_if_needed()
42
+
43
+ def _get_cache_dir(self) -> Path:
44
+ """获取缓存目录"""
45
+ system = platform.system().lower()
46
+
47
+ if system == 'windows':
48
+ base_dir = Path(os.environ.get('LOCALAPPDATA', Path.home() / 'AppData' / 'Local'))
49
+ elif system == 'darwin': # macOS
50
+ base_dir = Path.home() / 'Library' / 'Caches'
51
+ else: # Linux/Docker
52
+ base_dir = Path(os.environ.get('XDG_CACHE_HOME', Path.home() / '.cache'))
53
+
54
+ cache_dir = base_dir / 'orbit_assets' / self.asset_sub_folder
55
+ cache_dir.mkdir(parents=True, exist_ok=True)
56
+
57
+ print(f"You current system: >>>{system}<<<, with cache path: >>>{cache_dir}<<<")
58
+ return cache_dir
59
+
60
+ def _validate_file(self, file_path: Path) -> bool:
61
+ """验证文件"""
62
+ if not file_path.exists():
63
+ return False
64
+
65
+ if not self.expected_hash: # 如果没开启 hash 验证,则直接返回
66
+ return True
67
+
68
+ # 计算MD5
69
+ hash_md5 = hashlib.md5()
70
+ with open(file_path, 'rb') as f:
71
+ for chunk in iter(lambda: f.read(4096), b""):
72
+ hash_md5.update(chunk)
73
+
74
+ return hash_md5.hexdigest().lower() == self.expected_hash.lower()
75
+
76
+ def _download_file(self, url: str, target_path: Path) -> bool:
77
+ """下载文件"""
78
+ try:
79
+ print(f"正在下载: {url}")
80
+ response = requests.get(url, stream=True)
81
+ response.raise_for_status()
82
+
83
+ with open(target_path, 'wb') as f:
84
+ for chunk in response.iter_content(chunk_size=8192):
85
+ if chunk:
86
+ f.write(chunk)
87
+
88
+ print(f"下载完成: {target_path}")
89
+ return True
90
+ except Exception as e:
91
+ print(f"下载失败: {e}")
92
+ return False
93
+
94
+ def _download_if_needed(self):
95
+ """检查并下载资源"""
96
+ # 确定文件名
97
+ filename = os.path.basename(urlparse(self.download_url).path)
98
+ asset_file = self.cache_dir / filename
99
+
100
+ # 检查缓存
101
+ if self._validate_file(asset_file):
102
+ print(f"使用缓存文件: {asset_file}")
103
+ self.asset_path = asset_file
104
+ return
105
+
106
+ # 下载文件
107
+ if not self._download_file(self.download_url, asset_file):
108
+ raise RuntimeError(f"下载失败: {self.download_url}")
109
+
110
+ # 验证文件
111
+ if not self._validate_file(asset_file):
112
+ asset_file.unlink(missing_ok=True)
113
+ raise RuntimeError("文件验证失败")
114
+
115
+ self.asset_path = asset_file
116
+
117
+ def get_path(self) -> Path:
118
+ """获取资源路径"""
119
+ return self.asset_path
120
+
121
+
122
+ if __name__ == "__main__":
123
+ downloader = CacheAssetDownloader(
124
+ asset_sub_folder="fasttext",
125
+ download_url="https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.bin",
126
+ )
127
+
128
+ # cache_dir = downloader._get_cache_dir()
129
+ # print(cache_dir)
130
+
131
+ model_path = downloader.get_path()
132
+ print(f"模型路径: {model_path}")
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.1
2
2
  Name: orbitkit
3
- Version: 0.8.36
3
+ Version: 0.8.37
4
4
  Summary: This project is only for Orbit Tech internal use.
5
5
  Home-page: https://github.com/clown-0726/orbitkit
6
6
  Author: Lilu Cao
@@ -28,18 +28,6 @@ Requires-Dist: prettytable>=3.0.0
28
28
  Requires-Dist: pytz>=2022.1
29
29
  Requires-Dist: Deprecated
30
30
  Requires-Dist: func_timeout
31
- Dynamic: author
32
- Dynamic: author-email
33
- Dynamic: classifier
34
- Dynamic: description
35
- Dynamic: description-content-type
36
- Dynamic: home-page
37
- Dynamic: license
38
- Dynamic: maintainer
39
- Dynamic: maintainer-email
40
- Dynamic: platform
41
- Dynamic: requires-dist
42
- Dynamic: summary
43
31
 
44
32
  # orbitkit
45
33
 
@@ -56,6 +56,7 @@ orbitkit/pdf_extractor_simple/utils.py
56
56
  orbitkit/pdf_writer/__init__.py
57
57
  orbitkit/pdf_writer/pdf_writer_simple.py
58
58
  orbitkit/util/__init__.py
59
+ orbitkit/util/cache_asset_downloader.py
59
60
  orbitkit/util/common.py
60
61
  orbitkit/util/customize_regix_manager.py
61
62
  orbitkit/util/secret_manager.py
@@ -1 +0,0 @@
1
- 0.8.36
File without changes
File without changes
File without changes
File without changes
File without changes