yt-framework 0.1.0__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 (55) hide show
  1. yt_framework-0.1.0/LICENSE +201 -0
  2. yt_framework-0.1.0/PKG-INFO +147 -0
  3. yt_framework-0.1.0/README.md +115 -0
  4. yt_framework-0.1.0/pyproject.toml +60 -0
  5. yt_framework-0.1.0/setup.cfg +4 -0
  6. yt_framework-0.1.0/yt_framework/__init__.py +1 -0
  7. yt_framework-0.1.0/yt_framework/core/__init__.py +7 -0
  8. yt_framework-0.1.0/yt_framework/core/dependencies.py +60 -0
  9. yt_framework-0.1.0/yt_framework/core/discovery.py +95 -0
  10. yt_framework-0.1.0/yt_framework/core/pipeline.py +413 -0
  11. yt_framework-0.1.0/yt_framework/core/registry.py +61 -0
  12. yt_framework-0.1.0/yt_framework/core/stage.py +129 -0
  13. yt_framework-0.1.0/yt_framework/operations/__init__.py +57 -0
  14. yt_framework-0.1.0/yt_framework/operations/checkpoint.py +110 -0
  15. yt_framework-0.1.0/yt_framework/operations/common.py +107 -0
  16. yt_framework-0.1.0/yt_framework/operations/dependencies.py +246 -0
  17. yt_framework-0.1.0/yt_framework/operations/dependency_strategy.py +165 -0
  18. yt_framework-0.1.0/yt_framework/operations/map.py +218 -0
  19. yt_framework-0.1.0/yt_framework/operations/s3.py +82 -0
  20. yt_framework-0.1.0/yt_framework/operations/table.py +86 -0
  21. yt_framework-0.1.0/yt_framework/operations/upload.py +505 -0
  22. yt_framework-0.1.0/yt_framework/operations/vanilla.py +217 -0
  23. yt_framework-0.1.0/yt_framework/utils/__init__.py +17 -0
  24. yt_framework-0.1.0/yt_framework/utils/archive.py +106 -0
  25. yt_framework-0.1.0/yt_framework/utils/env.py +63 -0
  26. yt_framework-0.1.0/yt_framework/utils/ignore.py +382 -0
  27. yt_framework-0.1.0/yt_framework/utils/logging.py +151 -0
  28. yt_framework-0.1.0/yt_framework/yt/__init__.py +6 -0
  29. yt_framework-0.1.0/yt_framework/yt/client_base.py +483 -0
  30. yt_framework-0.1.0/yt_framework/yt/client_dev.py +911 -0
  31. yt_framework-0.1.0/yt_framework/yt/client_prod.py +758 -0
  32. yt_framework-0.1.0/yt_framework/yt/dev_simulator.py +228 -0
  33. yt_framework-0.1.0/yt_framework/yt/factory.py +48 -0
  34. yt_framework-0.1.0/yt_framework/yt/yql_builder.py +454 -0
  35. yt_framework-0.1.0/yt_framework.egg-info/PKG-INFO +147 -0
  36. yt_framework-0.1.0/yt_framework.egg-info/SOURCES.txt +53 -0
  37. yt_framework-0.1.0/yt_framework.egg-info/dependency_links.txt +1 -0
  38. yt_framework-0.1.0/yt_framework.egg-info/requires.txt +10 -0
  39. yt_framework-0.1.0/yt_framework.egg-info/top_level.txt +2 -0
  40. yt_framework-0.1.0/ytjobs/__init__.py +24 -0
  41. yt_framework-0.1.0/ytjobs/chatml/__init__.py +5 -0
  42. yt_framework-0.1.0/ytjobs/chatml/chatml.py +60 -0
  43. yt_framework-0.1.0/ytjobs/checkpoint/__init__.py +17 -0
  44. yt_framework-0.1.0/ytjobs/checkpoint/utils.py +287 -0
  45. yt_framework-0.1.0/ytjobs/config/__init__.py +29 -0
  46. yt_framework-0.1.0/ytjobs/logging/__init__.py +16 -0
  47. yt_framework-0.1.0/ytjobs/logging/logger.py +148 -0
  48. yt_framework-0.1.0/ytjobs/logging/silencer.py +118 -0
  49. yt_framework-0.1.0/ytjobs/mapper/__init__.py +11 -0
  50. yt_framework-0.1.0/ytjobs/mapper/mappers.py +217 -0
  51. yt_framework-0.1.0/ytjobs/mapper/utils.py +119 -0
  52. yt_framework-0.1.0/ytjobs/s3/__init__.py +5 -0
  53. yt_framework-0.1.0/ytjobs/s3/client.py +197 -0
  54. yt_framework-0.1.0/ytjobs/video/__init__.py +17 -0
  55. yt_framework-0.1.0/ytjobs/video/utils.py +119 -0
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright [yyyy] [name of copyright owner]
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
@@ -0,0 +1,147 @@
1
+ Metadata-Version: 2.4
2
+ Name: yt_framework
3
+ Version: 0.1.0
4
+ Summary: YTsaurus pipeline framework with utilities and common modules
5
+ Author-email: Artem Zavarzin <artemutz555@gmail.com>, Gregory Koganovsky <g.koganovsky@gmail.com>
6
+ Maintainer-email: Gregory Koganovsky <g.koganovsky@gmail.com>, Artem Zavarzin <artemutz555@gmail.com>
7
+ License-Expression: Apache-2.0
8
+ Project-URL: Homepage, https://github.com/GregoryKogan/yt-framework
9
+ Project-URL: Repository, https://github.com/GregoryKogan/yt-framework
10
+ Project-URL: Issues, https://github.com/GregoryKogan/yt-framework/issues
11
+ Keywords: ytsaurus,yt,pipeline,data-processing,map-reduce,distributed-computing,big-data
12
+ Classifier: Development Status :: 4 - Beta
13
+ Classifier: Intended Audience :: Developers
14
+ Classifier: Programming Language :: Python :: 3
15
+ Classifier: Programming Language :: Python :: 3.11
16
+ Classifier: Topic :: Software Development :: Libraries :: Python Modules
17
+ Classifier: Topic :: Scientific/Engineering
18
+ Classifier: Topic :: System :: Distributed Computing
19
+ Requires-Python: >=3.11
20
+ Description-Content-Type: text/markdown
21
+ License-File: LICENSE
22
+ Requires-Dist: botocore==1.35.99
23
+ Requires-Dist: boto3==1.35.99
24
+ Requires-Dist: ytsaurus-client>=0.13.0
25
+ Requires-Dist: python-decouple>=3.8
26
+ Requires-Dist: duckdb>=1.0.0
27
+ Requires-Dist: omegaconf>=2.3.0
28
+ Provides-Extra: dev
29
+ Requires-Dist: pytest>=7.0.0; extra == "dev"
30
+ Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
31
+ Dynamic: license-file
32
+
33
+ # YT Framework
34
+
35
+ ![GitHub License](https://img.shields.io/github/license/GregoryKogan/yt-framework)
36
+ ![PyPI - Version](https://img.shields.io/pypi/v/yt_framework)
37
+ ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/yt_framework)
38
+
39
+ A powerful Python framework for building and executing data processing pipelines on YTsaurus (YT) clusters. YT Framework simplifies pipeline development with automatic stage discovery, seamless dev/prod mode switching, and comprehensive support for YT operations.
40
+
41
+ ## Key Features
42
+
43
+ - **Pipeline & Stage Architecture**: Organize complex workflows into reusable stages
44
+ - **Automatic Stage Discovery**: No manual registration needed - just create stages and run
45
+ - **Dev/Prod Modes**: Develop locally with file system simulation, deploy to YT cluster seamlessly
46
+ - **Multiple Operation Types**: Support for Map, Vanilla, YQL, and S3 operations
47
+ - **Code Upload**: Automatic code packaging and deployment to YT cluster
48
+ - **Docker Support**: Custom Docker images for GPU workloads and special dependencies
49
+ - **Checkpoint Management**: Built-in support for ML model checkpoints
50
+ - **Configuration Management**: Flexible YAML-based configuration with multiple config support
51
+
52
+ ## Quick Links
53
+
54
+ - **[Installation & Quick Start](docs/index.md#installation)** - Get up and running in minutes
55
+ - **[Pipelines & Stages](docs/pipelines-and-stages.md)** - Core concepts and architecture
56
+ - **[Operations Guide](docs/operations/)** - Map, Vanilla, YQL, and S3 operations
57
+ - **[Advanced Topics](docs/advanced/)** - Docker, checkpoints, code upload, and more
58
+ - **[Examples](examples/)** - Complete working examples for every feature
59
+
60
+ ## Installation
61
+
62
+ ### For Users
63
+
64
+ Install from PyPI:
65
+
66
+ ```bash
67
+ pip install yt_framework
68
+ ```
69
+
70
+ ### For Developers and Contributors
71
+
72
+ Install in editable mode from source:
73
+
74
+ ```bash
75
+ pip install -e .
76
+ ```
77
+
78
+ See [Installation Guide](docs/index.md#installation) for prerequisites and detailed setup instructions.
79
+
80
+ ## Quick Start
81
+
82
+ Create your first pipeline in 3 steps:
83
+
84
+ 1. **Create pipeline structure**:
85
+
86
+ ```bash
87
+ mkdir my_pipeline && cd my_pipeline
88
+ mkdir -p stages/my_stage configs
89
+ ```
90
+
91
+ 2. **Create `pipeline.py`**:
92
+
93
+ ```python
94
+ from yt_framework.core.pipeline import DefaultPipeline
95
+
96
+ if __name__ == "__main__":
97
+ DefaultPipeline.main()
98
+ ```
99
+
100
+ 3. **Create stage and config**:
101
+
102
+ ```python
103
+ # stages/my_stage/stage.py
104
+ from yt_framework.core.stage import BaseStage
105
+
106
+ class MyStage(BaseStage):
107
+ def run(self, debug):
108
+ self.logger.info("Hello from YT Framework!")
109
+ return debug
110
+ ```
111
+
112
+ See [Quick Start Guide](docs/index.md#quick-start) for complete example.
113
+
114
+ ## Examples
115
+
116
+ The `examples/` directory contains comprehensive examples demonstrating all framework features:
117
+
118
+ - **[01_hello_world](examples/01_hello_world/)** - Basic pipeline and table operations
119
+ - **[02_multi_stage_pipeline](examples/02_multi_stage_pipeline/)** - Multiple stages with data flow
120
+ - **[03_yql_operations](examples/03_yql_operations/)** - All YQL table operations
121
+ - **[04_map_operation](examples/04_map_operation/)** - Map operations with custom code
122
+ - **[05_vanilla_operation](examples/05_vanilla_operation/)** - Vanilla standalone jobs
123
+ - **[06_s3_integration](examples/06_s3_integration/)** - S3 file listing and processing
124
+ - **[07_custom_docker](examples/07_custom_docker/)** - Custom Docker images
125
+ - **[08_multiple_configs](examples/08_multiple_configs/)** - Multiple configuration files
126
+ - **[09_multiple_operations](examples/09_multiple_operations/)** - Combining operations in one stage
127
+ - **[environment_log](examples/environment_log/)** - Comprehensive environment logging
128
+ - **[video_gpu](examples/video_gpu/)** - GPU processing workflows
129
+
130
+ ## Documentation
131
+
132
+ Full documentation is available in the [`docs/`](docs/) directory:
133
+
134
+ - **[Main Documentation](docs/index.md)** - Installation, quick start, and overview
135
+ - **[Pipelines & Stages](docs/pipelines-and-stages.md)** - Core architecture
136
+ - **[Configuration](docs/configuration.md)** - Config files and secrets management
137
+ - **[Dev vs Prod](docs/dev-vs-prod.md)** - Development and production modes
138
+ - **[Operations](docs/operations/)** - Map, Vanilla, YQL, S3 operations
139
+ - **[Advanced Topics](docs/advanced/)** - Docker, checkpoints, code upload
140
+ - **[API Reference](docs/reference/api.md)** - Complete API documentation
141
+ - **[Troubleshooting](docs/troubleshooting.md)** - Common issues and solutions
142
+
143
+ ## Requirements
144
+
145
+ - Python 3.11+
146
+ - YTsaurus cluster access (for production mode)
147
+ - YT credentials (for production mode)
@@ -0,0 +1,115 @@
1
+ # YT Framework
2
+
3
+ ![GitHub License](https://img.shields.io/github/license/GregoryKogan/yt-framework)
4
+ ![PyPI - Version](https://img.shields.io/pypi/v/yt_framework)
5
+ ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/yt_framework)
6
+
7
+ A powerful Python framework for building and executing data processing pipelines on YTsaurus (YT) clusters. YT Framework simplifies pipeline development with automatic stage discovery, seamless dev/prod mode switching, and comprehensive support for YT operations.
8
+
9
+ ## Key Features
10
+
11
+ - **Pipeline & Stage Architecture**: Organize complex workflows into reusable stages
12
+ - **Automatic Stage Discovery**: No manual registration needed - just create stages and run
13
+ - **Dev/Prod Modes**: Develop locally with file system simulation, deploy to YT cluster seamlessly
14
+ - **Multiple Operation Types**: Support for Map, Vanilla, YQL, and S3 operations
15
+ - **Code Upload**: Automatic code packaging and deployment to YT cluster
16
+ - **Docker Support**: Custom Docker images for GPU workloads and special dependencies
17
+ - **Checkpoint Management**: Built-in support for ML model checkpoints
18
+ - **Configuration Management**: Flexible YAML-based configuration with multiple config support
19
+
20
+ ## Quick Links
21
+
22
+ - **[Installation & Quick Start](docs/index.md#installation)** - Get up and running in minutes
23
+ - **[Pipelines & Stages](docs/pipelines-and-stages.md)** - Core concepts and architecture
24
+ - **[Operations Guide](docs/operations/)** - Map, Vanilla, YQL, and S3 operations
25
+ - **[Advanced Topics](docs/advanced/)** - Docker, checkpoints, code upload, and more
26
+ - **[Examples](examples/)** - Complete working examples for every feature
27
+
28
+ ## Installation
29
+
30
+ ### For Users
31
+
32
+ Install from PyPI:
33
+
34
+ ```bash
35
+ pip install yt_framework
36
+ ```
37
+
38
+ ### For Developers and Contributors
39
+
40
+ Install in editable mode from source:
41
+
42
+ ```bash
43
+ pip install -e .
44
+ ```
45
+
46
+ See [Installation Guide](docs/index.md#installation) for prerequisites and detailed setup instructions.
47
+
48
+ ## Quick Start
49
+
50
+ Create your first pipeline in 3 steps:
51
+
52
+ 1. **Create pipeline structure**:
53
+
54
+ ```bash
55
+ mkdir my_pipeline && cd my_pipeline
56
+ mkdir -p stages/my_stage configs
57
+ ```
58
+
59
+ 2. **Create `pipeline.py`**:
60
+
61
+ ```python
62
+ from yt_framework.core.pipeline import DefaultPipeline
63
+
64
+ if __name__ == "__main__":
65
+ DefaultPipeline.main()
66
+ ```
67
+
68
+ 3. **Create stage and config**:
69
+
70
+ ```python
71
+ # stages/my_stage/stage.py
72
+ from yt_framework.core.stage import BaseStage
73
+
74
+ class MyStage(BaseStage):
75
+ def run(self, debug):
76
+ self.logger.info("Hello from YT Framework!")
77
+ return debug
78
+ ```
79
+
80
+ See [Quick Start Guide](docs/index.md#quick-start) for complete example.
81
+
82
+ ## Examples
83
+
84
+ The `examples/` directory contains comprehensive examples demonstrating all framework features:
85
+
86
+ - **[01_hello_world](examples/01_hello_world/)** - Basic pipeline and table operations
87
+ - **[02_multi_stage_pipeline](examples/02_multi_stage_pipeline/)** - Multiple stages with data flow
88
+ - **[03_yql_operations](examples/03_yql_operations/)** - All YQL table operations
89
+ - **[04_map_operation](examples/04_map_operation/)** - Map operations with custom code
90
+ - **[05_vanilla_operation](examples/05_vanilla_operation/)** - Vanilla standalone jobs
91
+ - **[06_s3_integration](examples/06_s3_integration/)** - S3 file listing and processing
92
+ - **[07_custom_docker](examples/07_custom_docker/)** - Custom Docker images
93
+ - **[08_multiple_configs](examples/08_multiple_configs/)** - Multiple configuration files
94
+ - **[09_multiple_operations](examples/09_multiple_operations/)** - Combining operations in one stage
95
+ - **[environment_log](examples/environment_log/)** - Comprehensive environment logging
96
+ - **[video_gpu](examples/video_gpu/)** - GPU processing workflows
97
+
98
+ ## Documentation
99
+
100
+ Full documentation is available in the [`docs/`](docs/) directory:
101
+
102
+ - **[Main Documentation](docs/index.md)** - Installation, quick start, and overview
103
+ - **[Pipelines & Stages](docs/pipelines-and-stages.md)** - Core architecture
104
+ - **[Configuration](docs/configuration.md)** - Config files and secrets management
105
+ - **[Dev vs Prod](docs/dev-vs-prod.md)** - Development and production modes
106
+ - **[Operations](docs/operations/)** - Map, Vanilla, YQL, S3 operations
107
+ - **[Advanced Topics](docs/advanced/)** - Docker, checkpoints, code upload
108
+ - **[API Reference](docs/reference/api.md)** - Complete API documentation
109
+ - **[Troubleshooting](docs/troubleshooting.md)** - Common issues and solutions
110
+
111
+ ## Requirements
112
+
113
+ - Python 3.11+
114
+ - YTsaurus cluster access (for production mode)
115
+ - YT credentials (for production mode)
@@ -0,0 +1,60 @@
1
+ [build-system]
2
+ requires = ["setuptools>=68.0", "wheel"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "yt_framework"
7
+ version = "v0.1.0"
8
+ description = "YTsaurus pipeline framework with utilities and common modules"
9
+ readme = "README.md"
10
+ requires-python = ">=3.11"
11
+ license = "Apache-2.0"
12
+ authors = [
13
+ {name = "Artem Zavarzin", email = "artemutz555@gmail.com"},
14
+ {name = "Gregory Koganovsky", email = "g.koganovsky@gmail.com"},
15
+ ]
16
+ maintainers = [
17
+ {name = "Gregory Koganovsky", email = "g.koganovsky@gmail.com"},
18
+ {name = "Artem Zavarzin", email = "artemutz555@gmail.com"},
19
+ ]
20
+ keywords = [
21
+ "ytsaurus",
22
+ "yt",
23
+ "pipeline",
24
+ "data-processing",
25
+ "map-reduce",
26
+ "distributed-computing",
27
+ "big-data",
28
+ ]
29
+ classifiers = [
30
+ "Development Status :: 4 - Beta",
31
+ "Intended Audience :: Developers",
32
+ "Programming Language :: Python :: 3",
33
+ "Programming Language :: Python :: 3.11",
34
+ "Topic :: Software Development :: Libraries :: Python Modules",
35
+ "Topic :: Scientific/Engineering",
36
+ "Topic :: System :: Distributed Computing",
37
+ ]
38
+ dependencies = [
39
+ "botocore==1.35.99",
40
+ "boto3==1.35.99",
41
+ "ytsaurus-client>=0.13.0",
42
+ "python-decouple>=3.8",
43
+ "duckdb>=1.0.0",
44
+ "omegaconf>=2.3.0",
45
+ ]
46
+
47
+ [project.urls]
48
+ Homepage = "https://github.com/GregoryKogan/yt-framework"
49
+ Repository = "https://github.com/GregoryKogan/yt-framework"
50
+ Issues = "https://github.com/GregoryKogan/yt-framework/issues"
51
+
52
+ [project.optional-dependencies]
53
+ dev = [
54
+ "pytest>=7.0.0",
55
+ "pytest-cov>=4.0.0",
56
+ ]
57
+
58
+ [tool.setuptools.packages.find]
59
+ where = ["."]
60
+ include = ["yt_framework*", "ytjobs*"]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
@@ -0,0 +1 @@
1
+ """YT Framework - YTsaurus pipeline framework."""
@@ -0,0 +1,7 @@
1
+ """Core framework classes."""
2
+
3
+ from .pipeline import BasePipeline
4
+ from .stage import BaseStage
5
+ from .registry import StageRegistry
6
+
7
+ __all__ = ["BasePipeline", "BaseStage", "StageRegistry"]
@@ -0,0 +1,60 @@
1
+ """
2
+ Stage Dependencies
3
+ ==================
4
+
5
+ Dependency injection container for stages.
6
+
7
+ This module provides a clean separation between stages and the pipeline,
8
+ following SOLID principles (especially Dependency Inversion and Interface Segregation).
9
+ """
10
+
11
+ from dataclasses import dataclass
12
+ from pathlib import Path
13
+ from typing import Protocol
14
+
15
+ from omegaconf import DictConfig
16
+ from yt_framework.yt.client_base import BaseYTClient
17
+
18
+
19
+ class StageDependencies(Protocol):
20
+ """
21
+ Protocol defining what dependencies stages need.
22
+
23
+ This is NOT the same as the 'context' parameter in run() methods:
24
+ - StageDependencies: Injected services/config (yt_client, config, etc.)
25
+ - context parameter: Shared data dictionary passed between stages
26
+
27
+ Benefits:
28
+ - Dependency Inversion: Depends on abstraction, not concrete Pipeline
29
+ - Interface Segregation: Only exposes what stages actually use
30
+ - Testability: Easy to create mock dependencies for testing
31
+ """
32
+
33
+ @property
34
+ def yt_client(self) -> BaseYTClient:
35
+ """YT client for operations."""
36
+ ...
37
+
38
+ @property
39
+ def pipeline_config(self) -> DictConfig:
40
+ """Pipeline-level configuration (contains build_folder and secrets)."""
41
+ ...
42
+
43
+ @property
44
+ def configs_dir(self) -> Path:
45
+ """Directory containing secrets.env and other config files."""
46
+ ...
47
+
48
+
49
+ @dataclass
50
+ class PipelineStageDependencies:
51
+ """
52
+ Default implementation of StageDependencies.
53
+
54
+ Used by BasePipeline to inject dependencies into stages.
55
+ This class is instantiated by the pipeline and passed to each stage.
56
+ """
57
+
58
+ yt_client: BaseYTClient
59
+ pipeline_config: DictConfig
60
+ configs_dir: Path