datamuru 0.1.0a0__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 (76) hide show
  1. datamuru-0.1.0a0/LICENSE +201 -0
  2. datamuru-0.1.0a0/PKG-INFO +168 -0
  3. datamuru-0.1.0a0/README.md +100 -0
  4. datamuru-0.1.0a0/datamuru/__init__.py +4 -0
  5. datamuru-0.1.0a0/datamuru/api.py +50 -0
  6. datamuru-0.1.0a0/datamuru/bootstrap.py +141 -0
  7. datamuru-0.1.0a0/datamuru/cli/__init__.py +1 -0
  8. datamuru-0.1.0a0/datamuru/cli/commands/__init__.py +19 -0
  9. datamuru-0.1.0a0/datamuru/cli/commands/apply.py +45 -0
  10. datamuru-0.1.0a0/datamuru/cli/commands/destroy.py +23 -0
  11. datamuru-0.1.0a0/datamuru/cli/commands/doctor.py +31 -0
  12. datamuru-0.1.0a0/datamuru/cli/commands/edition.py +32 -0
  13. datamuru-0.1.0a0/datamuru/cli/commands/import_.py +83 -0
  14. datamuru-0.1.0a0/datamuru/cli/commands/init.py +25 -0
  15. datamuru-0.1.0a0/datamuru/cli/commands/plan.py +32 -0
  16. datamuru-0.1.0a0/datamuru/cli/commands/validate.py +26 -0
  17. datamuru-0.1.0a0/datamuru/cli/guard.py +19 -0
  18. datamuru-0.1.0a0/datamuru/cli/main.py +22 -0
  19. datamuru-0.1.0a0/datamuru/cli/output.py +51 -0
  20. datamuru-0.1.0a0/datamuru/core/__init__.py +1 -0
  21. datamuru-0.1.0a0/datamuru/core/apply/__init__.py +5 -0
  22. datamuru-0.1.0a0/datamuru/core/apply/engine.py +10 -0
  23. datamuru-0.1.0a0/datamuru/core/apply/executor.py +88 -0
  24. datamuru-0.1.0a0/datamuru/core/apply/models.py +16 -0
  25. datamuru-0.1.0a0/datamuru/core/apply.py +31 -0
  26. datamuru-0.1.0a0/datamuru/core/config/__init__.py +31 -0
  27. datamuru-0.1.0a0/datamuru/core/config/models.py +75 -0
  28. datamuru-0.1.0a0/datamuru/core/config/parser.py +44 -0
  29. datamuru-0.1.0a0/datamuru/core/config/resolver.py +79 -0
  30. datamuru-0.1.0a0/datamuru/core/config/validator.py +370 -0
  31. datamuru-0.1.0a0/datamuru/core/config.py +123 -0
  32. datamuru-0.1.0a0/datamuru/core/engine.py +123 -0
  33. datamuru-0.1.0a0/datamuru/core/importer/__init__.py +5 -0
  34. datamuru-0.1.0a0/datamuru/core/importer/discovery.py +9 -0
  35. datamuru-0.1.0a0/datamuru/core/importer/engine.py +76 -0
  36. datamuru-0.1.0a0/datamuru/core/importer/generator.py +20 -0
  37. datamuru-0.1.0a0/datamuru/core/importer/models.py +43 -0
  38. datamuru-0.1.0a0/datamuru/core/models.py +80 -0
  39. datamuru-0.1.0a0/datamuru/core/plan/__init__.py +5 -0
  40. datamuru-0.1.0a0/datamuru/core/plan/engine.py +122 -0
  41. datamuru-0.1.0a0/datamuru/core/plan/models.py +60 -0
  42. datamuru-0.1.0a0/datamuru/core/plan/renderer.py +15 -0
  43. datamuru-0.1.0a0/datamuru/core/plan.py +66 -0
  44. datamuru-0.1.0a0/datamuru/core/schema.py +91 -0
  45. datamuru-0.1.0a0/datamuru/core/state/__init__.py +5 -0
  46. datamuru-0.1.0a0/datamuru/core/state/backends/__init__.py +4 -0
  47. datamuru-0.1.0a0/datamuru/core/state/backends/base.py +13 -0
  48. datamuru-0.1.0a0/datamuru/core/state/backends/local.py +33 -0
  49. datamuru-0.1.0a0/datamuru/core/state/manager.py +20 -0
  50. datamuru-0.1.0a0/datamuru/core/state/models.py +28 -0
  51. datamuru-0.1.0a0/datamuru/core/state.py +22 -0
  52. datamuru-0.1.0a0/datamuru/edition.py +74 -0
  53. datamuru-0.1.0a0/datamuru/errors.py +92 -0
  54. datamuru-0.1.0a0/datamuru/governance/__init__.py +1 -0
  55. datamuru-0.1.0a0/datamuru/governance/masking.py +19 -0
  56. datamuru-0.1.0a0/datamuru/governance/rbac.py +50 -0
  57. datamuru-0.1.0a0/datamuru/governance/taxonomy.py +29 -0
  58. datamuru-0.1.0a0/datamuru/modeling.py +7 -0
  59. datamuru-0.1.0a0/datamuru/providers/__init__.py +1 -0
  60. datamuru-0.1.0a0/datamuru/providers/base.py +32 -0
  61. datamuru-0.1.0a0/datamuru/providers/databricks/__init__.py +1 -0
  62. datamuru-0.1.0a0/datamuru/providers/databricks/auth.py +64 -0
  63. datamuru-0.1.0a0/datamuru/providers/databricks/client.py +837 -0
  64. datamuru-0.1.0a0/datamuru/providers/databricks/execution.py +38 -0
  65. datamuru-0.1.0a0/datamuru/providers/databricks/provider.py +1061 -0
  66. datamuru-0.1.0a0/datamuru/providers/factory.py +14 -0
  67. datamuru-0.1.0a0/datamuru/py.typed +1 -0
  68. datamuru-0.1.0a0/datamuru/types.py +74 -0
  69. datamuru-0.1.0a0/datamuru.egg-info/PKG-INFO +168 -0
  70. datamuru-0.1.0a0/datamuru.egg-info/SOURCES.txt +74 -0
  71. datamuru-0.1.0a0/datamuru.egg-info/dependency_links.txt +1 -0
  72. datamuru-0.1.0a0/datamuru.egg-info/entry_points.txt +2 -0
  73. datamuru-0.1.0a0/datamuru.egg-info/requires.txt +45 -0
  74. datamuru-0.1.0a0/datamuru.egg-info/top_level.txt +1 -0
  75. datamuru-0.1.0a0/pyproject.toml +120 -0
  76. datamuru-0.1.0a0/setup.cfg +4 -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 +1,168 @@
1
+ Metadata-Version: 2.4
2
+ Name: datamuru
3
+ Version: 0.1.0a0
4
+ Summary: Open source enterprise data infrastructure framework
5
+ Author: DataMuru
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/AjayAJ2000/DataMuru
8
+ Project-URL: Documentation, https://ajayaj2000.github.io/DataMuru/
9
+ Project-URL: Repository, https://github.com/AjayAJ2000/DataMuru
10
+ Project-URL: Issues, https://github.com/AjayAJ2000/DataMuru/issues
11
+ Project-URL: Changelog, https://github.com/AjayAJ2000/DataMuru/blob/main/CHANGELOG.md
12
+ Keywords: databricks,data-platform,data-mesh,data-governance,infrastructure
13
+ Classifier: Development Status :: 3 - Alpha
14
+ Classifier: Intended Audience :: Developers
15
+ Classifier: Intended Audience :: System Administrators
16
+ Classifier: Operating System :: OS Independent
17
+ Classifier: Programming Language :: Python :: 3
18
+ Classifier: Programming Language :: Python :: 3.10
19
+ Classifier: Programming Language :: Python :: 3.11
20
+ Classifier: Programming Language :: Python :: 3.12
21
+ Classifier: Programming Language :: Python :: 3.13
22
+ Classifier: Programming Language :: Python :: 3 :: Only
23
+ Classifier: Topic :: Software Development :: Libraries :: Python Modules
24
+ Classifier: Topic :: System :: Systems Administration
25
+ Classifier: Typing :: Typed
26
+ Requires-Python: >=3.10
27
+ Description-Content-Type: text/markdown
28
+ License-File: LICENSE
29
+ Requires-Dist: click<9,>=8.1
30
+ Requires-Dist: pydantic<3,>=2.0
31
+ Requires-Dist: PyYAML<7,>=6.0
32
+ Requires-Dist: requests<3,>=2.31
33
+ Requires-Dist: rich<14,>=13.0
34
+ Provides-Extra: databricks
35
+ Requires-Dist: databricks-sdk<1,>=0.18; extra == "databricks"
36
+ Provides-Extra: aws
37
+ Requires-Dist: boto3<2,>=1.34; extra == "aws"
38
+ Provides-Extra: azure
39
+ Requires-Dist: azure-identity<2,>=1.15; extra == "azure"
40
+ Requires-Dist: azure-keyvault-secrets<5,>=4.7; extra == "azure"
41
+ Requires-Dist: azure-storage-blob<13,>=12.19; extra == "azure"
42
+ Provides-Extra: gcp
43
+ Requires-Dist: google-cloud-secret-manager<3,>=2.16; extra == "gcp"
44
+ Requires-Dist: google-cloud-storage<3,>=2.13; extra == "gcp"
45
+ Provides-Extra: dev
46
+ Requires-Dist: build<2,>=1.2; extra == "dev"
47
+ Requires-Dist: mypy<2,>=1.8; extra == "dev"
48
+ Requires-Dist: pre-commit<4,>=3.6; extra == "dev"
49
+ Requires-Dist: pytest<9,>=8.0; extra == "dev"
50
+ Requires-Dist: pytest-asyncio<1,>=0.23; extra == "dev"
51
+ Requires-Dist: pytest-cov<6,>=4.1; extra == "dev"
52
+ Requires-Dist: pytest-mock<4,>=3.12; extra == "dev"
53
+ Requires-Dist: respx<1,>=0.21; extra == "dev"
54
+ Requires-Dist: ruff<1,>=0.2; extra == "dev"
55
+ Requires-Dist: twine<7,>=5; extra == "dev"
56
+ Provides-Extra: docs
57
+ Requires-Dist: mkdocs<2,>=1.6; extra == "docs"
58
+ Requires-Dist: mkdocs-material<10,>=9.5; extra == "docs"
59
+ Requires-Dist: mkdocstrings[python]<1,>=0.25; extra == "docs"
60
+ Provides-Extra: test
61
+ Requires-Dist: moto<6,>=5; extra == "test"
62
+ Requires-Dist: pytest<9,>=8.0; extra == "test"
63
+ Requires-Dist: pytest-asyncio<1,>=0.23; extra == "test"
64
+ Requires-Dist: pytest-cov<6,>=4.1; extra == "test"
65
+ Requires-Dist: pytest-mock<4,>=3.12; extra == "test"
66
+ Requires-Dist: respx<1,>=0.21; extra == "test"
67
+ Dynamic: license-file
68
+
69
+ # DataMuru
70
+
71
+ [![CI](https://github.com/AjayAJ2000/DataMuru/actions/workflows/ci.yml/badge.svg)](https://github.com/AjayAJ2000/DataMuru/actions/workflows/ci.yml)
72
+ [![Documentation](https://github.com/AjayAJ2000/DataMuru/actions/workflows/docs.yml/badge.svg)](https://ajayaj2000.github.io/DataMuru/)
73
+ [![PyPI](https://img.shields.io/pypi/v/datamuru.svg)](https://pypi.org/project/datamuru/)
74
+ ![License](https://img.shields.io/badge/License-Apache%202.0-0D7377)
75
+ [![Python](https://img.shields.io/pypi/pyversions/datamuru.svg)](https://pypi.org/project/datamuru/)
76
+
77
+ DataMuru is an Apache-2.0, Python-first data infrastructure framework.
78
+ It provisions and governs a Databricks-centered data estate from declarative configuration.
79
+ This public repository is the canonical home of the DataMuru Open Source Edition,
80
+ the shared configuration contract, the `datamuru` PyPI package, and the public documentation.
81
+
82
+ This repository contains the `v0.1 alpha` implementation with the following scope:
83
+
84
+ - Foundation layer: config loading, validation, local state, planning, apply, and destroy.
85
+ - Azure-first Databricks provider abstraction with multi-cloud-ready interfaces.
86
+ - Basic governance compilation: taxonomy, RBAC, and masking integration points.
87
+ - Core CLI surface: `init`, `validate`, `plan`, `apply`, and `destroy`.
88
+ - MkDocs-based product documentation written from an international SaaS product perspective.
89
+ - Live Databricks catalog, schema, ACL, import-discovery, and supported identity workflows.
90
+
91
+ ## Current stage
92
+
93
+ DataMuru is currently in the `v0.1 alpha` stage.
94
+
95
+ The package and CLI execute supported live Databricks operations when `execution_mode: live-apply` is configured. Alpha support currently covers catalogs, schemas, Unity Catalog ACLs, import discovery/config generation, and capability-aware account SCIM identity operations.
96
+
97
+ ## Open-core model
98
+
99
+ - **DataMuru OSS:** this public Apache-2.0 repository and PyPI package.
100
+ - **DataMuru Enterprise:** a private extension repository for paid capabilities such as multi-workspace orchestration, advanced compliance automation, hosted services, SSO/SAML, SIEM integrations, and SLA-backed operations.
101
+
102
+ Enterprise extends the public core; it does not maintain a competing fork of the core configuration model or CLI.
103
+
104
+ ## Design constraints
105
+
106
+ - Multi-cloud is an architectural requirement, but not a parity requirement for the alpha slice.
107
+ - `open-source` vs `enterprise` is the only runtime packaging boundary.
108
+ - Zero external data-tool runtime dependencies means no Terraform, dbt, Airflow, Great Expectations, Fivetran, or Airbyte required for the framework to operate.
109
+
110
+ ## Quick start
111
+
112
+ ```bash
113
+ pip install datamuru
114
+ datamuru validate --config datamuru.yml
115
+ datamuru doctor --config datamuru.yml
116
+ datamuru plan --config datamuru.yml
117
+ ```
118
+
119
+ ## Installation
120
+
121
+ From PyPI:
122
+
123
+ ```bash
124
+ pip install datamuru
125
+ ```
126
+
127
+ ## Documentation
128
+
129
+ This repository now includes a full MkDocs documentation site.
130
+
131
+ - MkDocs config: [mkdocs.yml](mkdocs.yml)
132
+ - Docs source: [docs](docs/)
133
+ - Published documentation: [ajayaj2000.github.io/DataMuru](https://ajayaj2000.github.io/DataMuru/)
134
+
135
+ To work on the documentation locally:
136
+
137
+ ```bash
138
+ python -m pip install -e ".[docs]"
139
+ python -m mkdocs serve
140
+ ```
141
+
142
+ ## Product usage guidance
143
+
144
+ For operator guidance and rollout practices, start with:
145
+
146
+ - [Product Usage Guidelines](docs/operations/usage-guidelines.md)
147
+ - [Team Adoption Guidelines](docs/operations/team-adoption-guidelines.md)
148
+
149
+ ## Trying it with Databricks Free Edition
150
+
151
+ If you want to try the framework with your own Databricks personal workspace, start here:
152
+
153
+ - [Databricks Free Edition Setup](docs/getting-started/databricks-free-edition.md)
154
+
155
+ For package-oriented team usage, also read:
156
+
157
+ - [Packaging and Distribution](docs/product/packaging-and-distribution.md)
158
+ - [Product Usage Guidelines](docs/operations/usage-guidelines.md)
159
+
160
+ ## Repository standards
161
+
162
+ - `datamuru/`: shared installable Python package
163
+ - `docs/`: versioned product documentation published through GitHub Pages
164
+ - `schemas/`: public configuration contracts
165
+ - `tests/`: unit, provider-contract, and end-to-end tests
166
+ - `.github/workflows/`: CI, documentation deployment, and trusted PyPI publishing
167
+
168
+ See [CONTRIBUTING.md](CONTRIBUTING.md) for the required local quality gate.
@@ -0,0 +1,100 @@
1
+ # DataMuru
2
+
3
+ [![CI](https://github.com/AjayAJ2000/DataMuru/actions/workflows/ci.yml/badge.svg)](https://github.com/AjayAJ2000/DataMuru/actions/workflows/ci.yml)
4
+ [![Documentation](https://github.com/AjayAJ2000/DataMuru/actions/workflows/docs.yml/badge.svg)](https://ajayaj2000.github.io/DataMuru/)
5
+ [![PyPI](https://img.shields.io/pypi/v/datamuru.svg)](https://pypi.org/project/datamuru/)
6
+ ![License](https://img.shields.io/badge/License-Apache%202.0-0D7377)
7
+ [![Python](https://img.shields.io/pypi/pyversions/datamuru.svg)](https://pypi.org/project/datamuru/)
8
+
9
+ DataMuru is an Apache-2.0, Python-first data infrastructure framework.
10
+ It provisions and governs a Databricks-centered data estate from declarative configuration.
11
+ This public repository is the canonical home of the DataMuru Open Source Edition,
12
+ the shared configuration contract, the `datamuru` PyPI package, and the public documentation.
13
+
14
+ This repository contains the `v0.1 alpha` implementation with the following scope:
15
+
16
+ - Foundation layer: config loading, validation, local state, planning, apply, and destroy.
17
+ - Azure-first Databricks provider abstraction with multi-cloud-ready interfaces.
18
+ - Basic governance compilation: taxonomy, RBAC, and masking integration points.
19
+ - Core CLI surface: `init`, `validate`, `plan`, `apply`, and `destroy`.
20
+ - MkDocs-based product documentation written from an international SaaS product perspective.
21
+ - Live Databricks catalog, schema, ACL, import-discovery, and supported identity workflows.
22
+
23
+ ## Current stage
24
+
25
+ DataMuru is currently in the `v0.1 alpha` stage.
26
+
27
+ The package and CLI execute supported live Databricks operations when `execution_mode: live-apply` is configured. Alpha support currently covers catalogs, schemas, Unity Catalog ACLs, import discovery/config generation, and capability-aware account SCIM identity operations.
28
+
29
+ ## Open-core model
30
+
31
+ - **DataMuru OSS:** this public Apache-2.0 repository and PyPI package.
32
+ - **DataMuru Enterprise:** a private extension repository for paid capabilities such as multi-workspace orchestration, advanced compliance automation, hosted services, SSO/SAML, SIEM integrations, and SLA-backed operations.
33
+
34
+ Enterprise extends the public core; it does not maintain a competing fork of the core configuration model or CLI.
35
+
36
+ ## Design constraints
37
+
38
+ - Multi-cloud is an architectural requirement, but not a parity requirement for the alpha slice.
39
+ - `open-source` vs `enterprise` is the only runtime packaging boundary.
40
+ - Zero external data-tool runtime dependencies means no Terraform, dbt, Airflow, Great Expectations, Fivetran, or Airbyte required for the framework to operate.
41
+
42
+ ## Quick start
43
+
44
+ ```bash
45
+ pip install datamuru
46
+ datamuru validate --config datamuru.yml
47
+ datamuru doctor --config datamuru.yml
48
+ datamuru plan --config datamuru.yml
49
+ ```
50
+
51
+ ## Installation
52
+
53
+ From PyPI:
54
+
55
+ ```bash
56
+ pip install datamuru
57
+ ```
58
+
59
+ ## Documentation
60
+
61
+ This repository now includes a full MkDocs documentation site.
62
+
63
+ - MkDocs config: [mkdocs.yml](mkdocs.yml)
64
+ - Docs source: [docs](docs/)
65
+ - Published documentation: [ajayaj2000.github.io/DataMuru](https://ajayaj2000.github.io/DataMuru/)
66
+
67
+ To work on the documentation locally:
68
+
69
+ ```bash
70
+ python -m pip install -e ".[docs]"
71
+ python -m mkdocs serve
72
+ ```
73
+
74
+ ## Product usage guidance
75
+
76
+ For operator guidance and rollout practices, start with:
77
+
78
+ - [Product Usage Guidelines](docs/operations/usage-guidelines.md)
79
+ - [Team Adoption Guidelines](docs/operations/team-adoption-guidelines.md)
80
+
81
+ ## Trying it with Databricks Free Edition
82
+
83
+ If you want to try the framework with your own Databricks personal workspace, start here:
84
+
85
+ - [Databricks Free Edition Setup](docs/getting-started/databricks-free-edition.md)
86
+
87
+ For package-oriented team usage, also read:
88
+
89
+ - [Packaging and Distribution](docs/product/packaging-and-distribution.md)
90
+ - [Product Usage Guidelines](docs/operations/usage-guidelines.md)
91
+
92
+ ## Repository standards
93
+
94
+ - `datamuru/`: shared installable Python package
95
+ - `docs/`: versioned product documentation published through GitHub Pages
96
+ - `schemas/`: public configuration contracts
97
+ - `tests/`: unit, provider-contract, and end-to-end tests
98
+ - `.github/workflows/`: CI, documentation deployment, and trusted PyPI publishing
99
+
100
+ See [CONTRIBUTING.md](CONTRIBUTING.md) for the required local quality gate.
@@ -0,0 +1,4 @@
1
+ from .api import DataMuru
2
+
3
+ __all__ = ["DataMuru"]
4
+ __version__ = "0.1.0a0"
@@ -0,0 +1,50 @@
1
+ from __future__ import annotations
2
+
3
+ from pathlib import Path
4
+
5
+ from datamuru.core.engine import DataMuruEngine
6
+
7
+
8
+ class DataMuru:
9
+ def __init__(self, config_path: str | Path, environment: str | None = None) -> None:
10
+ self.engine = DataMuruEngine(config_path=config_path, environment=environment)
11
+
12
+ def validate(self):
13
+ return self.engine.validate()
14
+
15
+ def plan(self, target: str | None = None):
16
+ return self.engine.plan(target=target)
17
+
18
+ def apply(self, target: str | None = None):
19
+ return self.engine.apply(target=target)
20
+
21
+ def apply_saved_plan(self, plan_path: str | Path):
22
+ return self.engine.apply_saved_plan(plan_path)
23
+
24
+ def destroy(self, target: str | None = None):
25
+ return self.engine.destroy(target=target)
26
+
27
+ def save_plan(self, output_path: str | Path, target: str | None = None):
28
+ return self.engine.save_plan(output_path=output_path, target=target)
29
+
30
+ def edition_summary(self):
31
+ return self.engine.edition_summary()
32
+
33
+ def doctor(self):
34
+ return self.engine.doctor()
35
+
36
+ def import_discover(self, include_system: bool = False):
37
+ return self.engine.import_discover(include_system=include_system)
38
+
39
+ def import_generate(
40
+ self,
41
+ *,
42
+ catalogs: list[str] | None = None,
43
+ include_groups: bool = False,
44
+ include_system: bool = False,
45
+ ):
46
+ return self.engine.import_generate(
47
+ catalogs=catalogs,
48
+ include_groups=include_groups,
49
+ include_system=include_system,
50
+ )
@@ -0,0 +1,141 @@
1
+ from __future__ import annotations
2
+
3
+ import textwrap
4
+ from pathlib import Path
5
+
6
+
7
+ class ProjectScaffolder:
8
+ def scaffold(
9
+ self,
10
+ output_dir: str | Path,
11
+ *,
12
+ name: str,
13
+ provider: str = "databricks",
14
+ cloud: str = "azure",
15
+ edition: str = "open-source",
16
+ ) -> list[Path]:
17
+ root = Path(output_dir)
18
+ created: list[Path] = []
19
+ for relative in [
20
+ Path("environments"),
21
+ Path("providers"),
22
+ Path("workspaces"),
23
+ Path("governance"),
24
+ ]:
25
+ target = root / relative
26
+ target.mkdir(parents=True, exist_ok=True)
27
+ created.append(target)
28
+
29
+ content = {
30
+ root / "datamuru.yml": textwrap.dedent(
31
+ f"""
32
+ project:
33
+ name: {name}
34
+ version: "0.1.0"
35
+ description: "Bootstrap DataMuru project"
36
+ edition: {edition}
37
+ provider: {provider}
38
+
39
+ environments:
40
+ - name: dev
41
+ config: ./environments/dev.yml
42
+
43
+ default_environment: dev
44
+
45
+ features:
46
+ governance: true
47
+ data_mesh: false
48
+ ingestion: false
49
+ modeling: false
50
+ observability: false
51
+ compliance_reporting: false
52
+ multi_workspace: false
53
+ hosted_control_plane: false
54
+ identity_management: false
55
+
56
+ state:
57
+ backend: local
58
+ path: ./.datamuru/state-dev.json
59
+
60
+ provider:
61
+ name: {provider}
62
+ cloud: {cloud}
63
+ config: ./providers/{provider}.yml
64
+ """
65
+ ).strip() + "\n",
66
+ root / "environments" / "dev.yml": "environment:\n name: dev\n",
67
+ root / "providers" / f"{provider}.yml": textwrap.dedent(
68
+ f"""
69
+ provider:
70
+ cloud: {cloud}
71
+ connect_timeout_seconds: 10
72
+ credential_mode: personal-access-token
73
+ execution_mode: state-only
74
+ auth_type: pat
75
+ token_env: DATABRICKS_TOKEN
76
+ host: https://adb-placeholder.{cloud}.databricks.example
77
+ """
78
+ ).strip() + "\n",
79
+ root / "workspaces" / "alpha-dev.yml": textwrap.dedent(
80
+ f"""
81
+ workspace:
82
+ name: alpha-dev
83
+ cloud: {cloud}
84
+ region: eastus2
85
+ catalogs:
86
+ - name: alpha_marketing
87
+ schemas:
88
+ - raw
89
+ - bronze
90
+ - silver
91
+ - gold
92
+ """
93
+ ).strip() + "\n",
94
+ root / "governance" / "taxonomy.yml": textwrap.dedent(
95
+ """
96
+ taxonomy:
97
+ name: bootstrap
98
+ version: "0.1"
99
+ categories:
100
+ - id: internal
101
+ label: Internal
102
+ description: "Internal data"
103
+ handling:
104
+ retention_years: 3
105
+ encryption: at_rest
106
+ """
107
+ ).strip() + "\n",
108
+ root / "governance" / "rbac.yml": textwrap.dedent(
109
+ """
110
+ rbac:
111
+ roles:
112
+ - id: data_consumer
113
+ name: Data Consumer
114
+ permissions:
115
+ - resource_type: schema
116
+ resource_pattern: "*.gold"
117
+ privilege: SELECT
118
+ assignments:
119
+ - principal: sample-consumers
120
+ type: group
121
+ roles:
122
+ - data_consumer
123
+ domains:
124
+ - alpha_marketing
125
+ """
126
+ ).strip() + "\n",
127
+ root / "governance" / "masking.yml": textwrap.dedent(
128
+ """
129
+ masking:
130
+ builtins:
131
+ - id: partial_mask
132
+ description: Show last four characters for strings.
133
+ strategy: partial_mask
134
+ """
135
+ ).strip() + "\n",
136
+ }
137
+ for path, value in content.items():
138
+ path.parent.mkdir(parents=True, exist_ok=True)
139
+ path.write_text(value, encoding="utf-8")
140
+ created.append(path)
141
+ return created
@@ -0,0 +1 @@
1
+