det-core 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.
det_core-0.1.0/LICENSE ADDED
@@ -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 +1,4 @@
1
+ include README.md
2
+ include LICENSE
3
+ recursive-include src/det/gui/static *
4
+
@@ -0,0 +1,206 @@
1
+ Metadata-Version: 2.4
2
+ Name: det-core
3
+ Version: 0.1.0
4
+ Summary: A modular, Python-first data engineering framework by det Labs.
5
+ Author-email: det Labs <saurabhr2@gmail.com>
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/saurabhr2/det
8
+ Project-URL: Repository, https://github.com/saurabhr2/det
9
+ Project-URL: Issues, https://github.com/saurabhr2/det/issues
10
+ Keywords: data-engineering,catalog,parquet,polars,pyarrow,schema,cli,gui
11
+ Classifier: Development Status :: 3 - Alpha
12
+ Classifier: Intended Audience :: Developers
13
+ Classifier: Programming Language :: Python :: 3
14
+ Classifier: Programming Language :: Python :: 3.15
15
+ Classifier: Topic :: Database
16
+ Classifier: Topic :: Software Development :: Libraries :: Python Modules
17
+ Requires-Python: >=3.15
18
+ Description-Content-Type: text/markdown
19
+ License-File: LICENSE
20
+ Requires-Dist: polars>=1.0.0
21
+ Requires-Dist: pyarrow>=15.0.0
22
+ Requires-Dist: pydantic>=2.7.0
23
+ Requires-Dist: sqlglot>=23.0.0
24
+ Requires-Dist: typer>=0.12.0
25
+ Requires-Dist: ruamel.yaml>=0.18.0
26
+ Requires-Dist: filelock>=3.13.0
27
+ Requires-Dist: fastapi>=0.110.0
28
+ Requires-Dist: uvicorn>=0.29.0
29
+ Provides-Extra: dev
30
+ Requires-Dist: pytest>=8.0.0; extra == "dev"
31
+ Requires-Dist: ruff>=0.4.0; extra == "dev"
32
+ Requires-Dist: httpx>=0.27.0; extra == "dev"
33
+ Dynamic: license-file
34
+
35
+ # <span style="color:#f45b00;">det</span> — Data Engineering Toolkit
36
+ ### by <span style="color:#f45b00;">det</span> <span style="color:#5d5d5f;">Labs</span>
37
+
38
+ > **A modular, Python-first data engineering framework built by <span style="color:#f45b00;">det</span> Labs for modern analytical workflows.**
39
+
40
+ [![CI](https://img.shields.io/badge/CI-passing-22c55e.svg)](https://github.com/saurabhr2/det/actions)
41
+ [![Python](https://img.shields.io/badge/python->=3.15-3776ab.svg)](https://www.python.org/downloads/release/python-3150/)
42
+ [![License](https://img.shields.io/badge/license-Apache--2.0-22c55e.svg)](LICENSE)
43
+ [![Version](https://img.shields.io/badge/version-0.1.0-f45b00.svg)](https://github.com/saurabhr2/det/releases)
44
+ [![det Labs](https://img.shields.io/badge/org-det%20Labs-f45b00.svg)](https://github.com/saurabhr2/det)
45
+
46
+ ---
47
+
48
+ ## Current Status: Version 0.1.0 (Catalog MVP Released)
49
+
50
+ **<span style="color:#f45b00;">det</span>** (developed by **det Labs**) has completed its **Version 0.1.0** milestone with the release of the **Catalog Module (`det.catalog`)**:
51
+ - Concurrency-safe, atomic YAML metadata persistence with file locks.
52
+ - Automated schema discovery for Parquet, CSV, TSV, JSON, NDJSON, Excel, and directory datasets using Polars and PyArrow.
53
+ - Leverages Python 3.15 stable native `lazy import` syntax for instantaneous engine load times.
54
+ - Full Python programmatic Command API (`CatalogService`).
55
+ - Interactive Local Browser Web GUI with vertical category explorer, draggable resizer, quick circular action buttons, Discover Schema modal, inline column description editing, and a 3-way theme switcher (Light / Dark / Auto System).
56
+ - Typer CLI (`det catalog ...` and `det-gui`).
57
+
58
+ ---
59
+
60
+ ## Architectural Vision & Module Roadmap
61
+
62
+ `det` is built from the ground up by det Labs to be modular, extensible, and Python-native:
63
+
64
+ ```
65
+ ┌─────────────────────────────────────────────────────────────┐
66
+ │ User Interfaces │
67
+ │ CLI (`det`) │ Web GUI (`det-gui`) │ API │
68
+ └──────────────┬──────────────────┬──────────────────┬────────┘
69
+ │ │ │
70
+ ┌──────────────▼──────────────────▼──────────────────▼────────┐
71
+ │ det Core Modules (det Labs) │
72
+ │ │
73
+ │ [ Released v0.1 ] │
74
+ │ ├── det.catalog Metadata, schemas, YAML store & GUI │
75
+ │ │
76
+ │ [ Planned Roadmap ] │
77
+ │ ├── det.engine Execution abstraction (DuckDB, Polars) │
78
+ │ ├── det.pipeline DAG orchestration & SQL/Python models │
79
+ │ ├── det.quality Schema contracts, profiling & tests │
80
+ │ ├── det.lineage Table & column-level dependency graphs │
81
+ │ └── det.connectors Ingestion & sync (Iceberg, Delta, S3) │
82
+ └─────────────────────────────────────────────────────────────┘
83
+ ```
84
+
85
+ ### Module Roadmap
86
+
87
+ | Module | Purpose | Status |
88
+ | :--- | :--- | :--- |
89
+ | **`det.catalog`** | Dataset discovery, typed schema inference, categories/namespaces, and visual catalog manager | **Released in v0.1.0** |
90
+ | **`det.engine`** | Unified query execution interface abstracting Polars, DuckDB, and Arrow in-memory compute | *Planned (v0.2)* |
91
+ | **`det.pipeline`** | Pipeline DAG execution, dbt-style transforms in SQL & Python, incremental materialization | *Planned (v0.3)* |
92
+ | **`det.quality`** | Data validation checks, statistical profiling, anomaly detection, and schema contracts | *Planned (v0.4)* |
93
+ | **`det.lineage`** | Column-level and dataset-level upstream/downstream lineage graphs | *Planned (v0.5)* |
94
+ | **`det.connectors`**| Multi-source extractors and destination sinks (S3, GCS, PostgreSQL, Snowflake, Iceberg, Delta) | *Planned (v0.6)* |
95
+
96
+ ---
97
+
98
+ ## Quickstart
99
+
100
+ ### Prerequisites
101
+ - **Python**: `>= 3.15` (Stable released October 9, 2026)
102
+
103
+ ### Installation
104
+
105
+ **From PyPI:**
106
+ ```bash
107
+ pip install det-core
108
+ ```
109
+
110
+ **Or from source:**
111
+ ```bash
112
+ # Clone the repository
113
+ git clone https://github.com/saurabhr2/det.git
114
+ cd det
115
+
116
+ # Create virtual environment with Python 3.15
117
+ py -3.15 -m venv .venv
118
+ .venv\Scripts\activate # On Windows
119
+ # source .venv/bin/activate # On Linux/macOS
120
+
121
+ # Install in editable mode with development tools
122
+ pip install -e ".[dev]"
123
+
124
+ # Verify test suite
125
+ pytest
126
+ ```
127
+
128
+ ### 1. Launch the Catalog Web GUI
129
+ Experience the interactive visual catalog manager directly in your local browser:
130
+
131
+ ```bash
132
+ det-gui
133
+ ```
134
+ Navigate to `http://127.0.0.1:8501`:
135
+ - Group datasets into categories / namespaces.
136
+ - Point to local files or folders and click **Discover Schema** to auto-infer columns and types.
137
+ - Drag the sidebar border to resize the explorer bar manually (double-click to reset).
138
+ - Switch themes between **Light**, **Dark**, or **Auto (System Default)**.
139
+ - Edit column descriptions inline by clicking on them.
140
+ - Switch between different YAML catalog files or create brand new catalogs.
141
+
142
+ ### 2. Using the CLI
143
+
144
+ ```bash
145
+ # View system & version info
146
+ det version
147
+ det info
148
+
149
+ # Scan a dataset to inspect its inferred schema without registering
150
+ det catalog scan sample_data/orders.parquet
151
+
152
+ # List all registered tables in active catalog
153
+ det catalog list
154
+
155
+ # Set a catalog file as the persistent default
156
+ det catalog set-default catalogs/main.yaml
157
+ ```
158
+
159
+ ### 3. Programmatic Python API
160
+
161
+ ```python
162
+ from det.catalog import CatalogService, DatasetMetadata
163
+
164
+ # Connect to catalog
165
+ service = CatalogService("catalogs/main.yaml")
166
+
167
+ # Discover schema from a Parquet or CSV file
168
+ scan = service.scan_path("data/customers.parquet")
169
+
170
+ # Register into catalog
171
+ service.register_dataset(DatasetMetadata(
172
+ id="crm.customers",
173
+ name="customers",
174
+ namespace="crm",
175
+ format="parquet",
176
+ location="data/customers.parquet",
177
+ description="Customer master records",
178
+ columns=scan.columns,
179
+ row_count=scan.row_count,
180
+ ))
181
+
182
+ # Retrieve and inspect
183
+ dataset = service.get_dataset("crm.customers")
184
+ print(f"Table {dataset.name} has {len(dataset.columns)} columns and {dataset.row_count} rows.")
185
+ ```
186
+
187
+ ---
188
+
189
+ ## Testing & Quality
190
+
191
+ All code adheres to strict standards:
192
+ - PEP 257 docstrings on all public functions, classes, and methods.
193
+ - Explicit type annotations.
194
+ - Python 3.15 `lazy import` integration.
195
+ - Fast, automated pytest test suite:
196
+
197
+ ```bash
198
+ pytest -v
199
+ ruff check .
200
+ ```
201
+
202
+ ---
203
+
204
+ ## License
205
+
206
+ Distributed under the **Apache License 2.0**. Copyright (c) 2026 det Labs. See [`LICENSE`](LICENSE) for details.
@@ -0,0 +1,172 @@
1
+ # <span style="color:#f45b00;">det</span> — Data Engineering Toolkit
2
+ ### by <span style="color:#f45b00;">det</span> <span style="color:#5d5d5f;">Labs</span>
3
+
4
+ > **A modular, Python-first data engineering framework built by <span style="color:#f45b00;">det</span> Labs for modern analytical workflows.**
5
+
6
+ [![CI](https://img.shields.io/badge/CI-passing-22c55e.svg)](https://github.com/saurabhr2/det/actions)
7
+ [![Python](https://img.shields.io/badge/python->=3.15-3776ab.svg)](https://www.python.org/downloads/release/python-3150/)
8
+ [![License](https://img.shields.io/badge/license-Apache--2.0-22c55e.svg)](LICENSE)
9
+ [![Version](https://img.shields.io/badge/version-0.1.0-f45b00.svg)](https://github.com/saurabhr2/det/releases)
10
+ [![det Labs](https://img.shields.io/badge/org-det%20Labs-f45b00.svg)](https://github.com/saurabhr2/det)
11
+
12
+ ---
13
+
14
+ ## Current Status: Version 0.1.0 (Catalog MVP Released)
15
+
16
+ **<span style="color:#f45b00;">det</span>** (developed by **det Labs**) has completed its **Version 0.1.0** milestone with the release of the **Catalog Module (`det.catalog`)**:
17
+ - Concurrency-safe, atomic YAML metadata persistence with file locks.
18
+ - Automated schema discovery for Parquet, CSV, TSV, JSON, NDJSON, Excel, and directory datasets using Polars and PyArrow.
19
+ - Leverages Python 3.15 stable native `lazy import` syntax for instantaneous engine load times.
20
+ - Full Python programmatic Command API (`CatalogService`).
21
+ - Interactive Local Browser Web GUI with vertical category explorer, draggable resizer, quick circular action buttons, Discover Schema modal, inline column description editing, and a 3-way theme switcher (Light / Dark / Auto System).
22
+ - Typer CLI (`det catalog ...` and `det-gui`).
23
+
24
+ ---
25
+
26
+ ## Architectural Vision & Module Roadmap
27
+
28
+ `det` is built from the ground up by det Labs to be modular, extensible, and Python-native:
29
+
30
+ ```
31
+ ┌─────────────────────────────────────────────────────────────┐
32
+ │ User Interfaces │
33
+ │ CLI (`det`) │ Web GUI (`det-gui`) │ API │
34
+ └──────────────┬──────────────────┬──────────────────┬────────┘
35
+ │ │ │
36
+ ┌──────────────▼──────────────────▼──────────────────▼────────┐
37
+ │ det Core Modules (det Labs) │
38
+ │ │
39
+ │ [ Released v0.1 ] │
40
+ │ ├── det.catalog Metadata, schemas, YAML store & GUI │
41
+ │ │
42
+ │ [ Planned Roadmap ] │
43
+ │ ├── det.engine Execution abstraction (DuckDB, Polars) │
44
+ │ ├── det.pipeline DAG orchestration & SQL/Python models │
45
+ │ ├── det.quality Schema contracts, profiling & tests │
46
+ │ ├── det.lineage Table & column-level dependency graphs │
47
+ │ └── det.connectors Ingestion & sync (Iceberg, Delta, S3) │
48
+ └─────────────────────────────────────────────────────────────┘
49
+ ```
50
+
51
+ ### Module Roadmap
52
+
53
+ | Module | Purpose | Status |
54
+ | :--- | :--- | :--- |
55
+ | **`det.catalog`** | Dataset discovery, typed schema inference, categories/namespaces, and visual catalog manager | **Released in v0.1.0** |
56
+ | **`det.engine`** | Unified query execution interface abstracting Polars, DuckDB, and Arrow in-memory compute | *Planned (v0.2)* |
57
+ | **`det.pipeline`** | Pipeline DAG execution, dbt-style transforms in SQL & Python, incremental materialization | *Planned (v0.3)* |
58
+ | **`det.quality`** | Data validation checks, statistical profiling, anomaly detection, and schema contracts | *Planned (v0.4)* |
59
+ | **`det.lineage`** | Column-level and dataset-level upstream/downstream lineage graphs | *Planned (v0.5)* |
60
+ | **`det.connectors`**| Multi-source extractors and destination sinks (S3, GCS, PostgreSQL, Snowflake, Iceberg, Delta) | *Planned (v0.6)* |
61
+
62
+ ---
63
+
64
+ ## Quickstart
65
+
66
+ ### Prerequisites
67
+ - **Python**: `>= 3.15` (Stable released October 9, 2026)
68
+
69
+ ### Installation
70
+
71
+ **From PyPI:**
72
+ ```bash
73
+ pip install det-core
74
+ ```
75
+
76
+ **Or from source:**
77
+ ```bash
78
+ # Clone the repository
79
+ git clone https://github.com/saurabhr2/det.git
80
+ cd det
81
+
82
+ # Create virtual environment with Python 3.15
83
+ py -3.15 -m venv .venv
84
+ .venv\Scripts\activate # On Windows
85
+ # source .venv/bin/activate # On Linux/macOS
86
+
87
+ # Install in editable mode with development tools
88
+ pip install -e ".[dev]"
89
+
90
+ # Verify test suite
91
+ pytest
92
+ ```
93
+
94
+ ### 1. Launch the Catalog Web GUI
95
+ Experience the interactive visual catalog manager directly in your local browser:
96
+
97
+ ```bash
98
+ det-gui
99
+ ```
100
+ Navigate to `http://127.0.0.1:8501`:
101
+ - Group datasets into categories / namespaces.
102
+ - Point to local files or folders and click **Discover Schema** to auto-infer columns and types.
103
+ - Drag the sidebar border to resize the explorer bar manually (double-click to reset).
104
+ - Switch themes between **Light**, **Dark**, or **Auto (System Default)**.
105
+ - Edit column descriptions inline by clicking on them.
106
+ - Switch between different YAML catalog files or create brand new catalogs.
107
+
108
+ ### 2. Using the CLI
109
+
110
+ ```bash
111
+ # View system & version info
112
+ det version
113
+ det info
114
+
115
+ # Scan a dataset to inspect its inferred schema without registering
116
+ det catalog scan sample_data/orders.parquet
117
+
118
+ # List all registered tables in active catalog
119
+ det catalog list
120
+
121
+ # Set a catalog file as the persistent default
122
+ det catalog set-default catalogs/main.yaml
123
+ ```
124
+
125
+ ### 3. Programmatic Python API
126
+
127
+ ```python
128
+ from det.catalog import CatalogService, DatasetMetadata
129
+
130
+ # Connect to catalog
131
+ service = CatalogService("catalogs/main.yaml")
132
+
133
+ # Discover schema from a Parquet or CSV file
134
+ scan = service.scan_path("data/customers.parquet")
135
+
136
+ # Register into catalog
137
+ service.register_dataset(DatasetMetadata(
138
+ id="crm.customers",
139
+ name="customers",
140
+ namespace="crm",
141
+ format="parquet",
142
+ location="data/customers.parquet",
143
+ description="Customer master records",
144
+ columns=scan.columns,
145
+ row_count=scan.row_count,
146
+ ))
147
+
148
+ # Retrieve and inspect
149
+ dataset = service.get_dataset("crm.customers")
150
+ print(f"Table {dataset.name} has {len(dataset.columns)} columns and {dataset.row_count} rows.")
151
+ ```
152
+
153
+ ---
154
+
155
+ ## Testing & Quality
156
+
157
+ All code adheres to strict standards:
158
+ - PEP 257 docstrings on all public functions, classes, and methods.
159
+ - Explicit type annotations.
160
+ - Python 3.15 `lazy import` integration.
161
+ - Fast, automated pytest test suite:
162
+
163
+ ```bash
164
+ pytest -v
165
+ ruff check .
166
+ ```
167
+
168
+ ---
169
+
170
+ ## License
171
+
172
+ Distributed under the **Apache License 2.0**. Copyright (c) 2026 det Labs. See [`LICENSE`](LICENSE) for details.
@@ -0,0 +1,65 @@
1
+ [build-system]
2
+ requires = ["setuptools>=61.0"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "det-core"
7
+ version = "0.1.0"
8
+ description = "A modular, Python-first data engineering framework by det Labs."
9
+ readme = "README.md"
10
+ requires-python = ">=3.15"
11
+ license = "Apache-2.0"
12
+ license-files = ["LICENSE"]
13
+ authors = [
14
+ { name = "det Labs", email = "saurabhr2@gmail.com" }
15
+ ]
16
+ keywords = ["data-engineering", "catalog", "parquet", "polars", "pyarrow", "schema", "cli", "gui"]
17
+ classifiers = [
18
+ "Development Status :: 3 - Alpha",
19
+ "Intended Audience :: Developers",
20
+ "Programming Language :: Python :: 3",
21
+ "Programming Language :: Python :: 3.15",
22
+ "Topic :: Database",
23
+ "Topic :: Software Development :: Libraries :: Python Modules",
24
+ ]
25
+
26
+ dependencies = [
27
+ "polars>=1.0.0",
28
+ "pyarrow>=15.0.0",
29
+ "pydantic>=2.7.0",
30
+ "sqlglot>=23.0.0",
31
+ "typer>=0.12.0",
32
+ "ruamel.yaml>=0.18.0",
33
+ "filelock>=3.13.0",
34
+ "fastapi>=0.110.0",
35
+ "uvicorn>=0.29.0",
36
+ ]
37
+
38
+ [project.urls]
39
+ Homepage = "https://github.com/saurabhr2/det"
40
+ Repository = "https://github.com/saurabhr2/det"
41
+ Issues = "https://github.com/saurabhr2/det/issues"
42
+
43
+ [project.optional-dependencies]
44
+ dev = [
45
+ "pytest>=8.0.0",
46
+ "ruff>=0.4.0",
47
+ "httpx>=0.27.0",
48
+ ]
49
+
50
+ [project.scripts]
51
+ det = "det.cli:main"
52
+ det-gui = "det.gui:cli_main"
53
+
54
+ [tool.setuptools.packages.find]
55
+ where = ["src"]
56
+
57
+ [tool.setuptools.package-data]
58
+ "det.gui" = ["static/*", "static/**/*"]
59
+
60
+ [tool.ruff]
61
+ line-length = 100
62
+ target-version = "py315"
63
+
64
+ [tool.pytest.ini_options]
65
+ testpaths = ["tests"]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
@@ -0,0 +1,3 @@
1
+ """det: Data Engineering Toolkit by det Labs."""
2
+
3
+ __version__ = "0.1.0"
@@ -0,0 +1,7 @@
1
+ """Entrypoint for python -m det."""
2
+
3
+ from det.cli import main
4
+
5
+ if __name__ == "__main__":
6
+ main()
7
+