dtex 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.
- dtex-0.1.0/.gitignore +20 -0
- dtex-0.1.0/CONTRIBUTING.md +152 -0
- dtex-0.1.0/LICENSE +201 -0
- dtex-0.1.0/PKG-INFO +140 -0
- dtex-0.1.0/README.md +90 -0
- dtex-0.1.0/docs/00-vision-and-naming.md +175 -0
- dtex-0.1.0/docs/01-landscape-and-comparison.md +210 -0
- dtex-0.1.0/docs/02-architecture.md +305 -0
- dtex-0.1.0/docs/03-connector-contract.md +692 -0
- dtex-0.1.0/docs/04-connector-body.md +353 -0
- dtex-0.1.0/docs/05-destinations-and-state.md +510 -0
- dtex-0.1.0/docs/06-project-anatomy.md +313 -0
- dtex-0.1.0/docs/07-cli-and-library-api.md +487 -0
- dtex-0.1.0/docs/08-security.md +350 -0
- dtex-0.1.0/docs/09-logging-and-observability.md +169 -0
- dtex-0.1.0/docs/10-roadmap-and-scope.md +93 -0
- dtex-0.1.0/docs/11-open-questions.md +254 -0
- dtex-0.1.0/docs/12-configs.md +214 -0
- dtex-0.1.0/docs/README.md +33 -0
- dtex-0.1.0/docs/_archive/stripe-research-2026-05.md +421 -0
- dtex-0.1.0/docs/_internal/release.md +107 -0
- dtex-0.1.0/dtex/__init__.py +129 -0
- dtex-0.1.0/dtex/cli/__init__.py +1255 -0
- dtex-0.1.0/dtex/cli/_discovery.py +141 -0
- dtex-0.1.0/dtex/cli/_format.py +216 -0
- dtex-0.1.0/dtex/cli/_runs.py +301 -0
- dtex-0.1.0/dtex/cli/_scaffold.py +383 -0
- dtex-0.1.0/dtex/cli/_secrets.py +262 -0
- dtex-0.1.0/dtex/cli/_state.py +202 -0
- dtex-0.1.0/dtex/destinations/__init__.py +2 -0
- dtex-0.1.0/dtex/destinations/bigquery/README.md +162 -0
- dtex-0.1.0/dtex/destinations/bigquery/__init__.py +12 -0
- dtex-0.1.0/dtex/destinations/bigquery/client.py +324 -0
- dtex-0.1.0/dtex/destinations/bigquery/ddl.py +450 -0
- dtex-0.1.0/dtex/destinations/bigquery/destination.py +1140 -0
- dtex-0.1.0/dtex/destinations/bigquery/register.yaml +72 -0
- dtex-0.1.0/dtex/destinations/duckdb/__init__.py +11 -0
- dtex-0.1.0/dtex/destinations/duckdb/ddl.py +140 -0
- dtex-0.1.0/dtex/destinations/duckdb/destination.py +856 -0
- dtex-0.1.0/dtex/destinations/duckdb/register.yaml +27 -0
- dtex-0.1.0/dtex/engine/__init__.py +53 -0
- dtex-0.1.0/dtex/engine/config.py +672 -0
- dtex-0.1.0/dtex/engine/configs.py +151 -0
- dtex-0.1.0/dtex/engine/discovery.py +411 -0
- dtex-0.1.0/dtex/engine/logger.py +315 -0
- dtex-0.1.0/dtex/engine/runner.py +1469 -0
- dtex-0.1.0/dtex/py.typed +0 -0
- dtex-0.1.0/dtex/registry.py +834 -0
- dtex-0.1.0/dtex/secrets/__init__.py +65 -0
- dtex-0.1.0/dtex/secrets/_aws.py +432 -0
- dtex-0.1.0/dtex/secrets/_gcp.py +312 -0
- dtex-0.1.0/dtex/secrets/_vault.py +337 -0
- dtex-0.1.0/dtex/secrets/resolvers.py +687 -0
- dtex-0.1.0/dtex/sources/__init__.py +2 -0
- dtex-0.1.0/dtex/sources/filesystem/README.md +70 -0
- dtex-0.1.0/dtex/sources/filesystem/__init__.py +10 -0
- dtex-0.1.0/dtex/sources/filesystem/backends.py +437 -0
- dtex-0.1.0/dtex/sources/filesystem/readers.py +260 -0
- dtex-0.1.0/dtex/sources/filesystem/register.yaml +124 -0
- dtex-0.1.0/dtex/sources/filesystem/source.py +236 -0
- dtex-0.1.0/dtex/sources/postgres/README.md +109 -0
- dtex-0.1.0/dtex/sources/postgres/__init__.py +12 -0
- dtex-0.1.0/dtex/sources/postgres/client.py +256 -0
- dtex-0.1.0/dtex/sources/postgres/register.yaml +99 -0
- dtex-0.1.0/dtex/sources/postgres/source.py +381 -0
- dtex-0.1.0/dtex/sources/postgres/type_mapping.py +178 -0
- dtex-0.1.0/dtex/sources/rest/README.md +133 -0
- dtex-0.1.0/dtex/sources/rest/__init__.py +15 -0
- dtex-0.1.0/dtex/sources/rest/client.py +271 -0
- dtex-0.1.0/dtex/sources/rest/extractors.py +207 -0
- dtex-0.1.0/dtex/sources/rest/pagination.py +469 -0
- dtex-0.1.0/dtex/sources/rest/register.yaml +103 -0
- dtex-0.1.0/dtex/sources/rest/source.py +239 -0
- dtex-0.1.0/dtex/sources/shiphero/README.md +97 -0
- dtex-0.1.0/dtex/sources/shiphero/__init__.py +10 -0
- dtex-0.1.0/dtex/sources/shiphero/client.py +278 -0
- dtex-0.1.0/dtex/sources/shiphero/pagination.py +121 -0
- dtex-0.1.0/dtex/sources/shiphero/queries.py +105 -0
- dtex-0.1.0/dtex/sources/shiphero/register.yaml +160 -0
- dtex-0.1.0/dtex/sources/shiphero/source.py +241 -0
- dtex-0.1.0/dtex/sources/shiphero/windows.py +122 -0
- dtex-0.1.0/dtex/sources/stripe/README.md +128 -0
- dtex-0.1.0/dtex/sources/stripe/__init__.py +9 -0
- dtex-0.1.0/dtex/sources/stripe/client.py +336 -0
- dtex-0.1.0/dtex/sources/stripe/pagination.py +106 -0
- dtex-0.1.0/dtex/sources/stripe/register.yaml +206 -0
- dtex-0.1.0/dtex/sources/stripe/source.py +222 -0
- dtex-0.1.0/dtex/types.py +1861 -0
- dtex-0.1.0/pyproject.toml +128 -0
- dtex-0.1.0/tests/__init__.py +0 -0
- dtex-0.1.0/tests/conftest.py +172 -0
- dtex-0.1.0/tests/connectors/__init__.py +1 -0
- dtex-0.1.0/tests/connectors/test_filesystem.py +751 -0
- dtex-0.1.0/tests/connectors/test_postgres.py +822 -0
- dtex-0.1.0/tests/connectors/test_rest.py +909 -0
- dtex-0.1.0/tests/connectors/test_shiphero.py +876 -0
- dtex-0.1.0/tests/connectors/test_stripe.py +616 -0
- dtex-0.1.0/tests/destinations/__init__.py +7 -0
- dtex-0.1.0/tests/destinations/test_bigquery.py +1814 -0
- dtex-0.1.0/tests/fixtures/configs/echo.yml +22 -0
- dtex-0.1.0/tests/fixtures/destinations/lockedfake/destination.py +237 -0
- dtex-0.1.0/tests/fixtures/destinations/lockedfake/register.yaml +21 -0
- dtex-0.1.0/tests/fixtures/dtex_project.yml +24 -0
- dtex-0.1.0/tests/fixtures/profiles.yml +34 -0
- dtex-0.1.0/tests/fixtures/sources/echo/register.yaml +44 -0
- dtex-0.1.0/tests/fixtures/sources/echo/source.py +93 -0
- dtex-0.1.0/tests/test_cli.py +1281 -0
- dtex-0.1.0/tests/test_configs.py +580 -0
- dtex-0.1.0/tests/test_duckdb_destination.py +762 -0
- dtex-0.1.0/tests/test_engine.py +2206 -0
- dtex-0.1.0/tests/test_registry.py +621 -0
- dtex-0.1.0/tests/test_run_records.py +829 -0
- dtex-0.1.0/tests/test_secret_resolver_aws.py +582 -0
- dtex-0.1.0/tests/test_secret_resolver_gcp.py +529 -0
- dtex-0.1.0/tests/test_secret_resolver_vault.py +517 -0
- dtex-0.1.0/tests/test_secret_resolvers.py +551 -0
- dtex-0.1.0/tests/test_skeleton.py +8 -0
- dtex-0.1.0/tests/test_smoke.py +204 -0
- dtex-0.1.0/tests/test_types.py +953 -0
dtex-0.1.0/.gitignore
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
# Python
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.pyc
|
|
4
|
+
|
|
5
|
+
# Virtual environments
|
|
6
|
+
.venv/
|
|
7
|
+
|
|
8
|
+
# Build artifacts
|
|
9
|
+
dist/
|
|
10
|
+
build/
|
|
11
|
+
*.egg-info/
|
|
12
|
+
|
|
13
|
+
# Test & type-check caches
|
|
14
|
+
.pytest_cache/
|
|
15
|
+
.mypy_cache/
|
|
16
|
+
.ruff_cache/
|
|
17
|
+
|
|
18
|
+
# dtex local state
|
|
19
|
+
.duckdb
|
|
20
|
+
.dtex/
|
|
@@ -0,0 +1,152 @@
|
|
|
1
|
+
# Contributing to dtex
|
|
2
|
+
|
|
3
|
+
Thanks for your interest in dtex. The governing principle is the
|
|
4
|
+
[design handbook](./docs/00-vision-and-naming.md): **keep it as simple as
|
|
5
|
+
possible.** This file covers dev setup, the PR process, and how to add a
|
|
6
|
+
new connector or secret-manager resolver.
|
|
7
|
+
|
|
8
|
+
By participating in this project you agree to abide by the
|
|
9
|
+
[Code of Conduct](./CODE_OF_CONDUCT.md).
|
|
10
|
+
|
|
11
|
+
## Dev setup
|
|
12
|
+
|
|
13
|
+
dtex targets Python 3.11+. Clone the repo, then create a virtual environment
|
|
14
|
+
and install the package in editable mode with the `dev` extras:
|
|
15
|
+
|
|
16
|
+
```sh
|
|
17
|
+
python -m venv .venv
|
|
18
|
+
source .venv/bin/activate
|
|
19
|
+
pip install -e ".[dev]"
|
|
20
|
+
```
|
|
21
|
+
|
|
22
|
+
## Run the tests
|
|
23
|
+
|
|
24
|
+
```sh
|
|
25
|
+
pytest -q
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
## Run the linter and type checker
|
|
29
|
+
|
|
30
|
+
```sh
|
|
31
|
+
ruff check .
|
|
32
|
+
mypy dtex
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
Please make sure `pytest`, `ruff check`, and `mypy` all pass before opening a
|
|
36
|
+
pull request.
|
|
37
|
+
|
|
38
|
+
## Spec precedence: code is the source of truth
|
|
39
|
+
|
|
40
|
+
The [design handbook](./docs/) (`docs/00`–`docs/12`) was written before the
|
|
41
|
+
implementation and remains the canonical *intent*. But once a contract is
|
|
42
|
+
implemented in code, **the code is the source of truth** — if the handbook and
|
|
43
|
+
the code diverge, fix the handbook to match the code, not the other way around.
|
|
44
|
+
This avoids re-litigating handbook ambiguities at every stage.
|
|
45
|
+
|
|
46
|
+
Worked examples already in the tree:
|
|
47
|
+
|
|
48
|
+
- `dtex/types.py::StateRecord` defines the canonical `_dtex_state` schema
|
|
49
|
+
(docs/03 §3.5 and docs/05 §5.1 follow it).
|
|
50
|
+
- **Configs are the runtime unit.** The CLI's `-p / --conf` arg and
|
|
51
|
+
`dtex.run(config=...)` library entry point both take a *config name* —
|
|
52
|
+
there is no source-alone selector. Documents `06`, `07`, and `12` follow
|
|
53
|
+
this.
|
|
54
|
+
|
|
55
|
+
## PR process
|
|
56
|
+
|
|
57
|
+
1. Branch off `main`.
|
|
58
|
+
2. Make one logical change per PR — small PRs review faster and revert cleaner.
|
|
59
|
+
3. Run the local checks before pushing:
|
|
60
|
+
```sh
|
|
61
|
+
pytest -q && ruff check . && mypy dtex
|
|
62
|
+
```
|
|
63
|
+
4. Add or update tests for any new code path. Bug-fix PRs should land a
|
|
64
|
+
regression test alongside the fix.
|
|
65
|
+
5. If you touch the public surface (a contract type, a CLI flag, a baked
|
|
66
|
+
connector's `register.yaml`, the secret-resolver protocol), update the
|
|
67
|
+
relevant chapter under `docs/` in the same PR.
|
|
68
|
+
6. Add an entry under the `## [Unreleased]` section of
|
|
69
|
+
[`CHANGELOG.md`](./CHANGELOG.md). Group it under **Added** / **Changed** /
|
|
70
|
+
**Fixed** / **Removed** / **Deprecated** / **Security**.
|
|
71
|
+
7. Write a descriptive commit message and link any related issue in the PR
|
|
72
|
+
description. Reviewers may request changes — that is the point of review,
|
|
73
|
+
not a verdict on your work.
|
|
74
|
+
|
|
75
|
+
### Commit message style
|
|
76
|
+
|
|
77
|
+
Conventional-commit prefixes are **recommended but not enforced**:
|
|
78
|
+
|
|
79
|
+
- `feat:` — a user-visible new capability
|
|
80
|
+
- `fix:` — a bug fix
|
|
81
|
+
- `docs:` — documentation only
|
|
82
|
+
- `test:` — tests only
|
|
83
|
+
- `refactor:` — internal restructuring with no behavior change
|
|
84
|
+
- `chore:` — build, tooling, dependencies
|
|
85
|
+
|
|
86
|
+
Consistency helps readers skim the log; we will not bounce a PR for
|
|
87
|
+
deviating.
|
|
88
|
+
|
|
89
|
+
## Adding a new source connector
|
|
90
|
+
|
|
91
|
+
A source connector is a folder under `dtex/sources/<name>/` (for a baked
|
|
92
|
+
one) or `connectors/sources/<name>/` (in a user project) containing:
|
|
93
|
+
|
|
94
|
+
1. **`register.yaml`** — the manifest. Declares connector name, capabilities,
|
|
95
|
+
config keys (with `secret: true` for any sensitive field), and the streams
|
|
96
|
+
it exposes. See [docs/03 — The Connector Contract](./docs/03-connector-contract.md).
|
|
97
|
+
2. **`source.py`** — the connector body. Generator functions decorated with
|
|
98
|
+
`@stream` or `@resource` that yield records. See
|
|
99
|
+
[docs/04 — Connector Body](./docs/04-connector-body.md).
|
|
100
|
+
3. **Tests** under `tests/sources/<name>/` — at minimum, a smoke test that
|
|
101
|
+
exercises the happy path with a recorded fixture or a mocked HTTP layer.
|
|
102
|
+
Live-service tests should be gated by an env var and marked with the
|
|
103
|
+
`integration` pytest marker (see `pyproject.toml`).
|
|
104
|
+
4. **`README.md`** in the connector folder — what it extracts, how to
|
|
105
|
+
authenticate, any operational notes.
|
|
106
|
+
|
|
107
|
+
The fastest scaffold is `dtex new source <name>` — it writes a skeletal
|
|
108
|
+
`register.yaml` plus a `source.py` you fill in.
|
|
109
|
+
|
|
110
|
+
## Adding a new destination connector
|
|
111
|
+
|
|
112
|
+
Destinations follow the same folder + `register.yaml` + decorator shape, but
|
|
113
|
+
they accept records instead of yielding them. The folder lives under
|
|
114
|
+
`dtex/destinations/<name>/`, and the body uses `@destination`-hooked
|
|
115
|
+
functions. The destination contract — capabilities, the state-table shape,
|
|
116
|
+
the transactional-load expectation, schema evolution — is in
|
|
117
|
+
[docs/05 — Destinations and State](./docs/05-destinations-and-state.md).
|
|
118
|
+
|
|
119
|
+
Scaffold: `dtex new destination <name>`.
|
|
120
|
+
|
|
121
|
+
## Adding a new secret-manager resolver
|
|
122
|
+
|
|
123
|
+
A secret-manager resolver is any object whose class declares
|
|
124
|
+
`scheme: ClassVar[str]` and implements `resolve(path, field) -> str`. It is
|
|
125
|
+
distributed either as a third-party package via the
|
|
126
|
+
`dtex.secret_resolvers` entry-point, or as a project-local
|
|
127
|
+
`dtex_plugins.py`. The protocol, registration mechanics, and the URL form
|
|
128
|
+
(`secret://<scheme>/<path>[#<field>]`) are in
|
|
129
|
+
[docs/08 §3 — Secret references and pluggable secret managers](./docs/08-security.md).
|
|
130
|
+
|
|
131
|
+
## Releases
|
|
132
|
+
|
|
133
|
+
See [`docs/_internal/release.md`](./docs/_internal/release.md) for the
|
|
134
|
+
maintainer's release runbook.
|
|
135
|
+
|
|
136
|
+
## Issue templates
|
|
137
|
+
|
|
138
|
+
Use the templates under
|
|
139
|
+
[`.github/ISSUE_TEMPLATE/`](./.github/ISSUE_TEMPLATE) to file a bug
|
|
140
|
+
report, feature request, or connector request. Security issues go through
|
|
141
|
+
the private channel described in [`SECURITY.md`](./SECURITY.md), **not**
|
|
142
|
+
the issue tracker.
|
|
143
|
+
|
|
144
|
+
## License and contribution sign-off
|
|
145
|
+
|
|
146
|
+
By submitting a pull request you agree that your contribution is licensed
|
|
147
|
+
under the [Apache License 2.0](./LICENSE), the same license as the rest of
|
|
148
|
+
the project.
|
|
149
|
+
|
|
150
|
+
A Developer Certificate of Origin sign-off (`git commit -s`) is
|
|
151
|
+
**recommended** in v0.1 and will become **required** for v1.0. Adopting it
|
|
152
|
+
now is the lowest-friction way to ramp up.
|
dtex-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 2026 Albinas Plesnys
|
|
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.
|
dtex-0.1.0/PKG-INFO
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: dtex
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: dtex (data extraction tool) — an open-source Python EL tool: pipelines as configs, connectors as folders, CLI-first.
|
|
5
|
+
Project-URL: Homepage, https://github.com/vej-ai/dtex
|
|
6
|
+
Project-URL: Documentation, https://github.com/vej-ai/dtex/tree/main/docs
|
|
7
|
+
Project-URL: Source, https://github.com/vej-ai/dtex
|
|
8
|
+
Project-URL: Bug Tracker, https://github.com/vej-ai/dtex/issues
|
|
9
|
+
Project-URL: Changelog, https://github.com/vej-ai/dtex/blob/main/CHANGELOG.md
|
|
10
|
+
Author: Albinas Plesnys
|
|
11
|
+
License-Expression: Apache-2.0
|
|
12
|
+
License-File: LICENSE
|
|
13
|
+
Keywords: connectors,data-engineering,dbt,el,elt,extract-load
|
|
14
|
+
Classifier: Development Status :: 3 - Alpha
|
|
15
|
+
Classifier: Intended Audience :: Developers
|
|
16
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
17
|
+
Classifier: Programming Language :: Python :: 3
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
20
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
21
|
+
Classifier: Topic :: Database
|
|
22
|
+
Classifier: Typing :: Typed
|
|
23
|
+
Requires-Python: >=3.11
|
|
24
|
+
Requires-Dist: click
|
|
25
|
+
Requires-Dist: duckdb
|
|
26
|
+
Requires-Dist: google-cloud-bigquery>=3.20
|
|
27
|
+
Requires-Dist: google-cloud-storage>=2.10
|
|
28
|
+
Requires-Dist: psycopg[binary]>=3.1
|
|
29
|
+
Requires-Dist: pyarrow>=15
|
|
30
|
+
Requires-Dist: pyyaml
|
|
31
|
+
Requires-Dist: requests>=2.31
|
|
32
|
+
Provides-Extra: aws-secrets
|
|
33
|
+
Requires-Dist: boto3>=1.28; extra == 'aws-secrets'
|
|
34
|
+
Provides-Extra: dev
|
|
35
|
+
Requires-Dist: mypy; extra == 'dev'
|
|
36
|
+
Requires-Dist: pytest; extra == 'dev'
|
|
37
|
+
Requires-Dist: pytest-cov; extra == 'dev'
|
|
38
|
+
Requires-Dist: ruff; extra == 'dev'
|
|
39
|
+
Requires-Dist: types-pyyaml; extra == 'dev'
|
|
40
|
+
Requires-Dist: types-requests; extra == 'dev'
|
|
41
|
+
Provides-Extra: gcp-secrets
|
|
42
|
+
Requires-Dist: google-cloud-secret-manager>=2.20; extra == 'gcp-secrets'
|
|
43
|
+
Provides-Extra: gcs
|
|
44
|
+
Requires-Dist: google-cloud-storage>=2.10; extra == 'gcs'
|
|
45
|
+
Provides-Extra: s3
|
|
46
|
+
Requires-Dist: boto3>=1.28; extra == 's3'
|
|
47
|
+
Provides-Extra: vault
|
|
48
|
+
Requires-Dist: hvac>=2.0; extra == 'vault'
|
|
49
|
+
Description-Content-Type: text/markdown
|
|
50
|
+
|
|
51
|
+
# dtex
|
|
52
|
+
|
|
53
|
+
[](https://pypi.org/project/dtex/)
|
|
54
|
+
[](https://pypi.org/project/dtex/)
|
|
55
|
+
[](https://opensource.org/licenses/Apache-2.0)
|
|
56
|
+
[](https://github.com/vej-ai/dtex/actions/workflows/ci.yml)
|
|
57
|
+
|
|
58
|
+
**dtex** ("data extraction tool") is an open-source, self-hosted Python
|
|
59
|
+
**extract-load (EL)** tool. It moves data from a **source** (an API, a
|
|
60
|
+
database, a file drop) into a **destination** (a warehouse, a database, an
|
|
61
|
+
object store) — and nothing more. Transformation is dbt's job.
|
|
62
|
+
|
|
63
|
+
The pitch in one line: **a CLI-first, dbt-shaped extract-load tool —
|
|
64
|
+
pipelines are configs, connectors are folders, no UI blackbox.** The #1
|
|
65
|
+
principle is to keep it as simple as possible.
|
|
66
|
+
|
|
67
|
+
## Install
|
|
68
|
+
|
|
69
|
+
```sh
|
|
70
|
+
pip install dtex # every baked connector, ready
|
|
71
|
+
pip install 'dtex[gcs,s3]' # add gs:// / s3:// filesystem reads
|
|
72
|
+
pip install 'dtex[gcp-secrets]' # add the GCP Secret Manager resolver
|
|
73
|
+
pip install 'dtex[aws-secrets]' # add the AWS Secrets Manager resolver
|
|
74
|
+
pip install 'dtex[vault]' # add the HashiCorp Vault resolver
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
`pip install dtex` ships every baked source and destination — DuckDB,
|
|
78
|
+
BigQuery, the filesystem source's local + Parquet path, the REST / Postgres
|
|
79
|
+
/ ShipHero / Stripe sources, the engine, the CLI. Extras stay opt-in for the
|
|
80
|
+
cloud-storage paths of the filesystem source (`gs://` / `s3://`) and for
|
|
81
|
+
secret managers (only relevant if your `profiles.yml` uses `secret://` URLs).
|
|
82
|
+
|
|
83
|
+
dtex requires Python 3.11+. It installs both a CLI (`dtex`) and an importable
|
|
84
|
+
library (`import dtex`).
|
|
85
|
+
|
|
86
|
+
## Usage
|
|
87
|
+
|
|
88
|
+
```sh
|
|
89
|
+
dtex init my_project # scaffold a project
|
|
90
|
+
cd my_project
|
|
91
|
+
dtex new source my_api # scaffold a source connector
|
|
92
|
+
dtex new config my_pipeline # scaffold a pipeline config
|
|
93
|
+
dtex validate # check everything
|
|
94
|
+
dtex run -p my_pipeline # run the pipeline
|
|
95
|
+
dtex runs list -p my_pipeline # show recent run history
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
A *pipeline* is one config file binding a source + a destination + a target +
|
|
99
|
+
params. Run it with `dtex run -p <config>`. The library equivalent is
|
|
100
|
+
`dtex.run(config="my_pipeline")` and returns a structured `RunResult`.
|
|
101
|
+
|
|
102
|
+
## Pre-baked connectors
|
|
103
|
+
|
|
104
|
+
**Sources:** `filesystem` (CSV/JSONL/Parquet from local, GCS, or S3),
|
|
105
|
+
`rest` (paginated REST APIs — 4 pagination strategies, 4 auth modes),
|
|
106
|
+
`postgres` (keyset pagination, no `OFFSET`), `shiphero` (GraphQL),
|
|
107
|
+
`stripe` (resource-as-stream over the REST API).
|
|
108
|
+
|
|
109
|
+
**Destinations:** `duckdb` (zero-config dev default, all 5 capabilities) and
|
|
110
|
+
`bigquery` (production warehouse — Parquet-staged via GCS + LOAD jobs,
|
|
111
|
+
MERGE upserts, cursor-based partitioning).
|
|
112
|
+
|
|
113
|
+
**Engine:** per-stream commit + atomic transactions (rollback on failure),
|
|
114
|
+
state in the destination's `_dtex_state` table, run records in `_dtex_runs`,
|
|
115
|
+
structured JSON-lines logs per run, secret redaction, schema evolution
|
|
116
|
+
(`evolve` default, `strict` opt-in), pipeline-level parallelism with
|
|
117
|
+
per-destination caps.
|
|
118
|
+
|
|
119
|
+
**Secret managers:** GCP Secret Manager, AWS Secrets Manager, HashiCorp
|
|
120
|
+
Vault — each as an opt-in extra.
|
|
121
|
+
|
|
122
|
+
## Documentation
|
|
123
|
+
|
|
124
|
+
The full design handbook lives in [`docs/`](./docs/README.md). Start with
|
|
125
|
+
[00 — Vision & Naming](./docs/00-vision-and-naming.md),
|
|
126
|
+
[02 — Architecture](./docs/02-architecture.md),
|
|
127
|
+
[06 — Project Anatomy](./docs/06-project-anatomy.md),
|
|
128
|
+
[12 — Configs](./docs/12-configs.md), and
|
|
129
|
+
[10 — Roadmap and Scope](./docs/10-roadmap-and-scope.md).
|
|
130
|
+
|
|
131
|
+
## Security · Contributing · Code of Conduct
|
|
132
|
+
|
|
133
|
+
- [Security policy](./SECURITY.md) — how to report a vulnerability.
|
|
134
|
+
- [Contributing](./CONTRIBUTING.md) — dev setup, PR process, how to add a connector.
|
|
135
|
+
- [Code of Conduct](./CODE_OF_CONDUCT.md).
|
|
136
|
+
- [Changelog](./CHANGELOG.md).
|
|
137
|
+
|
|
138
|
+
## License
|
|
139
|
+
|
|
140
|
+
Apache License 2.0 — see [LICENSE](./LICENSE).
|
dtex-0.1.0/README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
1
|
+
# dtex
|
|
2
|
+
|
|
3
|
+
[](https://pypi.org/project/dtex/)
|
|
4
|
+
[](https://pypi.org/project/dtex/)
|
|
5
|
+
[](https://opensource.org/licenses/Apache-2.0)
|
|
6
|
+
[](https://github.com/vej-ai/dtex/actions/workflows/ci.yml)
|
|
7
|
+
|
|
8
|
+
**dtex** ("data extraction tool") is an open-source, self-hosted Python
|
|
9
|
+
**extract-load (EL)** tool. It moves data from a **source** (an API, a
|
|
10
|
+
database, a file drop) into a **destination** (a warehouse, a database, an
|
|
11
|
+
object store) — and nothing more. Transformation is dbt's job.
|
|
12
|
+
|
|
13
|
+
The pitch in one line: **a CLI-first, dbt-shaped extract-load tool —
|
|
14
|
+
pipelines are configs, connectors are folders, no UI blackbox.** The #1
|
|
15
|
+
principle is to keep it as simple as possible.
|
|
16
|
+
|
|
17
|
+
## Install
|
|
18
|
+
|
|
19
|
+
```sh
|
|
20
|
+
pip install dtex # every baked connector, ready
|
|
21
|
+
pip install 'dtex[gcs,s3]' # add gs:// / s3:// filesystem reads
|
|
22
|
+
pip install 'dtex[gcp-secrets]' # add the GCP Secret Manager resolver
|
|
23
|
+
pip install 'dtex[aws-secrets]' # add the AWS Secrets Manager resolver
|
|
24
|
+
pip install 'dtex[vault]' # add the HashiCorp Vault resolver
|
|
25
|
+
```
|
|
26
|
+
|
|
27
|
+
`pip install dtex` ships every baked source and destination — DuckDB,
|
|
28
|
+
BigQuery, the filesystem source's local + Parquet path, the REST / Postgres
|
|
29
|
+
/ ShipHero / Stripe sources, the engine, the CLI. Extras stay opt-in for the
|
|
30
|
+
cloud-storage paths of the filesystem source (`gs://` / `s3://`) and for
|
|
31
|
+
secret managers (only relevant if your `profiles.yml` uses `secret://` URLs).
|
|
32
|
+
|
|
33
|
+
dtex requires Python 3.11+. It installs both a CLI (`dtex`) and an importable
|
|
34
|
+
library (`import dtex`).
|
|
35
|
+
|
|
36
|
+
## Usage
|
|
37
|
+
|
|
38
|
+
```sh
|
|
39
|
+
dtex init my_project # scaffold a project
|
|
40
|
+
cd my_project
|
|
41
|
+
dtex new source my_api # scaffold a source connector
|
|
42
|
+
dtex new config my_pipeline # scaffold a pipeline config
|
|
43
|
+
dtex validate # check everything
|
|
44
|
+
dtex run -p my_pipeline # run the pipeline
|
|
45
|
+
dtex runs list -p my_pipeline # show recent run history
|
|
46
|
+
```
|
|
47
|
+
|
|
48
|
+
A *pipeline* is one config file binding a source + a destination + a target +
|
|
49
|
+
params. Run it with `dtex run -p <config>`. The library equivalent is
|
|
50
|
+
`dtex.run(config="my_pipeline")` and returns a structured `RunResult`.
|
|
51
|
+
|
|
52
|
+
## Pre-baked connectors
|
|
53
|
+
|
|
54
|
+
**Sources:** `filesystem` (CSV/JSONL/Parquet from local, GCS, or S3),
|
|
55
|
+
`rest` (paginated REST APIs — 4 pagination strategies, 4 auth modes),
|
|
56
|
+
`postgres` (keyset pagination, no `OFFSET`), `shiphero` (GraphQL),
|
|
57
|
+
`stripe` (resource-as-stream over the REST API).
|
|
58
|
+
|
|
59
|
+
**Destinations:** `duckdb` (zero-config dev default, all 5 capabilities) and
|
|
60
|
+
`bigquery` (production warehouse — Parquet-staged via GCS + LOAD jobs,
|
|
61
|
+
MERGE upserts, cursor-based partitioning).
|
|
62
|
+
|
|
63
|
+
**Engine:** per-stream commit + atomic transactions (rollback on failure),
|
|
64
|
+
state in the destination's `_dtex_state` table, run records in `_dtex_runs`,
|
|
65
|
+
structured JSON-lines logs per run, secret redaction, schema evolution
|
|
66
|
+
(`evolve` default, `strict` opt-in), pipeline-level parallelism with
|
|
67
|
+
per-destination caps.
|
|
68
|
+
|
|
69
|
+
**Secret managers:** GCP Secret Manager, AWS Secrets Manager, HashiCorp
|
|
70
|
+
Vault — each as an opt-in extra.
|
|
71
|
+
|
|
72
|
+
## Documentation
|
|
73
|
+
|
|
74
|
+
The full design handbook lives in [`docs/`](./docs/README.md). Start with
|
|
75
|
+
[00 — Vision & Naming](./docs/00-vision-and-naming.md),
|
|
76
|
+
[02 — Architecture](./docs/02-architecture.md),
|
|
77
|
+
[06 — Project Anatomy](./docs/06-project-anatomy.md),
|
|
78
|
+
[12 — Configs](./docs/12-configs.md), and
|
|
79
|
+
[10 — Roadmap and Scope](./docs/10-roadmap-and-scope.md).
|
|
80
|
+
|
|
81
|
+
## Security · Contributing · Code of Conduct
|
|
82
|
+
|
|
83
|
+
- [Security policy](./SECURITY.md) — how to report a vulnerability.
|
|
84
|
+
- [Contributing](./CONTRIBUTING.md) — dev setup, PR process, how to add a connector.
|
|
85
|
+
- [Code of Conduct](./CODE_OF_CONDUCT.md).
|
|
86
|
+
- [Changelog](./CHANGELOG.md).
|
|
87
|
+
|
|
88
|
+
## License
|
|
89
|
+
|
|
90
|
+
Apache License 2.0 — see [LICENSE](./LICENSE).
|