qualis-bigquery 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.
- qualis_bigquery-0.1.0/.github/workflows/ci.yml +48 -0
- qualis_bigquery-0.1.0/.github/workflows/release.yml +60 -0
- qualis_bigquery-0.1.0/.gitignore +16 -0
- qualis_bigquery-0.1.0/.python-version +1 -0
- qualis_bigquery-0.1.0/LICENSE +176 -0
- qualis_bigquery-0.1.0/PKG-INFO +59 -0
- qualis_bigquery-0.1.0/README.md +34 -0
- qualis_bigquery-0.1.0/pyproject.toml +62 -0
- qualis_bigquery-0.1.0/src/qualis_bigquery/__init__.py +9 -0
- qualis_bigquery-0.1.0/src/qualis_bigquery/adapter.py +206 -0
- qualis_bigquery-0.1.0/src/qualis_bigquery/py.typed +0 -0
- qualis_bigquery-0.1.0/src/qualis_bigquery/sql_templates.py +82 -0
- qualis_bigquery-0.1.0/tests/__init__.py +0 -0
- qualis_bigquery-0.1.0/tests/integration/__init__.py +0 -0
- qualis_bigquery-0.1.0/tests/integration/test_adapter_integration.py +69 -0
- qualis_bigquery-0.1.0/tests/unit/__init__.py +0 -0
- qualis_bigquery-0.1.0/tests/unit/test_adapter.py +49 -0
- qualis_bigquery-0.1.0/tests/unit/test_sql_templates.py +63 -0
- qualis_bigquery-0.1.0/uv.lock +1235 -0
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
name: CI
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
push:
|
|
5
|
+
branches: [main]
|
|
6
|
+
pull_request:
|
|
7
|
+
branches: [main]
|
|
8
|
+
|
|
9
|
+
permissions:
|
|
10
|
+
contents: read
|
|
11
|
+
|
|
12
|
+
jobs:
|
|
13
|
+
test:
|
|
14
|
+
name: test (Python ${{ matrix.python-version }})
|
|
15
|
+
runs-on: ubuntu-latest
|
|
16
|
+
strategy:
|
|
17
|
+
fail-fast: false
|
|
18
|
+
matrix:
|
|
19
|
+
python-version: ["3.12", "3.13"]
|
|
20
|
+
steps:
|
|
21
|
+
- uses: actions/checkout@v4
|
|
22
|
+
|
|
23
|
+
- name: Set up uv
|
|
24
|
+
uses: astral-sh/setup-uv@v3
|
|
25
|
+
with:
|
|
26
|
+
enable-cache: true
|
|
27
|
+
|
|
28
|
+
- name: Set up Python ${{ matrix.python-version }}
|
|
29
|
+
run: uv python install ${{ matrix.python-version }}
|
|
30
|
+
|
|
31
|
+
- name: Install dependencies
|
|
32
|
+
run: uv sync --dev
|
|
33
|
+
|
|
34
|
+
- name: Lint with ruff
|
|
35
|
+
run: uv run ruff check src/ tests/
|
|
36
|
+
|
|
37
|
+
- name: Typecheck with mypy
|
|
38
|
+
run: uv run mypy src/
|
|
39
|
+
|
|
40
|
+
- name: Run tests
|
|
41
|
+
run: uv run pytest --cov=qualis_bigquery --cov-report=term-missing
|
|
42
|
+
|
|
43
|
+
- name: Enforce coverage threshold
|
|
44
|
+
# 55% is appropriate for a thin SDK adapter: SQL templates +
|
|
45
|
+
# adapter dispatch are fully covered via mocked tests; the
|
|
46
|
+
# uncovered paths are connection/stream lifecycle that only
|
|
47
|
+
# exercise with a live BigQuery client.
|
|
48
|
+
run: uv run pytest --cov=qualis_bigquery --cov-fail-under=55
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
name: Release
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
push:
|
|
5
|
+
tags:
|
|
6
|
+
- "v*"
|
|
7
|
+
|
|
8
|
+
permissions:
|
|
9
|
+
contents: read
|
|
10
|
+
|
|
11
|
+
jobs:
|
|
12
|
+
build:
|
|
13
|
+
name: Build sdist and wheel
|
|
14
|
+
runs-on: ubuntu-latest
|
|
15
|
+
steps:
|
|
16
|
+
- uses: actions/checkout@v4
|
|
17
|
+
|
|
18
|
+
- name: Set up uv
|
|
19
|
+
uses: astral-sh/setup-uv@v3
|
|
20
|
+
|
|
21
|
+
- name: Set up Python
|
|
22
|
+
run: uv python install 3.12
|
|
23
|
+
|
|
24
|
+
- name: Build artefacts
|
|
25
|
+
run: uv build
|
|
26
|
+
|
|
27
|
+
- name: Verify version matches tag
|
|
28
|
+
run: |
|
|
29
|
+
VERSION_IN_PYPROJECT=$(grep '^version = ' pyproject.toml | head -1 | sed 's/.*"\(.*\)"/\1/')
|
|
30
|
+
TAG_VERSION="${GITHUB_REF#refs/tags/v}"
|
|
31
|
+
if [ "$VERSION_IN_PYPROJECT" != "$TAG_VERSION" ]; then
|
|
32
|
+
echo "Version mismatch: pyproject.toml says '$VERSION_IN_PYPROJECT', tag is '$TAG_VERSION'"
|
|
33
|
+
exit 1
|
|
34
|
+
fi
|
|
35
|
+
echo "Version $VERSION_IN_PYPROJECT matches tag v$TAG_VERSION"
|
|
36
|
+
|
|
37
|
+
- name: Upload artefacts
|
|
38
|
+
uses: actions/upload-artifact@v4
|
|
39
|
+
with:
|
|
40
|
+
name: dist
|
|
41
|
+
path: dist/
|
|
42
|
+
|
|
43
|
+
publish:
|
|
44
|
+
name: Publish to PyPI
|
|
45
|
+
needs: build
|
|
46
|
+
runs-on: ubuntu-latest
|
|
47
|
+
environment:
|
|
48
|
+
name: pypi
|
|
49
|
+
url: https://pypi.org/p/qualis-bigquery
|
|
50
|
+
permissions:
|
|
51
|
+
id-token: write
|
|
52
|
+
steps:
|
|
53
|
+
- name: Download artefacts
|
|
54
|
+
uses: actions/download-artifact@v4
|
|
55
|
+
with:
|
|
56
|
+
name: dist
|
|
57
|
+
path: dist/
|
|
58
|
+
|
|
59
|
+
- name: Publish to PyPI
|
|
60
|
+
uses: pypa/gh-action-pypi-publish@release/v1
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
3.12
|
|
@@ -0,0 +1,176 @@
|
|
|
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 made available under
|
|
36
|
+
the License, as indicated by a copyright notice that is included in
|
|
37
|
+
or attached to the work (an example is provided in the Appendix below).
|
|
38
|
+
|
|
39
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
40
|
+
form, that is based on (or derived from) the Work and for which the
|
|
41
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
42
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
43
|
+
of this License, Derivative Works shall not include works that remain
|
|
44
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
45
|
+
the Work and Derivative Works thereof.
|
|
46
|
+
|
|
47
|
+
"Contribution" shall mean, as submitted to the Licensor for inclusion
|
|
48
|
+
in the Work by the copyright owner or by an individual or Legal Entity
|
|
49
|
+
authorized to submit on behalf of the copyright owner. For the purposes
|
|
50
|
+
of this definition, "submitted" means any form of electronic, verbal,
|
|
51
|
+
or written communication sent to the Licensor or its representatives,
|
|
52
|
+
including but not limited to communication on electronic mailing lists,
|
|
53
|
+
source code control systems, and issue tracking systems that are managed
|
|
54
|
+
by, or on behalf of, the Licensor for the purpose of recording
|
|
55
|
+
instructions given to the Licensor.
|
|
56
|
+
|
|
57
|
+
"Contributor" shall mean Licensor and any Legal Entity on behalf of
|
|
58
|
+
whom a Contribution has been received by the Licensor and is included
|
|
59
|
+
in the Work.
|
|
60
|
+
|
|
61
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
62
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
63
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
64
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
65
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
66
|
+
Work and such Derivative Works in Source or Object form.
|
|
67
|
+
|
|
68
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
69
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
70
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
71
|
+
(except as stated in this section) patent license to make, have made,
|
|
72
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
73
|
+
where such license applies only to those Contributions necessary to
|
|
74
|
+
make, use, sell, offer to sell, import, or otherwise transfer the Work.
|
|
75
|
+
|
|
76
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
77
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
78
|
+
modifications, and in Source or Object form, provided that You
|
|
79
|
+
meet the following conditions:
|
|
80
|
+
|
|
81
|
+
(a) You must give any other recipients of the Work or Derivative
|
|
82
|
+
Works a copy of this License; and
|
|
83
|
+
|
|
84
|
+
(b) You must reproduce the above copyright notices for use,
|
|
85
|
+
reproduction, and distribution, and a relevant copyright notice
|
|
86
|
+
in the Derivative Works; and
|
|
87
|
+
|
|
88
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
89
|
+
that You distribute, all copyright, patent, trademark, and
|
|
90
|
+
attribution notices from the Source form of the Work,
|
|
91
|
+
excluding those notices that do not pertain to any part of
|
|
92
|
+
the Derivative Works; and
|
|
93
|
+
|
|
94
|
+
(d) If the Work includes a "NOTICE" text file, the contents
|
|
95
|
+
of the NOTICE file are for informational purposes only
|
|
96
|
+
and do not modify the License. You may add Your own attribution
|
|
97
|
+
notices within Derivative Works that You distribute, alongside
|
|
98
|
+
or in addition to the NOTICE text from the Work, provided
|
|
99
|
+
that such additional attribution notices cannot be construed
|
|
100
|
+
as modifying the License.
|
|
101
|
+
|
|
102
|
+
You may add Your own license statement for Your modifications and
|
|
103
|
+
may provide additional grant of rights to use, copy, modify, merge,
|
|
104
|
+
publish, distribute, sublicense, and/or sell copies of the Work.
|
|
105
|
+
|
|
106
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
107
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
108
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
109
|
+
this License, without any additional terms or conditions.
|
|
110
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
111
|
+
the terms of any separate license agreement you may have executed
|
|
112
|
+
with Licensor regarding such Contributions.
|
|
113
|
+
|
|
114
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
115
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
116
|
+
except as required for reasonable and customary use in describing the
|
|
117
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
118
|
+
|
|
119
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
120
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
121
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
122
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
123
|
+
implied, including, without limitation, any warranties or conditions
|
|
124
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
125
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
126
|
+
appropriateness of using or reproducing the Work and assume any
|
|
127
|
+
risks associated with Your exercise of permissions under this License.
|
|
128
|
+
|
|
129
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
130
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
131
|
+
unless required by applicable law (such as deliberate and grossly
|
|
132
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
133
|
+
liable to You for damages, including any direct, indirect, special,
|
|
134
|
+
incidental, or exemplary damages of any character arising as a
|
|
135
|
+
result of this License or out of the use or inability to use the
|
|
136
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
137
|
+
work stoppage, computer failure or malfunction, or all other
|
|
138
|
+
commercial damages or losses), even if such Contributor has been
|
|
139
|
+
advised of the possibility of such damages.
|
|
140
|
+
|
|
141
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
142
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
143
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
144
|
+
or other liability obligations and/or rights consistent with this
|
|
145
|
+
License. However, in accepting such obligations, You may offer only
|
|
146
|
+
conditions that are consistent with this full terms and conditions,
|
|
147
|
+
including warranty disclaimers and limitation of liability contained
|
|
148
|
+
in this License, or any of the terms and conditions contained in a
|
|
149
|
+
Section 9 of the License, including without limitation
|
|
150
|
+
indemnification.
|
|
151
|
+
|
|
152
|
+
END OF TERMS AND CONDITIONS
|
|
153
|
+
|
|
154
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
155
|
+
|
|
156
|
+
To apply the Apache License to your work, attach the following
|
|
157
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
158
|
+
replaced with your own identifying information. (Don't include
|
|
159
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
160
|
+
comment syntax for the format of the file. We also recommend that
|
|
161
|
+
a file or directory name be given, with a reference to where the
|
|
162
|
+
full text can be found.
|
|
163
|
+
|
|
164
|
+
Copyright 2024 Ahmed Ashraf
|
|
165
|
+
|
|
166
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
167
|
+
you may not use this file except in compliance with the License.
|
|
168
|
+
You may obtain a copy of the License at
|
|
169
|
+
|
|
170
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
171
|
+
|
|
172
|
+
Unless required by applicable law or agreed to in writing, software
|
|
173
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
174
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
175
|
+
See the License for the specific language governing permissions and
|
|
176
|
+
limitations under the License.
|
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: qualis-bigquery
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: BigQuery adapter for Qualis (data quality framework)
|
|
5
|
+
Project-URL: Homepage, https://github.com/ahmedashraffcih/qualis-bigquery
|
|
6
|
+
Project-URL: Repository, https://github.com/ahmedashraffcih/qualis-bigquery
|
|
7
|
+
Project-URL: Issues, https://github.com/ahmedashraffcih/qualis-bigquery/issues
|
|
8
|
+
Author-email: Ahmed Ashraf <ahmedashraffcih@gmail.com>
|
|
9
|
+
License: Apache-2.0
|
|
10
|
+
License-File: LICENSE
|
|
11
|
+
Keywords: bigquery,data-quality,dq,qualis
|
|
12
|
+
Classifier: Development Status :: 4 - Beta
|
|
13
|
+
Classifier: Intended Audience :: Developers
|
|
14
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
15
|
+
Classifier: Operating System :: OS Independent
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
18
|
+
Classifier: Topic :: Database
|
|
19
|
+
Classifier: Topic :: Software Development :: Quality Assurance
|
|
20
|
+
Classifier: Typing :: Typed
|
|
21
|
+
Requires-Python: >=3.12
|
|
22
|
+
Requires-Dist: google-cloud-bigquery>=3.0
|
|
23
|
+
Requires-Dist: qualis>=0.3.1
|
|
24
|
+
Description-Content-Type: text/markdown
|
|
25
|
+
|
|
26
|
+
# qualis-bigquery
|
|
27
|
+
|
|
28
|
+
BigQuery adapter for [Qualis](https://github.com/ahmedashraffcih/qualis) —
|
|
29
|
+
the open-source data quality framework.
|
|
30
|
+
|
|
31
|
+
## Install
|
|
32
|
+
|
|
33
|
+
```bash
|
|
34
|
+
pip install qualis qualis-bigquery
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
## Usage
|
|
38
|
+
|
|
39
|
+
```yaml
|
|
40
|
+
# qualis.yaml
|
|
41
|
+
adapter: bigquery
|
|
42
|
+
project: my-gcp-project
|
|
43
|
+
dataset: my_dataset
|
|
44
|
+
# Auth: standard GCP application default credentials
|
|
45
|
+
# gcloud auth application-default login
|
|
46
|
+
```
|
|
47
|
+
|
|
48
|
+
## Supported checks
|
|
49
|
+
|
|
50
|
+
- not_null, unique, between, regex, in_set
|
|
51
|
+
- row_count, not_negative
|
|
52
|
+
- reference_lookup
|
|
53
|
+
|
|
54
|
+
The adapter is read-only by contract — DML statements
|
|
55
|
+
(INSERT/UPDATE/DELETE/MERGE/DROP/CREATE/ALTER) are explicitly refused.
|
|
56
|
+
|
|
57
|
+
## License
|
|
58
|
+
|
|
59
|
+
Apache 2.0.
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
# qualis-bigquery
|
|
2
|
+
|
|
3
|
+
BigQuery adapter for [Qualis](https://github.com/ahmedashraffcih/qualis) —
|
|
4
|
+
the open-source data quality framework.
|
|
5
|
+
|
|
6
|
+
## Install
|
|
7
|
+
|
|
8
|
+
```bash
|
|
9
|
+
pip install qualis qualis-bigquery
|
|
10
|
+
```
|
|
11
|
+
|
|
12
|
+
## Usage
|
|
13
|
+
|
|
14
|
+
```yaml
|
|
15
|
+
# qualis.yaml
|
|
16
|
+
adapter: bigquery
|
|
17
|
+
project: my-gcp-project
|
|
18
|
+
dataset: my_dataset
|
|
19
|
+
# Auth: standard GCP application default credentials
|
|
20
|
+
# gcloud auth application-default login
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
## Supported checks
|
|
24
|
+
|
|
25
|
+
- not_null, unique, between, regex, in_set
|
|
26
|
+
- row_count, not_negative
|
|
27
|
+
- reference_lookup
|
|
28
|
+
|
|
29
|
+
The adapter is read-only by contract — DML statements
|
|
30
|
+
(INSERT/UPDATE/DELETE/MERGE/DROP/CREATE/ALTER) are explicitly refused.
|
|
31
|
+
|
|
32
|
+
## License
|
|
33
|
+
|
|
34
|
+
Apache 2.0.
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["hatchling"]
|
|
3
|
+
build-backend = "hatchling.build"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "qualis-bigquery"
|
|
7
|
+
version = "0.1.0"
|
|
8
|
+
description = "BigQuery adapter for Qualis (data quality framework)"
|
|
9
|
+
readme = "README.md"
|
|
10
|
+
license = { text = "Apache-2.0" }
|
|
11
|
+
requires-python = ">=3.12"
|
|
12
|
+
authors = [
|
|
13
|
+
{ name = "Ahmed Ashraf", email = "ahmedashraffcih@gmail.com" },
|
|
14
|
+
]
|
|
15
|
+
keywords = ["data-quality", "bigquery", "qualis", "dq"]
|
|
16
|
+
classifiers = [
|
|
17
|
+
"Development Status :: 4 - Beta",
|
|
18
|
+
"Intended Audience :: Developers",
|
|
19
|
+
"License :: OSI Approved :: Apache Software License",
|
|
20
|
+
"Operating System :: OS Independent",
|
|
21
|
+
"Programming Language :: Python :: 3.12",
|
|
22
|
+
"Programming Language :: Python :: 3.13",
|
|
23
|
+
"Topic :: Database",
|
|
24
|
+
"Topic :: Software Development :: Quality Assurance",
|
|
25
|
+
"Typing :: Typed",
|
|
26
|
+
]
|
|
27
|
+
dependencies = [
|
|
28
|
+
"qualis>=0.3.1",
|
|
29
|
+
"google-cloud-bigquery>=3.0",
|
|
30
|
+
]
|
|
31
|
+
|
|
32
|
+
[project.entry-points."qualis.adapters"]
|
|
33
|
+
bigquery = "qualis_bigquery.adapter:BigQueryAdapter"
|
|
34
|
+
|
|
35
|
+
[project.urls]
|
|
36
|
+
Homepage = "https://github.com/ahmedashraffcih/qualis-bigquery"
|
|
37
|
+
Repository = "https://github.com/ahmedashraffcih/qualis-bigquery"
|
|
38
|
+
Issues = "https://github.com/ahmedashraffcih/qualis-bigquery/issues"
|
|
39
|
+
|
|
40
|
+
[tool.hatch.build.targets.wheel]
|
|
41
|
+
packages = ["src/qualis_bigquery"]
|
|
42
|
+
|
|
43
|
+
[tool.pytest.ini_options]
|
|
44
|
+
testpaths = ["tests"]
|
|
45
|
+
|
|
46
|
+
[tool.mypy]
|
|
47
|
+
strict = true
|
|
48
|
+
python_version = "3.12"
|
|
49
|
+
|
|
50
|
+
[tool.ruff]
|
|
51
|
+
line-length = 100
|
|
52
|
+
|
|
53
|
+
[tool.ruff.lint]
|
|
54
|
+
select = ["E", "F", "I", "B", "UP", "RUF", "TC"]
|
|
55
|
+
|
|
56
|
+
[dependency-groups]
|
|
57
|
+
dev = [
|
|
58
|
+
"mypy>=1.0",
|
|
59
|
+
"pytest>=8.0",
|
|
60
|
+
"pytest-cov>=4.0",
|
|
61
|
+
"ruff>=0.5",
|
|
62
|
+
]
|
|
@@ -0,0 +1,206 @@
|
|
|
1
|
+
"""BigQueryAdapter implementing qualis.ports.database.DatabasePort.
|
|
2
|
+
|
|
3
|
+
BigQuery query execution uses parameterised queries via
|
|
4
|
+
``ScalarQueryParameter`` / ``ArrayQueryParameter``. Authentication uses
|
|
5
|
+
GCP Application Default Credentials.
|
|
6
|
+
"""
|
|
7
|
+
|
|
8
|
+
from __future__ import annotations
|
|
9
|
+
|
|
10
|
+
from typing import TYPE_CHECKING, Any
|
|
11
|
+
|
|
12
|
+
from qualis_bigquery.sql_templates import (
|
|
13
|
+
BETWEEN_SQL,
|
|
14
|
+
IN_SET_SQL,
|
|
15
|
+
NOT_NEGATIVE_SQL,
|
|
16
|
+
NOT_NULL_SQL,
|
|
17
|
+
REFERENCE_LOOKUP_SQL,
|
|
18
|
+
REGEX_SQL,
|
|
19
|
+
ROW_COUNT_SQL,
|
|
20
|
+
UNIQUE_SQL,
|
|
21
|
+
)
|
|
22
|
+
|
|
23
|
+
if TYPE_CHECKING:
|
|
24
|
+
from collections.abc import Iterator
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
class BigQueryAdapter:
|
|
28
|
+
"""Implements DatabasePort against Google BigQuery."""
|
|
29
|
+
|
|
30
|
+
def __init__(self, project: str, location: str | None = None) -> None:
|
|
31
|
+
self._project = project
|
|
32
|
+
self._location = location
|
|
33
|
+
self._client: Any = None
|
|
34
|
+
|
|
35
|
+
def _get_client(self) -> Any:
|
|
36
|
+
if self._client is None:
|
|
37
|
+
from google.cloud import bigquery
|
|
38
|
+
self._client = bigquery.Client(
|
|
39
|
+
project=self._project, location=self._location,
|
|
40
|
+
)
|
|
41
|
+
return self._client
|
|
42
|
+
|
|
43
|
+
def _qualified(self, schema: str, table: str) -> str:
|
|
44
|
+
"""Return a ``project.dataset.table`` reference (backticked at SQL-render time)."""
|
|
45
|
+
return f"{self._project}.{schema}.{table}"
|
|
46
|
+
|
|
47
|
+
def _make_scalar_param(self, name: str, value: str) -> Any:
|
|
48
|
+
from google.cloud.bigquery import ScalarQueryParameter
|
|
49
|
+
return ScalarQueryParameter(name, "STRING", value)
|
|
50
|
+
|
|
51
|
+
def _make_array_param(self, name: str, values: list[str]) -> Any:
|
|
52
|
+
from google.cloud.bigquery import ArrayQueryParameter
|
|
53
|
+
return ArrayQueryParameter(name, "STRING", values)
|
|
54
|
+
|
|
55
|
+
def _run_query(
|
|
56
|
+
self, sql: str, parameters: list[Any] | None = None,
|
|
57
|
+
) -> list[dict[str, Any]]:
|
|
58
|
+
from google.cloud.bigquery import QueryJobConfig
|
|
59
|
+
client = self._get_client()
|
|
60
|
+
config = QueryJobConfig(query_parameters=parameters or [])
|
|
61
|
+
job = client.query(sql, job_config=config)
|
|
62
|
+
return [dict(row.items()) for row in job.result()]
|
|
63
|
+
|
|
64
|
+
# ------------------------------------------------------------------
|
|
65
|
+
# DatabasePort methods
|
|
66
|
+
# ------------------------------------------------------------------
|
|
67
|
+
|
|
68
|
+
def query(self, sql: str, params: dict[str, Any] | None = None) -> list[dict[str, Any]]:
|
|
69
|
+
bq_params = [
|
|
70
|
+
self._make_scalar_param(k, str(v))
|
|
71
|
+
for k, v in (params or {}).items()
|
|
72
|
+
]
|
|
73
|
+
return self._run_query(sql, bq_params)
|
|
74
|
+
|
|
75
|
+
def execute(self, sql: str, params: dict[str, Any] | None = None) -> int:
|
|
76
|
+
# Safety gate: refuse DML — adapter is read-only by design.
|
|
77
|
+
first_word = sql.strip().split(None, 1)[0].upper() if sql.strip() else ""
|
|
78
|
+
if first_word in {"INSERT", "UPDATE", "DELETE", "MERGE", "DROP", "CREATE", "ALTER"}:
|
|
79
|
+
raise PermissionError(
|
|
80
|
+
f"BigQueryAdapter refuses DML statement starting with {first_word!r}"
|
|
81
|
+
)
|
|
82
|
+
rows = self.query(sql, params)
|
|
83
|
+
return len(rows)
|
|
84
|
+
|
|
85
|
+
def stream(
|
|
86
|
+
self, sql: str, params: dict[str, Any] | None = None,
|
|
87
|
+
chunk_size: int = 10_000,
|
|
88
|
+
) -> Iterator[list[dict[str, Any]]]:
|
|
89
|
+
bq_params = [
|
|
90
|
+
self._make_scalar_param(k, str(v))
|
|
91
|
+
for k, v in (params or {}).items()
|
|
92
|
+
]
|
|
93
|
+
from google.cloud.bigquery import QueryJobConfig
|
|
94
|
+
client = self._get_client()
|
|
95
|
+
config = QueryJobConfig(query_parameters=bq_params)
|
|
96
|
+
job = client.query(sql, job_config=config)
|
|
97
|
+
chunk: list[dict[str, Any]] = []
|
|
98
|
+
for row in job.result():
|
|
99
|
+
chunk.append(dict(row.items()))
|
|
100
|
+
if len(chunk) >= chunk_size:
|
|
101
|
+
yield chunk
|
|
102
|
+
chunk = []
|
|
103
|
+
if chunk:
|
|
104
|
+
yield chunk
|
|
105
|
+
|
|
106
|
+
def table_exists(self, schema: str, table: str) -> bool:
|
|
107
|
+
from google.cloud import bigquery
|
|
108
|
+
client = self._get_client()
|
|
109
|
+
ref = bigquery.TableReference.from_string(
|
|
110
|
+
f"{self._project}.{schema}.{table}"
|
|
111
|
+
)
|
|
112
|
+
try:
|
|
113
|
+
client.get_table(ref)
|
|
114
|
+
return True
|
|
115
|
+
except Exception:
|
|
116
|
+
return False
|
|
117
|
+
|
|
118
|
+
def check_not_null(self, schema: str, table: str, column: str) -> dict[str, int]:
|
|
119
|
+
sql = NOT_NULL_SQL.format(column=column, table=self._qualified(schema, table))
|
|
120
|
+
rows = self._run_query(sql)
|
|
121
|
+
return {
|
|
122
|
+
"null_count": int(rows[0]["null_count"]),
|
|
123
|
+
"total_count": int(rows[0]["total_count"]),
|
|
124
|
+
}
|
|
125
|
+
|
|
126
|
+
def check_unique(self, schema: str, table: str, column: str) -> dict[str, int]:
|
|
127
|
+
sql_dup = UNIQUE_SQL.format(column=column, table=self._qualified(schema, table))
|
|
128
|
+
sql_total = ROW_COUNT_SQL.format(table=self._qualified(schema, table))
|
|
129
|
+
dup_rows = self._run_query(sql_dup)
|
|
130
|
+
total_rows = self._run_query(sql_total)
|
|
131
|
+
return {
|
|
132
|
+
"duplicate_count": int(dup_rows[0]["duplicate_count"]) if dup_rows else 0,
|
|
133
|
+
"total_count": int(total_rows[0]["row_count"]) if total_rows else 0,
|
|
134
|
+
}
|
|
135
|
+
|
|
136
|
+
def check_between(
|
|
137
|
+
self, schema: str, table: str, column: str,
|
|
138
|
+
min_val: str, max_val: str,
|
|
139
|
+
) -> dict[str, int]:
|
|
140
|
+
sql = BETWEEN_SQL.format(column=column, table=self._qualified(schema, table))
|
|
141
|
+
params = [
|
|
142
|
+
self._make_scalar_param("min", min_val),
|
|
143
|
+
self._make_scalar_param("max", max_val),
|
|
144
|
+
]
|
|
145
|
+
rows = self._run_query(sql, params)
|
|
146
|
+
return {
|
|
147
|
+
"out_of_range_count": int(rows[0]["out_of_range_count"]),
|
|
148
|
+
"total_count": int(rows[0]["total_count"]),
|
|
149
|
+
"checked": int(rows[0]["checked"]),
|
|
150
|
+
}
|
|
151
|
+
|
|
152
|
+
def check_regex(
|
|
153
|
+
self, schema: str, table: str, column: str, pattern: str,
|
|
154
|
+
) -> dict[str, int]:
|
|
155
|
+
sql = REGEX_SQL.format(column=column, table=self._qualified(schema, table))
|
|
156
|
+
params = [self._make_scalar_param("pattern", pattern)]
|
|
157
|
+
rows = self._run_query(sql, params)
|
|
158
|
+
return {
|
|
159
|
+
"non_matching_count": int(rows[0]["non_matching_count"]),
|
|
160
|
+
"total_count": int(rows[0]["total_count"]),
|
|
161
|
+
}
|
|
162
|
+
|
|
163
|
+
def check_in_set(
|
|
164
|
+
self, schema: str, table: str, column: str, values: list[str],
|
|
165
|
+
) -> dict[str, int]:
|
|
166
|
+
sql = IN_SET_SQL.format(column=column, table=self._qualified(schema, table))
|
|
167
|
+
params = [self._make_array_param("values", values)]
|
|
168
|
+
rows = self._run_query(sql, params)
|
|
169
|
+
return {
|
|
170
|
+
"invalid_count": int(rows[0]["invalid_count"]),
|
|
171
|
+
"total_count": int(rows[0]["total_count"]),
|
|
172
|
+
}
|
|
173
|
+
|
|
174
|
+
def check_row_count(self, schema: str, table: str) -> dict[str, int]:
|
|
175
|
+
sql = ROW_COUNT_SQL.format(table=self._qualified(schema, table))
|
|
176
|
+
rows = self._run_query(sql)
|
|
177
|
+
return {"row_count": int(rows[0]["row_count"]) if rows else 0}
|
|
178
|
+
|
|
179
|
+
def check_not_negative(
|
|
180
|
+
self, schema: str, table: str, column: str,
|
|
181
|
+
) -> dict[str, int]:
|
|
182
|
+
sql = NOT_NEGATIVE_SQL.format(column=column, table=self._qualified(schema, table))
|
|
183
|
+
rows = self._run_query(sql)
|
|
184
|
+
return {
|
|
185
|
+
"negative_count": int(rows[0]["negative_count"]),
|
|
186
|
+
"total_count": int(rows[0]["total_count"]),
|
|
187
|
+
}
|
|
188
|
+
|
|
189
|
+
def check_reference_lookup(
|
|
190
|
+
self, schema: str, table: str, column: str,
|
|
191
|
+
valid_values: list[str],
|
|
192
|
+
) -> dict[str, int]:
|
|
193
|
+
sql = REFERENCE_LOOKUP_SQL.format(
|
|
194
|
+
column=column, table=self._qualified(schema, table),
|
|
195
|
+
)
|
|
196
|
+
params = [self._make_array_param("valid_values", valid_values)]
|
|
197
|
+
rows = self._run_query(sql, params)
|
|
198
|
+
return {
|
|
199
|
+
"invalid_count": int(rows[0]["invalid_count"]),
|
|
200
|
+
"total_count": int(rows[0]["total_count"]),
|
|
201
|
+
}
|
|
202
|
+
|
|
203
|
+
def close(self) -> None:
|
|
204
|
+
if self._client is not None:
|
|
205
|
+
self._client.close()
|
|
206
|
+
self._client = None
|
|
File without changes
|