├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── LICENSE ├── README.md ├── setup.py ├── tests ├── __init__.py └── test_cli.py └── yaml_to_sqlite ├── __init__.py └── cli.py /.github/workflows/publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish Python Package 2 | 3 | on: 4 | release: 5 | types: [created] 6 | 7 | jobs: 8 | test: 9 | runs-on: ubuntu-latest 10 | strategy: 11 | matrix: 12 | python-version: [3.6, 3.7, 3.8, 3.9] 13 | steps: 14 | - name: Install ripgrep 15 | run: sudo snap install ripgrep --classic 16 | - uses: actions/checkout@v2 17 | - name: Set up Python ${{ matrix.python-version }} 18 | uses: actions/setup-python@v2 19 | with: 20 | python-version: ${{ matrix.python-version }} 21 | - uses: actions/cache@v2 22 | name: Configure pip caching 23 | with: 24 | path: ~/.cache/pip 25 | key: ${{ runner.os }}-pip-${{ hashFiles('**/setup.py') }} 26 | restore-keys: | 27 | ${{ runner.os }}-pip- 28 | - name: Install dependencies 29 | run: | 30 | pip install -e '.[test]' 31 | - name: Run tests 32 | run: | 33 | pytest -vv 34 | deploy: 35 | runs-on: ubuntu-latest 36 | needs: [test] 37 | steps: 38 | - uses: actions/checkout@v2 39 | - name: Set up Python 40 | uses: actions/setup-python@v2 41 | with: 42 | python-version: '3.9' 43 | - uses: actions/cache@v2 44 | name: Configure pip caching 45 | with: 46 | path: ~/.cache/pip 47 | key: ${{ runner.os }}-publish-pip-${{ hashFiles('**/setup.py') }} 48 | restore-keys: | 49 | ${{ runner.os }}-publish-pip- 50 | - name: Install dependencies 51 | run: | 52 | pip install setuptools wheel twine 53 | - name: Publish 54 | env: 55 | TWINE_USERNAME: __token__ 56 | TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }} 57 | run: | 58 | python setup.py sdist bdist_wheel 59 | twine upload dist/* 60 | 61 | -------------------------------------------------------------------------------- /.github/workflows/test.yml: -------------------------------------------------------------------------------- 1 | name: Test 2 | 3 | on: [push] 4 | 5 | jobs: 6 | test: 7 | runs-on: ubuntu-latest 8 | strategy: 9 | matrix: 10 | python-version: [3.6, 3.7, 3.8, 3.9] 11 | steps: 12 | - name: Install ripgrep 13 | run: sudo snap install ripgrep --classic 14 | - uses: actions/checkout@v2 15 | - name: Set up Python ${{ matrix.python-version }} 16 | uses: actions/setup-python@v2 17 | with: 18 | python-version: ${{ matrix.python-version }} 19 | - uses: actions/cache@v2 20 | name: Configure pip caching 21 | with: 22 | path: ~/.cache/pip 23 | key: ${{ runner.os }}-pip-${{ hashFiles('**/setup.py') }} 24 | restore-keys: | 25 | ${{ runner.os }}-pip- 26 | - name: Install dependencies 27 | run: | 28 | pip install -e '.[test]' 29 | - name: Run tests 30 | run: | 31 | pytest -vv 32 | 33 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | venv 6 | .eggs 7 | .pytest_cache 8 | *.egg-info 9 | .DS_Store 10 | .schema 11 | .vscode 12 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 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. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # yaml-to-sqlite 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/yaml-to-sqlite.svg)](https://pypi.org/project/yaml-to-sqlite/) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/yaml-to-sqlite?include_prereleases&label=changelog)](https://github.com/simonw/yaml-to-sqlite/releases) 5 | [![Tests](https://github.com/simonw/yaml-to-sqlite/workflows/Test/badge.svg)](https://github.com/simonw/yaml-to-sqlite/actions?query=workflow%3ATest) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/yaml-to-sqlite/blob/main/LICENSE) 7 | 8 | Load the contents of a YAML file into a SQLite database table. 9 | 10 | ``` 11 | $ yaml-to-sqlite --help 12 | Usage: yaml-to-sqlite [OPTIONS] DB_PATH TABLE YAML_FILE 13 | 14 | Convert YAML files to SQLite 15 | 16 | Options: 17 | --version Show the version and exit. 18 | --pk TEXT Column to use as a primary key 19 | --single-column TEXT If YAML file is a list of values, populate this column 20 | --help Show this message and exit. 21 | ``` 22 | ## Usage 23 | 24 | Given a `news.yml` file containing the following: 25 | ```yaml 26 | - date: 2021-06-05 27 | body: |- 28 | [Datasette 0.57](https://docs.datasette.io/en/stable/changelog.html#v0-57) is out with an important security patch. 29 | - date: 2021-05-10 30 | body: |- 31 | [Django SQL Dashboard](https://simonwillison.net/2021/May/10/django-sql-dashboard/) is a new tool that brings a useful authenticated subset of Datasette to Django projects that are built on top of PostgreSQL. 32 | ``` 33 | Running this command: 34 | ```bash 35 | $ yaml-to-sqlite news.db stories news.yml 36 | ``` 37 | Will create a database file with this schema: 38 | ```bash 39 | $ sqlite-utils schema news.db 40 | CREATE TABLE [stories] ( 41 | [date] TEXT, 42 | [body] TEXT 43 | ); 44 | ``` 45 | The `--pk` option can be used to set a column as the primary key for the table: 46 | 47 | ```bash 48 | $ yaml-to-sqlite news.db stories news.yml --pk date 49 | $ sqlite-utils schema news.db 50 | CREATE TABLE [stories] ( 51 | [date] TEXT PRIMARY KEY, 52 | [body] TEXT 53 | ); 54 | ``` 55 | ## Single column YAML lists 56 | 57 | The `--single-column` option can be used when the YAML file is a list of values, for example a file called `dogs.yml` containing the following: 58 | 59 | ```yaml 60 | - Cleo 61 | - Pancakes 62 | - Nixie 63 | ``` 64 | Running this command: 65 | ```bash 66 | $ yaml-to-sqlite dogs.db dogs.yaml --single-column=name 67 | ``` 68 | Will create a single `dogs` table with a single `name` column that is the primary key: 69 | 70 | ```bash 71 | $ sqlite-utils schema dogs.db 72 | CREATE TABLE [dogs] ( 73 | [name] TEXT PRIMARY KEY 74 | ); 75 | $ sqlite-utils dogs.db 'select * from dogs' -t 76 | name 77 | -------- 78 | Cleo 79 | Pancakes 80 | Nixie 81 | ``` 82 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup, find_packages 2 | import io 3 | import os 4 | 5 | VERSION = "1.0" 6 | 7 | 8 | def get_long_description(): 9 | with io.open( 10 | os.path.join(os.path.dirname(os.path.abspath(__file__)), "README.md"), 11 | encoding="utf8", 12 | ) as fp: 13 | return fp.read() 14 | 15 | 16 | setup( 17 | name="yaml-to-sqlite", 18 | description="Utility for converting YAML files to SQLite", 19 | long_description=get_long_description(), 20 | long_description_content_type="text/markdown", 21 | author="Simon Willison", 22 | version=VERSION, 23 | license="Apache License, Version 2.0", 24 | packages=find_packages(), 25 | install_requires=["click", "PyYAML", "sqlite-utils>=3.9.1"], 26 | setup_requires=["pytest-runner"], 27 | extras_require={"test": ["pytest"]}, 28 | entry_points=""" 29 | [console_scripts] 30 | yaml-to-sqlite=yaml_to_sqlite.cli:cli 31 | """, 32 | tests_require=["yaml-to-sqlite[test]"], 33 | url="https://github.com/simonw/yaml-to-sqlite", 34 | classifiers=[ 35 | "Development Status :: 3 - Alpha", 36 | "Intended Audience :: Developers", 37 | "Intended Audience :: Science/Research", 38 | "Intended Audience :: End Users/Desktop", 39 | "License :: OSI Approved :: Apache Software License", 40 | "Programming Language :: Python :: 3.6", 41 | "Programming Language :: Python :: 3.7", 42 | ], 43 | ) 44 | -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/simonw/yaml-to-sqlite/1405bc83c8f2d4d8cd772ccacc340754f22b153e/tests/__init__.py -------------------------------------------------------------------------------- /tests/test_cli.py: -------------------------------------------------------------------------------- 1 | from click.testing import CliRunner 2 | from yaml_to_sqlite import cli 3 | import sqlite_utils 4 | import json 5 | import textwrap 6 | 7 | 8 | TEST_YAML = """ 9 | - name: datasette-cluster-map 10 | url: https://github.com/simonw/datasette-cluster-map 11 | - name: datasette-vega 12 | url: https://github.com/simonw/datasette-vega 13 | nested_with_date: 14 | - title: Hello 15 | date: 2010-01-01 16 | """ 17 | EXPECTED = [ 18 | { 19 | "name": "datasette-cluster-map", 20 | "url": "https://github.com/simonw/datasette-cluster-map", 21 | "nested_with_date": None, 22 | }, 23 | { 24 | "name": "datasette-vega", 25 | "url": "https://github.com/simonw/datasette-vega", 26 | "nested_with_date": json.dumps([{"title": "Hello", "date": "2010-01-01"}]), 27 | }, 28 | ] 29 | 30 | 31 | def test_without_pk(tmpdir): 32 | db_path = tmpdir / "db.db" 33 | assert ( 34 | 0 35 | == CliRunner() 36 | .invoke(cli.cli, [str(db_path), "items", "-"], input=TEST_YAML) 37 | .exit_code 38 | ) 39 | db = sqlite_utils.Database(str(db_path)) 40 | assert EXPECTED == list(db["items"].rows) 41 | # Run it again should get double the rows 42 | CliRunner().invoke(cli.cli, [str(db_path), "items", "-"], input=TEST_YAML) 43 | assert EXPECTED + EXPECTED == list(db["items"].rows) 44 | 45 | 46 | def test_with_pk(tmpdir): 47 | db_path = tmpdir / "db.db" 48 | assert ( 49 | 0 50 | == CliRunner() 51 | .invoke(cli.cli, [str(db_path), "items", "-", "--pk", "name"], input=TEST_YAML) 52 | .exit_code 53 | ) 54 | db = sqlite_utils.Database(str(db_path)) 55 | assert EXPECTED == list(db["items"].rows) 56 | # Run it again should get same number of rows 57 | CliRunner().invoke(cli.cli, [str(db_path), "items", "-"], input=TEST_YAML) 58 | assert EXPECTED == list(db["items"].rows) 59 | 60 | 61 | def test_single_column(tmpdir): 62 | db_path = tmpdir / "db.db" 63 | test_yaml = "- One\n" "- Two\n" "- Three\n" 64 | assert ( 65 | 0 66 | == CliRunner() 67 | .invoke( 68 | cli.cli, 69 | [str(db_path), "numbers", "-", "--single-column", "name"], 70 | input=test_yaml, 71 | ) 72 | .exit_code 73 | ) 74 | db = sqlite_utils.Database(str(db_path)) 75 | actual = list(db["numbers"].rows) 76 | assert actual == [{"name": "One"}, {"name": "Two"}, {"name": "Three"}] 77 | assert db["numbers"].pks == ["name"] 78 | 79 | 80 | def test_alters_if_necessary(tmpdir): 81 | db_path = tmpdir / "db.db" 82 | assert ( 83 | 0 84 | == CliRunner() 85 | .invoke(cli.cli, [str(db_path), "items", "-"], input=TEST_YAML) 86 | .exit_code 87 | ) 88 | more_input = textwrap.dedent( 89 | """ 90 | - name: some-other-thing 91 | new_column: A new column 92 | """ 93 | ) 94 | assert ( 95 | 0 96 | == CliRunner() 97 | .invoke(cli.cli, [str(db_path), "items", "-"], input=more_input) 98 | .exit_code 99 | ) 100 | db = sqlite_utils.Database(str(db_path)) 101 | assert db["items"].columns_dict == { 102 | "name": str, 103 | "url": str, 104 | "nested_with_date": str, 105 | "new_column": str, 106 | } 107 | -------------------------------------------------------------------------------- /yaml_to_sqlite/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/simonw/yaml-to-sqlite/1405bc83c8f2d4d8cd772ccacc340754f22b153e/yaml_to_sqlite/__init__.py -------------------------------------------------------------------------------- /yaml_to_sqlite/cli.py: -------------------------------------------------------------------------------- 1 | import click 2 | import yaml 3 | import sqlite_utils 4 | import json 5 | 6 | 7 | @click.command() 8 | @click.version_option() 9 | @click.argument( 10 | "db_path", type=click.Path(file_okay=True, dir_okay=False, allow_dash=False) 11 | ) 12 | @click.argument("table", type=str) 13 | @click.argument("yaml_file", type=click.File()) 14 | @click.option("--pk", type=str, help="Column to use as a primary key") 15 | @click.option( 16 | "--single-column", 17 | type=str, 18 | help="If YAML file is a list of values, populate this column", 19 | ) 20 | def cli(db_path, table, yaml_file, pk, single_column): 21 | "Convert YAML files to SQLite" 22 | db = sqlite_utils.Database(db_path) 23 | docs = yaml.safe_load(yaml_file) 24 | if single_column: 25 | if not isinstance(docs, list): 26 | raise click.ClickException( 27 | "If --single-column is provided input must be a YAML list" 28 | ) 29 | docs = [{single_column: value} for value in docs] 30 | pk = single_column 31 | # We round-trip the docs to JSON to ensure anything unexpected 32 | # like date objects is converted to valid JSON values 33 | docs = json.loads(json.dumps(docs, default=str)) 34 | if pk: 35 | db[table].upsert_all(docs, pk=pk, alter=True) 36 | else: 37 | db[table].insert_all(docs, alter=True) 38 | --------------------------------------------------------------------------------