├── markdown_to_sqlite ├── __init__.py └── cli.py ├── setup.cfg ├── .gitignore ├── .github └── workflows │ ├── test.yml │ └── publish.yml ├── README.md ├── setup.py ├── tests └── test_cli.py └── LICENSE /markdown_to_sqlite/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | [aliases] 2 | test=pytest 3 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .vscode 2 | *.egg-info 3 | __pycache__ 4 | dist 5 | build -------------------------------------------------------------------------------- /.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 | - uses: actions/checkout@v2 13 | - name: Set up Python ${{ matrix.python-version }} 14 | uses: actions/setup-python@v2 15 | with: 16 | python-version: ${{ matrix.python-version }} 17 | - uses: actions/cache@v2 18 | name: Configure pip caching 19 | with: 20 | path: ~/.cache/pip 21 | key: ${{ runner.os }}-pip-${{ hashFiles('**/setup.py') }} 22 | restore-keys: | 23 | ${{ runner.os }}-pip- 24 | - name: Install dependencies 25 | run: | 26 | pip install -e '.[test]' 27 | - name: Run tests 28 | run: | 29 | pytest 30 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # markdown-to-sqlite 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/markdown-to-sqlite.svg)](https://pypi.python.org/pypi/markdown-to-sqlite) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/markdown-to-sqlite?include_prereleases&label=changelog)](https://github.com/simonw/markdown-to-sqlite/releases) 5 | [![Tests](https://github.com/simonw/markdown-to-sqlite/workflows/Test/badge.svg)](https://github.com/simonw/markdown-to-sqlite/actions?query=workflow%3ATest) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/markdown-to-sqlite/blob/main/LICENSE) 7 | 8 | CLI tool for loading markdown files into a SQLite database. 9 | 10 | YAML embedded in the markdown files will be used to populate additional columns. 11 | 12 | Usage: markdown-to-sqlite [OPTIONS] DBNAME TABLE PATHS... 13 | 14 | For example: 15 | 16 | $ markdown-to-sqlite docs.db documents file1.md file2.md 17 | 18 | ## Breaking change 19 | 20 | Prior to version 1.0 this argument order was different - markdown files were listed before the database and table. 21 | -------------------------------------------------------------------------------- /markdown_to_sqlite/cli.py: -------------------------------------------------------------------------------- 1 | import click 2 | from pathlib import Path 3 | import sqlite3 4 | from sqlite_utils import Database 5 | import hashlib 6 | import markdown 7 | import yamldown 8 | from yaml.scanner import ScannerError 9 | 10 | 11 | @click.command() 12 | @click.version_option() 13 | @click.argument("dbname", nargs=1) 14 | @click.argument("table", nargs=1) 15 | @click.argument("paths", type=click.Path(exists=True), nargs=-1, required=True) 16 | def cli(paths, dbname, table): 17 | """ 18 | Load markdown files into a SQLite database 19 | 20 | https://datasette.io/tools/markdown-to-sqlite 21 | """ 22 | db = Database(dbname) 23 | md = markdown.Markdown() 24 | docs = [] 25 | for path in paths: 26 | try: 27 | metadata, text = yamldown.load(open(path)) 28 | html = md.convert(text) 29 | doc = { 30 | "_id": hashlib.sha1(path.encode("utf8")).hexdigest(), 31 | "_path": path, 32 | "text": text, 33 | "html": html, 34 | **(metadata or {}), 35 | } 36 | except (TypeError, ScannerError): 37 | doc = { 38 | "_id": hashlib.sha1(path.encode("utf8")).hexdigest(), 39 | "_path": path, 40 | "text": text, 41 | "html": html, 42 | } 43 | docs.append(doc) 44 | db[table].upsert_all(docs, pk="_id") 45 | -------------------------------------------------------------------------------- /.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 | - 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 32 | deploy: 33 | runs-on: ubuntu-latest 34 | needs: [test] 35 | steps: 36 | - uses: actions/checkout@v2 37 | - name: Set up Python 38 | uses: actions/setup-python@v2 39 | with: 40 | python-version: '3.9' 41 | - uses: actions/cache@v2 42 | name: Configure pip caching 43 | with: 44 | path: ~/.cache/pip 45 | key: ${{ runner.os }}-publish-pip-${{ hashFiles('**/setup.py') }} 46 | restore-keys: | 47 | ${{ runner.os }}-publish-pip- 48 | - name: Install dependencies 49 | run: | 50 | pip install setuptools wheel twine 51 | - name: Publish 52 | env: 53 | TWINE_USERNAME: __token__ 54 | TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }} 55 | run: | 56 | python setup.py sdist bdist_wheel 57 | twine upload dist/* 58 | -------------------------------------------------------------------------------- /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="markdown-to-sqlite", 18 | description="CLI tool for loading markdown files into a SQLite database", 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=["yamldown", "markdown", "sqlite-utils", "click"], 26 | extras_require={"test": ["pytest"]}, 27 | tests_require=["markdown-to-sqlite[test]"], 28 | setup_requires=["pytest-runner"], 29 | entry_points=""" 30 | [console_scripts] 31 | markdown-to-sqlite=markdown_to_sqlite.cli:cli 32 | """, 33 | url="https://github.com/simonw/markdown-to-sqlite", 34 | project_urls={ 35 | "Issues": "https://github.com/simonw/markdown-to-sqlite/issues", 36 | "CI": "https://github.com/simonw/markdown-to-sqlite/actions", 37 | "Changelog": "https://github.com/simonw/markdown-to-sqlite/releases", 38 | }, 39 | classifiers=[ 40 | "Intended Audience :: Developers", 41 | "Intended Audience :: Science/Research", 42 | "Intended Audience :: End Users/Desktop", 43 | "Topic :: Database", 44 | "License :: OSI Approved :: Apache Software License", 45 | "Programming Language :: Python :: 3.6", 46 | "Programming Language :: Python :: 3.7", 47 | ], 48 | python_requires=">=3.6", 49 | ) 50 | -------------------------------------------------------------------------------- /tests/test_cli.py: -------------------------------------------------------------------------------- 1 | from sqlite_utils import Database 2 | from markdown_to_sqlite import cli 3 | from click.testing import CliRunner 4 | import json 5 | 6 | ONE = """--- 7 | abstract: This is an abstract 8 | accepted: true 9 | date: 2018-10-14 09:00:00 10 | presenters: 11 | - twitter: simonw 12 | website: https://simonwillison.net/ 13 | - twitter: natbat 14 | website: http://blog.natbat.net/ 15 | --- 16 | # Heading 17 | 18 | Text 19 | 20 | * list 21 | * list 22 | """ 23 | 24 | TWO = """ 25 | --- 26 | abstract: Second abstract 27 | accepted: false 28 | date: 2018-11-14 09:00:00 29 | presenters: 30 | - twitter: cleopaws 31 | --- 32 | # Heading 2 33 | """ 34 | 35 | THREE = """ 36 | --- 37 | abstract: Third abstract 38 | accepted: false 39 | date: 2021-07-09 10:45:00 40 | presenters: 41 | - twitter: ryancheley 42 | website: https://ryancheley.com/ 43 | --- 44 | 45 | 46 | # Trial 1 47 | 48 | Method Start Dirty Cleaned 49 | ---------------- ----------------------------------------------------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------------------------------------------------------------- 50 | Water ![Trial1_Start_Water](/images/uploads/2016/12/Trial1_Start_Water-300x300.jpg){.alignnone .size-medium .wp-image-139 width="300" height="300"} ![Trial1_Dirty_Water](/images/uploads/2016/12/Trial1_Dirty_Water-300x300.jpg){.alignnone .size-medium .wp-image-136 width="300" height="300"} ![Trial1_Clean_Water](/images/uploads/2016/12/Trial1_Clean_Water-300x300.jpg){.alignnone .size-medium .wp-image-156 width="300" height="300"} 51 | ------------------------------------------------------------------------ 52 | 53 | """ 54 | 55 | 56 | 57 | def test_basic(tmpdir): 58 | (tmpdir / "one.md").write(ONE) 59 | (tmpdir / "two.md").write(TWO) 60 | (tmpdir / "three.md").write(THREE) 61 | result = CliRunner().invoke( 62 | cli.cli, 63 | [ 64 | str(tmpdir / "info.db"), 65 | "talks", 66 | str(tmpdir / "one.md"), 67 | str(tmpdir / "two.md"), 68 | str(tmpdir / "three.md"), 69 | ], 70 | ) 71 | db = Database(str(tmpdir / "info.db")) 72 | assert ["talks"] == db.table_names() 73 | assert 3 == db["talks"].count 74 | one, two, three = db.execute_returning_dicts("select * from talks") 75 | 76 | # Test row 1 77 | assert ( 78 | "

Heading

\n

Text

\n" 79 | == one["html"] 80 | ) 81 | assert "This is an abstract" == one["abstract"] 82 | assert [ 83 | {"twitter": "simonw", "website": "https://simonwillison.net/"}, 84 | {"twitter": "natbat", "website": "http://blog.natbat.net/"}, 85 | ] == json.loads(one["presenters"]) 86 | assert 1 == one["accepted"] 87 | assert "2018-10-14T09:00:00" == one["date"] 88 | 89 | # Test row 2 90 | assert "

Heading 2

" == two["html"] 91 | assert "Second abstract" == two["abstract"] 92 | assert [{"twitter": "cleopaws"}] == json.loads(two["presenters"]) 93 | assert 0 == two["accepted"] 94 | assert "2018-11-14T09:00:00" == two["date"] 95 | 96 | # test row 3 97 | assert "Third abstract" == three["abstract"] 98 | assert [ 99 | {"twitter": "ryancheley", "website": "https://ryancheley.com/"}, 100 | ] == json.loads(three["presenters"]) 101 | assert 0 == three["accepted"] 102 | assert "2021-07-09T10:45:00" == three["date"] 103 | assert 'Start' in three["html"] 104 | assert 'Dirty' in three["html"] 105 | assert 'Cleaned' in three["html"] 106 | assert 'Water' in three["html"] 107 | assert 'Method' in three["html"] 108 | assert 'images' in three["html"] -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------