github-to-sqlite 2.9__tar.gz → 2.9.1__tar.gz

{github-to-sqlite-2.9 → github_to_sqlite-2.9.1}/PKG-INFO

@@ -1,19 +1,19 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: github-to-sqlite
-Version: 2.9
+Version: 2.9.1
 Summary: Save data from GitHub to a SQLite database
-Home-page: https://github.com/dogsheep/github-to-sqlite
 Author: Simon Willison
-License: Apache License, Version 2.0
-Description-Content-Type: text/markdown
+License-Expression: Apache-2.0
 License-File: LICENSE
-Requires-Dist: sqlite-utils>=2.7.2
+Requires-Dist: sqlite-utils>4
 Requires-Dist: requests
-Requires-Dist: PyYAML
-Provides-Extra: test
-Requires-Dist: pytest; extra == "test"
-Requires-Dist: requests-mock; extra == "test"
-Requires-Dist: bs4; extra == "test"
+Requires-Dist: pyyaml
+Requires-Python: >=3.10
+Project-URL: Homepage, https://github.com/dogsheep/github-to-sqlite
+Project-URL: Changelog, https://github.com/dogsheep/github-to-sqlite/releases
+Project-URL: Issues, https://github.com/dogsheep/github-to-sqlite/issues
+Project-URL: CI, https://github.com/dogsheep/github-to-sqlite/actions
+Description-Content-Type: text/markdown
 
 # github-to-sqlite
 

{github-to-sqlite-2.9 → github_to_sqlite-2.9.1}/github_to_sqlite/cli.py

@@ -142,15 +142,16 @@ def pull_requests(db_path, repo, pull_request_ids, auth, load, orgs, state, sear
     else:
         if orgs:
             repos = itertools.chain.from_iterable(
-                utils.fetch_all_repos(token=token, org=org)
-                for org in orgs
+                utils.fetch_all_repos(token=token, org=org) for org in orgs
             )
         else:
             repos = [utils.fetch_repo(repo, token)]
         for repo_full in repos:
             utils.save_repo(db, repo_full)
             repo = repo_full["full_name"]
-            pull_requests = utils.fetch_pull_requests(repo, state, token, pull_request_ids)
+            pull_requests = utils.fetch_pull_requests(
+                repo, state, token, pull_request_ids
+            )
             utils.save_pull_requests(db, pull_requests, repo_full)
     utils.ensure_db_shape(db)
 
@@ -499,7 +500,9 @@ def scrape_dependents(db_path, repos, auth, verbose):
                     {
                         "repo": repo_full["id"],
                         "dependent": dependent_id,
-                        "first_seen_utc": datetime.datetime.utcnow().isoformat(),
+                        "first_seen_utc": datetime.datetime.now(datetime.timezone.utc)
+                        .replace(tzinfo=None)
+                        .isoformat(),
                     },
                     pk=("repo", "dependent"),
                     foreign_keys=(

{github-to-sqlite-2.9 → github_to_sqlite-2.9.1}/github_to_sqlite/utils.py

@@ -229,11 +229,11 @@ def save_pull_requests(db, pull_requests, repo):
 
 
 def save_user(db, user):
-    # Under some conditions, GitHub caches removed repositories with  
+    # Under some conditions, GitHub caches removed repositories with
     # stars and ends up leaving dangling `None` user references.
     if user is None:
         return None
-    
+
     # Remove all url fields except avatar_url and html_url
     to_save = {
         key: value
@@ -461,7 +461,9 @@ def fetch_stargazers(repo, token=None):
 
 
 def fetch_all_repos(username=None, token=None, org=None):
-    assert username or token or org, "Must provide username= or token= or org= or a combination"
+    assert (
+        username or token or org
+    ), "Must provide username= or token= or org= or a combination"
     headers = make_headers(token)
     # Get topics for each repo:
     headers["Accept"] = "application/vnd.github.mercy-preview+json"
@@ -695,7 +697,10 @@ def ensure_foreign_keys(db):
     for expected_foreign_key in FOREIGN_KEYS:
         table, column, table2, column2 = expected_foreign_key
         if (
-            expected_foreign_key not in db[table].foreign_keys
+            expected_foreign_key not in {
+                (fk.table, fk.column, fk.other_table, fk.other_column)
+                for fk in db[table].foreign_keys
+            }
             and
             # Ensure all tables and columns exist
             db[table].exists()

github_to_sqlite-2.9.1/pyproject.toml

@@ -0,0 +1,39 @@
+[project]
+name = "github-to-sqlite"
+version = "2.9.1"
+description = "Save data from GitHub to a SQLite database"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+dependencies = [
+    "sqlite-utils>4",
+    "requests",
+    "PyYAML",
+]
+
+[[project.authors]]
+name = "Simon Willison"
+
+[project.urls]
+Homepage = "https://github.com/dogsheep/github-to-sqlite"
+Changelog = "https://github.com/dogsheep/github-to-sqlite/releases"
+Issues = "https://github.com/dogsheep/github-to-sqlite/issues"
+CI = "https://github.com/dogsheep/github-to-sqlite/actions"
+
+[project.scripts]
+github-to-sqlite = "github_to_sqlite.cli:cli"
+
+[dependency-groups]
+dev = [
+    "pytest",
+    "requests-mock",
+    "bs4",
+]
+
+[build-system]
+requires = ["uv_build>=0.9.18,<0.12.0"]
+build-backend = "uv_build"
+
+[tool.uv.build-backend]
+module-root = ""

github_to_sqlite-2.9.1/pyproject.toml.orig

@@ -0,0 +1,37 @@
+[project]
+name = "github-to-sqlite"
+version = "2.9.1"
+description = "Save data from GitHub to a SQLite database"
+readme = "README.md"
+requires-python = ">=3.10"
+authors = [{name = "Simon Willison"}]
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+dependencies = [
+    "sqlite-utils>4",
+    "requests",
+    "PyYAML",
+]
+
+[project.urls]
+Homepage = "https://github.com/dogsheep/github-to-sqlite"
+Changelog = "https://github.com/dogsheep/github-to-sqlite/releases"
+Issues = "https://github.com/dogsheep/github-to-sqlite/issues"
+CI = "https://github.com/dogsheep/github-to-sqlite/actions"
+
+[project.scripts]
+github-to-sqlite = "github_to_sqlite.cli:cli"
+
+[dependency-groups]
+dev = [
+    "pytest",
+    "requests-mock",
+    "bs4",
+]
+
+[build-system]
+requires = ["uv_build>=0.9.18,<0.12.0"]
+build-backend = "uv_build"
+
+[tool.uv.build-backend]
+module-root = ""

github-to-sqlite-2.9/github_to_sqlite.egg-info/PKG-INFO

@@ -1,277 +0,0 @@
-Metadata-Version: 2.1
-Name: github-to-sqlite
-Version: 2.9
-Summary: Save data from GitHub to a SQLite database
-Home-page: https://github.com/dogsheep/github-to-sqlite
-Author: Simon Willison
-License: Apache License, Version 2.0
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: sqlite-utils>=2.7.2
-Requires-Dist: requests
-Requires-Dist: PyYAML
-Provides-Extra: test
-Requires-Dist: pytest; extra == "test"
-Requires-Dist: requests-mock; extra == "test"
-Requires-Dist: bs4; extra == "test"
-
-# github-to-sqlite
-
-[![PyPI](https://img.shields.io/pypi/v/github-to-sqlite.svg)](https://pypi.org/project/github-to-sqlite/)
-[![Changelog](https://img.shields.io/github/v/release/dogsheep/github-to-sqlite?include_prereleases&label=changelog)](https://github.com/dogsheep/github-to-sqlite/releases)
-[![Tests](https://github.com/dogsheep/github-to-sqlite/workflows/Test/badge.svg)](https://github.com/dogsheep/github-to-sqlite/actions?query=workflow%3ATest)
-[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/dogsheep/github-to-sqlite/blob/main/LICENSE)
-
-Save data from GitHub to a SQLite database.
-
-<!-- toc -->
-
-- [Demo](#demo)
-- [How to install](#how-to-install)
-- [Authentication](#authentication)
-- [Fetching issues for a repository](#fetching-issues-for-a-repository)
-- [Fetching pull requests for a repository](#fetching-pull-requests-for-a-repository)
-- [Fetching issue comments for a repository](#fetching-issue-comments-for-a-repository)
-- [Fetching commits for a repository](#fetching-commits-for-a-repository)
-- [Fetching releases for a repository](#fetching-releases-for-a-repository)
-- [Fetching tags for a repository](#fetching-tags-for-a-repository)
-- [Fetching contributors to a repository](#fetching-contributors-to-a-repository)
-- [Fetching repos belonging to a user or organization](#fetching-repos-belonging-to-a-user-or-organization)
-- [Fetching specific repositories](#fetching-specific-repositories)
-- [Fetching repos that have been starred by a user](#fetching-repos-that-have-been-starred-by-a-user)
-- [Fetching users that have starred specific repos](#fetching-users-that-have-starred-specific-repos)
-- [Fetching GitHub Actions workflows](#fetching-github-actions-workflows)
-- [Scraping dependents for a repository](#scraping-dependents-for-a-repository)
-- [Fetching emojis](#fetching-emojis)
-- [Making authenticated API calls](#making-authenticated-api-calls)
-
-<!-- tocstop -->
-
-## Demo
-
-https://github-to-sqlite.dogsheep.net/ hosts a [Datasette](https://datasette.io/) demo of a database created by [running this tool](https://github.com/dogsheep/github-to-sqlite/blob/main/.github/workflows/deploy-demo.yml#L40-L60) against all of the repositories in the [Dogsheep GitHub organization](https://github.com/dogsheep), plus the [datasette](https://github.com/simonw/datasette) and [sqlite-utils](https://github.com/simonw/sqlite-utils) repositories.
-
-## How to install
-
-    $ pip install github-to-sqlite
-
-## Authentication
-
-Create a GitHub personal access token: https://github.com/settings/tokens
-
-Run this command and paste in your new token:
-
-    $ github-to-sqlite auth
-
-This will create a file called `auth.json` in your current directory containing the required value. To save the file at a different path or filename, use the `--auth=myauth.json` option.
-
-As an alternative to using an `auth.json` file you can add your access token to an environment variable called `GITHUB_TOKEN`.
-
-## Fetching issues for a repository
-
-The `issues` command retrieves all of the issues belonging to a specified repository.
-
-    $ github-to-sqlite issues github.db simonw/datasette
-
-If an `auth.json` file is present it will use the token from that file. It works without authentication for public repositories but you should be aware that GitHub have strict IP-based rate limits for unauthenticated requests.
-
-You can point to a different location of `auth.json` using `-a`:
-
-    $ github-to-sqlite issues github.db simonw/datasette -a /path/to/auth.json
-
-You can use the `--issue` option one or more times to load specific issues:
-
-    $ github-to-sqlite issues github.db simonw/datasette --issue=1
-
-Example: [issues table](https://github-to-sqlite.dogsheep.net/github/issues)
-
-## Fetching pull requests for a repository
-
-While pull requests are a type of issue, you will get more information on pull requests by pulling them separately. For example, whether a pull request has been merged and when.
-
-Following the API of issues, the `pull-requests` command retrieves all of the pull requests belonging to a specified repository.
-
-    $ github-to-sqlite pull-requests github.db simonw/datasette
-
-You can use the `--pull-request` option one or more times to load specific pull request:
-
-    $ github-to-sqlite pull-requests github.db simonw/datasette --pull-request=81
-
-Note that the `merged_by` column on the `pull_requests` table will only be populated for pull requests that are loaded using the `--pull-request` option - the GitHub API does not return this field for pull requests that are loaded in bulk.
-
-You can load only pull requests in a certain state with the `--state` option:
-
-    $ github-to-sqlite pull-requests --state=open github.db simonw/datasette
-
-Pull requests across an entire organization (or more than one) can be loaded with `--org`:
-
-    $ github-to-sqlite pull-requests --state=open --org=psf --org=python github.db
-
-You can use a search query to find pull requests.  Note that no more than 1000 will be loaded (this is a GitHub API limitation), and some data will be missing (base and head SHAs).  When using searches, other filters are ignored; put all criteria into the search itself:
-
-    $ github-to-sqlite pull-requests --search='org:python defaultdict state:closed created:<2023-09-01' github.db
-
-Example: [pull_requests table](https://github-to-sqlite.dogsheep.net/github/pull_requests)
-
-## Fetching issue comments for a repository
-
-The `issue-comments` command retrieves all of the comments on all of the issues in a repository.
-
-It is recommended you run `issues` first, so that each imported comment can have a foreign key pointing to its issue.
-
-    $ github-to-sqlite issues github.db simonw/datasette
-    $ github-to-sqlite issue-comments github.db simonw/datasette
-
-You can use the `--issue` option to only load comments for a specific issue within that repository, for example:
-
-    $ github-to-sqlite issue-comments github.db simonw/datasette --issue=1
-
-Example: [issue_comments table](https://github-to-sqlite.dogsheep.net/github/issue_comments)
-
-## Fetching commits for a repository
-
-The `commits` command retrieves details of all of the commits for one or more repositories. It currently fetches the SHA, commit message and author and committer details; it does not retrieve the full commit body.
-
-    $ github-to-sqlite commits github.db simonw/datasette simonw/sqlite-utils
-
-The command accepts one or more repositories.
-
-By default it will stop as soon as it sees a commit that has previously been retrieved. You can force it to retrieve all commits (including those that have been previously inserted) using `--all`.
-
-Example: [commits table](https://github-to-sqlite.dogsheep.net/github/commits)
-
-## Fetching releases for a repository
-
-The `releases` command retrieves the releases for one or more repositories.
-
-    $ github-to-sqlite releases github.db simonw/datasette simonw/sqlite-utils
-
-The command accepts one or more repositories.
-
-Example: [releases table](https://github-to-sqlite.dogsheep.net/github/releases)
-
-## Fetching tags for a repository
-
-The `tags` command retrieves all of the tags for one or more repositories.
-
-    $ github-to-sqlite tags github.db simonw/datasette simonw/sqlite-utils
-
-Example: [tags table](https://github-to-sqlite.dogsheep.net/github/tags)
-
-## Fetching contributors to a repository
-
-The `contributors` command retrieves details of all of the contributors for one or more repositories.
-
-    $ github-to-sqlite contributors github.db simonw/datasette simonw/sqlite-utils
-
-The command accepts one or more repositories. It populates a `contributors` table, with foreign keys to `repos` and `users` and a `contributions` table listing the number of commits to that repository for each contributor.
-
-Example: [contributors table](https://github-to-sqlite.dogsheep.net/github/contributors)
-
-## Fetching repos belonging to a user or organization
-
-The `repos` command fetches repos belonging to a user or organization.
-
-Without any other arguments, this command will fetch all repos that the currently authenticated user owns, collaborates on or can access via one of their organizations:
-
-    $ github-to-sqlite repos github.db
-
-To fetch repos belonging to a specific user or organization, provide their username as an argument:
-
-    $ github-to-sqlite repos github.db dogsheep # organization
-    $ github-to-sqlite repos github.db simonw # user
-
-You can pass more than one username to fetch for multiple users or organizations at once:
-
-    $ github-to-sqlite repos github.db simonw dogsheep
-
-Add the `--readme` option to save the README for the repo in a column called `readme`. Add `--readme-html` to save the HTML rendered version of the README into a column called `readme_html`.
-
-Example: [repos table](https://github-to-sqlite.dogsheep.net/github/repos)
-
-## Fetching specific repositories
-
-You can use `-r` with the `repos` command one or more times to fetch just specific repositories.
-
-    $ github-to-sqlite repos github.db -r simonw/datasette -r dogsheep/github-to-sqlite
-
-## Fetching repos that have been starred by a user
-
-The `starred` command fetches the repos that have been starred by a user.
-
-    $ github-to-sqlite starred github.db simonw
-
-If you are using an `auth.json` file you can omit the username to retrieve the starred repos for the authenticated user.
-
-Example: [stars table](https://github-to-sqlite.dogsheep.net/github/stars)
-
-## Fetching users that have starred specific repos
-
-The `stargazers` command fetches the users that have starred the specified repos.
-
-    $ github-to-sqlite stargazers github.db simonw/datasette dogsheep/github-to-sqlite
-
-You can specify one or more repository using `owner/repo` syntax.
-
-Users fetched using this command will be inserted into the `users` table. Many-to-many records showing which repository they starred will be added to the `stars` table.
-
-## Fetching GitHub Actions workflows
-
-The `workflows` command fetches the YAML workflow configurations from each repository's `.github/workflows` directory and parses them to populate `workflows`, `jobs` and `steps` tables.
-
-    $ github-to-sqlite workflows github.db simonw/datasette dogsheep/github-to-sqlite
-
-You can specify one or more repository using `owner/repo` syntax.
-
-Example: [workflows table](https://github-to-sqlite.dogsheep.net/github/workflows), [jobs table](https://github-to-sqlite.dogsheep.net/github/jobs), [steps table](https://github-to-sqlite.dogsheep.net/github/steps)
-
-## Scraping dependents for a repository
-
-The GitHub dependency graph can show other GitHub projects that depend on a specific repo, for example [simonw/datasette/network/dependents](https://github.com/simonw/datasette/network/dependents).
-
-This data is not yet available through the GitHub API. The `scrape-dependents` command scrapes those pages and uses the GitHub API to load full versions of the dependent repositories.
-
-    $ github-to-sqlite scrape-dependents github.db simonw/datasette
-
-The command accepts one or more repositories.
-
-Add `-v` for verbose output.
-
-Example: [dependents table](https://github-to-sqlite.dogsheep.net/github/dependents?_sort_desc=first_seen_utc)
-
-## Fetching emojis
-
-You can fetch a list of every emoji supported by GitHub using the `emojis` command:
-
-    $ github-to-sqlite emojis github.db
-
-This will create a table called `emojis` with a primary key `name` and a `url` column.
-
-If you add the `--fetch` option the command will also fetch the binary content of the images and place them in an `image` column:
-
-    $ github-to-sqlite emojis emojis.db -f
-    [########----------------------------]  397/1799   22%  00:03:43
-
-You can then use the [datasette-render-images](https://github.com/simonw/datasette-render-images) plugin to browse them visually.
-
-Example: [emojis table](https://github-to-sqlite.dogsheep.net/github/emojis)
-
-## Making authenticated API calls
-
-The `github-to-sqlite get` command provides a convenient shortcut for making authenticated calls to the API. Once you have created your `auth.json` file (or set a `GITHUB_TOKEN` environment variable) you can use it like this:
-
-    $ github-to-sqlite get https://api.github.com/gists
-
-This will make an authenticated call to the URL you provide and pretty-print the resulting JSON to the console.
-
-You can omit the `https://api.github.com/` prefix, for example:
-
-    $ github-to-sqlite get /gists
-
-Many GitHub APIs are [paginated using the HTTP Link header](https://docs.github.com/en/rest/guides/traversing-with-pagination). You can follow this pagination and output a list of all of the resulting items using `--paginate`:
-
-    $ github-to-sqlite get /users/simonw/repos --paginate
-
-You can outline newline-delimited JSON for each item using `--nl`. This can be useful for streaming items into another tool.
-
-    $ github-to-sqlite get /users/simonw/repos --nl

github-to-sqlite-2.9/github_to_sqlite.egg-info/SOURCES.txt

@@ -1,25 +0,0 @@
-LICENSE
-README.md
-setup.py
-github_to_sqlite/__init__.py
-github_to_sqlite/cli.py
-github_to_sqlite/utils.py
-github_to_sqlite.egg-info/PKG-INFO
-github_to_sqlite.egg-info/SOURCES.txt
-github_to_sqlite.egg-info/dependency_links.txt
-github_to_sqlite.egg-info/entry_points.txt
-github_to_sqlite.egg-info/requires.txt
-github_to_sqlite.egg-info/top_level.txt
-tests/test_auth.py
-tests/test_commits.py
-tests/test_get.py
-tests/test_issue_comments.py
-tests/test_issues.py
-tests/test_pull_requests.py
-tests/test_releases.py
-tests/test_repos.py
-tests/test_scrape_dependents.py
-tests/test_stargazers.py
-tests/test_starred.py
-tests/test_tags.py
-tests/test_workflows.py

github-to-sqlite-2.9/github_to_sqlite.egg-info/dependency_links.txt

@@ -1 +0,0 @@
-

github-to-sqlite-2.9/github_to_sqlite.egg-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-github-to-sqlite = github_to_sqlite.cli:cli

github-to-sqlite-2.9/github_to_sqlite.egg-info/requires.txt

@@ -1,8 +0,0 @@
-sqlite-utils>=2.7.2
-requests
-PyYAML
-
-[test]
-pytest
-requests-mock
-bs4

github-to-sqlite-2.9/github_to_sqlite.egg-info/top_level.txt

@@ -1 +0,0 @@
-github_to_sqlite

github-to-sqlite-2.9/setup.cfg

@@ -1,4 +0,0 @@
-[egg_info]
-tag_build = 
-tag_date = 0
-

github-to-sqlite-2.9/setup.py

@@ -1,32 +0,0 @@
-from setuptools import setup
-import os
-
-VERSION = "2.9"
-
-
-def get_long_description():
-    with open(
-        os.path.join(os.path.dirname(os.path.abspath(__file__)), "README.md"),
-        encoding="utf8",
-    ) as fp:
-        return fp.read()
-
-
-setup(
-    name="github-to-sqlite",
-    description="Save data from GitHub to a SQLite database",
-    long_description=get_long_description(),
-    long_description_content_type="text/markdown",
-    author="Simon Willison",
-    url="https://github.com/dogsheep/github-to-sqlite",
-    license="Apache License, Version 2.0",
-    version=VERSION,
-    packages=["github_to_sqlite"],
-    entry_points="""
-        [console_scripts]
-        github-to-sqlite=github_to_sqlite.cli:cli
-    """,
-    install_requires=["sqlite-utils>=2.7.2", "requests", "PyYAML"],
-    extras_require={"test": ["pytest", "requests-mock", "bs4"]},
-    tests_require=["github-to-sqlite[test]"],
-)

github-to-sqlite-2.9/tests/test_auth.py

@@ -1,46 +0,0 @@
-from click.testing import CliRunner
-from github_to_sqlite import cli
-import json
-import os
-import pytest
-
-
-@pytest.fixture
-def mocked_starred(requests_mock):
-    requests_mock.get("https://api.github.com/user", json={"id": 1, "login": "test"})
-    m = requests_mock.get("https://api.github.com/user/starred", json=[])
-    return m
-
-
-def test_auth_command():
-    runner = CliRunner()
-    with runner.isolated_filesystem():
-        assert [] == os.listdir(".")
-        result = runner.invoke(cli.cli, ["auth"], input="zzz")
-        assert 0 == result.exit_code
-        assert ["auth.json"] == os.listdir(".")
-        assert {"github_personal_token": "zzz"} == json.load(open("auth.json"))
-
-
-def test_auth_file(mocked_starred):
-    runner = CliRunner()
-    with runner.isolated_filesystem():
-        open("auth.json", "w").write(json.dumps({"github_personal_token": "xxx"}))
-        result = runner.invoke(
-            cli.cli, ["starred", "starred.db"], catch_exceptions=False
-        )
-        assert 0 == result.exit_code
-        assert mocked_starred.called
-        assert "token xxx" == mocked_starred.last_request.headers["authorization"]
-
-
-def test_auth_environment_variable(mocked_starred, monkeypatch):
-    monkeypatch.setenv("GITHUB_TOKEN", "xyz")
-    runner = CliRunner()
-    with runner.isolated_filesystem():
-        result = runner.invoke(
-            cli.cli, ["starred", "starred.db"], catch_exceptions=False
-        )
-        assert 0 == result.exit_code
-        assert mocked_starred.called
-        assert "token xyz" == mocked_starred.last_request.headers["authorization"]

github-to-sqlite-2.9/tests/test_commits.py

@@ -1,89 +0,0 @@
-from github_to_sqlite import utils
-import pytest
-import pathlib
-import sqlite_utils
-from sqlite_utils.db import ForeignKey
-import json
-
-
-@pytest.fixture
-def commits():
-    return json.load(open(pathlib.Path(__file__).parent / "commits.json"))
-
-
-@pytest.fixture
-def repo():
-    return json.load(open(pathlib.Path(__file__).parent / "repo.json"))
-
-
-@pytest.fixture
-def db(commits, repo):
-    db = sqlite_utils.Database(memory=True)
-    utils.save_repo(db, repo)
-    utils.save_commits(db, commits, repo["id"])
-    return db
-
-
-def test_tables(db):
-    assert {"users", "commits", "raw_authors", "licenses", "repos"} == set(
-        db.table_names()
-    )
-    assert {
-        ForeignKey(
-            table="commits", column="committer", other_table="users", other_column="id"
-        ),
-        ForeignKey(
-            table="commits", column="author", other_table="users", other_column="id"
-        ),
-        ForeignKey(
-            table="commits",
-            column="raw_committer",
-            other_table="raw_authors",
-            other_column="id",
-        ),
-        ForeignKey(
-            table="commits",
-            column="raw_author",
-            other_table="raw_authors",
-            other_column="id",
-        ),
-        ForeignKey(
-            table="commits", column="repo", other_table="repos", other_column="id"
-        ),
-    } == set(db["commits"].foreign_keys)
-
-
-def test_commits(db):
-    commit_rows = list(db["commits"].rows)
-    raw_author_rows = list(db["raw_authors"].rows)
-    assert [
-        {
-            "sha": "9eb737090fafd0e5a7e314be48402374d99e9828",
-            "message": "Release 0.6",
-            "author_date": "2019-11-11T05:31:46Z",
-            "committer_date": "2019-11-11T05:31:46Z",
-            "raw_author": "13ae486343ea6454a93114c6f558ffea2f2c6874",
-            "raw_committer": "13ae486343ea6454a93114c6f558ffea2f2c6874",
-            "repo": 207052882,
-            "author": None,
-            "committer": None,
-        },
-        {
-            "sha": "1e6995a362e5b8f23331aafb84e631392eb81492",
-            "message": "--auth is now optional, closes #9",
-            "author_date": "2019-11-11T05:30:41Z",
-            "committer_date": "2019-11-11T05:30:41Z",
-            "raw_author": "13ae486343ea6454a93114c6f558ffea2f2c6874",
-            "raw_committer": "13ae486343ea6454a93114c6f558ffea2f2c6874",
-            "repo": 207052882,
-            "author": 9599,
-            "committer": 9599,
-        },
-    ] == commit_rows
-    assert [
-        {
-            "id": "13ae486343ea6454a93114c6f558ffea2f2c6874",
-            "name": "Simon Willison",
-            "email": "swillison@gmail.com",
-        }
-    ] == raw_author_rows