datasette-scan 0.1__tar.gz

datasette_scan-0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

datasette_scan-0.1/PKG-INFO

@@ -0,0 +1,120 @@
+Metadata-Version: 2.4
+Name: datasette-scan
+Version: 0.1
+Summary: Datasette plugin for scanning for SQLite files
+Author: Simon Willison
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/simonw/datasette-scan
+Project-URL: Changelog, https://github.com/simonw/datasette-scan/releases
+Project-URL: Issues, https://github.com/simonw/datasette-scan/issues
+Project-URL: CI, https://github.com/simonw/datasette-scan/actions
+Classifier: Framework :: Datasette
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: datasette
+Requires-Dist: sqlite-scanner>=0.1.1
+Dynamic: license-file
+
+# datasette-scan
+
+[![PyPI](https://img.shields.io/pypi/v/datasette-scan.svg)](https://pypi.org/project/datasette-scan/)
+[![Changelog](https://img.shields.io/github/v/release/simonw/datasette-scan?include_prereleases&label=changelog)](https://github.com/simonw/datasette-scan/releases)
+[![Tests](https://github.com/simonw/datasette-scan/actions/workflows/test.yml/badge.svg)](https://github.com/simonw/datasette-scan/actions/workflows/test.yml)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/datasette-scan/blob/main/LICENSE)
+
+Datasette plugin that scans directories for SQLite database files and serves them.
+
+## Installation
+
+Install this plugin in the same environment as Datasette.
+```bash
+datasette install datasette-scan
+```
+
+## Usage
+
+Scan the current directory for SQLite files and serve them:
+
+```bash
+datasette scan
+```
+
+Scan a specific directory:
+
+```bash
+datasette scan /path/to/directory
+```
+
+Scan multiple directories and include explicit database files:
+
+```bash
+datasette scan /data/projects /data/archives extra.db
+```
+
+Specify a port (or any other `datasette serve` option):
+
+```bash
+datasette scan -p 8001
+```
+
+All options accepted by `datasette serve` are also accepted by `datasette scan` -- these are introspected at runtime, so new options added to future versions of Datasette will be picked up automatically.
+
+### How it works
+
+- Positional arguments that are **directories** are scanned recursively for SQLite files using the [sqlite-scanner](https://pypi.org/project/sqlite-scanner/) binary, which identifies SQLite files by their magic bytes rather than file extension.
+- Positional arguments that are **files** are passed through directly as database files.
+- If no positional arguments are given, the current directory (`.`) is scanned.
+- Discovered files are then served as if you had run `datasette serve file1.db file2.db ...`.
+
+### Continuous scanning
+
+Use `--scan-interval` to periodically re-scan directories for new SQLite files while the server is running. New databases will be added automatically.
+
+```bash
+datasette scan /data --scan-interval 5
+```
+
+This re-scans every 5 seconds. Any new SQLite files that appear in the scanned directories will be added to the running Datasette instance without a restart.
+
+### Corrupted and locked files
+
+Since `datasette scan` discovers files automatically, it takes precautions against problematic databases:
+
+- **Corrupted files are skipped.** Each discovered file is validated by running `SELECT * FROM sqlite_master` before it is served. Files that fail this check are skipped with a warning to stderr.
+- **Locked files are handled safely.** Databases locked by another process are opened in read-only mode instead of causing the server to fail. (The `--nolock` option from `datasette serve` is always enabled and not exposed as a separate flag.)
+
+These protections apply to files discovered by scanning directories. Explicit file arguments are passed through to `datasette serve` without validation.
+
+### Examples
+
+Scan the current directory and open in a browser:
+
+```bash
+datasette scan -o
+```
+
+Scan with CORS enabled on a custom port:
+
+```bash
+datasette scan /data --cors -p 9000
+```
+
+Use `--get` to test without starting a server:
+
+```bash
+datasette scan /data --get /.json
+```
+
+## Development
+
+To set up this plugin locally, first checkout the code. You can confirm it is available like this:
+```bash
+cd datasette-scan
+# Confirm the plugin is visible
+uv run datasette plugins
+```
+To run the tests:
+```bash
+uv run pytest
+```

datasette_scan-0.1/README.md

@@ -0,0 +1,102 @@
+# datasette-scan
+
+[![PyPI](https://img.shields.io/pypi/v/datasette-scan.svg)](https://pypi.org/project/datasette-scan/)
+[![Changelog](https://img.shields.io/github/v/release/simonw/datasette-scan?include_prereleases&label=changelog)](https://github.com/simonw/datasette-scan/releases)
+[![Tests](https://github.com/simonw/datasette-scan/actions/workflows/test.yml/badge.svg)](https://github.com/simonw/datasette-scan/actions/workflows/test.yml)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/datasette-scan/blob/main/LICENSE)
+
+Datasette plugin that scans directories for SQLite database files and serves them.
+
+## Installation
+
+Install this plugin in the same environment as Datasette.
+```bash
+datasette install datasette-scan
+```
+
+## Usage
+
+Scan the current directory for SQLite files and serve them:
+
+```bash
+datasette scan
+```
+
+Scan a specific directory:
+
+```bash
+datasette scan /path/to/directory
+```
+
+Scan multiple directories and include explicit database files:
+
+```bash
+datasette scan /data/projects /data/archives extra.db
+```
+
+Specify a port (or any other `datasette serve` option):
+
+```bash
+datasette scan -p 8001
+```
+
+All options accepted by `datasette serve` are also accepted by `datasette scan` -- these are introspected at runtime, so new options added to future versions of Datasette will be picked up automatically.
+
+### How it works
+
+- Positional arguments that are **directories** are scanned recursively for SQLite files using the [sqlite-scanner](https://pypi.org/project/sqlite-scanner/) binary, which identifies SQLite files by their magic bytes rather than file extension.
+- Positional arguments that are **files** are passed through directly as database files.
+- If no positional arguments are given, the current directory (`.`) is scanned.
+- Discovered files are then served as if you had run `datasette serve file1.db file2.db ...`.
+
+### Continuous scanning
+
+Use `--scan-interval` to periodically re-scan directories for new SQLite files while the server is running. New databases will be added automatically.
+
+```bash
+datasette scan /data --scan-interval 5
+```
+
+This re-scans every 5 seconds. Any new SQLite files that appear in the scanned directories will be added to the running Datasette instance without a restart.
+
+### Corrupted and locked files
+
+Since `datasette scan` discovers files automatically, it takes precautions against problematic databases:
+
+- **Corrupted files are skipped.** Each discovered file is validated by running `SELECT * FROM sqlite_master` before it is served. Files that fail this check are skipped with a warning to stderr.
+- **Locked files are handled safely.** Databases locked by another process are opened in read-only mode instead of causing the server to fail. (The `--nolock` option from `datasette serve` is always enabled and not exposed as a separate flag.)
+
+These protections apply to files discovered by scanning directories. Explicit file arguments are passed through to `datasette serve` without validation.
+
+### Examples
+
+Scan the current directory and open in a browser:
+
+```bash
+datasette scan -o
+```
+
+Scan with CORS enabled on a custom port:
+
+```bash
+datasette scan /data --cors -p 9000
+```
+
+Use `--get` to test without starting a server:
+
+```bash
+datasette scan /data --get /.json
+```
+
+## Development
+
+To set up this plugin locally, first checkout the code. You can confirm it is available like this:
+```bash
+cd datasette-scan
+# Confirm the plugin is visible
+uv run datasette plugins
+```
+To run the tests:
+```bash
+uv run pytest
+```

datasette_scan-0.1/datasette_scan/__init__.py

@@ -0,0 +1,187 @@
+from datasette import hookimpl
+from datasette.database import Database
+import click
+import json
+import os
+import sqlite3
+import subprocess
+import sys
+import threading
+import time
+
+import sqlite_scanner
+
+
+def validate_databases(paths):
+    """Check each path is a readable SQLite database.
+
+    Returns (valid, skipped) where skipped is a list of (path, reason) tuples.
+    """
+    valid = []
+    skipped = []
+    for path in paths:
+        try:
+            conn = sqlite3.connect(f"file:{path}?mode=ro", uri=True)
+            try:
+                conn.execute("SELECT * FROM sqlite_master")
+                valid.append(path)
+            finally:
+                conn.close()
+        except Exception as e:
+            skipped.append((path, str(e)))
+    return valid, skipped
+
+
+def scan_directories(directories):
+    """Scan directories for SQLite files using the sqlite-scanner binary.
+
+    Returns a list of absolute paths to discovered SQLite files.
+    """
+    binary = sqlite_scanner.get_binary_path()
+    if not os.path.exists(binary):
+        raise click.ClickException(
+            f"sqlite-scanner binary not found at {binary}"
+        )
+    result = subprocess.run(
+        [binary, "--jsonl"] + list(directories),
+        capture_output=True,
+        text=True,
+    )
+    if result.returncode != 0:
+        raise click.ClickException(
+            f"sqlite-scanner failed: {result.stderr.strip()}"
+        )
+    paths = []
+    for line in result.stdout.strip().splitlines():
+        if line:
+            entry = json.loads(line)
+            paths.append(entry["path"])
+    return paths
+
+
+def rescan_and_add_databases(ds, directories, known_paths):
+    """Re-scan directories and add any newly discovered databases to Datasette.
+
+    Returns the updated set of known paths.
+    """
+    found = scan_directories(directories)
+    known_paths = set(known_paths)
+    for path in found:
+        if path not in known_paths:
+            db = Database(ds, path=path, is_mutable=True)
+            ds.add_database(db)
+            known_paths.add(path)
+    return known_paths
+
+
+def _background_scanner(ds, directories, known_paths, interval):
+    """Background thread that periodically re-scans for new databases."""
+    while True:
+        time.sleep(interval)
+        try:
+            known_paths = rescan_and_add_databases(ds, directories, known_paths)
+        except Exception as e:
+            click.echo(f"Scan error: {e}", err=True)
+
+
+@hookimpl
+def register_commands(cli):
+    serve_cmd = cli.commands.get("serve")
+
+    @cli.command()
+    @click.argument("paths", type=click.Path(), nargs=-1)
+    @click.option(
+        "--scan-interval",
+        type=float,
+        default=None,
+        help="Re-scan directories for new databases every N seconds",
+    )
+    def scan(paths, scan_interval, **kwargs):
+        """Scan directories for SQLite files and serve them with Datasette"""
+        if not paths:
+            paths = (".",)
+
+        # Separate files from directories
+        db_files = []
+        directories = []
+        for p in paths:
+            if os.path.isdir(p):
+                directories.append(p)
+            else:
+                db_files.append(p)
+
+        # Scan directories for SQLite files
+        scanned_files = []
+        if directories:
+            scanned_files = scan_directories(directories)
+
+        # Validate scanned files, skip corrupted ones
+        if scanned_files:
+            valid, skipped = validate_databases(scanned_files)
+            for path, reason in skipped:
+                click.echo(
+                    f"Skipping {path}: {reason}", err=True
+                )
+            db_files.extend(valid)
+
+        # Always use nolock for safety with discovered files
+        kwargs["nolock"] = True
+
+        if scan_interval is not None and directories:
+            # Continuous scanning mode: build and run the server ourselves
+            # so we can add databases to the running instance
+            known_paths = set(db_files)
+            ds = serve_cmd.callback(
+                files=tuple(db_files), return_instance=True, **kwargs
+            )
+            # Start background scanner thread
+            scanner_thread = threading.Thread(
+                target=_background_scanner,
+                args=(ds, directories, known_paths, scan_interval),
+                daemon=True,
+            )
+            scanner_thread.start()
+
+            # Handle --get: do the request and exit
+            get = kwargs.get("get")
+            if get:
+                from datasette.utils.testing import TestClient
+
+                client = TestClient(ds)
+                response = client.get(get)
+                click.echo(response.text)
+                sys.exit(0 if response.status == 200 else 1)
+
+            # Start the server
+            import uvicorn
+
+            host = kwargs.get("host", "127.0.0.1")
+            port = kwargs.get("port", 8001)
+            uvicorn_kwargs = dict(
+                host=host,
+                port=port,
+                log_level="info",
+                lifespan="on",
+                workers=1,
+            )
+            uds = kwargs.get("uds")
+            if uds:
+                uvicorn_kwargs["uds"] = uds
+            ssl_keyfile = kwargs.get("ssl_keyfile")
+            if ssl_keyfile:
+                uvicorn_kwargs["ssl_keyfile"] = ssl_keyfile
+            ssl_certfile = kwargs.get("ssl_certfile")
+            if ssl_certfile:
+                uvicorn_kwargs["ssl_certfile"] = ssl_certfile
+            uvicorn.run(ds.app(), **uvicorn_kwargs)
+        else:
+            # Simple mode: delegate to serve
+            ctx = click.get_current_context()
+            ctx.invoke(serve_cmd, files=tuple(db_files), **kwargs)
+
+    # Copy all options from serve to scan (but not arguments),
+    # excluding --nolock which is always enabled for scan
+    if serve_cmd:
+        for param in serve_cmd.params:
+            if isinstance(param, click.Option) and param.name != "nolock":
+                scan.params.append(param)

datasette_scan-0.1/datasette_scan.egg-info/PKG-INFO

@@ -0,0 +1,120 @@
+Metadata-Version: 2.4
+Name: datasette-scan
+Version: 0.1
+Summary: Datasette plugin for scanning for SQLite files
+Author: Simon Willison
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/simonw/datasette-scan
+Project-URL: Changelog, https://github.com/simonw/datasette-scan/releases
+Project-URL: Issues, https://github.com/simonw/datasette-scan/issues
+Project-URL: CI, https://github.com/simonw/datasette-scan/actions
+Classifier: Framework :: Datasette
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: datasette
+Requires-Dist: sqlite-scanner>=0.1.1
+Dynamic: license-file
+
+# datasette-scan
+
+[![PyPI](https://img.shields.io/pypi/v/datasette-scan.svg)](https://pypi.org/project/datasette-scan/)
+[![Changelog](https://img.shields.io/github/v/release/simonw/datasette-scan?include_prereleases&label=changelog)](https://github.com/simonw/datasette-scan/releases)
+[![Tests](https://github.com/simonw/datasette-scan/actions/workflows/test.yml/badge.svg)](https://github.com/simonw/datasette-scan/actions/workflows/test.yml)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/datasette-scan/blob/main/LICENSE)
+
+Datasette plugin that scans directories for SQLite database files and serves them.
+
+## Installation
+
+Install this plugin in the same environment as Datasette.
+```bash
+datasette install datasette-scan
+```
+
+## Usage
+
+Scan the current directory for SQLite files and serve them:
+
+```bash
+datasette scan
+```
+
+Scan a specific directory:
+
+```bash
+datasette scan /path/to/directory
+```
+
+Scan multiple directories and include explicit database files:
+
+```bash
+datasette scan /data/projects /data/archives extra.db
+```
+
+Specify a port (or any other `datasette serve` option):
+
+```bash
+datasette scan -p 8001
+```
+
+All options accepted by `datasette serve` are also accepted by `datasette scan` -- these are introspected at runtime, so new options added to future versions of Datasette will be picked up automatically.
+
+### How it works
+
+- Positional arguments that are **directories** are scanned recursively for SQLite files using the [sqlite-scanner](https://pypi.org/project/sqlite-scanner/) binary, which identifies SQLite files by their magic bytes rather than file extension.
+- Positional arguments that are **files** are passed through directly as database files.
+- If no positional arguments are given, the current directory (`.`) is scanned.
+- Discovered files are then served as if you had run `datasette serve file1.db file2.db ...`.
+
+### Continuous scanning
+
+Use `--scan-interval` to periodically re-scan directories for new SQLite files while the server is running. New databases will be added automatically.
+
+```bash
+datasette scan /data --scan-interval 5
+```
+
+This re-scans every 5 seconds. Any new SQLite files that appear in the scanned directories will be added to the running Datasette instance without a restart.
+
+### Corrupted and locked files
+
+Since `datasette scan` discovers files automatically, it takes precautions against problematic databases:
+
+- **Corrupted files are skipped.** Each discovered file is validated by running `SELECT * FROM sqlite_master` before it is served. Files that fail this check are skipped with a warning to stderr.
+- **Locked files are handled safely.** Databases locked by another process are opened in read-only mode instead of causing the server to fail. (The `--nolock` option from `datasette serve` is always enabled and not exposed as a separate flag.)
+
+These protections apply to files discovered by scanning directories. Explicit file arguments are passed through to `datasette serve` without validation.
+
+### Examples
+
+Scan the current directory and open in a browser:
+
+```bash
+datasette scan -o
+```
+
+Scan with CORS enabled on a custom port:
+
+```bash
+datasette scan /data --cors -p 9000
+```
+
+Use `--get` to test without starting a server:
+
+```bash
+datasette scan /data --get /.json
+```
+
+## Development
+
+To set up this plugin locally, first checkout the code. You can confirm it is available like this:
+```bash
+cd datasette-scan
+# Confirm the plugin is visible
+uv run datasette plugins
+```
+To run the tests:
+```bash
+uv run pytest
+```

datasette_scan-0.1/datasette_scan.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+LICENSE
+README.md
+pyproject.toml
+datasette_scan/__init__.py
+datasette_scan.egg-info/PKG-INFO
+datasette_scan.egg-info/SOURCES.txt
+datasette_scan.egg-info/dependency_links.txt
+datasette_scan.egg-info/entry_points.txt
+datasette_scan.egg-info/requires.txt
+datasette_scan.egg-info/top_level.txt
+tests/test_scan.py

datasette_scan-0.1/datasette_scan.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

datasette_scan-0.1/datasette_scan.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[datasette]
+scan = datasette_scan

datasette_scan-0.1/datasette_scan.egg-info/requires.txt

@@ -0,0 +1,2 @@
+datasette
+sqlite-scanner>=0.1.1

datasette_scan-0.1/datasette_scan.egg-info/top_level.txt

@@ -0,0 +1 @@
+datasette_scan

datasette_scan-0.1/pyproject.toml

@@ -0,0 +1,40 @@
+[project]
+name = "datasette-scan"
+version = "0.1"
+description = "Datasette plugin for scanning for SQLite files"
+readme = "README.md"
+authors = [{name = "Simon Willison"}]
+license = "Apache-2.0"
+classifiers=[
+    "Framework :: Datasette"
+]
+requires-python = ">=3.10"
+dependencies = [
+    "datasette",
+    "sqlite-scanner>=0.1.1"
+]
+
+[dependency-groups]
+dev = [
+    "pytest",
+    "pytest-asyncio"
+]
+
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+
+[project.urls]
+Homepage = "https://github.com/simonw/datasette-scan"
+Changelog = "https://github.com/simonw/datasette-scan/releases"
+Issues = "https://github.com/simonw/datasette-scan/issues"
+CI = "https://github.com/simonw/datasette-scan/actions"
+
+[project.entry-points.datasette]
+scan = "datasette_scan"
+
+[tool.pytest.ini_options]
+asyncio_mode = "strict"
+asyncio_default_fixture_loop_scope = "function"
+

datasette_scan-0.1/setup.cfg

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

datasette_scan-0.1/tests/test_scan.py

@@ -0,0 +1,312 @@
+import click
+from click.testing import CliRunner
+from datasette.app import Datasette
+from datasette.cli import cli
+from datasette_scan import scan_directories, rescan_and_add_databases, validate_databases
+import json
+import os
+import pytest
+import sqlite3
+import tempfile
+from pathlib import Path
+from unittest.mock import patch
+
+
+@pytest.fixture
+def tmp_with_dbs(tmp_path):
+    """Create a temp directory with some SQLite databases."""
+    db1 = tmp_path / "one.db"
+    db2 = tmp_path / "subdir" / "two.db"
+    db2.parent.mkdir()
+    for db_path in (db1, db2):
+        conn = sqlite3.connect(str(db_path))
+        conn.execute("CREATE TABLE t (id INTEGER PRIMARY KEY)")
+        conn.close()
+    # Non-SQLite file
+    (tmp_path / "not_a_db.txt").write_text("hello")
+    return tmp_path
+
+
+@pytest.mark.asyncio
+async def test_plugin_is_installed():
+    datasette = Datasette(memory=True)
+    response = await datasette.client.get("/-/plugins.json")
+    assert response.status_code == 200
+    installed_plugins = {p["name"] for p in response.json()}
+    assert "datasette-scan" in installed_plugins
+
+
+def test_scan_command_exists():
+    runner = CliRunner()
+    result = runner.invoke(cli, ["scan", "--help"])
+    assert result.exit_code == 0
+    assert "Usage: cli scan" in result.output
+
+
+def test_scan_has_serve_options():
+    """scan should have all of serve's options (except nolock, always enabled)."""
+    serve_cmd = cli.commands["serve"]
+    scan_cmd = cli.commands["scan"]
+    serve_option_names = {
+        p.name for p in serve_cmd.params if isinstance(p, click.Option)
+    }
+    scan_option_names = {
+        p.name for p in scan_cmd.params if isinstance(p, click.Option)
+    }
+    # All serve options except nolock should be present on scan
+    # nolock is always enabled for scan and not exposed as an option
+    missing = serve_option_names - scan_option_names - {"nolock"}
+    assert not missing, f"scan is missing these serve options: {missing}"
+
+
+def test_scan_has_scan_interval_option():
+    """scan should have the --scan-interval option that serve doesn't."""
+    scan_cmd = cli.commands["scan"]
+    scan_option_names = {
+        p.name for p in scan_cmd.params if isinstance(p, click.Option)
+    }
+    assert "scan_interval" in scan_option_names
+
+
+def test_scan_directories_finds_sqlite_files(tmp_with_dbs):
+    """scan_directories should find SQLite files using the sqlite-scanner binary."""
+    found = scan_directories([str(tmp_with_dbs)])
+    found_names = {Path(f).name for f in found}
+    assert "one.db" in found_names
+    assert "two.db" in found_names
+    assert "not_a_db.txt" not in found_names
+
+
+def test_scan_default_scans_current_directory(tmp_with_dbs):
+    """With no args, scan should scan the current directory."""
+    runner = CliRunner()
+    result = runner.invoke(
+        cli, ["scan", "--get", "/.json"], catch_exceptions=False
+    )
+    # We just need it to not error - with no SQLite in cwd it may serve
+    # empty but should not crash
+    assert result.exit_code == 0
+
+
+def test_scan_serves_discovered_files(tmp_with_dbs):
+    """scan should discover files and serve them via Datasette."""
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        ["scan", str(tmp_with_dbs), "--get", "/.json"],
+        catch_exceptions=False,
+    )
+    assert result.exit_code == 0
+    data = json.loads(result.output)
+    db_names = set(data.keys())
+    assert "one" in db_names
+    assert "two" in db_names
+
+
+def test_scan_explicit_file_args(tmp_with_dbs):
+    """Explicit file arguments should be passed through directly."""
+    db_path = str(tmp_with_dbs / "one.db")
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        ["scan", db_path, "--get", "/.json"],
+        catch_exceptions=False,
+    )
+    assert result.exit_code == 0
+    data = json.loads(result.output)
+    assert "one" in data
+
+
+def test_scan_mixed_files_and_dirs(tmp_with_dbs):
+    """Mix of explicit files and directories should work."""
+    # Create an extra database outside the scanned dir
+    extra_db = tmp_with_dbs / "extra" / "standalone.db"
+    extra_db.parent.mkdir()
+    conn = sqlite3.connect(str(extra_db))
+    conn.execute("CREATE TABLE t (id INTEGER PRIMARY KEY)")
+    conn.close()
+
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        [
+            "scan",
+            str(tmp_with_dbs / "subdir"),  # directory - will find two.db
+            str(extra_db),  # explicit file
+            "--get",
+            "/.json",
+        ],
+        catch_exceptions=False,
+    )
+    assert result.exit_code == 0
+    data = json.loads(result.output)
+    db_names = set(data.keys())
+    assert "two" in db_names
+    assert "standalone" in db_names
+    # one.db should NOT be found since we only scanned subdir
+    assert "one" not in db_names
+
+
+def test_scan_error_when_binary_missing():
+    """Should raise a clear error if sqlite-scanner binary isn't found."""
+    with patch("datasette_scan.sqlite_scanner.get_binary_path") as mock_path:
+        mock_path.return_value = "/nonexistent/sqlite-scanner"
+        runner = CliRunner()
+        result = runner.invoke(cli, ["scan", "--get", "/.json"])
+        assert result.exit_code != 0
+        assert "sqlite-scanner" in result.output.lower() or "Error" in result.output
+
+
+def test_scan_passes_port_option(tmp_with_dbs):
+    """Serve options like --port should be passed through."""
+    runner = CliRunner()
+    # Using --get bypasses actual server start, but port is still accepted
+    result = runner.invoke(
+        cli,
+        ["scan", str(tmp_with_dbs), "-p", "9999", "--get", "/.json"],
+        catch_exceptions=False,
+    )
+    assert result.exit_code == 0
+
+
+@pytest.mark.asyncio
+async def test_rescan_adds_new_databases(tmp_with_dbs):
+    """rescan_and_add_databases should add newly discovered files to Datasette."""
+    # Start with one.db already known
+    db1 = str(tmp_with_dbs / "one.db")
+    ds = Datasette([db1])
+    known = {db1}
+    initial_db_count = len(ds.databases)
+
+    # Rescan should find two.db and add it
+    known = rescan_and_add_databases(ds, [str(tmp_with_dbs)], known)
+    assert len(ds.databases) > initial_db_count
+    db_names = set(ds.databases.keys())
+    assert "two" in db_names
+
+    # The new file should now be in known
+    two_path = str(tmp_with_dbs / "subdir" / "two.db")
+    assert two_path in known
+
+
+@pytest.mark.asyncio
+async def test_rescan_does_not_duplicate(tmp_with_dbs):
+    """rescan_and_add_databases should not re-add already known files."""
+    ds = Datasette([])
+    known = set()
+
+    # First scan adds files
+    known = rescan_and_add_databases(ds, [str(tmp_with_dbs)], known)
+    count_after_first = len(ds.databases)
+
+    # Second scan should not add duplicates
+    known = rescan_and_add_databases(ds, [str(tmp_with_dbs)], known)
+    assert len(ds.databases) == count_after_first
+
+
+def test_validate_databases_accepts_good_files(tmp_with_dbs):
+    """validate_databases should accept valid SQLite files."""
+    paths = [
+        str(tmp_with_dbs / "one.db"),
+        str(tmp_with_dbs / "subdir" / "two.db"),
+    ]
+    valid, skipped = validate_databases(paths)
+    assert valid == paths
+    assert skipped == []
+
+
+def test_validate_databases_skips_corrupted(tmp_path):
+    """validate_databases should skip corrupted SQLite files."""
+    good = tmp_path / "good.db"
+    conn = sqlite3.connect(str(good))
+    conn.execute("CREATE TABLE t (id INTEGER PRIMARY KEY)")
+    conn.close()
+
+    corrupted = tmp_path / "corrupted.db"
+    data = bytearray(good.read_bytes())
+    for i in range(100, 200):
+        data[i] = 0xFF
+    corrupted.write_bytes(data)
+
+    valid, skipped = validate_databases([str(good), str(corrupted)])
+    assert valid == [str(good)]
+    assert len(skipped) == 1
+    assert skipped[0][0] == str(corrupted)
+    assert "malformed" in skipped[0][1].lower() or "error" in skipped[0][1].lower()
+
+
+def test_validate_databases_skips_truncated(tmp_path):
+    """validate_databases should skip truncated SQLite files."""
+    truncated = tmp_path / "truncated.db"
+    truncated.write_bytes(b"SQLite format 3\x00" + b"\x00" * 84)
+
+    valid, skipped = validate_databases([str(truncated)])
+    assert valid == []
+    assert len(skipped) == 1
+
+
+def test_scan_skips_corrupted_and_serves_good(tmp_path):
+    """scan should skip corrupted files and serve only valid ones."""
+    good = tmp_path / "good.db"
+    conn = sqlite3.connect(str(good))
+    conn.execute("CREATE TABLE t (id INTEGER PRIMARY KEY)")
+    conn.close()
+
+    corrupted = tmp_path / "corrupted.db"
+    data = bytearray(good.read_bytes())
+    for i in range(100, 200):
+        data[i] = 0xFF
+    corrupted.write_bytes(data)
+
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        ["scan", str(tmp_path), "--get", "/.json"],
+        catch_exceptions=False,
+    )
+    assert result.exit_code == 0
+    # Output may contain warning lines before the JSON; extract JSON part
+    lines = result.output.strip().splitlines()
+    json_lines = [l for l in lines if not l.startswith("Skipping ")]
+    data = json.loads("\n".join(json_lines))
+    assert "good" in data
+    assert "corrupted" not in data
+
+
+def test_scan_warns_about_skipped_files(tmp_path):
+    """scan should print warnings about skipped files."""
+    good = tmp_path / "good.db"
+    conn = sqlite3.connect(str(good))
+    conn.execute("CREATE TABLE t (id INTEGER PRIMARY KEY)")
+    conn.close()
+
+    corrupted = tmp_path / "corrupted.db"
+    data = bytearray(good.read_bytes())
+    for i in range(100, 200):
+        data[i] = 0xFF
+    corrupted.write_bytes(data)
+
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        ["scan", str(tmp_path), "--get", "/.json"],
+    )
+    assert result.exit_code == 0
+    assert "corrupted.db" in result.output
+    assert "Skipping" in result.output
+
+
+def test_scan_defaults_nolock(tmp_with_dbs):
+    """scan should pass --nolock by default to handle locked databases."""
+    # We can verify this by checking that the nolock kwarg is True
+    # when delegated to serve. We'll test indirectly: scan a directory
+    # and confirm it works (nolock doesn't break anything for unlocked files).
+    runner = CliRunner()
+    result = runner.invoke(
+        cli,
+        ["scan", str(tmp_with_dbs), "--get", "/.json"],
+        catch_exceptions=False,
+    )
+    assert result.exit_code == 0
+    data = json.loads(result.output)
+    assert "one" in data