Compare commits

..

4 commits

Author SHA1 Message Date
Simon Willison
693f4ed601 Show insert message in correct place, 1s inactive delay
Since I want this to be usable by untrusted datasette-apps it is important that
they cannot show the dialog in a way that tricks the user into clicking insert.

So a 1s delay on making that button active.
2026-06-20 12:23:52 -07:00
Simon Willison
76e6a3bc38 New .insertDialog() JavaScript method
Anywhere in Datasette can now open an insert dialog
pre-populated with suggested data.

Using it in one place already, on the row page
to provide an insert button for related rows.
2026-06-19 23:40:15 -07:00
Simon Willison
f3fa6ecf61 Render error pages using datasette.render_template()
Avoids risk of important variables not being present.
2026-06-19 23:38:50 -07:00
Simon Willison
a76646e3fd GET /db/table/-/insert returns data needed for dialog
As part of making the insert dialog less dependent on the table page.
2026-06-19 22:51:21 -07:00
215 changed files with 5906 additions and 25241 deletions

View file

@ -1,39 +0,0 @@
name: "Setup SQLite version"
description: "Build and activate a specific SQLite version from its amalgamation archive"
inputs:
version:
description: "The SQLite version to install"
required: true
cflags:
description: "CFLAGS to use when compiling SQLite"
required: false
default: ""
skip-activate:
description: "Set to true to skip modifying the library path"
required: false
default: "false"
fallback-urls:
description: "Whitespace-separated fallback download URLs to try after sqlite.org"
required: false
default: ""
outputs:
sqlite-location:
description: "Directory containing the compiled SQLite library"
value: ${{ steps.build.outputs.sqlite-location }}
runs:
using: "composite"
steps:
- shell: bash
run: mkdir -p "$RUNNER_TEMP/sqlite-versions/downloads"
- uses: actions/cache@v6
with:
path: ${{ runner.temp }}/sqlite-versions/downloads
key: setup-sqlite-version-${{ inputs.version }}-amalgamation-v1
- id: build
shell: bash
run: bash "$GITHUB_ACTION_PATH/setup-sqlite-version.sh"
env:
SQLITE_VERSION: ${{ inputs.version }}
SQLITE_CFLAGS: ${{ inputs.cflags }}
SQLITE_SKIP_ACTIVATE: ${{ inputs.skip-activate }}
SQLITE_EXTRA_FALLBACK_URLS: ${{ inputs.fallback-urls }}

View file

@ -1,144 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
version_spec="${SQLITE_VERSION:?SQLITE_VERSION is required}"
cflags="${SQLITE_CFLAGS:-}"
skip_activate="${SQLITE_SKIP_ACTIVATE:-false}"
extra_fallback_urls="${SQLITE_EXTRA_FALLBACK_URLS:-}"
case "$version_spec" in
3.46 | 3.46.0)
sqlite_version="3.46.0"
sqlite_year="2024"
amalgamation_id="3460000"
builtin_fallback_urls="https://static.simonwillison.net/static/2026/sqlite-amalgamation-3460000.zip"
;;
3.25 | 3.25.0)
sqlite_version="3.25.0"
sqlite_year="2018"
amalgamation_id="3250000"
builtin_fallback_urls="https://static.simonwillison.net/static/2026/sqlite-amalgamation-3250000.zip?v=1"
;;
*)
echo "::error::Unsupported SQLite version '$version_spec'. Add its release year and amalgamation id to $GITHUB_ACTION_PATH/setup-sqlite-version.sh."
exit 1
;;
esac
case "$(uname -s)" in
Linux)
library_name="libsqlite3.so.0"
library_path_var="LD_LIBRARY_PATH"
;;
Darwin)
library_name="libsqlite3.dylib"
library_path_var="DYLD_LIBRARY_PATH"
;;
*)
echo "::error::Unsupported platform $(uname -s)"
exit 1
;;
esac
runner_temp="${RUNNER_TEMP:-}"
if [ -z "$runner_temp" ]; then
runner_temp="$(mktemp -d)"
fi
filename="sqlite-amalgamation-${amalgamation_id}"
official_url="https://www.sqlite.org/${sqlite_year}/${filename}.zip"
download_dir="${runner_temp}/sqlite-versions/downloads"
source_root="${runner_temp}/sqlite-versions/source"
source_dir="${source_root}/${filename}"
build_dir="${runner_temp}/sqlite-versions/build/${sqlite_version}"
archive_path="${download_dir}/${filename}.zip"
mkdir -p "$download_dir" "$source_root" "$build_dir"
download_archive() {
local url
local candidate_path="${archive_path}.tmp"
local urls=("$official_url")
for url in $builtin_fallback_urls $extra_fallback_urls; do
urls+=("$url")
done
rm -f "$candidate_path"
for url in "${urls[@]}"; do
echo "Downloading SQLite ${sqlite_version} amalgamation from ${url}"
if curl \
--fail \
--location \
--show-error \
--retry 5 \
--retry-delay 2 \
--retry-max-time 180 \
--retry-all-errors \
--connect-timeout 20 \
--max-time 240 \
--output "$candidate_path" \
"$url"; then
mv "$candidate_path" "$archive_path"
return 0
fi
echo "::warning::Download failed from ${url}"
rm -f "$candidate_path"
done
echo "::error::Could not download SQLite ${sqlite_version} amalgamation"
return 1
}
if [ ! -f "${source_dir}/sqlite3.c" ]; then
if [ ! -f "$archive_path" ]; then
download_archive
fi
rm -rf "$source_dir"
unzip -q "$archive_path" -d "$source_root"
fi
if [ ! -f "${source_dir}/sqlite3.c" ]; then
echo "::error::Expected ${source_dir}/sqlite3.c after extracting ${archive_path}"
exit 1
fi
read -r -a cflag_args <<< "$cflags"
echo "Compiling SQLite ${sqlite_version} to ${build_dir}/${library_name}"
gcc \
-fPIC \
-shared \
"${cflag_args[@]}" \
"${source_dir}/sqlite3.c" \
"-I${source_dir}" \
-o "${build_dir}/${library_name}"
if [ "$library_name" = "libsqlite3.so.0" ]; then
ln -sf "$library_name" "${build_dir}/libsqlite3.so"
fi
if [ -n "${GITHUB_OUTPUT:-}" ]; then
echo "sqlite-location=${build_dir}" >> "$GITHUB_OUTPUT"
else
echo "sqlite-location=${build_dir}"
fi
case "$(printf '%s' "$skip_activate" | tr '[:upper:]' '[:lower:]')" in
true | 1 | yes)
echo "Skipping ${library_path_var} activation"
;;
*)
existing_value="${!library_path_var:-}"
if [ -n "${GITHUB_ENV:-}" ]; then
if [ -n "$existing_value" ]; then
echo "${library_path_var}=${build_dir}:${existing_value}" >> "$GITHUB_ENV"
else
echo "${library_path_var}=${build_dir}" >> "$GITHUB_ENV"
fi
fi
echo "Added ${build_dir} to ${library_path_var}"
;;
esac

View file

@ -14,46 +14,24 @@ jobs:
deploy:
runs-on: ubuntu-latest
steps:
- name: Check deployment prerequisites
id: deployment-prerequisites
env:
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
LATEST_DATASETTE_SECRET: ${{ secrets.LATEST_DATASETTE_SECRET }}
run: |
missing=()
for variable in GCP_SA_KEY LATEST_DATASETTE_SECRET; do
if [[ -z "${!variable:-}" ]]; then
missing+=("$variable")
fi
done
if (( ${#missing[@]} )); then
echo "::notice::Skipping deployment because required environment variables are missing: ${missing[*]}"
echo "available=false" >> "$GITHUB_OUTPUT"
else
echo "available=true" >> "$GITHUB_OUTPUT"
fi
- name: Check out datasette
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
uses: actions/checkout@v7
uses: actions/checkout@v6
- name: Set up Python
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
uses: actions/setup-python@v6
with:
python-version: "3.13"
cache: pip
- name: Install Python dependencies
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
run: |
python -m pip install --upgrade pip
python -m pip install . --group dev
python -m pip install sphinx-to-sqlite==0.1a1 "s3-credentials>=0.17"
python -m pip install sphinx-to-sqlite==0.1a1
- name: Run tests
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' && github.ref == 'refs/heads/main' }}
if: ${{ github.ref == 'refs/heads/main' }}
run: |
pytest -n auto -m "not serial"
pytest -m "serial"
- name: Build fixtures.db and other files needed to deploy the demo
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
run: |-
python tests/fixtures.py \
fixtures.db \
@ -62,14 +40,13 @@ jobs:
plugins \
--extra-db-filename extra_database.db
- name: Build docs.db
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' && github.ref == 'refs/heads/main' }}
if: ${{ github.ref == 'refs/heads/main' }}
run: |-
cd docs
DISABLE_SPHINX_INLINE_TABS=1 sphinx-build -b xml . _build
sphinx-to-sqlite ../docs.db _build
cd ..
- name: Set up the alternate-route demo
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
run: |
echo '
from datasette import hookimpl
@ -81,7 +58,6 @@ jobs:
' > plugins/alternative_route.py
cp fixtures.db fixtures2.db
- name: And the counters writable stored query demo
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
run: |
cat > plugins/counters.py <<EOF
from datasette import hookimpl
@ -121,15 +97,12 @@ jobs:
# cat metadata.json
- id: auth
name: Authenticate to Google Cloud
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
uses: google-github-actions/auth@v3
with:
credentials_json: ${{ secrets.GCP_SA_KEY }}
- name: Set up Cloud SDK
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
uses: google-github-actions/setup-gcloud@v3
- name: Deploy to Cloud Run
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' }}
env:
LATEST_DATASETTE_SECRET: ${{ secrets.LATEST_DATASETTE_SECRET }}
run: |-
@ -148,12 +121,12 @@ jobs:
--install 'datasette-ephemeral-tables>=0.2.2' \
--service "datasette-latest$SUFFIX" \
--secret $LATEST_DATASETTE_SECRET
- name: Upload latest documentation database to S3 (only for main)
if: ${{ steps.deployment-prerequisites.outputs.available == 'true' && github.ref == 'refs/heads/main' }}
env:
AWS_ACCESS_KEY_ID: ${{ secrets.S3_DATASETTE_DOCS_ACCESS_KEY }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.S3_DATASETTE_DOCS_SECRET_KEY }}
- name: Deploy to docs as well (only for main)
if: ${{ github.ref == 'refs/heads/main' }}
run: |-
# Keep development documentation separate from the stable release database.
s3-credentials put-object datasette-docs latest/docs.db docs.db \
--content-type application/octet-stream
# Deploy docs.db to a different service
datasette publish cloudrun docs.db \
--branch=$GITHUB_SHA \
--version-note=$GITHUB_SHA \
--extra-options="--setting template_debug 1" \
--service=datasette-docs-latest

View file

@ -0,0 +1,16 @@
name: Read the Docs Pull Request Preview
on:
pull_request:
types:
- opened
permissions:
pull-requests: write
jobs:
documentation-links:
runs-on: ubuntu-latest
steps:
- uses: readthedocs/actions/preview@v1
with:
project-slug: "datasette"

View file

@ -16,7 +16,7 @@ jobs:
matrix:
browser: [chromium, firefox, webkit]
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python 3.14
uses: actions/setup-python@v6
with:
@ -25,14 +25,14 @@ jobs:
cache: pip
cache-dependency-path: pyproject.toml
- name: Cache uv
uses: actions/cache@v6
uses: actions/cache@v5
with:
path: ~/.cache/uv
key: ${{ runner.os }}-py3.14-uv-${{ hashFiles('pyproject.toml') }}
restore-keys: |
${{ runner.os }}-py3.14-uv-
- name: Cache Playwright browsers
uses: actions/cache@v6
uses: actions/cache@v5
with:
path: ~/.cache/ms-playwright/
key: ${{ runner.os }}-playwright-${{ matrix.browser }}-${{ hashFiles('pyproject.toml') }}

View file

@ -10,8 +10,8 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Check out repo
uses: actions/checkout@v7
- uses: actions/cache@v6
uses: actions/checkout@v6
- uses: actions/cache@v5
name: Configure npm caching
with:
path: ~/.npm

View file

@ -2,7 +2,7 @@ name: Publish Python Package
on:
release:
types: [published]
types: [created]
permissions:
contents: read
@ -14,7 +14,7 @@ jobs:
matrix:
python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v6
with:
@ -35,7 +35,7 @@ jobs:
permissions:
id-token: write
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:
@ -51,14 +51,12 @@ jobs:
- name: Publish
uses: pypa/gh-action-pypi-publish@release/v1
# After the first non-prerelease 1.0 release, disable this job on 0.65.x,
# even for later 0.65 releases, so they cannot overwrite the 1.0 stable docs.
deploy_static_docs:
runs-on: ubuntu-latest
needs: [deploy]
if: "!github.event.release.prerelease"
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:
@ -68,27 +66,33 @@ jobs:
- name: Install dependencies
run: |
python -m pip install . --group dev
python -m pip install sphinx-to-sqlite==0.1a1 "s3-credentials>=0.17"
python -m pip install sphinx-to-sqlite==0.1a1
- name: Build docs.db
run: |-
cd docs
DISABLE_SPHINX_INLINE_TABS=1 sphinx-build -b xml . _build
sphinx-to-sqlite ../docs.db _build
cd ..
- name: Upload stable documentation database to S3
env:
AWS_ACCESS_KEY_ID: ${{ secrets.S3_DATASETTE_DOCS_ACCESS_KEY }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.S3_DATASETTE_DOCS_SECRET_KEY }}
- id: auth
name: Authenticate to Google Cloud
uses: google-github-actions/auth@v2
with:
credentials_json: ${{ secrets.GCP_SA_KEY }}
- name: Set up Cloud SDK
uses: google-github-actions/setup-gcloud@v3
- name: Deploy stable-docs.datasette.io to Cloud Run
run: |-
s3-credentials put-object datasette-docs docs.db docs.db \
--content-type application/octet-stream
gcloud config set run/region us-central1
gcloud config set project datasette-222320
datasette publish cloudrun docs.db \
--service=datasette-docs-stable
deploy_docker:
runs-on: ubuntu-latest
needs: [deploy]
if: "!github.event.release.prerelease"
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Build and push to Docker Hub
env:
DOCKER_USER: ${{ secrets.DOCKER_USER }}

View file

@ -13,7 +13,7 @@ jobs:
deploy_docker:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Build and push to Docker Hub
env:
DOCKER_USER: ${{ secrets.DOCKER_USER }}

View file

@ -9,7 +9,7 @@ jobs:
spellcheck:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:

View file

@ -15,7 +15,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v7
uses: actions/checkout@v6
with:
fetch-depth: 0 # We need all commits to find docs/ changes
- name: Set up Git user

View file

@ -15,7 +15,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Check out datasette
uses: actions/checkout@v7
uses: actions/checkout@v6
- name: Set up Python
uses: actions/setup-python@v6
with:

View file

@ -12,7 +12,7 @@ jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python 3.10
uses: actions/setup-python@v6
with:
@ -20,7 +20,7 @@ jobs:
cache: 'pip'
cache-dependency-path: '**/pyproject.toml'
- name: Cache Playwright browsers
uses: actions/cache@v6
uses: actions/cache@v5
with:
path: ~/.cache/ms-playwright/
key: ${{ runner.os }}-browsers

View file

@ -25,7 +25,7 @@ jobs:
#"3.23.1" # 2018-04-10, before UPSERT
]
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v6
with:
@ -34,7 +34,7 @@ jobs:
cache: pip
cache-dependency-path: pyproject.toml
- name: Set up SQLite ${{ matrix.sqlite-version }}
uses: ./.github/actions/setup-sqlite-version
uses: asg017/sqlite-versions@71ea0de37ae739c33e447af91ba71dda8fcf22e6
with:
version: ${{ matrix.sqlite-version }}
cflags: "-DSQLITE_ENABLE_DESERIALIZE -DSQLITE_ENABLE_FTS5 -DSQLITE_ENABLE_FTS4 -DSQLITE_ENABLE_FTS3_PARENTHESIS -DSQLITE_ENABLE_RTREE -DSQLITE_ENABLE_JSON1"

View file

@ -9,19 +9,17 @@ jobs:
test:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: ["3.10", "3.11", "3.12", "3.13", "3.14", "3.15"]
python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v7
uses: actions/setup-python@v6
with:
python-version: ${{ matrix.python-version }}
allow-prereleases: true
cache: pip
cache-dependency-path: pyproject.toml
check-latest: true
- name: Build extension for --load-extension test
run: |-
(cd tests && gcc ext.c -fPIC -shared -o ext.so)

View file

@ -10,6 +10,6 @@ jobs:
build:
runs-on: macos-latest
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Setup tmate session
uses: mxschmitt/action-tmate@v3

View file

@ -11,7 +11,7 @@ jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
- name: Setup tmate session
uses: mxschmitt/action-tmate@v3
env:

2
.gitignore vendored
View file

@ -5,8 +5,6 @@ datasets.json
scratchpad
ignored/
.vscode
uv.lock

View file

@ -1,4 +1,4 @@
FROM python:3.11-slim-bookworm AS build
FROM python:3.11.0-slim-bullseye as build
# Version of Datasette to install, e.g. 0.55
# docker build . -t datasette --build-arg VERSION=0.55

View file

@ -33,11 +33,10 @@ export DATASETTE_SECRET := "not_a_secret"
uv run codespell datasette -S datasette/static --ignore-words docs/codespell-ignore-words.txt
uv run codespell tests --ignore-words docs/codespell-ignore-words.txt
# Run linters: black, ruff, prettier, cog
# Run linters: black, ruff, cog
@lint: codespell
uv run black datasette tests --check
uv run ruff check datasette tests
npm run prettier -- --check
uv run cog --check README.md docs/*.rst
# Apply ruff fixes

View file

@ -1,14 +1,8 @@
from datasette.permissions import Permission # noqa
from datasette.version import __version_info__, __version__ # noqa
from datasette.events import Event # noqa
from datasette.tokens import TokenHandler, TokenInvalid, TokenRestrictions # noqa
from datasette.utils.asgi import ( # noqa
Forbidden,
NotFound,
PayloadTooLarge,
Request,
Response,
)
from datasette.tokens import TokenHandler, TokenRestrictions # noqa
from datasette.utils.asgi import Forbidden, NotFound, Request, Response # noqa
from datasette.utils import actor_matches_allow # noqa
from datasette.views import Context # noqa
from .hookspecs import hookimpl # noqa

View file

@ -89,8 +89,7 @@ def pytest_runtest_protocol(item, nextitem):
continue
try:
ds.close()
except Exception as e: # noqa: BLE001
# Surfaced as a pytest warning; teardown must not fail the run
except Exception as e:
item.warn(
pytest.PytestUnraisableExceptionWarning(
f"Error closing Datasette instance: {e!r}"

View file

@ -1,9 +1,7 @@
import time
from itsdangerous import BadSignature
from datasette import hookimpl
from itsdangerous import BadSignature
from datasette.utils import baseconv
import time
@hookimpl

File diff suppressed because it is too large Load diff

View file

@ -1,8 +1,7 @@
import hashlib
from datasette import hookimpl
from datasette.utils.asgi import Response, BadRequest
from datasette.utils import to_css_class
from datasette.utils.asgi import BadRequest, Response
import hashlib
_BLOB_COLUMN = "_blob_column"
_BLOB_HASH = "_blob_hash"

View file

@ -1,45 +1,43 @@
import asyncio
import uvicorn
import click
from click import formatting
from click.types import CompositeParamType
from click_default_group import DefaultGroup
import functools
import json
import os
import pathlib
from runpy import run_module
import shutil
from subprocess import call
import sys
import textwrap
import webbrowser
from runpy import run_module
from subprocess import call
import click
import uvicorn
from click import formatting
from click.types import CompositeParamType
from click_default_group import DefaultGroup
from .app import (
Datasette,
DEFAULT_SETTINGS,
SETTINGS,
SQLITE_LIMIT_ATTACHED,
Datasette,
pm,
)
from .inspect import inspect_tables
from .utils import (
ConnectionProblem,
LoadExtension,
SpatialiteConnectionProblem,
SpatialiteNotFound,
StartupError,
StaticMount,
ValueAsBooleanError,
check_connection,
deep_dict_update,
find_spatialite,
parse_metadata,
ConnectionProblem,
SpatialiteConnectionProblem,
initial_path_for_datasette,
pairs_to_nested_config,
parse_metadata,
temporary_docker_directory,
value_as_boolean,
SpatialiteNotFound,
StaticMount,
ValueAsBooleanError,
)
from .utils.sqlite import sqlite3
from .utils.testing import TestClient
@ -77,7 +75,7 @@ class Setting(CompositeParamType):
# Datasette 1.0, we turn bare setting names into setting.name
# Type checking for those older settings
default = DEFAULT_SETTINGS[name]
name = f"settings.{name}"
name = "settings.{}".format(name)
if isinstance(default, bool):
try:
return name, "true" if value_as_boolean(value) else "false"
@ -173,6 +171,7 @@ async def inspect_(files, sqlite_extensions):
@cli.group()
def publish():
"""Publish specified SQLite database files to the internet along with a Datasette-powered interface and API"""
pass
# Register publish plugins
@ -579,27 +578,27 @@ def serve(
# https://github.com/simonw/datasette/issues/2389
deep_dict_update(config_data, settings_updates)
kwargs = {
"immutables": immutable,
"cache_headers": not reload,
"cors": cors,
"inspect_data": inspect_data,
"config": config_data,
"metadata": metadata_data,
"sqlite_extensions": sqlite_extensions,
"template_dir": template_dir,
"plugins_dir": plugins_dir,
"static_mounts": static,
"settings": None, # These are passed in config= now
"memory": memory,
"secret": secret,
"version_note": version_note,
"pdb": pdb,
"crossdb": crossdb,
"nolock": nolock,
"internal": internal,
"default_deny": default_deny,
}
kwargs = dict(
immutables=immutable,
cache_headers=not reload,
cors=cors,
inspect_data=inspect_data,
config=config_data,
metadata=metadata_data,
sqlite_extensions=sqlite_extensions,
template_dir=template_dir,
plugins_dir=plugins_dir,
static_mounts=static,
settings=None, # These are passed in config= now
memory=memory,
secret=secret,
version_note=version_note,
pdb=pdb,
crossdb=crossdb,
nolock=nolock,
internal=internal,
default_deny=default_deny,
)
# Separate directories from files
directories = [f for f in files if os.path.isdir(f)]
@ -622,7 +621,9 @@ def serve(
conn.close()
else:
raise click.ClickException(
f"Invalid value for '[FILES]...': Path '{file}' does not exist."
"Invalid value for '[FILES]...': Path '{}' does not exist.".format(
file
)
)
# Check for duplicate files by resolving all paths to their absolute forms
@ -663,6 +664,16 @@ def serve(
# Private utility mechanism for writing unit tests
return ds
# Run async soundness checks before startup hooks, since invoke_startup
# now populates internal tables which requires querying each database
run_sync(lambda: check_databases(ds))
# Run the "startup" plugin hooks
try:
run_sync(ds.invoke_startup)
except StartupError as e:
raise click.ClickException(e.args[0])
if headers and not get:
raise click.ClickException("--headers can only be used with --get")
@ -670,18 +681,10 @@ def serve(
raise click.ClickException("--token can only be used with --get")
if get:
# --get means we don't run Uvicorn at all
run_sync(lambda: check_databases(ds))
try:
run_sync(ds.invoke_startup)
except StartupError as e:
raise click.ClickException(e.args[0])
client = TestClient(ds)
request_headers = {}
if token:
request_headers["Authorization"] = f"Bearer {token}"
request_headers["Authorization"] = "Bearer {}".format(token)
cookies = {}
if actor:
cookies["ds_actor"] = client.actor_cookie(json.loads(actor))
@ -702,54 +705,30 @@ def serve(
sys.exit(exit_code)
return
# check_databases, invoke_startup() and the uvicorn server all run on a
# single event loop, so that anything a plugin's "startup" hook schedules
# on the loop (asyncio.create_task, Lock/Queue/Event objects, ...) is
# still alive when the server starts handling requests.
async def _serve_async():
# Populate internal catalog tables before invoke_startup
await check_databases(ds)
# Run the full startup sequence (immutable-database table-count
# precompute + the "startup" plugin hooks) via the same entry point
# AsgiLifespan/AsgiRunOnFirstRequest use, so it's not skipped when
# uvicorn's lifespan.startup fires moments later.
try:
await ds._startup_sequence()
except StartupError as e:
raise click.ClickException(e.args[0])
# Start the server
url = None
if root:
ds.root_enabled = True
url = "http://{}:{}{}?token={}".format(
host, port, ds.urls.path("-/auth-token"), ds._root_token
)
click.echo(url)
if open_browser:
if url is None:
# Figure out most convenient URL - to table, database or homepage
path = await initial_path_for_datasette(ds)
url = f"http://{host}:{port}{path}"
webbrowser.open(url)
uvicorn_kwargs = {
"host": host,
"port": port,
"log_level": "info",
"lifespan": "on",
"workers": 1,
}
if uds:
uvicorn_kwargs["uds"] = uds
if ssl_keyfile:
uvicorn_kwargs["ssl_keyfile"] = ssl_keyfile
if ssl_certfile:
uvicorn_kwargs["ssl_certfile"] = ssl_certfile
server = uvicorn.Server(uvicorn.Config(ds.app(), **uvicorn_kwargs))
await server.serve()
asyncio.run(_serve_async())
# Start the server
url = None
if root:
ds.root_enabled = True
url = "http://{}:{}{}?token={}".format(
host, port, ds.urls.path("-/auth-token"), ds._root_token
)
click.echo(url)
if open_browser:
if url is None:
# Figure out most convenient URL - to table, database or homepage
path = run_sync(lambda: initial_path_for_datasette(ds))
url = f"http://{host}:{port}{path}"
webbrowser.open(url)
uvicorn_kwargs = dict(
host=host, port=port, log_level="info", lifespan="on", workers=1
)
if uds:
uvicorn_kwargs["uds"] = uds
if ssl_keyfile:
uvicorn_kwargs["ssl_keyfile"] = ssl_keyfile
if ssl_certfile:
uvicorn_kwargs["ssl_certfile"] = ssl_certfile
uvicorn.run(ds.app(), **uvicorn_kwargs)
@cli.command()
@ -906,7 +885,7 @@ async def check_databases(ds):
)
except ConnectionProblem as e:
raise click.UsageError(
f"Connection to {database.path} failed check: {e.args[0]!s}"
f"Connection to {database.path} failed check: {str(e.args[0])}"
)
# If --crossdb and more than SQLITE_LIMIT_ATTACHED show warning
if (
@ -914,5 +893,9 @@ async def check_databases(ds):
and len([db for db in ds.databases.values() if not db.is_memory])
> SQLITE_LIMIT_ATTACHED
):
msg = f"Warning: --crossdb only works with the first {SQLITE_LIMIT_ATTACHED} attached databases"
msg = (
"Warning: --crossdb only works with the first {} attached databases".format(
SQLITE_LIMIT_ATTACHED
)
)
click.echo(click.style(msg, bold=True, fg="yellow"), err=True)

View file

@ -64,14 +64,14 @@ class ColumnType:
Return an HTML string to render this cell value, or None to
fall through to the default render_cell plugin hook chain.
"""
return
return None
async def validate(self, value, datasette):
"""
Validate a value before it is written. Return None if valid,
or a string error message if invalid.
"""
return
return None
async def transform_value(self, value, datasette):
"""

View file

@ -40,12 +40,12 @@ def _origin_tuple(value):
scheme = (parsed.scheme or "").lower()
host = (parsed.hostname or "").lower()
if not scheme or not host:
raise ValueError(f"missing scheme or host in {value!r}")
raise ValueError("missing scheme or host in {!r}".format(value))
port = parsed.port # may raise ValueError on bad ports
if port is None:
port = DEFAULT_PORTS.get(scheme)
if port is None:
raise ValueError(f"unknown default port for scheme {scheme!r}")
raise ValueError("unknown default port for scheme {!r}".format(scheme))
return scheme, host, port
@ -125,7 +125,9 @@ class CrossOriginProtectionMiddleware:
return
await self._forbid(
send,
f"Sec-Fetch-Site was {sec_fetch_site!r}, expected 'same-origin' or 'none'",
"Sec-Fetch-Site was {!r}, expected 'same-origin' or 'none'".format(
sec_fetch_site
),
)
return
@ -139,11 +141,11 @@ class CrossOriginProtectionMiddleware:
request_scheme = self._request_scheme(scope)
try:
origin_tuple = _origin_tuple(origin)
expected_tuple = _origin_tuple(f"{request_scheme}://{host}")
expected_tuple = _origin_tuple("{}://{}".format(request_scheme, host))
except ValueError:
await self._forbid(
send,
f"Malformed Origin {origin!r} or Host {host!r}",
"Malformed Origin {!r} or Host {!r}".format(origin, host),
)
return
@ -153,7 +155,7 @@ class CrossOriginProtectionMiddleware:
await self._forbid(
send,
f"Origin {origin!r} does not match Host {host!r}",
"Origin {!r} does not match Host {!r}".format(origin, host),
)
def _request_scheme(self, scope):
@ -161,8 +163,7 @@ class CrossOriginProtectionMiddleware:
try:
if self.datasette.setting("force_https_urls"):
return "https"
except Exception: # noqa: BLE001, S110
# Settings may not be readable this early; fall back to the ASGI scheme
except Exception:
pass
return scope.get("scheme") or "http"

View file

@ -1,35 +1,33 @@
import asyncio
import atexit
from collections import namedtuple
import inspect
import os
from pathlib import Path
import queue
import sqlite_utils
import sys
import tempfile
import threading
import uuid
from collections import namedtuple
from pathlib import Path
import sqlite_utils
from .inspect import inspect_hash
from .tracer import trace
from .utils import (
call_with_supported_arguments,
detect_fts,
detect_primary_keys,
detect_spatialite,
escape_sqlite,
get_all_foreign_keys,
get_outbound_foreign_keys,
md5_not_usedforsecurity,
sqlite3,
sqlite_timelimit,
table_column_details,
sqlite3,
table_columns,
table_column_details,
)
from .utils.sql_analysis import SQLAnalysis, analyze_sql_tables
from .utils.sqlite import sqlite_derived_table_dependencies, sqlite_hidden_table_names
from .utils.sqlite import sqlite_hidden_table_names
from .inspect import inspect_hash
connections = threading.local()
@ -85,7 +83,6 @@ class Database:
self.cached_hash = None
self.cached_size = None
self._cached_table_counts = None
self._cached_derived_table_dependencies = None
self._write_thread = None
self._write_queue = None
self._closed = False
@ -101,7 +98,9 @@ class Database:
def _check_not_closed(self):
if self._closed:
raise DatasetteClosedError(f"Database {self.name!r} has been closed")
raise DatasetteClosedError(
"Database {!r} has been closed".format(self.name)
)
def _remove_pending_execute_future(self, future):
with self._pending_execute_futures_lock:
@ -140,7 +139,7 @@ class Database:
if write:
extra_kwargs["isolation_level"] = "IMMEDIATE"
if self.memory_name:
uri = f"file:{self.memory_name}?mode=memory&cache=shared"
uri = "file:{}?mode=memory&cache=shared".format(self.memory_name)
conn = sqlite3.connect(
uri, uri=True, check_same_thread=False, **extra_kwargs
)
@ -193,20 +192,21 @@ class Database:
write_thread.join(timeout=10)
if write_thread.is_alive():
sys.stderr.write(
f"Datasette: write thread for {self.name!r} did not exit within 10s\n"
"Datasette: write thread for {!r} did not exit within 10s\n".format(
self.name
)
)
sys.stderr.flush()
for future in pending_execute_futures:
try:
future.result()
except Exception: # noqa: BLE001, S110
# Shutdown teardown - a failed pending write must not block close()
except Exception:
pass
# Close anything still tracked in _all_file_connections
for connection in self._all_file_connections:
try:
connection.close()
except Exception: # noqa: BLE001, S110
except Exception:
pass
self._all_file_connections = []
# Drop per-thread cached read connections we can reach
@ -218,13 +218,13 @@ class Database:
if self._read_connection is not None:
try:
self._read_connection.close()
except Exception: # noqa: BLE001, S110
except Exception:
pass
self._read_connection = None
if self._write_connection is not None:
try:
self._write_connection.close()
except Exception: # noqa: BLE001, S110
except Exception:
pass
self._write_connection = None
if self.is_temp_disk:
@ -246,34 +246,19 @@ class Database:
request=None,
return_all=False,
returning_limit=EXECUTE_WRITE_RETURNING_LIMIT,
transaction=True,
time_limit_ms=2000,
):
self._check_not_closed()
if returning_limit < 0:
raise ValueError("returning_limit must be >= 0")
def execute_sql(conn):
def _inner(conn):
cursor = conn.execute(sql, params or [])
return ExecuteWriteResult.from_cursor(
cursor, return_all=return_all, returning_limit=returning_limit
)
def _inner(conn):
try:
if time_limit_ms is None:
return execute_sql(conn)
with sqlite_timelimit(conn, time_limit_ms):
return execute_sql(conn)
except (sqlite3.OperationalError, sqlite3.DatabaseError) as e:
if e.args == ("interrupted",):
raise QueryInterrupted(e, sql, params)
raise
with trace("sql", database=self.name, sql=sql.strip(), params=params):
results = await self.execute_write_fn(
_inner, block=block, request=request, transaction=transaction
)
results = await self.execute_write_fn(_inner, block=block, request=request)
return results
async def execute_write_script(self, sql, block=True, request=None):
@ -363,19 +348,9 @@ class Database:
self.ds._prepare_connection(self._write_connection, self.name)
if transaction:
with self._write_connection:
self._write_connection.execute("BEGIN IMMEDIATE")
result = fn(self._write_connection)
else:
result = fn(self._write_connection)
if not block:
# There is no write thread here, so the write has already
# finished. Hand back the same (task_id, reply_future) shape
# _send_to_write_thread() returns, with the future already
# resolved, so the block=False path below is identical in
# both modes.
reply_future = asyncio.get_running_loop().create_future()
reply_future.set_result(result)
result = (uuid.uuid4(), reply_future)
else:
result = await self._send_to_write_thread(
fn, block=block, transaction=transaction
@ -391,8 +366,7 @@ class Database:
async def _dispatch_events_after_write():
try:
await reply_future
except Exception: # noqa: BLE001
# The write failed; skip success events regardless of why
except Exception:
# if the write failed, don't emit success events
return
for event in pending_events:
@ -445,9 +419,11 @@ class Database:
self._write_thread = threading.Thread(
target=self._execute_writes, daemon=True
)
self._write_thread.name = f"_execute_writes for database {self.name}"
self._write_thread.name = "_execute_writes for database {}".format(
self.name
)
self._write_thread.start()
task_id = uuid.uuid4()
task_id = uuid.uuid5(uuid.NAMESPACE_DNS, "datasette.io")
loop = asyncio.get_running_loop()
reply_future = loop.create_future()
self._write_queue.put(
@ -466,8 +442,7 @@ class Database:
try:
conn = self.connect(write=True)
self.ds._prepare_connection(conn, self.name)
except Exception as e: # noqa: BLE001
# Stored and re-raised to whoever queues the next write
except Exception as e:
conn_exception = e
while True:
task = self._write_queue.get()
@ -475,8 +450,7 @@ class Database:
if conn is not None:
try:
conn.close()
except Exception: # noqa: BLE001, S110
# Best-effort close as the write thread exits
except Exception:
pass
return
exception = None
@ -495,21 +469,19 @@ class Database:
except ValueError:
# Was probably a memory connection
pass
except Exception as e: # noqa: BLE001
# Write thread must survive any task failure or the database wedges
sys.stderr.write(f"{e}\n")
except Exception as e:
sys.stderr.write("{}\n".format(e))
sys.stderr.flush()
exception = e
else:
try:
if task.transaction:
with conn:
conn.execute("BEGIN IMMEDIATE")
result = task.fn(conn)
else:
result = task.fn(conn)
except Exception as e: # noqa: BLE001
sys.stderr.write(f"{e}\n")
except Exception as e:
sys.stderr.write("{}\n".format(e))
sys.stderr.flush()
exception = e
_deliver_write_result(task, result, exception)
@ -576,7 +548,9 @@ class Database:
raise QueryInterrupted(e, sql, params)
if log_sql_errors:
sys.stderr.write(
f"ERROR: conn={conn}, sql = {sql!r}, params = {params}: {e}\n"
"ERROR: conn={}, sql = {}, params = {}: {}\n".format(
conn, repr(sql), params, e
)
)
sys.stderr.flush()
raise
@ -629,7 +603,7 @@ class Database:
try:
table_count = (
await self.execute(
f"select count(*) from (select * from {escape_sqlite(table)} limit {self.count_limit + 1})",
f"select count(*) from (select * from [{table}] limit {self.count_limit + 1})",
custom_time_limit=limit,
)
).rows[0][0]
@ -733,9 +707,9 @@ class Database:
column_names
and len(column_names) == 2
and ("id" in column_names or "pk" in column_names)
and set(column_names) != {"id", "pk"}
and not set(column_names) == {"id", "pk"}
):
return next(c for c in column_names if c not in ("id", "pk"))
return [c for c in column_names if c not in ("id", "pk")][0]
# Couldn't find a label:
return None
@ -781,17 +755,6 @@ class Database:
return hidden_tables
async def derived_table_dependencies(self):
"""Return implementation tables and the tables they derive from."""
schema_version = (await self.execute("PRAGMA schema_version")).first()[0]
if (
self._cached_derived_table_dependencies is None
or self._cached_derived_table_dependencies[0] != schema_version
):
dependencies = await self.execute_fn(sqlite_derived_table_dependencies)
self._cached_derived_table_dependencies = (schema_version, dependencies)
return self._cached_derived_table_dependencies[1]
async def view_names(self):
results = await self.execute("select name from sqlite_master where type='view'")
return [r[0] for r in results.rows]
@ -888,10 +851,10 @@ def _apply_write_wrapper(fn, wrapper_factory, track_event):
class WriteTask:
__slots__ = (
"fn",
"isolated_connection",
"task_id",
"loop",
"reply_future",
"task_id",
"isolated_connection",
"transaction",
)
@ -932,7 +895,7 @@ class QueryInterrupted(Exception):
self.params = params
def __str__(self):
return f"QueryInterrupted: {self.e}"
return "QueryInterrupted: {}".format(self.e)
class MultipleValues(Exception):

View file

@ -2,8 +2,8 @@ from datasette import hookimpl
from datasette.permissions import Action
from datasette.resources import (
DatabaseResource,
QueryResource,
TableResource,
QueryResource,
)
@ -61,12 +61,6 @@ def register_actions():
description="Create tables",
resource_class=DatabaseResource,
),
Action(
name="create-view",
abbr="cv",
description="Create views",
resource_class=DatabaseResource,
),
Action(
name="store-query",
abbr="sq",
@ -117,12 +111,6 @@ def register_actions():
description="Drop tables",
resource_class=TableResource,
),
Action(
name="drop-view",
abbr="dv",
description="Drop views",
resource_class=TableResource,
),
# Query-level actions (child-level)
Action(
name="view-query",

View file

@ -6,17 +6,6 @@ import markupsafe
from datasette import hookimpl
from datasette.column_types import ColumnType, SQLiteType
_HTTP_URL_RE = re.compile(r"https?://\S+", re.IGNORECASE)
def _normalize_http_url(value):
if not isinstance(value, str):
return None
normalized = value.strip()
if not _HTTP_URL_RE.fullmatch(normalized):
return None
return normalized
class UrlColumnType(ColumnType):
name = "url"
@ -26,10 +15,7 @@ class UrlColumnType(ColumnType):
async def render_cell(self, value, column, table, database, datasette, request):
if not value or not isinstance(value, str):
return None
normalized = _normalize_http_url(value)
if normalized is None:
return markupsafe.escape(value.strip())
escaped = markupsafe.escape(normalized)
escaped = markupsafe.escape(value.strip())
return markupsafe.Markup(f'<a href="{escaped}">{escaped}</a>')
async def validate(self, value, datasette):
@ -37,7 +23,7 @@ class UrlColumnType(ColumnType):
return None
if not isinstance(value, str):
return "URL must be a string"
if _normalize_http_url(value) is None:
if not re.match(r"^https?://\S+$", value.strip()):
return "Invalid URL"
return None

View file

@ -1,9 +1,8 @@
from datasette import hookimpl
import datetime
import os
import time
from datasette import hookimpl
def header(key, request):
key = key.replace("_", "-").encode("utf-8")

View file

@ -17,29 +17,18 @@ UNION/INTERSECT operations. The order of evaluation is:
from __future__ import annotations
from .config import config_permissions_sql as config_permissions_sql
from .defaults import (
DEFAULT_ALLOW_ACTIONS as DEFAULT_ALLOW_ACTIONS,
)
from .defaults import (
default_action_permissions_sql as default_action_permissions_sql,
)
from .defaults import (
# Avoid "datasette.default_permissions" does not explicitly export attribute
default_allow_sql_check as default_allow_sql_check,
)
from .defaults import (
default_query_permissions_sql as default_query_permissions_sql,
)
from .restrictions import (
ActorRestrictions as ActorRestrictions,
)
# Re-export all hooks and public utilities
from .restrictions import (
actor_restrictions_sql as actor_restrictions_sql,
)
from .restrictions import (
restrictions_allow_action as restrictions_allow_action,
ActorRestrictions as ActorRestrictions,
)
from .root import root_user_permissions_sql as root_user_permissions_sql
from .config import config_permissions_sql as config_permissions_sql
from .defaults import (
# Avoid "datasette.default_permissions" does not explicitly export attribute
default_allow_sql_check as default_allow_sql_check,
default_action_permissions_sql as default_action_permissions_sql,
default_query_permissions_sql as default_query_permissions_sql,
DEFAULT_ALLOW_ACTIONS as DEFAULT_ALLOW_ACTIONS,
)

View file

@ -6,7 +6,7 @@ Applies permission rules from datasette.yaml configuration.
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from typing import TYPE_CHECKING, Any, List, Optional, Set, Tuple
if TYPE_CHECKING:
from datasette.app import Datasette
@ -55,8 +55,8 @@ class ConfigPermissionProcessor:
def __init__(
self,
datasette: Datasette,
actor: dict | None,
datasette: "Datasette",
actor: Optional[dict],
action: str,
):
self.datasette = datasette
@ -74,8 +74,8 @@ class ConfigPermissionProcessor:
self.restrictions = actor.get("_r", {}) if actor else {}
# Pre-compute restriction info for efficiency
self.restricted_databases: set[str] = set()
self.restricted_tables: set[tuple[str, str]] = set()
self.restricted_databases: Set[str] = set()
self.restricted_tables: Set[Tuple[str, str]] = set()
if self.has_restrictions:
self.restricted_databases = {
@ -92,27 +92,16 @@ class ConfigPermissionProcessor:
# Tables implicitly reference their parent databases
self.restricted_databases.update(db for db, _ in self.restricted_tables)
# Resolve identity keys once per action, rather than scanning the
# restriction allowlist for every configured table's allow block.
self.restricted_table_keys = {
(db, self.action_obj.normalize_child(table) if self.action_obj else table)
for db, table in self.restricted_tables
}
def evaluate_allow_block(self, allow_block: Any) -> bool | None:
def evaluate_allow_block(self, allow_block: Any) -> Optional[bool]:
"""Evaluate an allow block against the current actor."""
if allow_block is None:
return None
# Values passed using ``-s permissions.* 1`` or ``0`` are parsed as
# integers, but should retain the CLI's boolean 1/0 behavior.
if isinstance(allow_block, int) and allow_block in (0, 1):
return bool(allow_block)
return actor_matches_allow(self.actor, allow_block)
def is_in_restriction_allowlist(
self,
parent: str | None,
child: str | None,
parent: Optional[str],
child: Optional[str],
) -> bool:
"""Check if resource is allowed by actor restrictions."""
if not self.has_restrictions:
@ -132,10 +121,8 @@ class ConfigPermissionProcessor:
if parent:
table_restrictions = (self.restrictions.get("r", {}) or {}).get(parent, {})
if child:
child_key = (
self.action_obj.normalize_child(child) if self.action_obj else child
)
if (parent, child_key) in self.restricted_table_keys:
table_actions = table_restrictions.get(child, [])
if self.action_checks.intersection(table_actions):
return True
else:
# Parent query should proceed if any child in this database is allowlisted
@ -156,9 +143,9 @@ class ConfigPermissionProcessor:
def add_permissions_rule(
self,
parent: str | None,
child: str | None,
permissions_block: dict | None,
parent: Optional[str],
child: Optional[str],
permissions_block: Optional[dict],
scope_desc: str,
) -> None:
"""Add a rule from a permissions:{action} block."""
@ -178,8 +165,8 @@ class ConfigPermissionProcessor:
def add_allow_block_rule(
self,
parent: str | None,
child: str | None,
parent: Optional[str],
child: Optional[str],
allow_block: Any,
scope_desc: str,
) -> None:
@ -211,8 +198,8 @@ class ConfigPermissionProcessor:
def _add_restriction_gate_denies(
self,
parent: str | None,
child: str | None,
parent: Optional[str],
child: Optional[str],
is_allowed: bool,
scope_desc: str,
) -> None:
@ -244,7 +231,7 @@ class ConfigPermissionProcessor:
if db_name == parent:
self.collector.add(db_name, table_name, False, reason)
def process(self) -> PermissionSQL | None:
def process(self) -> Optional[PermissionSQL]:
"""Process all config rules and return combined PermissionSQL."""
self._process_root_permissions()
self._process_databases()
@ -434,10 +421,10 @@ class ConfigPermissionProcessor:
@hookimpl(specname="permission_resources_sql")
async def config_permissions_sql(
datasette: Datasette,
actor: dict | None,
datasette: "Datasette",
actor: Optional[dict],
action: str,
) -> list[PermissionSQL] | None:
) -> Optional[List[PermissionSQL]]:
"""
Apply permission rules from datasette.yaml configuration.

View file

@ -6,7 +6,7 @@ Provides default allow rules for standard view/execute actions.
from __future__ import annotations
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, Optional
if TYPE_CHECKING:
from datasette.app import Datasette
@ -29,28 +29,29 @@ DEFAULT_ALLOW_ACTIONS = frozenset(
@hookimpl(specname="permission_resources_sql")
async def default_allow_sql_check(
datasette: Datasette,
actor: dict | None,
datasette: "Datasette",
actor: Optional[dict],
action: str,
) -> PermissionSQL | None:
) -> Optional[PermissionSQL]:
"""
Enforce the default_allow_sql setting.
When default_allow_sql is false (the default), execute-sql is denied
unless explicitly allowed by config or other rules.
"""
if action == "execute-sql" and not datasette.setting("default_allow_sql"):
return PermissionSQL.deny(reason="default_allow_sql is false")
if action == "execute-sql":
if not datasette.setting("default_allow_sql"):
return PermissionSQL.deny(reason="default_allow_sql is false")
return None
@hookimpl(specname="permission_resources_sql")
async def default_action_permissions_sql(
datasette: Datasette,
actor: dict | None,
datasette: "Datasette",
actor: Optional[dict],
action: str,
) -> PermissionSQL | None:
) -> Optional[PermissionSQL]:
"""
Provide default allow rules for standard view/execute actions.
@ -70,10 +71,10 @@ async def default_action_permissions_sql(
@hookimpl(specname="permission_resources_sql")
async def default_query_permissions_sql(
datasette: Datasette,
actor: dict | None,
datasette: "Datasette",
actor: Optional[dict],
action: str,
) -> PermissionSQL | None:
) -> Optional[PermissionSQL]:
actor_id = actor.get("id") if isinstance(actor, dict) else None
if action not in {"view-query", "update-query", "delete-query"}:

View file

@ -5,7 +5,7 @@ Shared helper utilities for default permission implementations.
from __future__ import annotations
from dataclasses import dataclass
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, List, Optional, Set
if TYPE_CHECKING:
from datasette.app import Datasette
@ -13,7 +13,7 @@ if TYPE_CHECKING:
from datasette.permissions import PermissionSQL
def get_action_name_variants(datasette: Datasette, action: str) -> set[str]:
def get_action_name_variants(datasette: "Datasette", action: str) -> Set[str]:
"""
Get all name variants for an action (full name and abbreviation).
@ -27,7 +27,7 @@ def get_action_name_variants(datasette: Datasette, action: str) -> set[str]:
return variants
def action_in_list(datasette: Datasette, action: str, action_list: list) -> bool:
def action_in_list(datasette: "Datasette", action: str, action_list: list) -> bool:
"""Check if an action (or its abbreviation) is in a list."""
return bool(get_action_name_variants(datasette, action).intersection(action_list))
@ -36,8 +36,8 @@ def action_in_list(datasette: Datasette, action: str, action_list: list) -> bool
class PermissionRow:
"""A single permission rule row."""
parent: str | None
child: str | None
parent: Optional[str]
child: Optional[str]
allow: bool
reason: str
@ -46,14 +46,14 @@ class PermissionRowCollector:
"""Collects permission rows and converts them to PermissionSQL."""
def __init__(self, prefix: str = "row"):
self.rows: list[PermissionRow] = []
self.rows: List[PermissionRow] = []
self.prefix = prefix
def add(
self,
parent: str | None,
child: str | None,
allow: bool | None,
parent: Optional[str],
child: Optional[str],
allow: Optional[bool],
reason: str,
if_not_none: bool = False,
) -> None:
@ -62,7 +62,7 @@ class PermissionRowCollector:
return
self.rows.append(PermissionRow(parent, child, allow, reason))
def to_permission_sql(self) -> PermissionSQL | None:
def to_permission_sql(self) -> Optional[PermissionSQL]:
"""Convert collected rows to a PermissionSQL object."""
if not self.rows:
return None

View file

@ -8,7 +8,7 @@ contains allowlists of resources the actor can access.
from __future__ import annotations
from dataclasses import dataclass
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, List, Optional, Set, Tuple
if TYPE_CHECKING:
from datasette.app import Datasette
@ -23,12 +23,12 @@ from .helpers import action_in_list, get_action_name_variants
class ActorRestrictions:
"""Parsed actor restrictions from the _r key."""
global_actions: list[str] # _r.a - globally allowed actions
global_actions: List[str] # _r.a - globally allowed actions
database_actions: dict # _r.d - {db_name: [actions]}
table_actions: dict # _r.r - {db_name: {table: [actions]}}
@classmethod
def from_actor(cls, actor: dict | None) -> ActorRestrictions | None:
def from_actor(cls, actor: Optional[dict]) -> Optional["ActorRestrictions"]:
"""Parse restrictions from actor dict. Returns None if no restrictions."""
if not actor:
return None
@ -44,11 +44,11 @@ class ActorRestrictions:
table_actions=restrictions.get("r", {}),
)
def is_action_globally_allowed(self, datasette: Datasette, action: str) -> bool:
def is_action_globally_allowed(self, datasette: "Datasette", action: str) -> bool:
"""Check if action is in the global allowlist."""
return action_in_list(datasette, action, self.global_actions)
def get_allowed_databases(self, datasette: Datasette, action: str) -> set[str]:
def get_allowed_databases(self, datasette: "Datasette", action: str) -> Set[str]:
"""Get database names where this action is allowed."""
allowed = set()
for db_name, db_actions in self.database_actions.items():
@ -57,8 +57,8 @@ class ActorRestrictions:
return allowed
def get_allowed_tables(
self, datasette: Datasette, action: str
) -> set[tuple[str, str]]:
self, datasette: "Datasette", action: str
) -> Set[Tuple[str, str]]:
"""Get (database, table) pairs where this action is allowed."""
allowed = set()
for db_name, tables in self.table_actions.items():
@ -70,10 +70,10 @@ class ActorRestrictions:
@hookimpl(specname="permission_resources_sql")
async def actor_restrictions_sql(
datasette: Datasette,
actor: dict | None,
datasette: "Datasette",
actor: Optional[dict],
action: str,
) -> list[PermissionSQL] | None:
) -> Optional[List[PermissionSQL]]:
"""
Handle actor restriction-based permission rules.
@ -140,10 +140,10 @@ async def actor_restrictions_sql(
def restrictions_allow_action(
datasette: Datasette,
datasette: "Datasette",
restrictions: dict,
action: str,
resource: str | tuple[str, str] | None,
resource: Optional[str | Tuple[str, str]],
) -> bool:
"""
Check if restrictions allow the requested action on the requested resource.
@ -185,15 +185,11 @@ def restrictions_allow_action(
# Check table/resource level
if resource is not None and not isinstance(resource, str) and len(resource) == 2:
database, table = resource
action_obj = datasette.actions.get(action)
normalize = action_obj.normalize_child if action_obj else lambda name: name
for table_name, table_allowed in (
restrictions.get("r", {}).get(database, {}).items()
):
if normalize(table_name) == normalize(table):
assert isinstance(table_allowed, list)
if to_check.intersection(table_allowed):
return True
table_allowed = restrictions.get("r", {}).get(database, {}).get(table)
if table_allowed is not None:
assert isinstance(table_allowed, list)
if to_check.intersection(table_allowed):
return True
# This action is not explicitly allowed, so reject it
return False

View file

@ -6,7 +6,7 @@ Grants full permissions to the root user when --root flag is used.
from __future__ import annotations
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, Optional
if TYPE_CHECKING:
from datasette.app import Datasette
@ -17,9 +17,9 @@ from datasette.permissions import PermissionSQL
@hookimpl(specname="permission_resources_sql")
async def root_user_permissions_sql(
datasette: Datasette,
actor: dict | None,
) -> PermissionSQL | None:
datasette: "Datasette",
actor: Optional[dict],
) -> Optional[PermissionSQL]:
"""
Grant root user full permissions when --root flag is used.
"""

View file

@ -1,25 +0,0 @@
"""Default table-access policy for SQLite optimizer statistics."""
import json
from datasette import hookimpl
from datasette.permissions import PermissionSQL
@hookimpl
def permission_resources_sql(action):
if action != "view-table":
return None
return PermissionSQL(
sql="""
SELECT database_name AS parent, value AS child, 0 AS allow,
'SQLite statistics tables are denied by default' AS reason
FROM catalog_databases
CROSS JOIN json_each(:sqlite_statistics_names)
""",
params={
"sqlite_statistics_names": json.dumps(
["sqlite_stat1", "sqlite_stat2", "sqlite_stat3", "sqlite_stat4"]
)
},
)

View file

@ -7,7 +7,7 @@ to datasette.verify_token() so all registered handlers are tried.
from __future__ import annotations
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, Optional
if TYPE_CHECKING:
from datasette.app import Datasette
@ -17,13 +17,15 @@ from datasette.tokens import SignedTokenHandler
@hookimpl
def register_token_handler(datasette: Datasette):
def register_token_handler(datasette: "Datasette"):
"""Register the default signed token handler."""
return SignedTokenHandler()
@hookimpl(specname="actor_from_request")
async def actor_from_signed_api_token(datasette: Datasette, request) -> dict | None:
async def actor_from_signed_api_token(
datasette: "Datasette", request
) -> Optional[dict]:
"""
Authenticate requests using API tokens by delegating to all registered
token handlers via datasette.verify_token().

View file

@ -1,29 +0,0 @@
from datasette import hookimpl
from datasette.resources import TableResource
@hookimpl
def table_actions(datasette, actor, database, table, request):
async def inner():
db = datasette.get_database(database)
if not db.is_mutable:
return []
if not await datasette.allowed(
action="alter-table",
resource=TableResource(database=database, table=table),
actor=actor,
):
return []
return [
{
"type": "button",
"label": "Alter table",
"description": "Change columns and primary key for this table.",
"attrs": {
"aria-label": f"Alter table {table}",
"data-table-action": "alter-table",
},
}
]
return inner

View file

@ -1,8 +1,7 @@
from abc import ABC, abstractproperty
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from datasette.hookspecs import hookimpl
from datetime import datetime, timezone
@dataclass

View file

@ -5,8 +5,6 @@ from typing import ClassVar
from asyncinject import Registry
from datasette.utils.asgi import BadRequest
def extra_names_from_request(request):
extra_bits = request.args.getlist("_extra")
@ -83,16 +81,6 @@ class ExtraRegistry:
def public_classes_for_scope(self, scope):
return self.classes_for_scope(scope, include_internal=False)
def internal_classes_for_scope(self, scope):
# Extras that are available to HTML templates but excluded from
# JSON responses - plain Providers are dependency plumbing and
# never surface as keys, so they are not included
return [
cls
for cls in self.classes_for_scope(scope)
if issubclass(cls, Extra) and not cls.public
]
def _registry_for_scope(self, scope):
registry = self._scope_registries.get(scope)
if registry is None:
@ -115,17 +103,6 @@ class ExtraRegistry:
self._allowed_names[key] = names
return names
def validate_requested(self, requested, scope):
"""
Raise BadRequest if any requested extra name is not a public extra
for this scope. Used by data formats such as .json - HTML pages
silently ignore unknown names instead.
"""
allowed = self._allowed_names_for_scope(scope, include_internal=False)
unknown = sorted(name for name in requested if name not in allowed)
if unknown:
raise BadRequest("Unknown _extra: {}".format(", ".join(unknown)))
async def resolve(self, requested, context, scope, include_internal=False):
allowed_names = self._allowed_names_for_scope(scope, include_internal)
requested_names = [name for name in requested if name in allowed_names]

View file

@ -1,13 +1,12 @@
import json
import urllib
from datasette import hookimpl
from datasette.database import QueryInterrupted
from datasette.utils import (
detect_json1,
escape_sqlite,
path_with_added_args,
path_with_removed_args,
detect_json1,
sqlite3,
)
@ -31,7 +30,7 @@ def load_facet_configs(request, table_config):
assert (
len(facet_config.values()) == 1
), "Metadata config dicts should be {type: config}"
type, facet_config = next(iter(facet_config.items()))
type, facet_config = list(facet_config.items())[0]
if isinstance(facet_config, str):
facet_config = {"simple": facet_config}
facet_configs.setdefault(type, []).append(
@ -86,7 +85,7 @@ class Facet:
self.database = database
# For foreign key expansion. Can be None for e.g. stored SQL queries:
self.table = table
self.sql = sql or f"select * from {escape_sqlite(table)}"
self.sql = sql or f"select * from [{table}]"
self.params = params or []
self.table_config = table_config
# row_count can be None, in which case we calculate it ourselves:
@ -161,13 +160,18 @@ class ColumnFacet(Facet):
for column in columns:
if column in already_enabled:
continue
suggested_facet_sql = f"""
with limited as (select * from ({self.sql}) limit {self.suggest_consider})
select {escape_sqlite(column)} as value, count(*) as n from limited
suggested_facet_sql = """
with limited as (select * from ({sql}) limit {suggest_consider})
select {column} as value, count(*) as n from limited
where value is not null
group by value
limit {facet_size + 1}
"""
limit {limit}
""".format(
column=escape_sqlite(column),
sql=self.sql,
limit=facet_size + 1,
suggest_consider=self.suggest_consider,
)
distinct_values = None
try:
distinct_values = await self.ds.execute(
@ -263,7 +267,7 @@ class ColumnFacet(Facet):
for row in facet_rows:
column_qs = column
if column.startswith("_"):
column_qs = f"{column}__exact"
column_qs = "{}__exact".format(column)
selected = (column_qs, str(row["value"])) in qs_pairs
if selected:
toggle_path = path_with_removed_args(
@ -338,12 +342,12 @@ class ArrayFacet(Facet):
for v in await self.ds.execute(
self.database,
(
f"select {escape_sqlite(column)} from ({self.sql}) "
f"where {escape_sqlite(column)} is not null "
f"and {escape_sqlite(column)} != '' "
f"and json_array_length({escape_sqlite(column)}) > 0 "
"select {column} from ({sql}) "
"where {column} is not null "
"and {column} != '' "
"and json_array_length({column}) > 0 "
"limit 100"
),
).format(column=escape_sqlite(column), sql=self.sql),
self.params,
truncate=False,
custom_time_limit=self.ds.setting(
@ -384,14 +388,14 @@ class ArrayFacet(Facet):
source = source_and_config["source"]
column = config.get("column") or config["simple"]
# https://github.com/simonw/datasette/issues/448
facet_sql = f"""
with inner as ({self.sql}),
facet_sql = """
with inner as ({sql}),
deduped_array_items as (
select
distinct j.value,
inner.*
from
json_each([inner].{escape_sqlite(column)}) j
json_each([inner].{col}) j
join inner
)
select
@ -402,8 +406,12 @@ class ArrayFacet(Facet):
group by
value
order by
count(*) desc, value limit {facet_size + 1}
"""
count(*) desc, value limit {limit}
""".format(
col=escape_sqlite(column),
sql=self.sql,
limit=facet_size + 1,
)
try:
facet_rows_results = await self.ds.execute(
self.database,

View file

@ -1,11 +1,8 @@
import json
from typing import ClassVar
from datasette import hookimpl
from datasette.resources import DatabaseResource, TableResource
from datasette.utils.asgi import BadRequest
from datasette.resources import DatabaseResource
from datasette.views.base import DatasetteError
from datasette.utils.asgi import BadRequest
import json
from .utils import detect_json1, escape_sqlite, path_with_removed_args
@ -51,20 +48,13 @@ def search_filters(request, database, table, datasette):
human_descriptions = []
extra_context = {}
# Figure out which trusted fts_table to use. Query string parameters can
# repeat this mapping (for backwards compatibility), but must not select
# a different table or primary key.
# Figure out which fts_table to use
table_metadata = await datasette.table_config(database, table)
db = datasette.get_database(database)
fts_table = table_metadata.get("fts_table")
fts_table = request.args.get("_fts_table")
fts_table = fts_table or table_metadata.get("fts_table")
fts_table = fts_table or await db.fts_table(table)
fts_pk = table_metadata.get("fts_pk", "rowid")
requested_fts_table = request.args.get("_fts_table")
requested_fts_pk = request.args.get("_fts_pk")
if (requested_fts_table and requested_fts_table != fts_table) or (
requested_fts_pk and requested_fts_pk != fts_pk
):
raise BadRequest("Invalid _fts_table or _fts_pk")
fts_pk = request.args.get("_fts_pk", table_metadata.get("fts_pk", "rowid"))
search_args = {
key: request.args[key]
for key in request.args
@ -82,11 +72,6 @@ def search_filters(request, database, table, datasette):
extra_context["supports_search"] = bool(fts_table)
if fts_table and search_args:
await datasette.ensure_permission(
action="view-table",
resource=TableResource(database=database, table=fts_table),
actor=request.actor,
)
if "_search" in search_args:
# Simple ?_search=xxx
search = search_args["_search"]
@ -114,9 +99,9 @@ def search_filters(request, database, table, datasette):
fts_table=escape_sqlite(fts_table),
search_col=escape_sqlite(search_col),
match_clause=(
f":search_{i}"
":search_{}".format(i)
if search_mode_raw
else f"escape_fts(:search_{i})"
else "escape_fts(:search_{})".format(i)
),
)
)
@ -147,18 +132,13 @@ def through_filters(request, database, table, datasette):
through_table = through_data["table"]
other_column = through_data["column"]
value = through_data["value"]
await datasette.ensure_permission(
action="view-table",
resource=TableResource(database=database, table=through_table),
actor=request.actor,
)
db = datasette.get_database(database)
outgoing_foreign_keys = await db.foreign_keys_for_table(through_table)
fk_to_us = next(
(fk for fk in outgoing_foreign_keys if fk["other_table"] == table),
None,
)
if fk_to_us is None:
try:
fk_to_us = [
fk for fk in outgoing_foreign_keys if fk["other_table"] == table
][0]
except IndexError:
raise DatasetteError(
"Invalid _through - could not find corresponding foreign key"
)
@ -226,14 +206,10 @@ class TemplatedFilter(Filter):
if self.numeric and converted.isdigit():
converted = int(converted)
if self.no_argument:
kwargs = {"c": _quote_sqlite_identifier(column)}
kwargs = {"c": column}
converted = None
else:
kwargs = {
"c": _quote_sqlite_identifier(column),
"p": f"p{param_counter}",
"t": _quote_sqlite_identifier(table),
}
kwargs = {"c": column, "p": f"p{param_counter}", "t": table}
return self.sql_template.format(**kwargs), converted
def human_clause(self, column, value):
@ -247,14 +223,6 @@ class TemplatedFilter(Filter):
return template.format(c=column, v=value)
def _quote_sqlite_identifier(identifier):
# Preserve the historic always-quoted SQL generated by TemplatedFilter.
escaped = escape_sqlite(identifier)
if escaped == identifier:
return f'"{identifier}"'
return escaped
class InFilter(Filter):
key = "in"
display = "in"
@ -296,56 +264,56 @@ class Filters:
TemplatedFilter(
"exact",
"=",
"{c} = :{p}",
'"{c}" = :{p}',
lambda c, v: "{c} = {v}" if v.isdigit() else '{c} = "{v}"',
),
TemplatedFilter(
"not",
"!=",
"{c} != :{p}",
'"{c}" != :{p}',
lambda c, v: "{c} != {v}" if v.isdigit() else '{c} != "{v}"',
),
TemplatedFilter(
"contains",
"contains",
"{c} like :{p}",
'"{c}" like :{p}',
'{c} contains "{v}"',
format="%{}%",
),
TemplatedFilter(
"notcontains",
"does not contain",
"{c} not like :{p}",
'"{c}" not like :{p}',
'{c} does not contain "{v}"',
format="%{}%",
),
TemplatedFilter(
"endswith",
"ends with",
"{c} like :{p}",
'"{c}" like :{p}',
'{c} ends with "{v}"',
format="%{}",
),
TemplatedFilter(
"startswith",
"starts with",
"{c} like :{p}",
'"{c}" like :{p}',
'{c} starts with "{v}"',
format="{}%",
),
TemplatedFilter("gt", ">", "{c} > :{p}", "{c} > {v}", numeric=True),
TemplatedFilter("gt", ">", '"{c}" > :{p}', "{c} > {v}", numeric=True),
TemplatedFilter(
"gte", "\u2265", "{c} >= :{p}", "{c} \u2265 {v}", numeric=True
"gte", "\u2265", '"{c}" >= :{p}', "{c} \u2265 {v}", numeric=True
),
TemplatedFilter("lt", "<", "{c} < :{p}", "{c} < {v}", numeric=True),
TemplatedFilter("lt", "<", '"{c}" < :{p}', "{c} < {v}", numeric=True),
TemplatedFilter(
"lte", "\u2264", "{c} <= :{p}", "{c} \u2264 {v}", numeric=True
"lte", "\u2264", '"{c}" <= :{p}', "{c} \u2264 {v}", numeric=True
),
TemplatedFilter("like", "like", "{c} like :{p}", '{c} like "{v}"'),
TemplatedFilter("like", "like", '"{c}" like :{p}', '{c} like "{v}"'),
TemplatedFilter(
"notlike", "not like", "{c} not like :{p}", '{c} not like "{v}"'
"notlike", "not like", '"{c}" not like :{p}', '{c} not like "{v}"'
),
TemplatedFilter("glob", "glob", "{c} glob :{p}", '{c} glob "{v}"'),
TemplatedFilter("glob", "glob", '"{c}" glob :{p}', '{c} glob "{v}"'),
InFilter(),
NotInFilter(),
]
@ -354,13 +322,13 @@ class Filters:
TemplatedFilter(
"arraycontains",
"array contains",
""":{p} in (select value from json_each({t}.{c}))""",
""":{p} in (select value from json_each([{t}].[{c}]))""",
'{c} contains "{v}"',
),
TemplatedFilter(
"arraynotcontains",
"array does not contain",
""":{p} not in (select value from json_each({t}.{c}))""",
""":{p} not in (select value from json_each([{t}].[{c}]))""",
'{c} does not contain "{v}"',
),
]
@ -368,34 +336,36 @@ class Filters:
else []
)
+ [
TemplatedFilter("date", "date", "date({c}) = :{p}", '"{c}" is on date {v}'),
TemplatedFilter(
"isnull", "is null", "{c} is null", "{c} is null", no_argument=True
"date", "date", 'date("{c}") = :{p}', '"{c}" is on date {v}'
),
TemplatedFilter(
"isnull", "is null", '"{c}" is null', "{c} is null", no_argument=True
),
TemplatedFilter(
"notnull",
"is not null",
"{c} is not null",
'"{c}" is not null',
"{c} is not null",
no_argument=True,
),
TemplatedFilter(
"isblank",
"is blank",
"({c} is null or {c} = '')",
'("{c}" is null or "{c}" = "")',
"{c} is blank",
no_argument=True,
),
TemplatedFilter(
"notblank",
"is not blank",
"({c} is not null and {c} != '')",
'("{c}" is not null and "{c}" != "")',
"{c} is not blank",
no_argument=True,
),
]
)
_filters_by_key: ClassVar[dict[str, Filter]] = {f.key: f for f in _filters}
_filters_by_key = {f.key: f for f in _filters}
def __init__(self, pairs):
self.pairs = pairs

View file

@ -1,10 +1,9 @@
from datasette.utils.sqlite import sqlite3
from datasette.utils import documented
import itertools
import random
import string
from datasette.utils import documented
from datasette.utils.sqlite import sqlite3
__all__ = [
"EXTRA_DATABASE_SQL",
"TABLES",
@ -347,7 +346,9 @@ CREATE VIEW searchable_view_configured_by_metadata AS
+ '\nINSERT INTO no_primary_key VALUES ("RENDER_CELL_DEMO", "a202", "b202", "c202");\n'
+ "\n".join(
[
f'INSERT INTO compound_three_primary_keys VALUES ("{a}", "{b}", "{c}", "{content}");'
'INSERT INTO compound_three_primary_keys VALUES ("{a}", "{b}", "{c}", "{content}");'.format(
a=a, b=b, c=c, content=content
)
for a, b, c, content in generate_compound_rows(1001)
]
)

View file

@ -1,20 +1,9 @@
from datasette import Response, hookimpl
from .utils import add_cors_headers
from datasette import hookimpl, Response
@hookimpl(trylast=True)
def forbidden(datasette, request, message):
async def inner():
if (
request.path.split("?")[0].endswith(".json")
or "application/json" in (request.headers.get("accept") or "")
or request.headers.get("content-type") == "application/json"
):
headers = {}
if datasette.cors:
add_cors_headers(headers)
return Response.error(message, 403, headers=headers)
return Response.html(
await datasette.render_template(
"error.html",

View file

@ -1,21 +1,16 @@
import traceback
from markupsafe import Markup
from datasette import Response, hookimpl
from .utils import add_cors_headers, error_body
from datasette import hookimpl, Response
from .utils import add_cors_headers
from .utils.asgi import (
Base400,
)
from .views.base import DatasetteError
from markupsafe import Markup
import traceback
# Debugger imports are deliberate - they back the "pdb" setting, which drops
# into a debugger on unhandled exceptions
try:
import ipdb as pdb # noqa: T100
import ipdb as pdb
except ImportError:
import pdb # noqa: T100
import pdb
try:
import rich
@ -33,7 +28,6 @@ def handle_exception(datasette, request, exception):
rich.get_console().print_exception(show_locals=True)
title = None
plain_message = None
if isinstance(exception, Base400):
status = exception.status
info = {}
@ -42,7 +36,6 @@ def handle_exception(datasette, request, exception):
status = exception.status
info = exception.error_dict
message = exception.message
plain_message = exception.plain_message
if exception.message_is_html:
message = Markup(message)
title = exception.title
@ -52,13 +45,6 @@ def handle_exception(datasette, request, exception):
message = str(exception)
traceback.print_exc()
templates = [f"{status}.html", "error.html"]
headers = {}
if datasette.cors:
add_cors_headers(headers)
if request.path.split("?")[0].endswith(".json"):
body = dict(info)
body.update(error_body(plain_message or message, status))
return Response.json(body, status=status, headers=headers)
info.update(
{
"ok": False,
@ -67,18 +53,21 @@ def handle_exception(datasette, request, exception):
"title": title,
}
)
environment = datasette.get_jinja_environment(request)
template = environment.select_template(templates)
return Response.html(
await template.render_async(
dict(
headers = {}
if datasette.cors:
add_cors_headers(headers)
if request.path.split("?")[0].endswith(".json"):
return Response.json(info, status=status, headers=headers)
else:
return Response.html(
await datasette.render_template(
templates,
info,
urls=datasette.urls,
menu_links=list,
)
),
status=status,
headers=headers,
)
request=request,
view_name="error",
),
status=status,
headers=headers,
)
return inner

View file

@ -1,4 +1,5 @@
from pluggy import HookimplMarker, HookspecMarker
from pluggy import HookimplMarker
from pluggy import HookspecMarker
hookspec = HookspecMarker("datasette")
hookimpl = HookimplMarker("datasette")

View file

@ -1,13 +1,13 @@
import hashlib
from .utils import (
detect_spatialite,
detect_fts,
detect_primary_keys,
detect_spatialite,
escape_sqlite,
get_all_foreign_keys,
sqlite3,
table_columns,
sqlite3,
)
HASH_BLOCK_SIZE = 1024 * 1024
@ -95,10 +95,10 @@ def inspect_tables(conn, database_metadata):
""")
]
for t, table_info in tables.items():
for t in tables.keys():
for hidden_table in hidden_tables:
if t == hidden_table or t.startswith(hidden_table):
table_info["hidden"] = True
tables[t]["hidden"] = True
continue
return tables

View file

@ -21,7 +21,7 @@ class JumpSQL:
search_text: str | None = None,
display_name: str | None = None,
item_type: str = "menu",
) -> JumpSQL:
) -> "JumpSQL":
if search_text is None:
search_text = " ".join(
text for text in (label, display_name, description) if text is not None

View file

@ -1,11 +1,7 @@
import contextvars
from abc import ABC, abstractmethod
from dataclasses import dataclass
from typing import Any, NamedTuple
_SQLITE_IDENTIFIER_CASE = str.maketrans(
"ABCDEFGHIJKLMNOPQRSTUVWXYZ", "abcdefghijklmnopqrstuvwxyz"
)
import contextvars
# Context variable to track when permission checks should be skipped
_skip_permission_checks = contextvars.ContextVar(
@ -53,15 +49,6 @@ class Resource(ABC):
# Class-level metadata (subclasses must define these)
name: str = None # e.g., "table", "database", "model"
parent_class: type["Resource"] | None = None # e.g., DatabaseResource for tables
case_insensitive_child: bool = False
@classmethod
def normalize_child(cls, child: str | None) -> str | None:
"""Return a comparison key without changing the resource's display name."""
if cls.case_insensitive_child and child is not None:
# Match SQLite NOCASE: fold ASCII only, not Unicode lower/casefold.
return child.translate(_SQLITE_IDENTIFIER_CASE)
return child
# Instance-level optional extra attributes
reasons: list[str] | None = None
@ -85,8 +72,8 @@ class Resource(ABC):
)
def __repr__(self) -> str:
return (
f"{self.__class__.__name__}(parent={self.parent!r}, child={self.child!r})"
return "{}(parent={!r}, child={!r})".format(
self.__class__.__name__, self.parent, self.child
)
@property
@ -142,6 +129,7 @@ class Resource(ABC):
Must return two columns: parent, child
"""
pass
class AllowedResource(NamedTuple):
@ -159,11 +147,6 @@ class Action:
resource_class: type[Resource] | None = None
also_requires: str | None = None # Optional action name that must also be allowed
def normalize_child(self, child: str | None) -> str | None:
if self.resource_class is None:
return child
return self.resource_class.normalize_child(child)
@property
def takes_parent(self) -> bool:
"""

View file

@ -1,14 +1,20 @@
import importlib
import importlib.metadata as importlib_metadata
import importlib.resources as importlib_resources
import os
import sys
from pprint import pprint
import pluggy
from pprint import pprint
import sys
from . import hookspecs
if sys.version_info >= (3, 9):
import importlib.resources as importlib_resources
else:
import importlib_resources
if sys.version_info >= (3, 10):
import importlib.metadata as importlib_metadata
else:
import importlib_metadata
DEFAULT_PLUGINS = (
"datasette.publish.heroku",
"datasette.publish.cloudrun",
@ -18,7 +24,6 @@ DEFAULT_PLUGINS = (
"datasette.actor_auth_cookie",
"datasette.default_permissions",
"datasette.default_permissions.tokens",
"datasette.default_permissions.sqlite_statistics",
"datasette.default_actions",
"datasette.default_column_types",
"datasette.default_magic_parameters",
@ -26,7 +31,6 @@ DEFAULT_PLUGINS = (
"datasette.default_debug_menu",
"datasette.default_jump_items",
"datasette.default_database_actions",
"datasette.default_table_actions",
"datasette.default_query_actions",
"datasette.handle_exception",
"datasette.forbidden",
@ -80,7 +84,7 @@ if DATASETTE_LOAD_PLUGINS is not None:
# Ensure name can be found in plugin_to_distinfo later:
pm._plugin_distinfo.append((mod, distribution))
except importlib_metadata.PackageNotFoundError:
sys.stderr.write(f"Plugin {package_name} could not be found\n")
sys.stderr.write("Plugin {} could not be found\n".format(package_name))
# Load default plugins

View file

@ -1,17 +1,15 @@
from datasette import hookimpl
import click
import json
import os
import re
from subprocess import CalledProcessError, check_call, check_output
import click
from datasette import hookimpl
from ..utils import temporary_docker_directory
from .common import (
add_common_publish_arguments_and_options,
fail_if_publish_binary_not_installed,
)
from ..utils import temporary_docker_directory
@hookimpl
@ -221,7 +219,7 @@ def publish_subcommand(publish):
check_call(
"gcloud builds submit --tag {}{}".format(
image_id, f" --timeout {timeout}" if timeout else ""
image_id, " --timeout {}".format(timeout) if timeout else ""
),
shell=True,
)
@ -233,7 +231,7 @@ def publish_subcommand(publish):
("--min-instances", min_instances),
):
if value is not None:
extra_deploy_options.append(f"{option} {value}")
extra_deploy_options.append("{} {}".format(option, value))
check_call(
"gcloud run deploy --allow-unauthenticated --platform=managed --image {} {}{}".format(
image_id,
@ -260,16 +258,24 @@ def _ensure_artifact_registry(artifact_project, artifact_region, artifact_reposi
) from exc
describe_cmd = (
f"gcloud artifacts repositories describe {artifact_repository} --project {artifact_project} "
f"--location {artifact_region} --quiet"
"gcloud artifacts repositories describe {repo} --project {project} "
"--location {location} --quiet"
).format(
repo=artifact_repository,
project=artifact_project,
location=artifact_region,
)
try:
check_call(describe_cmd, shell=True)
return
except CalledProcessError:
create_cmd = (
f"gcloud artifacts repositories create {artifact_repository} --repository-format=docker "
f'--location {artifact_region} --project {artifact_project} --description "Datasette Cloud Run images" --quiet'
"gcloud artifacts repositories create {repo} --repository-format=docker "
'--location {location} --project {project} --description "Datasette Cloud Run images" --quiet'
).format(
repo=artifact_repository,
location=artifact_region,
project=artifact_project,
)
try:
check_call(create_cmd, shell=True)

View file

@ -1,11 +1,9 @@
from ..utils import StaticMount
import click
import os
import shutil
import sys
import click
from ..utils import StaticMount
def add_common_publish_arguments_and_options(subcommand):
for decorator in reversed(
@ -78,7 +76,9 @@ def fail_if_publish_binary_not_installed(binary, publish_target, install_link):
"""Exit (with error message) if ``binary` isn't installed"""
if not shutil.which(binary):
click.secho(
f"Publishing to {publish_target} requires {binary} to be installed and configured",
"Publishing to {publish_target} requires {binary} to be installed and configured".format(
publish_target=publish_target, binary=binary
),
bg="red",
fg="white",
bold=True,

View file

@ -1,21 +1,19 @@
from contextlib import contextmanager
from datasette import hookimpl
import click
import json
import os
import pathlib
import shlex
import shutil
import tempfile
from contextlib import contextmanager
from subprocess import call, check_output
import click
from datasette import hookimpl
from datasette.utils import link_or_copy, link_or_copy_directory, parse_metadata
import tempfile
from .common import (
add_common_publish_arguments_and_options,
fail_if_publish_binary_not_installed,
)
from datasette.utils import link_or_copy, link_or_copy_directory, parse_metadata
@hookimpl
@ -236,7 +234,7 @@ def temporary_heroku_directory(
extras.extend(["--static", f"{mount_point}:{mount_point}"])
quoted_files = " ".join(
[f"-i {shlex.quote(file_name)}" for file_name in file_names]
["-i {}".format(shlex.quote(file_name)) for file_name in file_names]
)
procfile_cmd = "web: datasette serve --host 0.0.0.0 {quoted_files} --cors --port $PORT --inspect-file inspect-data.json {extras}".format(
quoted_files=quoted_files, extras=" ".join(extras)

View file

@ -1,13 +1,11 @@
import json
from datasette.extras import extra_names_from_request
from datasette.utils import (
CustomJSONEncoder,
error_body,
path_from_row_pks,
remove_infinites,
sqlite3,
value_as_boolean,
remove_infinites,
CustomJSONEncoder,
path_from_row_pks,
sqlite3,
)
from datasette.utils.asgi import Response
@ -54,7 +52,8 @@ def json_renderer(request, args, data, error, truncated=None):
if error:
shape = "objects"
status_code = 400
data.update(error_body(error, status_code))
data["error"] = error
data["ok"] = False
if truncated is not None:
data["truncated"] = truncated
@ -88,8 +87,7 @@ def json_renderer(request, args, data, error, truncated=None):
object_rows[pk_string] = row
data = object_rows
if shape_error:
status_code = 400
data = error_body(shape_error, status_code)
data = {"ok": False, "error": shape_error}
elif shape == "array":
data = data["rows"]
@ -102,7 +100,12 @@ def json_renderer(request, args, data, error, truncated=None):
data["rows"] = [list(row.values()) for row in data["rows"]]
else:
status_code = 400
data = error_body(f"Invalid _shape: {shape}", status_code)
data = {
"ok": False,
"error": f"Invalid _shape: {shape}",
"status": 400,
"title": None,
}
# Don't include "columns" in output
# https://github.com/simonw/datasette/issues/2136

View file

@ -25,7 +25,6 @@ class TableResource(Resource):
name = "table"
parent_class = DatabaseResource
case_insensitive_child = True
def __init__(self, database: str, table: str):
super().__init__(parent=database, child=table)

File diff suppressed because it is too large Load diff

View file

@ -472,13 +472,11 @@ class ColumnChooser extends HTMLElement {
<span class="drag-item-check">
<input type="checkbox" ${this._checked.has(col) ? "checked" : ""}>
</span>
<span class="drag-item-label"></span>
<span class="drag-item-label">${col}</span>
</label>
<div class="drop-indicator"></div>
`;
li.querySelector(".drag-item-label").textContent = col;
li.querySelector("input").addEventListener("change", (e) => {
e.target.checked ? this._checked.add(col) : this._checked.delete(col);
this._updateCounts();

View file

@ -25,6 +25,29 @@ const DOM_SELECTORS = {
facetResults: ".facet-results [data-column]",
};
let editToolsPromise = null;
let autocompletePromise = null;
function datasettePath(path) {
const baseUrl = window.datasetteBaseUrl || "/";
return baseUrl.replace(/\/?$/, "/") + String(path || "").replace(/^\/+/, "");
}
function parseInsertDialogRow(value) {
if (!value) {
return {};
}
try {
const row = JSON.parse(value);
if (!row || typeof row !== "object" || Array.isArray(row)) {
throw new Error("row must be an object");
}
return row;
} catch (error) {
throw new Error("Invalid insert dialog row: " + error.message);
}
}
/**
* Monolith class for interacting with Datasette JS API
* Imported with DEFER, runs after main document parsed
@ -39,6 +62,62 @@ const datasetteManager = {
// Does pluginMetadata need to be serializable, or can we let it be stateful / have functions?
plugins: new Map(),
path: datasettePath,
loadAutocomplete: () => {
if (!window.customElements) {
return Promise.resolve(null);
}
if (customElements.get("datasette-autocomplete")) {
return Promise.resolve(customElements.get("datasette-autocomplete"));
}
if (!autocompletePromise) {
const url =
window.datasetteAutocompleteUrl ||
datasettePath("/-/static/autocomplete.js");
autocompletePromise = import(url).then(() =>
customElements.get("datasette-autocomplete"),
);
}
return autocompletePromise;
},
loadEditTools: () => {
if (window.__DATASETTE_EDIT_TOOLS__) {
if (window.__DATASETTE_EDIT_TOOLS__.install) {
window.__DATASETTE_EDIT_TOOLS__.install(datasetteManager);
}
return Promise.resolve(window.__DATASETTE_EDIT_TOOLS__);
}
if (!editToolsPromise) {
const url =
window.datasetteEditToolsUrl ||
datasettePath("/-/static/edit-tools.js");
editToolsPromise = import(url).then(() => {
if (!window.__DATASETTE_EDIT_TOOLS__) {
throw new Error("edit-tools.js did not register its API");
}
if (window.__DATASETTE_EDIT_TOOLS__.install) {
window.__DATASETTE_EDIT_TOOLS__.install(datasetteManager);
}
return window.__DATASETTE_EDIT_TOOLS__;
});
}
return editToolsPromise;
},
insertDialog: async (database, table, row, message, options) => {
const editTools = await datasetteManager.loadEditTools();
return editTools.insertDialog(
datasetteManager,
database,
table,
row,
message,
options,
);
},
registerPlugin: (name, pluginMetadata) => {
if (datasetteManager.plugins.has(name)) {
console.warn(`Warning -> plugin ${name} was redefined`);
@ -230,9 +309,7 @@ const datasetteManager = {
};
const initializeDatasette = () => {
// Hide the global behind __ prefix. Ideally they should be listening for the
// DATASETTE_EVENTS.INIT event to avoid the habit of reading from the window.
window.datasette = datasetteManager;
window.__DATASETTE__ = datasetteManager;
const initDatasetteEvent = new CustomEvent(DATASETTE_EVENTS.INIT, {
@ -240,6 +317,43 @@ const initializeDatasette = () => {
});
document.dispatchEvent(initDatasetteEvent);
document.addEventListener("click", function (event) {
const button = event.target.closest("[data-insert-dialog]");
if (!button) {
return;
}
event.preventDefault();
let row;
try {
row = parseInsertDialogRow(button.dataset.row || "{}");
} catch (error) {
console.error(error);
return;
}
const reloadOnInsert = button.hasAttribute("data-insert-dialog-reload");
datasetteManager
.insertDialog(
button.dataset.database,
button.dataset.table,
row,
button.dataset.message || "",
{ flashMessage: reloadOnInsert },
)
.then((result) => {
if (
reloadOnInsert &&
result &&
result.ok &&
result.status === "inserted"
) {
window.location.reload();
}
})
.catch((error) => {
console.error(error);
});
});
};
/**

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,56 @@
/*
https://github.com/luyilin/json-format-highlight
From https://unpkg.com/json-format-highlight@1.0.1/dist/json-format-highlight.js
MIT Licensed
*/
(function (global, factory) {
typeof exports === "object" && typeof module !== "undefined"
? (module.exports = factory())
: typeof define === "function" && define.amd
? define(factory)
: (global.jsonFormatHighlight = factory());
})(this, function () {
"use strict";
var defaultColors = {
keyColor: "dimgray",
numberColor: "lightskyblue",
stringColor: "lightcoral",
trueColor: "lightseagreen",
falseColor: "#f66578",
nullColor: "cornflowerblue",
};
function index(json, colorOptions) {
if (colorOptions === void 0) colorOptions = {};
if (!json) {
return;
}
if (typeof json !== "string") {
json = JSON.stringify(json, null, 2);
}
var colors = Object.assign({}, defaultColors, colorOptions);
json = json.replace(/&/g, "&").replace(/</g, "<").replace(/>/g, ">");
return json.replace(
/("(\\u[a-zA-Z0-9]{4}|\\[^u]|[^\\"])*"(\s*:)?|\b(true|false|null)\b|-?\d+(?:\.\d*)?(?:[eE][+]?\d+)?)/g,
function (match) {
var color = colors.numberColor;
if (/^"/.test(match)) {
color = /:$/.test(match) ? colors.keyColor : colors.stringColor;
} else {
color = /true/.test(match)
? colors.trueColor
: /false/.test(match)
? colors.falseColor
: /null/.test(match)
? colors.nullColor
: color;
}
return '<span style="color: ' + color + '">' + match + "</span>";
},
);
}
return index;
});

View file

@ -633,151 +633,32 @@ const initDatasetteTable = function (manager) {
});
};
function filterRowSelector(manager) {
return manager.selectors.filterRows || manager.selectors.filterRow;
}
function filterRowsWithControls(manager) {
return Array.from(
document.querySelectorAll(filterRowSelector(manager)),
).filter((el) => el.querySelector(".filter-op"));
}
function filterRowNumberFromName(name) {
var match = name && name.match(/^_filter_column_(\d+)$/);
return match ? parseInt(match[1], 10) : 0;
}
function nextFilterRowNumber(manager) {
return filterRowsWithControls(manager).reduce((max, row) => {
var column = row.querySelector("select");
return Math.max(max, filterRowNumberFromName(column && column.name));
}, 0) + 1;
}
function setFilterRowNumber(row, number) {
row.querySelector("select").name = `_filter_column_${number}`;
row.querySelector(".filter-op select").name = `_filter_op_${number}`;
row.querySelector("input.filter-value").name = `_filter_value_${number}`;
}
function resetFilterRow(row) {
row.querySelector("select").value = "";
row.querySelector(".filter-op select").value = "exact";
row.querySelector("input.filter-value").value = "";
}
function updateFilterRowButtons(manager) {
var rows = filterRowsWithControls(manager);
rows.forEach((row, index) => {
var removeButton = row.querySelector(".filter-row-remove");
var addButton = row.querySelector(".filter-row-add");
var column = row.querySelector("select");
if (removeButton) {
removeButton.hidden = index === 0;
}
if (addButton) {
addButton.hidden = index !== rows.length - 1 || !column.value;
}
var visibleButtonCount = [removeButton, addButton].filter(function (button) {
return button && !button.hidden;
}).length;
row.classList.toggle(
"filter-controls-row-has-buttons",
visibleButtonCount > 0,
);
row.classList.toggle(
"filter-controls-row-one-button",
visibleButtonCount === 1,
);
row.classList.toggle(
"filter-controls-row-two-buttons",
visibleButtonCount === 2,
);
});
}
function cloneFilterRow(row) {
var clone = row.cloneNode(true);
clone.querySelector("select").name = "_filter_column";
clone.querySelector(".filter-op select").name = "_filter_op";
clone.querySelector("input.filter-value").name = "_filter_value";
resetFilterRow(clone);
clone.querySelectorAll(".filter-row-icon").forEach((button) => button.remove());
return clone;
}
var FILTER_REMOVE_ICON_SVG = `<svg class="filter-row-remove-icon" aria-hidden="true" xmlns="http://www.w3.org/2000/svg" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.1" stroke-linecap="round" stroke-linejoin="round">
<path d="M3 6h18"></path>
<path d="M8 6V4a2 2 0 0 1 2-2h4a2 2 0 0 1 2 2v2"></path>
<path d="M19 6l-1 14a2 2 0 0 1-2 2H8a2 2 0 0 1-2-2L5 6"></path>
<path d="M10 11v6"></path>
<path d="M14 11v6"></path>
</svg>`;
var FILTER_ADD_ICON_SVG = `<svg class="filter-row-add-icon" aria-hidden="true" xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="3" stroke-linecap="round" stroke-linejoin="round">
<path d="M5 12h14"></path>
<path d="M12 5v14"></path>
</svg>`;
function addFilterRowButtons(row, manager) {
var removeButton = document.createElement("button");
removeButton.type = "button";
removeButton.className = "filter-row-icon filter-row-remove";
removeButton.setAttribute("aria-label", "Remove this filter");
removeButton.title = "Remove this filter";
removeButton.tabIndex = 0;
removeButton.innerHTML = FILTER_REMOVE_ICON_SVG;
removeButton.addEventListener("click", (ev) => {
var row = ev.currentTarget.closest(filterRowSelector(manager));
var rows = filterRowsWithControls(manager);
var rowIndex = rows.indexOf(row);
var focusRow = rows[rowIndex + 1] || rows[rowIndex - 1] || null;
row.remove();
updateFilterRowButtons(manager);
if (focusRow) {
var focusTarget =
focusRow.querySelector(".filter-row-add:not([hidden])") ||
focusRow.querySelector("select");
if (focusTarget) {
focusTarget.focus();
}
}
});
row.appendChild(removeButton);
var addButton = document.createElement("button");
addButton.type = "button";
addButton.className = "filter-row-icon filter-row-add";
addButton.setAttribute("aria-label", "Add another filter");
addButton.title = "Add another filter";
addButton.tabIndex = 0;
addButton.innerHTML = FILTER_ADD_ICON_SVG;
addButton.addEventListener("click", (ev) => {
var row = ev.currentTarget.closest(filterRowSelector(manager));
if (row.querySelector("select").name === "_filter_column") {
setFilterRowNumber(row, nextFilterRowNumber(manager));
}
var clone = cloneFilterRow(row);
addFilterRowButtons(clone, manager);
row.parentNode.insertBefore(clone, row.nextSibling);
updateFilterRowButtons(manager);
clone.querySelector("select").focus();
});
row.appendChild(addButton);
row.querySelector("select").addEventListener("change", () => {
updateFilterRowButtons(manager);
});
}
/* Add buttons to the filter rows */
/* Add x buttons to the filter rows */
function addButtonsToFilterRows(manager) {
var rows = filterRowsWithControls(manager);
var x = "✖";
var rows = Array.from(
document.querySelectorAll(manager.selectors.filterRow),
).filter((el) => el.querySelector(".filter-op"));
rows.forEach((row) => {
addFilterRowButtons(row, manager);
var a = document.createElement("a");
a.setAttribute("href", "#");
a.setAttribute("aria-label", "Remove this filter");
a.style.textDecoration = "none";
a.innerText = x;
a.addEventListener("click", (ev) => {
ev.preventDefault();
let row = ev.target.closest("div");
row.querySelector("select").value = "";
row.querySelector(".filter-op select").value = "exact";
row.querySelector("input.filter-value").value = "";
ev.target.closest("a").style.display = "none";
});
row.appendChild(a);
var column = row.querySelector("select");
if (!column.value) {
a.style.display = "none";
}
});
updateFilterRowButtons(manager);
}
/* Set up datalist autocomplete for filter values */
@ -806,11 +687,11 @@ function initAutocompleteForFilterValues(manager) {
});
}
createDataLists();
// When any filter column select changes, update the datalist
// When any select with name=_filter_column changes, update the datalist
document.body.addEventListener("change", function (event) {
if (event.target.name && event.target.name.startsWith("_filter_column")) {
if (event.target.name === "_filter_column") {
event.target
.closest(filterRowSelector(manager))
.closest(manager.selectors.filterRow)
.querySelector(".filter-value")
.setAttribute("list", "datalist-" + event.target.value);
}

View file

@ -1,9 +1,8 @@
from __future__ import annotations
import json
from collections.abc import Iterable
from dataclasses import dataclass
from typing import Any
import json
from typing import Any, Iterable
from .utils import tilde_encode, urlsafe_components
@ -63,6 +62,7 @@ def stored_query_to_dict(query: StoredQuery) -> dict[str, Any]:
"description_html": query.description_html,
"hide_sql": query.hide_sql,
"fragment": query.fragment,
"params": list(query.parameters),
"parameters": list(query.parameters),
"is_write": query.is_write,
"is_private": query.is_private,
@ -84,6 +84,7 @@ def stored_query_page_to_dict(page: StoredQueryPage) -> dict[str, Any]:
return {
"queries": [stored_query_to_dict(query) for query in page.queries],
"next": page.next,
"has_more": page.has_more,
"limit": page.limit,
}
@ -387,7 +388,7 @@ async def count_queries(
OR q.sql LIKE :query_search
)
""")
params["query_search"] = f"%{q}%"
params["query_search"] = "%{}%".format(q)
if is_write is not None:
where_clauses.append("q.is_write = :query_is_write")
params["query_is_write"] = int(bool(is_write))
@ -463,7 +464,7 @@ async def list_queries(
except ValueError:
components = []
if database is None and len(components) == 3:
where_clauses.append(f"""
where_clauses.append("""
(
q.database_name > :cursor_database
OR (
@ -477,12 +478,12 @@ async def list_queries(
)
)
)
""")
""".format(sort_key_sql=sort_key_sql))
params["cursor_database"] = components[0]
params["cursor_sort_key"] = components[1]
params["cursor_name"] = components[2]
elif database is not None and len(components) == 2:
where_clauses.append(f"""
where_clauses.append("""
(
{sort_key_sql} > :cursor_sort_key
OR (
@ -490,7 +491,7 @@ async def list_queries(
AND q.name > :cursor_name
)
)
""")
""".format(sort_key_sql=sort_key_sql))
params["cursor_sort_key"] = components[0]
params["cursor_name"] = components[1]
@ -503,7 +504,7 @@ async def list_queries(
OR q.sql LIKE :query_search
)
""")
params["query_search"] = f"%{q}%"
params["query_search"] = "%{}%".format(q)
if is_write is not None:
where_clauses.append("q.is_write = :query_is_write")
params["query_is_write"] = int(bool(is_write))

View file

@ -1,40 +0,0 @@
"""
Index of the documented template contexts for Datasette's core HTML pages.
This module deliberately contains no documentation strings of its own -
the documentation lives next to the code it describes:
- Every page renders a Context dataclass defined in its view module
(DatabaseContext, QueryContext in views/database.py, TableContext in
views/table.py, RowContext in views/row.py). Fields added by view code
carry ``help`` metadata; fields declared with from_extra() take their
documentation from the description on the matching Extra class in
views/table_extras.py.
- The keys render_template() adds to every page are documented in
TEMPLATE_BASE_CONTEXT in datasette/app.py, next to the code that adds
them.
The contract tests in tests/test_template_context.py assert that the real
rendered context for each page exactly matches what is documented, and
docs/template_context_doc.py generates docs/template_context.rst from the
same classes.
"""
from datasette.app import TEMPLATE_BASE_CONTEXT
from datasette.views.database import DatabaseContext, QueryContext
from datasette.views.row import RowContext
from datasette.views.table import TableContext
PAGES = {
"database": DatabaseContext,
"query": QueryContext,
"table": TableContext,
"row": RowContext,
}
def documented_context_keys(page_name):
"Set of every documented key for the named page, including base context keys"
return set(TEMPLATE_BASE_CONTEXT) | {
f.name for f in PAGES[page_name].documented_fields()
}

View file

@ -1,5 +1,5 @@
<script src="{{ static('sql-formatter-2.3.3.min.js') }}" defer></script>
<script src="{{ static('cm-editor-6.0.1.bundle.js') }}"></script>
<script src="{{ base_url }}-/static/sql-formatter-2.3.3.min.js" defer></script>
<script src="{{ base_url }}-/static/cm-editor-6.0.1.bundle.js"></script>
<style>
.cm-editor {
resize: both;

View file

@ -6,20 +6,8 @@
padding: 1.5em;
margin-bottom: 2em;
}
.permission-form form {
max-width: 60rem;
}
.permission-form-grid {
display: grid;
gap: 1.5rem;
grid-template-columns: repeat(2, minmax(0, 1fr));
}
.permission-form-result {
margin-top: 1rem;
max-width: 60rem;
}
.form-section {
margin-bottom: 1.25em;
margin-bottom: 1em;
}
.form-section label {
display: block;
@ -27,51 +15,22 @@
font-weight: bold;
}
.form-section input[type="text"],
.form-section input[type="number"],
.form-section select,
.permission-textarea {
background-color: #fff;
border: 1px solid #aaa;
border-radius: 4px;
box-sizing: border-box;
box-shadow: inset 0 1px 2px rgba(0, 0, 0, 0.08);
color: #222;
font-family: inherit;
font-size: 1rem;
line-height: 1.4;
max-width: none;
width: 100%;
}
.form-section input[type="text"] {
height: 3rem;
padding: 0.6rem 0.75rem;
}
.form-section input[type="number"] {
height: 3rem;
max-width: 7rem;
padding: 0.6rem 0.75rem;
}
.form-section select {
height: 3rem;
padding: 0.6rem 0.75rem;
}
.permission-textarea {
font-family: monospace;
min-height: 12rem;
padding: 0.75rem;
resize: vertical;
width: 100%;
max-width: 500px;
padding: 0.5em;
box-sizing: border-box;
border: 1px solid #ccc;
border-radius: 3px;
}
.form-section input[type="text"]:focus,
.form-section input[type="number"]:focus,
.form-section select:focus,
.permission-textarea:focus {
.form-section select:focus {
outline: 2px solid #0066cc;
border-color: #0066cc;
box-shadow: 0 0 0 3px rgba(0, 102, 204, 0.18);
outline: none;
}
.form-section small {
display: block;
margin-top: 0.45em;
margin-top: 0.3em;
color: #666;
}
.form-actions {
@ -183,9 +142,4 @@
text-align: center;
color: #666;
}
@media only screen and (max-width: 576px) {
.permission-form-grid {
grid-template-columns: minmax(0, 1fr);
}
}
</style>

View file

@ -44,10 +44,10 @@
</style>
<nav class="permissions-debug-tabs">
<a href="{{ urls.path('-/check') }}{{ query_string }}" {% if current_tab == "check" %}class="active"{% endif %}>Explain</a>
<a href="{{ urls.path('-/allowed') }}{{ query_string }}" {% if current_tab == "allowed" %}class="active"{% endif %}>Access map</a>
<a href="{{ urls.path('-/rules') }}{{ query_string }}" {% if current_tab == "rules" %}class="active"{% endif %}>Rule explorer</a>
<a href="{{ urls.path('-/permissions') }}" {% if current_tab == "permissions" %}class="active"{% endif %}>Activity</a>
<a href="{{ urls.path('-/permissions') }}" {% if current_tab == "permissions" %}class="active"{% endif %}>Playground</a>
<a href="{{ urls.path('-/check') }}{{ query_string }}" {% if current_tab == "check" %}class="active"{% endif %}>Check</a>
<a href="{{ urls.path('-/allowed') }}{{ query_string }}" {% if current_tab == "allowed" %}class="active"{% endif %}>Allowed</a>
<a href="{{ urls.path('-/rules') }}{{ query_string }}" {% if current_tab == "rules" %}class="active"{% endif %}>Rules</a>
<a href="{{ urls.path('-/actions') }}" {% if current_tab == "actions" %}class="active"{% endif %}>Actions</a>
<a href="{{ urls.path('-/allow-debug') }}" {% if current_tab == "allow_debug" %}class="active"{% endif %}>Allow debug</a>
</nav>

View file

@ -3,11 +3,29 @@
{% block title %}Debug allow rules{% endblock %}
{% block extra_head %}
{% include "_permission_ui_styles.html" %}
<style>
textarea {
height: 10em;
width: 95%;
box-sizing: border-box;
padding: 0.5em;
border: 2px dotted black;
}
.two-col {
display: inline-block;
width: 48%;
}
.two-col label {
width: 48%;
}
p.message-warning {
white-space: pre-wrap;
}
@media only screen and (max-width: 576px) {
.two-col {
width: 100%;
}
}
</style>
{% endblock %}
@ -20,28 +38,24 @@ p.message-warning {
<p>Use this tool to try out different actor and allow combinations. See <a href="https://docs.datasette.io/en/stable/authentication.html#defining-permissions-with-allow-blocks">Defining permissions with "allow" blocks</a> for documentation.</p>
<div class="permission-form">
<form class="core" action="{{ urls.path('-/allow-debug') }}" method="get">
<div class="permission-form-grid">
<div class="form-section">
<label for="allow-block">Allow block</label>
<textarea class="permission-textarea" id="allow-block" name="allow">{{ allow_input }}</textarea>
</div>
<div class="form-section">
<label for="allow-actor">Actor</label>
<textarea class="permission-textarea" id="allow-actor" name="actor">{{ actor_input }}</textarea>
</div>
</div>
<div class="form-actions">
<button type="submit" class="submit-btn">Apply allow block to actor</button>
</div>
</form>
<form class="core" action="{{ urls.path('-/allow-debug') }}" method="get" style="margin-bottom: 1em">
<div class="two-col">
<p><label>Allow block</label></p>
<textarea name="allow">{{ allow_input }}</textarea>
</div>
<div class="two-col">
<p><label>Actor</label></p>
<textarea name="actor">{{ actor_input }}</textarea>
</div>
<div style="margin-top: 1em;">
<input type="submit" value="Apply allow block to actor">
</div>
</form>
{% if error %}<p class="message-warning permission-form-result">{{ error }}</p>{% endif %}
{% if error %}<p class="message-warning">{{ error }}</p>{% endif %}
{% if result == "True" %}<p class="message-info permission-form-result">Result: allow</p>{% endif %}
{% if result == "True" %}<p class="message-info">Result: allow</p>{% endif %}
{% if result == "False" %}<p class="message-error permission-form-result">Result: deny</p>{% endif %}
</div>
{% if result == "False" %}<p class="message-error">Result: deny</p>{% endif %}
{% endblock %}

View file

@ -3,6 +3,7 @@
{% block title %}API Explorer{% endblock %}
{% block extra_head %}
<script src="{{ base_url }}-/static/json-format-highlight-1.0.1.js"></script>
{% endblock %}
{% block content %}
@ -125,7 +126,7 @@ getForm.addEventListener("submit", (ev) => {
document.getElementById('response-status').textContent = response.status;
return response.json();
}).then((data) => {
output.querySelector('pre').textContent = JSON.stringify(data, null, 2);
output.querySelector('pre').innerHTML = jsonFormatHighlight(data);
errorList.style.display = 'none';
}).catch((error) => {
alert(error);
@ -173,7 +174,7 @@ postForm.addEventListener("submit", (ev) => {
} else {
errorList.style.display = 'none';
}
output.querySelector('pre').textContent = JSON.stringify(data, null, 2);
output.querySelector('pre').innerHTML = jsonFormatHighlight(data);
output.style.display = 'block';
}).catch(err => {
alert("Error: " + err);

View file

@ -2,13 +2,18 @@
<html lang="en">
<head>
<title>{% block title %}{% endblock %}</title>
<link rel="stylesheet" href="{{ static('app.css') }}">
<link rel="stylesheet" href="{{ urls.static('app.css') }}?{{ app_css_hash }}">
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
{% for url in extra_css_urls %}
<link rel="stylesheet" href="{{ url.url }}"{% if url.get("sri") %} integrity="{{ url.sri }}" crossorigin="anonymous"{% endif %}>
{% endfor %}
<script>window.datasetteVersion = '{{ datasette_version }}';</script>
<script src="{{ static('datasette-manager.js') }}" defer></script>
<script>
window.datasetteVersion = {{ datasette_version|tojson }};
window.datasetteBaseUrl = {{ base_url|tojson }};
window.datasetteEditToolsUrl = {{ (urls.static('edit-tools.js') ~ '?hash=' ~ edit_tools_js_hash)|tojson }};
window.datasetteAutocompleteUrl = {{ urls.static('autocomplete.js')|tojson }};
</script>
<script src="{{ urls.static('datasette-manager.js') }}" defer></script>
{% for url in extra_js_urls %}
<script {% if url.module %}type="module" {% endif %}src="{{ url.url }}"{% if url.get("sri") %} integrity="{{ url.sri }}" crossorigin="anonymous"{% endif %}></script>
{% endfor %}
@ -70,7 +75,7 @@
{% endfor %}
{% if select_templates %}<!-- Templates considered: {{ select_templates|join(", ") }} -->{% endif %}
<script src="{{ static('navigation-search.js') }}" defer></script>
<script src="{{ urls.static('navigation-search.js') }}" defer></script>
<navigation-search url="{{ urls.path("/-/jump") }}"></navigation-search>
</body>
</html>

View file

@ -6,10 +6,6 @@
{{- super() -}}
{% include "_codemirror.html" %}
{% include "_sql_parameter_styles.html" %}
{% if database_page_data.createTable %}
<script>window._datasetteDatabaseData = {{ database_page_data|tojson }};</script>
<script src="{{ static('edit-tools.js') }}" defer></script>
{% endif %}
{% endblock %}
{% block body_class %}db db-{{ database|to_css_class }}{% endblock %}
@ -76,7 +72,7 @@
<div class="db-table">
<h3><a href="{{ urls.table(database, table.name) }}">{{ table.name }}</a>{% if table.private %} 🔒{% endif %}{% if table.hidden %}<em> (hidden)</em>{% endif %}</h3>
<p><em>{% for column in table.columns %}{{ column }}{% if not loop.last %}, {% endif %}{% endfor %}</em></p>
<p>{% if table.count is none %}Many rows{% elif table.count_truncated %}&gt;{{ "{:,}".format(table.count - 1) }} rows{% else %}{{ "{:,}".format(table.count) }} row{% if table.count == 1 %}{% else %}s{% endif %}{% endif %}</p>
<p>{% if table.count is none %}Many rows{% elif table.count == count_limit + 1 %}&gt;{{ "{:,}".format(count_limit) }} rows{% else %}{{ "{:,}".format(table.count) }} row{% if table.count == 1 %}{% else %}s{% endif %}{% endif %}</p>
</div>
{% endif %}
{% endfor %}

View file

@ -9,7 +9,7 @@
{% include "_permissions_debug_tabs.html" %}
<p style="margin-bottom: 2em;">
This Datasette instance has registered {{ data.actions|length }} action{{ data.actions|length != 1 and "s" or "" }}.
This Datasette instance has registered {{ data|length }} action{{ data|length != 1 and "s" or "" }}.
Actions are used by the permission system to control access to different features.
</p>
@ -26,7 +26,7 @@
</tr>
</thead>
<tbody>
{% for action in data.actions %}
{% for action in data %}
<tr>
<td><strong>{{ action.name }}</strong></td>
<td>{% if action.abbr %}<code>{{ action.abbr }}</code>{% endif %}</td>

View file

@ -3,6 +3,7 @@
{% block title %}Allowed Resources{% endblock %}
{% block extra_head %}
<script src="{{ base_url }}-/static/json-format-highlight-1.0.1.js"></script>
{% include "_permission_ui_styles.html" %}
{% include "_debug_common_functions.html" %}
{% endblock %}
@ -48,7 +49,7 @@
<div class="form-section">
<label for="page_size">Page size:</label>
<input type="number" id="page_size" name="_size" value="50" min="1" max="200">
<input type="number" id="page_size" name="page_size" value="50" min="1" max="200" style="max-width: 100px;">
<small>Number of results per page (max 200)</small>
</div>
@ -87,7 +88,7 @@ const hasDebugPermission = {{ 'true' if has_debug_permission else 'false' }};
(function() {
const params = populateFormFromURL();
const action = params.get('action');
const page = params.get('_page');
const page = params.get('page');
if (action) {
fetchResults(page ? parseInt(page) : 1);
}
@ -101,14 +102,14 @@ async function fetchResults(page = 1) {
const params = new URLSearchParams();
for (const [key, value] of formData.entries()) {
if (value && key !== '_size' && key !== '_page') {
if (value && key !== 'page_size') {
params.append(key, value);
}
}
const pageSize = document.getElementById('page_size').value || '50';
params.append('_page', page.toString());
params.append('_size', pageSize);
params.append('page', page.toString());
params.append('page_size', pageSize);
try {
const response = await fetch('{{ urls.path("-/allowed.json") }}?' + params.toString(), {
@ -197,7 +198,7 @@ function displayResults(data) {
}
// Update raw JSON
document.getElementById('raw-json').textContent = JSON.stringify(data, null, 2);
document.getElementById('raw-json').innerHTML = jsonFormatHighlight(data);
}
function displayError(data) {
@ -207,7 +208,7 @@ function displayError(data) {
resultsContent.innerHTML = `<div class="error-message">Error: ${escapeHtml(data.error || 'Unknown error')}</div>`;
document.getElementById('raw-json').textContent = JSON.stringify(data, null, 2);
document.getElementById('raw-json').innerHTML = jsonFormatHighlight(data);
}
// Disable child input if parent is empty

View file

@ -4,7 +4,7 @@
{% block extra_head %}
{{ super() }}
<script src="{{ static('autocomplete.js') }}" defer></script>
<script src="{{ urls.static('autocomplete.js') }}" defer></script>
{% endblock %}
{% block content %}

View file

@ -1,8 +1,9 @@
{% extends "base.html" %}
{% block title %}Explain a permission decision{% endblock %}
{% block title %}Permission Check{% endblock %}
{% block extra_head %}
<script src="{{ base_url }}-/static/json-format-highlight-1.0.1.js"></script>
{% include "_permission_ui_styles.html" %}
{% include "_debug_common_functions.html" %}
<style>
@ -12,35 +13,29 @@
border-radius: 5px;
}
#output.allowed {
background-color: #f3fbf4;
background-color: #e8f5e9;
border: 2px solid #4caf50;
}
#output.denied {
background-color: #fff7f7;
background-color: #ffebee;
border: 2px solid #f44336;
}
#output h2 {
margin-top: 0;
}
#output h3 {
margin-bottom: 0.5em;
}
#output .result-badge,
.effect-badge,
.rule-status {
#output .result-badge {
display: inline-block;
padding: 0.2em 0.5em;
padding: 0.3em 0.8em;
border-radius: 3px;
font-weight: bold;
font-size: 1.1em;
}
#output .allowed-badge,
.effect-allow {
background-color: #2e7d32;
#output .allowed-badge {
background-color: #4caf50;
color: white;
}
#output .denied-badge,
.effect-deny {
background-color: #c62828;
#output .denied-badge {
background-color: #f44336;
color: white;
}
.details-section {
@ -53,130 +48,70 @@
.details-section dd {
margin-left: 1em;
}
.explanation-section {
background: rgba(255, 255, 255, 0.75);
border: 1px solid #ddd;
border-radius: 4px;
margin-top: 1em;
padding: 0 1em 1em;
}
.rules-table {
border-collapse: collapse;
width: 100%;
}
.rules-table th,
.rules-table td {
border-bottom: 1px solid #ddd;
padding: 0.5em;
text-align: left;
vertical-align: top;
}
.rule-status {
background: #e8f5e9;
color: #1b5e20;
}
.rule-ignored {
background: #eee;
color: #555;
font-weight: normal;
}
.requirement-allowed {
color: #1b5e20;
}
.requirement-denied {
color: #b71c1c;
}
@media only screen and (max-width: 576px) {
.rules-table,
.rules-table tbody,
.rules-table tr,
.rules-table td {
display: block;
}
.rules-table thead {
display: none;
}
.rules-table td::before {
content: attr(data-label) ": ";
font-weight: bold;
}
}
</style>
{% endblock %}
{% block content %}
<h1>Explain a permission decision</h1>
<h1>Permission check</h1>
{% set current_tab = "check" %}
{% include "_permissions_debug_tabs.html" %}
<p>Test an actor, action and resource. The result explains which rules matched, which specificity level won, and whether actor restrictions or required actions changed the verdict.</p>
<p>Use this tool to test permission checks for the current actor. It queries the <code>/-/check.json</code> API endpoint.</p>
{% if request.actor %}
<p>Current actor: <strong>{{ request.actor.get("id", "anonymous") }}</strong></p>
{% else %}
<p>Current actor: <strong>anonymous (not logged in)</strong></p>
{% endif %}
<div class="permission-form">
<form id="check-form" method="get" action="{{ urls.path('-/check') }}">
<form id="check-form" method="get" action="{{ urls.path("-/check") }}">
<div class="form-section">
<label for="actor">Actor JSON:</label>
<textarea class="permission-textarea" id="actor" name="actor">{{ actor_json }}</textarea>
<small>Use <code>null</code> for an anonymous actor. This actor is simulated; it does not change who you are signed in as.</small>
</div>
<div class="form-section">
<label for="action">Action:</label>
<label for="action">Action (permission name):</label>
<select id="action" name="action" required>
<option value="">Select an action...</option>
{% for action in actions %}
<option value="{{ action.name }}">{{ action.name }}{% if action.description %} — {{ action.description }}{% endif %}</option>
{% for action_name in sorted_actions %}
<option value="{{ action_name }}">{{ action_name }}</option>
{% endfor %}
</select>
<small id="action-help">The operation to evaluate</small>
<small>The permission action to check</small>
</div>
<div class="form-section" id="parent-section">
<label for="parent">Parent resource:</label>
<div class="form-section">
<label for="parent">Parent resource (optional):</label>
<input type="text" id="parent" name="parent" placeholder="e.g., database name">
<small>The database or other parent resource</small>
<small>For database-level permissions, specify the database name</small>
</div>
<div class="form-section" id="child-section">
<label for="child">Child resource:</label>
<input type="text" id="child" name="child" placeholder="e.g., table or query name">
<small>The table, query or other child resource</small>
<div class="form-section">
<label for="child">Child resource (optional):</label>
<input type="text" id="child" name="child" placeholder="e.g., table name">
<small>For table-level permissions, specify the table name (requires parent)</small>
</div>
<div class="form-actions">
<button type="submit" class="submit-btn" id="submit-btn">Explain decision</button>
<button type="submit" class="submit-btn" id="submit-btn">Check Permission</button>
</div>
</form>
</div>
<div id="output" style="display: none;">
<h2>Result: <span class="result-badge" id="result-badge"></span></h2>
<p id="result-summary"></p>
<dl class="details-section">
<dt>Actor:</dt>
<dd><code id="result-actor"></code></dd>
<dt>Action:</dt>
<dd><code id="result-action"></code></dd>
<dt>Resource:</dt>
<dd><code id="result-resource"></code></dd>
<dd id="result-action"></dd>
<dt>Resource Path:</dt>
<dd id="result-resource"></dd>
<dt>Actor ID:</dt>
<dd id="result-actor"></dd>
<div id="additional-details"></div>
</dl>
<section class="explanation-section">
<h3>Matching rules</h3>
<div id="matching-rules"></div>
</section>
<section class="explanation-section" id="restrictions-section">
<h3>Actor restrictions</h3>
<div id="restriction-results"></div>
</section>
<section class="explanation-section" id="requirements-section">
<h3>Required actions</h3>
<div id="requirement-results"></div>
</section>
<details style="margin-top: 1em;">
<summary style="cursor: pointer; font-weight: bold;">Raw JSON response</summary>
<pre id="raw-json" style="margin-top: 1em; padding: 1em; background-color: #f5f5f5; border: 1px solid #ddd; border-radius: 3px; overflow-x: auto;"></pre>
@ -184,134 +119,152 @@
</div>
<script>
const actions = Object.fromEntries({{ actions|tojson }}.map(action => [action.name, action]));
const form = document.getElementById('check-form');
const output = document.getElementById('output');
const submitBtn = document.getElementById('submit-btn');
const actionSelect = document.getElementById('action');
function updateResourceFields() {
const action = actions[actionSelect.value];
document.getElementById('parent-section').style.display = action && action.takes_parent ? 'block' : 'none';
document.getElementById('child-section').style.display = action && action.takes_child ? 'block' : 'none';
let help = action && action.description ? action.description : 'The operation to evaluate';
if (action && action.also_requires) {
help += `; also requires ${action.also_requires}`;
}
document.getElementById('action-help').textContent = help;
}
async function performCheck() {
submitBtn.disabled = true;
submitBtn.textContent = 'Explaining...';
const params = new URLSearchParams(new FormData(form));
submitBtn.textContent = 'Checking...';
const formData = new FormData(form);
const params = new URLSearchParams();
for (const [key, value] of formData.entries()) {
if (value) {
params.append(key, value);
}
}
try {
const response = await fetch('{{ urls.path("-/check.json") }}?' + params.toString(), {
headers: {'Accept': 'application/json'}
method: 'GET',
headers: {
'Accept': 'application/json',
}
});
const data = await response.json();
if (response.ok) {
displayResult(data);
} else {
displayError(data);
}
} catch (error) {
displayError({error: error.message});
alert('Error: ' + error.message);
} finally {
submitBtn.disabled = false;
submitBtn.textContent = 'Explain decision';
submitBtn.textContent = 'Check Permission';
}
}
// Populate form on initial load
(function() {
const params = populateFormFromURL();
const action = params.get('action');
if (action) {
performCheck();
}
})();
function displayResult(data) {
output.style.display = 'block';
// Set badge and styling
const resultBadge = document.getElementById('result-badge');
output.className = data.allowed ? 'allowed' : 'denied';
resultBadge.className = `result-badge ${data.allowed ? 'allowed-badge' : 'denied-badge'}`;
resultBadge.textContent = data.allowed ? 'ALLOWED ✓' : 'DENIED ✗';
document.getElementById('result-summary').textContent = data.explanation.summary;
document.getElementById('result-actor').textContent = data.actor === null ? 'anonymous' : JSON.stringify(data.actor);
document.getElementById('result-action').textContent = data.action;
document.getElementById('result-resource').textContent = data.resource.path;
displayRules(data.explanation);
displayRestrictions(data.explanation.restrictions);
displayRequirements(data.explanation.required_actions);
document.getElementById('raw-json').textContent = JSON.stringify(data, null, 2);
}
function displayRules(explanation) {
const container = document.getElementById('matching-rules');
if (!explanation.matched_rules.length) {
container.innerHTML = '<p>No rules matched. Datasette denies access when there is no matching rule.</p>';
return;
if (data.allowed) {
output.className = 'allowed';
resultBadge.className = 'result-badge allowed-badge';
resultBadge.textContent = 'ALLOWED ✓';
} else {
output.className = 'denied';
resultBadge.className = 'result-badge denied-badge';
resultBadge.textContent = 'DENIED ✗';
}
let html = '<table class="rules-table"><thead><tr><th>Effect</th><th>Scope</th><th>Source</th><th>Reason</th><th>Role in decision</th></tr></thead><tbody>';
for (const rule of explanation.matched_rules) {
const status = rule.decisive
? '<span class="rule-status">Decisive</span>'
: `<span class="rule-status rule-ignored">${escapeHtml(rule.ignored_because)}</span>`;
html += '<tr>';
html += `<td data-label="Effect"><span class="effect-badge effect-${rule.effect}">${rule.effect.toUpperCase()}</span></td>`;
html += `<td data-label="Scope">${escapeHtml(rule.scope)}</td>`;
html += `<td data-label="Source"><code>${escapeHtml(rule.source || 'unknown')}</code></td>`;
html += `<td data-label="Reason">${escapeHtml(rule.reason || 'No reason supplied')}</td>`;
html += `<td data-label="Role in decision">${status}</td>`;
html += '</tr>';
// Basic details
document.getElementById('result-action').textContent = data.action || 'N/A';
document.getElementById('result-resource').textContent = data.resource?.path || '/';
document.getElementById('result-actor').textContent = data.actor_id || 'anonymous';
// Additional details
const additionalDetails = document.getElementById('additional-details');
additionalDetails.innerHTML = '';
if (data.reason !== undefined) {
const dt = document.createElement('dt');
dt.textContent = 'Reason:';
const dd = document.createElement('dd');
dd.textContent = data.reason || 'N/A';
additionalDetails.appendChild(dt);
additionalDetails.appendChild(dd);
}
container.innerHTML = html + '</tbody></table>';
}
function displayRestrictions(restrictions) {
const section = document.getElementById('restrictions-section');
const container = document.getElementById('restriction-results');
section.style.display = restrictions.length ? 'block' : 'none';
container.innerHTML = restrictions.map(restriction => {
const className = restriction.allowed ? 'requirement-allowed' : 'requirement-denied';
const verdict = restriction.allowed ? 'INCLUDED ✓' : 'EXCLUDED ✗';
return `<p class="${className}"><strong>${verdict}</strong> by <code>${escapeHtml(restriction.source || 'unknown')}</code>: ${escapeHtml(restriction.reason)}</p>`;
}).join('');
}
if (data.source_plugin !== undefined) {
const dt = document.createElement('dt');
dt.textContent = 'Source Plugin:';
const dd = document.createElement('dd');
dd.textContent = data.source_plugin || 'N/A';
additionalDetails.appendChild(dt);
additionalDetails.appendChild(dd);
}
function displayRequirements(requirements) {
const section = document.getElementById('requirements-section');
const container = document.getElementById('requirement-results');
section.style.display = requirements.length ? 'block' : 'none';
container.innerHTML = requirements.map(requirement => {
const className = requirement.allowed ? 'requirement-allowed' : 'requirement-denied';
const verdict = requirement.allowed ? 'ALLOWED ✓' : 'DENIED ✗';
return `<p class="${className}"><strong>${escapeHtml(requirement.action)}: ${verdict}</strong> — ${escapeHtml(requirement.summary)}</p>`;
}).join('');
if (data.used_default !== undefined) {
const dt = document.createElement('dt');
dt.textContent = 'Used Default:';
const dd = document.createElement('dd');
dd.textContent = data.used_default ? 'Yes' : 'No';
additionalDetails.appendChild(dt);
additionalDetails.appendChild(dd);
}
if (data.depth !== undefined) {
const dt = document.createElement('dt');
dt.textContent = 'Depth:';
const dd = document.createElement('dd');
dd.textContent = data.depth;
additionalDetails.appendChild(dt);
additionalDetails.appendChild(dd);
}
// Raw JSON
document.getElementById('raw-json').innerHTML = jsonFormatHighlight(data);
// Scroll to output
output.scrollIntoView({ behavior: 'smooth', block: 'nearest' });
}
function displayError(data) {
output.style.display = 'block';
output.className = 'denied';
const resultBadge = document.getElementById('result-badge');
resultBadge.className = 'result-badge denied-badge';
resultBadge.textContent = 'ERROR';
document.getElementById('result-summary').textContent = data.error || 'Unknown error';
document.getElementById('result-actor').textContent = '—';
document.getElementById('result-action').textContent = '—';
document.getElementById('result-resource').textContent = '—';
document.getElementById('matching-rules').innerHTML = '';
document.getElementById('restrictions-section').style.display = 'none';
document.getElementById('requirements-section').style.display = 'none';
document.getElementById('raw-json').textContent = JSON.stringify(data, null, 2);
document.getElementById('result-action').textContent = 'N/A';
document.getElementById('result-resource').textContent = 'N/A';
document.getElementById('result-actor').textContent = 'N/A';
const additionalDetails = document.getElementById('additional-details');
additionalDetails.innerHTML = '<dt>Error:</dt><dd>' + (data.error || 'Unknown error') + '</dd>';
document.getElementById('raw-json').innerHTML = jsonFormatHighlight(data);
output.scrollIntoView({ behavior: 'smooth', block: 'nearest' });
}
form.addEventListener('submit', event => {
event.preventDefault();
performCheck();
});
actionSelect.addEventListener('change', updateResourceFields);
// Disable child input if parent is empty
const parentInput = document.getElementById('parent');
const childInput = document.getElementById('child');
(function initializeFromUrl() {
const params = populateFormFromURL();
updateResourceFields();
if (params.get('action')) {
performCheck();
childInput.addEventListener('focus', () => {
if (!parentInput.value) {
alert('Please specify a parent resource first before adding a child resource.');
parentInput.focus();
}
})();
});
</script>
{% endblock %}

View file

@ -1,6 +1,6 @@
{% extends "base.html" %}
{% block title %}Permission activity{% endblock %}
{% block title %}Debug permissions{% endblock %}
{% block extra_head %}
{% include "_permission_ui_styles.html" %}
@ -20,45 +20,60 @@
.check-action, .check-when, .check-result {
font-size: 1.3em;
}
textarea {
height: 10em;
width: 95%;
box-sizing: border-box;
padding: 0.5em;
border: 2px dotted black;
}
.two-col {
display: inline-block;
width: 48%;
}
.two-col label {
width: 48%;
}
@media only screen and (max-width: 576px) {
.two-col {
width: 100%;
}
}
</style>
{% endblock %}
{% block content %}
<h1>Permission activity</h1>
<h1>Permission playground</h1>
{% set current_tab = "permissions" %}
{% include "_permissions_debug_tabs.html" %}
<h2>Raw simulator</h2>
<p>This form runs a hypothetical permission check and returns its raw explanation JSON. Use the <a href="{{ urls.path('-/check') }}">Explain tool</a> for a visual explanation of the same decision.</p>
<p>This tool lets you simulate an actor and a permission check for that actor.</p>
<div class="permission-form">
<form action="{{ urls.path('-/permissions') }}" id="debug-post" method="post">
<div class="permission-form-grid">
<div>
<div class="form-section">
<label for="activity-actor">Actor</label>
<textarea class="permission-textarea" id="activity-actor" name="actor">{% if actor_input %}{{ actor_input }}{% else %}{"id": "root"}{% endif %}</textarea>
</div>
<div class="two-col">
<div class="form-section">
<label>Actor</label>
<textarea name="actor">{% if actor_input %}{{ actor_input }}{% else %}{"id": "root"}{% endif %}</textarea>
</div>
<div>
<div class="form-section">
<label for="permission">Action</label>
<select name="permission" id="permission">
{% for permission in permissions %}
<option value="{{ permission.name }}">{{ permission.name }}</option>
{% endfor %}
</select>
</div>
<div class="form-section">
<label for="resource_1">Parent</label>
<input type="text" id="resource_1" name="resource_1" placeholder="e.g., database name">
</div>
<div class="form-section">
<label for="resource_2">Child</label>
<input type="text" id="resource_2" name="resource_2" placeholder="e.g., table name">
</div>
</div>
<div class="two-col" style="vertical-align: top">
<div class="form-section">
<label for="permission">Action</label>
<select name="permission" id="permission">
{% for permission in permissions %}
<option value="{{ permission.name }}">{{ permission.name }}</option>
{% endfor %}
</select>
</div>
<div class="form-section">
<label for="resource_1">Parent</label>
<input type="text" id="resource_1" name="resource_1" placeholder="e.g., database name">
</div>
<div class="form-section">
<label for="resource_2">Child</label>
<input type="text" id="resource_2" name="resource_2" placeholder="e.g., table name">
</div>
</div>
<div class="form-actions">
@ -110,7 +125,7 @@ debugPost.addEventListener('submit', function(ev) {
});
</script>
<h2>Recent permission checks</h2>
<h1>Recent permissions checks</h1>
<p>
{% if filter != "all" %}<a href="?filter=all">All</a>{% else %}<strong>All</strong>{% endif %},

View file

@ -3,6 +3,7 @@
{% block title %}Permission Rules{% endblock %}
{% block extra_head %}
<script src="{{ base_url }}-/static/json-format-highlight-1.0.1.js"></script>
{% include "_permission_ui_styles.html" %}
{% include "_debug_common_functions.html" %}
{% endblock %}
@ -36,7 +37,7 @@
<div class="form-section">
<label for="page_size">Page size:</label>
<input type="number" id="page_size" name="_size" value="50" min="1" max="200">
<input type="number" id="page_size" name="page_size" value="50" min="1" max="200" style="max-width: 100px;">
<small>Number of results per page (max 200)</small>
</div>
@ -74,7 +75,7 @@ const submitBtn = document.getElementById('submit-btn');
(function() {
const params = populateFormFromURL();
const action = params.get('action');
const page = params.get('_page');
const page = params.get('page');
if (action) {
fetchResults(page ? parseInt(page) : 1);
}
@ -88,14 +89,14 @@ async function fetchResults(page = 1) {
const params = new URLSearchParams();
for (const [key, value] of formData.entries()) {
if (value && key !== '_size' && key !== '_page') {
if (value && key !== 'page_size') {
params.append(key, value);
}
}
const pageSize = document.getElementById('page_size').value || '50';
params.append('_page', page.toString());
params.append('_size', pageSize);
params.append('page', page.toString());
params.append('page_size', pageSize);
try {
const response = await fetch('{{ urls.path("-/rules.json") }}?' + params.toString(), {
@ -184,7 +185,7 @@ function displayResults(data) {
}
// Update raw JSON
document.getElementById('raw-json').textContent = JSON.stringify(data, null, 2);
document.getElementById('raw-json').innerHTML = jsonFormatHighlight(data);
}
function displayError(data) {
@ -194,7 +195,7 @@ function displayError(data) {
resultsContent.innerHTML = `<div class="error-message">Error: ${escapeHtml(data.error || 'Unknown error')}</div>`;
document.getElementById('raw-json').textContent = JSON.stringify(data, null, 2);
document.getElementById('raw-json').innerHTML = jsonFormatHighlight(data);
}
</script>

View file

@ -2,7 +2,7 @@
<html lang="en">
<head>
<title>Datasette: Pattern Portfolio</title>
<link rel="stylesheet" href="{{ static('app.css') }}">
<link rel="stylesheet" href="{{ base_url }}-/static/app.css?{{ app_css_hash }}">
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
<meta name="robots" content="noindex">
<style></style>
@ -202,9 +202,9 @@
<h3>3 rows
where characteristic_id = 2
</h3>
<form class="core filters" action="{{ base_url }}fixtures/roadside_attraction_characteristics" method="get">
<form class="filters" action="{{ base_url }}fixtures/roadside_attraction_characteristics" method="get">
<div class="search-row"><label for="_search">Search:</label><input id="_search" type="search" name="_search" value=""></div>
<div class="filter-row filter-controls-row">
<div class="filter-row">
<div class="select-wrapper">
<select name="_filter_column_1">
<option value="">- remove filter -</option>
@ -238,7 +238,7 @@
</select>
</div><input type="text" name="_filter_value_1" class="filter-value" value="2">
</div>
<div class="filter-row filter-controls-row">
<div class="filter-row">
<div class="select-wrapper">
<select name="_filter_column">
<option value="">- column -</option>
@ -272,8 +272,8 @@
</select>
</div><input type="text" name="_filter_value" class="filter-value">
</div>
<div class="filter-row filter-actions-row">
<div class="select-wrapper">
<div class="filter-row">
<div class="select-wrapper small-screen-only">
<select name="_sort" id="sort_by">
<option value="">Sort...</option>
<option value="rowid" selected>Sort by rowid</option>
@ -281,8 +281,8 @@
<option value="characteristic_id">Sort by characteristic_id</option>
</select>
</div>
<label class="sort_by_desc"><input type="checkbox" name="_sort_by_desc"> descending</label>
<input type="submit" value="Apply filters">
<label class="sort_by_desc small-screen-only"><input type="checkbox" name="_sort_by_desc"> descending</label>
<input type="submit" value="Apply">
</div>
</form>

View file

@ -7,9 +7,9 @@
{% if row_mutation_ui %}
<script>window._datasetteTableData = {{ table_page_data|tojson }};</script>
{% if table_page_data.foreignKeys %}
<script src="{{ static('autocomplete.js') }}" defer></script>
<script src="{{ urls.static('autocomplete.js') }}" defer></script>
{% endif %}
<script src="{{ static('edit-tools.js') }}" defer></script>
<script src="{{ urls.static('edit-tools.js') }}?hash={{ edit_tools_js_hash }}" defer></script>
{% endif %}
<style>
@media only screen and (max-width: 576px) {
@ -42,12 +42,24 @@
{% if foreign_key_tables %}
<h2>Links from other tables</h2>
<ul>
<ul class="row-foreign-key-tables">
{% for other in foreign_key_tables %}
<li>
<a href="{{ other.link }}">
{{ "{:,}".format(other.count) }} row{% if other.count == 1 %}{% else %}s{% endif %}</a>
from {{ other.other_column }} in {{ other.other_table }}
{% if other.can_insert %}
<button
type="button"
class="core row-foreign-key-insert"
data-insert-dialog
data-insert-dialog-reload
data-database="{{ database }}"
data-table="{{ other.other_table }}"
data-row="{{ other.insert_row|tojson|forceescape }}"
data-message="{{ other.insert_message }}"
>Insert</button>
{% endif %}
</li>
{% endfor %}
</ul>

View file

@ -1,17 +1,17 @@
{% extends "base.html" %}
{% block title %}{{ database }}: {{ table }}: {% if count_truncated %}&gt;{{ "{:,}".format(count - 1) }} rows{% elif count or count == 0 %}{{ "{:,}".format(count) }} row{% if count == 1 %}{% else %}s{% endif %}{% endif %}{% if human_description_en %} {{ human_description_en }}{% endif %}{% endblock %}
{% block title %}{{ database }}: {{ table }}: {% if count or count == 0 %}{{ "{:,}".format(count) }} row{% if count == 1 %}{% else %}s{% endif %}{% endif %}{% if human_description_en %} {{ human_description_en }}{% endif %}{% endblock %}
{% block extra_head %}
{{- super() -}}
<script>window._datasetteTableData = {{ table_page_data|tojson }};</script>
<script src="{{ static('column-chooser.js') }}" defer></script>
<script src="{{ urls.static('column-chooser.js') }}" defer></script>
{% if table_page_data.foreignKeys %}
<script src="{{ static('autocomplete.js') }}" defer></script>
<script src="{{ urls.static('autocomplete.js') }}" defer></script>
{% endif %}
<script src="{{ static('edit-tools.js') }}" defer></script>
<script src="{{ static('table.js') }}" defer></script>
<script src="{{ static('mobile-column-actions.js') }}" defer></script>
<script src="{{ urls.static('edit-tools.js') }}?hash={{ edit_tools_js_hash }}" defer></script>
<script src="{{ urls.static('table.js') }}?hash={{ table_js_hash }}" defer></script>
<script src="{{ urls.static('mobile-column-actions.js') }}" defer></script>
<script>DATASETTE_ALLOW_FACET = {{ datasette_allow_facet }};</script>
<style>
@media only screen and (max-width: 576px) {
@ -48,19 +48,19 @@
{% if count or human_description_en %}
<h3>
{% if count_truncated %}&gt;{{ "{:,}".format(count - 1) }} rows
{% if count == count_limit + 1 %}&gt;{{ "{:,}".format(count_limit) }} rows
{% if allow_execute_sql and query.sql %} <a class="count-sql" style="font-size: 0.8em;" href="{{ urls.database_query(database, count_sql) }}">count all</a>{% endif %}
{% elif count or count == 0 %}{{ "{:,}".format(count) }} row{% if count == 1 %}{% else %}s{% endif %}{% endif %}
{% if human_description_en %}{{ human_description_en }}{% endif %}
</h3>
{% endif %}
<form class="core filters" action="{{ urls.table(database, table) }}" method="get">
<form class="core" class="filters" action="{{ urls.table(database, table) }}" method="get">
{% if supports_search %}
<div class="search-row"><label for="_search">Search:</label><input id="_search" type="search" name="_search" value="{{ search }}"></div>
{% endif %}
{% for column, lookup, value in filters.selections() %}
<div class="filter-row filter-controls-row">
<div class="filter-row">
<div class="select-wrapper">
<select name="_filter_column_{{ loop.index }}">
<option value="">- remove filter -</option>
@ -77,7 +77,7 @@
</div><input type="text" name="_filter_value_{{ loop.index }}" class="filter-value" value="{{ value }}">
</div>
{% endfor %}
<div class="filter-row filter-controls-row">
<div class="filter-row">
<div class="select-wrapper">
<select name="_filter_column">
<option value="">- column -</option>
@ -93,9 +93,9 @@
</select>
</div><input type="text" name="_filter_value" class="filter-value">
</div>
<div class="filter-row filter-actions-row">
<div class="filter-row">
{% if is_sortable %}
<div class="select-wrapper">
<div class="select-wrapper small-screen-only">
<select name="_sort" id="sort_by">
<option value="">Sort...</option>
{% for column in display_columns %}
@ -105,12 +105,12 @@
{% endfor %}
</select>
</div>
<label class="sort_by_desc"><input type="checkbox" name="_sort_by_desc" tabindex="0"{% if sort_desc %} checked{% endif %}> descending</label>
<label class="sort_by_desc small-screen-only"><input type="checkbox" name="_sort_by_desc"{% if sort_desc %} checked{% endif %}> descending</label>
{% endif %}
{% for key, value in form_hidden_args %}
<input type="hidden" name="{{ key }}" value="{{ value }}">
{% endfor %}
<input type="submit" value="Apply filters" tabindex="0">
<input type="submit" value="Apply">
</div>
</form>

View file

@ -10,7 +10,7 @@ from __future__ import annotations
import dataclasses
import time
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, Optional
import itsdangerous
@ -18,21 +18,6 @@ if TYPE_CHECKING:
from datasette.app import Datasette
class TokenInvalid(Exception):
"""
Raised by a TokenHandler when a token it recognizes is invalid -
for example a bad signature, malformed payload or expired token.
Datasette responds to this with an HTTP 401 error. Handlers should
return None instead for tokens they do not recognize at all, so that
other registered handlers get a chance to verify them.
"""
def __init__(self, message="Invalid token"):
self.message = message
super().__init__(message)
@dataclasses.dataclass
class TokenRestrictions:
"""
@ -50,24 +35,24 @@ class TokenRestrictions:
database: dict[str, list[str]] = dataclasses.field(default_factory=dict)
resource: dict[str, dict[str, list[str]]] = dataclasses.field(default_factory=dict)
def allow_all(self, action: str) -> TokenRestrictions:
def allow_all(self, action: str) -> "TokenRestrictions":
"""Allow an action across all databases and resources."""
self.all.append(action)
return self
def allow_database(self, database: str, action: str) -> TokenRestrictions:
def allow_database(self, database: str, action: str) -> "TokenRestrictions":
"""Allow an action on a specific database."""
self.database.setdefault(database, []).append(action)
return self
def allow_resource(
self, database: str, resource: str, action: str
) -> TokenRestrictions:
) -> "TokenRestrictions":
"""Allow an action on a specific resource within a database."""
self.resource.setdefault(database, {}).setdefault(resource, []).append(action)
return self
def abbreviated(self, datasette: Datasette) -> dict | None:
def abbreviated(self, datasette: "Datasette") -> Optional[dict]:
"""
Return the abbreviated ``_r`` dictionary shape for this set of
restrictions, using action abbreviations registered with ``datasette``.
@ -112,23 +97,19 @@ class TokenHandler:
async def create_token(
self,
datasette: Datasette,
datasette: "Datasette",
actor_id: str,
*,
expires_after: int | None = None,
restrictions: TokenRestrictions | None = None,
expires_after: Optional[int] = None,
restrictions: Optional[TokenRestrictions] = None,
) -> str:
"""Create and return a token string for the given actor."""
raise NotImplementedError
async def verify_token(self, datasette: Datasette, token: str) -> dict | None:
async def verify_token(self, datasette: "Datasette", token: str) -> Optional[dict]:
"""
Verify a token and return an actor dict.
Return None if this handler does not recognize the token at all,
so other handlers can try it. Raise TokenInvalid if the token is
recognized but invalid (bad signature, malformed, expired) - the
request will fail with a 401 error.
Verify a token and return an actor dict, or None if this handler
does not recognize the token.
"""
raise NotImplementedError
@ -142,11 +123,11 @@ class SignedTokenHandler(TokenHandler):
async def create_token(
self,
datasette: Datasette,
datasette: "Datasette",
actor_id: str,
*,
expires_after: int | None = None,
restrictions: TokenRestrictions | None = None,
expires_after: Optional[int] = None,
restrictions: Optional[TokenRestrictions] = None,
) -> str:
if not datasette.setting("allow_signed_tokens"):
raise ValueError(
@ -163,35 +144,32 @@ class SignedTokenHandler(TokenHandler):
token["_r"] = abbreviated
return "dstok_{}".format(datasette.sign(token, namespace="token"))
async def verify_token(self, datasette: Datasette, token: str) -> dict | None:
async def verify_token(self, datasette: "Datasette", token: str) -> Optional[dict]:
prefix = "dstok_"
if not token.startswith(prefix):
# Not one of our tokens - leave it for other handlers
if not datasette.setting("allow_signed_tokens"):
return None
if not datasette.setting("allow_signed_tokens"):
raise TokenInvalid(
"Signed tokens are not enabled for this Datasette instance"
)
max_signed_tokens_ttl = datasette.setting("max_signed_tokens_ttl")
if not token.startswith(prefix):
return None
raw = token[len(prefix) :]
try:
decoded = datasette.unsign(raw, namespace="token")
except itsdangerous.BadSignature:
raise TokenInvalid("Invalid token signature")
return None
if "t" not in decoded:
raise TokenInvalid("Invalid token: no timestamp")
return None
created = decoded["t"]
if not isinstance(created, int):
raise TokenInvalid("Invalid token: invalid timestamp")
return None
duration = decoded.get("d")
if duration is not None and not isinstance(duration, int):
raise TokenInvalid("Invalid token: invalid duration")
return None
if (duration is None and max_signed_tokens_ttl) or (
duration is not None
@ -200,8 +178,9 @@ class SignedTokenHandler(TokenHandler):
):
duration = max_signed_tokens_ttl
if duration and time.time() - created > duration:
raise TokenInvalid("Token has expired")
if duration:
if time.time() - created > duration:
return None
actor = {"id": decoded["a"], "token": "dstok"}

View file

@ -1,11 +1,10 @@
import asyncio
import json
import time
import traceback
from contextlib import contextmanager
from contextvars import ContextVar
from markupsafe import escape
import time
import json
import traceback
tracers = {}
@ -133,17 +132,17 @@ class AsgiTracer:
"num_traces": len(traces),
"traces": traces,
}
content_type = next(
(
try:
content_type = [
v.decode("utf8")
for k, v in response_headers
if k.lower() == b"content-type"
),
"",
)
][0]
except IndexError:
content_type = ""
if "text/html" in content_type and b"</body>" in accumulated_body:
extra = escape(json.dumps(trace_info, indent=2))
extra_html = f"<pre>{extra}</pre></body>".encode()
extra_html = f"<pre>{extra}</pre></body>".encode("utf8")
accumulated_body = accumulated_body.replace(b"</body>", extra_html)
elif "json" in content_type and accumulated_body.startswith(b"{"):
data = json.loads(accumulated_body.decode("utf8"))

View file

@ -1,7 +1,6 @@
from .utils import tilde_encode, path_with_format, PrefixedUrlString
import urllib
from .utils import PrefixedUrlString, path_with_format, tilde_encode
class Urls:
def __init__(self, ds):
@ -9,7 +8,8 @@ class Urls:
def path(self, path, format=None):
if not isinstance(path, PrefixedUrlString):
path = path.removeprefix("/")
if path.startswith("/"):
path = path[1:]
path = self.ds.setting("base_url") + path
if format is not None:
path = path_with_format(path=path, format=format)
@ -56,7 +56,6 @@ class Urls:
return PrefixedUrlString(path)
def row_blob(self, database, table, row_path, column):
return (
self.table(database, table)
+ f"/{row_path}.blob?_blob_column={urllib.parse.quote_plus(column)}"
return self.table(database, table) + "/{}.blob?_blob_column={}".format(
row_path, urllib.parse.quote_plus(column)
)

View file

@ -1,31 +1,28 @@
import asyncio
import base64
import binascii
from contextlib import contextmanager
import aiofiles
import click
from collections import OrderedDict, namedtuple, Counter
import copy
import dataclasses
import base64
import hashlib
import inspect
import json
import os
import re
import secrets
import shlex
import shutil
import tempfile
import time
import types
import typing
import urllib
from collections import Counter, OrderedDict, namedtuple
from collections.abc import Iterable
from contextlib import contextmanager
import aiofiles
import click
import markupsafe
import mergedeep
import os
import re
import shlex
import tempfile
import typing
import time
import types
import secrets
import shutil
from typing import Iterable, List, Tuple
import urllib
import yaml
from .shutil_backport import copytree
from .sqlite import sqlite3, supports_table_xinfo
@ -38,7 +35,7 @@ if typing.TYPE_CHECKING:
class PaginatedResources:
"""Paginated results from allowed_resources query."""
resources: list["Resource"]
resources: List["Resource"]
next: str | None # Keyset token for next page (None if no more results)
_datasette: typing.Any = dataclasses.field(default=None, repr=False)
_action: str = dataclasses.field(default=None, repr=False)
@ -85,132 +82,22 @@ class PaginatedResources:
# From https://www.sqlite.org/lang_keywords.html
reserved_words = {
"abort",
"action",
"add",
"after",
"all",
"alter",
"analyze",
"and",
"as",
"asc",
"attach",
"autoincrement",
"before",
"begin",
"between",
"by",
"cascade",
"case",
"cast",
"check",
"collate",
"column",
"commit",
"conflict",
"constraint",
"create",
"cross",
"current_date",
"current_time",
"current_timestamp",
"database",
"default",
"deferrable",
"deferred",
"delete",
"desc",
"detach",
"distinct",
"drop",
"each",
"else",
"end",
"escape",
"except",
"exclusive",
"exists",
"explain",
"fail",
"for",
"foreign",
"from",
"full",
"glob",
"group",
"having",
"if",
"ignore",
"immediate",
"in",
"index",
"indexed",
"initially",
"inner",
"insert",
"instead",
"intersect",
"into",
"is",
"isnull",
"join",
"key",
"left",
"like",
"limit",
"match",
"natural",
"no",
"not",
"notnull",
"null",
"of",
"offset",
"on",
"or",
"order",
"outer",
"plan",
"pragma",
"primary",
"query",
"raise",
"recursive",
"references",
"regexp",
"reindex",
"release",
"rename",
"replace",
"restrict",
"right",
"rollback",
"row",
"savepoint",
"select",
"set",
"table",
"temp",
"temporary",
"then",
"to",
"transaction",
"trigger",
"union",
"unique",
"update",
"using",
"vacuum",
"values",
"view",
"virtual",
"when",
"where",
"with",
"without",
}
reserved_words = set(
(
"abort action add after all alter analyze and as asc attach autoincrement "
"before begin between by cascade case cast check collate column commit "
"conflict constraint create cross current_date current_time "
"current_timestamp database default deferrable deferred delete desc detach "
"distinct drop each else end escape except exclusive exists explain fail "
"for foreign from full glob group having if ignore immediate in index "
"indexed initially inner insert instead intersect into is isnull join key "
"left like limit match natural no not notnull null of offset on or order "
"outer plan pragma primary query raise recursive references regexp reindex "
"release rename replace restrict right rollback row savepoint select set "
"table temp temporary then to transaction trigger union unique update using "
"vacuum values view virtual when where with without"
).split()
)
APT_GET_DOCKERFILE_EXTRAS = r"""
RUN apt-get update && \
@ -270,7 +157,7 @@ functions_marked_as_documented = []
def documented(fn=None, *, label=None):
def decorate(fn):
fn._datasette_docs_label = label or f"internals_utils_{fn.__name__}"
fn._datasette_docs_label = label or "internals_utils_{}".format(fn.__name__)
functions_marked_as_documented.append(fn)
return fn
@ -337,71 +224,24 @@ def compound_keys_after_sql(pks, start_index=0):
return "({})".format("\n or\n".join(or_clauses))
@documented
class CustomJSONEncoder(json.JSONEncoder):
"""
The CustomJSONEncoder class handles serialization for objects commonly used by Datasette,
including SQLite cursors and binary blobs. Datasette uses it internally to serve .json endpoints,
and plugins that return JSON can use it to match Datasette's own handling.
Built-in types (text, numbers, lists, etc) are encoded the same as Python's built-in ``json`` module.
- ``sqlite3.Row`` becomes a tuple
- ``sqlite3.Cursor`` becomes a list
Binary blobs are encoded as an object, with the actual data base64-encoded,
like so: ::
{
"$base64": True,
"encoded": ...,
}
Example: https://latest.datasette.io/fixtures/binary_data.json
"""
def default(self, obj):
if isinstance(obj, sqlite3.Row):
return tuple(obj)
if isinstance(obj, sqlite3.Cursor):
return list(obj)
if isinstance(obj, bytes):
return {
"$base64": True,
"encoded": base64.b64encode(obj).decode("latin1"),
}
# Does it encode to utf8?
try:
return obj.decode("utf8")
except UnicodeDecodeError:
return {
"$base64": True,
"encoded": base64.b64encode(obj).decode("latin1"),
}
return json.JSONEncoder.default(self, obj)
class WriteJsonValueError(ValueError):
pass
def decode_write_json_cell(value):
if not isinstance(value, dict):
return value
keys = set(value.keys())
if keys == {"$raw"}:
return value["$raw"]
if keys == {"$base64", "encoded"} and value.get("$base64") is True:
encoded = value["encoded"]
if not isinstance(encoded, str):
raise WriteJsonValueError("$base64 encoded value must be a string")
try:
return base64.b64decode(encoded, validate=True)
except binascii.Error as ex:
raise WriteJsonValueError("Invalid $base64 encoded value") from ex
return value
def decode_write_json_row(row):
return {key: decode_write_json_cell(value) for key, value in row.items()}
def decode_write_json_rows(rows):
return [decode_write_json_row(row) for row in rows]
@contextmanager
def sqlite_timelimit(conn, ms):
deadline = time.perf_counter() + (ms / 1000)
@ -472,7 +312,7 @@ disallawed_sql_res = [
(
re.compile(f"pragma(?!_({'|'.join(allowed_pragmas)}))"),
"Statement contained a disallowed PRAGMA. Allowed pragma functions are {}".format(
", ".join(f"pragma_{pragma}()" for pragma in allowed_pragmas)
", ".join("pragma_{}()".format(pragma) for pragma in allowed_pragmas)
),
)
]
@ -570,7 +410,12 @@ def escape_css_string(s):
def escape_sqlite(s):
if _boring_keyword_re.match(s) and (s.lower() not in reserved_words):
return s
return '"{}"'.format(s.replace('"', '""'))
elif "]" in s:
# SQLite does not support escaping ] inside [bracket] quoting, so fall
# back to double-quote quoting (doubling any embedded ") - #2677
return '"{}"'.format(s.replace('"', '""'))
else:
return f"[{s}]"
def make_dockerfile(
@ -646,7 +491,10 @@ CMD {cmd}""".format(
else ""
),
environment_variables="\n".join(
[f"ENV {key} '{value}'" for key, value in environment_variables.items()]
[
"ENV {} '{}'".format(key, value)
for key, value in environment_variables.items()
]
),
install_from=" ".join(install),
files=" ".join(files),
@ -745,11 +593,11 @@ def detect_primary_keys(conn, table):
def get_outbound_foreign_keys(conn, table):
infos = conn.execute(f"PRAGMA foreign_key_list({escape_sqlite(table)})").fetchall()
infos = conn.execute(f"PRAGMA foreign_key_list([{table}])").fetchall()
fks = []
for info in infos:
if info is not None:
id, seq, table_name, from_, to_, _on_update, _on_delete, _match = info
id, seq, table_name, from_, to_, on_update, on_delete, match = info
fks.append(
{
"column": from_,
@ -820,8 +668,7 @@ def detect_spatialite(conn):
def detect_fts(conn, table):
"""Detect if table has a corresponding FTS virtual table and return it"""
sql, params = detect_fts_sql(table)
rows = conn.execute(sql, params).fetchall()
rows = conn.execute(detect_fts_sql(table)).fetchall()
if len(rows) == 0:
return None
else:
@ -829,26 +676,18 @@ def detect_fts(conn, table):
def detect_fts_sql(table):
escaped_table = table.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
return (
r"""
select name from sqlite_master
where rootpage = 0
and (
sql like :fts_double_quoted escape char(92)
or sql like :fts_bracket_quoted escape char(92)
or (
tbl_name = :table
and sql like '%VIRTUAL TABLE%USING FTS%'
)
return r"""
select name from sqlite_master
where rootpage = 0
and (
sql like '%VIRTUAL TABLE%USING FTS%content="{table}"%'
or sql like '%VIRTUAL TABLE%USING FTS%content=[{table}]%'
or (
tbl_name = "{table}"
and sql like '%VIRTUAL TABLE%USING FTS%'
)
""",
{
"fts_double_quoted": f'%VIRTUAL TABLE%USING FTS%content="{escaped_table}"%',
"fts_bracket_quoted": f"%VIRTUAL TABLE%USING FTS%content=[{escaped_table}]%",
"table": table,
},
)
)
""".format(table=table.replace("'", "''"))
def detect_json1(conn=None):
@ -859,7 +698,7 @@ def detect_json1(conn=None):
try:
conn.execute("SELECT json('{}')")
return True
except sqlite3.Error:
except Exception:
return False
finally:
if close_conn:
@ -939,7 +778,9 @@ def is_url(value):
if not value.startswith("http://") and not value.startswith("https://"):
return False
# Any whitespace at all is invalid
return not whitespace_re.search(value)
if whitespace_re.search(value):
return False
return True
css_class_re = re.compile(r"^[a-zA-Z]+[_a-zA-Z0-9-]*$")
@ -992,9 +833,7 @@ def module_from_path(path, name):
mod.__file__ = path
with open(path, "r") as file:
code = compile(file.read(), path, "exec", dont_inherit=True)
# Executing the file is the whole point - this is how --plugins-dir loads
# plugins and how metadata/config .py files are evaluated
exec(code, mod.__dict__) # noqa: S102
exec(code, mod.__dict__)
return mod
@ -1151,7 +990,9 @@ def escape_fts(query):
query += '"'
bits = _escape_fts_re.split(query)
bits = [b for b in bits if b and b != '""']
return " ".join(f'"{bit}"' if not bit.startswith('"') else bit for bit in bits)
return " ".join(
'"{}"'.format(bit) if not bit.startswith('"') else bit for bit in bits
)
class MultiParams:
@ -1163,7 +1004,7 @@ class MultiParams:
data[key], (list, tuple)
), "dictionary data should be a dictionary of key => [list]"
self._data = data
elif isinstance(data, (list, tuple)):
elif isinstance(data, list) or isinstance(data, tuple):
new_data = {}
for item in data:
assert (
@ -1253,7 +1094,9 @@ def _gather_arguments(fn, kwargs):
for parameter in parameters:
if parameter not in kwargs:
raise TypeError(
f"{fn} requires parameters {tuple(parameters)}, missing: {set(parameters) - set(kwargs.keys())}"
"{} requires parameters {}, missing: {}".format(
fn, tuple(parameters), set(parameters) - set(kwargs.keys())
)
)
call_with.append(kwargs[parameter])
return call_with
@ -1322,9 +1165,9 @@ def resolve_env_secrets(config, environ):
"""Create copy that recursively replaces {"$env": "NAME"} with values from environ"""
if isinstance(config, dict):
if list(config.keys()) == ["$env"]:
return environ.get(next(iter(config.values())))
return environ.get(list(config.values())[0])
elif list(config.keys()) == ["$file"]:
with open(next(iter(config.values()))) as fp:
with open(list(config.values())[0]) as fp:
return fp.read()
else:
return {
@ -1402,38 +1245,29 @@ class StartupError(Exception):
pass
# Comments and string literals, matched in a single pass so that whichever
# construct starts first "wins" - this ensures a comment marker inside a string
# literal (or a quote inside a comment) does not confuse the parameter scan.
_comments_and_strings_re = re.compile(
r"""
--[^\n]* # single line comment
| /\*.*?(?:\*/|\Z) # multi line comment, possibly to end-of-input
| '(?:''|[^'])*' # single quoted string ('' escapes a quote)
| "(?:""|[^"])*" # double quoted identifier ("" escapes a quote)
| \[(?:[^\]])*\] # square-bracket quoted identifier
| `(?:``|[^`])*` # backtick quoted identifier
""",
re.DOTALL | re.VERBOSE,
)
_single_line_comment_re = re.compile(r"--.*")
_multi_line_comment_re = re.compile(r"/\*.*?\*/", re.DOTALL)
_single_quote_re = re.compile(r"'(?:''|[^'])*'")
_double_quote_re = re.compile(r'"(?:\"\"|[^"])*"')
_named_param_re = re.compile(r":(\w+)")
@documented
def named_parameters(sql: str) -> list[str]:
def named_parameters(sql: str) -> List[str]:
"""
Given a SQL statement, return a list of named parameters that are used in the statement
e.g. for ``select * from foo where id=:id`` this would return ``["id"]``
"""
# Strip comments and string literals first so that any ":name" sequences
# inside them are not mistaken for named parameters
sql = _comments_and_strings_re.sub("", sql)
sql = _single_line_comment_re.sub("", sql)
sql = _multi_line_comment_re.sub("", sql)
sql = _single_quote_re.sub("", sql)
sql = _double_quote_re.sub("", sql)
# Extract parameters from what is left
return _named_param_re.findall(sql)
async def derive_named_parameters(db: "Database", sql: str) -> list[str]:
async def derive_named_parameters(db: "Database", sql: str) -> List[str]:
"""
This undocumented but stable method exists for backwards compatibility
with plugins that were using it before it switched to named_parameters()
@ -1441,54 +1275,6 @@ async def derive_named_parameters(db: "Database", sql: str) -> list[str]:
return named_parameters(sql)
def parse_size_limit(value, default, maximum, name="_size"):
"""
Parse a page-size parameter using the same semantics as the table
view's ?_size=: blank means default, "max" means maximum, integers
must be 0 or greater and no larger than maximum. Raises ValueError
with a message suitable for a 400 response.
"""
if value in (None, ""):
return default
if value == "max":
return maximum
try:
size = int(value)
if size < 0:
raise ValueError
except ValueError:
raise ValueError(f"{name} must be a positive integer")
if size > maximum:
raise ValueError(f"{name} must be <= {maximum}")
return size
UNSTABLE_API_MESSAGE = (
"This API is not part of Datasette's stable interface and may change at any time"
)
def error_body(messages, status):
"""
The canonical JSON error body used by every Datasette JSON error response:
{"ok": False, "error": "...", "errors": ["...", ...], "status": 400}
"error" is all of the messages joined with "; ", "errors" is the full
list, "status" matches the HTTP status code. Callers may add extra
context keys to the returned dictionary but must not remove these four.
"""
if isinstance(messages, str):
messages = [messages]
messages = [str(message) for message in messages]
return {
"ok": False,
"error": "; ".join(messages),
"errors": messages,
"status": status,
}
def add_cors_headers(headers):
headers["Access-Control-Allow-Origin"] = "*"
headers["Access-Control-Allow-Headers"] = "Authorization, Content-Type"
@ -1517,7 +1303,7 @@ class TildeEncoder(dict):
elif b == _space:
res = "+"
else:
res = f"~{b:02X}"
res = "~{:02X}".format(b)
self[b] = res
return res
@ -1566,13 +1352,7 @@ async def row_sql_params_pks(db, table, pk_values):
if use_rowid:
select = "rowid, *"
pks = ["rowid"]
wheres = []
for i, pk in enumerate(pks):
escaped_pk = escape_sqlite(pk)
# Preserve the historic always-quoted SQL exposed by _extra=query
if escaped_pk == pk:
escaped_pk = f'"{pk}"'
wheres.append(f"{escaped_pk}=:p{i}")
wheres = [f'"{pk}"=:p{i}' for i, pk in enumerate(pks)]
sql = f"select {select} from {escape_sqlite(table)} where {' AND '.join(wheres)}"
params = {}
for i, pk_value in enumerate(pk_values):
@ -1618,7 +1398,7 @@ def _combine(base: dict, update: dict) -> dict:
return base
def pairs_to_nested_config(pairs: list[tuple[str, typing.Any]]) -> dict:
def pairs_to_nested_config(pairs: typing.List[typing.Tuple[str, typing.Any]]) -> dict:
"""
Parse a list of key-value pairs into a nested dictionary.
"""
@ -1633,7 +1413,7 @@ def make_slot_function(name, datasette, request, **kwargs):
from datasette.plugins import pm
method = getattr(pm.hook, name, None)
assert method is not None, f"No hook found for {name}"
assert method is not None, "No hook found for {}".format(name)
async def inner():
html_bits = []
@ -1657,7 +1437,7 @@ def prune_empty_dicts(d: dict):
d.pop(key, None)
def move_plugins_and_allow(source: dict, destination: dict) -> tuple[dict, dict]:
def move_plugins_and_allow(source: dict, destination: dict) -> Tuple[dict, dict]:
"""
Move 'plugins' and 'allow' keys from source to destination dictionary. Creates
hierarchy in destination if needed. After moving, recursively remove any keys
@ -1744,7 +1524,7 @@ def redact_keys(original: dict, key_patterns: Iterable) -> dict:
return {
k: (
redact(v)
if not any(pattern in k.casefold() for pattern in key_patterns)
if not any(pattern in k for pattern in key_patterns)
else "***"
)
for k, v in data.items()
@ -1768,17 +1548,6 @@ def md5_not_usedforsecurity(s):
_etag_cache = {}
def sha256_file(filepath, chunk_size=4096):
hasher = hashlib.sha256()
with open(filepath, "rb") as fp:
while True:
chunk = fp.read(chunk_size)
if not chunk:
break
hasher.update(chunk)
return hasher.hexdigest()
async def calculate_etag(filepath, chunk_size=4096):
if filepath in _etag_cache:
return _etag_cache[filepath]

View file

@ -29,15 +29,6 @@ from datasette.utils.permissions import gather_permission_sql_from_hooks
if TYPE_CHECKING:
from datasette.app import Datasette
from datasette.permissions import Action
def _child_collation(action: "Action") -> str:
"""Match resource identity without changing the spelling returned by SQL."""
resource_class = action.resource_class
if resource_class is not None and resource_class.case_insensitive_child:
return "NOCASE"
return "BINARY"
async def build_allowed_resources_sql(
@ -158,7 +149,6 @@ async def _build_single_action_sql(
raise ValueError(f"Unknown action: {action}")
# Get base resources SQL from the resource class
child_collation = _child_collation(action_obj)
base_resources_sql = await action_obj.resource_class.resources_sql(
datasette, actor=actor
)
@ -195,7 +185,7 @@ async def _build_single_action_sql(
if permission_sql.sql is None:
continue
rule_sqls.append(f"""
SELECT parent, child COLLATE {child_collation} AS child, allow, reason, '{permission_sql.source}' AS source_plugin FROM (
SELECT parent, child, allow, reason, '{permission_sql.source}' AS source_plugin FROM (
{permission_sql.sql}
)
""".strip())
@ -262,62 +252,88 @@ async def _build_single_action_sql(
]
)
# Continue with the cascading logic.
# Aggregate the RULES by cascade level (small), rather than grouping
# base x rules (which scales with the number of resources).
def _agg(select_key, where, group_by):
parts = [
f" SELECT {select_key}",
" MAX(CASE WHEN allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN allow = 1 THEN 1 ELSE 0 END) AS any_allow,",
" json_group_array(CASE WHEN allow = 0 THEN source_plugin || ': ' || reason END) AS deny_reasons,",
" json_group_array(CASE WHEN allow = 1 THEN source_plugin || ': ' || reason END) AS allow_reasons",
f" FROM all_rules WHERE {where}",
]
if group_by:
parts.append(f" GROUP BY {group_by}")
return parts
# Continue with the cascading logic
query_parts.extend(
["child_agg AS ("]
+ _agg(
"parent, child,",
"parent IS NOT NULL AND child IS NOT NULL",
"parent, child",
)
+ ["),", "parent_agg AS ("]
+ _agg("parent,", "parent IS NOT NULL AND child IS NULL", "parent")
+ ["),", "global_agg AS ("]
+ _agg("", "parent IS NULL AND child IS NULL", None)
+ ["),"]
[
"child_lvl AS (",
" SELECT b.parent, b.child,",
" MAX(CASE WHEN ar.allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN ar.allow = 1 THEN 1 ELSE 0 END) AS any_allow,",
" json_group_array(CASE WHEN ar.allow = 0 THEN ar.source_plugin || ': ' || ar.reason END) AS deny_reasons,",
" json_group_array(CASE WHEN ar.allow = 1 THEN ar.source_plugin || ': ' || ar.reason END) AS allow_reasons",
" FROM base b",
" LEFT JOIN all_rules ar ON ar.parent = b.parent AND ar.child = b.child",
" GROUP BY b.parent, b.child",
"),",
"parent_lvl AS (",
" SELECT b.parent, b.child,",
" MAX(CASE WHEN ar.allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN ar.allow = 1 THEN 1 ELSE 0 END) AS any_allow,",
" json_group_array(CASE WHEN ar.allow = 0 THEN ar.source_plugin || ': ' || ar.reason END) AS deny_reasons,",
" json_group_array(CASE WHEN ar.allow = 1 THEN ar.source_plugin || ': ' || ar.reason END) AS allow_reasons",
" FROM base b",
" LEFT JOIN all_rules ar ON ar.parent = b.parent AND ar.child IS NULL",
" GROUP BY b.parent, b.child",
"),",
"global_lvl AS (",
" SELECT b.parent, b.child,",
" MAX(CASE WHEN ar.allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN ar.allow = 1 THEN 1 ELSE 0 END) AS any_allow,",
" json_group_array(CASE WHEN ar.allow = 0 THEN ar.source_plugin || ': ' || ar.reason END) AS deny_reasons,",
" json_group_array(CASE WHEN ar.allow = 1 THEN ar.source_plugin || ': ' || ar.reason END) AS allow_reasons",
" FROM base b",
" LEFT JOIN all_rules ar ON ar.parent IS NULL AND ar.child IS NULL",
" GROUP BY b.parent, b.child",
"),",
]
)
# Add anonymous decision logic if needed
if include_is_private:
def _anon_agg(select_key, where, group_by):
parts = [
f" SELECT {select_key}",
" MAX(CASE WHEN allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN allow = 1 THEN 1 ELSE 0 END) AS any_allow",
f" FROM anon_rules WHERE {where}",
]
if group_by:
parts.append(f" GROUP BY {group_by}")
return parts
query_parts.extend(
["anon_child_agg AS ("]
+ _anon_agg(
f"parent, child COLLATE {child_collation} AS child,",
"parent IS NOT NULL AND child IS NOT NULL",
f"parent, child COLLATE {child_collation}",
)
+ ["),", "anon_parent_agg AS ("]
+ _anon_agg("parent,", "parent IS NOT NULL AND child IS NULL", "parent")
+ ["),", "anon_global_agg AS ("]
+ _anon_agg("", "parent IS NULL AND child IS NULL", None)
+ ["),"]
[
"anon_child_lvl AS (",
" SELECT b.parent, b.child,",
" MAX(CASE WHEN ar.allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN ar.allow = 1 THEN 1 ELSE 0 END) AS any_allow",
" FROM base b",
" LEFT JOIN anon_rules ar ON ar.parent = b.parent AND ar.child = b.child",
" GROUP BY b.parent, b.child",
"),",
"anon_parent_lvl AS (",
" SELECT b.parent, b.child,",
" MAX(CASE WHEN ar.allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN ar.allow = 1 THEN 1 ELSE 0 END) AS any_allow",
" FROM base b",
" LEFT JOIN anon_rules ar ON ar.parent = b.parent AND ar.child IS NULL",
" GROUP BY b.parent, b.child",
"),",
"anon_global_lvl AS (",
" SELECT b.parent, b.child,",
" MAX(CASE WHEN ar.allow = 0 THEN 1 ELSE 0 END) AS any_deny,",
" MAX(CASE WHEN ar.allow = 1 THEN 1 ELSE 0 END) AS any_allow",
" FROM base b",
" LEFT JOIN anon_rules ar ON ar.parent IS NULL AND ar.child IS NULL",
" GROUP BY b.parent, b.child",
"),",
"anon_decisions AS (",
" SELECT",
" b.parent, b.child,",
" CASE",
" WHEN acl.any_deny = 1 THEN 0",
" WHEN acl.any_allow = 1 THEN 1",
" WHEN apl.any_deny = 1 THEN 0",
" WHEN apl.any_allow = 1 THEN 1",
" WHEN agl.any_deny = 1 THEN 0",
" WHEN agl.any_allow = 1 THEN 1",
" ELSE 0",
" END AS anon_is_allowed",
" FROM base b",
" JOIN anon_child_lvl acl ON b.parent = acl.parent AND (b.child = acl.child OR (b.child IS NULL AND acl.child IS NULL))",
" JOIN anon_parent_lvl apl ON b.parent = apl.parent AND (b.child = apl.child OR (b.child IS NULL AND apl.child IS NULL))",
" JOIN anon_global_lvl agl ON b.parent = agl.parent AND (b.child = agl.child OR (b.child IS NULL AND agl.child IS NULL))",
"),",
]
)
# Final decisions
@ -326,28 +342,31 @@ async def _build_single_action_sql(
"decisions AS (",
" SELECT",
" b.parent, b.child,",
" -- Cascading permission logic: child -> parent -> global, DENY beats ALLOW at each level",
" -- Cascading permission logic: child → parent → global, DENY beats ALLOW at each level",
" -- Priority order:",
" -- 1. Child-level deny 2. Child-level allow",
" -- 3. Parent-level deny 4. Parent-level allow",
" -- 5. Global-level deny 6. Global-level allow",
" -- 1. Child-level deny (most specific, blocks access)",
" -- 2. Child-level allow (most specific, grants access)",
" -- 3. Parent-level deny (intermediate, blocks access)",
" -- 4. Parent-level allow (intermediate, grants access)",
" -- 5. Global-level deny (least specific, blocks access)",
" -- 6. Global-level allow (least specific, grants access)",
" -- 7. Default deny (no rules match)",
" CASE",
" WHEN ca.any_deny = 1 THEN 0",
" WHEN ca.any_allow = 1 THEN 1",
" WHEN pa.any_deny = 1 THEN 0",
" WHEN pa.any_allow = 1 THEN 1",
" WHEN ga.any_deny = 1 THEN 0",
" WHEN ga.any_allow = 1 THEN 1",
" WHEN cl.any_deny = 1 THEN 0",
" WHEN cl.any_allow = 1 THEN 1",
" WHEN pl.any_deny = 1 THEN 0",
" WHEN pl.any_allow = 1 THEN 1",
" WHEN gl.any_deny = 1 THEN 0",
" WHEN gl.any_allow = 1 THEN 1",
" ELSE 0",
" END AS is_allowed,",
" CASE",
" WHEN ca.any_deny = 1 THEN ca.deny_reasons",
" WHEN ca.any_allow = 1 THEN ca.allow_reasons",
" WHEN pa.any_deny = 1 THEN pa.deny_reasons",
" WHEN pa.any_allow = 1 THEN pa.allow_reasons",
" WHEN ga.any_deny = 1 THEN ga.deny_reasons",
" WHEN ga.any_allow = 1 THEN ga.allow_reasons",
" WHEN cl.any_deny = 1 THEN cl.deny_reasons",
" WHEN cl.any_allow = 1 THEN cl.allow_reasons",
" WHEN pl.any_deny = 1 THEN pl.deny_reasons",
" WHEN pl.any_allow = 1 THEN pl.allow_reasons",
" WHEN gl.any_deny = 1 THEN gl.deny_reasons",
" WHEN gl.any_allow = 1 THEN gl.allow_reasons",
" ELSE '[]'",
" END AS reason",
]
@ -355,34 +374,21 @@ async def _build_single_action_sql(
if include_is_private:
query_parts.append(
" , CASE WHEN ("
"CASE"
" WHEN aca.any_deny = 1 THEN 0"
" WHEN aca.any_allow = 1 THEN 1"
" WHEN apa.any_deny = 1 THEN 0"
" WHEN apa.any_allow = 1 THEN 1"
" WHEN aga.any_deny = 1 THEN 0"
" WHEN aga.any_allow = 1 THEN 1"
" ELSE 0 END"
") = 0 THEN 1 ELSE 0 END AS is_private"
" , CASE WHEN ad.anon_is_allowed = 0 THEN 1 ELSE 0 END AS is_private"
)
query_parts.extend(
[
" FROM base b",
" LEFT JOIN child_agg ca ON ca.parent = b.parent AND ca.child = b.child",
" LEFT JOIN parent_agg pa ON pa.parent = b.parent",
" CROSS JOIN global_agg ga",
" JOIN child_lvl cl ON b.parent = cl.parent AND (b.child = cl.child OR (b.child IS NULL AND cl.child IS NULL))",
" JOIN parent_lvl pl ON b.parent = pl.parent AND (b.child = pl.child OR (b.child IS NULL AND pl.child IS NULL))",
" JOIN global_lvl gl ON b.parent = gl.parent AND (b.child = gl.child OR (b.child IS NULL AND gl.child IS NULL))",
]
)
if include_is_private:
query_parts.extend(
[
" LEFT JOIN anon_child_agg aca ON aca.parent = b.parent AND aca.child = b.child",
" LEFT JOIN anon_parent_agg apa ON apa.parent = b.parent",
" CROSS JOIN anon_global_agg aga",
]
query_parts.append(
" JOIN anon_decisions ad ON b.parent = ad.parent AND (b.child = ad.child OR (b.child IS NULL AND ad.child IS NULL))"
)
query_parts.append(")")
@ -392,31 +398,10 @@ async def _build_single_action_sql(
# Wrap each restriction_sql in a subquery to avoid operator precedence issues
# with UNION ALL inside the restriction SQL statements
restriction_intersect = "\nINTERSECT\n".join(
f"SELECT parent, child COLLATE {child_collation} AS child FROM ({sql})"
for sql in restriction_sqls
f"SELECT * FROM ({sql})" for sql in restriction_sqls
)
# Decompose by NULL-pattern so the final filter can use pure-equality
# EXISTS lookups (satisfiable via automatic indexes) instead of a
# correlated OR-scan over the whole list.
query_parts.extend(
[
",",
"restriction_list AS (",
f" {restriction_intersect}",
"),",
"restriction_exact AS (",
" SELECT parent, child FROM restriction_list WHERE parent IS NOT NULL AND child IS NOT NULL",
"),",
"restriction_parent_any AS (",
" SELECT DISTINCT parent FROM restriction_list WHERE parent IS NOT NULL AND child IS NULL",
"),",
"restriction_child_any AS (",
" SELECT DISTINCT child FROM restriction_list WHERE parent IS NULL AND child IS NOT NULL",
"),",
"restriction_all AS (",
" SELECT 1 AS matched FROM restriction_list WHERE parent IS NULL AND child IS NULL LIMIT 1",
")",
]
[",", "restriction_list AS (", f" {restriction_intersect}", ")"]
)
# Final SELECT
@ -431,11 +416,10 @@ async def _build_single_action_sql(
# Add restriction filter if there are restrictions
if restriction_sqls:
query_parts.append("""
AND (
EXISTS (SELECT 1 FROM restriction_all)
OR EXISTS (SELECT 1 FROM restriction_parent_any r WHERE r.parent = decisions.parent)
OR EXISTS (SELECT 1 FROM restriction_child_any r WHERE r.child = decisions.child)
OR EXISTS (SELECT 1 FROM restriction_exact r WHERE r.parent = decisions.parent AND r.child = decisions.child)
AND EXISTS (
SELECT 1 FROM restriction_list r
WHERE (r.parent = decisions.parent OR r.parent IS NULL)
AND (r.child = decisions.child OR r.child IS NULL)
)""")
# Add parent filter if specified
@ -491,7 +475,6 @@ async def build_permission_rules_sql(
union_parts = []
all_params = {}
restriction_sqls = []
child_collation = _child_collation(action_obj)
for permission_sql in permission_sqls:
all_params.update(permission_sql.params or {})
@ -505,7 +488,7 @@ async def build_permission_rules_sql(
continue
union_parts.append(f"""
SELECT parent, child COLLATE {child_collation} AS child, allow, reason, '{permission_sql.source}' AS source_plugin FROM (
SELECT parent, child, allow, reason, '{permission_sql.source}' AS source_plugin FROM (
{permission_sql.sql}
)
""".strip())
@ -576,7 +559,6 @@ async def check_permissions_for_actions(
verdicts = {}
for i, (action, permission_sqls) in enumerate(zip(unique_actions, gathered)):
child_collation = _child_collation(datasette.actions[action])
prefix = f"a{i}_"
rule_parts = []
restriction_parts = []
@ -602,7 +584,7 @@ async def check_permissions_for_actions(
if sql is None:
continue
rule_parts.append(
f"SELECT parent, child COLLATE {child_collation} AS child, allow, reason, '{permission_sql.source}' AS source_plugin FROM (\n{sql}\n)"
f"SELECT parent, child, allow, reason, '{permission_sql.source}' AS source_plugin FROM (\n{sql}\n)"
)
if not rule_parts:
@ -636,8 +618,7 @@ async def check_permissions_for_actions(
if restriction_parts:
# Database-level restrictions (parent, NULL) match all children
restriction_intersect = "\nINTERSECT\n".join(
f"SELECT parent, child COLLATE {child_collation} AS child FROM ({sql})"
for sql in restriction_parts
f"SELECT * FROM ({sql})" for sql in restriction_parts
)
ctes.append(f"a{i}_restriction AS (\n{restriction_intersect}\n)")
verdict_sql = f"""({verdict_sql}) AND EXISTS (
@ -692,240 +673,3 @@ async def check_permission_for_resource(
child=child,
)
return results[action]
async def explain_permission_for_resource(
*,
datasette: "Datasette",
actor: dict | None,
action: str,
parent: str | None,
child: str | None,
) -> dict:
"""Explain a permission decision for one action and resource.
This is intended for Datasette's permission debugging tools. It uses the
same ``permission_resources_sql`` hook results and the same resolution
rules as :func:`check_permissions_for_actions`, but also returns the
matching rules, actor restriction results and ``also_requires`` chain.
The returned dictionary is part of Datasette's unstable debugging API.
"""
action_obj = datasette.actions.get(action)
if action_obj is None:
raise ValueError(f"Unknown action: {action}")
explanation = await _explain_single_action(
datasette=datasette,
actor=actor,
action=action,
parent=parent,
child=child,
)
required_actions = []
if action_obj.also_requires:
required = await explain_permission_for_resource(
datasette=datasette,
actor=actor,
action=action_obj.also_requires,
parent=parent,
child=child,
)
required_actions.append(required)
explanation["required_actions"] = required_actions
explanation["allowed"] = bool(
explanation["rule_allowed"]
and explanation["restriction_allowed"]
and all(required["allowed"] for required in required_actions)
)
explanation["summary"] = _permission_explanation_summary(explanation)
return explanation
async def _explain_single_action(
*,
datasette: "Datasette",
actor: dict | None,
action: str,
parent: str | None,
child: str | None,
) -> dict:
"""Return matching rules and restrictions for a single action."""
from datasette.utils.permissions import SKIP_PERMISSION_CHECKS
permission_sqls = await gather_permission_sql_from_hooks(
datasette=datasette,
actor=actor,
action=action,
)
if permission_sqls is SKIP_PERMISSION_CHECKS:
return {
"action": action,
"rule_allowed": True,
"restriction_allowed": True,
"winning_scope": "global",
"matched_rules": [
{
"scope": "global",
"effect": "allow",
"source": "skip_permission_checks",
"reason": "Permission checks were explicitly skipped",
"decisive": True,
"ignored_because": None,
}
],
"restrictions": [],
}
db = datasette.get_internal_database()
matched_rules = []
restrictions = []
child_collation = _child_collation(datasette.actions[action])
for permission_sql in permission_sqls:
params = dict(permission_sql.params or {})
parent_param = _unused_parameter_name(params, "_explain_parent")
params[parent_param] = parent
child_param = _unused_parameter_name(params, "_explain_child")
params[child_param] = child
if permission_sql.sql:
rows = await db.execute(
f"""
SELECT parent, child, allow, reason
FROM ({permission_sql.sql}) AS permission_rules
WHERE (parent IS NULL OR parent = :{parent_param})
AND (child IS NULL OR child COLLATE {child_collation} = :{child_param})
""",
params,
)
for row in rows:
specificity = (
2
if row["child"] is not None
else 1 if row["parent"] is not None else 0
)
matched_rules.append(
{
"scope": ("resource", "parent", "global")[2 - specificity],
"effect": "allow" if row["allow"] else "deny",
"source": permission_sql.source,
"reason": row["reason"],
"_specificity": specificity,
}
)
if permission_sql.restriction_sql:
restriction_row = (
await db.execute(
f"""
SELECT EXISTS(
SELECT 1 FROM ({permission_sql.restriction_sql}) AS restriction_rules
WHERE (parent IS NULL OR parent = :{parent_param})
AND (child IS NULL OR child COLLATE {child_collation} = :{child_param})
) AS resource_is_in_allowlist
""",
params,
)
).first()
restriction_allowed = bool(restriction_row[0])
restrictions.append(
{
"source": permission_sql.source,
"allowed": restriction_allowed,
"reason": params.get("deny")
or (
"Resource is included in this restriction allowlist"
if restriction_allowed
else "Resource is not included in this restriction allowlist"
),
}
)
matched_rules.sort(
key=lambda rule: (
-rule["_specificity"],
0 if rule["effect"] == "deny" else 1,
rule["source"] or "",
rule["reason"] or "",
)
)
if matched_rules:
winning_specificity = matched_rules[0]["_specificity"]
winning_rules = [
rule
for rule in matched_rules
if rule["_specificity"] == winning_specificity
]
rule_allowed = not any(rule["effect"] == "deny" for rule in winning_rules)
winning_scope = winning_rules[0]["scope"]
else:
winning_specificity = None
rule_allowed = False
winning_scope = None
for rule in matched_rules:
specificity = rule.pop("_specificity")
if specificity != winning_specificity:
rule["decisive"] = False
rule["ignored_because"] = "A more specific rule matched"
elif not rule_allowed and rule["effect"] == "allow":
rule["decisive"] = False
rule["ignored_because"] = "A deny rule matched at the same scope"
else:
rule["decisive"] = True
rule["ignored_because"] = None
return {
"action": action,
"rule_allowed": rule_allowed,
"restriction_allowed": all(
restriction["allowed"] for restriction in restrictions
),
"winning_scope": winning_scope,
"matched_rules": matched_rules,
"restrictions": restrictions,
}
def _unused_parameter_name(params: dict, preferred: str) -> str:
"""Return a SQL parameter name that is not already in ``params``."""
candidate = preferred
suffix = 2
while candidate in params:
candidate = f"{preferred}_{suffix}"
suffix += 1
return candidate
def _permission_explanation_summary(explanation: dict) -> str:
denied_requirement = next(
(
required
for required in explanation["required_actions"]
if not required["allowed"]
),
None,
)
if denied_requirement:
return (
f"Denied because {explanation['action']} also requires "
f"{denied_requirement['action']}, which was denied."
)
if not explanation["matched_rules"]:
return "Denied because no permission rule matched this actor and resource."
if not explanation["rule_allowed"]:
return (
f"Denied by a {explanation['winning_scope']}-level rule. "
"Deny rules take precedence over allow rules at the same scope."
)
if not explanation["restriction_allowed"]:
return (
"Denied because the resource is not included in the actor's restrictions."
)
return f"Allowed by the matching {explanation['winning_scope']}-level rule."

View file

@ -1,30 +1,28 @@
import asyncio
import json
import re
from http.cookies import Morsel, SimpleCookie
from mimetypes import guess_type
from pathlib import Path
from urllib.parse import parse_qs, parse_qsl, urlunparse
import aiofiles
import aiofiles.os
from datasette.utils import MultiParams, calculate_etag, error_body, sha256_file
from typing import Optional
from datasette.utils import MultiParams, calculate_etag
from datasette.utils.multipart import (
DEFAULT_MAX_FIELD_SIZE,
DEFAULT_MAX_FIELDS,
parse_form_data,
MultipartParseError,
FormData,
DEFAULT_MAX_FILE_SIZE,
DEFAULT_MAX_REQUEST_SIZE,
DEFAULT_MAX_FIELDS,
DEFAULT_MAX_FILES,
DEFAULT_MAX_PARTS,
DEFAULT_MAX_FIELD_SIZE,
DEFAULT_MAX_MEMORY_FILE_SIZE,
DEFAULT_MAX_PART_HEADER_BYTES,
DEFAULT_MAX_PART_HEADER_LINES,
DEFAULT_MAX_PARTS,
DEFAULT_MAX_REQUEST_SIZE,
DEFAULT_MIN_FREE_DISK_BYTES,
FormData,
MultipartParseError,
parse_form_data,
)
from mimetypes import guess_type
from urllib.parse import parse_qs, urlunparse, parse_qsl
from pathlib import Path
from http.cookies import SimpleCookie, Morsel
import aiofiles
import aiofiles.os
import re
# Workaround for adding samesite support to pre 3.8 python
Morsel._reserved["samesite"] = "SameSite"
@ -69,28 +67,16 @@ class BadRequest(Base400):
status = 400
class PayloadTooLarge(Base400):
status = 413
SAMESITE_VALUES = ("strict", "lax", "none")
# Bodies read fully into memory (post_body/post_vars/json) are capped at this
# size unless the max_post_body_bytes setting says otherwise. Kept deliberately
# far below multipart's DEFAULT_MAX_REQUEST_SIZE: that parser streams to disk,
# while these bodies are held in RAM and json.loads() can multiply their
# footprint several times over.
DEFAULT_MAX_POST_BODY_BYTES = 2 * 1024 * 1024 # 2MB
class Request:
def __init__(self, scope, receive, max_post_body_bytes=DEFAULT_MAX_POST_BODY_BYTES):
def __init__(self, scope, receive):
self.scope = scope
self.receive = receive
self.max_post_body_bytes = max_post_body_bytes
def __repr__(self):
return f'<asgi.Request method="{self.method}" url="{self.url}">'
return '<asgi.Request method="{}" url="{}">'.format(self.method, self.url)
@property
def method(self):
@ -155,43 +141,15 @@ class Request:
def actor(self):
return self.scope.get("actor", None)
async def post_body(self, max_bytes=None):
"""
Read the request body fully into memory.
The body is capped at max_bytes - or self.max_post_body_bytes
(default 2MB, set from the max_post_body_bytes setting for requests
created by Datasette) if max_bytes is not provided. Pass max_bytes=0
to disable the limit. Raises PayloadTooLarge (HTTP 413) if exceeded -
oversized bodies are rejected as soon as the limit is passed, without
buffering the rest.
"""
if max_bytes is None:
max_bytes = self.max_post_body_bytes
too_large = PayloadTooLarge(
f"Request body exceeded maximum size of {max_bytes} bytes"
)
if max_bytes:
# Reject early if the client declares an oversized body
try:
if int(self.headers.get("content-length", "")) > max_bytes:
raise too_large
except ValueError:
# Missing or malformed - the streaming check below still applies
pass
chunks = []
received = 0
async def post_body(self):
body = b""
more_body = True
while more_body:
message = await self.receive()
assert message["type"] == "http.request", message
chunk = message.get("body", b"")
received += len(chunk)
if max_bytes and received > max_bytes:
raise too_large
chunks.append(chunk)
body += message.get("body", b"")
more_body = message.get("more_body", False)
return b"".join(chunks)
return body
async def post_vars(self):
body = await self.post_body()
@ -208,7 +166,7 @@ class Request:
max_request_size: int = DEFAULT_MAX_REQUEST_SIZE,
max_fields: int = DEFAULT_MAX_FIELDS,
max_files: int = DEFAULT_MAX_FILES,
max_parts: int | None = DEFAULT_MAX_PARTS,
max_parts: Optional[int] = DEFAULT_MAX_PARTS,
max_field_size: int = DEFAULT_MAX_FIELD_SIZE,
max_memory_file_size: int = DEFAULT_MAX_MEMORY_FILE_SIZE,
max_part_header_bytes: int = DEFAULT_MAX_PART_HEADER_BYTES,
@ -301,24 +259,12 @@ class AsgiLifespan:
while True:
message = await receive()
if message["type"] == "lifespan.startup":
try:
for fn in self.on_startup:
await fn()
except Exception as e: # noqa: BLE001
await send(
{"type": "lifespan.startup.failed", "message": str(e)}
)
return
for fn in self.on_startup:
await fn()
await send({"type": "lifespan.startup.complete"})
elif message["type"] == "lifespan.shutdown":
try:
for fn in self.on_shutdown:
await fn()
except Exception as e: # noqa: BLE001
await send(
{"type": "lifespan.shutdown.failed", "message": str(e)}
)
return
for fn in self.on_shutdown:
await fn()
await send({"type": "lifespan.shutdown.complete"})
return
else:
@ -451,9 +397,6 @@ async def asgi_send_file(
)
HASHED_STATIC_CACHE_CONTROL = "max-age=31536000, immutable, public"
def asgi_static(root_path, chunk_size=4096, headers=None, content_type=None):
root_path = Path(root_path)
static_headers = {}
@ -480,17 +423,11 @@ def asgi_static(root_path, chunk_size=4096, headers=None, content_type=None):
return
try:
# Calculate ETag for filepath
hash_value = request.args.get("_hash")
if (
hash_value
and hash_value == sha256_file(full_path, chunk_size=chunk_size)[:12]
):
headers["Cache-Control"] = HASHED_STATIC_CACHE_CONTROL
etag = await calculate_etag(full_path, chunk_size=chunk_size)
headers["ETag"] = etag
if_none_match = request.headers.get("if-none-match")
if if_none_match and if_none_match == etag:
return await asgi_send(send, "", 304, headers=headers)
return await asgi_send(send, "", 304)
await asgi_send_file(
send, full_path, chunk_size=chunk_size, headers=headers
)
@ -498,8 +435,6 @@ def asgi_static(root_path, chunk_size=4096, headers=None, content_type=None):
await asgi_send_html(send, "404: File not found", 404)
return
# Only the actual static-file handler can bypass dynamic response privacy.
inner_static._datasette_static = True
return inner_static
@ -545,9 +480,9 @@ class Response:
httponly=False,
samesite="lax",
):
assert (
samesite in SAMESITE_VALUES
), f"samesite should be one of {SAMESITE_VALUES}"
assert samesite in SAMESITE_VALUES, "samesite should be one of {}".format(
SAMESITE_VALUES
)
cookie = SimpleCookie()
cookie[key] = value
for prop_name, prop_value in (
@ -591,18 +526,6 @@ class Response:
content_type="application/json; charset=utf-8",
)
@classmethod
def error(cls, messages, status=400, headers=None):
"""
A JSON error response using Datasette's standard error format.
messages can be a single string or a list of strings. For errors
that should content-negotiate between JSON and HTML, raise
Forbidden, NotFound, BadRequest or DatasetteError instead and let
Datasette's error handling hooks build the response.
"""
return cls.json(error_body(messages, status), status=status, headers=headers)
@classmethod
def redirect(cls, path, status=302, headers=None):
headers = headers or {}
@ -639,23 +562,10 @@ class AsgiRunOnFirstRequest:
self.asgi = asgi
self.on_startup = on_startup
self._started = False
# Guards against concurrent early requests interleaving with startup:
# without this, several requests could all observe `_started is
# False` and proceed before any of them finish running the hooks.
self._lock = asyncio.Lock()
async def __call__(self, scope, receive, send):
# Leave "lifespan" scope events alone - this shim only exists as a
# fallback for hosts that never send them. It wraps AsgiLifespan, so
# if it ran on_startup here too, a startup exception would escape
# before AsgiLifespan's own try/except got a chance to turn it into
# a lifespan.startup.failed message.
if scope["type"] != "lifespan" and not self._started:
async with self._lock:
# Re-check: another request may have finished startup while
# we were waiting for the lock.
if not self._started:
for hook in self.on_startup:
await hook()
self._started = True
if not self._started:
self._started = True
for hook in self.on_startup:
await hook()
return await self.asgi(scope, receive, send)

View file

@ -13,7 +13,7 @@ Originally shared here: https://www.djangosnippets.org/snippets/1431/
"""
class BaseConverter:
class BaseConverter(object):
decimal_digits = "0123456789"
def __init__(self, digits):

View file

@ -1,6 +1,6 @@
import inspect
import types
from typing import Any, NamedTuple
from typing import NamedTuple, Any
class CallableStatus(NamedTuple):
@ -19,7 +19,7 @@ def check_callable(obj: Any) -> CallableStatus:
if isinstance(obj, types.FunctionType):
return CallableStatus(True, inspect.iscoroutinefunction(obj))
if callable(obj):
if hasattr(obj, "__call__"):
return CallableStatus(True, inspect.iscoroutinefunction(obj.__call__))
assert False, f"obj {obj!r} is somehow callable with no __call__ method"
assert False, "obj {} is somehow callable with no __call__ method".format(repr(obj))

View file

@ -1,30 +1,9 @@
import textwrap
from datasette.utils import table_column_details
from sqlite_utils import Database as SQLiteUtilsDatabase
from sqlite_utils import Migrations
from datasette.utils import escape_sqlite, table_column_details
INTERNAL_DB_SCHEMA_TABLES = {
"catalog_databases",
"catalog_tables",
"catalog_views",
"catalog_columns",
"catalog_indexes",
"catalog_foreign_keys",
"metadata_instance",
"metadata_databases",
"metadata_resources",
"metadata_columns",
"column_types",
"queries",
}
INTERNAL_DB_SCHEMA_INDEXES = {
"queries_owner_idx",
}
INTERNAL_DB_SCHEMA_SQL = textwrap.dedent("""
async def init_internal_db(db):
create_tables_sql = textwrap.dedent("""
CREATE TABLE IF NOT EXISTS catalog_databases (
database_name TEXT PRIMARY KEY,
path TEXT,
@ -88,101 +67,99 @@ INTERNAL_DB_SCHEMA_SQL = textwrap.dedent("""
FOREIGN KEY (database_name) REFERENCES catalog_databases(database_name),
FOREIGN KEY (database_name, table_name) REFERENCES catalog_tables(database_name, table_name)
);
CREATE TABLE IF NOT EXISTS metadata_instance (
key text,
value text,
unique(key)
);
CREATE TABLE IF NOT EXISTS metadata_databases (
database_name text,
key text,
value text,
unique(database_name, key)
);
CREATE TABLE IF NOT EXISTS metadata_resources (
database_name text,
resource_name text,
key text,
value text,
unique(database_name, resource_name, key)
);
CREATE TABLE IF NOT EXISTS metadata_columns (
database_name text,
resource_name text,
column_name text,
key text,
value text,
unique(database_name, resource_name, column_name, key)
);
CREATE TABLE IF NOT EXISTS column_types (
database_name TEXT NOT NULL,
resource_name TEXT NOT NULL,
column_name TEXT NOT NULL,
column_type TEXT NOT NULL,
config TEXT,
PRIMARY KEY (database_name, resource_name, column_name)
);
CREATE TABLE IF NOT EXISTS queries (
database_name TEXT NOT NULL,
name TEXT NOT NULL,
sql TEXT NOT NULL,
title TEXT,
description TEXT,
description_html TEXT,
options TEXT NOT NULL DEFAULT '{}',
parameters TEXT NOT NULL DEFAULT '[]',
is_write INTEGER NOT NULL DEFAULT 0 CHECK (is_write IN (0, 1)),
is_private INTEGER NOT NULL DEFAULT 0 CHECK (is_private IN (0, 1)),
is_trusted INTEGER NOT NULL DEFAULT 0 CHECK (is_trusted IN (0, 1)),
source TEXT NOT NULL DEFAULT 'user',
owner_id TEXT,
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY (database_name, name)
);
CREATE INDEX IF NOT EXISTS queries_owner_idx
ON queries(owner_id);
""").strip()
await db.execute_write_script(create_tables_sql)
await initialize_metadata_tables(db)
internal_migrations = Migrations("datasette_internal")
async def initialize_metadata_tables(db):
await db.execute_write_script(textwrap.dedent("""
CREATE TABLE IF NOT EXISTS metadata_instance (
key text,
value text,
unique(key)
);
CREATE TABLE IF NOT EXISTS metadata_databases (
database_name text,
key text,
value text,
unique(database_name, key)
);
CREATE TABLE IF NOT EXISTS metadata_resources (
database_name text,
resource_name text,
key text,
value text,
unique(database_name, resource_name, key)
);
CREATE TABLE IF NOT EXISTS metadata_columns (
database_name text,
resource_name text,
column_name text,
key text,
value text,
unique(database_name, resource_name, column_name, key)
);
CREATE TABLE IF NOT EXISTS column_types (
database_name TEXT NOT NULL,
resource_name TEXT NOT NULL,
column_name TEXT NOT NULL,
column_type TEXT NOT NULL,
config TEXT,
PRIMARY KEY (database_name, resource_name, column_name)
);
CREATE TABLE IF NOT EXISTS queries (
database_name TEXT NOT NULL,
name TEXT NOT NULL,
sql TEXT NOT NULL,
title TEXT,
description TEXT,
description_html TEXT,
options TEXT NOT NULL DEFAULT '{}',
parameters TEXT NOT NULL DEFAULT '[]',
is_write INTEGER NOT NULL DEFAULT 0 CHECK (is_write IN (0, 1)),
is_private INTEGER NOT NULL DEFAULT 0 CHECK (is_private IN (0, 1)),
is_trusted INTEGER NOT NULL DEFAULT 0 CHECK (is_trusted IN (0, 1)),
source TEXT NOT NULL DEFAULT 'user',
owner_id TEXT,
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY (database_name, name)
);
CREATE INDEX IF NOT EXISTS queries_owner_idx
ON queries(owner_id);
"""))
def _internal_schema_exists(db):
table_names = set(db.table_names())
if not INTERNAL_DB_SCHEMA_TABLES.issubset(table_names):
return False
index_names = {
row[0]
for row in db.execute("select name from sqlite_master where type = 'index'")
}
return INTERNAL_DB_SCHEMA_INDEXES.issubset(index_names)
@internal_migrations(name="0001_initial")
def initial_internal_schema(db):
if _internal_schema_exists(db):
return
db.executescript(INTERNAL_DB_SCHEMA_SQL)
async def init_internal_db(db):
def apply_migrations(conn):
internal_migrations.apply(SQLiteUtilsDatabase(conn, execute_plugins=False))
await db.execute_write_fn(apply_migrations, transaction=False)
async def populate_schema_tables(internal_db, db, schema_version):
async def populate_schema_tables(internal_db, db):
database_name = db.name
def delete_everything(conn):
conn.execute(
"DELETE FROM catalog_tables WHERE database_name = ?", [database_name]
)
conn.execute(
"DELETE FROM catalog_views WHERE database_name = ?", [database_name]
)
conn.execute(
"DELETE FROM catalog_columns WHERE database_name = ?", [database_name]
)
conn.execute(
"DELETE FROM catalog_foreign_keys WHERE database_name = ?",
[database_name],
)
conn.execute(
"DELETE FROM catalog_indexes WHERE database_name = ?", [database_name]
)
await internal_db.execute_write_fn(delete_everything)
tables = (await db.execute("select * from sqlite_master WHERE type = 'table'")).rows
views = (await db.execute("select * from sqlite_master WHERE type = 'view'")).rows
@ -207,30 +184,25 @@ async def populate_schema_tables(internal_db, db, schema_version):
columns = table_column_details(conn, table_name)
columns_to_insert.extend(
{
"database_name": database_name,
"table_name": table_name,
**{"database_name": database_name, "table_name": table_name},
**column._asdict(),
}
for column in columns
)
foreign_keys = conn.execute(
f"PRAGMA foreign_key_list({escape_sqlite(table_name)})"
f"PRAGMA foreign_key_list([{table_name}])"
).fetchall()
foreign_keys_to_insert.extend(
{
"database_name": database_name,
"table_name": table_name,
**{"database_name": database_name, "table_name": table_name},
**dict(foreign_key),
}
for foreign_key in foreign_keys
)
indexes = conn.execute(
f"PRAGMA index_list({escape_sqlite(table_name)})"
).fetchall()
indexes = conn.execute(f"PRAGMA index_list([{table_name}])").fetchall()
indexes_to_insert.extend(
{
"database_name": database_name,
"table_name": table_name,
**{"database_name": database_name, "table_name": table_name},
**dict(index),
}
for index in indexes
@ -251,76 +223,47 @@ async def populate_schema_tables(internal_db, db, schema_version):
indexes_to_insert,
) = await db.execute_fn(collect_info)
def replace_catalog(conn):
# Delete child rows before their catalog_tables parents so this also
# works if a prepare_connection plugin enables foreign key enforcement.
for table in (
"catalog_columns",
"catalog_foreign_keys",
"catalog_indexes",
"catalog_views",
"catalog_tables",
):
conn.execute(
f"DELETE FROM {table} WHERE database_name = ?",
[database_name],
)
conn.execute(
"""
INSERT OR REPLACE INTO catalog_databases (
database_name, path, is_memory, schema_version
) VALUES (?, ?, ?, ?)
""",
[
database_name,
str(db.path) if db.path is not None else None,
db.is_memory,
schema_version,
],
await internal_db.execute_write_many(
"""
INSERT INTO catalog_tables (database_name, table_name, rootpage, sql)
values (?, ?, ?, ?)
""",
tables_to_insert,
)
await internal_db.execute_write_many(
"""
INSERT INTO catalog_views (database_name, view_name, rootpage, sql)
values (?, ?, ?, ?)
""",
views_to_insert,
)
await internal_db.execute_write_many(
"""
INSERT INTO catalog_columns (
database_name, table_name, cid, name, type, "notnull", default_value, is_pk, hidden
) VALUES (
:database_name, :table_name, :cid, :name, :type, :notnull, :default_value, :is_pk, :hidden
)
conn.executemany(
"""
INSERT INTO catalog_tables (database_name, table_name, rootpage, sql)
values (?, ?, ?, ?)
""",
tables_to_insert,
""",
columns_to_insert,
)
await internal_db.execute_write_many(
"""
INSERT INTO catalog_foreign_keys (
database_name, table_name, "id", seq, "table", "from", "to", on_update, on_delete, match
) VALUES (
:database_name, :table_name, :id, :seq, :table, :from, :to, :on_update, :on_delete, :match
)
conn.executemany(
"""
INSERT INTO catalog_views (database_name, view_name, rootpage, sql)
values (?, ?, ?, ?)
""",
views_to_insert,
""",
foreign_keys_to_insert,
)
await internal_db.execute_write_many(
"""
INSERT INTO catalog_indexes (
database_name, table_name, seq, name, "unique", origin, partial
) VALUES (
:database_name, :table_name, :seq, :name, :unique, :origin, :partial
)
conn.executemany(
"""
INSERT INTO catalog_columns (
database_name, table_name, cid, name, type, "notnull", default_value, is_pk, hidden
) VALUES (
:database_name, :table_name, :cid, :name, :type, :notnull, :default_value, :is_pk, :hidden
)
""",
columns_to_insert,
)
conn.executemany(
"""
INSERT INTO catalog_foreign_keys (
database_name, table_name, "id", seq, "table", "from", "to", on_update, on_delete, match
) VALUES (
:database_name, :table_name, :id, :seq, :table, :from, :to, :on_update, :on_delete, :match
)
""",
foreign_keys_to_insert,
)
conn.executemany(
"""
INSERT INTO catalog_indexes (
database_name, table_name, seq, name, "unique", origin, partial
) VALUES (
:database_name, :table_name, :seq, :name, :unique, :origin, :partial
)
""",
indexes_to_insert,
)
await internal_db.execute_write_fn(replace_catalog)
""",
indexes_to_insert,
)

View file

@ -11,10 +11,15 @@ Supports:
import asyncio
import shutil
import tempfile
from collections.abc import Callable
from dataclasses import dataclass, field
from typing import (
Any,
Callable,
Dict,
List,
Optional,
Tuple,
Union,
)
from urllib.parse import parse_qsl
@ -24,7 +29,7 @@ DEFAULT_MAX_REQUEST_SIZE = 100 * 1024 * 1024 # 100MB
DEFAULT_MAX_FIELDS = 1000
DEFAULT_MAX_FILES = 100
# If max_parts is not specified, it defaults to max_fields + max_files
DEFAULT_MAX_PARTS: int | None = None
DEFAULT_MAX_PARTS: Optional[int] = None
DEFAULT_MAX_FIELD_SIZE = 100 * 1024 # 100KB
DEFAULT_MAX_MEMORY_FILE_SIZE = 1024 * 1024 # 1MB
DEFAULT_MAX_PART_HEADER_BYTES = 16 * 1024 # 16KB
@ -35,6 +40,8 @@ DEFAULT_MIN_FREE_DISK_BYTES = 50 * 1024 * 1024 # 50MB
class MultipartParseError(Exception):
"""Raised when multipart parsing fails."""
pass
@dataclass
class UploadedFile:
@ -50,7 +57,7 @@ class UploadedFile:
name: str
filename: str
content_type: str | None
content_type: Optional[str]
size: int
_file: tempfile.SpooledTemporaryFile = field(repr=False)
@ -79,8 +86,7 @@ class UploadedFile:
def __del__(self):
try:
self._file.close()
except Exception: # noqa: BLE001, S110
# __del__ must never raise
except Exception:
pass
@ -92,27 +98,27 @@ class FormData:
"""
def __init__(self):
self._data: list[tuple[str, str | UploadedFile]] = []
self._data: List[Tuple[str, Union[str, UploadedFile]]] = []
def append(self, key: str, value: str | UploadedFile) -> None:
def append(self, key: str, value: Union[str, UploadedFile]) -> None:
"""Add a key-value pair."""
self._data.append((key, value))
def __getitem__(self, key: str) -> str | UploadedFile:
def __getitem__(self, key: str) -> Union[str, UploadedFile]:
"""Get the first value for a key."""
for k, v in self._data:
if k == key:
return v
raise KeyError(key)
def get(self, key: str, default: Any = None) -> str | UploadedFile | None:
def get(self, key: str, default: Any = None) -> Optional[Union[str, UploadedFile]]:
"""Get the first value for a key, or default if not found."""
try:
return self[key]
except KeyError:
return default
def getlist(self, key: str) -> list[str | UploadedFile]:
def getlist(self, key: str) -> List[Union[str, UploadedFile]]:
"""Get all values for a key."""
return [v for k, v in self._data if k == key]
@ -136,15 +142,15 @@ class FormData:
"""Return unique keys."""
return list(self)
def items(self) -> list[tuple[str, str | UploadedFile]]:
def items(self) -> List[Tuple[str, Union[str, UploadedFile]]]:
"""Return all key-value pairs."""
return list(self._data)
def values(self) -> list[str | UploadedFile]:
def values(self) -> List[Union[str, UploadedFile]]:
"""Return all values."""
return [v for _, v in self._data]
def _uploaded_files(self) -> list[UploadedFile]:
def _uploaded_files(self) -> List[UploadedFile]:
"""Return UploadedFile instances contained in this form."""
return [v for _, v in self._data if isinstance(v, UploadedFile)]
@ -157,7 +163,7 @@ class FormData:
for uploaded in self._uploaded_files():
try:
uploaded.close_sync()
except Exception: # noqa: BLE001, S110
except Exception:
# Best-effort cleanup; ignore close errors
pass
@ -166,7 +172,7 @@ class FormData:
for uploaded in self._uploaded_files():
try:
await uploaded.close()
except Exception: # noqa: BLE001, S110
except Exception:
# Best-effort cleanup; ignore close errors
pass
@ -183,13 +189,13 @@ class FormData:
await self.aclose()
def parse_content_disposition(header: str) -> dict[str, str | None]:
def parse_content_disposition(header: str) -> Dict[str, Optional[str]]:
"""
Parse Content-Disposition header value.
Returns dict with 'name', 'filename' keys (filename may be None).
"""
result: dict[str, str | None] = {"name": None, "filename": None}
result: Dict[str, Optional[str]] = {"name": None, "filename": None}
# Split on semicolons, handling quoted strings
parts = []
@ -232,8 +238,7 @@ def parse_content_disposition(header: str) -> dict[str, str | None]:
from urllib.parse import unquote
result["filename"] = unquote(encoded, encoding="utf-8")
except Exception: # noqa: BLE001, S110
# Malformed RFC 5987 filename* - fall back to the plain filename
except Exception:
pass
continue
@ -245,19 +250,20 @@ def parse_content_disposition(header: str) -> dict[str, str | None]:
if key == "name":
result["name"] = value
# Only set filename if filename* hasn't already set it
elif key == "filename" and result["filename"] is None:
# Strip path components (security)
# Handle both Unix and Windows paths
value = value.replace("\\", "/")
if "/" in value:
value = value.rsplit("/", 1)[-1]
result["filename"] = value
elif key == "filename":
# Only set if filename* hasn't already set it
if result["filename"] is None:
# Strip path components (security)
# Handle both Unix and Windows paths
value = value.replace("\\", "/")
if "/" in value:
value = value.rsplit("/", 1)[-1]
result["filename"] = value
return result
def parse_content_type(header: str) -> tuple[str, dict[str, str]]:
def parse_content_type(header: str) -> Tuple[str, Dict[str, str]]:
"""
Parse Content-Type header value.
@ -301,7 +307,7 @@ class MultipartParser:
max_request_size: int = DEFAULT_MAX_REQUEST_SIZE,
max_fields: int = DEFAULT_MAX_FIELDS,
max_files: int = DEFAULT_MAX_FILES,
max_parts: int | None = DEFAULT_MAX_PARTS,
max_parts: Optional[int] = DEFAULT_MAX_PARTS,
max_field_size: int = DEFAULT_MAX_FIELD_SIZE,
max_memory_file_size: int = DEFAULT_MAX_MEMORY_FILE_SIZE,
max_part_header_bytes: int = DEFAULT_MAX_PART_HEADER_BYTES,
@ -342,12 +348,12 @@ class MultipartParser:
self._tempdir = tempfile.gettempdir()
# Current part state
self.current_headers: dict[str, str] = {}
self.current_file: tempfile.SpooledTemporaryFile | None = None
self.current_headers: Dict[str, str] = {}
self.current_file: Optional[tempfile.SpooledTemporaryFile] = None
self.current_body = bytearray()
self.current_name: str | None = None
self.current_filename: str | None = None
self.current_content_type: str | None = None
self.current_name: Optional[str] = None
self.current_filename: Optional[str] = None
self.current_content_type: Optional[str] = None
def feed(self, chunk: bytes) -> None:
"""Feed a chunk of data to the parser."""
@ -448,7 +454,7 @@ class MultipartParser:
# Parse header
try:
line_str = line.decode("utf-8", errors="replace")
except UnicodeDecodeError:
except Exception:
line_str = line.decode("latin-1")
if ":" in line_str:
@ -475,9 +481,7 @@ class MultipartParser:
if self.file_count > self.max_files:
raise MultipartParseError("Too many files")
if self.handle_files:
# Outlives this method - it is filled in across parser callbacks
# and then handed to the UploadedFile the caller consumes
self.current_file = tempfile.SpooledTemporaryFile( # noqa: SIM115
self.current_file = tempfile.SpooledTemporaryFile(
max_size=self.max_memory_file_size
)
else:
@ -640,7 +644,7 @@ async def parse_form_data(
max_request_size: int = DEFAULT_MAX_REQUEST_SIZE,
max_fields: int = DEFAULT_MAX_FIELDS,
max_files: int = DEFAULT_MAX_FILES,
max_parts: int | None = DEFAULT_MAX_PARTS,
max_parts: Optional[int] = DEFAULT_MAX_PARTS,
max_field_size: int = DEFAULT_MAX_FIELD_SIZE,
max_memory_file_size: int = DEFAULT_MAX_MEMORY_FILE_SIZE,
max_part_header_bytes: int = DEFAULT_MAX_PART_HEADER_BYTES,

View file

@ -2,9 +2,8 @@
from __future__ import annotations
import json
from typing import Any, Dict, Iterable, List, Sequence, Tuple
import sqlite3
from collections.abc import Iterable, Sequence
from typing import Any
from datasette.permissions import PermissionSQL
from datasette.plugins import pm
@ -16,7 +15,7 @@ SKIP_PERMISSION_CHECKS = object()
async def gather_permission_sql_from_hooks(
*, datasette, actor: dict | None, action: str
) -> list[PermissionSQL] | object:
) -> List[PermissionSQL] | object:
"""Collect PermissionSQL objects from the permission_resources_sql hook.
Ensures that each returned PermissionSQL has a populated ``source``.
@ -35,7 +34,7 @@ async def gather_permission_sql_from_hooks(
hookimpls = hook_caller.get_hookimpls()
hook_results = list(hook_caller(datasette=datasette, actor=actor, action=action))
collected: list[PermissionSQL] = []
collected: List[PermissionSQL] = []
actor_json = json.dumps(actor) if actor is not None else None
actor_id = actor.get("id") if isinstance(actor, dict) else None
@ -72,7 +71,7 @@ def _iter_permission_sql_from_result(
if isinstance(result, PermissionSQL):
return [result]
if isinstance(result, (list, tuple)):
collected: list[PermissionSQL] = []
collected: List[PermissionSQL] = []
for item in result:
collected.extend(_iter_permission_sql_from_result(item, action=action))
return collected
@ -91,7 +90,7 @@ def _iter_permission_sql_from_result(
def build_rules_union(
actor: dict | None, plugins: Sequence[PermissionSQL]
) -> tuple[str, dict[str, Any]]:
) -> Tuple[str, Dict[str, Any]]:
"""
Compose plugin SQL into a UNION ALL.
@ -103,10 +102,10 @@ def build_rules_union(
The system reserves these parameter names: :actor, :actor_id, :action, :filter_parent
Plugin parameters should be prefixed with a unique identifier (e.g., source name).
"""
parts: list[str] = []
parts: List[str] = []
actor_json = json.dumps(actor) if actor else None
actor_id = actor.get("id") if actor else None
params: dict[str, Any] = {"actor": actor_json, "actor_id": actor_id}
params: Dict[str, Any] = {"actor": actor_json, "actor_id": actor_id}
for p in plugins:
# No namespacing - just use plugin params as-is
@ -142,10 +141,10 @@ async def resolve_permissions_from_catalog(
plugins: Sequence[Any],
action: str,
candidate_sql: str,
candidate_params: dict[str, Any] | None = None,
candidate_params: Dict[str, Any] | None = None,
*,
implicit_deny: bool = True,
) -> list[dict[str, Any]]:
) -> List[Dict[str, Any]]:
"""
Resolve permissions by embedding the provided *candidate_sql* in a CTE.
@ -169,8 +168,8 @@ async def resolve_permissions_from_catalog(
- parent, child, allow, reason, source_plugin, depth
- resource (rendered "/parent/child" or "/parent" or "/")
"""
resolved_plugins: list[PermissionSQL] = []
restriction_sqls: list[str] = []
resolved_plugins: List[PermissionSQL] = []
restriction_sqls: List[str] = []
for plugin in plugins:
if callable(plugin) and not isinstance(plugin, PermissionSQL):
@ -399,11 +398,11 @@ async def resolve_permissions_with_candidates(
db,
actor: dict | None,
plugins: Sequence[Any],
candidates: list[tuple[str, str | None]],
candidates: List[Tuple[str, str | None]],
action: str,
*,
implicit_deny: bool = True,
) -> list[dict[str, Any]]:
) -> List[Dict[str, Any]]:
"""
Resolve permissions without any external candidate table by embedding
the candidates as a UNION of parameterized SELECTs in a CTE.
@ -412,8 +411,8 @@ async def resolve_permissions_with_candidates(
actor: actor dict (or None), made available as :actor (JSON), :actor_id, and :action
"""
# Build a small CTE for candidates.
cand_rows_sql: list[str] = []
cand_params: dict[str, Any] = {}
cand_rows_sql: List[str] = []
cand_params: Dict[str, Any] = {}
for i, (parent, child) in enumerate(candidates):
pkey = f"cand_p_{i}"
ckey = f"cand_c_{i}"

View file

@ -6,7 +6,7 @@ https://github.com/python/cpython/blob/v3.8.3/LICENSE
"""
import os
from shutil import Error, copy, copy2, copystat
from shutil import copy, copy2, copystat, Error
def _copytree(

View file

@ -1,8 +1,6 @@
import sys
from dataclasses import dataclass
from typing import Literal
from datasette.utils import escape_sqlite
from datasette.utils.sqlite import SQLiteTableType, sqlite3, sqlite_table_type
SQLOperation = Literal[
@ -152,6 +150,7 @@ _SQLITE_INTERNAL_SCHEMA_FUNCTIONS = {
"sqlite_rename_test",
"substr",
}
_AUTHORIZER_ACTION_NAMES = {
getattr(sqlite3, name): name
for name in (
@ -197,16 +196,6 @@ def _allow_authorizer_action(*args):
return sqlite3.SQLITE_OK
def _disable_authorizer(conn):
# Python 3.11 added support for unregistering an authorizer using None.
# On Python 3.10, None is installed as the callback instead, and the next
# statement fails with "not authorized" when sqlite3 tries to call it.
if sys.version_info >= (3, 11):
conn.set_authorizer(None)
else:
conn.set_authorizer(_allow_authorizer_action)
def analyze_sql_tables(
conn,
sql: str,
@ -220,9 +209,7 @@ def analyze_sql_tables(
This function is synchronous and connection-based. It temporarily installs a
SQLite authorizer, prepares ``EXPLAIN <sql>``, and returns the operation
callbacks observed while SQLite compiles the statement. ``CREATE VIEW`` is
additionally executed inside a rolled-back savepoint so its source-table reads
can be discovered by analyzing a query against the temporary view.
callbacks observed while SQLite compiles the statement.
"""
operations: dict[OperationKey, set[str]] = {}
@ -404,10 +391,6 @@ def analyze_sql_tables(
)
return sqlite3.SQLITE_OK
if action == sqlite3.SQLITE_RECURSIVE:
# Recursive CTE bookkeeping; table reads are reported separately.
return sqlite3.SQLITE_OK
if action == sqlite3.SQLITE_FUNCTION and arg2 is not None:
record(
"function",
@ -427,12 +410,12 @@ def analyze_sql_tables(
database=None,
table=None,
sqlite_schema=sqlite_schema,
target=f"{arg1} {arg2}" if arg2 is not None else arg1,
target="{} {}".format(arg1, arg2) if arg2 is not None else arg1,
source=source,
)
return sqlite3.SQLITE_OK
action_name = _AUTHORIZER_ACTION_NAMES.get(action, f"SQLITE_{action}")
action_name = _AUTHORIZER_ACTION_NAMES.get(action, "SQLITE_{}".format(action))
record(
"unknown",
"unknown",
@ -495,24 +478,24 @@ def analyze_sql_tables(
conn, key.table, schema=key.sqlite_schema
)
finally:
_disable_authorizer(conn)
conn.set_authorizer(None)
has_schema_operation = any(
key.target_type in {"table", "index", "view", "trigger", "virtual-table"}
and key.operation in {"create", "alter", "drop"}
for key in operations
)
dropped_tables_and_views = {
dropped_tables = {
(key.database, key.table)
for key in operations
if key.operation == "drop" and key.target_type in {"table", "view"}
if key.operation == "drop" and key.target_type == "table"
}
def key_is_drop_table_delete(key: OperationKey) -> bool:
return (
key.operation == "delete"
and key.target_type == "table"
and (key.database, key.table) in dropped_tables_and_views
and (key.database, key.table) in dropped_tables
)
has_user_table_access_in_schema_operation = any(
@ -535,7 +518,9 @@ def analyze_sql_tables(
and key.target in _SQLITE_INTERNAL_SCHEMA_FUNCTIONS
):
return True
return bool(key_is_drop_table_delete(key))
if key_is_drop_table_delete(key):
return True
return False
def table_kind_for(key: OperationKey) -> SQLiteTableType | None:
if (
@ -546,7 +531,7 @@ def analyze_sql_tables(
return None
return table_kind_cache[(key.sqlite_schema, key.table)]
analysis = SQLAnalysis(
return SQLAnalysis(
operations=tuple(
Operation(
operation=key.operation,
@ -563,58 +548,3 @@ def analyze_sql_tables(
for key, columns in operations.items()
)
)
# SQLite does not resolve the SELECT body of a view when preparing CREATE
# VIEW, so its authorizer does not report reads from the view's source
# tables. Temporarily create the view, analyze a query against it (which
# does resolve the body), then roll the schema change back. Database-level
# callers use an isolated writable connection for this analysis.
create_view_operations = tuple(
operation
for operation in analysis.operations
if operation.operation == "create" and operation.target_type == "view"
)
if not create_view_operations:
return analysis
savepoint = "datasette_analyze_create_view"
conn.execute(f"SAVEPOINT {savepoint}")
try:
conn.execute(sql, params if params is not None else {})
dependency_reads = []
for view_operation in create_view_operations:
if view_operation.sqlite_schema is None or view_operation.table is None:
raise sqlite3.OperationalError(
"Could not determine the created view name"
)
quoted_schema = escape_sqlite(view_operation.sqlite_schema)
quoted_view = escape_sqlite(view_operation.table)
qualified_view = f"{quoted_schema}.{quoted_view}"
view_analysis = analyze_sql_tables(
conn,
f"SELECT * FROM {qualified_view}",
database_name=database_name,
schema_to_database=schema_to_database,
)
dependency_reads.extend(
operation
for operation in view_analysis.operations
if operation.operation == "read"
and not (
operation.sqlite_schema == view_operation.sqlite_schema
and operation.table == view_operation.table
)
)
finally:
conn.execute(f"ROLLBACK TO {savepoint}")
conn.execute(f"RELEASE {savepoint}")
existing_operations = set(analysis.operations)
return SQLAnalysis(
operations=analysis.operations
+ tuple(
operation
for operation in dependency_reads
if operation not in existing_operations
)
)

View file

@ -15,17 +15,8 @@ if hasattr(sqlite3, "enable_callback_tracebacks"):
_cached_sqlite_version = None
_cached_supports_returning = None
SQLiteTableType = Literal["table", "view", "virtual", "shadow"]
_SQLITE_IDENTIFIER_RE = (
r"""(?:"(?:[^"]|"")*"|'(?:[^']|'')*'|`(?:[^`]|``)*`|\[[^\]]*\]|[^\s.()'"`\[\]]+)"""
)
_VIRTUAL_TABLE_MODULE_RE = re.compile(
r"^\s*CREATE\s+VIRTUAL\s+TABLE\b\s*(?:IF\s+NOT\s+EXISTS\s+)?"
+ _SQLITE_IDENTIFIER_RE
+ r"(?:\s*\.\s*"
+ _SQLITE_IDENTIFIER_RE
+ r")?\s*\bUSING\b\s*("
+ _SQLITE_IDENTIFIER_RE
+ r")",
r"\bCREATE\s+VIRTUAL\s+TABLE\b.*?\bUSING\s+([^\s(]+)",
re.IGNORECASE | re.DOTALL,
)
_VIRTUAL_TABLE_SHADOW_SUFFIXES = {
@ -92,58 +83,24 @@ def sqlite_table_type(
) -> SQLiteTableType | None:
if supports_table_list():
try:
# Use the "PRAGMA table_list" statement form rather than the
# pragma_table_list(...) table-valued function. The
# table-valued function is resolved like an ordinary relation
# name, so an attacker-created table or view literally named
# "pragma_table_list" can shadow it and spoof the reported
# type (e.g. claiming a virtual table is an ordinary table).
# The PRAGMA statement form is a distinct piece of SQL syntax
# that always invokes SQLite's built-in pragma, so it cannot
# be shadowed by a user-created relation.
query = "select type from pragma_table_list where name = ?"
params: tuple[str, ...] = (table,)
if schema is not None:
query = f"PRAGMA {_quote_identifier(schema)}.table_list"
else:
query = "PRAGMA table_list"
cursor = conn.execute(query)
columns = [description[0] for description in cursor.description]
for row in cursor.fetchall():
record = dict(zip(columns, row))
if record.get("name") != table:
continue
if schema is not None and record.get("schema") != schema:
continue
row_type = record.get("type")
if row_type in {"table", "view", "virtual", "shadow"}:
return row_type
query += " and schema = ?"
params = (table, schema)
row = conn.execute(query, params).fetchone()
if row is not None and row[0] in {"table", "view", "virtual", "shadow"}:
return row[0]
except sqlite3.DatabaseError:
pass
return _sqlite_table_type_from_schema(conn, table, schema=schema)
def check_structured_write_table(conn, table: str, *, allow_missing=False):
"""Validate a row-write target on the connection that will perform the write."""
# SQLite resolves identifiers case-insensitively. The create API must not
# treat a differently cased existing name as a missing table.
row = conn.execute(
"select name from main.sqlite_master where name = ? collate nocase "
"and type in ('table', 'view')",
(table,),
).fetchone()
if row is None and allow_missing:
return
if row is not None and sqlite_table_type(conn, row[0]) == "table":
return
# Virtual table modules can interpret row writes as administrative operations.
# Their shadow tables are internal storage, not independently writable data.
raise ValueError("Structured writes require an ordinary table")
def sqlite_hidden_table_names(conn, *, schema: str | None = "main") -> list[str]:
schema_table = _sqlite_schema_table(schema)
try:
rows = conn.execute(
f"select name, sql from {schema_table} where type = 'table'"
"select name, sql from {} where type = 'table'".format(schema_table)
).fetchall()
except sqlite3.DatabaseError:
return []
@ -161,63 +118,6 @@ def sqlite_hidden_table_names(conn, *, schema: str | None = "main") -> list[str]
return sorted(hidden_tables) + content_fts_tables
def sqlite_derived_table_dependencies(
conn, *, schema: str | None = "main"
) -> dict[str, str]:
"""Return implementation table -> logical/content table dependencies.
``PRAGMA table_list`` safely identifies virtual and shadow tables, but
does not report which virtual table owns a shadow table or which table is
named by an FTS ``content=`` option. Derive those relationships from
``sqlite_master`` DDL and the documented shadow-table suffixes.
Database errors propagate: failed discovery must not be mistaken for an
empty dependency map and cached as permission to skip inheritance.
"""
schema_table = _sqlite_schema_table(schema)
rows = conn.execute(
f"select name, sql from {schema_table} where type = 'table'"
).fetchall()
table_names = {row[0] for row in rows}
# SQLite identifiers fold ASCII letters only.
identifier_case = str.maketrans(
"ABCDEFGHIJKLMNOPQRSTUVWXYZ", "abcdefghijklmnopqrstuvwxyz"
)
canonical_names = {name.translate(identifier_case): name for name in table_names}
dependencies = {}
for virtual_table, sql in rows:
module = _virtual_table_module(sql)
if module is None:
continue
# SQLite's documented shadow tables are implementation details of
# their logical virtual table.
for suffix in _VIRTUAL_TABLE_SHADOW_SUFFIXES.get(module, ()):
shadow_table = virtual_table + suffix
if shadow_table in table_names:
dependencies[shadow_table] = virtual_table
# An external-content FTS table can expose values fetched from its
# content table, so it must also depend on that table's permission.
if module in {"fts3", "fts4", "fts5"}:
content_table = _fts_external_content_table(sql)
if content_table:
dependencies[virtual_table] = content_table
if module in {"fts5vocab", "fts4aux"}:
source = _fts_vocabulary_source(sql, module, schema or "main")
source = (
canonical_names.get(source.translate(identifier_case))
if source
else None
)
# An unresolved source is itself derived, so the one-hop policy denies it.
dependencies[virtual_table] = source or virtual_table
return dependencies
def _sqlite_table_type_from_schema(
conn,
table: str,
@ -227,7 +127,7 @@ def _sqlite_table_type_from_schema(
schema_table = _sqlite_schema_table(schema)
try:
row = conn.execute(
f"select type, sql from {schema_table} where name = ?",
"select type, sql from {} where name = ?".format(schema_table),
(table,),
).fetchone()
except sqlite3.DatabaseError:
@ -255,7 +155,7 @@ def _is_known_shadow_table(
schema_table = _sqlite_schema_table(schema)
try:
rows = conn.execute(
f"select name, sql from {schema_table} where type = 'table'"
"select name, sql from {} where type = 'table'".format(schema_table)
).fetchall()
except sqlite3.DatabaseError:
return False
@ -274,7 +174,7 @@ def _sqlite_schema_table(schema: str | None) -> str:
return "sqlite_master"
if schema == "temp":
return "sqlite_temp_master"
return f"{_quote_identifier(schema)}.sqlite_master"
return "{}.sqlite_master".format(_quote_identifier(schema))
def _quote_identifier(value: str) -> str:
@ -284,151 +184,10 @@ def _quote_identifier(value: str) -> str:
def _virtual_table_module(sql: str | None) -> str | None:
if not sql:
return None
match = _VIRTUAL_TABLE_MODULE_RE.search(_strip_sql_comments(sql))
if match is None:
return None
return _unquote_sql_value(match.group(1)).lower()
def _fts_external_content_table(sql: str | None) -> str | None:
"""Extract the external ``content=`` table from an FTS declaration."""
if not sql:
return None
sql = _strip_sql_comments(sql)
match = _VIRTUAL_TABLE_MODULE_RE.search(sql)
if match is None:
return None
open_paren = sql.find("(", match.end())
if open_paren == -1:
return None
close_paren = sql.rfind(")")
if close_paren <= open_paren:
return None
for argument in _split_sql_arguments(sql[open_paren + 1 : close_paren]):
key, separator, value = argument.partition("=")
if not separator or key.strip().lower() != "content":
continue
return _unquote_sql_value(value.strip())
return None
def _fts_vocabulary_source(sql: str, module: str, schema: str) -> str | None:
"""Resolve a vocabulary source within the current SQLite schema.
Cross-schema sources cannot be represented by the dependency map and
are conservatively left unresolved.
"""
sql = _strip_sql_comments(sql)
match = _VIRTUAL_TABLE_MODULE_RE.search(sql)
if match is None:
return None
start = sql.find("(", match.end())
end = sql.rfind(")")
if start < 0 or end <= start:
return None
arguments = [
_unquote_sql_value(arg.strip())
for arg in _split_sql_arguments(sql[start + 1 : end])
]
expected = 2 if module == "fts5vocab" else 1
if len(arguments) == expected:
return arguments[0]
if len(arguments) == expected + 1 and arguments[0].lower() == schema.lower():
return arguments[1]
return None
def _split_sql_arguments(arguments: str) -> list[str]:
"""Split comma-separated SQLite arguments without splitting quoted text."""
parts = []
start = 0
quote = None
closing_quote = None
index = 0
while index < len(arguments):
char = arguments[index]
if quote is None:
if char in {"'", '"', "`", "["}:
quote = char
closing_quote = "]" if char == "[" else char
elif char == ",":
parts.append(arguments[start:index])
start = index + 1
elif char == closing_quote:
# Single/double/backtick quoting escapes the delimiter by
# doubling it. Square-bracket identifiers do not.
if (
quote != "["
and index + 1 < len(arguments)
and arguments[index + 1] == closing_quote
):
index += 1
else:
quote = None
closing_quote = None
index += 1
parts.append(arguments[start:])
return parts
def _strip_sql_comments(sql: str) -> str:
"""Remove SQLite comments while preserving quoted strings/identifiers."""
output = []
quote = None
closing_quote = None
index = 0
while index < len(sql):
char = sql[index]
next_char = sql[index + 1] if index + 1 < len(sql) else ""
if quote is None:
if char in {"'", '"', "`", "["}:
quote = char
closing_quote = "]" if char == "[" else char
output.append(char)
elif char == "-" and next_char == "-":
index += 2
while index < len(sql) and sql[index] not in "\r\n":
index += 1
output.append(" ")
continue
elif char == "/" and next_char == "*":
index += 2
while index + 1 < len(sql) and sql[index : index + 2] != "*/":
index += 1
index = min(index + 2, len(sql))
output.append(" ")
continue
else:
output.append(char)
else:
output.append(char)
if char == closing_quote:
if (
quote != "["
and index + 1 < len(sql)
and sql[index + 1] == closing_quote
):
output.append(sql[index + 1])
index += 1
else:
quote = None
closing_quote = None
index += 1
return "".join(output)
def _unquote_sql_value(value: str) -> str:
if len(value) < 2:
return value
pairs = {"'": "'", '"': '"', "`": "`", "[": "]"}
closing = pairs.get(value[0])
if closing is None or value[-1] != closing:
return value
unquoted = value[1:-1]
if value[0] != "[":
unquoted = unquoted.replace(closing * 2, closing)
return unquoted
return match.group(1).strip("\"'[]`").lower()
def _is_fts_content_virtual_table(sql: str | None) -> bool:

View file

@ -1,10 +1,9 @@
import json
from urllib.parse import urlencode
from asgiref.sync import async_to_sync
from urllib.parse import urlencode
import json
# These wrapper classes pre-date the introduction of
# datasette.client and httpx2 to Datasette. They could
# datasette.client and httpx to Datasette. They could
# be removed if the Datasette tests are modified to
# call datasette.client directly.

View file

@ -1,2 +1,2 @@
__version__ = "1.0a39"
__version__ = "1.0a34"
__version_info__ = tuple(__version__.split("."))

View file

@ -1,87 +1,2 @@
import dataclasses
import types
import typing
from dataclasses import dataclass
@dataclass(frozen=True)
class ContextField:
name: str
type_name: str
help: str
from_extra: bool = False
def _type_name(type_):
if type_ is type(None):
return "None"
origin = typing.get_origin(type_)
args = typing.get_args(type_)
if origin in (typing.Union, types.UnionType):
return " | ".join(_type_name(arg) for arg in args)
if origin is not None:
name = getattr(origin, "__name__", str(origin).removeprefix("typing."))
return "{}[{}]".format(name, ", ".join(_type_name(arg) for arg in args))
return getattr(type_, "__name__", str(type_).removeprefix("typing."))
def from_extra():
"""
Declare a Context dataclass field whose value comes from a registered
Extra of the same name - its documentation is the Extra description,
so the doc string lives next to the resolve() code rather than being
duplicated on the dataclass.
"""
return dataclasses.field(metadata={"from_extra": True})
class Context:
"Base class for all documented contexts"
# Set on subclasses whose from_extra() fields should be resolved
# against the extras registry for this scope
extras_scope = None
@classmethod
def documented_fields(cls):
"List of ContextField describing the documented fields of this context"
documented = []
for f in dataclasses.fields(cls):
if f.name.startswith("_"):
continue
is_from_extra = bool(f.metadata.get("from_extra"))
if is_from_extra:
help_text = cls._extra_description(f.name)
else:
help_text = f.metadata.get("help", "")
documented.append(
ContextField(
name=f.name,
type_name=_type_name(f.type),
help=help_text,
from_extra=is_from_extra,
)
)
return documented
@classmethod
def _extra_description(cls, name):
# Imported lazily - table_extras is not needed just to define
# Context subclasses
from datasette.views.table_extras import table_extra_registry
try:
extra_class = table_extra_registry.classes_by_name[name]
except KeyError:
raise KeyError(
f"{cls.__name__}.{name} is declared with from_extra() but there is no "
"registered extra of that name"
)
if cls.extras_scope is not None and not extra_class.available_for(
cls.extras_scope
):
raise ValueError(
f"{cls.__name__}.{name} is declared with from_extra() but the {name} extra is "
f"not available for scope {cls.extras_scope}"
)
return extra_class.description or ""

View file

@ -1,21 +1,33 @@
import asyncio
import csv
import hashlib
import sys
import textwrap
import time
import urllib
from markupsafe import escape
from datasette.database import QueryInterrupted
from datasette.utils.asgi import Request
from datasette.utils import (
add_cors_headers,
await_me_maybe,
EscapeHtmlWriter,
InvalidSql,
LimitedWriter,
add_cors_headers,
call_with_supported_arguments,
path_from_row_pks,
path_with_added_args,
path_with_removed_args,
path_with_format,
sqlite3,
)
from datasette.utils.asgi import (
AsgiStream,
BadRequest,
Request,
NotFound,
Response,
BadRequest,
)
@ -28,15 +40,12 @@ class DatasetteError(Exception):
status=500,
template=None,
message_is_html=False,
plain_message=None,
):
self.message = message
self.title = title
self.error_dict = error_dict or {}
self.status = status
self.message_is_html = message_is_html
# Plain text used for JSON error responses when message is HTML
self.plain_message = plain_message
class View:
@ -52,7 +61,9 @@ class View:
request.path.endswith(".json")
or request.headers.get("content-type") == "application/json"
):
response = Response.error("Method not allowed", 405)
response = Response.json(
{"ok": False, "error": "Method not allowed"}, status=405
)
else:
response = Response.text("Method not allowed", status=405)
return response
@ -91,7 +102,9 @@ class BaseView:
request.path.endswith(".json")
or request.headers.get("content-type") == "application/json"
):
response = Response.error("Method not allowed", 405)
response = Response.json(
{"ok": False, "error": "Method not allowed"}, status=405
)
else:
response = Response.text("Method not allowed", status=405)
return response
@ -129,10 +142,12 @@ class BaseView:
template = environment.select_template(templates)
template_context = {
**context,
"select_templates": [
f"{'*' if template_name == template.name else ''}{template_name}"
for template_name in templates
],
**{
"select_templates": [
f"{'*' if template_name == template.name else ''}{template_name}"
for template_name in templates
],
},
}
headers = {}
if self.has_json_alternate:
@ -149,7 +164,9 @@ class BaseView:
template_context["alternate_url_json"] = alternate_url_json
headers.update(
{
"Link": f'<{alternate_url_json}>; rel="alternate"; type="application/json+datasette"'
"Link": '<{}>; rel="alternate"; type="application/json+datasette"'.format(
alternate_url_json
)
}
)
return Response.html(
@ -175,12 +192,239 @@ class BaseView:
return view
class DataView(BaseView):
name = ""
def redirect(self, request, path, forward_querystring=True, remove_args=None):
if request.query_string and "?" not in path and forward_querystring:
path = f"{path}?{request.query_string}"
if remove_args:
path = path_with_removed_args(request, remove_args, path=path)
r = Response.redirect(path)
r.headers["Link"] = f"<{path}>; rel=preload"
if self.ds.cors:
add_cors_headers(r.headers)
return r
async def data(self, request):
raise NotImplementedError
async def as_csv(self, request, database):
return await stream_csv(self.ds, self.data, request, database)
async def get(self, request):
db = await self.ds.resolve_database(request)
database = db.name
database_route = db.route
_format = request.url_vars["format"]
data_kwargs = {}
if _format == "csv":
return await self.as_csv(request, database_route)
if _format is None:
# HTML views default to expanding all foreign key labels
data_kwargs["default_labels"] = True
extra_template_data = {}
start = time.perf_counter()
status_code = None
templates = []
try:
response_or_template_contexts = await self.data(request, **data_kwargs)
if isinstance(response_or_template_contexts, Response):
return response_or_template_contexts
# If it has four items, it includes an HTTP status code
if len(response_or_template_contexts) == 4:
(
data,
extra_template_data,
templates,
status_code,
) = response_or_template_contexts
else:
data, extra_template_data, templates = response_or_template_contexts
except QueryInterrupted as ex:
raise DatasetteError(
textwrap.dedent("""
<p>SQL query took too long. The time limit is controlled by the
<a href="https://docs.datasette.io/en/stable/settings.html#sql-time-limit-ms">sql_time_limit_ms</a>
configuration option.</p>
<textarea style="width: 90%">{}</textarea>
<script>
let ta = document.querySelector("textarea");
ta.style.height = ta.scrollHeight + "px";
</script>
""".format(escape(ex.sql))).strip(),
title="SQL Interrupted",
status=400,
message_is_html=True,
)
except (sqlite3.OperationalError, InvalidSql) as e:
raise DatasetteError(str(e), title="Invalid SQL", status=400)
except sqlite3.OperationalError as e:
raise DatasetteError(str(e))
except DatasetteError:
raise
end = time.perf_counter()
data["query_ms"] = (end - start) * 1000
# Special case for .jsono extension - redirect to _shape=objects
if _format == "jsono":
return self.redirect(
request,
path_with_added_args(
request,
{"_shape": "objects"},
path=request.path.rsplit(".jsono", 1)[0] + ".json",
),
forward_querystring=False,
)
if _format in self.ds.renderers.keys():
# Dispatch request to the correct output format renderer
# (CSV is not handled here due to streaming)
result = call_with_supported_arguments(
self.ds.renderers[_format][0],
datasette=self.ds,
columns=data.get("columns") or [],
rows=data.get("rows") or [],
sql=data.get("query", {}).get("sql", None),
query_name=data.get("query_name"),
database=database,
table=data.get("table"),
request=request,
view_name=self.name,
truncated=False, # TODO: support this
error=data.get("error"),
# These will be deprecated in Datasette 1.0:
args=request.args,
data=data,
)
if asyncio.iscoroutine(result):
result = await result
if result is None:
raise NotFound("No data")
if isinstance(result, dict):
r = Response(
body=result.get("body"),
status=result.get("status_code", status_code or 200),
content_type=result.get("content_type", "text/plain"),
headers=result.get("headers"),
)
elif isinstance(result, Response):
r = result
if status_code is not None:
# Over-ride the status code
r.status = status_code
else:
assert False, f"{result} should be dict or Response"
else:
extras = {}
if callable(extra_template_data):
extras = extra_template_data()
if asyncio.iscoroutine(extras):
extras = await extras
else:
extras = extra_template_data
url_labels_extra = {}
if data.get("expandable_columns"):
url_labels_extra = {"_labels": "on"}
renderers = {}
for key, (_, can_render) in self.ds.renderers.items():
it_can_render = call_with_supported_arguments(
can_render,
datasette=self.ds,
columns=data.get("columns") or [],
rows=data.get("rows") or [],
sql=data.get("query", {}).get("sql", None),
query_name=data.get("query_name"),
database=database,
table=data.get("table"),
request=request,
view_name=self.name,
)
it_can_render = await await_me_maybe(it_can_render)
if it_can_render:
renderers[key] = self.ds.urls.path(
path_with_format(
request=request,
path=request.scope.get("route_path"),
format=key,
extra_qs={**url_labels_extra},
)
)
url_csv_args = {"_size": "max", **url_labels_extra}
url_csv = self.ds.urls.path(
path_with_format(
request=request,
path=request.scope.get("route_path"),
format="csv",
extra_qs=url_csv_args,
)
)
url_csv_path = url_csv.split("?")[0]
context = {
**data,
**extras,
**{
"renderers": renderers,
"url_csv": url_csv,
"url_csv_path": url_csv_path,
"url_csv_hidden_args": [
(key, value)
for key, value in urllib.parse.parse_qsl(request.query_string)
if key not in ("_labels", "_facet", "_size")
]
+ [("_size", "max")],
"settings": self.ds.settings_dict(),
},
}
if "metadata" not in context:
context["metadata"] = await self.ds.get_instance_metadata()
r = await self.render(templates, request=request, context=context)
if status_code is not None:
r.status = status_code
ttl = request.args.get("_ttl", None)
if ttl is None or not ttl.isdigit():
ttl = self.ds.setting("default_cache_ttl")
return self.set_response_headers(r, ttl)
def set_response_headers(self, response, ttl):
# Set far-future cache expiry
if self.ds.cache_headers and response.status == 200:
ttl = int(ttl)
if ttl == 0:
ttl_header = "no-cache"
else:
ttl_header = f"max-age={ttl}"
response.headers["Cache-Control"] = ttl_header
response.headers["Referrer-Policy"] = "no-referrer"
if self.ds.cors:
add_cors_headers(response.headers)
return response
def _error(messages, status=400):
return Response.json({"ok": False, "errors": messages}, status=status)
async def stream_csv(datasette, fetch_data, request, database):
kwargs = {}
stream = request.args.get("_stream")
# Do not calculate facets or counts:
extra_parameters = [
f"{key}=1" for key in ("_nofacet", "_nocount") if not request.args.get(key)
"{}=1".format(key)
for key in ("_nofacet", "_nocount")
if not request.args.get(key)
]
if extra_parameters:
# Replace request object with a new one with modified scope
@ -210,6 +454,9 @@ async def stream_csv(datasette, fetch_data, request, database):
except (sqlite3.OperationalError, InvalidSql) as e:
raise DatasetteError(str(e), title="Invalid SQL", status=400)
except sqlite3.OperationalError as e:
raise DatasetteError(str(e))
except DatasetteError:
raise
@ -316,9 +563,8 @@ async def stream_csv(datasette, fetch_data, request, database):
else:
new_row.append(cell)
await writer.writerow(new_row)
except Exception as ex: # noqa: BLE001
# Streaming CSV: report the error into the response body and stop
sys.stderr.write(f"Caught this error: {ex}\n")
except Exception as ex:
sys.stderr.write("Caught this error: {}\n".format(ex))
sys.stderr.flush()
await r.write(str(ex))
return

View file

@ -1,79 +1,50 @@
from dataclasses import dataclass, field
from urllib.parse import parse_qsl, urlencode
import asyncio
import hashlib
import itertools
import json
import os
import textwrap
from dataclasses import asdict, dataclass, field
from urllib.parse import parse_qsl, urlencode
import markupsafe
import os
import re
import sqlite_utils
import textwrap
from datasette.events import AlterTableEvent, CreateTableEvent, InsertRowsEvent
from datasette.extras import extra_names_from_request
from datasette.database import QueryInterrupted
from datasette.extras import ExtraScope, extra_names_from_request
from datasette.plugins import pm
from datasette.resources import DatabaseResource, QueryResource
from datasette.stored_queries import StoredQuery, stored_query_to_dict
from datasette.stored_queries import stored_query_to_dict
from datasette.write_sql import QueryWriteRejected
from datasette.utils import (
InvalidSql,
add_cors_headers,
await_me_maybe,
call_with_supported_arguments,
error_body,
named_parameters as derive_named_parameters,
format_bytes,
is_url,
make_slot_function,
tilde_decode,
to_css_class,
validate_sql_select,
is_url,
path_with_added_args,
path_with_format,
path_with_removed_args,
sqlite3,
tilde_decode,
to_css_class,
truncate_url,
validate_sql_select,
InvalidSql,
)
from datasette.utils import (
named_parameters as derive_named_parameters,
)
from datasette.utils.asgi import AsgiFileDownload, Forbidden, NotFound, Response
from datasette.write_sql import QueryWriteRejected
from datasette.utils.asgi import AsgiFileDownload, NotFound, Response, Forbidden
from datasette.plugins import pm
from . import Context
from .base import DatasetteError, View, stream_csv
from .query_helpers import (
_block_framing,
_ensure_stored_query_execution_permissions,
_table_columns,
)
from .table_create_alter import _create_table_ui_context
from .base import BaseView, DatasetteError, View, _error, stream_csv
from .query_helpers import _ensure_stored_query_execution_permissions, _table_columns
from .table_extras import (
QueryExtraContext,
resolve_query_extras,
table_extra_registry,
)
@dataclass
class DatabaseTable:
"Summary of a table or view shown on database and query pages."
name: str
columns: list[str]
primary_keys: list[str]
count: int | None
count_truncated: bool
hidden: bool
fts_table: str | None
foreign_keys: dict[str, list[dict[str, str]]]
private: bool
@dataclass
class DatabaseViewInfo:
"Summary of a SQLite view shown on the database page."
name: str
private: bool
from . import Context
class DatabaseView(View):
@ -107,7 +78,7 @@ class DatabaseView(View):
return response
if format_ not in ("html", "json"):
raise NotFound(f"Invalid format: {format_}")
raise NotFound("Invalid format: {}".format(format_))
metadata = await datasette.get_database_metadata(database)
@ -125,7 +96,7 @@ class DatabaseView(View):
# Filter to just views
view_names_set = set(await db.view_names())
sql_views = [
DatabaseViewInfo(name=name, private=allowed_dict[name].private)
{"name": name, "private": allowed_dict[name].private}
for name in allowed_dict
if name in view_names_set
]
@ -146,36 +117,21 @@ class DatabaseView(View):
else len(stored_queries)
)
# Resolve the registered database-level actions for this database in
# one batched query, seeding the request permission cache so allowed()
# calls made inside plugin hooks below are served from the cache.
database_action_permissions = await datasette.allowed_many(
actions=[
name
for name, action in datasette.actions.items()
if action.resource_class is DatabaseResource
],
resource=DatabaseResource(database),
actor=request.actor,
)
create_table_ui = await _create_table_ui_context(
datasette, request, db, database, database_action_permissions
)
async def database_actions():
# Resolve the registered database-level actions for this
# database in one batched query, seeding the request permission
# cache so that allowed() calls made inside the plugin hooks
# below are served from the cache
await datasette.allowed_many(
actions=[
name
for name, action in datasette.actions.items()
if action.resource_class is DatabaseResource
],
resource=DatabaseResource(database),
actor=request.actor,
)
links = []
if create_table_ui:
links.append(
{
"type": "button",
"label": "Create table",
"description": "Create a new table in this database.",
"attrs": {
"aria-label": f"Create table in {database}",
"data-database-action": "create-table",
},
}
)
for hook in pm.hook.database_actions(
datasette=datasette,
database=database,
@ -200,9 +156,9 @@ class DatabaseView(View):
"private": private,
"path": datasette.urls.database(database),
"size": db.size,
"tables": [asdict(table) for table in tables],
"hidden_count": len([table for table in tables if table.hidden]),
"views": [asdict(view) for view in sql_views],
"tables": tables,
"hidden_count": len([t for t in tables if t["hidden"]]),
"views": sql_views,
"queries": [stored_query_to_dict(query) for query in stored_queries],
"queries_more": queries_more,
"queries_count": queries_count,
@ -242,7 +198,7 @@ class DatabaseView(View):
path=datasette.urls.database(database),
size=db.size,
tables=tables,
hidden_count=len([table for table in tables if table.hidden]),
hidden_count=len([t for t in tables if t["hidden"]]),
views=sql_views,
queries=stored_queries,
queries_more=queries_more,
@ -255,12 +211,10 @@ class DatabaseView(View):
),
metadata=metadata,
database_color=db.color,
database_page_data=(
{"createTable": create_table_ui} if create_table_ui else {}
),
database_actions=database_actions,
show_hidden=request.args.get("_show_hidden"),
editable=True,
count_limit=db.count_limit,
allow_download=datasette.setting("allow_download")
and not db.is_mutable
and not db.is_memory,
@ -278,39 +232,25 @@ class DatabaseView(View):
view_name="database",
),
headers={
"Link": f'<{alternate_url_json}>; rel="alternate"; type="application/json+datasette"'
"Link": '<{}>; rel="alternate"; type="application/json+datasette"'.format(
alternate_url_json
)
},
)
@dataclass
class DatabaseContext(Context):
"The page listing the tables, views and queries in a database, e.g. /fixtures."
documented_template = "database.html"
database: str = field(metadata={"help": "The name of the database"})
private: bool = field(
metadata={"help": "Boolean indicating if this is a private database"}
)
path: str = field(metadata={"help": "The URL path to this database"})
size: int = field(metadata={"help": "The size of the database in bytes"})
tables: list[DatabaseTable] = field(
metadata={
"help": "List of ``DatabaseTable`` objects describing tables in the database. Each item has ``name``, ``columns``, ``primary_keys``, ``count``, ``count_truncated``, ``hidden``, ``fts_table``, ``foreign_keys`` and ``private`` attributes. ``count_truncated`` is true if ``count`` is a capped lower bound rather than an exact total."
}
)
tables: list = field(metadata={"help": "List of table objects in the database"})
hidden_count: int = field(metadata={"help": "Count of hidden tables"})
views: list[DatabaseViewInfo] = field(
metadata={
"help": "List of ``DatabaseViewInfo`` objects describing SQLite views in the database. Each item has ``name`` and ``private`` attributes."
}
)
queries: list[StoredQuery] = field(
metadata={
"help": "List of ``StoredQuery`` objects. Each has attributes including ``name``, ``sql``, ``title``, ``description``, ``description_html``, ``hide_sql``, ``fragment``, ``parameters``, ``is_write`` and ``private``."
}
)
views: list = field(metadata={"help": "List of view objects in the database"})
queries: list = field(metadata={"help": "List of stored query objects"})
queries_more: bool = field(
metadata={"help": "Boolean indicating if more stored queries are available"}
)
@ -319,65 +259,45 @@ class DatabaseContext(Context):
metadata={"help": "Boolean indicating if custom SQL can be executed"}
)
table_columns: dict = field(
metadata={
"help": "Dictionary mapping table names to lists of column names, used to power SQL autocomplete."
}
)
metadata: dict = field(
metadata={
"help": "Metadata dictionary for the database, such as ``title``, ``description``, ``license`` and ``source`` values from Datasette metadata."
}
metadata={"help": "Dictionary mapping table names to their column lists"}
)
metadata: dict = field(metadata={"help": "Metadata for the database"})
database_color: str = field(metadata={"help": "The color assigned to the database"})
database_page_data: dict = field(
metadata={
"help": 'JSON data used by JavaScript on the database page. Currently ``{}`` or ``{"createTable": {...}}`` where ``createTable`` includes ``path``, ``foreignKeyTargetsPath``, ``databaseName``, ``columnTypes``, ``defaultExpressions``, ``canInsertRows`` and optional ``customColumnTypes``.'
}
)
database_actions: callable = field(
metadata={
"help": 'Async callable returning action items for the database menu. Each item is either a link with ``href``, ``label`` and optional ``description`` keys, or a button with ``type: "button"``, ``label``, optional ``description`` and optional ``attrs``. See :ref:`plugin_actions` and :ref:`plugin_hook_database_actions`.'
"help": "Callable returning list of action links for the database menu"
}
)
show_hidden: str = field(metadata={"help": "Value of _show_hidden query parameter"})
editable: bool = field(
metadata={"help": "Boolean indicating if the database is editable"}
)
count_limit: int = field(metadata={"help": "The maximum number of rows to count"})
allow_download: bool = field(
metadata={"help": "Boolean indicating if database download is allowed"}
)
attached_databases: list = field(
metadata={
"help": "List of names of databases attached to this SQLite connection. This is only populated for the special ``/_memory`` database when Datasette is started with ``--crossdb`` for :ref:`cross_database_queries`."
}
metadata={"help": "List of names of attached databases"}
)
alternate_url_json: str = field(
metadata={"help": "URL for the alternate JSON version of this page"}
)
select_templates: list = field(
metadata={
"help": "List of template names that were considered for this page, with the selected template prefixed by ``*``."
"help": "List of templates that were considered for rendering this page"
}
)
top_database: callable = field(
metadata={
"help": "Async callable that renders the ``top_database`` plugin slot for this database and returns HTML."
}
metadata={"help": "Callable to render the top_database slot"}
)
@dataclass
class QueryContext(Context):
"The page for arbitrary SQL queries (/database/-/query?sql=...) and stored queries (/database/query-name)."
documented_template = "query.html"
database: str = field(metadata={"help": "The name of the database being queried"})
database_color: str = field(metadata={"help": "The color of the database"})
query: dict = field(
metadata={
"help": "Dictionary describing the SQL query being executed, with ``sql`` and ``params`` keys."
}
metadata={"help": "The SQL query object containing the `sql` string"}
)
stored_query: str = field(
metadata={"help": "The name of the stored query if this is a stored query"}
@ -394,9 +314,7 @@ class QueryContext(Context):
}
)
metadata: dict = field(
metadata={
"help": "Metadata dictionary for the database or stored query. Stored query metadata may include options such as ``hide_sql``, ``on_success_message`` and ``on_error_redirect``."
}
metadata={"help": "Metadata about the database or the stored query"}
)
db_is_immutable: bool = field(
metadata={"help": "Boolean indicating if this database is immutable"}
@ -420,44 +338,22 @@ class QueryContext(Context):
save_query_url: str = field(
metadata={"help": "URL to save the current arbitrary SQL as a query"}
)
tables: list[DatabaseTable] = field(
metadata={
"help": "List of ``DatabaseTable`` objects describing tables in the database. Each item has ``name``, ``columns``, ``primary_keys``, ``count``, ``count_truncated``, ``hidden``, ``fts_table``, ``foreign_keys`` and ``private`` attributes. ``count_truncated`` is true if ``count`` is a capped lower bound rather than an exact total."
}
)
tables: list = field(metadata={"help": "List of table objects in the database"})
named_parameter_values: dict = field(
metadata={
"help": "Dictionary of named SQL parameter values, keyed by parameter name without the leading ``:``."
}
metadata={"help": "Dictionary of parameter names/values"}
)
edit_sql_url: str = field(
metadata={"help": "URL to edit the SQL for a stored query"}
)
display_rows: list = field(
metadata={
"help": "List of result rows formatted for HTML display. Each row is a list of rendered cell values in the same order as ``columns``."
}
)
columns: list = field(
metadata={
"help": "List of result column names in the order they appear in ``display_rows`` and ``rows``."
}
)
renderers: dict = field(
metadata={
"help": "Dictionary mapping output format names such as ``json`` to URLs for this query in that format."
}
)
display_rows: list = field(metadata={"help": "List of result rows to display"})
columns: list = field(metadata={"help": "List of column names"})
renderers: dict = field(metadata={"help": "Dictionary of renderer name to URL"})
url_csv: str = field(metadata={"help": "URL for CSV export"})
show_hide_hidden: str = field(
metadata={
"help": "Rendered hidden ``<input>`` HTML preserving the current ``_hide_sql`` or ``_show_sql`` state."
}
metadata={"help": "Hidden input field for the _show_sql parameter"}
)
table_columns: dict = field(
metadata={
"help": "Dictionary mapping table names to lists of column names, used to power SQL autocomplete."
}
metadata={"help": "Dictionary of table name to list of column names"}
)
alternate_url_json: str = field(
metadata={"help": "URL for alternate JSON version of this page"}
@ -465,27 +361,23 @@ class QueryContext(Context):
# TODO: refactor this to somewhere else, probably ds.render_template()
select_templates: list = field(
metadata={
"help": "List of template names that were considered for this page, with the selected template prefixed by ``*``."
"help": "List of templates that were considered for rendering this page"
}
)
top_query: callable = field(
metadata={
"help": "Async callable that renders the ``top_query`` plugin slot for this query and returns HTML."
}
metadata={"help": "Callable to render the top_query slot"}
)
top_stored_query: callable = field(
metadata={
"help": "Async callable that renders the ``top_stored_query`` plugin slot for stored queries and returns HTML."
}
metadata={"help": "Callable to render the top_stored_query slot"}
)
query_actions: callable = field(
metadata={
"help": 'Async callable returning action items for the query menu. Each item is either a link with ``href``, ``label`` and optional ``description`` keys, or a button with ``type: "button"``, ``label``, optional ``description`` and optional ``attrs``. See :ref:`plugin_actions` and :ref:`plugin_hook_query_actions`.'
"help": "Callable returning a list of links for the query action menu"
}
)
async def get_tables(datasette, request, db, allowed_dict) -> list[DatabaseTable]:
async def get_tables(datasette, request, db, allowed_dict):
"""
Get list of tables with metadata for the database view.
@ -506,36 +398,21 @@ async def get_tables(datasette, request, db, allowed_dict) -> list[DatabaseTable
table_columns = await db.table_columns(table)
tables.append(
DatabaseTable(
name=table,
columns=table_columns,
primary_keys=await db.primary_keys(table),
count=table_counts[table],
count_truncated=_table_count_truncated(
datasette, db, table, table_counts[table]
),
hidden=table in hidden_table_names,
fts_table=await db.fts_table(table),
foreign_keys=all_foreign_keys[table],
private=allowed_dict[table].private,
)
{
"name": table,
"columns": table_columns,
"primary_keys": await db.primary_keys(table),
"count": table_counts[table],
"hidden": table in hidden_table_names,
"fts_table": await db.fts_table(table),
"foreign_keys": all_foreign_keys[table],
"private": allowed_dict[table].private,
}
)
tables.sort(key=lambda table: (table.hidden, table.name))
tables.sort(key=lambda t: (t["hidden"], t["name"]))
return tables
def _table_count_truncated(datasette, db, table, count):
if count != db.count_limit + 1:
return False
if not db.is_mutable and datasette.inspect_data:
try:
datasette.inspect_data[db.name]["tables"][table]["count"]
return False
except KeyError:
pass
return True
async def database_download(request, datasette):
from datasette.resources import DatabaseResource
@ -561,7 +438,7 @@ async def database_download(request, datasette):
if datasette.cors:
add_cors_headers(headers)
if db.hash:
etag = f'"{db.hash}"'
etag = '"{}"'.format(db.hash)
headers["Etag"] = etag
# Has user seen this already?
if_none_match = request.headers.get("if-none-match")
@ -613,7 +490,11 @@ class QueryView(View):
"_json"
):
return Response.json(
dict(error_body([ex.message], 403), redirect=None),
{
"ok": False,
"message": ex.message,
"redirect": None,
},
status=403,
)
datasette.add_message(request, ex.message, datasette.ERROR)
@ -648,15 +529,8 @@ class QueryView(View):
ok = None
redirect_url = None
try:
execute_write_kwargs = {"request": request}
if stored_query.is_trusted:
analysis = await db.analyze_sql(stored_query.sql, params_for_query)
if any(
operation.operation == "vacuum" for operation in analysis.operations
):
execute_write_kwargs["transaction"] = False
cursor = await db.execute_write(
stored_query.sql, params_for_query, **execute_write_kwargs
stored_query.sql, params_for_query, request=request
)
# success message can come from on_success_message or on_success_message_sql
message = None
@ -669,9 +543,8 @@ class QueryView(View):
).first()
if message_result:
message = message_result[0]
except Exception as ex: # noqa: BLE001
# Stored-query on_success_message_sql is user-authored
message = f"Error running on_success_message_sql: {ex}"
except Exception as ex:
message = "Error running on_success_message_sql: {}".format(ex)
message_type = datasette.ERROR
if not message:
if stored_query.on_success_message:
@ -685,24 +558,18 @@ class QueryView(View):
redirect_url = stored_query.on_success_redirect
ok = True
except Exception as ex: # noqa: BLE001
# Stored-query execution is user-authored SQL
except Exception as ex:
message = stored_query.on_error_message or str(ex)
message_type = datasette.ERROR
redirect_url = stored_query.on_error_redirect
ok = False
if should_return_json:
if ok:
return Response.json(
{
"ok": True,
"message": message,
"redirect": redirect_url,
}
)
return Response.json(
dict(error_body([message], 400), redirect=redirect_url),
status=400,
{
"ok": ok,
"message": message,
"redirect": redirect_url,
}
)
else:
datasette.add_message(request, message, message_type)
@ -820,23 +687,19 @@ class QueryView(View):
rows = results.rows
except QueryInterrupted as ex:
raise DatasetteError(
textwrap.dedent(f"""
textwrap.dedent("""
<p>SQL query took too long. The time limit is controlled by the
<a href="https://docs.datasette.io/en/stable/settings.html#sql-time-limit-ms">sql_time_limit_ms</a>
configuration option.</p>
<textarea style="width: 90%">{markupsafe.escape(ex.sql)}</textarea>
<textarea style="width: 90%">{}</textarea>
<script>
let ta = document.querySelector("textarea");
ta.style.height = ta.scrollHeight + "px";
</script>
""").strip(),
""".format(markupsafe.escape(ex.sql))).strip(),
title="SQL Interrupted",
status=400,
message_is_html=True,
plain_message=(
"SQL query took too long. The time limit is"
" controlled by the sql_time_limit_ms setting."
),
)
except sqlite3.DatabaseError as ex:
query_error = str(ex)
@ -845,6 +708,8 @@ class QueryView(View):
columns = []
except (sqlite3.OperationalError, InvalidSql) as ex:
raise DatasetteError(str(ex), title="Invalid SQL", status=400)
except sqlite3.OperationalError as ex:
raise DatasetteError(str(ex))
except DatasetteError:
raise
@ -861,18 +726,14 @@ class QueryView(View):
raise DatasetteError("?sql= is required", status=400)
async def fetch_data_for_csv(request, _next=None):
# Reuse the trusted magic parameter values prepared above.
results = await db.execute(sql, params_for_query, truncate=True)
results = await db.execute(sql, params, truncate=True)
data = {"rows": results.rows, "columns": results.columns}
return data, None, None
return await stream_csv(datasette, fetch_data_for_csv, request, db.name)
elif format_ in datasette.renderers:
if not sql:
raise DatasetteError("?sql= is required", status=400)
elif format_ in datasette.renderers.keys():
data = {"ok": True, "rows": rows, "columns": columns}
extras = extra_names_from_request(request)
table_extra_registry.validate_requested(extras, ExtraScope.QUERY)
if extras:
query_extra_context = QueryExtraContext(
datasette=datasette,
@ -959,7 +820,9 @@ class QueryView(View):
}
headers.update(
{
"Link": f'<{alternate_url_json}>; rel="alternate"; type="application/json+datasette"'
"Link": '<{}>; rel="alternate"; type="application/json+datasette"'.format(
alternate_url_json
)
}
)
metadata = await query_metadata()
@ -1040,7 +903,9 @@ class QueryView(View):
+ "?"
+ urlencode(
{
"sql": sql,
**{
"sql": sql,
},
**named_parameter_values,
}
)
@ -1142,11 +1007,9 @@ class QueryView(View):
headers=headers,
)
else:
assert False, f"Invalid format: {format_}"
assert False, "Invalid format: {}".format(format_)
if datasette.cors:
add_cors_headers(r.headers)
if stored_query_write and format_ == "html":
_block_framing(r)
return r
@ -1192,6 +1055,260 @@ class MagicParameters(dict):
return super().__getitem__(key)
class TableCreateView(BaseView):
name = "table-create"
_valid_keys = {
"table",
"rows",
"row",
"columns",
"pk",
"pks",
"ignore",
"replace",
"alter",
}
_supported_column_types = {
"text",
"integer",
"float",
"blob",
}
# Any string that does not contain a newline or start with sqlite_
_table_name_re = re.compile(r"^(?!sqlite_)[^\n]+$")
def __init__(self, datasette):
self.ds = datasette
async def post(self, request):
db = await self.ds.resolve_database(request)
database_name = db.name
# Must have create-table permission
if not await self.ds.allowed(
action="create-table",
resource=DatabaseResource(database=database_name),
actor=request.actor,
):
return _error(["Permission denied"], 403)
try:
data = await request.json()
except json.JSONDecodeError as e:
return _error(["Invalid JSON: {}".format(e)])
if not isinstance(data, dict):
return _error(["JSON must be an object"])
invalid_keys = set(data.keys()) - self._valid_keys
if invalid_keys:
return _error(["Invalid keys: {}".format(", ".join(invalid_keys))])
# ignore and replace are mutually exclusive
if data.get("ignore") and data.get("replace"):
return _error(["ignore and replace are mutually exclusive"])
# ignore and replace only allowed with row or rows
if "ignore" in data or "replace" in data:
if not data.get("row") and not data.get("rows"):
return _error(["ignore and replace require row or rows"])
# ignore and replace require pk or pks
if "ignore" in data or "replace" in data:
if not data.get("pk") and not data.get("pks"):
return _error(["ignore and replace require pk or pks"])
ignore = data.get("ignore")
replace = data.get("replace")
if replace:
# Must have update-row permission
if not await self.ds.allowed(
action="update-row",
resource=DatabaseResource(database=database_name),
actor=request.actor,
):
return _error(["Permission denied: need update-row"], 403)
table_name = data.get("table")
if not table_name:
return _error(["Table is required"])
if not self._table_name_re.match(table_name):
return _error(["Invalid table name"])
table_exists = await db.table_exists(data["table"])
columns = data.get("columns")
rows = data.get("rows")
row = data.get("row")
if not columns and not rows and not row:
return _error(["columns, rows or row is required"])
if rows and row:
return _error(["Cannot specify both rows and row"])
if rows or row:
# Must have insert-row permission
if not await self.ds.allowed(
action="insert-row",
resource=DatabaseResource(database=database_name),
actor=request.actor,
):
return _error(["Permission denied: need insert-row"], 403)
alter = False
if rows or row:
if not table_exists:
# if table is being created for the first time, alter=True
alter = True
else:
# alter=True only if they request it AND they have permission
if data.get("alter"):
if not await self.ds.allowed(
action="alter-table",
resource=DatabaseResource(database=database_name),
actor=request.actor,
):
return _error(["Permission denied: need alter-table"], 403)
alter = True
if columns:
if rows or row:
return _error(["Cannot specify columns with rows or row"])
if not isinstance(columns, list):
return _error(["columns must be a list"])
for column in columns:
if not isinstance(column, dict):
return _error(["columns must be a list of objects"])
if not column.get("name") or not isinstance(column.get("name"), str):
return _error(["Column name is required"])
if not column.get("type"):
column["type"] = "text"
if column["type"] not in self._supported_column_types:
return _error(
["Unsupported column type: {}".format(column["type"])]
)
# No duplicate column names
dupes = {c["name"] for c in columns if columns.count(c) > 1}
if dupes:
return _error(["Duplicate column name: {}".format(", ".join(dupes))])
if row:
rows = [row]
if rows:
if not isinstance(rows, list):
return _error(["rows must be a list"])
for row in rows:
if not isinstance(row, dict):
return _error(["rows must be a list of objects"])
pk = data.get("pk")
pks = data.get("pks")
if pk and pks:
return _error(["Cannot specify both pk and pks"])
if pk:
if not isinstance(pk, str):
return _error(["pk must be a string"])
if pks:
if not isinstance(pks, list):
return _error(["pks must be a list"])
for pk in pks:
if not isinstance(pk, str):
return _error(["pks must be a list of strings"])
# If table exists already, read pks from that instead
if table_exists:
actual_pks = await db.primary_keys(table_name)
# if pk passed and table already exists check it does not change
bad_pks = False
if len(actual_pks) == 1 and data.get("pk") and data["pk"] != actual_pks[0]:
bad_pks = True
elif (
len(actual_pks) > 1
and data.get("pks")
and set(data["pks"]) != set(actual_pks)
):
bad_pks = True
if bad_pks:
return _error(["pk cannot be changed for existing table"])
pks = actual_pks
initial_schema = None
if table_exists:
initial_schema = await db.execute_fn(
lambda conn: sqlite_utils.Database(conn)[table_name].schema
)
def create_table(conn):
table = sqlite_utils.Database(conn)[table_name]
if rows:
table.insert_all(
rows, pk=pks or pk, ignore=ignore, replace=replace, alter=alter
)
else:
table.create(
{c["name"]: c["type"] for c in columns},
pk=pks or pk,
)
return table.schema
try:
schema = await db.execute_write_fn(create_table, request=request)
except Exception as e:
return _error([str(e)])
if initial_schema is not None and initial_schema != schema:
await self.ds.track_event(
AlterTableEvent(
request.actor,
database=database_name,
table=table_name,
before_schema=initial_schema,
after_schema=schema,
)
)
table_url = self.ds.absolute_url(
request, self.ds.urls.table(db.name, table_name)
)
table_api_url = self.ds.absolute_url(
request, self.ds.urls.table(db.name, table_name, format="json")
)
details = {
"ok": True,
"database": db.name,
"table": table_name,
"table_url": table_url,
"table_api_url": table_api_url,
"schema": schema,
}
if rows:
details["row_count"] = len(rows)
if not table_exists:
# Only log creation if we created a table
await self.ds.track_event(
CreateTableEvent(
request.actor, database=db.name, table=table_name, schema=schema
)
)
if rows:
await self.ds.track_event(
InsertRowsEvent(
request.actor,
database=db.name,
table=table_name,
num_rows=len(rows),
ignore=ignore,
replace=replace,
)
)
return Response.json(details, status=201)
async def display_rows(datasette, database, request, rows, columns):
display_rows = []
truncate_cells = datasette.setting("truncate_cells_html")
@ -1245,7 +1362,7 @@ async def display_rows(datasette, database, request, rows, columns):
'<a class="blob-download" href="{}"{}>&lt;Binary:&nbsp;{:,}&nbsp;byte{}&gt;</a>'.format(
blob_url,
(
f' title="{formatted}"'
' title="{}"'.format(formatted)
if "bytes" not in formatted
else ""
),

Some files were not shown because too many files have changed in this diff Show more