From 76ceb4915c003a2674d2eb9e0e1596c1f000c608 Mon Sep 17 00:00:00 2001 From: Ben Warren <75187597+warrenbhw@users.noreply.github.com> Date: Sun, 24 Nov 2024 01:15:17 -0800 Subject: [PATCH] Initial commit --- .editorconfig | 1 + .github/workflows/ExtensionTemplate.yml | 178 ++++++++++++++++++ .../workflows/MainDistributionPipeline.yml | 39 ++++ .github/workflows/_extension_deploy.yml | 121 ++++++++++++ .gitignore | 8 + .gitmodules | 8 + CMakeLists.txt | 30 +++ LICENSE | 7 + Makefile | 8 + docs/NEXT_README.md | 86 +++++++++ docs/README.md | 137 ++++++++++++++ docs/UPDATING.md | 23 +++ duckdb | 1 + extension-ci-tools | 1 + extension_config.cmake | 10 + scripts/bootstrap-template.py | 94 +++++++++ scripts/extension-upload.sh | 90 +++++++++ scripts/setup-custom-toolchain.sh | 11 ++ src/include/quack_extension.hpp | 14 ++ src/quack_extension.cpp | 78 ++++++++ test/README.md | 11 ++ test/sql/quack.test | 23 +++ vcpkg.json | 5 + 23 files changed, 984 insertions(+) create mode 120000 .editorconfig create mode 100644 .github/workflows/ExtensionTemplate.yml create mode 100644 .github/workflows/MainDistributionPipeline.yml create mode 100644 .github/workflows/_extension_deploy.yml create mode 100644 .gitignore create mode 100644 .gitmodules create mode 100644 CMakeLists.txt create mode 100644 LICENSE create mode 100644 Makefile create mode 100644 docs/NEXT_README.md create mode 100644 docs/README.md create mode 100644 docs/UPDATING.md create mode 160000 duckdb create mode 160000 extension-ci-tools create mode 100644 extension_config.cmake create mode 100755 scripts/bootstrap-template.py create mode 100755 scripts/extension-upload.sh create mode 100644 scripts/setup-custom-toolchain.sh create mode 100644 src/include/quack_extension.hpp create mode 100644 src/quack_extension.cpp create mode 100644 test/README.md create mode 100644 test/sql/quack.test create mode 100644 vcpkg.json diff --git a/.editorconfig b/.editorconfig new file mode 120000 index 0000000..ec7786c --- /dev/null +++ b/.editorconfig @@ -0,0 +1 @@ +duckdb/.editorconfig \ No newline at end of file diff --git a/.github/workflows/ExtensionTemplate.yml b/.github/workflows/ExtensionTemplate.yml new file mode 100644 index 0000000..0b2c52c --- /dev/null +++ b/.github/workflows/ExtensionTemplate.yml @@ -0,0 +1,178 @@ +# +# NOTE: this workflow is for testing the extension template itself, +# this workflow will be removed when scripts/bootstrap-template.py is run +# +name: Extension Template +on: [push, pull_request,repository_dispatch] +concurrency: + group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || '' }}-${{ github.base_ref || '' }}-${{ github.ref != 'refs/heads/main' || github.sha }} + cancel-in-progress: true + +jobs: + linux: + name: Linux + if: ${{ vars.RUN_RENAME_TEST == 'true' || github.repository == 'duckdb/extension-template' }} + runs-on: ubuntu-latest + container: ubuntu:18.04 + strategy: + matrix: + # Add commits/tags to build against other DuckDB versions + duckdb_version: [ '' ] + env: + VCPKG_TOOLCHAIN_PATH: ${{ github.workspace }}/vcpkg/scripts/buildsystems/vcpkg.cmake + VCPKG_TARGET_TRIPLET: 'x64-linux' + GEN: ninja + ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true + defaults: + run: + shell: bash + + steps: + - name: Install required ubuntu packages + run: | + apt-get update -y -qq + apt-get install -y -qq software-properties-common + add-apt-repository ppa:git-core/ppa + apt-get update -y -qq + apt-get install -y -qq ninja-build make gcc-multilib g++-multilib libssl-dev wget openjdk-8-jdk zip maven unixodbc-dev libc6-dev-i386 lib32readline6-dev libssl-dev libcurl4-gnutls-dev libexpat1-dev gettext unzip build-essential checkinstall libffi-dev curl libz-dev openssh-client + + - name: Install Git 2.18.5 + run: | + wget https://github.com/git/git/archive/refs/tags/v2.18.5.tar.gz + tar xvf v2.18.5.tar.gz + cd git-2.18.5 + make + make prefix=/usr install + git --version + + - uses: actions/checkout@v3 + with: + fetch-depth: 0 + submodules: 'true' + + - name: Checkout DuckDB to version + if: ${{ matrix.duckdb_version != ''}} + run: | + cd duckdb + git checkout ${{ matrix.duckdb_version }} + + - uses: ./duckdb/.github/actions/ubuntu_18_setup + + - name: Setup vcpkg + uses: lukka/run-vcpkg@v11.1 + with: + vcpkgGitCommitId: a1a1cbc975abf909a6c8985a6a2b8fe20bbd9bd6 + + - name: Rename extension + run: | + python3 scripts/bootstrap-template.py ext_1_a_123b_b11 + + - name: Build + run: | + make + + - name: Test + run: | + make test + + macos: + name: MacOS + if: ${{ vars.RUN_RENAME_TEST == 'true' || github.repository == 'duckdb/extension-template' }} + runs-on: macos-latest + strategy: + matrix: + # Add commits/tags to build against other DuckDB versions + duckdb_version: [ ''] + env: + VCPKG_TOOLCHAIN_PATH: ${{ github.workspace }}/vcpkg/scripts/buildsystems/vcpkg.cmake + VCPKG_TARGET_TRIPLET: 'x64-osx' + OSX_BUILD_ARCH: 'x86_64' + GEN: ninja + defaults: + run: + shell: bash + + steps: + - uses: actions/checkout@v3 + with: + fetch-depth: 0 + submodules: 'true' + + - name: Install Ninja + run: brew install ninja + + - uses: actions/setup-python@v2 + with: + python-version: '3.11' + + - name: Checkout DuckDB to version + if: ${{ matrix.duckdb_version != ''}} + run: | + cd duckdb + git checkout ${{ matrix.duckdb_version }} + + - name: Setup vcpkg + uses: lukka/run-vcpkg@v11.1 + with: + vcpkgGitCommitId: a1a1cbc975abf909a6c8985a6a2b8fe20bbd9bd6 + + - name: Rename extension + run: | + python scripts/bootstrap-template.py ext_1_a_123b_b11 + + - name: Build + run: | + make + + - name: Test + run: | + make test + + windows: + name: Windows + if: ${{ vars.RUN_RENAME_TEST == 'true' || github.repository == 'duckdb/extension-template' }} + runs-on: windows-latest + strategy: + matrix: + # Add commits/tags to build against other DuckDB versions + duckdb_version: [ '' ] + env: + VCPKG_TOOLCHAIN_PATH: ${{ github.workspace }}/vcpkg/scripts/buildsystems/vcpkg.cmake + VCPKG_TARGET_TRIPLET: 'x64-windows-static-md' + defaults: + run: + shell: bash + + steps: + - uses: actions/checkout@v3 + with: + fetch-depth: 0 + submodules: 'true' + + - uses: actions/setup-python@v2 + with: + python-version: '3.11' + + - name: Checkout DuckDB to version + # Add commits/tags to build against other DuckDB versions + if: ${{ matrix.duckdb_version != ''}} + run: | + cd duckdb + git checkout ${{ matrix.duckdb_version }} + + - name: Setup vcpkg + uses: lukka/run-vcpkg@v11.1 + with: + vcpkgGitCommitId: a1a1cbc975abf909a6c8985a6a2b8fe20bbd9bd6 + + - name: Rename extension + run: | + python scripts/bootstrap-template.py ext_1_a_123b_b11 + + - name: Build + run: | + make + + - name: Test extension + run: | + build/release/test/Release/unittest.exe \ No newline at end of file diff --git a/.github/workflows/MainDistributionPipeline.yml b/.github/workflows/MainDistributionPipeline.yml new file mode 100644 index 0000000..0b96e22 --- /dev/null +++ b/.github/workflows/MainDistributionPipeline.yml @@ -0,0 +1,39 @@ +# +# This workflow calls the main distribution pipeline from DuckDB to build, test and (optionally) release the extension +# +name: Main Extension Distribution Pipeline +on: + push: + pull_request: + workflow_dispatch: + +concurrency: + group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || '' }}-${{ github.base_ref || '' }}-${{ github.ref != 'refs/heads/main' || github.sha }} + cancel-in-progress: true + +jobs: + duckdb-next-build: + name: Build extension binaries + uses: duckdb/extension-ci-tools/.github/workflows/_extension_distribution.yml@main + with: + duckdb_version: main + ci_tools_version: main + extension_name: quack + + duckdb-stable-build: + name: Build extension binaries + uses: duckdb/extension-ci-tools/.github/workflows/_extension_distribution.yml@v1.1.3 + with: + duckdb_version: v1.1.3 + ci_tools_version: v1.1.3 + extension_name: quack + + duckdb-stable-deploy: + name: Deploy extension binaries + needs: duckdb-stable-build + uses: ./.github/workflows/_extension_deploy.yml + secrets: inherit + with: + duckdb_version: v1.1.3 + extension_name: quack + deploy_latest: ${{ startsWith(github.ref, 'refs/tags/v') || github.ref == 'refs/heads/main' }} diff --git a/.github/workflows/_extension_deploy.yml b/.github/workflows/_extension_deploy.yml new file mode 100644 index 0000000..604a24a --- /dev/null +++ b/.github/workflows/_extension_deploy.yml @@ -0,0 +1,121 @@ +# +# Reusable workflow that deploys the artifacts produced by github.com/duckdb/duckdb/.github/workflows/_extension_distribution.yml +# +# note: this workflow needs to be located in the extension repository, as it requires secrets to be passed to the +# deploy script. However, it should generally not be necessary to modify this workflow in your extension repository, as +# this workflow can be configured to use a custom deploy script. + + +name: Extension Deployment +on: + workflow_call: + inputs: + # The name of the extension + extension_name: + required: true + type: string + # DuckDB version to build against + duckdb_version: + required: true + type: string + # ';' separated list of architectures to exclude, for example: 'linux_amd64;osx_arm64' + exclude_archs: + required: false + type: string + default: "" + # Whether to upload this deployment as the latest. This may overwrite a previous deployment. + deploy_latest: + required: false + type: boolean + default: false + # Whether to upload this deployment under a versioned path. These will not be deleted automatically + deploy_versioned: + required: false + type: boolean + default: false + # Postfix added to artifact names. Can be used to guarantee unique names when this workflow is called multiple times + artifact_postfix: + required: false + type: string + default: "" + # Override the default deploy script with a custom script + deploy_script: + required: false + type: string + default: "./scripts/extension-upload.sh" + # Override the default matrix parse script with a custom script + matrix_parse_script: + required: false + type: string + default: "./duckdb/scripts/modify_distribution_matrix.py" + +jobs: + generate_matrix: + name: Generate matrix + runs-on: ubuntu-latest + outputs: + deploy_matrix: ${{ steps.parse-matrices.outputs.deploy_matrix }} + steps: + - uses: actions/checkout@v3 + with: + fetch-depth: 0 + submodules: 'true' + + - name: Checkout DuckDB to version + run: | + cd duckdb + git checkout ${{ inputs.duckdb_version }} + + - id: parse-matrices + run: | + python3 ${{ inputs.matrix_parse_script }} --input ./duckdb/.github/config/distribution_matrix.json --deploy_matrix --output deploy_matrix.json --exclude "${{ inputs.exclude_archs }}" --pretty + deploy_matrix="`cat deploy_matrix.json`" + echo deploy_matrix=$deploy_matrix >> $GITHUB_OUTPUT + echo `cat $GITHUB_OUTPUT` + + deploy: + name: Deploy + runs-on: ubuntu-latest + needs: generate_matrix + if: ${{ needs.generate_matrix.outputs.deploy_matrix != '{}' && needs.generate_matrix.outputs.deploy_matrix != '' }} + strategy: + matrix: ${{fromJson(needs.generate_matrix.outputs.deploy_matrix)}} + + steps: + - uses: actions/checkout@v3 + with: + fetch-depth: 0 + submodules: 'true' + + - name: Checkout DuckDB to version + run: | + cd duckdb + git checkout ${{ inputs.duckdb_version }} + + - uses: actions/download-artifact@v3 + with: + name: ${{ inputs.extension_name }}-${{ inputs.duckdb_version }}-extension-${{matrix.duckdb_arch}}${{inputs.artifact_postfix}}${{startsWith(matrix.duckdb, 'wasm') && '.wasm' || ''}} + path: | + /tmp/extension + + - name: Deploy + shell: bash + env: + AWS_ACCESS_KEY_ID: ${{ secrets.S3_DEPLOY_ID }} + AWS_SECRET_ACCESS_KEY: ${{ secrets.S3_DEPLOY_KEY }} + AWS_DEFAULT_REGION: ${{ secrets.S3_REGION }} + BUCKET_NAME: ${{ secrets.S3_BUCKET }} + DUCKDB_EXTENSION_SIGNING_PK: ${{ secrets.S3_DUCKDB_ORG_EXTENSION_SIGNING_PK }} + run: | + pwd + python3 -m pip install pip awscli + git config --global --add safe.directory '*' + cd duckdb + git fetch --tags + export DUCKDB_VERSION=`git tag --points-at HEAD` + export DUCKDB_VERSION=${DUCKDB_VERSION:=`git log -1 --format=%h`} + cd .. + git fetch --tags + export EXT_VERSION=`git tag --points-at HEAD` + export EXT_VERSION=${EXT_VERSION:=`git log -1 --format=%h`} + ${{ inputs.deploy_script }} ${{ inputs.extension_name }} $EXT_VERSION $DUCKDB_VERSION ${{ matrix.duckdb_arch }} $BUCKET_NAME ${{inputs.deploy_latest || 'true' && 'false'}} ${{inputs.deploy_versioned || 'true' && 'false'}} diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..b9f264b --- /dev/null +++ b/.gitignore @@ -0,0 +1,8 @@ +build +.idea +cmake-build-debug +duckdb_unittest_tempdir/ +.DS_Store +testext +test/python/__pycache__/ +.Rhistory diff --git a/.gitmodules b/.gitmodules new file mode 100644 index 0000000..01b02cb --- /dev/null +++ b/.gitmodules @@ -0,0 +1,8 @@ +[submodule "duckdb"] + path = duckdb + url = https://github.com/duckdb/duckdb + branch = main +[submodule "extension-ci-tools"] + path = extension-ci-tools + url = https://github.com/duckdb/extension-ci-tools + branch = main \ No newline at end of file diff --git a/CMakeLists.txt b/CMakeLists.txt new file mode 100644 index 0000000..1d144aa --- /dev/null +++ b/CMakeLists.txt @@ -0,0 +1,30 @@ +cmake_minimum_required(VERSION 3.5) + +# Set extension name here +set(TARGET_NAME quack) + +# DuckDB's extension distribution supports vcpkg. As such, dependencies can be added in ./vcpkg.json and then +# used in cmake with find_package. Feel free to remove or replace with other dependencies. +# Note that it should also be removed from vcpkg.json to prevent needlessly installing it.. +find_package(OpenSSL REQUIRED) + +set(EXTENSION_NAME ${TARGET_NAME}_extension) +set(LOADABLE_EXTENSION_NAME ${TARGET_NAME}_loadable_extension) + +project(${TARGET_NAME}) +include_directories(src/include) + +set(EXTENSION_SOURCES src/quack_extension.cpp) + +build_static_extension(${TARGET_NAME} ${EXTENSION_SOURCES}) +build_loadable_extension(${TARGET_NAME} " " ${EXTENSION_SOURCES}) + +# Link OpenSSL in both the static library as the loadable extension +target_link_libraries(${EXTENSION_NAME} OpenSSL::SSL OpenSSL::Crypto) +target_link_libraries(${LOADABLE_EXTENSION_NAME} OpenSSL::SSL OpenSSL::Crypto) + +install( + TARGETS ${EXTENSION_NAME} + EXPORT "${DUCKDB_EXPORT_SET}" + LIBRARY DESTINATION "${INSTALL_LIB_DIR}" + ARCHIVE DESTINATION "${INSTALL_LIB_DIR}") diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..4ab49ab --- /dev/null +++ b/LICENSE @@ -0,0 +1,7 @@ +Copyright 2018-2024 Stichting DuckDB Foundation + +Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. \ No newline at end of file diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..e91db43 --- /dev/null +++ b/Makefile @@ -0,0 +1,8 @@ +PROJ_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST)))) + +# Configuration of extension +EXT_NAME=quack +EXT_CONFIG=${PROJ_DIR}extension_config.cmake + +# Include the Makefile from extension-ci-tools +include extension-ci-tools/makefiles/duckdb_extension.Makefile \ No newline at end of file diff --git a/docs/NEXT_README.md b/docs/NEXT_README.md new file mode 100644 index 0000000..96f0482 --- /dev/null +++ b/docs/NEXT_README.md @@ -0,0 +1,86 @@ +# Quack + +This repository is based on https://github.com/duckdb/extension-template, check it out if you want to build and ship your own DuckDB extension. + +--- + +This extension, Quack, allow you to ... . + + +## Building +### Managing dependencies +DuckDB extensions uses VCPKG for dependency management. Enabling VCPKG is very simple: follow the [installation instructions](https://vcpkg.io/en/getting-started) or just run the following: +```shell +git clone https://github.com/Microsoft/vcpkg.git +./vcpkg/bootstrap-vcpkg.sh +export VCPKG_TOOLCHAIN_PATH=`pwd`/vcpkg/scripts/buildsystems/vcpkg.cmake +``` +Note: VCPKG is only required for extensions that want to rely on it for dependency management. If you want to develop an extension without dependencies, or want to do your own dependency management, just skip this step. Note that the example extension uses VCPKG to build with a dependency for instructive purposes, so when skipping this step the build may not work without removing the dependency. + +### Build steps +Now to build the extension, run: +```sh +make +``` +The main binaries that will be built are: +```sh +./build/release/duckdb +./build/release/test/unittest +./build/release/extension/quack/quack.duckdb_extension +``` +- `duckdb` is the binary for the duckdb shell with the extension code automatically loaded. +- `unittest` is the test runner of duckdb. Again, the extension is already linked into the binary. +- `quack.duckdb_extension` is the loadable binary as it would be distributed. + +## Running the extension +To run the extension code, simply start the shell with `./build/release/duckdb`. + +Now we can use the features from the extension directly in DuckDB. The template contains a single scalar function `quack()` that takes a string arguments and returns a string: +``` +D select quack('Jane') as result; +┌───────────────┐ +│ result │ +│ varchar │ +├───────────────┤ +│ Quack Jane 🐥 │ +└───────────────┘ +``` + +## Running the tests +Different tests can be created for DuckDB extensions. The primary way of testing DuckDB extensions should be the SQL tests in `./test/sql`. These SQL tests can be run using: +```sh +make test +``` + +### Installing the deployed binaries +To install your extension binaries from S3, you will need to do two things. Firstly, DuckDB should be launched with the +`allow_unsigned_extensions` option set to true. How to set this will depend on the client you're using. Some examples: + +CLI: +```shell +duckdb -unsigned +``` + +Python: +```python +con = duckdb.connect(':memory:', config={'allow_unsigned_extensions' : 'true'}) +``` + +NodeJS: +```js +db = new duckdb.Database(':memory:', {"allow_unsigned_extensions": "true"}); +``` + +Secondly, you will need to set the repository endpoint in DuckDB to the HTTP url of your bucket + version of the extension +you want to install. To do this run the following SQL query in DuckDB: +```sql +SET custom_extension_repository='bucket.s3.eu-west-1.amazonaws.com//latest'; +``` +Note that the `/latest` path will allow you to install the latest extension version available for your current version of +DuckDB. To specify a specific version, you can pass the version instead. + +After running these steps, you can install and load your extension using the regular INSTALL/LOAD commands in DuckDB: +```sql +INSTALL quack +LOAD quack +``` diff --git a/docs/README.md b/docs/README.md new file mode 100644 index 0000000..7825350 --- /dev/null +++ b/docs/README.md @@ -0,0 +1,137 @@ +# DuckDB Extension Template +This repository contains a template for creating a DuckDB extension. The main goal of this template is to allow users to easily develop, test and distribute their own DuckDB extension. The main branch of the template is always based on the latest stable DuckDB allowing you to try out your extension right away. + +## Getting started +First step to getting started is to create your own repo from this template by clicking `Use this template`. Then clone your new repository using +```sh +git clone --recurse-submodules https://github.com//.git +``` +Note that `--recurse-submodules` will ensure DuckDB is pulled which is required to build the extension. + +## Building +### Managing dependencies +DuckDB extensions uses VCPKG for dependency management. Enabling VCPKG is very simple: follow the [installation instructions](https://vcpkg.io/en/getting-started) or just run the following: +```shell +cd +git clone https://github.com/Microsoft/vcpkg.git +sh ./vcpkg/scripts/bootstrap.sh -disableMetrics +export VCPKG_TOOLCHAIN_PATH=`pwd`/vcpkg/scripts/buildsystems/vcpkg.cmake +``` +Note: VCPKG is only required for extensions that want to rely on it for dependency management. If you want to develop an extension without dependencies, or want to do your own dependency management, just skip this step. Note that the example extension uses VCPKG to build with a dependency for instructive purposes, so when skipping this step the build may not work without removing the dependency. + +### Build steps +Now to build the extension, run: +```sh +make +``` +The main binaries that will be built are: +```sh +./build/release/duckdb +./build/release/test/unittest +./build/release/extension//.duckdb_extension +``` +- `duckdb` is the binary for the duckdb shell with the extension code automatically loaded. +- `unittest` is the test runner of duckdb. Again, the extension is already linked into the binary. +- `.duckdb_extension` is the loadable binary as it would be distributed. + +## Running the extension +To run the extension code, simply start the shell with `./build/release/duckdb`. This shell will have the extension pre-loaded. + +Now we can use the features from the extension directly in DuckDB. The template contains a single scalar function `quack()` that takes a string arguments and returns a string: +``` +D select quack('Jane') as result; +┌───────────────┐ +│ result │ +│ varchar │ +├───────────────┤ +│ Quack Jane 🐥 │ +└───────────────┘ +``` + +## Running the tests +Different tests can be created for DuckDB extensions. The primary way of testing DuckDB extensions should be the SQL tests in `./test/sql`. These SQL tests can be run using: +```sh +make test +``` + +## Getting started with your own extension +After creating a repository from this template, the first step is to name your extension. To rename the extension, run: +``` +python3 ./scripts/bootstrap-template.py +``` +Feel free to delete the script after this step. + +Now you're good to go! After a (re)build, you should now be able to use your duckdb extension: +``` +./build/release/duckdb +D select ('Jane') as result; +┌─────────────────────────────────────┐ +│ result │ +│ varchar │ +├─────────────────────────────────────┤ +│ Jane 🐥 │ +└─────────────────────────────────────┘ +``` + +For inspiration/examples on how to extend DuckDB in a more meaningful way, check out the [test extensions](https://github.com/duckdb/duckdb/blob/main/test/extension), +the [in-tree extensions](https://github.com/duckdb/duckdb/tree/main/extension), and the [out-of-tree extensions](https://github.com/duckdblabs). + +## Distributing your extension +Easy distribution of extensions built with this template is facilitated using a similar process used by DuckDB itself. +Binaries are generated for various versions/platforms allowing duckdb to automatically install the correct binary. + +This step requires that you pass the following 4 parameters to your GitHub repo as action secrets: + +| secret name | description | +| ------------- | ----------------------------------- | +| S3_REGION | s3 region holding your bucket | +| S3_BUCKET | the name of the bucket to deploy to | +| S3_DEPLOY_ID | the S3 key id | +| S3_DEPLOY_KEY | the S3 key secret | + +After setting these variables, all pushes to main will trigger a new (dev) release. Note that your AWS token should +have full permissions to the bucket, and you will need to have ACLs enabled. + +### Installing the deployed binaries +To install your extension binaries from S3, you will need to do two things. Firstly, DuckDB should be launched with the +`allow_unsigned_extensions` option set to true. How to set this will depend on the client you're using. Some examples: + +CLI: +```shell +duckdb -unsigned +``` + +Secondly, you will need to set the repository endpoint in DuckDB to the HTTP url of your bucket + version of the extension +you want to install. To do this run the following SQL query in DuckDB: +```sql +SET custom_extension_repository='bucket.s3.eu-west-1.amazonaws.com//latest'; +``` +Note that the `/latest` path will allow you to install the latest extension version available for your current version of +DuckDB. To specify a specific version, you can pass the version instead. + +After running these steps, you can install and load your extension using the regular INSTALL/LOAD commands in DuckDB: +```sql +INSTALL +LOAD +``` + +### Versioning of your extension +Extension binaries will only work for the specific DuckDB version they were built for. The version of DuckDB that is targeted +is set to the latest stable release for the main branch of the template so initially that is all you need. As new releases +of DuckDB are published however, the extension repository will need to be updated. The template comes with a workflow set-up +that will automatically build the binaries for all DuckDB target architectures that are available in the corresponding DuckDB +version. This workflow is found in `.github/workflows/MainDistributionPipeline.yml`. It is up to the extension developer to keep +this up to date with DuckDB. Note also that its possible to distribute binaries for multiple DuckDB versions in this workflow +by simply duplicating the jobs. + +## Setting up CLion + +### Opening project +Configuring CLion with the extension template requires a little work. Firstly, make sure that the DuckDB submodule is available. +Then make sure to open `./duckdb/CMakeLists.txt` (so not the top level `CMakeLists.txt` file from this repo) as a project in CLion. +Now to fix your project path go to `tools->CMake->Change Project Root`([docs](https://www.jetbrains.com/help/clion/change-project-root-directory.html)) to set the project root to the root dir of this repo. + +### Debugging +To set up debugging in CLion, there are two simple steps required. Firstly, in `CLion -> Settings / Preferences -> Build, Execution, Deploy -> CMake` you will need to add the desired builds (e.g. Debug, Release, RelDebug, etc). There's different ways to configure this, but the easiest is to leave all empty, except the `build path`, which needs to be set to `../build/{build type}`. Now on a clean repository you will first need to run `make {build type}` to initialize the CMake build directory. After running make, you will be able to (re)build from CLion by using the build target we just created. If you use the CLion editor, you can create a CLion CMake profiles matching the CMake variables that are described in the makefile, and then you don't need to invoke the Makefile. + +The second step is to configure the unittest runner as a run/debug configuration. To do this, go to `Run -> Edit Configurations` and click `+ -> Cmake Application`. The target and executable should be `unittest`. This will run all the DuckDB tests. To specify only running the extension specific tests, add `--test-dir ../../.. [sql]` to the `Program Arguments`. Note that it is recommended to use the `unittest` executable for testing/development within CLion. The actual DuckDB CLI currently does not reliably work as a run target in CLion. diff --git a/docs/UPDATING.md b/docs/UPDATING.md new file mode 100644 index 0000000..a3ac73e --- /dev/null +++ b/docs/UPDATING.md @@ -0,0 +1,23 @@ +# Extension updating +When cloning this template, the target version of DuckDB should be the latest stable release of DuckDB. However, there +will inevitably come a time when a new DuckDB is released and the extension repository needs updating. This process goes +as follows: + +- Bump submodules + - `./duckdb` should be set to latest tagged release + - `./extension-ci-tools` should be set to updated branch corresponding to latest DuckDB release. So if you're building for DuckDB `v1.1.0` there will be a branch in `extension-ci-tools` named `v1.1.0` to which you should check out. +- Bump versions in `./github/workflows` + - `duckdb_version` input in `duckdb-stable-build` job in `MainDistributionPipeline.yml` should be set to latest tagged release + - `duckdb_version` input in `duckdb-stable-deploy` job in `MainDistributionPipeline.yml` should be set to latest tagged release + - the reusable workflow `duckdb/extension-ci-tools/.github/workflows/_extension_distribution.yml` for the `duckdb-stable-build` job should be set to latest tagged release + +# API changes +DuckDB extensions built with this extension template are built against the internal C++ API of DuckDB. This API is not guaranteed to be stable. +What this means for extension development is that when updating your extensions DuckDB target version using the above steps, you may run into the fact that your extension no longer builds properly. + +Currently, DuckDB does not (yet) provide a specific change log for these API changes, but it is generally not too hard to figure out what has changed. + +For figuring out how and why the C++ API changed, we recommend using the following resources: +- DuckDB's [Release Notes](https://github.com/duckdb/duckdb/releases) +- DuckDB's history of [Core extension patches](https://github.com/duckdb/duckdb/commits/main/.github/patches/extensions) +- The git history of the relevant C++ Header file of the API that has changed \ No newline at end of file diff --git a/duckdb b/duckdb new file mode 160000 index 0000000..1986445 --- /dev/null +++ b/duckdb @@ -0,0 +1 @@ +Subproject commit 19864453f7d0ed095256d848b46e7b8630989bac diff --git a/extension-ci-tools b/extension-ci-tools new file mode 160000 index 0000000..83f847f --- /dev/null +++ b/extension-ci-tools @@ -0,0 +1 @@ +Subproject commit 83f847f8467a760f6c66dc7996c13300210220a8 diff --git a/extension_config.cmake b/extension_config.cmake new file mode 100644 index 0000000..959e702 --- /dev/null +++ b/extension_config.cmake @@ -0,0 +1,10 @@ +# This file is included by DuckDB's build system. It specifies which extension to load + +# Extension from this repo +duckdb_extension_load(quack + SOURCE_DIR ${CMAKE_CURRENT_LIST_DIR} + LOAD_TESTS +) + +# Any extra extensions that should be built +# e.g.: duckdb_extension_load(json) \ No newline at end of file diff --git a/scripts/bootstrap-template.py b/scripts/bootstrap-template.py new file mode 100755 index 0000000..8f78fec --- /dev/null +++ b/scripts/bootstrap-template.py @@ -0,0 +1,94 @@ +#!/usr/bin/python3 + +import sys, os, shutil, re +from pathlib import Path + + +def is_snake_case(s): + # Define the regex pattern for snake case with numbers + pattern = r"^[a-z0-9]+(_[a-z0-9]+)*$" + + # Use re.match to check if the string matches the pattern + if re.match(pattern, s): + return True + else: + return False + + +def to_camel_case(snake_str): + return "".join(x.capitalize() for x in snake_str.lower().split("_")) + + +def replace(file_name, to_find, to_replace): + with open(file_name, "r", encoding="utf8") as file: + filedata = file.read() + filedata = filedata.replace(to_find, to_replace) + with open(file_name, "w", encoding="utf8") as file: + file.write(filedata) + + +def replace_everywhere(to_find, to_replace): + for path in files_to_search: + replace(path, to_find, to_replace) + replace(path, to_find.capitalize(), to_camel_case(to_replace)) + replace(path, to_find.upper(), to_replace.upper()) + + replace("./CMakeLists.txt", to_find, to_replace) + replace("./Makefile", to_find, to_replace) + replace("./Makefile", to_find.capitalize(), to_camel_case(to_replace)) + replace("./Makefile", to_find.upper(), to_replace.upper()) + replace("./README.md", to_find, to_replace) + replace("./extension_config.cmake", to_find, to_replace) + replace("./scripts/setup-custom-toolchain.sh", to_find, to_replace) + + +if __name__ == "__main__": + if len(sys.argv) != 2: + raise Exception( + "usage: python3 bootstrap-template.py " + ) + + name_extension = sys.argv[1] + + if name_extension[0].isdigit(): + raise Exception("Please dont start your extension name with a number.") + + if not is_snake_case(name_extension): + raise Exception( + "Please enter the name of your extension in valid snake_case containing only lower case letters and numbers" + ) + + shutil.copyfile("docs/NEXT_README.md", "README.md") + os.remove("docs/NEXT_README.md") + os.remove("docs/README.md") + + files_to_search = [] + files_to_search.extend(Path("./.github").rglob("./**/*.yml")) + files_to_search.extend(Path("./test").rglob("./**/*.test")) + files_to_search.extend(Path("./src").rglob("./**/*.hpp")) + files_to_search.extend(Path("./src").rglob("./**/*.cpp")) + files_to_search.extend(Path("./src").rglob("./**/*.txt")) + files_to_search.extend(Path("./src").rglob("./*.md")) + + replace_everywhere("quack", name_extension) + replace_everywhere("Quack", name_extension.capitalize()) + replace_everywhere("", name_extension) + + string_to_replace = name_extension + string_to_find = "quack" + + # rename files + os.rename(f"test/sql/{string_to_find}.test", f"test/sql/{string_to_replace}.test") + os.rename( + f"src/{string_to_find}_extension.cpp", f"src/{string_to_replace}_extension.cpp" + ) + os.rename( + f"src/include/{string_to_find}_extension.hpp", + f"src/include/{string_to_replace}_extension.hpp", + ) + + # remove template-specific files + os.remove(".github/workflows/ExtensionTemplate.yml") + + # finally, remove this bootstrap file + os.remove(__file__) diff --git a/scripts/extension-upload.sh b/scripts/extension-upload.sh new file mode 100755 index 0000000..9fd5b39 --- /dev/null +++ b/scripts/extension-upload.sh @@ -0,0 +1,90 @@ +#!/bin/bash + +# Extension upload script + +# Usage: ./extension-upload.sh +# : Name of the extension +# : Version (commit / version tag) of the extension +# : Version (commit / version tag) of DuckDB +# : Architecture target of the extension binary +# : S3 bucket to upload to +# : Set this as the latest version ("true" / "false", default: "false") +# : Set this as a versioned version that will prevent its deletion + +set -e + +if [[ $4 == wasm* ]]; then + ext="/tmp/extension/$1.duckdb_extension.wasm" +else + ext="/tmp/extension/$1.duckdb_extension" +fi + +echo $ext + +script_dir="$(dirname "$(readlink -f "$0")")" + +# calculate SHA256 hash of extension binary +cat $ext > $ext.append + +if [[ $4 == wasm* ]]; then + # 0 for custom section + # 113 in hex = 275 in decimal, total lenght of what follows (1 + 16 + 2 + 256) + # [1(continuation) + 0010011(payload) = \x93, 0(continuation) + 10(payload) = \x02] + echo -n -e '\x00' >> $ext.append + echo -n -e '\x93\x02' >> $ext.append + # 10 in hex = 16 in decimal, lenght of name, 1 byte + echo -n -e '\x10' >> $ext.append + echo -n -e 'duckdb_signature' >> $ext.append + # the name of the WebAssembly custom section, 16 bytes + # 100 in hex, 256 in decimal + # [1(continuation) + 0000000(payload) = ff, 0(continuation) + 10(payload)], + # for a grand total of 2 bytes + echo -n -e '\x80\x02' >> $ext.append +fi + +# (Optionally) Sign binary +if [ "$DUCKDB_EXTENSION_SIGNING_PK" != "" ]; then + echo "$DUCKDB_EXTENSION_SIGNING_PK" > private.pem + $script_dir/../duckdb/scripts/compute-extension-hash.sh $ext.append > $ext.hash + openssl pkeyutl -sign -in $ext.hash -inkey private.pem -pkeyopt digest:sha256 -out $ext.sign + rm -f private.pem +fi + +# Signature is always there, potentially defaulting to 256 zeros +truncate -s 256 $ext.sign + +# append signature to extension binary +cat $ext.sign >> $ext.append + +# compress extension binary +if [[ $4 == wasm_* ]]; then + brotli < $ext.append > "$ext.compressed" +else + gzip < $ext.append > "$ext.compressed" +fi + +set -e + +# Abort if AWS key is not set +if [ -z "$AWS_ACCESS_KEY_ID" ]; then + echo "No AWS key found, skipping.." + exit 0 +fi + +# upload versioned version +if [[ $7 = 'true' ]]; then + if [[ $4 == wasm* ]]; then + aws s3 cp $ext.compressed s3://$5/$1/$2/$3/$4/$1.duckdb_extension.wasm --acl public-read --content-encoding br --content-type="application/wasm" + else + aws s3 cp $ext.compressed s3://$5/$1/$2/$3/$4/$1.duckdb_extension.gz --acl public-read + fi +fi + +# upload to latest version +if [[ $6 = 'true' ]]; then + if [[ $4 == wasm* ]]; then + aws s3 cp $ext.compressed s3://$5/$3/$4/$1.duckdb_extension.wasm --acl public-read --content-encoding br --content-type="application/wasm" + else + aws s3 cp $ext.compressed s3://$5/$3/$4/$1.duckdb_extension.gz --acl public-read + fi +fi diff --git a/scripts/setup-custom-toolchain.sh b/scripts/setup-custom-toolchain.sh new file mode 100644 index 0000000..4a846fc --- /dev/null +++ b/scripts/setup-custom-toolchain.sh @@ -0,0 +1,11 @@ +#!/bin/bash + +# This is an example script that can be used to install additional toolchain dependencies. Feel free to remove this script +# if no additional toolchains are required + +# To enable this script, set the `custom_toolchain_script` option to true when calling the reusable workflow +# `.github/workflows/_extension_distribution.yml` from `https://github.com/duckdb/extension-ci-tools` + +# note that the $DUCKDB_PLATFORM environment variable can be used to discern between the platforms +echo "This is the sample custom toolchain script running for architecture '$DUCKDB_PLATFORM' for the quack extension." + diff --git a/src/include/quack_extension.hpp b/src/include/quack_extension.hpp new file mode 100644 index 0000000..494467b --- /dev/null +++ b/src/include/quack_extension.hpp @@ -0,0 +1,14 @@ +#pragma once + +#include "duckdb.hpp" + +namespace duckdb { + +class QuackExtension : public Extension { +public: + void Load(DuckDB &db) override; + std::string Name() override; + std::string Version() const override; +}; + +} // namespace duckdb diff --git a/src/quack_extension.cpp b/src/quack_extension.cpp new file mode 100644 index 0000000..468b2e2 --- /dev/null +++ b/src/quack_extension.cpp @@ -0,0 +1,78 @@ +#define DUCKDB_EXTENSION_MAIN + +#include "quack_extension.hpp" +#include "duckdb.hpp" +#include "duckdb/common/exception.hpp" +#include "duckdb/common/string_util.hpp" +#include "duckdb/function/scalar_function.hpp" +#include "duckdb/main/extension_util.hpp" +#include + +// OpenSSL linked through vcpkg +#include + +namespace duckdb { + +inline void QuackScalarFun(DataChunk &args, ExpressionState &state, Vector &result) { + auto &name_vector = args.data[0]; + UnaryExecutor::Execute( + name_vector, result, args.size(), + [&](string_t name) { + return StringVector::AddString(result, "Quack "+name.GetString()+" 🐥");; + }); +} + +inline void QuackOpenSSLVersionScalarFun(DataChunk &args, ExpressionState &state, Vector &result) { + auto &name_vector = args.data[0]; + UnaryExecutor::Execute( + name_vector, result, args.size(), + [&](string_t name) { + return StringVector::AddString(result, "Quack " + name.GetString() + + ", my linked OpenSSL version is " + + OPENSSL_VERSION_TEXT );; + }); +} + +static void LoadInternal(DatabaseInstance &instance) { + // Register a scalar function + auto quack_scalar_function = ScalarFunction("quack", {LogicalType::VARCHAR}, LogicalType::VARCHAR, QuackScalarFun); + ExtensionUtil::RegisterFunction(instance, quack_scalar_function); + + // Register another scalar function + auto quack_openssl_version_scalar_function = ScalarFunction("quack_openssl_version", {LogicalType::VARCHAR}, + LogicalType::VARCHAR, QuackOpenSSLVersionScalarFun); + ExtensionUtil::RegisterFunction(instance, quack_openssl_version_scalar_function); +} + +void QuackExtension::Load(DuckDB &db) { + LoadInternal(*db.instance); +} +std::string QuackExtension::Name() { + return "quack"; +} + +std::string QuackExtension::Version() const { +#ifdef EXT_VERSION_QUACK + return EXT_VERSION_QUACK; +#else + return ""; +#endif +} + +} // namespace duckdb + +extern "C" { + +DUCKDB_EXTENSION_API void quack_init(duckdb::DatabaseInstance &db) { + duckdb::DuckDB db_wrapper(db); + db_wrapper.LoadExtension(); +} + +DUCKDB_EXTENSION_API const char *quack_version() { + return duckdb::DuckDB::LibraryVersion(); +} +} + +#ifndef DUCKDB_EXTENSION_MAIN +#error DUCKDB_EXTENSION_MAIN not defined +#endif diff --git a/test/README.md b/test/README.md new file mode 100644 index 0000000..fb5e514 --- /dev/null +++ b/test/README.md @@ -0,0 +1,11 @@ +# Testing this extension +This directory contains all the tests for this extension. The `sql` directory holds tests that are written as [SQLLogicTests](https://duckdb.org/dev/sqllogictest/intro.html). DuckDB aims to have most its tests in this format as SQL statements, so for the quack extension, this should probably be the goal too. + +The root makefile contains targets to build and run all of these tests. To run the SQLLogicTests: +```bash +make test +``` +or +```bash +make test_debug +``` \ No newline at end of file diff --git a/test/sql/quack.test b/test/sql/quack.test new file mode 100644 index 0000000..519a354 --- /dev/null +++ b/test/sql/quack.test @@ -0,0 +1,23 @@ +# name: test/sql/quack.test +# description: test quack extension +# group: [quack] + +# Before we load the extension, this will fail +statement error +SELECT quack('Sam'); +---- +Catalog Error: Scalar Function with name quack does not exist! + +# Require statement will ensure this test is run with this extension loaded +require quack + +# Confirm the extension works +query I +SELECT quack('Sam'); +---- +Quack Sam 🐥 + +query I +SELECT quack_openssl_version('Michael') ILIKE 'Quack Michael, my linked OpenSSL version is OpenSSL%'; +---- +true diff --git a/vcpkg.json b/vcpkg.json new file mode 100644 index 0000000..85936bf --- /dev/null +++ b/vcpkg.json @@ -0,0 +1,5 @@ +{ + "dependencies": [ + "openssl" + ] +} \ No newline at end of file