Initial commit

.github/workflows/build_and_tests.yml

@@ -0,0 +1,31 @@
+name: Build and test
+
+on:
+  push:
+    branches:
+      - master
+
+jobs:
+  build-and-test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+    env:
+      RUST_BACKTRACE: 1
+    steps:
+      - name: Checkout pg_stats_exporter repository
+        uses: actions/checkout@v3
+        # In order to fetch changed files
+        with:
+          fetch-depth: 0
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: stable
+          components: rustfmt, clippy
+      - name: Checkout DuckDB source code
+        run: make duckdb
+      - name: Build extension
+        run: make
+      - name: Run tests
+        run: make test

.gitignore

@@ -0,0 +1,7 @@
+duckdb
+build
+cmake-build-debug
+.idea
+.DS_Store
+.clang-format
+.vscode

CMakeLists.txt

@@ -0,0 +1,36 @@
+cmake_minimum_required(VERSION 2.8.12)
+set(TARGET_NAME csv_scanner)
+project(${TARGET_NAME})
+
+set(OVERRIDE_GIT_DESCRIBE "v1.1.1")
+
+if(NOT MSVC)
+  set(CSV_SCANNER_EXTRA_CFLAGS
+      "-Wno-pedantic -Wno-sign-compare -Wno-unused-variable")
+endif()
+
+set(CMAKE_CXX_FLAGS_DEBUG
+    "${CMAKE_CXX_FLAGS_DEBUG} ${CSV_SCANNER_EXTRA_CFLAGS}")
+set(CMAKE_CXX_FLAGS_RELEASE
+    "${CMAKE_CXX_FLAGS_RELEASE} ${CSV_SCANNER_EXTRA_CFLAGS}")
+set(CMAKE_CXX_FLAGS_RELWITHDEBINFO
+    "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} ${CSV_SCANNER_EXTRA_CFLAGS}")
+
+set(CMAKE_C_FLAGS_DEBUG
+    "${CMAKE_C_FLAGS_DEBUG} ${CSV_SCANNER_EXTRA_CFLAGS} ${CSV_SCANNER_EXTRA_CFLAGS}"
+)
+set(CMAKE_C_FLAGS_RELEASE
+    "${CMAKE_C_FLAGS_RELEASE} ${CSV_SCANNER_EXTRA_CFLAGS}")
+set(CMAKE_C_FLAGS_RELWITHDEBINFO
+    "${CMAKE_C_FLAGS_RELWITHDEBINFO} ${CSV_SCANNER_EXTRA_CFLAGS}")
+
+add_subdirectory(src)
+
+
+set(PARAMETERS "-no-warnings")
+build_loadable_extension(${TARGET_NAME} ${PARAMETERS} ${ALL_OBJECT_FILES})
+
+if(WIN32)
+  target_include_directories(
+    ${TARGET_NAME}_loadable_extension)
+endif()

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.

Makefile

@@ -0,0 +1,80 @@
+.PHONY: all clean format debug release pull
+
+all: release
+
+DUCKDB_VERSION = "1.1.3"
+
+MKFILE_PATH := $(abspath $(lastword $(MAKEFILE_LIST)))
+PROJ_DIR := $(dir $(MKFILE_PATH))
+
+ifeq ($(OS),Windows_NT)
+	TEST_PATH="/test/Release/unittest.exe"
+else
+	TEST_PATH="/test/unittest"
+endif
+
+#### OSX config
+OSX_BUILD_FLAG=
+ifneq (${OSX_BUILD_ARCH}, "")
+	OSX_BUILD_FLAG=-DOSX_BUILD_ARCH=${OSX_BUILD_ARCH}
+endif
+
+#### VCPKG config
+VCPKG_TOOLCHAIN_PATH?=
+ifneq ("${VCPKG_TOOLCHAIN_PATH}", "")
+	TOOLCHAIN_FLAGS:=${TOOLCHAIN_FLAGS} -DVCPKG_MANIFEST_DIR='${PROJ_DIR}' -DVCPKG_BUILD=1 -DCMAKE_TOOLCHAIN_FILE='${VCPKG_TOOLCHAIN_PATH}'
+endif
+ifneq ("${VCPKG_TARGET_TRIPLET}", "")
+	TOOLCHAIN_FLAGS:=${TOOLCHAIN_FLAGS} -DVCPKG_TARGET_TRIPLET='${VCPKG_TARGET_TRIPLET}'
+endif
+
+#### Enable Ninja as generator
+ifeq ($(GEN),ninja)
+	GENERATOR=-G "Ninja" -DFORCE_COLORED_OUTPUT=1
+endif
+
+#### Configuration for this extension
+EXTENSION_NAME=CSV_SCANNER
+EXTENSION_FLAGS=\
+-DDUCKDB_EXTENSION_NAMES="csv_scanner" \
+-DDUCKDB_EXTENSION_${EXTENSION_NAME}_PATH="$(PROJ_DIR)" \
+-DDUCKDB_EXTENSION_${EXTENSION_NAME}_SHOULD_LINK=0 \
+-DDUCKDB_EXTENSION_${EXTENSION_NAME}_LOAD_TESTS=1 \
+-DDUCKDB_EXTENSION_${EXTENSION_NAME}_TEST_PATH="$(PROJ_DIR)test/sql"
+
+BUILD_FLAGS=-DEXTENSION_STATIC_BUILD=1 $(EXTENSION_FLAGS) $(OSX_BUILD_FLAG) $(TOOLCHAIN_FLAGS) -DDUCKDB_EXPLICIT_PLATFORM='${DUCKDB_PLATFORM}'
+
+duckdb:
+	./duckconfigure $(DUCKDB_VERSION)
+
+clean:
+	rm -rf build
+	[ -d "duckdb" ] && (cd duckdb && make clean)
+
+# Main build
+debug: duckdb
+	mkdir -p  build/debug && \
+	cmake $(GENERATOR) $(BUILD_FLAGS) -DCMAKE_BUILD_TYPE=Debug -S ./duckdb/ -B build/debug && \
+	cmake --build build/debug --config Debug
+
+reldebug: duckdb
+	mkdir -p build/reldebug && \
+	cmake $(GENERATOR) $(BUILD_FLAGS) -DCMAKE_BUILD_TYPE=RelWithDebInfo -S ./duckdb/ -B build/reldebug && \
+	cmake --build build/reldebug --config RelWithDebInfo
+
+release: duckdb
+	mkdir -p build/release && \
+	cmake $(GENERATOR) $(BUILD_FLAGS) -DCMAKE_BUILD_TYPE=Release -S ./duckdb/ -B build/release && \
+	cmake --build build/release --config Release
+
+test: test_release
+test_release: release
+	./build/release/$(TEST_PATH) --test-dir "$(PROJ_DIR)" "test/*"
+test_debug: debug
+	./build/debug/$(TEST_PATH) --test-dir "$(PROJ_DIR)" "test/*"
+
+format:
+	cp duckdb/.clang-format .
+	find src/ -iname "*.hpp" -o -iname "*.cpp" | xargs clang-format --sort-includes=0 -style=file -i
+	cmake-format -i CMakeLists.txt
+	rm .clang-format

README.md

@@ -0,0 +1,82 @@
+[![Build and test](https://github.com/maropu/duckdb_scanner_example/actions/workflows/build_and_tets.yml/badge.svg)](https://github.com/maropu/duckdb_scanner_example/actions/workflows/build_and_tets.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+This repository aims not to implenet a full-fledge CSV parser for DuckDB but to demonstrate a minimum table
+function example for letting you know how to implement a custom scanner for your datasource.
+
+# Minimum Required Components
+
+```bash
+.
+|-- CMakeLists.txt                  // Root CMake build file
+|-- Makefile                        // Build script to wrap cmake
+|-- data                            // Test data used in `test/sql/csv_scanner.test`
+|   |-- random.csv
+|   `-- test.csv
+|-- duckdb                          // DuckDB source code that this extension depends on
+|-- src
+|   |-- CMakeLists.txt              // CMake build file to list source files
+|   |-- csv_scanner_extension.cpp   // CSV parser implmenetation
+|   |-- include
+|   |   `-- csv_scanner.hpp         // Header file for the CSV parser
+|   `-- scan_csv.cpp                // Entrypoint where DuckDB loads this extension
+`-- test
+    `-- sql
+        `-- csv_scanner.test        // Test code
+```
+
+# Specification of this toy CSV parser
+
+ - Multi-threading for scanning CSV data supported
+ - VARCHAR, BIGINT, and DOUBLE types only supported
+ - Schema inference not supported
+
+# Running this example
+
+```bash
+$ make
+mkdir -p build/release && \
+	cmake  -DEXTENSION_STATIC_BUILD=1 -DDUCKDB_EXTENSION_NAMES="csv_scanner" -DDUCKDB_EXTENSION_CSV_SCANNER_PATH="./duckdb/duckdb_scanner_example/" -DDUCKDB_EXTENSION_CSV_SCANNER_SHOULD_LINK=0 -DDUCKDB_EXTENSION_CSV_SCANNER_LOAD_TESTS=1 -DDUCKDB_EXTENSION_CSV_SCANNER_TEST_PATH="./duckdb/duckdb_scanner_example/test/sql" -DOSX_BUILD_ARCH=  -DDUCKDB_EXPLICIT_PLATFORM='' -DCMAKE_BUILD_TYPE=Release -S ./duckdb/ -B build/release && \
+	cmake --build build/release --config Release
+-- git hash af39bd0dcf, version v1.1.3, extension folder v1.1.3
+-- Extensions will be deployed to: ./duckdb/duckdb_scanner_example/build/release/repository
+-- Load extension 'csv_scanner' from './duckdb/duckdb_scanner_example/'
+-- Load extension 'parquet' from './duckdb/duckdb_scanner_example/duckdb/extensions' @ v1.1.3
+-- Extensions linked into DuckDB: [parquet]
+-- Extensions built but not linked: [csv_scanner]
+-- Tests loaded for extensions: [csv_scanner]
+-- Configuring done
+-- Generating done
+-- Build files have been written to: ./duckdb/duckdb_scanner_example/build/release
+[  1%] Built target duckdb_platform_binary
+[  1%] Built target duckdb_platform
+...
+[100%] Linking CXX executable unittest
+[100%] Built target unittest
+[100%] Built target imdb
+
+$ make test
+...
+[1/1] (100%): test/sql/csv_scanner.test
+===============================================================================
+All tests passed (13 assertions in 1 test case)
+
+$ duckdb -unsigned
+v1.1.3 af39bd0dcf
+Enter ".help" for usage hints.
+D LOAD './build/release/extension/csv_scanner/csv_scanner.duckdb_extension';
+D SELECT * FROM scan_csv_ex('data/test.csv', {'a': 'varchar', 'b': 'bigint', 'c': 'double'});
+┌─────────┬───────┬────────┐
+│    a    │   b   │   c    │
+│ varchar │ int64 │ double │
+├─────────┼───────┼────────┤
+│ aaa     │     1 │   1.23 │
+│ bbb     │     2 │   3.14 │
+│ ccc     │     3 │   2.56 │
+└─────────┴───────┴────────┘
+```
+
+## Any Question
+
+If you have any question, please feel free to leave it on [Issues](https://github.com/maropu/duckdb_scanner_example/issues)
+or Twitter ([@maropu](http://twitter.com/#!/maropu)).