Merge pull request #85 from godatadriven/84-make-it-easier-to-install…

…-and-use-whirl

84 make it easier to install and use whirl

.gitattributes

@@ -1,4 +1,15 @@
 *        text=auto
 *.sh     text eol=lf
 *.bat    text eol=crlf
-*.cmd    text eol=crlf
+*.cmd    text eol=crlf
+
+.gitattributes  export-ignore
+.gitignore      export-ignore
+.github         export-ignore
+.gitkeep        export-ignore
+.editorconfig   export-ignore
+logo            export-ignore
+
+#Non finished examples and their envs
+examples/dbt**  export-ignore
+envs/dbt**      export-ignore

.github/workflows/whirl-ci.yml

@@ -24,8 +24,20 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - id: setdirs # Give it an id to handle to get step outputs in the outputs key above
-        run: echo "::set-output name=dir::$(ls -d ./examples/* | jq -R -s -c 'split("\n")[:-1]')"
-        # Define step output named dir base on ls command transformed to JSON thanks to jq
+        # run: echo "::set-output name=dir::$(ls -d ./examples/* | jq -R -s -c 'split("\n")[:-1]')"
+        run: echo "dir=$(ls -d ./examples/* | jq -R -s -c 'split("\n")[:-1]')" >> $GITHUB_OUTPUT
+        # Define step output named dir based on ls command transformed to JSON thanks to jq
+
+  examples: # Job that list subdirectories of ./examples
+    runs-on: ubuntu-latest
+    outputs:
+      # generate output name example by using inner step output
+      example: ${{ steps.setexamples.outputs.example }}
+    steps:
+      - uses: actions/checkout@v2
+      - id: setexamples # Give it an id to handle to get step outputs in the outputs key above
+        run: echo "example=$(ls -d ./examples/* | sed -r 's/\.\/examples\/(.*)/\1/g' | jq -R -s -c 'split("\n")[:-1]')" >> $GITHUB_OUTPUT
+        # Define step output named example based on ls command transformed to JSON thanks to jq
 
   whirl-ci-default-envs:
     needs: [directories]
@@ -34,27 +46,54 @@ jobs:
       fail-fast: false
       max-parallel: 4
       matrix:
-        example: ${{ fromJson(needs.directories.outputs.dir) }}
+        example_dir: ${{ fromJson(needs.directories.outputs.dir) }}
         python_version: ["3.8", "3.9"]
-        airflow_version: ["2.2.5", "2.3.2"]
+        airflow_version: ["2.2.5", "2.5.0"]
         exclude:
           # Needs more memory than available on the runner
-          - example: ./examples/dbt-spark-example
-          - example: ./examples/spark-delta-sharing
-          - example: ./examples/spark-s3-to-hive
+          - example_dir: ./examples/dbt-spark-example
+          - example_dir: ./examples/spark-delta-sharing
+          - example_dir: ./examples/spark-s3-to-hive
           # Exclude failing dbt runs
-          - example: ./examples/dbt-example
+          - example_dir: ./examples/dbt-example
     env:
       PYTHON_VERSION: ${{ matrix.python_version }}
       AIRFLOW_VERSION: ${{ matrix.airflow_version }}
     steps:
       - uses: actions/checkout@v2
-      - name: Run whirl CI ${{ matrix.example }}
-        working-directory: ${{ matrix.example }}
+      - name: Run whirl CI ${{ matrix.example_dir }}
+        working-directory: ${{ matrix.example_dir }}
         run: |
-          echo Run Ci for example ${{ matrix.example }}
+          echo Run Ci from example directory ${{ matrix.example_dir }}
           ../../whirl ci
 
+  whirl-ci-default-envs-from-root-dir:
+    needs: [examples]
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      max-parallel: 4
+      matrix:
+        example: ${{ fromJson(needs.examples.outputs.example) }}
+        python_version: ["3.8", "3.9"]
+        airflow_version: ["2.2.5", "2.5.0"]
+        exclude:
+          # Needs more memory than available on the runner
+          - example: dbt-spark-example
+          - example: spark-delta-sharing
+          - example: spark-s3-to-hive
+          # Exclude failing dbt runs
+          - example: dbt-example
+    env:
+      PYTHON_VERSION: ${{ matrix.python_version }}
+      AIRFLOW_VERSION: ${{ matrix.airflow_version }}
+    steps:
+      - uses: actions/checkout@v2
+      - name: Run whirl CI example ${{ matrix.example }}
+        run: |
+          echo Run Ci for example ${{ matrix.example }}
+          ./whirl -x ${{ matrix.example }} ci
+
 
   whirl-ci-extra-env-spark-s3-to-postgres:
     runs-on: ubuntu-latest
@@ -72,7 +111,7 @@ jobs:
       max-parallel: 4
       matrix:
         python_version: ["3.8", "3.9"]
-        airflow_version: ["2.2.5", "2.3.2"]
+        airflow_version: ["2.2.5", "2.5.0"]
     runs-on: ubuntu-latest
     env:
       PYTHON_VERSION: ${{ matrix.python_version }}
@@ -91,7 +130,7 @@ jobs:
       max-parallel: 4
       matrix:
         python_version: ["3.8", "3.9"]
-        airflow_version: ["2.2.5", "2.3.2"]
+        airflow_version: ["2.2.5", "2.5.0"]
     runs-on: ubuntu-latest
     env:
       PYTHON_VERSION: ${{ matrix.python_version }}

.github/workflows/whirl-release.yml

@@ -0,0 +1,21 @@
+name: Publish minimal release archive
+on:
+  release:
+    types: [published]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write  # for upload release asset
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Run git-archive command to create a release artifact
+        run: git archive --format=tar.gz --prefix=whirl/ --output=whirl-release.tar.gz HEAD
+
+      - name: upload Whirl release artifact
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: |
+          gh release upload ${{ github.event.release.tag_name }} whirl-release.tar.gz --clobber

README.md

@@ -15,7 +15,7 @@ NOTE: _whirl_ is not intended to replace proper (unit) testing of the logic you
 
 _whirl_ relies on [Docker](https://www.docker.com/) and [Docker Compose](https://docs.docker.com/compose/). Make sure you have it installed. If using _Docker for Mac_ or _Windows_ ensure that you have configured it with sufficient RAM (8GB or more recommended) for running all your containers.
 
-When you want to use _whirl_ in your CI pipeline (currently work in progress), you need to have `jq` installed. For example, with Homebrew:
+When you want to use _whirl_ in your CI pipeline, you need to have `jq` installed. For example, with Homebrew:
 
 ```bash
 brew install jq
@@ -28,6 +28,8 @@ As of January 2021, Whirl uses Airflow 2.x.x as the default version. A specific
 
 ## Getting Started
 
+### Development
+
 Clone this repository:
 
 ```
@@ -38,6 +40,21 @@ For ease of use you can add the base directory to your `PATH` environment variab
 export PATH=<target directory of whirl>:${PATH}
 ```
 
+### Use the release
+
+Download the [latest Whirl release artifact](https://github.com/godatadriven/whirl/releases/download/latest/whirl-release.tar.gz)
+
+Extract the file (for example into `/usr/local/opt`)
+
+```bash
+tar -xvzf whirl-release.tar.gz -C /usr/local/opt
+```
+
+Make sure the whirl script is available on your path
+```bash
+export PATH=/usr/local/opt/whirl:$PATH
+```
+
 ## Usage
 
 The `whirl` script is used to perform all actions.
@@ -51,18 +68,22 @@ $ whirl --help
 
 #### Starting whirl
 
-The default action is to start the DAG in your current directory. It expects an environment to be configured. You can pass this as a command line argument or you can configure it in a `.whirl.env` file. (See [Configuring environment variables](#configuring-environment-variables).) The environment refers to a directory with the same name in the `envs` directory located near the _whirl_ script.
+The default action is to start the DAG in your current directory.
+
+With the `[-x example]` commandline argument you can run whirl from anywhere and tell whirl which example dag to run. The example refers to a directory with the same name in the `examples` directory located near the _whirl_ script.
+
+Whirl expects an environment to be configured. You can pass this as a command line argument `[-e environment]` or you can configure it as environment variable `WHIRL_ENVIRONMENT` in a `.whirl.env` file. (See [Configuring environment variables](#configuring-environment-variables).) The environment refers to a directory with the same name in the `envs` directory located near the _whirl_ script.
 
 ```bash
-$ whirl [start] [-d <directory>] [-e <environment>]
+$ whirl [-x example] [-e <environment>] [start]
 ```
 
 Specifying the `start` command line argument is a more explicit way to start _whirl_.
 
 #### Stopping whirl
 
 ```bash
-$ whirl stop [-d <directory>] [-e <environment>]
+$ whirl  [-x example] [-e <environment>] stop
 ```
 Stops the configured environment.
 
@@ -134,8 +155,6 @@ Each example contains it's own README file to explain the specifics of that exam
 
 #### Generic running of examples
 
-From within the example directory the `whirl` command can be executed. 
-
 To run a example:
 
 ```bash
@@ -144,6 +163,13 @@ $ cd ./examples/<example-dag-directory>
 $ whirl -e <environment to use>
 ```
 
+or
+```bash
+$
+# Note: here we pass the whirl environment as a command-line argument. It can also be configured with the WHIRL_ENVIRONMENT variable
+$ whirl -x <example to run> -e <environment to use>
+```
+
 Open your browser to [http://localhost:5000](http://localhost:5000) to access the Airflow UI. Manually enable the DAG and watch the pipeline run to successful completion.
 
 

envs/dbt-example/.whirl.env

@@ -22,3 +22,5 @@ AIRFLOW__CORE__EXPOSE_CONFIG=True
 AIRFLOW__WEBSERVER__EXPOSE_CONFIG=True
 AIRFLOW__CORE__LOAD_DEFAULT_CONNECTIONS=False
 AIRFLOW__CORE__LOAD_EXAMPLES=False
+
+MINIMAL_AIRFLOW_VERSION=2.3.0

envs/postgres-s3-external-spark/.whirl.env

@@ -20,3 +20,5 @@ AIRFLOW__CORE__EXPOSE_CONFIG=True
 AIRFLOW__WEBSERVER__EXPOSE_CONFIG=True
 AIRFLOW__CORE__LOAD_DEFAULT_CONNECTIONS=False
 AIRFLOW__CORE__LOAD_EXAMPLES=False
+
+MINIMAL_AIRFLOW_VERSION=2.3.0

envs/postgres-s3-spark/.whirl.env

@@ -20,3 +20,5 @@ AIRFLOW__CORE__EXPOSE_CONFIG=True
 AIRFLOW__WEBSERVER__EXPOSE_CONFIG=True
 AIRFLOW__CORE__LOAD_DEFAULT_CONNECTIONS=False
 AIRFLOW__CORE__LOAD_EXAMPLES=False
+
+MINIMAL_AIRFLOW_VERSION=2.3.0

envs/s3-external-spark-hive/.whirl.env

@@ -15,3 +15,5 @@ AIRFLOW__CORE__EXPOSE_CONFIG=True
 AIRFLOW__WEBSERVER__EXPOSE_CONFIG=True
 AIRFLOW__CORE__LOAD_DEFAULT_CONNECTIONS=False
 AIRFLOW__CORE__LOAD_EXAMPLES=False
+
+MINIMAL_AIRFLOW_VERSION=2.3.0

envs/s3-spark-delta-sharing-minio/.whirl.env

@@ -14,3 +14,5 @@ AIRFLOW__CORE__EXPOSE_CONFIG=True
 AIRFLOW__CORE__LOAD_DEFAULT_CONNECTIONS=False
 AIRFLOW__CORE__LOAD_EXAMPLES=False
 AIRFLOW__WEBSERVER__EXPOSE_CONFIG=True
+
+MINIMAL_AIRFLOW_VERSION=2.3.0

envs/s3-spark-delta-sharing-riverbank/.whirl.env

@@ -21,3 +21,5 @@ AIRFLOW__CORE__EXPOSE_CONFIG=True
 AIRFLOW__CORE__LOAD_DEFAULT_CONNECTIONS=False
 AIRFLOW__CORE__LOAD_EXAMPLES=False
 AIRFLOW__WEBSERVER__EXPOSE_CONFIG=True
+
+MINIMAL_AIRFLOW_VERSION=2.3.0

envs/s3-spark-delta-sharing/.whirl.env

@@ -14,3 +14,5 @@ AIRFLOW__CORE__EXPOSE_CONFIG=True
 AIRFLOW__CORE__LOAD_DEFAULT_CONNECTIONS=False
 AIRFLOW__CORE__LOAD_EXAMPLES=False
 AIRFLOW__WEBSERVER__EXPOSE_CONFIG=True
+
+MINIMAL_AIRFLOW_VERSION=2.3.0

envs/sftp-mysql-example/.whirl.env

@@ -1,4 +1,4 @@
-MOCK_DATA_FOLDER=$(pwd)/mock-data
+MOCK_DATA_FOLDER=${DAG_FOLDER}/mock-data
 
 
 # Airflow variables

examples/dbt-example/.whirl.env

@@ -1,2 +1,2 @@
 WHIRL_ENVIRONMENT=dbt-example
-MOCK_DATA_FOLDER=$(pwd)/mock-data
+MOCK_DATA_FOLDER=${DAG_FOLDER}/mock-data

examples/dbt-spark-example/.whirl.env

@@ -1,2 +1,2 @@
 WHIRL_ENVIRONMENT=s3-external-spark-hive
-MOCK_DATA_FOLDER=$(pwd)/mock-data
+MOCK_DATA_FOLDER=${DAG_FOLDER}/mock-data

examples/spark-delta-sharing/.whirl.env

@@ -1,3 +1,3 @@
 WHIRL_ENVIRONMENT=s3-spark-delta-sharing
-MOCK_DATA_FOLDER=$(pwd)/mock-data
+MOCK_DATA_FOLDER=${DAG_FOLDER}/mock-data
 

examples/spark-s3-to-hive/.whirl.env

@@ -1,3 +1,2 @@
 WHIRL_ENVIRONMENT=s3-external-spark-hive
-MOCK_DATA_FOLDER=$(pwd)/mock-data
-
+MOCK_DATA_FOLDER=${DAG_FOLDER}/mock-data

examples/spark-s3-to-postgres/.whirl.env

@@ -1,2 +1,3 @@
 WHIRL_ENVIRONMENT=postgres-s3-external-spark
-MOCK_DATA_FOLDER=$(pwd)/mock-data
+MOCK_DATA_FOLDER=${DAG_FOLDER}/mock-data
+MINIMAL_AIRFLOW_VERSION=2.3.0

whirl

@@ -21,10 +21,6 @@ function export_environment_vars() {
   # shellcheck disable=SC2034
   DOCKER_CONTEXT_FOLDER=${SCRIPT_DIR}/docker
   # shellcheck disable=SC2034
-  DAG_FOLDER=$(pwd)
-  # shellcheck disable=SC2034
-  PROJECTNAME=$(basename "${DAG_FOLDER}")
-  # shellcheck disable=SC2034
   WHIRL_INITIATOR=$(whoami)
   # shellcheck disable=SC2034
   WHIRL_SETUP_FOLDER=/etc/airflow/whirl.setup.d
@@ -41,6 +37,17 @@ function export_environment_vars() {
     . "${SCRIPT_DIR}/.whirl.env"
   fi
 
+  # determine whether to use the example set at the commandline or
+  # in the current folder
+  if [ -z "${WHIRL_EXAMPLE_ARG}" ]; then
+    # shellcheck disable=SC2034
+    DAG_FOLDER=$(pwd)
+  else
+    DAG_FOLDER=${SCRIPT_DIR}/examples/${WHIRL_EXAMPLE_ARG}
+  fi
+  # shellcheck disable=SC2034
+  PROJECTNAME=$(basename "${DAG_FOLDER}")
+
   # determine whether to use the environment set at the commandline or
   # in the DAG FOLDER .whirl.env
   if [ -z "${WHIRL_ENVIRONMENT_ARG}" ]; then
@@ -113,7 +120,7 @@ function export_environment_vars() {
 }
 
 detect_potential_dag() {
-  test "$(find . -type f -name '*.py' -o -name '*.zip' | wc -l)" -gt 0
+  test "$(find "${DAG_FOLDER}" -type f -name '*.py' -maxdepth 1 -o -name '*.zip' | wc -l)" -gt 0
 }
 
 check_next_dagrun_scheduled_today() {
@@ -340,6 +347,7 @@ logs() {
 usage() {
   echo "usage: ${BASH_SOURCE[0]} [-h|--help] [-e|--environment env] [start|stop|ci]"
   echo "  -h|--help                          display usage"
+  echo "  -x|--example example               specify example to run"
   echo "  -e|--environment environment       specify environment to use"
   echo "  -d|--directory environment_folder  specify the folder that contains the environments (defaults to SCRIPT_DIR)"
   echo "  -l|--logs servicename              tail the logs of the service"
@@ -354,6 +362,11 @@ function read_arguments() {
   do
       key="${1}"
       case ${key} in
+      -x|--example)
+          WHIRL_EXAMPLE_ARG="${2}"
+          shift # past argument
+          shift # past value
+          ;;
       -e|--environment)
           WHIRL_ENVIRONMENT_ARG="${2}"
           shift # past argument
@@ -401,8 +414,8 @@ function read_arguments() {
 function main() {
   read_arguments "$@"
 
+  export_environment_vars
   if detect_potential_dag; then
-    export_environment_vars
 
     if [ -z "${LOGS}" ]; then
       if [ -z "${STOP}" ]; then
@@ -414,7 +427,8 @@ function main() {
       logs
     fi
   else
-    echo "No .py or .zip files found that may contain an Apache Airflow DAG"
+    echo "No .py or .zip files found in ${DAG_FOLDER} that may contain an Apache Airflow DAG"
+    echo "did you correctly specify the example directory?"
   fi
 }