Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Deploy Databricks jobs from source folder #23

Closed
wants to merge 3 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
13 changes: 13 additions & 0 deletions README.md
Expand Up @@ -179,6 +179,19 @@ specify for this compilation. It will override the value if set on `build.sbt`.
> [new issue](https://github.com/microsoft/azdo-databricks/issues)
> on GitHub if you experience any problem.

### Deploy Databricks Jobs

#### Parameters

- **Jobs Folder Path**: a folder that contains the jobs to be deployed. For example:
- `$(System.DefaultWorkingDirectory)/<artifact name>/jobs`
- **Delete Missing Jobs (optional)**: This task will remove jobs that do not exist in the folder from the workspace when this is true.

#### Supported Agents

- Hosted Ubuntu 1604
- Hosted VS2017

## Release Notes

Please check the [Release Notes](https://github.com/microsoft/azdo-databricks/blob/master/docs/RELEASENOTES.md)
Expand Down
2 changes: 2 additions & 0 deletions tasks/DeployJobsTask/DeployJobsV1/.gitignore
@@ -0,0 +1,2 @@
node_modules
*.js
Binary file added tasks/DeployJobsTask/DeployJobsV1/icon.png
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
150 changes: 150 additions & 0 deletions tasks/DeployJobsTask/DeployJobsV1/index.ts
@@ -0,0 +1,150 @@
import tl = require('azure-pipelines-task-lib/task');
import path = require('path');
import fs = require('fs');
import { async } from 'q';
import { fstat } from 'fs';

async function run() {
try {
const jobsFolderPath: string = tl.getPathInput('jobsFolderPath', true);
var deleteMissingJobs: boolean = tl.getBoolInput('deleteMissingJobs', false);
if (!deleteMissingJobs) { deleteMissingJobs = false }

if (!isDirSync(jobsFolderPath)) {
tl.setResult(tl.TaskResult.Failed, 'The specified path for jobs folder is a file.')
}

var existingJobsArray = GetExistingJobs();
var deployableJobsArray = GetDeployableJobs(jobsFolderPath);
CreateMissingJobsInDatabricks(existingJobsArray, deployableJobsArray);
if (deleteMissingJobs) {
DeleteMissingJobs(existingJobsArray, deployableJobsArray);
}
}
catch (err) {
tl.setResult(tl.TaskResult.Failed, err.message);
}
}

class DeployableJob {
constructor(private path: string, public name: string) { }
public deploy() {
tl.execSync('databricks', 'jobs create --json-file ' + this.path + ' --profile AZDO');
}
public reset(existingJobId: number) {
tl.execSync('databricks', 'jobs reset --json-file ' + this.path + ' --job-id ' + existingJobId + ' --profile AZDO');
}
}

class ExistingJob {
constructor(public id: number, public name: string) { }
public remove() {
tl.execSync('databricks', 'jobs delete --job-id ' + this.id + ' --profile AZDO');
}
}

function DeleteMissingJobs(existingJobsArray: Array<ExistingJob>, deployableJobsArray: Array<DeployableJob>) {
var deployableJobNamesArray = deployableJobsArray.map(function (d) { return d.name; });
for (var i in existingJobsArray) {
if (deployableJobNamesArray.indexOf(existingJobsArray[i].name) === -1) {
existingJobsArray[i].remove();
}
}
}

function CreateMissingJobsInDatabricks(existingJobsArray: Array<ExistingJob>, deployableJobsArray: Array<DeployableJob>) {
var existingJobNamesArray = existingJobsArray.map(function (e) { return e.name });
deployableJobsArray.forEach((deployableJob, index) => {
var existingJob = existingJobsArray.find((existingJob) => existingJob.name === deployableJob.name);
if (!existingJob) {
deployableJob.deploy();
} else {
deployableJob.reset(existingJob.id);
}
});
}

function GetExistingJobs(): Array<ExistingJob> {
var result: Array<ExistingJob> = [];
var listResult = tl.execSync('databricks', 'jobs list --output JSON --profile AZDO');
if (listResult.code != 0) {
tl.setResult(tl.TaskResult.Failed, "Databricks Job list failed with " + listResult.stderr);
} else {
var jobsObject = JSON.parse(listResult.stdout);
jobsObject.jobs.forEach((job) => {
result.push(new ExistingJob(job.job_id, job.settings.name));
});
}
return result;
}

function GetDeployableJobs(jobsFolderPath: string): Array<DeployableJob> {
var jobFiles = GetJobFiles(jobsFolderPath);
var result = [];
for (var i in jobFiles) {
let jobContent = fs.readFileSync(jobFiles[i], {
encoding: 'utf8'
}).toString();
let jobObject = JSON.parse(jobContent);
result.push(new DeployableJob(jobFiles[i], jobObject.name));
}
return result;
}

function GetJobFiles(jobsFolderPath: string): Array<string> {
var jobsFileNameArray = fs.readdirSync(jobsFolderPath);
var result = [];
for (var jobFileNameIndex in jobsFileNameArray) {
result.push(path.join(jobsFolderPath, jobsFileNameArray[jobFileNameIndex]));
}
return result;
}

function isDirSync(aPath: string) {
try {
return fs.statSync(aPath).isDirectory();
} catch (e) {
if (e.code === 'ENOENT') {
return false;
} else {
throw e;
}
}
}

function isPython3Selected(): boolean {
let pythonInfo = tl.execSync("python", "-V");

if (pythonInfo.code != 0) {
tl.setResult(tl.TaskResult.Failed, `Failed to check python version. ${pythonInfo.stderr}`.trim())
}

let version: string = "";

if (pythonInfo.stderr != "") {
version = pythonInfo.stderr.split(' ')[1];
} else if (pythonInfo.stdout != "") {
version = pythonInfo.stdout.split(' ')[1];
} else {
tl.setResult(tl.TaskResult.Failed, `Failed to retrieve Python Version: ${pythonInfo.stderr}`);
return false;
}

if (!version.startsWith('3')) {
tl.setResult(tl.TaskResult.Failed, `Active Python Version: ${version}`);
return false;
}

console.log(`Version: ${version}`);

return true;
}

let python3Selected = isPython3Selected();

if (python3Selected) {
console.log("Python3 selected. Running...");
run();
} else {
tl.setResult(tl.TaskResult.Failed, "You must add 'Use Python Version 3.x' as the very first task for this pipeline.");
}
30 changes: 30 additions & 0 deletions tasks/DeployJobsTask/DeployJobsV1/package.json
@@ -0,0 +1,30 @@
{
"name": "deployjobs",
"version": "0.1.0",
"description": "A Pipeline task for deploying jobs from a given folder to a Databricks workspace. Jobs should be saved in the folder as JSON files",
"main": "index.js",
"scripts": {
"build": "tsc",
"test": "npm run build && mocha tests/_suite.js"
},
"repository": {
"type": "git",
"url": "git+https://github.com/microsoft/azdo-databricks.git"
},
"keywords": [
"azdo",
"devops",
"databricks",
"data"
],
"author": "Microsoft DevLabs",
"license": "MIT",
"dependencies": {
"azure-pipelines-task-lib": "^2.8.0"
},
"devDependencies": {
"@types/mocha": "^5.2.7",
"@types/node": "^12.0.8",
"@types/q": "^1.5.2"
}
}
38 changes: 38 additions & 0 deletions tasks/DeployJobsTask/DeployJobsV1/task.json
@@ -0,0 +1,38 @@
{
"id": "95290384-0fd3-4bcf-98e4-5586d81588de",
"name": "deployjobs",
"friendlyName": "Deploy Databricks Jobs",
"description": "Recursively deploys Jobs saved as json files from a given folder to a Databricks workspace. Each job that does not exist in the Databricks workspace will be created. If the job exists it will be reset.",
"helpMarkDown": "",
"category": "Deploy",
"author": "Microsoft DevLabs",
"version": {
"Major": 0,
"Minor": 1,
"Patch": 0
},
"instanceNameFormat": "Deploy jobs to Workspace",
"inputs": [
{
"name": "jobsFolderPath",
"type": "filePath",
"label": "jobs folder",
"defaultValue": "",
"required": true,
"helpMarkDown": "Specify the path to the folder that contains the jobs to be published to the workspace."
},
{
"name": "deleteMissingJobs",
"type": "boolean",
"label": "Delete Jobs from Databricks",
"defaultValue": "false",
"required": false,
"helpMarkDown": "If this is true, this task will remove all jobs from Databricks that are not specified in JSON files. Jobs are matched by name."
}
],
"execution": {
"Node": {
"target": "index.js"
}
}
}
63 changes: 63 additions & 0 deletions tasks/DeployJobsTask/DeployJobsV1/tsconfig.json
@@ -0,0 +1,63 @@
{
"compilerOptions": {
/* Basic Options */
// "incremental": true, /* Enable incremental compilation */
"target": "es6", /* Specify ECMAScript target version: 'ES3' (default), 'ES5', 'ES2015', 'ES2016', 'ES2017', 'ES2018', 'ES2019' or 'ESNEXT'. */
"module": "commonjs", /* Specify module code generation: 'none', 'commonjs', 'amd', 'system', 'umd', 'es2015', or 'ESNext'. */
// "lib": [], /* Specify library files to be included in the compilation. */
// "allowJs": true, /* Allow javascript files to be compiled. */
// "checkJs": true, /* Report errors in .js files. */
// "jsx": "preserve", /* Specify JSX code generation: 'preserve', 'react-native', or 'react'. */
// "declaration": true, /* Generates corresponding '.d.ts' file. */
// "declarationMap": true, /* Generates a sourcemap for each corresponding '.d.ts' file. */
// "sourceMap": true, /* Generates corresponding '.map' file. */
// "outFile": "./", /* Concatenate and emit output to single file. */
// "outDir": "./", /* Redirect output structure to the directory. */
// "rootDir": "./", /* Specify the root directory of input files. Use to control the output directory structure with --outDir. */
// "composite": true, /* Enable project compilation */
// "tsBuildInfoFile": "./", /* Specify file to store incremental compilation information */
// "removeComments": true, /* Do not emit comments to output. */
// "noEmit": true, /* Do not emit outputs. */
// "importHelpers": true, /* Import emit helpers from 'tslib'. */
// "downlevelIteration": true, /* Provide full support for iterables in 'for-of', spread, and destructuring when targeting 'ES5' or 'ES3'. */
// "isolatedModules": true, /* Transpile each file as a separate module (similar to 'ts.transpileModule'). */

/* Strict Type-Checking Options */
"strict": true, /* Enable all strict type-checking options. */
// "noImplicitAny": true, /* Raise error on expressions and declarations with an implied 'any' type. */
// "strictNullChecks": true, /* Enable strict null checks. */
// "strictFunctionTypes": true, /* Enable strict checking of function types. */
// "strictBindCallApply": true, /* Enable strict 'bind', 'call', and 'apply' methods on functions. */
// "strictPropertyInitialization": true, /* Enable strict checking of property initialization in classes. */
// "noImplicitThis": true, /* Raise error on 'this' expressions with an implied 'any' type. */
// "alwaysStrict": true, /* Parse in strict mode and emit "use strict" for each source file. */

/* Additional Checks */
// "noUnusedLocals": true, /* Report errors on unused locals. */
// "noUnusedParameters": true, /* Report errors on unused parameters. */
// "noImplicitReturns": true, /* Report error when not all code paths in function return a value. */
// "noFallthroughCasesInSwitch": true, /* Report errors for fallthrough cases in switch statement. */

/* Module Resolution Options */
// "moduleResolution": "node", /* Specify module resolution strategy: 'node' (Node.js) or 'classic' (TypeScript pre-1.6). */
// "baseUrl": "./", /* Base directory to resolve non-absolute module names. */
// "paths": {}, /* A series of entries which re-map imports to lookup locations relative to the 'baseUrl'. */
// "rootDirs": [], /* List of root folders whose combined content represents the structure of the project at runtime. */
// "typeRoots": [], /* List of folders to include type definitions from. */
// "types": [], /* Type declaration files to be included in compilation. */
// "allowSyntheticDefaultImports": true, /* Allow default imports from modules with no default export. This does not affect code emit, just typechecking. */
"esModuleInterop": true /* Enables emit interoperability between CommonJS and ES Modules via creation of namespace objects for all imports. Implies 'allowSyntheticDefaultImports'. */
// "preserveSymlinks": true, /* Do not resolve the real path of symlinks. */
// "allowUmdGlobalAccess": true, /* Allow accessing UMD globals from modules. */

/* Source Map Options */
// "sourceRoot": "", /* Specify the location where debugger should locate TypeScript files instead of source locations. */
// "mapRoot": "", /* Specify the location where debugger should locate map files instead of generated locations. */
// "inlineSourceMap": true, /* Emit a single file with source maps instead of having a separate file. */
// "inlineSources": true, /* Emit the source alongside the sourcemaps within a single file; requires '--inlineSourceMap' or '--sourceMap' to be set. */

/* Experimental Options */
// "experimentalDecorators": true, /* Enables experimental support for ES7 decorators. */
// "emitDecoratorMetadata": true, /* Enables experimental support for emitting type metadata for decorators. */
}
}