Last active
March 4, 2016 21:21
-
-
Save dannycoates/c4370760473cea2571db to your computer and use it in GitHub Desktop.
Example AWS Lambda for converting heka logs into json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var Zlib = require('zlib') | |
var AWS = require('aws-sdk') | |
var HekaDecodeStream = require('heka-decode-stream') | |
var through = require('through2') | |
var s3 = new AWS.S3() | |
exports.handler = function (event, context) { | |
var i = 0 | |
var record = event.Records[0].s3 | |
var sourceBucket = record.bucket.name | |
var sourceKey = decodeURIComponent(record.object.key.replace(/\+/g, " ")) | |
var outputBucket = sourceBucket + '-json' | |
var outputKey = 'json-' + sourceKey | |
var output = s3.getObject{ Bucket: sourceBucket, Key: sourceKey }).createReadStream() | |
.pipe(Zlib.createGunzip()) | |
.pipe(HekaDecodeStream({ | |
filter: function (m) { return m.type === 'mozsvc.metrics' } | |
})) | |
.pipe(through.obj(function (o, _, cb) { | |
i++ | |
if (i % 10000 === 0) { | |
console.log('record: ' + i + ' at ' + Date.now()) | |
} | |
cb(null, JSON.stringify(o) + '\n') | |
})) | |
.pipe(Zlib.createGzip()) | |
s3.upload({ Bucket: outputBucket, Key: outputKey, Body: output }, | |
function (err, data) { | |
context.done(err, data) | |
}) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment