alexanderdean

{
	"schema": "iglu:com.channel2.vod/video_played/jsonschema/1-0-0",
	"data":   {
		"length": 213,
		"id":     "hY7gQrO"
	}
}

alexanderdean

{
	"$schema": "http://iglucentral.com/schemas/com.snowplowanalytics.self-desc/schema/jsonschema/1-0-0#",
	"description": "Schema for a video_played event",
	"self": {
		"vendor": "com.channel2.vod",
		"name": "video_played",
		"format": "jsonschema",
		"version": "1-0-0"
	},
	"type": "object",

alexanderdean

input_lines = LOAD '$INPUT' AS (line:chararray);

-- Extract words from each line and put them into a pig bag
-- datatype, then flatten the bag to get one word on each row
words = FOREACH input_lines GENERATE FLATTEN(TOKENIZE(line)) AS word;

-- filter out any words that are just white spaces
filtered_words = FILTER words BY word MATCHES '\\w+';

-- create a group for each word

alexanderdean

// Request body expected to validate against this JSON Schema
private val PayloadDataSchema =
  SchemaCriterion("com.snowplowanalytics.snowplow", "payload_data", "jsonschema", 1, 0)

// Check JSON is a payload_data version 1-0-*, and verify it against the schema
val body: ValidatedNel[JsonNode] = bodyNode.verifySchemaAndValidate(schemaCriterion)

alexanderdean

/* 
 * Copyright (c) 2015 Tim Harper.
 */
import sbt._
import Keys._

import xerial.sbt.Pack._

object SamzaTasks {