Google App Engine: Using Big Query on datastore?

Question

Have a GAE datastore kind with several 100'000s of objects in them. Want to do several involved queries (involving counting queries). Big Query seems a god fit for doing this.

Is there currently an easy way to query a live AppEngine Datastore using Big Query?

Answer 1

You can't run a BigQuery directly on DataStore entities, but you can write a Mapper Pipeline that reads entities out of DataStore, writes them to CSV in Google Cloud Storage, and then ingests those into BigQuery - you can even automate the process. Here's an example of using the Mapper API classes for just the DataStore to CSV step:

import re
import time
from datetime import datetime
import urllib
import httplib2
import pickle

from google.appengine.ext import blobstore
from google.appengine.ext import db
from google.appengine.ext import webapp

from google.appengine.ext.webapp.util import run_wsgi_app
from google.appengine.ext.webapp import blobstore_handlers
from google.appengine.ext.webapp import util
from google.appengine.ext.webapp import template

from mapreduce.lib import files
from google.appengine.api import taskqueue
from google.appengine.api import users

from mapreduce import base_handler
from mapreduce import mapreduce_pipeline
from mapreduce import operation as op

from apiclient.discovery import build
from google.appengine.api import memcache
from oauth2client.appengine import AppAssertionCredentials


#Number of shards to use in the Mapper pipeline
SHARDS = 20

# Name of the project's Google Cloud Storage Bucket
GS_BUCKET = 'your bucket'

# DataStore Model
class YourEntity(db.Expando):
  field1 = db.StringProperty() # etc, etc

ENTITY_KIND = 'main.YourEntity'


class MapReduceStart(webapp.RequestHandler):
  """Handler that provides link for user to start MapReduce pipeline.
  """
  def get(self):
    pipeline = IteratorPipeline(ENTITY_KIND)
    pipeline.start()
    path = pipeline.base_path + "/status?root=" + pipeline.pipeline_id
    logging.info('Redirecting to: %s' % path)
    self.redirect(path)


class IteratorPipeline(base_handler.PipelineBase):
  """ A pipeline that iterates through datastore
  """
  def run(self, entity_type):
    output = yield mapreduce_pipeline.MapperPipeline(
      "DataStore_to_Google_Storage_Pipeline",
      "main.datastore_map",
      "mapreduce.input_readers.DatastoreInputReader",
      output_writer_spec="mapreduce.output_writers.FileOutputWriter",
      params={
          "input_reader":{
              "entity_kind": entity_type,
              },
          "output_writer":{
              "filesystem": "gs",
              "gs_bucket_name": GS_BUCKET,
              "output_sharding":"none",
              }
          },
          shards=SHARDS)


def datastore_map(entity_type):
  props = GetPropsFor(entity_type)
  data = db.to_dict(entity_type)
  result = ','.join(['"%s"' % str(data.get(k)) for k in props])
  yield('%s\n' % result)


def GetPropsFor(entity_or_kind):
  if (isinstance(entity_or_kind, basestring)):
    kind = entity_or_kind
  else:
    kind = entity_or_kind.kind()
  cls = globals().get(kind)
  return cls.properties()


application = webapp.WSGIApplication(
                                     [('/start', MapReduceStart)],
                                     debug=True)

def main():
  run_wsgi_app(application)

if __name__ == "__main__":
  main()

If you append this to the end of your IteratorPipeline class: yield CloudStorageToBigQuery(output), you can pipe the resulting csv filehandle into a BigQuery ingestion pipe... like this:

class CloudStorageToBigQuery(base_handler.PipelineBase):
  """A Pipeline that kicks off a BigQuery ingestion job.
  """
  def run(self, output):

# BigQuery API Settings
SCOPE = 'https://www.googleapis.com/auth/bigquery'
PROJECT_ID = 'Some_ProjectXXXX'
DATASET_ID = 'Some_DATASET'

# Create a new API service for interacting with BigQuery
credentials = AppAssertionCredentials(scope=SCOPE)
http = credentials.authorize(httplib2.Http())
bigquery_service = build("bigquery", "v2", http=http)

jobs = bigquery_service.jobs()
table_name = 'datastore_dump_%s' % datetime.utcnow().strftime(
    '%m%d%Y_%H%M%S')
files = [str(f.replace('/gs/', 'gs://')) for f in output]
result = jobs.insert(projectId=PROJECT_ID,
                    body=build_job_data(table_name,files)).execute()
logging.info(result)

def build_job_data(table_name, files):
  return {"projectId": PROJECT_ID,
          "configuration":{
              "load": {
                  "sourceUris": files,
                  "schema":{
                      # put your schema here
                      "fields": fields
                      },
                  "destinationTable":{
                      "projectId": PROJECT_ID,
                      "datasetId": DATASET_ID,
                      "tableId": table_name,
                      },
                  }
              }
          }