Difference between revisions of "DgraphAndWeaviateTest"

From BITPlan Wiki
Jump to navigation Jump to search
 
Line 142: Line 142:
  
 
= Example unit tests =
 
= Example unit tests =
−
== Apache unit test ==
 
−
see https://github.com/WolfgangFahl/DgraphAndWeaviateTest/blob/master/tests/testJena.py
 
−
<source lang='python'>
 
−
'''
 
−
Created on 2020-08-14
 
−
@author: wf
 
−
'''
 
−
import unittest
 
−
import getpass
 
−
from dg.jena import Jena
 
−
import time
 
−
import sys
 
−
from datetime import datetime,date
 
  
−
class TestJena(unittest.TestCase):
 
−
    ''' Test Apache Jena access via Wrapper'''
 
−
 
−
    def setUp(self):
 
−
        pass
 
−
 
−
 
−
    def tearDown(self):
 
−
        pass
 
−
 
−
    def getJena(self,mode='query',debug=False,typedLiterals=False):
 
−
        '''
 
−
        get the jena endpoint for the given mode
 
−
        '''
 
−
        endpoint="http://localhost:3030/example"
 
−
        jena=Jena(endpoint,mode=mode,debug=debug,typedLiterals=typedLiterals)
 
−
        return jena
 
−
 
−
    def testJenaQuery(self):
 
−
        '''
 
−
        test Apache Jena Fuseki SPARQL endpoint with example SELECT query
 
−
        '''
 
−
        jena=self.getJena()
 
−
        queryString = "SELECT * WHERE { ?s ?p ?o. }"
 
−
        results=jena.query(queryString)
 
−
        self.assertTrue(len(results)>20)
 
−
        pass
 
−
   
 
−
    def testJenaInsert(self):
 
−
        '''
 
−
        test a Jena INSERT DATA
 
−
        '''
 
−
        jena=self.getJena(mode="update")
 
−
        insertCommands = [ """
 
−
        PREFIX cr: <http://cr.bitplan.com/>
 
−
        INSERT DATA {
 
−
          cr:version cr:author "Wolfgang Fahl".
 
−
        }
 
−
        """,'INVALID COMMAND']
 
−
        for index,insertCommand in enumerate(insertCommands):
 
−
            try:
 
−
                result=jena.insert(insertCommand)
 
−
                self.assertTrue(index==0)
 
−
                print(result)
 
−
            except Exception as ex:
 
−
                self.assertTrue(index==1)
 
−
                msg=ex.args[0]
 
−
                self.assertTrue("QueryBadFormed" in msg)
 
−
                self.assertTrue("Error 400" in msg)
 
−
                pass
 
−
           
 
−
    def checkErrors(self,errors):     
 
−
        if len(errors)>0:
 
−
            print("ERRORS:")
 
−
            for error in errors:
 
−
                print(error)
 
−
        self.assertEquals(0,len(errors))   
 
−
       
 
−
       
 
−
    def dob(self,isoDateString):
 
−
        ''' get the date of birth from the given iso date state'''
 
−
        if sys.version_info >= (3, 7):
 
−
            dt=datetime.fromisoformat(isoDateString)
 
−
        else:
 
−
            dt=datetime.strptime(isoDateString,"%y-%m-%d") 
 
−
        return dt.date()   
 
−
           
 
−
    def testListOfDictInsert(self):
 
−
        '''
 
−
        test inserting a list of Dicts using FOAF example
 
−
        https://en.wikipedia.org/wiki/FOAF_(ontology)
 
−
        '''
 
−
        listofDicts=[
 
−
            {'name': 'Elizabeth Alexandra Mary Windsor', 'born': self.dob('1926-04-21'), 'numberInLine': 0, 'wikidataurl': 'https://www.wikidata.org/wiki/Q9682' },
 
−
            {'name': 'Charles, Prince of Wales',        'born': self.dob('1948-11-14'), 'numberInLine': 1, 'wikidataurl': 'https://www.wikidata.org/wiki/Q43274' },
 
−
            {'name': 'George of Cambridge',              'born': self.dob('2013-07-22'), 'numberInLine': 3, 'wikidataurl': 'https://www.wikidata.org/wiki/Q1359041'},
 
−
            {'name': 'Harry Duke of Sussex',            'born': self.dob('1984-09-15'), 'numberInLine': 5, 'wikidataurl': 'https://www.wikidata.org/wiki/Q152316'}
 
−
        ]
 
−
        today=date.today()
 
−
        for person in listofDicts:
 
−
            born=person['born']
 
−
            age=(today - born).days / 365.2425
 
−
            person['age']=age
 
−
            person['ofAge']=age>=18
 
−
        typedLiteralModes=[True,False]
 
−
        for typedLiteralMode in typedLiteralModes:
 
−
            jena=self.getJena(mode='update',typedLiterals=typedLiteralMode,debug=True)
 
−
            errors=jena.insertListOfDicts(listofDicts,'foaf:Person','name','PREFIX foaf: <http://xmlns.com/foaf/0.1/>')
 
−
            self.checkErrors(errors)
 
−
           
 
−
       
 
−
    def testListOfDictSpeed(self):
 
−
        '''
 
−
        test the speed of adding data
 
−
        '''
 
−
        listOfDicts=[]
 
−
        limit=1000
 
−
        for index in range(limit):
 
−
            listOfDicts.append({'pkey': "index%d" %index, 'index': "%d" %index})
 
−
        jena=self.getJena(mode='update',debug=True)
 
−
        entityType="ex:TestRecord"
 
−
        primaryKey='pkey'
 
−
        prefixes='PREFIX ex: <http://example.com/>'
 
−
        startTime=time.time()
 
−
        errors=jena.insertListOfDicts(listOfDicts, entityType, primaryKey, prefixes) 
 
−
        self.checkErrors(errors)
 
−
        elapsed=time.time()-startTime
 
−
        print ("adding %d records took %5.3f s => %5.f records/s" % (limit,elapsed,limit/elapsed))
 
−
   
 
−
    def testLocalWikdata(self):
 
−
        '''
 
−
        check local wikidata
 
−
        '''
 
−
        # check we have local wikidata copy:
 
−
        if getpass.getuser()=="wf":
 
−
            # use 2018 wikidata copy
 
−
            endpoint="http://blazegraph.bitplan.com/sparql"
 
−
            jena=Jena(endpoint)
 
−
            queryString="""
 
−
            SELECT ?item ?coord
 
−
WHERE
 
−
{
 
−
  # instance of whisky distillery
 
−
  ?item wdt:P31 wd:Q10373548.
 
−
  # get the coordindate
 
−
  ?item wdt:P625 ?coord.
 
−
}"""
 
−
            results=jena.query(queryString)
 
−
            self.assertEqual(238,len(results))
 
−
 
−
 
−
if __name__ == "__main__":
 
−
    #import sys;sys.argv = ['', 'Test.testName']
 
−
    unittest.main()
 
−
</source>
 
−
 
−
== Dgraph unit test ==
 
−
<source lang='python'>
 
−
def testDgraph(self):
 
−
        '''
 
−
        test basic Dgraph operation
 
−
        '''
 
−
        dgraph=Dgraph(debug=True)
 
−
        # drop all data and schemas
 
−
        dgraph.drop_all()
 
−
        # create a schema for Pokemons
 
−
        schema='''
 
−
        name: string @index(exact) .
 
−
        weight: float .
 
−
        height: float .
 
−
type Pokemon {
 
−
  name
 
−
  weight
 
−
  height
 
−
}'''
 
−
        dgraph.addSchema(schema)
 
−
        # prepare a list of Pokemons to be added
 
−
        pokemonList=[{'name':'Pikachu', 'weight':  6, 'height': 0.4 },
 
−
                  {'name':'Arbok',  'weight': 65, 'height': 3.5 },
 
−
                  {'name':'Raichu',  'weight': 30, 'height': 0.8 },
 
−
                  {'name':'Sandan',  'weight': 12, 'height': 0.6 }]
 
−
        # add the list in a single transaction
 
−
        dgraph.addData(obj=pokemonList)
 
−
        # retrieve the data via GraphQL+ query
 
−
        graphQuery='''{
 
−
# list of pokemons
 
−
  pokemons(func: has(name), orderasc: name) {
 
−
    name
 
−
    weight
 
−
    height
 
−
  }
 
−
}'''
 
−
        queryResult=dgraph.query(graphQuery)
 
−
        # check the result
 
−
        self.assertTrue('pokemons' in queryResult)
 
−
        pokemons=queryResult['pokemons']
 
−
        self.assertEqual(len(pokemonList),len(pokemons))
 
−
        sortindex=[1,0,2,3]
 
−
        for index,pokemon in enumerate(pokemons):
 
−
            expected=pokemonList[sortindex[index]]
 
−
            self.assertEquals(expected,pokemon)
 
−
        # close the database connection
 
−
        dgraph.close()
 
−
</source>
 
  
 
== Example test session ==
 
== Example test session ==
 
see https://travis-ci.org/github/WolfgangFahl/DgraphAndWeaviateTest/jobs/715131236
 
see https://travis-ci.org/github/WolfgangFahl/DgraphAndWeaviateTest/jobs/715131236

Latest revision as of 09:05, 22 September 2020

OsProject

OsProject
edit
id  DgraphAndWeaviateTest
state  
owner  Wolfgang Fahl
title  DgraphAndWeaviateTest
url  https://github.com/WolfgangFahl/DgraphAndWeaviateTest
version  0.0.1
description  
date  2020/08/05
since  
until  

This is sample project to test Python based storage with

The motivation for this project was the Choice of a Database storage system for the ProceedingsTitleParser

Installation and test

Prerequisites

  • python > version 3.6 - tested with version 3.6/3.7/3.8
  • docker e.g. docker desktop community - tested with e.g. docker desktop 2.3.0.4 Docker version 19.03.12
  • java e.g. openjdk - tested with Java 1.8 and Java 11
  • Operating system that can run bash scripts e.g. macports, linux - tested on Mac OS 10.13.6 Macports 2.6.2, Ubuntu 18.04 LTS

Installation

https://github.com/WolfgangFahl/DgraphAndWeaviateTest
cd DgraphAndWeaviateTest
scripts/install

Starting servers

see also DgraphAndWeaviateTest 

# command to run Dgraph
# pull dgraph
scripts/dgraph -p
# run dgraph
scripts/dgraph
# pull and run weaviate
scripts/weaviate
# install apache jena and load example data
scripts/jena -l sampledata/example.ttl
# run apache jena fuseki server
scripts/jena -f example

Test

scripts/test

Sample Data

UML

Python

@staticmethod
    def getRoyals():
        listOfDicts=[
            {'name': 'Elizabeth Alexandra Mary Windsor', 'born': Sample.dob('1926-04-21'), 'numberInLine': 0, 'wikidataurl': 'https://www.wikidata.org/wiki/Q9682' },
            {'name': 'Charles, Prince of Wales',         'born': Sample.dob('1948-11-14'), 'numberInLine': 1, 'wikidataurl': 'https://www.wikidata.org/wiki/Q43274' },
            {'name': 'George of Cambridge',              'born': Sample.dob('2013-07-22'), 'numberInLine': 3, 'wikidataurl': 'https://www.wikidata.org/wiki/Q1359041'},
            {'name': 'Harry Duke of Sussex',             'born': Sample.dob('1984-09-15'), 'numberInLine': 6, 'wikidataurl': 'https://www.wikidata.org/wiki/Q152316'}
        ]
        today=date.today()
        for person in listOfDicts:
            born=person['born']
            age=(today - born).days / 365.2425
            person['age']=age
            person['ofAge']=age>=18
            person['lastmodified']=datetime.now()
        return listOfDicts

Weaviate

Weaviate start

scripts/weaviate

Dgraph

Dgraph Installation

docker based pull: 

scripts/dgraph -p

Dgraph start

docker based start of

  • alpha
  • ratel
  • zero
scripts/dgraph

Dgraph stop

scripts/dgraph -k

scripts/dgraph usage

scripts/dgraph -h
scripts/dgraph [-b|--bash|-c|--clean|-h|--help|-k|--kill|-p|--pull]

-b | --bash: start a bash terminal shell within the currently running container
-h | --help: show this usage
-k | --kill: stop the docker image
-p | --pull: pull the docker image
-c | --clean: clean start with kill and purge of all data

Issues, Questions and Answers

Issues

Stackoverflow questions

Stackoverflow answers

Example unit tests

Example test session

see https://travis-ci.org/github/WolfgangFahl/DgraphAndWeaviateTest/jobs/715131236

Retrieved from "https://wiki.bitplan.com/index.php?title=DgraphAndWeaviateTest&oldid=12980"