#!/usr/bin/env python

# person2metadata.py - given the Wikidata QNumber of a person, output metadata in the form of json about them

# Eric Lease Morgan <emorgan@nd.edu>
# (c) University of Notre Dame; distributed under a GNU Public License

# January 4, 2025 - first cut; after learning of Mark's death
# April   6, 2025 - added a great deal of extra content; "Thank you, Susan Hoover!"


# configure
ENDPOINT = 'https://query.wikidata.org/sparql'
TEMPLATE = """
SELECT DISTINCT ?label
                ?description
                ?dateBirth
                ?dateDeath
                ?country
                ?gender
                ?imageURL
                (GROUP_CONCAT(DISTINCT ?occupationLabel; separator=";") AS ?occupations)
WHERE {
	wd:##QNUMBER## rdfs:label          ?label       .
	wd:##QNUMBER## schema:description  ?description .
	OPTIONAL {wd:##QNUMBER## wdt:P18  ?imageURL     .}
	OPTIONAL {wd:##QNUMBER## wdt:P21  ?gender       .}
	OPTIONAL {wd:##QNUMBER## wdt:P27  ?country      .}
	OPTIONAL {wd:##QNUMBER## wdt:P106 ?occupation   .}
	OPTIONAL {wd:##QNUMBER## wdt:P569 ?dateBirth    .}
	OPTIONAL {wd:##QNUMBER## wdt:P570 ?dateDeath    .}
	FILTER (langMatches(lang(?label),       'en'))
	FILTER (langMatches(lang(?description), 'en'))
	SERVICE wikibase:label {
		bd:serviceParam wikibase:language 'en'  .
		?occupation rdfs:label ?occupationLabel .
	}
}
GROUP BY ?label ?description ?dateBirth ?dateDeath ?country ?gender ?imageURL
LIMIT 1
"""

# require
from requests import get
from json     import dumps
from sys      import argv, exit

# get input
if len( argv ) != 2 : exit( "Usage: " + argv[ 0 ] + " <qnumber>" )
qnumber = argv[ 1 ]

# create a query and submit it
query    = TEMPLATE.replace( '##QNUMBER##', qnumber )
response = get( ENDPOINT, params={ 'format':'json', 'query':query } )

# output and done
print( dumps( response.json() ) )
exit()