def testPretokenizedWitness(self):
pretokenized_witness = {
"witnesses": [{
"id":
"A",
"tokens": [{
"t": "A",
"ref": 123
}, {
"t": "black",
"adj": True
}, {
"t": "cat",
"id": "xyz"
}, {
"t": "bird",
"id": "abc"
}]
}, {
"id":
"B",
"tokens": [{
"t": "A"
}, {
"t": "white",
"adj": True
}, {
"t": "mousedog bird",
"adj": False
}]
}]
}
c = Collation.create_from_dict(pretokenized_witness)
result = collate(c, segmentation=False)
self.assertEqual(len(result.rows[0].to_list()), 4)
self.assertEqual(len(result.rows[1].to_list()), 4)
# The second witness should have a token that reads 'mousedog bird'.
self.assertIn("mousedog bird", str(result.rows[1].to_list()))
'''
Created on Apr 20, 2014
Darwin Integration test
@author: Ronald Haentjens Dekker
'''
import json
from collatex import Collation, collate
if __name__ == '__main__':
# read source JSON data into dictionary
json_data=open('darwin_chapter1_para1.json')
data = json.load(json_data)
json_data.close()
#pprint(data)
# generate collation object from dictionary
collation = Collation.create_from_dict(data)
print(collate(collation))
# write_dot(graph.graph, "rawoutput")
