import json
from capreolus import constants
from capreolus.utils.loginit import get_logger
from . import Collection, IRDCollection
[docs]logger = get_logger(__name__)
@Collection.register
[docs]class Highwire(IRDCollection):
"""Highire collection used by TREC Genomics 2006 and 2007"""
[docs] module_name = "highwire"
[docs] ird_dataset_name = "highwire"
[docs] collection_type = "JsonCollection"
[docs] def doc_as_json(self, doc):
content = " ".join((span.text for span in doc.spans))
return json.dumps({"id": doc.doc_id, "contents": content})