def main():
db = MongoClient().poky
inverse_table = InverseTable()
parser = Parser("Stopword.txt")
for document in db.documents.find({"text": {"$exists": True}}):
for textlist in document[u'text'].values():
for text in textlist:
DRL = DocumentReverseList(parser.getIndexToken(text), document[u'_id'])
inverse_table.merge(DRL)
inverse_table.CalNormalizingPara()
# inverse_table.printRT()
for key in inverse_table.table:
term = {}
term['word'] = key
term['df'] = inverse_table.table[key]['df']
term['idf'] = inverse_table.table[key]['idf']
term['posting'] = [{'doc_id': id,
'tf': inverse_table.table[key]['posting'][id]
} for id in inverse_table.table[key]['posting']]
db.terms.save(term)
for key in inverse_table.Normalization:
document = db.documents.find_one({"_id": key})
document["normalization"] = inverse_table.Normalization[key]
db.documents.save(document)
def main():
db = MongoClient().poky
inverse_table = InverseTable()
parser = Parser("Stopword.txt")
for document in db.documents.find({"text": {"$exists": True}}):
for textlist in document[u'text'].values():
for text in textlist:
DRL = DocumentReverseList(parser.getIndexToken(text),
document[u'_id'])
inverse_table.merge(DRL)
inverse_table.CalNormalizingPara()
# inverse_table.printRT()
for key in inverse_table.table:
term = {}
term['word'] = key
term['df'] = inverse_table.table[key]['df']
term['idf'] = inverse_table.table[key]['idf']
term['posting'] = [{
'doc_id': id,
'tf': inverse_table.table[key]['posting'][id]
} for id in inverse_table.table[key]['posting']]
db.terms.save(term)
for key in inverse_table.Normalization:
document = db.documents.find_one({"_id": key})
document["normalization"] = inverse_table.Normalization[key]
db.documents.save(document)
class QueryAnalysis(object):
def __init__(self):
self.parser = Parser(
os.path.join(os.path.dirname(__file__), "Stopword.txt"))
def analysis(self, Query):
return self.parser.getIndexToken(Query)
class QueryAnalysis(object):
def __init__(self):
self.parser = Parser(os.path.join(os.path.dirname(__file__),
"Stopword.txt"))
def analysis(self, Query):
return self.parser.getIndexToken(Query)
