def docsLike(self, id, doc, max):
authors = doc.getValues("author")
authorQuery = BooleanQuery()
for author in authors:
authorQuery.add(TermQuery(Term("author", author)),
BooleanClause.Occur.SHOULD)
authorQuery.setBoost(2.0)
vector = self.reader.getTermFreqVector(id, "subject")
subjectQuery = BooleanQuery()
for term in vector.getTerms():
tq = TermQuery(Term("subject", term))
subjectQuery.add(tq, BooleanClause.Occur.SHOULD)
likeThisQuery = BooleanQuery()
likeThisQuery.add(authorQuery, BooleanClause.Occur.SHOULD)
likeThisQuery.add(subjectQuery, BooleanClause.Occur.SHOULD)
# exclude myself
likeThisQuery.add(TermQuery(Term("isbn", doc.get("isbn"))),
BooleanClause.Occur.MUST_NOT)
print " Query:", likeThisQuery.toString("contents")
scoreDocs = self.searcher.search(likeThisQuery, 50).scoreDocs
docs = []
for scoreDoc in scoreDocs:
doc = self.searcher.doc(scoreDoc.doc)
if len(docs) < max:
docs.append(doc)
else:
break
return docs
def docsLike(self, id, doc, max):
authors = doc.getValues("author")
authorQuery = BooleanQuery()
for author in authors:
authorQuery.add(TermQuery(Term("author", author)),
BooleanClause.Occur.SHOULD)
authorQuery.setBoost(2.0)
vector = self.reader.getTermFreqVector(id, "subject")
subjectQuery = BooleanQuery()
for term in vector.getTerms():
tq = TermQuery(Term("subject", term))
subjectQuery.add(tq, BooleanClause.Occur.SHOULD)
likeThisQuery = BooleanQuery()
likeThisQuery.add(authorQuery, BooleanClause.Occur.SHOULD)
likeThisQuery.add(subjectQuery, BooleanClause.Occur.SHOULD)
# exclude myself
likeThisQuery.add(TermQuery(Term("isbn", doc.get("isbn"))),
BooleanClause.Occur.MUST_NOT)
print " Query:", likeThisQuery.toString("contents")
scoreDocs = self.searcher.search(likeThisQuery, 50).scoreDocs
docs = []
for scoreDoc in scoreDocs:
doc = self.searcher.doc(scoreDoc.doc)
if len(docs) < max:
docs.append(doc)
else:
break
return docs
