class TextIndex(Persistent):
def __init__(self):
self.lexicon = Lexicon(Splitter(), CaseNormalizer(), StopWordRemover())
self.index = OkapiIndex(self.lexicon)
def index_text(self, docid, text):
self.index.index_doc(docid, text)
self._p_changed = 1 # XXX
def unindex(self, docid):
self.index.unindex_doc(docid)
self._p_changed = 1 # XXX
def query(self, query, nbest=10):
# returns a total hit count and a mapping from docids to scores
parser = QueryParser(self.lexicon)
tree = parser.parseQuery(query)
results = tree.executeQuery(self.index)
if results is None:
return [], 0
chooser = NBest(nbest)
chooser.addmany(results.items())
return chooser.getbest(), len(results)
def query_weight(self, query):
parser = QueryParser(self.lexicon)
tree = parser.parseQuery(query)
terms = tree.terms()
return self.index.query_weight(terms)
class TextIndex(Persistent):
def __init__(self):
self.lexicon = Lexicon(Splitter(), CaseNormalizer(), StopWordRemover())
self.index = OkapiIndex(self.lexicon)
def index_text(self, docid, text):
self.index.index_doc(docid, text)
self._p_changed = 1 # XXX
def unindex(self, docid):
self.index.unindex_doc(docid)
self._p_changed = 1 # XXX
def query(self, query, nbest=10):
# returns a total hit count and a mapping from docids to scores
parser = QueryParser(self.lexicon)
tree = parser.parseQuery(query)
results = tree.executeQuery(self.index)
if results is None:
return [], 0
chooser = NBest(nbest)
chooser.addmany(results.items())
return chooser.getbest(), len(results)
def query_weight(self, query):
parser = QueryParser(self.lexicon)
tree = parser.parseQuery(query)
terms = tree.terms()
return self.index.query_weight(terms)
