indexing with .Net Lucene

index.py

import clr
clr.AddReference( "Lucene.Net.dll" )

from System.IO import FileInfo
idx_dir = FileInfo( "index" )

from Lucene.Net.Index import IndexWriter, IndexReader
from Lucene.Net.Analysis.Standard import StandardAnalyzer
from Lucene.Net.Analysis import StopFilter

import System

stop_words = ['bit.ly','from', 'maplpro', 'and', 'at', 'are', 'a', 'all', 'but', 'be', 
                'create', 'how', 'is', 'in', 'it', 'get', 'for', 'http', 'an', 'no', 'can', 
                'data', 'if', 'new', 'of', 'on', 'only', 'rt', 'that', 'the', 'to', 'services', 
                'service', 'server', 'with', 'you', 'your', 'id', 'file', 'windows', 'web', 'just',
                'by', 'any', 'api', 'has', 'software', 'now' ]
                
index = IndexWriter( idx_dir, StandardAnalyzer( System.Array[str]( stop_words ) ), True )

def document(f):

    from Lucene.Net.Documents import Document, Field
    from System.IO import StreamReader
    from System.Text import Encoding
    
    document = Document()
    document.Add(Field("contents", StreamReader(f.FullName, Encoding.Default), Field.TermVector.YES ))
    
    return document

index.AddDocument( document( FileInfo( "activities.txt" ) ) )

index.Optimize()
index.Close()

reader = IndexReader.Open( idx_dir )
vectors = reader.GetTermFreqVectors(0)

terms = vectors[0].GetTerms()
print [(terms[x],y) for x,y in enumerate( vectors[0].GetTermFrequencies() ) if y > 3]