Spelling suggestions using whoosh

import os.path
import urllib
import codecs
import cStringIO as StringIO
import re
import string
from whoosh import index, qparser
from whoosh.fields import Schema, ID, TEXT
from whoosh.index import open_dir

def write_index(src_paths, dst_dir):
    """Write search index"""
    schema = Schema(path=ID(unique=True, stored=True),
                    content=TEXT(spelling=True))
    ix = index.create_in(dst_dir, schema=schema)
    writer = ix.writer()
    for src_path in src_paths:
        add_doc(writer, src_path)
    writer.commit()

def strip_punctuation(s):
    """strip all the punctuation from a string"""
    return re.sub("[%s]*" % re.escape(string.punctuation), "", s)

def add_doc(writer, path):
    """Add utf-8 encoded document to index"""
    fileObj = codecs.open(path, encoding="utf-8")
    content = strip_punctuation(fileObj.read())
    fileObj.close()
    for word in content.split():
        writer.add_document(path=path, content=word)

def parse_string(qstring, index):
    """Parse the user query string"""
    parser = qparser.QueryParser("content", index.schema)
    q = parser.parse(qstring)
    with index.searcher() as s:   # Try correcting the query
        corrected = s.correct_query(q, qstring)
        if corrected.query != q:
            print qstring, "--> Did you mean:", corrected.string

def extract_comments(fileObj):
    """Extract comments from spss syntax and strip out punctuation"""
    subst = strip_punctuation
    comments = [subst(line).split() for line in fileObj if line[0] == u"*"]
    fileObj.close()
    return reduce(list.__add__, comments)

syntax = u"""\
* Id iz jajaja to saj thad names shoult reveal intent. What we want to impress upon you is that
* we are serious about this. Choosing good names takes time but saves more than it takes.
* So take care with your names and change them when you find better ones. Everyone who
* reads your code (including you) will be happier if you do.
* The name of a variable, function, or class, should answer all the big questions. It
* should tell you why it exists, what it does, and how it is used. If a name requires a com-
* ment, then the name does not reveal its intent."""


if __name__ == "__main__":
    url = "http://www.gutenberg.org/ebooks/97.txt.utf-8"  # Flatland
    dst_dir = u"d:/temp"
    book = os.path.join(dst_dir, u"book.txt")
    if not os.path.exists(book):
        urllib.urlretrieve (url, book)
        write_index([book], dst_dir)
    comments = extract_comments(StringIO.StringIO(syntax))
    index = open_dir(dst_dir)  # open index from file
    for comment in comments:
        parse_string(comment, index)