From 8c61808d6eeb550c2156dbcb6b070d54a8666c61 Mon Sep 17 00:00:00 2001 From: j <0x006A@0x2620.org> Date: Mon, 17 May 2010 11:09:40 +0200 Subject: [PATCH] known unknowns --- oxlib/normalize.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/oxlib/normalize.py b/oxlib/normalize.py index 0aeb30d..7be2ca5 100644 --- a/oxlib/normalize.py +++ b/oxlib/normalize.py @@ -1,6 +1,6 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- # vi:si:et:sw=4:sts=4:ts=4 -# GPL 2008 +# GPL 2008 import re _articles = ('the', 'la', 'a', 'die', 'der', 'le', 'el', @@ -106,6 +106,8 @@ def canonicalName(name): # - single surname, composed name: 186604 # (2: 178315, 3: 6573, 4: 1219, 5: 352) # Don't convert names already in the canonical format. + if name in ('Unknown Director', ): + return name if name.find(', ') != -1: return name sname = name.split(' ') snl = len(sname)