From b768fe9411ceed100a37d70ed710138e98bf00ed Mon Sep 17 00:00:00 2001 From: Romain Deveaud Date: Wed, 20 Apr 2011 22:16:43 +0200 Subject: [PATCH] bugfix in document, more stopwords --- lib/mirimiri/document.rb | 2 +- lib/mirimiri/string.rb | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/lib/mirimiri/document.rb b/lib/mirimiri/document.rb index af57bb7..97af4ca 100644 --- a/lib/mirimiri/document.rb +++ b/lib/mirimiri/document.rb @@ -142,7 +142,7 @@ module Mirimiri end def self.get_url(name) - raise ArgumentError, "Bad encoding", name unless name.isutf9 + raise ArgumentError, "Bad encoding", name unless name.isutf8 atts = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml" ).unaccent.toutf8).elements['api/query/pages/page'].attributes diff --git a/lib/mirimiri/string.rb b/lib/mirimiri/string.rb index c72d215..d91a7a7 100644 --- a/lib/mirimiri/string.rb +++ b/lib/mirimiri/string.rb @@ -66,7 +66,8 @@ module Mirimiri "whew","which","whichever","whichsoever","while","whilst","whither","who","whoa", "whoever","whole","whom","whomever","whomsoever","whose","whosoever","why","will", "wilt","with","within","without","worse","worst","would","wow","ye","yet","year", -"yippee","you","your","yours","yourself","yourselves" +"yippee","you","your","yours","yourself","yourselves", + "edit", "new", "page", "article", "http", "www", "com", "org", "wikipedia", "en" ] Transmap = { -- 1.8.2.3