moss_ruby 1.1.1 → 1.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6388f6ab27c44a591101464aa52b353023baf4e8
-  data.tar.gz: a6ea6678cab87b739629d4dfe96070b5b07d9669
+  metadata.gz: 7501061523c707fa401f9a21744c3b9689b61eed
+  data.tar.gz: 0480f03c83f40c227e96897bbd26cf5b6a7a0b11
 SHA512:
-  metadata.gz: 230ff756021bca01adfb49e4f91103b421922b8ef10a05dde7754681d9426d0ccc2b32bbbddbefda2a4908f21b81b66d3be173961b97f72e8d75cce59debaeed
-  data.tar.gz: 1533a081ee20ba3f568338e1663af6bce61c6f8827360a4c8a07988f23eab25bab0b1bfafa6d15e6e3020bc490da586f5b6486e132aff417468a833acb7acee3
+  metadata.gz: 100549f657224335d56c6f2752cb65ea6cde75aa5fff8d7b498fdace12a5bbf1aff8ce20c3d3ce9033a1869bf9920f12bbb6cda72ae2e64a8af4215799f6ee24
+  data.tar.gz: 91cd8e2fe59e97351d1a27bbb56e115336facfc24de4cb872589ba65a338e55c54688ca9f5f1e8ec5ccb4b82d44b08b265410ec6942e47084a261bad2dcaf6e5

data/lib/moss_ruby.rb

@@ -168,7 +168,7 @@ class MossRuby
 
 				# read the two match files
 				match_url = "#{uri}/match#{id}-top.html"
-				match_top = open(match_url).read
+				match_top = open(match_url).read().encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '?')
 
 				callback.call(" - checking match #{match} percents") unless callback.nil?
 				top = read_pcts match_top
@@ -177,8 +177,8 @@ class MossRuby
 
 				callback.call(" - fetching #{match} html") unless callback.nil?
 
-				match_file[0] = open("#{uri}/match#{id}-0.html").read
-				match_file[1] = open("#{uri}/match#{id}-1.html").read
+				match_file[0] = open("#{uri}/match#{id}-0.html").read().encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '?')
+				match_file[1] = open("#{uri}/match#{id}-1.html").read().encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '?')
 
 				# puts match_top
 				# puts "---FILE0\n\n"
@@ -222,7 +222,7 @@ class MossRuby
 		result = Array.new
 		begin
 			callback.call(" - Reading match data") unless callback.nil?
-			page = open("#{uri}").read
+			page = open("#{uri}").read().encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '?')
 			regex = /<TR><TD><A HREF=".*?match(?<match_id>\d+).html">.*\((?<pct0>\d+)%\)<\/A>\n.*?<TD><A.*?((?<pct0>\d+)%\))/i
 			# puts "scanning page"
 			page.scan(regex).each do | match | 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: moss_ruby
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.1.2
 platform: ruby
 authors:
 - Andrew Cain
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-29 00:00:00.000000000 Z
+date: 2015-08-05 00:00:00.000000000 Z
 dependencies: []
 description: Moss-ruby is an unofficial ruby gem for the Moss system for Detecting
   Software Plagiarism (http://theory.stanford.edu/~aiken/moss/)