rchardet 1.0 → 1.1

data/lib/rchardet/charsetprober.rb

@@ -53,13 +53,18 @@ module CharDet
     end
 
     def filter_high_bit_only(aBuf)
-      aBuf.gsub!(/([\x00-\x7F])+/, ' ')
-      return aBuf
+      # DO NOT USE `gsub!`
+      # It will remove all characters from the buffer that is later used by
+      # other probers.  This is because gsub! removes data from the instance variable
+      # that will be passed to later probers, while gsub makes a new instance variable
+      # that will not. 
+      newBuf = aBuf.gsub(/([\x00-\x7F])+/, ' ')
+      return newBuf
     end
 
     def filter_without_english_letters(aBuf)
-      aBuf.gsub!(/([A-Za-z])+/,' ')
-      return aBuf
+      newBuf = aBuf.gsub(/([A-Za-z])+/,' ')
+      return newBuf
     end
 
     def filter_with_english_letters(aBuf)

metadata

@@ -1,10 +1,10 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.9.0
+rubygems_version: 0.9.2
 specification_version: 1
 name: rchardet
 version: !ruby/object:Gem::Version 
-  version: "1.0"
-date: 2007-04-03 00:00:00 -04:00
+  version: "1.1"
+date: 2007-07-05 00:00:00 -07:00
 summary: Character encoding auto-detection in Ruby
 require_paths: 
 - lib
@@ -30,7 +30,6 @@ authors:
 - Jeff Hodges
 files: 
 - lib/rchardet
-- lib/rchardet.rb
 - lib/rchardet/big5freq.rb
 - lib/rchardet/big5prober.rb
 - lib/rchardet/chardistribution.rb
@@ -65,6 +64,7 @@ files:
 - lib/rchardet/sjisprober.rb
 - lib/rchardet/universaldetector.rb
 - lib/rchardet/utf8prober.rb
+- lib/rchardet.rb
 - COPYING
 test_files: []