- trac url can't be resolved so early

[packages/cvsspam.git] / cvsspam-multibyte_enc_disables_highlight-patch1.diff

--- cvsspam.rb	(working copy)
+++ cvsspam.rb	2009-03-05 01:48:46.419779119 +0200
@@ -936,7 +936,10 @@
         addInfixSize = line.length - (prefixLen+suffixLen)
         oversize_change = deleteInfixSize*100/@lineJustDeleted.length>33 || addInfixSize*100/line.length>33
 
-        if prefixLen==1 && suffixLen==0 || deleteInfixSize<=0 || oversize_change
+        # avoid doing 'within-a-line highlighting' if a multibyte encoding
+        # is suspected, as all the suffix/prefix stuff above is byte, not
+        # character based
+        if multibyte_encoding? || prefixLen==1 && suffixLen==0 || deleteInfixSize<=0 || oversize_change
           print(htmlEncode(@lineJustDeleted))
         else
           print(htmlEncode(@lineJustDeleted[0,prefixLen]))
@@ -1118,7 +1121,7 @@
         @lineJustDeleted = nil
       end
       shift(initial)
-      if prefixLen==1 && suffixLen==0 || addInfixSize<=0 || oversize_change
+      if multibyte_encoding? || prefixLen==1 && suffixLen==0 || addInfixSize<=0 || oversize_change
         encoded = htmlEncode(line)
       else
         encoded = htmlEncode(line[0,prefixLen]) +
@@ -1297,6 +1300,11 @@
   end
 end
 
+# guess if the users selected encoding is multibyte, since some CVSspam code
+# isn't multibyte-safe, and needs to be disabled.
+def multibyte_encoding?
+  $charset && ["utf-8", "utf-16"].include?($charset.downcase)
+end
 
 cvsroot_dir = "#{ENV['CVSROOT']}/CVSROOT"
 $config = "#{cvsroot_dir}/cvsspam.conf"