commit b90a0e4090c921f3c4e5a8328a7cd93072eb22f6
parent 308953d67001f7d2b834c28d41d00c28f28086d3
Author: Nicolas Pouillard <nicolas.pouillard@gmail.com>
Date: Fri, 14 Nov 2008 13:31:02 +0100
Factor the Iconv decoding code, and be more lenient on encodings.
Diffstat:
3 files changed, 18 insertions(+), 8 deletions(-)
diff --git a/lib/sup/message.rb b/lib/sup/message.rb
@@ -434,11 +434,10 @@ private
end
def self.convert_from body, charset
- charset = "utf-8" if charset =~ /UTF_?8/i
begin
raise MessageFormatError, "RubyMail decode returned a null body" unless body
return body unless charset
- Iconv.iconv($encoding + "//IGNORE", charset, body + " ").join[0 .. -2]
+ Iconv.easy_decode($encoding, charset, body)
rescue Errno::EINVAL, Iconv::InvalidEncoding, Iconv::IllegalSequence, MessageFormatError => e
Redwood::log "warning: error (#{e.class.name}) decoding message body from #{charset}: #{e.message}"
File.open(File.join(BASE_DIR,"unable-to-decode.txt"), "w") { |f| f.write body }
diff --git a/lib/sup/rfc2047.rb b/lib/sup/rfc2047.rb
@@ -52,13 +52,8 @@ module Rfc2047
# WORD.
end
- charset = "utf-8" if charset =~ /UTF_?8/i
-
- # Convert:
- #
- # Remember - Iconv.open(to, from)!
begin
- text = Iconv.iconv(target + "//IGNORE", charset, text + " ").join[0 .. -2]
+ Iconv.easy_decode(target, charset, text)
rescue Iconv::InvalidCharacter
text
end
diff --git a/lib/sup/util.rb b/lib/sup/util.rb
@@ -617,3 +617,19 @@ class FinishLine
@m.synchronize { !@over && @over = true }
end
end
+
+class Iconv
+ def self.easy_decode target, charset, text
+ return text if charset =~ /^x-unknown$/i
+ charset = case charset
+ when /UTF[-_]?8/i: "utf-8"
+ when /(iso[-_])?latin[-_]?1$/i: "ISO-8859-1"
+ else charset
+ end
+
+ # Convert:
+ #
+ # Remember - Iconv.open(to, from)!
+ Iconv.iconv(target + "//IGNORE", charset, text + " ").join[0 .. -2]
+ end
+end