From mboxrd@z Thu Jan  1 00:00:00 1970
From: nicolas.pouillard@gmail.com (Nicolas Pouillard)
Date: Tue, 19 Feb 2008 11:17:50 +0100
Subject: [sup-talk] [PATCH] Unwrap br0ken URLs.
Message-ID: <12034162702820-git-send-email-nicolas.pouillard@gmail.com>

---
 lib/sup/message-chunks.rb |    2 +-
 lib/sup/util.rb           |   25 +++++++++++++++++++++++++
 2 files changed, 26 insertions(+), 1 deletions(-)

diff --git a/lib/sup/message-chunks.rb b/lib/sup/message-chunks.rb
index 0606395..98b829c 100644
--- a/lib/sup/message-chunks.rb
+++ b/lib/sup/message-chunks.rb
@@ -147,7 +147,7 @@ EOS
 
     attr_reader :lines
     def initialize lines
-      @lines = lines.map { |l| l.chomp.wrap WRAP_LEN }.flatten # wrap
+      @lines = lines.unwrap_urls.map { |l| l.chomp.wrap WRAP_LEN }.flatten # wrap
 
       ## trim off all empty lines except one
       @lines.pop while @lines.length > 1 && @lines[-1] =~ /^\s*$/ && @lines[-2] =~ /^\s*$/
diff --git a/lib/sup/util.rb b/lib/sup/util.rb
index ceaf0b8..99e73b4 100644
--- a/lib/sup/util.rb
+++ b/lib/sup/util.rb
@@ -401,6 +401,31 @@ class Array
 
   def last= e; self[-1] = e end
   def nonempty?; !empty? end
+
+  URL_CHAR      = /[a-zA-Z0-9\-@;\/?:&=%$_.+!*\x27()~,#]/
+  URL_CHAR_LESS = /[a-zA-Z0-9\-@;\/?:&=%$_.+!*\x27()~]/
+  URL_RE = %r{(?:https?://|ftp://|news://|mailto:|file://)#{URL_CHAR}+}
+  TRAILING_URL_RE = /#{URL_RE}$/
+  LEADING_URL_RE = /^#{URL_RE}/
+  URL_PART_RE = /^#{URL_CHAR}+#{URL_CHAR_LESS}/
+
+  def unwrap_urls
+    res = []
+    len = size
+    i = 0
+    while i < len do
+      x = self[i]
+      y = self[i+1]
+      if y && x =~ TRAILING_URL_RE && y =~ URL_PART_RE && y !~ LEADING_URL_RE
+        res << x.chomp + y
+        i += 2
+      else
+        res << x
+        i += 1
+      end
+    end
+    res
+  end
 end
 
 class Time
-- 
1.5.3.1.109.gacd69