email_reply_parser 0.3.0 → 0.4.0

data/email_reply_parser.gemspec

@@ -13,8 +13,8 @@ Gem::Specification.new do |s|
   ## If your rubyforge_project name is different, then edit it and comment out
   ## the sub! line in the Rakefile
   s.name              = 'email_reply_parser'
-  s.version           = '0.3.0'
-  s.date              = '2011-08-23'
+  s.version           = '0.4.0'
+  s.date              = '2012-03-01'
   s.rubyforge_project = 'email_reply_parser'
 
   ## Make sure your summary is short. The description may be as long
@@ -65,10 +65,13 @@ Gem::Specification.new do |s|
     email_reply_parser.gemspec
     lib/email_reply_parser.rb
     test/email_reply_parser_test.rb
+    test/emails/correct_sig.txt
     test/emails/email_1_1.txt
     test/emails/email_1_2.txt
     test/emails/email_1_3.txt
     test/emails/email_1_4.txt
+    test/emails/email_1_5.txt
+    test/emails/email_1_6.txt
   ]
   # = MANIFEST =
 

data/lib/email_reply_parser.rb

@@ -19,7 +19,7 @@ require 'strscan'
 #
 #     this is some text
 #
-#     -- 
+#     --
 #     Bob
 #     http://homepage.com/~bob
 #
@@ -30,7 +30,7 @@ require 'strscan'
 #
 # [mail]: https://github.com/mikel/mail
 class EmailReplyParser
-  VERSION = "0.3.0"
+  VERSION = "0.4.0"
 
   # Splits an email body into a list of Fragments.
   #
@@ -60,9 +60,16 @@ class EmailReplyParser
     #
     # Returns this same Email instance.
     def read(text)
+      # Check for multi-line reply headers. Some clients break up
+      # the "On DATE, NAME <EMAIL> wrote:" line into multiple lines.
+      if text =~ /^(On(.+)wrote:)$/m
+        # Remove all new lines from the reply header.
+        text.gsub! $1, $1.gsub("\n", " ")
+      end
+
       # The text is reversed initially due to the way we check for hidden
       # fragments.
-      text.reverse!
+      text = text.reverse
 
       # This determines if any 'visible' Fragment has been found.  Once any
       # visible Fragment is found, stop looking for hidden ones.
@@ -85,7 +92,7 @@ class EmailReplyParser
       end
 
       # Finish up the final fragment.  Finishing a fragment will detect any
-      # attributes (hidden, signature, reply), and join each line into a 
+      # attributes (hidden, signature, reply), and join each line into a
       # string.
       finish_fragment
 
@@ -98,6 +105,7 @@ class EmailReplyParser
 
   private
     EMPTY = "".freeze
+    SIG_REGEX = /(\s--|__|\w-)$/
 
     ### Line-by-Line Parsing
 
@@ -109,7 +117,7 @@ class EmailReplyParser
     # Returns nothing.
     def scan_line(line)
       line.chomp!("\n")
-      line.lstrip!
+      line.lstrip! unless line =~ SIG_REGEX
 
       # We're looking for leading `>`'s to see if this line is part of a
       # quoted Fragment.
@@ -118,7 +126,7 @@ class EmailReplyParser
       # Mark the current Fragment as a signature if the current line is empty
       # and the Fragment starts with a common signature indicator.
       if @fragment && line == EMPTY
-        if @fragment.lines.last =~ /[\-\_]$/
+        if @fragment.lines.last =~ SIG_REGEX
           @fragment.signature = true
           finish_fragment
         end
@@ -165,10 +173,10 @@ class EmailReplyParser
     #
     #     Go fish! (visible)
     #
-    #     > -- 
+    #     > --
     #     > Player 1 (quoted, hidden)
     #
-    #     -- 
+    #     --
     #     Player 2 (signature, hidden)
     #
     def finish_fragment

data/test/email_reply_parser_test.rb

@@ -71,6 +71,36 @@ I am currently using the Java HTTP API.\n", reply.fragments[0].to_s
     assert_match /Loader/,   reply.fragments[1].to_s
   end
 
+  def test_a_complex_body_with_only_one_fragment
+    reply = email :email_1_5
+
+    assert_equal 1, reply.fragments.size
+  end
+
+  def test_reads_email_with_correct_signature
+    reply = email :correct_sig
+    
+    assert_equal 2, reply.fragments.size
+    assert_equal [false, false], reply.fragments.map { |f| f.quoted? }
+    assert_equal [false, true], reply.fragments.map { |f| f.signature? }
+    assert_equal [false, true], reply.fragments.map { |f| f.hidden? }
+    assert_match /^-- \nrick/, reply.fragments[1].to_s
+  end
+
+  def test_deals_with_multiline_reply_headers
+    reply = email :email_1_6
+
+    assert_match /^I get/,   reply.fragments[0].to_s
+    assert_match /^On/,      reply.fragments[1].to_s
+    assert_match /Was this/, reply.fragments[1].to_s
+  end
+
+  def test_does_not_modify_input_string
+    original = "The Quick Brown Fox Jumps Over The Lazy Dog"
+    EmailReplyParser.read original
+    assert_equal "The Quick Brown Fox Jumps Over The Lazy Dog", original
+  end
+
   def email(name)
     body = IO.read EMAIL_FIXTURE_PATH.join("#{name}.txt").to_s
     EmailReplyParser.read body

data/test/emails/correct_sig.txt

@@ -0,0 +1,4 @@
+this is an email with a correct -- signature.
+
+-- 
+rick

data/test/emails/email_1_5.txt

@@ -0,0 +1,15 @@
+One: Here's what I've got.
+
+- This would be the first bullet point that wraps to the second line
+to the next
+- This is the second bullet point and it doesn't wrap
+- This is the third bullet point and I'm having trouble coming up with enough
+to say
+- This is the fourth bullet point
+
+Two:
+- Here is another bullet point
+- And another one
+
+This is a paragraph that talks about a bunch of stuff. It goes on and on
+for a while.

data/test/emails/email_1_6.txt

@@ -0,0 +1,15 @@
+I get proper rendering as well.
+
+Sent from a magnificent torch of pixels
+
+On Dec 16, 2011, at 12:47 PM, Corey Donohoe
+<reply@reply.github.com>
+wrote:
+
+> Was this caching related or fixed already?  I get proper rendering here.
+>
+> ![](https://img.skitch.com/20111216-m9munqjsy112yqap5cjee5wr6c.jpg)
+>
+> ---
+> Reply to this email directly or view it on GitHub:
+> https://github.com/github/github/issues/2278#issuecomment-3182418

metadata

@@ -1,72 +1,61 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: email_reply_parser
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 3
-  - 0
-  version: 0.3.0
+version: !ruby/object:Gem::Version
+  version: 0.4.0
+  prerelease: 
 platform: ruby
-authors: 
+authors:
 - Rick Olson
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2011-08-23 00:00:00 -07:00
-default_executable: 
+date: 2012-03-01 00:00:00.000000000 Z
 dependencies: []
-
 description: Long description. Maybe copied from the README.
 email: technoweenie@gmail.com
 executables: []
-
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files:
 - README.md
 - LICENSE
-files: 
+files:
 - LICENSE
 - README.md
 - Rakefile
 - email_reply_parser.gemspec
 - lib/email_reply_parser.rb
 - test/email_reply_parser_test.rb
+- test/emails/correct_sig.txt
 - test/emails/email_1_1.txt
 - test/emails/email_1_2.txt
 - test/emails/email_1_3.txt
 - test/emails/email_1_4.txt
-has_rdoc: true
+- test/emails/email_1_5.txt
+- test/emails/email_1_6.txt
 homepage: http://github.com/github/email_reply_parser
 licenses: []
-
 post_install_message: 
-rdoc_options: 
+rdoc_options:
 - --charset=UTF-8
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: email_reply_parser
-rubygems_version: 1.3.6
+rubygems_version: 1.8.11
 signing_key: 
 specification_version: 2
 summary: Short description used in Gem listings.
-test_files: 
+test_files:
 - test/email_reply_parser_test.rb