email_reply_parser 0.5.5 → 0.5.6

data/README.md

@@ -7,9 +7,9 @@ This is what GitHub uses to display comments that were created from
 email replies.  This code is being open sourced in an effort to
 crowdsource the quality of our email representation.
 
-See more at the [Rocco docs][rocco].
+See the [Ruby docs][rubydocs] for more information.
 
-[rocco]: http://help.github.com/code/email_reply_parser/
+[rubydocs]: http://rubydoc.info/gems/email_reply_parser/
 
 ##Usage
 
@@ -65,7 +65,7 @@ multiple lines.  GMail breaks up any lines over 80 characters for you.
     wrote:
     > blah
 
-Not to mention that we're search for "on" and "wrote".  It won't work
+Not to mention that we're searching for "on" and "wrote".  It won't work
 with other languages.
 
 Possible solution: Remove "reply@reply.github.com" lines...

data/email_reply_parser.gemspec

@@ -77,12 +77,14 @@ Gem::Specification.new do |s|
     test/emails/email_1_6.txt
     test/emails/email_1_7.txt
     test/emails/email_2_1.txt
+    test/emails/email_2_2.txt
     test/emails/email_BlackBerry.txt
     test/emails/email_bullets.txt
     test/emails/email_iPhone.txt
     test/emails/email_multi_word_sent_from_my_mobile_device.txt
     test/emails/email_one_is_not_on.txt
     test/emails/email_sent_from_my_not_signature.txt
+    test/emails/email_sig_delimiter_in_middle_of_line.txt
     test/emails/pathological.txt
   ]
   # = MANIFEST =

data/lib/email_reply_parser.rb

@@ -30,7 +30,7 @@ require 'strscan'
 #
 # [mail]: https://github.com/mikel/mail
 class EmailReplyParser
-  VERSION = "0.5.5"
+  VERSION = "0.5.6"
 
   # Public: Splits an email body into a list of Fragments.
   #
@@ -89,6 +89,12 @@ class EmailReplyParser
         text.gsub! $1, $1.gsub("\n", " ")
       end
 
+      # Some users may reply directly above a line of underscores.
+      # In order to ensure that these fragments are split correctly,
+      # make sure that all lines of underscores are preceded by
+      # at least two newline characters.
+      text.gsub!(/([^\n])(?=\n_{7}_+)$/m, "\\1\n")
+
       # The text is reversed initially due to the way we check for hidden
       # fragments.
       text = text.reverse
@@ -127,7 +133,7 @@ class EmailReplyParser
 
   private
     EMPTY = "".freeze
-    SIGNATURE = '(?m)(--|__|\w-$)|(^(\w+\s*){1,3} ym morf tneS$)'
+    SIGNATURE = '(?m)(--\s*$|__\s*$|\w-$)|(^(\w+\s*){1,3} ym morf tneS$)'
 
     begin
       require 're2'
@@ -146,7 +152,7 @@ class EmailReplyParser
     # Returns nothing.
     def scan_line(line)
       line.chomp!("\n")
-      line.lstrip! unless SIG_REGEX.match(line) 
+      line.lstrip! unless SIG_REGEX.match(line)
 
       # We're looking for leading `>`'s to see if this line is part of a
       # quoted Fragment.

data/test/email_reply_parser_test.rb

@@ -119,6 +119,11 @@ I am currently using the Java HTTP API.\n", reply.fragments[0].to_s
     assert_equal "Outlook with a reply", EmailReplyParser.parse_reply(body)
   end
 
+  def test_parse_out_just_top_for_outlook_with_reply_directly_above_line
+    body = IO.read EMAIL_FIXTURE_PATH.join("email_2_2.txt").to_s
+    assert_equal "Outlook with a reply directly above line", EmailReplyParser.parse_reply(body)
+  end
+
   def test_parse_out_sent_from_iPhone
     body = IO.read EMAIL_FIXTURE_PATH.join("email_iPhone.txt").to_s
     assert_equal "Here is another email", EmailReplyParser.parse_reply(body)
@@ -162,6 +167,11 @@ I am currently using the Java HTTP API.\n", reply.fragments[0].to_s
     assert (Time.now - t0) < 1, "Took too long, upgrade to re2 gem."
   end
 
+  def test_doesnt_remove_signature_delimiter_in_mid_line
+    reply = email(:email_sig_delimiter_in_middle_of_line)
+    assert_equal 1, reply.fragments.size
+  end
+
   def email(name)
     body = IO.read EMAIL_FIXTURE_PATH.join("#{name}.txt").to_s
     EmailReplyParser.read body

data/test/emails/email_2_2.txt

@@ -0,0 +1,10 @@
+Outlook with a reply directly above line
+________________________________________
+From: CRM Comments [crm-comment@example.com]
+Sent: Friday, 23 March 2012 5:08 p.m.
+To: John S. Greene
+Subject: [contact:106] John Greene
+
+A new comment has been added to the Contact named 'John Greene':
+
+I am replying to a comment.

data/test/emails/email_sig_delimiter_in_middle_of_line.txt

@@ -0,0 +1,7 @@
+Hi there!
+
+Stuff happened.
+
+And here is a fix -- this is not a signature.
+
+kthxbai

metadata

@@ -1,14 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: email_reply_parser
 version: !ruby/object:Gem::Version
-  version: 0.5.5
+  version: 0.5.6
+  prerelease: 
 platform: ruby
 authors:
 - Rick Olson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-11 00:00:00.000000000 Z
+date: 2014-05-30 00:00:00.000000000 Z
 dependencies: []
 description: Long description. Maybe copied from the README.
 email: technoweenie@gmail.com
@@ -33,34 +34,37 @@ files:
 - test/emails/email_1_6.txt
 - test/emails/email_1_7.txt
 - test/emails/email_2_1.txt
+- test/emails/email_2_2.txt
 - test/emails/email_BlackBerry.txt
 - test/emails/email_bullets.txt
 - test/emails/email_iPhone.txt
 - test/emails/email_multi_word_sent_from_my_mobile_device.txt
 - test/emails/email_one_is_not_on.txt
 - test/emails/email_sent_from_my_not_signature.txt
+- test/emails/email_sig_delimiter_in_middle_of_line.txt
 - test/emails/pathological.txt
 homepage: http://github.com/github/email_reply_parser
 licenses: []
-metadata: {}
 post_install_message: 
 rdoc_options:
 - --charset=UTF-8
 require_paths:
 - lib
 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: 2.0.3
+rubygems_version: 1.8.23
 signing_key: 
 specification_version: 2
 summary: Short description used in Gem listings.

checksums.yaml

@@ -1,7 +0,0 @@
----
-SHA1:
-  metadata.gz: 7ac6a5b1b44a4c6b58ec03ad6bca58d2bbfca5ab
-  data.tar.gz: a4c485aea71c6fdc5b221c80d7b37189ee7185ff
-SHA512:
-  metadata.gz: 8409fbf234b0c3c8f63ba6cae894f9301b588ca065ce69e802278ef6083f31599698d61f83555e2cd4194abfad50c223358fb5994ccc4315f08a6bb5e879b5eb
-  data.tar.gz: 86c7e2e2ea27d775dc530503687e9ef116d97d612736ec13e08c4077eb631e5e76179a3d739ab6a6e07a8c41d1520ea35cb435c750c2fefd8b17392601914e7d