From 872dabdbf8117b35dd05f287ba507be3476f3eb9 Mon Sep 17 00:00:00 2001
From: Joel McCoy <joelmccoy@gmail.com>
Date: Wed, 30 Apr 2014 20:30:54 -0400
Subject: [PATCH] Support consuming tweets.csv from official twitter archives

---
 lib/twitter_ebooks/model.rb   | 6 ++++++
 lib/twitter_ebooks/version.rb | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/lib/twitter_ebooks/model.rb b/lib/twitter_ebooks/model.rb
index 9924584..96674d2 100644
--- a/lib/twitter_ebooks/model.rb
+++ b/lib/twitter_ebooks/model.rb
@@ -4,6 +4,7 @@
 require 'json'
 require 'set'
 require 'digest/md5'
+require 'csv'
 
 module Ebooks
   class Model
@@ -26,6 +27,11 @@ module Ebooks
         lines = JSON.parse(content, symbolize_names: true).map do |tweet|
           tweet[:text]
         end
+      elsif path.split('.')[-1] == "csv"
+        log "Reading CSV corpus from #{path}"
+        lines = CSV.read(path).drop(1).map do |tweet|
+          tweet[5]
+        end
       else
         log "Reading plaintext corpus from #{path}"
         lines = content.split("\n")
diff --git a/lib/twitter_ebooks/version.rb b/lib/twitter_ebooks/version.rb
index c8da643..ab9a31b 100644
--- a/lib/twitter_ebooks/version.rb
+++ b/lib/twitter_ebooks/version.rb
@@ -1,3 +1,3 @@
 module Ebooks
-  VERSION = "2.2.3"
+  VERSION = "2.2.4"
 end