From fca6a9a9e13913db01ebc75e5cd322f780468a0e Mon Sep 17 00:00:00 2001
From: Joshua Peek <josh@joshpeek.com>
Date: Mon, 23 Jul 2012 16:19:56 -0500
Subject: [PATCH] Fix md5 nesting

---
 lib/linguist/md5.rb       | 36 ++++++++++++------------------------
 lib/linguist/samples.json |  2 +-
 test/test_md5.rb          | 12 ++++++------
 3 files changed, 19 insertions(+), 31 deletions(-)

diff --git a/lib/linguist/md5.rb b/lib/linguist/md5.rb
index 4860bcda..0b43fd8a 100644
--- a/lib/linguist/md5.rb
+++ b/lib/linguist/md5.rb
@@ -11,40 +11,28 @@ module Linguist
     # Returns String hex digest
     def self.hexdigest(obj)
       digest = Digest::MD5.new
-      digest_strings(obj).each { |e| digest.update(e) }
-      digest.hexdigest
-    end
 
-    # Internal: Get String representations for digest.
-    #
-    # obj - Object to digest
-    #
-    # Returns an Array of Strings.
-    def self.digest_strings(obj)
       case obj
-      when String
-        ["#{obj.class}", "#{obj}"]
-      when Symbol
-        ["#{obj.class}", "#{obj}"]
-      when Integer
-        ["#{obj.class}", "#{obj}"]
+      when String, Symbol, Integer
+        digest.update "#{obj.class}"
+        digest.update "#{obj}"
       when TrueClass, FalseClass, NilClass
-        ["#{obj.class}"]
+        digest.update "#{obj.class}"
       when Array
-        r = ["#{obj.class}"]
-        obj.each do |e|
-          r.concat(digest_strings(e))
+        digest.update "#{obj.class}"
+        for e in obj
+          digest.update(hexdigest(e))
         end
-        r
       when Hash
-        r = ["#{obj.class}"]
-        obj.map { |k, v| digest_strings([k, v]) }.sort.each do |e|
-          r.concat(digest_strings(e))
+        digest.update "#{obj.class}"
+        for e in obj.map { |(k, v)| hexdigest([k, v]) }.sort
+          digest.update(e)
         end
-        r
       else
         raise TypeError, "can't convert #{obj.inspect} into String"
       end
+
+      digest.hexdigest
     end
   end
 end
diff --git a/lib/linguist/samples.json b/lib/linguist/samples.json
index 942f4d62..831615d8 100644
--- a/lib/linguist/samples.json
+++ b/lib/linguist/samples.json
@@ -20099,5 +20099,5 @@
     "XSLT": 1,
     "YAML": 1
   },
-  "md5": "a0ebeafa2f804284407990bfedb1c7ee"
+  "md5": "5e73a20c894bdef413ab8409f9ba6406"
 }
\ No newline at end of file
diff --git a/test/test_md5.rb b/test/test_md5.rb
index 789e8b36..6019fcf5 100644
--- a/test/test_md5.rb
+++ b/test/test_md5.rb
@@ -40,16 +40,16 @@ class TestMD5 < Test::Unit::TestCase
 
   def test_hexdigest_array
     assert_equal "4410ec34d9e6c1a68100ca0ce033fb17", MD5.hexdigest([])
-    assert_equal "a57e31bc7bce57d04dd6a07e74fd0d88", MD5.hexdigest([1])
-    assert_equal "ecbda6354c6e0370df33d43ce14701f4", MD5.hexdigest([1, 2])
-    assert_equal "5c42a2601d344f359017e2b76390e2cc", MD5.hexdigest([1, 2, 3])
-    assert_equal "c1816755a379d2b32289647ad1870d12", MD5.hexdigest([1, 2, [3]])
+    assert_equal "759f28c1d0c20c22e79c91d339855d95", MD5.hexdigest([1])
+    assert_equal "9efe07b352dd94cd1cdc9d1a8d054f8f", MD5.hexdigest([1, 2])
+    assert_equal "60b1ef7201404f20c3d12f47499c3a1f", MD5.hexdigest([1, 2, 3])
+    assert_equal "2f82cdc166616208077ff1dd0a8faeff", MD5.hexdigest([1, 2, [3]])
   end
 
   def test_hexdigest_hash
     assert_equal "fae8a9257e154175da4193dbf6552ef6", MD5.hexdigest({})
-    assert_equal "b3646d6d84a803baa5ee2e5354057a65", MD5.hexdigest({:a => 1})
-    assert_equal "92c08085470d42ca0d33dd3ec5a8e098", MD5.hexdigest({:b => 2})
+    assert_equal "868ee214faf277829a85667cf332749f", MD5.hexdigest({:a => 1})
+    assert_equal "fa9df957c2b26de6fcca9d062ea8701e", MD5.hexdigest({:b => 2})
 
     assert_not_equal MD5.hexdigest([:b, 2]), MD5.hexdigest({:b => 2})