From e415a1351bf3e7eff0a33574400fa89c0941d9bf Mon Sep 17 00:00:00 2001
From: "Scott J. Goldman" <scottjg@github.com>
Date: Fri, 31 Aug 2012 22:47:19 -0700
Subject: [PATCH] When testing if a blob is indexable, check size first

Otherwise, charlock_holmes will allocate another large binary
buffer for testing the encoding, which is a problem if the binary
blob is many hundreds of MB large. It'll just fail and crash ruby.
---
 github-linguist.gemspec     | 1 +
 lib/linguist/blob_helper.rb | 6 +++---
 test/test_blob.rb           | 7 +++++++
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/github-linguist.gemspec b/github-linguist.gemspec
index 246824ac..3b1e3701 100644
--- a/github-linguist.gemspec
+++ b/github-linguist.gemspec
@@ -12,6 +12,7 @@ Gem::Specification.new do |s|
   s.add_dependency 'escape_utils',    '~> 0.2.3'
   s.add_dependency 'mime-types',      '~> 1.19'
   s.add_dependency 'pygments.rb',     '>= 0.2.13'
+  s.add_development_dependency 'mocha'
   s.add_development_dependency 'json'
   s.add_development_dependency 'rake'
   s.add_development_dependency 'yajl-ruby'
diff --git a/lib/linguist/blob_helper.rb b/lib/linguist/blob_helper.rb
index b2d72f11..fbbaff9c 100644
--- a/lib/linguist/blob_helper.rb
+++ b/lib/linguist/blob_helper.rb
@@ -250,7 +250,9 @@ module Linguist
     #
     # Return true or false
     def indexable?
-      if binary?
+      if size > 100 * 1024
+        false
+      elsif binary?
         false
       elsif extname == '.txt'
         true
@@ -260,8 +262,6 @@ module Linguist
         false
       elsif generated?
         false
-      elsif size > 100 * 1024
-        false
       else
         true
       end
diff --git a/test/test_blob.rb b/test/test_blob.rb
index 0832b8fd..17e9ef8c 100644
--- a/test/test_blob.rb
+++ b/test/test_blob.rb
@@ -2,6 +2,7 @@ require 'linguist/file_blob'
 require 'linguist/samples'
 
 require 'test/unit'
+require 'mocha'
 require 'mime/types'
 require 'pygments'
 
@@ -261,6 +262,12 @@ class TestBlob < Test::Unit::TestCase
     assert !blob("Text/dump.sql").indexable?
     assert !blob("Binary/github.po").indexable?
     assert !blob("Binary/linguist.gem").indexable?
+
+    # large binary blobs should fail on size check first, not call 
+    # into charlock_holmes and alloc big buffers for testing encoding
+    b = blob("Binary/octocat.ai")
+    b.expects(:binary?).never
+    assert !b.indexable?
   end
 
   def test_language