Merge pull request #247 from github/check-size-first

When testing if a blob is indexable or safe to colorize, check size first

github-linguist.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name    = 'github-linguist'
-  s.version = '2.3.1'
+  s.version = '2.3.2'
   s.summary = "GitHub Language detection"
 
   s.authors = "GitHub"
@@ -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'

lib/linguist/blob_helper.rb

@@ -160,7 +160,7 @@ module Linguist
     #
     # Return true or false
     def safe_to_colorize?
-      text? && !large? && !high_ratio_of_long_lines?
+      !large? && text? && !high_ratio_of_long_lines?
     end
 
     # Internal: Does the blob have a ratio of long lines?
@@ -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

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