Merge remote-tracking branch 'origin/master' into filename-matches-multiple-langages

* origin/master:
  Allow mime-types 2.x to be used with Linguist
  Upgrade to rugged 0.22.0b1
  Mention that languages need to be quite popular
  fix vendor/cache
  Gemfile.lock is nolonger considered generated
  Tests for BlobHelper#empty?
  remove reference to empty.js
  Remove more empty samples
  Bail earlier if the file is empty.
  Moving comments
  Use heuristics earlier to inform the rest of the classification process
  Removing inconsistency of `find_by_heuristics` (was sometimes returning nil and sometimes returning and empty array)
  Removing unused array of candidate languages.
  Reworking most heuristics to only return one match

lib/linguist/blob_helper.rb

@@ -146,6 +146,13 @@ module Linguist
       end
     end
 
+    # Public: Is the blob empty?
+    #
+    # Return true or false
+    def empty?
+      data.nil? || data == ""
+    end
+
     # Public: Is the blob text?
     #
     # Return true or false

lib/linguist/generated.rb

@@ -51,26 +51,25 @@ module Linguist
     #
     # Return true or false
     def generated?
-      name == 'Gemfile.lock' ||
-        minified_files? ||
-        compiled_coffeescript? ||
-        xcode_file? ||
-        generated_parser? ||
-        generated_net_docfile? ||
-        generated_net_designer_file? ||
-        generated_postscript? ||
-        generated_protocol_buffer? ||
-        generated_jni_header? ||
-        composer_lock? ||
-        node_modules? ||
-        godeps? ||
-        vcr_cassette? ||
-        generated_by_zephir?
+      minified_files? ||
+      compiled_coffeescript? ||
+      xcode_file? ||
+      generated_parser? ||
+      generated_net_docfile? ||
+      generated_net_designer_file? ||
+      generated_postscript? ||
+      generated_protocol_buffer? ||
+      generated_jni_header? ||
+      composer_lock? ||
+      node_modules? ||
+      godeps? ||
+      vcr_cassette? ||
+      generated_by_zephir?
     end
 
     # Internal: Is the blob an Xcode file?
     #
-    # Generated if the file extension is an Xcode 
+    # Generated if the file extension is an Xcode
     # file extension.
     #
     # Returns true of false.
@@ -265,4 +264,3 @@ module Linguist
     end
   end
 end
-

lib/linguist/heuristics.rb

@@ -13,26 +13,28 @@ module Linguist
     # Returns an array of Languages or []
     def self.find_by_heuristics(data, languages)
       if active?
+        result = []
+
         if languages.all? { |l| ["Perl", "Prolog"].include?(l) }
-          result = disambiguate_pl(data, languages)
+          result = disambiguate_pl(data)
         end
         if languages.all? { |l| ["ECL", "Prolog"].include?(l) }
-          result = disambiguate_ecl(data, languages)
+          result = disambiguate_ecl(data)
         end
         if languages.all? { |l| ["IDL", "Prolog"].include?(l) }
-          result = disambiguate_pro(data, languages)
+          result = disambiguate_pro(data)
         end
         if languages.all? { |l| ["Common Lisp", "OpenCL"].include?(l) }
-          result = disambiguate_cl(data, languages)
+          result = disambiguate_cl(data)
         end
         if languages.all? { |l| ["Hack", "PHP"].include?(l) }
-          result = disambiguate_hack(data, languages)
+          result = disambiguate_hack(data)
         end
         if languages.all? { |l| ["Scala", "SuperCollider"].include?(l) }
-          result = disambiguate_sc(data, languages)
+          result = disambiguate_sc(data)
         end
         if languages.all? { |l| ["AsciiDoc", "AGS Script"].include?(l) }
-          result = disambiguate_asc(data, languages)
+          result = disambiguate_asc(data)
         end
         return result
       end
@@ -42,28 +44,37 @@ module Linguist
     # We want to shortcut look for Objective-C _and_ now C++ too!
     #
     # Returns an array of Languages or []
-    def self.disambiguate_c(data, languages)
+    def self.disambiguate_c(data)
       matches = []
-      matches << Language["Objective-C"] if data.include?("@interface")
-      matches << Language["C++"] if data.include?("#include <cstdint>")
+      if data.include?("@interface")
+        matches << Language["Objective-C"]
+      elsif data.include?("#include <cstdint>")
+        matches << Language["C++"]
+      end
       matches
     end
 
-    def self.disambiguate_pl(data, languages)
+    def self.disambiguate_pl(data)
       matches = []
-      matches << Language["Prolog"] if data.include?(":-")
-      matches << Language["Perl"] if data.include?("use strict")
+      if data.include?("use strict")
+        matches << Language["Perl"]
+      elsif data.include?(":-")
+        matches << Language["Prolog"]
+      end
       matches
     end
 
-    def self.disambiguate_ecl(data, languages)
+    def self.disambiguate_ecl(data)
       matches = []
-      matches << Language["Prolog"] if data.include?(":-")
-      matches << Language["ECL"] if data.include?(":=")
+      if data.include?(":-")
+        matches << Language["Prolog"]
+      elsif data.include?(":=")
+        matches << Language["ECL"]
+      end
       matches
     end
 
-    def self.disambiguate_pro(data, languages)
+    def self.disambiguate_pro(data)
       matches = []
       if (data.include?(":-"))
         matches << Language["Prolog"]
@@ -73,7 +84,7 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_ts(data, languages)
+    def self.disambiguate_ts(data)
       matches = []
       if (data.include?("</translation>"))
         matches << Language["XML"]
@@ -83,21 +94,24 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_cl(data, languages)
+    def self.disambiguate_cl(data)
       matches = []
-      matches << Language["Common Lisp"] if data.include?("(defun ")
-      matches << Language["OpenCL"] if /\/\* |\/\/ |^\}/.match(data)
+      if data.include?("(defun ")
+        matches << Language["Common Lisp"]
+      elsif /\/\* |\/\/ |^\}/.match(data)
+        matches << Language["OpenCL"]
+      end
       matches
     end
 
-    def self.disambiguate_r(data, languages)
+    def self.disambiguate_r(data)
       matches = []
       matches << Language["Rebol"] if /\bRebol\b/i.match(data)
       matches << Language["R"] if data.include?("<-")
       matches
     end
 
-    def self.disambiguate_hack(data, languages)
+    def self.disambiguate_hack(data)
       matches = []
       if data.include?("<?hh")
         matches << Language["Hack"]
@@ -107,7 +121,7 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_sc(data, languages)
+    def self.disambiguate_sc(data)
       matches = []
       if (/\^(this|super)\./.match(data) || /^\s*(\+|\*)\s*\w+\s*{/.match(data) || /^\s*~\w+\s*=\./.match(data))
         matches << Language["SuperCollider"]
@@ -118,7 +132,7 @@ module Linguist
       matches
     end
 
-    def self.disambiguate_asc(data, languages)
+    def self.disambiguate_asc(data)
       matches = []
       matches << Language["AsciiDoc"] if /^=+(\s|\n)/.match(data)
       matches

lib/linguist/language.rb

@@ -100,12 +100,8 @@ module Linguist
     def self.detect(blob)
       name = blob.name.to_s
 
-      # Check if the blob is possibly binary and bail early; this is a cheap
-      # test that uses the extension name to guess a binary binary mime type.
-      #
-      # We'll perform a more comprehensive test later which actually involves
-      # looking for binary characters in the blob
-      return nil if blob.likely_binary? || blob.binary?
+      # Bail early if the blob is binary or empty.
+      return nil if blob.likely_binary? || blob.binary? || blob.empty?
 
       # A bit of an elegant hack. If the file is executable but extensionless,
       # append a "magic" extension so it can be classified with other
@@ -124,16 +120,18 @@ module Linguist
       if possible_languages.length > 1
         data = blob.data
         possible_language_names = possible_languages.map(&:name)
+        heuristic_languages = Heuristics.find_by_heuristics(data, possible_language_names)
+
+        if heuristic_languages.size > 1
+          possible_language_names = heuristic_languages.map(&:name)
+        end
 
-        # Don't bother with binary contents or an empty file
-        if data.nil? || data == ""
-          nil
         # Check if there's a shebang line and use that as authoritative
-        elsif (result = find_by_shebang(data)) && !result.empty?
+        if (result = find_by_shebang(data)) && !result.empty?
           result.first
         # No shebang. Still more work to do. Try to find it with our heuristics.
-        elsif (determined = Heuristics.find_by_heuristics(data, possible_language_names)) && !determined.empty?
-          determined.first
+        elsif heuristic_languages.size == 1
+          heuristic_languages.first
         # Lastly, fall back to the probabilistic classifier.
         elsif classified = Classifier.classify(Samples.cache, data, possible_language_names).first
           # Return the actual Language object based of the string language name (i.e., first element of `#classify`)