Extract strategies for detecting the language

lib/linguist/heuristics.rb

@@ -3,6 +3,10 @@ module Linguist
   class Heuristics
     ACTIVE = true
 
+    def self.call(blob, languages)
+      find_by_heuristics(blob.data, langauges)
+    end
+
     # Public: Given an array of String language names,
     # apply heuristics against the given data and return an array
     # of matching languages, or nil.

lib/linguist/language.rb

@@ -93,6 +93,17 @@ module Linguist
     end
 
     require 'linguist/strategy/filename'
+    require 'linguist/strategy/shebang'
+    require 'linguist/strategy/classifier'
+    STRATEGIES = [
+      Linguist::Strategy::Filename,
+      # Don't bother with binary contents or an empty file
+      lambda {|blob, langauges| [] if blob.data.nil? || blob.data == "" },
+      # Check if there's a shebang line and use that as authoritative
+      Linguist::Strategy::Shebang,
+      Linguist::Heuristics,
+      Linguist::Strategy::Classifier
+    ]
 
     # Public: Detects the Language of the blob.
     #
@@ -101,40 +112,20 @@ module Linguist
     #
     # Returns Language or nil.
     def self.detect(blob)
-      # Check if the blob is possibly binary and bail early; this is a cheap
+      # Check if the blob is possibly binary and bail early.
-      # 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?
 
-      possible_languages = Linguist::Strategy::Filename.new.call(blob)
+      STRATEGIES.reduce([]) do |languages, strategy|
-
+        if candidates = strategy.call(blob, languages)
-      # If there is more than one possible language with that extension (or no
+          if candidates.size > 1
-      # extension at all, in the case of extensionless scripts), we need to continue
+            candidates
-      # our detection work
+          else
-      if possible_languages.length > 1
+            break candidates
-        data = blob.data
+          end
-        possible_language_names = possible_languages.map(&:name)
+        else
-
+          languages
-        # 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?
-          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
-        # 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`)
-          Language[classified[0]]
         end
-      else
+      end.first
-        # Simplest and most common case, we can just return the one match based on extension
-        possible_languages.first
-      end
     end
 
     # Public: Get all Languages

lib/linguist/strategy/classifier.rb

@@ -0,0 +1,12 @@
+module Linguist
+  module Strategy
+    class Classifier
+      def self.call(blob, languages)
+        Linguist::Classifier.classify(Samples.cache, blob.data, possible_language_names).map do |name|
+          # Return the actual Language object based of the string language name (i.e., first element of `#classify`)
+          Language[name]
+        end
+      end
+    end
+  end
+end

lib/linguist/strategy/filename.rb

@@ -1,7 +1,7 @@
 module Linguist
   module Strategy
     class Filename
-      def call(blob)
+      def self.call(blob, _)
         name = blob.name.to_s
 
         # A bit of an elegant hack. If the file is executable but extensionless,
@@ -13,7 +13,7 @@ module Linguist
         end
 
         # First try to find languages that match based on filename.
-        possible_languages = Language.find_by_filename(name)
+        Language.find_by_filename(name)
       end
     end
   end

lib/linguist/strategy/shebang.rb

@@ -0,0 +1,9 @@
+module Linguist
+  module Strategy
+    class Shebang
+      def self.call(blob, _)
+        Language.find_by_shebang(blob.data)
+      end
+    end
+  end
+end