consolidate shebang logic

lib/linguist.rb

@@ -4,4 +4,5 @@ require 'linguist/heuristics'
 require 'linguist/language'
 require 'linguist/repository'
 require 'linguist/samples'
+require 'linguist/shebang'
 require 'linguist/version'

lib/linguist/language.rb

@@ -11,7 +11,7 @@ require 'linguist/samples'
 require 'linguist/file_blob'
 require 'linguist/blob_helper'
 require 'linguist/strategy/filename'
-require 'linguist/strategy/shebang'
+require 'linguist/shebang'
 
 module Linguist
   # Language names that are recognizable by GitHub. Defined languages
@@ -95,7 +95,7 @@ module Linguist
 
     STRATEGIES = [
       Linguist::Strategy::Filename,
-      Linguist::Strategy::Shebang,
+      Linguist::Shebang,
       Linguist::Heuristics,
       Linguist::Classifier
     ]
@@ -213,6 +213,21 @@ module Linguist
       @interpreter_index[Linguist.interpreter_from_shebang(data)]
     end
 
+    # Public: Look up Languages by interpreter.
+    #
+    # interpreter - String of interpreter name
+    #
+    # Examples
+    #
+    #   Language.find_by_interpreter("bash")
+    #   # => [#<Language name="Bash">]
+    #
+    # Returns the matching Language
+    def self.find_by_interpreter(interpreter)
+      @interpreter_index[interpreter]
+    end
+
+
     # Public: Look up Language by its name or lexer.
     #
     # name - The String name of the Language

lib/linguist/samples.rb

@@ -115,40 +115,9 @@ module Linguist
     end
   end
 
-  # Used to retrieve the interpreter from the shebang line of a file's
-  # data.
+  # Used to retrieve the interpreter from the shebang line of a file's data.
   def self.interpreter_from_shebang(data)
-    lines = data.lines.to_a
-
-    if lines.any? && (match = lines[0].match(/(.+)\n?/)) && (bang = match[0]) =~ /^#!/
-      bang.sub!(/^#! /, '#!')
-      tokens = bang.split(' ')
-      pieces = tokens.first.split('/')
-
-      if pieces.size > 1
-        script = pieces.last
-      else
-        script = pieces.first.sub('#!', '')
-      end
-
-      script = script == 'env' ? tokens[1] : script
-
-      # If script has an invalid shebang, we might get here
-      return unless script
-
-      # "python2.6" -> "python2"
-      script.sub! $1, '' if script =~ /(\.\d+)$/
-
-      # Check for multiline shebang hacks that call `exec`
-      if script == 'sh' &&
-        lines[0...5].any? { |l| l.match(/exec (\w+).+\$0.+\$@/) }
-        script = $1
-      end
-      
-      File.basename(script)
-    else
-      nil
-    end
+    Shebang.new(data).interpreter
   end
 
 end

lib/linguist/shebang.rb

@@ -0,0 +1,49 @@
+module Linguist
+  # Check if there's a shebang line and use that as authoritative
+  class Shebang
+    def self.call(blob, _)
+      Language.find_by_interpreter(new(blob.data).interpreter)
+    end
+
+    attr_reader :data
+
+    def initialize(data)
+      @data = data
+    end
+
+    def interpreter
+      lines = data.lines.to_a
+
+      if lines.any? && (match = lines[0].match(/(.+)\n?/)) && (bang = match[0]) =~ /^#!/
+        bang.sub!(/^#! /, '#!')
+        tokens = bang.split(' ')
+        pieces = tokens.first.split('/')
+
+        if pieces.size > 1
+          script = pieces.last
+        else
+          script = pieces.first.sub('#!', '')
+        end
+
+        script = script == 'env' ? tokens[1] : script
+
+        # If script has an invalid shebang, we might get here
+        return unless script
+
+        # "python2.6" -> "python2"
+        script.sub! $1, '' if script =~ /(\.\d+)$/
+
+        # Check for multiline shebang hacks that call `exec`
+        if script == 'sh' &&
+          lines[0...5].any? { |l| l.match(/exec (\w+).+\$0.+\$@/) }
+          script = $1
+        end
+
+        File.basename(script)
+      else
+        nil
+      end
+
+    end
+  end
+end

lib/linguist/strategy/shebang.rb

@@ -1,10 +0,0 @@
-module Linguist
-  module Strategy
-    # Check if there's a shebang line and use that as authoritative
-    class Shebang
-      def self.call(blob, _)
-        Language.find_by_shebang(blob.data)
-      end
-    end
-  end
-end