github-linguist 4.0.3 → 4.2.0

data/lib/linguist/samples.rb

@@ -6,6 +6,7 @@ end
 
 require 'linguist/md5'
 require 'linguist/classifier'
+require 'linguist/shebang'
 
 module Linguist
   # Model for accessing classifier training data.
@@ -52,14 +53,16 @@ module Linguist
               })
             end
           else
+            path = File.join(dirname, filename)
+
             if File.extname(filename) == ""
-              raise "#{File.join(dirname, filename)} is missing an extension, maybe it belongs in filenames/ subdir"
+              raise "#{path} is missing an extension, maybe it belongs in filenames/ subdir"
             end
 
             yield({
-              :path     => File.join(dirname, filename),
+              :path     => path,
               :language => category,
-              :interpreter => File.exist?(filename) ? Linguist.interpreter_from_shebang(File.read(filename)) : nil,
+              :interpreter => Shebang.interpreter(File.read(path)),
               :extname  => File.extname(filename)
             })
           end
@@ -112,40 +115,4 @@ module Linguist
       db
     end
   end
-
-  # 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
-
-      # "python2.6" -> "python"
-      if script =~ /((?:\d+\.?)+)/
-        script.sub! $1, ''
-      end
-
-      # Check for multiline shebang hacks that call `exec`
-      if script == 'sh' &&
-        lines[0...5].any? { |l| l.match(/exec (\w+).+\$0.+\$@/) }
-        script = $1
-      end
-
-      script
-    else
-      nil
-    end
-  end
-
 end

data/lib/linguist/shebang.rb

@@ -0,0 +1,44 @@
+module Linguist
+  class Shebang
+    # Public: Use shebang to detect language of the blob.
+    #
+    # blob               - An object that quacks like a blob.
+    #
+    # Examples
+    #
+    #   Shebang.call(FileBlob.new("path/to/file"))
+    #
+    # Returns an Array with one Language if the blob has a shebang with a valid
+    # interpreter, or empty if there is no shebang.
+    def self.call(blob, _ = nil)
+      Language.find_by_interpreter interpreter(blob.data)
+    end
+
+    # Public: Get the interpreter from the shebang
+    #
+    # Returns a String or nil
+    def self.interpreter(data)
+      lines = data.lines
+      return unless match = /^#! ?(.*)$/.match(lines.first)
+
+      tokens = match[1].split(' ')
+      script = tokens.first.split('/').last
+
+      script = tokens[1] if script == 'env'
+
+      # 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.first(5).any? { |l| l.match(/exec (\w+).+\$0.+\$@/) }
+        script = $1
+      end
+
+      File.basename(script)
+    end
+  end
+end

data/lib/linguist/strategy/filename.rb

@@ -0,0 +1,20 @@
+module Linguist
+  module Strategy
+    # Detects language based on filename and/or extension
+    class Filename
+      def self.call(blob, _)
+        name = blob.name.to_s
+
+        # A bit of an elegant hack. If the file is executable but extensionless,
+        # append a "magic" extension so it can be classified with other
+        # languages that have shebang scripts.
+        extensions = FileBlob.new(name).extensions
+        if extensions.empty? && blob.mode && (blob.mode.to_i(8) & 05) == 05
+          name += ".script!"
+        end
+
+        Language.find_by_filename(name)
+      end
+    end
+  end
+end

data/lib/linguist/vendor.yml

@@ -232,9 +232,6 @@
 # .DS_Store's
 - .[Dd][Ss]_[Ss]tore$
 
-# Mercury --use-subdirs
-- Mercury/
-
 # R packages
 - ^vignettes/
 - ^inst/extdata/

data/lib/linguist/version.rb

@@ -1,3 +1,3 @@
 module Linguist
-  VERSION = "4.0.3"
+  VERSION = "4.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: github-linguist
 version: !ruby/object:Gem::Version
-  version: 4.0.3
+  version: 4.2.0
 platform: ruby
 authors:
 - GitHub
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-11-21 00:00:00.000000000 Z
+date: 2014-12-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: charlock_holmes
@@ -58,14 +58,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.22.0b1
+        version: 0.22.0b4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.22.0b1
+        version: 0.22.0b4
 - !ruby/object:Gem::Dependency
   name: mocha
   requirement: !ruby/object:Gem::Requirement
@@ -147,6 +147,8 @@ files:
 - lib/linguist/repository.rb
 - lib/linguist/samples.json
 - lib/linguist/samples.rb
+- lib/linguist/shebang.rb
+- lib/linguist/strategy/filename.rb
 - lib/linguist/tokenizer.rb
 - lib/linguist/vendor.yml
 - lib/linguist/version.rb