github-linguist 4.5.4 → 4.5.5

data/lib/linguist/samples.rb

@@ -50,16 +50,13 @@ module Linguist
             end
           else
             path = File.join(dirname, filename)
-
-            if File.extname(filename) == ""
-              raise "#{path} is missing an extension, maybe it belongs in filenames/ subdir"
-            end
+            extname = File.extname(filename)
 
             yield({
               :path     => path,
               :language => category,
               :interpreter => Shebang.interpreter(File.read(path)),
-              :extname  => File.extname(filename)
+              :extname  => extname.empty? ? nil : extname
             })
           end
         end

data/lib/linguist/shebang.rb

@@ -23,17 +23,20 @@ module Linguist
       # First line must start with #!
       return unless shebang && shebang.start_with?("#!")
 
-      # Get the parts of the shebang without the #!
-      tokens = shebang.sub(/^#!\s*/, '').strip.split(' ')
+      s = StringScanner.new(shebang)
 
       # There was nothing after the #!
-      return if tokens.empty?
+      return unless path = s.scan(/^#!\s*\S+/)
 
-      # Get the name of the interpreter
-      script = File.basename(tokens.first)
+      # Keep going
+      script = path.split('/').last
 
-      # Get next argument if interpreter was /usr/bin/env
-      script = tokens[1] if script == 'env'
+      # if /usr/bin/env type shebang then walk the string
+      if script == 'env'
+        s.scan(/\s+/)
+        s.scan(/.*=[^\s]+\s+/) # skip over variable arguments e.g. foo=bar
+        script = s.scan(/\S+/)
+      end
 
       # Interpreter was /usr/bin/env with no arguments
       return unless script
@@ -41,6 +44,9 @@ module Linguist
       # "python2.6" -> "python2"
       script.sub! /(\.\d+)$/, ''
 
+      # #! perl -> perl
+      script.sub! /^#!\s*/, ''
+
       # Check for multiline shebang hacks that call `exec`
       if script == 'sh' &&
         data.lines.first(5).any? { |l| l.match(/exec (\w+).+\$0.+\$@/) }

data/lib/linguist/strategy/filename.rb

@@ -3,17 +3,7 @@ module Linguist
     # 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)
+        Language.find_by_filename(blob.name.to_s)
       end
     end
   end

data/lib/linguist/strategy/modeline.rb

@@ -2,7 +2,7 @@ module Linguist
   module Strategy
     class Modeline
       EmacsModeline = /-\*-\s*(?:(?!mode)[\w-]+\s*:\s*(?:[\w+-]+)\s*;?\s*)*(?:mode\s*:)?\s*([\w+-]+)\s*(?:;\s*(?!mode)[\w-]+\s*:\s*[\w+-]+\s*)*;?\s*-\*-/i
-      VimModeline = /\/\*\s*vim:\s*set\s*(?:ft|filetype)=(\w+):\s*\*\//i
+      VimModeline = /vim:\s*set\s*(?:ft|filetype)=(\w+):/i
 
       # Public: Detects language based on Vim and Emacs modelines
       #

data/lib/linguist/tokenizer.rb

@@ -22,8 +22,10 @@ module Linguist
     # Start state on token, ignore anything till the next newline
     SINGLE_LINE_COMMENTS = [
       '//', # C
+      '--', # Ada, Haskell, AppleScript
       '#',  # Ruby
       '%',  # Tex
+      '"',  # Vim
     ]
 
     # Start state on opening token, ignore anything until the closing
@@ -130,6 +132,9 @@ module Linguist
     #   extract_shebang("#!/usr/bin/env node")
     #   # => "node"
     #
+    #   extract_shebang("#!/usr/bin/env A=B foo=bar awk -f")
+    #   # => "awk"
+    #
     # Returns String token or nil it couldn't be parsed.
     def extract_shebang(data)
       s = StringScanner.new(data)
@@ -138,6 +143,7 @@ module Linguist
         script = path.split('/').last
         if script == 'env'
           s.scan(/\s+/)
+          s.scan(/.*=[^\s]+\s+/)
           script = s.scan(/\S+/)
         end
         script = script[/[^\d]+/, 0] if script

data/lib/linguist/version.rb

@@ -1,3 +1,3 @@
 module Linguist
-  VERSION = "4.5.4"
+  VERSION = "4.5.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: github-linguist
 version: !ruby/object:Gem::Version
-  version: 4.5.4
+  version: 4.5.5
 platform: ruby
 authors:
 - GitHub
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-01 00:00:00.000000000 Z
+date: 2015-05-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: charlock_holmes
@@ -136,6 +136,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: color-proximity
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.2.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.2.1
 description: We use this library at GitHub to detect blob languages, highlight code,
   ignore binary files, suppress generated files in diffs, and generate language breakdown
   graphs.