github-linguist 2.10.8 → 2.10.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6f0906667498f0302124bfafe4df703d167e1aa7
-  data.tar.gz: 8b1e758e4b3b18d1a656925248263c74fc9d5b6e
+  metadata.gz: cbb0e1dda522368ab523932eb54c49cd133e80ba
+  data.tar.gz: e76b8b1147c9f5ea2ec415f7178032b84288db2c
 SHA512:
-  metadata.gz: 8b6fac3c2976fde426d9f52bccbefb12a321364ad821f2b6452f05a7b0e0a5892b33dad3a4b5e5dfc26f8f2462f68954e02718995d1fac0442678317a4b52426
-  data.tar.gz: aab80deaa25c0051500426ae08a88ce5920e249de0e82cc53db0da35c07005dac94fc74336c0effad6774be6aa21c80a80a9626f3264054035ef07cb8c6d6298
+  metadata.gz: a7fe49b518c11ad84c9d1c83ab3288c15785189538b716e4cfa33634e6054b5111b1b2d5b3588f7630a2509619a086d910b1ff4b8f5e1e609af9770c46a0abbe
+  data.tar.gz: aa1d301167462211d21e40db3747abfd64510f7555c47d03bc56f499feac13476f9a01a13364545b445a2ec8aa64ae89792bec862c48ab276c03e4d31983d32a

data/bin/linguist

@@ -1,13 +1,22 @@
 #!/usr/bin/env ruby
 
 # linguist — detect language type for a file, or, given a directory, determine language breakdown
-#     usage: linguist <path>
+#     usage: linguist <path> [<--breakdown>]
 
 require 'linguist/file_blob'
 require 'linguist/repository'
 
 path = ARGV[0] || Dir.pwd
 
+# special case if not given a directory but still given the --breakdown option
+if path == "--breakdown"
+  path = Dir.pwd
+  breakdown = true
+end
+
+ARGV.shift
+breakdown = true if ARGV[0] == "--breakdown"
+
 if File.directory?(path)
   repo = Linguist::Repository.from_directory(path)
   repo.languages.sort_by { |_, size| size }.reverse.each do |language, size|
@@ -15,6 +24,13 @@ if File.directory?(path)
     percentage = sprintf '%.2f' % percentage
     puts "%-7s %s" % ["#{percentage}%", language]
   end
+  if breakdown
+    puts
+    file_breakdown = repo.breakdown_by_file
+    file_breakdown.each do |lang, files|
+      puts "#{lang}: #{files}"
+    end
+  end
 elsif File.file?(path)
   blob = Linguist::FileBlob.new(path, Dir.pwd)
   type = if blob.text?

data/lib/linguist/classifier.rb

@@ -83,8 +83,8 @@ module Linguist
       debug_dump_all_tokens(tokens, languages) if verbosity >= 2
 
       languages.each do |language|
-        debug_dump_probabilities(tokens, language) if verbosity >= 1
         scores[language] = tokens_probability(tokens, language) + language_probability(language)
+        debug_dump_probabilities(tokens, language, scores[language]) if verbosity >= 1
       end
 
       scores.sort { |a, b| b[1] <=> a[1] }.map { |score| [score[0], score[1]] }
@@ -130,9 +130,9 @@ module Linguist
         @verbosity ||= (ENV['LINGUIST_DEBUG'] || 0).to_i
       end
 
-      def debug_dump_probabilities(tokens, language)
+      def debug_dump_probabilities(tokens, language, score)
         printf("%10s = %10.3f + %7.3f = %10.3f\n",
-            language, tokens_probability(tokens, language), language_probability(language), scores[language])
+            language, tokens_probability(tokens, language), language_probability(language), score)
       end
 
       # Internal: show a table of probabilities for each <token,language> pair.

data/lib/linguist/heuristics.rb

@@ -14,7 +14,10 @@ module Linguist
     def self.find_by_heuristics(data, languages)
       if active?
         if languages.all? { |l| ["Objective-C", "C++"].include?(l) }
-          disambiguate_h(data, languages)
+          disambiguate_c(data, languages)
+        end
+        if languages.all? { |l| ["Perl", "Prolog"].include?(l) }
+          disambiguate_pl(data, languages)
         end
       end
     end
@@ -23,14 +26,19 @@ module Linguist
     # We want to shortcut look for Objective-C _and_ now C++ too!
     #
     # Returns an array of Languages or []
-    # TODO rename this method as we're not strictly disambiguating between .h files here.
-    def self.disambiguate_h(data, languages)
+    def self.disambiguate_c(data, languages)
       matches = []
       matches << Language["Objective-C"] if data.include?("@interface")
       matches << Language["C++"] if data.include?("#include <cstdint>")
       matches
     end
 
+    def self_disambiguate_pl(data, languages)
+      matches = []
+      matches << Language["Prolog"] if data.include?(":-")
+      matches
+    end
+
     def self.active?
       !!ACTIVE
     end

data/lib/linguist/languages.yml

@@ -839,6 +839,7 @@ JavaScript:
   - .jsm
   - .jss
   - .jsx
+  - .njs
   - .pac
   - .sjs
   - .ssjs
@@ -947,6 +948,8 @@ Lua:
   extensions:
   - .nse
   - .rbxs
+  interpreters:
+  - lua
 
 M:
   type: programming

data/lib/linguist/repository.rb

@@ -29,6 +29,7 @@ module Linguist
       @computed_stats = false
       @language = @size = nil
       @sizes = Hash.new { 0 }
+      @file_breakdown = Hash.new { |h,k| h[k] = Array.new }
     end
 
     # Public: Returns a breakdown of language stats.
@@ -60,6 +61,12 @@ module Linguist
       @size
     end
 
+    # Public: Return the language breakdown of this repository by file
+    def breakdown_by_file
+      compute_stats
+      @file_breakdown
+    end
+
     # Internal: Compute language breakdown for each blob in the Repository.
     #
     # Returns nothing
@@ -75,6 +82,10 @@ module Linguist
 
         # Only include programming languages and acceptable markup languages
         if blob.language.type == :programming || Language.detectable_markup.include?(blob.language.name)
+
+          # Build up the per-file breakdown stats
+          @file_breakdown[blob.language.group.name] << blob.name
+
           @sizes[blob.language.group] += blob.size
         end
       end

data/lib/linguist/vendor.yml

@@ -27,6 +27,9 @@
 # Node dependencies
 - node_modules/
 
+# Bower Components
+- bower_components/
+
 # Erlang bundles
 - ^rebar$
 
@@ -82,6 +85,9 @@
 - (^|/)shCore\.js$
 - (^|/)shLegacy\.js$
 
+# AngularJS
+- (^|/)angular([^.]*)(\.min)?\.js$
+
 ## Python ##
 
 # django

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: github-linguist
 version: !ruby/object:Gem::Version
-  version: 2.10.8
+  version: 2.10.9
 platform: ruby
 authors:
 - GitHub
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-27 00:00:00.000000000 Z
+date: 2013-12-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: charlock_holmes
@@ -122,7 +122,9 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: 
+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.
 email: 
 executables:
 - linguist
@@ -146,7 +148,8 @@ files:
 - lib/linguist.rb
 - bin/linguist
 homepage: https://github.com/github/linguist
-licenses: []
+licenses:
+- MIT
 metadata: {}
 post_install_message: 
 rdoc_options: []