Merge pull request #2097 from github/detect-all-markup

Detect all markup languages when computing language statistics

lib/linguist/blob_helper.rb

@@ -236,6 +236,21 @@ module Linguist
       name =~ VendoredRegexp ? true : false
     end
 
+    documentation_paths = YAML.load_file(File.expand_path("../documentation.yml", __FILE__))
+    DocumentationRegexp = Regexp.new(documentation_paths.join('|'))
+
+    # Public: Is the blob in a documentation directory?
+    #
+    # Documentation files are ignored by language statistics.
+    #
+    # See "documentation.yml" for a list of documentation conventions that match
+    # this pattern.
+    #
+    # Return true or false
+    def documentation?
+      name =~ DocumentationRegexp ? true : false
+    end
+
     # Public: Get each line of data
     #
     # Requires Blob#data
@@ -317,5 +332,15 @@ module Linguist
     def tm_scope
       language && language.tm_scope
     end
+
+    DETECTABLE_TYPES = [:programming, :markup].freeze
+
+    # Internal: Should this blob be included in repository language statistics?
+    def include_in_language_stats?
+      !vendored? &&
+      !documentation? &&
+      !generated? &&
+      language && DETECTABLE_TYPES.include?(language.type)
+    end
   end
 end

lib/linguist/documentation.yml

@@ -0,0 +1,19 @@
+# Documentation files and directories are excluded from language
+# statistics.
+#
+# Lines in this file are Regexps that are matched against the file
+# pathname.
+#
+# Please add additional test coverage to
+# `test/test_blob.rb#test_documentation` if you make any changes.
+
+## Documentation Conventions ##
+
+- ^docs?/
+- ^Documentation/
+
+- (^|/)CONTRIBUTING(\.|$)
+- (^|/)COPYING(\.|$)
+- (^|/)INSTALL(\.|$)
+- (^|/)LICEN[CS]E(\.|$)
+- (^|/)README(\.|$)

lib/linguist/language.rb

@@ -32,13 +32,6 @@ module Linguist
     # Valid Languages types
     TYPES = [:data, :markup, :programming, :prose]
 
-    # Names of non-programming languages that we will still detect
-    #
-    # Returns an array
-    def self.detectable_markup
-      ["CSS", "Less", "Sass", "SCSS", "Stylus", "TeX"]
-    end
-
     # Detect languages by a specific type
     #
     # type - A symbol that exists within TYPES

lib/linguist/languages.yml

@@ -439,6 +439,8 @@ COBOL:
   ace_mode: cobol
 
 CSS:
+  type: markup
+  tm_scope: source.css
   ace_mode: css
   color: "#563d7c"
   extensions:
@@ -1173,6 +1175,7 @@ HTML:
   type: markup
   tm_scope: text.html.basic
   ace_mode: html
+  color: "#e44b23"
   aliases:
   - xhtml
   extensions:
@@ -2684,6 +2687,13 @@ STON:
   tm_scope: source.smalltalk
   ace_mode: text
 
+SVG:
+  type: data
+  extensions:
+  - .svg
+  tm_scope: text.xml
+  ace_mode: xml
+
 Sage:
   type: programming
   group: Python
@@ -3199,7 +3209,6 @@ XML:
   - .srdf
   - .stTheme
   - .sublime-snippet
-  - .svg
   - .targets
   - .tmCommand
   - .tmLanguage

lib/linguist/lazy_blob.rb

@@ -4,7 +4,7 @@ require 'rugged'
 
 module Linguist
   class LazyBlob
-    GIT_ATTR = ['linguist-language', 'linguist-vendored']
+    GIT_ATTR = ['linguist-documentation', 'linguist-language', 'linguist-vendored']
     GIT_ATTR_OPTS = { :priority => [:index], :skip_system => true }
     GIT_ATTR_FLAGS = Rugged::Repository::Attributes.parse_opts(GIT_ATTR_OPTS)
 
@@ -37,6 +37,14 @@ module Linguist
       end
     end
 
+    def documentation?
+      if attr = git_attributes['linguist-documentation']
+        boolean_attribute(attr)
+      else
+        super
+      end
+    end
+
     def language
       return @language if defined?(@language)
 

lib/linguist/repository.rb

@@ -156,13 +156,8 @@ module Linguist
 
           blob = Linguist::LazyBlob.new(repository, delta.new_file[:oid], new, mode.to_s(8))
 
-          # Skip vendored or generated blobs
-          next if blob.vendored? || blob.generated? || blob.language.nil?
-
-          # Only include programming languages and acceptable markup languages
-          if blob.language.type == :programming || Language.detectable_markup.include?(blob.language.name)
-            file_map[new] = [blob.language.group.name, blob.size]
-          end
+          next unless blob.include_in_language_stats?
+          file_map[new] = [blob.language.group.name, blob.size]
         end
       end