github-linguist 9.5.0 → 9.7.0

data/lib/linguist/lazy_blob.rb

@@ -9,7 +9,8 @@ module Linguist
                 'linguist-language',
                 'linguist-vendored',
                 'linguist-generated',
-                'linguist-detectable']
+                'linguist-detectable',
+                'filter']
 
     # DEPRECATED: use Linguist::Source::RuggedRepository::GIT_ATTR_OPTS instead
     GIT_ATTR_OPTS = Linguist::Source::RuggedRepository::GIT_ATTR_OPTS
@@ -73,7 +74,25 @@ module Linguist
       return @language if defined?(@language)
 
       @language = if lang = git_attributes['linguist-language']
-        Language.find_by_alias(lang)
+        detected_language = Language.find_by_alias(lang)
+
+        # If strategies are being tracked, get the original strategy that would have been used
+        if detected_language && Linguist.instrumenter
+          # Get the original strategy by calling super (which calls Linguist.detect)
+          original_language = super
+          original_strategy_info = Linguist.instrumenter.detected_info[self.name]
+          original_strategy = original_strategy_info ? original_strategy_info[:strategy] : "Unknown"
+
+          if original_language == detected_language
+            strategy_name = "#{original_strategy} (confirmed by .gitattributes)"
+          else
+            strategy_name = "#{original_strategy} (overridden by .gitattributes)"
+          end
+
+          strategy = Struct.new(:name).new(strategy_name)
+          Linguist.instrument("linguist.detected", blob: self, strategy: strategy, language: detected_language)
+        end
+        detected_language
       else
         super
       end
@@ -87,6 +106,10 @@ module Linguist
       end
     end
 
+    def lfs_tracked?
+      git_attributes['filter'] == 'lfs'
+    end
+
     def data
       load_blob!
       @data

data/lib/linguist/samples.rb

@@ -15,7 +15,7 @@ module Linguist
     ROOT = File.expand_path("../../../samples", __FILE__)
 
     # Path for serialized samples db
-    PATH = File.expand_path('../samples.json', __FILE__)
+    PATH = File.expand_path('../samples_data.rb', __FILE__)
 
     # Hash of serialized samples object, cached in memory
     def self.cache
@@ -24,15 +24,9 @@ module Linguist
 
     # Hash of serialized samples object, uncached
     def self.load_samples
-      serializer = defined?(Yajl) ? Yajl : JSON
-      data = serializer.load(File.read(PATH, encoding: 'utf-8'))
-      # JSON serialization does not allow integer keys, we fix them here
-      for lang in data['centroids'].keys
-        fixed = data['centroids'][lang].to_a.map { |k,v| [k.to_i, v] }
-        data['centroids'][lang] = Hash[fixed]
-      end
-
-      data
+      mod = Module.new
+      load(PATH, mod)
+      mod::DATA
     end
 
     # Public: Iterate over each sample.