lib/linguist/heuristics.rb in github-linguist-5.3.1 vs lib/linguist/heuristics.rb in github-linguist-5.3.2

@@ -1,8 +1,10 @@
 module Linguist
   # A collection of simple heuristics that can be used to better analyze languages.
   class Heuristics
+    HEURISTICS_CONSIDER_BYTES = 50 * 1024
+
     # Public: Use heuristics to detect language of the blob.
     #
     # blob               - An object that quacks like a blob.
     # possible_languages - Array of Language objects
     #
@@ -12,11 +14,11 @@
     #     Language["Ruby"], Language["Python"]
     #   ])
     #
     # Returns an Array of languages, or empty if none matched or were inconclusive.
     def self.call(blob, candidates)
-      data = blob.data
+      data = blob.data[0...HEURISTICS_CONSIDER_BYTES]
 
       @heuristics.each do |heuristic|
         if heuristic.matches?(blob.name, candidates)
           return Array(heuristic.call(data))
         end
@@ -70,10 +72,18 @@
       @heuristic.call(data)
     end
 
     # Common heuristics
     ObjectiveCRegex = /^\s*(@(interface|class|protocol|property|end|synchronised|selector|implementation)\b|#import\s+.+\.h[">])/
+    CPlusPlusRegex = Regexp.union(
+        /^\s*#\s*include <(cstdint|string|vector|map|list|array|bitset|queue|stack|forward_list|unordered_map|unordered_set|(i|o|io)stream)>/,
+        /^\s*template\s*</,
+        /^[ \t]*try/,
+        /^[ \t]*catch\s*\(/,
+        /^[ \t]*(class|(using[ \t]+)?namespace)\s+\w+/,
+        /^[ \t]*(private|public|protected):$/,
+        /std::\w+/)
 
     disambiguate ".as" do |data|
       if /^\s*(package\s+[a-z0-9_\.]+|import\s+[a-zA-Z0-9_\.]+;|class\s+[A-Za-z0-9_]+\s+extends\s+[A-Za-z0-9_]+)/.match(data)
         Language["ActionScript"]
       else
@@ -217,12 +227,11 @@
     end
 
     disambiguate ".h" do |data|
       if ObjectiveCRegex.match(data)
         Language["Objective-C"]
-      elsif (/^\s*#\s*include <(cstdint|string|vector|map|list|array|bitset|queue|stack|forward_list|unordered_map|unordered_set|(i|o|io)stream)>/.match(data) ||
-        /^\s*template\s*</.match(data) || /^[ \t]*try/.match(data) || /^[ \t]*catch\s*\(/.match(data) || /^[ \t]*(class|(using[ \t]+)?namespace)\s+\w+/.match(data) || /^[ \t]*(private|public|protected):$/.match(data) || /std::\w+/.match(data))
+      elsif CPlusPlusRegex.match(data)
         Language["C++"]
       end
     end
 
     disambiguate ".inc" do |data|
@@ -356,13 +365,13 @@
         Language["Perl 6"]
       end
     end
 
     disambiguate ".pm" do |data|
-      if /^\s*(?:use\s+v6\s*;|(?:\bmy\s+)?class|module)\b/.match(data)
-        Language["Perl 6"]
-      elsif /\buse\s+(?:strict\b|v?5\.)/.match(data)
+      if /\buse\s+(?:strict\b|v?5\.)/.match(data)
         Language["Perl"]
+      elsif /^\s*(?:use\s+v6\s*;|(?:\bmy\s+)?class|module)\b/.match(data)
+        Language["Perl 6"]
       elsif /^\s*\/\* XPM \*\//.match(data)
         Language["XPM"]
       end
     end