A C++ shibboleth?

lib/linguist/heuristics.rb

@@ -16,12 +16,14 @@ module Linguist
     end
 
     # .h extensions are ambigious between C, C++, and Objective-C.
-    # We want to shortcut look for Objective-C.
+    # 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)
       matches = []
       matches << Language["Objective-C"] if data.include?("@interface")
+      matches << Language["C++"] if data.include?("#include <cstdint>")
       matches
     end
   end

lib/linguist/samples.json

@@ -163,6 +163,9 @@
       ".json",
       ".lock"
     ],
+    "JSON5": [
+      ".json5"
+    ],
     "Julia": [
       ".jl"
     ],
@@ -509,8 +512,8 @@
       ".gemrc"
     ]
   },
-  "tokens_total": 428226,
+  "tokens_total": 428289,
-  "languages_total": 503,
+  "languages_total": 506,
   "tokens": {
     "ABAP": {
       "*/**": 1,
@@ -8560,7 +8563,7 @@
     "C++": {
       "class": 40,
       "Bar": 2,
-      "{": 562,
+      "{": 563,
       "protected": 4,
       "char": 126,
       "*name": 6,
@@ -8570,15 +8573,15 @@
       "hello": 2,
       "(": 2498,
       ")": 2500,
-      "}": 562,
+      "}": 563,
       "#pragma": 2,
       "once": 2,
-      "#include": 117,
+      "#include": 118,
       "<string>": 4,
       "<vector>": 4,
       "<fstream>": 2,
       "using": 4,
-      "namespace": 30,
+      "namespace": 31,
       "std": 52,
       "#define": 197,
       "DEFAULT_DELIMITER": 1,
@@ -9957,6 +9960,8 @@
       "wrapMode": 2,
       "wmode.": 1,
       "wmode": 1,
+      "<cstdint>": 1,
+      "Gui": 1,
       "v8": 9,
       "Scanner": 16,
       "UnicodeCache*": 4,
@@ -23686,6 +23691,50 @@
       "}": 73,
       "true": 3
     },
+    "JSON5": {
+      "{": 6,
+      "foo": 1,
+      "while": 1,
+      "true": 1,
+      "this": 1,
+      "here": 1,
+      "//": 2,
+      "inline": 1,
+      "comment": 1,
+      "hex": 1,
+      "xDEADbeef": 1,
+      "half": 1,
+      ".5": 1,
+      "delta": 1,
+      "+": 1,
+      "to": 1,
+      "Infinity": 1,
+      "and": 1,
+      "beyond": 1,
+      "finally": 1,
+      "oh": 1,
+      "[": 3,
+      "]": 3,
+      "}": 6,
+      "name": 1,
+      "version": 1,
+      "description": 1,
+      "keywords": 1,
+      "author": 1,
+      "contributors": 1,
+      "main": 1,
+      "bin": 1,
+      "dependencies": 1,
+      "devDependencies": 1,
+      "mocha": 1,
+      "scripts": 1,
+      "build": 1,
+      "test": 1,
+      "homepage": 1,
+      "repository": 1,
+      "type": 1,
+      "url": 1
+    },
     "Julia": {
       "##": 5,
       "Test": 1,
@@ -45100,7 +45149,7 @@
     "Bluespec": 1298,
     "Brightscript": 579,
     "C": 58858,
-    "C++": 22665,
+    "C++": 22671,
     "Ceylon": 50,
     "Clojure": 510,
     "COBOL": 90,
@@ -45134,6 +45183,7 @@
     "Java": 8987,
     "JavaScript": 76934,
     "JSON": 183,
+    "JSON5": 57,
     "Julia": 247,
     "Kotlin": 155,
     "KRL": 25,
@@ -45235,7 +45285,7 @@
     "Bluespec": 2,
     "Brightscript": 1,
     "C": 26,
-    "C++": 23,
+    "C++": 24,
     "Ceylon": 1,
     "Clojure": 7,
     "COBOL": 4,
@@ -45269,6 +45319,7 @@
     "Java": 6,
     "JavaScript": 20,
     "JSON": 4,
+    "JSON5": 2,
     "Julia": 1,
     "Kotlin": 1,
     "KRL": 1,
@@ -45356,5 +45407,5 @@
     "Xtend": 2,
     "YAML": 1
   },
-  "md5": "7e305e6e7267f7d227fa871bf83546b8"
+  "md5": "1b96eb81ded03f57c14ee681d73d5db6"
 }

samples/C++/render_adapter.cpp

@@ -0,0 +1,6 @@
+#include <cstdint>
+
+namespace Gui
+{
+
+}

test/test_heuristics.rb

@@ -28,6 +28,12 @@ class TestHeuristcs < Test::Unit::TestCase
     end
   end
    
+  def test_cpp_by_heuristics
+    languages = ["C++", "Objective-C"]
+    results = Heuristics.find_by_heuristics(fixture("C++/render_adapter.cpp"), languages)
+    assert_equal Language["C++"], results.first
+  end
+
   def test_detect_still_works_if_nothing_matches
     match = Language.detect("Hello.m", fixture("Objective-C/hello.m"))
     assert_equal Language["Objective-C"], match