Merge pull request #3237 from github/3227-local

Revised Emacs modeline detection

lib/linguist/strategy/modeline.rb

@@ -1,7 +1,37 @@
 module Linguist
   module Strategy
     class Modeline
-      EMACS_MODELINE = /-\*-\s*(?:(?!mode)[\w-]+\s*:\s*(?:[\w+-]+)\s*;?\s*)*(?:mode\s*:)?\s*([\w+-]+)\s*(?:;\s*(?!mode)[\w-]+\s*:\s*[\w+-]+\s*)*;?\s*-\*-/i
+      EMACS_MODELINE = /
+        -\*-
+        (?:
+          # Short form: `-*- ruby -*-`
+          \s* (?= [^:;\s]+ \s* -\*-)
+          |
+          # Longer form: `-*- foo:bar; mode: ruby; -*-`
+          (?:
+            .*?       # Preceding variables: `-*- foo:bar bar:baz;`
+            [;\s]     # Which are delimited by spaces or semicolons
+            |
+            (?<=-\*-) # Not preceded by anything: `-*-mode:ruby-*-`
+          )
+          mode        # Major mode indicator
+          \s*:\s*     # Allow whitespace around colon: `mode : ruby`
+        )
+        ([^:;\s]+)    # Name of mode
+
+        # Ensure the mode is terminated correctly
+        (?=
+          # Followed by semicolon or whitespace
+          [\s;]
+          |
+          # Touching the ending sequence: `ruby-*-`
+          (?<![-*])   # Don't allow stuff like `ruby--*-` to match; it'll invalidate the mode
+          -\*-        # Emacs has no problems reading `ruby --*-`, however.
+        )
+        .*?           # Anything between a cleanly-terminated mode and the ending -*-
+        -\*-
+      /xi
+
       VIM_MODELINE   = /
 
         # Start modeline. Could be `vim:`, `vi:` or `ex:`

test/fixtures/Data/Modelines/seeplusplusEmacs10

@@ -0,0 +1,3 @@
+// -*- foo-bar mode: c++ -*-
+
+"Malformed modeline, but still understood by Emacs to be C++."

test/fixtures/Data/Modelines/seeplusplusEmacs11

@@ -0,0 +1 @@
+/* -*- mode: c++ -------*- */

test/fixtures/Data/Modelines/seeplusplusEmacs12

@@ -0,0 +1 @@
+-*--------- foo:bar mode: c++ -*-

test/test_grammars.rb

@@ -9,6 +9,7 @@ class TestGrammars < Minitest::Test
     "vendor/grammars/go-tmbundle",
     "vendor/grammars/jflex.tmbundle",
     "vendor/grammars/language-csharp",
+    "vendor/grammars/language-viml",
     "vendor/grammars/sublimeassembly"
   ].freeze
 

test/test_modelines.rb

@@ -30,6 +30,9 @@ class TestModelines < Minitest::Test
     assert_modeline Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs7")
     assert_modeline Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs8")
     assert_modeline Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs9")
+    assert_modeline Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs10")
+    assert_modeline Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs11")
+    assert_modeline Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs12")
     assert_modeline Language["Text"], fixture_blob("Data/Modelines/fundamentalEmacs.c")
     assert_modeline Language["Prolog"], fixture_blob("Data/Modelines/not_perl.pl")
     assert_modeline Language["Smalltalk"], fixture_blob("Data/Modelines/example_smalltalk.md")
@@ -53,6 +56,9 @@ class TestModelines < Minitest::Test
     assert_equal Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs7").language
     assert_equal Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs8").language
     assert_equal Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs9").language
+    assert_equal Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs10").language
+    assert_equal Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs11").language
+    assert_equal Language["C++"], fixture_blob("Data/Modelines/seeplusplusEmacs12").language
     assert_equal Language["Text"], fixture_blob("Data/Modelines/fundamentalEmacs.c").language
     assert_equal Language["Prolog"], fixture_blob("Data/Modelines/not_perl.pl").language
     assert_equal Language["Smalltalk"], fixture_blob("Data/Modelines/example_smalltalk.md").language