github-linguist 2.3.0 → 2.3.1

data/lib/linguist/tokenizer.rb

@@ -16,6 +16,9 @@ module Linguist
       new.extract_tokens(data)
     end
 
+    # Read up to 100KB
+    BYTE_LIMIT = 100_000
+
     # Start state on token, ignore anything till the next newline
     SINGLE_LINE_COMMENTS = [
       '//', # C
@@ -55,6 +58,8 @@ module Linguist
 
       tokens = []
       until s.eos?
+        break if s.pos >= BYTE_LIMIT
+
         if token = s.scan(/^#!.+$/)
           if name = extract_shebang(token)
             tokens << "SHEBANG#!#{name}"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: github-linguist
 version: !ruby/object:Gem::Version
-  version: 2.3.0
+  version: 2.3.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-08-20 00:00:00.000000000 Z
+date: 2012-08-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: charlock_holmes