github-linguist 2.11.0 → 2.11.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5f3d2afbe328769fe6d43290ac15e279a1fc839e
-  data.tar.gz: 6150cd186aa13e933e26c01ea48c3b2416ecf965
+  metadata.gz: 20cf20617d8a0934a17836c944818f33e9d1efa2
+  data.tar.gz: c9852f9e4df5fca5cbf768e1109ef343f685ec69
 SHA512:
-  metadata.gz: c0e276415c90ee3dcd43d6eed9f7357e4cd49838429c82200754a3fb7657ba298de3ba553c11ae481a8aa25735140f6181c1c3c78bc91e94d1d48e1aaf4b1db9
-  data.tar.gz: 4af5b1dd14a9b5dc42d49accac0241193f92491d1c99b17b2e918689c0e2d6aa3324cfaeebee80b4e1dc22aef51a9cd03b549449698aa1f34822c968c0a152c2
+  metadata.gz: 52bfdbda263546ec1075a93c3f5132726ff35e47611e295ff6b29169989cbfef9bf387a94578f74ef4ef1349d518b0b837f107e4008b1bb11a854fecc8488073
+  data.tar.gz: fe48a2abc882001aba7c700d8ee44438bbf004f5a7d85394a90aa9330b4b7bbb67b2f4c4f7cd27680dbfd0d124ce5647970b70c520e010a9fbb22dc2e389cd20

data/lib/linguist/blob_helper.rb

@@ -241,7 +241,25 @@ module Linguist
     def lines
       @lines ||=
         if viewable? && data
-          data.split(/\r\n|\r|\n/, -1)
+          # `data` is usually encoded as ASCII-8BIT even when the content has
+          # been detected as a different encoding. However, we are not allowed
+          # to change the encoding of `data` because we've made the implicit
+          # guarantee that each entry in `lines` is encoded the same way as
+          # `data`.
+          #
+          # Instead, we re-encode each possible newline sequence as the
+          # detected encoding, then force them back to the encoding of `data`
+          # (usually a binary encoding like ASCII-8BIT). This means that the
+          # byte sequence will match how newlines are likely encoded in the
+          # file, but we don't have to change the encoding of `data` as far as
+          # Ruby is concerned. This allows us to correctly parse out each line
+          # without changing the encoding of `data`, and
+          # also--importantly--without having to duplicate many (potentially
+          # large) strings.
+          encoded_newlines = ["\r\n", "\r", "\n"].
+            map { |nl| nl.encode(encoding).force_encoding(data.encoding) }
+
+          data.split(Regexp.union(encoded_newlines), -1)
         else
           []
         end

data/lib/linguist/version.rb

@@ -1,3 +1,3 @@
 module Linguist
-  VERSION = "2.11.0"
+  VERSION = "2.11.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: github-linguist
 version: !ruby/object:Gem::Version
-  version: 2.11.0
+  version: 2.11.1
 platform: ruby
 authors:
 - GitHub
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-16 00:00:00.000000000 Z
+date: 2014-05-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: charlock_holmes