From 0a4801e768cd93c79666f32460306f132009aa9d Mon Sep 17 00:00:00 2001
From: ktsj <ktsj@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Sat, 7 Sep 2013 04:34:27 +0000
Subject: * lib/find.rb (Find.find): respect the encodings of arguments.  
 [ruby-dev:47530] [Feature #8657]

* test/test_find.rb: add tests.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@42866 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 ChangeLog         |  7 +++++++
 lib/find.rb       | 40 +++++++++++++++++++++++-----------------
 test/test_find.rb | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 64 insertions(+), 17 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index d88544ba1c..8b3a82af70 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+Sat Sep  7 13:29:22 2013  Kazuki Tsujimoto  <kazuki@callcc.net>
+
+	* lib/find.rb (Find.find): respect the encodings of arguments.
+	  [ruby-dev:47530] [Feature #8657]
+
+	* test/test_find.rb: add tests.
+
 Sat Sep  7 10:40:32 2013  Tanaka Akira  <akr@fsij.org>
 
 	* ext/socket/mkconstants.rb (TCP_FASTOPEN): Defined for TCP fast open.
diff --git a/lib/find.rb b/lib/find.rb
index 571609cdef..6f3e4282ed 100644
--- a/lib/find.rb
+++ b/lib/find.rb
@@ -37,30 +37,36 @@ module Find
   def find(*paths) # :yield: path
     block_given? or return enum_for(__method__, *paths)
 
-    paths.collect!{|d| raise Errno::ENOENT unless File.exist?(d); d.dup}
-    while file = paths.shift
-      catch(:prune) do
-        yield file.dup.taint
-        begin
-          s = File.lstat(file)
-        rescue Errno::ENOENT, Errno::EACCES, Errno::ENOTDIR, Errno::ELOOP, Errno::ENAMETOOLONG
-          next
-        end
-        if s.directory? then
+    fs_encoding = Encoding.find("filesystem")
+
+    paths.collect!{|d| raise Errno::ENOENT unless File.exist?(d); d.dup}.each do |path|
+      enc = path.encoding == Encoding::US_ASCII ? fs_encoding : path.encoding
+      ps = [path]
+      while file = ps.shift
+        catch(:prune) do
+          yield file.dup.taint
           begin
-            fs = Dir.entries(file)
+            s = File.lstat(file)
           rescue Errno::ENOENT, Errno::EACCES, Errno::ENOTDIR, Errno::ELOOP, Errno::ENAMETOOLONG
             next
           end
-          fs.sort!
-          fs.reverse_each {|f|
-            next if f == "." or f == ".."
-            f = File.join(file, f)
-            paths.unshift f.untaint
-          }
+          if s.directory? then
+            begin
+              fs = Dir.entries(file, encoding: enc)
+            rescue Errno::ENOENT, Errno::EACCES, Errno::ENOTDIR, Errno::ELOOP, Errno::ENAMETOOLONG
+              next
+            end
+            fs.sort!
+            fs.reverse_each {|f|
+              next if f == "." or f == ".."
+              f = File.join(file, f)
+              ps.unshift f.untaint
+            }
+          end
         end
       end
     end
+    nil
   end
 
   #
diff --git a/test/test_find.rb b/test/test_find.rb
index f6e7f7a13d..b26debe547 100644
--- a/test/test_find.rb
+++ b/test/test_find.rb
@@ -210,6 +210,40 @@ class TestFind < Test::Unit::TestCase
     }
   end
 
+  def test_encoding_ascii
+    Dir.mktmpdir {|d|
+      File.open("#{d}/a", "w"){}
+      Dir.mkdir("#{d}/b")
+      a = []
+      Find.find(d.encode(Encoding::US_ASCII)) {|f| a << f }
+      a.each do |i|
+        assert(Encoding.compatible?(d.encode(Encoding.find('filesystem')), i))
+      end
+    }
+  end
+
+  def test_encoding_non_ascii
+    Dir.mktmpdir {|d|
+      File.open("#{d}/a", "w"){}
+      Dir.mkdir("#{d}/b")
+      euc_jp = Encoding::EUC_JP
+      win_31j = Encoding::Windows_31J
+      utf_8 = Encoding::UTF_8
+      a = []
+      Find.find(d.encode(euc_jp), d.encode(win_31j), d.encode(utf_8)) {|f| a << [f, f.encoding] }
+      assert_equal([[d, euc_jp], ["#{d}/a", euc_jp], ["#{d}/b", euc_jp],
+                    [d, win_31j], ["#{d}/a", win_31j], ["#{d}/b", win_31j],
+                    [d, utf_8], ["#{d}/a", utf_8], ["#{d}/b", utf_8]],
+                   a)
+      if /mswin|mingw/ =~ RUBY_PLATFORM
+        a = []
+        Dir.mkdir("#{d}/\u{2660}")
+        Find.find("#{d}".encode(utf_8)) {|f| a << [f, f.encoding] }
+        assert_equal([[d, utf_8], ["#{d}/a", utf_8], ["#{d}/b", utf_8], ["#{d}/\u{2660}", utf_8]], a)
+      end
+    }
+  end
+
   class TestInclude < Test::Unit::TestCase
     include Find
 
-- 
cgit v1.2.3