ruby-changes:34310
From: nobu <ko1@a...>
Date: Tue, 10 Jun 2014 10:57:14 +0900 (JST)
Subject: [ruby-changes:34310] nobu:r46391 (trunk): csv.rb: honor encoding option
nobu 2014-06-10 10:57:10 +0900 (Tue, 10 Jun 2014) New Revision: 46391 http://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=46391 Log: csv.rb: honor encoding option * lib/csv.rb (CSV#<<): honor explicity given encoding. based on the patch by DAISUKE TANIWAKI <daisuketaniwaki AT gmail.com> at [ruby-core:62113]. [Bug #9766] Modified files: trunk/ChangeLog trunk/lib/csv.rb trunk/test/csv/test_encodings.rb Index: ChangeLog =================================================================== --- ChangeLog (revision 46390) +++ ChangeLog (revision 46391) @@ -1,3 +1,9 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1 +Tue Jun 10 10:57:07 2014 Nobuyoshi Nakada <nobu@r...> + + * lib/csv.rb (CSV#<<): honor explicity given encoding. based on + the patch by DAISUKE TANIWAKI <daisuketaniwaki AT gmail.com> at + [ruby-core:62113]. [Bug #9766] + Mon Jun 9 20:40:48 2014 Koichi Sasada <ko1@a...> * gc.c: change full GC timing to keep lower memory usage. Index: lib/csv.rb =================================================================== --- lib/csv.rb (revision 46390) +++ lib/csv.rb (revision 46391) @@ -1148,9 +1148,9 @@ class CSV https://github.com/ruby/ruby/blob/trunk/lib/csv.rb#L1148 io.seek(0, IO::SEEK_END) args.unshift(io) else - encoding = (args[-1] = args[-1].dup).delete(:encoding) if args.last.is_a?(Hash) + encoding = args[-1][:encoding] if args.last.is_a?(Hash) str = "" - str.encode!(encoding) if encoding + str.force_encoding(encoding) if encoding args.unshift(str) end csv = new(*args) # wrap @@ -1524,7 +1524,7 @@ class CSV https://github.com/ruby/ruby/blob/trunk/lib/csv.rb#L1524 init_headers(options) init_comments(options) - options.delete(:encoding) + @force_encoding = !!(encoding || options.delete(:encoding)) options.delete(:internal_encoding) options.delete(:external_encoding) unless options.empty? @@ -1664,10 +1664,13 @@ class CSV https://github.com/ruby/ruby/blob/trunk/lib/csv.rb#L1664 output = row.map(&@quote).join(@col_sep) + @row_sep # quote and separate if @io.is_a?(StringIO) and - output.encoding != raw_encoding and - (compatible_encoding = Encoding.compatible?(@io.string, output)) - @io.set_encoding(compatible_encoding) - @io.seek(0, IO::SEEK_END) + output.encoding != (encoding = raw_encoding) + if @force_encoding + output = output.encode(encoding) + elsif (compatible_encoding = Encoding.compatible?(@io.string, output)) + @io.set_encoding(compatible_encoding) + @io.seek(0, IO::SEEK_END) + end end @io << output Index: test/csv/test_encodings.rb =================================================================== --- test/csv/test_encodings.rb (revision 46390) +++ test/csv/test_encodings.rb (revision 46391) @@ -247,6 +247,14 @@ class TestCSV::Encodings < TestCSV https://github.com/ruby/ruby/blob/trunk/test/csv/test_encodings.rb#L247 assert_equal("UTF-8", data.to_csv.encoding.name) end + def test_explicit_encoding + bug9766 = '[ruby-core:62113] [Bug #9766]' + s = CSV.generate(encoding: "Windows-31J") do |csv| + csv << ["foo".force_encoding("ISO-8859-1"), "\u3042"] + end + assert_equal(["foo,\u3042\n".encode(Encoding::Windows_31J), Encoding::Windows_31J], [s, s.encoding], bug9766) + end + private def assert_parses(fields, encoding, options = { }) -- ML: ruby-changes@q... Info: http://www.atdot.net/~ko1/quickml/