From 6ef87aa6333cab6763a3729e37f310f3408b97e5 Mon Sep 17 00:00:00 2001 From: nobu Date: Tue, 26 Apr 2016 14:35:24 +0000 Subject: Fix -e script encoding * ruby.c (process_options): convert -e script to the encoding given by a command line option on Windows. assume it is the expected encoding. [ruby-dev:49461] [Bug #11900] git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@54785 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- ChangeLog | 6 ++++++ ruby.c | 21 +++++++++++++++++++-- test/ruby/test_rubyoptions.rb | 28 ++++++++++++++++++++++++++++ 3 files changed, 53 insertions(+), 2 deletions(-) diff --git a/ChangeLog b/ChangeLog index 8039dad72b..04cd947cc3 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +Tue Apr 26 23:35:23 2016 Nobuyoshi Nakada + + * ruby.c (process_options): convert -e script to the encoding + given by a command line option on Windows. assume it is the + expected encoding. [ruby-dev:49461] [Bug #11900] + Tue Apr 26 21:11:02 2016 Tanaka Akira * numeric.c (rb_int_lshift): {Fixnum,Bignum}#<< is unified into diff --git a/ruby.c b/ruby.c index 128de434d2..0273815200 100644 --- a/ruby.c +++ b/ruby.c @@ -1414,6 +1414,9 @@ process_options(int argc, char **argv, struct cmdline_options *opt) VALUE parser; const rb_iseq_t *iseq; rb_encoding *enc, *lenc; +#if UTF8_PATH + rb_encoding *uenc, *ienc = 0; +#endif const char *s; char fbuf[MAXPATHLEN]; int i = (int)proc_options(argc, argv, opt, 0); @@ -1525,6 +1528,9 @@ process_options(int argc, char **argv, struct cmdline_options *opt) enc = rb_enc_from_index(opt->intern.enc.index); rb_enc_set_default_internal(rb_enc_from_encoding(enc)); opt->intern.enc.index = -1; +#if UTF8_PATH + ienc = enc; +#endif } rb_enc_associate(opt->script_name, lenc); rb_obj_freeze(opt->script_name); @@ -1559,8 +1565,11 @@ process_options(int argc, char **argv, struct cmdline_options *opt) #undef SET_COMPILE_OPTION } #if UTF8_PATH - opt->script_name = str_conv_enc(opt->script_name, rb_utf8_encoding(), lenc); - opt->script = RSTRING_PTR(opt->script_name); + uenc = rb_utf8_encoding(); + if (uenc != lenc) { + opt->script_name = str_conv_enc(opt->script_name, uenc, lenc); + opt->script = RSTRING_PTR(opt->script_name); + } #endif ruby_set_argv(argc, argv); process_sflag(&opt->sflag); @@ -1578,7 +1587,15 @@ process_options(int argc, char **argv, struct cmdline_options *opt) } else { eenc = lenc; +#if UTF8_PATH + if (ienc) eenc = ienc; +#endif } +#if UTF8_PATH + if (eenc != uenc) { + opt->e_script = str_conv_enc(opt->e_script, uenc, eenc); + } +#endif rb_enc_associate(opt->e_script, eenc); if (!(opt->dump & ~DUMP_BIT(version_v))) { ruby_set_script_name(opt->script_name); diff --git a/test/ruby/test_rubyoptions.rb b/test/ruby/test_rubyoptions.rb index 6db6126e28..2e5f76d692 100644 --- a/test/ruby/test_rubyoptions.rb +++ b/test/ruby/test_rubyoptions.rb @@ -768,6 +768,34 @@ class TestRubyOptions < Test::Unit::TestCase assert_in_out_err(["-e", "puts ARGV", "*.txt"], "", ougai) end end + + def assert_e_script_encoding(str, args = []) + cmds = [ + EnvUtil::LANG_ENVS.inject({}) {|h, k| h[k] = ENV[k]; h}, + *args, + '-e', "s = '#{str}'", + '-e', 'puts s.encoding.name', + '-e', 'puts s.dump', + ] + assert_in_out_err(cmds, "", [str.encoding.name, str.dump], [], + "#{str.encoding}:#{str.dump} #{args.inspect}") + end + + # tested codepages: 437 850 852 855 932 65001 + # Since the codepage is shared all processes per conhost.exe, do + # not chcp, or parallel test may break. + def test_locale_codepage + locale = Encoding.find("locale") + list = %W"\u{c7} \u{452} \u{3066 3059 3068}" + list.each do |s| + assert_e_script_encoding(s, %w[-U]) + end + list.each do |s| + s = s.encode(locale) rescue next + assert_e_script_encoding(s) + assert_e_script_encoding(s, %W[-E#{locale.name}]) + end + end when /cygwin/ def test_command_line_non_ascii assert_separately([{"LC_ALL"=>"ja_JP.SJIS"}, "-", "\u{3042}".encode("SJIS")], <<-"end;") -- cgit v1.2.3