From e490d925486bfff70eeb3630e9ab0a4dc1e6ee21 Mon Sep 17 00:00:00 2001 From: akr Date: Sat, 6 Sep 2008 06:07:34 +0000 Subject: [PATCH] * transcode.c (sym_html): new variable. (sym_text): ditto. (sym_attr): ditto. (econv_opts): check :html=>:text and :html=>:attr. (Init_transcode): initialize the above variables. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19180 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- ChangeLog | 8 ++++++++ test/ruby/test_econv.rb | 7 +++++++ transcode.c | 18 ++++++++++++++++++ 3 files changed, 33 insertions(+) diff --git a/ChangeLog b/ChangeLog index 545ee32d77..a214a8ed07 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,11 @@ +Sat Sep 6 15:06:21 2008 Tanaka Akira + + * transcode.c (sym_html): new variable. + (sym_text): ditto. + (sym_attr): ditto. + (econv_opts): check :html=>:text and :html=>:attr. + (Init_transcode): initialize the above variables. + Sat Sep 6 14:46:12 2008 Tanaka Akira * include/ruby/encoding.h (ECONV_HTML_TEXT_ENCODER): new constant. diff --git a/test/ruby/test_econv.rb b/test/ruby/test_econv.rb index 6966ff4e82..3f82d2742c 100644 --- a/test/ruby/test_econv.rb +++ b/test/ruby/test_econv.rb @@ -768,4 +768,11 @@ class TestEncodingConverter < Test::Unit::TestCase assert_equal("&\e$B$&\e(B&".force_encoding("iso-2022-jp"), ec.convert("&\u3046&")) assert_equal('', ec.finish) end + + def test_html_hasharg + assert_equal("&\e$B$&\e(B♥&\"'".force_encoding("iso-2022-jp"), + "&\u3046\u2665&\"'".encode("iso-2022-jp", html: :text)) + assert_equal("\"&\e$B$&\e(B♡&"'\"".force_encoding("iso-2022-jp"), + "&\u3046\u2661&\"'".encode("iso-2022-jp", html: :attr)) + end end diff --git a/transcode.c b/transcode.c index 20303286cd..cc3fc53c7a 100644 --- a/transcode.c +++ b/transcode.c @@ -21,6 +21,7 @@ VALUE rb_eNoConverter; VALUE rb_cEncodingConverter; static VALUE sym_invalid, sym_undef, sym_ignore, sym_replace; +static VALUE sym_html, sym_text, sym_attr; static VALUE sym_universal_newline_decoder; static VALUE sym_crlf_newline_encoder; static VALUE sym_cr_newline_encoder; @@ -2133,6 +2134,20 @@ econv_opts(VALUE opt) rb_raise(rb_eArgError, "unknown value for undefined character option"); } + v = rb_hash_aref(opt, sym_html); + if (!NIL_P(v)) { + v = rb_convert_type(v, T_SYMBOL, "Symbol", "to_sym"); + if (v==sym_text) { + ecflags |= ECONV_HTML_TEXT_ENCODER|ECONV_UNDEF_HEX_CHARREF; + } + else if (v==sym_attr) { + ecflags |= ECONV_HTML_ATTR_ENCODER|ECONV_UNDEF_HEX_CHARREF; + } + else { + rb_raise(rb_eArgError, "unexpected value for html option: %s", rb_id2name(SYM2ID(v))); + } + } + v = rb_hash_aref(opt, sym_universal_newline_decoder); if (RTEST(v)) ecflags |= ECONV_UNIVERSAL_NEWLINE_DECODER; @@ -3477,6 +3492,9 @@ Init_transcode(void) sym_undef = ID2SYM(rb_intern("undef")); sym_ignore = ID2SYM(rb_intern("ignore")); sym_replace = ID2SYM(rb_intern("replace")); + sym_html = ID2SYM(rb_intern("html")); + sym_text = ID2SYM(rb_intern("text")); + sym_attr = ID2SYM(rb_intern("attr")); sym_invalid_byte_sequence = ID2SYM(rb_intern("invalid_byte_sequence")); sym_undefined_conversion = ID2SYM(rb_intern("undefined_conversion"));