1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00

* encoding.c (rb_enc_mbclen): make it never fail.

(rb_enc_nth): don't check the return value of rb_enc_mbclen.
  (rb_enc_strlen): ditto.
  (rb_enc_precise_mbclen): return needmore(1) if e <= p.
  (rb_enc_get_ascii): new function for extracting ASCII character.

* include/ruby/encoding.h (rb_enc_get_ascii): declared.

* include/ruby/regex.h (ismbchar): removed.

* re.c (rb_reg_expr_str): use rb_enc_get_ascii.
  (unescape_escaped_nonascii): use rb_enc_precise_mbclen to determine
  the termination of escaped non-ASCII character.
  (unescape_nonascii): use rb_enc_precise_mbclen.
  (rb_reg_quote): use rb_enc_get_ascii.
  (rb_reg_regsub): use rb_enc_get_ascii.

* string.c (rb_str_reverse) don't check the return value of
  rb_enc_mbclen.
  (rb_str_split_m): don't call rb_enc_mbclen with e <= p.

* parse.y (is_identchar): use ISASCII.
  (parser_ismbchar): removed.
  (parser_precise_mbclen): new macro.
  (parser_isascii): new macro.
  (parser_tokadd_mbchar): use parser_precise_mbclen to check invalid
  character precisely.
  (parser_tokadd_string): use parser_isascii.
  (parser_yylex): ditto.
  (is_special_global_name): don't call is_identchar with e <= p.
  (rb_enc_symname_p): ditto.

  [ruby-dev:32455]

* ext/tk/sample/tkextlib/vu/canvSticker2.rb: remove coding cookie
  because the encoding is not UTF-8.  [ruby-dev:32475]


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14131 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
akr 2007-12-08 02:50:43 +00:00
parent 990bec9702
commit f1b7e60cb9
10 changed files with 119 additions and 53 deletions

View file

@ -20,7 +20,7 @@ class TestRegexp < Test::Unit::TestCase
def test_yoshidam_net_20041111_2
assert_raise(RegexpError) do
s = "[\xFF-\xFF]"
s = "[\xFF-\xFF]".force_encoding("utf-8")
Regexp.new(s, nil, "u")
end
end
@ -42,8 +42,8 @@ class TestRegexp < Test::Unit::TestCase
assert_equal :ok, begin
Regexp.union(
"a",
Regexp.new("\x80".force_encoding("euc-jp")),
Regexp.new("\x80".force_encoding("utf-8")))
Regexp.new("\xc2\xa1".force_encoding("euc-jp")),
Regexp.new("\xc2\xa1".force_encoding("utf-8")))
:ng
rescue ArgumentError
:ok