From: "drbrain (Eric Hodel)" <drbrain@...7.net>
Date: 2012-03-23T13:00:43+09:00
Subject: [ruby-core:43570] [ruby-trunk - Bug #6192] Integer() doesn't handle UTF-16 input


Issue #6192 has been updated by drbrain (Eric Hodel).


=begin
I made this patch:

  Index: bignum.c
  ===================================================================
  --- bignum.c	(revision 35117)
  +++ bignum.c	(working copy)
  @@ -11,6 +11,7 @@
   
   #include "ruby/ruby.h"
   #include "ruby/util.h"
  +#include "ruby/encoding.h"
   #include "internal.h"
   
   #include <math.h>
  @@ -24,6 +25,7 @@
   VALUE rb_cBignum;
   
   static VALUE big_three = Qnil;
  +static VALUE sym_replace = Qnil;
   
   #if defined __MINGW32__
   #define USHORT _USHORT
  @@ -773,8 +775,21 @@ rb_str_to_inum(VALUE str, int base, int 
       long len;
       VALUE v = 0;
       VALUE ret;
  +    VALUE encopts;
  +    rb_encoding *enc;
   
       StringValue(str);
  +
  +    enc = rb_enc_from_index(ENCODING_GET((str)));
  +
  +    if (enc != rb_usascii_encoding()) {
  +      encopts = rb_hash_new();
  +      rb_hash_aset(encopts, sym_replace, rb_str_new2(" "));
  +      rb_obj_freeze(encopts);
  +
  +      str = rb_str_conv_enc_opts(str, enc, rb_usascii_encoding(), 0, encopts);
  +    }
  +
       if (badcheck) {
   	s = StringValueCStr(str);
       }
  @@ -3809,5 +3824,6 @@ Init_Bignum(void)
       power_cache_init();
   
       big_three = rb_uint2big(3);
  +    sym_replace = ID2SYM(rb_intern("replace"));
       rb_gc_register_mark_object(big_three);
   }
  Index: test/ruby/test_literal.rb
  ===================================================================
  --- test/ruby/test_literal.rb	(revision 35117)
  +++ test/ruby/test_literal.rb	(working copy)
  @@ -261,6 +261,23 @@ class TestRubyLiteral < Test::Unit::Test
       }
     end
   
  +  def test_integer_encoding
  +    bug6192 = '[bug#6192]'
  +
  +    s = "2007".encode(Encoding::UTF_16LE)
  +
  +    assert_equal(2007, Integer(s), bug6192)
  +
  +    s = "3.14 is \xCF\x80"
  +    s.force_encoding Encoding::UTF_8
  +
  +    e = assert_raises(ArgumentError, bug6192) do
  +      Integer(s)
  +    end
  +
  +    assert_equal("Invalid value for Integer(): \"#{s}\"", e.message)
  +  end
  +
     def test_float
       head = ['', '-', '+']
       chars = ['0', '1', '_', '9', 'f', '.']

But there is a problem:

    1) Failure:
  test_integer_utf_16(TestRubyLiteral) [/Users/drbrain/Work/svn/ruby/trunk/test/ruby/test_literal.rb:278]:
  <"Invalid value for Integer(): \"3.14 is ��\""> expected but was
  <"invalid value for Integer(): \"3.14 is \\xCF\\x80\"">.
  
I'm not sure if this output is acceptable or not.
=end

----------------------------------------
Bug #6192: Integer() doesn't handle UTF-16 input
https://bugs.ruby-lang.org/issues/6192#change-25064

Author: john_firebaugh (John Firebaugh)
Status: Open
Priority: Normal
Assignee: 
Category: 
Target version: 
ruby -v: ruby 1.9.3p125 (2012-02-16 revision 34643) [x86_64-darwin11.3.0]


>> Integer("2007".encode("UTF-16le"))
ArgumentError: string contains null byte
	from (irb):209:in `Integer'
	from (irb):209
	from /Users/john/.rvm/rubies/ruby-1.9.3-p125/bin/irb:16:in `<main>'



-- 
http://bugs.ruby-lang.org/