nobu	2015-08-15 10:15:22 +0900 (Sat, 15 Aug 2015)

  New Revision: 51583

  http://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=51583

  Log:
    io.c: read more data
    
    * io.c (rb_io_each_codepoint): read more data when read partially.
      [ruby-core:70379] [Bug #11444]

  Modified files:
    trunk/ChangeLog
    trunk/io.c
    trunk/test/ruby/test_io_m17n.rb
Index: ChangeLog
===================================================================
--- ChangeLog	(revision 51582)
+++ ChangeLog	(revision 51583)
@@ -1,3 +1,8 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Sat Aug 15 10:15:20 2015  Nobuyoshi Nakada  <nobu@r...>
+
+	* io.c (rb_io_each_codepoint): read more data when read partially.
+	  [ruby-core:70379] [Bug #11444]
+
 Sat Aug 15 04:33:39 2015  Eric Wong  <e@8...>
 
 	* hash.c (any_hash): skip rb_objid_hash for static syms
Index: io.c
===================================================================
--- io.c	(revision 51582)
+++ io.c	(revision 51583)
@@ -3763,8 +3763,25 @@ rb_io_each_codepoint(VALUE io) https://github.com/ruby/ruby/blob/trunk/io.c#L3763
 	    rb_yield(UINT2NUM(c));
 	}
 	else if (MBCLEN_INVALID_P(r)) {
+	  invalid:
 	    rb_raise(rb_eArgError, "invalid byte sequence in %s", rb_enc_name(enc));
 	}
+	else if (MBCLEN_NEEDMORE_P(r)) {
+	    char cbuf[8], *p = cbuf;
+	    int more = MBCLEN_NEEDMORE_LEN(r);
+	    if (more > numberof(cbuf)) goto invalid;
+	    more += n = fptr->rbuf.len;
+	    if (more > numberof(cbuf)) goto invalid;
+	    while ((n = (int)read_buffered_data(p, more, fptr)) > 0 &&
+		   (p += n, (more -= n) > 0)) {
+		if (io_fillbuf(fptr) < 0) goto invalid;
+		if ((n = fptr->rbuf.len) > more) n = more;
+	    }
+	    r = rb_enc_precise_mbclen(cbuf, p, enc);
+	    if (!MBCLEN_CHARFOUND_P(r)) goto invalid;
+	    c = rb_enc_codepoint(cbuf, p, enc);
+	    rb_yield(UINT2NUM(c));
+	}
 	else {
 	    continue;
 	}
Index: test/ruby/test_io_m17n.rb
===================================================================
--- test/ruby/test_io_m17n.rb	(revision 51582)
+++ test/ruby/test_io_m17n.rb	(revision 51583)
@@ -2562,4 +2562,24 @@ EOT https://github.com/ruby/ruby/blob/trunk/test/ruby/test_io_m17n.rb#L2562
     a.close rescue nil
     b.close rescue nil
   end
+
+  def test_each_codepoint_need_more
+    code = <<-'end;'
+      c = nil
+      begin
+        STDIN.set_encoding(Encoding::UTF_8).each_codepoint{|i| c = i}
+      rescue ArgumentError => e
+        STDERR.puts e.message
+      else
+        printf "%x", c
+      end
+    end;
+    args = ['-e', code]
+    bug11444 = '[ruby-core:70379] [Bug #11444]'
+    assert_in_out_err(args, "\u{1f376}".b[0,3], [],
+                      ["invalid byte sequence in UTF-8"],
+                      bug11444, timeout: 1)
+    assert_in_out_err(args, "x"*8190+"\u{1f376}", ["1f376"], [],
+                      bug11444, timeout: 1)
+  end
 end

--
ML: ruby-changes@q...
Info: http://www.atdot.net/~ko1/quickml/