merge revision(s) 51583,51594,51638: [Backport #11444]

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

	* io.c (rb_io_each_codepoint): raise an exception at incomplete
	  character before EOF when conversion takes place.  [Bug #11444]


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_2_1@52831 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 24 insertions, 3 deletions

diff --git a/io.c b/io.c
index 249218d2c5..bf859578cc 100644
--- a/io.c
+++ b/io.c
@@ -3630,6 +3630,7 @@ rb_io_each_codepoint(VALUE io)
     READ_CHECK(fptr);
     if (NEED_READCONV(fptr)) {
 	SET_BINARY_MODE(fptr);
+	r = 1;		/* no invalid char yet */
 	for (;;) {
 	    make_readconv(fptr, 0);
 	    for (;;) {
@@ -3648,13 +3649,16 @@ rb_io_each_codepoint(VALUE io)
 		}
 		if (more_char(fptr) == MORE_CHAR_FINISHED) {
                     clear_readconv(fptr);
-		    /* ignore an incomplete character before EOF */
+		    if (!MBCLEN_CHARFOUND_P(r)) {
+			enc = fptr->encs.enc;
+			goto invalid;
+		    }
 		    return io;
 		}
 	    }
 	    if (MBCLEN_INVALID_P(r)) {
-		rb_raise(rb_eArgError, "invalid byte sequence in %s",
-			 rb_enc_name(fptr->encs.enc));
+		enc = fptr->encs.enc;
+		goto invalid;
 	    }
 	    n = MBCLEN_CHARFOUND_LEN(r);
 	    if (fptr->encs.enc) {
@@ -3684,8 +3688,25 @@ rb_io_each_codepoint(VALUE io)
 	    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;
 	}