(Retracted by #8264) More join() testing which was good because

[p5sagit/p5-mst-13.2.git] / utf8.c

diff --git a/utf8.c b/utf8.c
index 7a652b4..24dc692 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -183,17 +183,18 @@ Perl_is_utf8_string(pTHX_ U8 *s, STRLEN len)
 
 Returns the character value of the first character in the string C<s>
 which is assumed to be in UTF8 encoding and no longer than C<curlen>;
-C<retlen> will be set to the length, in bytes, of that character,
-and the pointer C<s> will be advanced to the end of the character.
+C<retlen> will be set to the length, in bytes, of that character.
 
 If C<s> does not point to a well-formed UTF8 character, the behaviour
 is dependent on the value of C<flags>: if it contains UTF8_CHECK_ONLY,
 it is assumed that the caller will raise a warning, and this function
-will set C<retlen> to C<-1> and return zero.  If the C<flags> does not
-contain UTF8_CHECK_ONLY, the UNICODE_REPLACEMENT (0xFFFD) will be
-returned, and C<retlen> will be set to the expected length of the
-UTF-8 character in bytes.  The C<flags> can also contain various flags
-to allow deviations from the strict UTF-8 encoding (see F<utf8.h>).
+will silently just set C<retlen> to C<-1> and return zero.  If the
+C<flags> does not contain UTF8_CHECK_ONLY, warnings about
+malformations will be given, C<retlen> will be set to the expected
+length of the UTF-8 character in bytes, and zero will be returned.
+
+The C<flags> can also contain various flags to allow deviations from
+the strict UTF-8 encoding (see F<utf8.h>).
 
 =cut */
 
@@ -339,9 +340,9 @@ malformed:
     }
 
     if (retlen)
-       *retlen = expectlen;
+       *retlen = expectlen ? expectlen : len;
 
-    return UNICODE_REPLACEMENT;
+    return 0;
 }
 
 /*
@@ -349,8 +350,7 @@ malformed:
 
 Returns the character value of the first character in the string C<s>
 which is assumed to be in UTF8 encoding; C<retlen> will be set to the
-length, in bytes, of that character, and the pointer C<s> will be
-advanced to the end of the character.
+length, in bytes, of that character.
 
 If C<s> does not point to a well-formed UTF8 character, zero is
 returned and retlen is set, if possible, to -1.
@@ -506,14 +506,9 @@ Perl_utf8_to_bytes(pTHX_ U8* s, STRLEN *len)
 
     d = s = save;
     while (s < send) {
-        if (*s < 0x80) {
-           *d++ = *s++;
-       }
-        else {
-            STRLEN ulen;
-            *d++ = (U8)utf8_to_uv_simple(s, &ulen);
-            s += ulen;
-        }
+        STRLEN ulen;
+        *d++ = (U8)utf8_to_uv_simple(s, &ulen);
+        s += ulen;
     }
     *d = '\0';
     *len = d - save;