Do not return the Unicode replacement character if UTF-8

decoding goes awry, it should be up to the caller to decide.

p4raw-id: //depot/perl@8042

diff --git a/pod/perlapi.pod b/pod/perlapi.pod
index 7fdc55e..cf7c5db 100644 (file)
--- a/pod/perlapi.pod
+++ b/pod/perlapi.pod
@@ -3279,11 +3279,13 @@ and the pointer C<s> will be advanced to the end of the 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>).
 
        U8* s   utf8_to_uv(STRLEN curlen, STRLEN *retlen, U32 flags)
 

diff --git a/utf8.c b/utf8.c
index e9c4386..8d812ab 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -189,11 +189,13 @@ and the pointer C<s> will be advanced to the end of the 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 +341,9 @@ malformed:
     }
 
     if (retlen)
-       *retlen = expectlen;
+       *retlen = expectlen ? expectlen : len;
 
-    return UNICODE_REPLACEMENT;
+    return 0;
 }
 
 /*