From: Jarkko Hietaniemi <jhi@iki.fi>
Date: Thu, 7 Dec 2000 19:05:32 +0000 (+0000)
Subject: Document utf8_to_uv() better.
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=4dffa63e352fd05b59c46f19323b72952b04b8ce;p=p5sagit%2Fp5-mst-13.2.git

Document utf8_to_uv() better.

p4raw-id: //depot/perl@8024
---

diff --git a/pod/perlapi.pod b/pod/perlapi.pod
index 8bcece2..50ac40c 100644
--- a/pod/perlapi.pod
+++ b/pod/perlapi.pod
@@ -3278,9 +3278,11 @@ 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.  The C<flags> can also contain
-various flags to allow deviations from the strict UTF-8 encoding 
-(see F<utf8.h>).
+will set C<retlen> to C<-1> and return zero.  If the C<flags> does not
+contain UTF8_CHECK_ONLY, the UNICODE_REPLACEMENT_CHARACTER (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>).
 
 	U8* s	utf8_to_uv(STRLEN curlen, STRLEN *retlen, U32 flags)
 
diff --git a/utf8.c b/utf8.c
index 244bb63..9ef7ce1 100644
--- a/utf8.c
+++ b/utf8.c
@@ -189,9 +189,11 @@ 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.  The C<flags> can also contain
-various flags to allow deviations from the strict UTF-8 encoding 
-(see F<utf8.h>).
+will set C<retlen> to C<-1> and return zero.  If the C<flags> does not
+contain UTF8_CHECK_ONLY, the UNICODE_REPLACEMENT_CHARACTER (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>).
 
 =cut */
 
@@ -336,7 +338,7 @@ malformed:
     }
 
     if (retlen)
-	*retlen = expectlen ? expectlen : len;
+	*retlen = expectlen;
 
     return UNICODE_REPLACEMENT_CHARACTER;
 }