From 13a6c0e08df522ae430c77e8a15932642751b605 Mon Sep 17 00:00:00 2001
From: Jarkko Hietaniemi <jhi@iki.fi>
Date: Mon, 11 Mar 2002 12:57:45 +0000
Subject: [PATCH] Undocument the use of
 .*utf8.*{upgrade,downgrade,encode,decode} as general purpose encoding
 transformation interfaces since that's not what they are.

p4raw-id: //depot/perl@15169
---
 lib/utf8.pm         | 18 ++++++++++++------
 pod/perlunicode.pod |  4 ++++
 sv.c                |  9 +++++++++
 3 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/lib/utf8.pm b/lib/utf8.pm
index 7b1ef0d..b18a043 100644
--- a/lib/utf8.pm
+++ b/lib/utf8.pm
@@ -79,21 +79,27 @@ The following functions are defined in the C<utf8::> package by the perl core.
 
 Converts internal representation of string to the Perl's internal
 I<UTF-X> form.  Returns the number of octets necessary to represent
-the string as I<UTF-X>.
+the string as I<UTF-X>.  Note that this should not be used to convert
+a legacy byte encoding to Unicode: use Encode for that.  Affected
+by the encoding pragma.
 
 =item * utf8::downgrade($string[, CHECK])
 
 Converts internal representation of string to be un-encoded bytes.
+Note that this should not be used to convert Unicode back to a legacy
+byte encoding: use Encode for that.  B<Not> affected by the encoding
+pragma.
 
 =item * utf8::encode($string)
 
-Converts (in-place) I<$string> from logical characters to octet sequence
-representing it in Perl's I<UTF-X> encoding.
-
-=item * $flag = utf8::decode($string)
+Converts (in-place) I<$string> from logical characters to octet
+sequence representing it in Perl's I<UTF-X> encoding.  Note that this
+should not be used to convert a legacy byte encoding to Unicode: use
+Encode for that.  =item * $flag = utf8::decode($string)
 
 Attempts to convert I<$string> in-place from Perl's I<UTF-X> encoding
-into logical characters.
+into logical characters.  Note that this should not be used to convert
+Unicode back to a legacy byte encoding: use Encode for that.
 
 =back
 
diff --git a/pod/perlunicode.pod b/pod/perlunicode.pod
index a885555..518d239 100644
--- a/pod/perlunicode.pod
+++ b/pod/perlunicode.pod
@@ -873,6 +873,10 @@ sv_utf8_upgrade(sv) converts the string of the scalar to its UTF-8
 encoded form.  sv_utf8_downgrade(sv) does the opposite (if possible).
 sv_utf8_encode(sv) is like sv_utf8_upgrade but the UTF8 flag does not
 get turned on.  sv_utf8_decode() does the opposite of sv_utf8_encode().
+Note that none of these are to be used as general purpose encoding/decoding
+interfaces: use Encode for that.  sv_utf8_upgrade() is affected by the
+encoding pragma, but sv_utf8_downgrade() is not (since the encoding
+pragma is designed to be a one-way street).
 
 =item *
 
diff --git a/sv.c b/sv.c
index 69f338c..83e2973 100644
--- a/sv.c
+++ b/sv.c
@@ -3313,6 +3313,9 @@ Forces the SV to string form if it is not already.
 Always sets the SvUTF8 flag to avoid future validity checks even
 if all the bytes have hibit clear.
 
+This is not as a general purpose byte encoding to Unicode interface:
+use the Encode extension for that.
+
 =cut
 */
 
@@ -3332,6 +3335,9 @@ if all the bytes have hibit clear. If C<flags> has C<SV_GMAGIC> bit set,
 will C<mg_get> on C<sv> if appropriate, else not. C<sv_utf8_upgrade> and
 C<sv_utf8_upgrade_nomg> are implemented in terms of this function.
 
+This is not as a general purpose byte encoding to Unicode interface:
+use the Encode extension for that.
+
 =cut
 */
 
@@ -3397,6 +3403,9 @@ This may not be possible if the PV contains non-byte encoding characters;
 if this is the case, either returns false or, if C<fail_ok> is not
 true, croaks.
 
+This is not as a general purpose Unicode to byte encoding interface:
+use the Encode extension for that.
+
 =cut
 */
 
-- 
2.7.4