From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
 id EE6143858D39; Fri, 11 Mar 2022 00:22:05 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org EE6143858D39
From: "redi at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug libstdc++/104875] libstdc++-v3/src/c++11/codecvt.cc:312:24:
 warning: left shift count >= width of type
Date: Fri, 11 Mar 2022 00:22:05 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: libstdc++
X-Bugzilla-Version: 12.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: redi at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: cf_reconfirmed_on bug_status everconfirmed
Message-ID: <bug-104875-4-PJtEC1rY99@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-104875-4@http.gcc.gnu.org/bugzilla/>
References: <bug-104875-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-BeenThere: gcc-bugs@gcc.gnu.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Gcc-bugs mailing list <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Fri, 11 Mar 2022 00:22:06 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D104875

Jonathan Wakely <redi at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Last reconfirmed|                            |2022-03-11
             Status|UNCONFIRMED                 |NEW
     Ever confirmed|0                           |1

--- Comment #1 from Jonathan Wakely <redi at gcc dot gnu.org> ---
(c1 << 12) is wrong too, because it loses the high bits.

We should just declare all those variables as char32_t in the first place.

--- a/libstdc++-v3/src/c++11/codecvt.cc
+++ b/libstdc++-v3/src/c++11/codecvt.cc
@@ -254,7 +254,7 @@ namespace
     const size_t avail =3D from.size();
     if (avail =3D=3D 0)
       return incomplete_mb_character;
-    unsigned char c1 =3D from[0];
+    char32_t c1 =3D (unsigned char) from[0];
     // https://en.wikipedia.org/wiki/UTF-8#Sample_code
     if (c1 < 0x80)
     {
@@ -267,7 +267,7 @@ namespace
     {
       if (avail < 2)
        return incomplete_mb_character;
-      unsigned char c2 =3D from[1];
+      char32_t c2 =3D (unsigned char) from[1];
       if ((c2 & 0xC0) !=3D 0x80)
        return invalid_mb_sequence;
       char32_t c =3D (c1 << 6) + c2 - 0x3080;
@@ -279,12 +279,12 @@ namespace
     {
       if (avail < 3)
        return incomplete_mb_character;
-      unsigned char c2 =3D from[1];
+      char32_t c2 =3D (unsigned char) from[1];
       if ((c2 & 0xC0) !=3D 0x80)
        return invalid_mb_sequence;
       if (c1 =3D=3D 0xE0 && c2 < 0xA0) // overlong
        return invalid_mb_sequence;
-      unsigned char c3 =3D from[2];
+      char32_t c3 =3D (unsigned char) from[2];
       if ((c3 & 0xC0) !=3D 0x80)
        return invalid_mb_sequence;
       char32_t c =3D (c1 << 12) + (c2 << 6) + c3 - 0xE2080;
@@ -296,17 +296,17 @@ namespace
     {
       if (avail < 4)
        return incomplete_mb_character;
-      unsigned char c2 =3D from[1];
+      char32_t c2 =3D (unsigned char) from[1];
       if ((c2 & 0xC0) !=3D 0x80)
        return invalid_mb_sequence;
       if (c1 =3D=3D 0xF0 && c2 < 0x90) // overlong
        return invalid_mb_sequence;
       if (c1 =3D=3D 0xF4 && c2 >=3D 0x90) // > U+10FFFF
       return invalid_mb_sequence;
-      unsigned char c3 =3D from[2];
+      char32_t c3 =3D (unsigned char) from[2];
       if ((c3 & 0xC0) !=3D 0x80)
        return invalid_mb_sequence;
-      unsigned char c4 =3D from[3];
+      char32_t c4 =3D (unsigned char) from[3];
       if ((c4 & 0xC0) !=3D 0x80)
        return invalid_mb_sequence;
       char32_t c =3D (c1 << 18) + (c2 << 12) + (c3 << 6) + c4 - 0x3C82080;=