From nobody Sat Oct 7 18:00:51 2023 X-Original-To: dev-commits-src-all@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 4S2tPv44vqz4x7gd; Sat, 7 Oct 2023 18:00:51 +0000 (UTC) (envelope-from git@FreeBSD.org) Received: from mxrelay.nyi.freebsd.org (mxrelay.nyi.freebsd.org [IPv6:2610:1c1:1:606c::19:3]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256 client-signature RSA-PSS (4096 bits) client-digest SHA256) (Client CN "mxrelay.nyi.freebsd.org", Issuer "R3" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 4S2tPv3B6Hz3ZXF; Sat, 7 Oct 2023 18:00:51 +0000 (UTC) (envelope-from git@FreeBSD.org) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=freebsd.org; s=dkim; t=1696701651; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=PjtaIpZBXhLRrOV4iwKdzmXx9naDb4GhbYLInmVVkls=; b=R3KJL7Y385p5PmnicISMSWe7nA/GXixZMHwm24os1uu5j0OwHboL5V9d9RSClSmEOMfLUE lQX05sIvMWbZHUWhX/TFqNFcARFkA3Qdb2T5Dopgc9BZnZDTEGc+AppcEg9PUDNCJNbTTN W/gl/at2DPRGy6BbsAWgD/ITVxlzghuCx1/vWxbOtMUGYQm0sPgyh6CexoJHAb8IUDxZ7v EqvWIottuh/z237L9oIOiXk4jOLrbPFTSBBRXHwN9rW+J3UELA718g2zjBtuKf6LpYPp4x 3JN/jg+5/U1T+Mw/1PjIbQiLcxCxATD1XkmbeoHLWqthTNSIo0spH2DcLRdJwA== ARC-Seal: i=1; s=dkim; d=freebsd.org; t=1696701651; a=rsa-sha256; cv=none; b=yt8dKbzS//isz2ANV8BE7jhtNIFzS8tybs07Pcmis8+q1BmpiNBfI4SJ1Qa2J8HABveaxg oJWIU6N1wgOsJaI8d/W8L9ft0qe+638xGbnh9dC1f15XCVhupPu1XkB7cnjo8gaGHcvBX5 YER4FaXrrIw94gUriKPJ4BF7lp0T49BvniKtkmo6W/eIEjvE+D6w1OVJ4K5L81+bkBbVAp wlCz+FCTIL+8n5qqsRx7wfbx+vwGK+ILw4bQG13/QSkg1xrpYv5zKOJZ3zYoixRGrWZjTz p3RyUZABgaf+sY+/DwkS2WFE3Euh7nfFe3cD9pSoX6hNIoX7izaE5Mf3Bu/Z8g== ARC-Authentication-Results: i=1; mx1.freebsd.org; none ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=freebsd.org; s=dkim; t=1696701651; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding; bh=PjtaIpZBXhLRrOV4iwKdzmXx9naDb4GhbYLInmVVkls=; b=o8/x+JsKdPl+IQgtv91I498TxfIgP4Pmsiu0RfakTsNGaP5mDGVelPTtXp+JmVb0+M+gCw XTZZh0IaPRJRQNPXzs30KWeEaUchVh2Oc3J/EXir/CyVYpSF/wV5aurkkJiWTZLnHoIuN+ hKajFXK7ymbtOJIOkvQNW4q6lkVaDIfMqEB91aDRvbtq2i9acSF6yHUFrWghrBCgkiBJik xdHYKDFzM65iH1MHKdvEVjV4cDD7FBZYvH7NGuFi3Puvrjtl/w5413CYpvbVvccNbinz7m +guO+6gitOmZ+H77B99LF/35kuZCM2M5xOgcOXeQdWozCASHwlyPAA9Eq/OdXA== Received: from gitrepo.freebsd.org (gitrepo.freebsd.org [IPv6:2610:1c1:1:6068::e6a:5]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (Client did not present a certificate) by mxrelay.nyi.freebsd.org (Postfix) with ESMTPS id 4S2tPv1xRTzgkD; Sat, 7 Oct 2023 18:00:51 +0000 (UTC) (envelope-from git@FreeBSD.org) Received: from gitrepo.freebsd.org ([127.0.1.44]) by gitrepo.freebsd.org (8.17.1/8.17.1) with ESMTP id 397I0pnj047834; Sat, 7 Oct 2023 18:00:51 GMT (envelope-from git@gitrepo.freebsd.org) Received: (from git@localhost) by gitrepo.freebsd.org (8.17.1/8.17.1/Submit) id 397I0p9G047831; Sat, 7 Oct 2023 18:00:51 GMT (envelope-from git) Date: Sat, 7 Oct 2023 18:00:51 GMT Message-Id: <202310071800.397I0p9G047831@gitrepo.freebsd.org> To: src-committers@FreeBSD.org, dev-commits-src-all@FreeBSD.org, dev-commits-src-main@FreeBSD.org From: Christos Margiolis Subject: git: 9e589b093857 - main - tty: fix improper backspace behaviour for UTF8 characters when in canonical mode List-Id: Commit messages for all branches of the src repository List-Archive: https://lists.freebsd.org/archives/dev-commits-src-all List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-dev-commits-src-all@freebsd.org X-BeenThere: dev-commits-src-all@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit X-Git-Committer: christos X-Git-Repository: src X-Git-Refname: refs/heads/main X-Git-Reftype: branch X-Git-Commit: 9e589b0938579f3f4d89fa5c051f845bf754184d Auto-Submitted: auto-generated The branch main has been updated by christos: URL: https://cgit.FreeBSD.org/src/commit/?id=9e589b0938579f3f4d89fa5c051f845bf754184d commit 9e589b0938579f3f4d89fa5c051f845bf754184d Author: Bojan Novković AuthorDate: 2023-10-07 18:00:11 +0000 Commit: Christos Margiolis CommitDate: 2023-10-07 18:00:11 +0000 tty: fix improper backspace behaviour for UTF8 characters when in canonical mode This patch adds additional logic in ttydisc_rubchar() to properly handle backspace behaviour for UTF-8 characters. Currently, typing in a backspace after a UTF8 character will delete only one byte from the byte sequence, leaving garbled output in the tty's output queue. With this change all of the character's bytes are deleted. This change is only active when the IUTF8 flag is set (see 19054eb6053189144aa962b2ecc1bf5087758a3e "(s)tty: add support for IUTF8 input flag") The code uses the teken_wcwidth() function to properly handle character column widths for different code points, and adds the teken_utf8_bytes_to_codepoint() function that converts a UTF-8 byte sequence to a codepoint, as specified in RFC3629. Reported by: christos Reviewed by: christos, imp MFC after: 2 weeks Differential Revision: https://reviews.freebsd.org/D42067 --- sys/kern/tty_ttydisc.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++ sys/teken/teken_wcwidth.h | 30 +++++++++++++++++++ 2 files changed, 104 insertions(+) diff --git a/sys/kern/tty_ttydisc.c b/sys/kern/tty_ttydisc.c index 665275ee93e7..eae7162e31c0 100644 --- a/sys/kern/tty_ttydisc.c +++ b/sys/kern/tty_ttydisc.c @@ -43,6 +43,9 @@ #include #include +#include +#include + /* * Standard TTYDISC `termios' line discipline. */ @@ -78,8 +81,13 @@ SYSCTL_ULONG(_kern, OID_AUTO, tty_nout, CTLFLAG_RD, /* Character is alphanumeric. */ #define CTL_ALNUM(c) (((c) >= '0' && (c) <= '9') || \ ((c) >= 'a' && (c) <= 'z') || ((c) >= 'A' && (c) <= 'Z')) +/* Character is UTF8-encoded. */ +#define CTL_UTF8(c) (!!((c) & 0x80)) +/* Character is a UTF8 continuation byte. */ +#define CTL_UTF8_CONT(c) (((c) & 0xc0) == 0x80) #define TTY_STACKBUF 256 +#define UTF8_STACKBUF 4 void ttydisc_open(struct tty *tp) @@ -800,6 +808,72 @@ ttydisc_rubchar(struct tty *tp) ttyoutq_write_nofrag(&tp->t_outq, "\b\b\b\b\b\b\b\b", tablen); return (0); + } else if ((tp->t_termios.c_iflag & IUTF8) != 0 && + CTL_UTF8(c)) { + uint8_t bytes[UTF8_STACKBUF] = { 0 }; + int curidx = UTF8_STACKBUF - 1, cwidth = 1, + nb = 0; + teken_char_t codepoint; + + /* Save current byte. */ + bytes[curidx] = c; + curidx--; + nb++; + /* Loop back through inq until we hit the + * leading byte. */ + while (CTL_UTF8_CONT(c) && nb < UTF8_STACKBUF) { + ttyinq_peekchar(&tp->t_inq, &c, "e); + ttyinq_unputchar(&tp->t_inq); + bytes[curidx] = c; + curidx--; + nb++; + } + /* + * Shift array so that the leading + * byte ends up at idx 0. + */ + if (nb < UTF8_STACKBUF) + memmove(&bytes[0], &bytes[curidx + 1], + nb * sizeof(uint8_t)); + /* Check for malformed UTF8 characters. */ + if (nb == UTF8_STACKBUF && + CTL_UTF8_CONT(bytes[0])) { + /* + * Place all bytes back into the inq and + * delete the last byte only. + */ + ttyinq_write(&tp->t_inq, bytes, + UTF8_STACKBUF, 0); + } else { + /* Find codepoint and width. */ + codepoint = + teken_utf8_bytes_to_codepoint(bytes, + nb); + if (codepoint != + TEKEN_UTF8_INVALID_CODEPOINT) { + cwidth = teken_wcwidth( + codepoint); + } else { + /* + * Place all bytes back into the + * inq and fall back to + * default behaviour. + */ + ttyinq_write(&tp->t_inq, bytes, + nb, 0); + } + } + tp->t_column -= cwidth; + /* + * Delete character by punching + * 'cwidth' spaces over it. + */ + if (cwidth == 1) + ttyoutq_write_nofrag(&tp->t_outq, + "\b \b", 3); + else if (cwidth == 2) + ttyoutq_write_nofrag(&tp->t_outq, + "\b\b \b\b", 6); } else { /* * Remove a regular character by diff --git a/sys/teken/teken_wcwidth.h b/sys/teken/teken_wcwidth.h index f57a185c2433..f5a23dbc9679 100644 --- a/sys/teken/teken_wcwidth.h +++ b/sys/teken/teken_wcwidth.h @@ -8,6 +8,8 @@ * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c */ +#define TEKEN_UTF8_INVALID_CODEPOINT -1 + struct interval { teken_char_t first; teken_char_t last; @@ -116,3 +118,31 @@ static int teken_wcwidth(teken_char_t ucs) (ucs >= 0x20000 && ucs <= 0x2fffd) || (ucs >= 0x30000 && ucs <= 0x3fffd))); } + +/* + * Converts an UTF-8 byte sequence to a codepoint as specified in + * https://datatracker.ietf.org/doc/html/rfc3629#section-3 . The function + * expects the 'bytes' array to start with the leading character. + */ +static teken_char_t +teken_utf8_bytes_to_codepoint(uint8_t bytes[4], int nbytes) +{ + + /* Check for malformed characters. */ + if (bitcount(bytes[0] & 0xf0) != nbytes) + return (TEKEN_UTF8_INVALID_CODEPOINT); + + switch (nbytes) { + case 1: + return (bytes[0] & 0x7f); + case 2: + return (bytes[0] & 0xf) << 6 | (bytes[1] & 0x3f); + case 3: + return (bytes[0] & 0xf) << 12 | (bytes[1] & 0x3f) << 6 | (bytes[2] & 0x3f); + case 4: + return (bytes[0] & 0x7) << 18 | (bytes[1] & 0x3f) << 12 | + (bytes[2] & 0x3f) << 6 | (bytes[3] & 0x3f); + default: + return (TEKEN_UTF8_INVALID_CODEPOINT); + } +}