From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=202.61.206.94 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795185883; b=V6gTcMLLnfrkw8olSG3wWIX9HLq95/AXymb3Vxbriga2USzVgNhLO5/M1tKdDiKiyWwe l2bLrjUNbhTR18kgUQzcSgxro7lhnlK+xVwrbvnTtasxe8lnCW+dVNEl7r7ad7SrUQQcy iD2W1um75AXA07gqSx4QVXU/LR7ebPBtdxEJrpMsd/vZ81/YEa+cDzfevmi+krPqNC+fR d5HqogieMh7dLinLTEKxGSjUgiKnzlqRzK129g8PMlkNklqWfGmhN/QFmbGoDMVY0t/AQ uZGLTYZCK8cFSX5UpqnhKku2FxTQ46YGdoUOIu3de4DzhhotAnMWx0P9LGMOGzi1GTA== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795185883; h=DMARC-Filter:Received:DKIM-Signature:From:Date:Subject:MIME-Version: Content-Type:Content-Transfer-Encoding:Message-Id:References: In-Reply-To:To:Cc:X-Mailer:X-Developer-Signature:X-Developer-Key; bh=EyTSTA0l2LTwi9VBlXpsvayoJQab6Gmg+pi5FTDmWEg=; b=1NzVw8Y9VliAhiSD+q5nchG0KKoYtVB84hqEwZDlt9W6IKzaDYtydqUii2QVCGDXnJ72 qeFVa+vuMImvaAOYqkiQfXgS4aUT3BPMVjtlL0IcKNdeU544Nnl1ud3U5EfOpH92AcNfv BOt3uO36zShFLtp73oNfyiWFWV1dWDX5lV8ORwu6RngYw/lE8/kBqPN0yxhF/9qvEa/Yz TYpiDVaf6KNbc15LGQfy/qbMxq9LkvPEKty7VzbsJW/56oxY8X0h1dt151M+f655SsNet cBGFFKLB9lSd9QNgieoQbX+5+21v51CraIyBQTh1DJWtCd6rHLsEmNwHsYOTzeYBbWA== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=gouders.net; spf=pass smtp.mailfrom=gouders.net; dkim=pass header.d=gouders.net header.i=@gouders.net header.a=rsa-sha256 header.s=gnet header.b=thHZDnTy; arc=none smtp.remote-ip=202.61.206.94 Received: from mx10.gouders.net (mx10.gouders.net [202.61.206.94]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2C5E8606A336 for ; Fri, 20 Nov 2026 14:44:41 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 2C5E8606A336 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=gouders.net Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gouders.net Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=gouders.net header.i=@gouders.net header.a=rsa-sha256 header.s=gnet header.b=thHZDnTy Received: from lena.gouders.net (ip-109-41-49-183.web.vodafone.de [109.41.49.183]) (authenticated bits=0) by mx10.gouders.net (8.18.2/8.17.1.9) with ESMTPSA id 6AKEiRtA2079849 (version=TLSv1.3 cipher=TLS_AES_256_GCM_SHA384 bits=256 verify=NO); Fri, 20 Nov 2026 15:44:31 +0100 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gouders.net; s=gnet; t=1795185871; bh=EyTSTA0l2LTwi9VBlXpsvayoJQab6Gmg+pi5FTDmWEg=; h=From:Date:Subject:References:In-Reply-To:To:Cc; b=thHZDnTyGfJ18QilK4VrCtpwr/EN0jjmg/7vpKSY7GFJPPmZ6VEuf0XZmd4MSLCMR KC3EYLdplr+KCfYrdjj23lzv9YfQf7wEp80QAsoE5oqlNLiuPwWrpqFItcZfGcXHZo xkdvFHYphnbgijRd5Si5Gi85rek4cibe3N9Jh6c4= From: Dirk Gouders Date: Fri, 20 Nov 2026 15:44:27 +0100 Subject: [PATCH v3 4/4] utf8: respect boundaries in utf8_strnwidth() X-Mailing-List: git@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit Message-Id: <20261120-master-v3-4-d28e8c75d26d@gouders.net> References: <20261120-master-v3-0-d28e8c75d26d@gouders.net> In-Reply-To: <20261120-master-v3-0-d28e8c75d26d@gouders.net> To: git@vger.kernel.org Cc: Junio C Hamano , Dirk Gouders X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=openpgp-sha256; l=5285; i=dirk@gouders.net; h=from:subject:message-id; bh=hSD6PmFkXUvDRFbtWF0Z6Kge/u0nq7eV7mIIBefU5Yo=; b=owGbwMvMwMW4JPzVNXNTrzmMp9WSGLIZYs5YPMzy+OO3cQO/uLn8MaY6WWGDs7eUJXdvVHa78 vBHvI98J+MEFgZGLoYqMUWWpZOK7NJUVrwo+6aaCTOIlQlkirRIAwMQsDDw5SbmlRrpGOmZahvq GQIZOkYOEDl+Bo30gnSH9PzSlNSiYr281BJHU0sjcyNjVzMzIxNHC1cLczM3MyNTM0tHE1NzV0c XM2NzY1MTR0tnBi5OAZh11/3Z/+muU/3/cbtYuGCexSRRwe3aR1RL7hTsv3NO0Hjnect1AqEbDv hzpuUENHXXrHijq/1k17yCBZK39hjmrD985preY4nthzME9LatXrnZ36BA3cBWQF42P/R+oF9A0 s5QnTPvuk5nCO92nHoqdJfjaldfhq2ztO9cNn116sMFh6QrPYl8t3/obJsok3T3s/HnY2tCWs+U bJTUcN94xL/reH/exNlrHINiPz810PjlLmm6UYgn68qftm0JtkXxrwMzRPZOUj/wm3mH4q78Y36 fXcRX9W0Oisq4wNbgZHIzMyL5RfLJirN//dxcF724oKkg8fLd7YeTvFec8Vv97JOPxf+E8KdH54 X1vT6S6GLu9gcA X-Developer-Key: i=dirk@gouders.net; a=openpgp; fpr=943B4FA3CAB8EBC55754E5EA0DA2395F431875F6 utf8_strnwidth() can be called with boundaries that effectively cause incomplete multibyte sequences and we should return "len" in such cases. But, utf8_width is used without its optional boundary argument and will thus work beyond the given boundary. Fix this by using the boundary argument for utf8_width. Add some tests that cover such situations. Signed-off-by: Dirk Gouders --- t/unit-tests/u-utf8-ansi.c | 26 ++++++++++++++++++++++++++ t/unit-tests/u-utf8-width.c | 9 +++++++++ utf8.c | 40 +++++++++++++++++++++++++++++----------- utf8.h | 1 + 4 files changed, 65 insertions(+), 11 deletions(-) diff --git a/t/unit-tests/u-utf8-ansi.c b/t/unit-tests/u-utf8-ansi.c index cb75c8612b..909643d07d 100644 --- a/t/unit-tests/u-utf8-ansi.c +++ b/t/unit-tests/u-utf8-ansi.c @@ -2,6 +2,32 @@ #include "utf8.h" #include "strbuf.h" +/* + * Test the greedy function display_mode_esc_sequence_len_all(). + */ +void test_utf8_ansi__sgr_len_greedy(void) +{ + char *s1 = (char *)"no ESC sequence"; + char *s2 = (char *)"\033[m"; + char *s3 = (char *)"\033[0;31m"; + char *s4 = (char *)"\033[0m\033[31m"; + + /* no sequences */ + cl_assert_equal_i(0, display_mode_esc_sequence_len_all("", "")); + cl_assert_equal_i(0, display_mode_esc_sequence_len_all(s1, s1 + 5)); + + /* single sequences */ + cl_assert_equal_i(3, display_mode_esc_sequence_len_all(s2, s2 + 3)); + cl_assert_equal_i(7, display_mode_esc_sequence_len_all(s3, s3 + 7)); + cl_assert_equal_i(0, display_mode_esc_sequence_len_all(s3, s3 + 3)); + + /* multiple sequences */ + cl_assert_equal_i(4, display_mode_esc_sequence_len_all(s4, s4 + 4)); + cl_assert_equal_i(9, display_mode_esc_sequence_len_all(s4, s4 + 9)); + cl_assert_equal_i(0, display_mode_esc_sequence_len_all(s4, s4 + 3)); + cl_assert_equal_i(4, display_mode_esc_sequence_len_all(s4, s4 + 8)); +} + /* * Test display_mode_esc_sequence_len() for NUL terminated strings. */ diff --git a/t/unit-tests/u-utf8-width.c b/t/unit-tests/u-utf8-width.c index 5e2b636db9..c4df4dd6a6 100644 --- a/t/unit-tests/u-utf8-width.c +++ b/t/unit-tests/u-utf8-width.c @@ -2,6 +2,15 @@ #include "utf8.h" #include "strbuf.h" +/* + * Test utf8_strnwidth for cjk characters invalidated by len argument. + */ +void test_utf8_width__strnwidth_cjk_chopped(void) +{ + cl_assert_equal_i(1, utf8_strnwidth("三bytes long, 二columns wide", 1, 1)); + cl_assert_equal_i(2, utf8_strnwidth("三bytes long, 二columns wide", 3, 1)); +} + /* * Test utf8_strnwidth for strings with SGR sequences and corner case length * arguments. diff --git a/utf8.c b/utf8.c index 493f723e3b..9478985cbb 100644 --- a/utf8.c +++ b/utf8.c @@ -39,6 +39,26 @@ size_t display_mode_esc_sequence_len(const char *start, const char *end) return p - start; } +/* + * Count the lenght of all leading ANSI display mode escape sequences that + * are a prefix of the string at start up to end. + */ +size_t display_mode_esc_sequence_len_all(const char *start, const char *end) +{ + size_t seq_len = 0; + + while (start + seq_len < end) { + size_t count = display_mode_esc_sequence_len(start + seq_len, end); + + if (!count) + break; + + seq_len += count; + } + + return seq_len; +} + /* auxiliary function for binary search in interval table */ static int bisearch(ucs_char_t ucs, const struct interval *table, int max) { @@ -224,17 +244,18 @@ int utf8_strnwidth(const char *string, size_t len, int skip_ansi) while (string && string < end) { int glyph_width; - size_t skip; + size_t remainder; if (skip_ansi) { - while ((skip = display_mode_esc_sequence_len(string, end))) - string += skip; + string += display_mode_esc_sequence_len_all(string, end); if (string >= end) break; } - glyph_width = utf8_width(&string, NULL); + remainder = end - string; + + glyph_width = utf8_width(&string, &remainder); if (glyph_width > 0) width += glyph_width; } @@ -311,10 +332,8 @@ void strbuf_add_wrapped_text(struct strbuf *buf, for (;;) { char c; - size_t skip; - while ((skip = display_mode_esc_sequence_len(text, end))) - text += skip; + text += display_mode_esc_sequence_len_all(text, end); c = *text; if (!c || isspace(c)) { @@ -392,10 +411,9 @@ void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width, int glyph_width; size_t n; - while ((n = display_mode_esc_sequence_len(src, end))) { - strbuf_add(&dst, src, n); - src += n; - } + n = display_mode_esc_sequence_len_all(src, end); + strbuf_add(&dst, src, n); + src += n; if (src >= end) break; diff --git a/utf8.h b/utf8.h index 7eb7bf042a..fdde5af782 100644 --- a/utf8.h +++ b/utf8.h @@ -6,6 +6,7 @@ struct strbuf; typedef unsigned int ucs_char_t; /* assuming 32bit int */ size_t display_mode_esc_sequence_len(const char *start, const char *end); +size_t display_mode_esc_sequence_len_all(const char *start, const char *end); int utf8_width(const char **start, size_t *remainder_p); int utf8_strnwidth(const char *string, size_t len, int skip_ansi); int utf8_strwidth(const char *string); -- 2.55.0