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=1795187498; b=Re2cjdAaHXs3hYW1lcAaBEkhDBWJ36kzFtJyytxXtVHx7gUuJ7/K62V2oAol1WwgfyCR ldg8GpCAX3GKtG+JbEEZRgwWr6DIctIy4ZptWw0+IYw1xQ2jlA+7FhV1SzYSjAQ01Gh9x kuQrg3VwFjM/I2HFTry1VCdsFDTCdfjlh3J24cEJf2+JzvcK7w1jsHZaZ3AMiyaXUWvQu mbBGIU4WqiwWmz3bdpM5GEtYHQPIPFh49RJZwfrG1G1okzlZfyoqh+eGZCcVjQOLSY5v/ z7c30Szu8vMDZr3UQ74z8nbyyW4ip/UYZuw39gAuUpSjl9xZDzEgMkonhDNr6ukA4mA== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795187498; 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=3OwlpOzQ/PLKdKJSIpz9xgotyrovZ7C8+JOZB1JHZHA=; b=aN1ndKVTkIorx/+rLbhu4Akut791IHBEZ63YZfVNvzPB3Q+R/kPRtHYx5Y7j08jmEx8A BnlQx6lpoexSvf+ugP8eY1Z4h2Kijfss+7rPtoU39uPtPG820OyjPYsh0wuW1gIEdhZML 7dbMn+dAcfYlRYYf2cnz5tekuwliYsivX39EBizCMt5ZI4YQNReXBLKZY0fXHXDAMw39j miJ+UigJLljr+Zyn6oLBR8o2GojX8qYCUy4dEX+qCpccY2udMxYAdfLNoRv7ZKg/hWFv+ gOEZFF20zhz0P8GvLwO1W7b7a8jlXvDpXli8g4H6pj3h6hm3jyAulZYToEhsD5e3DsQ== 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=OEpdS6y7; 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 87B2C606A332 for ; Fri, 20 Nov 2026 15:11:37 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 87B2C606A332 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=OEpdS6y7 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 6AKFBTTe2082197 (version=TLSv1.3 cipher=TLS_AES_256_GCM_SHA384 bits=256 verify=NO); Fri, 20 Nov 2026 16:11:31 +0100 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gouders.net; s=gnet; t=1795187492; bh=3OwlpOzQ/PLKdKJSIpz9xgotyrovZ7C8+JOZB1JHZHA=; h=From:Date:Subject:References:In-Reply-To:To:Cc; b=OEpdS6y717ncrCQTNgEeJE2wcFgo7RrH0vfSycSpnSCx1etybBWwwoDdQPQTG/0PK w0AUjnR56n663WGLlRKQkDL6LarMLdRdknxR0FEXeo33T9p8loYEij6YeotrvGwHZt MR7j35/4Drwh2Tf8O96NXEdWd7pqXUsNQHmSrnEA= From: Dirk Gouders Date: Fri, 20 Nov 2026 16:11:24 +0100 Subject: [PATCH v4 1/5] utf8: introduce bounds for display_mode_esc_sequence_len() 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-v4-1-5ff523db7285@gouders.net> References: <20261120-master-v4-0-5ff523db7285@gouders.net> In-Reply-To: <20261120-master-v4-0-5ff523db7285@gouders.net> To: git@vger.kernel.org Cc: Junio C Hamano , Dirk Gouders , Andy Koppe X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=openpgp-sha256; l=8301; i=dirk@gouders.net; h=from:subject:message-id; bh=dZWoVViLc8aoK9Uc7Krt+bY3/OHcS+o4n6GwpqUM7xY=; b=owGbwMvMwMW4JPzVNXNTrzmMp9WSGLIZkhUzqlQOxTar7C1f7RdbcPatrMXyP3UGE59+sOHXd pkRlVPSyTiBhYGRi6FKTJFl6aQiuzSVFS/KvqlmwgxiZQKZIi3SwAAELAx8uYl5pUY6Rnqm2oZ6 hkCGjpEDRI6fQSO9IN0hPb80JbWoWC8vtcTR1NLI3MjY1czMyMTRwtXC3MzNzMjUzNLRxNTc1dH FzNjc2NTE0dKZgYtTAGbdxNccDD3vm6Q28lYxhB+7oLWjN+Ax15nMbzaTu7bze9xoruVv2r0512 f9t/03695O32VmyzcjkukVg9qpl6oyWfsmeSZxLecMWLfqwdk/jb/4b/NxKG9lb34U3XVn6sfJl myhDDw9vy6u5GX9zqrxPUT9ratgZJqBTHLoggSOG18MbT71aykL1L45mGf3ksvhixm7YtZjvsQz Db5dhuXWGXELJ3w6uy45IuNo0q+ti5b+dvr96eihEvcctW8Hl6473LnsSM26mfqCL8uunQpbm9s eWmfOveXPCXkOA7WN6YdYpjWlMAZm7E4qSC2ul9/ZfVF4yRq95CMnft7OkJp3ezvTfKOIzvVP6h 6/19nFMWWBLwA= X-Developer-Key: i=dirk@gouders.net; a=openpgp; fpr=943B4FA3CAB8EBC55754E5EA0DA2395F431875F6 From: Junio C Hamano display_mode_esc_sequence_len() scans for an ANSI display mode escape sequence (e.g. "ESC [ 1 ; 31 m") at the start of a string, relying on NUL termination to stop. Some callers, however, work on a counted buffer: utf8_strnwidth() takes and must not scan past it, while strbuf_utf8_replace() and strbuf_add_wrapped_text() know (or can cheaply learn) the end. Introduce an optional end pointer to display_mode_esc_sequence_len() which then never reads *end or beyond when end is not NULL. If end is NULL, display_mode_esc_sequence_len() assumes a NUL terminated string as before. Andy Koppe pointed out the risk of performance degrading to O(n²) when functions process strings and have to check each position for an escape sequence [1]. This change doesn't carry this risk. Further, add thorough tests for both end pointer cases. [1] https://lore.kernel.org/git/CAHWeT-aWx1VwUjM+hZ--jjSAbcMenz5Mw11y9ouFavGndUMrSA@mail.gmail.com/ Cc: Andy Koppe Signed-off-by: Junio C Hamano Signed-off-by: Dirk Gouders --- Makefile | 1 + pretty.c | 2 +- t/meson.build | 1 + t/unit-tests/u-utf8-ansi.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++ utf8.c | 34 ++++++++++++++++---------- utf8.h | 2 +- 6 files changed, 85 insertions(+), 14 deletions(-) diff --git a/Makefile b/Makefile index 4c84eea6e2..db8f7f5c60 100644 --- a/Makefile +++ b/Makefile @@ -1563,6 +1563,7 @@ CLAR_TEST_SUITES += u-string-list CLAR_TEST_SUITES += u-strvec CLAR_TEST_SUITES += u-trailer CLAR_TEST_SUITES += u-urlmatch-normalization +CLAR_TEST_SUITES += u-utf8-ansi CLAR_TEST_SUITES += u-utf8-width CLAR_TEST_PROG = $(UNIT_TEST_BIN)/unit-tests$(X) CLAR_TEST_OBJS = $(patsubst %,$(UNIT_TEST_DIR)/%.o,$(CLAR_TEST_SUITES)) diff --git a/pretty.c b/pretty.c index d8a9f370f6..58dfeb61f4 100644 --- a/pretty.c +++ b/pretty.c @@ -1848,7 +1848,7 @@ static size_t format_and_pad_commit(struct strbuf *sb, /* in UTF-8 */ while (p > sb->buf && ch - p < 10 && *p != '\033') p--; if (*p != '\033' || - ch + 1 - p != display_mode_esc_sequence_len(p)) + ch + 1 - p != display_mode_esc_sequence_len(p, ch + 1)) break; /* * got a good ansi sequence, put it back to diff --git a/t/meson.build b/t/meson.build index 1cf1d95f70..ae7479a98e 100644 --- a/t/meson.build +++ b/t/meson.build @@ -26,6 +26,7 @@ clar_test_suites = [ 'unit-tests/u-strvec.c', 'unit-tests/u-trailer.c', 'unit-tests/u-urlmatch-normalization.c', + 'unit-tests/u-utf8-ansi.c', 'unit-tests/u-utf8-width.c', ] diff --git a/t/unit-tests/u-utf8-ansi.c b/t/unit-tests/u-utf8-ansi.c new file mode 100644 index 0000000000..cb75c8612b --- /dev/null +++ b/t/unit-tests/u-utf8-ansi.c @@ -0,0 +1,59 @@ +#include "unit-test.h" +#include "utf8.h" +#include "strbuf.h" + +/* + * Test display_mode_esc_sequence_len() for NUL terminated strings. + */ +void test_utf8_ansi__sgr_len_null(void) +{ + cl_assert_equal_i(0, display_mode_esc_sequence_len("", NULL)); + + cl_assert_equal_i(0, display_mode_esc_sequence_len("\033", NULL)); + cl_assert_equal_i(0, display_mode_esc_sequence_len("\033[", NULL)); + cl_assert_equal_i(3, display_mode_esc_sequence_len("\033[m", NULL)); + + cl_assert_equal_i(0, display_mode_esc_sequence_len("\033[3", NULL)); + cl_assert_equal_i(0, display_mode_esc_sequence_len("\033[31", NULL)); + cl_assert_equal_i(5, display_mode_esc_sequence_len("\033[31m", NULL)); + + cl_assert_equal_i(0, display_mode_esc_sequence_len("\033[31;", NULL)); + cl_assert_equal_i(6, display_mode_esc_sequence_len("\033[31;m", NULL)); + cl_assert_equal_i(7, display_mode_esc_sequence_len("\033[31;0m", NULL)); +} + +/* + * Test display_mode_esc_sequence_len() with end pointers. + */ +void test_utf8_ansi__sgr_len_end_ptr(void) +{ + char *sgr_1 = (char *)"\033[m"; + char *sgr_2 = (char *)"\033[31m"; + char *sgr_3 = (char *)"\033[31;m"; + char *sgr_4 = (char *)"\033[31;0m"; + + cl_assert_equal_i(0, display_mode_esc_sequence_len("", "")); + + cl_assert_equal_i(0, display_mode_esc_sequence_len(sgr_1, sgr_1 + 1)); + cl_assert_equal_i(0, display_mode_esc_sequence_len(sgr_1, sgr_1 + 2)); + cl_assert_equal_i(3, display_mode_esc_sequence_len(sgr_1, sgr_1 + 3)); + + cl_assert_equal_i(0, display_mode_esc_sequence_len(sgr_2, sgr_2 + 1)); + cl_assert_equal_i(0, display_mode_esc_sequence_len(sgr_2, sgr_2 + 2)); + cl_assert_equal_i(0, display_mode_esc_sequence_len(sgr_2, sgr_2 + 3)); + cl_assert_equal_i(0, display_mode_esc_sequence_len(sgr_2, sgr_2 + 4)); + cl_assert_equal_i(5, display_mode_esc_sequence_len(sgr_2, sgr_2 + 5)); + + cl_assert_equal_i(6, display_mode_esc_sequence_len(sgr_3, sgr_3 + sizeof(sgr_3) - 1)); + cl_assert_equal_i(7, display_mode_esc_sequence_len(sgr_4, sgr_4 + sizeof(sgr_4) - 1)); +} + +/* + * Test display_mode_esc_sequence_len() for swapped start and end pointers. + */ +void test_utf8_ansi__sgr_len_start_end_swap(void) +{ + char *sgr_1 = (char *)"\033[m"; + + cl_assert_equal_i(0, display_mode_esc_sequence_len(sgr_1 + 3, sgr_1)); +} diff --git a/utf8.c b/utf8.c index 96460cc414..48aa189624 100644 --- a/utf8.c +++ b/utf8.c @@ -16,18 +16,27 @@ struct interval { ucs_char_t last; }; -size_t display_mode_esc_sequence_len(const char *s) +/* + * Return the length of the ANSI display mode escape sequence (e.g., + * "\033[1;31m") that appears at the beginning of the string starting at start, + * or 0 if the string does not begin with a complete such sequence. + * If end is NULL, assume a NUL terminated string, else never look at *end or + * beyond. + */ +size_t display_mode_esc_sequence_len(const char *start, const char *end) { - const char *p = s; - if (*p++ != '\033') + const char *p = start; + + if ((end && end <= p) || *p++ != '\033') return 0; - if (*p++ != '[') + if ((end && end <= p) || *p++ != '[') return 0; - while (isdigit(*p) || *p == ';') + while (((end && p < end) || (!end && *p)) && (isdigit(*p) || *p == ';')) p++; - if (*p++ != 'm') + if ((end && end <= p) || (!end && !*p) || *p++ != 'm') return 0; - return p - s; + + return p - start; } /* auxiliary function for binary search in interval table */ @@ -210,15 +219,15 @@ int utf8_width(const char **start, size_t *remainder_p) */ int utf8_strnwidth(const char *string, size_t len, int skip_ansi) { - const char *orig = string; + const char *end = string + len; size_t width = 0; - while (string && string < orig + len) { + while (string && string < end) { int glyph_width; size_t skip; while (skip_ansi && - (skip = display_mode_esc_sequence_len(string)) != 0) + (skip = display_mode_esc_sequence_len(string, end))) string += skip; glyph_width = utf8_width(&string, NULL); @@ -279,6 +288,7 @@ void strbuf_add_wrapped_text(struct strbuf *buf, { int indent, w, assume_utf8 = 1; const char *bol, *space, *start = text; + const char *end = text + strlen(text); size_t orig_len = buf->len; if (width <= 0) { @@ -299,7 +309,7 @@ void strbuf_add_wrapped_text(struct strbuf *buf, char c; size_t skip; - while ((skip = display_mode_esc_sequence_len(text))) + while ((skip = display_mode_esc_sequence_len(text, end))) text += skip; c = *text; @@ -378,7 +388,7 @@ 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))) { + while ((n = display_mode_esc_sequence_len(src, end))) { strbuf_add(&dst, src, n); src += n; } diff --git a/utf8.h b/utf8.h index cf8ecb0f21..7eb7bf042a 100644 --- a/utf8.h +++ b/utf8.h @@ -5,7 +5,7 @@ struct strbuf; typedef unsigned int ucs_char_t; /* assuming 32bit int */ -size_t display_mode_esc_sequence_len(const char *s); +size_t display_mode_esc_sequence_len(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