All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] utf8: make display_mode_esc_sequence_len() take a length
@ 2026-11-17 16:50 Junio C Hamano
  2026-11-17 20:06 ` [PATCH v2] utf8: add display_mode_esc_sequence_len_counted() Junio C Hamano
  0 siblings, 1 reply; 11+ messages in thread
From: Junio C Hamano @ 2026-11-17 16:50 UTC (permalink / raw)
  To: git; +Cc: Dirk Gouders

display_mode_esc_sequence_len() scans for an ANSI display mode
escape sequence (e.g. "ESC [ 1 ; 31 m"), relying on NUL termination
to stop.  Some callers, however, use a counted <ptr, len> buffer or
need to stop at a specific position.

Teach it to take a buffer length and never read at or beyond
ptr[len], returning the length of a complete sequence at the start
or 0 otherwise.

Update the callers to pass the remaining byte count.  For
strbuf_add_wrapped_text(), which takes a NUL-terminated string,
compute the end once upfront instead of calling strlen() each time.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 * Copy of https://lore.kernel.org/git/xmqqse0zfn2n.fsf@gitster.g/
   with a proposed commit log message.

 pretty.c |  3 ++-
 utf8.c   | 27 ++++++++++++++++++---------
 utf8.h   |  2 +-
 3 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/pretty.c b/pretty.c
index 0bc8ad8a9a..a20fd61909 100644
--- a/pretty.c
+++ b/pretty.c
@@ -1834,7 +1834,8 @@ 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 - p))
 				break;
 			/*
 			 * got a good ansi sequence, put it back to
diff --git a/utf8.c b/utf8.c
index 96460cc414..544c5329f3 100644
--- a/utf8.c
+++ b/utf8.c
@@ -16,16 +16,23 @@ 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 "len" bytes
+ * of string "s", or 0 if the bytes do not begin with a complete
+ * such sequence.  Never looks at s[len] or beyond.
+ */
+size_t display_mode_esc_sequence_len(const char *s, size_t len)
 {
-	const char *p = s;
-	if (*p++ != '\033')
+	const char *p = s, *end = s + len;
+
+	if (end <= p || *p++ != '\033')
 		return 0;
-	if (*p++ != '[')
+	if (end <= p || *p++ != '[')
 		return 0;
-	while (isdigit(*p) || *p == ';')
+	while (p < end && (isdigit(*p) || *p == ';'))
 		p++;
-	if (*p++ != 'm')
+	if (end <= p || *p++ != 'm')
 		return 0;
 	return p - s;
 }
@@ -218,7 +225,8 @@ int utf8_strnwidth(const char *string, size_t len, int skip_ansi)
 		size_t skip;
 
 		while (skip_ansi &&
-		       (skip = display_mode_esc_sequence_len(string)) != 0)
+		       (skip = display_mode_esc_sequence_len(string,
+							     orig + len - string)) != 0)
 			string += skip;
 
 		glyph_width = utf8_width(&string, NULL);
@@ -279,6 +287,7 @@ 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 +308,7 @@ 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)))
 			text += skip;
 
 		c = *text;
@@ -378,7 +387,7 @@ 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 - src))) {
 			strbuf_add(&dst, src, n);
 			src += n;
 		}
diff --git a/utf8.h b/utf8.h
index cf8ecb0f21..fb2227a9e2 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 *s, size_t len);
 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);
-- 
2.56.1-740-gf38658f3d0


^ permalink raw reply related	[flat|nested] 11+ messages in thread

end of thread, other threads:[~2026-11-18  7:43 UTC | newest]

Thread overview: 11+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-17 16:50 [PATCH] utf8: make display_mode_esc_sequence_len() take a length Junio C Hamano
2026-11-17 20:06 ` [PATCH v2] utf8: add display_mode_esc_sequence_len_counted() Junio C Hamano
2026-11-17 21:26   ` Dirk Gouders
2026-11-17 21:43     ` Junio C Hamano
2026-11-17 22:03       ` Dirk Gouders
2026-11-18  1:33         ` Junio C Hamano
2026-11-18  7:37           ` Dirk Gouders
2026-11-17 23:08   ` Andy Koppe
2026-11-17 23:25     ` Junio C Hamano
2026-11-18  6:59       ` Andy Koppe
2026-11-18  7:43         ` Dirk Gouders

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.