From: Junio C Hamano Date: Tue, 17 Nov 2026 16:18:56 GMT Subject: Re: [PATCH 1/2] utf8: respect bounds in utf8_strnwidth() Message-ID: In-Reply-To: Junio C Hamano writes: > The problem is well spotted, but isn't the blame slightly misplaced? > ... > Even if display_mode_esc_sequence_len() were updated to take the > remaining number of bytes in string (which I think *is* a good > change, by the way), ... An update to display_mode_esc_sequence_len() to take the length limit, including its fallout, is shown below, and it does not look too bad. Not even compile-tested, but it should be sufficient as an illustration of the idea. This does not make your "after display_mode_esc_sequence_len() skips, make sure if we still have remaining string to grab one UTF-8 character" change unnecessary, as I said. pretty.c | 3 ++- utf8.c | 27 ++++++++++++++++++--------- utf8.h | 2 +- 3 files changed, 21 insertions(+), 11 deletions(-) diff --git c/pretty.c w/pretty.c index 0bc8ad8a9a..a20fd61909 100644 --- c/pretty.c +++ w/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 c/utf8.c w/utf8.c index 96460cc414..544c5329f3 100644 --- c/utf8.c +++ w/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 c/utf8.h w/utf8.h index cf8ecb0f21..fb2227a9e2 100644 --- c/utf8.h +++ w/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);