Re: [PATCH v2] utf8: add display_mode_esc_sequence_len_counted()
- From
Dirk Gouders <dirk@gouders.net>
- Date
- Nov 17, 2026, 21:26 UTC
- Message-ID
- <ghy0arkv39.fsf@gouders.net>
- In-Reply-To
- <xmqqqzgjcjes.fsf@gitster.g>
On Tue, Nov 17 2026, Junio C Hamano wrote:
Show 47 quoted lines
> 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 <string, len> and must not
> scan past it, while strbuf_utf8_replace() and
> strbuf_add_wrapped_text() know (or can cheaply learn) the end.
>
> Add display_mode_esc_sequence_len_counted() taking <ptr, len>,
> which never reads at or beyond ptr[len], and make
> display_mode_esc_sequence_len() a thin wrapper for NUL-terminated
> strings.
>
> Use the counted variant in utf8_strnwidth() for correctness, and in
> strbuf_utf8_replace() and strbuf_add_wrapped_text() (computing the
> end once upfront in the latter) to avoid measuring the remaining
> text in each iteration.
>
> Signed-off-by: Junio C Hamano <gitster@pobox.com>
> ---
> * As there are new patches that want to add new callers to this
> function, let's keep the original with the same API while adding
> a new helper function that allows us to limit the scan.
>
> utf8.c | 35 ++++++++++++++++++++++++++---------
> utf8.h | 1 +
> 2 files changed, 27 insertions(+), 9 deletions(-)
>
> diff --git a/utf8.c b/utf8.c
> index 96460cc414..d0546ab31f 100644
> --- a/utf8.c
> +++ b/utf8.c
> @@ -16,20 +16,33 @@ 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_counted(const char *s, size_t len)
> {
> - const char *p = s;
> - if (*p++ != '\033')
> + const char *p = s, *end = s + len;You have better knowledge of the users of this function: would an early return perhaps handle a significant amount of cases?
/* The shortest SGR sequence is "\033[m". */
if (len < 3)
return 0;And, why not add some tests (the untested function I showed had an off-by-one error):
diff --git a/Makefile b/Makefile index 4c84eea6e2..3c8dc9ca40 100644 --- a/Makefile +++ b/Makefile @@ -1564,6 +1564,7 @@ CLAR_TEST_SUITES += u-strvec CLAR_TEST_SUITES += u-trailer CLAR_TEST_SUITES += u-urlmatch-normalization CLAR_TEST_SUITES += u-utf8-width +CLAR_TEST_SUITES += u-utf8-ansi CLAR_TEST_PROG = $(UNIT_TEST_BIN)/unit-tests$(X) CLAR_TEST_OBJS = $(patsubst %,$(UNIT_TEST_DIR)/%.o,$(CLAR_TEST_SUITES)) CLAR_TEST_OBJS += $(UNIT_TEST_DIR)/clar/clar.o diff --git a/t/meson.build b/t/meson.build index 1cf1d95f70..e224df58c8 100644 --- a/t/meson.build +++ b/t/meson.build @@ -27,6 +27,7 @@ clar_test_suites = [ 'unit-tests/u-trailer.c', 'unit-tests/u-urlmatch-normalization.c', 'unit-tests/u-utf8-width.c', + 'unit-tests/u-utf8-ansi.c', ] clar_sources = [ diff --git a/t/unit-tests/u-utf8-ansi.c b/t/unit-tests/u-utf8-ansi.c new file mode 100644 index 0000000000..c19d8bce78 --- /dev/null +++ b/t/unit-tests/u-utf8-ansi.c @@ -0,0 +1,14 @@ +#include "unit-test.h" +#include "utf8.h" +#include "strbuf.h" + +/* + * Test len limited functions for ANSI SGR lengths. + */ +void test_utf8_ansi__sgr_len(void) +{ + cl_assert_equal_i(0, display_mode_esc_sequence_len_counted("\033[m", 2)); + cl_assert_equal_i(3, display_mode_esc_sequence_len_counted("\033[m", 3)); + cl_assert_equal_i(5, display_mode_esc_sequence_len_counted("\033[31m", 5)); + cl_assert_equal_i(7, display_mode_esc_sequence_len_counted("\033[0;31m", 7)); +} Regards, Dirk > + 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; > } > > +/* Same as above, but for a NUL-terminated string "s". */ > +size_t display_mode_esc_sequence_len(const char *s) > +{ > + return display_mode_esc_sequence_len_counted(s, strlen(s)); > +} > + > /* auxiliary function for binary search in interval table */ > static int bisearch(ucs_char_t ucs, const struct interval *table, int max) > { > @@ -218,7 +231,8 @@ 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_counted(string, > + orig + len - string)) != 0) > string += skip; > > glyph_width = utf8_width(&string, NULL); > @@ -279,6 +293,7 @@ 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 +314,8 @@ 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_counted(text, > + end - text))) > text += skip; > > c = *text; > @@ -378,7 +394,8 @@ 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_counted(src, > + end - src))) { > strbuf_add(&dst, src, n); > src += n; > } > diff --git a/utf8.h b/utf8.h > index cf8ecb0f21..57ca2ab270 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 *s); > +size_t display_mode_esc_sequence_len_counted(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);