Skip to content

Avoid some UTF8SKIPs #23695

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 5 commits into from
Closed

Avoid some UTF8SKIPs #23695

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8bb9817
regcomp.c: Avoid a UTF8SKIP
khwilliamson Sep 7, 2025
d0955c8
locale.c: Avoid a UTF8SKIP
khwilliamson Sep 8, 2025
1529196
regexec.c: regrepeat: Avoid UTF8SKIPs
khwilliamson Sep 8, 2025
8b8dbd7
toke.c: Remove unnecessary code
khwilliamson Sep 8, 2025
ea90d42
toke.c: Avoid some UTF8SKIPs
khwilliamson Sep 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 11 additions & 4 deletions locale.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -944,9 +944,16 @@ S_get_displayable_string(pTHX_
SAVEFREEPV(ret);

while (t < e) {
UV cp = (is_utf8)
? utf8_to_uv_or_die((const U8 *) t, (const U8 *) e, NULL)
: * (U8 *) t;
UV cp;
Size_t advance;
if (is_utf8) {
cp = utf8_to_uv_or_die((const U8 *) t, (const U8 *) e, &advance);
}
else {
cp = *t;
advance = 1;
}

if (isPRINT(cp)) {
if (! prev_was_printable) {
my_strlcat(ret, " ", size);
Expand All @@ -966,7 +973,7 @@ S_get_displayable_string(pTHX_
my_strlcat(ret, form("%02" UVXf, cp), size);
prev_was_printable = FALSE;
}
t += (is_utf8) ? UTF8SKIP(t) : 1;
t += advance;
first_time = FALSE;
}

Expand Down
5 changes: 3 additions & 2 deletions regcomp.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8183,10 +8183,11 @@ S_handle_possible_posix(pTHX_ RExC_state_t *pRExC_state,
p++;
}
else {
Size_t advance;
input_text[name_len++] = utf8_to_uv_or_die((const U8 *) p,
(const U8 *) e,
NULL);
p+= UTF8SKIP(p);
&advance);
p += advance;
}

/* The declaration of 'input_text' is how long we allow a potential
Expand Down
25 changes: 13 additions & 12 deletions regexec.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10461,6 +10461,7 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p,

switch (with_t_UTF8ness(OP(p), utf8_target)) {
SV * anyofh_list;
Size_t advance;

case REG_ANY_t8:
while (scan < this_eol && hardcount < max && *scan != '\n') {
Expand Down Expand Up @@ -10746,9 +10747,9 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p,
&& _invlist_contains_cp(anyofh_list,
utf8_to_uv_or_die((U8 *) scan,
(U8 *) this_eol,
NULL)))
&advance)))
{
scan += UTF8SKIP(scan);
scan += advance;
hardcount++;
}
break;
Expand All @@ -10762,9 +10763,9 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p,
&& _invlist_contains_cp(anyofh_list,
utf8_to_uv_or_die((U8 *) scan,
(U8 *) this_eol,
NULL)))
&advance)))
{
scan += UTF8SKIP(scan);
scan += advance;
hardcount++;
}
break;
Expand Down Expand Up @@ -10792,9 +10793,9 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p,
&& _invlist_contains_cp(anyofh_list,
utf8_to_uv_or_die((U8 *) scan,
(U8 *) this_eol,
NULL)))
&advance)))
{
scan += UTF8SKIP(scan);
scan += advance;
hardcount++;
}
break;
Expand All @@ -10807,9 +10808,9 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p,
&& _invlist_contains_cp(anyofh_list,
utf8_to_uv_or_die((U8 *) scan,
(U8 *) this_eol,
NULL)))
&advance)))
{
scan += UTF8SKIP(scan);
scan += advance;
hardcount++;
}
break;
Expand All @@ -10820,10 +10821,10 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p,
&& NATIVE_UTF8_TO_I8(*scan) >= ANYOF_FLAGS(p)
&& withinCOUNT(utf8_to_uv_or_die((U8 *) scan,
(U8 *) this_eol,
NULL),
&advance),
ANYOFRbase(p), ANYOFRdelta(p)))
{
scan += UTF8SKIP(scan);
scan += advance;
hardcount++;
}
break;
Expand All @@ -10844,10 +10845,10 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p,
&& (U8) *scan == ANYOF_FLAGS(p)
&& withinCOUNT(utf8_to_uv_or_die((U8 *) scan,
(U8 *) this_eol,
NULL),
&advance),
ANYOFRbase(p), ANYOFRdelta(p)))
{
scan += UTF8SKIP(scan);
scan += advance;
hardcount++;
}
break;
Expand Down
14 changes: 8 additions & 6 deletions toke.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -730,7 +730,7 @@ S_warn_expect_operator(pTHX_ const char *const what, char *s, I32 pop_oldbufptr)
const char *t= oldbp;
assert(s >= oldbp);
while (t < s && isSPACE(*t)) {
t += UTF ? UTF8SKIP(t) : 1;
t++;
}

sv_catpvf(message,
Expand Down Expand Up @@ -2964,14 +2964,15 @@ Perl_get_and_check_backslash_N_name(pTHX_ const char* s,
s += 2;
}
else {
Size_t advance;
if (! _invlist_contains_cp(PL_utf8_charname_begin,
utf8_to_uv_or_die((const U8 *) s,
(const U8 *) e,
NULL)))
&advance)))
{
goto bad_charname;
}
s += UTF8SKIP(s);
s += advance;
}

while (s < e) {
Expand All @@ -2992,14 +2993,15 @@ Perl_get_and_check_backslash_N_name(pTHX_ const char* s,
s += 2;
}
else {
Size_t advance;
if (! _invlist_contains_cp(PL_utf8_charname_continue,
utf8_to_uv_or_die((const U8 *) s,
(const U8 *) e,
NULL)))
&advance)))
{
goto bad_charname;
}
s += UTF8SKIP(s);
s += advance;
}
}
}
Expand Down Expand Up @@ -5390,7 +5392,7 @@ yyl_dollar(pTHX_ char *s)

while ( t < PL_bufend ) {
if (isSPACE(*t)) {
do { t += UTF ? UTF8SKIP(t) : 1; } while (t < PL_bufend && isSPACE(*t));
do { t++; } while (t < PL_bufend && isSPACE(*t));
/* consumed one or more space chars */
} else if (*t == '$' || *t == '@') {
/* could be more than one '$' like $$ref or @$ref */
Expand Down
Loading