In perl.git, the branch blead has been updated
<https://perl5.git.perl.org/perl.git/commitdiff/39cd6e6a879395d79d698d684b3839f9423d1607?hp=d0d8d0cb339722488ab4472815d936625b06704b>
- Log -----------------------------------------------------------------
commit 39cd6e6a879395d79d698d684b3839f9423d1607
Author: Karl Williamson <k...@cpan.org>
Date: Sun Oct 28 21:24:22 2018 -0600
regcomp.c: Make sure UTF-8 regex pattern uses /u
When a pattern is in UTF-8, Unicode rules should be selected. This
commit makes sure that this happens and that the displayable form of the
pattern shows /u.
I don't know of any bugs this fixes.
-----------------------------------------------------------------------
Summary of changes:
regcomp.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/regcomp.c b/regcomp.c
index 0a7940d0ef..3549619aae 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -6967,7 +6967,7 @@ S_set_regex_pv(pTHX_ RExC_state_t *pRExC_state, REGEXP
*Rx)
* properly wrapped with the right modifiers */
bool has_p = ((RExC_rx->extflags & RXf_PMf_KEEPCOPY) ==
RXf_PMf_KEEPCOPY);
- bool has_charset = (get_regex_charset(RExC_rx->extflags)
+ bool has_charset = RExC_utf8 || (get_regex_charset(RExC_rx->extflags)
!= REGEX_DEPENDS_CHARSET);
/* The caret is output if there are any defaults: if not all the STD
@@ -7011,7 +7011,14 @@ S_set_regex_pv(pTHX_ RExC_state_t *pRExC_state, REGEXP
*Rx)
}
if (has_charset) {
STRLEN len;
- const char* const name = get_regex_charset_name(RExC_rx->extflags,
&len);
+ const char* name;
+
+ name = get_regex_charset_name(RExC_rx->extflags, &len);
+ if strEQ(name, DEPENDS_PAT_MODS) { /* /d under UTF-8 => /u */
+ assert(RExC_utf8);
+ name = UNICODE_PAT_MODS;
+ len = sizeof(UNICODE_PAT_MODS) - 1;
+ }
Copy(name, p, len, char);
p += len;
}
--
Perl5 Master Repository
