diff options
| author | Inaba Hiroto <inaba@st.rim.or.jp> | 2000-12-30 23:27:10 +0900 |
|---|---|---|
| committer | Jarkko Hietaniemi <jhi@iki.fi> | 2000-12-30 17:14:19 +0000 |
| commit | 1aa99e6b6d14c469ac825dde483d9c9f913a3ee2 (patch) | |
| tree | 76ac8dd0d9473e84a19f6184baa4eddb6337e7b1 /pp.c | |
| parent | 13e8c8e316d3839d0834fb8b851566b00d81e876 (diff) | |
| download | perl-1aa99e6b6d14c469ac825dde483d9c9f913a3ee2.tar.gz | |
more UTF8 test suites and an UTF8 patch
Message-ID: <3A4D722D.243AFD88@st.rim.or.jp>
Just the patch part for now, and the pragma renamed
as unicode::distinct.
p4raw-id: //depot/perl@8267
Diffstat (limited to 'pp.c')
| -rw-r--r-- | pp.c | 14 |
1 files changed, 10 insertions, 4 deletions
@@ -5739,9 +5739,9 @@ PP(pp_split) AV *ary; register IV limit = POPi; /* note, negative is forever */ SV *sv = POPs; - bool do_utf8 = DO_UTF8(sv); STRLEN len; register char *s = SvPV(sv, len); + bool do_utf8 = DO_UTF8(sv); char *strend = s + len; register PMOP *pm; register REGEXP *rx; @@ -5878,7 +5878,7 @@ PP(pp_split) SV *csv = CALLREG_INTUIT_STRING(aTHX_ rx); len = rx->minlen; - if (len == 1 && !tail) { + if (len == 1 && !(rx->reganch & ROPT_UTF8) && !tail) { STRLEN n_a; char c = *SvPV(csv, n_a); while (--limit) { @@ -5895,7 +5895,10 @@ PP(pp_split) XPUSHs(dstr); /* The rx->minlen is in characters but we want to step * s ahead by bytes. */ - s = m + (do_utf8 ? SvCUR(csv) : len); + if (do_utf8) + s = (char*)utf8_hop((U8*)m, len); + else + s = m + len; /* Fake \n at the end */ } } else { @@ -5914,7 +5917,10 @@ PP(pp_split) XPUSHs(dstr); /* The rx->minlen is in characters but we want to step * s ahead by bytes. */ - s = m + (do_utf8 ? SvCUR(csv) : len); /* Fake \n at the end */ + if (do_utf8) + s = (char*)utf8_hop((U8*)m, len); + else + s = m + len; /* Fake \n at the end */ } } } |