diff options
| author | Karl Williamson <khw@cpan.org> | 2017-08-05 21:47:08 -0600 |
|---|---|---|
| committer | Karl Williamson <khw@cpan.org> | 2017-08-05 22:10:05 -0600 |
| commit | d819dc506b9fbd0d9bb316e42ca5bbefdd5f1d77 (patch) | |
| tree | 085700c1685076094cc365f0d6e8bddb4ae79daf | |
| parent | 3b890f763b669e3019e714e174a3d3dfc5075f55 (diff) | |
| download | perl-d819dc506b9fbd0d9bb316e42ca5bbefdd5f1d77.tar.gz | |
utf8_to_uvchr() EBCDIC fix
This fixes a warning message for EBCDIC. The native character set is
different than Unicode, and needs special handling. I earlier tried to
save an #ifdef, but the resulting warning was hard to test right, and
that helped convince me that it would be confusing to anyone trying to
make sense of the message. So, in goes the #ifdef.
| -rw-r--r-- | ext/XS-APItest/t/utf8_warn_base.pl | 2 | ||||
| -rw-r--r-- | utf8.c | 16 |
2 files changed, 12 insertions, 6 deletions
diff --git a/ext/XS-APItest/t/utf8_warn_base.pl b/ext/XS-APItest/t/utf8_warn_base.pl index 07652e8353..0f781c4002 100644 --- a/ext/XS-APItest/t/utf8_warn_base.pl +++ b/ext/XS-APItest/t/utf8_warn_base.pl @@ -121,7 +121,7 @@ my @tests; ], [ "overlong malformation, highest 2-byte", (isASCII) ? "\xc1\xbf" : I8_to_native("\xc4\xbf"), - (isASCII) ? 0x7F : 0x9F, # Output as U+, so no need to xlate + (isASCII) ? 0x7F : 0xFF, ], [ "overlong malformation, lowest 3-byte", (isASCII) ? "\xe0\x80\x80" : I8_to_native("\xe0\xa0\xa0"), @@ -1875,11 +1875,17 @@ Perl_utf8n_to_uvchr_error(pTHX_ const U8 *s, } else { U8 tmpbuf[UTF8_MAXBYTES+1]; - const U8 * const e = uvoffuni_to_utf8_flags(tmpbuf, - uv, 0); - const char * preface = (uv <= PERL_UNICODE_MAX) - ? "U+" - : "0x"; + const U8 * const e = uvchr_to_utf8_flags(tmpbuf, + uv, 0); + /* Don't use U+ for non-Unicode code points, which + * includes those in the Latin1 range */ + const char * preface = ( uv > PERL_UNICODE_MAX +#ifdef EBCDIC + || uv <= 0xFF +#endif + ) + ? "0x" + : "U+"; message = Perl_form(aTHX_ "%s: %s (overlong; instead use %s to represent" " %s%0*" UVXf ")", |