diff options
| author | Jarkko Hietaniemi <jhi@iki.fi> | 2002-04-02 20:35:13 +0000 |
|---|---|---|
| committer | Jarkko Hietaniemi <jhi@iki.fi> | 2002-04-02 20:35:13 +0000 |
| commit | 872c91ae155f6880f8bf2b15c143bda5279a5794 (patch) | |
| tree | 663505dbece632b3e75b0158fb36720c2d54829f /utf8.c | |
| parent | b929be1d26aeff4c8c3d4bbd655731a23247ecc8 (diff) | |
| download | perl-872c91ae155f6880f8bf2b15c143bda5279a5794.tar.gz | |
What started as a small nit (the charnames test, nit found
be Hugo), ballooned a bit... the goal is Larry's wish that
illegal Unicode (such as U+FFFF) by default doesn't warn,
since what if somebody WANTS to create illegal Unicode?
Now getting close to this in the regex runtime.
(Also, fix more of my fixation that BOM would be U+FFFE.)
p4raw-id: //depot/perl@15689
Diffstat (limited to 'utf8.c')
| -rw-r--r-- | utf8.c | 16 |
1 files changed, 10 insertions, 6 deletions
@@ -64,13 +64,13 @@ Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags) ((uv >= 0xFDD0 && uv <= 0xFDEF && !(flags & UNICODE_ALLOW_FDD0)) || - ((uv & 0xFFFF) == 0xFFFE && - !(flags & UNICODE_ALLOW_FFFE)) + (UNICODE_IS_BYTE_ORDER_MARK(uv) && + !(flags & UNICODE_ALLOW_BOM)) || ((uv & 0xFFFF) == 0xFFFF && !(flags & UNICODE_ALLOW_FFFF))) && /* UNICODE_ALLOW_SUPER includes - * FFFEs and FFFFs beyond 0x10FFFF. */ + * FFFFs beyond 0x10FFFF. */ ((uv <= PERL_UNICODE_MAX) || !(flags & UNICODE_ALLOW_SUPER)) ) @@ -500,7 +500,8 @@ returned and retlen is set, if possible, to -1. UV Perl_utf8_to_uvchr(pTHX_ U8 *s, STRLEN *retlen) { - return Perl_utf8n_to_uvchr(aTHX_ s, UTF8_MAXLEN, retlen, 0); + return Perl_utf8n_to_uvchr(aTHX_ s, UTF8_MAXLEN, retlen, + ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); } /* @@ -523,7 +524,8 @@ UV Perl_utf8_to_uvuni(pTHX_ U8 *s, STRLEN *retlen) { /* Call the low level routine asking for checks */ - return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXLEN, retlen, 0); + return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXLEN, retlen, + ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); } /* @@ -1626,7 +1628,9 @@ Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr, bool do_utf8) /* We use utf8n_to_uvuni() as we want an index into Unicode tables, not a native character number. */ - UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXLEN, NULL, 0); + UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXLEN, 0, + ckWARN(WARN_UTF8) ? + 0 : UTF8_ALLOW_ANY); SV *errsv_save; ENTER; SAVETMPS; |