diff options
author | David Mitchell <davem@iabyn.com> | 2011-03-19 19:26:49 +0000 |
---|---|---|
committer | David Mitchell <davem@iabyn.com> | 2011-03-19 19:41:55 +0000 |
commit | 75da9d4c616bae3e6791af93d2ced52dc8080f06 (patch) | |
tree | 5c0043963158345e1bb1c1c21526aa604fa9f06f /lib | |
parent | 912c63ed00375338703043928cac3c740d00cc9d (diff) | |
download | perl-75da9d4c616bae3e6791af93d2ced52dc8080f06.tar.gz |
reset pos and utf8 cache when de/encoding utf8 str
When using
utf8::upgrade
utf8::downgrade
utf8::encode
utf8::decode
or the underlying C-level functions
sv_utf8_upgrade_flags_grow
sv_utf8_downgrade
sv_utf8_encode
sv_utf8_decode
and
sv_recode_to_utf8
update the position of the pos magic, if any, and clear the utf8
length/position-mapping cache.
This fixes [perl #80190].
Diffstat (limited to 'lib')
-rw-r--r-- | lib/utf8.t | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/lib/utf8.t b/lib/utf8.t index 715ca3e7e1..ae81ccdc46 100644 --- a/lib/utf8.t +++ b/lib/utf8.t @@ -484,4 +484,52 @@ SKIP: { } } +# #80190 update pos, and cached length/position-mapping after +# utf8 upgrade/downgrade, encode/decode + +for my $pos (0..5) { + + my $pos1 = ($pos >= 3) ? 2 : ($pos >= 1) ? 1 : 0; + my $pos2 = ($pos1 == 2) ? 3 : $pos1; + + my $p; + my $s = "A\xc8\x81\xe8\xab\x86\x{100}"; + chop($s); + + pos($s) = $pos; + # also sets cache + is(length($s), 6, "(pos $pos) len before utf8::downgrade"); + is(pos($s), $pos, "(pos $pos) pos before utf8::downgrade"); + utf8::downgrade($s); + is(length($s), 6, "(pos $pos) len after utf8::downgrade"); + is(pos($s), $pos, "(pos $pos) pos after utf8::downgrade"); + is($s, "A\xc8\x81\xe8\xab\x86","(pos $pos) str after utf8::downgrade"); + utf8::decode($s); + is(length($s), 3, "(pos $pos) len after D; utf8::decode"); + is(pos($s), $pos1, "(pos $pos) pos after D; utf8::decode"); + is($s, "A\x{201}\x{8ac6}", "(pos $pos) str after D; utf8::decode"); + utf8::encode($s); + is(length($s), 6, "(pos $pos) len after D; utf8::encode"); + is(pos($s), $pos2, "(pos $pos) pos after D; utf8::encode"); + is($s, "A\xc8\x81\xe8\xab\x86","(pos $pos) str after D; utf8::encode"); + + $s = "A\xc8\x81\xe8\xab\x86"; + + pos($s) = $pos; + is(length($s), 6, "(pos $pos) len before utf8::upgrade"); + is(pos($s), $pos, "(pos $pos) pos before utf8::upgrade"); + utf8::upgrade($s); + is(length($s), 6, "(pos $pos) len after utf8::upgrade"); + is(pos($s), $pos, "(pos $pos) pos after utf8::upgrade"); + is($s, "A\xc8\x81\xe8\xab\x86","(pos $pos) str after utf8::upgrade"); + utf8::decode($s); + is(length($s), 3, "(pos $pos) len after U; utf8::decode"); + is(pos($s), $pos1, "(pos $pos) pos after U; utf8::decode"); + is($s, "A\x{201}\x{8ac6}", "(pos $pos) str after U; utf8::decode"); + utf8::encode($s); + is(length($s), 6, "(pos $pos) len after U; utf8::encode"); + is(pos($s), $pos2, "(pos $pos) pos after U; utf8::encode"); + is($s, "A\xc8\x81\xe8\xab\x86","(pos $pos) str after U; utf8::encode"); +} + done_testing(); |