mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-06 05:55:35 +00:00
ICU-5691 stop illegal HZ tilde sequences before the first byte that could start a new character
X-SVN-Rev: 24773
This commit is contained in:
parent
e10cfeebfe
commit
c801506d5d
2 changed files with 36 additions and 6 deletions
|
@ -198,10 +198,30 @@ UConverter_toUnicode_HZ_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
|
|||
/* if the first byte is equal to TILDE and the trail byte
|
||||
* is not a valid byte then it is an error condition
|
||||
*/
|
||||
mySourceChar = 0x7e00 | mySourceChar;
|
||||
targetUniChar = 0xffff;
|
||||
/*
|
||||
* Ticket 5691: consistent illegal sequences:
|
||||
* - We include at least the first byte in the illegal sequence.
|
||||
* - If any of the non-initial bytes could be the start of a character,
|
||||
* we stop the illegal sequence before the first one of those.
|
||||
*/
|
||||
myData->isEmptySegment = FALSE; /* different error here, reset this to avoid spurious future error */
|
||||
break;
|
||||
*err = U_ILLEGAL_ESCAPE_SEQUENCE;
|
||||
args->converter->toUBytes[0] = UCNV_TILDE;
|
||||
if( myData->isStateDBCS ?
|
||||
(0x21 <= mySourceChar && mySourceChar <= 0x7e) :
|
||||
mySourceChar <= 0x7f
|
||||
) {
|
||||
/* The current byte could be the start of a character: Back it out. */
|
||||
args->converter->toULength = 1;
|
||||
--mySource;
|
||||
} else {
|
||||
/* Include the current byte in the illegal sequence. */
|
||||
args->converter->toUBytes[1] = mySourceChar;
|
||||
args->converter->toULength = 2;
|
||||
}
|
||||
args->target = myTarget;
|
||||
args->source = mySource;
|
||||
return;
|
||||
}
|
||||
} else if(myData->isStateDBCS) {
|
||||
if(args->converter->toUnicodeStatus == 0x00){
|
||||
|
|
16
icu4c/source/test/testdata/conversion.txt
vendored
16
icu4c/source/test/testdata/conversion.txt
vendored
|
@ -162,6 +162,16 @@ conversion:table(nofallback) {
|
|||
:intvector{ 0,1,1,1,1,2,3,8,11,13,14,14,14,14,15,16 },
|
||||
:int{1}, :int{0}, "", "&C", :bin{""}
|
||||
}
|
||||
// HZ with illegal tilde sequences.
|
||||
{
|
||||
"HZ",
|
||||
:bin{ 417e20427e21437e80447e7b41417e207e41427e7f41437e7d5a },
|
||||
"A\\x7E B\\x7E!C\\x7E\\x80D\u4eae\\x7E\\x20\\x7E\u8c05\\x7E\\x7F\u64a9Z",
|
||||
:intvector{ 0,1,1,1,1,2,3,4,4,4,4,5,6,7,7,7,7,7,7,7,7,9, // SBCS
|
||||
12,14,14,14,14,14,14,14,14,16,16,16,16,17,19,19,19,19,19,19,19,19,21, // DBCS
|
||||
25 }, // SBCS
|
||||
:int{1}, :int{0}, "", "&C", :bin{""}
|
||||
}
|
||||
// Test bug 6071 (2:1 Unicode:charset SBCS mapping).
|
||||
{
|
||||
"*test1bmp",
|
||||
|
@ -173,9 +183,9 @@ conversion:table(nofallback) {
|
|||
// test that HZ limits its byte values to lead bytes 21..7d and trail bytes 21..7e
|
||||
{
|
||||
"HZ",
|
||||
:bin{ 7e7b21212120217e217f772100007e217e7d207e7e807e0a2b },
|
||||
"\u3000\ufffd\ufffd\u3013\ufffd\ufffd\u9ccc\ufffd\ufffd ~\ufffd+",
|
||||
:intvector{ 2,4,5,6,8,9,10,12,14,18,19,21,24 },
|
||||
:bin{ 7e7b21212120217e217f772100007e217e7e7d207e7e807e0a2b },
|
||||
"\u3000\ufffd\ufffd\u3013\ufffd\ufffd\u9ccc\ufffd\ufffd\u3013 ~\ufffd+",
|
||||
:intvector{ 2,4,5,6,8,9,10,12,14,15,19,20,22,25 },
|
||||
:int{1}, :int{1}, "", "?", :bin{""}
|
||||
}
|
||||
// improve coverage of ISO-2022-JP converter with hardcoded JIS X 0201 and
|
||||
|
|
Loading…
Add table
Reference in a new issue