diff options
author | Steve Bennett <steveb@workware.net.au> | 2017-12-14 20:27:53 +1000 |
---|---|---|
committer | Steve Bennett <steveb@workware.net.au> | 2017-12-31 11:47:55 +1000 |
commit | 6fd58cfc22b0968e71f67f378555aba74e392847 (patch) | |
tree | 58c8a628858657dded758c818361af325a235c8c /tests | |
parent | 2d2f74ebfeeb056130a37fec19189766a85cec81 (diff) | |
download | jimtcl-6fd58cfc22b0968e71f67f378555aba74e392847.zip jimtcl-6fd58cfc22b0968e71f67f378555aba74e392847.tar.gz jimtcl-6fd58cfc22b0968e71f67f378555aba74e392847.tar.bz2 |
utf8: Be more strict at rejecting invalid UTF-8 sequences.
RFC 3629 says:
Implementations of the decoding algorithm above MUST protect against
decoding invalid sequences
Signed-off-by: Steve Bennett <steveb@workware.net.au>
Diffstat (limited to 'tests')
-rw-r--r-- | tests/lsort.test | 20 | ||||
-rw-r--r-- | tests/utftcl.test | 5 |
2 files changed, 5 insertions, 20 deletions
diff --git a/tests/lsort.test b/tests/lsort.test index 69b7467..5808b89 100644 --- a/tests/lsort.test +++ b/tests/lsort.test @@ -203,24 +203,8 @@ test lsort-3.22 {lsort, unique sort with index} { } {0 4 5} test lsort-4.26 {DefaultCompare procedure, signed characters} utf8 { - set l [lsort [list "abc\u80" "abc"]] - set viewlist {} - foreach s $l { - set viewelem "" - set len [string length $s] - for {set i 0} {$i < $len} {incr i} { - set c [string index $s $i] - scan $c %c d - if {$d > 0 && $d < 128} { - append viewelem $c - } else { - append viewelem "\\[format %03o [expr {$d & 0xff}]]" - } - } - lappend viewlist $viewelem - } - set viewlist -} [list "abc" "abc\\200"] + lsort [list "abc\u80" "abc"] +} [list "abc" "abc\u80"] test lsort-5.1 "Sort case insensitive" { lsort -nocase {ba aB aa ce} diff --git a/tests/utftcl.test b/tests/utftcl.test index 33b8933..fac14ce 100644 --- a/tests/utftcl.test +++ b/tests/utftcl.test @@ -74,7 +74,8 @@ test utf-4.2 {Tcl_NumUtfChars: length 1} { test utf-4.3 {Tcl_NumUtfChars: long string} { testnumutfchars [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"] } {7} -test utf-4.4 {Tcl_NumUtfChars: #u0000} { +# This is an invalid utf-8 sequence. Not minimal, so should return 2 +test utf-4.4 {Tcl_NumUtfChars: #u0000} tcl { testnumutfchars [bytestring "\xC0\x80"] } {1} test utf-4.5 {Tcl_NumUtfChars: zero length, calc len} { @@ -86,7 +87,7 @@ test utf-4.6 {Tcl_NumUtfChars: length 1, calc len} { test utf-4.7 {Tcl_NumUtfChars: long string, calc len} { testnumutfchars [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"] 1 } {7} -test utf-4.8 {Tcl_NumUtfChars: #u0000, calc len} { +test utf-4.8 {Tcl_NumUtfChars: #u0000, calc len} tcl { testnumutfchars [bytestring "\xC0\x80"] 1 } {1} |