1 # This set of tests is for UTF-16 and UTF-32 support, including Unicode
2 # properties. It is relevant only to the 16-bit and 32-bit libraries. The
3 # output is different for each library, so there are separate output files.
5 /ÃÃÃxxx/IB,utf,no_utf_check
10 # Check maximum character size
34 /\x{D55c}\x{ad6d}\x{C5B4}/IB,utf
35 \x{D55c}\x{ad6d}\x{C5B4}
37 /\x{65e5}\x{672c}\x{8a9e}/IB,utf
38 \x{65e5}\x{672c}\x{8a9e}
50 /[^ab\xC0-\xF0]/IB,utf
60 \x{100}\x{100}\x{100}\x{100\x{100}
66 /(\x{100}{0,2}a|x)/IB,utf
68 /(\x{100}{1,2}a|x)/IB,utf
72 /a\x{100}\x{101}*/IB,utf
74 /a\x{100}\x{101}+/IB,utf
88 /\x{100}abc(xyz(?1))/IB,utf
94 /\x{100}+\x{200}/IB,utf
101 XX\x{d800}\=no_utf_check
102 XX\x{da00}\=no_utf_check
103 XX\x{dc00}\=no_utf_check
104 XX\x{de00}\=no_utf_check
105 XX\x{dfff}\=no_utf_check
132 /(*CRLF)(*UTF16)(*BSR_UNICODE)a\Rb/I
134 /(*CRLF)(*UTF32)(*BSR_UNICODE)a\Rb/I
159 /\R*A/I,bsr=unicode,utf
167 /\sxxx\s/I,utf,tables=2
171 /\S \S/I,utf,tables=2
181 \= Expect bad offset error
202 \= Expect bad UTF-16 offset, or no match in 32-bit
204 \x{10000}ab\=offset=1
205 \= Expect 16-bit match, 32-bit no match
206 \x{10000}ab\=offset=2
208 \x{10000}ab\=offset=3
209 \= Expect no match in 16-bit, bad offset in 32-bit
210 \x{10000}ab\=offset=4
212 \x{10000}ab\=offset=5
219 /\w+\x{C4}/B,utf,tables=2
225 /\W+\x{C4}/B,utf,tables=2
231 /\W+\x{A1}/B,utf,tables=2
237 /X\s+\x{A0}/B,utf,tables=2
243 /\S+\x{A0}/B,utf,tables=2
249 /\x{a0}+\s!/B,utf,tables=2
256 /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/IBi,utf
258 /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/IB,utf
264 /\x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}/Ii,utf
265 \x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}
266 \x{451}\x{440}\x{441}\x{442}\x{443}\x{444}\x{445}\x{446}\x{447}\x{448}\x{449}\x{44a}\x{44b}\x{44c}\x{44d}\x{44e}\x{44f}
280 # Non-UTF characters should give errors in both 16-bit and 32-bit modes.
289 /\x{100}*\d(?R)/IB,utf
302 /[ab\x{100}]abc(xyz(?1))/IB,utf
316 /[\x{105}-\x{109}]/IBi,utf
361 /[\s[:^ascii:]]/B,ucp
366 # A special extra option allows excaped surrogate code points in 32-bit mode,
367 # but subjects containing them must not be UTF-checked. These patterns give
368 # errors in 16-bit mode.
370 /\x{d800}/I,utf,allow_surrogate_escapes
371 \x{d800}\=no_utf_check
373 /\udfff\o{157401}/utf,alt_bsux,allow_surrogate_escapes
374 \x{dfff}\x{df01}\=no_utf_check
376 # This has different starting code units in 8-bit mode.