# This set of tests checks UTF and Unicode property support with the DFA # matching functionality of pcre2_dfa_match(). A default subject modifier is # used to force DFA matching for all tests. #subject dfa #newline_default LF any anyCRLF /\x{100}ab/utf \x{100}ab /a\x{100}*b/utf ab a\x{100}b a\x{100}\x{100}b /a\x{100}+b/utf a\x{100}b a\x{100}\x{100}b \= Expect no match ab /\bX/utf Xoanon +Xoanon \x{300}Xoanon \= Expect no match YXoanon /\BX/utf YXoanon \= Expect no match Xoanon +Xoanon \x{300}Xoanon /X\b/utf X+oanon ZX\x{300}oanon FAX \= Expect no match Xoanon /X\B/utf Xoanon \= Expect no match X+oanon ZX\x{300}oanon FAX /[^a]/utf abcd a\x{100} /^[abc\x{123}\x{400}-\x{402}]{2,3}\d/utf ab99 \x{123}\x{123}45 \x{400}\x{401}\x{402}6 \= Expect no match d99 \x{123}\x{122}4 \x{400}\x{403}6 \x{400}\x{401}\x{402}\x{402}6 /a.b/utf acb a\x7fb a\x{100}b \= Expect no match a\nb /a(.{3})b/utf a\x{4000}xyb a\x{4000}\x7fyb a\x{4000}\x{100}yb \= Expect no match a\x{4000}b ac\ncb /a(.*?)(.)/ a\xc0\x88b /a(.*?)(.)/utf a\x{100}b /a(.*)(.)/ a\xc0\x88b /a(.*)(.)/utf a\x{100}b /a(.)(.)/ a\xc0\x92bcd /a(.)(.)/utf a\x{240}bcd /a(.?)(.)/ a\xc0\x92bcd /a(.?)(.)/utf a\x{240}bcd /a(.??)(.)/ a\xc0\x92bcd /a(.??)(.)/utf a\x{240}bcd /a(.{3})b/utf a\x{1234}xyb a\x{1234}\x{4321}yb a\x{1234}\x{4321}\x{3412}b \= Expect no match a\x{1234}b ac\ncb /a(.{3,})b/utf a\x{1234}xyb a\x{1234}\x{4321}yb a\x{1234}\x{4321}\x{3412}b axxxxbcdefghijb a\x{1234}\x{4321}\x{3412}\x{3421}b \= Expect no match a\x{1234}b /a(.{3,}?)b/utf a\x{1234}xyb a\x{1234}\x{4321}yb a\x{1234}\x{4321}\x{3412}b axxxxbcdefghijb a\x{1234}\x{4321}\x{3412}\x{3421}b \= Expect no match a\x{1234}b /a(.{3,5})b/utf a\x{1234}xyb a\x{1234}\x{4321}yb a\x{1234}\x{4321}\x{3412}b axxxxbcdefghijb a\x{1234}\x{4321}\x{3412}\x{3421}b axbxxbcdefghijb axxxxxbcdefghijb \= Expect no match a\x{1234}b axxxxxxbcdefghijb /a(.{3,5}?)b/utf a\x{1234}xyb a\x{1234}\x{4321}yb a\x{1234}\x{4321}\x{3412}b axxxxbcdefghijb a\x{1234}\x{4321}\x{3412}\x{3421}b axbxxbcdefghijb axxxxxbcdefghijb \= Expect no match a\x{1234}b axxxxxxbcdefghijb /^[a\x{c0}]/utf \= Expect no match \x{100} /(?<=aXb)cd/utf aXbcd /(?<=a\x{100}b)cd/utf a\x{100}bcd /(?<=a\x{100000}b)cd/utf a\x{100000}bcd /(?:\x{100}){3}b/utf \x{100}\x{100}\x{100}b \= Expect no match \x{100}\x{100}b /\x{ab}/utf \x{ab} \xc2\xab \= Expect no match \x00{ab} /(?<=(.))X/utf WXYZ \x{256}XYZ \= Expect no match XYZ /[^a]+/g,utf bcd \x{100}aY\x{256}Z /^[^a]{2}/utf \x{100}bc /^[^a]{2,}/utf \x{100}bcAa /^[^a]{2,}?/utf \x{100}bca /[^a]+/gi,utf bcd \x{100}aY\x{256}Z /^[^a]{2}/i,utf \x{100}bc /^[^a]{2,}/i,utf \x{100}bcAa /^[^a]{2,}?/i,utf \x{100}bca /\x{100}{0,0}/utf abcd /\x{100}?/utf abcd \x{100}\x{100} /\x{100}{0,3}/utf \x{100}\x{100} \x{100}\x{100}\x{100}\x{100} /\x{100}*/utf abce \x{100}\x{100}\x{100}\x{100} /\x{100}{1,1}/utf abcd\x{100}\x{100}\x{100}\x{100} /\x{100}{1,3}/utf abcd\x{100}\x{100}\x{100}\x{100} /\x{100}+/utf abcd\x{100}\x{100}\x{100}\x{100} /\x{100}{3}/utf abcd\x{100}\x{100}\x{100}XX /\x{100}{3,5}/utf abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX /\x{100}{3,}/utf,no_auto_possess abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX /(?<=a\x{100}{2}b)X/utf Xyyya\x{100}\x{100}bXzzz /\D*/utf,no_auto_possess aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa /\D*/utf,no_auto_possess \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} /\D/utf 1X2 1\x{100}2 />\S/utf > >X Y > >\x{100} Y /\d/utf \x{100}3 /\s/utf \x{100} X /\D+/utf 12abcd34 \= Expect no match 1234 /\D{2,3}/utf 12abcd34 12ab34 \= Expect no match 1234 12a34 /\D{2,3}?/utf 12abcd34 12ab34 \= Expect no match 1234 12a34 /\d+/utf 12abcd34 /\d{2,3}/utf 12abcd34 1234abcd \= Expect no match 1.4 /\d{2,3}?/utf 12abcd34 1234abcd \= Expect no match 1.4 /\S+/utf 12abcd34 \= Expect no match \ \ /\S{2,3}/utf 12abcd34 1234abcd \= Expect no match \ \ /\S{2,3}?/utf 12abcd34 1234abcd \= Expect no match \ \ />\s+ <34 />\s{2,3} \s{2,3}? \xff< /[\xff]/utf >\x{ff}< /[^\xFF]/ XYZ /[^\xff]/utf XYZ \x{123} /^[ac]*b/utf \= Expect no match xb /^[ac\x{100}]*b/utf \= Expect no match xb /^[^x]*b/i,utf \= Expect no match xb /^[^x]*b/utf \= Expect no match xb /^\d*b/utf \= Expect no match xb /(|a)/g,utf catac a\x{256}a /^\x{85}$/i,utf \x{85} /^abc./gmx,newline=any,utf abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK /abc.$/gmx,newline=any,utf abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 /^a\Rb/bsr=unicode,utf a\nb a\rb a\r\nb a\x0bb a\x0cb a\x{85}b a\x{2028}b a\x{2029}b \= Expect no match a\n\rb /^a\R*b/bsr=unicode,utf ab a\nb a\rb a\r\nb a\x0bb a\x0c\x{2028}\x{2029}b a\x{85}b a\n\rb a\n\r\x{85}\x0cb /^a\R+b/bsr=unicode,utf a\nb a\rb a\r\nb a\x0bb a\x0c\x{2028}\x{2029}b a\x{85}b a\n\rb a\n\r\x{85}\x0cb \= Expect no match ab /^a\R{1,3}b/bsr=unicode,utf a\nb a\n\rb a\n\r\x{85}b a\r\n\r\nb a\r\n\r\n\r\nb a\n\r\n\rb a\n\n\r\nb \= Expect no match a\n\n\n\rb a\r /\h+\V?\v{3,4}/utf,no_auto_possess \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a /\V?\v{3,4}/utf,no_auto_possess \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a /\h+\V?\v{3,4}/utf,no_auto_possess >\x09\x20\x{a0}X\x0a\x0a\x0a< /\V?\v{3,4}/utf,no_auto_possess >\x09\x20\x{a0}X\x0a\x0a\x0a< /\H\h\V\v/utf X X\x0a X\x09X\x0b \= Expect no match \x{a0} X\x0a /\H*\h+\V?\v{3,4}/utf,no_auto_possess \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a \x09\x20\x{a0}\x0a\x0b\x0c \= Expect no match \x09\x20\x{a0}\x0a\x0b /\H\h\V\v/utf \x{3001}\x{3000}\x{2030}\x{2028} X\x{180e}X\x{85} \= Expect no match \x{2009} X\x0a /\H*\h+\V?\v{3,4}/utf,no_auto_possess \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a \x09\x20\x{202f}\x0a\x0b\x0c \= Expect no match \x09\x{200a}\x{a0}\x{2028}\x0b /a\Rb/I,bsr=anycrlf,utf a\rb a\nb a\r\nb \= Expect no match a\x{85}b a\x0bb /a\Rb/I,bsr=unicode,utf a\rb a\nb a\r\nb a\x{85}b a\x0bb /a\R?b/I,bsr=anycrlf,utf a\rb a\nb a\r\nb \= Expect no match a\x{85}b a\x0bb /a\R?b/I,bsr=unicode,utf a\rb a\nb a\r\nb a\x{85}b a\x0bb /X/newline=any,utf,firstline A\x{1ec5}ABCXYZ /abcd*/utf xxxxabcd\=ps xxxxabcd\=ph /abcd*/i,utf xxxxabcd\=ps xxxxabcd\=ph XXXXABCD\=ps XXXXABCD\=ph /abc\d*/utf xxxxabc1\=ps xxxxabc1\=ph /abc[de]*/utf xxxxabcde\=ps xxxxabcde\=ph /\bthe cat\b/utf the cat\=ps the cat\=ph /./newline=crlf,utf \r\=ps \r\=ph /.{2,3}/newline=crlf,utf \r\=ps \r\=ph \r\r\=ps \r\r\=ph \r\r\r\=ps \r\r\r\=ph /.{2,3}?/newline=crlf,utf \r\=ps \r\=ph \r\r\=ps \r\r\=ph \r\r\r\=ps \r\r\r\=ph /[^\x{100}]/utf \x{100}\x{101}X /[^\x{100}]+/utf \x{100}\x{101}X /\pL\P{Nd}/utf AB \= Expect no match A0 00 /\X./utf AB A\x{300}BC A\x{300}\x{301}\x{302}BC \= Expect no match \x{300} /\X\X/utf ABC A\x{300}B\x{300}\x{301}C A\x{300}\x{301}\x{302}BC \= Expect no match \x{300} /^\pL+/utf abcd a /^\PL+/utf 1234 = \= Expect no match abcd /^\X+/utf abcdA\x{300}\x{301}\x{302} A\x{300}\x{301}\x{302} A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} a \x{300}\x{301}\x{302} /\X?abc/utf abc A\x{300}abc A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz \x{300}abc /^\X?abc/utf abc A\x{300}abc \x{300}abc \= Expect no match A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz /\X*abc/utf abc A\x{300}abc A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz \x{300}abc /^\X*abc/utf abc A\x{300}abc A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz \x{300}abc /^\pL?=./utf A=b =c \= Expect no match 1=2 AAAA=b /^\pL*=./utf AAAA=b =c \= Expect no match 1=2 /^\X{2,3}X/utf A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X \= Expect no match X A\x{300}\x{301}\x{302}X A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X /^\pC\pL\pM\pN\pP\pS\pZ\p{Xsp}/utf >\x{1680}\x{2028}\x{0b} \= Expect no match \x{0b} /^>\p{Xsp}+/utf,no_auto_possess > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>\p{Xsp}*/utf,no_auto_possess > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>\p{Xsp}{2,9}/utf,no_auto_possess > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>[\p{Xsp}]/utf,no_auto_possess >\x{2028}\x{0b} /^>[\p{Xsp}]+/utf,no_auto_possess > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>\p{Xps}/utf >\x{1680}\x{2028}\x{0b} >\x{a0} \= Expect no match \x{0b} /^>\p{Xps}+/utf > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>\p{Xps}+?/utf >\x{1680}\x{2028}\x{0b} /^>\p{Xps}*/utf > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>\p{Xps}{2,9}/utf > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>\p{Xps}{2,9}?/utf > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^>[\p{Xps}]/utf >\x{2028}\x{0b} /^>[\p{Xps}]+/utf > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} /^\p{Xwd}/utf ABCD 1234 \x{6ca} \x{a6c} \x{10a7} _ABC \= Expect no match [] /^\p{Xwd}+/utf ABCD1234\x{6ca}\x{a6c}\x{10a7}_ /^\p{Xwd}*/utf ABCD1234\x{6ca}\x{a6c}\x{10a7}_ /^\p{Xwd}{2,9}/utf A_12\x{6ca}\x{a6c}\x{10a7} /^[\p{Xwd}]/utf ABCD1234_ 1234abcd_ \x{6ca} \x{a6c} \x{10a7} _ABC \= Expect no match [] /^[\p{Xwd}]+/utf ABCD1234\x{6ca}\x{a6c}\x{10a7}_ # Unicode properties for \b and \B /\b...\B/utf,ucp abc_ \x{37e}abc\x{376} \x{37e}\x{376}\x{371}\x{393}\x{394} !\x{c0}++\x{c1}\x{c2} !\x{c0}+++++ # Without PCRE_UCP, non-ASCII always fail, even if < 256 /\b...\B/utf abc_ \= Expect no match \x{37e}abc\x{376} \x{37e}\x{376}\x{371}\x{393}\x{394} !\x{c0}++\x{c1}\x{c2} !\x{c0}+++++ # With PCRE_UCP, non-UTF8 chars that are < 256 still check properties /\b...\B/ucp abc_ !\x{c0}++\x{c1}\x{c2} !\x{c0}+++++ # Caseless single negated characters > 127 need UCP support /[^\x{100}]/i,utf \x{100}\x{101}X /[^\x{100}]+/i,utf \x{100}\x{101}XX /^\X/utf A\=ps A\=ph A\x{300}\x{301}\=ps A\x{300}\x{301}\=ph A\x{301}\=ps A\x{301}\=ph /^\X{2,3}/utf A\=ps A\=ph AA\=ps AA\=ph A\x{300}\x{301}\=ps A\x{300}\x{301}\=ph A\x{300}\x{301}A\x{300}\x{301}\=ps A\x{300}\x{301}A\x{300}\x{301}\=ph /^\X{2}/utf AA\=ps AA\=ph A\x{300}\x{301}A\x{300}\x{301}\=ps A\x{300}\x{301}A\x{300}\x{301}\=ph /^\X+/utf AA\=ps AA\=ph /^\X+?Z/utf AA\=ps AA\=ph # These are tests for extended grapheme clusters /^\X/utf,aftertext G\x{34e}\x{34e}X \x{34e}\x{34e}X \x04X \x{1100}X \x{1100}\x{34e}X \x{1b04}\x{1b04}X \= These match up to the roman letters \x{1111}\x{1111}L,L \x{1111}\x{1111}\x{1169}L,L,V \x{1111}\x{ae4c}L, LV \x{1111}\x{ad89}L, LVT \x{1111}\x{ae4c}\x{1169}L, LV, V \x{1111}\x{ae4c}\x{1169}\x{1169}L, LV, V, V \x{1111}\x{ae4c}\x{1169}\x{11fe}L, LV, V, T \x{1111}\x{ad89}\x{11fe}L, LVT, T \x{1111}\x{ad89}\x{11fe}\x{11fe}L, LVT, T, T \x{ad89}\x{11fe}\x{11fe}LVT, T, T \= These match just the first codepoint (invalid sequence) \x{1111}\x{11fe}L, T \x{ae4c}\x{1111}LV, L \x{ae4c}\x{ae4c}LV, LV \x{ae4c}\x{ad89}LV, LVT \x{1169}\x{1111}V, L \x{1169}\x{ae4c}V, LV \x{1169}\x{ad89}V, LVT \x{ad89}\x{1111}LVT, L \x{ad89}\x{1169}LVT, V \x{ad89}\x{ae4c}LVT, LV \x{ad89}\x{ad89}LVT, LVT \x{11fe}\x{1111}T, L \x{11fe}\x{1169}T, V \x{11fe}\x{ae4c}T, LV \x{11fe}\x{ad89}T, LVT \= Test extend and spacing mark \x{1111}\x{ae4c}\x{0711}L, LV, extend \x{1111}\x{ae4c}\x{1b04}L, LV, spacing mark \x{1111}\x{ae4c}\x{1b04}\x{0711}\x{1b04}L, LV, spacing mark, extend, spacing mark \= Test CR, LF, and control \x0d\x{0711}CR, extend \x0d\x{1b04}CR, spacingmark \x0a\x{0711}LF, extend \x0a\x{1b04}LF, spacingmark \x0b\x{0711}Control, extend \x09\x{1b04}Control, spacingmark \= There are no Prepend characters, so we can't test Prepend, CR /^(?>\X{2})X/utf,aftertext \x{1111}\x{ae4c}\x{1111}\x{ae4c}X /^\X{2,4}X/utf,aftertext \x{1111}\x{ae4c}\x{1111}\x{ae4c}X \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X /^\X{2,4}?X/utf,aftertext \x{1111}\x{ae4c}\x{1111}\x{ae4c}X \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X /\x{1e9e}+/i,utf \x{1e9e}\x{00df} /[z\x{1e9e}]+/i,utf \x{1e9e}\x{00df} /\x{00df}+/i,utf \x{1e9e}\x{00df} /[z\x{00df}]+/i,utf \x{1e9e}\x{00df} /\x{1f88}+/i,utf \x{1f88}\x{1f80} /[z\x{1f88}]+/i,utf \x{1f88}\x{1f80} # Perl matches these /\x{00b5}+/i,utf \x{00b5}\x{039c}\x{03bc} /\x{039c}+/i,utf \x{00b5}\x{039c}\x{03bc} /\x{03bc}+/i,utf \x{00b5}\x{039c}\x{03bc} /\x{00c5}+/i,utf \x{00c5}\x{00e5}\x{212b} /\x{00e5}+/i,utf \x{00c5}\x{00e5}\x{212b} /\x{212b}+/i,utf \x{00c5}\x{00e5}\x{212b} /\x{01c4}+/i,utf \x{01c4}\x{01c5}\x{01c6} /\x{01c5}+/i,utf \x{01c4}\x{01c5}\x{01c6} /\x{01c6}+/i,utf \x{01c4}\x{01c5}\x{01c6} /\x{01c7}+/i,utf \x{01c7}\x{01c8}\x{01c9} /\x{01c8}+/i,utf \x{01c7}\x{01c8}\x{01c9} /\x{01c9}+/i,utf \x{01c7}\x{01c8}\x{01c9} /\x{01ca}+/i,utf \x{01ca}\x{01cb}\x{01cc} /\x{01cb}+/i,utf \x{01ca}\x{01cb}\x{01cc} /\x{01cc}+/i,utf \x{01ca}\x{01cb}\x{01cc} /\x{01f1}+/i,utf \x{01f1}\x{01f2}\x{01f3} /\x{01f2}+/i,utf \x{01f1}\x{01f2}\x{01f3} /\x{01f3}+/i,utf \x{01f1}\x{01f2}\x{01f3} /\x{0345}+/i,utf \x{0345}\x{0399}\x{03b9}\x{1fbe} /\x{0399}+/i,utf \x{0345}\x{0399}\x{03b9}\x{1fbe} /\x{03b9}+/i,utf \x{0345}\x{0399}\x{03b9}\x{1fbe} /\x{1fbe}+/i,utf \x{0345}\x{0399}\x{03b9}\x{1fbe} /\x{0392}+/i,utf \x{0392}\x{03b2}\x{03d0} /\x{03b2}+/i,utf \x{0392}\x{03b2}\x{03d0} /\x{03d0}+/i,utf \x{0392}\x{03b2}\x{03d0} /\x{0395}+/i,utf \x{0395}\x{03b5}\x{03f5} /\x{03b5}+/i,utf \x{0395}\x{03b5}\x{03f5} /\x{03f5}+/i,utf \x{0395}\x{03b5}\x{03f5} /\x{0398}+/i,utf \x{0398}\x{03b8}\x{03d1}\x{03f4} /\x{03b8}+/i,utf \x{0398}\x{03b8}\x{03d1}\x{03f4} /\x{03d1}+/i,utf \x{0398}\x{03b8}\x{03d1}\x{03f4} /\x{03f4}+/i,utf \x{0398}\x{03b8}\x{03d1}\x{03f4} /\x{039a}+/i,utf \x{039a}\x{03ba}\x{03f0} /\x{03ba}+/i,utf \x{039a}\x{03ba}\x{03f0} /\x{03f0}+/i,utf \x{039a}\x{03ba}\x{03f0} /\x{03a0}+/i,utf \x{03a0}\x{03c0}\x{03d6} /\x{03c0}+/i,utf \x{03a0}\x{03c0}\x{03d6} /\x{03d6}+/i,utf \x{03a0}\x{03c0}\x{03d6} /\x{03a1}+/i,utf \x{03a1}\x{03c1}\x{03f1} /\x{03c1}+/i,utf \x{03a1}\x{03c1}\x{03f1} /\x{03f1}+/i,utf \x{03a1}\x{03c1}\x{03f1} /\x{03a3}+/i,utf \x{03A3}\x{03C2}\x{03C3} /\x{03c2}+/i,utf \x{03A3}\x{03C2}\x{03C3} /\x{03c3}+/i,utf \x{03A3}\x{03C2}\x{03C3} /\x{03a6}+/i,utf \x{03a6}\x{03c6}\x{03d5} /\x{03c6}+/i,utf \x{03a6}\x{03c6}\x{03d5} /\x{03d5}+/i,utf \x{03a6}\x{03c6}\x{03d5} /\x{03c9}+/i,utf \x{03c9}\x{03a9}\x{2126} /\x{03a9}+/i,utf \x{03c9}\x{03a9}\x{2126} /\x{2126}+/i,utf \x{03c9}\x{03a9}\x{2126} /\x{1e60}+/i,utf \x{1e60}\x{1e61}\x{1e9b} /\x{1e61}+/i,utf \x{1e60}\x{1e61}\x{1e9b} /\x{1e9b}+/i,utf \x{1e60}\x{1e61}\x{1e9b} /\x{1e9e}+/i,utf \x{1e9e}\x{00df} /\x{00df}+/i,utf \x{1e9e}\x{00df} /\x{1f88}+/i,utf \x{1f88}\x{1f80} /\x{1f80}+/i,utf \x{1f88}\x{1f80} /\x{004b}+/i,utf \x{004b}\x{006b}\x{212a} /\x{006b}+/i,utf \x{004b}\x{006b}\x{212a} /\x{212a}+/i,utf \x{004b}\x{006b}\x{212a} /\x{0053}+/i,utf \x{0053}\x{0073}\x{017f} /\x{0073}+/i,utf \x{0053}\x{0073}\x{017f} /\x{017f}+/i,utf \x{0053}\x{0073}\x{017f} /ist/i,utf \= Expect no match ikt /is+t/i,utf iSs\x{17f}t \= Expect no match ikt /is+?t/i,utf \= Expect no match ikt /is?t/i,utf \= Expect no match ikt /is{2}t/i,utf \= Expect no match iskt /^\p{Xuc}/utf $abc @abc `abc \x{1234}abc \= Expect no match abc /^\p{Xuc}+/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^\p{Xuc}+?/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^\p{Xuc}+?\*/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^\p{Xuc}++/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^\p{Xuc}{3,5}/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^\p{Xuc}{3,5}?/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^[\p{Xuc}]/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^[\p{Xuc}]+/utf $@`\x{a0}\x{1234}\x{e000}** \= Expect no match \x{9f} /^\P{Xuc}/utf abc \= Expect no match $abc @abc `abc \x{1234}abc /^[\P{Xuc}]/utf abc \= Expect no match $abc @abc `abc \x{1234}abc /^A\s+Z/utf,ucp A\x{2005}Z A\x{85}\x{180e}\x{2005}Z /^A[\s]+Z/utf,ucp A\x{2005}Z A\x{85}\x{180e}\x{2005}Z /(?<=\x{100})\x{200}(?=\x{300})/utf,allusedtext \x{100}\x{200}\x{300} # ----------------------------------------------------------------------------- # Tests for bidi control and bidi class properties /\p{ bidi_control }/utf -->\x{202c}<-- /\p{bidicontrol}+/utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /\p{bidicontrol}+?/utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /\p{bidicontrol}++/utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /[\p{bidi_control}]/utf -->\x{202c}<-- /[\p{bidicontrol}]+/utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /[\p{bidicontrol}]+?/utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /[\p{bidicontrol}]++/utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /[\p{bidicontrol}<>]+/utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /\P{bidicontrol}+/g,utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /\p{^bidicontrol}+/g,utf -->\x{061c}\x{200e}\x{200f}\x{202a}\x{202b}\x{202c}\x{202d}<-- -->\x{2066}\x{2067}\x{2068}\x{2069}<-- /\p{bidi class = al}/utf -->\x{061D}<-- /\p{bidi class = al}+/utf -->\x{061D}\x{061e}\x{061f}<-- /\p{bidi_class : AL}+?/utf -->\x{061D}\x{061e}\x{061f}<-- /\p{Bidi_Class : AL}++/utf -->\x{061D}\x{061e}\x{061f}<-- /\p{bidi class = aN}+/utf -->\x{061D}\x{0602}\x{0604}\x{061f}<-- /\p{bidi class = B}+/utf -->\x{0a}\x{0d}\x{01c}\x{01e}\x{085}\x{2029}<-- /\p{bidi class:BN}+/utf -->\x{0}\x{08}\x{200c}\x{fffe}\x{dfffe}\x{10ffff}<-- /\p{bidiclass:cs}+/utf -->,.\x{060c}\x{ff1a}<-- /\p{bidiclass:En}+/utf -->09\x{b2}\x{2074}\x{1fbf9}<-- /\p{bidiclass:es}+/utf ==>+-\x{207a}\x{ff0d}<== /\p{bidiclass:et}+/utf -->#\{24}%\x{a2}\x{A838}\x{1e2ff}<-- /\p{bidiclass:FSI}+/utf -->\x{2068}<-- /\p{bidi class:L}+/utf -->ABC<-- /\P{bidi class:L}+/utf -->ABC<-- /\p{bidi class:LRE}+\p{bidiclass=lri}*\p{bidiclass:lro}/utf -->\x{202a}\x{2066}\x{202d}<-- /\p{bidi class:NSM}+/utf -->\x{9bc}\x{a71}\x{e31}<-- /\p{bidi class:ON}+/utf -->\x{21}'()*;@\x{384}\x{2039}<=- /\p{bidiclass:pdf}\p{bidiclass:pdi}/utf -->\x{202c}\x{2069}<-- /\p{bidi class:R}+/utf -->\x{590}\x{5c6}\x{200f}\x{10805}<-- /\p{bidi class:RLE}+\p{bidi class:RLI}*\p{bidi class:RLO}+/utf -->\x{202b}\x{2067}\x{202e}<-- /\p{bidi class:S}+\p{bidiclass:WS}+/utf -->\x{9}\x{b}\x{1f} \x{c} \x{2000} \x{3000}<-- # ----------------------------------------------------------------------------- /\p{katakana}/utf \x{30a1} \x{3001} /\p{scx:katakana}/utf \x{30a1} \x{3001} /\p{script extensions:katakana}/utf \x{30a1} \x{3001} /\p{sc:katakana}/utf \x{30a1} \= Expect no match \x{3001} /\p{script:katakana}/utf \x{30a1} \= Expect no match \x{3001} /\p{sc:katakana}{3,}/utf \x{30a1}\x{30fa}\x{32d0}\x{1b122}\x{ff66}\x{3001}ABC /\p{sc:katakana}{3,}?/utf \x{30a1}\x{30fa}\x{32d0}\x{1b122}\x{ff66}\x{3001}ABC # Tests for PCRE2_EXTRA_CASELESS_RESTRICT. Compare each test with and without # the restriction. /AskZ/i,utf,caseless_restrict AskZ aSKz \= Expect no match A\x{17f}kZ As\x{212a}Z /AskZ/i,utf AskZ aSKz A\x{17f}kZ As\x{212a}Z /A\x{17f}\x{212a}Z/ir,utf \= Expect no match AskZ /A\x{17f}\x{212a}Z/i,utf AskZ /[AskZ]+/i,utf,caseless_restrict AskZ aSKz A\x{17f}kZ As\x{212a}Z /[AskZ]+/i,utf AskZ aSKz A\x{17f}kZ As\x{212a}Z /[\x{17f}\x{212a}]+/ir,utf \= Expect no match AskZ /[\x{17f}\x{212a}]+/i,utf AskZ /[^s]+/ir,utf A\x{17f}Z /[^s]+/i,utf A\x{17f}Z /[^k]+/ir,utf A\x{212a}Z /[^k]+/i,utf A\x{212a}Z /[^sk]+/ir,utf A\x{17f}\x{212a}Z /[^sk]+/i,utf A\x{17f}\x{212a}Z /[^\x{17f}]+/ir,utf AsSZ /[^\x{17f}]+/i,utf AsSZ /[Ss]+/irB,utf Sss\x{17f}ss /[Ss]+/iB,utf Sss\x{17f}ss /[S\x{17f}]/irB,utf /[S\x{17f}]/iB,utf /[\x{17f}s]/irB,utf /[\x{17f}s]/iB,utf /[\x{4b}\x{6b}]/irB,utf /[\x{4b}\x{6b}]/iB,utf /s(?r)s(?-r)s(?r:s)s/i,utf \x{17f}S\x{17f}S\x{17f} \= Expect no match \x{17f}\x{17f}\x{17f}S\x{17f} \x{17f}S\x{17f}\x{17f}\x{17f} /k(?^i)k/ir,utf K\x{212a} \= Expect no match \x{212a}\x{212a} # End caseless restrict tests # TESTS for PCRE2_EXTRA_ASCII_xxx - again, tests with and without. # DIGITS /\d+/i,utf 123\x{660}456 /\d+/i,utf,ucp 123\x{660}456 /\d+/i,utf,ucp,ascii_bsd 123\x{660}456 /[\d]+/i,utf 123\x{660}456 /[\d]+/i,utf,ucp 123\x{660}456 /[\d]+/i,utf,ucp,ascii_bsd 123\x{660}456 /\d(?aD)\d(?-aD)\d/utf,ucp \x{660}9\x{660} \= Expect no match \x{660}\x{660}\x{660} /\d(?-aD)\d(?aD)\d/utf,ucp,ascii_bsd 999 9\x{660}9 /\d(?a)\d(?-a)\d/utf,ucp \x{660}9\x{660} \= Expect no match \x{660}\x{660}\x{660} /\d(?-aD)\d(?aD)\d/utf,ucp,ascii_bsd 999 9\x{660}9 # SPACES />\s+ < \= Expect no match >\x{a0} < />\s+ < >\x{a0} < />\s+ < \= Expect no match >\x{a0} < />[\s]+ < \= Expect no match >\x{a0} < />[\s]+ < >\x{a0} < />[\s]+ < \= Expect no match >\x{a0} < />\s(?aS)\s(?-aS)\s\x{a0} \x{a0}< \= Expect no match >\x{a0}\x{a0}\x{a0}< />\s(?a)\s(?-a)\s\x{a0} \x{a0}< \= Expect no match >\x{a0}\x{a0}\x{a0}< # WORDS /\w+/i,utf 123\x{660}abc /\w+/i,utf,ucp 123\x{660}abc /\w+/i,utf,ucp,ascii_bsw 123\x{660}abc /[\w]+/i,utf 123\x{660}abc /[\w]+/i,utf,ucp 123\x{660}abc /[\w]+/i,utf,ucp,ascii_bsw 123\x{660}abc /\w(?aW)\w(?-aW)\w/utf,ucp \x{660}A\x{c0} \= Expect no match \x{660}\x{c0}\x{c0} /\w(?a)\w(?-a)\w/utf,ucp \x{660}A\x{c0} \= Expect no match \x{660}\x{c0}\x{c0} # POSIX /^[[:digit:]]+$/utf,ucp 123456 123\x{660}456 /^[[:digit:]]+$/utf,ucp,ascii_digit 123456 \= Expect no match 123\x{660}456 /[[:digit:]]+/g,utf,ucp,ascii_digit 123\x{660}456 /(?-aT)[[:digit:]](?aT)[[:digit:]]/utf,ucp,ascii_digit 11 \x{ff11}1 \= Expect no match 1\x{ff11} /(?-aT:[[:digit:]])[[:digit:]]/utf,ucp,ascii_digit 11 \x{ff11}1 \= Expect no match 1\x{ff11} /(?-aT:[[:digit:]])[[:digit:]]/utf,never_ucp,ascii_digit 11 \= Expect no match \x{ff11}1 1\x{ff11} /[[:digit:]]+/utf,ucp,ascii_posix 123\x{660}456 /(?-aP)[[:digit:]](?aP)[[:digit:]]/utf,ucp,ascii_posix 11 \x{ff11}1 \= Expect no match 1\x{ff11} /(?-aP:[[:digit:]])[[:digit:]]/utf,ucp,ascii_posix 11 \x{ff11}1 \= Expect no match 1\x{ff11} /(?-a:[[:digit:]])[[:digit:]]/a,utf,ucp 11 \x{ff11}1 \= Expect no match 1\x{ff11} />[[:space:]]+\x{a0} \x{a0}< >\x{a0}\x{a0}\x{a0}< />[[:space:]]+\x{a0} \x{a0}< /(?aP)[[:alnum:]]+/i,ucp,utf abcáxyz abc\x{660}xyz /(?aP)[[:alnum:]\d]+/i,ucp,utf abc\x{660}xyz /(*UCP)(*UTF)[[:alnum:]](?aP:[[:alnum:]])[[:alnum:]]/ \x{660}A\x{660} \= Expect no match \x{660}\x{660}\x{660} # VARIOUS /[\d\s\w]+/a,ucp,utf 9 A\x{660}À 9 AÀ\x{660} # End PCRE2_EXTRA_ASCII_xxx tests /\w+/utf,ucp --cafe\x{300}_au\x{203f}lait! /[\w]+/utf,ucp --cafe\x{300}_au\x{203f}lait! /\b.+?\b/utf,ucp --cafe\x{300}_au\x{203f}lait! /caf\B.+?\B/utf,ucp --cafe\x{300}_au\x{203f}lait! # End of testinput7