From 5f318627d716c0e353f33fe412ad9bbd50c7e340 Mon Sep 17 00:00:00 2001 From: Rickard Green Date: Mon, 27 Mar 2017 15:08:43 +0200 Subject: Update tests for PCRE version 8.40 --- lib/stdlib/test/re_SUITE_data/testoutput5 | 138 +++++++++++++++++++++++++----- 1 file changed, 117 insertions(+), 21 deletions(-) (limited to 'lib/stdlib/test/re_SUITE_data/testoutput5') diff --git a/lib/stdlib/test/re_SUITE_data/testoutput5 b/lib/stdlib/test/re_SUITE_data/testoutput5 index d583119dd9..bab989ca7e 100644 --- a/lib/stdlib/test/re_SUITE_data/testoutput5 +++ b/lib/stdlib/test/re_SUITE_data/testoutput5 @@ -1,26 +1,47 @@ /-- This set of tests checks the API, internals, and non-Perl stuff for UTF support, excluding Unicode properties. However, tests that give different results in 8-bit and 16-bit modes are excluded (see tests 16 and 17). --/ + +< forbid W /\x{110000}/8DZ -Failed: character value in \x{...} sequence is too large at offset 9 +Failed: character value in \x{} or \o{} is too large at offset 9 + +/\o{4200000}/8DZ +Failed: character value in \x{} or \o{} is too large at offset 10 /\x{ffffffff}/8 -Failed: character value in \x{...} sequence is too large at offset 11 +Failed: character value in \x{} or \o{} is too large at offset 11 + +/\o{37777777777}/8 +Failed: character value in \x{} or \o{} is too large at offset 14 /\x{100000000}/8 -Failed: character value in \x{...} sequence is too large at offset 12 +Failed: character value in \x{} or \o{} is too large at offset 12 + +/\o{77777777777}/8 +Failed: character value in \x{} or \o{} is too large at offset 14 /\x{d800}/8 Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7 +/\o{154000}/8 +Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 9 + /\x{dfff}/8 Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7 +/\o{157777}/8 +Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 9 + /\x{d7ff}/8 +/\o{153777}/8 + /\x{e000}/8 +/\o{170000}/8 + /^\x{100}a\x{1234}/8 \x{100}a\x{1234}bcd 0: \x{100}a\x{1234} @@ -146,11 +167,12 @@ No match /\x{100}*/8DZ ------------------------------------------------------------------ Bra - \x{100}* + \x{100}*+ Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 +May match empty string Options: utf No first char No need char @@ -159,7 +181,7 @@ No need char ------------------------------------------------------------------ Bra a - \x{100}* + \x{100}*+ Ket End ------------------------------------------------------------------ @@ -172,7 +194,7 @@ No need char ------------------------------------------------------------------ Bra ab - \x{100}* + \x{100}*+ Ket End ------------------------------------------------------------------ @@ -248,7 +270,7 @@ No match /[z-\x{100}]/8DZ ------------------------------------------------------------------ Bra - [z-\x{100}] + [z-\xff\x{100}] Ket End ------------------------------------------------------------------ @@ -373,6 +395,7 @@ Need char = 'z' End ------------------------------------------------------------------ Capturing subpattern count = 2 +May match empty string Options: utf No first char No need char @@ -404,6 +427,7 @@ No need char End ------------------------------------------------------------------ Capturing subpattern count = 2 +May match empty string Options: utf No first char No need char @@ -424,6 +448,7 @@ No need char End ------------------------------------------------------------------ Capturing subpattern count = 2 +May match empty string Options: utf No first char No need char @@ -455,6 +480,7 @@ No need char End ------------------------------------------------------------------ Capturing subpattern count = 2 +May match empty string Options: utf No first char No need char @@ -768,7 +794,7 @@ No match /[\h]{3,}/8BZ ------------------------------------------------------------------ Bra - [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,} + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,}+ Ket End ------------------------------------------------------------------ @@ -786,7 +812,7 @@ No match /[\H]/8BZ ------------------------------------------------------------------ Bra - [\x00-\x08\x0a-\x1f!-\x9f\x{a1}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}] + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}] Ket End ------------------------------------------------------------------ @@ -794,7 +820,7 @@ No match /[\V]/8BZ ------------------------------------------------------------------ Bra - [\x00-\x09\x0e-\x84\x{86}-\x{2027}\x{202a}-\x{10ffff}] + [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}] Ket End ------------------------------------------------------------------ @@ -1510,7 +1536,7 @@ Options: caseless utf No first char No need char Subject length lower bound = 1 -No set of starting bytes +No starting char list /[^\x{1234}]+?/iS8I Capturing subpattern count = 0 @@ -1518,7 +1544,7 @@ Options: caseless utf No first char No need char Subject length lower bound = 1 -No set of starting bytes +No starting char list /[^\x{1234}]++/iS8I Capturing subpattern count = 0 @@ -1526,7 +1552,7 @@ Options: caseless utf No first char No need char Subject length lower bound = 1 -No set of starting bytes +No starting char list /[^\x{1234}]{2}/iS8I Capturing subpattern count = 0 @@ -1534,7 +1560,7 @@ Options: caseless utf No first char No need char Subject length lower bound = 2 -No set of starting bytes +No starting char list // Failed: inconsistent NEWLINE options at offset 0 @@ -1572,7 +1598,7 @@ Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7 /[\h\x{e000}]+/8BZ ------------------------------------------------------------------ Bra - [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}\x{e000}]+ + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}\x{e000}]++ Ket End ------------------------------------------------------------------ @@ -1594,7 +1620,7 @@ Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7 /[\H\x{d7ff}]+/8BZ ------------------------------------------------------------------ Bra - [\x00-\x08\x0a-\x1f!-\x9f\x{a1}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}\x{d7ff}]+ + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}\x{d7ff}]++ Ket End ------------------------------------------------------------------ @@ -1616,7 +1642,7 @@ Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7 /[\v\x{e000}]+/8BZ ------------------------------------------------------------------ Bra - [\x0a-\x0d\x85\x{2028}-\x{2029}\x{e000}]+ + [\x0a-\x0d\x85\x{2028}-\x{2029}\x{e000}]++ Ket End ------------------------------------------------------------------ @@ -1634,7 +1660,7 @@ Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7 /[\V\x{d7ff}]+/8BZ ------------------------------------------------------------------ Bra - [\x00-\x09\x0e-\x84\x{86}-\x{2027}\x{202a}-\x{10ffff}\x{d7ff}]+ + [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}\x{d7ff}]++ Ket End ------------------------------------------------------------------ @@ -1808,10 +1834,8 @@ Partial match: \x{0d}\x{0d} /i [^\x{8000}]* /i [^\x{7fff}]{2} /i [^\x{7fff}]{0,7}? - Once /i [^\x{fffff}]{5} - /i [^\x{fffff}]? - Ket + /i [^\x{fffff}]?+ Ket End ------------------------------------------------------------------ @@ -1846,4 +1870,76 @@ No match /\ud800/8 Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 5 +/^a+[a\x{200}]/8BZ +------------------------------------------------------------------ + Bra + ^ + a+ + [a\x{200}] + Ket + End +------------------------------------------------------------------ + aa + 0: aa + +/[b-d\x{200}-\x{250}]*[ae-h]?#[\x{200}-\x{250}]{0,8}[\x00-\xff]*#[\x{200}-\x{250}]+[a-z]/8BZ +------------------------------------------------------------------ + Bra + [b-d\x{200}-\x{250}]*+ + [ae-h]?+ + # + [\x{200}-\x{250}]{0,8}+ + [\x00-\xff]* + # + [\x{200}-\x{250}]++ + [a-z] + Ket + End +------------------------------------------------------------------ + +/[^\xff]*PRUNE:\x{100}abc(xyz(?1))/8DZ +------------------------------------------------------------------ + Bra + [^\x{ff}]* + PRUNE:\x{100}abc + CBra 1 + xyz + Recurse + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf +No first char +Need char = 'z' + +/(?<=\K\x{17f})/8g+ + \x{17f}\x{17f}\x{17f}\x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f}\x{17f}\x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f}\x{17f}\x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f}\x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f} + 0: \x{17f} + 0+ + +/(?<=\K\x{17f})/8G+ + \x{17f}\x{17f}\x{17f}\x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f}\x{17f}\x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f}\x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f}\x{17f} + 0: \x{17f} + 0+ \x{17f} + 0: \x{17f} + 0+ + /-- End of testinput5 --/ -- cgit v1.2.3