\By\b xy y - -
\by\B yz y - -
\By\B xyz y - -
+\B y - -
\w a y - -
\w - n - -
\W a n - -
((a)(b)c)(d) abcd y $-[4] 3
((a)(b)c)(d) abcd y $+[4] 4
[a-zA-Z_][a-zA-Z0-9_]* alpha y $& alpha
+[_A-Z] } n - - # This could match on EBCDIC if A-Z not excluding things in middle
^a(bc+|b[eh])g|.h$ abh y $&-$1 bh-
(bc+d$|ef*g.|h?i(j|k)) effgz y $&-$1-$2 effgz-effgz-
(bc+d$|ef*g.|h?i(j|k)) ij y $&-$1-$2 ij-ij-j
a(?{})b cabd y $& ab
a(?{f()+ - c - Missing right curly or square bracket
a(?{{1}+ - c - Missing right curly or square bracket
+ (?{(^{}) - c - syntax error
a(?{}})b - c -
a(?{"{"})b ab y - -
a(?{"\{"})b cabd y $& ab
([[:alpha:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd
([[:alnum:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd01Xy
([[:ascii:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd01Xy__-- ${nulnul}
-([[:cntrl:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ${nulnul}
+([[:cntrl:]]+) ABcd01Xy__-- ${nulnul}${ffff} ya $1 ${nulnul} ff is a control on EBCDIC (non-POSIX-BC), so this fails under /u rules
([[:digit:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 01
([[:graph:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd01Xy__--
([[:lower:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 cd
([[:^xdigit:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 Xy__-- ${nulnul}${ffff}
[[:foo:]] - c - POSIX class [:foo:] unknown
[[:^foo:]] - c - POSIX class [:^foo:] unknown
+'[[:^cntrl:]]+'u a\x80 y $& a \x80 was matching on EBCDIC platforms
((?>a+)b) aaab y $1 aaab
(?>(a+))b aaab y $1 aaa
((?>[^()]+)|\([^()]*\))+ ((abc(ade)ufh()()x y $& abc(ade)ufh()()x
(?=foo) foo y pos 0
(?=foo) XfooY y pos 1
.*(?=foo) XfooY y pos 1
+(?=.*P)P aP y pos 2
(?<=foo) foo y pos 3
(?<=foo) XfooY y pos 4
.*(?<=foo) foo y pos 3
(?P<n>foo)(??{ $+{n} }) snofooefoofoowaa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
(?P<=n>foo|bar|baz) - c - Group name must start with a non-digit word character
(?P<!n>foo|bar|baz) - c - Group name must start with a non-digit word character
-(?PX<n>foo|bar|baz) - c - Sequence (?PX<...) not recognized
+(?PX<n>foo|bar|baz) - c - Sequence (?PX...) not recognized
/(?'n'foo|bar|baz)/ snofooewa y $1 foo
/(?'n'foo|bar|baz)/ snofooewa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(?'n'foo|bar|baz)(?'m'[ew]+)/ snofooewa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(ab)+((?1))(fox)/ ababfox y $1-$2-$3 ab-ab-fox
/(ab){1,100}((?1))(fox)/ ababfox y $1-$2-$3 ab-ab-fox
/(ab){0,100}((?1))(fox)/ ababfox y $1-$2-$3 ab-ab-fox
+foo(?0)?bar phoofoofoobarbarbarr y $& foofoobarbar
+foo(?R)?bar phoofoofoobarbarbarr y $& foofoobarbar
# possessive captures
a++a aaaaa n - -
a*+a aaaaa n - -
# Verify that \N{U+...} forces Unicode rules
/\N{U+41}\x{c1}/i a\x{e1} y $& a\x{e1}
/[\N{U+41}\x{c1}]/i \x{e1} y $& \x{e1}
+'\N{U+41}' A y $& A # Even for single quoted patterns
+/\N{}\xe4/i \xc4 y $& \xc4 # Empty \N{} should change /d to /u
[\s][\S] \x{a0}\x{a0} n - - # Unicode complements should not match same character
/[\N{U+}]/ - Sc - Unmatched
/[\N{U+}]/ - sc - Syntax error in (?[...])
/abc\N{def/ - c - Missing right brace
-/\N{U+4AG3}/ - c - Illegal hexadecimal digit
-/[\N{U+4AG3}]/ - c - Illegal hexadecimal digit
+/\N{U+4AG3}/ - c - Invalid hexadecimal number
+/[\N{U+4AG3}]/ - Sc - Unmatched
+/[\N{U+4AG3}]/ - sc - Syntax error in (?[...])
# And verify that in single quotes which bypasses the lexer, the regex compiler
# figures it out.
/abc\N {U+41}/x - c - Missing braces
/abc\N {SPACE}/x - c - Missing braces
-# Verifies catches hex errors, and doesn't expose our . notation to the outside
-/\N{U+0xBEEF}/ - c - Illegal hexadecimal digit
-/\N{U+BEEF.BEAD}/ - c - Illegal hexadecimal digit
+# Verifies catches hex errors
+/\N{U+0xBEEF}/ - c - Invalid hexadecimal number
+# Used to be an error, but not any more:
+/\N{U+BEEF.BEAD}/ - c -
# Verify works in single quotish context; regex compiler delivers slightly different msg
# \N{U+BEEF.BEAD} succeeds here, because can't completely hide it from the outside.
\N{U+0xBEEF} - c - Invalid hexadecimal number
-\c` - c - \"\\c`\" is more clearly written simply as \"\\ \"
-\c1 - c - \"\\c1\" is more clearly written simply as \"q\"
-\cA \001 y $& \1
-
+\c` - ac - \"\\c`\" is more clearly written simply as \"\\ \"
+\c1 - ac - \"\\c1\" is more clearly written simply as \"q\"
+\c@ \0 y $& \0
+\cA \001 y $& \001
+\cB \002 y $& \002
+\cC \003 y $& \003
+\cI \011 y $& \011
+\cJ \012 y $& \012
+\cR \022 y $& \022
+\cS \023 y $& \023
+\cX \030 y $& \030
+\cY \031 y $& \031
+\cZ \032 y $& \032
+\c[ \033 y $& \033
+\c\X \034X y $& \034X
+\c] \035 y $& \035
+\c^ \036 y $& \036
+\c_ \037 y $& \037
+\c? \177 ay $& \177
+\c? \x9F ey $& \x9F \c? is APC on EBCDIC
\400 \x{100} y $& \x{100}
\600 \x{180} y $& \x{180}
\777 \x{1FF} y $& \x{1FF}
a(.)\g{4294967297} x c - Reference to nonexistent group in regex
a(.)\g{4294967298} x c - Reference to nonexistent group in regex
-(.)\2147483648 b\o{214}7483648 y $1 b
-(.)\2147483649 b\o{214}7483649 y $1 b
-(.)\2147483650 b\o{214}7483650 y $1 b
-(.)\4294967296 b\o{42}94967296 y $1 b
-(.)\4294967297 b\o{42}94967297 y $1 b
-(.)\4294967298 b\o{42}94967298 y $1 b
-a(.)\2147483648 ab\o{214}7483648 y $1 b
-a(.)\2147483649 ab\o{214}7483649 y $1 b
-a(.)\2147483650 ab\o{214}7483650 y $1 b
-a(.)\4294967296 ab\o{42}94967296 y $1 b
-a(.)\4294967297 ab\o{42}94967297 y $1 b
-a(.)\4294967298 ab\o{42}94967298 y $1 b
+(.)\2147483648 b\o{214}7483648 ya $1 b \d not converted to native; \o{} is
+(.)\2147483649 b\o{214}7483649 ya $1 b \d not converted to native; \o{} is
+(.)\2147483650 b\o{214}7483650 ya $1 b \d not converted to native; \o{} is
+(.)\4294967296 b\o{42}94967296 ya $1 b \d not converted to native; \o{} is
+(.)\4294967297 b\o{42}94967297 ya $1 b \d not converted to native; \o{} is
+(.)\4294967298 b\o{42}94967298 ya $1 b \d not converted to native; \o{} is
+a(.)\2147483648 ab\o{214}7483648 ya $1 b \d not converted to native; \o{} is
+a(.)\2147483649 ab\o{214}7483649 ya $1 b \d not converted to native; \o{} is
+a(.)\2147483650 ab\o{214}7483650 ya $1 b \d not converted to native; \o{} is
+a(.)\4294967296 ab\o{42}94967296 ya $1 b \d not converted to native; \o{} is
+a(.)\4294967297 ab\o{42}94967297 ya $1 b \d not converted to native; \o{} is
+a(.)\4294967298 ab\o{42}94967298 ya $1 b \d not converted to native; \o{} is
# The below was inserting a NULL into the character class.
[\8\9] \000 Sn - -
\d<(.*?)> a<> n - -
[bcd].{2,3}aaaa XbXaaaaa y - -
[bcd].{2,3}aaaa Xb\x{100}aaaaa y - -
-
+'\Awibble\z'm wibble y - -
+/(alias|status)es$/i Statuses y $1 Status # [perl #121778]
+/( (?&solution) | % ) \Z (?(DEFINE) (?<solution>7\%\ solution) )/x 7% solution y $1 7% solution # [perl #122890]
+(.)(?{$~=$^N}) \x{100} y $~ \x{100} # [perl #123135]
+
+/[a-z]/i \N{KELVIN SIGN} y $& \N{KELVIN SIGN}
+/[A-Z]/ia \N{KELVIN SIGN} y $& \N{KELVIN SIGN}
+/[A-Z]/iaa \N{KELVIN SIGN} n - -
+/[A-Z]/i \N{LATIN SMALL LETTER LONG S} y $& \N{LATIN SMALL LETTER LONG S}
+
+# RT #123840: these used to hang in re_intuit_start
+/w\zxy?\z/i \x{100}a\x{80}a n - -
+/w\z\R\z/i \x{100}a\x{80}a n - -
+
+/(a+){1}+a/ aaa n - - # [perl #125825]
+
+^((?(?=x)xb|ya)z) xbz y $1 xbz
+^((?(?=x)xb|ya)z) yaz y $1 yaz
+^((?(?!y)xb|ya)z) xbz y $1 xbz
+^((?(?!y)xb|ya)z) yaz y $1 yaz
+^((?(?!)xb|ya)z) xbz n - -
+^((?(?!)xb|ya)z) yaz y $1 yaz # [perl-126222]
+
+foo(*ACCEPT:foo) foo y $::REGMARK foo
+(foo(*ACCEPT:foo)) foo y $::REGMARK foo
+A(*FAIL:foo)[BC] A n $::REGERROR foo
# Keep these lines at the end of the file
# vim: softtabstop=0 noexpandtab
https://perl5.git.perl.org / perl5.git / blobdiff