# This stops me getting screenfulls of syntax errors every time I accidentally
-# run this file via a shell glob. Format of this file is given in regexp.t
-# Can't use \N{VALID NAME TEST} here because need 'use charnames'; but can use
-# \N{U+valid} here.
+# run this file via a shell glob. The full format of this file is given
+# in regexp.t
+# Prior to the implementation of autoloading of \N{}, tests that used \N{name}
+# could not go in this file, and were farmed out to other .t's.
+#
+# pat string y/n/etc expr expected-expr skip-reason
__END__
abc abc y $& abc
abc abc y $-[0] 0
([[:upper:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 AB
([[:xdigit:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd01
([[:^alpha:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 01
-([[:^alnum:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 __-- ${nulnul}${ffff}
+((?a)[[:^alnum:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 __-- ${nulnul}${ffff}
([[:^ascii:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ${ffff}
([[:^cntrl:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd01Xy__--
([[:^digit:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd
([[:^lower:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 AB
-([[:^print:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ${nulnul}${ffff}
+((?a)[[:^print:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ${nulnul}${ffff}
([[:^punct:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd01Xy
([[:^space:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 ABcd01Xy__--
-([[:^word:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 -- ${nulnul}${ffff}
+((?a)[[:^word:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 -- ${nulnul}${ffff}
([[:^upper:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 cd01
([[:^xdigit:]]+) ABcd01Xy__-- ${nulnul}${ffff} y $1 Xy__-- ${nulnul}${ffff}
[[:foo:]] - c - POSIX class [:foo:] unknown
^([^,]{0,3},){3,}d aaa,b,c,d y $1 c,
^([^,]{0,3},){0,3}d aaa,b,c,d y $1 c,
(?i) y - -
+(?a:((?u)\w)\W) \xC0\xC0 y $& \xC0\xC0
'(?!\A)x'm a\nxb\n y - -
^(a(b)?)+$ aba y -$1-$2- -a--
^(aa(bb)?)+$ aabbaa y -$1-$2- -aa--
((?2)*)([fF]o+) fooFoFoo y $1-$2 fooFo-Foo
(<(?:[^<>]+|(?R))*>) <<><<<><>>>> y $1 <<><<<><>>>>
(?<n>foo|bar|baz) snofooewa y $1 foo
-(?<n>foo|bar|baz) snofooewa y $+{n} foo
-(?<n>foo|bar|baz)(?<m>[ew]+) snofooewa y $+{n} foo
-(?<n>foo|bar|baz)(?<m>[ew]+) snofooewa y $+{m} ew
-(?<n>foo)|(?<n>bar)|(?<n>baz) snofooewa y $+{n} foo
-(?<n>foo)(??{ $+{n} }) snofooefoofoowaa y $+{n} 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
+(?<n>foo|bar|baz)(?<m>[ew]+) snofooewa yM $+{m} ew miniperl cannot load Tie::Hash::NamedCapture
+(?<n>foo)|(?<n>bar)|(?<n>baz) snofooewa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
+(?<n>foo)(??{ $+{n} }) snofooefoofoowaa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
(?P<n>foo|bar|baz) snofooewa y $1 foo
-(?P<n>foo|bar|baz) snofooewa y $+{n} foo
-(?P<n>foo|bar|baz)(?P<m>[ew]+) snofooewa y $+{n} foo
-(?P<n>foo|bar|baz)(?P<m>[ew]+) snofooewa y $+{m} ew
-(?P<n>foo)|(?P<n>bar)|(?P<n>baz) snofooewa y $+{n} foo
-(?P<n>foo)(??{ $+{n} }) snofooefoofoowaa y $+{n} foo
+(?P<n>foo|bar|baz) snofooewa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
+(?P<n>foo|bar|baz)(?P<m>[ew]+) snofooewa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
+(?P<n>foo|bar|baz)(?P<m>[ew]+) snofooewa yM $+{m} ew miniperl cannot load Tie::Hash::NamedCapture
+(?P<n>foo)|(?P<n>bar)|(?P<n>baz) snofooewa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
+(?P<n>foo)(??{ $+{n} }) snofooefoofoowaa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
(?P<=n>foo|bar|baz) snofooewa c - Sequence (?P<=...) not recognized
(?P<!n>foo|bar|baz) snofooewa c - Sequence (?P<!...) not recognized
(?PX<n>foo|bar|baz) snofooewa c - Sequence (?PX<...) not recognized
/(?'n'foo|bar|baz)/ snofooewa y $1 foo
-/(?'n'foo|bar|baz)/ snofooewa y $+{n} foo
-/(?'n'foo|bar|baz)(?'m'[ew]+)/ snofooewa y $+{n} foo
-/(?'n'foo|bar|baz)(?'m'[ew]+)/ snofooewa y $+{m} ew
-/(?'n'foo)|(?'n'bar)|(?<n>baz)/ snobazewa y $+{n} baz
-/(?'n'foo)(??{ $+{n} })/ snofooefoofoowaa y $+{n} 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
+/(?'n'foo|bar|baz)(?'m'[ew]+)/ snofooewa yM $+{m} ew miniperl cannot load Tie::Hash::NamedCapture
+/(?'n'foo)|(?'n'bar)|(?<n>baz)/ snobazewa yM $+{n} baz miniperl cannot load Tie::Hash::NamedCapture
+/(?'n'foo)(??{ $+{n} })/ snofooefoofoowaa yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(?'n'foo)\k<n>/ ..foofoo.. y $1 foo
-/(?'n'foo)\k<n>/ ..foofoo.. y $+{n} foo
+/(?'n'foo)\k<n>/ ..foofoo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(?<n>foo)\k'n'/ ..foofoo.. y $1 foo
-/(?<n>foo)\k'n'/ ..foofoo.. y $+{n} foo
-/(?:(?<n>foo)|(?<n>bar))\k<n>/ ..barbar.. y $+{n} bar
-/^(?'main'<(?:[^<>]+|(?&crap)|(?&main))*>)(?'empty')(?'crap'!>!>!>)$/ <<!>!>!>><>>!>!>!> y $+{main} <<!>!>!>><>>
+/(?<n>foo)\k'n'/ ..foofoo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?:(?<n>foo)|(?<n>bar))\k<n>/ ..barbar.. yM $+{n} bar miniperl cannot load Tie::Hash::NamedCapture
+/^(?'main'<(?:[^<>]+|(?&crap)|(?&main))*>)(?'empty')(?'crap'!>!>!>)$/ <<!>!>!>><>>!>!>!> yM $+{main} <<!>!>!>><>> miniperl cannot load Tie::Hash::NamedCapture
/^(?'main'<(?:[^<>]+|(?&main))*>)$/ <<><<<><>>>> y $1 <<><<<><>>>>
-/(?'first'(?&second)*)(?'second'[fF]o+)/ fooFoFoo y $+{first}-$+{second} fooFo-Foo
-(?<A>foo)?(?(<A>)bar|nada) foobar y $+{A} foo
+/(?'first'(?&second)*)(?'second'[fF]o+)/ fooFoFoo yM $+{first}-$+{second} fooFo-Foo miniperl cannot load Tie::Hash::NamedCapture
+(?<A>foo)?(?(<A>)bar|nada) foobar yM $+{A} foo miniperl cannot load Tie::Hash::NamedCapture
(?<A>foo)?(?(<A>)bar|nada) foo-barnada y $& nada
(?<A>foo)?(?(1)bar|nada) foo-barnada y $& nada
(?<A>foo(?(R)bar))?(?1) foofoobar y $1 foo
# \k<n> preceded by a literal
/(?'n'foo) \k<n>/ ..foo foo.. y $1 foo
-/(?'n'foo) \k<n>/ ..foo foo.. y $+{n} foo
+/(?'n'foo) \k<n>/ ..foo foo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(?<n>foo) \k'n'/ ..foo foo.. y $1 foo
-/(?<n>foo) \k'n'/ ..foo foo.. y $+{n} foo
-/(?'a1'foo) \k'a1'/ ..foo foo.. y $+{a1} foo
-/(?<a1>foo) \k<a1>/ ..foo foo.. y $+{a1} foo
-/(?'_'foo) \k'_'/ ..foo foo.. y $+{_} foo
-/(?<_>foo) \k<_>/ ..foo foo.. y $+{_} foo
-/(?'_0_'foo) \k'_0_'/ ..foo foo.. y $+{_0_} foo
-/(?<_0_>foo) \k<_0_>/ ..foo foo.. y $+{_0_} foo
+/(?<n>foo) \k'n'/ ..foo foo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?'a1'foo) \k'a1'/ ..foo foo.. yM $+{a1} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?<a1>foo) \k<a1>/ ..foo foo.. yM $+{a1} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?'_'foo) \k'_'/ ..foo foo.. yM $+{_} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?<_>foo) \k<_>/ ..foo foo.. yM $+{_} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?'_0_'foo) \k'_0_'/ ..foo foo.. yM $+{_0_} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?<_0_>foo) \k<_0_>/ ..foo foo.. yM $+{_0_} foo miniperl cannot load Tie::Hash::NamedCapture
/(?'0'foo) bar/ ..foo bar.. c - Sequence (?'
/(?<0>foo) bar/ ..foo bar.. c - Sequence (?<
/(?'12'foo) bar/ ..foo bar.. c - Sequence (?'
# \g{...} with a name as the argument
/(?'n'foo) \g{n}/ ..foo foo.. y $1 foo
-/(?'n'foo) \g{n}/ ..foo foo.. y $+{n} foo
+/(?'n'foo) \g{n}/ ..foo foo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(?<n>foo) \g{n}/ ..foo foo.. y $1 foo
-/(?<n>foo) \g{n}/ ..foo foo.. y $+{n} foo
+/(?<n>foo) \g{n}/ ..foo foo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(?<as>as) (\w+) \g{as} (\w+)/ as easy as pie y $1-$2-$3 as-easy-pie
# Python style named capture buffer stuff
/(?P<n>foo)(?P=n)/ ..foofoo.. y $1 foo
-/(?P<n>foo)(?P=n)/ ..foofoo.. y $+{n} foo
-/(?:(?P<n>foo)|(?P<n>bar))(?P=n)/ ..barbar.. y $+{n} bar
+/(?P<n>foo)(?P=n)/ ..foofoo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
+/(?:(?P<n>foo)|(?P<n>bar))(?P=n)/ ..barbar.. yM $+{n} bar miniperl cannot load Tie::Hash::NamedCapture
/^(?P<PAL>(?P<CHAR>.)((?P>PAL)|.?)(?P=CHAR))$/ madamimadam y $& madamimadam
/^(?P<PAL>(?P<CHAR>.)((?P>PAL)|.?)(?P=CHAR))$/ madamiamadam n - -
/(?P<n>foo) (?P=n)/ ..foo foo.. y $1 foo
-/(?P<n>foo) (?P=n)/ ..foo foo.. y $+{n} foo
+/(?P<n>foo) (?P=n)/ ..foo foo.. yM $+{n} foo miniperl cannot load Tie::Hash::NamedCapture
/(?P<as>as) (\w+) (?P=as) (\w+)/ as easy as pie y $1-$2-$3 as-easy-pie
#check that non identifiers as names are treated as the appropriate lookaround
(?|(?|(a)|(b))|(?|(c)|(d))) d y $1 d
(.)(?|(.)(.)x|(.)d)(.) abcde y $1-$2-$3-$4-$5- b-c--e--
(\N)(?|(\N)(\N)x|(\N)d)(\N) abcde y $1-$2-$3-$4-$5- b-c--e--
-(?|(?<foo>x)) x y $+{foo} x
-(?|(?<foo>x)|(?<bar>y)) x y $+{foo} x
-(?|(?<bar>y)|(?<foo>x)) x y $+{foo} x
-(?<bar>)(?|(?<foo>x)) x y $+{foo} x
+(?|(?<foo>x)) x yM $+{foo} x miniperl cannot load Tie::Hash::NamedCapture
+(?|(?<foo>x)|(?<bar>y)) x yM $+{foo} x miniperl cannot load Tie::Hash::NamedCapture
+(?|(?<bar>y)|(?<foo>x)) x yM $+{foo} x miniperl cannot load Tie::Hash::NamedCapture
+(?<bar>)(?|(?<foo>x)) x yM $+{foo} x miniperl cannot load Tie::Hash::NamedCapture
+# Used to crash, because the last branch was ignored when the parens
+# were counted:
+(?|(b)|()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()()(a)) a y $& a
#Bug #41492
(?(DEFINE)(?<A>(?&B)+)(?<B>a))(?&A) a y $& a
/\N{U+41}\x{c1}/i a\x{e1} y $& a\x{e1}
/[\N{U+41}\x{c1}]/i \x{e1} y $& \x{e1}
-[\s][\S] \x{a0}\x{a0} nT - - # Unicode complements should not match same character
+[\s][\S] \x{a0}\x{a0} n - - # Unicode complements should not match same character
# was generating malformed utf8
'[\x{100}\xff]'i \x{ff} y $& \x{ff}
# figures it out.
\N{U+} - c - Invalid hexadecimal number
[\N{U+}] - c - Invalid hexadecimal number
-\N{U+4AG3} - c - Invalid hexadecimal number
+\N{U+4AG3} - c - Illegal hexadecimal digit
[\N{U+4AG3}] - c - Invalid hexadecimal number
abc\N{def - c - \\N{NAME} must be resolved by the lexer
/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
+/\N{U+0xBEEF}/ - c - Illegal hexadecimal digit
+/\N{U+BEEF.BEAD}/ - c - Illegal hexadecimal digit
# 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
+\N{U+0xBEEF} - c - Illegal hexadecimal digit
+\c` - c - \"\\c`\" is more clearly written simply as \"\\ \"
+\c1 - c - \"\\c1\" is more clearly written simply as \"q\"
+\cA \001 y $& \1
-# vim: set noexpandtab
+\400 \x{100} y $& \x{100}
+\600 \x{180} y $& \x{180}
+\777 \x{1FF} y $& \x{1FF}
+[a\400] \x{100} y $& \x{100}
+[b\600] \x{180} y $& \x{180}
+[c\777] \x{1FF} y $& \x{1FF}
+\o{120} \x{50} y $& \x{50}
+\o{400} \x{100} y $& \x{100}
+\o{1000} \x{200} y $& \x{200}
+[a\o{120}] \x{50} y $& \x{50}
+[a\o{400}] \x{100} y $& \x{100}
+[a\o{1000}] \x{200} y $& \x{200}
+
+# The below was inserting a NULL into the character class.
+[\8\9] \000 n - -
+[\8\9] 8 y $& 8
+[\8\9] 9 y $& 9
+
+# Verify that reads 1-3 octal digits, and that \_ works in char class
+[\0] \000 y $& \000
+[\07] \007 y $& \007
+[\07] 7\000 n - -
+[\006] \006 y $& \006
+[\006] 6\000 n - -
+[\0005] \0005 y $& \000
+[\0005] 5\000 y $& 5
+[\_] _ y $& _
+
+# RT #79152
+(q1|.)*(q2|.)*(x(a|bc)*y){2,} xayxay y $& xayxay
+(q1|.)*(q2|.)*(x(a|bc)*y){2,3} xayxay y $& xayxay
+(q1|z)*(q2|z)*z{15}-.*?(x(a|bc)*y){2,3}Z zzzzzzzzzzzzzzzz-xayxayxayxayZ y $& zzzzzzzzzzzzzzzz-xayxayxayxayZ
+
+(?:(?:)foo|bar|zot|rt78356) foo y $& foo
+/\xe0\pL/i \xc0a y $& \xc0a
+
+# RT #85528
+(?{})[\x{100}] \x{100} y $& \x{100}
+
+# RT #85964
+^m?(\S)(.*)\1$ aba y $1 a
+^m?(\S)(.*)\1$ \tb\t n - -
+^m?(\s)(.*)\1$ \tb\t y $1 \t
+^m?(\s)(.*)\1$ aba n - -
+^m?(\W)(.*)\1$ :b: y $1 :
+^m?(\W)(.*)\1$ aba n - -
+^m?(\w)(.*)\1$ aba y $1 a
+^m?(\w)(.*)\1$ :b: n - -
+^m?(\D)(.*)\1$ aba y $1 a
+^m?(\D)(.*)\1$ 5b5 n - -
+^m?(\d)(.*)\1$ 5b5 y $1 5
+^m?(\d)(.*)\1$ aba n - -
+
+# 17F is 'Long s'; This makes sure the a's in /aa can be separate
+/s/ai \x{17F} y $& \x{17F}
+/s/aia \x{17F} n - -
+/s/aia S y $& S
+/(?aia:s)/ \x{17F} n - -
+/(?aia:s)/ S y $& S
+
+# Normally 1E9E generates a multi-char fold, but not in inverted class;
+# See [perl #89750]. This makes sure that the simple fold gets generated
+# in that case, to DF.
+/[^\x{1E9E}]/i \x{DF} n - -
+
+# RT #96354
+/^.*\d\H/ X1 n - -
+/^.*\d\V/ X1 n - -
+
+# \p{L_} was being misinterpreted as \p{L}. L_ matches cased letters, which
+# the ideograph below isn't, whereas it does match L
+/^\p{L_}/ \x{3400} n - -
+/^\p{L}/ \x{3400} y $& \x{3400}
+
+# RT #89774
+/[s\xDF]/ui \xDFs ybT $& \xDFs
+
+# RT #99928
+/^\R\x0A$/ \x0D\x0A n - -
+
+/ff/i \x{FB00}\x{FB01} y $& \x{FB00}
+/ff/i \x{FB01}\x{FB00} y $& \x{FB00}
+/fi/i \x{FB01}\x{FB00} y $& \x{FB01}
+/fi/i \x{FB00}\x{FB01} y $& \x{FB01}
+
+# These test that doesn't cut-off matching too soon in the string for
+# multi-char folds
+/ffiffl/i abcdef\x{FB03}\x{FB04} y $& \x{FB03}\x{FB04}
+/\xdf\xdf/ui abcdefssss y $& ssss
+
+/st/i \x{DF}\x{FB05} y $& \x{FB05}
+/ssst/i \x{DF}\x{FB05} y $& \x{DF}\x{FB05}
+
+# [perl #101970]
+/[[:lower:]]/i \x{100} y $& \x{100}
+/[[:upper:]]/i \x{101} y $& \x{101}
+
+# Was matching 'ss' only and failing the entire match, not seeing the
+# alternative that would succeed
+/s\xDF/ui \xDFs Ty $& \xDFs
+/sst/ui s\N{LATIN SMALL LIGATURE ST} Ty $& s\N{LATIN SMALL LIGATURE ST}
+/sst/ui s\N{LATIN SMALL LIGATURE LONG S T} Ty $& s\N{LATIN SMALL LIGATURE LONG S T}
+
+# vim: softtabstop=0 noexpandtab
https://perl5.git.perl.org / perl5.git / blobdiff