-# Copyright (c) 2001-2003 International Business Machines
+# Copyright (c) 2001-2012 International Business Machines
# Corporation and others. All Rights Reserved.
#
-# file:
+# file:
#
# ICU regular expression test cases.
#
# <pattern> = "<regular expression pattern>"
# <match string> = "<tagged string>"
# the quotes on the pattern and match string can be " or ' or /
-# <tagged string> = text, with the start and end of each
+# <tagged string> = text, with the start and end of each
# capture group tagged with <n>...</n>. The overall match,
# if any, is group 0, as in <0>matched text</0>
-# <flags> = any combination of
+# A region can be specified with <r>...</r> tags.
+# Standard ICU unescape will be applied, allowing \u, \U, etc. to appear.
+#
+# <flags> = any combination of
# i case insensitive match
# x free spacing and comments
# s dot-matches-all mode
-# m multi-line mode. $ and ^ match at embedded new-lines
+# m multi-line mode.
+# ($ and ^ match at embedded new-lines)
+# D Unix Lines mode (only recognize 0x0a as new-line)
+# Q UREGEX_LITERAL flag. Entire pattern is literal string.
+# v If icu configured without break iteration, this
+# regex test pattern should not compile.
+# e set the UREGEX_ERROR_ON_UNKNOWN_ESCAPES flag
# d dump the compiled pattern
# t trace operation of match engine.
+# 2-9 a digit between 2 and 9, specifies the number of
+# times to execute find(). The expected results are
+# for the last find() in the sequence.
+# G Only check match / no match. Do not check capture groups.
+# E Pattern compilation error expected
+# L Use LookingAt() rather than find()
+# M Use matches() rather than find().
+#
+# a Use non-Anchoring Bounds.
+# b Use Transparent Bounds.
+# The a and b options only make a difference if
+# a <r>region</r> has been specified in the string.
+# z|Z hitEnd was expected(z) or not expected (Z).
+# With neither, hitEnd is not checked.
+# y|Y Require End expected(y) or not expected (Y).
+#
# White space must be present between the flags and the match string.
#
+# Look-ahead expressions
+#
+"(?!0{5})(\d{5})" "<0><1>00001</1></0>zzzz"
+"(?!0{5})(\d{5})z" "<0><1>00001</1>z</0>zzz"
+"(?!0{5})(\d{5})(?!y)" "<0><1>00001</1></0>zzzz"
+"abc(?=def)" "<0>abc</0>def"
+"(.*)(?=c)" "<0><1>ab</1></0>cdef"
+
+"(?:.*)(?=c)" "<r>ab</r>cdef"
+"(?:.*)(?=c)" b "<r><0>ab</0></r>cdef" # transparent bounds
+"(?:.*)(?=c)" bM "<r><0>ab</0></r>cdef" # transparent bounds
+
+"(?:.*)(?=(c))" b "<0>ab</0><1>c</1>def" # Capture in look-ahead
+"(?=(.)\1\1)\1" "abcc<0><1>d</1></0>ddefg" # Backrefs to look-ahead capture
+
+".(?!\p{L})" "abc<0>d</0> " # Negated look-ahead
+".(?!(\p{L}))" "abc<0>d</0> " # Negated look-ahead, no capture
+ # visible outside of look-ahead
+"and(?=roid)" L "<0>and</0>roid"
+"and(?=roid)" M "<r>and</r>roid"
+"and(?=roid)" bM "<r><0>and</0></r>roid"
+
+"and(?!roid)" L "<0>and</0>roix"
+"and(?!roid)" L "android"
+
+"and(?!roid)" M "<r><0>and</0></r>roid" # Opaque bounds
+"and(?!roid)" bM "<r>and</r>roid"
+"and(?!roid)" bM "<r><0>and</0></r>roix"
+
+#
+# Negated Lookahead, various regions and region transparency
+#
+"abc(?!def)" "<0>abc</0>xyz"
+"abc(?!def)" "abcdef"
+"abc(?!def)" "<r><0>abc</0></r>def"
+"abc(?!def)" b "<r>abc</r>def"
+"abc(?!def)" b "<r><0>abc</0></r>xyz"
+
+#
+# Anchoring Bounds
+#
+"^def$" "abc<r><0>def</0></r>ghi" # anchoring (default) bounds
+"^def$" a "abc<r>def</r>ghi" # non-anchoring bounds
+"^def" a "<r><0>def</0></r>ghi" # non-anchoring bounds
+"def$" a "abc<r><0>def</0></r>" # non-anchoring bounds
+
+"^.*$" m "<0>line 1</0>\n line 2"
+"^.*$" m2 "line 1\n<0> line 2</0>"
+"^.*$" m3 "line 1\n line 2"
+"^.*$" m "li<r><0>ne </0></r>1\n line 2" # anchoring bounds
+"^.*$" m2 "li<r>ne </r>1\n line 2" # anchoring bounds
+"^.*$" am "li<r>ne </r>1\n line 2" # non-anchoring bounds
+"^.*$" am "li\n<r><0>ne </0></r>\n1\n line 2" # non-anchoring bounds
+
+#
+# HitEnd and RequireEnd for new-lines just before end-of-input
+#
+"xyz$" yz "<0>xyz</0>\n"
+"xyz$" yz "<0>xyz</0>\x{d}\x{a}"
+
+"xyz$" myz "<0>xyz</0>" # multi-line mode
+"xyz$" mYZ "<0>xyz</0>\n"
+"xyz$" mYZ "<0>xyz</0>\r\n"
+"xyz$" mYZ "<0>xyz</0>\x{85}abcd"
+
+"xyz$" Yz "xyz\nx"
+"xyz$" Yz "xyza"
+"xyz$" yz "<0>xyz</0>"
+
+#
+# HitEnd
+#
+"abcd" Lz "a"
+"abcd" Lz "ab"
+"abcd" Lz "abc"
+"abcd" LZ "<0>abcd</0>"
+"abcd" LZ "<0>abcd</0>e"
+"abcd" LZ "abcx"
+"abcd" LZ "abx"
+"abcd" Lzi "a"
+"abcd" Lzi "ab"
+"abcd" Lzi "abc"
+"abcd" LZi "<0>abcd</0>"
+"abcd" LZi "<0>abcd</0>e"
+"abcd" LZi "abcx"
+"abcd" LZi "abx"
+
+#
+# All Unicode line endings recognized.
+# 0a, 0b, 0c, 0d, 0x85, 0x2028, 0x2029
+# Multi-line and non-multiline mode take different paths, so repeated tests.
+#
+"^def$" mYZ "abc\x{a}<0>def</0>\x{a}ghi"
+"^def$" mYZ "abc\x{b}<0>def</0>\x{b}ghi"
+"^def$" mYZ "abc\x{c}<0>def</0>\x{c}ghi"
+"^def$" mYZ "abc\x{d}<0>def</0>\x{d}ghi"
+"^def$" mYZ "abc\x{85}<0>def</0>\x{85}ghi"
+"^def$" mYZ "abc\x{2028}<0>def</0>\x{2028}ghi"
+"^def$" mYZ "abc\x{2029}<0>def</0>\x{2029}ghi"
+"^def$" mYZ "abc\r\n<0>def</0>\r\nghi"
+
+"^def$" yz "<0>def</0>\x{a}"
+"^def$" yz "<0>def</0>\x{b}"
+"^def$" yz "<0>def</0>\x{c}"
+"^def$" yz "<0>def</0>\x{d}"
+"^def$" yz "<0>def</0>\x{85}"
+"^def$" yz "<0>def</0>\x{2028}"
+"^def$" yz "<0>def</0>\x{2029}"
+"^def$" yz "<0>def</0>\r\n"
+"^def$" yz "<0>def</0>"
+
+
+"^def$" "<0>def</0>\x{2028" #TODO: should be an error of some sort.
+
+#
+# UNIX_LINES mode
+#
+"abc$" D "<0>abc</0>\n"
+"abc$" D "abc\r"
+"abc$" D "abc\u0085"
+"a.b" D "<0>a\rb</0>"
+"a.b" D "a\nb"
+"(?d)abc$" "<0>abc</0>\n"
+"(?d)abc$" "abc\r"
+"abc$" mD "<0>abc</0>\ndef"
+"abc$" mD "abc\rdef"
+
+".*def" L "abc\r def xyz" # Normal mode, LookingAt() stops at \r
+".*def" DL "<0>abc\r def</0> xyz" # Unix Lines mode, \r not line end.
+".*def" DL "abc\n def xyz"
+
+"(?d)a.b" "a\nb"
+"(?d)a.b" "<0>a\rb</0>"
+
+"^abc" m "xyz\r<0>abc</0>"
+"^abc" Dm "xyz\rabc"
+"^abc" Dm "xyz\n<0>abc</0>"
+
+
# Capturing parens
".(..)." "<0>a<1>bc</1>d</0>"
"(hello)|(goodbye)" "<0><2>goodbye</2></0>"
"abc( +( inner(X?) +) xyz)" "leading cruft <0>abc<1> <2> inner<3></3> </2> xyz</1></0> cruft"
"\s*([ixsmdt]*)([:letter:]*)" "<0> <1>d</1><2></2></0> "
+"(a|b)c*d" "a<0><1>b</1>cd</0>"
# Non-capturing parens (?: stuff). Groups, but does not capture.
"(?:abc)*(tail)" "<0>abcabcabc<1>tail</1></0>"
".*\Ahello" "stuff\nhello" # don't match after embedded new-line.
# \b \B
+#
".*?\b(.).*" "<0> $%^&*( <1>h</1>ello123%^&*()gxx</0>"
"\ba\b" "-<0>a</0>"
"\by\b" "xy"
+"[ \b]" "<0>b</0>" # in a set, \b is a literal b.
# Finds first chars of up to 5 words
"(?:.*?\b(\w))?(?:.*?\b(\w))?(?:.*?\b(\w))?(?:.*?\b(\w))?(?:.*?\b(\w))?" "<0><1>T</1>the <2>q</2>ick <3>b</3>rown <4>f</4></0>ox"
"(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?.*" "<0> \u0301 \u0301<1>A</1>\u0302BC\u0303\u0304<2> </2>\u0305 \u0306<3>X</3>\u0307Y\u0308</0>"
+
+#
+# Unicode word boundary mode
+#
+"(?w).*?\b" v "<0></0>hello, world"
+"(?w).*?(\b.+?\b).*" v "<0><1> </1> 123.45 </0>"
+"(?w).*?(\b\d.*?\b).*" v "<0> <1>123.45</1> </0>"
+".*?(\b.+?\b).*" "<0> <1>123</1>.45 </0>"
+"(?w:.*?(\b\d.*?\b).*)" v "<0> <1>123.45</1> </0>"
+"(?w:.*?(\b.+?\b).*)" v "<0><1>don't</1> </0>"
+"(?w:.+?(\b\S.+?\b).*)" v "<0> <1>don't</1> </0>"
+"(?w:(\b.+?)(\b.+?)(\b.+?)(\b.+?)(\b.+?)(\b.+?)(\b.+?).*)" v "<0><1>.</1><2> </2><3>,</3><4>:</4><5>$</5><6>37,000.50</6><7> </7> </0>"
+
+#
+# Unicode word boundaries with Regions
+#
+"(?w).*?\b" v "abc<r><0>def</0></r>ghi"
+"(?w).*?\b" v2 "abc<r>def<0></0></r>ghi"
+"(?w).*?\b" v3 "abc<r>def</r>ghi"
+#"(?w).*?\b" vb "abc<r><0>def</0></r>ghi" # TODO: bug. Ticket 6073
+#"(?w).*?\b" vb2 "abc<r>def</r>ghi"
+
+
+
# . does not match new-lines
-"." "\u000a\u000d\u0085\u000c\u2028\u2029<0>X</0>\u000aY"
+"." "\u000a\u000d\u0085\u000c\u000b\u2028\u2029<0>X</0>\u000aY"
"A." "A\u000a "# no match
# \d for decimal digits
-"\d*" "<0>0123456789\u0660\u06F9\u0969\u0A66\u1369\u17E2\uFF10\U0001D7CE\U0001D7FF</0>non-digits"
+"\d*" "<0>0123456789\u0660\u06F9\u0969\u0A66\u17E2\uFF10\U0001D7CE\U0001D7FF</0>non-digits"
"\D+" "<0>non digits</0>"
"\D*(\d*)(\D*)" "<0>non-digits<1>3456666</1><2>more non digits</2></0>"
# \Q...\E quote mode
"hel\Qlo, worl\Ed" "<0>hello, world</0>"
"\Q$*^^(*)?\A\E(a*)" "<0>$*^^(*)?\\A<1>aaaaaaaaaaaaaaa</1></0>"
+"[abc\Q]\r\E]+" "<0>aaaccc]]]\\\\\\</0>\r..." # \Q ... \E escape in a [set]
+
+# UREGEX_LITERAL - entire pattern is a literal string, no escapes recognized.
+# Note that data strings in test cases still get escape processing.
+"abc\an\r\E\\abcd\u0031bye" Q "lead<0>abc\\an\\r\\E\\\\abcd\\u0031bye</0>extra"
+"case insensitive \\ (l)iteral" Qi "stuff!! <0>cAsE InSenSiTiVE \\\\ (L)ITeral</0>"
# \S and \s space characters
"\s+" "not_space<0> \t \r \n \u3000 \u2004 \u2028 \u2029</0>xyz"
".*^(Hello)" " Hello Hello Hello Hello Goodbye"# No Match
# $ matches only at end of line, or before a newline preceding the end of line
-".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
-".*?(Goodbye)" "<0>Hello <1>Goodbye</1></0> Goodbye Goodbye"
-".*?(Goodbye)$" "Hello Goodbye> Goodbye Goodbye "# No Match
+".*?(Goodbye)$" zy "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
+".*?(Goodbye)" ZY "<0>Hello <1>Goodbye</1></0> Goodbye Goodbye"
+".*?(Goodbye)$" z "Hello Goodbye> Goodbye Goodbye "# No Match
-".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
-".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
-".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\r\n"
-".*?(Goodbye)$" "Hello Goodbye Goodbye Goodbye\n\n"# No Match
+".*?(Goodbye)$" zy "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
+".*?(Goodbye)$" zy "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
+".*?(Goodbye)$" zy "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\r\n"
+".*?(Goodbye)$" z "Hello Goodbye Goodbye Goodbye\n\n"# No Match
# \Z matches at end of input, like $ with default flags.
-".*?(Goodbye)\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
-".*?(Goodbye)" "<0>Hello <1>Goodbye</1></0> Goodbye Goodbye"
-".*?(Goodbye)\Z" "Hello Goodbye> Goodbye Goodbye "# No Match
-"here$" "here\nthe end"# No Match
+".*?(Goodbye)\Z" zy "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
+".*?(Goodbye)" ZY "<0>Hello <1>Goodbye</1></0> Goodbye Goodbye"
+".*?(Goodbye)\Z" z "Hello Goodbye> Goodbye Goodbye "# No Match
+"here$" z "here\nthe end"# No Match
".*?(Goodbye)\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
# \z matches only at the end of string.
# no special treatment of new lines.
# no dependencies on flag settings.
-".*?(Goodbye)\z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
-".*?(Goodbye)\z" "Hello Goodbye Goodbye Goodbye "# No Match
-"here$" "here\nthe end"# No Match
+".*?(Goodbye)\z" zy "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
+".*?(Goodbye)\z" z "Hello Goodbye Goodbye Goodbye "# No Match
+"here$" z "here\nthe end"# No Match
-".*?(Goodbye)\z" "Hello Goodbye Goodbye Goodbye\n"# No Match
-".*?(Goodbye)\n\z" "<0>Hello Goodbye Goodbye <1>Goodbye</1>\n</0>"
+".*?(Goodbye)\z" z "Hello Goodbye Goodbye Goodbye\n"# No Match
+".*?(Goodbye)\n\z" zy "<0>Hello Goodbye Goodbye <1>Goodbye</1>\n</0>"
+"abc\z|def" ZY "abc<0>def</0>"
# (?# comment) doesn't muck up pattern
"Hello (?# this is a comment) world" " <0>Hello world</0>..."
"(x?)*xyz" "<0>xx<1></1>xyz</0>" # Sligthly wierd, but correct. The "last" time through (x?),
# it matches the empty string.
+# Set expressions, basic operators and escapes work
+#
+"[\d]+" "<0>0123</0>abc/.,"
+"[^\d]+" "0123<0>abc/.,</0>"
+"[\D]+" "0123<0>abc/.,</0>"
+"[^\D]+" "<0>0123</0>abc/.,"
+
+"[\s]+" "<0> \t</0>abc/.,"
+"[^\s]+" " \t<0>abc/.,</0>"
+"[\S]+" " \t<0>abc/.,</0>"
+"[^\S]+" "<0> \t</0>abc/.,"
+
+"[\w]+" "<0>abc123</0> .,;"
+"[^\w]+" "abc123<0> .,;</0>"
+"[\W]+" "abc123<0> .,;</0>"
+"[^\W]+" "<0>abc123</0> .,;"
+
+"[\z]+" "abc<0>zzz</0>def" # \z has no special meaning
+"[^\z]+" "<0>abc</0>zzzdef"
+"[\^]+" "abc<0>^^</0>"
+"[^\^]+" "<0>abc</0>^^"
+
+"[\u0041c]+" "<0>AcAc</0>def"
+"[\U00010002]+" "<0>\ud800\udc02</0>\U00010003"
+"[^\U00010002]+" "<0>Hello</0>\x{10002}"
+"[\x61b]+" "<0>abab</0>cde"
+#"[\x6z]+" "\x06" #TODO: single hex digits should fail
+"[\x{9}\x{75}\x{6d6}\x{6ba6}\x{6146B}\x{10ffe3}]+" "<0>\u0009\u0075\u06d6\u6ba6\U0006146B\U0010ffe3</0>abc"
+
+"[\N{LATIN CAPITAL LETTER TONE SIX}ab\N{VARIATION SELECTOR-70} ]+" "x<0> \u0184\U000E0135 ab</0>c"
+"[\N{LATIN SMALL LETTER C}-\N{LATIN SMALL LETTER F}]+" "ab<0>cdef</0>ghi"
+
+
+
+#
+# [set expressions], check the precedence of '-', '&', '--', '&&'
+# '-' and '&', for compatibility with ICU UnicodeSet, have the same
+# precedence as the implicit Union between adjacent items.
+# '--' and '&&', for compatibility with Java, have lower precedence than
+# the implicit Union operations. '--' and '&&' themselves
+# have the same precedence, and group left to right.
+#
+"[[a-m]-[f-w]p]+" "<0>dep</0>fgwxyz"
+"[^[a-m]-[f-w]p]+" "dep<0>fgwxyz</0>"
+
+"[[a-m]--[f-w]p]+" "<0>de</0>pfgwxyz"
+"[^[a-m]--[f-w]p]+" "de<0>pfgwxyz</0>"
+
+"[[a-m]&[e-s]w]+" "<0>efmw</0>adnst"
+"[^[a-m]&[e-s]w]+" "efmw<0>adnst</0>"
+
+"[[a-m]&[e-s]]+" "<0>efm</0>adnst"
+
+
+
# {min,max} iteration qualifier
"A{3}BC" "<0>AAABC</0>"
"ab(?:c|(d?))(\1)" "<0>ab<1></1><2></2></0>e"
"ab(?:c|(d?))(\1)" "<0>ab<1></1><2></2></0>"
+# Back References that hit/don't hit end
+"(abcd) \1" z "abcd abc"
+"(abcd) \1" Z "<0><1>abcd</1> abcd</0>"
+"(abcd) \1" Z "<0><1>abcd</1> abcd</0> "
+
+# Case Insensitve back references that hit/don't hit end.
+"(abcd) \1" zi "abcd abc"
+"(abcd) \1" Zi "<0><1>abcd</1> ABCD</0>"
+"(abcd) \1" Zi "<0><1>abcd</1> ABCD</0> "
+
+# Back references that hit/don't hit boundary limits.
+
+"(abcd) \1" z "<r>abcd abc</r>d "
+"(abcd) \1" Z "<r><0><1>abcd</1> abcd</0></r> "
+"(abcd) \1" Z "<r><0><1>abcd</1> abcd</0> </r>"
+
+"(abcd) \1" zi "<r>abcd abc</r>d "
+"(abcd) \1" Zi "<r><0><1>abcd</1> abcd</0></r> "
+"(abcd) \1" Zi "<r><0><1>abcd</1> abcd</0> </r>"
+
+# Back reference that fails match near the end of input without actually hitting the end.
+"(abcd) \1" ZL "abcd abd"
+"(abcd) \1" ZLi "abcd abd"
+
+# Back reference to a zero-length match. They are always a successful match.
+"ab(x?)cd(\1)ef" "<0>ab<1></1>cd<2></2>ef</0>"
+"ab(x?)cd(\1)ef" i "<0>ab<1></1>cd<2></2>ef</0>"
+
+# Back refs to capture groups that didn't participate in the match.
+"ab(?:(c)|(d))\1" "abde"
+"ab(?:(c)|(d))\1" "<0>ab<1>c</1>c</0>e"
+"ab(?:(c)|(d))\1" i "abde"
+"ab(?:(c)|(d))\1" i "<0>ab<1>c</1>c</0>e"
+
# Case Insensitive
-"aBc" i "<0>ABC</0>"
-"a[^bc]d" i "ABD"
+"aBc" i "<0>ABC</0>"
+"a[^bc]d" i "ABD"
'((((((((((a))))))))))\10' i "<0><1><2><3><4><5><6><7><8><9><10>A</10></9></8></7></6></5></4></3></2></1>A</0>"
"(?:(?i)a)b" "<0>Ab</0>"
"a b" "ab"
"abc " "abc"
"abc " "<0>abc </0>"
-"ab[cd e]z" "<0>ab z</0>"
+"ab[cd e]z" "<0>ab z</0>"
"ab\ c" "<0>ab c</0> "
"ab c" "<0>ab c</0> "
"ab c" x "ab c "
"ab\ c" x "<0>ab c</0> "
+#
+# Pattern Flags
+#
+"(?u)abc" "<0>abc</0>"
+"(?-u)abc" "<0>abc</0>"
+
+#
+# \c escapes (Control-whatever)
+#
+"\cA" "<0>\u0001</0>"
+"\ca" "<0>\u0001</0>"
+"\c\x" "<0>\u001cx</0>"
+
#Multi-line mode
-'b\s^' m "a\nb\n"
+'b\s^' m "a\nb\n"
+"(?m)^abc$" "abc \n abc\n<0>abc</0>\nabc"
+"(?m)^abc$" 2 "abc \n abc\nabc\n<0>abc</0>"
+"^abc$" 2 "abc \n abc\nabc\nabc"
+
+# Empty and full range
+"[\u0000-\U0010ffff]+" "<0>abc\u0000\uffff\U00010000\U0010ffffzz</0>"
+"[^\u0000-\U0010ffff]" "abc\u0000\uffff\U00010000\U0010ffffzz"
+"[^a--a]+" "<0>abc\u0000\uffff\U00010000\U0010ffffzz</0>"
# Free-spacing mode
"a b c # this is a comment" x "<0>abc</0> "
"abc.*$" "<0>abcdef</0>"
"abc(.*)" "<0>abc<1>def</1></0>"
"abc(.*)" "<0>abc<1></1></0>"
-"abc.*" "<0>abc</0>\ndef"
-"abc.*" s "<0>abc\ndef</0>"
+"abc.*" "<0>abc</0>\ndef"
+"abc.*" s "<0>abc\ndef</0>"
"abc.*$" s "<0>abc\ndef</0>"
"abc.*$" "abc\ndef"
"abc.*$" m "<0>abc</0>\ndef"
"ab\x09w" "<0>ab\u0009w</0>"
"ab\xabcdc" "<0>ab\u00abcdc</0>"
"ab\x{abcd}c" "<0>ab\uabcdc</0>"
-"ab\x{101234}c" "<0>ab\U00101234c</0>"
+"ab\x{101234}c" "<0>ab\U00101234c</0>"
"abα" "<0>abα</0>"
+#
+# Octal Escaping. This conforms to Java conventions, not Perl.
+"\0101\00\03\073\0154\01442" "<0>A\u0000\u0003\u003b\u006c\u0064\u0032</0>"
+"\0776" "<0>\u003f\u0036</0>" # overflow, the 6 is literal.
+"\0376xyz" "<0>\u00fexyz</0>"
+"\08" E "<0>\u00008</0>"
+"\0" E "x"
#
# \u Surrogate Pairs
"\ud800\udc00*" "<0>\U00010000\U00010000\U00010000</0>\U00010001"
"\ud800\ud800\udc00" "<0>\ud800\U00010000</0>\U00010000\U00010000\U00010001"
"(\ud800)(\udc00)" "\U00010000"
+"\U00010001+" "<0>\U00010001\U00010001</0>\udc01"
+
+#
+# hitEnd with find()
+#
+"abc" Z "aa<0>abc</0> abcab"
+"abc" 2Z "aaabc <0>abc</0>ab"
+"abc" 3z "aa>abc abcab"
+
+#
+# \ escaping
+#
+"abc\jkl" "<0>abcjkl</0>" # escape of a non-special letter is just itself.
+"abc[ \j]kl" "<0>abcjkl</0>"
+
+#
+# Bug xxxx
+#
+"(?:\-|(\-?\d+\d\d\d))?(?:\-|\-(\d\d))?(?:\-|\-(\d\d))?(T)?(?:(\d\d):(\d\d):(\d\d)(\.\d+)?)?(?:(?:((?:\+|\-)\d\d):(\d\d))|(Z))?" MG "<0>-1234-21-31T41:51:61.789+71:81</0>"
+
+
+#
+# A random, complex, meaningless pattern that should at least compile
+#
+"(?![^\<C\f\0146\0270\}&&[|\02-\x3E\}|X-\|]]{7,}+)[|\\\x98\<\?\u4FCFr\,\0025\}\004|\0025-\0521]|(?<![|\01-\u829E])|(?<!\p{Alpha})|^|(?-s:[^\x15\\\x24F\a\,\a\u97D8[\x38\a[\0224-\0306[^\0020-\u6A57]]]]??)(?xix:[^|\{\[\0367\t\e\x8C\{\[\074c\]V[|b\fu\r\0175\<\07f\066s[^D-\x5D]]])(?xx:^{5,}+)(?d)(?=^\D)|(?!\G)(?>\G)(?![^|\]\070\ne\{\t\[\053\?\\\x51\a\075\0023-\[&&[|\022-\xEA\00-\u41C2&&[^|a-\xCC&&[^\037\uECB3\u3D9A\x31\|\<b\0206\uF2EC\01m\,\ak\a\03&&\p{Punct}]]]])(?-dxs:[|\06-\07|\e-\x63&&[|Tp\u18A3\00\|\xE4\05\061\015\0116C|\r\{\}\006\xEA\0367\xC4\01\0042\0267\xBB\01T\}\0100\?[|\[-\u459B|\x23\x91\rF\0376[|\?-\x94\0113-\\\s]]]]{6}?)(?<=[^\t-\x42H\04\f\03\0172\?i\u97B6\e\f\uDAC2])(?=\B)(?>[^\016\r\{\,\uA29D\034\02[\02-\[|\t\056\uF599\x62\e\<\032\uF0AC\0026\0205Q\|\\\06\0164[|\057-\u7A98&&[\061-g|\|\0276\n\042\011\e\xE8\x64B\04\u6D0EDW^\p{Lower}]]]]?)(?<=[^\n\\\t\u8E13\,\0114\u656E\xA5\]&&[\03-\026|\uF39D\01\{i\u3BC2\u14FE]])(?<=[^|\uAE62\054H\|\}&&^\p{Space}])(?sxx)(?<=[\f\006\a\r\xB4]{1,5})|(?x-xd:^{5}+)()" "<0></0>abc"
+
+#
+# Bug 3225
+
+"1|9" "<0>1</0>"
+"1|9" "<0>9</0>"
+"1*|9" "<0>1</0>"
+"1*|9" "<0></0>9"
+
+"(?:a|ac)d" "<0>acd</0>"
+"a|ac" "<0>a</0>c"
+#
+# Bug 3320
+#
+"(a([^ ]+)){0,} (c)" "<0><1>a<2>b</2></1> <3>c</3></0> "
+"(a([^ ]+))* (c)" "<0><1>a<2>b</2></1> <3>c</3></0> "
#
+# Bug 3436
+#
+"(.*?) *$" "<0><1>test</1> </0>"
+
+#
+# Bug 4034
+#
+"\D" "<0>A</0>BC\u00ffDEF"
+"\d" "ABC\u00ffDEF"
+"\D" "<0>\u00ff</0>DEF"
+"\d" "\u00ffDEF"
+"\D" "123<0>\u00ff</0>DEF"
+"\D" "<0>\u0100</0>DEF"
+"\D" "123<0>\u0100</0>DEF"
+
+#
+#bug 4024, new line sequence handling
+#
+"(?m)^" "<0></0>AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+"(?m)^" 2 "AA\u000d\u000a<0></0>BB\u000d\u000aCC\u000d\u000a"
+"(?m)^" 3 "AA\u000d\u000aBB\u000d\u000a<0></0>CC\u000d\u000a"
+"(?m)^" 4 "AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+
+"(?m)$" "AA<0></0>\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+"(?m)$" 2 "AA\u000d\u000aBB<0></0>\u000d\u000aCC\u000d\u000a"
+"(?m)$" 3 "AA\u000d\u000aBB\u000d\u000aCC<0></0>\u000d\u000a"
+"(?m)$" 4 "AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a<0></0>"
+"(?m)$" 5 "AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+
+"$" "AA\u000d\u000aBB\u000d\u000aCC<0></0>\u000d\u000a"
+"$" 2 "AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a<0></0>"
+"$" 3 "AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+
+"$" "\u000a\u0000a<0></0>\u000a"
+"$" 2 "\u000a\u0000a\u000a<0></0>"
+"$" 3 "\u000a\u0000a\u000a"
+
+"$" "<0></0>"
+"$" 2 ""
+
+"$" "<0></0>\u000a"
+"$" 2 "\u000a<0></0>"
+"$" 3 "\u000a"
+
+"^" "<0></0>"
+"^" 2 ""
+
+"\Z" "<0></0>"
+"\Z" 2 ""
+"\Z" 2 "\u000a<0></0>"
+"\Z" "<0></0>\u000d\u000a"
+"\Z" 2 "\u000d\u000a<0></0>"
+
+
+# No matching ^ at interior new-lines if not in multi-line mode.
+"^" "<0></0>AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+"^" 2 "AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+
+#
+# Dot-matches-any mode, and stopping at new-lines if off.
+#
+"." "<0>1</0>23\u000aXYZ"
+"." 2 "1<0>2</0>3\u000aXYZ"
+"." 3 "12<0>3</0>\u000aXYZ"
+"." 4 "123\u000a<0>X</0>YZ" # . doesn't match newlines
+"." 4 "123\u000b<0>X</0>YZ"
+"." 4 "123\u000c<0>X</0>YZ"
+"." 4 "123\u000d<0>X</0>YZ"
+"." 4 "123\u000d\u000a<0>X</0>YZ"
+"." 4 "123\u0085<0>X</0>YZ"
+"." 4 "123\u2028<0>X</0>YZ"
+"." 4 "123\u2029<0>X</0>YZ"
+"." 4s "123<0>\u000a</0>XYZ" # . matches any
+"." 4s "123<0>\u000b</0>XYZ"
+"." 4s "123<0>\u000c</0>XYZ"
+"." 4s "123<0>\u000d</0>XYZ"
+"." 4s "123<0>\u000d\u000a</0>XYZ"
+"." 4s "123<0>\u0085</0>XYZ"
+"." 4s "123<0>\u2028</0>XYZ"
+"." 4s "123<0>\u2029</0>XYZ"
+".{6}" "123\u000a\u000dXYZ"
+".{6}" s "<0>123\u000a\u000dX</0>Y"
+
+
+#
+# Ranges
+#
+".*" "abc<r><0>def</0></r>ghi"
+"a" "aaa<r><0>a</0>aa</r>aaa"
+"a" 2 "aaa<r>a<0>a</0>a</r>aaa"
+"a" 3 "aaa<r>aa<0>a</0></r>aaa"
+"a" 4 "aaa<r>aaa</r>aaa"
+"a" "aaa<r><0>a</0>aa</r>aaa"
+
+#
+# [set] parsing, systematically run through all of the parser states.
+#
+#
+"[def]+" "abc<0>ddeeff</0>ghi" # set-open
+"[^def]+" "<0>abc</0>defghi"
+"[:digit:]+" "abc<0>123</0>def"
+"[:^digit:]+" "<0>abc</0>123def"
+"[\u005edef]+" "abc<0>de^f</0>ghi"
+
+"[]]+" "abc<0>]]]</0>[def" # set-open2
+"[^]]+" "<0>abc</0>]]][def"
+
+"[:Lu:]+" "abc<0>ABC</0>def" # set-posix
+"[:Lu]+" "abc<0>uL::Lu</0>"
+"[:^Lu]+" "abc<0>uL:^:Lu</0>"
+"[:]+" "abc<0>:::</0>def"
+"[:whats this:]" E " "
+"[--]+" dE "-------"
+
+"[[nested]]+" "xyz[<0>nnetsteed</0>]abc" #set-start
+"[\x{41}]+" "CB<0>AA</0>ZYX"
+"[\[\]\\]+" "&*<0>[]\\</0>..."
+"[*({<]+" "^&<0>{{(<<*</0>)))"
+
+
+"[-def]+" "abc<0>def-ef-d</0>xyz" # set-start-dash
+"[abc[--def]]" E " "
+
+"[x[&def]]+" "abc<0>def&</0>ghi" # set-start-amp
+"[&& is bad at start]" E " "
+
+"[abc" E " " # set-after-lit
+"[def]]" "abcdef"
+"[def]]" "abcde<0>f]</0>]"
+
+"[[def][ghi]]+" "abc]<0>defghi</0>[xyz" # set-after-set
+"[[def]ghi]+" "abc]<0>defghi</0>[xyz"
+"[[[[[[[[[[[abc]" E " "
+"[[abc]\p{Lu}]+" "def<0>abcABC</0>xyz"
+
+"[d-f]+" "abc<0>def</0>ghi" # set-after-range
+"[d-f[x-z]]+" "abc<0>defxyzzz</0>gw"
+"[\s\d]+" "abc<0> 123</0>def"
+"[d-f\d]+" "abc<0>def123</0>ghi"
+"[d-fr-t]+" "abc<0>defrst</0>uvw"
+
+"[abc--]" E " " # set-after-op
+"[[def]&&]" E " "
+"[-abcd---]+" "<0>abc</0>--" #[-abcd]--[-]
+"[&abcd&&&ac]+" "b<0>ac&&ca</0>d" #[&abcd]&&[&ac]
+
+"[[abcd]&[ac]]+" "b<0>acac</0>d" # set-set-amp
+"[[abcd]&&[ac]]+" "b<0>acac</0>d"
+"[[abcd]&&ac]+" "b<0>acac</0>d"
+"[[abcd]&ac]+" "<0>bacacd&&&</0>"
+
+"[abcd&[ac]]+" "<0>bacacd&&&</0>" #set-lit-amp
+"[abcd&&[ac]]+" "b<0>acac</0>d"
+"[abcd&&ac]+" "b<0>acac</0>d"
+
+"[[abcd]-[ac]]+" "a<0>bdbd</0>c" # set-set-dash
+"[[abcd]--[ac]]+" "a<0>bdbd</0>c"
+"[[abcd]--ac]+" "a<0>bdbd</0>c"
+"[[abcd]-ac]+" "<0>bacacd---</0>"
+
+"[a-d--[b-c]]+" "b<0>adad</0>c" # set-range-dash
+"[a-d--b-c]+" "b<0>adad</0>c"
+"[a-d-[b-c]]+" "<0>bad-adc</0>"
+"[a-d-b-c]+" "<0>bad-adc</0>"
+"[\w--[b-c]]+" "b<0>adad</0>c"
+"[\w--b-c]+" "b<0>adad</0>c"
+"[\w-[b-c]]+" "<0>bad-adc</0>"
+"[\w-b-c]+" "<0>bad-adc</0>"
+
+"[a-d&&[b-c]]+" "a<0>bcbc</0>d" # set-range-amp
+"[a-d&&b-c]+" "a<0>bcbc</0>d"
+"[a-d&[b-c]]+" "<0>abc&bcd</0>"
+"[a-d&b-c]+" "<0>abc&bcd</0>"
+
+"[abcd--bc]+" "b<0>adda</0>c" # set-lit-dash
+"[abcd--[bc]]+" "b<0>adda</0>c"
+"[abcd-[bc]]+" "<0>bad--dac</0>xyz"
+"[abcd-]+" "<0>bad--dac</0>xyz"
+
+"[abcd-\s]+" E "xyz<0>abcd --</0>xyz" # set-lit-dash-esc
+"[abcd-\N{LATIN SMALL LETTER G}]+" "xyz-<0>abcdefg</0>hij-"
+"[bcd-\{]+" "a<0>bcdefyz{</0>|}"
+
+"[\p{Ll}]+" "ABC<0>abc</0>^&*&" # set-escape
+"[\P{Ll}]+" "abc<0>ABC^&*&</0>xyz"
+"[\N{LATIN SMALL LETTER Q}]+" "mnop<0>qqq</0>rst"
+"[\sa]+" "cb<0>a a </0>(*&"
+"[\S]+" " <0>hello</0> "
+"[\w]+" " <0>hello_world</0>! "
+"[\W]+" "a<0> *$%#,</0>hello "
+"[\d]+" "abc<0>123</0>def"
+"[\D]+" "123<0>abc</0>567"
+"[\$\#]+" "123<0>$#$#</0>\\"
+
+#
+# Try each of the Java compatibility properties.
+# These are checked here, while normal Unicode properties aren't, because
+# these Java compatibility properties are implemented directly by regexp, while other
+# properties are handled by ICU's Property and UnicodeSet APIs.
+#
+# These tests are only to verify that the names are recognized and the
+# implementation isn't dead. They are not intended to verify that the
+# function defintions are 100% correct.
+#
+"[:InBasic Latin:]+" "ΓΔΕΖΗΘ<0>hello, world.</0>ニヌネノハバパ"
+"[:^InBasic Latin:]+" "<0>ΓΔΕΖΗΘ</0>hello, world.ニヌネノハバパ"
+"\p{InBasicLatin}+" "ΓΔΕΖΗΘ<0>hello, world.</0>ニヌネノハバパ"
+"\P{InBasicLatin}+" "<0>ΓΔΕΖΗΘ</0>hello, world.ニヌネノハバパ"
+"\p{InGreek}+" "<0>ΓΔΕΖΗΘ</0>hello, world.ニヌネノハバパ"
+"\p{InCombining Marks for Symbols}" "<0>\u20d0</0>"
+"\p{Incombiningmarksforsymbols}" "<0>\u20d0</0>"
+
+
+"\p{javaDefined}+" "\uffff<0>abcd</0>\U00045678"
+"\p{javaDigit}+" "abc<0>1234</0>xyz"
+"\p{javaIdentifierIgnorable}+" "abc<0>\u0000\u000e\u009f</0>xyz"
+"\p{javaISOControl}+" "abc<0>\u0000\u000d\u0083</0>xyz"
+"\p{javaJavaIdentifierPart}+" "#@!<0>abc123_$</0>;"
+"\p{javaJavaIdentifierStart}+" "123\u0301<0>abc$_</0>%^&"
+"\p{javaLetter}+" "123<0>abcDEF</0>&*()("
+"\p{javaLetterOrDigit}+" "$%^&*<0>123abcகஙசஜஞ</0>☺♘♚☔☎♬⚄⚡"
+"\p{javaLowerCase}+" "ABC<0>def</0>&^%#:="
+"\p{javaMirrored}+" "ab$%<0>(){}[]</0>xyz"
+"\p{javaSpaceChar}+" "abc<0> \u00ao\u2028</0>!@#"
+"\p{javaSupplementaryCodePoint}+" "abc\uffff<0>\U00010000\U0010ffff</0>\u0000"
+"\p{javaTitleCase}+" "abCE<0>Džῌᾨ</0>123"
+"\p{javaUnicodeIdentifierStart}+" "123<0>abcⅣ</0>%^&&*"
+"\p{javaUnicodeIdentifierPart}+" "%&&^<0>abc123\u0301\u0002</0>..."
+"\p{javaUpperCase}+" "abc<0>ABC</0>123"
+"\p{javaValidCodePoint}+" "<0>\u0000abc\ud800 unpaired \udfff |\U0010ffff</0>"
+"\p{javaWhitespace}+" "abc\u00a0\u2007\u202f<0> \u0009\u001c\u001f\u2028</0>42"
+"\p{all}+" "<0>123\u0000\U0010ffff</0>"
+"\P{all}+" "123\u0000\U0010ffff"
+
+# [:word:] is implemented directly by regexp. Not a java compat property, but PCRE and others.
+
+"[:word:]+" ".??$<0>abc123ΓΔΕΖΗ_</0>%%%"
+"\P{WORD}+" "<0>.??$</0>abc123ΓΔΕΖΗ_%%%"
+
+#
+# Errors on unrecognized ASCII letter escape sequences.
+#
+"[abc\Y]+" "<0>abcY</0>"
+"[abc\Y]+" eE "<0>abcY</0>"
+
+"(?:a|b|c|\Y)+" "<0>abcY</0>"
+"(?:a|b|c|\Y)+" eE "<0>abcY</0>"
+
+"\Q\Y\E" e "<0>\\Y</0>"
+
+#
+# Reported problem
+#
+"[a-\w]" E "x"
+
+#
+# Bug 4045
+#
+"A*" "<0>AAAA</0>"
+"A*" 2 "AAAA<0></0>"
+"A*" 3 "AAAA"
+"A*" 4 "AAAA"
+"A*" 5 "AAAA"
+"A*" 6 "AAAA"
+"A*" "<0></0>"
+"A*" 2 ""
+"A*" 3 ""
+"A*" 4 ""
+"A*" 5 ""
+
+#
+# Bug 4046
+#
+"(?m)^" "<0></0>AA\u000dBB\u000dCC\u000d"
+"(?m)^" 2 "AA\u000d<0></0>BB\u000dCC\u000d"
+"(?m)^" 3 "AA\u000dBB\u000d<0></0>CC\u000d"
+"(?m)^" 4 "AA\u000dBB\u000dCC\u000d"
+"(?m)^" 5 "AA\u000dBB\u000dCC\u000d"
+"(?m)^" 6 "AA\u000dBB\u000dCC\u000d"
+
+"(?m)^" "<0></0>AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+"(?m)^" 2 "AA\u000d\u000a<0></0>BB\u000d\u000aCC\u000d\u000a"
+"(?m)^" 3 "AA\u000d\u000aBB\u000d\u000a<0></0>CC\u000d\u000a"
+"(?m)^" 4 "AA\u000d\u000aBB\u000d\u000aCC\u000d\u000a"
+
+#
+# Bug 4059
+#
+"\w+" "<0>イチロー</0>"
+"\b....\b." "<0>イチロー?</0>"
+
+
+#
+# Bug 4058 ICU Unicode Set patterns have an odd feature -
+# A $ as the last character before the close bracket means match
+# a \uffff, which means off the end of the string in transliterators.
+# Didn't make sense for regular expressions, and is now fixed.
+#
+"[\$](P|C|D);" "<0>$<1>P</1>;</0>"
+"[$](P|C|D);" "<0>$<1>P</1>;</0>"
+"[$$](P|C|D);" "<0>$<1>P</1>;</0>"
+
+#
+# bug 4888 Flag settings lost in some cases.
+#
+"((a){2})|(#)" is "no"
+"((a){2})|(#)" is "<0><1>a<2>a</2></1></0>#"
+"((a){2})|(#)" is "a<0><3>#</3></0>"
+
+"((a|b){2})|c" is "<0>c</0>"
+"((a|b){2})|c" is "<0>C</0>"
+"((a|b){2})|c" s "C"
+
+#
+# bug 5617 ZWJ \u200d shoudn't cause word boundaries
+#
+".+?\b" "<0> </0>\u0935\u0915\u094D\u200D\u0924\u0947 "
+".+?\b" 2 " <0>\u0935\u0915\u094D\u200D\u0924\u0947</0> "
+".+?\b" 3 " \u0935\u0915\u094D\u200D\u0924\u0947 "
+
+#
+# bug 5386 "^.*$" should match empty input
+#
+"^.*$" "<0></0>"
+"^.*$" m "<0></0>"
+"^.*$" "<0></0>\n"
+"(?s)^.*$" "<0>\n</0>"
+
+#
+# bug 5386 Empty pattern and empty input should match.
+#
+"" "<0></0>abc"
+"" "<0></0>"
+
+#
+# bug 5386 Range upper and lower bounds can be equal
+#
+"[a-a]" "<0>a</0>"
+
+#
+# bug 5386 $* should not fail, should match empty string.
+#
+"$*" "<0></0>abc"
+
+#
+# bug 5386 \Q ... \E escaping problem
+#
+"[a-z\Q-$\E]+" "QE<0>abc-def$</0>."
+
+# More reported 5386 Java comaptibility failures
+#
+"[^]*abb]*" "<0>kkkk</0>"
+"\xa" "huh" # Java would like to be warned.
+"^.*$" "<0></0>"
+
+#
+# bug 5386 Empty left alternation should produce a zero length match.
+#
+"|a" "<0></0>a"
+"$|ab" "<0>ab</0>"
+"$|ba" "ab<0></0>"
+
+#
+# bug 5386 Java compatibility for set expressions
+#
+"[a-z&&[cde]]+" "ab<0>cde</0>fg"
+
+#
+# bug 6019 matches() needs to backtrack and check for a longer match if the
+# first match(es) found don't match the entire input.
+#
+"a?|b" "<0></0>b"
+"a?|b" M "<0>b</0>"
+"a?|.*?u|stuff|d" M "<0>stuff</0>"
+"a?|.*?(u)|stuff|d" M "<0>stuff<1>u</1></0>"
+"a+?" "<0>a</0>aaaaaaaaaaaa"
+"a+?" M "<0>aaaaaaaaaaaaa</0>"
+
+#
+# Bug 7724. Expression to validate zip codes.
+#
+"(?!0{5})(\d{5})(?!-?0{4})(-?\d{4})?" "<0><1>94040</1><2>-3344</2></0>"
+"(?!0{5})(\d{5})(?!-?0{4})(-?\d{4})?" "94040-0000"
+"(?!0{5})(\d{5})(?!-?0{4})(-?\d{4})?" "00000-3344"
+
+#
+# Bug 8666. Assertion failure on match, bad operand to JMP_SAV_X opcode.
+#
+"((.??)+|A)*" "<0><1><2></2></1></0>AAAAABBBBBCCCCCDDDDEEEEE"
+
+#
+# Bug 8826. Incorrect results with case insensitive matches.
+#
+"AS(X)" i "aßx"
+"AS.*" i "aßx" # Expansion of sharp s can't split between pattern terms.
+"ASßS" i "<0>aßß</0>" # All one literal string, does match.
+"ASß{1}S" i "aßß" # Pattern with terms, no match.
+"aßx" i "<0>assx</0>"
+"aßx" i "<0>ASSX</0>"
+"aßx" i "<0>aßx</0>"
+"ASS(.)" i "<0>aß<1>x</1></0>"
+
+# Case Insensitive, probe some corner cases.
+"ass+" i "aß" # Second 's' in pattern is qualified, can't combine with first.
+"as+" i "aß"
+"aßs" i "as" # Can't match half of a ß
+"aß+" i "<0>assssssss</0>s"
+"aß+" i "<0>assßSssSSS</0>s"
+"a(ß?)+" i "<0>assssssss<1></1></0>s"
+"a(ß?)+" i "<0>a<1></1></0>zzzzzzzzs"
+
+"\U00010400" i "<0>\U00010428</0>" # case folded supplemental code point.
+
+"sstuff" i "<0>ßtuff</0>" # exercise optimizations on what chars can start a match.
+"sstuff" i "s<0>ßtuff</0>" # exercise optimizations on what chars can start a match.
+"ßtuff" i "s<0>sstuff</0>"
+"ßtuff" i "s<0>Sstuff</0>"
+
+"a(..)\1" i "<0>A<1>bc</1>BC</0>def"
+"(ß)\1" i "aa<0><1>ss</1>ß</0>zz" # Case insensitive back reference
+"..(.)\1" i "<0>aa<1>ß</1>ss</0>"
+"ab(..)\1" i "xx<0>ab<1>ss</1>ß</0>ss"
+
+" (ss) ((\1.*)|(.*))" i "<0> <1>ss</1> <2><4>sß</4></2></0>" # The back reference 'ss' must not match in 'sß'
+
+# Bug 9057
+# \u200c and \u200d should be word characters.
+#
+"\w+" " <0>abc\u200cdef\u200dghi</0> "
+"\w+" i " <0>abc\u200cdef\u200dghi</0> "
+"[\w]+" " <0>abc\u200cdef\u200dghi</0> "
+"[\w]+" i " <0>abc\u200cdef\u200dghi</0> "
+
+# Bug 9283
+# uregex_open fails for look-behind assertion + case-insensitive
+
+"(ab)?(?<=ab)cd|ef" i "<0><1>ab</1>cd</0>"
+
# Random debugging, Temporary
#
-#"^(?:a?b?)*$" "a--"
-"^(?:a?b?)*$" "a--"
+#"^(?:a?b?)*$" "a--"
"This is a string with (?:one |two |three )endings" "<0>This is a string with two endings</0>"
"((?:a|b|c)whoop-dee-do) | [jkl]|zed" "x"
"^(http|https|ftp)\://[a-zA-Z0-9\-\.]+\.[a-zA-Z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+\&%\$#\=~])*$" G "<0>ftp://ftp.blah.co.uk:2828/blah%20blah.gif</0>"
"^(http|https|ftp)\://[a-zA-Z0-9\-\.]+\.[a-zA-Z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+\&%\$#\=~])*$" G "<0>https://blah.gov/blah-blah.as</0>"
"^(http|https|ftp)\://[a-zA-Z0-9\-\.]+\.[a-zA-Z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+\&%\$#\=~])*$" "www.blah.com"
-"^(http|https|ftp)\://[a-zA-Z0-9\-\.]+\.[a-zA-Z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+\&%\$#\=~])*$" "http://www.blah.com/I have spaces!"
+"^(http|https|ftp)\://[a-zA-Z0-9\-\.]+\.[a-zA-Z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+\&%\$#\=~])*$" "http://www.blah.com/I have spaces!"
"^(http|https|ftp)\://[a-zA-Z0-9\-\.]+\.[a-zA-Z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+\&%\$#\=~])*$" "ftp://blah_underscore/[nope]"
"^(([0-2]\d|[3][0-1])\/([0]\d|[1][0-2])\/[2][0]\d{2})$|^(([0-2]\d|[3][0-1])\/([0]\d|[1][0-2])\/[2][0]\d{2}\s([0-1]\d|[2][0-3])\:[0-5]\d\:[0-5]\d)$" G "<0>12/01/2002</0>"
"^(([0-2]\d|[3][0-1])\/([0]\d|[1][0-2])\/[2][0]\d{2})$|^(([0-2]\d|[3][0-1])\/([0]\d|[1][0-2])\/[2][0]\d{2}\s([0-1]\d|[2][0-3])\:[0-5]\d\:[0-5]\d)$" G "<0>12/01/2002 12:32:10</0>"
"^(((25[0-5]|2[0-4][0-9]|19[0-1]|19[3-9]|18[0-9]|17[0-1]|17[3-9]|1[0-6][0-9]|1[1-9]|[2-9][0-9]|[0-9])\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9]))|(192\.(25[0-5]|2[0-4][0-9]|16[0-7]|169|1[0-5][0-9]|1[7-9][0-9]|[1-9][0-9]|[0-9]))|(172\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|1[0-5]|3[2-9]|[4-9][0-9]|[0-9])))\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])$" "10.0.5.4"
"^(((25[0-5]|2[0-4][0-9]|19[0-1]|19[3-9]|18[0-9]|17[0-1]|17[3-9]|1[0-6][0-9]|1[1-9]|[2-9][0-9]|[0-9])\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9]))|(192\.(25[0-5]|2[0-4][0-9]|16[0-7]|169|1[0-5][0-9]|1[7-9][0-9]|[1-9][0-9]|[0-9]))|(172\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|1[0-5]|3[2-9]|[4-9][0-9]|[0-9])))\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])$" "192.168.0.1"
"^(((25[0-5]|2[0-4][0-9]|19[0-1]|19[3-9]|18[0-9]|17[0-1]|17[3-9]|1[0-6][0-9]|1[1-9]|[2-9][0-9]|[0-9])\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9]))|(192\.(25[0-5]|2[0-4][0-9]|16[0-7]|169|1[0-5][0-9]|1[7-9][0-9]|[1-9][0-9]|[0-9]))|(172\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|1[0-5]|3[2-9]|[4-9][0-9]|[0-9])))\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])$" "my ip address"
-#"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" G "<0>foo@foo.com</0>" # TODO: \w in pattern
-#"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" G "<0>foo@foo-foo.com.au</0>" # TODO: \w in pattern
-#"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" G "<0>foo@foo.foo.info</0>" # TODO: \w in pattern
-#"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" "foo@.com" # TODO: \w in pattern
-#"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" "foo@foo..com" # TODO: \w in pattern
-#"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" "foo@me@.com" # TODO: \w in pattern
-#"/\*[\d\D]*?\*/" G "<0>/* my comment */</0>"
-#"/\*[\d\D]*?\*/" G "<0>/* my multiline comment */</0>"
-#"/\*[\d\D]*?\*/" G "<0>/* my nested comment */</0>"
-#"/\*[\d\D]*?\*/" "*/ anything here /*"
-#"/\*[\d\D]*?\*/" "anything between 2 seperate comments"
-#"/\*[\d\D]*?\*/" "\* *\"
+"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" G "<0>foo@foo.com</0>"
+"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" G "<0>foo@foo-foo.com.au</0>"
+"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" G "<0>foo@foo.foo.info</0>"
+"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" "foo@.com"
+"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" "foo@foo..com"
+"^([\w\d\-\.]+)@{1}(([\w\d\-]{1,67})|([\w\d\-]+\.[\w\d\-]{1,67}))\.(([a-zA-Z\d]{2,4})(\.[a-zA-Z\d]{2})?)$" "foo@me@.com"
+"/\*[\d\D]*?\*/" G "<0>/* my comment */</0>"
+"/\*[\d\D]*?\*/" G "<0>/* my multiline comment */</0>"
+"/\*[\d\D]*?\*/" G "<0>/* my nested comment */</0>"
+"/\*[\d\D]*?\*/" "*/ anything here /*"
+"/\*[\d\D]*?\*/" "anything between 2 seperate comments"
+"/\*[\d\D]*?\*/" "\* *\"
"/\*[\p{N}\P{N}]*?\*/" G "<0>/* my comment */</0>"
"/\*[\p{N}\P{N}]*?\*/" G "<0>/* my multiline comment */</0>"
"/\*[\p{N}\P{N}]*?\*/" G "<0>/* my nested comment */</0>"
'^(([^<>;()\[\]\\.,;:@"]+(\.[^<>()\[\]\\.,;:@"]+)*)|(".+"))@((([a-z]([-a-z0-9]*[a-z0-9])?)|(#[0-9]+)|(\[((([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\.){3}(([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\]))\.)*(([a-z]([-a-z0-9]*[a-z0-9])?)|(#[0-9]+)|(\[((([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\.){3}(([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\]))$' G "<0>blah@[10.0.0.1]</0>"
'^(([^<>;()\[\]\\.,;:@"]+(\.[^<>()\[\]\\.,;:@"]+)*)|(".+"))@((([a-z]([-a-z0-9]*[a-z0-9])?)|(#[0-9]+)|(\[((([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\.){3}(([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\]))\.)*(([a-z]([-a-z0-9]*[a-z0-9])?)|(#[0-9]+)|(\[((([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\.){3}(([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\]))$' G "<0>a@b.c</0>"
'^(([^<>;()\[\]\\.,;:@"]+(\.[^<>()\[\]\\.,;:@"]+)*)|(".+"))@((([a-z]([-a-z0-9]*[a-z0-9])?)|(#[0-9]+)|(\[((([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\.){3}(([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\]))\.)*(([a-z]([-a-z0-9]*[a-z0-9])?)|(#[0-9]+)|(\[((([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\.){3}(([01]?[0-9]{0,2})|(2(([0-4][0-9])|(5[0-5]))))\]))$' "non@match@."
-#"^\d{9}[\d|X]$" G "<0>1234123412</0>"
-#"^\d{9}[\d|X]$" G "<0>123412341X</0>"
-#"^\d{9}[\d|X]$" "not an isbn"
+"^\d{9}[\d|X]$" G "<0>1234123412</0>"
+"^\d{9}[\d|X]$" G "<0>123412341X</0>"
+"^\d{9}[\d|X]$" "not an isbn"
"^\d{9}(\d|X)$" G "<0>1234123412</0>"
"^\d{9}(\d|X)$" G "<0>123412341X</0>"
"^\d{9}(\d|X)$" "not an isbn"
"\(([0-9]{2}|0{1}((x|[0-9]){2}[0-9]{2}))\)\s*[0-9]{3,4}[- ]*[0-9]{4}" "12 123 1234"
"\(([0-9]{2}|0{1}((x|[0-9]){2}[0-9]{2}))\)\s*[0-9]{3,4}[- ]*[0-9]{4}" "(012) 123/1234"
"\(([0-9]{2}|0{1}((x|[0-9]){2}[0-9]{2}))\)\s*[0-9]{3,4}[- ]*[0-9]{4}" "(012) 123 12345"
-#"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" G "<0>bob-smith@foo.com</0>" # TODO: \w in pattern
-#"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" G "<0>bob.smith@foo.com</0>" # TODO: \w in pattern
-#"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" G "<0>bob_smith@foo.com</0>" # TODO: \w in pattern
-#"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" "-smith@foo.com" # TODO: \w in pattern
-#"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" ".smith@foo.com" # TODO: \w in pattern
-#"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" "smith@foo_com" # TODO: \w in pattern
+"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" G "<0>bob-smith@foo.com</0>"
+"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" G "<0>bob.smith@foo.com</0>"
+"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" G "<0>bob_smith@foo.com</0>"
+"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" "-smith@foo.com"
+"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" ".smith@foo.com"
+"^\w+[\w-\.]*\@\w+((-\w+)|(\w*))\.[a-z]{2,3}$" "smith@foo_com"
"^(?=.*\d).{4,8}$" G "<0>1234</0>"
"^(?=.*\d).{4,8}$" G "<0>asdf1234</0>"
"^(?=.*\d).{4,8}$" G "<0>asp123</0>"
"^\$(\d{1,3}(\,\d{3})*|(\d+))(\.\d{2})?$" "$12,3456.01"
"^\$(\d{1,3}(\,\d{3})*|(\d+))(\.\d{2})?$" "12345"
"^\$(\d{1,3}(\,\d{3})*|(\d+))(\.\d{2})?$" "$1.234"
-"([A-Z]:\\[^/:\*\?<>\|]+\.\w{2,6})|(\\{2}[^/:\*\?<>\|]+\.\w{2,6})" G "<0>C:\\temp\\this allows spaces\\web.config</0>"
+"([A-Z]:\\[^/:\*\?<>\|]+\.\w{2,6})|(\\{2}[^/:\*\?<>\|]+\.\w{2,6})" G "<0>C:\\temp\\this allows spaces\\web.config</0>"
"([A-Z]:\\[^/:\*\?<>\|]+\.\w{2,6})|(\\{2}[^/:\*\?<>\|]+\.\w{2,6})" G "<0>\\\\Andromeda\\share\\file name.123</0>"
"([A-Z]:\\[^/:\*\?<>\|]+\.\w{2,6})|(\\{2}[^/:\*\?<>\|]+\.\w{2,6})" "tz:\temp\ fi*le?na:m<e>.doc"
"([A-Z]:\\[^/:\*\?<>\|]+\.\w{2,6})|(\\{2}[^/:\*\?<>\|]+\.\w{2,6})" "\\Andromeda\share\filename.a"
"^[A-Za-z0-9]{8}-[A-Za-z0-9]{4}-[A-Za-z0-9]{4}-[A-Za-z0-9]{4}-[A-Za-z0-9]{12}$" "qqqBFDB4D31-3E35-4DAB-AFCA-5E6E5C8F61EA"
"^[A-Za-z0-9]{8}-[A-Za-z0-9]{4}-[A-Za-z0-9]{4}-[A-Za-z0-9]{4}-[A-Za-z0-9]{12}$" "BFDB4D31-3E-4DAB-AFCA-5E6E5C8F61EA"
"^[A-Za-z0-9]{8}-[A-Za-z0-9]{4}-[A-Za-z0-9]{4}-[A-Za-z0-9]{4}-[A-Za-z0-9]{12}$" "BFDB4D31-3E35-4DAB-AF"
-#"^\d{2}(\x2e)(\d{3})(-\d{3})?$" G "<0>12.345-678</0>" # TODO: \x not implemented.
-#"^\d{2}(\x2e)(\d{3})(-\d{3})?$" G "<0>23.345-123</0>"
-#"^\d{2}(\x2e)(\d{3})(-\d{3})?$" G "<0>99.999</0>"
-#"^\d{2}(\x2e)(\d{3})(-\d{3})?$" "41222-222"
-#"^\d{2}(\x2e)(\d{3})(-\d{3})?$" "3.444-233"
-#"^\d{2}(\x2e)(\d{3})(-\d{3})?$" "43.324444"
+"^\d{2}(\x2e)(\d{3})(-\d{3})?$" G "<0>12.345-678</0>"
+"^\d{2}(\x2e)(\d{3})(-\d{3})?$" G "<0>23.345-123</0>"
+"^\d{2}(\x2e)(\d{3})(-\d{3})?$" G "<0>99.999</0>"
+"^\d{2}(\x2e)(\d{3})(-\d{3})?$" "41222-222"
+"^\d{2}(\x2e)(\d{3})(-\d{3})?$" "3.444-233"
+"^\d{2}(\x2e)(\d{3})(-\d{3})?$" "43.324444"
"^\d{2}(\u002e)(\d{3})(-\d{3})?$" G "<0>12.345-678</0>"
"^\d{2}(\u002e)(\d{3})(-\d{3})?$" G "<0>23.345-123</0>"
"^\d{2}(\u002e)(\d{3})(-\d{3})?$" G "<0>99.999</0>"
"^\d{2}(\u002e)(\d{3})(-\d{3})?$" "41222-222"
"^\d{2}(\u002e)(\d{3})(-\d{3})?$" "3.444-233"
"^\d{2}(\u002e)(\d{3})(-\d{3})?$" "43.324444"
-#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" G "<0>c:\file.txt</0>"
-#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" G "<0>c:\folder\sub folder\file.txt</0>"
-#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" G "<0>\\network\folder\file.txt</0>" # TODO: \w in pattern
-#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" "C:" # TODO: \w in pattern
-#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" "C:\file.xls" # TODO: \w in pattern
-#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" "folder.txt" # TODO: \w in pattern
+#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" G "<0>c:\file.txt</0>" # TODO: debug
+#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" G "<0>c:\folder\sub folder\file.txt</0>" # TODO: debug
+#"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" G "<0>\\network\folder\file.txt</0>" # TODO: debug
+"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" "C:"
+"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" "C:\file.xls"
+"^(([a-zA-Z]:)|(\\{2}\w+)\$?)(\\(\w[\w ]*))+\.(txt|TXT)$" "folder.txt"
"^[a-zA-Z0-9]+([a-zA-Z0-9\-\.]+)?\.(com|org|net|mil|edu|COM|ORG|NET|MIL|EDU)$" G "<0>my.domain.com</0>"
"^[a-zA-Z0-9]+([a-zA-Z0-9\-\.]+)?\.(com|org|net|mil|edu|COM|ORG|NET|MIL|EDU)$" G "<0>regexlib.com</0>"
"^[a-zA-Z0-9]+([a-zA-Z0-9\-\.]+)?\.(com|org|net|mil|edu|COM|ORG|NET|MIL|EDU)$" G "<0>big-reg.com</0>"
"^(1?(-?\d{3})-?)?(\d{3})(-?\d{4})$" "1-555-5555"
"^(1?(-?\d{3})-?)?(\d{3})(-?\d{4})$" "15553333"
"^(1?(-?\d{3})-?)?(\d{3})(-?\d{4})$" "0-561-555-1212"
-#"<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>" G "<0><input type = text name = "bob"></0>" # TODO: \w in pattern
-#"<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>" G "<0><select name = "fred"></0>" # TODO: \w in pattern
-#"<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>" G "<0><form</0>" # TODO: \w in pattern
-#"<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>" "<input type = submit>" # TODO: \w in pattern
-#"<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>" "<font face = "arial">" # TODO: \w in pattern
-#"<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>" "The drity brown fox stank like" # TODO: \w in pattern
+'<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>' G '<0><input type = text name = "bob"></0>'
+'<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>' G '<0><select name = "fred"></0>'
+#'<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>' G '<0><form></0>' #TODO: Debug
+'<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>' "<input type = submit>" # TODO: \w in pattern
+'<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>' '<font face = "arial">' # TODO: \w in pattern
+'<[^>]*name[\s]*=[\s]*"?[^\w_]*"?[^>]*>' "The drity brown fox stank like"
"^(1|01|2|02|3|03|4|04|5|05|6|06|7|07|8|08|9|09|10|11|12{1,2}):(([0-5]{1}[0-9]{1}\s{0,1})([AM|PM|am|pm]{2,2}))\W{0}$" G "<0>1:00 AM</0>"
"^(1|01|2|02|3|03|4|04|5|05|6|06|7|07|8|08|9|09|10|11|12{1,2}):(([0-5]{1}[0-9]{1}\s{0,1})([AM|PM|am|pm]{2,2}))\W{0}$" G "<0>12:00 PM</0>"
"^(1|01|2|02|3|03|4|04|5|05|6|06|7|07|8|08|9|09|10|11|12{1,2}):(([0-5]{1}[0-9]{1}\s{0,1})([AM|PM|am|pm]{2,2}))\W{0}$" G "<0>1:00am</0>"
"^(\d{1,2}|1\d\d|2[0-4]\d|25[0-5])\.(\d{1,2}|1\d\d|2[0-4]\d|25[0-5])\.(\d{1,2}|1\d\d|2[0-4]\d|25[0-5])\.(\d{1,2}|1\d\d|2[0-4]\d|25[0-5])$" "10.57.98.23."
"<img([^>]*[^/])>" G '<0><img src="bob"></0>'
"<img([^>]*[^/])>" '<img src="bob" />'
-#"<!--[\s\S]*?-->" G "<0><!-- comments --></0>"
-#"<!--[\s\S]*?-->" G "<0><!-- x = a > b - 3 --></0>"
-#"<!--[\s\S]*?-->" "<COMMENTS>this is a comment</COMMENTS>"
+"<!--[\s\S]*?-->" G "<0><!-- comments --></0>"
+"<!--[\s\S]*?-->" G "<0><!-- x = a > b - 3 --></0>"
+"<!--[\s\S]*?-->" "<COMMENTS>this is a comment</COMMENTS>"
"<!--[\p{Zs}\P{Zs}]*?-->" G "<0><!-- comments --></0>"
"<!--[\p{Zs}\P{Zs}]*?-->" G "<0><!-- x = a > b - 3 --></0>"
"<!--[\p{Zs}\P{Zs}]*?-->" "<COMMENTS>this is a comment</COMMENTS>"
"(\{\\f\d*)\\([^;]+;)" G "<0>{\\f1\\fswiss\\fcharset0\\fprq2{\\*\\panose 020b0604020202020204}Arial;</0>"
"(\{\\f\d*)\\([^;]+;)" G "{\\f"
"(\{\\f\d*)\\([^;]+;)" "{f0fs20 some text}"
-#"</?([a-zA-Z][-A-Za-z\d\.]{0,71})(\s+(\S+)(\s*=\s*([-\w\.]{1,1024}|"[^"]{0,1024}"|'[^']{0,1024}'))?)*\s*>" G "<0><IMG src='stars.gif' alt="space" height=1></0>" # TODO: \w in pattern
-#"</?([a-zA-Z][-A-Za-z\d\.]{0,71})(\s+(\S+)(\s*=\s*([-\w\.]{1,1024}|"[^"]{0,1024}"|'[^']{0,1024}'))?)*\s*>" "this is not a tag" # TODO: \w in pattern
+#"</?([a-zA-Z][-A-Za-z\d\.]{0,71})(\s+(\S+)(\s*=\s*([-\w\.]{1,1024}|"[^"]{0,1024}"|'[^']{0,1024}'))?)*\s*>" G '<0><IMG src='stars.gif' alt="space" height=1></0>' # TODO: Can't quote this pattern with the test syntax!
+#"</?([a-zA-Z][-A-Za-z\d\.]{0,71})(\s+(\S+)(\s*=\s*([-\w\.]{1,1024}|"[^"]{0,1024}"|'[^']{0,1024}'))?)*\s*>" "this is not a tag"
"^([0]\d|[1][0-2])\/([0-2]\d|[3][0-1])\/([2][01]|[1][6-9])\d{2}(\s([0-1]\d|[2][0-3])(\:[0-5]\d){1,2})?$" G "<0>12/30/2002</0>"
"^([0]\d|[1][0-2])\/([0-2]\d|[3][0-1])\/([2][01]|[1][6-9])\d{2}(\s([0-1]\d|[2][0-3])(\:[0-5]\d){1,2})?$" G "<0>01/12/1998 13:30</0>"
"^([0]\d|[1][0-2])\/([0-2]\d|[3][0-1])\/([2][01]|[1][6-9])\d{2}(\s([0-1]\d|[2][0-3])(\:[0-5]\d){1,2})?$" G "<0>01/28/2002 22:35:00</0>"
"^[0-9A-Za-z_ ]+(.[jJ][pP][gG]|.[gG][iI][fF])$" "bad.bad.gif"
"^[0-9A-Za-z_ ]+(.[jJ][pP][gG]|.[gG][iI][fF])$" "slash\gif."
"<[^>\s]*\bauthor\b[^>]*>" G '<0><author name="Daniel"></0>'
-#"<[^>\s]*\bauthor\b[^>]*>" G "<0></sch:author></0>"
-#"<[^>\s]*\bauthor\b[^>]*>" G '<0><pp:author name="Daniel"</0>'
+"<[^>\s]*\bauthor\b[^>]*>" G "<0></sch:author></0>"
+# "<[^>\s]*\bauthor\b[^>]*>" G '<0><pp:author name="Daniel"</0>' #Debug should work
"<[^> ]*\bauthor\b[^>]*>" G "<0></sch:author></0>"
-"<[^> ]*\bauthor\b[^>]*>" G '<0><pp:author name="Daniel"></0>'
+"<[^> ]*\bauthor\b[^>]*>" G '<0><pp:author name="Daniel"></0>'
"<[^>\s]*\bauthor\b[^>]*>" "<other>"
"<[^>\s]*\bauthor\b[^>]*>" "</authors>"
"<[^>\s]*\bauthor\b[^>]*>" "<work>author</work>"
"(^\d*\.?\d*[1-9]+\d*$)|(^[1-9]+\d*\.\d*$)" "0"
"(^\d*\.?\d*[1-9]+\d*$)|(^[1-9]+\d*\.\d*$)" "0.0"
"(^\d*\.?\d*[1-9]+\d*$)|(^[1-9]+\d*\.\d*$)" ".0"
-#"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" G "<0>Sacramento</0>" #TODO: Octal
-#"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" G "<0>San Francisco</0>"
-#"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" G "<0>San Luis Obispo</0>"
-#"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "SanFrancisco"
-#"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "SanLuisObispo"
-#"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "San francisco"
-#"^\{?[a-fA-F\d]{8}-([a-fA-F\d]{4}-){3}[a-fA-F\d]{12}\}?$" G "<0>{e02ff0e4-00ad-090A-c030-0d00a0008ba0}</0>"
-#"^\{?[a-fA-F\d]{8}-([a-fA-F\d]{4}-){3}[a-fA-F\d]{12}\}?$" G "<0>e02ff0e4-00ad-090A-c030-0d00a0008ba0</0>"
-#"^\{?[a-fA-F\d]{8}-([a-fA-F\d]{4}-){3}[a-fA-F\d]{12}\}?$" "0xe02ff0e400ad090Ac0300d00a0008ba0"
+"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" G "<0>Sacramento</0>"
+"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "<0><2>San Francisco</2></0>"
+"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "<0><3>San Luis Obispo</3></0>"
+"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "SanFrancisco"
+"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "SanLuisObispo"
+"^([A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^([A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,}\040[A-Z]{1}[a-z]{1,})$|^$" "San francisco"
+"^\{?[a-fA-F\d]{8}-([a-fA-F\d]{4}-){3}[a-fA-F\d]{12}\}?$" G "<0>{e02ff0e4-00ad-090A-c030-0d00a0008ba0}</0>"
+"^\{?[a-fA-F\d]{8}-([a-fA-F\d]{4}-){3}[a-fA-F\d]{12}\}?$" G "<0>e02ff0e4-00ad-090A-c030-0d00a0008ba0</0>"
+"^\{?[a-fA-F\d]{8}-([a-fA-F\d]{4}-){3}[a-fA-F\d]{12}\}?$" "0xe02ff0e400ad090Ac0300d00a0008ba0"
"^\{?[a-fA-F0-9]{8}-([a-fA-F0-9]{4}-){3}[a-fA-F0-9]{12}\}?$" G "<0>{e02ff0e4-00ad-090A-c030-0d00a0008ba0}</0>"
"^\{?[a-fA-F0-9]{8}-([a-fA-F0-9]{4}-){3}[a-fA-F0-9]{12}\}?$" G "<0>e02ff0e4-00ad-090A-c030-0d00a0008ba0</0>"
"^\{?[a-fA-F0-9]{8}-([a-fA-F0-9]{4}-){3}[a-fA-F0-9]{12}\}?$" "0xe02ff0e400ad090Ac0300d00a0008ba0"
"^((0[1-9])|(1[0-2]))\/(\d{2})$" G "<0>01/04</0>"
"^((0[1-9])|(1[0-2]))\/(\d{2})$" "13/03"
"^((0[1-9])|(1[0-2]))\/(\d{2})$" "10/2003"
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" G "<0><script language=javascript>document.write("one");</script></0>" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" "--" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" "A-Z][a-z]+" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" G "<0>strFirstName</0>" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" G "<0>intAgeInYears</0>" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" G "<0>Where the Wild Things Are</0>" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" "123" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" "abc" # TODO: \w in pattern
-#"<script[^>]*>[\w|\t|\r|\W]*</script>" "this has no caps in it" # TODO: \w in pattern
+"<script[^>]*>[\w|\t|\r|\W]*</script>" G '<0><script language=javascript>document.write("one");</script></0>'
+"<script[^>]*>[\w|\t|\r|\W]*</script>" "--"
+"<script[^>]*>[\w|\t|\r|\W]*</script>" "A-Z][a-z]+"
+#"<script[^>]*>[\w|\t|\r|\W]*</script>" G "<0>strFirstName</0>" # Test Case damaged?
+#"<script[^>]*>[\w|\t|\r|\W]*</script>" G "<0>intAgeInYears</0>" # Test Case damaged?
+#"<script[^>]*>[\w|\t|\r|\W]*</script>" G "<0>Where the Wild Things Are</0>" # Test Case damaged?
+"<script[^>]*>[\w|\t|\r|\W]*</script>" "123"
+"<script[^>]*>[\w|\t|\r|\W]*</script>" "abc"
+"<script[^>]*>[\w|\t|\r|\W]*</script>" "this has no caps in it"
"(^-\d*\.?\d*[1-9]+\d*$)|(^-[1-9]+\d*\.\d*$)" G "<0>-0.050</0>"
"(^-\d*\.?\d*[1-9]+\d*$)|(^-[1-9]+\d*\.\d*$)" G "<0>-5.000</0>"
"(^-\d*\.?\d*[1-9]+\d*$)|(^-[1-9]+\d*\.\d*$)" G "<0>-5</0>"
"^.{4,8}$" "asd"
"^.{4,8}$" "123"
"^.{4,8}$" "asdfe12345"
-#"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" G "<0>a@a.com</0>" # TODO: \w in pattern
-#"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" G "<0>a@a.com.au</ # TODO: \w in pattern0>"
-#"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" G "<0>a@a.au</0>" # TODO: \w in pattern
-#"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" "word" # TODO: \w in pattern
-#"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" "word@" # TODO: \w in pattern
-#"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" "@word" # TODO: \w in pattern
+"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" G "<0>a@a.com</0>"
+"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" G "<0>a@a.com.au</0>"
+"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" G "<0>a@a.au</0>"
+"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" "word"
+"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" "word@"
+"^[\w\.=-]+@[\w\.-]+\.[\w]{2,3}$" "@word"
"^\d{5}-\d{4}$" G "<0>22222-3333</0>"
"^\d{5}-\d{4}$" G "<0>34545-2367</0>"
"^\d{5}-\d{4}$" G "<0>56334-2343</0>"
"^[12345]$" "6"
"^[12345]$" "-1"
"^[12345]$" "abc"
-#"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" G "<0>joe@aol.com</0>" # TODO: \w in pattern
-#"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" G "<0>joe@wrox.co.uk</0>" # TODO: \w in pattern
-#"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" G "<0>joe@domain.info</0>" # TODO: \w in pattern
-#"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" "a@b" # TODO: \w in pattern
-#"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" "notanemail" # TODO: \w in pattern
-#"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" "joe@@." # TODO: \w in pattern
+"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" G "<0>joe@aol.com</0>"
+"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" G "<0>joe@wrox.co.uk</0>"
+"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" G "<0>joe@domain.info</0>"
+"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" "a@b"
+"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" "notanemail"
+"^[\w-\.]+@([\w-]+\.)+[\w-]{2,4}$" "joe@@."
"^\w+@[a-zA-Z_]+?\.[a-zA-Z]{2,3}$" G "<0>joe@aol.com</0>"
"^\w+@[a-zA-Z_]+?\.[a-zA-Z]{2,3}$" G "<0>ssmith@aspalliance.com</0>"
"^\w+@[a-zA-Z_]+?\.[a-zA-Z]{2,3}$" G "<0>a@b.cc</0>"
"^\w+@[a-zA-Z_]+?\.[a-zA-Z]{2,3}$" "joe@123aspx.com"
"^\w+@[a-zA-Z_]+?\.[a-zA-Z]{2,3}$" "joe@web.info"
"^\w+@[a-zA-Z_]+?\.[a-zA-Z]{2,3}$" "joe@company.co.uk"
-#"[\w-]+@([\w-]+\.)+[\w-]+" G "<0>joe@aol.com</0>" # TODO: \w in pattern
-#"[\w-]+@([\w-]+\.)+[\w-]+" G "<0>a@b.c</0>" # TODO: \w in pattern
-#"[\w-]+@([\w-]+\.)+[\w-]+" "asdf" # TODO: \w in pattern
-#"[\w-]+@([\w-]+\.)+[\w-]+" "1234" # TODO: \w in pattern
+"[\w-]+@([\w-]+\.)+[\w-]+" G "<0>joe@aol.com</0>"
+"[\w-]+@([\w-]+\.)+[\w-]+" G "<0>a@b.c</0>"
+"[\w-]+@([\w-]+\.)+[\w-]+" "asdf"
+"[\w-]+@([\w-]+\.)+[\w-]+" "1234"
"\d{4}-?\d{4}-?\d{4}-?\d{4}" G "<0>1234-1234-1234-1234</0>"
"\d{4}-?\d{4}-?\d{4}-?\d{4}" G "<0>1234123412341234</0>"
"\d{4}-?\d{4}-?\d{4}-?\d{4}" "1234123412345"
projects / apple / icu.git / blobdiff