scuffed-code/icu4c/source/test/testdata/regextst.txt

#
#  file:  
#
#   ICU regular expression test cases.
#
#   format:   one test case per line,
#               <test case>    =  <pattern>   <flags>  <match string>  [# comment]
#               <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 
#                                 capture group tagged with <n>...</n>.  The overall match,
#                                 if any, is group 0, as in <0>matched text</0>
#               <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
#                                   d      dump the compiled pattern
#                                   t      trace operation of match engine.
#                                 White space must be present between the flags and the match string.
#

# Capturing parens
".(..)."                       "<0>a<1>bc</1>d</0>"
 ".*\A( +hello)"               "<0><1>      hello</1></0>"
"(hello)|(goodbye)"            "<0><1>hello</1></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>  "

# Non-capturing parens (?: stuff).   Groups, but does not capture.
"(?:abc)*(tail)"               "<0>abcabcabc<1>tail</1></0>"

# Non-greedy  *? quantifier
".*?(abc)"                     "<0>    abx    <1>abc</1></0> abc abc abc"
".*(abc)"                      "<0>    abx     abc abc abc <1>abc</1></0>"

"((?:abc |xyz )*?)abc "        "<0><1>xyz </1>abc </0>abc abc "
"((?:abc |xyz )*)abc "         "<0><1>xyz abc abc </1>abc </0>"

# Non-greedy  +? quantifier
"(a+?)(a*)"                    "<0><1>a</1><2>aaaaaaaaaaaa</2></0>"
"(a+)(a*)"                     "<0><1>aaaaaaaaaaaaa</1><2></2></0>"

"((ab)+?)((ab)*)"              "<0><1><2>ab</2></1><3>ababababab<4>ab</4></3></0>"
"((ab)+)((ab)*)"               "<0><1>abababababab<2>ab</2></1><3></3></0>"

# Non-greedy ?? quantifier
"(ab)(ab)??(ab)??(ab)??(ab)??c"      "<0><1>ab</1><4>ab</4><5>ab</5>c</0>"

# Unicode Properties as naked elements in a pattern
"\p{Lu}+"                      "here we go ... <0>ABC</0> and no more."
"(\p{L}+)(\P{L}*?) (\p{Zs}*)"  "7999<0><1>letters</1><2>4949%^&*(</2> <3>   </3></0>"

# \w and \W
"\w+"                          "  $%^&*( <0>hello123</0>%^&*("
"\W+"                          "<0>  $%^&*( </0>hello123%^&*("

# \A   match at beginning of input only.
 ".*\Ahello"                   "<0>hello</0> hello"
 ".*hello"                     "<0>hello hello</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"

# 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"

"H.*?((?:\B.)+)"              "<0>H<1>ello</1></0> "
".*?((?:\B.)+).*?((?:\B.)+).*?((?:\B.)+)"    "<0>H<1>ello</1> <2>    </2>g<3>oodbye</3></0> "

"(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?.*"   "<0>   \u0301 \u0301<1>A</1>\u0302BC\u0303\u0304<2> </2>\u0305 \u0306<3>X</3>\u0307Y\u0308</0>"

# . does not match new-lines
"."                            "\u000a\u000d\u0085\u000c\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>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>"

# \S and \s  space characters
"\s+"                          "not_space<0> \t \r \n \u3000 \u2004 \u2028 \u2029</0>xyz"
"(\S+).*?(\S+).*"              "<0><1>Not-spaces</1>   <2>more-non-spaces</2>  </0>"

# \X  consume one combining char sequence.
"(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?"   "<0><1>A</1><2>B</2><3> </3><4>\r\n</4></0>"
"(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?"   "<0><1>A\u0301</1><2>\n</2><3>\u0305</3><4>a\u0302\u0303\u0304</4></0>"

# ^ matches only at beginning of line
".*^(Hello)"                   "<0><1>Hello</1></0> Hello Hello Hello Goodbye"
".*(Hello)"                    "<0>Hello Hello Hello <1>Hello</1></0> Goodbye"
".*^(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)$"                "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)$"                "<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

# \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"               "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)\Z"               "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)\Z"               "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\r\n"
".*?(Goodbye)\Z"               "Hello Goodbye Goodbye Goodbye\n\n"# No Match

# \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"               "Hello Goodbye Goodbye Goodbye\n"# No Match
".*?(Goodbye)\n\z"             "<0>Hello Goodbye Goodbye <1>Goodbye</1>\n</0>"

# (?# comment) doesn't muck up pattern
"Hello (?# this is a comment) world"  "  <0>Hello  world</0>..."

# Check some implementation corner cases base on the way literal strings are compiled.
"A"                            "<0>A</0>"
"AB"                           "<0>AB</0>ABABAB"
"AB+"                          "<0>ABBB</0>A"
"AB+"                          "<0>AB</0>ABAB"
"ABC+"                         "<0>ABC</0>ABC"
"ABC+"                         "<0>ABCCCC</0>ABC"
"(?:ABC)+"                     "<0>ABCABCABC</0>D"
"(?:ABC)DEF+"                  "<0>ABCDEFFF</0>D"
"AB\.C\eD\u0666E"              "<0>AB.C\u001BD\u0666E</0>F"
"ab\Bde"                        "<0>abde</0>"


# {min,max} iteration qualifier
"A{3}BC"                       "<0>AAABC</0>"

"(ABC){2,3}AB"                 "no matchAB"
"(ABC){2,3}AB"                 "ABCAB"
"(ABC){2,3}AB"                 "<0>ABC<1>ABC</1>AB</0>"
"(ABC){2,3}AB"                 "<0>ABCABC<1>ABC</1>AB</0>"
"(ABC){2,3}AB"                 "<0>ABCABC<1>ABC</1>AB</0>CAB"

"(ABC){2}AB"                   "ABCAB"
"(ABC){2}AB"                   "<0>ABC<1>ABC</1>AB</0>"
"(ABC){2}AB"                   "<0>ABC<1>ABC</1>AB</0>CAB"
"(ABC){2}AB"                   "<0>ABC<1>ABC</1>AB</0>CABCAB"

"(ABC){2,}AB"                  "ABCAB"
"(ABC){2,}AB"                  "<0>ABC<1>ABC</1>AB</0>"
"(ABC){2,}AB"                  "<0>ABCABC<1>ABC</1>AB</0>"
"(ABC){2,}AB"                  "<0>ABCABCABC<1>ABC</1>AB</0>"

"X{0,0}ABC"                    "<0>ABC</0>"
"X{0,1}ABC"                    "<0>ABC</0>"

"(?:Hello(!{1,3}) there){1}"   "Hello there"
"(?:Hello(!{1,3}) there){1}"   "<0>Hello<1>!</1> there</0>"
"(?:Hello(!{1,3}) there){1}"   "<0>Hello<1>!!</1> there</0>"
"(?:Hello(!{1,3}) there){1}"   "<0>Hello<1>!!!</1> there</0>"
"(?:Hello(!{1,3}) there){1}"   "Hello!!!! there"

# Nongreedy {min,max}? intervals
"(ABC){2,3}?AB"                "no matchAB"
"(ABC){2,3}?AB"                "ABCAB"
"(ABC){2,3}?AB"                "<0>ABC<1>ABC</1>AB</0>"
"(ABC){2,3}?AB"                "<0>ABC<1>ABC</1>AB</0>CAB"
"(ABC){2,3}?AB"                "<0>ABC<1>ABC</1>AB</0>CABCAB"
"(ABC){2,3}?AX"                "<0>ABCABC<1>ABC</1>AX</0>"
"(ABC){2,3}?AX"                "ABC<0>ABCABC<1>ABC</1>AX</0>"

# Atomic Grouping
"(?>.*)abc"                    "abcabcabc"  # no match.  .* consumed entire string.
"(?>(abc{2,4}?))(c*)"          "<0><1>abcc</1><2>ccc</2></0>ddd"
"(\.\d\d(?>[1-9]?))\d+"        "1.625"
"(\.\d\d(?>[1-9]?))\d+"        "1<0><1>.625</1>0</0>"

# Possessive *+
"(abc)*+a"                     "abcabcabc"
"(abc)*+a"                     "<0>abc<1>abc</1>a</0>b"
"(a*b)*+a"                     "<0><1>aaaab</1>a</0>aaa"

# Possessive ?+
"c?+ddd"                       "<0>cddd</0>"
"c?+cddd"                      "cddd"
"c?cddd"                       "<0>cddd</0>"

# Back Reference
"(?:ab(..)cd\1)*"              "<0>ab23cd23ab<1>ww</1>cdww</0>abxxcdyy"
"ab(?:c|(d?))(\1)"             "<0>ab<1><2></2></1></0>c"
"ab(?:c|(d?))(\1)"             "<0>ab<1>d</1><2>d</2></0>"
"ab(?:c|(d?))(\1)"             "<0>ab<1></1><2></2></0>e"
"ab(?:c|(d?))(\1)"             "<0>ab<1></1><2></2></0>"