diff --git a/RunTest b/RunTest index 1c0b3c5..435bfab 100755 --- a/RunTest +++ b/RunTest @@ -48,17 +48,16 @@ # Define test titles in variables so that they can be output as a list. Some # of them are modified (e.g. with -8 or -16) when used in the actual tests. -title1="Test 1: Main functionality (Compatible with Perl >= 5.10)" +title1="Test 1: Main non-UTF, non-UCP functionality (compatible with Perl >= 5.10)" title2="Test 2: API, errors, internals, and non-Perl stuff" title3="Test 3: Locale-specific features" title4A="Test 4: UTF" -title4B=" and Unicode property support (Compatible with Perl >= 5.10)" -#title5="Test 5: API, internals, and non-Perl stuff for UTF" -#title6="Test 6: Unicode property support (Compatible with Perl >= 5.10)" -#title7="Test 7: API, internals, and non-Perl stuff for Unicode property support" -#title8="Test 8: DFA matching main functionality" -#title9="Test 9: DFA matching with UTF" -#title10="Test 10: DFA matching with Unicode properties" +title4B=" and Unicode property support (compatible with Perl >= 5.10)" +title5A="Test 5: API, internals, and non-Perl stuff for UTF" +title5B=" and UCP support" +title6="Test 6: DFA matching main non-UTF, non-UCP functionality" +title7A="Test 7: DFA matching with UTF" +title7B=" and Unicode property support" #title11="Test 11: Internal offsets and code size tests" #title12="Test 12: JIT-specific features (when JIT is available)" #title13="Test 13: JIT-specific features (when JIT is not available)" @@ -80,12 +79,12 @@ maxtest=2 if [ $# -eq 1 -a "$1" = "list" ]; then echo $title1 - echo $title2 "(not UTF)" + echo $title2 "(not UTF or UCP)" echo $title3 echo $title4A $title4B -# echo $title5 support -# echo $title6 -# echo $title7 + echo $title5A $title5B + echo $title6 + echo $title7A $title7B # echo $title8 # echo $title9 # echo $title10 @@ -176,9 +175,9 @@ do1=no do2=no do3=no do4=no -#do5=no -#do6=no -#do7=no +do5=no +do6=no +do7=no #do8=no #do9=no #do10=no @@ -205,9 +204,9 @@ while [ $# -gt 0 ] ; do 2) do2=yes;; 3) do3=yes;; 4) do4=yes;; -# 5) do5=yes;; -# 6) do6=yes;; -# 7) do7=yes;; + 5) do5=yes;; + 6) do6=yes;; + 7) do7=yes;; # 8) do8=yes;; # 9) do9=yes;; # 10) do10=yes;; @@ -346,9 +345,10 @@ fi # If no specific tests were requested, select all. Those that are not # relevant will be automatically skipped. -if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no \ +if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a \ + $do5 = no -a $do6 = no -a $do7 = no \ ]; then -# -a $do5 = no -a $do6 = no -a $do7 = no -a $do8 = no -a \ +# -a $do8 = no -a \ # $do9 = no -a $do10 = no -a $do11 = no -a $do12 = no -a \ # $do13 = no -a $do14 = no -a $do15 = no -a $do16 = no -a \ # $do17 = no -a $do18 = no -a $do19 = no -a $do20 = no -a \ @@ -359,9 +359,9 @@ if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no \ do2=yes do3=yes do4=yes -# do5=yes -# do6=yes -# do7=yes + do5=yes + do6=yes + do7=yes # do8=yes # do9=yes # do10=yes @@ -425,7 +425,7 @@ fi # PCRE2 tests that are not JIT or Perl-compatible: API, errors, internals if [ $do2 = yes ] ; then - echo $title2 "(not UTF-$bits)" + echo $title2 "(excluding UTF-$bits)" for opt in "" $jitopt; do $sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput2 testtry if [ $? = 0 ] ; then @@ -537,117 +537,53 @@ if [ $do4 = yes ] ; then fi fi -#if [ $do5 = yes ] ; then -# echo ${title5}-${bits} support -# if [ $utf -eq 0 ] ; then -# echo " Skipped because UTF-$bits support is not available" -# else -# for opt in "" "-s" $jitopt; do -# $sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput5 testtry -# if [ $? = 0 ] ; then -# $cf $testdata/testoutput5 testtry -# if [ $? != 0 ] ; then exit 1; fi -# else exit 1 -# fi -# if [ "$opt" = "-s" ] ; then echo " OK with study" -# elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" -# else echo " OK" -# fi -# done -# fi -#fi -# -#if [ $do6 = yes ] ; then -# echo $title6 -# if [ $utf -eq 0 -o $ucp -eq 0 ] ; then -# echo " Skipped because Unicode property support is not available" -# else -# for opt in "" "-s" $jitopt; do -# $sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput6 testtry -# if [ $? = 0 ] ; then -# $cf $testdata/testoutput6 testtry -# if [ $? != 0 ] ; then exit 1; fi -# else exit 1 -# fi -# if [ "$opt" = "-s" ] ; then echo " OK with study" -# elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" -# else echo " OK" -# fi -# done -# fi -#fi -# -## Test non-Perl-compatible Unicode property support -# -#if [ $do7 = yes ] ; then -# echo $title7 -# if [ $utf -eq 0 -o $ucp -eq 0 ] ; then -# echo " Skipped because Unicode property support is not available" -# else -# for opt in "" "-s" $jitopt; do -# $sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput7 testtry -# if [ $? = 0 ] ; then -# $cf $testdata/testoutput7 testtry -# if [ $? != 0 ] ; then exit 1; fi -# else exit 1 -# fi -# if [ "$opt" = "-s" ] ; then echo " OK with study" -# elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" -# else echo " OK" -# fi -# done -# fi -#fi -# -## Tests for DFA matching support -# -#if [ $do8 = yes ] ; then -# echo $title8 -# for opt in "" "-s"; do -# $sim $valgrind ./pcre2test -q $bmode $opt -dfa $testdata/testinput8 testtry -# if [ $? = 0 ] ; then -# $cf $testdata/testoutput8 testtry -# if [ $? != 0 ] ; then exit 1; fi -# else exit 1 -# fi -# if [ "$opt" = "-s" ] ; then echo " OK with study" ; else echo " OK"; fi -# done -#fi -# -#if [ $do9 = yes ] ; then -# echo ${title9}-${bits} -# if [ $utf -eq 0 ] ; then -# echo " Skipped because UTF-$bits support is not available" -# else -# for opt in "" "-s"; do -# $sim $valgrind ./pcre2test -q $bmode $opt -dfa $testdata/testinput9 testtry -# if [ $? = 0 ] ; then -# $cf $testdata/testoutput9 testtry -# if [ $? != 0 ] ; then exit 1; fi -# else exit 1 -# fi -# if [ "$opt" = "-s" ] ; then echo " OK with study" ; else echo " OK"; fi -# done -# fi -#fi -# -#if [ $do10 = yes ] ; then -# echo $title10 -# if [ $utf -eq 0 -o $ucp -eq 0 ] ; then -# echo " Skipped because Unicode property support is not available" -# else -# for opt in "" "-s"; do -# $sim $valgrind ./pcre2test -q $bmode $opt -dfa $testdata/testinput10 testtry -# if [ $? = 0 ] ; then -# $cf $testdata/testoutput10 testtry -# if [ $? != 0 ] ; then exit 1; fi -# else exit 1 -# fi -# if [ "$opt" = "-s" ] ; then echo " OK with study" ; else echo " OK"; fi -# done -# fi -#fi -# +if [ $do5 = yes ] ; then + echo ${title5A}-${bits}$title5B + if [ $utf -eq 0 ] ; then + echo " Skipped because UTF-$bits support is not available" + else + for opt in "" $jitopt; do + $sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput5 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput5 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + if [ "$opt" = "-jit" ] ; then echo " OK with JIT" + else echo " OK" + fi + done + fi +fi + +# Tests for DFA matching support + +if [ $do6 = yes ] ; then + echo $title6 + $sim $valgrind ./pcre2test -q $bmode $testdata/testinput6 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput6 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo " OK" +fi + +if [ $do7 = yes ] ; then + echo ${title7A}-${bits}$title7B + if [ $utf -eq 0 ] ; then + echo " Skipped because UTF-$bits support is not available" + else + $sim $valgrind ./pcre2test -q $bmode $opt $testdata/testinput7 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput7 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo " OK" + fi +fi + ## Test of internal offsets and code sizes. This test is run only when there ## is Unicode property support and the link size is 2. The actual tests are ## mostly the same as in some of the above, but in this test we inspect some diff --git a/src/pcre2.h b/src/pcre2.h index 967e7f4..ca74493 100644 --- a/src/pcre2.h +++ b/src/pcre2.h @@ -123,19 +123,21 @@ D is inspected during pcre2_dfa_match() execution #define PCRE2_JIT_PARTIAL_SOFT 0x00000002 #define PCRE2_JIT_PARTIAL_HARD 0x00000004 -/* These are for pcre2_match() and pcre2_dfa_match(). */ +/* These are for pcre2_match() and pcre2_dfa_match(). Note that PCRE2_ANCHORED, +PCRE2_NO_START_OPTIMIZE, and PCRE2_NO_UTF_CHECK can also be passed to these +functions, so take care not to define synonyms by mistake. */ -#define PCRE2_NOTBOL 0x00000001 -#define PCRE2_NOTEOL 0x00000002 -#define PCRE2_NOTEMPTY 0x00000004 -#define PCRE2_NOTEMPTY_ATSTART 0x00000008 -#define PCRE2_PARTIAL_SOFT 0x00000010 -#define PCRE2_PARTIAL_HARD 0x00000020 +#define PCRE2_NOTBOL 0x00000008 +#define PCRE2_NOTEOL 0x00000010 +#define PCRE2_NOTEMPTY 0x00000020 +#define PCRE2_NOTEMPTY_ATSTART 0x00000040 +#define PCRE2_PARTIAL_SOFT 0x00000080 +#define PCRE2_PARTIAL_HARD 0x00000100 /* These are additional options for pcre2_dfa_match(). */ -#define PCRE2_DFA_RESTART 0x00000040 -#define PCRE2_DFA_SHORTEST 0x00000080 +#define PCRE2_DFA_RESTART 0x00000200 +#define PCRE2_DFA_SHORTEST 0x00000400 /* Newline and \R settings, for use in the compile and match contexts. The newline values must be kept in step with values set in config.h and both sets diff --git a/src/pcre2.h.in b/src/pcre2.h.in index 24ab70e..5b4cc15 100644 --- a/src/pcre2.h.in +++ b/src/pcre2.h.in @@ -123,19 +123,21 @@ D is inspected during pcre2_dfa_match() execution #define PCRE2_JIT_PARTIAL_SOFT 0x00000002 #define PCRE2_JIT_PARTIAL_HARD 0x00000004 -/* These are for pcre2_match() and pcre2_dfa_match(). */ +/* These are for pcre2_match() and pcre2_dfa_match(). Note that PCRE2_ANCHORED, +PCRE2_NO_START_OPTIMIZE, and PCRE2_NO_UTF_CHECK can also be passed to these +functions, so take care not to define synonyms by mistake. */ -#define PCRE2_NOTBOL 0x00000001 -#define PCRE2_NOTEOL 0x00000002 -#define PCRE2_NOTEMPTY 0x00000004 -#define PCRE2_NOTEMPTY_ATSTART 0x00000008 -#define PCRE2_PARTIAL_SOFT 0x00000010 -#define PCRE2_PARTIAL_HARD 0x00000020 +#define PCRE2_NOTBOL 0x00000008 +#define PCRE2_NOTEOL 0x00000010 +#define PCRE2_NOTEMPTY 0x00000020 +#define PCRE2_NOTEMPTY_ATSTART 0x00000040 +#define PCRE2_PARTIAL_SOFT 0x00000080 +#define PCRE2_PARTIAL_HARD 0x00000100 /* These are additional options for pcre2_dfa_match(). */ -#define PCRE2_DFA_RESTART 0x00000040 -#define PCRE2_DFA_SHORTEST 0x00000080 +#define PCRE2_DFA_RESTART 0x00000200 +#define PCRE2_DFA_SHORTEST 0x00000400 /* Newline and \R settings, for use in the compile and match contexts. The newline values must be kept in step with values set in config.h and both sets diff --git a/src/pcre2_byte_order.c b/src/pcre2_byte_order.c index 8ef44f0..4526541 100644 --- a/src/pcre2_byte_order.c +++ b/src/pcre2_byte_order.c @@ -107,14 +107,14 @@ return -1; REAL_PCRE *re = (REAL_PCRE *)argument_re; pcre_study_data *study; -#ifndef COMPILE_PCRE8 +#if PCRE2_CODE_UNIT_WIDTH != 8 pcre_uchar *ptr; int length; -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +#if defined SUPPORT_UTF && PCRE2_CODE_UNIT_WIDTH == 16 BOOL utf; BOOL utf16_char; -#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ -#endif /* !COMPILE_PCRE8 */ +#endif +#endif if (re == NULL) return PCRE_ERROR_NULL; if (re->magic_number == MAGIC_NUMBER) @@ -134,10 +134,10 @@ re->flags = swap_uint32(re->flags); re->limit_match = swap_uint32(re->limit_match); re->limit_recursion = swap_uint32(re->limit_recursion); -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 +#if PCRE2_CODE_UNIT_WIDTH == 8 || PCRE2_CODE_UNIT_WIDTH == 16 re->first_char = swap_uint16(re->first_char); re->req_char = swap_uint16(re->req_char); -#elif defined COMPILE_PCRE32 +#elif PCRE2_CODE_UNIT_WIDTH == 32 re->first_char = swap_uint32(re->first_char); re->req_char = swap_uint32(re->req_char); #endif @@ -159,27 +159,27 @@ if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) study->minlength = swap_uint32(study->minlength); } -#ifndef COMPILE_PCRE8 +#if PCRE2_CODE_UNIT_WIDTH != 8 ptr = (pcre_uchar *)re + re->name_table_offset; length = re->name_count * re->name_entry_size; -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +#if defined SUPPORT_UTF && PCRE2_CODE_UNIT_WIDTH == 16 utf = (re->options & PCRE_UTF16) != 0; utf16_char = FALSE; -#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ +#endif while(TRUE) { /* Swap previous characters. */ while (length-- > 0) { -#if defined COMPILE_PCRE16 +#if PCRE2_CODE_UNIT_WIDTH == 16 *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 +#elif PCRE2_CODE_UNIT_WIDTH == 32 *ptr = swap_uint32(*ptr); #endif ptr++; } -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +#if defined SUPPORT_UTF && PCRE2_CODE_UNIT_WIDTH == 16 if (utf16_char) { if (HAS_EXTRALEN(ptr[-1])) @@ -194,9 +194,9 @@ while(TRUE) /* Get next opcode. */ length = 0; -#if defined COMPILE_PCRE16 +#if PCRE2_CODE_UNIT_WIDTH == 16 *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 +#elif PCRE2_CODE_UNIT_WIDTH == 32 *ptr = swap_uint32(*ptr); #endif switch (*ptr) @@ -204,7 +204,7 @@ while(TRUE) case OP_END: return 0; -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 +#if defined SUPPORT_UTF && PCRE2_CODE_UNIT_WIDTH == 16 case OP_CHAR: case OP_CHARI: case OP_NOT: @@ -279,12 +279,12 @@ while(TRUE) case OP_XCLASS: /* Reverse the size of the XCLASS instance. */ ptr++; -#if defined COMPILE_PCRE16 +#if PCRE2_CODE_UNIT_WIDTH == 16 *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 +#elif PCRE2_CODE_UNIT_WIDTH == 32 *ptr = swap_uint32(*ptr); #endif -#ifndef COMPILE_PCRE32 +#if PCRE2_CODE_UNIT_WIDTH != 32 if (LINK_SIZE > 1) { /* LINK_SIZE can be 1 or 2 in 16 bit mode. */ @@ -294,9 +294,9 @@ while(TRUE) #endif ptr++; length = (GET(ptr, -LINK_SIZE)) - (1 + LINK_SIZE + 1); -#if defined COMPILE_PCRE16 +#if PCRE2_CODE_UNIT_WIDTH == 16 *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 +#elif PCRE2_CODE_UNIT_WIDTH == 32 *ptr = swap_uint32(*ptr); #endif if ((*ptr & XCL_MAP) != 0) @@ -310,7 +310,7 @@ while(TRUE) ptr++; } /* Control should never reach here in 16/32 bit mode. */ -#endif /* !COMPILE_PCRE8 */ +#endif #endif /* NEVER */ diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c index f82b8ac..f307198 100644 --- a/src/pcre2_compile.c +++ b/src/pcre2_compile.c @@ -54,21 +54,22 @@ POSSIBILITY OF SUCH DAMAGE. by defining macros in order to minimize #if usage. */ #if PCRE2_CODE_UNIT_WIDTH == 8 -#define STRING_UTFn_RIGHTPAR STRING_UTF8_RIGHTPAR, 5 -#define XDIGIT(c) xdigitab[c] +#define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */ +#define STRING_UTFn_RIGHTPAR STRING_UTF8_RIGHTPAR, 5 +#define XDIGIT(c) xdigitab[c] #else /* Either 16-bit or 32-bit */ -#define XDIGIT(c) (MAX_255(c)? xdigitab[c] : 0xff) +#define XDIGIT(c) (MAX_255(c)? xdigitab[c] : 0xff) #if PCRE2_CODE_UNIT_WIDTH == 16 -#define STRING_UTFn_RIGHTPAR STRING_UTF16_RIGHTPAR, 6 +#define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */ +#define STRING_UTFn_RIGHTPAR STRING_UTF16_RIGHTPAR, 6 -#else -#define STRING_UTFn_RIGHTPAR STRING_UTF32_RIGHTPAR, 6 +#else /* 33-bit */ +#define STRING_UTFn_RIGHTPAR STRING_UTF32_RIGHTPAR, 6 #endif #endif - /* Function definitions to allow mutual recursion */ static int @@ -1308,7 +1309,7 @@ for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE); actual length is stored in the compiled code, so we must update "code" here. */ -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 +#if defined SUPPORT_UTF || PCRE2_CODE_UNIT_WIDTH != 8 case OP_XCLASS: ccode = code += GET(code, 1); goto CHECK_CLASS_REPEAT; @@ -1318,7 +1319,7 @@ for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE); case OP_NCLASS: ccode = code + PRIV(OP_lengths)[OP_CLASS]; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 +#if defined SUPPORT_UTF || PCRE2_CODE_UNIT_WIDTH != 8 CHECK_CLASS_REPEAT: #endif @@ -1875,7 +1876,7 @@ else c -= CHAR_0; while(i++ < 2 && ptr[1] >= CHAR_0 && ptr[1] <= CHAR_7) c = c * 8 + *(++ptr) - CHAR_0; -#ifdef COMPILE_PCRE8 +#if PCRE2_CODE_UNIT_WIDTH == 8 if (!utf && c > 0xff) *errorcodeptr = ERR51; #endif break; @@ -1894,15 +1895,15 @@ else { cc = *ptr++; if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ -#ifdef COMPILE_PCRE32 +#if PCRE2_CODE_UNIT_WIDTH == 32 if (c >= 0x20000000l) { overflow = TRUE; break; } #endif c = (c << 3) + cc - CHAR_0 ; -#if defined COMPILE_PCRE8 +#if PCRE2_CODE_UNIT_WIDTH == 8 if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE16 +#elif PCRE2_CODE_UNIT_WIDTH == 16 if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE32 +#elif PCRE2_CODE_UNIT_WIDTH == 32 if (utf && c > 0x10ffffU) { overflow = TRUE; break; } #endif } @@ -2241,7 +2242,7 @@ PRIV(find_bracket)(PCRE2_SPTR code, BOOL utf, int number) for (;;) { register PCRE2_UCHAR c = *code; - + if (c == OP_END) return NULL; /* XCLASS is used for classes that cannot be represented just by a bit @@ -3039,7 +3040,6 @@ dynamically as we process the pattern. */ #ifdef SUPPORT_UTF BOOL utf = (options & PCRE2_UTF) != 0; #if PCRE2_CODE_UNIT_WIDTH != 32 -#define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */ PCRE2_UCHAR utf_units[6]; /* For setting up multi-cu chars */ #endif @@ -7608,7 +7608,7 @@ help in the case when a regex compiled on a system with 4-byte pointers is run on another with 8-byte pointers. */ #ifdef FIXME -#ifdef COMPILE_PCRE32 +#if PCRE2_CODE_UNIT_WIDTH == 32 re->dummy = 0; #else re->dummy1 = re->dummy2 = re->dummy3 = 0; diff --git a/src/pcre2_dfa_match.c b/src/pcre2_dfa_match.c index e6fa08f..de6622c 100644 --- a/src/pcre2_dfa_match.c +++ b/src/pcre2_dfa_match.c @@ -632,7 +632,7 @@ for (;;) /* If this opcode inspects a character, but we are at the end of the subject, remember the fact for use when testing for a partial match. */ - + if (clen == 0 && poptable[codevalue] != 0) could_continue = TRUE; @@ -1400,7 +1400,7 @@ for (;;) case 0x2028: case 0x2029: #endif /* Not EBCDIC */ - if ((mb->moptions & PCRE2_BSR_ANYCRLF) != 0) break; + if (mb->bsr_convention == PCRE2_BSR_ANYCRLF) break; goto ANYNL01; case CHAR_CR: @@ -1669,7 +1669,7 @@ for (;;) case 0x2028: case 0x2029: #endif /* Not EBCDIC */ - if ((mb->moptions & PCRE2_BSR_ANYCRLF) != 0) break; + if (mb->bsr_convention == PCRE2_BSR_ANYCRLF) break; goto ANYNL02; case CHAR_CR: @@ -1939,7 +1939,7 @@ for (;;) case 0x2028: case 0x2029: #endif /* Not EBCDIC */ - if ((mb->moptions & PCRE2_BSR_ANYCRLF) != 0) break; + if (mb->bsr_convention == PCRE2_BSR_ANYCRLF) break; goto ANYNL03; case CHAR_CR: @@ -2121,7 +2121,7 @@ for (;;) case 0x2028: case 0x2029: #endif /* Not EBCDIC */ - if ((mb->moptions & PCRE2_BSR_ANYCRLF) != 0) break; + if (mb->bsr_convention == PCRE2_BSR_ANYCRLF) break; case CHAR_LF: ADD_NEW(state_offset + 1, 0); @@ -2985,7 +2985,7 @@ for (;;) The "could_continue" variable is true if a state could have continued but for the fact that the end of the subject was reached. */ - + if (new_count <= 0) { if (rlevel == 1 && /* Top level, and */ @@ -3378,7 +3378,7 @@ for (;;) /* The following two optimizations are disabled for partial matching. */ - if ((mb->moptions & PCRE2_PARTIAL_HARD & PCRE2_PARTIAL_SOFT) == 0) + if ((mb->moptions & (PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT)) == 0) { /* The minimum matching length is a lower bound; no actual string of that length may actually match the pattern. Although the value is, strictly, @@ -3461,7 +3461,7 @@ for (;;) /* Anything other than "no match" means we are done, always; otherwise, carry on only if not anchored. */ - + if (rc != PCRE2_ERROR_NOMATCH || anchored) { if (rc == PCRE2_ERROR_PARTIAL && match_data->oveccount > 0) @@ -3470,6 +3470,8 @@ for (;;) match_data->ovector[1] = (PCRE2_OFFSET)(end_subject - subject); } match_data->leftchar = (PCRE2_OFFSET)(mb->start_used_ptr - subject); + match_data->rightchar = 0; /* FIXME */ + match_data->startchar = (PCRE2_OFFSET)(start_match - subject); match_data->rc = rc; return rc; } diff --git a/src/pcre2_printint.c b/src/pcre2_printint.c index 4ac818b..936a81d 100644 --- a/src/pcre2_printint.c +++ b/src/pcre2_printint.c @@ -90,30 +90,26 @@ static unsigned int print_char(FILE *f, PCRE2_SPTR ptr, BOOL utf) { uint32_t c = *ptr; -#if defined SUPPORT_UTF && PCRE2_CODE_UNIT_WIDTH == 8 -int a, i, s; -#endif +BOOL one_code_unit = !utf; -/* If UTF is supported and requested, check for a one-code-unit character. The -16-bit and 32-bit tests are for malformed UTF, and should only trigger if the -sanity check is turned off. */ +/* If UTF is supported and requested, check for a valid single code unit. */ #ifdef SUPPORT_UTF if (utf) { #if PCRE2_CODE_UNIT_WIDTH == 8 - utf = (c & 0xc0) == 0xc0; + one_code_unit = c < 0x80; #elif PCRE2_CODE_UNIT_WIDTH == 16 - utf = (c & 0xfc00) == 0xd800; + one_code_unit = (c & 0xfc00) != 0xd800; #else - utf = (c & 0xfffff800u) != 0xd800u; + one_code_unit = (c & 0xfffff800u) != 0xd800u; #endif } #endif /* SUPPORT_UTF */ -/* Handle a one-code-unit character at any width. */ +/* Handle a valid one-code-unit character at any width. */ -if (!utf) +if (one_code_unit) { if (PRINTABLE(c)) fprintf(f, "%c", (char)c); else if (c < 0x80) fprintf(f, "\\x%02x", c); @@ -121,41 +117,43 @@ if (!utf) return 0; } -/* Per-width code for handling non-one-code-unit UTF characters. */ +/* Per-width code for invalid UTF code units and multi-unit UTF characters. */ #ifdef SUPPORT_UTF -/* Handle a multi-byte UTF-8 character. */ +/* Malformed UTF-8 should occur only if the sanity check has been turned off. +Rather than swallow random bytes, just stop if we hit a bad one. Print it with +\X instead of \x as an indication. */ #if PCRE2_CODE_UNIT_WIDTH == 8 -a = utf8_table4[c & 0x3f]; /* Number of additional bytes */ -s = 6*a; -c = (c & utf8_table3[a]) << s; -for (i = 1; i <= a; i++) +if ((c & 0xc0) != 0xc0) { - /* This is a check for malformed UTF-8; it should only occur if the sanity - check has been turned off. Rather than swallow random bytes, just stop if - we hit a bad one. Print it with \X instead of \x as an indication. */ - - if ((ptr[i] & 0xc0) != 0x80) + fprintf(f, "\\X{%x}", c); /* Invalid starting byte */ + return 0; + } +else + { + int i; + int a = utf8_table4[c & 0x3f]; /* Number of additional bytes */ + int s = 6*a; + c = (c & utf8_table3[a]) << s; + for (i = 1; i <= a; i++) { - fprintf(f, "\\X{%x}", c); - return i - 1; + if ((ptr[i] & 0xc0) != 0x80) + { + fprintf(f, "\\X{%x}", c); /* Invalid secondary byte */ + return i - 1; + } + s -= 6; + c |= (ptr[i] & 0x3f) << s; } - - /* The byte is OK */ - - s -= 6; - c |= (ptr[i] & 0x3f) << s; - } -fprintf(f, "\\x{%x}", c); -return a; + fprintf(f, "\\x{%x}", c); + return a; +} #endif /* PCRE2_CODE_UNIT_WIDTH == 8 */ -/* Handle a multi-code-unit UTF-16 character, starting with a check for -malformed UTF-16; it should only occur if the sanity check has been turned off. -Rather than swallow a low surrogate, just stop if we hit a bad one. Print it -with \X instead of \x as an indication. */ +/* UTF-16: rather than swallow a low surrogate, just stop if we hit a bad one. +Print it with \X instead of \x as an indication. */ #if PCRE2_CODE_UNIT_WIDTH == 16 if ((ptr[1] & 0xfc00) != 0xdc00) @@ -176,7 +174,7 @@ as an indication. */ fprintf(f, "\\X{%x}", c); return 0; #endif /* PCRE2_CODE_UNIT_WIDTH == 32 */ -#endif /* SUPPORT_UTF */ +#endif /* SUPPORT_UTF */ } diff --git a/src/pcre2_study.c b/src/pcre2_study.c index c702d00..7ede428 100644 --- a/src/pcre2_study.c +++ b/src/pcre2_study.c @@ -751,7 +751,7 @@ set_start_bits(pcre2_real_code *re, PCRE2_SPTR code, BOOL utf) register uint32_t c; int yield = SSB_DONE; -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 +#if defined SUPPORT_UTF && PCRE2_CODE_UNIT_WIDTH == 8 int table_limit = utf? 16:32; #else int table_limit = 32; diff --git a/testdata/testinput5 b/testdata/testinput5 new file mode 100644 index 0000000..4955bcc --- /dev/null +++ b/testdata/testinput5 @@ -0,0 +1,1569 @@ +# 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). + + +/\x{110000}/IB,utf + +/\o{4200000}/IB,utf + +/\x{ffffffff}/utf + +/\o{37777777777}/utf + +/\x{100000000}/utf + +/\o{77777777777}/utf + +/\x{d800}/utf + +/\o{154000}/utf + +/\x{dfff}/utf + +/\o{157777}/utf + +/\x{d7ff}/utf + +/\o{153777}/utf + +/\x{e000}/utf + +/\o{170000}/utf + +/^\x{100}a\x{1234}/utf + \x{100}a\x{1234}bcd + +/\x{0041}\x{2262}\x{0391}\x{002e}/IB,utf + \x{0041}\x{2262}\x{0391}\x{002e} + +/.{3,5}X/IB,utf + \x{212ab}\x{212ab}\x{212ab}\x{861}X + +/.{3,5}?/IB,utf + \x{212ab}\x{212ab}\x{212ab}\x{861} + +/(?<=\C)X/utf + Should produce an error diagnostic + +/^[ab]/IB,utf + bar + *** Failers + c + \x{ff} + \x{100} + +/^[^ab]/IB,utf + c + \x{ff} + \x{100} + *** Failers + aaa + +/\x{100}*(\d+|"(?1)")/utf + 1234 + "1234" + \x{100}1234 + "\x{100}1234" + \x{100}\x{100}12ab + \x{100}\x{100}"12" + *** Failers + \x{100}\x{100}abcd + +/\x{100}*/IB,utf + +/a\x{100}*/IB,utf + +/ab\x{100}*/IB,utf + +/[\x{200}-\x{100}]/utf + +/[Ā-Ą]/utf + \x{100} + \x{104} + *** Failers + \x{105} + \x{ff} + +/[\xFF]/IB + >\xff< + +/[^\xFF]/IB + +/[Ä-Ü]/utf + Ö # Matches without Study + \x{d6} + +/[Ä-Ü]/utf + Ö <-- Same with Study + \x{d6} + +/[\x{c4}-\x{dc}]/utf + Ö # Matches without Study + \x{d6} + +/[\x{c4}-\x{dc}]/utf + Ö <-- Same with Study + \x{d6} + +/[^\x{100}]abc(xyz(?1))/IB,utf + +/(\x{100}(b(?2)c))?/IB,utf + +/(\x{100}(b(?2)c)){0,2}/IB,utf + +/(\x{100}(b(?1)c))?/IB,utf + +/(\x{100}(b(?1)c)){0,2}/IB,utf + +/\W/utf + A.B + A\x{100}B + +/\w/utf + \x{100}X + +/^\ሴ/IB,utf + +/()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + A (x) (?41) B/x,utf + AxxB + +/^[\x{100}\E-\Q\E\x{150}]/B,utf + +/^[\QĀ\E-\QŐ\E]/B,utf + +/^abc./gmx,newline=any,utf + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/gmx,newline=any,utf + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + +/^a\Rb/bsr=unicode,utf + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x{85}b + a\x{2028}b + a\x{2029}b + ** Failers + a\n\rb + +/^a\R*b/bsr=unicode,utf + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + +/^a\R+b/bsr=unicode,utf + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + ** Failers + ab + +/^a\R{1,3}b/bsr=unicode,utf + a\nb + a\n\rb + a\n\r\x{85}b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/\H\h\V\v/utf + X X\x0a + X\x09X\x0b + ** Failers + \x{a0} X\x0a + +/\H*\h+\V?\v{3,4}/utf + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c + ** Failers + \x09\x20\x{a0}\x0a\x0b + +/\H\h\V\v/utf + \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + ** Failers + \x{2009} X\x0a + +/\H*\h+\V?\v{3,4}/utf + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + \x09\x20\x{202f}\x0a\x0b\x0c + ** Failers + \x09\x{200a}\x{a0}\x{2028}\x0b + +/[\h]/B,utf + >\x{1680} + +/[\h]{3,}/B,utf + >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< + +/[\v]/B,utf + +/[\H]/B,utf + +/[\V]/B,utf + +/.*$/newline=any,utf + \x{1ec5} + +/a\Rb/I,bsr=anycrlf,utf + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I,bsr=unicode,utf + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\=bsr=anycrlf + a\x0bb\=bsr=anycrlf + +/a\R?b/I,bsr=anycrlf,utf + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I,bsr=unicode,utf + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\=bsr=anycrlf + a\x0bb\=bsr=anycrlf + +/.*a.*=.b.*/utf,newline=any + QQQ\x{2029}ABCaXYZ=!bPQR + ** Failers + a\x{2029}b + \x61\xe2\x80\xa9\x62 + +/[[:a\x{100}b:]]/utf + +/a[^]b/utf,alt_bsux,allow_empty_class,match_unset_backref + a\x{1234}b + a\nb + ** Failers + ab + +/a[^]+b/utf,alt_bsux,allow_empty_class,match_unset_backref + aXb + a\nX\nX\x{1234}b + ** Failers + ab + +/(\x{de})\1/ + \x{de}\x{de} + +/X/newline=any,utf,firstline + A\x{1ec5}ABCXYZ + +/Xa{2,4}b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/Xa{2,4}?b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/Xa{2,4}+b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/X\x{123}{2,4}b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X\x{123}{2,4}?b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X\x{123}{2,4}+b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X\x{123}{2,4}b/utf + Xx\=P + X\x{123}x\=P + X\x{123}\x{123}x\=P + X\x{123}\x{123}\x{123}x\=P + X\x{123}\x{123}\x{123}\x{123}x\=P + +/X\x{123}{2,4}?b/utf + Xx\=P + X\x{123}x\=P + X\x{123}\x{123}x\=P + X\x{123}\x{123}\x{123}x\=P + X\x{123}\x{123}\x{123}\x{123}x\=P + +/X\x{123}{2,4}+b/utf + Xx\=P + X\x{123}x\=P + X\x{123}\x{123}x\=P + X\x{123}\x{123}\x{123}x\=P + X\x{123}\x{123}\x{123}\x{123}x\=P + +/X\d{2,4}b/utf + X\=P + X3\=P + X33\=P + X333\=P + X3333\=P + +/X\d{2,4}?b/utf + X\=P + X3\=P + X33\=P + X333\=P + X3333\=P + +/X\d{2,4}+b/utf + X\=P + X3\=P + X33\=P + X333\=P + X3333\=P + +/X\D{2,4}b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/X\D{2,4}?b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/X\D{2,4}+b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/X\D{2,4}b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X\D{2,4}?b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X\D{2,4}+b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X[abc]{2,4}b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/X[abc]{2,4}?b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/X[abc]{2,4}+b/utf + X\=P + Xa\=P + Xaa\=P + Xaaa\=P + Xaaaa\=P + +/X[abc\x{123}]{2,4}b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X[abc\x{123}]{2,4}?b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X[abc\x{123}]{2,4}+b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X[^a]{2,4}b/utf + X\=P + Xz\=P + Xzz\=P + Xzzz\=P + Xzzzz\=P + +/X[^a]{2,4}?b/utf + X\=P + Xz\=P + Xzz\=P + Xzzz\=P + Xzzzz\=P + +/X[^a]{2,4}+b/utf + X\=P + Xz\=P + Xzz\=P + Xzzz\=P + Xzzzz\=P + +/X[^a]{2,4}b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X[^a]{2,4}?b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/X[^a]{2,4}+b/utf + X\=P + X\x{123}\=P + X\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\=P + X\x{123}\x{123}\x{123}\x{123}\=P + +/(Y)X\1{2,4}b/utf + YX\=P + YXY\=P + YXYY\=P + YXYYY\=P + YXYYYY\=P + +/(Y)X\1{2,4}?b/utf + YX\=P + YXY\=P + YXYY\=P + YXYYY\=P + YXYYYY\=P + +/(Y)X\1{2,4}+b/utf + YX\=P + YXY\=P + YXYY\=P + YXYYY\=P + YXYYYY\=P + +/(\x{123})X\1{2,4}b/utf + \x{123}X\=P + \x{123}X\x{123}\=P + \x{123}X\x{123}\x{123}\=P + \x{123}X\x{123}\x{123}\x{123}\=P + \x{123}X\x{123}\x{123}\x{123}\x{123}\=P + +/(\x{123})X\1{2,4}?b/utf + \x{123}X\=P + \x{123}X\x{123}\=P + \x{123}X\x{123}\x{123}\=P + \x{123}X\x{123}\x{123}\x{123}\=P + \x{123}X\x{123}\x{123}\x{123}\x{123}\=P + +/(\x{123})X\1{2,4}+b/utf + \x{123}X\=P + \x{123}X\x{123}\=P + \x{123}X\x{123}\x{123}\=P + \x{123}X\x{123}\x{123}\x{123}\=P + \x{123}X\x{123}\x{123}\x{123}\x{123}\=P + +/\bthe cat\b/utf + the cat\=P + the cat\=PP + +/abcd*/utf + xxxxabcd\=P + xxxxabcd\=PP + +/abcd*/i,utf + xxxxabcd\=P + xxxxabcd\=PP + XXXXABCD\=P + XXXXABCD\=PP + +/abc\d*/utf + xxxxabc1\=P + xxxxabc1\=PP + +/(a)bc\1*/utf + xxxxabca\=P + xxxxabca\=PP + +/abc[de]*/utf + xxxxabcde\=P + xxxxabcde\=PP + +/X\W{3}X/utf + X\=P + +/\sxxx\s/utf,tables=1 + AB\x{85}xxx\x{a0}XYZ + AB\x{a0}xxx\x{85}XYZ + +/\S \S/utf,tables=1 + \x{a2} \x{84} + +'A#хц'Bx,newline=any,utf + +'A#хц + PQ'Bx,newline=any,utf + +/a+#хaa + z#XX?/Bx,newline=any,utf + +/a+#хaa + z#х?/Bx,newline=any,utf + +/\g{A}xxx#bXX(?'A'123) (?'A'456)/Bx,newline=any,utf + +/\g{A}xxx#bх(?'A'123) (?'A'456)/Bx,newline=any,utf + +/^\cģ/utf + +/(\R*)(.)/s,utf + \r\n + \r\r\n\n\r + \r\r\n\n\r\n + +/(\R)*(.)/s,utf + \r\n + \r\r\n\n\r + \r\r\n\n\r\n + +/[^\x{1234}]+/Ii,utf + +/[^\x{1234}]+?/Ii,utf + +/[^\x{1234}]++/Ii,utf + +/[^\x{1234}]{2}/Ii,utf + +/f.*/ + for\=PP + +/f.*/s + for\=PP + +/f.*/utf + for\=PP + +/f.*/s,utf + for\=PP + +/\x{d7ff}\x{e000}/utf + +/\x{d800}/utf + +/\x{dfff}/utf + +/\h+/utf + \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000} + \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000} + +/[\h\x{e000}]+/B,utf + \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000} + \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000} + +/\H+/utf + \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f} + \x{2000}\x{200a}\x{1fff}\x{200b} + \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060} + \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001} + +/[\H\x{d7ff}]+/B,utf + \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f} + \x{2000}\x{200a}\x{1fff}\x{200b} + \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060} + \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001} + +/\v+/utf + \x{2027}\x{2030}\x{2028}\x{2029} + \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d + +/[\v\x{e000}]+/B,utf + \x{2027}\x{2030}\x{2028}\x{2029} + \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d + +/\V+/utf + \x{2028}\x{2029}\x{2027}\x{2030} + \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86} + +/[\V\x{d7ff}]+/B,utf + \x{2028}\x{2029}\x{2027}\x{2030} + \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86} + +/\R+/bsr=unicode,utf + \x{2027}\x{2030}\x{2028}\x{2029} + \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d + +/(..)\1/utf + ab\=P + aba\=P + abab\=P + +/(..)\1/i,utf + ab\=P + abA\=P + aBAb\=P + +/(..)\1{2,}/utf + ab\=P + aba\=P + abab\=P + ababa\=P + ababab\=P + ababab\=PP + abababa\=P + abababa\=PP + +/(..)\1{2,}/i,utf + ab\=P + aBa\=P + aBAb\=P + AbaBA\=P + abABAb\=P + aBAbaB\=PP + abABabA\=P + abaBABa\=PP + +/(..)\1{2,}?x/i,utf + ab\=P + abA\=P + aBAb\=P + abaBA\=P + abAbaB\=P + abaBabA\=P + abAbABaBx\=P + +/./utf,newline=crlf + \r\=P + \r\=PP + +/.{2,3}/utf,newline=crlf + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + +/.{2,3}?/utf,newline=crlf + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + +/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/B,utf + +/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/Bi,utf + +/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/B,utf + +/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/Bi,utf + +/(?<=\x{1234}\x{1234})\bxy/I,utf + +/(?\p{Xsp}/utf + >\x{1680}\x{2028}\x{0b} + >\x{a0} + ** Failers + \x{0b} + +/^>\p{Xsp}+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}+?/utf + >\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}*/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}{2,9}/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}{2,9}?/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>[\p{Xsp}]/utf + >\x{2028}\x{0b} + +/^>[\p{Xsp}]+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}/utf + >\x{1680}\x{2028}\x{0b} + >\x{a0} + ** Failers + \x{0b} + +/^>\p{Xps}+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}+?/utf + >\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}*/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}?/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>[\p{Xps}]/utf + >\x{2028}\x{0b} + +/^>[\p{Xps}]+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^\p{Xwd}/utf + ABCD + 1234 + \x{6ca} + \x{a6c} + \x{10a7} + _ABC + ** Failers + [] + +/^\p{Xwd}+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}+?/utf + \x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}*/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}{2,9}/utf + A_B12\x{6ca}\x{a6c}\x{10a7} + +/^\p{Xwd}{2,9}?/utf + \x{6ca}\x{a6c}\x{10a7}_ + +/^[\p{Xwd}]/utf + ABCD1234_ + 1234abcd_ + \x{6ca} + \x{a6c} + \x{10a7} + _ABC + ** Failers + [] + +/^[\p{Xwd}]+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +# A check not in UTF-8 mode + +/^[\p{Xwd}]+/ + ABCD1234_ + +# Some negative checks + +/^[\P{Xwd}]+/utf + !.+\x{019}\x{35a}AB + +/^[\p{^Xwd}]+/utf + !.+\x{019}\x{35a}AB + +/[\D]/B,utf,ucp + 1\x{3c8}2 + +/[\d]/B,utf,ucp + >\x{6f4}< + +/[\S]/B,utf,ucp + \x{1680}\x{6f4}\x{1680} + +/[\s]/B,utf,ucp + >\x{1680}< + +/[\W]/B,utf,ucp + A\x{1712}B + +/[\w]/B,utf,ucp + >\x{1723}< + +/\D/B,utf,ucp + 1\x{3c8}2 + +/\d/B,utf,ucp + >\x{6f4}< + +/\S/B,utf,ucp + \x{1680}\x{6f4}\x{1680} + +/\s/B,utf,ucp + >\x{1680}> + +/\W/B,utf,ucp + A\x{1712}B + +/\w/B,utf,ucp + >\x{1723}< + +/[[:alpha:]]/B,ucp + +/[[:lower:]]/B,ucp + +/[[:upper:]]/B,ucp + +/[[:alnum:]]/B,ucp + +/[[:ascii:]]/B,ucp + +/[[:cntrl:]]/B,ucp + +/[[:digit:]]/B,ucp + +/[[:graph:]]/B,ucp + +/[[:print:]]/B,ucp + +/[[:punct:]]/B,ucp + +/[[:space:]]/B,ucp + +/[[:word:]]/B,ucp + +/[[:xdigit:]]/B,ucp + +# Unicode properties for \b abd \B + +/\b...\B/utf,ucp + abc_ + \x{37e}abc\x{376} + \x{37e}\x{376}\x{371}\x{393}\x{394} + !\x{c0}++\x{c1}\x{c2} + !\x{c0}+++++ + +# Without PCRE_UCP, non-ASCII always fail, even if < 256 + +/\b...\B/utf + abc_ + ** Failers + \x{37e}abc\x{376} + \x{37e}\x{376}\x{371}\x{393}\x{394} + !\x{c0}++\x{c1}\x{c2} + !\x{c0}+++++ + +# With PCRE_UCP, non-UTF8 chars that are < 256 still check properties + +/\b...\B/ucp + abc_ + !\x{c0}++\x{c1}\x{c2} + !\x{c0}+++++ + +# Some of these are silly, but they check various combinations + +/[[:^alpha:][:^cntrl:]]+/B,utf,ucp + 123 + abc + +/[[:^cntrl:][:^alpha:]]+/B,utf,ucp + 123 + abc + +/[[:alpha:]]+/B,utf,ucp + abc + +/[[:^alpha:]\S]+/B,utf,ucp + 123 + abc + +/[^\d]+/B,utf,ucp + abc123 + abc\x{123} + \x{660}abc + +/\p{Lu}+9\p{Lu}+B\p{Lu}+b/B + +/\p{^Lu}+9\p{^Lu}+B\p{^Lu}+b/B + +/\P{Lu}+9\P{Lu}+B\P{Lu}+b/B + +/\p{Han}+X\p{Greek}+\x{370}/B,utf + +/\p{Xan}+!\p{Xan}+A/B + +/\p{Xsp}+!\p{Xsp}\t/B + +/\p{Xps}+!\p{Xps}\t/B + +/\p{Xwd}+!\p{Xwd}_/B + +/A+\p{N}A+\dB+\p{N}*B+\d*/B,ucp + +# These behaved oddly in Perl, so they are kept in this test + +/(\x{23a}\x{23a}\x{23a})?\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65} + +/(ȺȺȺ)?\1/i,utf + ȺȺȺⱥⱥ + +/(\x{23a}\x{23a}\x{23a})?\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + +/(ȺȺȺ)?\1/i,utf + ȺȺȺⱥⱥⱥ + +/(\x{23a}\x{23a}\x{23a})\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65} + +/(ȺȺȺ)\1/i,utf + ȺȺȺⱥⱥ + +/(\x{23a}\x{23a}\x{23a})\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + +/(ȺȺȺ)\1/i,utf + ȺȺȺⱥⱥⱥ + +/(\x{2c65}\x{2c65})\1/i,utf + \x{2c65}\x{2c65}\x{23a}\x{23a} + +/(ⱥⱥ)\1/i,utf + ⱥⱥȺȺ + +/(\x{23a}\x{23a}\x{23a})\1Y/i,utf + X\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}YZ + +/(\x{2c65}\x{2c65})\1Y/i,utf + X\x{2c65}\x{2c65}\x{23a}\x{23a}YZ + +# + +# These scripts weren't yet in Perl when I added Unicode 6.0.0 to PCRE + +/^[\p{Batak}]/utf + \x{1bc0} + \x{1bff} + ** Failers + \x{1bf4} + +/^[\p{Brahmi}]/utf + \x{11000} + \x{1106f} + ** Failers + \x{1104e} + +/^[\p{Mandaic}]/utf + \x{840} + \x{85e} + ** Failers + \x{85c} + \x{85d} + +# + +/(\X*)(.)/s,utf + A\x{300} + +/^S(\X*)e(\X*)$/utf + Stéréo + +/^\X/utf + ́réo + +/^a\X41z/alt_bsux,allow_empty_class,match_unset_backref,dupnames + aX41z + *** Failers + aAz + +/(?<=ab\Cde)X/utf + +/\X/ + a\=P + a\=PP + +/\Xa/ + aa\=P + aa\=PP + +/\X{2}/ + aa\=P + aa\=PP + +/\X+a/ + a\=P + aa\=P + aa\=PP + +/\X+?a/ + a\=P + ab\=P + aa\=P + aa\=PP + aba\=P + +# These Unicode 6.1.0 scripts are not known to Perl. + +/\p{Chakma}\d/utf,ucp + \x{11100}\x{1113c} + +/\p{Takri}\d/utf,ucp + \x{11680}\x{116c0} + +/^\X/utf + A\=P + A\=PP + A\x{300}\x{301}\=P + A\x{300}\x{301}\=PP + A\x{301}\=P + A\x{301}\=PP + +/^\X{2,3}/utf + A\=P + A\=PP + AA\=P + AA\=PP + A\x{300}\x{301}\=P + A\x{300}\x{301}\=PP + A\x{300}\x{301}A\x{300}\x{301}\=P + A\x{300}\x{301}A\x{300}\x{301}\=PP + +/^\X{2}/utf + AA\=P + AA\=PP + A\x{300}\x{301}A\x{300}\x{301}\=P + A\x{300}\x{301}A\x{300}\x{301}\=PP + +/^\X+/utf + AA\=P + AA\=PP + +/^\X+?Z/utf + AA\=P + AA\=PP + +/A\x{3a3}B/IBi,utf + +/[\x{3a3}]/Bi,utf + +/[^\x{3a3}]/Bi,utf + +/[\x{3a3}]+/Bi,utf + +/[^\x{3a3}]+/Bi,utf + +/a*\x{3a3}/Bi,utf + +/\x{3a3}+a/Bi,utf + +/\x{3a3}*\x{3c2}/Bi,utf + +/\x{3a3}{3}/i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + +/\x{3a3}{2,4}/i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + +/\x{3a3}{2,4}?/i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + +/\x{3a3}+./i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + +/\x{3a3}++./i,utf,aftertext + ** Failers + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + +/\x{3a3}*\x{3c2}/Bi,utf + +/[^\x{3a3}]*\x{3c2}/Bi,utf + +/[^a]*\x{3c2}/Bi,utf + +/ist/Bi,utf + ikt + +/is+t/i,utf + iSs\x{17f}t + ikt + +/is+?t/i,utf + ikt + +/is?t/i,utf + ikt + +/is{2}t/i,utf + iskt + +# This property is a PCRE special + +/^\p{Xuc}/utf + $abc + @abc + `abc + \x{1234}abc + ** Failers + abc + +/^\p{Xuc}+/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}+?/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}+?\*/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}++/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}{3,5}/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}{3,5}?/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^[\p{Xuc}]/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^[\p{Xuc}]+/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\P{Xuc}/utf + abc + ** Failers + $abc + @abc + `abc + \x{1234}abc + +/^[\P{Xuc}]/utf + abc + ** Failers + $abc + @abc + `abc + \x{1234}abc + +# Some auto-possessification tests + +/\pN+\z/B + +/\PN+\z/B + +/\pN+/B + +/\PN+/B + +/\p{Any}+\p{Any} \p{Any}+\P{Any} \p{Any}+\p{L&} \p{Any}+\p{L} \p{Any}+\p{Lu} \p{Any}+\p{Han} \p{Any}+\p{Xan} \p{Any}+\p{Xsp} \p{Any}+\p{Xps} \p{Xwd}+\p{Any} \p{Any}+\p{Xuc}/Bx,ucp + +/\p{L&}+\p{Any} \p{L&}+\p{L&} \P{L&}+\p{L&} \p{L&}+\p{L} \p{L&}+\p{Lu} \p{L&}+\p{Han} \p{L&}+\p{Xan} \p{L&}+\P{Xan} \p{L&}+\p{Xsp} \p{L&}+\p{Xps} \p{Xwd}+\p{L&} \p{L&}+\p{Xuc}/Bx,ucp + +/\p{N}+\p{Any} \p{N}+\p{L&} \p{N}+\p{L} \p{N}+\P{L} \p{N}+\P{N} \p{N}+\p{Lu} \p{N}+\p{Han} \p{N}+\p{Xan} \p{N}+\p{Xsp} \p{N}+\p{Xps} \p{Xwd}+\p{N} \p{N}+\p{Xuc}/Bx,ucp + +/\p{Lu}+\p{Any} \p{Lu}+\p{L&} \p{Lu}+\p{L} \p{Lu}+\p{Lu} \P{Lu}+\p{Lu} \p{Lu}+\p{Nd} \p{Lu}+\P{Nd} \p{Lu}+\p{Han} \p{Lu}+\p{Xan} \p{Lu}+\p{Xsp} \p{Lu}+\p{Xps} \p{Xwd}+\p{Lu} \p{Lu}+\p{Xuc}/Bx,ucp + +/\p{Han}+\p{Lu} \p{Han}+\p{L&} \p{Han}+\p{L} \p{Han}+\p{Lu} \p{Han}+\p{Arabic} \p{Arabic}+\p{Arabic} \p{Han}+\p{Xan} \p{Han}+\p{Xsp} \p{Han}+\p{Xps} \p{Xwd}+\p{Han} \p{Han}+\p{Xuc}/Bx,ucp + +/\p{Xan}+\p{Any} \p{Xan}+\p{L&} \P{Xan}+\p{L&} \p{Xan}+\p{L} \p{Xan}+\p{Lu} \p{Xan}+\p{Han} \p{Xan}+\p{Xan} \p{Xan}+\P{Xan} \p{Xan}+\p{Xsp} \p{Xan}+\p{Xps} \p{Xwd}+\p{Xan} \p{Xan}+\p{Xuc}/Bx,ucp + +/\p{Xsp}+\p{Any} \p{Xsp}+\p{L&} \p{Xsp}+\p{L} \p{Xsp}+\p{Lu} \p{Xsp}+\p{Han} \p{Xsp}+\p{Xan} \p{Xsp}+\p{Xsp} \P{Xsp}+\p{Xsp} \p{Xsp}+\p{Xps} \p{Xwd}+\p{Xsp} \p{Xsp}+\p{Xuc}/Bx,ucp + +/\p{Xwd}+\p{Any} \p{Xwd}+\p{L&} \p{Xwd}+\p{L} \p{Xwd}+\p{Lu} \p{Xwd}+\p{Han} \p{Xwd}+\p{Xan} \p{Xwd}+\p{Xsp} \p{Xwd}+\p{Xps} \p{Xwd}+\p{Xwd} \p{Xwd}+\P{Xwd} \p{Xwd}+\p{Xuc}/Bx,ucp + +/\p{Xuc}+\p{Any} \p{Xuc}+\p{L&} \p{Xuc}+\p{L} \p{Xuc}+\p{Lu} \p{Xuc}+\p{Han} \p{Xuc}+\p{Xan} \p{Xuc}+\p{Xsp} \p{Xuc}+\p{Xps} \p{Xwd}+\p{Xuc} \p{Xuc}+\p{Xuc} \p{Xuc}+\P{Xuc}/Bx,ucp + +/\p{N}+\p{Ll} \p{N}+\p{Nd} \p{N}+\P{Nd}/Bx,ucp + +/\p{Xan}+\p{L} \p{Xan}+\p{N} \p{Xan}+\p{C} \p{Xan}+\P{L} \P{Xan}+\p{N} \p{Xan}+\P{C}/Bx,ucp + +/\p{L}+\p{Xan} \p{N}+\p{Xan} \p{C}+\p{Xan} \P{L}+\p{Xan} \p{N}+\p{Xan} \P{C}+\p{Xan} \p{L}+\P{Xan}/Bx,ucp + +/\p{Xan}+\p{Lu} \p{Xan}+\p{Nd} \p{Xan}+\p{Cc} \p{Xan}+\P{Ll} \P{Xan}+\p{No} \p{Xan}+\P{Cf}/Bx,ucp + +/\p{Lu}+\p{Xan} \p{Nd}+\p{Xan} \p{Cs}+\p{Xan} \P{Lt}+\p{Xan} \p{Nl}+\p{Xan} \P{Cc}+\p{Xan} \p{Lt}+\P{Xan}/Bx,ucp + +/\w+\p{P} \w+\p{Po} \w+\s \p{Xan}+\s \s+\p{Xan} \s+\w/Bx,ucp + +/\w+\P{P} \W+\p{Po} \w+\S \P{Xan}+\s \s+\P{Xan} \s+\W/Bx,ucp + +/\w+\p{Po} \w+\p{Pc} \W+\p{Po} \W+\p{Pc} \w+\P{Po} \w+\P{Pc}/Bx,ucp + +/\p{Nl}+\p{Xan} \P{Nl}+\p{Xan} \p{Nl}+\P{Xan} \P{Nl}+\P{Xan}/Bx,ucp + +/\p{Xan}+\p{Nl} \P{Xan}+\p{Nl} \p{Xan}+\P{Nl} \P{Xan}+\P{Nl}/Bx,ucp + +/\p{Xan}+\p{Nd} \P{Xan}+\p{Nd} \p{Xan}+\P{Nd} \P{Xan}+\P{Nd}/Bx,ucp + +# End auto-possessification tests + +/\w+/B,utf,ucp,auto_callout + abcd + +/[\p{N}]?+/B,no_auto_possess + +/[\p{L}ab]{2,3}+/B,no_auto_possess + +/\D+\X \d+\X \S+\X \s+\X \W+\X \w+\X \C+\X \R+\X \H+\X \h+\X \V+\X \v+\X a+\X \n+\X .+\X/Bx + +/.+\X/Bsx + +/\X+$/Bmx + +/\X+\D \X+\d \X+\S \X+\s \X+\W \X+\w \X+. \X+\C \X+\R \X+\H \X+\h \X+\V \X+\v \X+\X \X+\Z \X+\z \X+$/Bx + +/\d+\s{0,5}=\s*\S?=\w{0,4}\W*/B,utf,ucp + +/[RST]+/Bi,utf,ucp + +/[R-T]+/Bi,utf,ucp + +/[Q-U]+/Bi,utf,ucp + +/^s?c/Iim,utf + scat + +# End of testinput5 diff --git a/testdata/testinput6 b/testdata/testinput6 new file mode 100644 index 0000000..20c5cdd --- /dev/null +++ b/testdata/testinput6 @@ -0,0 +1,4786 @@ +# This set of tests check the DFA matching functionality of pcre2_dfa_match(), +# excluding UTF and Unicode property support. All matches are done using DFA, +# forced by setting a default subject modifier at the start. + +#forbid_utf +#subject dfa + +/abc/ + abc + +/ab*c/ + abc + abbbbc + ac + +/ab+c/ + abc + abbbbbbc + *** Failers + ac + ab + +/a*/no_auto_possess + a + aaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\=ovector=10 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\=dfa_shortest + +/(a|abcd|african)/ + a + abcd + african + +/^abc/ + abcdef + *** Failers + xyzabc + xyz\nabc + +/^abc/m + abcdef + xyz\nabc + *** Failers + xyzabc + +/\Aabc/ + abcdef + *** Failers + xyzabc + xyz\nabc + +/\Aabc/m + abcdef + *** Failers + xyzabc + xyz\nabc + +/\Gabc/ + abcdef + xyzabc\=offset=3 + *** Failers + xyzabc + xyzabc\=offset=2 + +/x\dy\Dz/ + x9yzz + x0y+z + *** Failers + xyz + xxy0z + +/x\sy\Sz/ + x yzz + x y+z + *** Failers + xyz + xxyyz + +/x\wy\Wz/ + xxy+z + *** Failers + xxy0z + x+y+z + +/x.y/ + x+y + x-y + *** Failers + x\ny + +/x.y/s + x+y + x-y + x\ny + +/(a.b(?s)c.d|x.y)p.q/ + a+bc+dp+q + a+bc\ndp+q + x\nyp+q + *** Failers + a\nbc\ndp+q + a+bc\ndp\nq + x\nyp\nq + +/a\d\z/ + ba0 + *** Failers + ba0\n + ba0\ncd + +/a\d\z/m + ba0 + *** Failers + ba0\n + ba0\ncd + +/a\d\Z/ + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d\Z/m + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d$/ + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d$/m + ba0 + ba0\n + ba0\ncd + *** Failers + +/abc/i + abc + aBc + ABC + +/[^a]/ + abcd + +/ab?\w/ + abz + abbz + azz + +/x{0,3}yz/ + ayzq + axyzq + axxyz + axxxyzq + axxxxyzq + *** Failers + ax + axx + +/x{3}yz/ + axxxyzq + axxxxyzq + *** Failers + ax + axx + ayzq + axyzq + axxyz + +/x{2,3}yz/ + axxyz + axxxyzq + axxxxyzq + *** Failers + ax + axx + ayzq + axyzq + +/[^a]+/no_auto_possess + bac + bcdefax + *** Failers + aaaaa + +/[^a]*/no_auto_possess + bac + bcdefax + *** Failers + aaaaa + +/[^a]{3,5}/no_auto_possess + xyz + awxyza + abcdefa + abcdefghijk + *** Failers + axya + axa + aaaaa + +/\d*/ + 1234b567 + xyz + +/\D*/ + a1234b567 + xyz + +/\d+/ + ab1234c56 + *** Failers + xyz + +/\D+/ + ab123c56 + *** Failers + 789 + +/\d?A/ + 045ABC + ABC + *** Failers + XYZ + +/\D?A/ + ABC + BAC + 9ABC + *** Failers + +/a+/ + aaaa + +/^.*xyz/ + xyz + ggggggggxyz + +/^.+xyz/ + abcdxyz + axyz + *** Failers + xyz + +/^.?xyz/ + xyz + cxyz + +/^\d{2,3}X/ + 12X + 123X + *** Failers + X + 1X + 1234X + +/^[abcd]\d/ + a45 + b93 + c99z + d04 + *** Failers + e45 + abcd + abcd1234 + 1234 + +/^[abcd]*\d/ + a45 + b93 + c99z + d04 + abcd1234 + 1234 + *** Failers + e45 + abcd + +/^[abcd]+\d/ + a45 + b93 + c99z + d04 + abcd1234 + *** Failers + 1234 + e45 + abcd + +/^a+X/ + aX + aaX + +/^[abcd]?\d/ + a45 + b93 + c99z + d04 + 1234 + *** Failers + abcd1234 + e45 + +/^[abcd]{2,3}\d/ + ab45 + bcd93 + *** Failers + 1234 + a36 + abcd1234 + ee45 + +/^(abc)*\d/ + abc45 + abcabcabc45 + 42xyz + *** Failers + +/^(abc)+\d/ + abc45 + abcabcabc45 + *** Failers + 42xyz + +/^(abc)?\d/ + abc45 + 42xyz + *** Failers + abcabcabc45 + +/^(abc){2,3}\d/ + abcabc45 + abcabcabc45 + *** Failers + abcabcabcabc45 + abc45 + 42xyz + +/1(abc|xyz)2(?1)3/ + 1abc2abc3456 + 1abc2xyz3456 + +/^(a*\w|ab)=(a*\w|ab)/ + ab=ab + +/^(a*\w|ab)=(?1)/ + ab=ab + +/^([^()]|\((?1)*\))*$/ + abc + a(b)c + a(b(c))d + *** Failers) + a(b(c)d + +/^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)a*)\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 + *** Failers + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x + <> + + hij> + hij> + def> + + *** Failers + >>aaabxyzpqrrrabbxyyyypqAzz + >aaaabxyzpqrrrabbxyyyypqAzz + >>>>abcxyzpqrrrabbxyyyypqAzz + *** Failers + abxyzpqrrabbxyyyypqAzz + abxyzpqrrrrabbxyyyypqAzz + abxyzpqrrrabxyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyypqAzz + aaabcxyzpqrrrabbxyyyypqqqqqqqAzz + +/^(abc){1,2}zz/ + abczz + abcabczz + *** Failers + zz + abcabcabczz + >>abczz + +/^(b+?|a){1,2}?c/ + bc + bbc + bbbc + bac + bbac + aac + abbbbbbbbbbbc + bbbbbbbbbbbac + *** Failers + aaac + abbbbbbbbbbbac + +/^(b+|a){1,2}c/ + bc + bbc + bbbc + bac + bbac + aac + abbbbbbbbbbbc + bbbbbbbbbbbac + *** Failers + aaac + abbbbbbbbbbbac + +/^(b+|a){1,2}?bc/ + bbc + +/^(b*|ba){1,2}?bc/ + babc + bbabc + bababc + *** Failers + bababbc + babababc + +/^(ba|b*){1,2}?bc/ + babc + bbabc + bababc + *** Failers + bababbc + babababc + +/^\ca\cA\c[\c{\c:/ + \x01\x01\e;z + +/^[ab\]cde]/ + athing + bthing + ]thing + cthing + dthing + ething + *** Failers + fthing + [thing + \\thing + +/^[]cde]/ + ]thing + cthing + dthing + ething + *** Failers + athing + fthing + +/^[^ab\]cde]/ + fthing + [thing + \\thing + *** Failers + athing + bthing + ]thing + cthing + dthing + ething + +/^[^]cde]/ + athing + fthing + *** Failers + ]thing + cthing + dthing + ething + +/^\/ + + +/^/ + + +/^[0-9]+$/ + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8 + 9 + 10 + 100 + *** Failers + abc + +/^.*nter/ + enter + inter + uponter + +/^xxx[0-9]+$/ + xxx0 + xxx1234 + *** Failers + xxx + +/^.+[0-9][0-9][0-9]$/ + x123 + xx123 + 123456 + *** Failers + 123 + x1234 + +/^.+?[0-9][0-9][0-9]$/ + x123 + xx123 + 123456 + *** Failers + 123 + x1234 + +/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ + abc!pqr=apquxz.ixr.zzz.ac.uk + *** Failers + !pqr=apquxz.ixr.zzz.ac.uk + abc!=apquxz.ixr.zzz.ac.uk + abc!pqr=apquxz:ixr.zzz.ac.uk + abc!pqr=apquxz.ixr.zzz.ac.ukk + +/:/ + Well, we need a colon: somewhere + *** Fail if we don't + +/([\da-f:]+)$/i + 0abc + abc + fed + E + :: + 5f03:12C0::932e + fed def + Any old stuff + *** Failers + 0zzz + gzzz + fed\x20 + Any old rubbish + +/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ + .1.2.3 + A.12.123.0 + *** Failers + .1.2.3333 + 1.2.3 + 1234.2.3 + +/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ + 1 IN SOA non-sp1 non-sp2( + 1 IN SOA non-sp1 non-sp2 ( + *** Failers + 1IN SOA non-sp1 non-sp2( + +/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ + a. + Z. + 2. + ab-c.pq-r. + sxk.zzz.ac.uk. + x-.y-. + *** Failers + -abc.peq. + +/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ + *.a + *.b0-a + *.c3-b.c + *.c-a.b-c + *** Failers + *.0 + *.a- + *.a-b.c- + *.c-a.0-c + +/^(?=ab(de))(abd)(e)/ + abde + +/^(?!(ab)de|x)(abd)(f)/ + abdf + +/^(?=(ab(cd)))(ab)/ + abcd + +/^[\da-f](\.[\da-f])*$/i + a.b.c.d + A.B.C.D + a.b.c.1.2.3.C + +/^\".*\"\s*(;.*)?$/ + \"1234\" + \"abcd\" ; + \"\" ; rhubarb + *** Failers + \"1234\" : things + +/^$/ + \ + *** Failers + +/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x + ab c + *** Failers + abc + ab cde + +/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ + ab c + *** Failers + abc + ab cde + +/^ a\ b[c ]d $/x + a bcd + a b d + *** Failers + abcd + ab d + +/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ + abcdefhijklm + +/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ + abcdefhijklm + +/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ + a+ Z0+\x08\n\x1d\x12 + +/^[.^$|()*+?{,}]+/ + .^\$(*+)|{?,?} + +/^a*\w/ + z + az + aaaz + a + aa + aaaa + a+ + aa+ + +/^a*?\w/ + z + az + aaaz + a + aa + aaaa + a+ + aa+ + +/^a+\w/ + az + aaaz + aa + aaaa + aa+ + +/^a+?\w/ + az + aaaz + aa + aaaa + aa+ + +/^\d{8}\w{2,}/ + 1234567890 + 12345678ab + 12345678__ + *** Failers + 1234567 + +/^[aeiou\d]{4,5}$/ + uoie + 1234 + 12345 + aaaaa + *** Failers + 123456 + +/^[aeiou\d]{4,5}?/ + uoie + 1234 + 12345 + aaaaa + 123456 + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + From abcd Mon Sep 1 12:33:02 1997 + *** Failers + From abcd Sep 01 12:33:02 1997 + +/^12.34/s + 12\n34 + 12\r34 + +/\w+(?=\t)/ + the quick brown\t fox + +/foo(?!bar)(.*)/ + foobar is foolish see? + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + barrel + 2barrel + A barrel + +/^(\D*)(?=\d)(?!123)/ + abc456 + *** Failers + abc123 + +/^1234(?# test newlines + inside)/ + 1234 + +/^1234 #comment in extended re + /x + 1234 + +/#rhubarb + abcd/x + abcd + +/^abcd#rhubarb/x + abcd + +/(?!^)abc/ + the abc + *** Failers + abc + +/(?=^)abc/ + abc + *** Failers + the abc + +/^[ab]{1,3}(ab*|b)/no_auto_possess + aabbbbb + +/^[ab]{1,3}?(ab*|b)/no_auto_possess + aabbbbb + +/^[ab]{1,3}?(ab*?|b)/no_auto_possess + aabbbbb + +/^[ab]{1,3}(ab*?|b)/no_auto_possess + aabbbbb + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + + user\@dom.ain + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +# leading word +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces +(?: +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +| +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +) # "special" comment or quoted string +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" +)* +< +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# < +(?: +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +(?: , +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +)* # additional domains +: +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address spec +> # > +# name and address +) +/x + Alan Other + + user\@dom.ain + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + A missing angle ]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + a\nb + +/a.b/ + acb + *** Failers + a\nb + +/a[^a]b/s + acb + a\nb + +/a.b/s + acb + a\nb + +/^(b+?|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/^(b+|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/(?!\A)x/m + x\nb\n + a\bx\n + +/\x0{ab}/ + \0{ab} + +/(A|B)*?CD/ + CD + +/(A|B)*CD/ + CD + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 1.875000282 + *** Failers + 1.235 + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + *** Failers + this is not a line with only words and spaces! + +/(\d+)(\w)/ + 12345a + 12345+ + +/((?>\d+))(\w)/ + 12345a + *** Failers + 12345+ + +/(?>a+)b/ + aaab + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/(?>b)+/ + aaabbbccc + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + +/(a+|b+|c+)*c/ + aaabbbbccccd + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + (abc(def)xyz) + *** Failers + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/a(?-i)b/i + ab + Ab + *** Failers + aB + AB + +/(a (?x)b c)d e/ + a bcd e + *** Failers + a b cd e + abcd e + a bcde + +/(a b(?x)c d (?-x)e f)/ + a bcde f + *** Failers + abcdef + +/(a(?i)b)c/ + abc + aBc + *** Failers + abC + aBC + Abc + ABc + ABC + AbC + +/a(?i:b)c/ + abc + aBc + *** Failers + ABC + abC + aBC + +/a(?i:b)*c/ + aBc + aBBc + *** Failers + aBC + aBBC + +/a(?=b(?i)c)\w\wd/ + abcd + abCd + *** Failers + aBCd + abcD + +/(?s-i:more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?:(?s-i)more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?>a(?i)b+)+c/ + abc + aBbc + aBBc + *** Failers + Abc + abAb + abbC + +/(?=a(?i)b)\w\wc/ + abc + aBc + *** Failers + Ab + abC + aBC + +/(?<=a(?i)b)(\w\w)c/ + abxxc + aBxxc + *** Failers + Abxxc + ABxxc + abxxC + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 12 + *** Failers + 123 + xyz + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 12 + *** Failers + 123 + xyz + +/(?(?<=foo)bar|cat)/ + foobar + cat + fcat + focat + *** Failers + foocat + +/(?(?a*)*/ + a + aa + aaaa + +/(abc|)+/ + abc + abcabc + abcabcabc + xyz + +/([a]*)*/ + a + aaaaa + +/([ab]*)*/ + a + b + ababab + aaaabcde + bbbb + +/([^a]*)*/ + b + bbbb + aaa + +/([^ab]*)*/ + cccc + abab + +/([a]*?)*/ + a + aaaa + +/([ab]*?)*/ + a + b + abab + baba + +/([^a]*?)*/ + b + bbbb + aaa + +/([^ab]*?)*/ + c + cccc + baba + +/(?>a*)*/ + a + aaabcde + +/((?>a*))*/ + aaaaa + aabbaa + +/((?>a*?))*/ + aaaaa + aabbaa + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 12-09-98 + *** Failers + sep-12-98 + +/(?i:saturday|sunday)/ + saturday + sunday + Saturday + Sunday + SATURDAY + SUNDAY + SunDay + +/(a(?i)bc|BB)x/ + abcx + aBCx + bbx + BBx + *** Failers + abcX + aBCX + bbX + BBX + +/^([ab](?i)[cd]|[ef])/ + ac + aC + bD + elephant + Europe + frog + France + *** Failers + Africa + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + aBd + xy + xY + zebra + Zambesi + *** Failers + aCD + XY + +/(?<=foo\n)^bar/m + foo\nbar + *** Failers + bar + baz\nbar + +/(?<=(?]&/ + <&OUT + +/(?:(f)(o)(o)|(b)(a)(r))*/ + foobar + +/(?<=a)b/ + ab + *** Failers + cb + b + +/(?a+)ab/ + +/(?>a+)b/ + aaab + +/([[:]+)/ + a:[b]: + +/([[=]+)/ + a=[b]= + +/([[.]+)/ + a.[b]. + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/a\Z/ + *** Failers + aaab + a\nb\n + +/b\Z/ + a\nb\n + +/b\z/ + +/b\Z/ + a\nb + +/b\z/ + a\nb + *** Failers + +/(?>.*)(?<=(abcd|wxyz))/ + alphabetabcd + endingwxyz + *** Failers + a rather long string that doesn't end with one of them + +/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark + +/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope + +/(?<=\d{3}(?!999))foo/ + 999foo + 123999foo + *** Failers + 123abcfoo + +/(?<=(?!...999)\d{3})foo/ + 999foo + 123999foo + *** Failers + 123abcfoo + +/(?<=\d{3}(?!999)...)foo/ + 123abcfoo + 123456foo + *** Failers + 123999foo + +/(?<=\d{3}...)(?Z)+|A)*/ + ZABCDEFG + +/((?>)+|A)*/ + ZABCDEFG + +/a*/g + abbab + +/^[\d-a]/ + abcde + -things + 0digit + *** Failers + bcdef + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + +/a b/x + ab + +/(?!\A)x/m + a\nxb\n + +/(?!^)x/m + a\nxb\n + +/abc\Qabc\Eabc/ + abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + *** Failers + abcabcabc + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + +/\Gabc/ + abc + *** Failers + xyzabc + +/\Gabc./g + abc1abc2xyzabc3 + +/abc./g + abc1abc2xyzabc3 + +/a(?x: b c )d/ + XabcdY + *** Failers + Xa b c d Y + +/((?x)x y z | a b c)/ + XabcY + AxyzB + +/(?i)AB(?-i)C/ + XabCY + *** Failers + XabcY + +/((?i)AB(?-i)C|D)E/ + abCE + DE + *** Failers + abcE + abCe + dE + De + +/[z\Qa-d]\E]/ + z + a + - + d + ] + *** Failers + b + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/(?i)reg(?:ul(?:[a]|ae)r|ex)/ + REGular + regulaer + Regex + regulr + +/[--]+/ + + + + + +/(?<=Z)X./ + \x84XAZXB + +/^(?(2)a|(1)(2))+$/ + 123a + +/(?<=a|bbbb)c/ + ac + bbbbc + +/line\nbreak/ + this is a line\nbreak + line one\nthis is a line\nbreak in the second line + +/line\nbreak/firstline + this is a line\nbreak + ** Failers + line one\nthis is a line\nbreak in the second line + +/line\nbreak/m,firstline + this is a line\nbreak + ** Failers + line one\nthis is a line\nbreak in the second line + +/1234/ + 123\=P + a4\=P,dfa_restart + +/1234/ + 123\=P + 4\=P,dfa_restart + +/^/gm + a\nb\nc\n + \ + +/(?<=C\n)^/gm + A\nC\nC\n + +/(?s)A?B/ + AB + aB + +/(?s)A*B/ + AB + aB + +/(?m)A?B/ + AB + aB + +/(?m)A*B/ + AB + aB + +/Content-Type\x3A[^\r\n]{6,}/ + Content-Type:xxxxxyyy + +/Content-Type\x3A[^\r\n]{6,}z/ + Content-Type:xxxxxyyyz + +/Content-Type\x3A[^a]{6,}/ + Content-Type:xxxyyy + +/Content-Type\x3A[^a]{6,}z/ + Content-Type:xxxyyyz + +/^abc/m + xyz\nabc + xyz\nabc\=newline=lf + xyz\r\nabc\=newline=lf + xyz\rabc\=newline=cr + xyz\r\nabc\=newline=crlf + ** Failers + xyz\nabc\=newline=cr + xyz\r\nabc\=newline=cr + xyz\nabc\=newline=crlf + xyz\rabc\=newline=crlf + xyz\rabc\=newline=lf + +/abc$/m,newline=lf + xyzabc + xyzabc\n + xyzabc\npqr + xyzabc\r\=newline=cr + xyzabc\rpqr\=newline=cr + xyzabc\r\n\=newline=crlf + xyzabc\r\npqr\=newline=crlf + ** Failers + xyzabc\r + xyzabc\rpqr + xyzabc\r\n + xyzabc\r\npqr + +/^abc/m,newline=cr + xyz\rabcdef + xyz\nabcdef\=newline=lf + ** Failers + xyz\nabcdef + +/^abc/m,newline=lf + xyz\nabcdef + xyz\rabcdef\=newline=cr + ** Failers + xyz\rabcdef + +/^abc/m,newline=crlf + xyz\r\nabcdef + xyz\rabcdef\=newline=cr + ** Failers + xyz\rabcdef + +/.*/newline=lf + abc\ndef + abc\rdef + abc\r\ndef + abc\ndef\=newline=cr + abc\rdef\=newline=cr + abc\r\ndef\=newline=cr + abc\ndef\=newline=crlf + abc\rdef\=newline=crlf + abc\r\ndef\=newline=crlf + +/\w+(.)(.)?def/s + abc\ndef + abc\rdef + abc\r\ndef + +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + +/^(a()*)*/ + aaaa + +/^(?:a(?:(?:))*)*/ + aaaa + +/^(a()+)+/ + aaaa + +/^(?:a(?:(?:))+)+/ + aaaa + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/newline=lf + a\rb + a\nb\=newline=cr + ** Failers + a\nb + a\nb\=newline=any + a\rb\=newline=cr + a\rb\=newline=any + +/^abc./gmx,newline=any + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK + +/abc.$/gmx,newline=any + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 + +/^a\Rb/bsr=unicode + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + ** Failers + a\n\rb + +/^a\R*b/bsr=unicode + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + +/^a\R+b/bsr=unicode + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + ** Failers + ab + +/^a\R{1,3}b/bsr=unicode + a\nb + a\n\rb + a\n\r\x85b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/.+foo/ + afoo + ** Failers + \r\nfoo + \nfoo + +/.+foo/newline=crlf + afoo + \nfoo + ** Failers + \r\nfoo + +/.+foo/newline=any + afoo + ** Failers + \nfoo + \r\nfoo + +/.+foo/s + afoo + \r\nfoo + \nfoo + +/^$/gm,newline=any + abc\r\rxyz + abc\n\rxyz + ** Failers + abc\r\nxyz + +/^X/m + XABC + ** Failers + XABC\=notbol + +/(?m)^$/g,newline=any,aftertext + abc\r\n\r\n + +/(?m)^$|^\r\n/g,newline=any,aftertext + abc\r\n\r\n + +/(?m)$/g,newline=any,aftertext + abc\r\n\r\n + +/(?|(abc)|(xyz))/ + >abc< + >xyz< + +/(x)(?|(abc)|(xyz))(x)/ + xabcx + xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/ + xabcpqrx + xxyzx + +/(?|(abc)|(xyz))(?1)/ + abcabc + xyzabc + ** Failers + xyzxyz + +/\H\h\V\v/ + X X\x0a + X\x09X\x0b + ** Failers + \xa0 X\x0a + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c + ** Failers + \x09\x20\xa0\x0a\x0b + +/\H{3,4}/ + XY ABCDE + XY PQR ST + +/.\h{3,4}./ + XY AB PQRS + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + > X NYQZ + ** Failers + >XYZ + > X NY Z + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/.+A/newline=crlf + \r\nA + +/\nA/newline=crlf + \r\nA + +/[\r\n]A/newline=crlf + \r\nA + +/(\r|\n)A/newline=crlf + \r\nA + +/a\Rb/I,bsr=anycrlf + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I,bsr=unicode + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\=bsr=anycrlf + a\x0bb\=bsr=anycrlf + +/a\R?b/I,bsr=anycrlf + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I,bsr=unicode + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\=bsr=anycrlf + a\x0bb\=bsr=anycrlf + +/a\R{2,4}b/I,bsr=anycrlf + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\x85b + a\x0b\0bb + +/a\R{2,4}b/I,bsr=unicode + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\x85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\x85b\=bsr=anycrlf + a\x0b\0bb\=bsr=anycrlf + +/a(?!)|\wbc/ + abc + +/a[]b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + ** Failers + ab + +/a[]+b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + ** Failers + ab + +/a[]*+b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + ** Failers + ab + +/a[^]b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + aXb + a\nb + ** Failers + ab + +/a[^]+b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + aXb + a\nX\nXb + ** Failers + ab + +/X$/dollar_endonly + X + ** Failers + X\n + +/X$/ + X + X\n + +/xyz/auto_callout + xyz + abcxyz + abcxyz\=no_start_optimize + ** Failers + abc + abc\=no_start_optimize + abcxypqr + abcxypqr\=no_start_optimize + +/(*NO_START_OPT)xyz/auto_callout + abcxyz + +/(?C)ab/ + ab + ab\=callout_none + +/ab/auto_callout + ab + ab\=callout_none + +/^"((?(?=[a])[^"])|b)*"$/auto_callout + "ab" + "ab"\=callout_none + +/\d+X|9+Y/ + ++++123999\=P + ++++123999Y\=P + +/Z(*F)/ + Z\=P + ZA\=P + +/Z(?!)/ + Z\=P + ZA\=P + +/dog(sbody)?/ + dogs\=P + dogs\=PP + +/dog(sbody)??/ + dogs\=P + dogs\=PP + +/dog|dogsbody/ + dogs\=P + dogs\=PP + +/dogsbody|dog/ + dogs\=P + dogs\=PP + +/Z(*F)Q|ZXY/ + Z\=P + ZA\=P + X\=P + +/\bthe cat\b/ + the cat\=P + the cat\=PP + +/dog(sbody)?/ + dogs\=P + body\=dfa_restart + +/dog(sbody)?/ + dogs\=PP + body\=dfa_restart + +/abc/ + abc\=P + abc\=PP + +/abc\K123/ + xyzabc123pqr + +/(?<=abc)123/ + xyzabc123pqr + xyzabc12\=P + xyzabc12\=PP + +/\babc\b/ + +++abc+++ + +++ab\=P + +++ab\=PP + +/(?=C)/g,aftertext + ABCDECBA + +/(abc|def|xyz)/I + terhjk;abcdaadsfe + the quick xyz brown fox + terhjk;abcdaadsfe\=no_start_optimize + the quick xyz brown fox\=no_start_optimize + ** Failers + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd\=no_start_optimize + +/(abc|def|xyz)/I + terhjk;abcdaadsfe + the quick xyz brown fox + terhjk;abcdaadsfe\=no_start_optimize + the quick xyz brown fox\=no_start_optimize + ** Failers + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd\=no_start_optimize + +/abcd*/aftertext + xxxxabcd\=P + xxxxabcd\=PP + dddxxx\=dfa_restart + xxxxabcd\=PP + xxx\=dfa_restart + +/abcd*/i + xxxxabcd\=P + xxxxabcd\=PP + XXXXABCD\=P + XXXXABCD\=PP + +/abc\d*/ + xxxxabc1\=P + xxxxabc1\=PP + +/abc[de]*/ + xxxxabcde\=P + xxxxabcde\=PP + +/(?:(?1)|B)(A(*F)|C)/ + ABCD + CCD + ** Failers + CAD + +/^(?:(?1)|B)(A(*F)|C)/ + CCD + BCD + ** Failers + ABCD + CAD + BAD + +/^(?!a(*SKIP)b)/ + ac + +/^(?=a(*SKIP)b|ac)/ + ** Failers + ac + +/^(?=a(*THEN)b|ac)/ + ac + +/^(?=a(*PRUNE)b)/ + ab + ** Failers + ac + +/^(?(?!a(*SKIP)b))/ + ac + +/(?<=abc)def/ + abc\=PP + +/abc$/ + abc + abc\=P + abc\=PP + +/abc$/m + abc + abc\n + abc\=PP + abc\n\=PP + abc\=P + abc\n\=P + +/abc\z/ + abc + abc\=P + abc\=PP + +/abc\Z/ + abc + abc\=P + abc\=PP + +/abc\b/ + abc + abc\=P + abc\=PP + +/abc\B/ + abc + abc\=P + abc\=PP + +/.+/ + abc\=offset=0 + abc\=offset=1 + abc\=offset=2 + abc\=offset=3 + abc\=offset=4 + abc\=offset=-4 + +/^(?:a)++\w/ + aaaab + ** Failers + aaaa + bbb + +/^(?:aa|(?:a)++\w)/ + aaaab + aaaa + ** Failers + bbb + +/^(?:a)*+\w/ + aaaab + bbb + ** Failers + aaaa + +/^(a)++\w/ + aaaab + ** Failers + aaaa + bbb + +/^(a|)++\w/ + aaaab + ** Failers + aaaa + bbb + +/(?=abc){3}abc/aftertext + abcabcabc + ** Failers + xyz + +/(?=abc)+abc/aftertext + abcabcabc + ** Failers + xyz + +/(?=abc)++abc/aftertext + abcabcabc + ** Failers + xyz + +/(?=abc){0}xyz/ + xyz + +/(?=abc){1}xyz/ + ** Failers + xyz + +/(?=(a))?./ + ab + bc + +/(?=(a))??./ + ab + bc + +/^(?=(a)){0}b(?1)/ + backgammon + +/^(?=(?1))?[az]([abc])d/ + abd + zcdxx + +/^(?!a){0}\w+/ + aaaaa + +/(?<=(abc))?xyz/ + abcxyz + pqrxyz + +/((?2))((?1))/ + abc + +/(?(R)a+|(?R)b)/ + aaaabcde + +/(?(R)a+|((?R))b)/ + aaaabcde + +/((?(R)a+|(?1)b))/ + aaaabcde + +/((?(R2)a+|(?1)b))/ + aaaabcde + +/(?(R)a*(?1)|((?R))b)/ + aaaabcde + +/(a+)/no_auto_possess + aaaa\=ovector=3 + aaaa\=ovector=4 + +/ab\Cde/ + abXde + +/(?<=ab\Cde)X/ + abZdeX + +/^\R/ + \r\=P + \r\=PP + +/^\R{2,3}x/ + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + \r\rx + \r\r\rx + +/^\R{2,3}?x/ + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + \r\rx + \r\r\rx + +/^\R?x/ + \r\=P + \r\=PP + x + \rx + +/^\R+x/ + \r\=P + \r\=PP + \r\n\=P + \r\n\=PP + \rx + +/^a$/newline=crlf + a\r\=P + a\r\=PP + +/^a$/m,newline=crlf + a\r\=P + a\r\=PP + +/^(a$|a\r)/newline=crlf + a\r\=P + a\r\=PP + +/^(a$|a\r)/m,newline=crlf + a\r\=P + a\r\=PP + +/./newline=crlf + \r\=P + \r\=PP + +/.{2,3}/newline=crlf + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + +/.{2,3}?/newline=crlf + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + +# Test simple validity check for restarts + +/abcdef/ + abc\=dfa_restart + +/)(.)|(?R))++)*F>/ + text text xxxxx text F> text2 more text. + +/^(?>.{4})abc|^\w\w.xabcd/ + xxxxabcd + xx\xa0xabcd + +/^(.{4}){2}+abc|^\w\w.x\w\w\w\wabcd/ + xxxxxxxxabcd + xx\xa0xxxxxabcd + +/abcd/ + abcd\=ovector=0 + +# These tests show up auto-possessification + +/[ab]*/ + aaaa + +/[ab]*?/ + aaaa + +/[ab]?/ + aaaa + +/[ab]??/ + aaaa + +/[ab]+/ + aaaa + +/[ab]+?/ + aaaa + +/[ab]{2,3}/ + aaaa + +/[ab]{2,3}?/ + aaaa + +/[ab]{2,}/ + aaaa + +/[ab]{2,}?/ + aaaa + +'\A(?:[^\"]++|\"(?:[^\"]*+|\"\")*+\")++' + NON QUOTED \"QUOT\"\"ED\" AFTER \"NOT MATCHED + +'\A(?:[^\"]++|\"(?:[^\"]++|\"\")*+\")++' + NON QUOTED \"QUOT\"\"ED\" AFTER \"NOT MATCHED + +# End of testinput8 diff --git a/testdata/testinput7 b/testdata/testinput7 new file mode 100644 index 0000000..c50a05c --- /dev/null +++ b/testdata/testinput7 @@ -0,0 +1,2126 @@ +# This set of tests checks UTF and Unicode property support with the DFA +# matching functionality of pcre_dfa_match(). A default subject modifier is +# used to force DFA matching for all tests. + +#subject dfa + +/\x{100}ab/utf + \x{100}ab + +/a\x{100}*b/utf + ab + a\x{100}b + a\x{100}\x{100}b + +/a\x{100}+b/utf + a\x{100}b + a\x{100}\x{100}b + *** Failers + ab + +/\bX/utf + Xoanon + +Xoanon + \x{300}Xoanon + *** Failers + YXoanon + +/\BX/utf + YXoanon + *** Failers + Xoanon + +Xoanon + \x{300}Xoanon + +/X\b/utf + X+oanon + ZX\x{300}oanon + FAX + *** Failers + Xoanon + +/X\B/utf + Xoanon + *** Failers + X+oanon + ZX\x{300}oanon + FAX + +/[^a]/utf + abcd + a\x{100} + +/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/utf + ab99 + \x{123}\x{123}45 + \x{400}\x{401}\x{402}6 + *** Failers + d99 + \x{123}\x{122}4 + \x{400}\x{403}6 + \x{400}\x{401}\x{402}\x{402}6 + +/a.b/utf + acb + a\x7fb + a\x{100}b + *** Failers + a\nb + +/a(.{3})b/utf + a\x{4000}xyb + a\x{4000}\x7fyb + a\x{4000}\x{100}yb + *** Failers + a\x{4000}b + ac\ncb + +/a(.*?)(.)/ + a\xc0\x88b + +/a(.*?)(.)/utf + a\x{100}b + +/a(.*)(.)/ + a\xc0\x88b + +/a(.*)(.)/utf + a\x{100}b + +/a(.)(.)/ + a\xc0\x92bcd + +/a(.)(.)/utf + a\x{240}bcd + +/a(.?)(.)/ + a\xc0\x92bcd + +/a(.?)(.)/utf + a\x{240}bcd + +/a(.??)(.)/ + a\xc0\x92bcd + +/a(.??)(.)/utf + a\x{240}bcd + +/a(.{3})b/utf + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + *** Failers + a\x{1234}b + ac\ncb + +/a(.{3,})b/utf + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,}?)b/utf + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,5})b/utf + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/a(.{3,5}?)b/utf + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/^[a\x{c0}]/utf + *** Failers + \x{100} + +/(?<=aXb)cd/utf + aXbcd + +/(?<=a\x{100}b)cd/utf + a\x{100}bcd + +/(?<=a\x{100000}b)cd/utf + a\x{100000}bcd + +/(?:\x{100}){3}b/utf + \x{100}\x{100}\x{100}b + *** Failers + \x{100}\x{100}b + +/\x{ab}/utf + \x{ab} + \xc2\xab + *** Failers + \x00{ab} + +/(?<=(.))X/utf + WXYZ + \x{256}XYZ + *** Failers + XYZ + +/[^a]+/g,utf + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/utf + \x{100}bc + +/^[^a]{2,}/utf + \x{100}bcAa + +/^[^a]{2,}?/utf + \x{100}bca + +/[^a]+/gi,utf + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/i,utf + \x{100}bc + +/^[^a]{2,}/i,utf + \x{100}bcAa + +/^[^a]{2,}?/i,utf + \x{100}bca + +/\x{100}{0,0}/utf + abcd + +/\x{100}?/utf + abcd + \x{100}\x{100} + +/\x{100}{0,3}/utf + \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + +/\x{100}*/utf + abce + \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/utf + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,3}/utf + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}+/utf + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/utf + abcd\x{100}\x{100}\x{100}XX + +/\x{100}{3,5}/utf + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/\x{100}{3,}/utf,no_auto_possess + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/(?<=a\x{100}{2}b)X/utf + Xyyya\x{100}\x{100}bXzzz + +/\D*/utf,no_auto_possess + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/utf,no_auto_possess + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/utf + 1X2 + 1\x{100}2 + +/>\S/utf + > >X Y + > >\x{100} Y + +/\d/utf + \x{100}3 + +/\s/utf + \x{100} X + +/\D+/utf + 12abcd34 + *** Failers + 1234 + +/\D{2,3}/utf + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\D{2,3}?/utf + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\d+/utf + 12abcd34 + *** Failers + +/\d{2,3}/utf + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\d{2,3}?/utf + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\S+/utf + 12abcd34 + *** Failers + \ \ + +/\S{2,3}/utf + 12abcd34 + 1234abcd + *** Failers + \ \ + +/\S{2,3}?/utf + 12abcd34 + 1234abcd + *** Failers + \ \ + +/>\s+ <34 + *** Failers + +/>\s{2,3} \s{2,3}? \xff< + +/[\xff]/utf + >\x{ff}< + +/[^\xFF]/ + XYZ + +/[^\xff]/utf + XYZ + \x{123} + +/^[ac]*b/utf + xb + +/^[ac\x{100}]*b/utf + xb + +/^[^x]*b/i,utf + xb + +/^[^x]*b/utf + xb + +/^\d*b/utf + xb + +/(|a)/g,utf + catac + a\x{256}a + +/^\x{85}$/i,utf + \x{85} + +/^abc./gmx,newline=any,utf + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/gmx,newline=any,utf + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + +/^a\Rb/bsr=unicode,utf + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x{85}b + a\x{2028}b + a\x{2029}b + ** Failers + a\n\rb + +/^a\R*b/bsr=unicode,utf + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + +/^a\R+b/bsr=unicode,utf + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + ** Failers + ab + +/^a\R{1,3}b/bsr=unicode,utf + a\nb + a\n\rb + a\n\r\x{85}b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/\h+\V?\v{3,4}/utf,no_auto_possess + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + +/\V?\v{3,4}/utf,no_auto_possess + \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + +/\h+\V?\v{3,4}/utf,no_auto_possess + >\x09\x20\x{a0}X\x0a\x0a\x0a< + +/\V?\v{3,4}/utf,no_auto_possess + >\x09\x20\x{a0}X\x0a\x0a\x0a< + +/\H\h\V\v/utf + X X\x0a + X\x09X\x0b + ** Failers + \x{a0} X\x0a + +/\H*\h+\V?\v{3,4}/utf,no_auto_possess + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c + ** Failers + \x09\x20\x{a0}\x0a\x0b + +/\H\h\V\v/utf + \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + ** Failers + \x{2009} X\x0a + +/\H*\h+\V?\v{3,4}/utf,no_auto_possess + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + \x09\x20\x{202f}\x0a\x0b\x0c + ** Failers + \x09\x{200a}\x{a0}\x{2028}\x0b + +/a\Rb/I,bsr=anycrlf,utf + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I,bsr=unicode,utf + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\=bsr=anycrlf + a\x0bb\=bsr=anycrlf + +/a\R?b/I,bsr=anycrlf,utf + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I,bsr=unicode,utf + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\=bsr=anycrlf + a\x0bb\=bsr=anycrlf + +/X/newline=any,utf,firstline + A\x{1ec5}ABCXYZ + +/abcd*/utf + xxxxabcd\=P + xxxxabcd\=PP + +/abcd*/i,utf + xxxxabcd\=P + xxxxabcd\=PP + XXXXABCD\=P + XXXXABCD\=PP + +/abc\d*/utf + xxxxabc1\=P + xxxxabc1\=PP + +/abc[de]*/utf + xxxxabcde\=P + xxxxabcde\=PP + +/\bthe cat\b/utf + the cat\=P + the cat\=PP + +/ab\Cde/utf + abXde + +/(?<=ab\Cde)X/utf + +/./newline=crlf,utf + \r\=P + \r\=PP + +/.{2,3}/newline=crlf,utf + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + +/.{2,3}?/newline=crlf,utf + \r\=P + \r\=PP + \r\r\=P + \r\r\=PP + \r\r\r\=P + \r\r\r\=PP + +/[^\x{100}]/utf + \x{100}\x{101}X + +/[^\x{100}]+/utf + \x{100}\x{101}X + +/\pL\P{Nd}/utf + AB + *** Failers + A0 + 00 + +/\X./utf + AB + A\x{300}BC + A\x{300}\x{301}\x{302}BC + *** Failers + \x{300} + +/\X\X/utf + ABC + A\x{300}B\x{300}\x{301}C + A\x{300}\x{301}\x{302}BC + *** Failers + \x{300} + +/^\pL+/utf + abcd + a + *** Failers + +/^\PL+/utf + 1234 + = + *** Failers + abcd + +/^\X+/utf + abcdA\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + a + *** Failers + \x{300}\x{301}\x{302} + +/\X?abc/utf + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + *** Failers + +/^\X?abc/utf + abc + A\x{300}abc + *** Failers + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + +/\X*abc/utf + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + *** Failers + +/^\X*abc/utf + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + *** Failers + \x{300}abc + +/^\pL?=./utf + A=b + =c + *** Failers + 1=2 + AAAA=b + +/^\pL*=./utf + AAAA=b + =c + *** Failers + 1=2 + +/^\X{2,3}X/utf + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + *** Failers + X + A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + +/^\pC\pL\pM\pN\pP\pS\pZ\p{Xsp}/utf + >\x{1680}\x{2028}\x{0b} + ** Failers + \x{0b} + +/^>\p{Xsp}+/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}*/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}{2,9}/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>[\p{Xsp}]/utf,no_auto_possess + >\x{2028}\x{0b} + +/^>[\p{Xsp}]+/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}/utf + >\x{1680}\x{2028}\x{0b} + >\x{a0} + ** Failers + \x{0b} + +/^>\p{Xps}+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}+?/utf + >\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}*/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}?/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>[\p{Xps}]/utf + >\x{2028}\x{0b} + +/^>[\p{Xps}]+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^\p{Xwd}/utf + ABCD + 1234 + \x{6ca} + \x{a6c} + \x{10a7} + _ABC + ** Failers + [] + +/^\p{Xwd}+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}*/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}{2,9}/utf + A_12\x{6ca}\x{a6c}\x{10a7} + +/^[\p{Xwd}]/utf + ABCD1234_ + 1234abcd_ + \x{6ca} + \x{a6c} + \x{10a7} + _ABC + ** Failers + [] + +/^[\p{Xwd}]+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +# Unicode properties for \b abd \B + +/\b...\B/utf,ucp + abc_ + \x{37e}abc\x{376} + \x{37e}\x{376}\x{371}\x{393}\x{394} + !\x{c0}++\x{c1}\x{c2} + !\x{c0}+++++ + +# Without PCRE_UCP, non-ASCII always fail, even if < 256 + +/\b...\B/utf + abc_ + ** Failers + \x{37e}abc\x{376} + \x{37e}\x{376}\x{371}\x{393}\x{394} + !\x{c0}++\x{c1}\x{c2} + !\x{c0}+++++ + +# With PCRE_UCP, non-UTF8 chars that are < 256 still check properties + +/\b...\B/ucp + abc_ + !\x{c0}++\x{c1}\x{c2} + !\x{c0}+++++ + +# Caseless single negated characters > 127 need UCP support + +/[^\x{100}]/i,utf + \x{100}\x{101}X + +/[^\x{100}]+/i,utf + \x{100}\x{101}XX + +/^\X/utf + A\=P + A\=PP + A\x{300}\x{301}\=P + A\x{300}\x{301}\=PP + A\x{301}\=P + A\x{301}\=PP + +/^\X{2,3}/utf + A\=P + A\=PP + AA\=P + AA\=PP + A\x{300}\x{301}\=P + A\x{300}\x{301}\=PP + A\x{300}\x{301}A\x{300}\x{301}\=P + A\x{300}\x{301}A\x{300}\x{301}\=PP + +/^\X{2}/utf + AA\=P + AA\=PP + A\x{300}\x{301}A\x{300}\x{301}\=P + A\x{300}\x{301}A\x{300}\x{301}\=PP + +/^\X+/utf + AA\=P + AA\=PP + +/^\X+?Z/utf + AA\=P + AA\=PP + +# These are tests for extended grapheme clusters + +/^\X/utf,aftertext + G\x{34e}\x{34e}X + \x{34e}\x{34e}X + \x04X + \x{1100}X + \x{1100}\x{34e}X + \x{1b04}\x{1b04}X + *These match up to the roman letters + \x{1111}\x{1111}L,L + \x{1111}\x{1111}\x{1169}L,L,V + \x{1111}\x{ae4c}L, LV + \x{1111}\x{ad89}L, LVT + \x{1111}\x{ae4c}\x{1169}L, LV, V + \x{1111}\x{ae4c}\x{1169}\x{1169}L, LV, V, V + \x{1111}\x{ae4c}\x{1169}\x{11fe}L, LV, V, T + \x{1111}\x{ad89}\x{11fe}L, LVT, T + \x{1111}\x{ad89}\x{11fe}\x{11fe}L, LVT, T, T + \x{ad89}\x{11fe}\x{11fe}LVT, T, T + *These match just the first codepoint (invalid sequence) + \x{1111}\x{11fe}L, T + \x{ae4c}\x{1111}LV, L + \x{ae4c}\x{ae4c}LV, LV + \x{ae4c}\x{ad89}LV, LVT + \x{1169}\x{1111}V, L + \x{1169}\x{ae4c}V, LV + \x{1169}\x{ad89}V, LVT + \x{ad89}\x{1111}LVT, L + \x{ad89}\x{1169}LVT, V + \x{ad89}\x{ae4c}LVT, LV + \x{ad89}\x{ad89}LVT, LVT + \x{11fe}\x{1111}T, L + \x{11fe}\x{1169}T, V + \x{11fe}\x{ae4c}T, LV + \x{11fe}\x{ad89}T, LVT + *Test extend and spacing mark + \x{1111}\x{ae4c}\x{0711}L, LV, extend + \x{1111}\x{ae4c}\x{1b04}L, LV, spacing mark + \x{1111}\x{ae4c}\x{1b04}\x{0711}\x{1b04}L, LV, spacing mark, extend, spacing mark + *Test CR, LF, and control + \x0d\x{0711}CR, extend + \x0d\x{1b04}CR, spacingmark + \x0a\x{0711}LF, extend + \x0a\x{1b04}LF, spacingmark + \x0b\x{0711}Control, extend + \x09\x{1b04}Control, spacingmark + *There are no Prepend characters, so we can't test Prepend, CR + +/^(?>\X{2})X/utf,aftertext + \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + +/^\X{2,4}X/utf,aftertext + \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + +/^\X{2,4}?X/utf,aftertext + \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + +/\x{1e9e}+/i,utf + \x{1e9e}\x{00df} + +/[z\x{1e9e}]+/i,utf + \x{1e9e}\x{00df} + +/\x{00df}+/i,utf + \x{1e9e}\x{00df} + +/[z\x{00df}]+/i,utf + \x{1e9e}\x{00df} + +/\x{1f88}+/i,utf + \x{1f88}\x{1f80} + +/[z\x{1f88}]+/i,utf + \x{1f88}\x{1f80} + +# Perl matches these + +/\x{00b5}+/i,utf + \x{00b5}\x{039c}\x{03bc} + +/\x{039c}+/i,utf + \x{00b5}\x{039c}\x{03bc} + +/\x{03bc}+/i,utf + \x{00b5}\x{039c}\x{03bc} + + +/\x{00c5}+/i,utf + \x{00c5}\x{00e5}\x{212b} + +/\x{00e5}+/i,utf + \x{00c5}\x{00e5}\x{212b} + +/\x{212b}+/i,utf + \x{00c5}\x{00e5}\x{212b} + + +/\x{01c4}+/i,utf + \x{01c4}\x{01c5}\x{01c6} + +/\x{01c5}+/i,utf + \x{01c4}\x{01c5}\x{01c6} + +/\x{01c6}+/i,utf + \x{01c4}\x{01c5}\x{01c6} + + +/\x{01c7}+/i,utf + \x{01c7}\x{01c8}\x{01c9} + +/\x{01c8}+/i,utf + \x{01c7}\x{01c8}\x{01c9} + +/\x{01c9}+/i,utf + \x{01c7}\x{01c8}\x{01c9} + + +/\x{01ca}+/i,utf + \x{01ca}\x{01cb}\x{01cc} + +/\x{01cb}+/i,utf + \x{01ca}\x{01cb}\x{01cc} + +/\x{01cc}+/i,utf + \x{01ca}\x{01cb}\x{01cc} + + +/\x{01f1}+/i,utf + \x{01f1}\x{01f2}\x{01f3} + +/\x{01f2}+/i,utf + \x{01f1}\x{01f2}\x{01f3} + +/\x{01f3}+/i,utf + \x{01f1}\x{01f2}\x{01f3} + + +/\x{0345}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + +/\x{0399}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + +/\x{03b9}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + +/\x{1fbe}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + + +/\x{0392}+/i,utf + \x{0392}\x{03b2}\x{03d0} + +/\x{03b2}+/i,utf + \x{0392}\x{03b2}\x{03d0} + +/\x{03d0}+/i,utf + \x{0392}\x{03b2}\x{03d0} + + +/\x{0395}+/i,utf + \x{0395}\x{03b5}\x{03f5} + +/\x{03b5}+/i,utf + \x{0395}\x{03b5}\x{03f5} + +/\x{03f5}+/i,utf + \x{0395}\x{03b5}\x{03f5} + + +/\x{0398}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + +/\x{03b8}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + +/\x{03d1}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + +/\x{03f4}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + + +/\x{039a}+/i,utf + \x{039a}\x{03ba}\x{03f0} + +/\x{03ba}+/i,utf + \x{039a}\x{03ba}\x{03f0} + +/\x{03f0}+/i,utf + \x{039a}\x{03ba}\x{03f0} + + +/\x{03a0}+/i,utf + \x{03a0}\x{03c0}\x{03d6} + +/\x{03c0}+/i,utf + \x{03a0}\x{03c0}\x{03d6} + +/\x{03d6}+/i,utf + \x{03a0}\x{03c0}\x{03d6} + + +/\x{03a1}+/i,utf + \x{03a1}\x{03c1}\x{03f1} + +/\x{03c1}+/i,utf + \x{03a1}\x{03c1}\x{03f1} + +/\x{03f1}+/i,utf + \x{03a1}\x{03c1}\x{03f1} + + +/\x{03a3}+/i,utf + \x{03A3}\x{03C2}\x{03C3} + +/\x{03c2}+/i,utf + \x{03A3}\x{03C2}\x{03C3} + +/\x{03c3}+/i,utf + \x{03A3}\x{03C2}\x{03C3} + + +/\x{03a6}+/i,utf + \x{03a6}\x{03c6}\x{03d5} + +/\x{03c6}+/i,utf + \x{03a6}\x{03c6}\x{03d5} + +/\x{03d5}+/i,utf + \x{03a6}\x{03c6}\x{03d5} + + +/\x{03c9}+/i,utf + \x{03c9}\x{03a9}\x{2126} + +/\x{03a9}+/i,utf + \x{03c9}\x{03a9}\x{2126} + +/\x{2126}+/i,utf + \x{03c9}\x{03a9}\x{2126} + + +/\x{1e60}+/i,utf + \x{1e60}\x{1e61}\x{1e9b} + +/\x{1e61}+/i,utf + \x{1e60}\x{1e61}\x{1e9b} + +/\x{1e9b}+/i,utf + \x{1e60}\x{1e61}\x{1e9b} + + +/\x{1e9e}+/i,utf + \x{1e9e}\x{00df} + +/\x{00df}+/i,utf + \x{1e9e}\x{00df} + + +/\x{1f88}+/i,utf + \x{1f88}\x{1f80} + +/\x{1f80}+/i,utf + \x{1f88}\x{1f80} + +/\x{004b}+/i,utf + \x{004b}\x{006b}\x{212a} + +/\x{006b}+/i,utf + \x{004b}\x{006b}\x{212a} + +/\x{212a}+/i,utf + \x{004b}\x{006b}\x{212a} + + +/\x{0053}+/i,utf + \x{0053}\x{0073}\x{017f} + +/\x{0073}+/i,utf + \x{0053}\x{0073}\x{017f} + +/\x{017f}+/i,utf + \x{0053}\x{0073}\x{017f} + +/ist/i,utf + ikt + +/is+t/i,utf + iSs\x{17f}t + ikt + +/is+?t/i,utf + ikt + +/is?t/i,utf + ikt + +/is{2}t/i,utf + iskt + +/^\p{Xuc}/utf + $abc + @abc + `abc + \x{1234}abc + ** Failers + abc + +/^\p{Xuc}+/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}+?/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}+?\*/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}++/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}{3,5}/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\p{Xuc}{3,5}?/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^[\p{Xuc}]/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^[\p{Xuc}]+/utf + $@`\x{a0}\x{1234}\x{e000}** + ** Failers + \x{9f} + +/^\P{Xuc}/utf + abc + ** Failers + $abc + @abc + `abc + \x{1234}abc + +/^[\P{Xuc}]/utf + abc + ** Failers + $abc + @abc + `abc + \x{1234}abc + +/^A\s+Z/utf,ucp + A\x{2005}Z + A\x{85}\x{180e}\x{2005}Z + +/^A[\s]+Z/utf,ucp + A\x{2005}Z + A\x{85}\x{180e}\x{2005}Z + +# End of testinput7 diff --git a/testdata/testoutput2 b/testdata/testoutput2 index b4303ff..a5e91e9 100644 --- a/testdata/testoutput2 +++ b/testdata/testoutput2 @@ -47,7 +47,7 @@ Subject length lower bound = 3 abc 0: abc abc\=anchored -No match + 0: abc *** Failers No match defabc @@ -352,7 +352,7 @@ Subject length lower bound = 3 abcdef 0: abc abcdef\=notbol -No match + 0: def /.*((abc)$|(def))/I Capturing subpattern count = 3 diff --git a/testdata/testoutput5 b/testdata/testoutput5 new file mode 100644 index 0000000..c7621c5 --- /dev/null +++ b/testdata/testoutput5 @@ -0,0 +1,3963 @@ +# 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). + + +/\x{110000}/IB,utf +Failed: error 134 at offset 9: character code point value in \x{} or \o{} is too large + +/\o{4200000}/IB,utf +Failed: error 134 at offset 10: character code point value in \x{} or \o{} is too large + +/\x{ffffffff}/utf +Failed: error 134 at offset 11: character code point value in \x{} or \o{} is too large + +/\o{37777777777}/utf +Failed: error 134 at offset 14: character code point value in \x{} or \o{} is too large + +/\x{100000000}/utf +Failed: error 134 at offset 12: character code point value in \x{} or \o{} is too large + +/\o{77777777777}/utf +Failed: error 134 at offset 14: character code point value in \x{} or \o{} is too large + +/\x{d800}/utf +Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + +/\o{154000}/utf +Failed: error 173 at offset 9: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + +/\x{dfff}/utf +Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + +/\o{157777}/utf +Failed: error 173 at offset 9: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + +/\x{d7ff}/utf + +/\o{153777}/utf + +/\x{e000}/utf + +/\o{170000}/utf + +/^\x{100}a\x{1234}/utf + \x{100}a\x{1234}bcd + 0: \x{100}a\x{1234} + +/\x{0041}\x{2262}\x{0391}\x{002e}/IB,utf +------------------------------------------------------------------ + Bra + A\x{2262}\x{391}. + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +First code unit = 'A' +Last code unit = '.' +Subject length lower bound = 4 + \x{0041}\x{2262}\x{0391}\x{002e} + 0: A\x{2262}\x{391}. + +/.{3,5}X/IB,utf +------------------------------------------------------------------ + Bra + Any{3} + Any{0,2} + X + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +No first code unit +Last code unit = 'X' +Subject length lower bound = 4 + \x{212ab}\x{212ab}\x{212ab}\x{861}X + 0: \x{212ab}\x{212ab}\x{212ab}\x{861}X + +/.{3,5}?/IB,utf +------------------------------------------------------------------ + Bra + Any{3} + Any{0,2}? + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +No first code unit +No last code unit +Subject length lower bound = 3 + \x{212ab}\x{212ab}\x{212ab}\x{861} + 0: \x{212ab}\x{212ab}\x{212ab} + +/(?<=\C)X/utf +Failed: error 136 at offset 6: \C is not allowed in a lookbehind assertion + Should produce an error diagnostic + +/^[ab]/IB,utf +------------------------------------------------------------------ + Bra + ^ + [ab] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Compile options: utf +Overall options: anchored utf +No first code unit +No last code unit +Subject length lower bound = 1 + bar + 0: b + *** Failers +No match + c +No match + \x{ff} +No match + \x{100} +No match + +/^[^ab]/IB,utf +------------------------------------------------------------------ + Bra + ^ + [\x00-`c-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Compile options: utf +Overall options: anchored utf +No first code unit +No last code unit +Subject length lower bound = 1 + c + 0: c + \x{ff} + 0: \x{ff} + \x{100} + 0: \x{100} + *** Failers + 0: * + aaa +No match + +/\x{100}*(\d+|"(?1)")/utf + 1234 + 0: 1234 + 1: 1234 + "1234" + 0: "1234" + 1: "1234" + \x{100}1234 + 0: \x{100}1234 + 1: 1234 + "\x{100}1234" + 0: \x{100}1234 + 1: 1234 + \x{100}\x{100}12ab + 0: \x{100}\x{100}12 + 1: 12 + \x{100}\x{100}"12" + 0: \x{100}\x{100}"12" + 1: "12" + *** Failers +No match + \x{100}\x{100}abcd +No match + +/\x{100}*/IB,utf +------------------------------------------------------------------ + Bra + \x{100}*+ + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +May match empty string +Options: utf +No first code unit +No last code unit +Subject length lower bound = 0 + +/a\x{100}*/IB,utf +------------------------------------------------------------------ + Bra + a + \x{100}*+ + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +First code unit = 'a' +No last code unit +Subject length lower bound = 1 + +/ab\x{100}*/IB,utf +------------------------------------------------------------------ + Bra + ab + \x{100}*+ + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 2 + +/[\x{200}-\x{100}]/utf +Failed: error 108 at offset 15: range out of order in character class + +/[Ā-Ą]/utf + \x{100} + 0: \x{100} + \x{104} + 0: \x{104} + *** Failers +No match + \x{105} +No match + \x{ff} +No match + +/[\xFF]/IB +------------------------------------------------------------------ + Bra + \x{ff} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First code unit = \xff +No last code unit +Subject length lower bound = 1 + >\xff< + 0: \xff + +/[^\xFF]/IB +------------------------------------------------------------------ + Bra + [^\x{ff}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first code unit +No last code unit +Subject length lower bound = 1 + +/[Ä-Ü]/utf + Ö # Matches without Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[Ä-Ü]/utf + Ö <-- Same with Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[\x{c4}-\x{dc}]/utf + Ö # Matches without Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[\x{c4}-\x{dc}]/utf + Ö <-- Same with Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[^\x{100}]abc(xyz(?1))/IB,utf +------------------------------------------------------------------ + Bra + [^\x{100}] + abc + CBra 1 + xyz + Recurse + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf +No first code unit +Last code unit = 'z' +Subject length lower bound = 7 + +/(\x{100}(b(?2)c))?/IB,utf +------------------------------------------------------------------ + Bra + Brazero + CBra 1 + \x{100} + CBra 2 + b + Recurse + c + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +May match empty string +Options: utf +No first code unit +No last code unit +Subject length lower bound = 0 + +/(\x{100}(b(?2)c)){0,2}/IB,utf +------------------------------------------------------------------ + Bra + Brazero + Bra + CBra 1 + \x{100} + CBra 2 + b + Recurse + c + Ket + Ket + Brazero + CBra 1 + \x{100} + CBra 2 + b + Recurse + c + Ket + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +May match empty string +Options: utf +No first code unit +No last code unit +Subject length lower bound = 0 + +/(\x{100}(b(?1)c))?/IB,utf +------------------------------------------------------------------ + Bra + Brazero + CBra 1 + \x{100} + CBra 2 + b + Recurse + c + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +May match empty string +Options: utf +No first code unit +No last code unit +Subject length lower bound = 0 + +/(\x{100}(b(?1)c)){0,2}/IB,utf +------------------------------------------------------------------ + Bra + Brazero + Bra + CBra 1 + \x{100} + CBra 2 + b + Recurse + c + Ket + Ket + Brazero + CBra 1 + \x{100} + CBra 2 + b + Recurse + c + Ket + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +May match empty string +Options: utf +No first code unit +No last code unit +Subject length lower bound = 0 + +/\W/utf + A.B + 0: . + A\x{100}B + 0: \x{100} + +/\w/utf + \x{100}X + 0: X + +/^\ሴ/IB,utf +------------------------------------------------------------------ + Bra + ^ + \x{1234} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Compile options: utf +Overall options: anchored utf +No first code unit +No last code unit +Subject length lower bound = 1 + +/()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + A (x) (?41) B/x,utf + AxxB +Matched, but too many substrings + 0: AxxB + 1: + 2: + 3: + 4: + 5: + 6: + 7: + 8: + 9: +10: +11: +12: +13: +14: + +/^[\x{100}\E-\Q\E\x{150}]/B,utf +------------------------------------------------------------------ + Bra + ^ + [\x{100}-\x{150}] + Ket + End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E]/B,utf +------------------------------------------------------------------ + Bra + ^ + [\x{100}-\x{150}] + Ket + End +------------------------------------------------------------------ + +/^abc./gmx,newline=any,utf + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/abc.$/gmx,newline=any,utf + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/^a\Rb/bsr=unicode,utf + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0cb + 0: a\x{0c}b + a\x{85}b + 0: a\x{85}b + a\x{2028}b + 0: a\x{2028}b + a\x{2029}b + 0: a\x{2029}b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/bsr=unicode,utf + ab + 0: ab + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + +/^a\R+b/bsr=unicode,utf + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + ** Failers +No match + ab +No match + +/^a\R{1,3}b/bsr=unicode,utf + a\nb + 0: a\x{0a}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}b + 0: a\x{0a}\x{0d}\x{85}b + a\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}b + a\r\n\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b + a\n\r\n\rb + 0: a\x{0a}\x{0d}\x{0a}\x{0d}b + a\n\n\r\nb + 0: a\x{0a}\x{0a}\x{0d}\x{0a}b + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/\H\h\V\v/utf + X X\x0a + 0: X X\x{0a} + X\x09X\x0b + 0: X\x{09}X\x{0b} + ** Failers +No match + \x{a0} X\x0a +No match + +/\H*\h+\V?\v{3,4}/utf + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} + \x09\x20\x{a0}\x0a\x0b\x0c + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x20\x{a0}\x0a\x0b +No match + +/\H\h\V\v/utf + \x{3001}\x{3000}\x{2030}\x{2028} + 0: \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + 0: X\x{180e}X\x{85} + ** Failers +No match + \x{2009} X\x0a +No match + +/\H*\h+\V?\v{3,4}/utf + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} + \x09\x20\x{202f}\x0a\x0b\x0c + 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x{200a}\x{a0}\x{2028}\x0b +No match + +/[\h]/B,utf +------------------------------------------------------------------ + Bra + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}] + Ket + End +------------------------------------------------------------------ + >\x{1680} + 0: \x{1680} + +/[\h]{3,}/B,utf +------------------------------------------------------------------ + Bra + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,}+ + Ket + End +------------------------------------------------------------------ + >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< + 0: \x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000} + +/[\v]/B,utf +------------------------------------------------------------------ + Bra + [\x0a-\x0d\x85\x{2028}-\x{2029}] + Ket + End +------------------------------------------------------------------ + +/[\H]/B,utf +------------------------------------------------------------------ + Bra + [\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 +------------------------------------------------------------------ + +/[\V]/B,utf +------------------------------------------------------------------ + Bra + [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}] + Ket + End +------------------------------------------------------------------ + +/.*$/newline=any,utf + \x{1ec5} + 0: \x{1ec5} + +/a\Rb/I,bsr=anycrlf,utf +Capturing subpattern count = 0 +Options: utf +\R matches CR, LF, or CRLF +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 3 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I,bsr=unicode,utf +Capturing subpattern count = 0 +Options: utf +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 3 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\=bsr=anycrlf +No match + a\x0bb\=bsr=anycrlf +No match + +/a\R?b/I,bsr=anycrlf,utf +Capturing subpattern count = 0 +Options: utf +\R matches CR, LF, or CRLF +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 2 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I,bsr=unicode,utf +Capturing subpattern count = 0 +Options: utf +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 2 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\=bsr=anycrlf +No match + a\x0bb\=bsr=anycrlf +No match + +/.*a.*=.b.*/utf,newline=any + QQQ\x{2029}ABCaXYZ=!bPQR + 0: ABCaXYZ=!bPQR + ** Failers +No match + a\x{2029}b +No match + \x61\xe2\x80\xa9\x62 +No match + +/[[:a\x{100}b:]]/utf +Failed: error 130 at offset 3: unknown POSIX class name + +/a[^]b/utf,alt_bsux,allow_empty_class,match_unset_backref + a\x{1234}b + 0: a\x{1234}b + a\nb + 0: a\x{0a}b + ** Failers +No match + ab +No match + +/a[^]+b/utf,alt_bsux,allow_empty_class,match_unset_backref + aXb + 0: aXb + a\nX\nX\x{1234}b + 0: a\x{0a}X\x{0a}X\x{1234}b + ** Failers +No match + ab +No match + +/(\x{de})\1/ + \x{de}\x{de} + 0: \xde\xde + 1: \xde + +/X/newline=any,utf,firstline + A\x{1ec5}ABCXYZ + 0: X + +/Xa{2,4}b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/Xa{2,4}?b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/Xa{2,4}+b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/X\x{123}{2,4}b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X\x{123}{2,4}?b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X\x{123}{2,4}+b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X\x{123}{2,4}b/utf + Xx\=P +No match + X\x{123}x\=P +No match + X\x{123}\x{123}x\=P +No match + X\x{123}\x{123}\x{123}x\=P +No match + X\x{123}\x{123}\x{123}\x{123}x\=P +No match + +/X\x{123}{2,4}?b/utf + Xx\=P +No match + X\x{123}x\=P +No match + X\x{123}\x{123}x\=P +No match + X\x{123}\x{123}\x{123}x\=P +No match + X\x{123}\x{123}\x{123}\x{123}x\=P +No match + +/X\x{123}{2,4}+b/utf + Xx\=P +No match + X\x{123}x\=P +No match + X\x{123}\x{123}x\=P +No match + X\x{123}\x{123}\x{123}x\=P +No match + X\x{123}\x{123}\x{123}\x{123}x\=P +No match + +/X\d{2,4}b/utf + X\=P +Partial match: X + X3\=P +Partial match: X3 + X33\=P +Partial match: X33 + X333\=P +Partial match: X333 + X3333\=P +Partial match: X3333 + +/X\d{2,4}?b/utf + X\=P +Partial match: X + X3\=P +Partial match: X3 + X33\=P +Partial match: X33 + X333\=P +Partial match: X333 + X3333\=P +Partial match: X3333 + +/X\d{2,4}+b/utf + X\=P +Partial match: X + X3\=P +Partial match: X3 + X33\=P +Partial match: X33 + X333\=P +Partial match: X333 + X3333\=P +Partial match: X3333 + +/X\D{2,4}b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/X\D{2,4}?b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/X\D{2,4}+b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/X\D{2,4}b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X\D{2,4}?b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X\D{2,4}+b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X[abc]{2,4}b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/X[abc]{2,4}?b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/X[abc]{2,4}+b/utf + X\=P +Partial match: X + Xa\=P +Partial match: Xa + Xaa\=P +Partial match: Xaa + Xaaa\=P +Partial match: Xaaa + Xaaaa\=P +Partial match: Xaaaa + +/X[abc\x{123}]{2,4}b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X[abc\x{123}]{2,4}?b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X[abc\x{123}]{2,4}+b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X[^a]{2,4}b/utf + X\=P +Partial match: X + Xz\=P +Partial match: Xz + Xzz\=P +Partial match: Xzz + Xzzz\=P +Partial match: Xzzz + Xzzzz\=P +Partial match: Xzzzz + +/X[^a]{2,4}?b/utf + X\=P +Partial match: X + Xz\=P +Partial match: Xz + Xzz\=P +Partial match: Xzz + Xzzz\=P +Partial match: Xzzz + Xzzzz\=P +Partial match: Xzzzz + +/X[^a]{2,4}+b/utf + X\=P +Partial match: X + Xz\=P +Partial match: Xz + Xzz\=P +Partial match: Xzz + Xzzz\=P +Partial match: Xzzz + Xzzzz\=P +Partial match: Xzzzz + +/X[^a]{2,4}b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X[^a]{2,4}?b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/X[^a]{2,4}+b/utf + X\=P +Partial match: X + X\x{123}\=P +Partial match: X\x{123} + X\x{123}\x{123}\=P +Partial match: X\x{123}\x{123} + X\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123} + X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: X\x{123}\x{123}\x{123}\x{123} + +/(Y)X\1{2,4}b/utf + YX\=P +Partial match: YX + YXY\=P +Partial match: YXY + YXYY\=P +Partial match: YXYY + YXYYY\=P +Partial match: YXYYY + YXYYYY\=P +Partial match: YXYYYY + +/(Y)X\1{2,4}?b/utf + YX\=P +Partial match: YX + YXY\=P +Partial match: YXY + YXYY\=P +Partial match: YXYY + YXYYY\=P +Partial match: YXYYY + YXYYYY\=P +Partial match: YXYYYY + +/(Y)X\1{2,4}+b/utf + YX\=P +Partial match: YX + YXY\=P +Partial match: YXY + YXYY\=P +Partial match: YXYY + YXYYY\=P +Partial match: YXYYY + YXYYYY\=P +Partial match: YXYYYY + +/(\x{123})X\1{2,4}b/utf + \x{123}X\=P +Partial match: \x{123}X + \x{123}X\x{123}\=P +Partial match: \x{123}X\x{123} + \x{123}X\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123} + \x{123}X\x{123}\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123}\x{123} + \x{123}X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123} + +/(\x{123})X\1{2,4}?b/utf + \x{123}X\=P +Partial match: \x{123}X + \x{123}X\x{123}\=P +Partial match: \x{123}X\x{123} + \x{123}X\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123} + \x{123}X\x{123}\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123}\x{123} + \x{123}X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123} + +/(\x{123})X\1{2,4}+b/utf + \x{123}X\=P +Partial match: \x{123}X + \x{123}X\x{123}\=P +Partial match: \x{123}X\x{123} + \x{123}X\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123} + \x{123}X\x{123}\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123}\x{123} + \x{123}X\x{123}\x{123}\x{123}\x{123}\=P +Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123} + +/\bthe cat\b/utf + the cat\=P + 0: the cat + the cat\=PP +Partial match: the cat + +/abcd*/utf + xxxxabcd\=P + 0: abcd + xxxxabcd\=PP +Partial match: abcd + +/abcd*/i,utf + xxxxabcd\=P + 0: abcd + xxxxabcd\=PP +Partial match: abcd + XXXXABCD\=P + 0: ABCD + XXXXABCD\=PP +Partial match: ABCD + +/abc\d*/utf + xxxxabc1\=P + 0: abc1 + xxxxabc1\=PP +Partial match: abc1 + +/(a)bc\1*/utf + xxxxabca\=P + 0: abca + 1: a + xxxxabca\=PP +Partial match: abca + +/abc[de]*/utf + xxxxabcde\=P + 0: abcde + xxxxabcde\=PP +Partial match: abcde + +/X\W{3}X/utf + X\=P +Partial match: X + +/\sxxx\s/utf,tables=1 + AB\x{85}xxx\x{a0}XYZ +No match + AB\x{a0}xxx\x{85}XYZ +No match + +/\S \S/utf,tables=1 + \x{a2} \x{84} + 0: \x{a2} \x{84} + +'A#хц'Bx,newline=any,utf +------------------------------------------------------------------ + Bra + A + Ket + End +------------------------------------------------------------------ + +'A#хц + PQ'Bx,newline=any,utf +------------------------------------------------------------------ + Bra + APQ + Ket + End +------------------------------------------------------------------ + +/a+#хaa + z#XX?/Bx,newline=any,utf +------------------------------------------------------------------ + Bra + a++ + z + Ket + End +------------------------------------------------------------------ + +/a+#хaa + z#х?/Bx,newline=any,utf +------------------------------------------------------------------ + Bra + a++ + z + Ket + End +------------------------------------------------------------------ + +/\g{A}xxx#bXX(?'A'123) (?'A'456)/Bx,newline=any,utf +------------------------------------------------------------------ + Bra + \1 + xxx + CBra 1 + 456 + Ket + Ket + End +------------------------------------------------------------------ + +/\g{A}xxx#bх(?'A'123) (?'A'456)/Bx,newline=any,utf +------------------------------------------------------------------ + Bra + \1 + xxx + CBra 1 + 456 + Ket + Ket + End +------------------------------------------------------------------ + +/^\cģ/utf +Failed: error 168 at offset 3: \c must be followed by a printable ASCII character + +/(\R*)(.)/s,utf + \r\n + 0: \x{0d} + 1: + 2: \x{0d} + \r\r\n\n\r + 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d} + 1: \x{0d}\x{0d}\x{0a}\x{0a} + 2: \x{0d} + \r\r\n\n\r\n + 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d} + 1: \x{0d}\x{0d}\x{0a}\x{0a} + 2: \x{0d} + +/(\R)*(.)/s,utf + \r\n + 0: \x{0d} + 1: + 2: \x{0d} + \r\r\n\n\r + 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d} + 1: \x{0a} + 2: \x{0d} + \r\r\n\n\r\n + 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d} + 1: \x{0a} + 2: \x{0d} + +/[^\x{1234}]+/Ii,utf +Capturing subpattern count = 0 +Options: caseless utf +No first code unit +No last code unit +Subject length lower bound = 1 + +/[^\x{1234}]+?/Ii,utf +Capturing subpattern count = 0 +Options: caseless utf +No first code unit +No last code unit +Subject length lower bound = 1 + +/[^\x{1234}]++/Ii,utf +Capturing subpattern count = 0 +Options: caseless utf +No first code unit +No last code unit +Subject length lower bound = 1 + +/[^\x{1234}]{2}/Ii,utf +Capturing subpattern count = 0 +Options: caseless utf +No first code unit +No last code unit +Subject length lower bound = 2 + +/f.*/ + for\=PP +Partial match: for + +/f.*/s + for\=PP +Partial match: for + +/f.*/utf + for\=PP +Partial match: for + +/f.*/s,utf + for\=PP +Partial match: for + +/\x{d7ff}\x{e000}/utf + +/\x{d800}/utf +Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + +/\x{dfff}/utf +Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + +/\h+/utf + \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000} + 0: \x{1680}\x{2000}\x{202f}\x{3000} + \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000} + 0: \x{200a}\x{a0}\x{2000} + +/[\h\x{e000}]+/B,utf +------------------------------------------------------------------ + Bra + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}\x{e000}]++ + Ket + End +------------------------------------------------------------------ + \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000} + 0: \x{1680}\x{2000}\x{202f}\x{3000} + \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000} + 0: \x{200a}\x{a0}\x{2000} + +/\H+/utf + \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f} + 0: \x{167f}\x{1681}\x{180d}\x{180f} + \x{2000}\x{200a}\x{1fff}\x{200b} + 0: \x{1fff}\x{200b} + \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060} + 0: \x{202e}\x{2030}\x{205e}\x{2060} + \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001} + 0: \x{9f}\x{a1}\x{2fff}\x{3001} + +/[\H\x{d7ff}]+/B,utf +------------------------------------------------------------------ + Bra + [\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 +------------------------------------------------------------------ + \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f} + 0: \x{167f}\x{1681}\x{180d}\x{180f} + \x{2000}\x{200a}\x{1fff}\x{200b} + 0: \x{1fff}\x{200b} + \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060} + 0: \x{202e}\x{2030}\x{205e}\x{2060} + \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001} + 0: \x{9f}\x{a1}\x{2fff}\x{3001} + +/\v+/utf + \x{2027}\x{2030}\x{2028}\x{2029} + 0: \x{2028}\x{2029} + \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d + 0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d} + +/[\v\x{e000}]+/B,utf +------------------------------------------------------------------ + Bra + [\x0a-\x0d\x85\x{2028}-\x{2029}\x{e000}]++ + Ket + End +------------------------------------------------------------------ + \x{2027}\x{2030}\x{2028}\x{2029} + 0: \x{2028}\x{2029} + \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d + 0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d} + +/\V+/utf + \x{2028}\x{2029}\x{2027}\x{2030} + 0: \x{2027}\x{2030} + \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86} + 0: \x{09}\x{0e}\x{84}\x{86} + +/[\V\x{d7ff}]+/B,utf +------------------------------------------------------------------ + Bra + [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}\x{d7ff}]++ + Ket + End +------------------------------------------------------------------ + \x{2028}\x{2029}\x{2027}\x{2030} + 0: \x{2027}\x{2030} + \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86} + 0: \x{09}\x{0e}\x{84}\x{86} + +/\R+/bsr=unicode,utf + \x{2027}\x{2030}\x{2028}\x{2029} + 0: \x{2028}\x{2029} + \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d + 0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d} + +/(..)\1/utf + ab\=P +Partial match: ab + aba\=P +Partial match: aba + abab\=P + 0: abab + 1: ab + +/(..)\1/i,utf + ab\=P +Partial match: ab + abA\=P +Partial match: abA + aBAb\=P + 0: aBAb + 1: aB + +/(..)\1{2,}/utf + ab\=P +Partial match: ab + aba\=P +Partial match: aba + abab\=P +Partial match: abab + ababa\=P +Partial match: ababa + ababab\=P + 0: ababab + 1: ab + ababab\=PP +Partial match: ababab + abababa\=P + 0: ababab + 1: ab + abababa\=PP +Partial match: abababa + +/(..)\1{2,}/i,utf + ab\=P +Partial match: ab + aBa\=P +Partial match: aBa + aBAb\=P +Partial match: aBAb + AbaBA\=P +Partial match: AbaBA + abABAb\=P + 0: abABAb + 1: ab + aBAbaB\=PP +Partial match: aBAbaB + abABabA\=P + 0: abABab + 1: ab + abaBABa\=PP +Partial match: abaBABa + +/(..)\1{2,}?x/i,utf + ab\=P +Partial match: ab + abA\=P +Partial match: abA + aBAb\=P +Partial match: aBAb + abaBA\=P +Partial match: abaBA + abAbaB\=P +Partial match: abAbaB + abaBabA\=P +Partial match: abaBabA + abAbABaBx\=P + 0: abAbABaBx + 1: ab + +/./utf,newline=crlf + \r\=P + 0: \x{0d} + \r\=PP +Partial match: \x{0d} + +/.{2,3}/utf,newline=crlf + \r\=P +Partial match: \x{0d} + \r\=PP +Partial match: \x{0d} + \r\r\=P + 0: \x{0d}\x{0d} + \r\r\=PP +Partial match: \x{0d}\x{0d} + \r\r\r\=P + 0: \x{0d}\x{0d}\x{0d} + \r\r\r\=PP +Partial match: \x{0d}\x{0d}\x{0d} + +/.{2,3}?/utf,newline=crlf + \r\=P +Partial match: \x{0d} + \r\=PP +Partial match: \x{0d} + \r\r\=P + 0: \x{0d}\x{0d} + \r\r\=PP +Partial match: \x{0d}\x{0d} + \r\r\r\=P + 0: \x{0d}\x{0d} + \r\r\r\=PP + 0: \x{0d}\x{0d} + +/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/B,utf +------------------------------------------------------------------ + Bra + [^\x{100}] + [^\x{1234}] + [^\x{ffff}] + [^\x{10000}] + [^\x{10ffff}] + Ket + End +------------------------------------------------------------------ + +/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/Bi,utf +------------------------------------------------------------------ + Bra + /i [^\x{100}] + /i [^\x{1234}] + /i [^\x{ffff}] + /i [^\x{10000}] + /i [^\x{10ffff}] + Ket + End +------------------------------------------------------------------ + +/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/B,utf +------------------------------------------------------------------ + Bra + [^\x{100}]* + [^\x{10000}]+ + [^\x{10ffff}]?? + [^\x{8000}]{4} + [^\x{8000}]* + [^\x{7fff}]{2} + [^\x{7fff}]{0,7}? + [^\x{fffff}]{5} + [^\x{fffff}]?+ + Ket + End +------------------------------------------------------------------ + +/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/Bi,utf +------------------------------------------------------------------ + Bra + /i [^\x{100}]* + /i [^\x{10000}]+ + /i [^\x{10ffff}]?? + /i [^\x{8000}]{4} + /i [^\x{8000}]* + /i [^\x{7fff}]{2} + /i [^\x{7fff}]{0,7}? + /i [^\x{fffff}]{5} + /i [^\x{fffff}]?+ + Ket + End +------------------------------------------------------------------ + +/(?<=\x{1234}\x{1234})\bxy/I,utf +Capturing subpattern count = 0 +Max lookbehind = 2 +Options: utf +First code unit = 'x' +Last code unit = 'y' +Subject length lower bound = 2 + +/(?= 0xd800 && <= 0xdfff) + +/^a+[a\x{200}]/B,utf +------------------------------------------------------------------ + 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]/B,utf +------------------------------------------------------------------ + 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 +------------------------------------------------------------------ + +/[\p{L}]/IB +------------------------------------------------------------------ + Bra + [\p{L}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first code unit +No last code unit +Subject length lower bound = 1 + +/[\p{^L}]/IB +------------------------------------------------------------------ + Bra + [\P{L}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first code unit +No last code unit +Subject length lower bound = 1 + +/[\P{L}]/IB +------------------------------------------------------------------ + Bra + [\P{L}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first code unit +No last code unit +Subject length lower bound = 1 + +/[\P{^L}]/IB +------------------------------------------------------------------ + Bra + [\p{L}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first code unit +No last code unit +Subject length lower bound = 1 + +/[abc\p{L}\x{0660}]/IB,utf +------------------------------------------------------------------ + Bra + [a-c\p{L}\x{660}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +No first code unit +No last code unit +Subject length lower bound = 1 + +/[\p{Nd}]/IB,utf +------------------------------------------------------------------ + Bra + [\p{Nd}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +No first code unit +No last code unit +Subject length lower bound = 1 + 1234 + 0: 1 + +/[\p{Nd}+-]+/IB,utf +------------------------------------------------------------------ + Bra + [+\-\p{Nd}]++ + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf +No first code unit +No last code unit +Subject length lower bound = 1 + 1234 + 0: 1234 + 12-34 + 0: 12-34 + 12+\x{661}-34 + 0: 12+\x{661}-34 + ** Failers +No match + abcd +No match + +/(?:[\PPa*]*){8,}/ + +/[\P{Any}]/B +------------------------------------------------------------------ + Bra + [\P{Any}] + Ket + End +------------------------------------------------------------------ + +/[\P{Any}\E]/B +------------------------------------------------------------------ + Bra + [\P{Any}] + Ket + End +------------------------------------------------------------------ + +/(\P{Yi}+\277)/ + +/(\P{Yi}+\277)?/ + +/(?<=\P{Yi}{3}A)X/ + +/\p{Yi}+(\P{Yi}+)(?1)/ + +/(\P{Yi}{2}\277)?/ + +/[\P{Yi}A]/ + +/[\P{Yi}\P{Yi}\P{Yi}A]/ + +/[^\P{Yi}A]/ + +/[^\P{Yi}\P{Yi}\P{Yi}A]/ + +/(\P{Yi}*\277)*/ + +/(\P{Yi}*?\277)*/ + +/(\p{Yi}*+\277)*/ + +/(\P{Yi}?\277)*/ + +/(\P{Yi}??\277)*/ + +/(\p{Yi}?+\277)*/ + +/(\P{Yi}{0,3}\277)*/ + +/(\P{Yi}{0,3}?\277)*/ + +/(\p{Yi}{0,3}+\277)*/ + +/\p{Zl}{2,3}+/B,utf +------------------------------------------------------------------ + Bra + prop Zl {2} + prop Zl ?+ + Ket + End +------------------------------------------------------------------ + 

 + 0: \x{2028}\x{2028} + \x{2028}\x{2028}\x{2028} + 0: \x{2028}\x{2028}\x{2028} + +/\p{Zl}/B,utf +------------------------------------------------------------------ + Bra + prop Zl + Ket + End +------------------------------------------------------------------ + +/\p{Lu}{3}+/B,utf +------------------------------------------------------------------ + Bra + prop Lu {3} + Ket + End +------------------------------------------------------------------ + +/\pL{2}+/B,utf +------------------------------------------------------------------ + Bra + prop L {2} + Ket + End +------------------------------------------------------------------ + +/\p{Cc}{2}+/B,utf +------------------------------------------------------------------ + Bra + prop Cc {2} + Ket + End +------------------------------------------------------------------ + +/^\p{Cf}/utf + \x{180e} + 0: \x{180e} + \x{061c} + 0: \x{61c} + \x{2066} + 0: \x{2066} + \x{2067} + 0: \x{2067} + \x{2068} + 0: \x{2068} + \x{2069} + 0: \x{2069} + +/^\p{Cs}/utf + \x{dfff}\=no_utf_check + 0: \x{dfff} + ** Failers +No match + \x{09f} +No match + +/^\p{Mn}/utf + \x{1a1b} + 0: \x{1a1b} + +/^\p{Pe}/utf + \x{2309} + 0: \x{2309} + \x{230b} + 0: \x{230b} + +/^\p{Ps}/utf + \x{2308} + 0: \x{2308} + \x{230a} + 0: \x{230a} + +/^\p{Sc}+/utf + $\x{a2}\x{a3}\x{a4}\x{a5}\x{a6} + 0: $\x{a2}\x{a3}\x{a4}\x{a5} + \x{9f2} + 0: \x{9f2} + ** Failers +No match + X +No match + \x{2c2} +No match + +/^\p{Zs}/utf + \ \ + 0: + \x{a0} + 0: \x{a0} + \x{1680} + 0: \x{1680} + \x{2000} + 0: \x{2000} + \x{2001} + 0: \x{2001} + ** Failers +No match + \x{2028} +No match + \x{200d} +No match + +# These are here rather than in test 6 because Perl has problems with +# the negative versions of the properties and behaves has changed how +# it behaves for caseless matching. + +/\p{^Lu}/i,utf + 1234 + 0: 1 + ** Failers + 0: * + ABC +No match + +/\P{Lu}/i,utf + 1234 + 0: 1 + ** Failers + 0: * + ABC +No match + +/\p{Ll}/i,utf + a + 0: a + Az + 0: z + ** Failers + 0: a + ABC +No match + +/\p{Lu}/i,utf + A + 0: A + a\x{10a0}B + 0: \x{10a0} + ** Failers + 0: F + a +No match + \x{1d00} +No match + +/\p{Lu}/i,utf + A + 0: A + aZ + 0: Z + ** Failers + 0: F + abc +No match + +/[\x{c0}\x{391}]/i,utf + \x{c0} + 0: \x{c0} + \x{e0} + 0: \x{e0} + +# The next two are special cases where the lengths of the different cases of +# the same character differ. The first went wrong with heap frame storage; the +# second was broken in all cases. + +/^\x{023a}+?(\x{0130}+)/i,utf + \x{023a}\x{2c65}\x{0130} + 0: \x{23a}\x{2c65}\x{130} + 1: \x{130} + +/^\x{023a}+([^X])/i,utf + \x{023a}\x{2c65}X + 0: \x{23a}\x{2c65} + 1: \x{2c65} + +/\x{c0}+\x{116}+/i,utf + \x{c0}\x{e0}\x{116}\x{117} + 0: \x{c0}\x{e0}\x{116}\x{117} + +/[\x{c0}\x{116}]+/i,utf + \x{c0}\x{e0}\x{116}\x{117} + 0: \x{c0}\x{e0}\x{116}\x{117} + +/(\x{de})\1/i,utf + \x{de}\x{de} + 0: \x{de}\x{de} + 1: \x{de} + \x{de}\x{fe} + 0: \x{de}\x{fe} + 1: \x{de} + \x{fe}\x{fe} + 0: \x{fe}\x{fe} + 1: \x{fe} + \x{fe}\x{de} + 0: \x{fe}\x{de} + 1: \x{fe} + +/^\x{c0}$/i,utf + \x{c0} + 0: \x{c0} + \x{e0} + 0: \x{e0} + +/^\x{e0}$/i,utf + \x{c0} + 0: \x{c0} + \x{e0} + 0: \x{e0} + +# The next two should be Perl-compatible, but it fails to match \x{e0}. PCRE +# will match it only with UCP support, because without that it has no notion +# of case for anything other than the ASCII letters. + +/((?i)[\x{c0}])/utf + \x{c0} + 0: \x{c0} + 1: \x{c0} + \x{e0} + 0: \x{e0} + 1: \x{e0} + +/(?i:[\x{c0}])/utf + \x{c0} + 0: \x{c0} + \x{e0} + 0: \x{e0} + +# These are PCRE's extra properties to help with Unicodizing \d etc. + +/^\p{Xan}/utf + ABCD + 0: A + 1234 + 0: 1 + \x{6ca} + 0: \x{6ca} + \x{a6c} + 0: \x{a6c} + \x{10a7} + 0: \x{10a7} + ** Failers +No match + _ABC +No match + +/^\p{Xan}+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7} + ** Failers +No match + _ABC +No match + +/^\p{Xan}+?/utf + \x{6ca}\x{a6c}\x{10a7}_ + 0: \x{6ca} + +/^\p{Xan}*/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7} + +/^\p{Xan}{2,9}/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca} + +/^\p{Xan}{2,9}?/utf + \x{6ca}\x{a6c}\x{10a7}_ + 0: \x{6ca}\x{a6c} + +/^[\p{Xan}]/utf + ABCD1234_ + 0: A + 1234abcd_ + 0: 1 + \x{6ca} + 0: \x{6ca} + \x{a6c} + 0: \x{a6c} + \x{10a7} + 0: \x{10a7} + ** Failers +No match + _ABC +No match + +/^[\p{Xan}]+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7} + ** Failers +No match + _ABC +No match + +/^>\p{Xsp}/utf + >\x{1680}\x{2028}\x{0b} + 0: >\x{1680} + >\x{a0} + 0: >\x{a0} + ** Failers +No match + \x{0b} +No match + +/^>\p{Xsp}+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}+?/utf + >\x{1680}\x{2028}\x{0b} + 0: >\x{1680} + +/^>\p{Xsp}*/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}{2,9}/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xsp}{2,9}?/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09} + +/^>[\p{Xsp}]/utf + >\x{2028}\x{0b} + 0: >\x{2028} + +/^>[\p{Xsp}]+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}/utf + >\x{1680}\x{2028}\x{0b} + 0: >\x{1680} + >\x{a0} + 0: >\x{a0} + ** Failers +No match + \x{0b} +No match + +/^>\p{Xps}+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}+?/utf + >\x{1680}\x{2028}\x{0b} + 0: >\x{1680} + +/^>\p{Xps}*/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}?/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09} + +/^>[\p{Xps}]/utf + >\x{2028}\x{0b} + 0: >\x{2028} + +/^>[\p{Xps}]+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^\p{Xwd}/utf + ABCD + 0: A + 1234 + 0: 1 + \x{6ca} + 0: \x{6ca} + \x{a6c} + 0: \x{a6c} + \x{10a7} + 0: \x{10a7} + _ABC + 0: _ + ** Failers +No match + [] +No match + +/^\p{Xwd}+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}+?/utf + \x{6ca}\x{a6c}\x{10a7}_ + 0: \x{6ca} + +/^\p{Xwd}*/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}{2,9}/utf + A_B12\x{6ca}\x{a6c}\x{10a7} + 0: A_B12\x{6ca}\x{a6c}\x{10a7} + +/^\p{Xwd}{2,9}?/utf + \x{6ca}\x{a6c}\x{10a7}_ + 0: \x{6ca}\x{a6c} + +/^[\p{Xwd}]/utf + ABCD1234_ + 0: A + 1234abcd_ + 0: 1 + \x{6ca} + 0: \x{6ca} + \x{a6c} + 0: \x{a6c} + \x{10a7} + 0: \x{10a7} + _ABC + 0: _ + ** Failers +No match + [] +No match + +/^[\p{Xwd}]+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +# A check not in UTF-8 mode + +/^[\p{Xwd}]+/ + ABCD1234_ + 0: ABCD1234_ + +# Some negative checks + +/^[\P{Xwd}]+/utf + !.+\x{019}\x{35a}AB + 0: !.+\x{19}\x{35a} + +/^[\p{^Xwd}]+/utf + !.+\x{019}\x{35a}AB + 0: !.+\x{19}\x{35a} + +/[\D]/B,utf,ucp +------------------------------------------------------------------ + Bra + [\P{Nd}] + Ket + End +------------------------------------------------------------------ + 1\x{3c8}2 + 0: \x{3c8} + +/[\d]/B,utf,ucp +------------------------------------------------------------------ + Bra + [\p{Nd}] + Ket + End +------------------------------------------------------------------ + >\x{6f4}< + 0: \x{6f4} + +/[\S]/B,utf,ucp +------------------------------------------------------------------ + Bra + [\P{Xsp}] + Ket + End +------------------------------------------------------------------ + \x{1680}\x{6f4}\x{1680} + 0: \x{6f4} + +/[\s]/B,utf,ucp +------------------------------------------------------------------ + Bra + [\p{Xsp}] + Ket + End +------------------------------------------------------------------ + >\x{1680}< + 0: \x{1680} + +/[\W]/B,utf,ucp +------------------------------------------------------------------ + Bra + [\P{Xwd}] + Ket + End +------------------------------------------------------------------ + A\x{1712}B + 0: \x{1712} + +/[\w]/B,utf,ucp +------------------------------------------------------------------ + Bra + [\p{Xwd}] + Ket + End +------------------------------------------------------------------ + >\x{1723}< + 0: \x{1723} + +/\D/B,utf,ucp +------------------------------------------------------------------ + Bra + notprop Nd + Ket + End +------------------------------------------------------------------ + 1\x{3c8}2 + 0: \x{3c8} + +/\d/B,utf,ucp +------------------------------------------------------------------ + Bra + prop Nd + Ket + End +------------------------------------------------------------------ + >\x{6f4}< + 0: \x{6f4} + +/\S/B,utf,ucp +------------------------------------------------------------------ + Bra + notprop Xsp + Ket + End +------------------------------------------------------------------ + \x{1680}\x{6f4}\x{1680} + 0: \x{6f4} + +/\s/B,utf,ucp +------------------------------------------------------------------ + Bra + prop Xsp + Ket + End +------------------------------------------------------------------ + >\x{1680}> + 0: \x{1680} + +/\W/B,utf,ucp +------------------------------------------------------------------ + Bra + notprop Xwd + Ket + End +------------------------------------------------------------------ + A\x{1712}B + 0: \x{1712} + +/\w/B,utf,ucp +------------------------------------------------------------------ + Bra + prop Xwd + Ket + End +------------------------------------------------------------------ + >\x{1723}< + 0: \x{1723} + +/[[:alpha:]]/B,ucp +------------------------------------------------------------------ + Bra + [\p{L}] + Ket + End +------------------------------------------------------------------ + +/[[:lower:]]/B,ucp +------------------------------------------------------------------ + Bra + [\p{Ll}] + Ket + End +------------------------------------------------------------------ + +/[[:upper:]]/B,ucp +------------------------------------------------------------------ + Bra + [\p{Lu}] + Ket + End +------------------------------------------------------------------ + +/[[:alnum:]]/B,ucp +------------------------------------------------------------------ + Bra + [\p{Xan}] + Ket + End +------------------------------------------------------------------ + +/[[:ascii:]]/B,ucp +------------------------------------------------------------------ + Bra + [\x00-\x7f] + Ket + End +------------------------------------------------------------------ + +/[[:cntrl:]]/B,ucp +------------------------------------------------------------------ + Bra + [\x00-\x1f\x7f] + Ket + End +------------------------------------------------------------------ + +/[[:digit:]]/B,ucp +------------------------------------------------------------------ + Bra + [\p{Nd}] + Ket + End +------------------------------------------------------------------ + +/[[:graph:]]/B,ucp +------------------------------------------------------------------ + Bra + [[:graph:]] + Ket + End +------------------------------------------------------------------ + +/[[:print:]]/B,ucp +------------------------------------------------------------------ + Bra + [[:print:]] + Ket + End +------------------------------------------------------------------ + +/[[:punct:]]/B,ucp +------------------------------------------------------------------ + Bra + [[:punct:]] + Ket + End +------------------------------------------------------------------ + +/[[:space:]]/B,ucp +------------------------------------------------------------------ + Bra + [\p{Xps}] + Ket + End +------------------------------------------------------------------ + +/[[:word:]]/B,ucp +------------------------------------------------------------------ + Bra + [\p{Xwd}] + Ket + End +------------------------------------------------------------------ + +/[[:xdigit:]]/B,ucp +------------------------------------------------------------------ + Bra + [0-9A-Fa-f] + Ket + End +------------------------------------------------------------------ + +# Unicode properties for \b abd \B + +/\b...\B/utf,ucp + abc_ + 0: abc + \x{37e}abc\x{376} + 0: abc + \x{37e}\x{376}\x{371}\x{393}\x{394} + 0: \x{376}\x{371}\x{393} + !\x{c0}++\x{c1}\x{c2} + 0: ++\x{c1} + !\x{c0}+++++ + 0: \x{c0}++ + +# Without PCRE_UCP, non-ASCII always fail, even if < 256 + +/\b...\B/utf + abc_ + 0: abc + ** Failers + 0: Fai + \x{37e}abc\x{376} +No match + \x{37e}\x{376}\x{371}\x{393}\x{394} +No match + !\x{c0}++\x{c1}\x{c2} +No match + !\x{c0}+++++ +No match + +# With PCRE_UCP, non-UTF8 chars that are < 256 still check properties + +/\b...\B/ucp + abc_ + 0: abc + !\x{c0}++\x{c1}\x{c2} + 0: ++\xc1 + !\x{c0}+++++ + 0: \xc0++ + +# Some of these are silly, but they check various combinations + +/[[:^alpha:][:^cntrl:]]+/B,utf,ucp +------------------------------------------------------------------ + Bra + [ -~\x80-\xff\P{L}]++ + Ket + End +------------------------------------------------------------------ + 123 + 0: 123 + abc + 0: abc + +/[[:^cntrl:][:^alpha:]]+/B,utf,ucp +------------------------------------------------------------------ + Bra + [ -~\x80-\xff\P{L}]++ + Ket + End +------------------------------------------------------------------ + 123 + 0: 123 + abc + 0: abc + +/[[:alpha:]]+/B,utf,ucp +------------------------------------------------------------------ + Bra + [\p{L}]++ + Ket + End +------------------------------------------------------------------ + abc + 0: abc + +/[[:^alpha:]\S]+/B,utf,ucp +------------------------------------------------------------------ + Bra + [\P{L}\P{Xsp}]++ + Ket + End +------------------------------------------------------------------ + 123 + 0: 123 + abc + 0: abc + +/[^\d]+/B,utf,ucp +------------------------------------------------------------------ + Bra + [^\p{Nd}]++ + Ket + End +------------------------------------------------------------------ + abc123 + 0: abc + abc\x{123} + 0: abc\x{123} + \x{660}abc + 0: abc + +/\p{Lu}+9\p{Lu}+B\p{Lu}+b/B +------------------------------------------------------------------ + Bra + prop Lu ++ + 9 + prop Lu + + B + prop Lu ++ + b + Ket + End +------------------------------------------------------------------ + +/\p{^Lu}+9\p{^Lu}+B\p{^Lu}+b/B +------------------------------------------------------------------ + Bra + notprop Lu + + 9 + notprop Lu ++ + B + notprop Lu + + b + Ket + End +------------------------------------------------------------------ + +/\P{Lu}+9\P{Lu}+B\P{Lu}+b/B +------------------------------------------------------------------ + Bra + notprop Lu + + 9 + notprop Lu ++ + B + notprop Lu + + b + Ket + End +------------------------------------------------------------------ + +/\p{Han}+X\p{Greek}+\x{370}/B,utf +------------------------------------------------------------------ + Bra + prop Han ++ + X + prop Greek + + \x{370} + Ket + End +------------------------------------------------------------------ + +/\p{Xan}+!\p{Xan}+A/B +------------------------------------------------------------------ + Bra + prop Xan ++ + ! + prop Xan + + A + Ket + End +------------------------------------------------------------------ + +/\p{Xsp}+!\p{Xsp}\t/B +------------------------------------------------------------------ + Bra + prop Xsp ++ + ! + prop Xsp + \x09 + Ket + End +------------------------------------------------------------------ + +/\p{Xps}+!\p{Xps}\t/B +------------------------------------------------------------------ + Bra + prop Xps ++ + ! + prop Xps + \x09 + Ket + End +------------------------------------------------------------------ + +/\p{Xwd}+!\p{Xwd}_/B +------------------------------------------------------------------ + Bra + prop Xwd ++ + ! + prop Xwd + _ + Ket + End +------------------------------------------------------------------ + +/A+\p{N}A+\dB+\p{N}*B+\d*/B,ucp +------------------------------------------------------------------ + Bra + A++ + prop N + A++ + prop Nd + B+ + prop N *+ + B++ + prop Nd *+ + Ket + End +------------------------------------------------------------------ + +# These behaved oddly in Perl, so they are kept in this test + +/(\x{23a}\x{23a}\x{23a})?\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65} +No match + +/(ȺȺȺ)?\1/i,utf + ȺȺȺⱥⱥ +No match + +/(\x{23a}\x{23a}\x{23a})?\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + 1: \x{23a}\x{23a}\x{23a} + +/(ȺȺȺ)?\1/i,utf + ȺȺȺⱥⱥⱥ + 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + 1: \x{23a}\x{23a}\x{23a} + +/(\x{23a}\x{23a}\x{23a})\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65} +No match + +/(ȺȺȺ)\1/i,utf + ȺȺȺⱥⱥ +No match + +/(\x{23a}\x{23a}\x{23a})\1/i,utf + \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + 1: \x{23a}\x{23a}\x{23a} + +/(ȺȺȺ)\1/i,utf + ȺȺȺⱥⱥⱥ + 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65} + 1: \x{23a}\x{23a}\x{23a} + +/(\x{2c65}\x{2c65})\1/i,utf + \x{2c65}\x{2c65}\x{23a}\x{23a} + 0: \x{2c65}\x{2c65}\x{23a}\x{23a} + 1: \x{2c65}\x{2c65} + +/(ⱥⱥ)\1/i,utf + ⱥⱥȺȺ + 0: \x{2c65}\x{2c65}\x{23a}\x{23a} + 1: \x{2c65}\x{2c65} + +/(\x{23a}\x{23a}\x{23a})\1Y/i,utf + X\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}YZ + 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}Y + 1: \x{23a}\x{23a}\x{23a} + +/(\x{2c65}\x{2c65})\1Y/i,utf + X\x{2c65}\x{2c65}\x{23a}\x{23a}YZ + 0: \x{2c65}\x{2c65}\x{23a}\x{23a}Y + 1: \x{2c65}\x{2c65} + +# + +# These scripts weren't yet in Perl when I added Unicode 6.0.0 to PCRE + +/^[\p{Batak}]/utf + \x{1bc0} + 0: \x{1bc0} + \x{1bff} + 0: \x{1bff} + ** Failers +No match + \x{1bf4} +No match + +/^[\p{Brahmi}]/utf + \x{11000} + 0: \x{11000} + \x{1106f} + 0: \x{1106f} + ** Failers +No match + \x{1104e} +No match + +/^[\p{Mandaic}]/utf + \x{840} + 0: \x{840} + \x{85e} + 0: \x{85e} + ** Failers +No match + \x{85c} +No match + \x{85d} +No match + +# + +/(\X*)(.)/s,utf + A\x{300} + 0: A + 1: + 2: A + +/^S(\X*)e(\X*)$/utf + Stéréo + 0: Ste\x{301}re\x{301}o + 1: te\x{301}r + 2: \x{301}o + +/^\X/utf + ́réo + 0: \x{301} + +/^a\X41z/alt_bsux,allow_empty_class,match_unset_backref,dupnames + aX41z + 0: aX41z + *** Failers +No match + aAz +No match + +/(?<=ab\Cde)X/utf +Failed: error 136 at offset 10: \C is not allowed in a lookbehind assertion + +/\X/ + a\=P + 0: a + a\=PP +Partial match: a + +/\Xa/ + aa\=P + 0: aa + aa\=PP + 0: aa + +/\X{2}/ + aa\=P + 0: aa + aa\=PP +Partial match: aa + +/\X+a/ + a\=P +Partial match: a + aa\=P + 0: aa + aa\=PP +Partial match: aa + +/\X+?a/ + a\=P +Partial match: a + ab\=P +Partial match: ab + aa\=P + 0: aa + aa\=PP + 0: aa + aba\=P + 0: aba + +# These Unicode 6.1.0 scripts are not known to Perl. + +/\p{Chakma}\d/utf,ucp + \x{11100}\x{1113c} + 0: \x{11100}\x{1113c} + +/\p{Takri}\d/utf,ucp + \x{11680}\x{116c0} + 0: \x{11680}\x{116c0} + +/^\X/utf + A\=P + 0: A + A\=PP +Partial match: A + A\x{300}\x{301}\=P + 0: A\x{300}\x{301} + A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301} + A\x{301}\=P + 0: A\x{301} + A\x{301}\=PP +Partial match: A\x{301} + +/^\X{2,3}/utf + A\=P +Partial match: A + A\=PP +Partial match: A + AA\=P + 0: AA + AA\=PP +Partial match: AA + A\x{300}\x{301}\=P +Partial match: A\x{300}\x{301} + A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301} + A\x{300}\x{301}A\x{300}\x{301}\=P + 0: A\x{300}\x{301}A\x{300}\x{301} + A\x{300}\x{301}A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301}A\x{300}\x{301} + +/^\X{2}/utf + AA\=P + 0: AA + AA\=PP +Partial match: AA + A\x{300}\x{301}A\x{300}\x{301}\=P + 0: A\x{300}\x{301}A\x{300}\x{301} + A\x{300}\x{301}A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301}A\x{300}\x{301} + +/^\X+/utf + AA\=P + 0: AA + AA\=PP +Partial match: AA + +/^\X+?Z/utf + AA\=P +Partial match: AA + AA\=PP +Partial match: AA + +/A\x{3a3}B/IBi,utf +------------------------------------------------------------------ + Bra + /i A + clist 03a3 03c2 03c3 + /i B + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: caseless utf +First code unit = 'A' (caseless) +Last code unit = 'B' (caseless) +Subject length lower bound = 3 + +/[\x{3a3}]/Bi,utf +------------------------------------------------------------------ + Bra + clist 03a3 03c2 03c3 + Ket + End +------------------------------------------------------------------ + +/[^\x{3a3}]/Bi,utf +------------------------------------------------------------------ + Bra + not clist 03a3 03c2 03c3 + Ket + End +------------------------------------------------------------------ + +/[\x{3a3}]+/Bi,utf +------------------------------------------------------------------ + Bra + clist 03a3 03c2 03c3 ++ + Ket + End +------------------------------------------------------------------ + +/[^\x{3a3}]+/Bi,utf +------------------------------------------------------------------ + Bra + not clist 03a3 03c2 03c3 ++ + Ket + End +------------------------------------------------------------------ + +/a*\x{3a3}/Bi,utf +------------------------------------------------------------------ + Bra + /i a*+ + clist 03a3 03c2 03c3 + Ket + End +------------------------------------------------------------------ + +/\x{3a3}+a/Bi,utf +------------------------------------------------------------------ + Bra + clist 03a3 03c2 03c3 ++ + /i a + Ket + End +------------------------------------------------------------------ + +/\x{3a3}*\x{3c2}/Bi,utf +------------------------------------------------------------------ + Bra + clist 03a3 03c2 03c3 * + clist 03a3 03c2 03c3 + Ket + End +------------------------------------------------------------------ + +/\x{3a3}{3}/i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + 0: \x{3a3}\x{3c3}\x{3c2} + 0+ \x{3a3}\x{3c3}\x{3c2} + +/\x{3a3}{2,4}/i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + 0: \x{3a3}\x{3c3}\x{3c2}\x{3a3} + 0+ \x{3c3}\x{3c2} + +/\x{3a3}{2,4}?/i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + 0: \x{3a3}\x{3c3} + 0+ \x{3c2}\x{3a3}\x{3c3}\x{3c2} + +/\x{3a3}+./i,utf,aftertext + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + 0: \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} + 0+ + +/\x{3a3}++./i,utf,aftertext + ** Failers +No match + \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2} +No match + +/\x{3a3}*\x{3c2}/Bi,utf +------------------------------------------------------------------ + Bra + clist 03a3 03c2 03c3 * + clist 03a3 03c2 03c3 + Ket + End +------------------------------------------------------------------ + +/[^\x{3a3}]*\x{3c2}/Bi,utf +------------------------------------------------------------------ + Bra + not clist 03a3 03c2 03c3 *+ + clist 03a3 03c2 03c3 + Ket + End +------------------------------------------------------------------ + +/[^a]*\x{3c2}/Bi,utf +------------------------------------------------------------------ + Bra + /i [^a]* + clist 03a3 03c2 03c3 + Ket + End +------------------------------------------------------------------ + +/ist/Bi,utf +------------------------------------------------------------------ + Bra + /i i + clist 0053 0073 017f + /i t + Ket + End +------------------------------------------------------------------ + ikt +No match + +/is+t/i,utf + iSs\x{17f}t + 0: iSs\x{17f}t + ikt +No match + +/is+?t/i,utf + ikt +No match + +/is?t/i,utf + ikt +No match + +/is{2}t/i,utf + iskt +No match + +# This property is a PCRE special + +/^\p{Xuc}/utf + $abc + 0: $ + @abc + 0: @ + `abc + 0: ` + \x{1234}abc + 0: \x{1234} + ** Failers +No match + abc +No match + +/^\p{Xuc}+/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000} + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}+?/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $ + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}+?\*/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000}* + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}++/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000} + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}{3,5}/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234} + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}{3,5}?/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@` + ** Failers +No match + \x{9f} +No match + +/^[\p{Xuc}]/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $ + ** Failers +No match + \x{9f} +No match + +/^[\p{Xuc}]+/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000} + ** Failers +No match + \x{9f} +No match + +/^\P{Xuc}/utf + abc + 0: a + ** Failers + 0: * + $abc +No match + @abc +No match + `abc +No match + \x{1234}abc +No match + +/^[\P{Xuc}]/utf + abc + 0: a + ** Failers + 0: * + $abc +No match + @abc +No match + `abc +No match + \x{1234}abc +No match + +# Some auto-possessification tests + +/\pN+\z/B +------------------------------------------------------------------ + Bra + prop N ++ + \z + Ket + End +------------------------------------------------------------------ + +/\PN+\z/B +------------------------------------------------------------------ + Bra + notprop N ++ + \z + Ket + End +------------------------------------------------------------------ + +/\pN+/B +------------------------------------------------------------------ + Bra + prop N ++ + Ket + End +------------------------------------------------------------------ + +/\PN+/B +------------------------------------------------------------------ + Bra + notprop N ++ + Ket + End +------------------------------------------------------------------ + +/\p{Any}+\p{Any} \p{Any}+\P{Any} \p{Any}+\p{L&} \p{Any}+\p{L} \p{Any}+\p{Lu} \p{Any}+\p{Han} \p{Any}+\p{Xan} \p{Any}+\p{Xsp} \p{Any}+\p{Xps} \p{Xwd}+\p{Any} \p{Any}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Any + + prop Any + prop Any + + notprop Any + prop Any + + prop L& + prop Any + + prop L + prop Any + + prop Lu + prop Any + + prop Han + prop Any + + prop Xan + prop Any + + prop Xsp + prop Any + + prop Xps + prop Xwd + + prop Any + prop Any + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{L&}+\p{Any} \p{L&}+\p{L&} \P{L&}+\p{L&} \p{L&}+\p{L} \p{L&}+\p{Lu} \p{L&}+\p{Han} \p{L&}+\p{Xan} \p{L&}+\P{Xan} \p{L&}+\p{Xsp} \p{L&}+\p{Xps} \p{Xwd}+\p{L&} \p{L&}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop L& + + prop Any + prop L& + + prop L& + notprop L& ++ + prop L& + prop L& + + prop L + prop L& + + prop Lu + prop L& + + prop Han + prop L& + + prop Xan + prop L& ++ + notprop Xan + prop L& ++ + prop Xsp + prop L& ++ + prop Xps + prop Xwd + + prop L& + prop L& + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{N}+\p{Any} \p{N}+\p{L&} \p{N}+\p{L} \p{N}+\P{L} \p{N}+\P{N} \p{N}+\p{Lu} \p{N}+\p{Han} \p{N}+\p{Xan} \p{N}+\p{Xsp} \p{N}+\p{Xps} \p{Xwd}+\p{N} \p{N}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop N + + prop Any + prop N + + prop L& + prop N ++ + prop L + prop N + + notprop L + prop N ++ + notprop N + prop N ++ + prop Lu + prop N + + prop Han + prop N + + prop Xan + prop N ++ + prop Xsp + prop N ++ + prop Xps + prop Xwd + + prop N + prop N + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{Lu}+\p{Any} \p{Lu}+\p{L&} \p{Lu}+\p{L} \p{Lu}+\p{Lu} \P{Lu}+\p{Lu} \p{Lu}+\p{Nd} \p{Lu}+\P{Nd} \p{Lu}+\p{Han} \p{Lu}+\p{Xan} \p{Lu}+\p{Xsp} \p{Lu}+\p{Xps} \p{Xwd}+\p{Lu} \p{Lu}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Lu + + prop Any + prop Lu + + prop L& + prop Lu + + prop L + prop Lu + + prop Lu + notprop Lu ++ + prop Lu + prop Lu ++ + prop Nd + prop Lu + + notprop Nd + prop Lu + + prop Han + prop Lu + + prop Xan + prop Lu ++ + prop Xsp + prop Lu ++ + prop Xps + prop Xwd + + prop Lu + prop Lu + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{Han}+\p{Lu} \p{Han}+\p{L&} \p{Han}+\p{L} \p{Han}+\p{Lu} \p{Han}+\p{Arabic} \p{Arabic}+\p{Arabic} \p{Han}+\p{Xan} \p{Han}+\p{Xsp} \p{Han}+\p{Xps} \p{Xwd}+\p{Han} \p{Han}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Han + + prop Lu + prop Han + + prop L& + prop Han + + prop L + prop Han + + prop Lu + prop Han ++ + prop Arabic + prop Arabic + + prop Arabic + prop Han + + prop Xan + prop Han + + prop Xsp + prop Han + + prop Xps + prop Xwd + + prop Han + prop Han + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{Xan}+\p{Any} \p{Xan}+\p{L&} \P{Xan}+\p{L&} \p{Xan}+\p{L} \p{Xan}+\p{Lu} \p{Xan}+\p{Han} \p{Xan}+\p{Xan} \p{Xan}+\P{Xan} \p{Xan}+\p{Xsp} \p{Xan}+\p{Xps} \p{Xwd}+\p{Xan} \p{Xan}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xan + + prop Any + prop Xan + + prop L& + notprop Xan ++ + prop L& + prop Xan + + prop L + prop Xan + + prop Lu + prop Xan + + prop Han + prop Xan + + prop Xan + prop Xan ++ + notprop Xan + prop Xan ++ + prop Xsp + prop Xan ++ + prop Xps + prop Xwd + + prop Xan + prop Xan + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{Xsp}+\p{Any} \p{Xsp}+\p{L&} \p{Xsp}+\p{L} \p{Xsp}+\p{Lu} \p{Xsp}+\p{Han} \p{Xsp}+\p{Xan} \p{Xsp}+\p{Xsp} \P{Xsp}+\p{Xsp} \p{Xsp}+\p{Xps} \p{Xwd}+\p{Xsp} \p{Xsp}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xsp + + prop Any + prop Xsp ++ + prop L& + prop Xsp ++ + prop L + prop Xsp ++ + prop Lu + prop Xsp + + prop Han + prop Xsp ++ + prop Xan + prop Xsp + + prop Xsp + notprop Xsp ++ + prop Xsp + prop Xsp + + prop Xps + prop Xwd ++ + prop Xsp + prop Xsp + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{Xwd}+\p{Any} \p{Xwd}+\p{L&} \p{Xwd}+\p{L} \p{Xwd}+\p{Lu} \p{Xwd}+\p{Han} \p{Xwd}+\p{Xan} \p{Xwd}+\p{Xsp} \p{Xwd}+\p{Xps} \p{Xwd}+\p{Xwd} \p{Xwd}+\P{Xwd} \p{Xwd}+\p{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xwd + + prop Any + prop Xwd + + prop L& + prop Xwd + + prop L + prop Xwd + + prop Lu + prop Xwd + + prop Han + prop Xwd + + prop Xan + prop Xwd ++ + prop Xsp + prop Xwd ++ + prop Xps + prop Xwd + + prop Xwd + prop Xwd ++ + notprop Xwd + prop Xwd + + prop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{Xuc}+\p{Any} \p{Xuc}+\p{L&} \p{Xuc}+\p{L} \p{Xuc}+\p{Lu} \p{Xuc}+\p{Han} \p{Xuc}+\p{Xan} \p{Xuc}+\p{Xsp} \p{Xuc}+\p{Xps} \p{Xwd}+\p{Xuc} \p{Xuc}+\p{Xuc} \p{Xuc}+\P{Xuc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xuc + + prop Any + prop Xuc + + prop L& + prop Xuc + + prop L + prop Xuc + + prop Lu + prop Xuc + + prop Han + prop Xuc + + prop Xan + prop Xuc + + prop Xsp + prop Xuc + + prop Xps + prop Xwd + + prop Xuc + prop Xuc + + prop Xuc + prop Xuc ++ + notprop Xuc + Ket + End +------------------------------------------------------------------ + +/\p{N}+\p{Ll} \p{N}+\p{Nd} \p{N}+\P{Nd}/Bx,ucp +------------------------------------------------------------------ + Bra + prop N ++ + prop Ll + prop N + + prop Nd + prop N + + notprop Nd + Ket + End +------------------------------------------------------------------ + +/\p{Xan}+\p{L} \p{Xan}+\p{N} \p{Xan}+\p{C} \p{Xan}+\P{L} \P{Xan}+\p{N} \p{Xan}+\P{C}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xan + + prop L + prop Xan + + prop N + prop Xan ++ + prop C + prop Xan + + notprop L + notprop Xan ++ + prop N + prop Xan + + notprop C + Ket + End +------------------------------------------------------------------ + +/\p{L}+\p{Xan} \p{N}+\p{Xan} \p{C}+\p{Xan} \P{L}+\p{Xan} \p{N}+\p{Xan} \P{C}+\p{Xan} \p{L}+\P{Xan}/Bx,ucp +------------------------------------------------------------------ + Bra + prop L + + prop Xan + prop N + + prop Xan + prop C ++ + prop Xan + notprop L + + prop Xan + prop N + + prop Xan + notprop C + + prop Xan + prop L ++ + notprop Xan + Ket + End +------------------------------------------------------------------ + +/\p{Xan}+\p{Lu} \p{Xan}+\p{Nd} \p{Xan}+\p{Cc} \p{Xan}+\P{Ll} \P{Xan}+\p{No} \p{Xan}+\P{Cf}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xan + + prop Lu + prop Xan + + prop Nd + prop Xan ++ + prop Cc + prop Xan + + notprop Ll + notprop Xan ++ + prop No + prop Xan + + notprop Cf + Ket + End +------------------------------------------------------------------ + +/\p{Lu}+\p{Xan} \p{Nd}+\p{Xan} \p{Cs}+\p{Xan} \P{Lt}+\p{Xan} \p{Nl}+\p{Xan} \P{Cc}+\p{Xan} \p{Lt}+\P{Xan}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Lu + + prop Xan + prop Nd + + prop Xan + prop Cs ++ + prop Xan + notprop Lt + + prop Xan + prop Nl + + prop Xan + notprop Cc + + prop Xan + prop Lt ++ + notprop Xan + Ket + End +------------------------------------------------------------------ + +/\w+\p{P} \w+\p{Po} \w+\s \p{Xan}+\s \s+\p{Xan} \s+\w/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xwd + + prop P + prop Xwd + + prop Po + prop Xwd ++ + prop Xsp + prop Xan ++ + prop Xsp + prop Xsp ++ + prop Xan + prop Xsp ++ + prop Xwd + Ket + End +------------------------------------------------------------------ + +/\w+\P{P} \W+\p{Po} \w+\S \P{Xan}+\s \s+\P{Xan} \s+\W/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xwd + + notprop P + notprop Xwd + + prop Po + prop Xwd + + notprop Xsp + notprop Xan + + prop Xsp + prop Xsp + + notprop Xan + prop Xsp + + notprop Xwd + Ket + End +------------------------------------------------------------------ + +/\w+\p{Po} \w+\p{Pc} \W+\p{Po} \W+\p{Pc} \w+\P{Po} \w+\P{Pc}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xwd + + prop Po + prop Xwd ++ + prop Pc + notprop Xwd + + prop Po + notprop Xwd + + prop Pc + prop Xwd + + notprop Po + prop Xwd + + notprop Pc + Ket + End +------------------------------------------------------------------ + +/\p{Nl}+\p{Xan} \P{Nl}+\p{Xan} \p{Nl}+\P{Xan} \P{Nl}+\P{Xan}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Nl + + prop Xan + notprop Nl + + prop Xan + prop Nl ++ + notprop Xan + notprop Nl + + notprop Xan + Ket + End +------------------------------------------------------------------ + +/\p{Xan}+\p{Nl} \P{Xan}+\p{Nl} \p{Xan}+\P{Nl} \P{Xan}+\P{Nl}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xan + + prop Nl + notprop Xan ++ + prop Nl + prop Xan + + notprop Nl + notprop Xan + + notprop Nl + Ket + End +------------------------------------------------------------------ + +/\p{Xan}+\p{Nd} \P{Xan}+\p{Nd} \p{Xan}+\P{Nd} \P{Xan}+\P{Nd}/Bx,ucp +------------------------------------------------------------------ + Bra + prop Xan + + prop Nd + notprop Xan ++ + prop Nd + prop Xan + + notprop Nd + notprop Xan + + notprop Nd + Ket + End +------------------------------------------------------------------ + +# End auto-possessification tests + +/\w+/B,utf,ucp,auto_callout +------------------------------------------------------------------ + Bra + Callout 255 0 3 + prop Xwd ++ + Callout 255 3 0 + Ket + End +------------------------------------------------------------------ + abcd +--->abcd + +0 ^ \w+ + +3 ^ ^ + 0: abcd + +/[\p{N}]?+/B,no_auto_possess +------------------------------------------------------------------ + Bra + [\p{N}]?+ + Ket + End +------------------------------------------------------------------ + +/[\p{L}ab]{2,3}+/B,no_auto_possess +------------------------------------------------------------------ + Bra + [ab\p{L}]{2,3}+ + Ket + End +------------------------------------------------------------------ + +/\D+\X \d+\X \S+\X \s+\X \W+\X \w+\X \C+\X \R+\X \H+\X \h+\X \V+\X \v+\X a+\X \n+\X .+\X/Bx +------------------------------------------------------------------ + Bra + \D+ + extuni + \d+ + extuni + \S+ + extuni + \s+ + extuni + \W+ + extuni + \w+ + extuni + AllAny+ + extuni + \R+ + extuni + \H+ + extuni + \h+ + extuni + \V+ + extuni + \v+ + extuni + a+ + extuni + \x0a+ + extuni + Any+ + extuni + Ket + End +------------------------------------------------------------------ + +/.+\X/Bsx +------------------------------------------------------------------ + Bra + AllAny+ + extuni + Ket + End +------------------------------------------------------------------ + +/\X+$/Bmx +------------------------------------------------------------------ + Bra + extuni+ + /m $ + Ket + End +------------------------------------------------------------------ + +/\X+\D \X+\d \X+\S \X+\s \X+\W \X+\w \X+. \X+\C \X+\R \X+\H \X+\h \X+\V \X+\v \X+\X \X+\Z \X+\z \X+$/Bx +------------------------------------------------------------------ + Bra + extuni+ + \D + extuni+ + \d + extuni+ + \S + extuni+ + \s + extuni+ + \W + extuni+ + \w + extuni+ + Any + extuni+ + AllAny + extuni+ + \R + extuni+ + \H + extuni+ + \h + extuni+ + \V + extuni+ + \v + extuni+ + extuni + extuni+ + \Z + extuni++ + \z + extuni+ + $ + Ket + End +------------------------------------------------------------------ + +/\d+\s{0,5}=\s*\S?=\w{0,4}\W*/B,utf,ucp +------------------------------------------------------------------ + Bra + prop Nd ++ + prop Xsp {0,5}+ + = + prop Xsp *+ + notprop Xsp ? + = + prop Xwd {0,4}+ + notprop Xwd *+ + Ket + End +------------------------------------------------------------------ + +/[RST]+/Bi,utf,ucp +------------------------------------------------------------------ + Bra + [R-Tr-t\x{17f}]++ + Ket + End +------------------------------------------------------------------ + +/[R-T]+/Bi,utf,ucp +------------------------------------------------------------------ + Bra + [R-Tr-t\x{17f}]++ + Ket + End +------------------------------------------------------------------ + +/[Q-U]+/Bi,utf,ucp +------------------------------------------------------------------ + Bra + [Q-Uq-u\x{17f}]++ + Ket + End +------------------------------------------------------------------ + +/^s?c/Iim,utf +Capturing subpattern count = 0 +Options: caseless multiline utf +First code unit at start or follows newline +Last code unit = 'c' (caseless) +Subject length lower bound = 1 + scat + 0: sc + +# End of testinput5 diff --git a/testdata/testoutput6 b/testdata/testoutput6 new file mode 100644 index 0000000..520e734 --- /dev/null +++ b/testdata/testoutput6 @@ -0,0 +1,7669 @@ +# This set of tests check the DFA matching functionality of pcre2_dfa_match(), +# excluding UTF and Unicode property support. All matches are done using DFA, +# forced by setting a default subject modifier at the start. + +#forbid_utf +#subject dfa + +/abc/ + abc + 0: abc + +/ab*c/ + abc + 0: abc + abbbbc + 0: abbbbc + ac + 0: ac + +/ab+c/ + abc + 0: abc + abbbbbbc + 0: abbbbbbc + *** Failers +No match + ac +No match + ab +No match + +/a*/no_auto_possess + a + 0: a + 1: + aaaaaaaaaaaaaaaaa +Matched, but offsets vector is too small to show all matches + 0: aaaaaaaaaaaaaaaaa + 1: aaaaaaaaaaaaaaaa + 2: aaaaaaaaaaaaaaa + 3: aaaaaaaaaaaaaa + 4: aaaaaaaaaaaaa + 5: aaaaaaaaaaaa + 6: aaaaaaaaaaa + 7: aaaaaaaaaa + 8: aaaaaaaaa + 9: aaaaaaaa +10: aaaaaaa +11: aaaaaa +12: aaaaa +13: aaaa +14: aaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\=ovector=10 +Matched, but offsets vector is too small to show all matches + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaa + 3: aaaaaaaaaaaaaaaaaaaaaaaaaaa + 4: aaaaaaaaaaaaaaaaaaaaaaaaaa + 5: aaaaaaaaaaaaaaaaaaaaaaaaa + 6: aaaaaaaaaaaaaaaaaaaaaaaa + 7: aaaaaaaaaaaaaaaaaaaaaaa + 8: aaaaaaaaaaaaaaaaaaaaaa + 9: aaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\=dfa_shortest + 0: + +/(a|abcd|african)/ + a + 0: a + abcd + 0: abcd + 1: a + african + 0: african + 1: a + +/^abc/ + abcdef + 0: abc + *** Failers +No match + xyzabc +No match + xyz\nabc +No match + +/^abc/m + abcdef + 0: abc + xyz\nabc + 0: abc + *** Failers +No match + xyzabc +No match + +/\Aabc/ + abcdef + 0: abc + *** Failers +No match + xyzabc +No match + xyz\nabc +No match + +/\Aabc/m + abcdef + 0: abc + *** Failers +No match + xyzabc +No match + xyz\nabc +No match + +/\Gabc/ + abcdef + 0: abc + xyzabc\=offset=3 + 0: abc + *** Failers +No match + xyzabc +No match + xyzabc\=offset=2 +No match + +/x\dy\Dz/ + x9yzz + 0: x9yzz + x0y+z + 0: x0y+z + *** Failers +No match + xyz +No match + xxy0z +No match + +/x\sy\Sz/ + x yzz + 0: x yzz + x y+z + 0: x y+z + *** Failers +No match + xyz +No match + xxyyz +No match + +/x\wy\Wz/ + xxy+z + 0: xxy+z + *** Failers +No match + xxy0z +No match + x+y+z +No match + +/x.y/ + x+y + 0: x+y + x-y + 0: x-y + *** Failers +No match + x\ny +No match + +/x.y/s + x+y + 0: x+y + x-y + 0: x-y + x\ny + 0: x\x0ay + +/(a.b(?s)c.d|x.y)p.q/ + a+bc+dp+q + 0: a+bc+dp+q + a+bc\ndp+q + 0: a+bc\x0adp+q + x\nyp+q + 0: x\x0ayp+q + *** Failers +No match + a\nbc\ndp+q +No match + a+bc\ndp\nq +No match + x\nyp\nq +No match + +/a\d\z/ + ba0 + 0: a0 + *** Failers +No match + ba0\n +No match + ba0\ncd +No match + +/a\d\z/m + ba0 + 0: a0 + *** Failers +No match + ba0\n +No match + ba0\ncd +No match + +/a\d\Z/ + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d\Z/m + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d$/ + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d$/m + ba0 + 0: a0 + ba0\n + 0: a0 + ba0\ncd + 0: a0 + *** Failers +No match + +/abc/i + abc + 0: abc + aBc + 0: aBc + ABC + 0: ABC + +/[^a]/ + abcd + 0: b + +/ab?\w/ + abz + 0: abz + 1: ab + abbz + 0: abb + 1: ab + azz + 0: az + +/x{0,3}yz/ + ayzq + 0: yz + axyzq + 0: xyz + axxyz + 0: xxyz + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + +/x{3}yz/ + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + ayzq +No match + axyzq +No match + axxyz +No match + +/x{2,3}yz/ + axxyz + 0: xxyz + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + ayzq +No match + axyzq +No match + +/[^a]+/no_auto_possess + bac + 0: b + bcdefax + 0: bcdef + 1: bcde + 2: bcd + 3: bc + 4: b + *** Failers + 0: *** F + 1: *** + 2: *** + 3: ** + 4: * + aaaaa +No match + +/[^a]*/no_auto_possess + bac + 0: b + 1: + bcdefax + 0: bcdef + 1: bcde + 2: bcd + 3: bc + 4: b + 5: + *** Failers + 0: *** F + 1: *** + 2: *** + 3: ** + 4: * + 5: + aaaaa + 0: + +/[^a]{3,5}/no_auto_possess + xyz + 0: xyz + awxyza + 0: wxyz + 1: wxy + abcdefa + 0: bcdef + 1: bcde + 2: bcd + abcdefghijk + 0: bcdef + 1: bcde + 2: bcd + *** Failers + 0: *** F + 1: *** + 2: *** + axya +No match + axa +No match + aaaaa +No match + +/\d*/ + 1234b567 + 0: 1234 + xyz + 0: + +/\D*/ + a1234b567 + 0: a + xyz + 0: xyz + +/\d+/ + ab1234c56 + 0: 1234 + *** Failers +No match + xyz +No match + +/\D+/ + ab123c56 + 0: ab + *** Failers + 0: *** Failers + 789 +No match + +/\d?A/ + 045ABC + 0: 5A + ABC + 0: A + *** Failers +No match + XYZ +No match + +/\D?A/ + ABC + 0: A + BAC + 0: BA + 9ABC + 0: A + *** Failers +No match + +/a+/ + aaaa + 0: aaaa + +/^.*xyz/ + xyz + 0: xyz + ggggggggxyz + 0: ggggggggxyz + +/^.+xyz/ + abcdxyz + 0: abcdxyz + axyz + 0: axyz + *** Failers +No match + xyz +No match + +/^.?xyz/ + xyz + 0: xyz + cxyz + 0: cxyz + +/^\d{2,3}X/ + 12X + 0: 12X + 123X + 0: 123X + *** Failers +No match + X +No match + 1X +No match + 1234X +No match + +/^[abcd]\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + *** Failers +No match + e45 +No match + abcd +No match + abcd1234 +No match + 1234 +No match + +/^[abcd]*\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + abcd1234 + 0: abcd1 + 1234 + 0: 1 + *** Failers +No match + e45 +No match + abcd +No match + +/^[abcd]+\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + abcd1234 + 0: abcd1 + *** Failers +No match + 1234 +No match + e45 +No match + abcd +No match + +/^a+X/ + aX + 0: aX + aaX + 0: aaX + +/^[abcd]?\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + 1234 + 0: 1 + *** Failers +No match + abcd1234 +No match + e45 +No match + +/^[abcd]{2,3}\d/ + ab45 + 0: ab4 + bcd93 + 0: bcd9 + *** Failers +No match + 1234 +No match + a36 +No match + abcd1234 +No match + ee45 +No match + +/^(abc)*\d/ + abc45 + 0: abc4 + abcabcabc45 + 0: abcabcabc4 + 42xyz + 0: 4 + *** Failers +No match + +/^(abc)+\d/ + abc45 + 0: abc4 + abcabcabc45 + 0: abcabcabc4 + *** Failers +No match + 42xyz +No match + +/^(abc)?\d/ + abc45 + 0: abc4 + 42xyz + 0: 4 + *** Failers +No match + abcabcabc45 +No match + +/^(abc){2,3}\d/ + abcabc45 + 0: abcabc4 + abcabcabc45 + 0: abcabcabc4 + *** Failers +No match + abcabcabcabc45 +No match + abc45 +No match + 42xyz +No match + +/1(abc|xyz)2(?1)3/ + 1abc2abc3456 + 0: 1abc2abc3 + 1abc2xyz3456 + 0: 1abc2xyz3 + +/^(a*\w|ab)=(a*\w|ab)/ + ab=ab + 0: ab=ab + 1: ab=a + +/^(a*\w|ab)=(?1)/ + ab=ab + 0: ab=ab + 1: ab=a + +/^([^()]|\((?1)*\))*$/ + abc + 0: abc + a(b)c + 0: a(b)c + a(b(c))d + 0: a(b(c))d + *** Failers) +No match + a(b(c)d +No match + +/^>abc>([^()]|\((?1)*\))*abc>123abc>123abc>1(2)3abc>1(2)3abc>(1(2)3)abc>(1(2)3)a*)\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9 + *** Failers +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x + <> + 0: <> + + 0: + hij> + 0: hij> + hij> + 0: + def> + 0: def> + + 0: <> + *** Failers +No match + abcxyz + 1 ^ ^ x + 0: abcxyz + 123abcxyz999 +--->123abcxyz999 + 1 ^ ^ x + 0: abcxyz + +/(ab|cd){3,4}/auto_callout + ababab +--->ababab + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + 0: ababab + abcdabcd +--->abcdabcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdabcd + 1: abcdab + abcdcdcdcdcd +--->abcdcdcdcdcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdcdcd + 1: abcdcd + +/^abc/ + abcdef + 0: abc + *** Failers +No match + abcdef\=notbol +No match + +/^(a*|xyz)/ + bcd + 0: + aaabcd + 0: aaa + xyz + 0: xyz + 1: + xyz\=notempty + 0: xyz + *** Failers + 0: + bcd\=notempty +No match + +/xyz$/ + xyz + 0: xyz + xyz\n + 0: xyz + *** Failers +No match + xyz\=noteol +No match + xyz\n\=noteol +No match + +/xyz$/m + xyz + 0: xyz + xyz\n + 0: xyz + abcxyz\npqr + 0: xyz + abcxyz\npqr\=noteol + 0: xyz + xyz\n\=noteol + 0: xyz + *** Failers +No match + xyz\=noteol +No match + +/\Gabc/ + abcdef + 0: abc + defabcxyz\=offset=3 + 0: abc + *** Failers +No match + defabcxyz +No match + +/^abcdef/ + ab\=P +Partial match: ab + abcde\=P +Partial match: abcde + abcdef\=P + 0: abcdef + *** Failers +No match + abx\=P +No match + +/^a{2,4}\d+z/ + a\=P +Partial match: a + aa\=P +Partial match: aa + aa2\=P +Partial match: aa2 + aaa\=P +Partial match: aaa + aaa23\=P +Partial match: aaa23 + aaaa12345\=P +Partial match: aaaa12345 + aa0z\=P + 0: aa0z + aaaa4444444444444z\=P + 0: aaaa4444444444444z + *** Failers +No match + az\=P +No match + aaaaa\=P +No match + a56\=P +No match + +/^abcdef/ + abc\=P +Partial match: abc + def\=dfa_restart + 0: def + +/(?<=foo)bar/ + xyzfo\=P +No match + foob\=P,offset=2 +Partial match at offset 3: foob + foobar...\=P,dfa_restart,offset=4 + 0: ar + xyzfo\=P +No match + foobar\=offset=2 + 0: bar + *** Failers +No match + xyzfo\=P +No match + obar\=dfa_restart +No match + +/(ab*(cd|ef))+X/ + adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\=P,noteol +No match + lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\=P,notbol,noteol +Partial match: abbbbbbcdaefabbbbbbbefa + cdabbbbbbbb\=P,notbol,dfa_restart,noteol +Partial match: cdabbbbbbbb + efabbbbbbbbbbbbbbbb\=P,notbol,dfa_restart,noteol +Partial match: efabbbbbbbbbbbbbbbb + bbbbbbbbbbbbcdXyasdfadf\=P,notbol,dfa_restart,noteol + 0: bbbbbbbbbbbbcdX + +/the quick brown fox/ + the quick brown fox + 0: the quick brown fox + The quick brown FOX +No match + What do you know about the quick brown fox? + 0: the quick brown fox + What do you know about THE QUICK BROWN FOX? +No match + +/The quick brown fox/i + the quick brown fox + 0: the quick brown fox + The quick brown FOX + 0: The quick brown FOX + What do you know about the quick brown fox? + 0: the quick brown fox + What do you know about THE QUICK BROWN FOX? + 0: THE QUICK BROWN FOX + +/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/ + abcd\t\n\r\f\a\e9;\$\\?caxyz + 0: abcd\x09\x0a\x0d\x0c\x07\x1b9;$\?caxyz + +/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/ + abxyzpqrrrabbxyyyypqAzz + 0: abxyzpqrrrabbxyyyypqAzz + abxyzpqrrrabbxyyyypqAzz + 0: abxyzpqrrrabbxyyyypqAzz + aabxyzpqrrrabbxyyyypqAzz + 0: aabxyzpqrrrabbxyyyypqAzz + aaabxyzpqrrrabbxyyyypqAzz + 0: aaabxyzpqrrrabbxyyyypqAzz + aaaabxyzpqrrrabbxyyyypqAzz + 0: aaaabxyzpqrrrabbxyyyypqAzz + abcxyzpqrrrabbxyyyypqAzz + 0: abcxyzpqrrrabbxyyyypqAzz + aabcxyzpqrrrabbxyyyypqAzz + 0: aabcxyzpqrrrabbxyyyypqAzz + aaabcxyzpqrrrabbxyyyypAzz + 0: aaabcxyzpqrrrabbxyyyypAzz + aaabcxyzpqrrrabbxyyyypqAzz + 0: aaabcxyzpqrrrabbxyyyypqAzz + aaabcxyzpqrrrabbxyyyypqqAzz + 0: aaabcxyzpqrrrabbxyyyypqqAzz + aaabcxyzpqrrrabbxyyyypqqqAzz + 0: aaabcxyzpqrrrabbxyyyypqqqAzz + aaabcxyzpqrrrabbxyyyypqqqqAzz + 0: aaabcxyzpqrrrabbxyyyypqqqqAzz + aaabcxyzpqrrrabbxyyyypqqqqqAzz + 0: aaabcxyzpqrrrabbxyyyypqqqqqAzz + aaabcxyzpqrrrabbxyyyypqqqqqqAzz + 0: aaabcxyzpqrrrabbxyyyypqqqqqqAzz + aaaabcxyzpqrrrabbxyyyypqAzz + 0: aaaabcxyzpqrrrabbxyyyypqAzz + abxyzzpqrrrabbxyyyypqAzz + 0: abxyzzpqrrrabbxyyyypqAzz + aabxyzzzpqrrrabbxyyyypqAzz + 0: aabxyzzzpqrrrabbxyyyypqAzz + aaabxyzzzzpqrrrabbxyyyypqAzz + 0: aaabxyzzzzpqrrrabbxyyyypqAzz + aaaabxyzzzzpqrrrabbxyyyypqAzz + 0: aaaabxyzzzzpqrrrabbxyyyypqAzz + abcxyzzpqrrrabbxyyyypqAzz + 0: abcxyzzpqrrrabbxyyyypqAzz + aabcxyzzzpqrrrabbxyyyypqAzz + 0: aabcxyzzzpqrrrabbxyyyypqAzz + aaabcxyzzzzpqrrrabbxyyyypqAzz + 0: aaabcxyzzzzpqrrrabbxyyyypqAzz + aaaabcxyzzzzpqrrrabbxyyyypqAzz + 0: aaaabcxyzzzzpqrrrabbxyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyyypqAzz + 0: aaaabcxyzzzzpqrrrabbbxyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyyyypqAzz + 0: aaaabcxyzzzzpqrrrabbbxyyyyypqAzz + aaabcxyzpqrrrabbxyyyypABzz + 0: aaabcxyzpqrrrabbxyyyypABzz + aaabcxyzpqrrrabbxyyyypABBzz + 0: aaabcxyzpqrrrabbxyyyypABBzz + >>>aaabxyzpqrrrabbxyyyypqAzz + 0: aaabxyzpqrrrabbxyyyypqAzz + >aaaabxyzpqrrrabbxyyyypqAzz + 0: aaaabxyzpqrrrabbxyyyypqAzz + >>>>abcxyzpqrrrabbxyyyypqAzz + 0: abcxyzpqrrrabbxyyyypqAzz + *** Failers +No match + abxyzpqrrabbxyyyypqAzz +No match + abxyzpqrrrrabbxyyyypqAzz +No match + abxyzpqrrrabxyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyypqAzz +No match + aaabcxyzpqrrrabbxyyyypqqqqqqqAzz +No match + +/^(abc){1,2}zz/ + abczz + 0: abczz + abcabczz + 0: abcabczz + *** Failers +No match + zz +No match + abcabcabczz +No match + >>abczz +No match + +/^(b+?|a){1,2}?c/ + bc + 0: bc + bbc + 0: bbc + bbbc + 0: bbbc + bac + 0: bac + bbac + 0: bbac + aac + 0: aac + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}c/ + bc + 0: bc + bbc + 0: bbc + bbbc + 0: bbbc + bac + 0: bac + bbac + 0: bbac + aac + 0: aac + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}?bc/ + bbc + 0: bbc + +/^(b*|ba){1,2}?bc/ + babc + 0: babc + bbabc + 0: bbabc + bababc + 0: bababc + *** Failers +No match + bababbc +No match + babababc +No match + +/^(ba|b*){1,2}?bc/ + babc + 0: babc + bbabc + 0: bbabc + bababc + 0: bababc + *** Failers +No match + bababbc +No match + babababc +No match + +/^\ca\cA\c[\c{\c:/ + \x01\x01\e;z + 0: \x01\x01\x1b;z + +/^[ab\]cde]/ + athing + 0: a + bthing + 0: b + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + fthing +No match + [thing +No match + \\thing +No match + +/^[]cde]/ + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + athing +No match + fthing +No match + +/^[^ab\]cde]/ + fthing + 0: f + [thing + 0: [ + \\thing + 0: \ + *** Failers + 0: * + athing +No match + bthing +No match + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^[^]cde]/ + athing + 0: a + fthing + 0: f + *** Failers + 0: * + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^\/ + + 0: \x81 + +/^/ + + 0: \xff + +/^[0-9]+$/ + 0 + 0: 0 + 1 + 0: 1 + 2 + 0: 2 + 3 + 0: 3 + 4 + 0: 4 + 5 + 0: 5 + 6 + 0: 6 + 7 + 0: 7 + 8 + 0: 8 + 9 + 0: 9 + 10 + 0: 10 + 100 + 0: 100 + *** Failers +No match + abc +No match + +/^.*nter/ + enter + 0: enter + inter + 0: inter + uponter + 0: uponter + +/^xxx[0-9]+$/ + xxx0 + 0: xxx0 + xxx1234 + 0: xxx1234 + *** Failers +No match + xxx +No match + +/^.+[0-9][0-9][0-9]$/ + x123 + 0: x123 + xx123 + 0: xx123 + 123456 + 0: 123456 + *** Failers +No match + 123 +No match + x1234 + 0: x1234 + +/^.+?[0-9][0-9][0-9]$/ + x123 + 0: x123 + xx123 + 0: xx123 + 123456 + 0: 123456 + *** Failers +No match + 123 +No match + x1234 + 0: x1234 + +/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ + abc!pqr=apquxz.ixr.zzz.ac.uk + 0: abc!pqr=apquxz.ixr.zzz.ac.uk + *** Failers +No match + !pqr=apquxz.ixr.zzz.ac.uk +No match + abc!=apquxz.ixr.zzz.ac.uk +No match + abc!pqr=apquxz:ixr.zzz.ac.uk +No match + abc!pqr=apquxz.ixr.zzz.ac.ukk +No match + +/:/ + Well, we need a colon: somewhere + 0: : + *** Fail if we don't +No match + +/([\da-f:]+)$/i + 0abc + 0: 0abc + abc + 0: abc + fed + 0: fed + E + 0: E + :: + 0: :: + 5f03:12C0::932e + 0: 5f03:12C0::932e + fed def + 0: def + Any old stuff + 0: ff + *** Failers +No match + 0zzz +No match + gzzz +No match + fed\x20 +No match + Any old rubbish +No match + +/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ + .1.2.3 + 0: .1.2.3 + A.12.123.0 + 0: A.12.123.0 + *** Failers +No match + .1.2.3333 +No match + 1.2.3 +No match + 1234.2.3 +No match + +/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ + 1 IN SOA non-sp1 non-sp2( + 0: 1 IN SOA non-sp1 non-sp2( + 1 IN SOA non-sp1 non-sp2 ( + 0: 1 IN SOA non-sp1 non-sp2 ( + *** Failers +No match + 1IN SOA non-sp1 non-sp2( +No match + +/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ + a. + 0: a. + Z. + 0: Z. + 2. + 0: 2. + ab-c.pq-r. + 0: ab-c.pq-r. + sxk.zzz.ac.uk. + 0: sxk.zzz.ac.uk. + x-.y-. + 0: x-.y-. + *** Failers +No match + -abc.peq. +No match + +/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ + *.a + 0: *.a + *.b0-a + 0: *.b0-a + *.c3-b.c + 0: *.c3-b.c + *.c-a.b-c + 0: *.c-a.b-c + *** Failers +No match + *.0 +No match + *.a- +No match + *.a-b.c- +No match + *.c-a.0-c +No match + +/^(?=ab(de))(abd)(e)/ + abde + 0: abde + +/^(?!(ab)de|x)(abd)(f)/ + abdf + 0: abdf + +/^(?=(ab(cd)))(ab)/ + abcd + 0: ab + +/^[\da-f](\.[\da-f])*$/i + a.b.c.d + 0: a.b.c.d + A.B.C.D + 0: A.B.C.D + a.b.c.1.2.3.C + 0: a.b.c.1.2.3.C + +/^\".*\"\s*(;.*)?$/ + \"1234\" + 0: "1234" + \"abcd\" ; + 0: "abcd" ; + \"\" ; rhubarb + 0: "" ; rhubarb + *** Failers +No match + \"1234\" : things +No match + +/^$/ + \ + 0: + *** Failers +No match + +/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/^ a\ b[c ]d $/x + a bcd + 0: a bcd + a b d + 0: a b d + *** Failers +No match + abcd +No match + ab d +No match + +/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + +/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + +/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ + a+ Z0+\x08\n\x1d\x12 + 0: a+ Z0+\x08\x0a\x1d\x12 + +/^[.^$|()*+?{,}]+/ + .^\$(*+)|{?,?} + 0: .^$(*+)|{?,?} + +/^a*\w/ + z + 0: z + az + 0: az + 1: a + aaaz + 0: aaaz + 1: aaa + 2: aa + 3: a + a + 0: a + aa + 0: aa + 1: a + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + a+ + 0: a + aa+ + 0: aa + 1: a + +/^a*?\w/ + z + 0: z + az + 0: az + 1: a + aaaz + 0: aaaz + 1: aaa + 2: aa + 3: a + a + 0: a + aa + 0: aa + 1: a + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + a+ + 0: a + aa+ + 0: aa + 1: a + +/^a+\w/ + az + 0: az + aaaz + 0: aaaz + 1: aaa + 2: aa + aa + 0: aa + aaaa + 0: aaaa + 1: aaa + 2: aa + aa+ + 0: aa + +/^a+?\w/ + az + 0: az + aaaz + 0: aaaz + 1: aaa + 2: aa + aa + 0: aa + aaaa + 0: aaaa + 1: aaa + 2: aa + aa+ + 0: aa + +/^\d{8}\w{2,}/ + 1234567890 + 0: 1234567890 + 12345678ab + 0: 12345678ab + 12345678__ + 0: 12345678__ + *** Failers +No match + 1234567 +No match + +/^[aeiou\d]{4,5}$/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 12345 + aaaaa + 0: aaaaa + *** Failers +No match + 123456 +No match + +/^[aeiou\d]{4,5}?/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 12345 + 1: 1234 + aaaaa + 0: aaaaa + 1: aaaa + 123456 + 0: 12345 + 1: 1234 + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + From abcd Mon Sep 1 12:33:02 1997 + 0: From abcd Mon Sep 1 12:33 + *** Failers +No match + From abcd Sep 01 12:33:02 1997 +No match + +/^12.34/s + 12\n34 + 0: 12\x0a34 + 12\r34 + 0: 12\x0d34 + +/\w+(?=\t)/ + the quick brown\t fox + 0: brown + +/foo(?!bar)(.*)/ + foobar is foolish see? + 0: foolish see? + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + 0: rowbar etc + barrel + 0: barrel + 2barrel + 0: 2barrel + A barrel + 0: A barrel + +/^(\D*)(?=\d)(?!123)/ + abc456 + 0: abc + *** Failers +No match + abc123 +No match + +/^1234(?# test newlines + inside)/ + 1234 + 0: 1234 + +/^1234 #comment in extended re + /x + 1234 + 0: 1234 + +/#rhubarb + abcd/x + abcd + 0: abcd + +/^abcd#rhubarb/x + abcd + 0: abcd + +/(?!^)abc/ + the abc + 0: abc + *** Failers +No match + abc +No match + +/(?=^)abc/ + abc + 0: abc + *** Failers +No match + the abc +No match + +/^[ab]{1,3}(ab*|b)/no_auto_possess + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}?(ab*|b)/no_auto_possess + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}?(ab*?|b)/no_auto_possess + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}(ab*?|b)/no_auto_possess + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + 0: Alan Other + + 0: user@dom.ain + 1: user@dom + user\@dom.ain + 0: user@dom.ain + 1: user@dom + \"A. Other\" (a comment) + 0: "A. Other" (a comment) + 1: "A. Other" + 2: "A. Other" + A. Other (a comment) + 0: Other (a comment) + 1: Other + 2: Other + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re + A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +# leading word +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces +(?: +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +| +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +) # "special" comment or quoted string +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" +)* +< +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# < +(?: +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +(?: , +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +)* # additional domains +: +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address spec +> # > +# name and address +) +/x + Alan Other + 0: Alan Other + + 0: user@dom.ain + 1: user@dom + user\@dom.ain + 0: user@dom.ain + 1: user@dom + \"A. Other\" (a comment) + 0: "A. Other" + A. Other (a comment) + 0: Other + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re + A missing angle ?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff + +/P[^*]TAIRE[^*]{1,6}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/P[^*]TAIRE[^*]{1,}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/(\.\d\d[1-9]?)\d+/ + 1.230003938 + 0: .230003938 + 1.875000282 + 0: .875000282 + 1.235 + 0: .235 + +/(\.\d\d((?=0)|\d(?=\d)))/ + 1.230003938 + 0: .230 + 1: .23 + 1.875000282 + 0: .875 + *** Failers +No match + 1.235 +No match + +/a(?)b/ + ab + 0: ab + +/\b(foo)\s+(\w+)/i + Food is on the foo table + 0: foo table + +/foo(.*)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: food is under the bar + +/foo(.*?)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: food is under the bar + +/(.*)(\d*)/no_auto_possess + I have 2 numbers: 53147 +Matched, but offsets vector is too small to show all matches + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 numbers: + 6: I have 2 numbers: + 7: I have 2 numbers + 8: I have 2 number + 9: I have 2 numbe +10: I have 2 numb +11: I have 2 num +12: I have 2 nu +13: I have 2 n +14: I have 2 + +/(.*)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 + +/(.*?)(\d*)/no_auto_possess + I have 2 numbers: 53147 +Matched, but offsets vector is too small to show all matches + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 numbers: + 6: I have 2 numbers: + 7: I have 2 numbers + 8: I have 2 number + 9: I have 2 numbe +10: I have 2 numb +11: I have 2 num +12: I have 2 nu +13: I have 2 n +14: I have 2 + +/(.*?)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 + +/(.*)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*?)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*)\b(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*\D)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/^\D*(?!123)/ + ABC123 + 0: AB + 1: A + 2: + +/^(\D*)(?=\d)(?!123)/ + ABC445 + 0: ABC + *** Failers +No match + ABC123 +No match + +/^[W-]46]/ + W46]789 + 0: W46] + -46]789 + 0: -46] + *** Failers +No match + Wall +No match + Zebra +No match + 42 +No match + [abcd] +No match + ]abcd[ +No match + +/^[W-\]46]/ + W46]789 + 0: W + Wall + 0: W + Zebra + 0: Z + Xylophone + 0: X + 42 + 0: 4 + [abcd] + 0: [ + ]abcd[ + 0: ] + \\backslash + 0: \ + *** Failers +No match + -46]789 +No match + well +No match + +/\d\d\/\d\d\/\d\d\d\d/ + 01/01/2000 + 0: 01/01/2000 + +/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/^(a){0,0}/ + bcd + 0: + abc + 0: + aab + 0: + +/^(a){0,1}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: a + 1: + +/^(a){0,2}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + +/^(a){0,3}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + aaa + 0: aaa + 1: aa + 2: a + 3: + +/^(a){0,}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + aaa + 0: aaa + 1: aa + 2: a + 3: + aaaaaaaa + 0: aaaaaaaa + 1: aaaaaaa + 2: aaaaaa + 3: aaaaa + 4: aaaa + 5: aaa + 6: aa + 7: a + 8: + +/^(a){1,1}/ + bcd +No match + abc + 0: a + aab + 0: a + +/^(a){1,2}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + +/^(a){1,3}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: aa + 2: a + +/^(a){1,}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: aa + 2: a + aaaaaaaa + 0: aaaaaaaa + 1: aaaaaaa + 2: aaaaaa + 3: aaaaa + 4: aaaa + 5: aaa + 6: aa + 7: a + +/.*\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.{0,}\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/m + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*\.gif/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*$/ + borfle\nbib.gif\nno + 0: no + +/.*$/m + borfle\nbib.gif\nno + 0: borfle + +/.*$/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + 1: borfle\x0abib.gif + 2: borfle + +/.*$/ + borfle\nbib.gif\nno\n + 0: no + +/.*$/m + borfle\nbib.gif\nno\n + 0: borfle + +/.*$/s + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + 1: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + 1: borfle\x0abib.gif\x0ano + 2: borfle\x0abib.gif + 3: borfle + +/(.*X|^B)/ + abcde\n1234Xyz + 0: 1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/m + abcde\n1234Xyz + 0: 1234X + BarFoo + 0: B + abcde\nBar + 0: B + +/(.*X|^B)/s + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/ms + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + abcde\nBar + 0: B + +/(?s)(.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(?s:.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/^.*B/ + **** Failers +No match + abc\nB +No match + +/(?s)^.*B/ + abc\nB + 0: abc\x0aB + +/(?m)^.*B/ + abc\nB + 0: B + +/(?ms)^.*B/ + abc\nB + 0: abc\x0aB + +/(?ms)^B/ + abc\nB + 0: B + +/(?s)B$/ + B\n + 0: B + +/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ + 123456654321 + 0: 123456654321 + +/^\d\d\d\d\d\d\d\d\d\d\d\d/ + 123456654321 + 0: 123456654321 + +/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ + 123456654321 + 0: 123456654321 + +/^[abc]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[a-c]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^(a|b|c){12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[abcdefghijklmnopqrstuvwxy0123456789]/ + n + 0: n + *** Failers +No match + z +No match + +/abcde{0,0}/ + abcd + 0: abcd + *** Failers +No match + abce +No match + +/ab[cd]{0,0}e/ + abe + 0: abe + *** Failers +No match + abcde +No match + +/ab(c){0,0}d/ + abd + 0: abd + *** Failers +No match + abcd +No match + +/a(b*)/ + a + 0: a + ab + 0: ab + abbbb + 0: abbbb + *** Failers + 0: a + bbbbb +No match + +/ab\d{0}e/ + abe + 0: abe + *** Failers +No match + ab1e +No match + +/"([^\\"]+|\\.)*"/ + the \"quick\" brown fox + 0: "quick" + \"the \\\"quick\\\" brown fox\" + 0: "the \"quick\" brown fox" + +/.*?/g,aftertext + abc + 0: abc + 0+ + 1: ab + 2: a + 3: + 0: + 0+ + +/\b/g,aftertext + abc + 0: + 0+ abc + 0: + 0+ + +/\b/g,aftertext + abc + 0: + 0+ abc + 0: + 0+ + +//g + abc + 0: + 0: + 0: + 0: + +/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + 0: 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/ + acb + 0: acb + *** Failers +No match + a\nb +No match + +/a[^a]b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/^(b+?|a){1,2}?c/ + bac + 0: bac + bbac + 0: bbac + bbbac + 0: bbbac + bbbbac + 0: bbbbac + bbbbbac + 0: bbbbbac + +/^(b+|a){1,2}?c/ + bac + 0: bac + bbac + 0: bbac + bbbac + 0: bbbac + bbbbac + 0: bbbbac + bbbbbac + 0: bbbbbac + +/(?!\A)x/m + x\nb\n +No match + a\bx\n + 0: x + +/\x0{ab}/ + \0{ab} + 0: \x00{ab} + +/(A|B)*?CD/ + CD + 0: CD + +/(A|B)*CD/ + CD + 0: CD + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ +No match + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 0: .230003938 + 1.875000282 + 0: .875000282 + *** Failers +No match + 1.235 +No match + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + 0: now is the time for all good men to come to the aid of the party + *** Failers +No match + this is not a line with only words and spaces! +No match + +/(\d+)(\w)/ + 12345a + 0: 12345a + 1: 12345 + 2: 1234 + 3: 123 + 4: 12 + 12345+ + 0: 12345 + 1: 1234 + 2: 123 + 3: 12 + +/((?>\d+))(\w)/ + 12345a + 0: 12345a + *** Failers +No match + 12345+ +No match + +/(?>a+)b/ + aaab + 0: aaab + +/((?>a+)b)/ + aaab + 0: aaab + +/(?>(a+))b/ + aaab + 0: aaab + +/(?>b)+/ + aaabbbccc + 0: bbb + 1: bb + 2: b + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbcccc + 1: aaabbbbc + +/(a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbcccc + 1: aaabbbbccc + 2: aaabbbbcc + 3: aaabbbbc + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: abc(ade)ufh()() + 2: abc(ade)ufh() + 3: abc(ade)ufh + 4: abc(ade) + 5: abc + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + 0: (abc) + (abc(def)xyz) + 0: (abc(def)xyz) + *** Failers +No match + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/a(?-i)b/i + ab + 0: ab + Ab + 0: Ab + *** Failers +No match + aB +No match + AB +No match + +/(a (?x)b c)d e/ + a bcd e + 0: a bcd e + *** Failers +No match + a b cd e +No match + abcd e +No match + a bcde +No match + +/(a b(?x)c d (?-x)e f)/ + a bcde f + 0: a bcde f + *** Failers +No match + abcdef +No match + +/(a(?i)b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + abC +No match + aBC +No match + Abc +No match + ABc +No match + ABC +No match + AbC +No match + +/a(?i:b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + ABC +No match + abC +No match + aBC +No match + +/a(?i:b)*c/ + aBc + 0: aBc + aBBc + 0: aBBc + *** Failers +No match + aBC +No match + aBBC +No match + +/a(?=b(?i)c)\w\wd/ + abcd + 0: abcd + abCd + 0: abCd + *** Failers +No match + aBCd +No match + abcD +No match + +/(?s-i:more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?:(?s-i)more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?>a(?i)b+)+c/ + abc + 0: abc + aBbc + 0: aBbc + aBBc + 0: aBBc + *** Failers +No match + Abc +No match + abAb +No match + abbC +No match + +/(?=a(?i)b)\w\wc/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + Ab +No match + abC +No match + aBC +No match + +/(?<=a(?i)b)(\w\w)c/ + abxxc + 0: xxc + aBxxc + 0: xxc + *** Failers +No match + Abxxc +No match + ABxxc +No match + abxxC +No match + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/(?(?<=foo)bar|cat)/ + foobar + 0: bar + cat + 0: cat + fcat + 0: cat + focat + 0: cat + *** Failers +No match + foocat +No match + +/(?(?a*)*/ + a + 0: a + 1: + aa + 0: aa + 1: + aaaa + 0: aaaa + 1: + +/(abc|)+/ + abc + 0: abc + 1: + abcabc + 0: abcabc + 1: abc + 2: + abcabcabc + 0: abcabcabc + 1: abcabc + 2: abc + 3: + xyz + 0: + +/([a]*)*/ + a + 0: a + 1: + aaaaa + 0: aaaaa + 1: aaaa + 2: aaa + 3: aa + 4: a + 5: + +/([ab]*)*/ + a + 0: a + 1: + b + 0: b + 1: + ababab + 0: ababab + 1: ababa + 2: abab + 3: aba + 4: ab + 5: a + 6: + aaaabcde + 0: aaaab + 1: aaaa + 2: aaa + 3: aa + 4: a + 5: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + +/([^a]*)*/ + b + 0: b + 1: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + aaa + 0: + +/([^ab]*)*/ + cccc + 0: cccc + 1: ccc + 2: cc + 3: c + 4: + abab + 0: + +/([a]*?)*/ + a + 0: a + 1: + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/([ab]*?)*/ + a + 0: a + 1: + b + 0: b + 1: + abab + 0: abab + 1: aba + 2: ab + 3: a + 4: + baba + 0: baba + 1: bab + 2: ba + 3: b + 4: + +/([^a]*?)*/ + b + 0: b + 1: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + aaa + 0: + +/([^ab]*?)*/ + c + 0: c + 1: + cccc + 0: cccc + 1: ccc + 2: cc + 3: c + 4: + baba + 0: + +/(?>a*)*/ + a + 0: a + 1: + aaabcde + 0: aaa + 1: + +/((?>a*))*/ + aaaaa + 0: aaaaa + 1: + aabbaa + 0: aa + 1: + +/((?>a*?))*/ + aaaaa + 0: aaaaa + 1: + aabbaa + 0: aa + 1: + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 0: 12-sep-98 + 12-09-98 + 0: 12-09-98 + *** Failers +No match + sep-12-98 +No match + +/(?i:saturday|sunday)/ + saturday + 0: saturday + sunday + 0: sunday + Saturday + 0: Saturday + Sunday + 0: Sunday + SATURDAY + 0: SATURDAY + SUNDAY + 0: SUNDAY + SunDay + 0: SunDay + +/(a(?i)bc|BB)x/ + abcx + 0: abcx + aBCx + 0: aBCx + bbx + 0: bbx + BBx + 0: BBx + *** Failers +No match + abcX +No match + aBCX +No match + bbX +No match + BBX +No match + +/^([ab](?i)[cd]|[ef])/ + ac + 0: ac + aC + 0: aC + bD + 0: bD + elephant + 0: e + Europe + 0: E + frog + 0: f + France + 0: F + *** Failers +No match + Africa +No match + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + 0: ab + aBd + 0: aBd + xy + 0: xy + xY + 0: xY + zebra + 0: z + Zambesi + 0: Z + *** Failers +No match + aCD +No match + XY +No match + +/(?<=foo\n)^bar/m + foo\nbar + 0: bar + *** Failers +No match + bar +No match + baz\nbar +No match + +/(?<=(?]&/ + <&OUT + 0: <& + +/(?:(f)(o)(o)|(b)(a)(r))*/ + foobar + 0: foobar + 1: foo + 2: + +/(?<=a)b/ + ab + 0: b + *** Failers +No match + cb +No match + b +No match + +/(?a+)ab/ + +/(?>a+)b/ + aaab + 0: aaab + +/([[:]+)/ + a:[b]: + 0: :[ + +/([[=]+)/ + a=[b]= + 0: =[ + +/([[.]+)/ + a.[b]. + 0: .[ + +/((?>a+)b)/ + aaab + 0: aaab + +/(?>(a+))b/ + aaab + 0: aaab + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: abc(ade)ufh()() + 2: abc(ade)ufh() + 3: abc(ade)ufh + 4: abc(ade) + 5: abc + +/a\Z/ + *** Failers +No match + aaab +No match + a\nb\n +No match + +/b\Z/ + a\nb\n + 0: b + +/b\z/ + +/b\Z/ + a\nb + 0: b + +/b\z/ + a\nb + 0: b + *** Failers +No match + +/(?>.*)(?<=(abcd|wxyz))/ + alphabetabcd + 0: alphabetabcd + endingwxyz + 0: endingwxyz + *** Failers +No match + a rather long string that doesn't end with one of them +No match + +/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/(?<=\d{3}(?!999))foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=(?!...999)\d{3})foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=\d{3}(?!999)...)foo/ + 123abcfoo + 0: foo + 123456foo + 0: foo + *** Failers +No match + 123999foo +No match + +/(?<=\d{3}...)(?Z)+|A)*/ + ZABCDEFG + 0: ZA + 1: Z + 2: + +/((?>)+|A)*/ + ZABCDEFG + 0: + +/a*/g + abbab + 0: a + 0: + 0: + 0: a + 0: + 0: + +/^[\d-a]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d\x0b + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09 + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d\x0b + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d\x0b + +/a b/x + ab + 0: ab + +/(?!\A)x/m + a\nxb\n + 0: x + +/(?!^)x/m + a\nxb\n +No match + +/abc\Qabc\Eabc/ + abcabcabc + 0: abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + 0: abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + 0: abc abcabc + *** Failers +No match + abcabcabc +No match + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + 0: abc\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + 0: abc$xyz + +/\Gabc/ + abc + 0: abc + *** Failers +No match + xyzabc +No match + +/\Gabc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + +/abc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + 0: abc3 + +/a(?x: b c )d/ + XabcdY + 0: abcd + *** Failers +No match + Xa b c d Y +No match + +/((?x)x y z | a b c)/ + XabcY + 0: abc + AxyzB + 0: xyz + +/(?i)AB(?-i)C/ + XabCY + 0: abC + *** Failers +No match + XabcY +No match + +/((?i)AB(?-i)C|D)E/ + abCE + 0: abCE + DE + 0: DE + *** Failers +No match + abcE +No match + abCe +No match + dE +No match + De +No match + +/[z\Qa-d]\E]/ + z + 0: z + a + 0: a + - + 0: - + d + 0: d + ] + 0: ] + *** Failers + 0: a + b +No match + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/(?i)reg(?:ul(?:[a]|ae)r|ex)/ + REGular + 0: REGular + regulaer + 0: regulaer + Regex + 0: Regex + regulr + 0: regul\xe4r + +/[--]+/ + + 0: \xc5\xe6\xe5\xe4\xe0 + + 0: \xc5\xe6\xe5\xe4\xff + + 0: \xc5\xe6\xe5\xe4\xc0 + + 0: \xc5\xe6\xe5\xe4\xdf + +/(?<=Z)X./ + \x84XAZXB + 0: XB + +/^(?(2)a|(1)(2))+$/ + 123a +Failed: error -40: backreference condition or recursion test not supported for DFA matching + +/(?<=a|bbbb)c/ + ac + 0: c + bbbbc + 0: c + +/line\nbreak/ + this is a line\nbreak + 0: line\x0abreak + line one\nthis is a line\nbreak in the second line + 0: line\x0abreak + +/line\nbreak/firstline + this is a line\nbreak + 0: line\x0abreak + ** Failers +No match + line one\nthis is a line\nbreak in the second line +No match + +/line\nbreak/m,firstline + this is a line\nbreak + 0: line\x0abreak + ** Failers +No match + line one\nthis is a line\nbreak in the second line +No match + +/1234/ + 123\=P +Partial match: 123 + a4\=P,dfa_restart +No match + +/1234/ + 123\=P +Partial match: 123 + 4\=P,dfa_restart + 0: 4 + +/^/gm + a\nb\nc\n + 0: + 0: + 0: + \ + 0: + +/(?<=C\n)^/gm + A\nC\nC\n + 0: + +/(?s)A?B/ + AB + 0: AB + aB + 0: B + +/(?s)A*B/ + AB + 0: AB + aB + 0: B + +/(?m)A?B/ + AB + 0: AB + aB + 0: B + +/(?m)A*B/ + AB + 0: AB + aB + 0: B + +/Content-Type\x3A[^\r\n]{6,}/ + Content-Type:xxxxxyyy + 0: Content-Type:xxxxxyyy + +/Content-Type\x3A[^\r\n]{6,}z/ + Content-Type:xxxxxyyyz + 0: Content-Type:xxxxxyyyz + +/Content-Type\x3A[^a]{6,}/ + Content-Type:xxxyyy + 0: Content-Type:xxxyyy + +/Content-Type\x3A[^a]{6,}z/ + Content-Type:xxxyyyz + 0: Content-Type:xxxyyyz + +/^abc/m + xyz\nabc + 0: abc + xyz\nabc\=newline=lf + 0: abc + xyz\r\nabc\=newline=lf + 0: abc + xyz\rabc\=newline=cr + 0: abc + xyz\r\nabc\=newline=crlf + 0: abc + ** Failers +No match + xyz\nabc\=newline=cr +No match + xyz\r\nabc\=newline=cr +No match + xyz\nabc\=newline=crlf +No match + xyz\rabc\=newline=crlf +No match + xyz\rabc\=newline=lf +No match + +/abc$/m,newline=lf + xyzabc + 0: abc + xyzabc\n + 0: abc + xyzabc\npqr + 0: abc + xyzabc\r\=newline=cr + 0: abc + xyzabc\rpqr\=newline=cr + 0: abc + xyzabc\r\n\=newline=crlf + 0: abc + xyzabc\r\npqr\=newline=crlf + 0: abc + ** Failers +No match + xyzabc\r +No match + xyzabc\rpqr +No match + xyzabc\r\n +No match + xyzabc\r\npqr +No match + +/^abc/m,newline=cr + xyz\rabcdef + 0: abc + xyz\nabcdef\=newline=lf + 0: abc + ** Failers +No match + xyz\nabcdef +No match + +/^abc/m,newline=lf + xyz\nabcdef + 0: abc + xyz\rabcdef\=newline=cr + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/^abc/m,newline=crlf + xyz\r\nabcdef + 0: abc + xyz\rabcdef\=newline=cr + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/.*/newline=lf + abc\ndef + 0: abc + abc\rdef + 0: abc\x0ddef + abc\r\ndef + 0: abc\x0d + abc\ndef\=newline=cr + 0: abc\x0adef + abc\rdef\=newline=cr + 0: abc + abc\r\ndef\=newline=cr + 0: abc + abc\ndef\=newline=crlf + 0: abc\x0adef + abc\rdef\=newline=crlf + 0: abc\x0ddef + abc\r\ndef\=newline=crlf + 0: abc + +/\w+(.)(.)?def/s + abc\ndef + 0: abc\x0adef + abc\rdef + 0: abc\x0ddef + abc\r\ndef + 0: abc\x0d\x0adef + +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + 0: abc=xyz\\x0apqr + 1: abc=xyz\\x0apq + 2: abc=xyz\\x0ap + 3: abc=xyz\\x0a + 4: abc=xyz\ + 5: abc=xyz + 6: abc=xy + 7: abc=x + 8: abc= + +/^(a()*)*/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/^(?:a(?:(?:))*)*/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/^(a()+)+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/^(?:a(?:(?:))+)+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/newline=lf + a\rb + 0: a\x0db + a\nb\=newline=cr + 0: a\x0ab + ** Failers +No match + a\nb +No match + a\nb\=newline=any +No match + a\rb\=newline=cr +No match + a\rb\=newline=any +No match + +/^abc./gmx,newline=any + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + +/abc.$/gmx,newline=any + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc9 + +/^a\Rb/bsr=unicode + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/bsr=unicode + ab + 0: ab + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + +/^a\R+b/bsr=unicode + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + ** Failers +No match + ab +No match + +/^a\R{1,3}b/bsr=unicode + a\nb + 0: a\x0ab + a\n\rb + 0: a\x0a\x0db + a\n\r\x85b + 0: a\x0a\x0d\x85b + a\r\n\r\nb + 0: a\x0d\x0a\x0d\x0ab + a\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0ab + a\n\r\n\rb + 0: a\x0a\x0d\x0a\x0db + a\n\n\r\nb + 0: a\x0a\x0a\x0d\x0ab + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/.+foo/ + afoo + 0: afoo + ** Failers +No match + \r\nfoo +No match + \nfoo +No match + +/.+foo/newline=crlf + afoo + 0: afoo + \nfoo + 0: \x0afoo + ** Failers +No match + \r\nfoo +No match + +/.+foo/newline=any + afoo + 0: afoo + ** Failers +No match + \nfoo +No match + \r\nfoo +No match + +/.+foo/s + afoo + 0: afoo + \r\nfoo + 0: \x0d\x0afoo + \nfoo + 0: \x0afoo + +/^$/gm,newline=any + abc\r\rxyz + 0: + abc\n\rxyz + 0: + ** Failers +No match + abc\r\nxyz +No match + +/^X/m + XABC + 0: X + ** Failers +No match + XABC\=notbol +No match + +/(?m)^$/g,newline=any,aftertext + abc\r\n\r\n + 0: + 0+ \x0d\x0a + +/(?m)^$|^\r\n/g,newline=any,aftertext + abc\r\n\r\n + 0: \x0d\x0a + 0+ + 1: + +/(?m)$/g,newline=any,aftertext + abc\r\n\r\n + 0: + 0+ \x0d\x0a\x0d\x0a + 0: + 0+ \x0d\x0a + 0: + 0+ + +/(?|(abc)|(xyz))/ + >abc< + 0: abc + >xyz< + 0: xyz + +/(x)(?|(abc)|(xyz))(x)/ + xabcx + 0: xabcx + xxyzx + 0: xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/ + xabcpqrx + 0: xabcpqrx + xxyzx + 0: xxyzx + +/(?|(abc)|(xyz))(?1)/ + abcabc + 0: abcabc + xyzabc + 0: xyzabc + ** Failers +No match + xyzxyz +No match + +/\H\h\V\v/ + X X\x0a + 0: X X\x0a + X\x09X\x0b + 0: X\x09X\x0b + ** Failers +No match + \xa0 X\x0a +No match + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0X\x0a\x0b\x0c\x0d + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0\x0a\x0b\x0c\x0d + \x09\x20\xa0\x0a\x0b\x0c + 0: \x09 \xa0\x0a\x0b\x0c + ** Failers +No match + \x09\x20\xa0\x0a\x0b +No match + +/\H{3,4}/ + XY ABCDE + 0: ABCD + XY PQR ST + 0: PQR + +/.\h{3,4}./ + XY AB PQRS + 0: B P + 1: B + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + 0: XNNNYZ + > X NYQZ + 0: X NYQZ + ** Failers +No match + >XYZ +No match + > X NY Z +No match + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + 0: XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/.+A/newline=crlf + \r\nA +No match + +/\nA/newline=crlf + \r\nA + 0: \x0aA + +/[\r\n]A/newline=crlf + \r\nA + 0: \x0aA + +/(\r|\n)A/newline=crlf + \r\nA + 0: \x0aA + +/a\Rb/I,bsr=anycrlf +Capturing subpattern count = 0 +No options +\R matches CR, LF, or CRLF +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 3 + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I,bsr=unicode +Capturing subpattern count = 0 +No options +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 3 + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\=bsr=anycrlf +No match + a\x0bb\=bsr=anycrlf +No match + +/a\R?b/I,bsr=anycrlf +Capturing subpattern count = 0 +No options +\R matches CR, LF, or CRLF +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 2 + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I,bsr=unicode +Capturing subpattern count = 0 +No options +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 2 + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\=bsr=anycrlf +No match + a\x0bb\=bsr=anycrlf +No match + +/a\R{2,4}b/I,bsr=anycrlf +Capturing subpattern count = 0 +No options +\R matches CR, LF, or CRLF +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 4 + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\x85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I,bsr=unicode +Capturing subpattern count = 0 +No options +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 4 + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\x85b + 0: a\x85\x85b + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\x85b\=bsr=anycrlf +No match + a\x0b\0bb\=bsr=anycrlf +No match + +/a(?!)|\wbc/ + abc + 0: abc + +/a[]b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + ** Failers +No match + ab +No match + +/a[]+b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + ** Failers +No match + ab +No match + +/a[]*+b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + ** Failers +No match + ab +No match + +/a[^]b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + aXb + 0: aXb + a\nb + 0: a\x0ab + ** Failers +No match + ab +No match + +/a[^]+b/alt_bsux,allow_empty_class,match_unset_backref,dupnames + aXb + 0: aXb + a\nX\nXb + 0: a\x0aX\x0aXb + ** Failers +No match + ab +No match + +/X$/dollar_endonly + X + 0: X + ** Failers +No match + X\n +No match + +/X$/ + X + 0: X + X\n + 0: X + +/xyz/auto_callout + xyz +--->xyz + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + abcxyz +--->abcxyz + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + abcxyz\=no_start_optimize +--->abcxyz + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +3 ^ ^ + 0: xyz + ** Failers +No match + abc +No match + abc\=no_start_optimize +--->abc + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x +No match + abcxypqr +No match + abcxypqr\=no_start_optimize +--->abcxypqr + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +1 ^^ y + +2 ^ ^ z + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x + +0 ^ x +No match + +/(*NO_START_OPT)xyz/auto_callout + abcxyz +--->abcxyz ++15 ^ x ++15 ^ x ++15 ^ x ++15 ^ x ++16 ^^ y ++17 ^ ^ z ++18 ^ ^ + 0: xyz + +/(?C)ab/ + ab +--->ab + 0 ^ a + 0: ab + ab\=callout_none + 0: ab + +/ab/auto_callout + ab +--->ab + +0 ^ a + +1 ^^ b + +2 ^ ^ + 0: ab + ab\=callout_none + 0: ab + +/^"((?(?=[a])[^"])|b)*"$/auto_callout + "ab" +--->"ab" + +0 ^ ^ + +1 ^ " + +2 ^^ ((?(?=[a])[^"])|b)* ++21 ^^ " + +3 ^^ (?(?=[a])[^"]) ++18 ^^ b + +5 ^^ (?=[a]) + +8 ^ [a] ++11 ^^ ) ++12 ^^ [^"] ++16 ^ ^ ) ++17 ^ ^ | ++21 ^ ^ " + +3 ^ ^ (?(?=[a])[^"]) ++18 ^ ^ b + +5 ^ ^ (?=[a]) + +8 ^ [a] ++19 ^ ^ ) ++21 ^ ^ " + +3 ^ ^ (?(?=[a])[^"]) ++18 ^ ^ b + +5 ^ ^ (?=[a]) + +8 ^ [a] ++17 ^ ^ | ++22 ^ ^ $ ++23 ^ ^ + 0: "ab" + "ab"\=callout_none + 0: "ab" + +/\d+X|9+Y/ + ++++123999\=P +Partial match: 123999 + ++++123999Y\=P + 0: 999Y + +/Z(*F)/ + Z\=P +No match + ZA\=P +No match + +/Z(?!)/ + Z\=P +No match + ZA\=P +No match + +/dog(sbody)?/ + dogs\=P + 0: dog + dogs\=PP +Partial match: dogs + +/dog(sbody)??/ + dogs\=P + 0: dog + dogs\=PP +Partial match: dogs + +/dog|dogsbody/ + dogs\=P + 0: dog + dogs\=PP +Partial match: dogs + +/dogsbody|dog/ + dogs\=P + 0: dog + dogs\=PP +Partial match: dogs + +/Z(*F)Q|ZXY/ + Z\=P +Partial match: Z + ZA\=P +No match + X\=P +No match + +/\bthe cat\b/ + the cat\=P + 0: the cat + the cat\=PP +Partial match: the cat + +/dog(sbody)?/ + dogs\=P + 0: dog + body\=dfa_restart + 0: body + +/dog(sbody)?/ + dogs\=PP +Partial match: dogs + body\=dfa_restart + 0: body + +/abc/ + abc\=P + 0: abc + abc\=PP + 0: abc + +/abc\K123/ + xyzabc123pqr +Failed: error -41: item unsupported for DFA matching + +/(?<=abc)123/ + xyzabc123pqr + 0: 123 + xyzabc12\=P +Partial match at offset 6: abc12 + xyzabc12\=PP +Partial match at offset 6: abc12 + +/\babc\b/ + +++abc+++ + 0: abc + +++ab\=P +Partial match at offset 3: +ab + +++ab\=PP +Partial match at offset 3: +ab + +/(?=C)/g,aftertext + ABCDECBA + 0: + 0+ CDECBA + 0: + 0+ CBA + +/(abc|def|xyz)/I +Capturing subpattern count = 1 +No options +Starting code units: a d x +No last code unit +Subject length lower bound = 3 + terhjk;abcdaadsfe + 0: abc + the quick xyz brown fox + 0: xyz + terhjk;abcdaadsfe\=no_start_optimize + 0: abc + the quick xyz brown fox\=no_start_optimize + 0: xyz + ** Failers +No match + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd +No match + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd\=no_start_optimize +No match + +/(abc|def|xyz)/I +Capturing subpattern count = 1 +No options +Starting code units: a d x +No last code unit +Subject length lower bound = 3 + terhjk;abcdaadsfe + 0: abc + the quick xyz brown fox + 0: xyz + terhjk;abcdaadsfe\=no_start_optimize + 0: abc + the quick xyz brown fox\=no_start_optimize + 0: xyz + ** Failers +No match + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd +No match + thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd\=no_start_optimize +No match + +/abcd*/aftertext + xxxxabcd\=P + 0: abcd + 0+ + xxxxabcd\=PP +Partial match: abcd + dddxxx\=dfa_restart + 0: ddd + 0+ xxx + xxxxabcd\=PP +Partial match: abcd + xxx\=dfa_restart + 0: + 0+ xxx + +/abcd*/i + xxxxabcd\=P + 0: abcd + xxxxabcd\=PP +Partial match: abcd + XXXXABCD\=P + 0: ABCD + XXXXABCD\=PP +Partial match: ABCD + +/abc\d*/ + xxxxabc1\=P + 0: abc1 + xxxxabc1\=PP +Partial match: abc1 + +/abc[de]*/ + xxxxabcde\=P + 0: abcde + xxxxabcde\=PP +Partial match: abcde + +/(?:(?1)|B)(A(*F)|C)/ + ABCD + 0: BC + CCD + 0: CC + ** Failers +No match + CAD +No match + +/^(?:(?1)|B)(A(*F)|C)/ + CCD + 0: CC + BCD + 0: BC + ** Failers +No match + ABCD +No match + CAD +No match + BAD +No match + +/^(?!a(*SKIP)b)/ + ac +Failed: error -41: item unsupported for DFA matching + +/^(?=a(*SKIP)b|ac)/ + ** Failers +No match + ac +Failed: error -41: item unsupported for DFA matching + +/^(?=a(*THEN)b|ac)/ + ac +Failed: error -41: item unsupported for DFA matching + +/^(?=a(*PRUNE)b)/ + ab +Failed: error -41: item unsupported for DFA matching + ** Failers +No match + ac +Failed: error -41: item unsupported for DFA matching + +/^(?(?!a(*SKIP)b))/ + ac +Failed: error -41: item unsupported for DFA matching + +/(?<=abc)def/ + abc\=PP +Partial match at offset 3: abc + +/abc$/ + abc + 0: abc + abc\=P + 0: abc + abc\=PP +Partial match: abc + +/abc$/m + abc + 0: abc + abc\n + 0: abc + abc\=PP +Partial match: abc + abc\n\=PP + 0: abc + abc\=P + 0: abc + abc\n\=P + 0: abc + +/abc\z/ + abc + 0: abc + abc\=P + 0: abc + abc\=PP +Partial match: abc + +/abc\Z/ + abc + 0: abc + abc\=P + 0: abc + abc\=PP +Partial match: abc + +/abc\b/ + abc + 0: abc + abc\=P + 0: abc + abc\=PP +Partial match: abc + +/abc\B/ + abc +No match + abc\=P +Partial match: abc + abc\=PP +Partial match: abc + +/.+/ + abc\=offset=0 + 0: abc + abc\=offset=1 + 0: bc + abc\=offset=2 + 0: c + abc\=offset=3 +No match + abc\=offset=4 +Failed: error -34: bad offset value + abc\=offset=-4 +** Invalid value in 'offset=-4' + +/^(?:a)++\w/ + aaaab + 0: aaaab + ** Failers +No match + aaaa +No match + bbb +No match + +/^(?:aa|(?:a)++\w)/ + aaaab + 0: aaaab + 1: aa + aaaa + 0: aa + ** Failers +No match + bbb +No match + +/^(?:a)*+\w/ + aaaab + 0: aaaab + bbb + 0: b + ** Failers +No match + aaaa +No match + +/^(a)++\w/ + aaaab + 0: aaaab + ** Failers +No match + aaaa +No match + bbb +No match + +/^(a|)++\w/ + aaaab + 0: aaaab + ** Failers +No match + aaaa +No match + bbb +No match + +/(?=abc){3}abc/aftertext + abcabcabc + 0: abc + 0+ abcabc + ** Failers +No match + xyz +No match + +/(?=abc)+abc/aftertext + abcabcabc + 0: abc + 0+ abcabc + ** Failers +No match + xyz +No match + +/(?=abc)++abc/aftertext + abcabcabc + 0: abc + 0+ abcabc + ** Failers +No match + xyz +No match + +/(?=abc){0}xyz/ + xyz + 0: xyz + +/(?=abc){1}xyz/ + ** Failers +No match + xyz +No match + +/(?=(a))?./ + ab + 0: a + bc + 0: b + +/(?=(a))??./ + ab + 0: a + bc + 0: b + +/^(?=(a)){0}b(?1)/ + backgammon + 0: ba + +/^(?=(?1))?[az]([abc])d/ + abd + 0: abd + zcdxx + 0: zcd + +/^(?!a){0}\w+/ + aaaaa + 0: aaaaa + +/(?<=(abc))?xyz/ + abcxyz + 0: xyz + pqrxyz + 0: xyz + +/((?2))((?1))/ + abc +Failed: error -51: nested recursion at the same subject position + +/(?(R)a+|(?R)b)/ + aaaabcde + 0: aaaab + +/(?(R)a+|((?R))b)/ + aaaabcde + 0: aaaab + +/((?(R)a+|(?1)b))/ + aaaabcde + 0: aaaab + +/((?(R2)a+|(?1)b))/ + aaaabcde +Failed: error -40: backreference condition or recursion test not supported for DFA matching + +/(?(R)a*(?1)|((?R))b)/ + aaaabcde +Failed: error -51: nested recursion at the same subject position + +/(a+)/no_auto_possess + aaaa\=ovector=3 +Matched, but offsets vector is too small to show all matches + 0: aaaa + 1: aaa + 2: aa + aaaa\=ovector=4 + 0: aaaa + 1: aaa + 2: aa + 3: a + +/ab\Cde/ + abXde + 0: abXde + +/(?<=ab\Cde)X/ + abZdeX + 0: X + +/^\R/ + \r\=P + 0: \x0d + \r\=PP +Partial match: \x0d + +/^\R{2,3}x/ + \r\=P +Partial match: \x0d + \r\=PP +Partial match: \x0d + \r\r\=P +Partial match: \x0d\x0d + \r\r\=PP +Partial match: \x0d\x0d + \r\r\r\=P +Partial match: \x0d\x0d\x0d + \r\r\r\=PP +Partial match: \x0d\x0d\x0d + \r\rx + 0: \x0d\x0dx + \r\r\rx + 0: \x0d\x0d\x0dx + +/^\R{2,3}?x/ + \r\=P +Partial match: \x0d + \r\=PP +Partial match: \x0d + \r\r\=P +Partial match: \x0d\x0d + \r\r\=PP +Partial match: \x0d\x0d + \r\r\r\=P +Partial match: \x0d\x0d\x0d + \r\r\r\=PP +Partial match: \x0d\x0d\x0d + \r\rx + 0: \x0d\x0dx + \r\r\rx + 0: \x0d\x0d\x0dx + +/^\R?x/ + \r\=P +Partial match: \x0d + \r\=PP +Partial match: \x0d + x + 0: x + \rx + 0: \x0dx + +/^\R+x/ + \r\=P +Partial match: \x0d + \r\=PP +Partial match: \x0d + \r\n\=P +Partial match: \x0d\x0a + \r\n\=PP +Partial match: \x0d\x0a + \rx + 0: \x0dx + +/^a$/newline=crlf + a\r\=P +Partial match: a\x0d + a\r\=PP +Partial match: a\x0d + +/^a$/m,newline=crlf + a\r\=P +Partial match: a\x0d + a\r\=PP +Partial match: a\x0d + +/^(a$|a\r)/newline=crlf + a\r\=P + 0: a\x0d + a\r\=PP +Partial match: a\x0d + +/^(a$|a\r)/m,newline=crlf + a\r\=P + 0: a\x0d + a\r\=PP +Partial match: a\x0d + +/./newline=crlf + \r\=P + 0: \x0d + \r\=PP +Partial match: \x0d + +/.{2,3}/newline=crlf + \r\=P +Partial match: \x0d + \r\=PP +Partial match: \x0d + \r\r\=P + 0: \x0d\x0d + \r\r\=PP +Partial match: \x0d\x0d + \r\r\r\=P + 0: \x0d\x0d\x0d + \r\r\r\=PP +Partial match: \x0d\x0d\x0d + +/.{2,3}?/newline=crlf + \r\=P +Partial match: \x0d + \r\=PP +Partial match: \x0d + \r\r\=P + 0: \x0d\x0d + \r\r\=PP +Partial match: \x0d\x0d + \r\r\r\=P + 0: \x0d\x0d\x0d + 1: \x0d\x0d + \r\r\r\=PP +Partial match: \x0d\x0d\x0d + +# Test simple validity check for restarts + +/abcdef/ + abc\=dfa_restart +Failed: error -38: invalid data in workspace for DFA restart + +/)(.)|(?R))++)*F>/ + text text xxxxx text F> text2 more text. + 0: text xxxxx text F> + +/^(?>.{4})abc|^\w\w.xabcd/ + xxxxabcd + 0: xxxxabcd + 1: xxxxabc + xx\xa0xabcd + 0: xx\xa0xabcd + 1: xx\xa0xabc + +/^(.{4}){2}+abc|^\w\w.x\w\w\w\wabcd/ + xxxxxxxxabcd + 0: xxxxxxxxabcd + 1: xxxxxxxxabc + xx\xa0xxxxxabcd + 0: xx\xa0xxxxxabcd + 1: xx\xa0xxxxxabc + +/abcd/ + abcd\=ovector=0 +Matched, but offsets vector is too small to show all matches + +# These tests show up auto-possessification + +/[ab]*/ + aaaa + 0: aaaa + +/[ab]*?/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/[ab]?/ + aaaa + 0: a + +/[ab]??/ + aaaa + 0: a + 1: + +/[ab]+/ + aaaa + 0: aaaa + +/[ab]+?/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/[ab]{2,3}/ + aaaa + 0: aaa + +/[ab]{2,3}?/ + aaaa + 0: aaa + 1: aa + +/[ab]{2,}/ + aaaa + 0: aaaa + +/[ab]{2,}?/ + aaaa + 0: aaaa + 1: aaa + 2: aa + +'\A(?:[^\"]++|\"(?:[^\"]*+|\"\")*+\")++' + NON QUOTED \"QUOT\"\"ED\" AFTER \"NOT MATCHED + 0: NON QUOTED "QUOT""ED" AFTER + +'\A(?:[^\"]++|\"(?:[^\"]++|\"\")*+\")++' + NON QUOTED \"QUOT\"\"ED\" AFTER \"NOT MATCHED + 0: NON QUOTED "QUOT""ED" AFTER + +# End of testinput8 diff --git a/testdata/testoutput7 b/testdata/testoutput7 new file mode 100644 index 0000000..b58d7c1 --- /dev/null +++ b/testdata/testoutput7 @@ -0,0 +1,3772 @@ +# This set of tests checks UTF and Unicode property support with the DFA +# matching functionality of pcre_dfa_match(). A default subject modifier is +# used to force DFA matching for all tests. + +#subject dfa + +/\x{100}ab/utf + \x{100}ab + 0: \x{100}ab + +/a\x{100}*b/utf + ab + 0: ab + a\x{100}b + 0: a\x{100}b + a\x{100}\x{100}b + 0: a\x{100}\x{100}b + +/a\x{100}+b/utf + a\x{100}b + 0: a\x{100}b + a\x{100}\x{100}b + 0: a\x{100}\x{100}b + *** Failers +No match + ab +No match + +/\bX/utf + Xoanon + 0: X + +Xoanon + 0: X + \x{300}Xoanon + 0: X + *** Failers +No match + YXoanon +No match + +/\BX/utf + YXoanon + 0: X + *** Failers +No match + Xoanon +No match + +Xoanon +No match + \x{300}Xoanon +No match + +/X\b/utf + X+oanon + 0: X + ZX\x{300}oanon + 0: X + FAX + 0: X + *** Failers +No match + Xoanon +No match + +/X\B/utf + Xoanon + 0: X + *** Failers +No match + X+oanon +No match + ZX\x{300}oanon +No match + FAX +No match + +/[^a]/utf + abcd + 0: b + a\x{100} + 0: \x{100} + +/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/utf + ab99 + 0: ab9 + \x{123}\x{123}45 + 0: \x{123}\x{123}4 + \x{400}\x{401}\x{402}6 + 0: \x{400}\x{401}\x{402}6 + *** Failers +No match + d99 +No match + \x{123}\x{122}4 +No match + \x{400}\x{403}6 +No match + \x{400}\x{401}\x{402}\x{402}6 +No match + +/a.b/utf + acb + 0: acb + a\x7fb + 0: a\x{7f}b + a\x{100}b + 0: a\x{100}b + *** Failers +No match + a\nb +No match + +/a(.{3})b/utf + a\x{4000}xyb + 0: a\x{4000}xyb + a\x{4000}\x7fyb + 0: a\x{4000}\x{7f}yb + a\x{4000}\x{100}yb + 0: a\x{4000}\x{100}yb + *** Failers +No match + a\x{4000}b +No match + ac\ncb +No match + +/a(.*?)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: a\xc0\x88 + 2: a\xc0 + +/a(.*?)(.)/utf + a\x{100}b + 0: a\x{100}b + 1: a\x{100} + +/a(.*)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: a\xc0\x88 + 2: a\xc0 + +/a(.*)(.)/utf + a\x{100}b + 0: a\x{100}b + 1: a\x{100} + +/a(.)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + +/a(.)(.)/utf + a\x{240}bcd + 0: a\x{240}b + +/a(.?)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: a\xc0 + +/a(.?)(.)/utf + a\x{240}bcd + 0: a\x{240}b + 1: a\x{240} + +/a(.??)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: a\xc0 + +/a(.??)(.)/utf + a\x{240}bcd + 0: a\x{240}b + 1: a\x{240} + +/a(.{3})b/utf + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + *** Failers +No match + a\x{1234}b +No match + ac\ncb +No match + +/a(.{3,})b/utf + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,}?)b/utf + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,5})b/utf + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + 0: axbxxb + axxxxxbcdefghijb + 0: axxxxxb + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/a(.{3,5}?)b/utf + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + 0: axbxxb + axxxxxbcdefghijb + 0: axxxxxb + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/^[a\x{c0}]/utf + *** Failers +No match + \x{100} +No match + +/(?<=aXb)cd/utf + aXbcd + 0: cd + +/(?<=a\x{100}b)cd/utf + a\x{100}bcd + 0: cd + +/(?<=a\x{100000}b)cd/utf + a\x{100000}bcd + 0: cd + +/(?:\x{100}){3}b/utf + \x{100}\x{100}\x{100}b + 0: \x{100}\x{100}\x{100}b + *** Failers +No match + \x{100}\x{100}b +No match + +/\x{ab}/utf + \x{ab} + 0: \x{ab} + \xc2\xab + 0: \x{ab} + *** Failers +No match + \x00{ab} +No match + +/(?<=(.))X/utf + WXYZ + 0: X + \x{256}XYZ + 0: X + *** Failers +No match + XYZ +No match + +/[^a]+/g,utf + bcd + 0: bcd + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + +/^[^a]{2}/utf + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/utf + \x{100}bcAa + 0: \x{100}bcA + +/^[^a]{2,}?/utf + \x{100}bca + 0: \x{100}bc + 1: \x{100}b + +/[^a]+/gi,utf + bcd + 0: bcd + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + +/^[^a]{2}/i,utf + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/i,utf + \x{100}bcAa + 0: \x{100}bc + +/^[^a]{2,}?/i,utf + \x{100}bca + 0: \x{100}bc + 1: \x{100}b + +/\x{100}{0,0}/utf + abcd + 0: + +/\x{100}?/utf + abcd + 0: + \x{100}\x{100} + 0: \x{100} + +/\x{100}{0,3}/utf + \x{100}\x{100} + 0: \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + +/\x{100}*/utf + abce + 0: + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/utf + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100} + +/\x{100}{1,3}/utf + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + +/\x{100}+/utf + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/utf + abcd\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100} + +/\x{100}{3,5}/utf + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3,}/utf,no_auto_possess + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100}\x{100}\x{100} + 3: \x{100}\x{100}\x{100}\x{100} + 4: \x{100}\x{100}\x{100} + +/(?<=a\x{100}{2}b)X/utf + Xyyya\x{100}\x{100}bXzzz + 0: X + +/\D*/utf,no_auto_possess + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +Matched, but offsets vector is too small to show all matches + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/utf,no_auto_possess + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +Matched, but offsets vector is too small to show all matches + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 3: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 4: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 5: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 6: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 7: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 8: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 9: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +10: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +11: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +12: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +13: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +14: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/utf + 1X2 + 0: X + 1\x{100}2 + 0: \x{100} + +/>\S/utf + > >X Y + 0: >X + > >\x{100} Y + 0: >\x{100} + +/\d/utf + \x{100}3 + 0: 3 + +/\s/utf + \x{100} X + 0: + +/\D+/utf + 12abcd34 + 0: abcd + *** Failers + 0: *** Failers + 1234 +No match + +/\D{2,3}/utf + 12abcd34 + 0: abc + 12ab34 + 0: ab + *** Failers + 0: *** + 1234 +No match + 12a34 +No match + +/\D{2,3}?/utf + 12abcd34 + 0: abc + 1: ab + 12ab34 + 0: ab + *** Failers + 0: *** + 1: ** + 1234 +No match + 12a34 +No match + +/\d+/utf + 12abcd34 + 0: 12 + *** Failers +No match + +/\d{2,3}/utf + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + *** Failers +No match + 1.4 +No match + +/\d{2,3}?/utf + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers +No match + 1.4 +No match + +/\S+/utf + 12abcd34 + 0: 12abcd34 + *** Failers + 0: *** + \ \ +No match + +/\S{2,3}/utf + 12abcd34 + 0: 12a + 1234abcd + 0: 123 + *** Failers + 0: *** + \ \ +No match + +/\S{2,3}?/utf + 12abcd34 + 0: 12a + 1: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers + 0: *** + 1: ** + \ \ +No match + +/>\s+ <34 + 0: > < + *** Failers +No match + +/>\s{2,3} < + ab> < + *** Failers +No match + ab> \s{2,3}? < + ab> < + *** Failers +No match + ab> \xff< + 0: \xff + +/[\xff]/utf + >\x{ff}< + 0: \x{ff} + +/[^\xFF]/ + XYZ + 0: X + +/[^\xff]/utf + XYZ + 0: X + \x{123} + 0: \x{123} + +/^[ac]*b/utf + xb +No match + +/^[ac\x{100}]*b/utf + xb +No match + +/^[^x]*b/i,utf + xb +No match + +/^[^x]*b/utf + xb +No match + +/^\d*b/utf + xb +No match + +/(|a)/g,utf + catac + 0: + 0: a + 1: + 0: + 0: a + 1: + 0: + 0: + a\x{256}a + 0: a + 1: + 0: + 0: a + 1: + 0: + +/^\x{85}$/i,utf + \x{85} + 0: \x{85} + +/^abc./gmx,newline=any,utf + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/abc.$/gmx,newline=any,utf + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/^a\Rb/bsr=unicode,utf + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0cb + 0: a\x{0c}b + a\x{85}b + 0: a\x{85}b + a\x{2028}b + 0: a\x{2028}b + a\x{2029}b + 0: a\x{2029}b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/bsr=unicode,utf + ab + 0: ab + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + +/^a\R+b/bsr=unicode,utf + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + ** Failers +No match + ab +No match + +/^a\R{1,3}b/bsr=unicode,utf + a\nb + 0: a\x{0a}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}b + 0: a\x{0a}\x{0d}\x{85}b + a\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}b + a\r\n\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b + a\n\r\n\rb + 0: a\x{0a}\x{0d}\x{0a}\x{0d}b + a\n\n\r\nb + 0: a\x{0a}\x{0a}\x{0d}\x{0a}b + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/\h+\V?\v{3,4}/utf,no_auto_possess + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} + +/\V?\v{3,4}/utf,no_auto_possess + \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: X\x{0a}\x{0b}\x{0c}\x{0d} + 1: X\x{0a}\x{0b}\x{0c} + +/\h+\V?\v{3,4}/utf,no_auto_possess + >\x09\x20\x{a0}X\x0a\x0a\x0a< + 0: \x{09} \x{a0}X\x{0a}\x{0a}\x{0a} + +/\V?\v{3,4}/utf,no_auto_possess + >\x09\x20\x{a0}X\x0a\x0a\x0a< + 0: X\x{0a}\x{0a}\x{0a} + +/\H\h\V\v/utf + X X\x0a + 0: X X\x{0a} + X\x09X\x0b + 0: X\x{09}X\x{0b} + ** Failers +No match + \x{a0} X\x0a +No match + +/\H*\h+\V?\v{3,4}/utf,no_auto_possess + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + \x09\x20\x{a0}\x0a\x0b\x0c + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x20\x{a0}\x0a\x0b +No match + +/\H\h\V\v/utf + \x{3001}\x{3000}\x{2030}\x{2028} + 0: \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + 0: X\x{180e}X\x{85} + ** Failers +No match + \x{2009} X\x0a +No match + +/\H*\h+\V?\v{3,4}/utf,no_auto_possess + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} + 1: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c} + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} + 1: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c} + \x09\x20\x{202f}\x0a\x0b\x0c + 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x{200a}\x{a0}\x{2028}\x0b +No match + +/a\Rb/I,bsr=anycrlf,utf +Capturing subpattern count = 0 +Options: utf +\R matches CR, LF, or CRLF +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 3 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I,bsr=unicode,utf +Capturing subpattern count = 0 +Options: utf +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 3 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\=bsr=anycrlf +No match + a\x0bb\=bsr=anycrlf +No match + +/a\R?b/I,bsr=anycrlf,utf +Capturing subpattern count = 0 +Options: utf +\R matches CR, LF, or CRLF +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 2 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I,bsr=unicode,utf +Capturing subpattern count = 0 +Options: utf +First code unit = 'a' +Last code unit = 'b' +Subject length lower bound = 2 + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\=bsr=anycrlf +No match + a\x0bb\=bsr=anycrlf +No match + +/X/newline=any,utf,firstline + A\x{1ec5}ABCXYZ + 0: X + +/abcd*/utf + xxxxabcd\=P + 0: abcd + xxxxabcd\=PP +Partial match: abcd + +/abcd*/i,utf + xxxxabcd\=P + 0: abcd + xxxxabcd\=PP +Partial match: abcd + XXXXABCD\=P + 0: ABCD + XXXXABCD\=PP +Partial match: ABCD + +/abc\d*/utf + xxxxabc1\=P + 0: abc1 + xxxxabc1\=PP +Partial match: abc1 + +/abc[de]*/utf + xxxxabcde\=P + 0: abcde + xxxxabcde\=PP +Partial match: abcde + +/\bthe cat\b/utf + the cat\=P + 0: the cat + the cat\=PP +Partial match: the cat + +/ab\Cde/utf + abXde +Failed: error -41: item unsupported for DFA matching + +/(?<=ab\Cde)X/utf +Failed: error 136 at offset 10: \C is not allowed in a lookbehind assertion + +/./newline=crlf,utf + \r\=P + 0: \x{0d} + \r\=PP +Partial match: \x{0d} + +/.{2,3}/newline=crlf,utf + \r\=P +Partial match: \x{0d} + \r\=PP +Partial match: \x{0d} + \r\r\=P + 0: \x{0d}\x{0d} + \r\r\=PP +Partial match: \x{0d}\x{0d} + \r\r\r\=P + 0: \x{0d}\x{0d}\x{0d} + \r\r\r\=PP +Partial match: \x{0d}\x{0d}\x{0d} + +/.{2,3}?/newline=crlf,utf + \r\=P +Partial match: \x{0d} + \r\=PP +Partial match: \x{0d} + \r\r\=P + 0: \x{0d}\x{0d} + \r\r\=PP +Partial match: \x{0d}\x{0d} + \r\r\r\=P + 0: \x{0d}\x{0d}\x{0d} + 1: \x{0d}\x{0d} + \r\r\r\=PP +Partial match: \x{0d}\x{0d}\x{0d} + +/[^\x{100}]/utf + \x{100}\x{101}X + 0: \x{101} + +/[^\x{100}]+/utf + \x{100}\x{101}X + 0: \x{101}X + +/\pL\P{Nd}/utf + AB + 0: AB + *** Failers + 0: Fa + A0 +No match + 00 +No match + +/\X./utf + AB + 0: AB + A\x{300}BC + 0: A\x{300}B + A\x{300}\x{301}\x{302}BC + 0: A\x{300}\x{301}\x{302}B + *** Failers + 0: ** + \x{300} +No match + +/\X\X/utf + ABC + 0: AB + A\x{300}B\x{300}\x{301}C + 0: A\x{300}B\x{300}\x{301} + A\x{300}\x{301}\x{302}BC + 0: A\x{300}\x{301}\x{302}B + *** Failers + 0: ** + \x{300} +No match + +/^\pL+/utf + abcd + 0: abcd + a + 0: a + *** Failers +No match + +/^\PL+/utf + 1234 + 0: 1234 + = + 0: = + *** Failers + 0: *** + abcd +No match + +/^\X+/utf + abcdA\x{300}\x{301}\x{302} + 0: abcdA\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302} + 0: A\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + a + 0: a + *** Failers + 0: *** Failers + \x{300}\x{301}\x{302} + 0: \x{300}\x{301}\x{302} + +/\X?abc/utf + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}abc + \x{300}abc + 0: \x{300}abc + *** Failers +No match + +/^\X?abc/utf + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + *** Failers +No match + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz +No match + \x{300}abc + 0: \x{300}abc + +/\X*abc/utf + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc + \x{300}abc + 0: \x{300}abc + *** Failers +No match + +/^\X*abc/utf + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc + *** Failers +No match + \x{300}abc + 0: \x{300}abc + +/^\pL?=./utf + A=b + 0: A=b + =c + 0: =c + *** Failers +No match + 1=2 +No match + AAAA=b +No match + +/^\pL*=./utf + AAAA=b + 0: AAAA=b + =c + 0: =c + *** Failers +No match + 1=2 +No match + +/^\X{2,3}X/utf + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + *** Failers +No match + X +No match + A\x{300}\x{301}\x{302}X +No match + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X +No match + +/^\pC\pL\pM\pN\pP\pS\pZ\p{Xsp}/utf + >\x{1680}\x{2028}\x{0b} + 0: >\x{1680} + ** Failers +No match + \x{0b} +No match + +/^>\p{Xsp}+/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028} + 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680} + 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0} + 4: > \x{09}\x{0a}\x{0c}\x{0d} + 5: > \x{09}\x{0a}\x{0c} + 6: > \x{09}\x{0a} + 7: > \x{09} + 8: > + +/^>\p{Xsp}*/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028} + 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680} + 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0} + 4: > \x{09}\x{0a}\x{0c}\x{0d} + 5: > \x{09}\x{0a}\x{0c} + 6: > \x{09}\x{0a} + 7: > \x{09} + 8: > + 9: > + +/^>\p{Xsp}{2,9}/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028} + 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680} + 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0} + 4: > \x{09}\x{0a}\x{0c}\x{0d} + 5: > \x{09}\x{0a}\x{0c} + 6: > \x{09}\x{0a} + 7: > \x{09} + +/^>[\p{Xsp}]/utf,no_auto_possess + >\x{2028}\x{0b} + 0: >\x{2028} + +/^>[\p{Xsp}]+/utf,no_auto_possess + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028} + 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680} + 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0} + 4: > \x{09}\x{0a}\x{0c}\x{0d} + 5: > \x{09}\x{0a}\x{0c} + 6: > \x{09}\x{0a} + 7: > \x{09} + 8: > + +/^>\p{Xps}/utf + >\x{1680}\x{2028}\x{0b} + 0: >\x{1680} + >\x{a0} + 0: >\x{a0} + ** Failers +No match + \x{0b} +No match + +/^>\p{Xps}+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}+?/utf + >\x{1680}\x{2028}\x{0b} + 0: >\x{1680}\x{2028}\x{0b} + 1: >\x{1680}\x{2028} + 2: >\x{1680} + +/^>\p{Xps}*/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^>\p{Xps}{2,9}?/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028} + 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680} + 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0} + 4: > \x{09}\x{0a}\x{0c}\x{0d} + 5: > \x{09}\x{0a}\x{0c} + 6: > \x{09}\x{0a} + 7: > \x{09} + +/^>[\p{Xps}]/utf + >\x{2028}\x{0b} + 0: >\x{2028} + +/^>[\p{Xps}]+/utf + > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b} + +/^\p{Xwd}/utf + ABCD + 0: A + 1234 + 0: 1 + \x{6ca} + 0: \x{6ca} + \x{a6c} + 0: \x{a6c} + \x{10a7} + 0: \x{10a7} + _ABC + 0: _ + ** Failers +No match + [] +No match + +/^\p{Xwd}+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}*/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +/^\p{Xwd}{2,9}/utf + A_12\x{6ca}\x{a6c}\x{10a7} + 0: A_12\x{6ca}\x{a6c}\x{10a7} + +/^[\p{Xwd}]/utf + ABCD1234_ + 0: A + 1234abcd_ + 0: 1 + \x{6ca} + 0: \x{6ca} + \x{a6c} + 0: \x{a6c} + \x{10a7} + 0: \x{10a7} + _ABC + 0: _ + ** Failers +No match + [] +No match + +/^[\p{Xwd}]+/utf + ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_ + +# Unicode properties for \b abd \B + +/\b...\B/utf,ucp + abc_ + 0: abc + \x{37e}abc\x{376} + 0: abc + \x{37e}\x{376}\x{371}\x{393}\x{394} + 0: \x{376}\x{371}\x{393} + !\x{c0}++\x{c1}\x{c2} + 0: ++\x{c1} + !\x{c0}+++++ + 0: \x{c0}++ + +# Without PCRE_UCP, non-ASCII always fail, even if < 256 + +/\b...\B/utf + abc_ + 0: abc + ** Failers + 0: Fai + \x{37e}abc\x{376} +No match + \x{37e}\x{376}\x{371}\x{393}\x{394} +No match + !\x{c0}++\x{c1}\x{c2} +No match + !\x{c0}+++++ +No match + +# With PCRE_UCP, non-UTF8 chars that are < 256 still check properties + +/\b...\B/ucp + abc_ + 0: abc + !\x{c0}++\x{c1}\x{c2} + 0: ++\xc1 + !\x{c0}+++++ + 0: \xc0++ + +# Caseless single negated characters > 127 need UCP support + +/[^\x{100}]/i,utf + \x{100}\x{101}X + 0: X + +/[^\x{100}]+/i,utf + \x{100}\x{101}XX + 0: XX + +/^\X/utf + A\=P + 0: A + A\=PP +Partial match: A + A\x{300}\x{301}\=P + 0: A\x{300}\x{301} + A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301} + A\x{301}\=P + 0: A\x{301} + A\x{301}\=PP +Partial match: A\x{301} + +/^\X{2,3}/utf + A\=P +Partial match: A + A\=PP +Partial match: A + AA\=P + 0: AA + AA\=PP +Partial match: AA + A\x{300}\x{301}\=P +Partial match: A\x{300}\x{301} + A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301} + A\x{300}\x{301}A\x{300}\x{301}\=P + 0: A\x{300}\x{301}A\x{300}\x{301} + A\x{300}\x{301}A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301}A\x{300}\x{301} + +/^\X{2}/utf + AA\=P + 0: AA + AA\=PP +Partial match: AA + A\x{300}\x{301}A\x{300}\x{301}\=P + 0: A\x{300}\x{301}A\x{300}\x{301} + A\x{300}\x{301}A\x{300}\x{301}\=PP +Partial match: A\x{300}\x{301}A\x{300}\x{301} + +/^\X+/utf + AA\=P + 0: AA + AA\=PP +Partial match: AA + +/^\X+?Z/utf + AA\=P +Partial match: AA + AA\=PP +Partial match: AA + +# These are tests for extended grapheme clusters + +/^\X/utf,aftertext + G\x{34e}\x{34e}X + 0: G\x{34e}\x{34e} + 0+ X + \x{34e}\x{34e}X + 0: \x{34e}\x{34e} + 0+ X + \x04X + 0: \x{04} + 0+ X + \x{1100}X + 0: \x{1100} + 0+ X + \x{1100}\x{34e}X + 0: \x{1100}\x{34e} + 0+ X + \x{1b04}\x{1b04}X + 0: \x{1b04}\x{1b04} + 0+ X + *These match up to the roman letters + 0: * + 0+ These match up to the roman letters + \x{1111}\x{1111}L,L + 0: \x{1111}\x{1111} + 0+ L,L + \x{1111}\x{1111}\x{1169}L,L,V + 0: \x{1111}\x{1111}\x{1169} + 0+ L,L,V + \x{1111}\x{ae4c}L, LV + 0: \x{1111}\x{ae4c} + 0+ L, LV + \x{1111}\x{ad89}L, LVT + 0: \x{1111}\x{ad89} + 0+ L, LVT + \x{1111}\x{ae4c}\x{1169}L, LV, V + 0: \x{1111}\x{ae4c}\x{1169} + 0+ L, LV, V + \x{1111}\x{ae4c}\x{1169}\x{1169}L, LV, V, V + 0: \x{1111}\x{ae4c}\x{1169}\x{1169} + 0+ L, LV, V, V + \x{1111}\x{ae4c}\x{1169}\x{11fe}L, LV, V, T + 0: \x{1111}\x{ae4c}\x{1169}\x{11fe} + 0+ L, LV, V, T + \x{1111}\x{ad89}\x{11fe}L, LVT, T + 0: \x{1111}\x{ad89}\x{11fe} + 0+ L, LVT, T + \x{1111}\x{ad89}\x{11fe}\x{11fe}L, LVT, T, T + 0: \x{1111}\x{ad89}\x{11fe}\x{11fe} + 0+ L, LVT, T, T + \x{ad89}\x{11fe}\x{11fe}LVT, T, T + 0: \x{ad89}\x{11fe}\x{11fe} + 0+ LVT, T, T + *These match just the first codepoint (invalid sequence) + 0: * + 0+ These match just the first codepoint (invalid sequence) + \x{1111}\x{11fe}L, T + 0: \x{1111} + 0+ \x{11fe}L, T + \x{ae4c}\x{1111}LV, L + 0: \x{ae4c} + 0+ \x{1111}LV, L + \x{ae4c}\x{ae4c}LV, LV + 0: \x{ae4c} + 0+ \x{ae4c}LV, LV + \x{ae4c}\x{ad89}LV, LVT + 0: \x{ae4c} + 0+ \x{ad89}LV, LVT + \x{1169}\x{1111}V, L + 0: \x{1169} + 0+ \x{1111}V, L + \x{1169}\x{ae4c}V, LV + 0: \x{1169} + 0+ \x{ae4c}V, LV + \x{1169}\x{ad89}V, LVT + 0: \x{1169} + 0+ \x{ad89}V, LVT + \x{ad89}\x{1111}LVT, L + 0: \x{ad89} + 0+ \x{1111}LVT, L + \x{ad89}\x{1169}LVT, V + 0: \x{ad89} + 0+ \x{1169}LVT, V + \x{ad89}\x{ae4c}LVT, LV + 0: \x{ad89} + 0+ \x{ae4c}LVT, LV + \x{ad89}\x{ad89}LVT, LVT + 0: \x{ad89} + 0+ \x{ad89}LVT, LVT + \x{11fe}\x{1111}T, L + 0: \x{11fe} + 0+ \x{1111}T, L + \x{11fe}\x{1169}T, V + 0: \x{11fe} + 0+ \x{1169}T, V + \x{11fe}\x{ae4c}T, LV + 0: \x{11fe} + 0+ \x{ae4c}T, LV + \x{11fe}\x{ad89}T, LVT + 0: \x{11fe} + 0+ \x{ad89}T, LVT + *Test extend and spacing mark + 0: * + 0+ Test extend and spacing mark + \x{1111}\x{ae4c}\x{0711}L, LV, extend + 0: \x{1111}\x{ae4c}\x{711} + 0+ L, LV, extend + \x{1111}\x{ae4c}\x{1b04}L, LV, spacing mark + 0: \x{1111}\x{ae4c}\x{1b04} + 0+ L, LV, spacing mark + \x{1111}\x{ae4c}\x{1b04}\x{0711}\x{1b04}L, LV, spacing mark, extend, spacing mark + 0: \x{1111}\x{ae4c}\x{1b04}\x{711}\x{1b04} + 0+ L, LV, spacing mark, extend, spacing mark + *Test CR, LF, and control + 0: * + 0+ Test CR, LF, and control + \x0d\x{0711}CR, extend + 0: \x{0d} + 0+ \x{711}CR, extend + \x0d\x{1b04}CR, spacingmark + 0: \x{0d} + 0+ \x{1b04}CR, spacingmark + \x0a\x{0711}LF, extend + 0: \x{0a} + 0+ \x{711}LF, extend + \x0a\x{1b04}LF, spacingmark + 0: \x{0a} + 0+ \x{1b04}LF, spacingmark + \x0b\x{0711}Control, extend + 0: \x{0b} + 0+ \x{711}Control, extend + \x09\x{1b04}Control, spacingmark + 0: \x{09} + 0+ \x{1b04}Control, spacingmark + *There are no Prepend characters, so we can't test Prepend, CR + 0: * + 0+ There are no Prepend characters, so we can't test Prepend, CR + +/^(?>\X{2})X/utf,aftertext + \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0: \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0+ + +/^\X{2,4}X/utf,aftertext + \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0: \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0+ + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0: \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0+ + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0: \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0+ + +/^\X{2,4}?X/utf,aftertext + \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0: \x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0+ + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0: \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0+ + \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0: \x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}\x{1111}\x{ae4c}X + 0+ + +/\x{1e9e}+/i,utf + \x{1e9e}\x{00df} + 0: \x{1e9e}\x{df} + +/[z\x{1e9e}]+/i,utf + \x{1e9e}\x{00df} + 0: \x{1e9e}\x{df} + +/\x{00df}+/i,utf + \x{1e9e}\x{00df} + 0: \x{1e9e}\x{df} + +/[z\x{00df}]+/i,utf + \x{1e9e}\x{00df} + 0: \x{1e9e}\x{df} + +/\x{1f88}+/i,utf + \x{1f88}\x{1f80} + 0: \x{1f88}\x{1f80} + +/[z\x{1f88}]+/i,utf + \x{1f88}\x{1f80} + 0: \x{1f88}\x{1f80} + +# Perl matches these + +/\x{00b5}+/i,utf + \x{00b5}\x{039c}\x{03bc} + 0: \x{b5}\x{39c}\x{3bc} + +/\x{039c}+/i,utf + \x{00b5}\x{039c}\x{03bc} + 0: \x{b5}\x{39c}\x{3bc} + +/\x{03bc}+/i,utf + \x{00b5}\x{039c}\x{03bc} + 0: \x{b5}\x{39c}\x{3bc} + + +/\x{00c5}+/i,utf + \x{00c5}\x{00e5}\x{212b} + 0: \x{c5}\x{e5}\x{212b} + +/\x{00e5}+/i,utf + \x{00c5}\x{00e5}\x{212b} + 0: \x{c5}\x{e5}\x{212b} + +/\x{212b}+/i,utf + \x{00c5}\x{00e5}\x{212b} + 0: \x{c5}\x{e5}\x{212b} + + +/\x{01c4}+/i,utf + \x{01c4}\x{01c5}\x{01c6} + 0: \x{1c4}\x{1c5}\x{1c6} + +/\x{01c5}+/i,utf + \x{01c4}\x{01c5}\x{01c6} + 0: \x{1c4}\x{1c5}\x{1c6} + +/\x{01c6}+/i,utf + \x{01c4}\x{01c5}\x{01c6} + 0: \x{1c4}\x{1c5}\x{1c6} + + +/\x{01c7}+/i,utf + \x{01c7}\x{01c8}\x{01c9} + 0: \x{1c7}\x{1c8}\x{1c9} + +/\x{01c8}+/i,utf + \x{01c7}\x{01c8}\x{01c9} + 0: \x{1c7}\x{1c8}\x{1c9} + +/\x{01c9}+/i,utf + \x{01c7}\x{01c8}\x{01c9} + 0: \x{1c7}\x{1c8}\x{1c9} + + +/\x{01ca}+/i,utf + \x{01ca}\x{01cb}\x{01cc} + 0: \x{1ca}\x{1cb}\x{1cc} + +/\x{01cb}+/i,utf + \x{01ca}\x{01cb}\x{01cc} + 0: \x{1ca}\x{1cb}\x{1cc} + +/\x{01cc}+/i,utf + \x{01ca}\x{01cb}\x{01cc} + 0: \x{1ca}\x{1cb}\x{1cc} + + +/\x{01f1}+/i,utf + \x{01f1}\x{01f2}\x{01f3} + 0: \x{1f1}\x{1f2}\x{1f3} + +/\x{01f2}+/i,utf + \x{01f1}\x{01f2}\x{01f3} + 0: \x{1f1}\x{1f2}\x{1f3} + +/\x{01f3}+/i,utf + \x{01f1}\x{01f2}\x{01f3} + 0: \x{1f1}\x{1f2}\x{1f3} + + +/\x{0345}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + 0: \x{345}\x{399}\x{3b9}\x{1fbe} + +/\x{0399}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + 0: \x{345}\x{399}\x{3b9}\x{1fbe} + +/\x{03b9}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + 0: \x{345}\x{399}\x{3b9}\x{1fbe} + +/\x{1fbe}+/i,utf + \x{0345}\x{0399}\x{03b9}\x{1fbe} + 0: \x{345}\x{399}\x{3b9}\x{1fbe} + + +/\x{0392}+/i,utf + \x{0392}\x{03b2}\x{03d0} + 0: \x{392}\x{3b2}\x{3d0} + +/\x{03b2}+/i,utf + \x{0392}\x{03b2}\x{03d0} + 0: \x{392}\x{3b2}\x{3d0} + +/\x{03d0}+/i,utf + \x{0392}\x{03b2}\x{03d0} + 0: \x{392}\x{3b2}\x{3d0} + + +/\x{0395}+/i,utf + \x{0395}\x{03b5}\x{03f5} + 0: \x{395}\x{3b5}\x{3f5} + +/\x{03b5}+/i,utf + \x{0395}\x{03b5}\x{03f5} + 0: \x{395}\x{3b5}\x{3f5} + +/\x{03f5}+/i,utf + \x{0395}\x{03b5}\x{03f5} + 0: \x{395}\x{3b5}\x{3f5} + + +/\x{0398}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + 0: \x{398}\x{3b8}\x{3d1}\x{3f4} + +/\x{03b8}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + 0: \x{398}\x{3b8}\x{3d1}\x{3f4} + +/\x{03d1}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + 0: \x{398}\x{3b8}\x{3d1}\x{3f4} + +/\x{03f4}+/i,utf + \x{0398}\x{03b8}\x{03d1}\x{03f4} + 0: \x{398}\x{3b8}\x{3d1}\x{3f4} + + +/\x{039a}+/i,utf + \x{039a}\x{03ba}\x{03f0} + 0: \x{39a}\x{3ba}\x{3f0} + +/\x{03ba}+/i,utf + \x{039a}\x{03ba}\x{03f0} + 0: \x{39a}\x{3ba}\x{3f0} + +/\x{03f0}+/i,utf + \x{039a}\x{03ba}\x{03f0} + 0: \x{39a}\x{3ba}\x{3f0} + + +/\x{03a0}+/i,utf + \x{03a0}\x{03c0}\x{03d6} + 0: \x{3a0}\x{3c0}\x{3d6} + +/\x{03c0}+/i,utf + \x{03a0}\x{03c0}\x{03d6} + 0: \x{3a0}\x{3c0}\x{3d6} + +/\x{03d6}+/i,utf + \x{03a0}\x{03c0}\x{03d6} + 0: \x{3a0}\x{3c0}\x{3d6} + + +/\x{03a1}+/i,utf + \x{03a1}\x{03c1}\x{03f1} + 0: \x{3a1}\x{3c1}\x{3f1} + +/\x{03c1}+/i,utf + \x{03a1}\x{03c1}\x{03f1} + 0: \x{3a1}\x{3c1}\x{3f1} + +/\x{03f1}+/i,utf + \x{03a1}\x{03c1}\x{03f1} + 0: \x{3a1}\x{3c1}\x{3f1} + + +/\x{03a3}+/i,utf + \x{03A3}\x{03C2}\x{03C3} + 0: \x{3a3}\x{3c2}\x{3c3} + +/\x{03c2}+/i,utf + \x{03A3}\x{03C2}\x{03C3} + 0: \x{3a3}\x{3c2}\x{3c3} + +/\x{03c3}+/i,utf + \x{03A3}\x{03C2}\x{03C3} + 0: \x{3a3}\x{3c2}\x{3c3} + + +/\x{03a6}+/i,utf + \x{03a6}\x{03c6}\x{03d5} + 0: \x{3a6}\x{3c6}\x{3d5} + +/\x{03c6}+/i,utf + \x{03a6}\x{03c6}\x{03d5} + 0: \x{3a6}\x{3c6}\x{3d5} + +/\x{03d5}+/i,utf + \x{03a6}\x{03c6}\x{03d5} + 0: \x{3a6}\x{3c6}\x{3d5} + + +/\x{03c9}+/i,utf + \x{03c9}\x{03a9}\x{2126} + 0: \x{3c9}\x{3a9}\x{2126} + +/\x{03a9}+/i,utf + \x{03c9}\x{03a9}\x{2126} + 0: \x{3c9}\x{3a9}\x{2126} + +/\x{2126}+/i,utf + \x{03c9}\x{03a9}\x{2126} + 0: \x{3c9}\x{3a9}\x{2126} + + +/\x{1e60}+/i,utf + \x{1e60}\x{1e61}\x{1e9b} + 0: \x{1e60}\x{1e61}\x{1e9b} + +/\x{1e61}+/i,utf + \x{1e60}\x{1e61}\x{1e9b} + 0: \x{1e60}\x{1e61}\x{1e9b} + +/\x{1e9b}+/i,utf + \x{1e60}\x{1e61}\x{1e9b} + 0: \x{1e60}\x{1e61}\x{1e9b} + + +/\x{1e9e}+/i,utf + \x{1e9e}\x{00df} + 0: \x{1e9e}\x{df} + +/\x{00df}+/i,utf + \x{1e9e}\x{00df} + 0: \x{1e9e}\x{df} + + +/\x{1f88}+/i,utf + \x{1f88}\x{1f80} + 0: \x{1f88}\x{1f80} + +/\x{1f80}+/i,utf + \x{1f88}\x{1f80} + 0: \x{1f88}\x{1f80} + +/\x{004b}+/i,utf + \x{004b}\x{006b}\x{212a} + 0: Kk\x{212a} + +/\x{006b}+/i,utf + \x{004b}\x{006b}\x{212a} + 0: Kk\x{212a} + +/\x{212a}+/i,utf + \x{004b}\x{006b}\x{212a} + 0: Kk\x{212a} + + +/\x{0053}+/i,utf + \x{0053}\x{0073}\x{017f} + 0: Ss\x{17f} + +/\x{0073}+/i,utf + \x{0053}\x{0073}\x{017f} + 0: Ss\x{17f} + +/\x{017f}+/i,utf + \x{0053}\x{0073}\x{017f} + 0: Ss\x{17f} + +/ist/i,utf + ikt +No match + +/is+t/i,utf + iSs\x{17f}t + 0: iSs\x{17f}t + ikt +No match + +/is+?t/i,utf + ikt +No match + +/is?t/i,utf + ikt +No match + +/is{2}t/i,utf + iskt +No match + +/^\p{Xuc}/utf + $abc + 0: $ + @abc + 0: @ + `abc + 0: ` + \x{1234}abc + 0: \x{1234} + ** Failers +No match + abc +No match + +/^\p{Xuc}+/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000} + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}+?/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000} + 1: $@`\x{a0}\x{1234} + 2: $@`\x{a0} + 3: $@` + 4: $@ + 5: $ + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}+?\*/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000}* + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}++/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000} + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}{3,5}/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234} + ** Failers +No match + \x{9f} +No match + +/^\p{Xuc}{3,5}?/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234} + 1: $@`\x{a0} + 2: $@` + ** Failers +No match + \x{9f} +No match + +/^[\p{Xuc}]/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $ + ** Failers +No match + \x{9f} +No match + +/^[\p{Xuc}]+/utf + $@`\x{a0}\x{1234}\x{e000}** + 0: $@`\x{a0}\x{1234}\x{e000} + ** Failers +No match + \x{9f} +No match + +/^\P{Xuc}/utf + abc + 0: a + ** Failers + 0: * + $abc +No match + @abc +No match + `abc +No match + \x{1234}abc +No match + +/^[\P{Xuc}]/utf + abc + 0: a + ** Failers + 0: * + $abc +No match + @abc +No match + `abc +No match + \x{1234}abc +No match + +/^A\s+Z/utf,ucp + A\x{2005}Z + 0: A\x{2005}Z + A\x{85}\x{180e}\x{2005}Z + 0: A\x{85}\x{180e}\x{2005}Z + +/^A[\s]+Z/utf,ucp + A\x{2005}Z + 0: A\x{2005}Z + A\x{85}\x{180e}\x{2005}Z + 0: A\x{85}\x{180e}\x{2005}Z + +# End of testinput7