Regular Expressions

Below is sample of EZY Prolog programs which demonstrates how to use regular expressions.

Regular Expression:	String	Results
-?[0-9]+	Valid Integer -93334	Syntax emacs, Found: {-93334} at 15 , Len 6
*(\+\|-)?[0-9]\.[0-9]([Ee](\+\|-)?[0-9]+)*	Valid Real Value +734.11e-1234	Syntax awk, Found: {+734.11e-1234} at 18 , Len 13
http:+(\\\|//)+([a-zA-Z_0-9.]+(\\\|/))+([a-zA-Z_0-9]).htm*	URL in form http://www.ser.com/dir/file.htm	Syntax awk, Found: {http://www.ser.com/dir/file.htm} at 13 , Len 31
($[0-9]{3}$)+(-\| )+([0-9]{3})+(-\| )+([0-9]{4})	Valid Phone number (415)-999-8888	Syntax posix_awk, Found: {(415)-999-8888} at 38 , Len 14
($[0-9]{3}$)+(-\| )+([0-9]{3})+(-\| )+([0-9]{4})	Valid Phone number (415) 999-8888	Syntax posix_awk, Found: {(415) 999-8888} at 38 , Len 14
([0-9]{2})([ ]+)([a-z]+)([ ]+)([1-2]([0-9]{3}))	Valid date DD Month Year 12 February 2001	Syntax posix_awk, Found: {12 February 2001} at 44 , Len 19
([0-1][0-2](\\\|/\|-\|.))([0-9]{2}(\\\|/\|-\|.))([1-2][0-9]{3})	Valid date MM-DD-YYYY 02/02/2000	Syntax posix_awk, Found: {02/02/2000} at 41 , Len 10
([0-1][0-2](\\\|/\|-\|.))([0-9]{2}(\\\|/\|-\|.))([1-2][0-9]{3})	Valid date MM-DD-YYYY 12-02/2000	Syntax posix_awk, Found: {12-02/2000} at 41 , Len 10
([0-1][0-2](\\\|/\|-\|.))([0-9]{2}(\\\|/\|-\|.))([1-2][0-9]{3})	Invalid date MM-DD-YYYY 22/02/2000	Fail {Invalid date MM-DD-YYYY 22/02/2000}
Chapter+[ ][0-9]	Chapter followed by a single whitespace character (space, tab, newline, etc), followed by a single digit Chapter 9 bla-bla	Syntax emacs, Found: {Chapter 9} at 106 , Len 9
Chapter+[ ]\w*	Chapter followed by a space, followed by a word character	Syntax emacs, Found: {Chapter followed} at 1 , Len 16
*((jan[a-z])\|(feb[a-z])\|(mar[a-z])\|(apr[a-z])\|(may)\|(ju[a-z])\|(aug[a-z])\|(sep[a-z])\|(oct[a-z])\|(nov[a-z])\|(dec[a-z]))+([ ]+\|\.\|-)+([0-9]{2}([ ]+\|.\|-))(([1-2][0-9]{3})\|[0-9]{2})*	Line with march 12 1999 or mar 12 1999	Syntax posix_awk, Found: {march 12 1999} at 29 , Len 13
*((jan[a-z])\|(feb[a-z])\|(mar[a-z])\|(apr[a-z])\|(may)\|(ju[a-z])\|(aug[a-z])\|(sep[a-z])\|(oct[a-z])\|(nov[a-z])\|(dec[a-z]))+([ ]+\|\.\|-)+([0-9]{2}([ ]+\|.\|-))(([1-2][0-9]{3})\|[0-9]{2})*	Text with march 12, 99 or march 12, 99	Fail {Text with march 12, 99 or march 12, 99}
*((jan[a-z])\|(feb[a-z])\|(mar[a-z])\|(apr[a-z])\|(may)\|(ju[a-z])\|(aug[a-z])\|(sep[a-z])\|(oct[a-z])\|(nov[a-z])\|(dec[a-z]))+([ ]+\|\.\|-)+([0-9]{2}([ ]+\|.\|-))(([1-2][0-9]{3})\|[0-9]{2})*	Para with mar 12, 1999 or mar 12, 99	Fail {Para with mar 12, 1999 or mar 12, 99}
*(d{1,2}):(\d\d)\s(am\|pm\|\s)*	04:30 pm	Fail {04:30 pm}
*(\d{1,2}):(\d\d)\s(am\|pm\|\s)*	12:45am	Fail {12:45am}
*(\d{1,2}):(\d\d)\s(am\|pm\|\s)*	14:45	Fail {14:45}
ab{2}	matches a string that has an a followed by exactly two b's abb	Syntax posix_awk, Found: {abb} at 78 , Len 3
ab{2,}	there are at least two b's "abb", "abbbb", etc.)	Syntax posix_awk, Found: {abb} at 47 , Len 3
ab{3,5}	from three to five b's ("abbb", "abbbb", or "abbbbb")	Syntax posix_awk, Found: {abbb} at 44 , Len 4
a?b+	a possible a followed by one or more b's ending a string	Syntax emacs, Found: {b} at 8 , Len 1
a(bc)*	matches a string that has an a followed by zero or more copies of the sequence bc	Syntax awk, Found: {a} at 2 , Len 1
a(bc){1,5}	one through five copies of bc such as abcbc	Syntax posix_awk, Found: {abcbc} at 64 , Len 5
hi\|hello	matches a string that has either hi or hello in it;	Syntax awk, Found: {hi} at 52 , Len 2
(b\|cd)ef	a string that has either bef or cdef	Syntax awk, Found: {bef} at 44 , Len 3
*(a\|b)c**	a string that has bc sequence of alternating a's and b's ending in a c	Syntax awk, Found: {c} at 25 , Len 1
*(a\|b)c**	a string that has ac sequence of alternating a's and b's ending in a c	Syntax awk, Found: {c} at 25 , Len 1
a.[0-9]	matches a string that has an a followed by one character and a digit a0234	Syntax emacs, Found: {a02} at 88 , Len 3
a..[0-9]	matches a string that has an a followed by one character and a digit a0234	Syntax emacs, Found: {a023} at 88 , Len 4
.{5}	a string with exactly 5 characters	Syntax posix_awk, Found: {a str} at 1 , Len 5
[0-9]%	a string that has a single digit before a percent sign 6%	Syntax emacs, Found: {674} at 2 , Len %
,[a-zA-Z0-9]	a string that ends in a comma followed by an alphanumeric character ,C	Syntax emacs, Found: {,C} at 87 , Len 2
%[^a-zA-Z]%	matches a string with a character that is not a letter between two percent signs %6%	Syntax emacs, Found: { 1003} at % , Len %
*$([0-9]+\|[0-9]{1,3}(,[0-9]{3}))(\.[0-9]{1,2})?**	money as $10000.00	Syntax awk, Found: {$10000} at 10 , Len 6
*$([0-9]+\|[0-9]{1,3}(,[0-9]{3}))(\.[0-9]{1,2})?**	money as $10,000.00	Syntax awk, Found: {$10} at 10 , Len 3
*$([0-9]+\|[0-9]{1,3}(,[0-9]{3}))(\.[0-9]{1,2})?**	money without the cents: $10000	Syntax awk, Found: {$10000} at 26 , Len 6
*$([0-9]+\|[0-9]{1,3}(,[0-9]{3}))(\.[0-9]{1,2})?**	money without the cents: $10,000	Syntax awk, Found: {$10} at 26 , Len 3
$[A-Za-z]\:$$[A-Za-z]+$\.$[A-Za-z]+$	MS DOS file names c:file.txt	Syntax emacs, Found: {c:file.txt} at 19 , Len 10
[_a-z0-9-]+(\.[_a-z0-9-]+)@[a-z0-9-]+(\.[a-z0-9-]+)	Find email address username@servername.com	Syntax awk, Found: {username@servername.com} at 38 , Len 23
[_a-z0-9-]+(\.[_a-z0-9-]+)@[a-z0-9-]+(\.[a-z0-9-]+)	Find email address name.department@servername.com	Syntax awk, Found: {name.department@servername.com} at 38 , Len 30
Chapter [0-9]	Chapter X, Chapter 1, bla-bla-bla	Syntax emacs, Found: {Chapter 1} at 12 , Len 9
Chapter [^0-9]	Chapter 1, Chapter X, bla-bla-bla	Syntax emacs, Found: {Chapter X} at 12 , Len 9
a+x	ax, bx, aax, abx, bax, bbx, aaax, aabx, abax, abbx, baax, babx, bbax, bbbx, aaaax ....	Syntax emacs, Found: {ax} at 1 , Len 2
[abcde]x	ax, bx, cx, dx, ex	Syntax emacs, Found: {ax} at 1 , Len 2
[a-e]x	ax, bx, cx, dx, ex	Syntax emacs, Found: {ax} at 1 , Len 2
[-ae]x	ax, bx, cx, dx, ex	Syntax emacs, Found: {ax} at 1 , Len 2
[ae-]x	-x, ax, ex	Syntax emacs, Found: {-x} at 1 , Len 2
[ae-]x	-x, ax, ex,	Syntax emacs, Found: {-x} at 2 , Len 2
[a-e-[bd]]x	ax, cx, ex	Fail {ax, cx, ex}
[^0-9]x	any non-digit character followed by the character ZY6x ZCVx BBB	Syntax emacs, Found: {Vx} at 59 , Len 2
[0-9]x	any digit character followed by the character ZY6x ZCVx BBB	Syntax emacs, Found: {6x} at 50 , Len 2
\Dx	any non-digit character followed by the character Bx9 BBxF	Fail { any non-digit character followed by the character Bx9 BBxF}
.abc.	1x2abc, abc1x2, z3456abchooray ....	Syntax emacs, Found: {1x2abc, abc1x2, z3456abchooray ....} at 1 , Len 35
[0-9][0-9]	two digits 98 bbbb	Syntax emacs, Found: {98} at 12 , Len 2
ab{2}x	abbx	Syntax posix_awk, Found: {abbx} at 1 , Len 4
ab{2,4}x	abbx, abbbx, abbbbx	Syntax posix_awk, Found: {abbx} at 1 , Len 4
ab{2,}x	abbx, abbbx, abbbbx ....	Syntax posix_awk, Found: {abbx} at 1 , Len 4
(ab){2}x	ababx	Syntax posix_awk, Found: {ababx} at 1 , Len 5
a*	aaabc	Syntax emacs, Found: {aaa} at 1 , Len 3
abc	abc	Syntax emacs, Found: {abc} at 1 , Len 3
abc	xbc	Fail {xbc}
abc	axc	Fail {axc}
abc	abx	Fail {abx}
abc	xabcy	Syntax emacs, Found: {abc} at 2 , Len 3
abc	ababc	Syntax emacs, Found: {abc} at 3 , Len 3
*abc**	abc	Syntax emacs, Found: {abc} at 1 , Len 3
*abbc**	abc	Syntax emacs, Found: {abc} at 1 , Len 3
*abbc**	abbc	Syntax emacs, Found: {abbc} at 1 , Len 4
*abbc**	abbbbc	Syntax emacs, Found: {abbbbc} at 1 , Len 6
ab+bc	abbc	Syntax emacs, Found: {abbc} at 1 , Len 4
ab+bc	abc	Fail {abc}
ab+bc	abq	Fail {abq}
ab+bc	abbbbc	Syntax emacs, Found: {abbbbc} at 1 , Len 6
ab?bc	abbc	Syntax emacs, Found: {abbc} at 1 , Len 4
ab?bc	abc	Syntax emacs, Found: {abc} at 1 , Len 3
ab?bc	abbbbc	Fail {abbbbc}
ab?c	abc	Syntax emacs, Found: {abc} at 1 , Len 3
^abc$	abc	Syntax emacs, Found: {abc} at 1 , Len 3
^abc$	abcc	Fail {abcc}
^abc	abcc	Syntax emacs, Found: {abc} at 1 , Len 3
^abc$	aabc	Fail {aabc}
abc$	aabc	Syntax emacs, Found: {abc} at 2 , Len 3
^	abc	Fail {abc}
$	abc	Fail {abc}
a.c	abc	Syntax emacs, Found: {abc} at 1 , Len 3
a.c	axc	Syntax emacs, Found: {axc} at 1 , Len 3
*a.c**	axyzc	Syntax emacs, Found: {axyzc} at 1 , Len 5
*a.c**	axyzd	Fail {axyzd}
a[bc]d	abc	Fail {abc}
a[bc]d	abd	Syntax emacs, Found: {abd} at 1 , Len 3
a[b-d]e	abd	Fail {abd}
a[b-d]e	ace	Syntax emacs, Found: {ace} at 1 , Len 3
a[b-d]	aac	Syntax emacs, Found: {ac} at 2 , Len 2
a[-b]	a-	Syntax emacs, Found: {a-} at 1 , Len 2
a[b-]	a-	Syntax emacs, Found: {a-} at 1 , Len 2
[k]	ab	Fail {ab}
a[b-a]	-	Fail {-}
a[]b	-	Fail {-}
a[	-	Fail {-}
a]	a]	Syntax emacs, Found: {a]} at 1 , Len 2
a[]]b	a]b	Syntax emacs, Found: {a]b} at 1 , Len 3
a[^bc]d	aed	Syntax emacs, Found: {aed} at 1 , Len 3
a[^bc]d	abd	Fail {abd}
a[^-b]c	adc	Syntax emacs, Found: {adc} at 1 , Len 3
a[^-b]c	a-c	Fail {a-c}
a[^]b]c	a]c	Fail {a]c}
a[^]b]c	adc	Syntax emacs, Found: {adc} at 1 , Len 3
ab\|cd	abc	Syntax awk, Found: {ab} at 1 , Len 2
ab\|cd	abcd	Syntax awk, Found: {ab} at 1 , Len 2
()ef	def	Syntax awk, Found: {ef} at 2 , Len 2
()*	-	Fail {-}
*a	-	Fail {-}
^*	-	Fail {-}
$*	-	Fail {-}
*()b**	-	Fail {-}
$b	b	Fail {b}
a\	-	Fail {-}
a\(b	a(b	Syntax awk, Found: {a(b} at 1 , Len 3
*a\(b**	ab	Syntax awk, Found: {ab} at 1 , Len 2
*a\(b**	a((b	Syntax awk, Found: {a((b} at 1 , Len 4
a\\b	a\b	Syntax emacs, Found: {a\b} at 1 , Len 3
abc)	-	Fail {-}
(abc	-	Fail {-}
((a))	abc	Syntax awk, Found: {a} at 1 , Len 1
(a)b(c)	abc	Syntax awk, Found: {abc} at 1 , Len 3
a+b+c	aabbabc	Syntax emacs, Found: {abc} at 5 , Len 3
a**	-	Fail {-}
*a?**	-	Fail {-}
(a)	-	Fail {-}
*(a)+**	-	Fail {-}
(a\|)*	-	Fail {-}
(a\|b)	-	Fail {-}
(a+\|b)*	ab	Syntax awk, Found: {ab} at 1 , Len 2
(a+\|b)+	ab	Syntax awk, Found: {ab} at 1 , Len 2
(a+\|b)?	ab	Syntax awk, Found: {a} at 1 , Len 1
[^ab]*	cde	Syntax emacs, Found: {cde} at 1 , Len 3
(^)*	-	Fail {-}
(ab\|)*	-	Fail {-}
)(	-	Fail {-}
	abc	Fail {abc}
abc		Fail {}
a*		Fail {}
abcd	abcd	Syntax emacs, Found: {abcd} at 1 , Len 4
a(bc)d	abcd	Syntax awk, Found: {abcd} at 1 , Len 4
*([abc])d**	abbbcd	Syntax awk, Found: {abbbcd} at 1 , Len 6
*([abc])bcd**	abcd	Syntax awk, Found: {abcd} at 1 , Len 4
a\|b\|c\|d\|e	e	Syntax awk, Found: {e} at 1 , Len 1
(a\|b\|c\|d\|e)f	ef	Syntax awk, Found: {ef} at 1 , Len 2
((a\|b))	-	Fail {-}
*abcdefg**	abcdefg	Syntax emacs, Found: {abcdefg} at 1 , Len 7
ab*	xabyabbbz	Syntax emacs, Found: {ab} at 2 , Len 2
ab*	xayabbbz	Syntax emacs, Found: {a} at 2 , Len 1
(ab\|cd)e	abcde	Syntax awk, Found: {cde} at 3 , Len 3
[abhgefdc]ij	hij	Syntax emacs, Found: {hij} at 1 , Len 3
^(ab\|cd)e	abcde	Fail {abcde}
(abc\|)ef	abcdef	Syntax awk, Found: {ef} at 5 , Len 2
*(a\|b)cd**	abcd	Syntax awk, Found: {bcd} at 2 , Len 3
*(ab\|ab)bc**	abc	Syntax awk, Found: {abc} at 1 , Len 3
a([bc])c	abc	Syntax awk, Found: {abc} at 1 , Len 3
*a([bc])(cd)*	abcd	Syntax awk, Found: {abcd} at 1 , Len 4
*a([bc]+)(cd)**	abcd	Syntax awk, Found: {abcd} at 1 , Len 4
*a([bc])(c+d)**	abcd	Syntax awk, Found: {abcd} at 1 , Len 4
*a[bcd]dcdcde**	adcdcde	Syntax emacs, Found: {adcdcde} at 1 , Len 7
a[bcd]+dcdcde	adcdcde	Fail {adcdcde}
*(ab\|a)bc**	abc	Syntax awk, Found: {abc} at 1 , Len 3
((a)(b)c)(d)	abcd	Syntax awk, Found: {abcd} at 1 , Len 4
[ -~]*	abcy	Syntax emacs, Found: {abc} at 1 , Len 3
[ -~ -~]*	abc	Syntax emacs, Found: {abc} at 1 , Len 3
[ -~ -~ -~]*	abc	Syntax emacs, Found: {abc} at 1 , Len 3
[ -~ -~ -~ -~]*	abc	Syntax emacs, Found: {abc} at 1 , Len 3
[ -~ -~ -~ -~ -~]*	abc	Syntax emacs, Found: {abc} at 1 , Len 3
[ -~ -~ -~ -~ -~ -~]*	abc	Syntax emacs, Found: {abc} at 1 , Len 3
[ -~ -~ -~ -~ -~ -~ -~]*	abc	Syntax emacs, Found: {abc} at 1 , Len 3
[a-zA-Z_][a-zA-Z0-9_]*	alpha	Syntax emacs, Found: {alpha} at 1 , Len 5
^a(bc+\|b[eh])g\|.h$	abh	Syntax awk, Found: {bh} at 2 , Len 2
*(bc+d$\|efg.\|h?i(j\|k))**	effgz	Syntax awk, Found: {effgz} at 1 , Len 5
*(bc+d$\|efg.\|h?i(j\|k))**	ij	Syntax awk, Found: {ij} at 1 , Len 2
*(bc+d$\|efg.\|h?i(j\|k))**	effg	Fail {effg}
*(bc+d$\|efg.\|h?i(j\|k))**	bcdd	Fail {bcdd}
*(bc+d$\|efg.\|h?i(j\|k))**	reffgz	Syntax awk, Found: {effgz} at 2 , Len 5
((((((((((a))))))))))	-	Fail {-}
(((((((((a)))))))))	a	Syntax awk, Found: {a} at 1 , Len 1
multiple words of text	uh-uh	Fail {uh-uh}
multiple words	multiple words, yeah	Syntax emacs, Found: {multiple words} at 1 , Len 14
*(.)c(.)*	abcde	Syntax awk, Found: {abcde} at 1 , Len 5
*$(.), (.)$*	(a, b)	Syntax awk, Found: {(a, b)} at 1 , Len 6

	prolog_main():- syspath ( PATH , _ ), format ( RESULTFILE , "%sRegexpression_results.txt" , PATH ), tell ( RESULTFILE ), write ( "EZY PROLOG Regular Expressions test\n" ), print_regexp_test_header , MAX = 1 , for ( I , 1 , MAX ), nl , write ( "Running test " , I , " of " , MAX ),nl , regexp_test , pie_process_events , I = MAX , told (), write ( "Test completed - see results in " , RESULTFILE ),nl , file_str ( RESULTFILE , RESULTS ), write ( RESULTS ),nl , ! .
	regexp_test():- write ( "Possible Regular Expression syntax:" ), nl , regexp_syntax_values ( SYNTAX ), write ( "" , SYNTAX ),nl , fail . regexp_test():- write ( "Start test" ),nl , syspath ( PATH , _ ), format ( FULLNAME , "%sRegexpression_Tests.txt" , PATH ), write ( "Regexp file:" , FULLNAME ),nl , see ( FULLNAME ), repeat , readln ( Line ), regular_expression_extract( Line , REGESP , STRING ), write ( "/***EVALUATE/\nRegular Expression:" , REGESP ),nl , write ( "String:" , STRING ),nl , regular_expression_evaluate( STRING , REGESP , RESULT ), write ( "Results:" , RESULT ),nl , end_of_file ( FULLNAME ), ! . regexp_test():-! .
	regular_expression_extract( LINE , REGESP , STRING ):- searchstring ( LINE , "" , POS ), P = POS + 1 , frontstr ( P , LINE , REGESP , S1 ), frontchar ( S1 , _ , STRING ), ! . regular_expression_extract( Line , Line , "Failed" ):- ! .
	regular_expression_evaluate( STRING , REGESP , RESULT ):- regexp_syntax_values ( SYNTAX_LIST ), found_regexp_syntax( SYNTAX_LIST , STRING , REGESP , RESULT ), ! . regular_expression_evaluate( STRING , _ , RESULT ):- format ( RESULT , "Fail in {%s}" , STRING ), ! .
	found_regexp_syntax([], _ , _ , _ ):-! ,fail . found_regexp_syntax([ SYNTAX \|_], STRING , REGESP , RESULT ):- regexp_search ( SYNTAX , STRING , REGESP , FOUNDPOS , LENGTH ), LENGTH > 0 , substring ( STRING , FOUNDPOS , LENGTH , FOUND_STRING ), format ( RESULT , "Syntax [%], Found: {%s} at % , Len % " , SYNTAX , FOUND_STRING , FOUNDPOS , LENGTH ), ! . found_regexp_syntax([ _ \|SYNTAX_LIST], STRING , REGESP , RESULT ):- found_regexp_syntax( SYNTAX_LIST , STRING , REGESP , RESULT ), ! .
	print_regexp_test_header():- write ( "This is a test for Pattern Search via Regular Expressions" ), nl , regexp_version ( VERSION ), write ( "Regular expression engine: " , VERSION ), nl , ! .