use strict;
my $str = 'one trillion
seven hundred twenty two
7even
zero point nine five
nine hundred ninety nine thousand two hundred thirteen';
my $regex = qr/(?x) # free-spacing mode
(?(DEFINE)
# Within this DEFINE block, we'll define many subroutines
# They build on each other like lego until we can define
# a "big number"
(?<one_to_9>
# The basic regex:
# one|two|three|four|five|six|seven|eight|nine
# We'll use an optimized version:
# Option 1: four|eight|(?:fiv|(?:ni|o)n)e|t(?:wo|hree)|
# s(?:ix|even)
# Option 2:
(?:f(?:ive|our)|s(?:even|ix)|t(?:hree|wo)|(?:ni|o)ne|eight)
) # end one_to_9 definition
(?<ten_to_19>
# The basic regex:
# ten|eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen|
# eighteen|nineteen
# We'll use an optimized version:
# Option 1: twelve|(?:(?:elev|t)e|(?:fif|eigh|nine|(?:thi|fou)r|
# s(?:ix|even))tee)n
# Option 2:
(?:(?:(?:s(?:even|ix)|f(?:our|if)|nine)te|e(?:ighte|lev))en|
t(?:(?:hirte)?en|welve))
) # end ten_to_19 definition
(?<two_digit_prefix>
# The basic regex:
# twenty|thirty|forty|fifty|sixty|seventy|eighty|ninety
# We'll use an optimized version:
# Option 1: (?:fif|six|eigh|nine|(?:tw|sev)en|(?:thi|fo)r)ty
# Option 2:
(?:s(?:even|ix)|t(?:hir|wen)|f(?:if|or)|eigh|nine)ty
) # end two_digit_prefix definition
(?<one_to_99>
(?&two_digit_prefix)(?:[- ](?&one_to_9))?|(?&ten_to_19)|
(?&one_to_9)
) # end one_to_99 definition
(?<one_to_999>
(?&one_to_9)[ ]hundred(?:[ ](?:and[ ])?(?&one_to_99))?|
(?&one_to_99)
) # end one_to_999 definition
(?<one_to_999_999>
(?&one_to_999)[ ]thousand(?:[ ](?&one_to_999))?|
(?&one_to_999)
) # end one_to_999_999 definition
(?<one_to_999_999_999>
(?&one_to_999)[ ]million(?:[ ](?&one_to_999_999))?|
(?&one_to_999_999)
) # end one_to_999_999_999 definition
(?<one_to_999_999_999_999>
(?&one_to_999)[ ]billion(?:[ ](?&one_to_999_999_999))?|
(?&one_to_999_999_999)
) # end one_to_999_999_999_999 definition
(?<one_to_999_999_999_999_999>
(?&one_to_999)[ ]trillion(?:[ ](?&one_to_999_999_999_999))?|
(?&one_to_999_999_999_999)
) # end one_to_999_999_999_999_999 definition
(?<bignumber>
zero|(?&one_to_999_999_999_999_999)
) # end bignumber definition
(?<zero_to_9>
(?&one_to_9)|zero
) # end zero to 9 definition
(?<decimals>
point(?:[ ](?&zero_to_9))+
) # end decimals definition
) # End DEFINE
####### The Regex Matching Starts Here ########
^(?&bignumber)(?:[ ](?&decimals))?$
### Other examples of groups we could match ###
#(?&bignumber)
# (?&one_to_99)
# (?&one_to_999)
# (?&one_to_999_999)
# (?&one_to_999_999_999)
# (?&one_to_999_999_999_999)
# (?&one_to_999_999_999_999_999)/mp;
if ( $str =~ /$regex/g ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Perl, please visit: http://perldoc.perl.org/perlre.html