问用于匹配对象尺寸的正则表达式

EN

#!/usr/local/bin/perl 
use Modern::Perl;
use Test::More;

my $re1 = qr/\d+(?:\.\d+)?[\s-]*(?:\d+)?(?:\/\d+)?(?:cm|mm|yd|"|'|feet)/;
my $re2 = qr/(?:\s*x\s*|\s*by\s*)/;
my $re3 = qr/\d+(?:\.\d+)?[\s-]*(?:\d+)?(?:\/\d+)?(?:cm|mm|yd|"|'|feet|frames)/;
my @out = (
'11 1/2" x 32"',
'8 x 10-3/5',
'22" x 17"',
'42 1/2" x 60 yd',
'5.76 by 8 frames',
'84cm',
'13/19"',
'86 cm',
'12 yd',
'99 cm',
'no match',
'22" x 17" x 12 cm',
'no match',
'no match',
'no match',
);
my $i = 0;
my $xx = '22" x 17"';
while(<DATA>) {
    chomp;
    if (/($re1(?:$re2$re3)?(?:$re2$re1)?)/) {
        ok($1 eq $out[$i], $1 . ' in ' . $_);
    } else {
        ok($out[$i] eq 'no match', ' got "no match" in '.$_);
    }
    $i++;
}
done_testing;


__DATA__
Hello blah blah. It's around 11 1/2" x 32".
The dimensions are 8 x 10-3/5!
Probably somewhere in the region of 22" x 17".
The roll is quite large: 42 1/2" x 60 yd.
They are all 5.76 by 8 frames.
Yeah, maybe it's around 84cm long.
I think about 13/19".
No, it's probably 86 cm actually.
The last but one test case is 12 yd x.
The last test case is 99 cm by.
This sentence doesn't have dimensions in it: 342 / 5553 / 222.
Three dimensions? 22" x 17" x 12 cm
This is a product code: c720 with another number 83 x better.  
A number on its own 21.
A volume shouldn't match 0.332 oz.

#   Failed test ' got "no match" in The dimensions are 8 x 10-3/5!'
#   at C:\tests\perl\test6.pl line 42.
#   Failed test ' got "no match" in They are all 5.76 by 8 frames.'
#   at C:\tests\perl\test6.pl line 42.
# Looks like you failed 2 tests of 15.
ok 1 - 11 1/2" x 32" in Hello blah blah. It's around 11 1/2" x 32".
not ok 2 -  got "no match" in The dimensions are 8 x 10-3/5!
ok 3 - 22" x 17" in Probably somewhere in the region of 22" x 17".
ok 4 - 42 1/2" x 60 yd in The roll is quite large: 42 1/2" x 60 yd.
not ok 5 -  got "no match" in They are all 5.76 by 8 frames.
ok 6 - 84cm in Yeah, maybe it's around 84cm long.
ok 7 - 13/19" in I think about 13/19".
ok 8 - 86 cm in No, it's probably 86 cm actually.
ok 9 - 12 yd in The last but one test case is 12 yd x.
ok 10 - 99 cm in The last test case is 99 cm by.
ok 11 -  got "no match" in This sentence doesn't have dimensions in it: 342 / 5553 / 222.
ok 12 - 22" x 17" x 12 cm in Three dimensions? 22" x 17" x 12 cm
ok 13 -  got "no match" in This is a product code: c720 with another number 83 x better.  
ok 14 -  got "no match" in A number on its own 21.
ok 15 -  got "no match" in A volume shouldn't match 0.332 oz.
1..15

foundMatch = Regex.IsMatch(SubjectString, @"\d+(?: |cm|\.|""|/)[\d/""x -]*(?:\b(?:by\s*\d+|cm|yd)\b)?");

"
\d             # Match a single digit 0..9
   +              # Between one and unlimited times, as many times as possible, giving back as needed (greedy)
(?:            # Match the regular expression below
                  # Match either the regular expression below (attempting the next alternative only if this one fails)
      \           # Match the character “ ” literally
   |              # Or match regular expression number 2 below (attempting the next alternative only if this one fails)
      cm          # Match the characters “cm” literally
   |              # Or match regular expression number 3 below (attempting the next alternative only if this one fails)
      \.          # Match the character “.” literally
   |              # Or match regular expression number 4 below (attempting the next alternative only if this one fails)
      ""          # Match the character “""” literally
   |              # Or match regular expression number 5 below (the entire group fails if this one fails to match)
      /           # Match the character “/” literally
)
[\d/""x -]        # Match a single character present in the list below
                  # A single digit 0..9
                  # One of the characters “/""x”
                  # The character “ ”
                  # The character “-”
   *              # Between zero and unlimited times, as many times as possible, giving back as needed (greedy)
(?:               # Match the regular expression below
   \b             # Assert position at a word boundary
   (?:            # Match the regular expression below
                  # Match either the regular expression below (attempting the next alternative only if this one fails)
         by       # Match the characters “by” literally
         \s       # Match a single character that is a “whitespace character” (spaces, tabs, line breaks, etc.)
            *     # Between zero and unlimited times, as many times as possible, giving back as needed (greedy)
         \d       # Match a single digit 0..9
            +     # Between one and unlimited times, as many times as possible, giving back as needed (greedy)
      |           # Or match regular expression number 2 below (attempting the next alternative only if this one fails)
         cm       # Match the characters “cm” literally
      |           # Or match regular expression number 3 below (the entire group fails if this one fails to match)
         yd       # Match the characters “yd” literally
   )
   \b             # Assert position at a word boundary
)?                # Between zero and one times, as many times as possible, giving back as needed (greedy)
"

\d.*\d(?:\s+\S+|\S+)

\d        # One digit.
.*        # Any number of characters.
\d        # One digit. All joined means to find all content between first and last digit.
\s+\S+    # A non-space characters after some space. It tries to match any unit like 'cm' or 'yd'.
|         # Or. Select one of two expressions between parentheses.
\S+       # Any number of non-space characters. It tries to match double-quotes, or units joined to the 
          # last number.

use warnings;
use strict;

while ( <DATA> ) {
        print qq[$1\n] if m/(\d.*\d(\s+\S+|\S+))/
}

__DATA__
Hello blah blah. It's around 11 1/2" x 32".
The dimensions are 8 x 10-3/5!
Probably somewhere in the region of 22" x 17".
The roll is quite large: 42 1/2" x 60 yd.
They are all 5.76 by 8 frames.
Yeah, maybe it's around 84cm long.
I think about 13/19".
No, it's probably 86 cm actually.

perl script.pl

11 1/2" x 32".
8 x 10-3/5!
22" x 17".
42 1/2" x 60 yd.
5.76 by 8 frames.
84cm
13/19".
86 cm