#!/usr/bin/env perl

use 5.010;
use warnings;
use strict;

my $n; # line no
while (my $x = <DATA>) {
    chomp $x;
    say $x;
    while (
        $x =~ m/
        ([[:punct:]]*)      # $1: leading punct marks
        (                   # $2: a "word" consisting of
            (?: [[:word:]']+ - )* # optional segments with
                                  # embedded {'}s ending with
                                  # single {-}
            [[:word:]]+     # and ending in pure word characters
        )
        ([[:punct:]]* \ ? )   # $3: trailing punct marks ending
                              # with space (except at end of
                              # line?)
        /xxg
    )
    {
        printf "  %3s {%s|%s|%s}\n", ++$n,
            # make whitespace visible
            map {(my $y = $_ // '') =~ tr/ /_/; $y}  $1, $2, $3;
    }
}
__DATA__
"'Uncouth' about sums it up."
The word they will use is 'uncouth'.
"It's the old story."
It's a will-o'-the-wisp--a two-fer--and Bob's-yer-uncle at four o'clock.
It's two o'clock--time for a nap.
Remember 45's?
What about (this)?
[Editor's note: blah blah] and so on...
A ... and B
I said--"What's the expression?"

##</code><code>##

"'Uncouth' about sums it up."
    1 {"'|Uncouth|'_}
    2 {|about|_}
    3 {|sums|_}
    4 {|it|_}
    5 {|up|."}
The word they will use is 'uncouth'.
    6 {|The|_}
    7 {|word|_}
    8 {|they|_}
    9 {|will|_}
   10 {|use|_}
   11 {|is|_}
   12 {'|uncouth|'.}
"It's the old story."
   13 {"|It|'}                    <- should be {"|It's|_}
   14 {|s|_}
   15 {|the|_}
   16 {|old|_}
   17 {|story|."}
It's a will-o'-the-wisp--a two-fer--and Bob's-yer-uncle at four o'clock.
   18 {|It|'}                              <- same problem
   19 {|s|_}
   20 {|a|_}
   21 {|will-o'-the-wisp|--}     <- perfect!
   22 {|a|_}
   23 {|two-fer|--}
   24 {|and|_}
   25 {|Bob's-yer-uncle|_}
   26 {|at|_}
   27 {|four|_}
   28 {|o|'}                            <- should be {|o'clock|.}
   29 {|clock|.}
It's two o'clock--time for a nap.
   30 {|It|'}
   31 {|s|_}
   32 {|two|_}
   33 {|o|'}                            <- should be {|o'clock|--}
   34 {|clock|--}
   35 {|time|_}
   36 {|for|_}
   37 {|a|_}
   38 {|nap|.}
Remember 45's?
   39 {|Remember|_}
   40 {|45|'}                                 <-
   41 {|s|?}
What about (this)?
   42 {|What|_}
   43 {|about|_}
   44 {(|this|)?}
[Editor's note: blah blah] and so on...
   45 {[|Editor|'}                           <-
   46 {|s|_}
   47 {|note|:_}
   48 {|blah|_}
   49 {|blah|]_}
   50 {|and|_}
   51 {|so|_}
   52 {|on|...}
A ... and B
   53 {|A|_}           <- correct to omit detached elipsis
   54 {|and|_}
   55 {|B|}
I said--"What's the expression?"
   56 {|I|_}
   57 {|said|--"}             <- should be {|said|--}
   58 {|What|'}               <- should be {"|What's|_}
   59 {|s|_}
   60 {|the|_}
   61 {|expression|?"}