Same code with expanded regex with comments
#!/usr/bin/perl # https://perlmonks.org/?node_id=1224600 use strict; use warnings; use Data::Dump 'dd'; my $data = <<'END'; interface XYZ given param1 -> child of "interface XYZ" given param2 -> child of "interface XYZ" given param2.1 -> child of "given param2" given param2.1.1 -> child of "given param2.1" given param2.1.2 -> child of "given param2.1" given param2.2 -> child of "given param2" given param3 -> child of "interface XYZ" given param4 -> child of "interface XYZ" interface SECOND given param5 -> child of "interface SECOND" END my $struct = buildstruct($data); dd $struct; sub buildstruct { my $block = shift; my @answers; while( $block =~ /^ # make sure to start at beginning of a line (wit +h m) (\ *) # match leading spaces of header line (.*) # match rest of line, save as head \n # and match the newline ( (?: # match all following lines with \1 # same whitespace as head \ + # plus at least one more space ( i.e. indented ) .*\n # contents to be looked at later )* # as many as possible ) # save as rest /gmx ) # global, multiline, and extra whitespace { my ($head, $rest) = ($2, $3); $head =~ s/ ->.*//; push @answers, $rest ? { $head => buildstruct($rest) } : $head; } \@answers; }
I hope this helps :)
The regex matches each line, gets the indentation space string, then also matches all
following lines that are indented that much plus at least one more space.
In reply to Re^3: Parsing by indentation
by tybalt89
in thread Parsing by indentation
by llarochelle
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |