slp_misc/nb2nikola-rev2.pl

#!/usr/bin/perl -w
use strict;
use Date::Manip;
use Unicode::Normalize;

sub slugify($) {
    my ($input) = @_;

    $input = NFKD($input);         # Normalize the Unicode string
    $input =~ tr/\000-\177//cd;    # Strip non-ASCII characters (>127)
    $input =~ s/[^\w\s-]//g;       # Remove all characters that are not word characters (includes _), spaces, or hyphens
    $input =~ s/^\s+|\s+$//g;      # Trim whitespace from both ends
    $input = lc($input);
    $input =~ s/[-\s]+/-/g;        # Replace all occurrences of spaces and hyphens with a single hyphen

    return $input;
}

my %catlist = (
    1 => "photos",
    2 => "free_software",
    3 => "old_advogato",
    4 => "old_diaryland",
    5 => "life_and_bs",
    6 => "writings",
    7 => "project365",
    8 => "food"
);

Date_Init();

while (<STDIN>) {
    chomp;
    
    my ($fname, $cat) = split(/>/, $_);

    my @cats = split(/,/, $cat);

    for (my $i = 0; $i < scalar(@cats) ; $i++) {
	$cats[$i] = $catlist{$cats[$i]};
    }
    
    my ($title, $date, $slug, $author, $desc, $format, $body);

    $body = "";
    
    open INFILE, "<$fname";
    while (<INFILE>) {
	if ($_ =~ /TITLE:\s*(.*)/) {
	    $title = $1;
	    $slug = slugify($title);
	} elsif ($_ =~ /DATE:\s*(.*)@(.*)/) {
	    $date = new Date::Manip::Date;	    
	    $date->parse("$1 $2");
	} elsif ($_ =~ /AUTHOR:\cs*(.*)/) {
	    $author = $1;
	} elsif ($_ =~ /DESC:\s*(.*)/) {
	    $desc = $1;
	} elsif ($_ =~ /FORMAT:\s*(.*)/) {
	    $format = $1;
	} elsif ($_ =~ /BODY:\s*/) {
	    # SKIP
	} elsif ($_ =~ /-----/) {
	    # SKIP
	} elsif ($_ =~ /END-----/) {
	    last;
	} else {
	    $body .= $_;
	}
    }
    close INFILE;

    $fname = $date->printf("%q");
    open OUTFILE, ">$fname-$slug.md";
    print OUTFILE "<!--\n";
    print OUTFILE ".. title: $title\n";
    print OUTFILE ".. slug: $fname-$slug\n";
    print OUTFILE ".. date: " . $date->printf("%Y-%m-%d %H:%M:%S UTC%z") . "\n";
    print OUTFILE ".. tags: " . join(",", @cats) . "\n";    
    print OUTFILE ".. category: blog\n";
    print OUTFILE ".. link: \n";
    print OUTFILE ".. description: $desc\n";
    print OUTFILE ".. type: text\n";
    print OUTFILE "-->\n";
    print OUTFILE $body;
    close OUTFILE;
    

    
}