# An obsession with data (normalization)
=> .. Up a Level

# Go through all the files in the combined and pull out the first column (the filename).

while () { # Clean up the line. chomp;

```
# Pull out the fist column.
my @p = split(/t/);
my $f = $p[0];

# Test to see if the file exists.
if (! -f $f)
{
	# The file doesn't exist, so complain.
	print STDERR "Can't find $fn";
}
```

}

## Keep track of files we've already seen.

%seen = ();

## Go through the input.

while () { # Clean up the input line. chomp;

```
# Split out the columns.
my @p = split(/t/);

# If we already saw it, tell the user we skipped it. If not, then
# print it out and add it to the hash so we don't print it again.
if (exists $seen{$p[0]})
{
	print STDERR "Skipping $p[0]n";
}
else
{
	print "$_n";
	$seen{$p[0]} = 1;
}
```

}

> In Miw?fu, they call those who cannot use magic `miw: bachir?ma`. Translated into Lorban, it means “cursed to be forever mundane.” – Awakened Magic, Dastor Malink $

## 

## Setup

## 

## Directives

use strict; use warnings;

## 

## Parameters

## 

## The first parameter is the directory.

my $dir = $ARGV[0];

die “USAGE: dir input” unless -d $dir;

my $input = $ARGV[1];

die “USAGE: dir input” unless -f $input;

## 

## Slurp up the contents of the file.

## 

my %files = ();

open FILES, "<$input" or die "Cannot open input $input ($!)";

while () { chomp; my @p = split(/t/); $files{$p[0]} = $p[1]; }

close FILES;

## 

## Get a list of all the files in the directory.

## 

open PIPE, “find ‘$dir’ -type f |” or die "Cannot open pipe ($!)";

while () { # Clean up the line. chomp;

```
# Ignore . files.
next if m@/.@;
next unless m@.txt$@;

# Trim off the leading characters.
s@./@@;

# See if the file exists.
my $file = $_;

if (exists $files{$file})
{
	# We found the file.
	my $date = $files{$file};
	print "HIT  $date $filen";

	# Pull out the entries so we can report what was missing after
	# we're done processing.
	delete $files{$file};

	# Open up the file and read in the metadata section, looking
	# for an already existing date.
	my $found_date = 0;

	open FILE, "<$file" or die "Cannot open $file ($!)";

	while ()
	{
		# Clean up the line.
		chomp;

		if (m@^* Date:s*(.*?)$@)
		{
			my $old_date = $1;

			$found_date = 1;

			if ($date eq $old_date)
			{
				# Nothing to do, we're good.
				last;
			}

			print "       $1n";

		}
	}

	close FILE;

	# If we didn't find the date, we need to add it into the file.
	unless ($found_date)
	{
		my $need_date = 1;

		print "       Date: $daten";

		open IN, "tmp" or die "Cannot open tmp ($!)";

		while ()
		{
			print OUTPUT $_;

			if ($need_date && $_ =~ /^= /)
			{
				print OUTPUT "* Date: $daten";
				$need_date = 0;
			}
		}

		close IN;
		close OUTPUT;

		rename($file, "$file.bak");
		rename("tmp", $file);
	}
}
else
{
	# Print the file.
	#print "SKIP $_n";
}
```

}

close PIPE;

## Write out any remaining files.

foreach my $file (sort(keys(%files))) { print “MISS $filen”; }


# Metadata

Categories:

=> /categories/programming/ Programming
=> /categories/writing/ Writing

Tags:

=> /tags/perl/ Perl

# Footer

Below are various useful links within this site and to related sites (not all have been converted over to Gemini).

=> /now/ Now
=> /contact/ Contact
=> /bio/ Biography
=> /bibliography/ Bibliography
=> /support/ Support

=> /fiction/ Fiction
=> //fedran.com/ Fedran
=> https://mfgames.com/ Coding
=> https://moonfire.us/ The Moonfires

=> /categories/ Categories
=> /tags/ Tags

=> /privacy/ Privacy
=> /colophon/ Colophon
=> /license/ License

=> https://lists.typewriter.press/subscription?f=RDQ6f3AFHXnX2o763d5TgUmaYP7N763gR6FjZyGUUFWhyRkpgZF9I35ySICDBEdFFtgG Mailing List

=> https://d.moonfire.us/blog/2012/04/29/an-obsession-with-data-normalization/