💾 Archived View for d.moonfire.us › blog › 2012 › 04 › 24 › an-obsession-with-data-git captured on 2022-03-01 at 15:45:32. Gemini links have been rewritten to link to archived content

-=-=-=-=-=-=-

An obsession with data (Git version)

Up a Level

Setup

Directives

use strict; use warnings;

Directory Parsing

Go through all the files in the command-line arguments.

while (@ARGV) { # If it isn't a directory, we don't care. my $dir = shift @ARGV; $dir =~ s@/$@@sg;

if (! -d $dir)
{
	print STDERR "Ignoring $dir (not a directory)n";
	next;
}

my $git_dir = "$dir/.git";

if (! -d $dir)
{
	print STDERR "Ignoring $dir (no .git inside)n";
	next;
}

# We're processing this directory.
print STDERR "Processing $dirn";

# Set the GIT_DIR and GIT_WORK_TREE so we don't have to move into
# that directory.
$ENV{GIT_WORK_TREE} = $dir;
$ENV{GIT_DIR} = $git_dir;

# We want to build up a log of the entire repository. We want to
# know each of the files and date that they were checked in.
my $last_timestamp;
my %files = ();

open GIT, "git log --name-only --pretty=%ai |"
	or die "Cannot open Git for $dir ($!)";

while ()
{
	# Clean up the line and ignore blanks.
	chomp;
	next if /^s*$/;

	# In general, we will have two types of lines. One is in a
	# timestamp and the other is the name of the file.
	if (/^(d+)-(d+)-(d+) (d+):(d+):(d+)/)
	{
		# We only care about the date of the check-in.
		$last_timestamp = "$1-$2-$3";
	}
	else
	{
		# For everything else, we get a filename. There are a few
		# things that we frequently ignore, such as hidden files
		# (start with a period).
		next if /^./;
		next if m@/.@;

		# We add the file and the current timestamp to the
		# hash. Since we replace with each one, and `git log` goes
		# backwards in time, the last time we see the file is the
		# point it was first added to the repository.

		# Print out the line.
		$files{$_} = $last_timestamp;
	}
}

close GIT;

# Now that we are done parsing, we output the merged results.
open REPORT, ">$dir.files" or die "Cannot write $dir.files ($!)";

foreach my $file (sort(keys(%files)))
{
	# Pull out the date.
	my $date = $files{$file};

	# Keep track if this file exists.
	my $exists = 0;
	$exists = 1 if -f "$dir/$file";

	#print "$filet$daten";
	#print "$datet$existst$filen";
	print REPORT "$filet$existst$daten";
}

close REPORT;

}