#!/usr/bin/perl

# Program:  find-new-files.perl
# Purpose:  initialize and maintain a record of files in a
#           directory tree
# Written by:  dave graff

# If a file called "paths.logged" does not exist in the cwd, we create
# one, and treat all contents under cwd as "new".  If "paths.logged"
# already exists, we find directories with modification dates more
# recent than this file, and treat only these as "new".

# For each "new" directory, assume a file.manifest is there (create an
# empty one if there isn't one), and diff that file against the current
# inventory of data files, storing all new files to an array.

# Of course, this will fail in all paths where the current user does
# not have write permission, but such paths can be avoided by adding
# a suitable condition to the first "find" command.

use strict;

my $path_log = "paths.logged";
my ($list_name,$new_list) = ("file.manifest","new.manifest");
my $new_flag = ( -e $path_log ) ? "-newer $path_log" : "";
my @new_dirs = `find . -type d $new_flag`;
#  add "-user uname" and/or "-group gname" to avoid directories where
#  the current user might not have write permission

my $diff_cmd =
    "cd 'THISPATH' && touch $list_name && ".
    "find . -type f -maxdepth 1 | tee $new_list | diff - $list_name | grep '<'";

# the shell functions in $diff_cmd will:
#  - chdir to a given path,
#  - create file.manifest there if it does not yet exist,
#  - find data files in that path (not subdirs, not files in subdirs),
#  - create a "new.manifest" file containing this current file list,
#  - diff the new list of files against the existing file.manifest,
#  - return only current files not found in the existing manifest.
# since it's a sub-shell, the chdir is forgotten when the sub-shell is done.

open( OUT, ">new-file-path.list" );

foreach my $path ( @new_dirs ) {
    chomp $path;
    my $cmd = $diff_cmd;
    $cmd =~ s{THISPATH}{$path}g;

# the output of the shell command needs to be conditioned to have the
# path string prepended to each file name (we can leave the new-line
# in place at the end of the name):

    print OUT join "", map { s{^< \.(.*)}{$path$1}; $_ } ( `$cmd` );

# replace the old manifest:
    rename "$path/$new_list", "$path/$list_name" or
        warn "failed to update $path/$list_name\n";
}

close OUT;

`touch $path_log`;