#!/usr/bin/env perl

###############################################################################################
# This script was written for www.philforhumanity.com.
# If you have any questions, issues, or enhancement requests, please contact us via the website.
# Use this script at your own risk.
###############################################################################################

# regrep version 1.2

$|=1;    # set output buffering to off
$[=0;    # set array base to 0
$,=" ";  # set output field separator
$\="\n";  # set output record separator
 
use Getopt::Long;
use File::Basename;
#use File::which;
 
my ($list,$edit,$verbose,$nocase,$help,$debug,$pattern);
my $editor = "kate";
 
# Get arguments
GetOptions (
 'list'       => \$list,
 'edit'       => \$edit,
 'verbose'    => \$verbose,
 'nocase'     => \$nocase,
 'help'       => \$help,
 'pattern=s'       => \$pattern,
 'debug'      => \$debug
);

# If "-help" is the only argument, then print the usage and exit.
if ($help == 1) 
{
  &usage;
  exit;
};
 
# Check the number of arguments, and exit with usage if no arguments
my $number_of_arguments = scalar(@ARGV);
&usage("ERROR: Incorrect number of arguments.") if (scalar(@ARGV)<1);
 
# If "-nocase" argument is used, then see flag to "-i" for grep, otherwise set flag to nothing.
my $nocaseflag = (defined $nocase ? '-i' : '');
 
#if no file pattern is specified, default to *
$pattern = $pattern || '*';
 
# Define query word
my $grep_query = $ARGV[0];
 
# If more than one argument, then collect the paths to search in
my @paths_to_search = (".");  # Default is the current directory
if ($number_of_arguments > 1)
{
  # Remove first argument, since it is not a path and we collected that data already.
  shift @ARGV;

  # Save paths to a meaningful variable name, and overwrite default value
  @paths_to_search = @ARGV;
}
 
# Query each path for files only
my @list_of_files = ();
my $path;
foreach $path (@paths_to_search)
{
  @list_of_files = (@list_of_files, `find $path -type f -name '$pattern' -print`);
}

my $file_found;
`file .`; # Since Git Bash does not have the file command, test if it exists.
if ($?)
{
  $file_found = 0; # Not found
}
else
{
  $file_found = 1; # Found
}

# For each file found, find which files are text files and then grep only text files
my $file;
my $find_output;
my $found = 0;
my @grep_output;
my $line;
my @foundfiles;
my $matchcount=0;
chomp @list_of_files;
foreach $file (@list_of_files)
{
  #skip editor backup files, or zip files
  next if ($file =~ /(~|\.bak|\.zip|\.gz|\.msi|\.doc|\.xls)$/);
   # Debug line
# print "file=$file";

  if ($file_found == 1)
  {
    @grep_output = `file "$file"`;
    $find_output = @grep_output[0];
    if ($find_output !~ /text/)
    {
     next;
    }
  }

  # Grep for data (-n is for line numbers)
  @grep_output = `grep -n $nocaseflag $grep_query "$file"`;  # Was fgrep
 
  # Output data if grep found something
  if (@grep_output)
  {
    chomp(@grep_output);
    if ($verbose) 
    {
      print "==================================================================";
      print "File: $file";
 	}
    push(@foundfiles,$file);
    $matchcount += scalar(@grep_output);
    foreach $line (@grep_output)
    {
      print $line if ($verbose);
    }
    $found = 1;
  }
}
 
# Print ending delimiter if anything was found
if ($found == 1)
{
  my $matchfiles = scalar(@foundfiles);
  print "==================================================================" if ($verbose);
  print qq{$matchcount matches in $matchfiles files};

  #if the --list option was specified, display a list of all the matching files
  if ($list) 
  {
    print qq{Matched files:};
    foreach (@foundfiles) 
    {
 	  print "   $_";
    }
  }
  if ($edit)
  {
    `$editor @foundfiles`;
  }
}
 
sub usage 
{
   my $message = shift;
   print qq{\n$message} if ($message);
   my $script = basename($0);
   print qq{
   USAGE: $script <word> [path1] [path2] ... [options]

   options:
    -verbose      - display the matched lines for each file searched.
    -list         - list the files that have matching text.
    -edit         - open the matching files in an editor.
    -nocase       - performs a case insensitive search.
    -pattern=STR  - only searches files that have filenames containing a string of user's choice.

   The default path is the current directory.
   Spaces must be escaped to be included in the search string.
   Files ending in '~', '.zip' or '.gz' are automatically ignored.

   examples:
    $script 'Time\\ Clock' --list (searches files for the string "Time Clock" and displays a list of files that have matching text)
    $script Groucho --edit (searches files for the string "Groucho" and opens the files in an editor)
    $script Groucho --edit --nocase (searches files for the string "Groucho" (case insensitive) and opens the files in an editor)
    $script Harpo   --verbose (searches files for the string "Harpo" and displays all the matches to the screen)
    $script -pattern=*txt* TODAY (searches all files that have "txt" in their filenames for the string "TODAY")
   };
   exit 1;
}#sub
 
# Exit
exit 0;