/etc/init.d/multipathd
|-- binary: basename
|-- binary: test
|-- teardown_slaves
|   |-- binary: pwd
|   |-- binary: sed
|   |-- binary: echo
|   |-- binary: readlink
|   |-- function: teardown_slaves
|   |-- binary: sed
|   `-- binary: echo
|-- binary: test
|-- binary: echo
|-- binary: touch
|-- binary: echo
|-- binary: echo
|-- binary: echo
`-- binary: echo

/etc/init.d/multipathd
        Code lines:     102
        Comment lines:  13
        Empty lines:    12
        Total lines:    127
        Function(s):
                teardown_slaves
        Uses function(s):
                teardown_slaves
        Uses binarie(s):
                basename
                echo
                info
                pwd
                readlink
                rm
                sed
                test
                touch
        Uses RPM(s):
                coreutils-5.97-19.el5
                info-4.8-14.el5
                sed-4.1.5-5.fc6

##</code><code>##

-------------------------------------------
Duplicate local function names:
5       stop
5       start
2       status
2       restart
2       condrestart
1       do_restart_sanity_check
1       makedev
1       start_isdnlog
...
-------------------------------------------
Most used functions:
18      stop
12      start
6       restart
4       status
4       invoke_command
...
-------------------------------------------
Most used binaries:
422     echo
72      rm
57      touch
40      grep
36      test
30      awk
...
-------------------------------------------
Most used RPM's:
671     coreutils-5.97-19.el5
50      grep-2.5.1-54.2.el5
30      gawk-3.1.5-14.el5
19      util-linux-2.13-0.50.el5
10      sed-4.1.5-5.fc6
9       file-4.17-15.el5_3.1
4       xorg-x11-xfs-1.0.2-4
...
-------------------------------------------
Total code lines:       4438
Total comment lines:    989
Total empty lines:      705
Total lines:            6132
Total files:            51

##</code><code>##

#!/usr/bin/perl
# Bash Parser v0.9
#
# Creates a dependency and statistics report of a directory with BASH scripts.
#
# Copyright (c) 2009, Michael Persson (mickep76@mac.com)
# All rights reserved.

# Error checking for files

use strict;

# Check arguments
die "usage: bash_reporter directory\n" if $#ARGV;

my $path = $ARGV[0];
die "Please specify a valid directory\n" if not -d $path;

# Ignore functions
our %ignore_functions = (
#  'echo' => 1,
#  'true' => 1
);

# Ignore binaries
our %ignore_binaries = (
#  'sed'  => 1,
#  'awk'  => 1,
#  'echo' => 1,
#  'cut'  => 1
);

# BASH keywords 'compgen -k'
our %bash_keywords = (
  'if'       => 1,
  'then'     => 1,
  'else'     => 1,
  'elif'     => 1,
  'fi'       => 1,
  'case'     => 1,
  'esac'     => 1,
  'for'      => 1,
  'select'   => 1,
  'while'    => 1,
  'until'    => 1,
  'do'       => 1,
  'done'     => 1,
  'in'       => 1,
  'function' => 1,
  'time'     => 1
);

# Global hashes
our %binaries_in_path;
our %binaries_to_rpm;
our %all_sources;
our %all_functions;
our %dependencies;
our %variables;

# Global statistics hashes
our %stat_sources;
our %stat_functions;
our %stat_uses_binaries;
our %stat_uses_functions;
our %stat_uses_rpms;

# Global totals
our $tot_code_lines = 0;
our $tot_comment_lines = 0;
our $tot_empty_lines = 0;
our $tot_lines = 0;
our $tot_files = 0;

# Get all binaries in the PATH
get_binaries();

# Recurse through all files in the path
recurse($path);

# Go through all sourced files
foreach(keys %all_sources) { match($_, 0) }

# Print statistics
print_stat_hash(\%stat_sources, "Most sourced files:");
print_stat_hash(\%stat_functions, "Duplicate local function names:", 1);
print_stat_hash(\%stat_uses_functions, "Most used functions:");
print_stat_hash(\%stat_uses_binaries, "Most used binaries:");
print_stat_hash(\%stat_uses_rpms, "Most used RPM's:");

# Print totals
print_separator();
print "Total code lines:\t$tot_code_lines\n";
print "Total comment lines:\t$tot_comment_lines\n";
print "Total empty lines:\t$tot_empty_lines\n";
print "Total lines:\t\t$tot_lines\n";
print "Total files:\t\t$tot_files\n";

# Get all binaries in the PATH
sub get_binaries {
  foreach my $directory (split ':', $ENV{'PATH'}) {
    foreach(glob("$directory/*")) {
      my $file = $_;
      if(-f $_ && -x $_) { s/.*\///; $binaries_in_path{$_} = $file; }
    }
  }
}

# Recurse through all files in a given path
sub recurse {
  my $path = shift;

  foreach(glob("$path/*")) {
    if(-d $_) { recurse($_) }
    else { match($_, 1) }
  }
}

# Find sources, functions and binaries used in file
sub match {
  my $file = shift;
  my $check_if_bash = shift;

  undef %all_functions;
  undef %dependencies;
  undef %variables;

  my %functions;
  my %sources;
  my %uses_binaries;
  my %uses_functions;
  my %uses_rpms;

  my $function = undef;
  my $line_number = 1;
  my $comment_lines = 0;
  my $empty_lines = 0;
  my $text_block = undef;
  my $function_line = undef;

  open FH, "<$file" or die "Failed to open file $file: $!\n";
  foreach(<FH>) {
    chomp();

    my $ignore_line = 0;

    # Check if file is a Bash script
    if($check_if_bash == 1 && $line_number == 1 && ! /bash/) { return }

    # Count comments and empty lines
    elsif(/(\%\%.*\%\%)/) {
      if($1 eq $text_block) { $text_block = undef }
      else { $text_block = $1; }
    }
    elsif(/^[ \t]*#/) { $comment_lines++; $ignore_line = 1; }
    elsif($text_block) { $ignore_line = 1 }
    elsif($_ eq '') { $empty_lines++ }

    # Get variable assignments
    elsif(/([\w\.\-\_]+)=(.*)/) {
      $variables{$1} = $2;
    }

    # Get files sourced by script
    elsif(/^[ \t]*source +([\w\-\/\.\_]+)/) {
      my $source = expand_path($1);
      $sources{$source}++;
      $stat_sources{$source}++;
      push @{$dependencies{$file}}, $source;
      get_sources($source);
    }

    # Get functions in script
    elsif((/function +([\w\.\-\_]+)/ || /([\w\.\-\_]+)\(\)/) && ! $bash_keywords{$1}) {
      $function = $1;
      $function_line = $line_number;
    } elsif($function ne undef && ($function_line + 1) == $line_number) {
      if(/^{/) {
        $functions{$function}++;
        $all_functions{$function}++;
        $stat_functions{$function}++;
        push @{$dependencies{$file}}, $function;
      } else {
        $function = undef;
        $function_line = undef;
      }
    } elsif(/^}/) {
      $function = undef;
      $function_line = undef;
    }

    $line_number++;

    if($ignore_line) { next }

    # Get all binaries and functions called from script
    s/\#.*//;
    foreach my $word (split /[\`\;\| \t]+/) {
      if($all_functions{$word} && ! $ignore_functions{$word}) {
        $uses_functions{$word}++; 
        $stat_uses_functions{$word}++;
        if($function eq undef) { push @{$dependencies{$file}}, "function: $word" }
        else { push @{$dependencies{$function}}, "function: $word" }
      }
      elsif($binaries_in_path{$word} ne undef && ! $ignore_binaries{$word}) {
         $uses_binaries{$word}++;
         $stat_uses_binaries{$word}++; 
         if($function eq undef) { push @{$dependencies{$file}}, "binary: $word" }
         else { push @{$dependencies{$function}}, "binary: $word" }

         if($binaries_to_rpm{$word} eq undef) {
           my $rpm = `rpm -qf $binaries_in_path{$word}`;
           if($rpm =~ /([\w\.\-\_]+)/ && $rpm !~ /not owned/) {
             $uses_rpms{$1}++;
             $binaries_to_rpm{$word} = $1;
             $stat_uses_rpms{$1}++;
           }
         } else {
           $uses_rpms{$binaries_to_rpm{$word}}++;
           $stat_uses_rpms{$binaries_to_rpm{$word}}++;
         }
      }
    }
  }
  close FH;

  $tot_code_lines += $line_number - $comment_lines - $empty_lines - 1;
  $tot_comment_lines += $comment_lines;
  $tot_empty_lines += $empty_lines;
  $tot_lines += $line_number - 1;
  $tot_files++;

  print_separator();
  print_dependencies($file);

  print "\n$file\n";
  printf "\tCode lines:\t%s\n", $line_number - $comment_lines - $empty_lines - 1;
  printf "\tComment lines:\t%s\n", $comment_lines;
  printf "\tEmpty lines:\t%s\n", $empty_lines;
  printf "\tTotal lines:\t%s\n", $line_number - 1;
  print_hash(\%sources, 'Source(s):');
  print_hash(\%functions, 'Function(s):');
  print_hash(\%uses_functions, 'Uses function(s):');
  print_hash(\%uses_binaries, 'Uses binarie(s):');
  print_hash(\%uses_rpms, 'Uses RPM(s):');
}

# Get all functions for sourced files and place in all_functions
sub get_sources {
  my $file = shift;

  $all_sources{$file}++;

  my $function = undef;

  open FH, "<$file" or die "Failed to open file $file: $!\n";
  foreach(<FH>) {
    chomp();

    # Get files sourced by script
    if(/^[ \t]*source +([\w\-\/\.\_\$]+)/) {
      my $source = expand_path($1);
      push @{$dependencies{$file}}, $source;
      get_sources($source);
    }

    # Get variable assignments
    elsif(/([\w\.\-\_]+)=(.*)/) {
      $variables{$1} = $2;
    }
    
    # Get functions in script
    elsif(/function +([\w\.\-]+)/ || /([\w\.\-]+)\(\)/) { $function = $1; }
    elsif($function ne undef && /{/ && ! $bash_keywords{$function}) { $all_functions{$function}++; }
    elsif(/}/) { $function = undef; }
  }
  close FH;
}

# Expand variables in path
sub expand_path {
  my $path = shift;

  if($path =~ /\$([\w\-\.\_]+)/) {
    my $variable = $1;
    $path =~ s/\$$variable/$variables{$variable}/;
  }
  return $path;
}

# Print separator
sub print_separator {
  print "-" x 100 . "\n";
}

# Print hash
sub print_hash {
  my $hash = shift;
  my $heading = shift;

  if(scalar(keys %{$hash}) > 0) { print "\t$heading\n" }
  foreach(sort keys %{$hash}) { print "\t\t$_\n" }
}

# Print statistics hash
sub print_stat_hash {
  my $hash = shift;
  my $heading = shift;
  my $minimum = shift;

  if(scalar(keys %{$hash}) > 0) {
    print_separator();
    print "$heading\n";
  }
  foreach(sort { ${$hash}{$b} <=> ${$hash}{$a} } keys %{$hash}) {
    if(${$hash}{$_} > $minimum) { printf "%s\t$_\n", ${$hash}{$_} }
  }
}

# Print dependency tree
sub print_dependencies {
  my $function = shift;
  my $padding = shift;
  my $where = shift;

  if($where eq 'middle') {
    print "$padding|-- ";
    $padding .= '|   ';
  }
  elsif($where eq 'last') {
    print "$padding`-- ";
    $padding .= '    ';
  }
  print "$function\n";

  $where = "middle";
  my $count = 1;
  foreach(@{$dependencies{$function}}) {
    if($count++ == scalar(@{$dependencies{$function}})) { $where = "last" }
    if($function ne $_) { print_dependencies($_, $padding, $where) }
  }
}