#!/usr/bin/perl -w

# Copyright (C) 2005, 2006 Apple Computer, Inc.  All rights reserved.

#

# Redistribution and use in source and binary forms, with or without

# modification, are permitted provided that the following conditions

# are met:

#

# 1.  Redistributions of source code must retain the above copyright

#     notice, this list of conditions and the following disclaimer. 

# 2.  Redistributions in binary form must reproduce the above copyright

#     notice, this list of conditions and the following disclaimer in the

#     documentation and/or other materials provided with the distribution. 

# 3.  Neither the name of Apple Computer, Inc. ("Apple") nor the names of

#     its contributors may be used to endorse or promote products derived

#     from this software without specific prior written permission. 

#

# THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY

# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED

# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE

# DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY

# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES

# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;

# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND

# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF

# THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

# "report-include-statistics" script for Web Kit Open Source Project

use strict;

use File::Find;

find(\&wanted, @ARGV ? @ARGV : ".");

my %paths;

my %sources;

my %includes;

sub wanted

{

    my $file = $_;

    if ($file eq "icu") {

        $File::Find::prune = 1;

        return;

    }

    if ($file !~ /^\./ && $file =~ /\.(h|cpp|c|mm|m)$/) {

        $paths{$file} = $File::Find::name;

        $sources{$file} = $File::Find::name if $file !~ /\.h/;

        open FILE, $file or die;

        while (<FILE>) {

            if (m-^\s*#\s*(include|import)\s+["<]((\S+/)*)(\S+)[">]-) {

                my $include = ($2 eq "sys/" ? $2 : "") . $4;

                $includes{$file}{$include}++;

            }

        }

        close FILE;

    }

}

my %totalIncludes;

sub fillOut

{

    my ($file) = @_;

    return if defined $totalIncludes{$file};

    for my $include (keys %{ $includes{$file} }) {

        $totalIncludes{$file}{$include} = 1;

        fillOut($include);

        for my $i (keys %{ $totalIncludes{$include} }) {

            $totalIncludes{$file}{$i} = 1;

        }

    }

}

my %inclusionCounts;

for my $file (keys %includes) {

    $inclusionCounts{$file} = 0;

    fillOut($file);

}

for my $file (keys %sources) {

    for my $include (keys %{ $totalIncludes{$file} }) {

        $inclusionCounts{$include}++;

    }

}

for my $file (sort mostincludedcmp keys %includes) {

    next if !$paths{$file};

    my $count = $inclusionCounts{$file};

    my $numIncludes = keys %{ $includes{$file} };

    my $numTotalIncludes = keys %{ $totalIncludes{$file} };

    print "$file is included $count times, includes $numIncludes files directly, $numTotalIncludes files total.\n"

}

# Sort most-included files first.

sub mostincludedcmp($$)

{

    my ($filea, $fileb) = @_;

    my $counta = $inclusionCounts{$filea} || 0;

    my $countb = $inclusionCounts{$fileb} || 0;

    return $countb <=> $counta if $counta != $countb;

    my $ta = keys %{ $totalIncludes{$filea} };

    my $tb = keys %{ $totalIncludes{$fileb} };

    return $ta <=> $tb if $ta != $tb;

    return $filea cmp $fileb;

}