#!/usr/bin/perl -w
#
# Clean a text file -- or directory of text files -- of stealth whitespace.
# WARNING: this can be a highly destructive operation.  Use with caution.
#

use bytes;
use File::Basename;

# Default options
$max_width = 79;

# Clean up space-tab sequences, either by removing spaces or
# replacing them with tabs.
sub clean_space_tabs($)
{
    no bytes;			# Tab alignment depends on characters

    my($li) = @_;
    my($lo) = '';
    my $pos = 0;
    my $nsp = 0;
    my($i, $c);

    for ($i = 0; $i < length($li); $i++) {
	$c = substr($li, $i, 1);
	if ($c eq "\t") {
	    my $npos = ($pos+$nsp+8) & ~7;
	    my $ntab = ($npos >> 3) - ($pos >> 3);
	    $lo .= "\t" x $ntab;
	    $pos = $npos;
	    $nsp = 0;
	} elsif ($c eq "\n" || $c eq "\r") {
	    $lo .= " " x $nsp;
	    $pos += $nsp;
	    $nsp = 0;
	    $lo .= $c;
	    $pos = 0;
	} elsif ($c eq " ") {
	    $nsp++;
	} else {
	    $lo .= " " x $nsp;
	    $pos += $nsp;
	    $nsp = 0;
	    $lo .= $c;
	    $pos++;
	}
    }
    $lo .= " " x $nsp;
    return $lo;
}

# Compute the visual width of a string
sub strwidth($) {
    no bytes;			# Tab alignment depends on characters

    my($li) = @_;
    my($c, $i);
    my $pos = 0;
    my $mlen = 0;

    for ($i = 0; $i < length($li); $i++) {
	$c = substr($li,$i,1);
	if ($c eq "\t") {
	    $pos = ($pos+8) & ~7;
	} elsif ($c eq "\n") {
	    $mlen = $pos if ($pos > $mlen);
	    $pos = 0;
	} else {
	    $pos++;
	}
    }

    $mlen = $pos if ($pos > $mlen);
    return $mlen;
}

$name = basename($0);

@files = ();

while (defined($a = shift(@ARGV))) {
    if ($a =~ /^-/) {
	if ($a eq '-width' || $a eq '-w') {
	    $max_width = shift(@ARGV)+0;
	} else {
	    print STDERR "Usage: $name [-width #] files...\n";
	    exit 1;
	}
    } else {
	push(@files, $a);
    }
}

foreach $f ( @files ) {
    print STDERR "$name: $f\n";

    if (! -f $f) {
	print STDERR "$f: not a file\n";
	next;
    }

    if (!open(FILE, '+<', $f)) {
	print STDERR "$name: Cannot open file: $f: $!\n";
	next;
    }

    binmode FILE;

    # First, verify that it is not a binary file; consider any file
    # with a zero byte to be a binary file.  Is there any better, or
    # additional, heuristic that should be applied?
    $is_binary = 0;

    while (read(FILE, $data, 65536) > 0) {
	if ($data =~ /\0/) {
	    $is_binary = 1;
	    last;
	}
    }

    if ($is_binary) {
	print STDERR "$name: $f: binary file\n";
	next;
    }

    seek(FILE, 0, 0);

    $in_bytes = 0;
    $out_bytes = 0;
    $blank_bytes = 0;

    @blanks = ();
    @lines  = ();
    $lineno = 0;

    while ( defined($line = <FILE>) ) {
	$lineno++;
	$in_bytes += length($line);
	$line =~ s/[ \t\r]*$//;		# Remove trailing spaces
	$line = clean_space_tabs($line);

	if ( $line eq "\n" ) {
	    push(@blanks, $line);
	    $blank_bytes += length($line);
	} else {
	    push(@lines, @blanks);
	    $out_bytes += $blank_bytes;
	    push(@lines, $line);
	    $out_bytes += length($line);
	    @blanks = ();
	    $blank_bytes = 0;
	}

	$l_width = strwidth($line);
	if ($max_width && $l_width > $max_width) {
	    print STDERR
		"$f:$lineno: line exceeds $max_width characters ($l_width)\n";
	}
    }

    # Any blanks at the end of the file are discarded

    if ($in_bytes != $out_bytes) {
	# Only write to the file if changed
	seek(FILE, 0, 0);
	print FILE @lines;

	if ( !defined($where = tell(FILE)) ||
	     !truncate(FILE, $where) ) {
	    die "$name: Failed to truncate modified file: $f: $!\n";
	}
    }

    close(FILE);
}
id=661091093918657ab544fb8ca91a5ab172a986dc'>net: ipv4: remove fib_lookup.h from devinet.c include list</a></td><td>David Ahern</td><td>1</td><td><span class='deletions'>-2</span>/<span class='insertions'>+0</span></td></tr>
<tr><td><span title='2017-02-02 23:03:05 -0500'>2017-02-02</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=b9ea2a7be758f2c07a0c044645edc409a8a388fd'>net: remove useless pfmemalloc setting</a></td><td>Eric Dumazet</td><td>1</td><td><span class='deletions'>-1</span>/<span class='insertions'>+0</span></td></tr>
<tr><td><span title='2017-02-02 21:58:02 -0500'>2017-02-02</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=ba94f3088b792b16ea576a256a6030feddc87f24'>unix: add ioctl to open a unix socket file with O_PATH</a></td><td>Andrey Vagin</td><td>1</td><td><span class='deletions'>-0</span>/<span class='insertions'>+41</span></td></tr>
<tr><td><span title='2017-02-02 16:54:00 -0500'>2017-02-02</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=e2160156bf2a7d5018e99a9993fbcdda0abac09b'>Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net</a></td><td>David S. Miller</td><td>12</td><td><span class='deletions'>-104</span>/<span class='insertions'>+93</span></td></tr>
<tr><td><span title='2017-02-01 11:52:27 -0800'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=6d04dfc8966019b8b0977b2cb942351f13d2b178'>Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net</a></td><td>Linus Torvalds</td><td>10</td><td><span class='deletions'>-103</span>/<span class='insertions'>+86</span></td></tr>
<tr><td><span title='2017-02-01 14:10:03 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=f3b20313aef93f9cfda76fec2c05625f88510f18'>net/sched: act_psample: Remove unnecessary ASSERT_RTNL</a></td><td>Yotam Gigi</td><td>1</td><td><span class='deletions'>-1</span>/<span class='insertions'>+0</span></td></tr>
<tr><td><span title='2017-02-01 14:10:03 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=cadb9c9fdbc6a624d57b5ecdfd412b5800848703'>net/sched: act_sample: Fix error path in init</a></td><td>Yotam Gigi</td><td>1</td><td><span class='deletions'>-1</span>/<span class='insertions'>+4</span></td></tr>
<tr><td><span title='2017-02-01 12:55:42 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=06425c308b92eaf60767bc71d359f4cbc7a561f8'>tcp: fix 0 divide in __tcp_select_window()</a></td><td>Eric Dumazet</td><td>1</td><td><span class='deletions'>-2</span>/<span class='insertions'>+4</span></td></tr>
<tr><td><span title='2017-02-01 12:27:33 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=63117f09c768be05a0bf465911297dc76394f686'>ipv6: pointer math error in ip6_tnl_parse_tlv_enc_lim()</a></td><td>Dan Carpenter</td><td>1</td><td><span class='deletions'>-1</span>/<span class='insertions'>+1</span></td></tr>
<tr><td><span title='2017-02-01 12:13:52 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=1f5e29ce7989eb75652774004b962ee1eb6e56ca'>net: ipv6: add NLM_F_APPEND in notifications when applicable</a></td><td>David Ahern</td><td>1</td><td><span class='deletions'>-0</span>/<span class='insertions'>+3</span></td></tr>
<tr><td><span title='2017-02-01 12:02:48 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=b2504a5dbef3305ef41988ad270b0e8ec289331c'>net: reduce skb_warn_bad_offload() noise</a></td><td>Eric Dumazet</td><td>1</td><td><span class='deletions'>-3</span>/<span class='insertions'>+9</span></td></tr>
<tr><td><span title='2017-02-01 11:57:33 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=fd62d9f5c575f0792f150109f1fd24a0d4b3f854'>net/sched: matchall: Fix configuration race</a></td><td>Yotam Gigi</td><td>1</td><td><span class='deletions'>-82</span>/<span class='insertions'>+45</span></td></tr>
<tr><td><span title='2017-02-01 11:53:23 -0500'>2017-02-01</span></td><td><a href='/cgit.cgi/linux/net-next.git/commit/net?id=160ca0142431c19386db976302fd4b07c587f651'>rtnetlink: Handle IFLA_MASTER parameter when processing rtnl_newlink</a></td><td>Theuns Verwoerd</td><td>1</td><td><span class='deletions'>-1</span>/<span class='insertions'>+6</span></td></tr>