#!/usr/bin/perl -w
# NAME: genhtmlindex.pl
# AIM: Given a folder name, seek ALL .htm[l] docs and generate an index.html to jump to each
# Maybe extract the
from each to fill out the index table
# 05/11/2013 geoff mclane http://geoffair.net/mperl
use strict;
use warnings;
use File::Basename; # split path ($name,$dir,$ext) = fileparse($file [, qr/\.[^.]*/] )
use Cwd;
my $os = $^O;
my $perl_dir = '/home/geoff/bin';
my $PATH_SEP = '/';
my $temp_dir = '/tmp';
if ($os =~ /win/i) {
$perl_dir = 'C:\GTools\perl';
$temp_dir = $perl_dir;
$PATH_SEP = "\\";
}
unshift(@INC, $perl_dir);
require 'lib_utils.pl' or die "Unable to load 'lib_utils.pl' Check paths in \@INC...\n";
require 'lib_html.pl' or die "Unable to load 'lib_html.pl' Check paths in \@INC...\n";
# log file stuff
our ($LF);
my $pgmname = $0;
if ($pgmname =~ /(\\|\/)/) {
my @tmpsp = split(/(\\|\/)/,$pgmname);
$pgmname = $tmpsp[-1];
}
my $outfile = $temp_dir.$PATH_SEP."temp.$pgmname.txt";
open_log($outfile);
# user variables
my $VERS = "0.0.1 2013-03-17";
my $load_log = 0;
my $in_dir = '';
my $verbosity = 0;
my $out_file = '';
my $tmp_out = $temp_dir.$PATH_SEP."tempindex.html";
# ### DEBUG ###
my $debug_on = 1;
my $def_file = 'C:\OSGeo4W\apache\htdocs\openlayers\examples';
### program variables
my @warnings = ();
my $cwd = cwd();
sub VERB1() { return $verbosity >= 1; }
sub VERB2() { return $verbosity >= 2; }
sub VERB5() { return $verbosity >= 5; }
sub VERB9() { return $verbosity >= 9; }
sub show_warnings($) {
my ($val) = @_;
if (@warnings) {
prt( "\nGot ".scalar @warnings." WARNINGS...\n" );
foreach my $itm (@warnings) {
prt("$itm\n");
}
prt("\n");
} else {
prt( "\nNo warnings issued.\n\n" ) if (VERB9());
}
}
sub pgm_exit($$) {
my ($val,$msg) = @_;
if (length($msg)) {
$msg .= "\n" if (!($msg =~ /\n$/));
prt($msg);
}
show_warnings($val);
close_log($outfile,$load_log);
exit($val);
}
sub prtw($) {
my ($tx) = shift;
$tx =~ s/\n$//;
prt("$tx\n");
push(@warnings,$tx);
}
sub process_in_file($) {
my ($inf) = @_;
if (! open INF, "<$inf") {
pgm_exit(1,"ERROR: Unable to open file [$inf]\n");
}
my @lines = ;
close INF;
my $lncnt = scalar @lines;
prt("Processing $lncnt lines, from [$inf]...\n");
my ($line,$inc,$lnn);
$lnn = 0;
foreach $line (@lines) {
chomp $line;
$lnn++;
if ($line =~ /\s*#\s*include\s+(.+)$/) {
$inc = $1;
prt("$lnn: $inc\n");
}
}
}
sub get_html_head() {
my $txt = <
HTML index
Index of HTML files
EOF
return $txt;
}
sub process_html($) {
my $ra = shift;
my ($file,$title,$name,$dir,$min,$len,$i);
set_show_warnings(0);
my @arr = ();
$min = 0;
foreach $file (@{$ra}) {
($name,$dir) = fileparse($file);
$title = get_html_title_from_file($file);
$title = $name if (length($title) == 0);
prt("$name [$title]\n") if (VERB9());
push(@arr,[$name,$title]);
$len = length($name);
$min = $len if ($len > $min);
}
$len = scalar @arr;
prt("Collected $len titles... using file name if none...\n");
my $html = get_html_head();
my $col = 0;
my $wrap = 4;
for ($i = 0; $i < $len; $i++) {
$name = $arr[$i][0];
$title = $arr[$i][1];
$html .= " \n" if ($col == 0);
$html .= " $name | \n";
$col++;
$html .= " $title | \n";
$col++;
if ($col == $wrap) {
$col = 0;
$html .= "
\n";
}
# for display only
$name .= ' ' while (length($name) < $min);
prt("$name [$title]\n") if (VERB5());
}
if ($col) {
while ($col < $wrap) {
$col++;
$html .= " | \n";
$col++;
$html .= " | \n";
}
$html .= " \n";
}
$html .= "
\n";
$html .= " \n";
$html .= "\n";
$name = '';
if (length($out_file) == 0) {
$out_file = $tmp_out;
$name = 'since no -o file given...';
}
write2file($html,$out_file);
prt("HTML written to $out_file... $name\n");
}
sub my_type($) {
my $fil = shift;
return 1 if ($fil =~ /\.html$/i);
return 1 if ($fil =~ /\.htm$/i);
return 0;
}
sub process_in_dir($) {
my $dir = shift;
if (!opendir(DIR,$dir)) {
pgm_exit(1,"ERROR: Unable to open directory $dir!\n");
}
my @files = readdir(DIR);
closedir(DIR);
my ($file,$ff,$cnt);
ut_fix_directory(\$dir);
my @dirs = ();
my @hfiles = ();
foreach $file (@files) {
next if ($file eq '.');
next if ($file eq '..');
$ff = $dir.$file;
if (-d $ff) {
push(@dirs,$ff);
} elsif (-f $ff) {
if (my_type($file)) {
push(@hfiles,$ff);
}
} else {
prtw("WARNING: WHAT IS THIS [$ff]\n");
}
}
$cnt = scalar @hfiles;
prt("Found $cnt HTML files in $dir...\n");
process_html(\@hfiles) if ($cnt);
}
#########################################
### MAIN ###
parse_args(@ARGV);
process_in_dir($in_dir);
pgm_exit(0,"");
########################################
sub need_arg {
my ($arg,@av) = @_;
pgm_exit(1,"ERROR: [$arg] must have a following argument!\n") if (!@av);
}
sub parse_args {
my (@av) = @_;
my ($arg,$sarg);
while (@av) {
$arg = $av[0];
if ($arg =~ /^-/) {
$sarg = substr($arg,1);
$sarg = substr($sarg,1) while ($sarg =~ /^-/);
if (($sarg =~ /^h/i)||($sarg eq '?')) {
give_help();
pgm_exit(0,"Help exit(0)");
} elsif ($sarg =~ /^v/) {
if ($sarg =~ /^v.*(\d+)$/) {
$verbosity = $1;
} else {
while ($sarg =~ /^v/) {
$verbosity++;
$sarg = substr($sarg,1);
}
}
prt("Verbosity = $verbosity\n") if (VERB1());
} elsif ($sarg =~ /^l/) {
if ($sarg =~ /^ll/) {
$load_log = 2;
} else {
$load_log = 1;
}
prt("Set to load log at end. ($load_log)\n") if (VERB1());
} elsif ($sarg =~ /^o/) {
need_arg(@av);
shift @av;
$sarg = $av[0];
$out_file = $sarg;
prt("Set out file to [$out_file].\n") if (VERB1());
} else {
pgm_exit(1,"ERROR: Invalid argument [$arg]! Try -?\n");
}
} else {
$in_dir = $arg;
prt("Set input to [$in_dir]\n") if (VERB1());
}
shift @av;
}
if ($debug_on) {
prtw("WARNING: DEBUG is ON!\n");
if (length($in_dir) == 0) {
$in_dir = $def_file;
prt("Set DEFAULT input to [$in_dir]\n");
}
}
if (length($in_dir) == 0) {
pgm_exit(1,"ERROR: No input directory found in command!\n");
}
if (! -d $in_dir) {
pgm_exit(1,"ERROR: Unable to find in directory [$in_dir]! Check name, location...\n");
}
}
sub give_help {
prt("$pgmname: version $VERS\n");
prt("Usage: $pgmname [options] in-dir\n");
prt("Options:\n");
prt(" --help (-h or -?) = This help, and exit 0.\n");
prt(" --verb[n] (-v) = Bump [or set] verbosity. def=$verbosity\n");
prt(" --load (-l) = Load LOG at end. ($outfile)\n");
prt(" --out (-o) = Write output to this file.\n");
prt(" Given an input directory, search for all htm[l] files, and generate an index.\n");
}
# eof - genhtmlindex.pl