#!/usr/bin/perl

#
# html_table_to_db.pm
# Copyright (C) 2005-2015 by John Heidemann <johnh@isi.edu>
# $Id: 025cc75c8e0df7ccdb092d89696480e5dee7dd08 $
#
# This program is distributed under terms of the GNU general
# public license, version 2.  See the file COPYING
# in $dblib for details.
#


=head1 NAME

html_table_to_db - convert HTML tables into fsdb

=head1 SYNOPSIS

    html_table_to_db <source.html >dest.fsdb

=head1 DESCRIPTION

Converts a HTML table to Fsdb format.

The input is an HTML table (I<not> fsdb).
Column names are taken from C<TH> elements,
or defined as C<column0> through C<columnN> if 
no such elements appear.

The output is two-space-separated fsdb.
(Someday more general field separators should be supported.)
Fsdb fields are normalized version of the html file:
multiple spaces are compressed to one.

=for comment
begin_standard_fsdb_options

This module also supports the standard fsdb options:

=over 4

=item B<-d>

Enable debugging output.

=item B<-i> or B<--input> InputSource

Read from InputSource, typically a file name, or C<-> for standard input,
or (if in Perl) a IO::Handle, Fsdb::IO or Fsdb::BoundedQueue objects.

=item B<-o> or B<--output> OutputDestination

Write to OutputDestination, typically a file name, or C<-> for standard output,
or (if in Perl) a IO::Handle, Fsdb::IO or Fsdb::BoundedQueue objects.

=item B<--autorun> or B<--noautorun>

By default, programs process automatically,
but Fsdb::Filter objects in Perl do not run until you invoke
the run() method.
The C<--(no)autorun> option controls that behavior within Perl.

=item B<--help>

Show help.

=item B<--man>

Show full manual.

=back

=for comment
end_standard_fsdb_options


=head1 SAMPLE USAGE

=head2 Input:

	<table>
	<tr><th>account</th> <th>passwd</th> <th>uid</th> <th>gid</th> <th>fullname</th> <th>homedir</th> <th>shell</th> </tr>
	<tr bgcolor="#f0f0f0"><td>johnh</td> <td>*</td> <td>2274</td> <td>134</td> <td>John &amp; Ampersand</td> <td>/home/johnh</td> <td>/bin/bash</td> </tr>
	<tr bgcolor="#f0f0f0"><td>greg</td> <td>*</td> <td>2275</td> <td>134</td> <td>Greg &lt; Lessthan</td> <td>/home/greg</td> <td>/bin/bash</td> </tr>
	<tr bgcolor="#f0f0f0"><td>root</td> <td>*</td> <td>0</td> <td>0</td> <td>Root ; Semi</td> <td>/root</td> <td>/bin/bash</td> </tr>
	<tr bgcolor="#d0d0d0"><td>four</td> <td>*</td> <td>1</td> <td>1</td> <td>Fourth Row</td> <td>/home/four</td> <td>/bin/bash</td> </tr>
	</table>

=head2 Command:

    html_table_to_db

=head2 Output:

	#fsdb -F S account passwd uid gid fullname homedir shell
	johnh  *  2274  134  John & Ampersand  /home/johnh  /bin/bash
	greg  *  2275  134  Greg < Lessthan  /home/greg  /bin/bash
	root  *  0  0  Root ; Semi  /root  /bin/bash
	four  *  1  1  Fourth Row  /home/four  /bin/bash


=head1 SEE ALSO

L<Fsdb>.
L<db_to_html_table>.


=cut


# WARNING: This code is derived from html_table_to_db.pm; that is the master copy.

use Fsdb::Filter::html_table_to_db;
my $f = new Fsdb::Filter::html_table_to_db(@ARGV);
$f->setup_run_finish;  # or could just --autorun
exit 0;


=head1 AUTHOR and COPYRIGHT

Copyright (C) 1991-2015 by John Heidemann <johnh@isi.edu>

This program is distributed under terms of the GNU general
public license, version 2.  See the file COPYING
with the distribution for details.

=cut

1;