troff-me.sum

harvest是一个下载html网页得机器人

: # *-*-perl-*-*
    eval 'exec perl -S $0 "$@"'
    if $running_under_some_shell;  
#
#  Troff-me.sum - generate a summary of a -me file using semantic information
#
#  Interesting -me Macros
#  -----------------------
#  .bu			bulleted paragraph
#  .ip x i		indented paragraph with hanging tag
#  .np			numbered parapraph
#  .lp			parapraph
#  .pp			parapraph
#  .sh n x		section header x, depth n
#  .uh x		section header x
#
#  Darren Hardy, [e-mail], March 1994
#
#  Troff-me.sum,v 1.6 1995/09/05 20:17:41 hardy Exp
#
#######################################################################
#
#  Copyright (c) 1994, 1995.  All rights reserved.
#  
#    The Harvest software was developed by the Internet Research Task
#    Force Research Group on Resource Discovery (IRTF-RD):
#  
#          Mic Bowman of Transarc Corporation.
#          Peter Danzig of the University of Southern California.
#          Darren R. Hardy of the University of Colorado at Boulder.
#          Udi Manber of the University of Arizona.
#          Michael F. Schwartz of the University of Colorado at Boulder.
#          Duane Wessels of the University of Colorado at Boulder.
#  
#    This copyright notice applies to software in the Harvest
#    ``src/'' directory only.  Users should consult the individual
#    copyright notices in the ``components/'' subdirectories for
#    copyright information about other software bundled with the
#    Harvest source code distribution.
#  
#  TERMS OF USE
#    
#    The Harvest software may be used and re-distributed without
#    charge, provided that the software origin and research team are
#    cited in any use of the system.  Most commonly this is
#    accomplished by including a link to the Harvest Home Page
#    (http://harvest.cs.colorado.edu/) from the query page of any
#    Broker you deploy, as well as in the query result pages.  These
#    links are generated automatically by the standard Broker
#    software distribution.
#    
#    The Harvest software is provided ``as is'', without express or
#    implied warranty, and with no support nor obligation to assist
#    in its use, correction, modification or enhancement.  We assume
#    no liability with respect to the infringement of copyrights,
#    trade secrets, or any patents, and are not responsible for
#    consequential damages.  Proper use of the Harvest software is
#    entirely the responsibility of the user.
#  
#  DERIVATIVE WORKS
#  
#    Users may make derivative works from the Harvest software, subject 
#    to the following constraints:
#  
#      - You must include the above copyright notice and these 
#        accompanying paragraphs in all forms of derivative works, 
#        and any documentation and other materials related to such 
#        distribution and use acknowledge that the software was 
#        developed at the above institutions.
#  
#      - You must notify IRTF-RD regarding your distribution of 
#        the derivative work.
#  
#      - You must clearly notify users that your are distributing 
#        a modified version and not the original Harvest software.
#  
#      - Any derivative product is also subject to these copyright 
#        and use restrictions.
#  
#    Note that the Harvest software is NOT in the public domain.  We
#    retain copyright, as specified above.
#  
#  HISTORY OF FREE SOFTWARE STATUS
#  
#    Originally we required sites to license the software in cases
#    where they were going to build commercial products/services
#    around Harvest.  In June 1995 we changed this policy.  We now
#    allow people to use the core Harvest software (the code found in
#    the Harvest ``src/'' directory) for free.  We made this change
#    in the interest of encouraging the widest possible deployment of
#    the technology.  The Harvest software is really a reference
#    implementation of a set of protocols and formats, some of which
#    we intend to standardize.  We encourage commercial
#    re-implementations of code complying to this set of standards.  
#  
#
&usage() if ($#ARGV != 0);
$file = shift(@ARGV);
&usage() if ($file eq "");
undef %values;

#
#  Read in the values array
#
open(INPUT, "< $file") || die "Cannot read $file";
while (<INPUT>) {
	next if (/^[\.']+\\\"/o);
	&grab("Title", $2), next if (/^\.(sh|uh)(.*)$/o);
	&grab("Partial-Text", $1), next if (/^\.ip(.*)$/o);
}
close(INPUT);

#
#  Print the formmated values array
#
foreach $k (sort keys %values) {
	$values{$k} =~ s/\\[\*fs].//g;	# remove in-line troff 
	$values{$k} =~ s/\\.//g;	# remove in-line troff 
	print "$k" , "{" , length($values{$k}) , "}:\t";
	print $values{$k};
	print "\n";
}
exit(0);

sub usage {
	print STDERR "Usage: Troff-me.sum filename\n";
	exit(1);
}

# grab_line uses the next input line that isn't a troff directive
sub grab_line {
	local($tag) = @_;
	while (<INPUT>) {
		next if (/^\.\w\w/o);
		s/"//g;
		$values{$tag} .= $_;
		last;
	}
}

# grab_para uses all of the input until a paragraph break
sub grab_para {
	local($tag) = @_;
	$npara = 0;
	while (<INPUT>) {
		next if (/^\.(iX|so)/o);	# skip garbage
		next if (/^\.(PP|LP)/o && $npara++ == 0);
		last if (/^\.(np|bu|bp|pp|lp|ip)/io || $npara > 1);
		$values{$tag} .= $_;
	}
}


# grab_sect uses all of the input until the line starts with $end
sub grab_sect {
	local($tag, $end) = @_;
	while (<INPUT>) {
		last if (/^$end/);
		$values{$tag} .= $_;
	}
}

# grab associates $in with $tag
sub grab {
	local($tag, $in) = @_;
	$values{$tag} .= $in . "\n";
}