sourcedistribution-raw.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;  
#
#  SourceDistribution-raw.sum - simple summary of a directory containing C
#  files and a Makefile (at least).  Does not use Essence to type files;
#  instead (for performance reasons) uses simple filename matching (which
#  almost) always works for C and Makefile's) to determine types.  
#
#  Usage: SourceDistribution.sum directory
#
#  Darren Hardy, [e-mail], June 1994
#
#  SourceDistribution-raw.sum,v 1.2 1995/09/05 20:17:31 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.  
#  
#
do usage() if ($#ARGV < 0);
$directory = shift(@ARGV);
do usage() if ($directory eq "");
exit(1) if (! -d $directory);	# make sure we've got a directory

opendir(DIR, $directory) || die "Cannot open $directory";
@files = sort grep(!/^\./, readdir(DIR));
closedir(DIR);
foreach $file (@files) {
	next if (! -r "$directory/$file");
	do sum_readme($file), next 	if ($file =~ /^.*readme.*$/io);
	do sum_readme($file), next 	if ($file =~ /^INSTALL.*$/o);
	do sum_makefile($file), next 	if ($file =~ /^.*makefile.*$/io);
	do sum_c($file), next 		if ($file =~ /^.*\.[ch]$/o);
	do sum_manpage($file), next     if ($file =~ /^.*\.([1-8]|man)$/o);
	print "Embedded: $file\n";	# default is to print the filename
}
exit(0);

#
#  Look for information in each file
#
sub sum_readme {
	local($file) = @_;
	print "Embedded: $file (README)\n";
	#
	#  Extract first 40 lines of the readme
	#
	$nlines = 1;
	open(FILE, "< $directory/$file") || die "Cannot read $file";
	while (<FILE>) {
		next if (/^\n/o);	# skip empty lines
		print;
		last if (++$nlines > 40);
	}
	close(FILE);
}

sub sum_c {
	local($file) = @_;
	print "Embedded: $file (C)\n";
	print `print-c-comments $directory/$file | head -20`;
}

sub sum_makefile {
	local($file) = @_;
	print "Embedded: $file (Makefile)\n";
	$nlines = 0;
	open(FILE, "< $directory/$file") || die "Cannot read $file";
	while (<FILE>) {
		# only use first 100 lines of makefile
		last if ($nlines++ > 100);
		print, next if (/^#/o);
		print "$1\n" if (/^(\w+):\t/o);
	}
	close(FILE);
}

sub sum_manpage {
	local($file) = @_;
	print "Embedded: $file (ManPage)\n";
	print `ManPage.sum $directory/$file`;
}
sub usage {
	print "Usage: SourceDistribution.sum directory\n";
	exit(1);
}