#!/usr/bin/perl
# TmNetWiki version 0.4 (September 11, 2002)
# Copyright (C) 2002 Adam Brate
#   <ab@adambrate.com> 
# Based on the GPLed UseModWiki 0.92
# Copyright (C) 2000-2001 Clifford A. Adams
#    <caadams@frontiernet.net> or <usemod@usemod.com>
# Based on the GPLed AtisWiki 0.3  (C) 1998 Markus Denker
#    <marcus@ira.uka.de>
# ...which was based on
#    the LGPLed CVWiki CVS-patches (C) 1997 Peter Merel
#    and The Original WikiWikiWeb  (C) Ward Cunningham
#        <ward@c2.com> (code reused with permission)
# Email and ThinLine options by Jim Mahoney <mahoney@marlboro.edu>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the
#    Free Software Foundation, Inc.
#    59 Temple Place, Suite 330
#    Boston, MA 02111-1307 USA

package Wiki::search;
use strict;
# needs subs   Wiki::template: GetHeader, GetCommonFooter
#              Wiki::utility: QuoteHtml
#              Wiki::index: PrintPageList
#              Wiki::translate: Ts
#              Wiki::page: OpenPage
#              Wiki::text: OpenText
# needs consts $XSearchDisp

use base 'Exporter';
use Wiki::consts;
use Wiki::template;
use Wiki::utility;
use Wiki::index;
use Wiki::translate;
use Wiki::page;
use Wiki::text;
#if ($^V and $^V gt v5.6.0) {
#    our @EXPORT;
#else {
    use vars qw(@EXPORT);
#}
@EXPORT = qw(
  DoSearch
);

sub SearchTitleAndBody;
sub SearchBody;
sub PrintSearchResults;

# This is a very simple search. I think it would be good if redirects
# were recursively expanded.

sub DoSearch {
  my ($string) = @_;

  if ($string eq '') {
    &DoIndex();
    return;
  }
  print &GetHeader('', &QuoteHtml(Ts('Search for: %s', $string)), '');
  print '<br>';
  if ( $XSearchDisp ) { # managed by config file (?)
    &PrintSearchResults($string,&SearchTitleAndBody($string)) ;
  } else {
    &PrintPageList(&SearchTitleAndBody($string));
  }
#  &PrintPageList(&SearchTitleAndBody($string));
  print &GetCommonFooter();
}

sub SearchTitleAndBody {
    my ($string) = @_;
    my ($name, $freeName, @found,@titlefound);
    
    foreach $name (&AllPagesList()) {
	my $found =0;
	&OpenPage($name);
	&OpenDefaultText();
	if ($name =~ /$string/i) {
	    push(@titlefound,$name);
	    $found=1;
	} elsif ($FreeLinks && ($name =~ m/_/)) {
	    $freeName = $name;
	    $freeName =~ s/_/ /g;
	    if ($freeName =~ /$string/i) {
		push(@titlefound, $name);
		$found = 1;
	    }
	} 
	if ($found == 0 && $Text{'text'} =~ /$string/i) {
	    push(@found, $name);
	}
    }
    @found = (@titlefound,@found);
    return @found;
}

sub SearchBody {
  my ($string) = @_;
  my ($name, @found);

  foreach $name (&AllPagesList()) {
    &OpenPage($name);
    &OpenDefaultText();
    if ($Text{'text'} =~ /$string/i){
      push(@found, $name);
    }
  }
  return @found;
}

sub PrintSearchResults {
	 my ( $searchstring, @results ) = @_ ;  #  inputs
	 my ( $output ) ;

	 my ( $name ) ;
	 my ( $pageText ) ;
	 my ( $t, $j, $jsnippet, $start, $end ) ;
	 my ( $snippetlen, $maxsnippets ) = ( 100, 4 ) ; #  these seem nice.

	 print "\n<h2>", ($#results + 1), " pages found:</h2>";

	 foreach $name (@results) {
    #  get the page, filter it, remove all tags (since we're presenting in
    #  plaintext, not HTML, a la google(tm)).
		  &OpenPage($name);
		  &OpenDefaultText();
		  $pageText = &QuoteHtml($Text{'text'});
		  $pageText =~ s/$Consts->{FS}//g;  # Remove separators (paranoia)
		  $pageText =~ s/[\s]+/ /g;  #  Shrink whitespace
		  $pageText =~ s/([-_=\\*\\.]){10,}/$1$1$1$1$1/g ; # e.g. shrink "----------"
		  foreach $t (@HtmlPairs, "pre", "nowiki", "code" ) {
				$pageText =~ s/\<$t(\s[^<>]+?)?\>(.*?)\<\/$t\>/$2/gis;
		  }
		  foreach $t (@HtmlSingle) {
				$pageText =~ s/\<$t(\s[^<>]+?)?\>//gi;
		  }

    #  entry header
		  $output = "\n\n" ;
		  $output .= "... "  if ($name =~ m|/|);
		  $output .= "<font size=+1>" . &GetPageLink($name) . "</font><br>\n" ;

    #  show a snippet from the top of the document
		  $j = index( $pageText, " ", $snippetlen ) ;  #  end on word boundary
		  $output .= substr( $pageText, 0, $j ) . " <b>...</b> " ;
		  $pageText = substr( $pageText, $j ) ;  #  to avoid rematching

    #  search for occurrences of searchstring
		  $jsnippet = 0 ;
    while ( $jsnippet < $maxsnippets
				&&  $pageText =~ m/($searchstring)/i ) {  #  captures match as $1
		  $jsnippet++ ;  #  paranoid about looping
		  if ( ($j = index( $pageText, $1 )) > -1 ) {  #  get index of match
        #  get substr containing (start of) match, ending on word boundaries
				$start = index( $pageText, " ", $j-($snippetlen/2) ) ;
				$start = 0  if ( $start == -1 ) ;
				$end = index( $pageText, " ", $j+($snippetlen/2) ) ;
				$end = length( $pageText )  if ( $end == -1 ) ;
				$t = substr( $pageText, $start, $end-$start ) ;
        #  highlight occurrences and tack on to output stream.
				$t =~ s/($searchstring)/<b>\1<\/b>/gi ;
				$output .= $t . " <b>...</b> " ;
        #  truncate text to avoid rematching the same string.
				$pageText = substr( $pageText, $end ) ;
		  }
    }

    #  entry trailer
    $output .= "<br><i><font size=-1>"
        . int((length($pageText)/1024)+1) . "K - last updated "
        . &TimeToText($Section{ts}) . " by "
        . &GetAuthorLink( $Section{'host'}, $Section{'username'},
								  $Section{'id'} )
        . "</font></i><br><br>" ;

		  print $output ;

	 }
}