#
#  file: edgar-html.pl
#  desc: support to convert SEC EDGAR (edgardoc DTD format) XML documents to
#        HTML
#

# limit scope
package EDGAR::HTML;

use strict;
use vars qw($TMPL $TMPLV2);

BEGIN {
	my $iw_root = ($ENV{IW}) ? $ENV{IW} : "/iw";
	my $edgar_root = "$iw_root/skulker/edgar/current";

	# where we find our local libraries
	my($libdir) = "$edgar_root/lib";
	if ( -d $libdir) {
		unshift(@INC, $libdir);
	}

	# HTML template support
	use HTML::Template;

	# text to HTML conversion
	use HTML::FromText;

	# generic edgar support data
	require 'edgar-lib.pl';

	# EDGAR generic utility support
	require 'edgar-util.pl';

	# EDGAR table support
	require 'edgar-table.pl';
}

# HTML template directory
my $tmpldir = "$EDGAR::lib::edgar_root/lib";

# HTML template file
$TMPL = "$tmpldir/edgardoc.html.tmpl";
$TMPLV2 = "$tmpldir/edgardoc.html.2.tmpl";

# debug
my $debug = 0;

#
# generate HTML format edgardoc
#
sub toHTML {
	my($edgardoc) = shift;
	my($template) = shift;
	my($templateVersion) = shift;

	my %transformer = %{$edgardoc->{'transformer'}};
	my %submission = %{$edgardoc->{'submission'}};
	my %parsedEdgar = %{$edgardoc->{'parsed-edgar'}};
	my @stamps = @{$edgardoc->{'stamps'}};
	my $tmpl = new HTML::Template(filename => $template);

	generateSubmissionHeader(\%submission, $tmpl, $templateVersion);
	generateTransformer(\%transformer, $tmpl);
	generateRegistrants(\@{$submission{'registrants'}}, $tmpl, $templateVersion);
	generateDocuments(\@{$submission{'documents'}}, \@{$parsedEdgar{'parsed-documents'}}, $tmpl, $templateVersion);
	generateParsedDocuments(\@{$parsedEdgar{'parsed-documents'}}, $tmpl);
	generateStamps(\@stamps, $tmpl);
	generateToC(\%submission, $tmpl);

	return $tmpl->output();
}



#
# generate Submission header info
#
sub generateSubmissionHeader {
	my($edgardoc) = shift;
	my($tmpl) = shift;
	my($version) = shift;

	my %submission = %{$edgardoc};

	my @submission_hdr = ();
	my %header_tags = (
		'accession-number'           => 'ACCESSION: ',
		'confirming-copy'            => 'CONFIRMING COPY: ',
		'date-of-filing-date-change' => 'FILING DATE CHANGE: ',
		'effectiveness-date'         => 'EFFECTIVENESS DATE: ',
		'filing-date'                => 'FILING DATE: ',
		'group-members'              => 'GROUP MEMBERS: ',
		'items'                      => 'ITEMS: ',
		'period'                     => 'PERIOD: ',
		'references-429'             => 'REFERENCES 429: ',
		'sros'                       => 'SROS: ',
		'type'                       => 'TYPE: ',
	);

	# submission header -- required fields
	my @fields = ('accession-number', 'type', 'filing-date');

	# submission header -- optional fields
	my @options = ('confirming-copy', 'date-of-filing-date-change',
		'effectiveness-date', 'group-members', 'items', 'period',
		'references-429', 'sros' );
	for (@options) {
		if ($submission{$_}) {
			push(@fields, $_);
		}
	}

	# change the filing date to be from YYYYMMDD to month day year
	$submission{'filing-date'} = &EDGAR::util::convertDate($submission{'filing-date'});

	if ($version == 1) {
		for (my $i=0 ; $i <= $#fields ; $i+=2) {
			push(@submission_hdr,
			  {
			    'HEADER_TAG1' => $header_tags{$fields[$i]},
			    'HEADER_VAL1' => $submission{$fields[$i]},
			    'HEADER_TAG2' => $header_tags{$fields[$i+1]},
			    'HEADER_VAL2' => $submission{$fields[$i+1]}
			  });
		}
	} else {
		for (my $i=0 ; $i <= $#fields ; $i++) {
			push(@submission_hdr,
			  {
			    'HEADER_TAG' => $header_tags{$fields[$i]},
			    'HEADER_VAL' => $submission{$fields[$i]},
			  });
		}
	}

	$tmpl->param('SUBMISSION_HEADER' => \@submission_hdr);

	# get company name
	my $company = '';
	for (@{$submission{'registrants'}}) {
		my %registrant = %{$_};

		my $type = $registrant{'type'};
		if ($type eq 'subject-company' || $type eq 'filer') {
			$company = $registrant{'company-data'}{'conformed-name'};
			last;
		}
	}

	$tmpl->param('SUBMISSION_COMPANY' => $company);
	$tmpl->param('SUBMISSION_TYPE' => $submission{'type'});
	$tmpl->param('SUBMISSION_DATE' => $submission{'filing-date'});

	
	# version 1 outputs these items
	if ($version == 1) {
		# document specific BUG data
		$tmpl->param('DOC_BUG' => 'SEC');

		# ToC BUG data
		$tmpl->param('TOC_BUG' => 'TOC');
	}

	# generic name for this document SPACE
	$tmpl->param('SPACE_NAME' => 'SEC');
}


#
# generate Transformer info
#
sub generateTransformer {
	my($transformer) = shift;
	my($tmpl) = shift;

	$tmpl->param('TRANSFORMER_CANONICAL' => $transformer->{'canonical'});
	$tmpl->param('TRANSFORMER_CITY'      => $transformer->{'city'});
	$tmpl->param('TRANSFORMER_CODE'      => $transformer->{'code'});
	$tmpl->param('TRANSFORMER_COUNTRY'   => $transformer->{'country'});
	$tmpl->param('TRANSFORMER_DATE'      => $transformer->{'date'});
	$tmpl->param('TRANSFORMER_EMAIL'     => $transformer->{'email'});
	$tmpl->param('TRANSFORMER_ORG'       => $transformer->{'organization'});
	$tmpl->param('TRANSFORMER_REGION'    => $transformer->{'region'});
	$tmpl->param('TRANSFORMER_STREET'    => join("<br>", split(/\|/, $transformer->{'street'})));
	$tmpl->param('TRANSFORMER_URI'       => $transformer->{'uri'});
}


#
# generate Registrants info
#
sub generateRegistrants {
	my($registrants) = shift;
	my($tmpl) = shift;
	my($version) = shift;

	my %reg_type = (
		'filed-by'        => 'Filed By:',
		'filer'           => 'Filer:',
		'reporting-owner' => 'Reporting Owner:',
		'serial-company'  => 'Serial Company:',
		'subject-company' => 'Subject Company:',
	);

	my %reg_tag = (
		# company data
		'cik'                    => 'CIK:',
		'assigned-sic'           => 'SIC:',
		'irs-number'             => 'IRS Number:',
		'state-of-incorporation' => 'Incorporation:',
		'fiscal-year-end'        => 'Fiscal Year End:',
		# filing values
		'form-type'              => 'Form Type:',
		'act'                    => 'SEC Act:',
		'file-number'            => 'File Number:',
		'film-number'            => 'Film Number:',
		# address
		'business-address'       => 'Business Address:',
		'mail-address'           => 'Mail Address:',
		'phone'                  => 'Phone:',
		# former company data
		'former-conformed-name'  => 'Former Name:',
		'date-changed'           => 'Date Changed:',
	);

	my %tmpl_tag = (
		# company data
		'conformed-name'         => 'REG_FILER',
		'cik'                    => 'REG_CIK',
		'assigned-sic'           => 'REG_SIC',
		'irs-number'             => 'REG_IRS_NUMBER',
		'state-of-incorporation' => 'REG_STATE_OF_INCORPORATION',
		'fiscal-year-end'        => 'REG_FISCAL_YEAR_END',
		# filing values
		'form-type'              => 'REG_FORM_TYPE',
		'act'                    => 'REG_SEC_ACT',
		'file-number'            => 'REG_FILE_NUMBER',
		'film-number'            => 'REG_FILM_NUMBER',
		# contact information
		#'contact-information'    => 'REG_CONTACT_INFORMATION',
		# address
		'business-address'       => 'REG_BUSINESS_ADDRESS',
		'mail-address'           => 'REG_MAIL_ADDRESS',
		'phone'                  => 'REG_PHONE',
		# former company data
		'former-conformed-name'  => 'REG_FORMER_NAME',
		'date-changed'           => 'REG_DATE_CHANGED',
	);


	my @regs = ();
	for (@{$registrants}) {
		my %registrant = %{$_};

		if ($version == 1) {
			push(@regs,
			{ 'REGISTRANT_TAG' => $reg_type{$registrant{'type'}},
		    	'REGISTRANT_VAL' => $registrant{'company-data'}{'conformed-name'}
		  	},);

			# company data -- required fields
			my @fields = ('cik', 'assigned-sic');

			# company data -- optional fields
			my @options = ('irs-number', 'state-of-incorporation', 
								'fiscal-year-end');
			for (@options) {
				if ($registrant{'company-data'}{$_}) {
					push(@fields, $_);
				}
			}

			for (@fields) {
				my $val = $registrant{'company-data'}{$_};
				# rewrite SIC text
				if ($_ eq 'assigned-sic' && $val) {
					my($sic_html) = qq|<a href="http://edgar.space.invisible.net/help/edgar/sic/|;
                                        # " for color syntax

				        $sic_html .= "sic_" . $val . ".html" . "\">$val</a>";

					$val = "$EDGAR::lib::sic_codes{$val} [$sic_html]";
					$val = EDGAR::XML::decode($val);
				}

				push(@regs, { 'REGISTRANT_TAG' => $reg_tag{$_},
				              'REGISTRANT_VAL' => $val });
			}

			# filing values
			for (@{$registrant{'filing-values'}}) {
				my %filing = %{$_};

				# filing values -- required fields
				@fields = ('form-type', 'act');

				# filing values -- optional fields
				@options = ('file-number', 'film-number');
				for (@options) {
					if ($filing{$_}) {
						push(@fields, $_);
					}
				}

				for (@fields) {
					push(@regs, {'REGISTRANT_TAG' => $reg_tag{$_},
					             'REGISTRANT_VAL' => $filing{$_} });
				}
			}

			# business address
			my %addr = %{$registrant{'business-address'}};
			my $address = $addr{'street1'};
			$address .= "<br>" . $addr{'street2'}
				if ($addr{'street2'});
			$address .= "<br>" . $addr{'city'}
				if ($addr{'city'});
			$address .= ", " . $addr{'state'}
				if ($addr{'state'});
			$address .= " " . $addr{'zip'}
				if ($addr{'zip'});
			$address .= "<br>" . $addr{'country'}
				if ($addr{'country'});

			if ($address) {
				push(@regs, {'REGISTRANT_TAG' => $reg_tag{'business-address'},
				             'REGISTRANT_VAL' => $address });
			}

			if ($addr{'phone'}) {
				push(@regs, {'REGISTRANT_TAG' => $reg_tag{'phone'},
			 	             'REGISTRANT_VAL' => $addr{'phone'} });
			}

			# mail address
			%addr = %{$registrant{'mail-address'}};
			$address = $addr{'street1'};
			$address .= "<br>" . $addr{'street2'}
				if ($addr{'street2'});
			$address .= "<br>" . $addr{'city'}
				if ($addr{'city'});
			$address .= ", " . $addr{'state'}
				if ($addr{'state'});
			$address .= " " . $addr{'zip'}
				if ($addr{'zip'});
			$address .= "<br>" . $addr{'country'}
				if ($addr{'country'});

			if ($address) {
			push(@regs, {'REGISTRANT_TAG' => $reg_tag{'mail-address'},
				             'REGISTRANT_VAL' => $address });
			}

			# former company data
			for (@{$registrant{'former-company'}}) {
				my %company = %{$_};

				# former company -- required fields
				@fields = ('former-conformed-name', 'date-changed');

				for (@fields) {
					push(@regs, {'REGISTRANT_TAG' => $reg_tag{$_},
					             'REGISTRANT_VAL' => $company{$_} });
				}
			}

			# spacer row
			push(@regs, {REGISTRANT_TAG => '', 'REGISTRANT_VAL' => ''});

		} else {

			my($none) = "NO DATA";
			my($key);

			foreach $key (keys %tmpl_tag) {
				$tmpl->param($tmpl_tag{$key} => $none);
			}

			my(@fields) = ('conformed-name', 'cik', 'irs-number', 
								'state-of-incorporation', 'fiscal-year-end');

			my($data);
			my($field);
			foreach $field (@fields) {
				$data = $registrant{'company-data'}{$field};
				if ($data) {
					$tmpl->param($tmpl_tag{$field} => $data);
				}
			}

			# rewrite SIC text
			my($val) = $registrant{'company-data'}{'assigned-sic'};
			if ($val =~ /\w+/) {
				my($sic_html) = qq|<a href="http://edgar.space.invisible.net/help/edgar/sic/|;
                                # " for color syntax

				$sic_html .= "sic_" . $val . ".html" . "\">$val</a>";
				$val = "$EDGAR::lib::sic_codes{$val} [$sic_html]";
				$val = EDGAR::XML::decode($val);
				$tmpl->param('REG_SIC' => $val);
			}


			@fields = ('form-type', 'act', 'file-number', 'film-number');

			for (@{$registrant{'filing-values'}}) {
				my %filing = %{$_};
				foreach $field (@fields) {
					$data = $filing{$field};
					if ($data) {
						$tmpl->param($tmpl_tag{$field} => $data);
					}
				}
			}

			# business address
			my %addr = %{$registrant{'business-address'}};
			my $address = $addr{'street1'};
			$address .= "<br>" . $addr{'street2'}
				if ($addr{'street2'});
			$address .= "<br>" . $addr{'city'}
				if ($addr{'city'});
			$address .= ", " . $addr{'state'}
				if ($addr{'state'});
			$address .= " " . $addr{'zip'}
				if ($addr{'zip'});
			$address .= "<br>" . $addr{'country'}
				if ($addr{'country'});

			$data = $addr{'phone'};
			if ($data) {
				$tmpl->param($tmpl_tag{'phone'} => $data);
			}

			if ($address) {
				$tmpl->param($tmpl_tag{'business-address'} => $address);
			}

			# mail address
			if (defined %{$registrant{'mail-address'}}) {
				%addr = %{$registrant{'mail-address'}};
				$address = $addr{'street1'};
				$address .= "<br>" . $addr{'street2'} 
				        if ($addr{'street2'});
				$address .= "<br>" . $addr{'city'}
				        if ($addr{'city'});
				$address .= ", " . $addr{'state'}
				        if ($addr{'state'});
				$address .= " " . $addr{'zip'}
				        if ($addr{'zip'});
				$address .= "<br>" . $addr{'country'}
				        if ($addr{'country'});

				$tmpl->param($tmpl_tag{'mail-address'} => $address)
				    if ($address);
			}

			@fields = ('former-conformed-name', 'date-changed');

			for (@{$registrant{'former-company'}}) {
				my %company = %{$_};
				foreach $field (@fields) {
					$data = $company{$field};
					if ($data) {
						$tmpl->param($tmpl_tag{$field} => $data);
					}
				}
			}

		}
	}

	if ($version == 1) {
		$tmpl->param('REGISTRANTS' => \@regs);
	}
}


#
# generate Documents info
#
sub generateDocuments {
	my($documents) = shift;
	my($parsed_docs) = shift;
	my($tmpl) = shift;
	my($tmplversion) = shift;

	my($parsed_tag, %ptag_hash, $doc, $doc_tag);
	my $debug_cnt = 0;

	# get parsed tables for ALL parsed documents
	my %parsed_tables = ();
	foreach $doc (@{$parsed_docs}) {
		for (keys %{$doc->{'parsed-tables'}}) { 
			$doc->{'parsed-tables'}{$_} =~ /<parsed[\.-]table id="([^"]+)/;
	                $parsed_tag = $1;
			$ptag_hash{$parsed_tag} = $doc->{'parsed-tables'}->{$_};
		}
	}

	my @docs = ();
	for (@{$documents}) {
		my %document = %{$_};

		my $text = $document{'text'};

		# clean up document text a little
		$text = &cleanText($text);

		# split the text block into parsiable hunks
		my $textStrut = &splitText($text);

		# reset the text var
		$text = "";

                my $array_ref;
		foreach $array_ref (@{$textStrut}) {
			if ($debug > 8) {
		                $debug_cnt++;
				open (DEBUG, ">$array_ref->[0]-$debug_cnt.txt");
				print DEBUG join("\n", @{$array_ref->[1]});
				close DEBUG;
			}
		
			if ($array_ref->[0] eq "docTable") {
				${$array_ref->[1]}[0] =~ /<document[\.-]table id="([^"]+)/;
                        	$doc_tag = $1;
                                if ($ptag_hash{$doc_tag}) {
					$text .= &addTableStyleSheet( 
						    &parsedTable2html($ptag_hash{$doc_tag})
								      );
				} else {
					$text .= &formatText($array_ref->[0], 
							     $array_ref->[1],
							     $array_ref->[2]);
				}
	
                        } else {
                                $text .= &formatText($array_ref->[0], $array_ref->[1],
						     $array_ref->[2]);
                        }
		}

		my $docDesc = $document{'description'};
		if (!$docDesc || ($docDesc !~ /\w+/)) {
			$docDesc = $document{'type'};
			if (!$docDesc || ($docDesc =~ /^\d+$/)) {
				$docDesc = "FORM " . $docDesc;
			}
		}

		if ($tmplversion == 1) {
			# _NUMBER is plus 1 due to registrant data always being first
			push(@docs, {'DOCUMENT_NUMBER'   => $document{'sequence'} + 1,
							'DOCUMENT_TITLE'    => $docDesc,
							'DOCUMENT_CONTENTS' => $text,
							'TOC_BUG'           => 'TOC'
		            	});
		} else {
			# _NUMBER is plus 1 due to registrant data always being first
			push(@docs, {'DOCUMENT_NUMBER'   => $document{'sequence'} + 1,
							'DOCUMENT_TITLE'    => $docDesc,
							'DOCUMENT_CONTENTS' => $text
		            	});
		}
	}

	$tmpl->param('DOCUMENTS' => \@docs);
}


#
# generate parsed.edgar info
#
sub fixBrackets {
	my($text) = shift;

	# turn anchor brackets back
	$text =~ s#&lt;a name=&quot;(.+)&quot;&gt;#<a name="$1">#gm;
	$text =~ s#&lt;/a&gt;#</a>#gm;

	# turn h4 brackets back
	$text =~ s#&lt;h4&gt;#<h4>#gm;
	$text =~ s#&lt;/h4&gt;#</h4>#gm;

	$text;
}


#
# generate parsed.edgar info
#
sub generateParsedDocuments {
	my($documents) = shift;
	my($tmpl) = shift;

	my @docs = ();
	for (@{$documents}) {
		my %document = %{$_};

		# clean up document text a little
		my $text = $document{'parsed-form'};
		return "" if (!$text);

		# get the form type
		my ($type) = ($text =~ /<parsed\.form.*?type=[\s+|'|"](.*)['|"]>?/g);
                # " for color syntax

		# get the function to call for the form type to generate 
		#	the HTML
		my $htmlFunc = $EDGAR::Forms::htmlType{$type};

		# call the subroutine, '$parseFunc' and get the parsed output.
		if ($htmlFunc && $text) {
			my $html = &$htmlFunc($text);

			# create PARSED_CONTENTS entry for template
			push(@docs, { 'PARSED_CONTENTS' => $html });

			$tmpl->param('PARSED_SUBMISSION' => 1);
		}
	}

	$tmpl->param('PARSED_EDGAR' => \@docs);
}

#
# generate Stamps info
#
sub generateStamps {
	my($stamps) = shift;
	my($tmpl) = shift;
	my @out_stamps = ();

	for (@{$stamps}) {
		push(@out_stamps, {'TRANSFORMER_STAMP' => $_->{'data'}});
	}

	$tmpl->param('STAMPS' => \@out_stamps);
}


#
# generate Table of Contents info
#
sub generateToC {
	my($edgardoc) = shift;
	my($tmpl) = shift;

	my($index, $desc, $type, $id, $anchor, $docCnt);
	my($tocPart, $tocItem, $tocNote, $tocTable);
	my($innerIndex, $tableCnt, $innerTableCnt, $partCnt, $itemCnt, $noteCnt);
	my %submission = %{$edgardoc};

	my @docData = ();
	my @toc = ();
	my $table_toc = ();
	# index of security considerations and parsed submission section 
	#	(at end of documents)
	my $parsed_index = 2;
	my $security_index = 2;

	$docCnt = 1;
	$tableCnt = 1;

	my ($tocValue, $indexStr, @toc_table);
	for (@{$submission{'documents'}}) {
		my %document = %{$_};
		my $docDesc = $document{'description'};
		if (!$docDesc || ($docDesc !~ /\w+/)) {
			$docDesc = $document{'type'};
			if (!$docDesc || ($docDesc =~ /^\d+$/)) {
				$docDesc = "FORM " . $docDesc;
			}
		}
		$docDesc = "Document " . $docCnt . ": " . $docDesc;

		# NUMBER is plus 1 due to registrant data always being first
		$index = $document{'sequence'} + 1;
		$anchor = "anchor" . $index;

		push(@toc, {'TOC_ANCHOR'=> $anchor, 'TOC_INDEX' => $index,
		            'TOC_TEXT'  => $docDesc, 'TOC_DOCUMENT' => 1,
			    'TOC_PART' => 0, 'TOC_ITEM' => 0,
			    'TOC_NOTE' => 0, 'TOC_TABLE' => 0
		           });

		# grab the document.item, document.part, document.note, and
		#    document.table items
		(@docData) = ($document{'text'} =~ /<document\.(.*)>/g);

		$innerIndex = $innerTableCnt = $partCnt = $itemCnt = $noteCnt = 1;
		foreach $tocValue (@docData) {
			$tocPart = $tocItem = $tocNote = $tocTable = 0;

			# pull out the id information from the document.(item|note|part|table)
			#    data to be used as the anchor string
			($anchor) = ($tocValue =~ /.*?id=[\s|"|']+(.*?)[\s|"|']+/);
                        # ' for color syntax
                       
			($desc) = ($tocValue =~ /.*?description=[\s|"|']+(.*)[\s|"|']+$/);
                        # ' for color syntax

        		($type) = ($tocValue =~ /^(.*?)\s.*/);
	        	if ($type eq "table") {
				if (!$desc || ($desc !~ /\w+/)) {
					$desc = "Document " . $docCnt . ": Table " . $innerTableCnt;
				}
				$tocTable = 1;

				if ($tocTable) {
					$tmpl->param('HAS_TABLE' => 1);
				} else {
					$tmpl->param('HAS_TABLE' => 0);
				}
				
				push(@toc_table, {'TOC_ANCHOR' => $anchor,  
						  'TOC_INDEX' => $tableCnt,
						  'TOC_TEXT'  => $desc,
						  'TOC_TABLE' => $tocTable,
					      });
				$tableCnt++;
				$innerTableCnt++;
				next;
			} elsif ($type eq "part") {
				$desc = "Part " . $partCnt . ": " . $desc;
				$partCnt++;
				$tocPart = 1;
			} elsif ($type eq "item") {
				$desc = "Item " . $itemCnt . ": " . $desc;
				$itemCnt++;
				$tocItem = 1;
			} elsif ($type eq "note") {
				$desc = "Note " . $noteCnt . ": " . $desc;
				$noteCnt++;
				$tocNote = 1;
			} else {
				print STDERR "generateToC: unknown type [$type]\n" 
				    if ($debug > 1);
			}

			$indexStr = $index . "." . $innerIndex;	
        		push(@toc, {'TOC_ANCHOR' => $anchor, 'TOC_INDEX' => $indexStr,
				    'TOC_TEXT'  => $desc, 'TOC_DOCUMENT' => 0,
				    'TOC_PART' => $tocPart, 'TOC_ITEM' => $tocItem,
				    'TOC_NOTE' => $tocNote, 'TOC_TABLE' => $tocTable
				});
			$innerIndex++;
		}

		$security_index++;
		$parsed_index++;
		$docCnt++;
	}

	$tmpl->param('TOC' => \@toc);
	$tmpl->param('TOC_TABLE' => \@toc_table);

	# if there's a parsed submission, the number associated with the 
	#	security item in the list needs to bump up 1
	my $parsedSub = $tmpl->param('PARSED_SUBMISSION');
	if ($parsedSub) {
		$security_index++;
	}

	# security index is last -- for now
	$tmpl->param('SECURITY_INDEX' => $security_index);
	$tmpl->param('PARSED_INDEX' => $parsed_index);
}


sub extractSection {
	my($data) = shift;
	my($start_text) = shift;
	my($end_text) = shift;

	# extracted section data
	my($sect) = "";

	$$data =~ /(${start_text}.*?${end_text})/gs && ($sect = $1);

	if ($sect) {
		# remove extracted section from data
		$$data =~ s/\Q$sect\E\n?//gs;
		# remove start/end tags from result
		$sect =~ s/${start_text}|$end_text//gs;
		# eat leading/trailing blank lines
		$sect =~ s/^(\s*\n)+|(\s*\n)+$//gs;
	}

	# return extracted section text
	$sect;
}

sub getNumberOfCols {
        my $text = shift;
        my($num_of_cols, $cols); 
        my $done = 0;
        while (!$done) {
                $text =~ s@<trow>\s+(.+?)</trow>@@s;
	        $cols = $1;   
                next if ($cols =~ /colspan/);
                $num_of_cols = $cols =~ tr/\n/\n/;
                $done = 1;
        }
	return $num_of_cols
}

#
# generate HTML version of parsed edgar table
#
sub parsedTable2html {
	my($xml) = shift;

	my $html = '';
	
	# save table description, if available
	$xml =~ s@<parsed\.table id="([^"]+)" document="\d+" sequence="\d+">@@;
        # " for color syntax
        my $id = $1;
        $id = "<A name=\"$id\"></A>\n";  

	# strip table element but save table description, if available
	$xml =~ s@<parsed\.table\s+.*?>@@gs;
	# strip table close element
	$xml =~ s@</parsed\.table>@@gs;

	# extract table parts
        my $caption = &extractSection(\$xml, "<tcaption>", "</tcaption>");

        my $header = &extractSection(\$xml, "<thead>", "</thead>");
        $header = &EDGAR::XML::encode($header);
	my $footer = &extractSection(\$xml, "<tfoot>", "</tfoot>");
        $footer = &EDGAR::XML::encode($footer);

	# everything else is body data
	my $body = $xml;

	# strip leading/trailing blank lines
	$body =~ s@^(\s*\n)+@@s;
	$body =~ s@(\s*\n)+$@@s;

        # remove the tbody tag
        $body =~ s@</?tbody>@@gs;

	# rows
	$body =~ s@<(/?)trow>@<$1TR>@gs;

	# columns
	$body =~ s@ ?<(/?)tcol[^>]*>@<$1TD>@gs;
  
	# open the HTML table
	$html = "<TABLE>";

	# table header
        my $num_of_cols;
        if ($header) {
                $num_of_cols = &getNumberOfCols($xml);
                $html .= "<TR><TD COLSPAN=\"$num_of_cols\">$header</TD></TR>\n";
        }

	# caption?
        if ($caption) {
                $caption = &parsedTableCaption2html($caption);
                $html .= $caption;
        }

	# table body
	$html .= $body . "\n";

	# table footer
        if ($footer) {
                $num_of_cols = &getNumberOfCols($xml) if (!$num_of_cols);
                $footer =~ s/---+|___+|===+//g;
                $html .= "<TR><TD COLSPAN=\"$num_of_cols\">$footer</TD></TR>";
        } 

	# close the HTML table
	$html .= "</TABLE>" . "\n";

        $html = $id . $html;
}

sub parsedTableCaption2html {
	my $caption = shift;

	# strip leading/trailing blank lines
	$caption =~ s@^(\s*\n)+@@s;
	$caption =~ s@(\s*\n)+$@@s;

	# rows
	$caption =~ s@<(/?)trow>@<$1TR>@gs;

	# columns
	$caption =~ s@ ?<(/?)tcol[^>]*>@<$1TH>@gs;

	if ($caption =~ /colspan/) {
		# deal with colspan
		# make into array
		my(@array) = split(/\n/, $caption);
		$caption = "";

		my($i, $colspan, $data);
		$colspan = 0;
		for $i (0 .. $#array) {
			if ($colspan) {
				$colspan--;
				next;
			}
			if ($array[$i] =~ m@colspan=("\d+")[^>]*>([^<]*)<@) {
				$colspan = $1;
				$data = $2;
				$caption .= "    <TH COLSPAN=$colspan>";
				$caption .= &EDGAR::XML::encode($data) . "</TH>\n"; 
				$colspan--;
			} else {
				$caption .= $array[$i] . "\n";
			}
		}
		$caption .= "  </TR>\n";

	} else {
		$caption =~ s@<(/?)tcol.*?>@<$1TH>@gs;
	}
		
	return $caption;
}

	
#
# get an element array from an XML tag
#
sub getElementArr {
	my($elementName) = shift;
	my($text) = shift;

	my(@elementArr) = ($text =~ /(<$elementName>.*?<\/$elementName>)/gs);

	my $element;
	if ($debug > 1) {
		foreach $element (@elementArr) {
			print STDERR "$elementName: $element\n";
		}
	}

	return(@elementArr);
}


#
# get an element from an XML tag
#
sub getElement {
	my($elementName) = shift;
	my($text) = shift;

	my($element) = ($text =~ /<$elementName.*?>(.*?)<\/$elementName>/s);

	if ($debug > 1) {
		print STDERR "$elementName: $element\n";
	}

	$element;
}

#
# get an element from an XML tag
#
sub getElementAll {
	my($elementName) = shift;
	my($text) = shift;

	my($element) = ($text =~ /(<$elementName.*?>.*?<\/$elementName>)/s);

	if ($debug > 1) {
		print STDERR "$elementName: $element\n";
	}

	$element;
}


#
# get an attribute from an item
#
sub getAttribute {
	my($element) = shift;
	my($attributeName) = shift;
	my($text) = shift;

	my($attribute) = ($text =~ /<$element.*?$attributeName\s*=['|"](.*?)['|"].*>/);
        # " for color syntax only

        if ($debug > 1) {
        	print STDERR "$element ($attributeName): $attribute\n"; 
        }

        $attribute;
}


#
# get an attribute array from an item
#
sub getAttributeArr {
	my($element) = shift;
	my($attributeName) = shift;
	my($text) = shift;

	my(@attributeArr) = ($text =~ /<$element.*?$attributeName\s*=['|"](.*?)['|"].*?>/gs);
        # " for color syntax only

	my $attribute;							      
	if ($debug > 1) {
		foreach $attribute (@attributeArr) {
			print STDERR "$element ($attributeName): $attribute\n"; 
		}
	}

	return(@attributeArr);
}

#######################################################
### paul miller pmiller new subs here
#######################################################

#
# do some minor clean up for all the text in a document
#
sub cleanText {
	my($text) = shift;

	$text =~ s@</?TEXT>@@gs;

	# get rid of large sections of blanks lines, messes up FromText
	$text =~ s/\n{5,}\n/\n\n/g;

	# remove PAGE tags and page numbers 
	$text =~ s@^\s*<PAGE/>\s*\n@\n\n@gm;
	$text =~ s@^\s*<PAGE/>\s+PAGE\s+\d+\s*\n@\n\n@gm;
	$text =~ s@^\s*SCREEN NUMBER:\s+\d+\s+PAGE NUMBER:\s+\d+@\n\n@gm;

	# remove <PAGE #> tags
	$text =~ s@<PAGE\s*\d*/?>@@gs;

	# remove numbers that are by themselves
	$text =~ s/^\s*\d+\s*$//gm;

	# XML entity clean up -- text2html encodes & -> &amp;
	$text = EDGAR::XML::decode($text);

	# clean up HTML/PDF document links
	$text =~ s@<(html|img|pdf)\s+src="([^"]+?)"\s*/>@$2@gs;
        # " for color syntax

 	$text;
}

#
# split text in to parsable hunks
#
sub splitText {
	my($text) = shift;
	my(@textStruct, $type, $data_ref, $hints);

	my @textList = split(/\n/, $text); 
	my $textList_aref = \@textList;

	my @array;

	# title text if exists is always first
	&gatherDebuggingInfo_start("title_split");
	$data_ref = &splitTitleText($textList_aref);
	&gatherDebuggingInfo_end("title_split", $data_ref, "title_split");

	$array[0] = "title";
	$array[1] = $data_ref;
	$array[2] = "";
	push(@textStruct, \@array);

	&gatherDebuggingInfo_start("unknown");
	($data_ref, $type, $hints) = &splitUnknownTypeText($textList_aref);
	&gatherDebuggingInfo_end($type . "_split", $data_ref, "unknown");

	my $cnt;
	while ($type ne "done") {
		my(@array);
		$array[0] = $type;
		$array[1] = $data_ref;
		$array[2] = $hints;
		push(@textStruct, \@array);

		&gatherDebuggingInfo_start("unknown");
		($data_ref, $type, $hints) = &splitUnknownTypeText($textList_aref);
		&gatherDebuggingInfo_end($type . "_split", $data_ref, "unknown");
	}

	return (\@textStruct);
}


#
# returns 1 if the text is centered
#
sub centeredText {
	my ($line) = shift;
	my ($lineLength) = 80;
	my ($error_padding) = 15;	
					# number of char away from center and 
					# still called centered text
	my ($frontPad, $sentenceLength, $ratio);

	$line =~ /^(\s*)(\S.+)/;
	$frontPad = length($1);
	$sentenceLength = length($2);

	# if line starts with 11 spaces or less spaces not centered
	return 0 if ($frontPad < 12);

	$ratio = ($frontPad*2 + $sentenceLength) - ($lineLength); # should be zero

	if ( abs($ratio) > $error_padding ) {
		return 0;	# not centered
	} else {
		return 1;	# centered
	}
} 


#
# this is a known type of text, must come first.  
# Does a minimum processing on the text, and splits it from the rest of
# the text.
#
sub splitTitleText {
	my($text_aref) = shift;
	my($newText, $line, $realTitleoff, $endHeader);
	
	my ($addedTitleInfo) = 0;
	my ($headerCnt) = 0;

	if ($#{$text_aref} < 6) {
		# no title with this few of lines
		$logger::DEBUG->saveErrorsCurrent('-error' => 
				"small doc length [$#{$text_aref}] no title");
		return [];
	}

	my $index = -1;
	while (++$index < $#{$text_aref}) {
		# some documents have info before the title
		# skip this "extra" info

		$line = $text_aref->[$index];
		next if (!$line || ($line =~ /^\s+$/) ||
			 ($line =~ /^[-_= ]+---|___|===[-_= ]+$/));

		last if (($line =~ /^\s/) || ($line =~ /\<document[\.\-]/));

		if ($index > 10) {
			# can't find the real title, skip it
			$index = 0;
			last;
		}
	}

	$text_aref->[$index] = "~~~TITLE-START~~~" . $text_aref->[$index];

	while (++$index < $#{$text_aref}) {
		$line = $text_aref->[$index];

		next if (!$line || ($line =~ /^\s+$/) ||
			 ($line =~ /^[-_= ]+---|___|===[-_= ]+$/));

		# end title on any document tags 
		last if ($line =~ /\<document[\.\-]/);

		# end title on char in first column
		last if ($line =~ /^\S/);

		if ( !&centeredText($line) ) {  
			# Title text must be centered, 
			# but check the next lines to be sure
			$index++;
			while ($text_aref->[$index] =~ /^\s*$/) { 
				last if ($index > $#{$text_aref});
				$index++; 	# find non-empty line
			} 

			# two non-centered lines in a row, end of title
			last if ( !&centeredText($text_aref->[$index]) );
		}
	}
	my @array = splice(@{$text_aref}, 0, $index-1);

	return \@array;
}

#
# the document table type of text.  <TABLE>..</TABLE>
# note these should also be in parsed.table
#
sub splitDocumentTable {
	my $text_aref = shift;

	my $index = -1;
	while (++$index < $#{$text_aref}) {

		last if ($text_aref->[$index] =~ m@</TABLE@i);
	}
	my @array = splice(@{$text_aref}, 0, $index+1);
	return \@array;
}


sub splitTableOfContents  {
	my($text_aref) = shift;

	# get rid of my TABLE OF CONTENTS TAG
	$text_aref->[0] =~ s/~~~TABLE-OF-CONTENTS~~~//;

	my $index = -1;
	# move down until out of Table of Contents
	while (++$index <= $#{$text_aref}) {
		last if ($text_aref->[$index] =~ /<\/?document[\.-]/);

		next if ($text_aref->[$index] =~ /^\s+$/);
		next if ($text_aref->[$index] =~ /\w\s*\.{5,}\s*\w/);

		# test next line
		next if ($text_aref->[$index+1] =~ /\w\s*\.{5,}\s*\w/);

		# test next line
		next if ($text_aref->[$index+2] =~ /\w\s*\.{5,}\s*\w/);

		# nope, get out
		last;
	}

	my @array = splice(@{$text_aref}, 0, $index);

	return (\@array);
}


####################################
# name  : splitTextTable
# input : an array ref
# output: list 	1 - string : table text
#		2 - array ref : the standard columns for the table
# side effects : the input ref gets changed
#
# describtion: 
# 	splits out the text table type of text for the rest of the text
#
sub splitTextTable {
	my($text_aref) = shift;
	my($table_row, @this_lines_cols);

	# get rid of my Table Tag and keep the std_cols 
 	$text_aref->[0] =~ s/~~~TEXT-TABLE~~~\[([^]]+)\]//;
        my @std_cols = split(/\s/, $1);

	# find the end of the table
	my $index = 0;  # get the first one for free
        while (++$index <= $#{$text_aref}) {
		last if (!$text_aref->[$index] || ($text_aref->[$index] =~ /^\s+$/));

		next if ($text_aref->[$index] =~ /^[-|_|= ]+---|___|===[-|_|= ]+$/);

		# test to see if the columns all line up
		# stay in table if "close" to being okay
		@this_lines_cols = ();
		push @this_lines_cols, 0 if ($text_aref->[$index] !~ /^\s\s/); 
		while ($text_aref->[$index] =~ /\s( +)(?=[^ ])/g) {  
			push @this_lines_cols, pos($text_aref->[$index]);
		}

		$table_row = &EDGAR::Table::inTableRow(\@std_cols, 
						       \@this_lines_cols);

		if (!$table_row) {
			# this row is not in the table, test next row
			last if (!$text_aref->[$index+1] || 
				($text_aref->[$index+1] =~ /^\s+$/));

			@this_lines_cols = ();
			push @this_lines_cols, 0 
			    if ($text_aref->[$index+1] !~ /^\s\s/);
			while ($text_aref->[$index+1] =~ /\s( +)(?=[^ ])/g) {  
				push @this_lines_cols, pos($text_aref->[$index+1]);
			}

			$table_row = &EDGAR::Table::inTableRow(\@std_cols, 
							       \@this_lines_cols);

			last if (!$table_row);
		}
	}
        my @new_text = splice(@{$text_aref}, 0, $index);

	return (\@new_text, \@std_cols);
}



####################################
# name  : splitUnknownTypeText
# input : an array ref
# output: list 	1 - string : text
#		2 - string : the type of text
#		3 - array ref : (currently only for tables), 
#				the standard column positions
# side effects : the input ref gets changed
#
# describtion: 
# 	takes an unknown type of text, figure out what type of text it is, 
# 	and split it from the rest of the text.
#
sub splitUnknownTypeText {
	my($text_aref) = shift;

	my($array_ref, $line, $hints);
	my($line_ref, $new_line_ptr);

	my $centered  = 0;
	my $prev_line = "";
	my $type = "general";  # the default type

	return (undef, "done", "") if ($#{$text_aref} < 0);

	# look at the first line of this text section
	$line = $text_aref->[0];

	if ($line =~ /<document[\.-]table/) {
		($array_ref) = &splitDocumentTable($text_aref);
		return ($array_ref, "docTable", ""); 
	}

	if ($line =~ /~~~TEXT-TABLE~~~/) {
		($array_ref, $hints) = &splitTextTable($text_aref);
		return ($array_ref, "textTable", $hints);
	}

  	if ($line =~ /~~~TABLE-OF-CONTENTS~~~/) {
  		($array_ref) = &splitTableOfContents($text_aref);
 		return ($array_ref, "tableOfContents", "");
 	}


	my (@std_columns, $start_location);
	my $line_ptr = -1;
	while (++$line_ptr <= $#{$text_aref}) {
		$line = $text_aref->[$line_ptr];

		# we are now in the "general" text type
		last if ($line =~ /\<document[\.-]table/);

		if (!$line || ($line =~ /^\s+$/)) {
			$prev_line = "";
			next;
		}

		# check to see if we are in a table
		@std_columns = &EDGAR::Table::ifTextTable($line_ptr, $text_aref);
		if ($#std_columns != -1) {
			$start_location = &EDGAR::Table::findStartOfTable($line_ptr, 
									  $text_aref, 
									  \@std_columns);
			my @array = splice(@{$text_aref}, 0, $start_location);
			$text_aref->[0] .= "~~~TEXT-TABLE~~~[@std_columns]";
			return (\@array, $type, "");
		}

		# check to see if we are in the Table Of Content
		$new_line_ptr = &ifTableOfContent($line_ptr, $text_aref);
 		if ($new_line_ptr) {
			my @array = splice(@{$text_aref}, 0, $new_line_ptr);
			$text_aref->[0] .= "~~~TABLE-OF-CONTENTS~~~";
 	 		return (\@array, $type, "");
 		}

		$prev_line = $line;
	}

	my @array = splice(@{$text_aref}, 0, $line_ptr);

	return (\@array, $type, "");
}

sub ifTableOfContent {
	my($line_ptr) = shift;
	my($text_aref) = shift;

	my($inToC);
	my $i = $line_ptr;

	if ($text_aref->[$line_ptr] =~ /^\s*TABLE OF CONTENTS?\s*$/i) {
		# looking for "TABLE OF CONTENTS" then following lines of
		# 	WORDS..........WORDS
		while (++$i < $line_ptr+10) {
			# not in a ToC
			return 0 if ($text_aref->[$i] =~ /<\/?document[\.-]/);

			# return the first line of the ToC
			return $i if ($text_aref->[$i] =~ /\w\s*\.{5,}\s*\w/);
		}
		# did not find the first line of ToC which in 10, give up
		return 0;

	} elsif ($text_aref->[$line_ptr] =~ /\w\s*\.{5,}\s*\w/) {
		return 0 if ($text_aref->[$line_ptr] =~ /<\/?document[\.-]/);

		# check lines below, need three line for ToC
		$inToC = 0;
		while (++$i < $line_ptr+6) {
			return 0 if ($text_aref->[$i] =~ /<\/?document[\.-]/);
			if ($text_aref->[$i] =~ /\w\s*\.{5,}\s*\w/) {
				$inToC++;
			}
		}

		return 0 if ($inToC < 2);

		$i = $line_ptr;
		# check lines above, stop on an empty line, or a tag
		while (--$i > 0) {
			if (!$text_aref->[$i] || ($text_aref->[$i] =~ /^\s+$/) ||
			    ($text_aref->[$i] =~ /<\/?document[\.-]/)) {
				return $i ? $i : 1;
			}
		}
	}

	return 0;
}


sub fixTableOfContents {
	my($text) = shift;
	my(%toc_hash, $new_text, $row_aref, $length, $spaces);

	%toc_hash = &parseTableOfContents($text);

	foreach $row_aref (@{$toc_hash{'body'}}) {

		$length = $toc_hash{'max_article'};
		$spaces = $length - length($row_aref->[0]);
		$row_aref->[0] .= sprintf(" ") x $spaces;

		$length = $toc_hash{'max_section'};
		$spaces = $length - length($row_aref->[1]);
		$row_aref->[1] .= sprintf(" ") x $spaces;

		$length = $toc_hash{'max_description'};
		$spaces = $length - length($row_aref->[2]);
		$row_aref->[2] .= sprintf(" ") x $spaces;

		$new_text .= $row_aref->[0] ."  ". $row_aref->[1] ."  ". 
		             $row_aref->[2] ."  ". $row_aref->[3] . "\n";
	}

	return $new_text;
}

# 
# toc_hash is
# 	page 	-> if exists "PAGE" header
# 	toc  	-> if exists "TABLE OF CONTENTS" header
# 	header	-> if exists any other header stuff
# 	body	-> \@@toc_list	
# 	max_article 	-> max length of the article part
# 	max_section 	-> max length of the section part
# 	max_description	-> max length of the description part
# 
# \@toc_list is
# 	0 -> article
# 	1 -> section
# 	2 -> description
# 	3 -> page number
# 
sub parseTableOfContents {
	my($text) = shift;
	my(%toc_hash);

	if (($text =~ /ARTICLE/) && ($text =~ /SECTION/)) {
		%toc_hash = &parseTableOfContentsARTICLE($text); 
		return %toc_hash;
	}

	return ();
}

sub parseTableOfContentsARTICLE {
	my($text) = shift;

	my(@toc_list, %toc_hash, $i, $cnt);
	my(@textArray) = split(/\n/, $text);

	$i = 0;
	# get header
	while ($textArray[$i] !~ /\w\.\.\.+\w/) {
		last if ($i > $#textArray);

		if ($textArray[$i] =~ /^\s+Page\s*$/i) {
			$toc_hash{'page'} = "Page";
		} elsif ($textArray[$i] =~ /TABLE OF CONTENTS/i) {
			$toc_hash{'toc'} = "TABLE OF CONTENTS";
		} elsif ($textArray[$i] =~ /\S/) {
			$toc_hash{'header'} .= $textArray[$i];
		}
		$i++;
	}

	my($article, $section, $description, $pageNum);
	my($max_article, $max_section, $max_description, $length);

	for ($cnt=$i; $cnt<=$#textArray; $cnt++) {
		next if ($textArray[$cnt] =~ /^\s+$/);

		$article = " "; 	$section = " ";
		$description = " "; 	$pageNum = " ";

		if ($textArray[$cnt] =~ s/^\s*(ARTICLE[^\.]+)\.+//) {
			$article = $1;
			$length = length($article);
			$max_article = $length if ($length > $max_article);

			($description) = $textArray[$cnt] =~ /(.+?)\s+\d+$/;
			$length = length($description);
			$max_description = $length if ($length > $max_description);
			
			($pageNum) = $textArray[$cnt] =~ /(\d+)\s*$/;
			$pageNum = " " if (!$pageNum);

			my(@tmp_array);  # keep ref
			push(@tmp_array, ($article, $section, $description, $pageNum));
			$toc_list[$i] = \@tmp_array;
			$i++;

		} elsif ($textArray[$cnt] =~ s/^\s*(SECTION\s+[\d\.]+)//) {
			$section = $1;
			$length = length($section);
			$max_section = $length if ($length > $max_section);

			($description) = $textArray[$cnt] =~ /^\s*([^\.]+)/;
			$length = length($description);
			$max_description = $length if ($length > $max_description);

			($pageNum) = $textArray[$cnt] =~ /(\d+)\s*$/;
			$pageNum = " " if (!$pageNum);
	
			my(@tmp_array);  # keep ref
			push(@tmp_array, ($article, $section, $description, $pageNum));
			$toc_list[$i] = \@tmp_array;
			$i++;

		} else {
			($description) = $textArray[$cnt] =~ /^\s*([^\.]+)/;
			($pageNum) = $textArray[$cnt] =~ /(\d+)\s*$/;
	
			$toc_list[$i-1][2] =~ s/\s*$/ /;
			$toc_list[$i-1][2] .= $description;
			$pageNum = " " if (!$pageNum);
			$toc_list[$i-1][3] = $pageNum;

			$length = length($toc_list[$i-1][2]);
			$max_description = $length if ($length > $max_description);
		}
	}
	$toc_hash{'max_article'} = $max_article;
	$toc_hash{'max_section'} = $max_section;
	$toc_hash{'max_description'} = $max_description;
	$toc_hash{'body'} = \@toc_list;

	return %toc_hash;
}


#
# formate the text into HTML
#
sub formatText {
	my($type) = shift;
	my($text_ref) = shift;
	my($hints) = shift;
	my $text;

	&gatherDebuggingInfo_start("known");  # yes I know the type

	if ($type eq "title") {
		$text = &formatTitleText($text_ref);
	} elsif ($type eq "general") {
		$text = &formatGeneralText($text_ref);
	} elsif ($type eq "docTable") {
		$text = &formatDocumentTable($text_ref);
	} elsif ($type eq "textTable") {
		$text = &formatTextTable($text_ref, $hints);
	} elsif ($type eq "tableOfContents") {
		$text = &formatTableOfContents($text_ref);
	} else {
		# if here, a major problem!
		print STDERR "edgar-html.pl: formatText Error unknown type [$type]\n"
			if ($debug > 1);
		$logger::DEBUG->saveErrorsCurrent('-error' => "unknown type [$type]");
	}
	&gatherDebuggingInfo_end_text($type . "_format", $text, "known");

	$text;
}

#
# formate this type text (title text) into HTML
#
sub formatTitleText {
	my($text_ref) = shift;
	my $text = join("\n", @{$text_ref});
	return "" if (!$text || ($text =~ /^\s+$/));

	# get rid of long dashed lines
	$text =~ s/^[-|_|= ]+---|___|===[-|_|= ]+$//gm;

	$text =~ s/\n/<BR>\n/g;
	$text =~ s/~~~TITLE-START~~~/<P CLASS="HEADER">\n/;
	$text .= "</P>\n";
}

#
# formate this type text (general text) into HTML
#
sub formatGeneralText {
	my $text_ref = shift;
	my $text = join("\n", @{$text_ref});
	return "" if (!$text || ($text =~ /^\s+$/s));

	# get rid of long dashed lines
	$text =~ s/^[-|_|= ]+---|___|===[-|_|= ]+$//gm;

	# change [o . -]  to * for bullets in unordered lists
	$text =~ s/^\s+[o\.-]\s+/ * /gm;

	# get rid of large blocks of empty text
	$text =~ s/\n[ \n]+\n/\n\n/g;

	$text =~ s/(\[.?.?\].*$)/$&~~~BR~~~/gm;

	# add Line Breaks after lines with dots (.....)
	$text =~ s/^([^\.]+\.{5,}.+)$/$1~~~BR~~~/gm;

	# keep the footnotes, put them on a seperate line
	$text =~ s@<(/?F[^>]+)>@\n\n~~~FOOTNOTE~~~$1~~~ETONTOOF~~~\n\n@gs;

	$text = text2html($text, paras => 1, bullets => 1,
				 urls => 1, email => 1);

	$text = &makeDocTags($text);

	# change footnotes back
	$text =~ s/~~~FOOTNOTE~~~([^~]+)~~~ETONTOOF~~~/<$1>/gs;

	# change BR tags
	$text =~ s/~~~BR~~~/<BR>/g; 

	$text;
}

#
# formate Document taged tables into HTML
#
sub formatDocumentTable {
	my $text_ref = shift;
	my $text = join("\n", @{$text_ref});
	return "" if (!$text || ($text =~ /^\s+$/));
	$logger::DEBUG->saveErrorsCurrent('-error' => "failing to a pre");

	# remove any custom tags
	$text =~ s/~~~[^~]+~~~//g;

	$text =~ s@</?TABLE>@@g; 
	$text =~ s@</?CAPTION>@@g; 
	$text =~ s@<C/>@@g; 
	$text =~ s@<S/>@@g; 
	$text = text2html($text, urls => 1, email => 1, pre => 1);
	$text = &makeDocTags($text);

	$text;
}

#
# formate text tables into HTML
#
sub formatTextTable {
	my $text_ref = shift;
	my $std_col_aref = shift;

	my $html = "<DIV align=\"CENTER\">\n";
	$html .= &EDGAR::Table::textTable2HTML($text_ref, $std_col_aref);
	$html .= "</DIV>\n";

	# remove any other custom tags
	$html =~ s/~~~[^~]+~~~//g;

	$html;
}


sub formatTableOfContents {
	my $text_ref = shift;
	my $text = join("\n", @{$text_ref});
	my $untouched = $text;

	# keep the footnotes, put them on a seperate line
	$text =~ s@<(/?F[^>]+)>@\n\n~~~FOOTNOTE~~~$1~~~ETONTOOF~~~\n\n@gs;

	# try and parse the ToC
	$text = &fixTableOfContents($text);

	if ($text) {
		$text = &text2html($text, paras => 1, urls => 1, email => 1, 
				   tables => 1);
	} else {
		$text = "could not fix the table of contents, use untouched";
	}

	if ($text !~ /<TABLE>/) {
		# the text2html could not make it a table, fail to a pre
	 	$text = text2html($untouched, urls => 1, email => 1, pre => 1);
		$logger::DEBUG->saveErrorsCurrent('-error' => "failing to a pre");
	}

	$text = &makeDocTags($text);

	# change footnotes back
	$text =~ s@\n~~~FOOTNOTE~~~([^~]+)~~~ETONTOOF~~~\n@<$1>@g;

	# remove the problem tag if there
	$text =~ s/~~~TABLE-PROBLEM~~~//;

	$text;
}


sub addTableStyleSheet {
	my($text) = shift;

	# center it
	$text = "<DIV align=\"CENTER\">\n" . $text . "\n</DIV>";
	$text =~ s@<TD>([\%\$\d,\.\(\) ]+)</TD>@<TD CLASS="NUMBER">$1</TD>@gm;
	$text =~ s@<TD>(.+?)</TD>@<TD CLASS="GENERIC">$1</TD>@gm; 

	$text;
}

#
# The text2html changed the document.table tags, change them back here
#
sub makeDocTags {
	my($doc) = shift;
	my($docWithTags,$line);

	foreach $line (split(/\n/, $doc)) {
		if ($line =~ /^([^\&]*)\&lt;document[\.-]\S+ id=\&quot;([^\&]+)/) {
			$line = "<P>$1\n<A name=\"$2\"></A>\n";
		} 
		$line =~ s@&lt;/document[\.-]\S+&gt;@<BR>@;
		$docWithTags .= $line."\n";
	}
	$docWithTags;
}

sub gatherDebuggingInfo_start {
	my $name = shift;
	$logger::DEBUG->current('-name' => $name);
	$logger::DEBUG->timerOnCurrent();
}

sub gatherDebuggingInfo_end {
	my $name = shift;
	my $amount_ref = shift;
	my $del_name = shift;

	$logger::DEBUG->increment('-name' => $name);  # increament the group
	$logger::DEBUG->changeCurrent('-name' => $name, '-del-name' => $del_name);
	$logger::DEBUG->timerOffCurrent();
	$logger::DEBUG->currentLines('-value' => $#{$amount_ref});
}

sub gatherDebuggingInfo_end_text {
	my $name = shift;
	my $text = shift;
	my $del_name = shift;

	$logger::DEBUG->increment('-name' => $name);  # increament the group
	$logger::DEBUG->changeCurrent('-name' => $name, '-del-name' => $del_name);
	$logger::DEBUG->timerOffCurrent();
	$logger::DEBUG->currentLines('-value' => $text);
}

#######################################################
## paul miller pmiller end of new subs
#######################################################

#
# generate HTML from parsed edgar for beneficial 1 data
#
sub edgarBeneficial1 {
	my($text) = shift;
	my($html) = "";

	if ($debug > 1) {
		print STDERR "TEXT IN:\n$text\n\n";
	}

	#
	# HEADER 
	#
	my($class) = getAttribute("parsed.form", "class", $text);
	my($sequence) = getAttribute("parsed.form", "sequence", $text);
	my($type) = getAttribute("parsed.form", "type", $text);

	#<!ELEMENT header.b1  (issuer.b1, (filer|seller), eventDate?, originalDate?,
   #	                (securityTitle,  broker?, numberShares?, marketValue?,
	#	                 numberOutstanding?, saleDate?, securitiesExchange?)* )? >
	my ($header) = getElement("header.b1", $text);

	#<!ELEMENT issuer.b1     (irs-id?, filedBy?, fileNumber?, address?) >
	#<!ATTLIST issuer.b1
   #	       name       CDATA  #IMPLIED
   #	       symbol     CDATA  #IMPLIED >
	my ($issuer) = getElementAll("issuer.b1", $header);
	my($issuerName) = getAttribute("issuer.b1", "name", $issuer);
	my($issuerSymbol) = getAttribute("issuer.b1", "symbol", $issuer);
	my($issuerIrsId) = getElement("irs-id", $issuer);
	my($filedBy) = getAttribute("filedBy", "type", $issuer);
	my($fileNumber) = getElement("fileNumber", $issuer);
	my($issuerStreet) = getElement("street", $issuer);
	my($issuerCity) = getElement("city", $issuer);
	my($issuerState) = getElement("region", $issuer);
	my($issuerZip) = getElement("code", $issuer);
	my($issuerCountry) = getElement("country", $issuer);

	#<!ELEMENT filer      (irs-id?, relationshipToIssuer?, address?) >
	#<!ATTLIST filer
   #       lastName   %personName;  #REQUIRED
   #       firstName  %personName;  #REQUIRED
   #       middleName %personName;  #IMPLIED
   #       fullName   %personName;  #REQUIRED >
	my($filer) = getElementAll("filer", $header);
	my($filerName) = getAttribute("filer", "fullName", $filer);
	my($filerIrsId) = getElement("irs-id", $filer);
	my($addendum) = getAttribute("relationshipToIssuer", "addendum", $filer);
	my($director) = getAttribute("relationshipToIssuer", "director", $filer);
	my($officer) = getAttribute("relationshipToIssuer", "officer", $filer);
	my($owner) = getAttribute("relationshipToIssuer", "owner", $filer);
	my($other) = getAttribute("relationshipToIssuer", "other", $filer);
	my($filerStreet) = getElement("street", $filer);
	my($filerCity) = getElement("city", $filer);
	my($filerState) = getElement("region", $filer);
	my($filerZip) = getElement("code", $filer);
	my($filerCountry) = getElement("country", $filer);

	#<!ELEMENT eventDate EMPTY>
	#<!ATTLIST eventDate
   #	       day       %DAY;    #IMPLIED
   #	       month     %MONTH;  #REQUIRED
   #	       year      %YEAR;   #REQUIRED >
	my($eventDay) = getAttribute("eventDate", "day", $header);
	my($eventMonth) = getAttribute("eventDate", "month", $header);
	my($eventYear) = getAttribute("eventDate", "year", $header);

	#<!ELEMENT originalDate EMPTY>
	#<!ATTLIST originalDate
   #	       day       %DAY;    #IMPLIED
   #	       month     %MONTH;  #REQUIRED
   #	       year      %YEAR;   #REQUIRED >
	my($originalDay) = getAttribute("originalDate", "day", $header);
	my($originalMonth) = getAttribute("originalDate", "month", $header);
	my($originalYear) = getAttribute("originalDate", "year", $header);

	#<!ELEMENT securityTitle (#PCDATA) >
	#<!ATTLIST securityTitle
   #	       footnote      IDREF  #IMPLIED >
	my($securityTitle) = getElement("securityTitle", $header);

	#<!ELEMENT broker       (brokerNumber?, address?) >
	#<!ATTLIST broker
   #	       lastName     %personName;    #REQUIRED
   #	       firstName    %personName;    #REQUIRED
   #	       middleName   %personName;    #IMPLIED
   #	       fullName     %personName;    #REQUIRED >
	my($broker) = getElementAll("broker", $header);
	my($brokerName) = getAttribute("fullName", "broker", $broker);
	my($brokerNumber) = getElement("brokerNumber", $broker);
	my($brokerStreet) = getElement("street", $broker);
	my($brokerCity) = getElement("city", $broker);
	my($brokerState) = getElement("region", $broker);
	my($brokerZip) = getElement("code", $broker);
	my($brokerCountry) = getElement("country", $broker);

	#<!ELEMENT numberShares  (#PCDATA) >
	my($numberShares) = getElement("numberShares", $header);

	#<!ELEMENT marketValue (marketDate) >
	#<!ATTLIST marketValue
   #	       currency    (%CURRENCY;)   'USD'
   #	       value       %dollarAmount; #REQUIRED >
	my($marketValue) = getElementAll("marketValue", $header);
	my($marketValueCurrency) = getAttribute("marketValue", "currency", $marketValue);
	my($marketValueValue) = getAttribute("marketValue", "value", $marketValue);

	#<!ELEMENT marketDate  EMPTY > 
	#<!ATTLIST marketDate
   #	       day         %DAY;           #IMPLIED
   #	       month       %MONTH;         #REQUIRED
   #	       year        %YEAR;          #REQUIRED >
	my($marketDay) = getAttribute("marketDate", "day", $marketValue);
	my($marketMonth) = getAttribute("marketDate", "month", $marketValue);
	my($marketYear) = getAttribute("marketDate", "year", $marketValue);

	#<!ELEMENT numberOutstanding  (#PCDATA) >
	my($numberOutstanding) = getElement("numberOutstanding", $header);

	#<!ELEMENT saleDate EMPTY >
	#<!ATTLIST saleDate
   #	       day      %DAY;    #IMPLIED
   #	       month    %MONTH;  #REQUIRED
   #	       year     %YEAR;   #REQUIRED >
	my($saleDay) = getAttribute("saleDate", "day", $header);
	my($saleMonth) = getAttribute("saleDate", "month", $header);
	my($saleYear) = getAttribute("saleDate", "year", $header);

	#<!ELEMENT securitiesExchange (#PCDATA) >
	#<!ATTLIST securitiesExchange
   #	       footnote           IDREF  #IMPLIED >
	my($securitiesExchange) = getElement("securitiesExchange", $header);

	# HTMLize HEADER data
	$html .= "<H3>$class</H3>\n";
	$html .= "<TABLE>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Type:</TD><TD>$type</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Sequence:</TD><TD>$sequence</TD>\n";
	$html .= "	</TR>\n";
	$html .= "</TABLE>\n";
	$html .= "<P>\n";

	$html .= "<TABLE>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Name:</TD><TD>$issuerName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Symbol:</TD><TD>$issuerSymbol</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer IRS Id:</TD><TD>$issuerIrsId</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filed By:</TD><TD>$filedBy</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>File Number:</TD><TD>$fileNumber</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Address:</TD><TD>$issuerStreet<BR>\n";
	$html .= "		                            $issuerCity, $issuerState $issuerZip<BR>\n";
	$html .= "		                            $issuerCountry</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filer Name:</TD><TD>$filerName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filer IRS Id:</TD><TD>$filerIrsId</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filer Relationship to Issuer:</TD><TD>director = $director<BR>\n";
	$html .= "		                                          officer = $officer<BR>\n";
	$html .= "		                                          owner = $owner<BR>\n";
	$html .= "		                                          other = $other<BR>\n";
	$html .= "		                                          addendum = $addendum</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filer Address:</TD><TD>$filerStreet<BR>\n";
	$html .= "		                            $filerCity, $filerState $filerZip<BR>\n";
	$html .= "		                            $filerCountry</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Event Date:</TD>\n";
	$html .= "		<TD>$eventMonth $eventDay, $eventYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Original Date:</TD>\n";
	$html .= "		<TD>$originalMonth $originalDay, $originalYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Security Title:</TD><TD>$securityTitle</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Broker Name:</TD><TD>$brokerName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Broker Number:</TD><TD>$brokerNumber</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Broker Address:</TD><TD>$brokerStreet<BR>\n";
	$html .= "		                            $brokerCity, $brokerState $brokerZip<BR>\n";
	$html .= "		                            $brokerCountry</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Number of Shares:</TD><TD>$numberShares</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Market Value:</TD><TD>$marketValueValue $marketValueCurrency</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Market Date:</TD>\n";
	$html .= "		<TD>$marketMonth $marketDay, $marketYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Number Outstanding:</TD><TD>$numberOutstanding</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Sale Date:</TD>\n";
	$html .= "		<TD>$saleMonth $saleDay, $saleYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Securities Exchange:</TD><TD>$securitiesExchange</TD>\n";
	$html .= "	</TR>\n";
	$html .= "</TABLE>\n";
	$html .= "<P>\n";

	#
	# NON-DERIVATIVE
	#

	if ($type eq "144") { 
		$html .= "<H3>Securities to be Sold</H3>\n";
	} else {
		$html .= "<H3>Non-Derivative Securities Beneficially Owned</H3>\n";
	}
	#<!ELEMENT nonDerivative  ((securityTitle, ownership, natureOfOwnership?),
   #	                       (amountOwned?, transactionDate?, transactionCode?,
   #	                        acquireDispose?, amountOwnedEOY?,
   #	                        amountOwnedEOM?)? )* >
	my (@nonDerivative) = getElementArr("nonDerivative", $text);
	my $nonDeriv;
	foreach $nonDeriv (@nonDerivative) {
		my($securityTitle) = getElement("securityTitle", $nonDeriv);
		#<!ELEMENT ownership EMPTY >
		#<!ATTLIST ownership
      #		    form      (D | I) 'D' >
		my($ownership) = getAttribute("ownership", "form", $nonDeriv);
      if ($ownership eq "D") {
         $ownership = "direct";
      } elsif ($ownership eq "I") {
         $ownership = "indirect";
      }

		#<!ELEMENT natureOfOwnership  (#PCDATA) >
		my($natureOfOwnership) = getElement("natureOfOwnership", $nonDeriv);

		#<!ELEMENT amountOwned  (#PCDATA) >
		my($amountOwned) = getElement("amountOwned", $nonDeriv);


		#<!ELEMENT transactionDate EMPTY >
		#<!ATTLIST transactionDate
      #    day   %DAY;     #IMPLIED
      #    month %MONTH;   #REQUIRED
      #    year  %YEAR;    #REQUIRED >
		my($transactionDay) = getAttribute("transactionDate", "day", $nonDeriv);
		my($transactionMonth) = getAttribute("transactionDate", "month", $nonDeriv);
		my($transactionYear) = getAttribute("transactionDate", "year", $nonDeriv);

		#<!ELEMENT transactionCode EMPTY >
		#<!ATTLIST transactionCode
      #	    code            CDATA  #IMPLIED
      #	    v.code          CDATA  #IMPLIED >
		my($transactionCode) = getAttribute("transactionCode", "code", $nonDeriv);
		my($transactionVCode) = getAttribute("transactionCode", "v.code", $nonDeriv);

		#<!ELEMENT acquireDispose      EMPTY >
		#<!ATTLIST acquireDispose
      #	    amount              CDATA        #IMPLIED
      #	    price               CDATA        #IMPLIED
      #	    acquiredOrDisposed  (A | D | NA) 'NA'
      #	    securitiesAcquired  CDATA        ''
      #	    securitiesDisposed  CDATA        ''
      #	    footnote            IDREF        #IMPLIED >
		my($acqDisAmount) = getAttribute("acquireDispose", "amount", $nonDeriv);
		my($acqDisPrice) = getAttribute("acquireDispose", "price", $nonDeriv);
		my($acqDis) = getAttribute("acquireDispose", "acquiredOrDisposed", $nonDeriv);
      if ($acqDis eq "A") {
         $acqDis = "acquired";
      } elsif ($acqDis eq "D") {
         $acqDis = "disposed";
      }
		my($securitiesAcq) = getAttribute("acquireDispose", "securitiesAcquired", $nonDeriv);
		my($securitiesDis) = getAttribute("acquireDispose", "securitiesDisposed", $nonDeriv);
		my($footnote) = getAttribute("acquireDispose", "footnote", $nonDeriv);

		#<!ELEMENT amountOwnedEOY  (#PCDATA) >
		my($amountOwnedEOY) = getElement("amountOwnedEOY", $nonDeriv);

		#<!ELEMENT amountOwnedEOM  (#PCDATA) >
		my($amountOwnedEOM) = getElement("amountOwnedEOM", $nonDeriv);

		# HTMLize NON-DERIVATIVE data
		$html .= "<TABLE>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Security Title:</TD><TD>$securityTitle</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership:</TD><TD>$ownership</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Nature of Ownership:</TD><TD>$natureOfOwnership</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Amount Owned:</TD><TD>$amountOwned</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Transaction Date:</TD>\n";
		$html .= "		<TD>$transactionMonth $transactionDay, $transactionYear</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Transaction Code:</TD><TD>$transactionCode</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Amount Acquired or Disposed:</TD><TD>$acqDisAmount</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Price:</TD><TD>$acqDisPrice</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Acquired or Disposed:</TD><TD>$acqDis</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Securities Acquired:</TD><TD>$securitiesAcq</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Securities Disposed:</TD><TD>$securitiesDis</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Amount Owned at End of Year:</TD><TD>$amountOwnedEOY</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Amount Owned at End of Month:</TD><TD>$amountOwnedEOM</TD>\n";
		$html .= "	</TR>\n";
		$html .= "</TABLE>\n";
		$html .= "<P>\n";
	}

	#
	# DERIVATIVE
	#
	if ($type eq "144") { 
		$html .= "<H3>Securities Sold During the Past Three Months</H3>\n";
	} else {
		$html .= "<H3>Derivative Securities Beneficially Owned</H3>\n";
	}

	#<!ELEMENT derivative  ((securityTitle, exercisableDate?, expirationDate?,
   #	                     underlyingSecurity, price?, ownership?,
   #	                     natureOfOwnership?), ((amountOwnedEOM|amountOwnedEOY),
   #	                     transactionDate, transactionCode, acquireDispose)?)? >
	my (@derivative) = getElementArr("derivative", $text);
	my $deriv;
	foreach $deriv (@derivative) {
		my($securityTitle) = getElement("securityTitle", $deriv);

		#<!ELEMENT exercisableDate EMPTY >
		#<!ATTLIST exercisableDate
      #    day   %DAY;     #IMPLIED
      #    month %MONTH;   #REQUIRED
      #    year  %YEAR;    #REQUIRED >
		my($exercisableDay) = getAttribute("exercisableDate", "day", $deriv);
		my($exercisableMonth) = getAttribute("exercisableDate", "month", $deriv);
		my($exercisableYear) = getAttribute("exercisableDate", "year", $deriv);

		#<!ELEMENT expirationDate EMPTY >
		#<!ATTLIST expirationDate
      #    day   %DAY;     #IMPLIED
      #    month %MONTH;   #REQUIRED
      #    year  %YEAR;    #REQUIRED >
		my($expirationDay) = getAttribute("expirationDate", "day", $deriv);
		my($expirationMonth) = getAttribute("expirationDate", "month", $deriv);
		my($expirationYear) = getAttribute("expirationDate", "year", $deriv);

		#<!ELEMENT underlyingSecurity  (amount)? >
		#<!ATTLIST underlyingSecurity
      #	    securityTitle       CDATA  #IMPLIED
      #	    footnote            IDREF  #IMPLIED >
		my($underlyingSecurity) = getElementAll("underlyingSecurity", $deriv);
		my($underlyingSecurityTitle) = getAttribute("underlyingSecurity", "securityTitle", $underlyingSecurity);

		#<!ELEMENT price       EMPTY >
		#<!ATTLIST price
      #		    dollarValue %dollarAmount;  #REQUIRED >
		my($price) = getAttribute("price", "dollarValue", $deriv);

		#<!ELEMENT ownership EMPTY >
		#<!ATTLIST ownership
      #		    form      (D | I) 'D' >
		my($ownership) = getAttribute("ownership", "form", $deriv);
		if ($ownership eq "D") {
			$ownership = "direct";
		} elsif ($ownership eq "I") {
			$ownership = "indirect";
		}

		#<!ELEMENT natureOfOwnership  (#PCDATA) >
		my($natureOfOwnership) = getElement("natureOfOwnership", $deriv);

		#<!ELEMENT amountOwnedEOY  (#PCDATA) >
		my($amountOwnedEOY) = getElement("amountOwnedEOY", $deriv);

		#<!ELEMENT amountOwnedEOM  (#PCDATA) >
		my($amountOwnedEOM) = getElement("amountOwnedEOM", $deriv);

		#<!ELEMENT transactionDate EMPTY >
		#<!ATTLIST transactionDate
      #    day   %DAY;     #IMPLIED
      #    month %MONTH;   #REQUIRED
      #    year  %YEAR;    #REQUIRED >
		my($transactionDay) = getAttribute("transactionDate", "day", $deriv);
		my($transactionMonth) = getAttribute("transactionDate", "month", $deriv);
		my($transactionYear) = getAttribute("transactionDate", "year", $deriv);

		#<!ELEMENT transactionCode EMPTY >
		#<!ATTLIST transactionCode
      #	    code            CDATA  #IMPLIED
      #	    v.code          CDATA  #IMPLIED >
		my($transactionCode) = getAttribute("transactionCode", "code", $deriv);
		my($transactionVCode) = getAttribute("transactionCode", "v.code", $deriv);

		#<!ELEMENT acquireDispose      EMPTY >
		#<!ATTLIST acquireDispose
      #	    amount              CDATA        #IMPLIED
      #	    price               CDATA        #IMPLIED
      #	    acquiredOrDisposed  (A | D | NA) 'NA'
      #	    securitiesAcquired  CDATA        ''
      #	    securitiesDisposed  CDATA        ''
      #	    footnote            IDREF        #IMPLIED >
		my($acqDisAmount) = getAttribute("acquireDispose", "amount", $deriv);
		my($acqDisPrice) = getAttribute("acquireDispose", "price", $deriv);
		my($acqDis) = getAttribute("acquireDispose", "acquiredOrDisposed", $deriv);
		if ($acqDis eq "A") {
			$acqDis = "acquired";
		} elsif ($acqDis eq "D") {
			$acqDis = "disposed";
		}
		my($securitiesAcq) = getAttribute("acquireDispose", "securitiesAcquired", $deriv);
		my($securitiesDis) = getAttribute("acquireDispose", "securitiesDisposed", $deriv);
		my($footnote) = getAttribute("acquireDispose", "footnote", $deriv);

		# HTMLize DERIVATIVE data
		$html .= "<TABLE>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Security Title:</TD><TD>$securityTitle</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Exercisable Date:</TD>\n";
		$html .= "		<TD>$exercisableMonth $exercisableDay, $exercisableYear</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Expiration Date:</TD>\n";
		$html .= "		<TD>$expirationMonth $expirationDay, $expirationYear</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Underlying Security Title:</TD><TD>$underlyingSecurityTitle</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Price:</TD><TD>$price</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership:</TD><TD>$ownership</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Nature of Ownership:</TD><TD>$natureOfOwnership</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Amount Owned at End of Year:</TD><TD>$amountOwnedEOY</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Amount Owned at End of Month:</TD><TD>$amountOwnedEOM</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Transaction Date:</TD>\n";
		$html .= "		<TD>$transactionMonth $transactionDay, $transactionYear</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Transaction Code:</TD><TD>$transactionCode</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Amount Acquired or Disposed:</TD><TD>$acqDisAmount</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Price:</TD><TD>$acqDisPrice</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Acquired or Disposed:</TD><TD>$acqDis</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Securities Acquired:</TD><TD>$securitiesAcq</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Securities Disposed:</TD><TD>$securitiesDis</TD>\n";
		$html .= "	</TR>\n";
		$html .= "</TABLE>\n";
		$html .= "<P>\n";
	}

	#
	# FOOTER
	#

	#<!ELEMENT footer   (signature*, signatureDate*, footnotes*, filer?) >
	my($footer) = getElement("footer", $text);
	my(@signature) = getElementArr("signature", $footer);
	my($signatureDay) = getAttribute("signatureDate", "day", $footer);
	my($signatureMonth) = getAttribute("signatureDate", "month", $footer);
	my($signatureYear) = getAttribute("signatureDate", "year", $footer);

	# HTMLize FOOTER data
	$html .= "<TABLE>\n";
	my $sig;
	foreach $sig (@signature) {
		$html .= "	<TR>\n";
		$html .= "		<TD>Signature:</TD><TD>$sig</TD>\n";
		$html .= "	</TR>\n";
	}
	$html .= "	<TR>\n";
	$html .= "		<TD>Signature Date:</TD>\n";
	$html .= "		<TD>$signatureMonth $signatureDay, $signatureYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "</TABLE>\n";

	if ($debug > 1) {
		print STDERR "\n\n\n************* HTML **********\n\n$html\n\n";
	}

	$html;

}


#
# generate HTML from parsed edgar for beneficial 2 data
#
sub edgarBeneficial2 {

	my($text) = shift;
	my($html) = "";

	if ($debug > 1) {
		print STDERR "TEXT IN:\n$text\n\n";
	}

	#
	# HEADER 
	#
	my($class) = getAttribute("parsed.form", "class", $text);
	my($sequence) = getAttribute("parsed.form", "sequence", $text);
	my($type) = getAttribute("parsed.form", "type", $text);

	#<!ELEMENT header.b2  (amendmentNumber?, issuer.b2, securityTitle, 
	#								eventDate?, (contact?, checkboxHeader)?) >
	my ($header) = getElement("header.b2", $text);

	#<!ELEMENT amendmentNumber  (#PCDATA) >
	my ($amendmentNum) = getElement("amendmentNumber", $header);


	#<!ELEMENT issuer.b2  (address?) >
	#<!ATTLIST issuer.b2
   #	       name    CDATA  ''
   #	       symbol  CDATA  '' >
	my($issuer) = getElementAll("issuer.b2", $header);
	my($issuerName) = getAttribute("issuer.b2", "name", $header);
	my($issuerSymbol) = getAttribute("issuer.b2", "symbol", $header);
	my($issuerStreet) = getElement("street", $issuer);
	my($issuerCity) = getElement("city", $issuer);
	my($issuerState) = getElement("region", $issuer);
	my($issuerZip) = getElement("code", $issuer);
	my($issuerCountry) = getElement("country", $issuer);

	#<!ELEMENT securityTitle (#PCDATA) >
	#<!ATTLIST securityTitle
   #	       footnote      IDREF  #IMPLIED >
	my($securityTitle) = getElement("securityTitle", $header);

	#<!ELEMENT cusip  (#PCDATA) >
	my($cusip) = getElement("cusip", $header);

	#<!ELEMENT eventDate EMPTY>
	#<!ATTLIST eventDate
   #	       day       %DAY;    #IMPLIED
   #	       month     %MONTH;  #REQUIRED
   #	       year      %YEAR;   #REQUIRED >
	my($eventDay) = getAttribute("eventDate", "day", $header);
	my($eventMonth) = getAttribute("eventDate", "month", $header);
	my($eventYear) = getAttribute("eventDate", "year", $header);

	#<!ELEMENT contact     (address?) >
	#<!ATTLIST contact
	#	        lastName    %personName;   #REQUIRED
	#          firstName   %personName;   #REQUIRED
	#          middleName  %personName;   #IMPLIED
	#          fullName    %personName;   #REQUIRED >
	my($contact) = getElementAll("contact", $header);
	my($contactName) = getAttribute("fullName", "contact", $contact);
	my($contactStreet) = getElement("street", $contact);
	my($contactCity) = getElement("city", $contact);
	my($contactState) = getElement("region", $contact);
	my($contactZip) = getElement("code", $contact);
	my($contactCountry) = getElement("country", $contact);

	#<!ELEMENT checkboxHeader  EMPTY >
	#<!ATTLIST checkboxHeader
	#          filed13G        (Y | N) 'N'
	#          paidFee         (Y | N) 'N' >
	my($filed13G) = getAttribute("checkboxHeader", "filed13G", $header);
	my($paidFee) = getAttribute("checkboxHeader", "paidFee", $header);

	# HTMLize HEADER data
	$html .= "<H3>$class</H3>\n";
	$html .= "<TABLE>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Type:</TD><TD>$type</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Sequence:</TD><TD>$sequence</TD>\n";
	$html .= "	</TR>\n";
	$html .= "</TABLE>\n";
	$html .= "<P>\n";

	$html .= "<TABLE>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Amendment Number:</TD><TD>$amendmentNum</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Name:</TD><TD>$issuerName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Symbol:</TD><TD>$issuerSymbol</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Address:</TD><TD>$issuerStreet<BR>\n";
	$html .= "		                            $issuerCity, $issuerState $issuerZip<BR>\n";
	$html .= "		                            $issuerCountry</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Security Title:</TD><TD>$securityTitle</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>CUSIP:</TD><TD>$cusip</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Event Date:</TD>\n";
	$html .= "		<TD>$eventMonth $eventDay, $eventYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Contact Name:</TD><TD>$contactName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Contact Address:</TD><TD>$contactStreet<BR>\n";
	$html .= "		                            $contactCity, $contactState $contactZip<BR>\n";
	$html .= "		                            $contactCountry</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filed 13G?:</TD><TD>$filed13G</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Paid Fee?:</TD><TD>$paidFee</TD>\n";
	$html .= "	</TR>\n";
	$html .= "</TABLE>\n";
	$html .= "<P>\n";


	#
	# COVER
	#

	$html .= "<H3>Cover Data</H3>\n";

	#<!ELEMENT cover  ((cusip, filer?, secOnly?, fundSource*, citizenship?,
	#                   sharesOwned, checkboxCover, aggregateAmount, 
	#                   classPercent, (personType*))+) >
	my (@coverArr) = getElementArr("cover", $text);

	my $cover;
	foreach $cover (@coverArr) {

		#<!ELEMENT cusip  (#PCDATA) >
		my($cusip) = getElement("cusip", $cover);

		#<!ELEMENT filer      (irs-id?, address?) >
		#<!ATTLIST filer
		#          lastName   %personName;  #REQUIRED
 		#          firstName  %personName;  #REQUIRED
		#          middleName %personName;  #IMPLIED
		#          fullName   %personName;  #REQUIRED >
		my($filer) = getElementAll("filer", $cover);
		my($filerName) = getAttribute("filer", "fullName", $filer);
		my($filerIrsId) = getElement("irs-id", $filer);
		my($filerStreet) = getElement("street", $filer);
		my($filerCity) = getElement("city", $filer);
		my($filerState) = getElement("region", $filer);
		my($filerZip) = getElement("code", $filer);
		my($filerCountry) = getElement("country", $filer);

		#<!ELEMENT secOnly  (#PCDATA) >
		my($secOnly) = getElement("secOnly", $cover);

		#<!ELEMENT fundSource  EMPTY >
		#<!ATTLIST fundSource
		#          category    (sc|bk|af|wc|pf|oo) #IMPLIED >
		my($fundSourceCat) = getAttribute("fundSource", "category", $cover);

		#<!ELEMENT citizenship  (#PCDATA) >
		my($citizenship) = getElement("citizenship", $cover);

		#<!ELEMENT sharesOwned        EMPTY >
		#<!ATTLIST sharesOwned
		#          soleVote           CDATA  #REQUIRED
		#          sharedVote         CDATA  #REQUIRED
		#          soleDispositive    CDATA  #IMPLIED
		#          sharedDispositive  CDATA  #REQUIRED >
		my($soleVote) = getAttribute("sharesOwned", "soleVote", $cover);
		my($sharedVote) = getAttribute("sharesOwned", "sharedVote", $cover);
		my($soleDispositive) = getAttribute("sharesOwned", "soleDispositive", $cover);
		my($sharedDispositive) = getAttribute("sharesOwned", "sharedDispositive", $cover);

		#<!ELEMENT checkboxCover EMPTY >
		#<!ATTLIST checkboxCover
		#          group         (a | b)     #IMPLIED
		#          disclosure    (Y | N)     'N'
		#          aggregate     (Y | N)     'N'
		#          checkRule     (b | c | d) #IMPLIED >
		my($checkBoxGroup) = getAttribute("checkboxCover", "group", $cover);
		my($checkBoxDisc) = getAttribute("checkboxCover", "disclosure", $cover);
		my($checkBoxAgg) = getAttribute("checkboxCover", "aggregate", $cover);
		my($checkBoxRule) = getAttribute("checkboxCover", "checkRule", $cover);

		#<!ELEMENT aggregateAmount (#PCDATA) >
		my($aggregateAmount) = getElement("aggregateAmount", $cover);

		#<!ELEMENT classPercent (#PCDATA) >
		my($classPercent) = getElement("classPercent", $cover);

		#<!ELEMENT personType  (role?, notes?) >
		my($personType) = getElement("personType", $cover);

		#<!ELEMENT role     EMPTY >
		#<!ATTLIST role
		#          category (bd | bk | ic | iv | 
		#                    ia | ep | hc | sa | 
		#                    cp | co | pn | in | 
		#                    oo
		#                   )  #REQUIRED >
		my(@roleCategoryArr) = getAttributeArr("role", "category", $personType);

		#<!ELEMENT notes  (#PCDATA) >
		my($notes) = getElement("notes", $personType);


		# HTMLize COVER data
		$html .= "<TABLE>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>CUSIP:</TD><TD>$cusip</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Filer Name:</TD><TD>$filerName</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Filer IRS Id:</TD><TD>$filerIrsId</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Filer Address:</TD><TD>$filerStreet<BR>\n";
		$html .= "		                            $filerCity, $filerState $filerZip<BR>\n";
		$html .= "		                            $filerCountry</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>SEC Only:</TD><TD>$secOnly</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Fund Source Category:</TD><TD>$fundSourceCat</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Citizenship:</TD><TD>$citizenship</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Shares Owned Sole Vote:</TD><TD>$soleVote</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Shares Owned Shared Vote:</TD><TD>$sharedVote</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Shares Owned Sole Dispositive:</TD><TD>$soleDispositive</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Shares Owned Shared Dispositive:</TD><TD>$sharedDispositive</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Check Box Cover Group:</TD><TD>$checkBoxGroup</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Check Box Cover Disclosure:</TD><TD>$checkBoxDisc</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Check Box Cover Aggregate:</TD><TD>$checkBoxAgg</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Check Box Cover Rule:</TD><TD>$checkBoxRule</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Aggregate Amount:</TD><TD>$aggregateAmount</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Class Percent:</TD><TD>$classPercent</TD>\n";
		$html .= "	</TR>\n";
		my $roleCategory;
		foreach $roleCategory (@roleCategoryArr) {
			$html .= "	<TR>\n";
			$html .= "		<TD>Role Category:</TD><TD>$roleCategory</TD>\n";
			$html .= "	</TR>\n";
		}
		$html .= "	<TR>\n";
		$html .= "		<TD>Notes:</TD><TD>$notes</TD>\n";
		$html .= "	</TR>\n";
		$html .= "</TABLE>\n";
		$html .= "<P>\n";
	}

	#
	# ITEMS
	#

	$html .= "<H3>Items Data</H3>\n";

	#<!ELEMENT items ((securityTitle, issuer.b2), (filer?, occupation?, 
	#                  criminalRecord?, civilRecord?, citizenship?, cusip),
	#                  (otherReceiver), (considerationSource?, purpose?,
	#                  issuerInterest?, contracts?, exhibits*), (roleCheck*,
	#                  ownership.b2?, ownershipCeased?, subsidiary?, groupID?,
	#                  dissolution?, certification?)) >
	my ($items) = getElementArr("items", $text);

	#<!ELEMENT securityTitle  (#PCDATA) >
	$securityTitle = getElement("securityTitle", $items);

	#<!ELEMENT issuer.b2  (address?) >
	#<!ATTLIST issuer.b2
   #	       name    CDATA  ''
   #	       symbol  CDATA  '' >
	$issuer = getElementAll("issuer.b2", $items);
	$issuerName = getAttribute("issuer.b2", "name", $items);
	$issuerSymbol = getAttribute("issuer.b2", "symbol", $items);
	$issuerStreet = getElement("street", $issuer);
	$issuerCity = getElement("city", $issuer);
	$issuerState = getElement("region", $issuer);
	$issuerZip = getElement("code", $issuer);
	$issuerCountry = getElement("country", $issuer);

	#<!ELEMENT filer      (irs-id?, address?) >
	#<!ATTLIST filer
	#          lastName   %personName;  #REQUIRED
 	#          firstName  %personName;  #REQUIRED
	#          middleName %personName;  #IMPLIED
	#          fullName   %personName;  #REQUIRED >
	my($filer) = getElementAll("filer", $items);
	my($filerName) = getAttribute("filer", "fullName", $filer);
	my($filerIrsId) = getElement("irs-id", $filer);
	my($filerStreet) = getElement("street", $filer);
	my($filerCity) = getElement("city", $filer);
	my($filerState) = getElement("region", $filer);
	my($filerZip) = getElement("code", $filer);
	my($filerCountry) = getElement("country", $filer);

	#<!ELEMENT occupation        (address?) >
	#<!ATTLIST occupation
	#          description       CDATA ''
	#          businessName      CDATA ''
	#          principalBusiness CDATA ''
	#          footnote          IDREF    #IMPLIED >
	my($occupation) = getElementAll("occupation", $items);
	my($occDesc) = getAttribute("occupation", "description", $occupation);
	my($occBusName) = getAttribute("occupation", "businessName", $occupation);
	my($occPrinBus) = getAttribute("occupation", "principalBusiness", $occupation);

	#<!ELEMENT criminalRecord  (#PCDATA) >
	my($criminalRecord) = getElement("criminalRecord", $items);

	#<!ELEMENT civilRecord  (#PCDATA) >
	my($civilRecord) = getElement("civilRecord", $items);

	#<!ELEMENT citizenship  (#PCDATA) >
	my($citizenship) = getElement("citizenship", $items);

	#<!ELEMENT cusip  (#PCDATA) >
	$cusip = getElement("cusip", $items);

	#<!ELEMENT otherReceiver  (#PCDATA) >
	my($otherReceiver) = getElement("otherReceiver", $items);

	#<!ELEMENT considerationSource EMPTY >
	#<!ATTLIST considerationSource
	#          source              CDATA ''
	#          amount              CDATA ''
	#          footnote            IDREF #IMPLIED >
	my($conSource) = getAttribute("considerationSource", "source", $items);
	my($conAmount) = getAttribute("considerationSource", "amount", $items);

	#<!ELEMENT purpose  (#PCDATA) >
	my($purpose) = getElement("purpose", $items);

	#<!ELEMENT issuerInterest (beneficiallyOwned*, solePower?, 
	#                          recentTransactions?, otherReceiver?, 
	#                          ownershipCeased?) >
	my($issuerInterest) = getElement("issuerInterest", $items);

	#<!ELEMENT beneficiallyOwned  (securityTitle) >
	#<!ATTLIST beneficiallyOwned
	#          acquireRight       CDATA        #IMPLIED
	#          aggregateAmount    CDATA        #REQUIRED
	#          percentOfClass     %percentage; #REQUIRED
	#          footnote           IDREF        #IMPLIED >
	my($beneficiallyOwned) = getElementAll("beneficiallyOwned", $issuerInterest);
	my($benOwnSecurityTitle) = getElement("securityTitle", $beneficiallyOwned);
	my($benOwnAcqRight) = getAttribute("beneficiallyOwned", "acquireRight", 
                                      $beneficiallyOwned);
	my($benOwnAggAmount) = getAttribute("beneficiallyOwned", "aggregateAmount", 
                                      $beneficiallyOwned);
	my($benOwnPercentClass) = getAttribute("beneficiallyOwned","percentOfClass", 
                                      $beneficiallyOwned);

	#<!ELEMENT solePower  (#PCDATA) >
	my($solePower) = getElement("solePower", $issuerInterest);

	#<!ELEMENT recentTransactions  (amount) >
	#<!ATTLIST recentTransactions
	#          lastName            %personName;  #IMPLIED
	#          firstName           %personName;  #IMPLIED
	#          middleName          %personName;  #IMPLIED
	#          fullName            %personName;  #IMPLIED
	#          day                 %DAY;         #IMPLIED
	#          month               %MONTH;       #IMPLIED
	#          year                %YEAR;        #IMPLIED
	#          averagePrice        CDATA         ''
	#          transactionDetail   CDATA         ''
	#          amount              CDATA         ''
	#          footnote            IDREF         #IMPLIED >
	my($recentTransactions) = getElementAll("recentTransactions", 
                                           $issuerInterest);
	my($recTranAmount) = getElement("amount", $recentTransactions);
	my($recTranName) = getAttribute("recentTransactions","fullName", 
                                      $recentTransactions);
	my($recTranDay) = getAttribute("recentTransactions","day", 
                                      $recentTransactions);
	my($recTranMonth) = getAttribute("recentTransactions","month", 
                                      $recentTransactions);
	my($recTranYear) = getAttribute("recentTransactions","year", 
                                      $recentTransactions);
	my($recTranAvePrice) = getAttribute("recentTransactions","averagePrice", 
                                      $recentTransactions);
	my($recTranDetail) = getAttribute("recentTransactions","transactionDetail", 
                                      $recentTransactions);

	#<!ELEMENT otherReceiver  (#PCDATA) >
	my($otherReceiverIssuer) = getElement("otherReceiver", $issuerInterest);

	#<!ELEMENT ownershipCeased  EMPTY >
	#<!ATTLIST ownershipCeased
	#          check            (Y | N )  'N'
	#          day              %DAY;     #IMPLIED
	#          month            %MONTH;   #IMPLIED
	#          year             %YEAR;    #IMPLIED
	#          footnote         IDREF     #IMPLIED >
	my($ownCeasedCheck) = getAttribute("ownershipCeased","check", 
                                      $issuerInterest);
	my($ownCeasedDay) = getAttribute("ownershipCeased","day", 
                                      $issuerInterest);
	my($ownCeasedMonth) = getAttribute("ownershipCeased","month", 
                                      $issuerInterest);
	my($ownCeasedYear) = getAttribute("ownershipCeased","year", 
                                      $issuerInterest);

	#<!ELEMENT contracts (#PCDATA) >
	my($contracts) = getElement("contracts", $items);

	#<!ELEMENT exhibits    EMPTY >
	#<!ATTLIST exhibits
	#          name        CDATA  ''
	#          description CDATA  ''
	#          footnote    IDREF  #IMPLIED >
	my($exhibitsName) = getAttribute("exhibits", "name", $items);
	my($exhibitsDesc) = getAttribute("exhibits", "description", $items);

	#<!ELEMENT roleCheck     EMPTY >
	#<!ATTLIST roleCheck
	#          checkOptions  (bd | bk | ic | ric | 
	#                         ia | bp | hc | sa | 
	#                         cp | gp
	#                        )  #REQUIRED >
	my($checkOptions) = getAttribute("roleCheck", "checkOptions", $items);

	#<!ELEMENT ownership.b2  EMPTY >
	#<!ATTLIST ownership.b2
	#          amount            CDATA ''
	#          percent           CDATA ''
	#          soleVote          CDATA ''
	#          sharedVote        CDATA ''
	#          sharedDispositive CDATA ''
	#          soleDispositive   CDATA ''
	#          footnote          IDREF #IMPLIED >
	my(@ownershipAmount) = getAttributeArr("ownership.b2", "amount", $items);
	my(@ownershipPercent) = getAttributeArr("ownership.b2", "percent", $items);
	my(@ownershipSoleVote) = getAttributeArr("ownership.b2", "soleVote", $items);
	my(@ownershipSharedVote) = getAttributeArr("ownership.b2", "sharedVote", 
                                           $items);
	my(@ownershipSharedDisp) = getAttributeArr("ownership.b2", "sharedDispositive", 
                                           $items);
	my(@ownershipSoleDisp) = getAttributeArr("ownership.b2", "soleDispositive", 
                                           $items);

	#<!ELEMENT ownershipCeased  EMPTY >
	#<!ATTLIST ownershipCeased
	#          check            (Y | N )  'N'
	#          day              %DAY;     #IMPLIED
	#          month            %MONTH;   #IMPLIED
	#          year             %YEAR;    #IMPLIED
	#          footnote         IDREF     #IMPLIED >
	$ownCeasedCheck = getAttribute("ownershipCeased","check", $items);
	$ownCeasedDay = getAttribute("ownershipCeased","day", $items);
	$ownCeasedMonth = getAttribute("ownershipCeased","month", $items);
	$ownCeasedYear = getAttribute("ownershipCeased","year", $items);

	#<!ELEMENT subsidiary  (#PCDATA) >
	my($subsidiary) = getElement("subsidiary", $items);

	#<!ELEMENT groupID  EMPTY >
	#<!ATTLIST groupID
	#          id       CDATA ''
	#          class    CDATA ''
	#          footnote IDREF #IMPLIED >
	my($groupId) = getAttribute("groupID","id", $items);
	my($groupIdClass) = getAttribute("groupID","class", $items);

	#<!ELEMENT dissolution  (#PCDATA) >
	my($dissolution) = getElement("dissolution", $items);

	#<!ELEMENT certification  EMPTY >
	#<!ATTLIST certification
	#          rule           (A | B) #IMPLIED >
	my($certificationRule) = getAttribute("certification","rule", $items);


	# HTMLize ITEMS data
	$html .= "<TABLE>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Security Title:</TD><TD>$securityTitle</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Name:</TD><TD>$issuerName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Symbol:</TD><TD>$issuerSymbol</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Issuer Address:</TD><TD>$issuerStreet<BR>\n";
	$html .= "		                            $issuerCity, $issuerState $issuerZip<BR>\n";
	$html .= "		                            $issuerCountry</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filer Name:</TD><TD>$filerName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filer IRS ID:</TD><TD>$filerIrsId</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Filer Address:</TD><TD>$filerStreet<BR>\n";
	$html .= "		                            $filerCity, $filerState $filerZip<BR>\n";
	$html .= "		                            $filerCountry</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Occupation Description:</TD><TD>$occDesc</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Occupation Business Name:</TD><TD>$occBusName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Occupation Principal Business:</TD><TD>$occPrinBus</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Criminal Record:</TD><TD>$criminalRecord</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Civil Record:</TD><TD>$civilRecord</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Citizenship:</TD><TD>$citizenship</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>CUSIP:</TD><TD>$cusip</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Other Receiver:</TD><TD>$otherReceiver</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Consideration Source:</TD><TD>$conSource</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Consideration Amount:</TD><TD>$conAmount</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Purpose:</TD><TD>$purpose</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Beneficially Owned Security Title:</TD><TD>$benOwnSecurityTitle</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Beneficially Owned Acquire Right:</TD><TD>$benOwnAcqRight</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Beneficially Owned Aggregate Amount:</TD><TD>$benOwnAggAmount</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Beneficially Owned Percent Class:</TD><TD>$benOwnPercentClass</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Sole Power:</TD><TD>$solePower</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Recent Transactions Amount:</TD><TD>$recTranAmount</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Recent Transactions Name:</TD><TD>$recTranName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Recent Transactions Date:</TD>\n";
	$html .= "		<TD>$recTranMonth $recTranDay, $recTranYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Recent Transactions Average Price:</TD><TD>$recTranAvePrice</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Recent Transactions Detail:</TD><TD>$recTranDetail</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Other Receiver (Issuer):</TD><TD>$otherReceiverIssuer</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Owner Ceased Check:</TD><TD>$ownCeasedCheck</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Owner Ceased Date:</TD>\n";
	$html .= "		<TD>$ownCeasedMonth $ownCeasedDay, $ownCeasedYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Contracts:</TD><TD>$contracts</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Exhibits Name:</TD><TD>$exhibitsName</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Exhibits Description:</TD><TD>$exhibitsDesc</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Role Check Options:</TD><TD>$checkOptions</TD>\n";
	$html .= "	</TR>\n";

	$html .= "	<TR>\n";
	$html .= "		<TD COLSPAN=2><B>Ownership</B></TD>\n";
	$html .= "	</TR>\n";
	my $cnt;
	for ($cnt = 0; $cnt < $#ownershipAmount; $cnt++) {
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership Amount:</TD><TD>$ownershipAmount[$cnt]</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership Percent:</TD><TD>$ownershipPercent[$cnt]</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership Sole Vote:</TD><TD>$ownershipSoleVote[$cnt]</TD>\n"; 
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership Shared Vote:</TD><TD>$ownershipSharedVote[$cnt]</TD>\n";
		$html .= "	</TR>\n";
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership Shared Dispositive:</TD><TD>$ownershipSharedDisp[$cnt]</TD>\n";
		$html .= "	</TR>\n"; 
		$html .= "	<TR>\n";
		$html .= "		<TD>Ownership Sole Dispositive:</TD><TD>$ownershipSoleDisp[$cnt]</TD>\n";
		$html .= "	</TR>\n";
	}

	$html .= "	<TR>\n";
	$html .= "		<TD>Ownership Ceased Check:</TD><TD>$ownCeasedCheck</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Ownership Ceased Date:</TD>\n";
	$html .= "		<TD>$ownCeasedMonth $ownCeasedDay, $ownCeasedYear</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Subsidiary:</TD><TD>$subsidiary</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Group ID:</TD><TD>$groupId</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Group ID Class:</TD><TD>$groupIdClass</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	$html .= "		<TD>Dissolution:</TD><TD>$dissolution</TD>\n";
	$html .= "	</TR>\n";
	$html .= "	<TR>\n";
	my $certification;  # broken!!!!!!!!
	$html .= "		<TD>Certification:</TD><TD>$certification</TD>\n";
	$html .= "	</TR>\n";
	$html .= "</TABLE>\n";
	$html .= "<P>\n";

	#
	# FOOTER
	#

	#<!ELEMENT footer   (signature*, signatureDate*, footnotes*, filer?) >
	my($footer) = getElement("footer", $text);
	my(@signatureArr) = getElementArr("signature", $footer);
	my($signatureDay) = getAttribute("signatureDate", "day", $footer);
	my($signatureMonth) = getAttribute("signatureDate", "month", $footer);
	my($signatureYear) = getAttribute("signatureDate", "year", $footer);
	my(@filerArr) = getAttributeArr("filer", "fullName", $footer);

	# HTMLize FOOTER data
	$html .= "<TABLE>\n";
	my $signature;
	foreach $signature (@signatureArr) {
		$html .= "	<TR>\n";
		$html .= "		<TD>Signature:</TD><TD>$signature</TD>\n";
		$html .= "	</TR>\n";
	}
	$html .= "	<TR>\n";
	$html .= "		<TD>Signature Date:</TD>\n";
	$html .= "		<TD>$signatureMonth $signatureDay, $signatureYear</TD>\n";
	$html .= "	</TR>\n";
	foreach $filer (@filerArr) {
		$html .= "	<TR>\n";
		$html .= "		<TD>Filer:</TD><TD>$filer</TD>\n";
		$html .= "	</TR>\n";
	}
	$html .= "</TABLE>\n";

	if ($debug > 1) {
		print STDERR "\n\n\n************* HTML **********\n\n$html\n\n";
	}

	$html;

}

1;



=head1 NAME

edgar-html.pl - EDGAR date routines

=head1 PACKAGE

EDGAR::HTML

=head1 SYNOPSIS

require edgar-html.pl;


=head1 REQUIRES

Perl, version 5.001 or higher, HTML::Template, and HTML::FromText.

=head1 DESCRIPTION

support to convert SEC EDGAR (edgardoc DTD format) XML documents to
HTML  

=over 3

=head1 METHODS


=head2 toHTML

=item *

generate HTML format edgardoc

=item *

HTML text is returned. 

=item example:

my ($HTML) = &EDGAR::HTML::toHTML(\%edgardoc, $template, $templateVersion);


=head2 generateSubmissionHeader

=item *

generate submission header information

=item *

The HTML template is updated. 

=item example:

&EDGAR::HTML::generateSubmissionHeader(\%submission, $tmpl, $templateVersion);


=head2 generateTransformer

=item *

generate transformer information

=item *

The HTML template is updated. 

=item example:

&EDGAR::HTML::generateTransformer(\%submission, $tmpl, $templateVersion);



=head2 generateRegistrants

=item *

generate registrant information

=item *

The HTML template is updated. 

=item example:

&EDGAR::HTML::generateRegistrant(\%submission, $tmpl, $templateVersion);



=head2 generateDocuments

=item *

generate document information

=item *

The HTML template is updated. 

=item example:

&EDGAR::HTML::generateDocument(\%submission, $tmpl, $templateVersion);



=head2 generateParsedEdgar

=item *

generate parsed EDGAR information

=item *

The HTML template is updated. 

=item example:

&EDGAR::HTML::generateParsedEdgar(\%submission, $tmpl);



=head2 generateStamps

=item *

generate stamps information

=item *

The HTML template is updated. 

=item example:

&EDGAR::HTML::generateStamps(\@stamps, $tmpl);


=head2 generateToC

=item *

generate table of contents information

=item *

The HTML template is updated. 

=item example:

&EDGAR::HTML::generateToC(\%submission, $tmpl);



=head2 getElementArr

=item *

obtains an element from an XML tag

=item *

An array of elements that are within the tag is returned.

=item example:

my(@elementData) = &EDGAR::HTML::getElementArr("elementName", $text);



=head2 getElement

=item *

obtains an element from an XML tag

=item *

An element that is within a tag is returned.

=item example:

my($elementData) = &EDGAR::HTML::getElement("elementName", $text);



=head2 getElementAll

=item *

obtains an element and attributes of an XML tag

=item *

An element and its attributes that are within the tag is returned.

=item example:

my($elementData) = &EDGAR::HTML::getElementAll("elementName", $text);


=head2 getAttribute

=item *

obtains an attribute of an XML tag

=item *

An attributes value is returned.

=item example:

my($attrVal) = &EDGAR::HTML::getAttribute("elementName", "attributeName", $text);



=head2 getAttributeArr

=item *

obtains an array of attribute values of an XML tag

=item *

An array of attribute values is returned.

=item example:

my(@attrVal) = &EDGAR::HTML::getAttributeArr("elementName", "attributeName", $text);



=head2 toParagraphs

=item *

generates paragraph tags within the text

=item *

The string passed in is returned with HTML paragraph tags in places where it is believed they should be.

=item example:

my($parText) = &EDGAR::HTML::toParagraphs($text);



=head2 edgarBeneficial1

=item *

generates HTML from parsed edgar data for beneficial 1 forms

=item *

Beneficial 1 XML data is returned in HTML format.

=item example:

my($HTMLtext) = &EDGAR::HTML::edgarBeneficial1($xml);


=head2 edgarBeneficial2

=item *

generates HTML from parsed edgar data for beneficial 2 forms

=item *

Beneficial 2 XML data is returned in HTML format.

=item example:

my($HTMLtext) = &EDGAR::HTML::edgarBeneficial2($xml);




=back

=head1 COPYRIGHT

Copyright 1999 Invisible Worlds.

=cut