#!/bin/perl # # concat.pl $Id: concat.pl,v 1.2 2002/06/19 16:39:34 lmiller Exp $ # Dan Brickley # A fearful hack. # mangles together a heap of original and derrived HTML docs. use strict; my $cfg = shift || 'conf/concat.txt'; my $debug=1; #my $base = '../../summary/'; my $base = ''; my $out = ''; my %toc; $out .= "SWAD-Europe: Description of Work\n\n"; $out .= "\n"; $out .= "\n\n \n\n\n\n\n"; my @parts; my @sources; my %bysource; my $chart; open (IN, $cfg) || die "no config $cfg"; while() { next if (m/^#/); next unless (m/\S/); chomp; # print STDERR "Debug: $_ \n"; $chart=''; my $fileinfo=$_; $fileinfo =~ m/^(\S+)\s*(.*)/; my $fn=$1; my $meta=$2; # print STDERR "CONCAT: Parts: $fn meta: $meta\n"; $meta =~ m/T=(.+)N=*/i; my $title=$1 || 'no_title'; $meta =~ m/N=(\S+)\s*/i; my $n=$1 || '0'; print STDERR "concat.pl: Parts: $fn meta: $meta Title=$title Num=$n\n"; push (@sources,$fn); my $file = $base . $fn; $toc{$n} = $fn. ' '. $title; if (-e $file) { # print STDERR "Exists! loading and processing $file\n" if $debug; my $wp = $1 if ($file =~ m#esw-wp-(\d.*)\.html#i); my $LINKIMG=0; # don't do this any more (pics too big) # special case stuff if we identify a workpackage if ($LINKIMG) { print STDERR "File $file is a workpackage: $wp \n"; #crossref to files such as:views/img/chart_esw-wp-3.svg or .png my $imgbase = "views/img/_chart_esw-wp-$wp"; my $png = $imgbase . '.png'; my $svg = $imgbase . '.svg'; print STDERR "Checking $png\n" if $debug; $chart .= "\n\n"; # not really a chart if (-e $png ) { # *if* we have an image... (single partner WPs don't...), see extract_projdata.pl for details # $chart = "\n\n
\n\n\"pie\n\n"; $chart .= "\n(svg) \n\n\n"; # print STDERR "Matched WP $wp to image $imgbase (png/svg) \n" if $debug; } } my $ch; open (CHAPTER, $file) || die "Can't open chapter $file"; while () { next if (m/xml version=/); next if (m/DOCTYPE/); next if (m/Transitional\/\//); s//
/gi; $ch .= $_; } close CHAPTER; # Some clumsy hacks that try to junk HTML head and other per-doc stuff # $ch =~ s#]+)>(.*)]+)># \n\n\n\n#igs; $ch =~ s#<\?xml version="1.0"\?>##gis; $ch =~ s#([^<]*)##gsi; # $ch =~ s#]*)>##gsi; # $ch =~ s#]*)>##gsi; # $ch =~ s#]*)>##gsi; $ch =~ s#"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">##gi; $ch =~ s###ig; $ch =~ s###ig; $ch =~ s###ig; $ch =~ s#<\!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"##gs; #"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> $ch =~ s#"http://www\.w3\.org/TR/xhtml1/DTD/xhtml1\-transitional\.dtd">##gi; $ch =~ s#"http([^"]+)"(>)*##gis; ## Add any extra stuff $ch =~ s#^\s*>##sg; $ch = $chart . $ch; push(@parts, $ch); # print STDERR "Storing chunk under $fn\n" if $debug; $bysource{$fn}= $ch; } else { die "concat.pl: required file not found: $file -- update config $cfg or create file.\n"; } } print $out; foreach my $chunk (@sources) { print "\n\n\n\n"; print "[SOURCE: $chunk] \n" if $debug; # output 'where it came from' for debugging print $bysource{$chunk} ."\n\n\n"; } ### GENERATE Table Of Contents open (TOC,">_autotoc.html")|| die "Can't write ToC $!"; print TOC "SWAD-Europe: Table of Contents\n\n"; print TOC "

Contents

\n\n
    "; my $t; foreach my $i (sort {$a <=> $b} keys %toc) { my $info = $toc{$i}; $info =~ s/(\S+)\s+//; my $file = $1; my $label = $info; # print STDERR "TocGEN: $i -> $toc{$i}\n"; if ($i =~ m/9\.30?(.*)/) { $label .= "(todo: add WP $1 name)\n"; } print TOC "
  • $i. $label
    • \n"; # base rel uri ok? } print TOC "\n
\n\n\n\n"; close TOC; # see also... # http://www.w3.org/DOM/Group/drafts/scripts/ # cool, thanks. # htmlcat # htmltrim # $(HTMLCAT) - $(FILES) | $(HTMLTRIM) div navbar - $@