sisu harvest, introduce module along with header syntax addition & modification

* sisu markup, additional header and new format rule:
  * @creator: / @author: header field, introduced author name format rules
    for more usable metadata harvesting: surname comma other names, additional
    authors separated by semi-colon
  * param added meta-tag, @topic_register: formatting topic levels are
    separated from sub-levels by a colon, a semi-colon separates main topics
    if there are multiple topics at lowest sub-level, a pipe can be used to
    create multiple headings

* harvest module, harvests metadata from document set currently extracts: (i)
  authors and their writings from document set; (ii) topics and associated
  writings from document set (topics use topic_register header). harvest
  (when run against documents common to a directory of a site) extracts
  metadata and organises the documents on a site by author and topic
  information provided (there is a new "topic_register" header, with
  formatting rules similar to those of the book index), results are placed in
  [output_path]/sisu_site_metadata.
    sisu --harvest *.sst
  * by author (see change in param @creator: / @author: header field)
  * by topic / subject index (see addition in param of @topic_register:
    header field)
  initially there should be an example samples here:
    http://www.jus.uio.no/sisu/sisu_site_metadata/harvest_authors.html
    http://www.jus.uio.no/sisu/sisu_site_metadata/harvest_topics.html
  together with update markup source files

  The authors and their writings list will be made to take on a more
  biblographical form, with the use of additional fields as required.
  (concept example, suitable for medium sized sites [to remove size
  constraint: implement SQL equivalent]) make feature more robust

* css, for harvest output added

* remote placement of sisu_site_metadata (output produced by metadata harvest)

* sisu markup, update document samples accordingly

* tidy copyright marks in program headers, remove repetition of dates

[version bump because formatting rule introduced to author / creator header -
where new site metadata harvest feature is used, (at present changes changes
should not be noticed except when using metadata harvest)]

1 files changed, 18 insertions, 20 deletions

diff --git a/lib/sisu/v0/dal_idx.rb b/lib/sisu/v0/dal_idx.rb
index 0b5c74c7..8633579f 100644
--- a/lib/sisu/v0/dal_idx.rb
+++ b/lib/sisu/v0/dal_idx.rb
@@ -4,7 +4,6 @@
  * Name: SiSU
 
  * Description: a framework for document structuring, publishing and search
-   #___#
 
  * Author: Ralph Amissah
 
@@ -15,8 +14,7 @@
 
    SiSU, a framework for document structuring, publishing and search
 
-   Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
-   2007 Ralph Amissah
+   Copyright (C) Ralph Amissah
 
    This program is free software: you can redistribute it and/or modify it
    under the terms of the GNU General Public License as published by the Free
@@ -137,22 +135,22 @@ module SiSU_book_index
           i.strip!
           i,r=/(.+?)\+(\d+)/.match(i)[1,2] if i =~/.+?\+\d+/
           x=if idx_lst.length == 1 or idx_lst[0].gsub(/\+\d+/,'') == i
-            @the_idx[use]['a1']=[] unless @the_idx[use]['a1'] and defined? @the_idx[use]['a1']
+            @the_idx[use]['term_node_lev1']=[] unless @the_idx[use]['term_node_lev1'] and defined? @the_idx[use]['term_node_lev1']
             x=if r
-              @the_idx[use]['a1'] << { :ocn => idx[:ocn], :range => "#{idx[:ocn]}-#{idx[:ocn].to_i+r.to_i}", :seg => idx[:seg] }
+              @the_idx[use]['term_node_lev1'] << { :ocn => idx[:ocn], :range => "#{idx[:ocn]}-#{idx[:ocn].to_i+r.to_i}", :seg => idx[:seg] }
               "#{i} #{idx[:ocn]}-#{idx[:ocn].to_i+r.to_i}"
             else
-              @the_idx[use]['a1'] << { :ocn => idx[:ocn], :seg => idx[:seg] }
+              @the_idx[use]['term_node_lev1'] << { :ocn => idx[:ocn], :seg => idx[:seg] }
               "#{i} #{idx[:ocn]}"
             end
           else
-            @the_idx[use]['b1']={} unless @the_idx[use]['b1'] and defined? @the_idx[use]['b1']
-            @the_idx[use]['b1'][i]=[] unless @the_idx[use]['b1'][i] and defined? @the_idx[use]['b1'][i]
+            @the_idx[use]['term_node_lev2']={} unless @the_idx[use]['term_node_lev2'] and defined? @the_idx[use]['term_node_lev2']
+            @the_idx[use]['term_node_lev2'][i]=[] unless @the_idx[use]['term_node_lev2'][i] and defined? @the_idx[use]['term_node_lev2'][i]
             x=if r
-              @the_idx[use]['b1'][i] << { :ocn => idx[:ocn], :range => "#{idx[:ocn]}-#{idx[:ocn].to_i+r.to_i}", :seg => idx[:seg] }
+              @the_idx[use]['term_node_lev2'][i] << { :ocn => idx[:ocn], :range => "#{idx[:ocn]}-#{idx[:ocn].to_i+r.to_i}", :seg => idx[:seg] }
               "#{idx_lst[0]}:#{i} #{idx[:ocn]}-#{idx[:ocn].to_i+r.to_i}"
             else
-              @the_idx[use]['b1'][i] << { :ocn => idx[:ocn], :seg => idx[:seg] }
+              @the_idx[use]['term_node_lev2'][i] << { :ocn => idx[:ocn], :seg => idx[:seg] }
               "#{idx_lst[0]}:#{i} #{idx[:ocn]}"
             end
           end
@@ -203,8 +201,8 @@ module SiSU_book_index
             p 'array error? -->'
             print x
           elsif x.class == Hash
-            if x['a1'].class == Array
-              x['a1'].each do |a|
+            if x['term_node_lev1'].class == Array
+              x['term_node_lev1'].each do |a|
                 if a[:range]
                   @idx[:sst][@o]=@idx[:sst][@o] + %{#{Mx[:lnk_o]}#{a[:range]}#{Mx[:lnk_c]}#{@env.url.root}/#{@md.fnb}/#{a[:seg]}.html##{a[:ocn]}, }
                   @idx[:html][@q]=@idx[:html][@q] + %{<a href="#{a[:seg]}.html##{a[:ocn]}">#{a[:range]}</a>, }
@@ -218,11 +216,11 @@ module SiSU_book_index
               end
               @idx[:html][@q]=@idx[:html][@q] + '</p>'
             end
-            if x['b1']
-              m=x['b1']
+            if x['term_node_lev2']
+              m=x['term_node_lev2']
               m=m.sort
               m.each do |k,y|
-                if k !~/a1/
+                if k !~/term_node_lev1/
                   @idx[:sst][@o]=@idx[:sst][@o] + %{#{k}, }
                   @idx[:html][@q]=@idx[:html][@q] + %{\n<p class="book_index_lev2">#{k}, }
                   print "\n\t" + k + ', ' if @md.cmd =~/V/
@@ -259,8 +257,8 @@ module SiSU_book_index
             p 'array error? -->'
             print x
           elsif x.class == Hash
-            if x['a1'].class == Array
-              x['a1'].each do |a|
+            if x['term_node_lev1'].class == Array
+              x['term_node_lev1'].each do |a|
                 if a[:range]
                   print a[:range] + ', '
                 elsif a[:ocn]
@@ -269,11 +267,11 @@ module SiSU_book_index
                 end
               end
             end
-            if x['b1']
-              m=x['b1']
+            if x['term_node_lev2']
+              m=x['term_node_lev2']
               m=m.sort
               m.each do |k,y|
-                if k !~/a1/
+                if k !~/term_node_lev1/
                   print "\n\t" + k + ', '
                   #p y
                   y.each do |z|