# encoding: utf-8 =begin * Name: SiSU * Description: a framework for document structuring, publishing and search * Author: Ralph Amissah * Copyright: (C) 1997 - 2011, Ralph Amissah, All Rights Reserved. * License: GPL 3 or later: SiSU, a framework for document structuring, publishing and search 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 Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program. If not, see . If you have Internet connection, the latest version of the GPL should be available at these locations: * SiSU uses: * Standard SiSU markup syntax, * Standard SiSU meta-markup syntax, and the * Standard SiSU object citation numbering and system * Hompages: * Download: * Ralph Amissah ** Description: system environment, resource control and configuration details =end module SiSU_hash require_relative 'shared_markup_alt.rb' #shared_markup_alt.rb class Object_digest def initialize(md,data,env=nil) @md,@data,@env=md,data,env @env ||=SiSU_Env::Info_env.new(@md.fns) end def object_digest # 1. clean/stripped text without any markup, paragraph, headings etc. without endnotes # 2. endnotes clean/stripped text digest only (there may be several endnotes within a paragraph) # 3. whole object, text with markup and any endnotes, (question: with or without the endnote digests??? presumption better without, [however may be easier to check with?]) # [digests should not include other digests] data=@data @tuned_file=[] data.compact! sha_ =(@env.digest.type=='sha256' ? true : false) sha_ ? (require 'digest/sha2') : (require 'digest/md5') data.each do |t_o| unless t_o.obj.class==Array t_o.obj.strip! end if t_o.of !~/structure|comment|layout/ \ and t_o.ocn.class==Fixnum if sha_ for hash_class in [ Digest::SHA256 ] @tuned_file << stamped(t_o,hash_class) end else for hash_class in [ Digest::MD5 ] @tuned_file << stamped(t_o,hash_class) end end else @tuned_file << t_o unless t_o.nil? end end @tuned_file=@tuned_file.flatten #use md5 or to create hash of each dal object including ocn, & add into to each dal object end def endnote_digest(data) t_o_bit=[] data.each do |en_plus| t_o_bit <<= case en_plus when /#{Mx[:en_a_o]}|#{Mx[:en_b_o]}/ if en_plus =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]}/ t_o_txt,en_open,en_txt,en_close=/(.*?)(#{Mx[:en_a_o]}|#{Mx[:en_b_o]})(.+?)(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m.match(en_plus)[1..4] stripped_en=SiSU_text_representation::Alter.new(en_txt).strip_clean_of_markup digest_en_strip=if @env.digest.type =~/sha256/ Digest::SHA256.hexdigest(stripped_en) else Digest::MD5.hexdigest(stripped_en) end t_o_txt + en_open + en_txt + Mx[:id_o] + digest_en_strip + Mx[:id_c] + en_close else puts "Error Exception - problem encountered with:\n#{en_plus}" #arbitrary exception, tidy up end else en_plus end end t_o_bit.join end def stamped(t_o,hash_class) #decide what hash information is most useful, is compromise necessary? t_o.obj=SiSU_text_representation::Alter.new(t_o).strip_clean_of_extra_spaces t_obj=t_o.inspect.sub(/:0x[0-9a-f]{8}\s/,': ') stripped=SiSU_text_representation::Alter.new(t_o).strip_clean_of_markup markup=SiSU_text_representation::Alter.new(t_o).semi_revert_markup digests=SiSU_text_representation::Modified_text_plus_Hash_digest.new(@md,t_o).composite.dgst unless t_o.is=='code' case t_o.obj when /#{Mx[:en_a_o]}[\d*+]+\s+.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}[*+]\d+\s+.+?#{Mx[:en_b_c]}/m en_and_t_o,en_and_t_o_digest=[],[] t_o.obj.gsub!(/\s*(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m,' \1') #watch t_o_plus_en=t_o.obj.scan(/.*?#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|.*?#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]}/m) t_o_tail=if t_o.obj =~/(?:.*?#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|.*?#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]})+([\s\S]+)/m /(?:.*?#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|.*?#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]})+.*/m.match(t_o.obj)[1] else '' end t_o_plus_en << t_o_tail en_and_t_o_digest << endnote_digest(t_o_plus_en) t_o_new=en_and_t_o_digest.join(' ') #@tuned << t_o_new + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless t_o.nil? else #@tuned << t_o + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless t_o.nil? end else #@tuned << t_o + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless t_o.nil? end t_o #KEEP intact end def strip_clean_extra_spaces(s) # dal output tuned s=s.dup s=s.gsub(/[ ]+([,.;:?](?:$|\s))/,'\1') unless s =~/#{Mx[:en_a_o]}|#{Mx[:en_b_o]}/ s=s.gsub(/ [ ]+/,' ') s=s.gsub(/^ [ ]+/,'') s=s.gsub(/ [ ]+$/,'') s=s.gsub(/((?:#{Mx[:fa_bold_c]}|#{Mx[:fa_italics_c]})')[ ]+(s )/,'\1\2') s=s.gsub(/((?:#{Mx[:fa_bold_c]}|#{Mx[:fa_italics_c]})')[ ]+(s )/,'\1\2') end end end __END__