From d29a3e5469d8468084641c385ebf16948f7c2437 Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Tue, 22 Jul 2008 20:00:59 -0400 Subject: sisu-0.68.0 proposed * middle layer document representation changed, (accounting for substantial patch) * texpdf multiple document sizes as specified in config * numerous small fixes [should on the whole be easier to maintain] --- lib/sisu/v0/dal.rb | 451 +++++++++++++++++++++++++++-------------------------- 1 file changed, 226 insertions(+), 225 deletions(-) (limited to 'lib/sisu/v0/dal.rb') diff --git a/lib/sisu/v0/dal.rb b/lib/sisu/v0/dal.rb index 3e5e11ac..cb6d70f8 100644 --- a/lib/sisu/v0/dal.rb +++ b/lib/sisu/v0/dal.rb @@ -70,7 +70,7 @@ module SiSU_DAL include SiSU_Env include SiSU_Param include SiSU_Viz - include Syntax + include SiSU_Syntax class Instantiate < SiSU_Param::Parameters::Instructions def initialize @@flag_vocab=0 @@ -199,6 +199,7 @@ module SiSU_DAL data=data.join.split("\n\n") data=expand_insertions?(data) data=SiSU_document_structure::Code.new(@md,data).code + data=substitutions_and_insertions?(data) data_new=[] data.each do |x| data_new << if x =~ /\n\n/m; x.split(/\n\n+/) @@ -206,8 +207,7 @@ module SiSU_DAL end end data=data_new.flatten - data=substitutions_and_insertions?(data) - data=Syntax::Markup.new(@md,data).songsheet + data=SiSU_Syntax::Markup.new(@md,data).songsheet data=character_check(data) data=images(data) data=SiSU_document_structure::Tables.new(@md,data).tables @@ -234,12 +234,12 @@ module SiSU_DAL para.gsub!(/^([12])~\?\s+/,'\1~ ') #conditional header for incorporated document 2004w12 para.gsub!(/^[{~}]\s*$/,'') para.gsub!(/^#{@@comment}.*/,'') #remove comment and divider #% - para.gsub!(/<~#>|~#\s*/,'<~#>') - para.gsub!(/-#\s*/,'<-#><~#>') + para.gsub!(/<~#>|~#\s*/,"#{Mx[:fa_o]}~##{Mx[:fa_c]}") + para.gsub!(/-#\s*/,"#{Mx[:fa_o]}-##{Mx[:fa_c]}#{Mx[:fa_o]}~##{Mx[:fa_c]}") #para.gsub!(/(#\{{3} arch-tag:|0\{{3}~cvs)\s+/, "0{{~rcs ") #KEEP ... ENABLE WIDER USE OF REVISION CONTROL - para.gsub!(/(~\{ )\s+/,'\1') - para.gsub!(/ \/\//,'
') #added 2004w29 - para.gsub!(/
/,'
') #needed by xml, xhtml etc. + para.gsub!(/(#{Mx[:en_a_o]} )\s+/,'\1'); para.gsub!(/(~\{ )\s+/,'\1') + para.gsub!(/ \/\//,"#{Mx[:br_line]}") #added 2004w29 + para.gsub!(/
/,"#{Mx[:br_line]}") #needed by xml, xhtml etc. #para.gsub!(/

/,'

') #consider para.gsub!(/`/,"'") para.gsub!(/\t/,' ') @@ -252,12 +252,12 @@ module SiSU_DAL para.gsub!(/\\trademark\b|\\tm\b/,'®') #non_utf8(para) para=para + "\n" - unless para =~/^<:code>/ + unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/ case para when /\^~/ # endnotes #% Note must do this first (earlier loop) and then enter gathered data into ~^\d+ sub_para=para.dup - @@endnote_array << sub_para.gsub!(/\n/,'').gsub!(/\^~\s+(.+)\s*/, %{~\{#{endnote_no} \\1 \}~}).strip + @@endnote_array << sub_para.gsub!(/\n/,'').gsub!(/\^~\s+(.+)\s*/, %{#{Mx[:en_a_o]}#{endnote_no} \\1 #{Mx[:en_a_c]}}).strip endnote_no+=1 para=nil if para =~/\^~ .+/ #removes 'binary' endnote now in endnote array for later insertion end @@ -383,7 +383,7 @@ module SiSU_DAL manifest="#{pre}{#{txt} }#{@u.remote}/#{url_dir}/toc.html#{note}\n\n" else puts "error, does currently support relative paths (reltive paths were removed, as had problems for citation, and was not suited to all output types should possibly reconsider) #{__FILE__} #{__LINE__}" - if para =~/\{(?:~\^\s+)?(.+?)\s\[(\d[sS]*)\]\}\.\.\/(\S+?)\/(\s+~\{.+?\}~)?/ + if para =~/\{(?:~\^\s+)?(.+?)\s\[(\d[sS]*)\]\}\.\.\/(\S+?)\/(\s+#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]})?/ txt,cmd,url_dir,note=$1,$2,$3,$4 manifest="{ #{txt} }../#{url_dir}/toc.html#{note}\n\n" end @@ -452,7 +452,7 @@ module SiSU_DAL tuned_file end def substitutions_and_insertions?(data) - tuned_file=[] + data_expand=[] if data[0] =~ /^#!\s*(?:\/usr\/bin\/env sisu|\/usr\/bin\/sisu)/ # remove bang from top #! (however file is stripped, so will be removed provided no content preceeds it) data[0].gsub!(/^#!\s*\/usr\/bin\/sisu/,'') data[0].gsub!(/^#!\s*\/usr\/bin\/env sisu/,'') @@ -462,16 +462,6 @@ module SiSU_DAL data[0].gsub!(/^(sisu-[\d.]+)$/,'% \1') end data.each do |para| - para=if @md.markup_version.to_f >= 0.38 - SiSU_document_structure::Structure.new(@md,para).structure_markup_normalize - else para - end - #para.gsub!(//,'\1') #consider, would permit use of text hyperlinks if desired, dal_syntax more appropriate? - para.gsub!(/^((?:[1-9]|:?[A-C])~\S*)\s*$/,'\1~ [Note: heading marker::required title missing]~#') #conditional header for incorporated document 2004w12 - if para =~/^@\S+?:/ - para.gsub!(/^@(\S+?):\s+/,'0~\1 ') - para.gsub!(/^@(\S+?):([+-])\s+/,'0~\1\2 ') - end if para =~/<:insert\d+!?>/ \ and para !~/^%\s+/ @skin.select @@ -501,13 +491,25 @@ module SiSU_DAL para=[] ins.insert7.split(/\n\n/).each{|x| para << x << "\n"} end - para.each{|x| tuned_file << x } - else tuned_file << para + para.each{|x| data_expand << x } + else data_expand << para + end + data_expand.flatten! + data_expand.compact! + end + data_expand.each do |para| + para=if @md.markup_version.to_f >= 0.38 + SiSU_document_structure::Structure.new(@md,para).structure_markup_normalize + else + SiSU_document_structure::Structure.new(@md,para).structure_marks + end + #para.gsub!(//,'\1') #consider, would permit use of text hyperlinks if desired, dal_syntax more appropriate? + para.gsub!(/^((?:[1-9]|:?[A-C])~\S*)\s*$/,'\1~ [Note: heading marker::required title missing]~#') #conditional header for incorporated document 2004w12 + if para =~/^@\S+?:/ + para.gsub!(/^@(\S+?):\s+/,"#{Mx[:meta_o]}\\1#{Mx[:meta_c]}") + para.gsub!(/^@(\S+?):([+-])\s+/,"#{Mx[:meta_o]}\\1\\2#{Mx[:meta_c]}") end - tuned_file.flatten! - tuned_file.compact! end - tuned_file end def numbering_song(data) data=number_plaintext_para(data) @@ -524,8 +526,10 @@ module SiSU_DAL def number_plaintext_para(data) @tuned_file=[] data.each do |para| - para.gsub!(/(^|[^<][^v][^>])\n/,'\1 ') #messy, but idea is that tables should retain breaks - para.gsub!(/^/,"\n") unless para =~/¡/u + if para !~/#{Mx[:gr_o]}(?:code|group|alt|poem|verse)#{Mx[:gr_c]}|#{Mx[:gr_o]}Th|#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}/ + para.gsub!(/(.+)\n/,'\1 ') #messy, but idea is that tables should retain breaks + end + para.gsub!(/^/,"\n") unless para =~/#{Mx[:tc_p]}/u para.gsub!(/^\s+|\s$/,"\n") @tuned_file << para end @@ -557,27 +561,27 @@ module SiSU_DAL # debug 2003w46 adding revision control info if @md.flag_auto_endnotes \ and @md.flag_separate_endnotes_make - @tuned_file << "\n4~endnotes Endnotes <-#> <~0;0:0;u0>" + @tuned_file << "\n#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}Endnotes #{Mx[:gl_o]}-##{Mx[:gl_c]} #{Mx[:id_o]}~0;0:0;u0#{Mx[:id_c]}" end - @tuned_file << "\n" + @tuned_file << "\n#{Mx[:br_endnotes]}" #DECIDE ON @tuned_file=@tuned_file.flatten end def owner_details_seg - data << '4~owner.details Owner Details' + data << "#{Mx[:lv_o]}4:owner.details#{Mx[:lv_c]}Owner Details" end def number_sub_heading(para,num,title_no) case para - when /#{num}~- /; para.gsub!(/#{num}~- /,"#{title_no} ") - when /^#{num}~#\s*/; para.gsub!(/^#{num}~#\s*/,"#{title_no} ") - when /^#{num}~[a-z_\.]+ / - para.gsub!(/^#{num}~([a-z_\.]+)\s+(.+)/i,%{#{num}~\\1 #{title_no} \\2 <:name##{title_no}>}) - when /^#{num}~\s+#{title_no}/ - para.gsub!(/^#{num}~ /,"#{num}~#{title_no} ") #where title contains title number - else para.gsub!(/^#{num}~ /,"#{num}~#{title_no} #{title_no} ") #main, where title number is to be provided + when /#{Mx[:lv_o]}#{num}:-#{Mx[:lv_c]}/; para.gsub!(/#{Mx[:lv_o]}#{num}:-#{Mx[:lv_c]}/,"#{title_no} ") + when /^#{Mx[:lv_o]}#{num}:##{Mx[:lv_c]}/; para.gsub!(/^#{Mx[:lv_o]}#{num}:##{Mx[:lv_c]}/,"#{title_no} ") + when /^#{Mx[:lv_o]}#{num}:[a-z_\.]+#{Mx[:lv_c]}/ + para.gsub!(/^#{Mx[:lv_o]}#{num}:([a-z_\.]+)#{Mx[:lv_c]}\s*(.+)/i,%{#{Mx[:lv_o]}#{num}:\\1#{Mx[:lv_c]} #{title_no} \\2 #{Mx[:fa_o]}:name##{title_no}#{Mx[:fa_c]}}) + when /^#{Mx[:lv_o]}#{num}:#{Mx[:lv_c]}\s*#{title_no}/ + para.gsub!(/^#{Mx[:lv_o]}#{num}:#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{num}:#{title_no}#{Mx[:lv_c]}") #where title contains title number + else para.gsub!(/^#{Mx[:lv_o]}#{num}:#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{num}:#{title_no}#{Mx[:lv_c]} #{title_no} ") #main, where title number is to be provided end if @md.toc_lev_limit \ and @md.toc_lev_limit < num - para.gsub!(/^[5-8]~(?:~\S+)?\s*/,'!_ ') + para.gsub!(/^#{Mx[:lv_o]}[5-9]:\S*?#{Mx[:lv_c]}/,'!_ ') #bold line, watch end para end @@ -596,61 +600,61 @@ module SiSU_DAL if (@md.markup =~/num_top/ \ or (@md.num_top \ and @md.num_top !~/^$/)) \ - and para !~/^0~/ + and para !~/^#{Rx[:meta]}/ if (para =~/^(?:#{no1}|^#{no2}|^#{no3}#{no4})~#/ \ - and para !~/^4~endnotes?/) + and para !~/^#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}/) t_not+=1 #; t_no2=0; t_no3=0 - para.gsub!(/^(#{no1})~#\s*/,"\\1~ps#{t_not} ") - para.gsub!(/^(#{no2})~#\s*/,"\\1~ps#{t_not} ") - para.gsub!(/^(#{no3})~#\s*/,"\\1~ps#{t_not} ") - para.gsub!(/^(#{no4})~#\s*/,"\\1~ps#{t_not} ") + para.gsub!(/^(#{Mx[:lv_o]}#{no1}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2") + para.gsub!(/^(#{Mx[:lv_o]}#{no2}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2") + para.gsub!(/^(#{Mx[:lv_o]}#{no3}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2") + para.gsub!(/^(#{Mx[:lv_o]}#{no4}):#(#{Mx[:lv_c]})/,"\\1:ps#{t_not}\\2") end - if para =~/#{no1}~/ + if para =~/#{Mx[:lv_o]}#{no1}:/ @subnumber=1 - @subnumber=0 if para =~/#{no1}~/ + @subnumber=0 if para =~/#{Mx[:lv_o]}#{no1}:/ end - if para =~/^[0-6]~[ \w-]/ \ - and para !~ /(?:[0-6]~[\w-]+-|4~endnotes|^[0-6]~([a-z_\.]+)\s+[\d.]+)\s/ \ - and para !~/<~#>|<-#>/ - if para =~/^#{no1}~/ + if para =~/^#{Mx[:lv_o]}[1-6]:[\w-]*#{Mx[:lv_c]}/ \ + and para !~ /(?:#{Mx[:lv_o]}[1-6]:[\w-]+-#{Mx[:lv_c]}|#{Mx[:lv_o]}4:endnotes#{Mx[:lv_c]}|^#{Mx[:lv_o]}[1-6]:[a-z_\.]+#{Mx[:lv_c]}\s+[\d.]+)\s/ \ + and para !~/#{Mx[:fa_o]}(?:~#|-#)#{Mx[:fa_c]}/ + if para =~/^#{Mx[:lv_o]}#{no1}:/ t_no1+=1; t_no2=0; t_no3=0 title_no="#{t_no1}" if not @md.seg_names.nil? \ and not @md.seg_names.include?(title_no) - para.gsub!(/^#{no1}~\s+(\S+)#/,"#{no1}~#{title_no} \\1 #{title_no} ") #shift placement of auto-number to after first word, e.g. Article # not # Article, added on occasion of ABF (20040329) + para.gsub!(/^#{Mx[:lv_o]}#{no1}:#{Mx[:lv_c]}\s*(\S+)#/,"#{Mx[:lv_o]}#{no1}:#{title_no}#{Mx[:lv_c]} \\1 #{title_no} ") #shift placement of auto-number to after first word, e.g. Article # not # Article, added on occasion of ABF (20040329) para.gsub!(/^#{no1}\{\s+(Article|Clause|Section)\s+#/i,%{#{no1}~#{title_no} \\1 #{title_no}. }) - unless para =~/^#{no1}~\s+[\d.]+\s/ #fix -> if the title starts with a numbering scheme, do not auto-number, review - para.gsub!(/^#{no1}~\s+/,"#{no1}~#{title_no} #{title_no}. ") + unless para =~/^#{Mx[:lv_o]}#{no1}:#{Mx[:lv_c]}\s*[\d.]+\s/ #fix -> if the title starts with a numbering scheme, do not auto-number, review + para.gsub!(/^#{Mx[:lv_o]}#{no1}:#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no1}:#{title_no}#{Mx[:lv_c]}#{title_no}. ") end @md.seg_names << title_no #else puts "warning segment name #{title_no} already exists" end - unless para =~/^#{no1}~([a-z_\.]+)\s+[A-Z]\.?\s/ #bug -> tmp fix, excludes A. B. C. lettering, but not roman numerals, is arbitrary, review required - para.gsub!(/^#{no1}~([a-z_\.]+)\s+(.+)/i,%{#{no1}~\\1 #{title_no}. \\2 <:name##{title_no}>}) + unless para =~/^#{Mx[:lv_o]}#{no1}:([a-z_\.]+)#{Mx[:lv_c]}\s*[A-Z]\.?\s/ #bug -> tmp fix, excludes A. B. C. lettering, but not roman numerals, is arbitrary, review required + para.gsub!(/^#{Mx[:lv_o]}#{no1}:([a-z_\.]+)#{Mx[:lv_c]}\s*(.+)/i, + %{#{Mx[:lv_o]}#{no1}:\\1#{Mx[:lv_c]}#{title_no}. \\2 #{Mx[:fa_o]}:name##{title_no}#{Mx[:fa_c]}}) end + para.gsub!(/^#{Mx[:lv_o]}#{no1}:##{Mx[:lv_c]}/,"#{title_no}. ") #watch para.gsub!(/^#{no1}~#\s*/,"#{title_no}. ") end - if para =~/^#{no2}~/ + if para =~/^#{Mx[:lv_o]}#{no2}:\S*?#{Mx[:lv_c]}/ t_no2+=1; t_no3=0 title_no="#{t_no1}.#{t_no2}" para=number_sub_heading(para,no2,title_no) end - if para =~/^#{no3}~/ + if para =~/^#{Mx[:lv_o]}#{no3}:\S*?#{Mx[:lv_c]}/ t_no3+=1 title_no="#{t_no1}.#{t_no2}.#{t_no3}" para=number_sub_heading(para,no3,title_no) end - elsif para =~ /^[0-6]~[\w-]+-/ # endnotes, watch2005 - para.gsub!(/^#{no1}~([a-z_\.]+)- /,"#{no1}~\\1 ") - para.gsub!(/^#{no2}~([a-z_\.]+)- /,"#{no2}~\\1 ") - para.gsub!(/^#{no3}~([a-z_\.]+)- /,"#{no3}~\\1 ") + elsif para =~/^#{Mx[:lv_o]}[1-6]:[\w-]+-#{Mx[:lv_c]}/ # endnotes, watch2005 + para.gsub!(/^#{Mx[:lv_o]}#{no1}:([a-z_\.]+)-#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no1}:\\1#{Mx[:lv_c]}") #"#{no1}~\\1 ") + para.gsub!(/^#{Mx[:lv_o]}#{no2}:([a-z_\.]+)-#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no2}:\\1#{Mx[:lv_c]}") + para.gsub!(/^#{Mx[:lv_o]}#{no3}:([a-z_\.]+)-#{Mx[:lv_c]}/,"#{Mx[:lv_o]}#{no3}:\\1#{Mx[:lv_c]}") end elsif @md.markup =~/num_extract/ #AS DANGEROUS force enable with document, note already does this type of numbering for cisg, locate and coordinate logic, is currently misplaced in code, chengwei inspired 2004w23/4 - unless para =~ /^[0-6]~\S+/ #endnotes watch? - if para =~/^[1-6]~\s+([\d\.]+)/ #risky (must be unique) consider output to 4~~\d instead of 4~\d - name_num=$1 - para.gsub!(/^([1-6]~)\s+/,"\\1#{name_num} ") - end + if para =~/^#{Mx[:lv_o]}[1-9]:#{Mx[:lv_c]}([\d\.]+)/ #risky (must be unique) consider output to 4~~\d instead of 4~\d + name_num=$1 + para.gsub!(/^#{Mx[:lv_o]}([1-9]:)#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1#{name_num}#{Mx[:lv_c]}") end if @md.toc_lev_limit end @@ -663,7 +667,7 @@ module SiSU_DAL @tuned_file=[] object_array=SiSU_document_structure::OCN.new(@md,data).ocn object_array.each do |o| - @tuned_file <<= if o.ocn; "#{o.txt} <~#{o.ocn};#{o.lv};#{o.type}>" #main ocn descriptor + @tuned_file <<= if o.ocn; "#{o.txt} #{Mx[:id_o]}~#{o.ocn};#{o.lv};#{o.type}#{Mx[:id_c]}" #main ocn descriptor else o.txt end end @@ -675,8 +679,8 @@ module SiSU_DAL letter=%w( a b c d e f g h i j k l m n o p q r s t u v w x y z ) data.each do |para| if para =~/\w|\S|<|\(/ - if para !~/^%% |^0~|^4~endnotes|^<\/center>|<:ee>|<:e[:_]>|^\^~ |<:e[:_]\d+?>|^<:p[bn]>|^<:\#|<:- |<[:!]!4|^(?:alt|code|group|poem|table)\{|^\}(?:alt|code|group|poem|table)|^\}table$|||||<\/tr>|

|\[endnotes\]|<:zz>|<:isbn-|<:journal-|<:conference-|/i #ocn here #  added with Tune.code #¡ - if para=~/^[1-8]~/; number_small,letter_small=0,0 #% sub-number system, (baby numbering) reset with any change of major number (more obviously should be placed in number titles, but that is conditionally executed, check and move later) + if para !~/^%% |#{Rx[:meta]}|^0~|^#{Mx[:lv_o]}endnotes:|^4~endnotes|^<\/center>|<:ee>|<:e[:_]>|^\^~ |<:e[:_]\d+?>|^#{Mx[:fa_o]}:p[bn]#{Mx[:fa_c]}|^<:\#|<:- |<[:!]!4|#{Mx[:gr_o]}(?:alt|code|group|poem|table)#{Mx[:gr_c]}|^(?:alt|code|group|poem|table)\{|^\}(?:alt|code|group|poem|table)|^\}table$|||||<\/tr>|
|\[endnotes\]|<:zz>|<:isbn-|<:journal-|<:conference-|#{Mx[:br_endnotes]}/i #ocn here #  added with Tune.code #¡ + if para=~/^#{Mx[:lv_o]}[1-9]:\S*?#{Mx[:lv_c]}/; number_small,letter_small=0,0 #% sub-number system, (baby numbering) reset with any change of major number (more obviously should be placed in number titles, but that is conditionally executed, check and move later) end if para =~/^#[ 1]/ letter_small=0 @@ -685,7 +689,7 @@ module SiSU_DAL para.gsub!(/^#[ 1]/,"#{number_small}. ") #change 2004 end if para =~/^_# / - para.gsub!(/^_# /,"<:i1> #{letter[letter_small]}. ") #change 2004 + para.gsub!(/^_# /,"#{Mx[:fa_o]}:i1#{Mx[:fa_c]} #{letter[letter_small]}. ") #change 2004 letter_small+=1 end end @@ -717,53 +721,51 @@ module SiSU_DAL end data.each do |para| para=SiSU_document_structure::Structure.new(@md,para).structure_markup - if para =~/^[456]~ / - if para=~/^4/ \ + if para =~/^#{Mx[:lv_o]}[456]:#{Mx[:lv_c]}/ + if para=~/^#{Mx[:lv_o]}[4]:#{Mx[:lv_c]}/ \ and not @md.set_heading_seg @md.set_heading_seg=true end - if para =~/^[456]~(?:\s\S+)?\s+([\d.,:-]+)/m #heading starts with a recognised numeric or word followed by a recognised numerical construct, use that as name + if para =~/^#{Mx[:lv_o]}[456]:#{Mx[:lv_c]}(?:\s*\S+)?\s+([\d.,:-]+)/m #heading starts with a recognised numeric or word followed by a recognised numerical construct, use that as name pattern=$1 pattern.gsub!(/(?:[:,-]|\W)/,'.') pattern.gsub!(/\.$/,'') if not @md.seg_names.nil? \ and not @md.seg_names.include?(pattern) - para.gsub!(/^([456])~\s*/,"\\1~#{pattern} ") + para.gsub!(/^#{Mx[:lv_o]}([456]):#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1:#{pattern}#{Mx[:lv_c]}") @md.seg_names << pattern else puts 'warn, there may be a conflicting numbering scheme' if @md.cmd =~/[VM]/ end end - if para =~/^4~\s.+?;4:(\d+);/m #extract segment name from embedded document structure info + if para =~/^#{Mx[:lv_o]}4:#{Mx[:lv_c]}.+?;4:(\d+);/m #extract segment name from embedded document structure info pattern=$1 pattern.gsub!(/(?:[:,-]|\W)/,'.') pattern.gsub!(/\.$/,'') if not @md.seg_names.nil? \ and not @md.seg_names.include?(pattern) - para.gsub!(/^(4)~\s*/,"\\1~#{pattern} ") + para.gsub!(/^#{Mx[:lv_o]}(4:)#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1#{pattern}#{Mx[:lv_c]}") @md.seg_names << pattern else - para.gsub!(/^(4)~\s*/,"\\1~~#{pattern} ") + para.gsub!(/^#{Mx[:lv_o]}(4:)#{Mx[:lv_c]}/,"#{Mx[:lv_o]}\\1~#{pattern}#{Mx[:lv_c]}") @md.seg_names << "~#{pattern}" end end - if para =~/^4~\s+/ #if still not segment name, provide a numerical one + if para =~/^#{Mx[:lv_o]}4:#{Mx[:lv_c]}/ #if still not segment name, provide a numerical one if not @md.seg_names.nil? \ and not @md.seg_names.include?(art_filename_auto) - para.gsub!(/^4~\s+/,%{4~_#{art_filename_auto} }) + para.gsub!(/^#{Mx[:lv_o]}(4:)#{Mx[:lv_c]}/,%{#{Mx[:lv_o]}\\1~#{art_filename_auto}#{Mx[:lv_c]}}) @md.seg_names << art_filename_auto else puts 'segment name (numbering) error' end art_filename_auto+=1 end end - @tuned_file << if para =~/^([1-6])~/m \ - and (@md.pagenew \ - or @md.pagebreak) + @tuned_file << if para =~/^#{Mx[:lv_o]}([1-6]):\S*?#{Mx[:lv_c]}/m \ + and (@md.pagenew or @md.pagebreak) m=$1 #watch ref~ para_tmp=[] - if @md.pagenew.inspect =~/#{m}/; para_tmp << "<:pn>\n" << para - end - if @md.pagebreak.inspect =~/#{m}/; para_tmp << "<:pb>\n" << para + if @md.pagenew.inspect =~/#{m}/; para_tmp << "#{Mx[:br_page_new]}\n" << para + elsif @md.pagebreak.inspect =~/#{m}/; para_tmp << "#{Mx[:br_page]}\n" << para end para_result=unless para_tmp.length > 0; para else para_tmp @@ -782,11 +784,11 @@ module SiSU_DAL @tuned_file=[] data.each do |para| unless @md.set_heading_top - if para !~/^(?:@\S+:|0~\S+)\s/m \ + if para !~/^(?:#{Rx[:meta]}|@\S+:|0~\S+)\s/m \ and para !~/\A\s*\Z/m @md.set_heading_top=true - head=if @md.title ; "1~ #{@md.title}" - else '1~ [no title provided]' + head=if @md.title ; "#{Mx[:lv_o]}1:#{Mx[:lv_c]} #{@md.title}" + else "#{Mx[:lv_o]}1:#{Mx[:lv_c]} [no title provided]" end @tuned_file << head end @@ -802,12 +804,12 @@ module SiSU_DAL @tuned_file=[] data.each do |para| unless @md.set_heading_seg - if para !~/^(?:@\S+:|0~\S+|[123]~)/m \ + if para !~/^(?:#{Rx[:meta]}|#{Mx[:lv_o]}[123]:\S*?#{Mx[:lv_c]})/m \ and para !~/\A\s*\Z/m \ - and para !~/<:p[bn]>/ + and para !~/#{Mx[:br_page]}|#{Mx[:br_page_new]}/ @md.set_heading_seg=true - head=if @md.title ; "4~seg [#{@md.title}]" - else '4~seg [segment]' + head=if @md.title ; "#{Mx[:lv_o]}4:seg#{Mx[:lv_c]} [#{@md.title}]" + else "#{Mx[:lv_o]}4:seg#{Mx[:lv_c]} [segment]" end @tuned_file << head end @@ -825,7 +827,7 @@ module SiSU_DAL unless @md.set_header_title if para !~/^%{1,2}\s/m \ and para !~/\A\s*\Z/m - @tuned_file << "0~title #{@md.heading_seg_first}" + @tuned_file << "#{Mx[:meta_o]}title#{Mx[:meta_c]} #{@md.heading_seg_first}" @md.title=@md.heading_seg_first @md.set_header_title=true end @@ -842,23 +844,23 @@ module SiSU_DAL data.each do |para| # manually numbered endnotes --> if @md.mod.inspect =~/--no-asterisk|--no-annotate/ - para.gsub!(/~\[[*]\s.+?\]~/,'') + para.gsub!(/#{Mx[:en_b_o]}\s.+?#{Mx[:en_b_c]}/,'') end if @md.mod.inspect =~/--no-dagger|--no-annotate/ - para.gsub!(/~\[[+]\s.+?\]~/,'') + para.gsub!(/#{Mx[:en_b_o]}[+]\s.+?#{Mx[:en_b_c]}/,'') end - unless para =~/^<:code>/ + unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/ case para # auto-numbered endnotes --> - when /~\{\s+.+?\}~|~\[[*+]\s+.+?\]~/ - para.gsub!(/\s*(\}~|\]~)/,' \1') # required 2003w31 - word_mode=para.scan(/<:group>\n|\n<:group-end>|\S+/m) + when /#{Mx[:en_a_o]}\s+.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}[*+]\s+.+?#{Mx[:en_b_c]}/ + para.gsub!(/\s*(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/,' \1') # required 2003w31 + word_mode=para.scan(/#{Mx[:gr_o]}group#{Mx[:gr_c]}\n|\n#{Mx[:gr_o]}group-end#{Mx[:gr_c]}|\S+/m) word_mode=endnote_call_number(word_mode) para=word_mode.join(' ') endnote_ref+=1 when /~\^(?:\s|$)|<:e>/ #%Note inserts endnotes previously gathered from /^(|[-~]\{{3})/ (in earlier loop) - word_mode=para.scan(/<:group>\n|\n<:group-end>|\S+/m) + word_mode=para.scan(/#{Mx[:gr_o]}group#{Mx[:gr_c]}\n|\n#{Mx[:gr_o]}group-end#{Mx[:gr_c]}|\S+/m) word_mode=endnote_call_number(word_mode) para=word_mode.join(' ') endnote_ref+=1 @@ -870,19 +872,19 @@ module SiSU_DAL end def endnote_call_number(data) data.each do |word| - unless data =~/^<:code>/ + unless data =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/ case word - when /~\{/ - unless word =~/~\{[*+]+/ - word.gsub!(/~\{/,"~\{#{@@endnote_counter} ") + when /#{Mx[:en_a_o]}/ + unless word =~/#{Mx[:en_a_o]}[*+]+/ + word.gsub!(/#{Mx[:en_a_o]}/,"#{Mx[:en_a_o]}#{@@endnote_counter} ") @@endnote_counter+=1 end - when /~\[/ - if word =~/~\[[+]/ - word.gsub!(/~\[[+]/,"~\[\+#{@@endnote_counter_dag} ") + when /#{Mx[:en_b_o]}/ + if word =~/#{Mx[:en_b_o]}[+]/ + word.gsub!(/#{Mx[:en_b_o]}[+]/,"#{Mx[:en_b_o]}\+#{@@endnote_counter_dag} ") @@endnote_counter_dag+=1 else - word.gsub!(/~\[[*]?/,"~\[\*#{@@endnote_counter_asterisk} ") + word.gsub!(/#{Mx[:en_b_o]}[*]?/,"#{Mx[:en_b_o]}\*#{@@endnote_counter_asterisk} ") @@endnote_counter_asterisk+=1 end when /~\^|<:e>/ @@ -898,106 +900,105 @@ module SiSU_DAL base_html="#{dir.url.root}/#{@md.fnb}" ocnm=ocnd=ocnv=0 ocnm+=1 - header0='<:pn>' - header1="\n1~meta Document Information (metadata) <~0;0:0;m#{ocnm}>" + header1="\n#{Mx[:lv_o_1]}meta#{Mx[:lv_c]}Document Information (metadata) #{Mx[:id_o]}~0;0:0;m#{ocnm}#{Mx[:id_c]}" ocnm+=1 - header4="\n4~metadata Metadata <~0;m#{ocnm};m#{ocnm}>" + header4="\n#{Mx[:lv_o_4]}metadata#{Mx[:lv_c]}Metadata #{Mx[:id_o]}~0;m#{ocnm};m#{ocnm}#{Mx[:id_c]}" ocnm+=1; ocnd+=1 - head_no_dc="<~0;m#{ocnm};d#{ocnd}>" + head_no_dc="#{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" ocnm+=1; ocnd+=1 - head_no_dc_tag="<~0;m#{ocnm};d#{ocnd}>" + head_no_dc_tag="#{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" data.each do |para| case para - when /^0~(title|creator|author|translator|translated_by|illustrator|illustrated_by|prepared_by|digitized_by|description|publisher|contributor|date\.created|date\.issued|date\.available|date\.valid|date\.modified|date|type|format|rights|identifier|source|language)/i + when /^#{Mx[:meta_o]}(title|creator|author|translator|translated_by|illustrator|illustrated_by|prepared_by|digitized_by|description|publisher|contributor|date\.created|date\.issued|date\.available|date\.valid|date\.modified|date|type|format|rights|identifier|source|language)#{Mx[:meta_c]}/i m=$1 ocnm+=1; ocnd+=1 @dc << case para - when /^0~title/ - "\n#{@tr.dc_title}: #{@md.dc_title} <~0;m#{ocnm};d#{ocnd}>" - when /^0~(?:creator|author)/ - "\n#{@tr.creator}: #{@md.dc_creator} <~0;m#{ocnm};d#{ocnd}>" - when /0~(?:translator|translated_by)/ - "\n#{@tr.translator}: #{@md.translator} <~0;m#{ocnm};d#{ocnd}>" - when /^0~(?:illustrator|illustrated_by)/ - "\n#{@tr.illustrator}: #{@md.illustrator} <~0;m#{ocnm};d#{ocnd}>" - when /^0~prepared_by/ - "\n#{@tr.prepared_by}: #{@md.prepared_by} <~0;m#{ocnm};d#{ocnd}>" - when /^0~digitized_by/ - "\n#{@tr.digitized_by}: #{@md.digitized_by} <~0;m#{ocnm};d#{ocnd}>" - when /^0~description/ - "\n#{@tr.description}: #{@md.dc_description} <~0;m#{ocnm};d#{ocnd}>" - when /^0~subject/ - "\n#{@tr.subject}: #{@md.dc_subject} <~0;m#{ocnm};d#{ocnd}>" - when /^0~abstract/ - "\n#{@tr.abstract}: #{@md.dc_abstract} <~0;m#{ocnm};d#{ocnd}>" - when /^0~publisher/ - "\n#{@tr.publisher}: #{@md.dc_publisher} <~0;m#{ocnm};d#{ocnd}>" - when /^0~contributor/ - "\n#{@tr.contributor}: #{@md.dc_contributor} <~0;m#{ocnm};d#{ocnd}>" - when /^0~date.created/ - "\n#{@tr.date_created}: #{@md.dc_date_created} <~0;m#{ocnm};d#{ocnd}>" - when /^0~date.issued/ - "\n#{@tr.date_issued}: #{@md.dc_date_issued} <~0;m#{ocnm};d#{ocnd}>" - when /^0~date.available/ - "\n#{@tr.date_available}: #{@md.dc_date_available} <~0;m#{ocnm};d#{ocnd}>" - when /^0~date.modified/ - "\n#{@tr.date_modified}: #{@md.dc_date_modified} <~0;m#{ocnm};d#{ocnd}>" - when /^0~date.valid/ - "\n#{@tr.date_valid}: #{@md.dc_date_valid} <~0;m#{ocnm};d#{ocnd}>" - when /^0~date/ - "\n#{@tr.date}: #{@md.dc_date} <~0;m#{ocnm};d#{ocnd}>" - when /^0~type/ - "\n#{@tr.type}: #{@md.dc_type} <~0;m#{ocnm};d#{ocnd}>" - when /^0~format/ - "\n#{@tr.format}: #{@md.dc_format} <~0;m#{ocnm};d#{ocnd}>" - when /^0~rights/ - "\n#{@tr.rights}: #{@md.dc_rights} <~0;m#{ocnm};d#{ocnd}>" - when /^0~identifier/ - "\n#{@tr.identifier}: #{@md.dc_identifier} <~0;m#{ocnm};d#{ocnd}>" - when /^0~source/ - "\n#{@tr.source}: #{@md.dc_source} <~0;m#{ocnm};d#{ocnd}>" - when /^0~language/ - "\n#{@tr.language}: #{@md.dc_language} <~0;m#{ocnm};d#{ocnd}>" - when /^0~language.original/ - "\n#{@tr.language_original}: #{@md.language_original} <~0;m#{ocnm};d#{ocnd}>" - when /^0~relation/ - "\n#{@tr.relation}: #{@md.dc_relation} <~0;m#{ocnm};d#{ocnd}>" - when /^0~coverage/ - "\n#{@tr.coverage}: #{@md.dc_coverage} <~0;m#{ocnm};d#{ocnd}>" - when /^0~keywords/ - "\n#{@tr.keywords}: #{@md.keywords} <~0;m#{ocnm};d#{ocnd}>" - when /^0~comments/ - "\n#{@tr.comments}: #{@md.comments} <~0;m#{ocnm};d#{ocnd}>" - when /^0~cls_loc/ - "\n#{@cls_dewey}: #{@md.cls_dewey} <~0;m#{ocnm};d#{ocnd}>" - when /^0~cls_dewey/ - "\n#{@tr.cls_dewey}: #{@md.cls_dewey} <~0;m#{ocnm};d#{ocnd}>" - when /^0~cls_gutenberg|0~cls_pg/ - "\n#{@tr.cls_gutenberg}: #{@md.cls_gutenberg} <~0;m#{ocnm};d#{ocnd}>" - #"\n#{@tr.cls_gutenberg}: #{@md.cls_pg} <~0;m#{ocnm};d#{ocnd}>" - when /^0~cls_isbn/ - "\n#{@tr.cls_isbn}: #{@md.cls_isbn} <~0;m#{ocnm};d#{ocnd}>" - when /^0~prefix(?:_a)?/ - "\n#{@tr.prefix_a}: #{@md.prefix_a} <~0;m#{ocnm};d#{ocnd}>" - when /^0~prefix_b/ - "\n#{@tr.prefix_b}: #{@md.prefix_b} <~0;m#{ocnm};d#{ocnd}>" - else para.gsub(/^0~(#{m})\s+(.+)/m,"\n#{m.capitalize}: \\2 <~0;m#{ocnm};d#{ocnd}>") + when /^#{Mx[:meta_o]}title#{Mx[:meta_c]}/ + "\n#{@tr.dc_title}: #{Mx[:fa_underscore_o]}#{@md.dc_title}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}(?:creator|author)#{Mx[:meta_c]}/ + "\n#{@tr.creator}: #{Mx[:fa_underscore_o]}#{@md.dc_creator}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /#{Mx[:meta_o]}(?:translator|translated_by)#{Mx[:meta_c]}/ + "\n#{@tr.translator}: #{Mx[:fa_underscore_o]}#{@md.translator}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}(?:illustrator|illustrated_by)#{Mx[:meta_c]}/ + "\n#{@tr.illustrator}: #{Mx[:fa_underscore_o]}#{@md.illustrator}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}prepared_by#{Mx[:meta_c]}/ + "\n#{@tr.prepared_by}: #{Mx[:fa_underscore_o]}#{@md.prepared_by}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}digitized_by#{Mx[:meta_c]}/ + "\n#{@tr.digitized_by}: #{Mx[:fa_underscore_o]}#{@md.digitized_by}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}description#{Mx[:meta_c]}/ + "\n#{@tr.description}: #{Mx[:fa_underscore_o]}#{@md.dc_description}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}subject#{Mx[:meta_c]}/ + "\n#{@tr.subject}: #{Mx[:fa_underscore_o]}#{@md.dc_subject}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}abstract#{Mx[:meta_c]}/ + "\n#{@tr.abstract}: #{Mx[:fa_underscore_o]}#{@md.dc_abstract}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}publisher#{Mx[:meta_c]}/ + "\n#{@tr.publisher}: #{Mx[:fa_underscore_o]}#{@md.dc_publisher}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}contributor#{Mx[:meta_c]}/ + "\n#{@tr.contributor}: #{Mx[:fa_underscore_o]}#{@md.dc_contributor}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}date.created#{Mx[:meta_c]}/ + "\n#{@tr.date_created}: #{Mx[:fa_underscore_o]}#{@md.dc_date_created}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}date.issued#{Mx[:meta_c]}/ + "\n#{@tr.date_issued}: #{Mx[:fa_underscore_o]}#{@md.dc_date_issued}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}date.available#{Mx[:meta_c]}/ + "\n#{@tr.date_available}: #{Mx[:fa_underscore_o]}#{@md.dc_date_available}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}date.modified#{Mx[:meta_c]}/ + "\n#{@tr.date_modified}: #{Mx[:fa_underscore_o]}#{@md.dc_date_modified}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}date.valid#{Mx[:meta_c]}/ + "\n#{@tr.date_valid}: #{Mx[:fa_underscore_o]}#{@md.dc_date_valid}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}date#{Mx[:meta_c]}/ + "\n#{@tr.date}: #{Mx[:fa_underscore_o]}#{@md.dc_date}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}type#{Mx[:meta_c]}/ + "\n#{@tr.type}: #{Mx[:fa_underscore_o]}#{@md.dc_type}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}format#{Mx[:meta_c]}/ + "\n#{@tr.format}: #{Mx[:fa_underscore_o]}#{@md.dc_format}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}rights#{Mx[:meta_c]}/ + "\n#{@tr.rights}: #{Mx[:fa_underscore_o]}#{@md.dc_rights}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}identifier#{Mx[:meta_c]}/ + "\n#{@tr.identifier}: #{Mx[:fa_underscore_o]}#{@md.dc_identifier}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}source#{Mx[:meta_c]}/ + "\n#{@tr.source}: #{Mx[:fa_underscore_o]}#{@md.dc_source}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}language#{Mx[:meta_c]}/ + "\n#{@tr.language}: #{Mx[:fa_underscore_o]}#{@md.dc_language}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}language.original#{Mx[:meta_c]}/ + "\n#{@tr.language_original}: #{Mx[:fa_underscore_o]}#{@md.language_original}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}relation#{Mx[:meta_c]}/ + "\n#{@tr.relation}: #{Mx[:fa_underscore_o]}#{@md.dc_relation}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}coverage#{Mx[:meta_c]}/ + "\n#{@tr.coverage}: #{Mx[:fa_underscore_o]}#{@md.dc_coverage}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}keywords#{Mx[:meta_c]}/ + "\n#{@tr.keywords}: #{Mx[:fa_underscore_o]}#{@md.keywords}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}comments#{Mx[:meta_c]}/ + "\n#{@tr.comments}: #{Mx[:fa_underscore_o]}#{@md.comments}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}cls_loc#{Mx[:meta_c]}/ + "\n#{@cls_dewey}: #{Mx[:fa_underscore_o]}#{@md.cls_dewey}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}cls_dewey#{Mx[:meta_c]}/ + "\n#{@tr.cls_dewey}: #{Mx[:fa_underscore_o]}#{@md.cls_dewey}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}(?:cls_gutenberg|cls_pg)#{Mx[:meta_c]}/ + "\n#{@tr.cls_gutenberg}: #{Mx[:fa_underscore_o]}#{@md.cls_gutenberg}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + #"\n#{@tr.cls_gutenberg}: #{@md.cls_pg} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}cls_isbn#{Mx[:meta_c]}/ + "\n#{@tr.cls_isbn}: #{Mx[:fa_underscore_o]}#{@md.cls_isbn}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}prefix(?:_a)?#{Mx[:meta_c]}/ + "\n#{@tr.prefix_a}: #{Mx[:fa_underscore_o]}#{@md.prefix_a}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + when /^#{Mx[:meta_o]}prefix_b#{Mx[:meta_c]}/ + "\n#{@tr.prefix_b}: #{Mx[:fa_underscore_o]}#{@md.prefix_b}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}" + else para.gsub(/^#{Mx[:meta_o]}(#{m})\s+(.+)/m,"\n#{m.capitalize}: #{Mx[:fa_underscore_o]}\\2#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}") end end end ocnm+=1; ocnv+=1 - head_no_rc="<~0;m#{ocnm};v#{ocnv}>" + head_no_rc="#{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 - head_no_rc_tag="<~0;m#{ocnm};v#{ocnv}>" + head_no_rc_tag="#{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" data.each do |para| case para when /^0~(?:cvs|rcs)\+\s+/ #note the + sign to turn on use of cvs id ocnm+=1; ocnv+=1 - @cvs << "#{@tr.sc_number}: #{@md.sc_number} <~0;m#{ocnm};v#{ocnv}>" + @cvs << "#{@tr.sc_number}: #{Mx[:fa_underscore_o]}#{@md.sc_number}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 - @cvs << "#{@tr.sc_date}: #{@md.sc_date} <~0;m#{ocnm};v#{ocnv}>" + @cvs << "#{@tr.sc_date}: #{Mx[:fa_underscore_o]}#{@md.sc_date}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 - @cvs << "CVS/RCS time: #{@md.sc_time} <~0;m#{ocnm};v#{ocnv}>" + @cvs << "CVS/RCS time: #{Mx[:fa_underscore_o]}#{@md.sc_time}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 when /^0~cvs[+\s]/ #enable pattern above instead if you wish the default to be to include cvs tags from all documents KEEP when /^0~cvs\s+/ #enable pattern above instead if you wish the default to be to include cvs tags from all documents KEEP @@ -1007,47 +1008,45 @@ module SiSU_DAL ocnm+=1; ocnv+=1 if @md.sc_filename \ and @md.sc_filename.length > 3 - @rc << "#{@tr.sourcefile}: #{@md.sc_filename} <~0;m#{ocnm};v#{ocnv}>" - else @rc << "#{@tr.sourcefile}: #{@md.fns} <~0;m#{ocnm};v#{ocnv}>" + @rc << "#{@tr.sourcefile}: #{Mx[:fa_underscore_o]}#{@md.sc_filename}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" + else @rc << "#{@tr.sourcefile}: #{Mx[:fa_underscore_o]}#{@md.fns}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" end ocnm+=1; ocnv+=1 if @md.file_encoding \ and @md.file_encoding.length > 3 #translate - @rc << "Filetype: #{@md.file_encoding} <~0;m#{ocnm};v#{ocnv}>" + @rc << "Filetype: #{Mx[:fa_underscore_o]}#{@md.file_encoding}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" end ocnm+=1; ocnv+=1 if @md.dgst #change. enable by default - @rc << "#{@tr.sourcefile_digest}, #{@md.dgst[0]} #{@md.dgst[1]} <~0;m#{ocnm};v#{ocnv}>" + @rc << "#{@tr.sourcefile_digest}, #{@md.dgst[0]} #{Mx[:fa_underscore_o]}#{@md.dgst[1]}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 end if @md.dgst_skin #change. enable by default - @rc << "Skin_Digest: #{@md.dgst_skin[0]} #{@md.dgst_skin[1]} <~0;m#{ocnm};v#{ocnv}>" + @rc << "Skin_Digest: #{@md.dgst_skin[0]} #{Mx[:fa_underscore_o]}#{@md.dgst_skin[1]}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 end - @rc << "Generated #{head_no_rc}" if @rc.length > 0 - @rc << "#{@tr.last_generated}: #{Time.now} <~0;m#{ocnm};v#{ocnv}>" + @rc << "#{Mx[:fa_bold_o]}Generated#{Mx[:fa_bold_c]} #{head_no_rc}" if @rc.length > 0 + @rc << "#{@tr.last_generated}: #{Mx[:fa_underscore_o]}#{Time.now}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 if @md.sisu_version[:version] - @rc << "#{@tr.sisu_version}: #{@md.sisu_version[:project]} #{@md.sisu_version[:version]} of #{@md.sisu_version[:date_stamp]} (#{@md.sisu_version[:date]}) <~0;m#{ocnm};v#{ocnv}>" + @rc << "#{@tr.sisu_version}: #{Mx[:fa_underscore_o]}#{@md.sisu_version[:project]}#{Mx[:fa_underscore_c]} #{Mx[:fa_underscore_o]}#{@md.sisu_version[:version]}#{Mx[:fa_underscore_c]} of #{@md.sisu_version[:date_stamp]} (#{@md.sisu_version[:date]}) #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" ocnm+=1; ocnv+=1 end - @rc << "#{@tr.ruby_version}: #{@md.ruby_version} <~0;m#{ocnm};v#{ocnv}>" + @rc << "#{@tr.ruby_version}: #{Mx[:fa_underscore_o]} #{@md.ruby_version}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}" end - meta << header0 - meta << header1 - meta << header4 - meta << "Document Manifest @\n #{base_html}/#{@md.fn[:manifest]} <~0;m#{ocnm};m#{ocnm}>" - meta << "Dublin Core (DC) #{head_no_dc}" if @dc.length > 0 - meta << "DC tags included with this document are provided here. #{head_no_dc_tag}" if @dc.length > 0 + meta << Mx[:br_page_new] << header1 << header4 + meta << "Document Manifest @\n #{base_html}/#{@md.fn[:manifest]} #{Mx[:id_o]}~0;m#{ocnm};m#{ocnm}#{Mx[:id_c]}" + meta << "#{Mx[:fa_bold_o]}Dublin Core#{Mx[:fa_bold_c]} (DC) #{head_no_dc}" if @dc.length > 0 + meta << "#{Mx[:fa_italics_o]}DC tags included with this document are provided here.#{Mx[:fa_italics_c]} #{head_no_dc_tag}" if @dc.length > 0 @dc.each { |x| meta << x } - meta << "Version Information #{head_no_rc}" if @rc.length > 0 + meta << "#{Mx[:fa_bold_o]}Version Information#{Mx[:fa_bold_c]} #{head_no_rc}" if @rc.length > 0 if @cvs.length > 0 - meta << "Note the version information provided here, is specific to the host site. #{head_no_rc_tag}" + meta << "#{Mx[:fa_italics_o]}Note the version information provided here, is specific to the host site.#{Mx[:fa_italics_c]} #{head_no_rc_tag}" @cvs.each { |x| meta << x } end @rc.each { |x| meta << x } ## ENDNOTE RELATED endnote related - meta << "\n" + meta << "\n#{Mx[:br_eof]}" meta=object_digest(meta) end def stamped(para,hash_class) @@ -1056,23 +1055,23 @@ module SiSU_DAL digest_all=hash_class.hexdigest(para) # print "#{hash_class.name}: "; puts digest_all #length==32 or 64 stripped=strip_clean_of_markup(para) digest_strip=hash_class.hexdigest(stripped) - unless para =~/<:code>/ + unless para =~/#{Mx[:fa_o]}code#{Mx[:fa_c]}/ case para - when /~\{[\d*+]+\s+.+?\}~|~\[[*+]\d+\s+.+?\]~/m + when /#{Mx[:en_a_o]}[\d*+]+\s+.+?#{Mx[:en_a_c]}|#{Mx[:en_b_o]}[*+]\d+\s+.+?#{Mx[:en_b_c]}/m en_and_para,en_and_para_digest=[],[] - para.gsub!(/\s*(\}~|\]~)/m,' \1') #watch - para_plus_en=para.scan(/.*?~\{.+?\}~|.*?~\[.+?\]~/m) - para_tail=if para =~/(?:.*?~\{.+?\}~|.*?~\[.+?\]~)+([\s\S]+)/m - /(?:.*?~\{.+?\}~|.*?~\[.+?\]~)+(.+?<~\d+;(?:\w|[0-6]:)\d+;\w\d+>)/m.match(para)[1] + para.gsub!(/\s*(#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/m,' \1') #watch + para_plus_en=para.scan(/.*?#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}|.*?#{Mx[:en_b_o]}.+?#{Mx[:en_b_c]}/m) + para_tail=if para =~/(?:.*?#{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]})+(.+?#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]})/m.match(para)[1] else '' end para_plus_en << para_tail en_and_para_digest << endnote_digest(para_plus_en) para_new=en_and_para_digest.join(' ') - @tuned << para_new + '<' + digest_strip + ':' + digest_all + '>' unless para.nil? - else @tuned << para + '<' + digest_strip + ':' + digest_all + '>' unless para.nil? + @tuned << para_new + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless para.nil? + else @tuned << para + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless para.nil? end - else @tuned << para + '<' + digest_strip + ':' + digest_all + '>' unless para.nil? + else @tuned << para + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless para.nil? end @tuned.join end @@ -1088,7 +1087,8 @@ module SiSU_DAL data.compact! data.each do |para| para.strip! - if para=~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+>/ + if para=~/#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}/ \ + and para !~/#{Rx[:meta]}/ #test should not be necessary remove if @env.digest.type =~/sha256/ for hash_class in [ Digest::SHA256 ] @tuned_file << stamped(para,hash_class) @@ -1108,16 +1108,16 @@ module SiSU_DAL para_bit=[] data.each do |en_plus| para_bit <<= case en_plus - when /~\{|~\[/ - if en_plus =~/~\{.+?\}~|~\[.+?\]~/ - para_txt,en_open,en_txt,en_close=/(.*?)(~\{|~\[)(.+?)(\}~|\]~)/m.match(en_plus)[1..4] + 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]}/ + para_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=strip_clean_of_markup(en_txt) digest_en_strip=if @env.digest.type =~/sha256/ Digest::SHA256.hexdigest(stripped_en) else Digest::MD5.hexdigest(stripped_en) end - para_txt + en_open + en_txt + '<' + digest_en_strip + '>' + en_close + para_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 @@ -1131,12 +1131,13 @@ module SiSU_DAL s=s.gsub(/ [ ]+/,' ') s=s.gsub(/^ [ ]+/,'') s=s.gsub(/ [ ]+$/,'') - s=s.gsub(/(<\/[bi]>')[ ]+(s )/,'\1\2') + 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 def strip_clean_of_markup(s) # used for digest, define rules, make same as in db clean #consider: <\/?[ib]>|<(?:\/ )?br>|(.+?)<\/del> s=s.dup - s=s.gsub(/(?:<\/?[ib]>|<~\d+;(?:\w|[0-6]:)\d+;\w\d+>|<#@dp:#@dp>|^[1-6]~\S+|~\{\d+\s.+?\}~)/m,'') # markup and endnotes removed + s=s.gsub(/(?:<\/?[ib]>|#{Mx[:id_o]}~\d+;(?:\w|[0-6]:)\d+;\w\d+#{Mx[:id_c]}|#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}|^#{Mx[:lv_o]}[1-6]:\S+?#{Mx[:lv_c]}|#{Mx[:en_a_o]}\d+\s.+?#{Mx[:en_a_c]})/m,'') # markup and endnotes removed #% same as db clean --> s=s.gsub(/(.+?)<\/del>/,'DELETED(\1)') # deletions s=s.gsub(/(\d+)<\/sup>/,'[\1]') -- cgit v1.2.3