aboutsummaryrefslogtreecommitdiffhomepage
path: root/lib/sisu/v0/dal.rb
diff options
context:
space:
mode:
authorRalph Amissah <ralph@amissah.com>2008-09-08 22:24:15 -0400
committerRalph Amissah <ralph@amissah.com>2008-09-08 22:24:15 -0400
commit798d710dea23806e428ec7636dad4c1d872166e3 (patch)
tree8d57b551d873f9b912e416e590efba5d8e1f33cc /lib/sisu/v0/dal.rb
parentbook index (markup adjustment, dal module); dal numbering moved to separate m... (diff)
dal, several modules split into separate files
Diffstat (limited to 'lib/sisu/v0/dal.rb')
-rw-r--r--lib/sisu/v0/dal.rb608
1 files changed, 26 insertions, 582 deletions
diff --git a/lib/sisu/v0/dal.rb b/lib/sisu/v0/dal.rb
index aa4758b7..d091284d 100644
--- a/lib/sisu/v0/dal.rb
+++ b/lib/sisu/v0/dal.rb
@@ -60,15 +60,22 @@
=end
module SiSU_DAL
- require "#{SiSU_lib}/defaults"
- require "#{SiSU_lib}/sysenv"
- require "#{SiSU_lib}/param"
- require "#{SiSU_lib}/dal_syntax"
- require "#{SiSU_lib}/dal_doc_str"
- require "#{SiSU_lib}/dal_idx"
- require "#{SiSU_lib}/dal_numbering"
- require "#{SiSU_lib}/i18n"
- require "#{SiSU_lib}/shared_sem"
+ require "#{SiSU_lib}/defaults" # defaults.rb
+ require "#{SiSU_lib}/sysenv" # sysenv.rb
+ require "#{SiSU_lib}/param" # param.rb
+ require "#{SiSU_lib}/dal_syntax" # dal_syntax.rb
+ require "#{SiSU_lib}/dal_doc_str" # dal_doc_str.rb
+ require "#{SiSU_lib}/dal_idx" # dal_idx.rb
+ require "#{SiSU_lib}/dal_numbering" # dal_numbering.rb
+ require "#{SiSU_lib}/dal_hash_digest" # dal_hash_digest.rb
+ require "#{SiSU_lib}/dal_endnotes" # dal_endnotes.rb
+ require "#{SiSU_lib}/dal_images" # dal_images.rb
+ require "#{SiSU_lib}/dal_metadata" # dal_metadata.rb
+ require "#{SiSU_lib}/dal_character_check" # dal_character_check.rb
+ require "#{SiSU_lib}/dal_substitutions_and_insertions" # dal_substitutions_and_insertions.rb
+ require "#{SiSU_lib}/dal_expand_insertions" # dal_expand_insertions.rb
+ require "#{SiSU_lib}/i18n" # i18n.rb
+ require "#{SiSU_lib}/shared_sem" # shared_sem.rb
include SiSU_Env
include SiSU_Param
include SiSU_Viz
@@ -76,9 +83,6 @@ module SiSU_DAL
class Instantiate < SiSU_Param::Parameters::Instructions
def initialize
@@flag_vocab=0
- @@endnote={}
- @@endnote_array=@@word_mode=[]
- @@endnote_counter,@@endnote_counter_asterisk,@@endnote_counter_dag=1,1,1 #added
@@line_mode=''
end
end
@@ -171,26 +175,17 @@ module SiSU_DAL
end
end
class Make
- @@endnote={}
- @@endnote_array=@@word_mode=[]
- @@endnote_counter,@@endnote_counter_asterisk,@@endnote_counter_dag=1,1,1
- @@comment='%'
+ #@@comment='%'
@@dp=nil
def initialize(md,data)
@md,@data=md,data
- @@word_mode=[]
+ #@@word_mode=[]
@env=SiSU_Env::Info_env.new(@md.fns)
@skin=SiSU_Env::Info_skin.new(@md)
@dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern
- l=SiSU_Env::Standardise_language.new.file_to_language(@md.fns)
- @language=l[:l]
- @tr=SiSU_Translate::Source.new(@md,@language)
end
def reset
@@flag_vocab=0
- @@endnote={}
- @@endnote_array=@@word_mode=[]
- @@endnote_counter,@@endnote_counter_asterisk,@@endnote_counter_dag=1,1,1
@@line_mode=''
end
def song
@@ -199,9 +194,9 @@ module SiSU_DAL
@metafile="#{@env.path.dal}/#{@md.fns}.meta"
my_make_source_file=SiSU_Env::Create_file.new(@md.cmd,@md.fns)
data=data.join.split("\n\n")
- data=expand_insertions?(data)
+ data=SiSU_insertions::Insertions.new(data).expand_insertions?
data=SiSU_document_structure::Code.new(@md,data).code
- data=substitutions_and_insertions?(data)
+ data=SiSU_substitute_and_insert::SI.new(@md,data).substitutions_and_insertions?
data_new=[]
data.each do |x|
data_new << if x =~ /\n\n/m; x.split(/\n\n+/)
@@ -210,14 +205,15 @@ module SiSU_DAL
end
data=data_new.flatten
data=SiSU_Syntax::Markup.new(@md,data).songsheet
- data=character_check(data)
- data=images(data)
+ data,endnote_array=SiSU_character_check::Check.new(data).character_check_and_oldstyle_endnote_array
+ data=SiSU_images::Images.new(@md,data).images
data=SiSU_document_structure::Tables.new(@md,data).tables
data=SiSU_numbering::Numbering.new(@md,data).numbering_song
data=SiSU_book_index::Book_index.new(data).indexing_song if @md.book_index
- data=endnotes(data)
- data=object_digest(data)
- meta=metadata(data)
+ data=SiSU_endnotes::Endnotes.new(@md,data,endnote_array).endnotes
+ data=SiSU_hash::Object_digest.new(@md,data,@env).object_digest
+ meta=SiSU_metadata::Metadata.new(@md,data).metadata
+ #meta=metadata(data)
outputdata=data + meta
if @md.cmd =~/[mM]/
SiSU_DAL::Output.new(@md,outputdata).hard_output
@@ -227,100 +223,6 @@ module SiSU_DAL
outputdata
end
protected
- def character_check(data)
- require 'iconv'
- reset
- @tuned_file=[]
- endnote_no=1
- data.each do |para|
- para.strip!
- para.gsub!(/^([12])~\?\s+/,'\1~ ') #conditional header for incorporated document 2004w12
- para.gsub!(/^[{~}]\s*$/,'')
- para.gsub!(/^#{@@comment}.*/,'') #remove comment and divider #%
- 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!(/(#{Mx[:en_a_o]})\s*\s+/,'\1 '); para.gsub!(/(~\{\s*)\s+/,'\1 ')
- para.gsub!(/ \/\//,"#{Mx[:br_line]}") #added 2004w29
- para.gsub!(/<br>/,"#{Mx[:br_line]}") #needed by xml, xhtml etc.
- para.gsub!(/\t/,' ')
- para.gsub!(/\342\200\231/u,"'") #if para =~/’/ #Avoid #&lsquo; &rsquo; #&ldquo; &rdquo;
- para.gsub!(/�/u,' ') #watch, replace with char code
- para.gsub!(/·/u,'*')
- para.gsub!(/\\copy(?:right)?\b/,'&#169;')
- para.gsub!(/\\trademark\b|\\tm\b/,'&#174;')
- #non_utf8(para)
- para=para + "\n"
- 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*/,%{#{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
- end
- @tuned_file << para unless para.nil?
- end
- @tuned_file=@tuned_file.flatten
- end
- def images(data)
- tuned_file=[]
- @rmgk=false
- if SiSU_Env::Info_settings.new.program?('rmagick'); @rmgk=SiSU_Env::Load.new('RMagick').prog
- else tell=SiSU_Screen::Ansi.new(@md.cmd,'use of RMagick is not enabled in sisurc.yml')
- tell.warn if @md.cmd =~/[vVM]/
- end
- data.each do |para|
- para.strip!
- if para =~/#{Mx[:lnk_o]}\s*\S+\.(?:png|jpg|gif)(?:\s*|\s+.+)?#{Mx[:lnk_c]}(?:(?:https?|file|ftp):\S+|image)/
- if para !~/#{Mx[:lnk_o]}\s*\S+\.(?:png|jpg|gif)\s+\d+x\d+\s+/
- m=/#{Mx[:lnk_o]}\s*(\S+\.(?:png|jpg|gif))/
- if @rmgk
- imgs=para.scan(m).flatten
- images=imgs.each do |image|
- dir=SiSU_Env::Info_env.new(@md.fns)
- path_image=[dir.path.image_source_local_tex,dir.path.image_source_remote_tex,dir.path.image_source_tex]
- image_path=nil
- path_image.each do |image_path|
- break if FileTest.exist?("#{image_path}/#{image}")
- end
- if FileTest.exist?("#{image_path}/#{image}")
- img=Magick::ImageList.new("#{image_path}/#{image}")
- img_col,img_row=img.columns,img.rows
- if img_col > img_row #landscape
- if img_col> 640 #480
- img_col=640 #480
- img_row=((1.00*img_col/img.columns)*img.rows).round
- end
- else #portrait
- if img_col> 640 #480
- img_col=640 #480
- img_row=((1.00*img_col/img.columns)*img.rows).round
- end
- if img_row > 640
- img_row=640
- img_col=((1.00*img_row/img.rows)*img.columns).round
- end
- end
- para.gsub!(/(#{image})/,"#{image} #{img_col}x#{img_row}")
- else para.gsub!(/#{Mx[:lnk_o]}\s*(\S+)\.(png|jpg|gif).+?#{Mx[:lnk_c]}((?:https?|file|ftp):\S+|image)/,'[ \1 (\2 missing) ]')
- end
- end
- else
- images=para.scan(m) do |image|
- tell=SiSU_Screen::Ansi.new(@md.cmd,'where image dimensions have not been provided RMagick is required',image)
- tell.warn #unless @opt.cmd =~/q/
- end
- end
- end
- end
- para.gsub!(/(#{Mx[:lnk_o]})\s*(\S+\.(?:png|jpg|gif))\s+/i,'\1\2 ') if para =~/#{Mx[:lnk_o]}\s*\S+\.(?:png|jpg|gif).+?#{Mx[:lnk_c]}(?:(?:https?|file|ftp):\S+|image)/
- tuned_file << para unless para.nil?
- end
- tuned_file
- end
def output_filetypes_in_cmd(cmd_shortcut,source=nil)
#make list of file types in shortcut command (as configured), e.g. when sisu -3 is used
cf_defaults=SiSU_Env::Info_processing_flag.new
@@ -366,464 +268,6 @@ module SiSU_DAL
file_type_names[:src]=file_type_names[:src].flatten
file_type_names
end
- def expand_insertions?(data)
- tuned_file,tuned_file_tmp=[],[]
- data.each do |para|
- if para !~/^%+\s/ \
- and para =~/\{(?:~\^\s+)?(.+?)\s\[(?:\d(?:[sS]*))\]\}(?:\.\.\/\S+?\/|\S+?\.ss[tm]\b)/
- txt,cmd,source,url_dir,note,manifest=nil,nil,nil,nil,nil,nil
- @u=SiSU_Env::Info_env.new.url
- if defined? @u.remote
- if para =~/(.+?)\{(.+?)\s\[(\d[sS]*)\]\}((\S+?)\.ss[tm]\b)(.*)/m
- pre,txt,cmd,source,url_dir,note="#{$1.strip} ",$2,$3,$4,$5,$6
- elsif para =~/\{(.+?)\s\[(\d[sS]*)\]\}((\S+?)\.ss[tm]\b)(.*)/
- pre,txt,cmd,source,url_dir,note='',$1,$2,$3,$4,$5
- end
- 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+#{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
- end
- tuned_file_tmp << manifest
- output_filetypes=output_filetypes_in_cmd(cmd,source)
- output_filetypes[:gen].each do |o_f|
- describe = case o_f
- when /sisu_manifest.html/; '~^ document manifest'
- when /toc.html/; ' html, segmented text'
- when /doc.html/; ' html, scroll, document in one'
- when /landscape.pdf/; ' pdf, landscape'
- when /portrait.pdf/; ' pdf, portrait'
- when /opendocument.odt/; ' odf:odt, open document text'
- when /scroll.xhtml/; ' xhtml scroll'
- when /sax.xml/; ' xml, sax'
- when /dom.xml/; ' xml, dom'
- when /plain.txt/; ' plain text utf-8'
- #when /manpage.1/; ' man, 1'
- when /wiki.txt/; ' wiki text'
- when /concordance.html/; ' concordance'
- when /digest.txt/; ' dcc, document content certificate (digests)'
- else nil
- end
- if describe
- tuned_file_tmp << if @u.remote #to double space <:br> at beginning of entry
- if describe =~/^~\^ /
- "#{Mx[:nbsp]*4} {#{describe} }#{@u.remote}/#{url_dir}/#{o_f} "
- else
- "#{Mx[:nbsp]*4} { #{describe} }#{@u.remote}/#{url_dir}/#{o_f} "
- end
- else
- if describe =~/^~\^ /
- "#{Mx[:nbsp]*4} {#{describe} }../#{url_dir}/#{o_f} "
- else "#{Mx[:nbsp]*4} { #{describe} }../#{url_dir}/#{o_f} "
- end
- end
- end
- end
- output_filetypes[:src].each do |o_f|
- describe=case o_f
- when /#{source}\.zip/; ' markup source (zipped) pod'
- when /#{source}/; ' markup source text'
- else nil
- end
- if describe
- tuned_file_tmp << if @u.remote
- x=if describe =~/zip/
- "#{Mx[:nbsp]*4} {#{describe} }#{@u.src_pod}/#{o_f} "
- else "#{Mx[:nbsp]*4} {#{describe} }#{@u.src_txt}/#{o_f} "
- end
- else
- x=if describe =~/zip/
- "#{Mx[:nbsp]*4} { #{describe} }../pod/#{o_f} "
- else "#{Mx[:nbsp]*4} { #{describe} }../zip/#{o_f} "
- end
- end
- end
- end
- tuned_file << 'group{' << tuned_file_tmp.join("\n") << '}group'
- #tuned_file << 'group{' << tuned_file_tmp.join("\n").strip << '}group'
- tuned_file_tmp=[]
- else tuned_file << para
- end
- end
- tuned_file
- end
- def substitutions_and_insertions?(data)
- 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 precedes it)
- data[0].gsub!(/^#!\s*\/usr\/bin\/sisu/,'')
- data[0].gsub!(/^#!\s*\/usr\/bin\/env sisu/,'')
- end
- if data[0] =~ /^(SiSU\s+[\d.]*|sisu-[\d.]+)$/ # SiSU identifier
- data[0].gsub!(/^(SiSU\s*[\d.]*)$/,'% \1')
- data[0].gsub!(/^(sisu-[\d.]+)$/,'% \1')
- end
- data.each do |para|
- if para =~/<:insert\d+!?>/ \
- and para !~/^%\s+/
- @skin.select
- ins=SiSU_Viz::Inserts.new
- case para
- when /^\s*<:insert1>\s*$/
- para=[]
- ins.insert1.split(/\n\n/).each{|x| para << x }
- when /^\s*<:insert2>\s*$/
- para=[]
- ins.insert2.split(/\n\n/).each{|x| para << x }
- when /^\s*<:insert3>\s*$/
- para=[]
- ins.insert3.split(/\n\n/).each{|x| para << x << "\n"}
- para=ins.insert3
- when /^\s*<:insert4>\s*$/
- para=[]
- ins.insert4.split(/\n\n/).each{|x| para << x << "\n"}
- para=ins.insert4
- when /^\s*<:insert5>\s*$/
- para=[]
- ins.insert5.split(/\n\n/).each{|x| para << x << "\n"}
- when /^\s*<:insert6>\s*$/
- para=[]
- ins.insert6.split(/\n\n/).each{|x| para << x << "\n"}
- when /^\s*<:insert7>\s*$/
- para=[]
- ins.insert7.split(/\n\n/).each{|x| para << x << "\n"}
- end
- para.each{|x| data_expand << x }
- else data_expand << para
- end
- data_expand.flatten!
- data_expand.compact!
- end
- data_expand.each do |para|
- para=if @md.markup_version.to_f >= 0.38
- SiSU_document_structure::Structure.new(@md,para).structure_markup_normalize
- else
- SiSU_document_structure::Structure.new(@md,para).structure_marks
- end
- #para.gsub!(/<url:(\S+?)>/,'\1') #consider, would permit use of text hyperlinks if desired, dal_syntax more appropriate?
- para.gsub!(/^((?:[1-9]|:?[A-C])~\S*)\s*$/,'\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
- end
- end
- def endnotes(data)
- @tuned_file=[]
- endnote_no,endnote_ref=1,1
- #% endnote work zone
- data.each do |para|
- # manually numbered endnotes <!e(\d)!> <!e_(\d)!> -->
- if @md.mod.inspect =~/--no-asterisk|--no-annotate/
- para.gsub!(/#{Mx[:en_b_o]}\s.+?#{Mx[:en_b_c]}/,'')
- end
- if @md.mod.inspect =~/--no-dagger|--no-annotate/
- para.gsub!(/#{Mx[:en_b_o]}[+]\s.+?#{Mx[:en_b_c]}/,'')
- end
- unless para =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/
- case para
- # auto-numbered endnotes <!e!> <!e_!> -->
- when /#{Mx[:en_a_o]}.+?#{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 /^(<!e[:_]!>|[-~]\{{3})/ (in earlier loop)
- 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
- end
- end
- @tuned_file << para
- end
- @tuned_file=@tuned_file.flatten
- end
- def endnote_call_number(data)
- data.each do |word|
- unless data =~/^#{Mx[:gr_o]}code#{Mx[:gr_c]}/
- case word
- 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 /#{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!(/#{Mx[:en_b_o]}[*]?/,"#{Mx[:en_b_o]}\*#{@@endnote_counter_asterisk} ")
- @@endnote_counter_asterisk+=1
- end
- when /~\^|<:e>/
- word.gsub!(/~\^|<:e>/,"#{@@endnote_array[@@endnote_counter-1]}")
- @@endnote_counter+=1
- end
- end
- end
- end
- def metadata(data)
- meta,@dc,@rc,@cvs,dctitle,add=Array.new(6){[]}
- dir=SiSU_Env::Info_env.new(@md.fns)
- base_html="#{dir.url.root}/#{@md.fnb}"
- ocnm=ocnd=ocnv=0
- ocnm+=1
- 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="\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="#{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}"
- ocnm+=1; ocnd+=1
- head_no_dc_tag="#{Mx[:id_o]}~0;m#{ocnm};d#{ocnd}#{Mx[:id_c]}"
- data.each do |para|
- case para
- 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 /^#{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}: <u>#{@md.cls_pg}</u> #{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="#{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"
- ocnm+=1; ocnv+=1
- 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}: #{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}: #{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: #{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
- end
- end
- if true #default version information
- ocnm+=1; ocnv+=1
- if @md.sc_filename \
- and @md.sc_filename.length > 3
- @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: #{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]} #{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]} #{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 << "#{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}: #{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}: #{Mx[:fa_underscore_o]} #{@md.ruby_version}#{Mx[:fa_underscore_c]} #{Mx[:id_o]}~0;m#{ocnm};v#{ocnv}#{Mx[:id_c]}"
- end
- 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 << "#{Mx[:fa_bold_o]}Version Information#{Mx[:fa_bold_c]} #{head_no_rc}" if @rc.length > 0
- if @cvs.length > 0
- 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#{Mx[:br_eof]}"
- meta=object_digest(meta)
- end
- def stamped(para,hash_class)
- @tuned=[]
- para=strip_clean_extra_spaces(para)
- 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 =~/#{Mx[:fa_o]}code#{Mx[:fa_c]}/
- case para
- 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*(#{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 + 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 + Mx[:id_o] + digest_strip + ':' + digest_all + Mx[:id_c] unless para.nil?
- end
- @tuned.join
- end
- def object_digest(data)
- # 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]
- # vim==/<[0-9a-f]\{#{@@dl}\}\(:[0-9a-f]\{#{@@dl}\}\)\?>/
- require 'digest/md5'
- require 'digest/sha2'
- @tuned_file=[]
- data.compact!
- data.each do |para|
- para.strip!
- 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)
- end
- else
- for hash_class in [ Digest::MD5 ]
- @tuned_file << stamped(para,hash_class)
- end
- end
- else @tuned_file << para unless para.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)
- para_bit=[]
- data.each do |en_plus|
- para_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]}/
- 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 + 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
- para_bit.join
- 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
- def strip_clean_of_markup(s) # used for digest, define rules, make same as in db clean
- #consider: <\/?[ib]>|<(?:\/ )?br>|<del>(.+?)<\/del>
- s=s.dup
- 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>(.+?)<\/del>/,'DELETED(\1)') # deletions
- s=s.gsub(/<sup>(\d+)<\/sup>/,'[\1]')
- s=s.gsub(/(?:#{Mx[:nbsp]})+/,' ')
- #s=s.gsub(/<!T[h]?¡.+?!>/,"[TABLE]\n") # tables
- #s=s.gsub(/<!¡¡\d+(.+?)!>/,'\1') # tables
- #s=s.gsub(/¡¡\d+¡/,' ') # tables
- #s=s.gsub(/¡/,' ') # tables tidy later
- #s=s.gsub(/<.+?>/,'')
- s=s.gsub(/#{Mx[:lnk_o]}.+?\.(?:png|jpg|gif).+?#{Mx[:lnk_c]}(?:https?|file|ftp)\\\:\S+ /,' [image] ') # else image names found in search
- s=s.gsub(/\s\s+/,' ')
- s=s.strip
- end
end
end
__END__