=begin * Name: SiSU information Structuring Universe - Structured information, Serialized Units * Author: Ralph Amissah * http://www.jus.uio.no/sisu * http://www.jus.uio.no/sisu/SiSU/download.html * Description: modules shared by the different db types, dbi, postgresql, sqlite * Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007 Ralph Amissah * License: GPL 2 or later Summary of GPL 2 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 2 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, write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA If you have Internet connection, the latest version of the GPL should be available at these locations: http://www.fsf.org/licenses/gpl.html http://www.gnu.org/copyleft/gpl.html http://www.jus.uio.no/sisu/gpl2.fsf SiSU was first released to the public on January 4th 2005 SiSU uses: * Standard SiSU markup syntax, * Standard SiSU meta-markup syntax, and the * Standard SiSU object citation numbering and system © Ralph Amissah 1997, current 2007. All Rights Reserved. * Ralph Amissah: ralph@amissah.com ralph.amissah@gmail.com =end module SiSU_DB_import require "#{SiSU_lib}/db_columns" require "#{SiSU_lib}/db_load_tuple" require "#{SiSU_lib}/shared_html_lite" class Import < SiSU_DB_columns::Column_size include SiSU_Param include SiSU_Screen @@dl=nil attr_accessor :tp def initialize(opt,conn='',sql_type='pg') @opt,@conn,@sql_type=opt,conn,sql_type @cX=SiSU_Screen::Ansi.new(@opt.cmd).cX @env=SiSU_Env::Info_env.new(@opt.fns) @dal="#{@env.path.dal}" if @opt.fns.empty? or @opt.cmd.empty?; @fnb='' else @md=SiSU_Param::Parameters.new(@opt).get @fnb=@md.fnb end @suffix=@opt.fns[/(?:.+?)\.[_-]?sst/,1] @fnm="#@dal/#{@opt.fns}.meta.rbm" @@seg='' @@seg_full='' #create? consider placing field just before clean text as opposed to seg which contains seg(.html) name info seg_full would contain seg info for levels 5 & 6 where available eg seg_full may be 7.3 (level 5) and 7.3.1 (level 6) where seg is 7 @col=Hash.new('') @col[:ocn]='' @counter={} sql='SELECT MAX(lid) FROM documents' @col[:lid]=@conn.execute( sql ) { |x| x.fetch_all.to_s.to_i } @col[:lid] ||=0 sql='SELECT MAX(nid) FROM endnotes' @id_n=@conn.execute( sql ) { |x| x.fetch_all.to_s.to_i } @id_n ||=0 @col[:lv1]=@col[:lv2]=@col[:lv3]=@col[:lv4]=@col[:lv5]=@col[:lv6]=0 @db=SiSU_Env::Info_db.new @@dl ||=SiSU_Env::Info_env.new.digest.length end def marshal_load require "#{SiSU_lib}/dal" @dal_array=SiSU_DAL::Source.new(@opt).get # dal file drawn here #@dal_array.each { |x| puts x.inspect; sleep 1 } tell=SiSU_Screen::Ansi.new(@opt.cmd,"#{@db.db_psql}::#{@opt.fns}") tell.puts_blue unless @opt.cmd =~/q/ tell=SiSU_Screen::Ansi.new(@opt.cmd,'Marshal Load',@fnm) tell.print_grey if @opt.cmd =~/v/ case @sql_type when /sqlite/ #fix logic for sqlite ! import_db_metadata(@dal_array) import_documents(@dal_array) import_db_urls(@dal_array,@fnm) #import OID on/off @conn.commit #sqlite watch else file_exist=@conn.select_one(%{ SELECT metadata.tid FROM metadata WHERE metadata.filename ~ '#{@opt.fns}'; }) unless file_exist @conn.execute('BEGIN') import_db_metadata(@dal_array) import_documents(@dal_array) import_db_urls(@dal_array,@fnm) #import OID on/off @conn.execute('COMMIT') else @db=SiSU_Env::Info_db.new puts "\n#{@cX.grey}file #{@cX.off} #{@cX.blue}#{@opt.fns}#{@cX.off} #{@cX.grey}already exists in database#{@cX.off} #{@cX.blue}#{@db.db_psql}#{@cX.off} #{@cX.brown}update instead?#{@cX.off}" end end end def special_character_escape(string) string.gsub!(/'/,"''") string.gsub!(/<:br>/,"
\n") string.gsub!(/<:(?:code|alt|group|verse)(?:-end)?>/,'') string.gsub!(/<:name#\S+?>/,'') string.gsub!(/\{\s*(\S+?\.(?:png|jpg))(?:\s+\d+x\d+)?(.+?)\}\S+/,'[image: \1] \2') string.gsub!(/\{\s*(.+?)\s*\}http:\/\/\S+?([.,!?]?(?:\s|$))/,'\1\2') end def unicode_special_character_escape(string) #string.gsub!(/(["';:,])/, %{\\\\\\1}) end def strip_markup(string) #define rules, make same as in dal clean string.gsub!(/(\d+)<\/sup>/,'[\1]') string.gsub!(/<:i[12]>/,'') string.gsub!(/(?: \\;)+/,' ') string.gsub!(//,"[TABLE]\n") #tables string.gsub!(//,'\1') #tables string.gsub!(/¡¡\d+¡/,' ') #tables string.gsub!(/¡/,' ') #tables tidy later string.gsub!(/<.+?>/,'') string.gsub!(/\{.+?\.(?:png|jpg|gif).+?\}(?:https?|ftp)\\\:\S+ /,' [image] ') # else image names found in search string.gsub!(/\s\s+/,' ') string.strip! end #% import into database tables def import_db_metadata(dbi_unit) #% import documents - populate database print %{ #{@cX.grey}import documents dbi_unit #{@cX.off} } unless @opt.cmd =~/q/ @tp={} @md=SiSU_Param::Parameters.new(@opt).get if @md.title; @tp[:title]=@md.title special_character_escape(@tp[:title]) @tp[:title_f],@tp[:title_i]='title, ',"'#{@tp[:title]}', " sql="SELECT MAX(tid) FROM metadata" id_t=@conn.execute( sql ) { |x| x.fetch_all.to_s.to_i } @@id_t=id_t if id_t @@id_t ||=0 @@id_t+=1 #bug related, needs to be performed once at start of file, but consider moving, as, placed here it means program will fail if document header lacks 0~title puts %{\n#{@cX.grey}Processing file number#{@cX.off}: #{@cX.green}#{@@id_t}#{@@cX.off}} unless @opt.cmd =~/q/ end if @md.dc_title; @tp[:long_title]=@md.dc_title #sql="SELECT MAX(tid) FROM metadata" #id_t=@conn.execute( sql ) { |x| x.fetch_all.to_s.to_i } #@@id_t=id_t if id_t #@@id_t ||=0 #@@id_t+=1 #bug related, needs to be performed once at start of file, but consider moving, as, placed here it means program will fail if document header lacks 0~title #puts %{\n#{@cX.grey}Processing file number#{@cX.off}: #{@cX.green}#{@@id_t}#{@@cX.off}} end if @md.subtitle; @tp[:subtitle]=@md.subtitle special_character_escape(@tp[:subtitle]) @tp[:subtitle_f],@tp[:subtitle_i]='subtitle, ',"'#{@tp[:subtitle]}', " end if @md.dc_creator; @tp[:creator]=@md.dc_creator special_character_escape(@tp[:creator]) @tp[:creator_f],@tp[:creator_i]='creator, ',"'#{@tp[:creator]}', " end if @md.dc_contributor; @tp[:contributor]=@md.dc_contributor special_character_escape(@tp[:contributor]) @tp[:contributor_f],@tp[:contributor_i]='contributor, ',"'#{@tp[:contributor]}', " end if @md.translator; @tp[:translator]=@md.translator special_character_escape(@tp[:translator]) @tp[:translator_f],@tp[:translator_i]='translator, ',"'#{@tp[:translator]}', " end if @md.illustrator; @tp[:illustrator]=@md.illustrator special_character_escape(@tp[:illustrator]) @tp[:illustrator_f],@tp[:illustrator_i]='illustrator, ',"'#{@tp[:illustrator]}', " end if @md.dc_publisher; @tp[:publisher]=@md.dc_publisher special_character_escape(@tp[:publisher]) @tp[:publisher_f],@tp[:publisher_i]='publisher, ',"'#{@tp[:publisher]}', " end if @md.prepared_by; @tp[:prepared_by]=@md.prepared_by special_character_escape(@tp[:prepared_by]) @tp[:prepared_by_f],@tp[:prepared_by_i]='prepared_by, ',"'#{@tp[:prepared_by]}', " end if @md.digitized_by; @tp[:digitized_by]=@md.digitized_by special_character_escape(@tp[:digitized_by]) @tp[:digitized_by_f],@tp[:digitized_by_i]='digitized_by, ',"'#{@tp[:digitized_by]}', " end if @md.dc_subject; @tp[:subject]=@md.dc_subject special_character_escape(@tp[:subject]) @tp[:subject_f],@tp[:subject_i]='subject, ',"'#{@tp[:subject]}', " end if @md.dc_description; @tp[:description]=@md.dc_description special_character_escape(@tp[:description]) @tp[:description_f],@tp[:description_i]='description, ',"'#{@tp[:description]}', " end if @md.abstract; @tp[:abstract]=@md.abstract special_character_escape(@tp[:abstract]) @tp[:abstract_f],@tp[:abstract_i]='abstract, ',"'#{@tp[:abstract]}', " end if @md.dc_type; @tp[:type]=@md.dc_type special_character_escape(@tp[:type]) @tp[:type_f],@tp[:type_i]='type, ',"'#{@tp[:type]}', " end #if @md.owner; @tp[:owner]=@md.owner # special_character_escape(@tp[:owner]) # @tp[:owner_f],@tp[:owner_i]='owner, ',"'#{@tp[:owner}', " #end #if @md.copyright; @tp[:copyright]=@md.copyright # special_character_escape(@tp[:copyright]) # @tp[:copyright_f],@tp[:copyright_i]='copyright, ',"'#{@tp[:copyright]}', " #end if @md.dc_rights; @tp[:rights]=@md.dc_rights special_character_escape(@tp[:rights]) @tp[:rights_f],@tp[:rights_i]='rights, ',"'#{@tp[:rights]}', " end if @md.dc_date; @tp[:date]=@md.dc_date special_character_escape(@tp[:date]) @tp[:date_f],@tp[:date_i]='date, ',"'#{@tp[:date]}', " end if @md.dc_date_created; @tp[:date_created]=@md.dc_date_created special_character_escape(@tp[:date_created]) @tp[:date_created_f],@tp[:date_created_i]='date_created, ',"'#{@tp[:date_created]}', " end if @md.dc_date_issued; @tp[:date_issued]=@md.dc_date_issued special_character_escape(@tp[:date_issued]) @tp[:date_issued_f],@tp[:date_issued_i]='date_issued, ',"'#{@tp[:date_issued]}', " end if @md.dc_date_available; @tp[:date_available]=@md.dc_date_available special_character_escape(@tp[:date_available]) @tp[:date_available_f],@tp[:date_available_i]='date_available, ',"'#{@tp[:date_available]}', " end if @md.dc_date_modified; @tp[:date_modified]=@md.dc_date_modified special_character_escape(@tp[:date_modified]) @tp[:date_modified_f],@tp[:date_modified_i]='date_modified, ',"'#{@tp[:date_modified]}', " end if @md.dc_date_valid; @tp[:date_valid]=@md.dc_date_valid special_character_escape(@tp[:date_valid]) @tp[:date_valid_f],@tp[:date_valid_i]='date_valid, ',"'#{@tp[:date_valid]}', " end if @md.dc_language[:name]; @tp[:language]=@md.dc_language[:name] special_character_escape(@tp[:language]) @tp[:language_f],@tp[:language_i]='language, ',"'#{@tp[:language]}', " end if @md.language_original[:name]; @tp[:language_original]=@md.language_original[:name] special_character_escape(@tp[:language_original]) @tp[:language_original_f],@tp[:language_original_i]='language_original, ',"'#{@tp[:language_original]}', " end if @md.dc_format; @tp[:format]=@md.dc_format special_character_escape(@tp[:format]) @tp[:format_f],@tp[:format_i]='format, ',"'#{@tp[:format]}', " end if @md.dc_identifier; @tp[:identifier]=@md.dc_identifier special_character_escape(@tp[:identifier]) @tp[:identifier_f],@tp[:identifier_i]='identifier, ',"'#{@tp[:identifier]}', " end if @md.dc_source; @tp[:source]=@md.dc_source special_character_escape(@tp[:source]) @tp[:source_f],@tp[:source_i]='source, ',"'#{@tp[:source]}', " end if @md.dc_relation; @tp[:relation]=@md.dc_relation special_character_escape(@tp[:relation]) @tp[:relation_f],@tp[:relation_i]='relation, ',"'#{@tp[:relation]}', " end if @md.dc_coverage; @tp[:coverage]=@md.dc_coverage special_character_escape(@tp[:coverage]) @tp[:coverage_f],@tp[:coverage_i]='coverage, ',"'#{@tp[:coverage]}', " end if @md.keywords; @tp[:keywords]=@md.keywords special_character_escape(@tp[:keywords]) @tp[:keywords_f],@tp[:keywords_i]='keywords, ',"'#{@tp[:keywords]}', " end if @md.comments; @tp[:comments]=@md.comments special_character_escape(@tp[:comments]) @tp[:comments_f],@tp[:comments_i]='comments, ',"'#{@tp[:comments]}', " end if @md.cls_loc; @tp[:cls_loc]=@md.cls_loc special_character_escape(@tp[:cls_loc]) @tp[:cls_loc_f],@tp[:cls_loc_i]='cls_loc, ',"'#{@tp[:cls_loc]}', " end if @md.cls_dewey; @tp[:cls_dewey]=@md.cls_dewey special_character_escape(@tp[:cls_dewey]) @tp[:cls_dewey_f],@tp[:cls_dewey_i]='cls_dewey, ',"'#{@tp[:cls_dewey]}', " end if @md.cls_pg; @tp[:cls_pg]=@md.cls_pg special_character_escape(@tp[:cls_pg]) @tp[:cls_pg_f],@tp[:cls_pg_i]='cls_pg, ',"'#{@tp[:cls_pg]}', " end if @md.cls_isbn; @tp[:cls_isbn]=@md.cls_isbn special_character_escape(@tp[:cls_isbn]) @tp[:cls_isbn_f],@tp[:cls_isbn_i]='cls_isbn, ',"'#{@tp[:cls_isbn]}', " end if @md.prefix_a; @tp[:prefix_a]=@md.prefix_a special_character_escape(@tp[:prefix_a]) @tp[:prefix_a_f],@tp[:prefix_a_i]='prefix_a, ',"'#{@tp[:prefix_a]}', " end if @md.prefix_b; @tp[:prefix_b]=@md.prefix_b special_character_escape(@tp[:prefix_b]) @tp[:prefix_b_f],@tp[:prefix_b_i]='prefix_b, ',"'#{@tp[:prefix_b]}', " end #if @md.suffix; @tp[:suffix]=@md.suffix # special_character_escape(@tp[:suffix]) # @tp[:suffix_f],@tp[:suffix_i]='suffix, ',"'#{@tp[:suffix]}', " #end if @md.fns; @tp[:fns]=@md.fns special_character_escape(@tp[:fns]) @tp[:fns_f],@tp[:fns_i]="filename, ","'#{@tp[:fns]}', " end #if @md.en[:mismatch] > 0 # id,info='WARNING document error in endnote markup, number mismatch',"endnotes: #{@md.en[:note]} != endnote reference marks: #{@md.en[:mark]} (difference = #{@md.en[:mismatch]})" #end if @md.wc_words; @tp[:wc_words]=@md.wc_words @tp[:wc_words_f],@tp[:wc_words_i]='wc_words, ',"'#{@tp[:wc_words]}', " end if @md.dgst; @tp[:dgst]=@md.dgst @tp[:dgst_f],@tp[:dgst_i]='dgst, ',"'#{@tp[:dgst]}', " end if @md.sc_number; @tp[:sc_number]=@md.sc_number @tp[:sc_number_f],@tp[:sc_number_i]='sc_number, ',"'#{@tp[:sc_number]}', " end if @md.sc_date; @tp[:sc_date]=@md.sc_date @tp[:sc_date_f],@tp[:sc_date_i]='sc_date, ',"'#{@tp[:sc_date]}', " end if @md.generated; @tp[:generated]=@md.generated @tp[:generated_f],@tp[:generated_i]='generated, ',"'#{@tp[:generated]}', " end #if @md.sisu_version; special_character_escape(@md.sisu_version) # #id,info='Generated by',"#{@md.sisu_version[:project]} #{@md.sisu_version[:version]} #{@md.sisu_version[:date_stamp]} (#{@md.sisu_version[:date]})" #end #if @md.ruby_version; special_character_escape(@md.ruby_version) SiSU_DB::Test.new(self,@opt).verify #% import title names, filenames (tuple) @conn.execute(%{ INSERT INTO metadata (#{@tp[:fns_f]} #{@tp[:suffix_f]} #{@tp[:title_f]} #{@tp[:subtitle_f]} #{@tp[:creator_f]} #{@tp[:illustrator_f]} #{@tp[:translator_f]} #{@tp[:subject_f]} #{@tp[:description_f]} #{@tp[:publisher_f]} #{@tp[:contributor_f]} #{@tp[:prepared_by_f]} #{@tp[:digitized_by_f]} #{@tp[:date_f]} #{@tp[:date_created_f]} #{@tp[:date_issued_f]} #{@tp[:date_valid_f]} #{@tp[:date_available_f]} #{@tp[:date_modified_f]} #{@tp[:type_f]} #{@tp[:format_f]} #{@tp[:identifier_f]} #{@tp[:source_f]} #{@tp[:language_f]} #{@tp[:language_original_f]} #{@tp[:relation_f]} #{@tp[:coverage_f]} #{@tp[:rights_f]} #{@tp[:copyright_f]} #{@tp[:owner_f]} #{@tp[:keywords_f]} #{@tp[:abstract_f]} #{@tp[:comment_f]} #{@tp[:loc_f]} #{@tp[:dewey_f]} #{@tp[:isbn_f]} #{@tp[:pg_f]} #{@tp[:prefix_a_f]} #{@tp[:prefix_b_f]} tid) VALUES (#{@tp[:fns_i]} #{@tp[:suffix_i]} #{@tp[:title_i]} #{@tp[:subtitle_i]} #{@tp[:creator_i]} #{@tp[:illustrator_i]} #{@tp[:translator_i]} #{@tp[:subject_i]} #{@tp[:description_i]} #{@tp[:publisher_i]} #{@tp[:contributor_i]} #{@tp[:prepared_by_i]} #{@tp[:digitized_by_i]} #{@tp[:date_i]} #{@tp[:date_created_i]} #{@tp[:date_issued_i]} #{@tp[:date_valid_i]} #{@tp[:date_available_i]} #{@tp[:date_modified_i]} #{@tp[:type_i]} #{@tp[:format_i]} #{@tp[:identifier_i]} #{@tp[:source_i]} #{@tp[:language_i]} #{@tp[:language_original_i]} #{@tp[:relation_i]} #{@tp[:coverage_i]} #{@tp[:rights_i]} #{@tp[:copyright_i]} #{@tp[:owner_i]} #{@tp[:keywords_i]} #{@tp[:abstract_i]} #{@tp[:comment_i]} #{@tp[:loc_i]} #{@tp[:dewey_i]} #{@tp[:isbn_i]} #{@tp[:pg_i]} #{@tp[:prefix_a_i]} #{@tp[:prefix_b_i]} #{@@id_t}); }) end def import_documents(dbi_unit) #% import documents - populate main database table #% import into substantive database tables (tuple) begin @col[:tid]=@@id_t @en,@en_ast,@en_pls=[],[],[] @col[:en_a]=nil @col[:en_z]=nil dbi_unit.each do |data| #data.gsub!(/<[biu]>(.+?)<\/[biu]>/,'\1') # remove bold, italics, underscore data.gsub!(/(.+?)<\/b>/,'\1') # remove bold, italics, underscore data.gsub!(/(.+?)<\/i>/,'\1') # remove bold, italics, underscore data.gsub!(/(.+?)<\/u>/,'\1') # remove bold, italics, underscore #data.gsub!(/<:name#\S+?>/,'') @col[:seg]=@@seg if data =~/<~\d+;(?:\w|[0-6]:)\d+;\w\d+><[0-9a-f]{#{@@dl}}:[0-9a-f]{#{@@dl}}>/m # regular text notedata=data.dup if data[/^([123])~\s+(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/] @col[:lev],txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6,$7 @col[:lid]+=1 if txt =~/~\{.+?\}~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en << txt.scan(/~\{(\d+).+?\}~/) txt.gsub!(/~\{(\d+).+?\}~/,'\1') end if txt =~/~\[\*.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_ast << txt.scan(/~\[[*](\d+).+?\]~/) txt.gsub!(/~\[([*]\d+).+?\]~/,'\1') end if txt =~/~\[\+.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_pls << txt.scan(/~\[[+](\d+).+?\]~/) txt.gsub!(/~\[([+]\d+).+?\]~/,'\1') end @col[:body]=SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:lev]).lev4_minus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup strip_markup(@col[:plaintext]) if @en[0]; @en_a,@en_z=@en[0].first,@en[0].last end if @en_ast[0]; @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last end if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_tuple.new(@conn,@col,@opt) t.tuple case @col[:lev] when /1/; @col[:lv1]+=1 when /2/; @col[:lv2]+=1 when /3/; @col[:lv3]+=1 end @col[:lev]=@col[:plaintext]=@col[:body]='' elsif data[/^4~(.+?)\s+(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/] @@seg,txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6,$7 @col[:seg]=@@seg @col[:lv4]+=1 @col[:lid]+=1 @col[:lev]=4 if txt =~ /~\{.+?\}~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en << txt.scan(/~\{(\d+).+?\}~/) txt.gsub!(/~\{(\d+).+?\}~/,'\1') end if txt =~/~\[\*.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_ast << txt.scan(/~\[[*](\d+).+?\]~/) txt.gsub!(/~\[([*]\d+).+?\]~/,'\1') end if txt =~/~\[\+.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_pls << txt.scan(/~\[[+](\d+).+?\]~/) txt.gsub!(/~\[([+]\d+).+?\]~/,'\1') end @col[:body]=SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:lev],@col[:seg]).lev4_plus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup strip_markup(@col[:plaintext]) if @en[0]; @en_a,@en_z=@en[0].first,@en[0].last end if @en_ast[0]; @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last end if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_tuple.new(@conn,@col,@opt) t.tuple @col[:lev]=@col[:plaintext]=@col[:body]='' elsif data[/^5~(?:~\S+)?(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/] # header lev5 seg level txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6 re=/^5~(.+?)\s+/ @@seg_full=re.match(data)[1] if data=~re #create? @@seg ||='' #nil # watch @col[:seg]=@@seg @col[:lv5]+=1 @col[:lid]+=1 @col[:lev]=5 if txt =~ /~\{.+?\}~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en << txt.scan(/~\{(\d+).+?\}~/) txt.gsub!(/~\{(\d+).+?\}~/,'\1') end if txt =~/~\[\*.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_ast << txt.scan(/~\[[*](\d+).+?\]~/) txt.gsub!(/~\[([*]\d+).+?\]~/,'\1') end if txt =~/~\[\+.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_pls << txt.scan(/~\[[+](\d+).+?\]~/) txt.gsub!(/~\[([+]\d+).+?\]~/,'\1') end @col[:body]=SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:lev],@col[:seg]).lev4_plus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup strip_markup(@col[:plaintext]) if @en[0]; @en_a,@en_z=@en[0].first,@en[0].last end if @en_ast[0]; @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last end if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_tuple.new(@conn,@col,@opt) t.tuple @col[:lev]=@col[:plaintext]=@col[:body]='' elsif data[/^6~(?:~\S+)?(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/] # header lev6 seg level txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=$1,$2,$3,$4,$5,$6 re=/^6~(.+?)\s+/ @@seg_full=re.match(data)[1] if data=~re #create? @@seg ||='' #nil # watch @col[:seg]=@@seg @col[:lv6]+=1 @col[:lid]+=1 @col[:lev]=6 if txt =~ /~\{.+?\}~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en << txt.scan(/~\{(\d+).+?\}~/) txt.gsub!(/~\{(\d+).+?\}~/,'\1') end if txt =~/~\[\*.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_ast << txt.scan(/~\[[*](\d+).+?\]~/) txt.gsub!(/~\[([*]\d+).+?\]~/,'\1') end if txt =~/~\[\+.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_pls << txt.scan(/~\[[+](\d+).+?\]~/) txt.gsub!(/~\[([+]\d+).+?\]~/,'\1') end @col[:body]=SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:lev],@col[:seg]).lev4_plus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup strip_markup(@col[:plaintext]) if @en[0]; @en_a,@en_z=@en[0].first,@en[0].last end if @en_ast[0]; @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last end if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end t=SiSU_DB_tuple::Load_tuple.new(@conn,@col,@opt) t.tuple @col[:lev]=@col[:plaintext]=@col[:body]='' else #% regular text @col[:lid]+=1 txt='' txt,@col[:ocn],@col[:ocnd],@col[:ocns],@col[:digest_clean],@col[:digest_all]=(/(.+?)<~(\d+);((?:\w|[0-6]:)\d+);(\w\d+)><([0-9a-f]{#{@@dl}}):([0-9a-f]{#{@@dl}})>/m).match(data).captures if txt =~ /~\{.+?\}~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en << txt.scan(/~\{(\d+).+?\}~/) txt.gsub!(/~\{(\d+).+?\}~/,'\1') #txt.gsub!(/~\{(\d+).+?\}~/,'^[\1]') # remove endnote, keep endnote reference number, display as, e.g. [^1] end if txt =~/~\[\*.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_ast << txt.scan(/~\[[*](\d+).+?\]~/) txt.gsub!(/~\[([*]\d+).+?\]~/,'\1') end if txt =~/~\[\+.+?\]~/ word_mode=txt.scan(/\S+/) endnote_range(word_mode) @en_pls << txt.scan(/~\[[+](\d+).+?\]~/) txt.gsub!(/~\[([+]\d+).+?\]~/,'\1') end if @sql_type=~/pg/ and txt.size > (document_clean - 1) #% examine pg build & remove limitation puts "\n\nTOO LARGE (TXT - see error log)\n\n" open("#{Dir.pwd}/pg_documents_error_log",'a') do |error| error.puts("\n#{@opt.fns}\nTEXT BODY\n#{@col[:body].size} object #{@col[:ocn]} -> #{@col[:body].slice(0..500)}") end txt=%{\n\nLARGE TEXT BLOCK OMITTED\n\n} end if @en[0]; @en_a,@en_z=@en[0].first,@en[0].last end if @en_ast[0]; @en_a_asterisk,@en_z_asterisk=@en_ast[0].first,@en_ast[0].last end if @en_pls[0]; @en_a_plus,@en_z_plus=@en_pls[0].first,@en_pls[0].last end @col[:body]=if txt=~// #watch SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns]).html_table elsif txt=~/<:i1>/ SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns]).indent1 elsif txt=~/<:i2>/ SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns]).indent2 else SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns]).norm end special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup strip_markup(@col[:plaintext]) t=SiSU_DB_tuple::Load_tuple.new(@conn,@col,@opt) t.tuple @en,@en_ast,@en_pls=[],[],[] @col[:en_a]=@col[:en_z]=nil @col[:lev]=@col[:plaintext]=@col[:body]='' end if notedata =~ /~\{.+?\}~/ #% import into database endnotes tables endnote_array=notedata.scan(/~\{.+?\}~/) endnote_array.each do |inf| if inf[/~\{\d+.+?<[0-9a-f]{#{@@dl}}>\}~/] # dal new endnotes 2003w31/1 if inf[/~\{(\d+)(.+?)<([0-9a-f]{#{@@dl}})>\}~/] # dal new endnotes 2003w31/1 en,txt,digest_clean=$1,$2,$3 end @id_n+=1 body=SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns],en).endnote special_character_escape(body) special_character_escape(txt) strip_markup(txt) if txt.size > (endnote_clean - 1) puts "\n\nTOO LARGE (ENDNOTE - see error log)\n\n" open("#{Dir.pwd}/pg_documents_error_log",'a') do |error| error.puts("\n#{@opt.fns}\nENDNOTE\n#{txt.size} object #{@col[:ocn]},#{@col[:ocnd]},#{@col[:ocns]} -> #{txt.slice(0..500)}") end txt=%{\n\nLARGE TEXT BLOCK OMITTED\n\n} end if txt #puts "'#{@id_n}', '#{@col[:lid]}', '#{en}', '#{txt}', '#{body}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@@id_t}'" #% endnotes @conn.execute(%{ INSERT INTO endnotes (nid, document_lid, nr, clean, body, ocn, ocnd, ocns, metadata_tid, digest_clean) VALUES ('#{@id_n}', '#{@col[:lid]}', '#{en}', '#{txt}', '#{body}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@@id_t}', '#{digest_clean}'); }) end end end word_mode=notedata.scan(/\S+/) end if notedata =~ /~\[\*.+?\]~/ #% import into database endnotes tables endnote_array=notedata.scan(/~\[\*.+?\]~/) endnote_array.each do |inf| if inf[/~\[\*\d+.+?<[0-9a-f]{#{@@dl}}>\]~/] # dal new endnotes 2003w31/1 if inf[/~\[[*](\d+)(.+?)<([0-9a-f]{#{@@dl}})>\]~/] # dal new endnotes 2003w31/1 en,txt,digest_clean=$1,$2,$3 end @id_n+=1 body=SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns],en).endnote special_character_escape(body) special_character_escape(txt) strip_markup(txt) if txt.size > (endnote_clean - 1) puts "\n\nTOO LARGE (ENDNOTE - see error log)\n\n" open("#{Dir.pwd}/pg_documents_error_log",'a') do |error| error.puts("\n#{@opt.fns}\nENDNOTE\n#{txt.size} object #{@col[:ocn]},#{@col[:ocnd]},#{@col[:ocns]} -> #{txt.slice(0..500)}") end txt=%{\n\nLARGE TEXT BLOCK OMITTED\n\n} end if txt #puts "'#{@id_n}', '#{@col[:lid]}', '#{en}', '#{txt}', '#{body}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@@id_t}'" #% endnotes @conn.execute(%{ INSERT INTO endnotes_asterisk (nid, document_lid, nr, clean, body, ocn, ocnd, ocns, metadata_tid, digest_clean) VALUES ('#{@id_n}', '#{@col[:lid]}', '#{en}', '#{txt}', '#{body}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@@id_t}', '#{digest_clean}'); }) end end end word_mode=notedata.scan(/\S+/) end if notedata =~ /~\[\+.+?\]~/ #% import into database endnotes tables endnote_array=notedata.scan(/~\[\+.+?\]~/) endnote_array.each do |inf| if inf[/~\[\+\d+.+?<[0-9a-f]{#{@@dl}}>\]~/] # dal new endnotes 2003w31/1 if inf[/~\[[+](\d+)(.+?)<([0-9a-f]{#{@@dl}})>\]~/] # dal new endnotes 2003w31/1 en,txt,digest_clean=$1,$2,$3 end @id_n+=1 body=SiSU_Format_Shared::CSS_Format.new(txt,@col[:ocn],@col[:ocnd],@col[:ocns],en).endnote special_character_escape(body) special_character_escape(txt) strip_markup(txt) if txt.size > (endnote_clean - 1) puts "\n\nTOO LARGE (ENDNOTE - see error log)\n\n" open("#{Dir.pwd}/pg_documents_error_log",'a') do |error| error.puts("\n#{@opt.fns}\nENDNOTE\n#{txt.size} object #{@col[:ocn]},#{@col[:ocnd]},#{@col[:ocns]} -> #{txt.slice(0..500)}") end txt=%{\n\nLARGE TEXT BLOCK OMITTED\n\n} end if txt #puts "'#{@id_n}', '#{@col[:lid]}', '#{en}', '#{txt}', '#{body}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@@id_t}'" #% endnotes @conn.execute(%{ INSERT INTO endnotes_plus (nid, document_lid, nr, clean, body, ocn, ocnd, ocns, metadata_tid, digest_clean) VALUES ('#{@id_n}', '#{@col[:lid]}', '#{en}', '#{txt}', '#{body}', '#{@col[:ocn]}', '#{@col[:ocnd]}', '#{@col[:ocns]}', '#{@@id_t}', '#{digest_clean}'); }) end end end word_mode=notedata.scan(/\S+/) end end end rescue; SiSU_Errors::Info_error.new($!,$@,@opt.cmd,@opt.fns).error ensure end end def endnote_range(word_array) @col[:en_a]=@col[:en_z]=nil word_array.each do |w| if w[/~[{\[][*+]?(\d+)\s+.+?[}\]]~/] # not tested since change 2003w31 @col[:en_a]=$1 unless @col[:en_a] @col[:en_z]=@col[:en_a].dup unless @col[:en_a] @col[:en_z]=$1 if @col[:en_a] end end end def import_db_urls(dbi_unit,meta) #% import documents OID - populate database begin @fnm=meta @env=SiSU_Env::Info_env.new(@opt.fns) base=@env.url.root out=@env.path.output markup,meta,latex,plaintext,html_toc,html_doc,xml_sax,xml_dom,pdf_p,pdf_l,concordance,sisupod='','','','','','','','','','','','' markup_li,meta_li,latex_li,plaintext_li,html_li,xml_sax_li,xml_dom_li,pdf_p_li,pdf_l_li,concordance_li,sisupod_li='','','','','','','','','','','' if @fnb.empty? or @fnb.nil?; p 'file output path error' #remove end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:plain]}")==true) plaintext,plaintext_li='plaintext,', "'#{base}/#@fnb/#{@md.fn[:plain]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:toc]}")==true) html_toc,html_toc_li='html_toc,', "'#{base}/#@fnb/#{@md.fn[:toc]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:doc]}")==true) html_doc,html_doc_li='html_doc,', "'#{base}/#@fnb/#{@md.fn[:doc]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:xhtml]}")==true) xhtml,xhtml_li='xhtml,', "'#{base}/#@fnb/#{@md.fn[:xhtml]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:sax]}")==true) xml_sax,xml_sax_li='xml_sax,', "'#{base}/#@fnb/#{@md.fn[:sax]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:dom]}")==true) xml_dom,xml_dom_li='xml_dom,', "'#{base}/#@fnb/#{@md.fn[:dom]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:odf]}")==true) odf,odf_li='odf,', "'#{base}/#@fnb/#{@md.fn[:odf]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:pdf_p]}")==true) pdf_p,pdf_p_li='pdf_p,', "'#{base}/#@fnb/#{@md.fn[:pdf_p]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:pdf_l]}")==true) pdf_l,pdf_l_li='pdf_l,', "'#{base}/#@fnb/#{@md.fn[:pdf_l]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:concordance]}")==true) concordance,concordance_li='concordance,', "'#{base}/#@fnb/#{@md.fn[:concordance]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@opt.fns}.tex")==true) latex_p,latex_p_li='latex_p,', "'#{base}/#@fnb/#{@opt.fns}.tex'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@opt.fns}.landscape.tex")==true) latex_l,latex_l_li='latex_l,', "'#{base}/#@fnb/#@opt.fns}.landscape.tex'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:digest]}")==true) digest,digest_li='digest,', "'#{base}/#@fnb/#{@md.fn[:digest]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@md.fn[:manifest]}")==true) #revisit, was to be text, this is html manifest,manifest_li='manifest,', "'#{base}/#@fnb/#{@md.fn[:manifest]}'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@opt.fns}.meta")==true) markup,markup_li='markup,', "'#{base}/#@fnb/#{@opt.fns}.meta'," end if @opt.cmd !~/e/ or (@opt.cmd=~/e/ and FileTest.file?("#{out}/#@fnb/#{@opt.fns}.tgz")==true) sisupod,sisupod_li='sisupod,', "'#{base}/#@fnb/#{@opt.fns}.tgz'," end @conn.execute(%{ INSERT INTO urls (#{plaintext} #{html_toc} #{html_doc} #{xhtml} #{xml_sax} #{xml_dom} #{odf} #{pdf_p} #{pdf_l} #{concordance} #{latex_p} #{latex_l} #{manifest} #{digest} #{markup} #{sisupod} metadata_tid) VALUES (#{plaintext_li} #{html_toc_li} #{html_doc_li} #{xhtml_li} #{xml_sax_li} #{xml_dom_li} #{odf_li} #{pdf_p_li} #{pdf_l_li} #{concordance_li} #{latex_p_li} #{latex_l_li} #{manifest_li} #{digest_li} #{markup_li} #{sisupod_li} #{@@id_t}); }) rescue; SiSU_Errors::Info_error.new($!,$@,@opt.cmd,@opt.fns).error ensure end end end end __END__