From aa47d1db8596aa65746db05d369441d1def62aa4 Mon Sep 17 00:00:00 2001 From: Ralph Amissah Date: Fri, 16 Apr 2010 10:12:46 -0400 Subject: db sql table and column structure changes, name prefix "sisu_v2a_" resulting sisu version bump 2.1.0, plus other lesser fixes [Note: it is necessary to create new database and tables and to populate them] * db (sql) database table name and column structure changes, new pgsql db name prefix "sisu_v2a_" (version bump), continue to review (db_columns, db_create, db_import, db_sqltxt) * db remove and update fix, match filename for removal with = (not LIKE or ~) * db sqlite, issue with --recreate, bugfix (db_drop) --- lib/sisu/v2/db_import.rb | 321 ++++++----------------------------------------- 1 file changed, 40 insertions(+), 281 deletions(-) (limited to 'lib/sisu/v2/db_import.rb') diff --git a/lib/sisu/v2/db_import.rb b/lib/sisu/v2/db_import.rb index 1f795e68..5610a1d0 100644 --- a/lib/sisu/v2/db_import.rb +++ b/lib/sisu/v2/db_import.rb @@ -60,9 +60,10 @@ module SiSU_DB_import require "#{SiSU_lib}/db_columns" # db_columns.rb require "#{SiSU_lib}/db_load_tuple" # db_load_tuple.rb + require "#{SiSU_lib}/db_sqltxt" # db_sqltxt.rb require "#{SiSU_lib}/shared_html_lite" # shared_html_lite.rb require 'sqlite3' - class Import < SiSU_DB_columns::Column_size + class Import < SiSU_DB_text::Prepare include SiSU_Param include SiSU_Screen @@dl=nil @@ -86,7 +87,7 @@ module SiSU_DB_import @counter={} @db=SiSU_Env::Info_db.new @driver_sqlite3=(@conn.inspect.match(/^(.{10})/)[1]==@db.sqlite.conn_sqlite3.inspect.match(/^(.{10})/)[1]) ? true : false - sql='SELECT MAX(lid) FROM documents' + sql='SELECT MAX(lid) FROM doc_objects' begin @col[:lid] ||=0 @col[:lid]=if @driver_sqlite3 @@ -122,7 +123,7 @@ module SiSU_DB_import tell.print_grey if @opt.cmd =~/v/ file_exist=if @sql_type=~/sqlite/; nil else - @conn.select_one(%{ SELECT metadata.tid FROM metadata WHERE metadata.filename ~ '#{@opt.fns}'; }) + @conn.select_one(%{ SELECT metadata_and_text.tid FROM metadata_and_text WHERE metadata_and_text.filename = '#{@opt.fns}'; }) end if (@sql_type!~/sqlite/ and not file_exist) \ or @sql_type=~/sqlite/ @@ -192,28 +193,6 @@ module SiSU_DB_import end end end - def special_character_escape(str) - str.gsub!(/'/,"''") #string.gsub!(/'/,"\047") #string.gsub!(/'/,"\\'") - str.gsub!(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,"
\n") - str.gsub!(/#{Mx[:tag_o]}\S+?#{Mx[:tag_c]}/,'') #check - str.gsub!(/#{Mx[:lnk_o]}\s*(\S+?\.(?:png|jpg))(?:\s+\d+x\d+)?(.+?)#{Mx[:lnk_c]}\S+/,'[image: \1] \2') - str.gsub!(/#{Mx[:lnk_o]}\s*(.+?)\s*#{Mx[:lnk_c]}(?:file|ftp):\/\/\S+?([.,!?]?(?:\s|$))/,'\1\2') - str.gsub!(/#{Mx[:lnk_o]}\s*(.+?)\s*#{Mx[:lnk_c]}#{Mx[:url_o]}\S+?#{Mx[:url_c]}/,'\1') - str - end - def strip_markup(str) #define rules, make same as in dal clean - str.gsub!(/#{Mx[:fa_superscript_o]}(\d+)#{Mx[:fa_superscript_c]}/,'[\1]') - str.gsub!(/(?: \\;|#{Mx[:nbsp]})+/,' ') - str.gsub!(/#{Mx[:tc_o]}#{Mx[:tc_p]}#{Mx[:tc_p]}\d+(.+)#{Mx[:tc_c]}/u,'\1') #tables - str.gsub!(/#{Mx[:tc_p]}#{Mx[:tc_p]}\d+#{Mx[:tc_p]}/u,' ') #tables - str.gsub!(/#{Mx[:tc_p]}/u,' ') #tables tidy later - str.gsub!(/<.+?>/,'') - str.gsub!(/#{Mx[:lnk_o]}.+?\.(?:png|jpg|gif).+?#{Mx[:lnk_c]}(?:file|ftp)\/\/:\S+ /,' [image] ') # else image names found in search - str.gsub!(/#{Mx[:lnk_o]}.+?\.(?:png|jpg|gif).+?#{Mx[:lnk_c]}#{Mx[:url_o]}\S+?#{Mx[:url_c]}/,' [image]') # else image names found in search - str.gsub!(/\s\s+/,' ') - str.strip! - str - end def pf_db_import_transaction_open end def pf_db_import_transaction_close @@ -222,12 +201,23 @@ module SiSU_DB_import print %{ #{@cX.grey}import documents dbi_unit #{@cX.off} } unless @opt.cmd =~/q/ @tp={} @md=SiSU_Param::Parameters.new(@opt).get +#% sisutxt & fulltxt + if FileTest.exist?(@md.fns) + txt_arr=IO.readlines(@md.fns,'') + src=txt_arr.join("\n") + src=special_character_escape(src) + @tp[:sisutxt_f],@tp[:sisutxt_i]='sisutxt, ',"'#{src}', " + txt=clean_searchable_text(txt_arr) + #special_character_escape(txt) + @tp[:fulltxt_f],@tp[:fulltxt_i]='fulltxt, ',"'#{txt}', " + end +#% title if defined? @md.title.full \ and @md.title.full=~/\S+/ # DublinCore 1 - title - @tp[:title]=@md.title.full - special_character_escape(@tp[:title]) - @tp[:title_f],@tp[:title_i]='title, ',"'#{@tp[:title]}', " - sql='SELECT MAX(tid) FROM metadata' + #@tp[:title]=@md.title.full + #special_character_escape(@tp[:title]) + #@tp[:title_f],@tp[:title_i]='title, ',"'#{@tp[:title]}', " + sql='SELECT MAX(tid) FROM metadata_and_text' begin @@id_t ||=0 id_t=if @driver_sqlite3 @@ -242,220 +232,9 @@ module SiSU_DB_import @@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 @title: puts %{\n#{@cX.grey}Processing file number#{@cX.off}: #{@cX.green}#{@@id_t}#{@@cX.off}} unless @opt.cmd =~/q/ end - if defined? @md.creator.author \ - and @md.creator.author=~/\S+/ # DublinCore 2 - creator/author (author) - txt=@md.creator.author #dc - special_character_escape(txt) - @tp[:creator_f],@tp[:creator_i]='creator, ',"'#{txt}', " - end - if defined? @md.creator.contributor \ - and @md.creator.contributor=~/\S+/ # DublinCore 6 - contributor - txt=@md.creator.contributor #dc - special_character_escape(txt) - @tp[:contributor_f],@tp[:contributor_i]='contributor, ',"'#{txt}', " - end - if defined? @md.creator.translator \ - and @md.creator.translator=~/\S+/ - txt=@md.creator.translator - special_character_escape(txt) - @tp[:translator_f],@tp[:translator_i]='translator, ',"'#{txt}', " - end - if defined? @md.creator.illustrator \ - and @md.creator.illustrator=~/\S+/ - txt=@md.creator.illustrator - special_character_escape(txt) - @tp[:illustrator_f],@tp[:illustrator_i]='illustrator, ',"'#{txt}', " - end - if defined? @md.publisher \ - and @md.publisher - txt=@md.publisher #dc - special_character_escape(txt) - @tp[:publisher_f],@tp[:publisher_i]='publisher, ',"'#{txt}', " - end - if defined? @md.creator.prepared_by \ - and @md.creator.prepared_by=~/\S+/ - txt=@md.creator.prepared_by - special_character_escape(txt) - @tp[:prepared_by_f],@tp[:prepared_by_i]='prepared_by, ',"'#{txt}', " - end - if defined? @md.creator.digitized_by \ - and @md.creator.digitized_by=~/\S+/ - txt=@md.creator.digitized_by - special_character_escape(txt) - @tp[:digitized_by_f],@tp[:digitized_by_i]='digitized_by, ',"'#{txt}', " - end - if defined? @md.classify.subject \ - and @md.classify.subject=~/\S+/ # DublinCore 3 - subject (us library of congress, eric or udc, or schema???) - txt=@md.classify.subject #dc - special_character_escape(txt) - @tp[:subject_f],@tp[:subject_i]='subject, ',"'#{txt}', " - end - if defined? @md.notes.description \ - and @md.notes.description=~/\S+/ # DublinCore 4 - description - txt=@md.notes.description #dc - special_character_escape(txt) - @tp[:description_f],@tp[:description_i]='description, ',"'#{txt}', " - end - if defined? @md.classify.subject \ - and @md.classify.subject=~/\S+/ # DublinCore 8 - type (genre eg. report, convention etc) - txt=@md.classify.abstract - special_character_escape(txt) - @tp[:abstract_f],@tp[:abstract_i]='abstract, ',"'#{txt}', " - end - if defined? @md.rights.all \ - and @md.rights.all=~/\S+/ # DublinCore 15 - rights - txt=@md.rights.all #dc - special_character_escape(txt) - @tp[:rights_f],@tp[:rights_i]='rights, ',"'#{txt}', " - end - if defined? @md.date.published \ - and @md.date.published=~/\S+/ # DublinCore 7 - date year-mm-dd - txt=@md.date.published #dc - special_character_escape(txt) - @tp[:date_f],@tp[:date_i]='date, ',"'#{txt}', " - end - if defined? @md.date.created \ - and @md.date.created=~/\S+/ - txt=@md.date.created #dc - special_character_escape(txt) - @tp[:date_created_f],@tp[:date_created_i]='date_created, ',"'#{txt}', " - end - if defined? @md.date.issued \ - and @md.date.issued=~/\S+/ - txt=@md.date.issued #dc - special_character_escape(txt) - @tp[:date_issued_f],@tp[:date_issued_i]='date_issued, ',"'#{txt}', " - end - if defined? @md.date.available \ - and @md.date.available=~/\S+/ - txt=@md.date.available #dc - special_character_escape(txt) - @tp[:date_available_f],@tp[:date_available_i]='date_available, ',"'#{txt}', " - end - if defined? @md.date.modified \ - and @md.date.modified=~/\S+/ - txt=@md.date.modified #dc - special_character_escape(txt) - @tp[:date_modified_f],@tp[:date_modified_i]='date_modified, ',"'#{txt}', " - end - if defined? @md.date.valid \ - and @md.date.valid=~/\S+/ - txt=@md.date.valid #dc - special_character_escape(txt) - @tp[:date_valid_f],@tp[:date_valid_i]='date_valid, ',"'#{txt}', " - end - if defined? @md.title.language \ - and @md.title.language=~/\S+/ - txt=@md.title.language - special_character_escape(txt) - @tp[:language_f],@tp[:language_i]='language, ',"'#{txt}', " - end - if defined? @md.original.language \ - and @md.original.language=~/\S+/ - txt=@md.original.language - special_character_escape(txt) - @tp[:language_original_f],@tp[:language_original_i]='language_original, ',"'#{txt}', " - end - if defined? @md.classify.format \ - and @md.classify.format=~/\S+/ # DublinCore 9 - format (use your mime type) - txt=@md.classify.format #dc - special_character_escape(txt) - @tp[:format_f],@tp[:format_i]='format, ',"'#{txt}', " - end - if defined? @md.classify.identifier \ - and @md.classify.identifier=~/\S+/ # DublinCore 10 - identifier (your identifier, could use urn which is free) - txt=@md.classify.identifier #dc - special_character_escape(txt) - @tp[:identifier_f],@tp[:identifier_i]='identifier, ',"'#{txt}', " - end - if defined? @md.original.source \ - and @md.original.source=~/\S+/ # DublinCore 11 - source (document source) - txt=@md.original.source #dc - special_character_escape(txt) - @tp[:source_f],@tp[:source_i]='source, ',"'#{txt}', " - end - if defined? @md.classify.relation \ - and @md.classify.relation=~/\S+/ # DublinCore 13 - relation - txt=@md.classify.relation #dc - special_character_escape(txt) - @tp[:relation_f],@tp[:relation_i]='relation, ',"'#{txt}', " - end - if defined? @md.classify.coverage \ - and @md.classify.coverage=~/\S+/ # DublinCore 14 - coverage - txt=@md.classify.coverage #dc - special_character_escape(txt) - @tp[:coverage_f],@tp[:coverage_i]='coverage, ',"'#{txt}', " - end - if defined? @md.classify.keywords \ - and @md.classify.keywords=~/\S+/ - txt=@md.classify.keywords - special_character_escape(txt) - @tp[:keywords_f],@tp[:keywords_i]='keywords, ',"'#{txt}', " - end - if defined? @md.notes.comment \ - and @md.notes.comment=~/\S+/ - txt=@md.notes.comments - special_character_escape(txt) - @tp[:comments_f],@tp[:comments_i]='comments, ',"'#{txt}', " - end - if defined? @md.classify.loc \ - and @md.classify.loc=~/\S+/ - txt=@md.classify.loc - special_character_escape(txt) - @tp[:cls_loc_f],@tp[:cls_loc_i]='cls_loc, ',"'#{txt}', " - end - if defined? @md.classify.dewey \ - and @md.classify.dewey=~/\S+/ - txt=@md.classify.dewey - special_character_escape(txt) - @tp[:cls_dewey_f],@tp[:cls_dewey_i]='cls_dewey, ',"'#{txt}', " - end - if defined? @md.classify.pg \ - and @md.classify.pg=~/\S+/ - txt=@md.classify.pg - special_character_escape(txt) - @tp[:cls_pg_f],@tp[:cls_pg_i]='cls_pg, ',"'#{txt}', " - end - if defined? @md.classify.isbn \ - and @md.classify.isbn=~/\S+/ - txt=@md.classify.isbn - special_character_escape(txt) - @tp[:cls_isbn_f],@tp[:cls_isbn_i]='cls_isbn, ',"'#{txt}', " - end - if defined? @md.notes.prefix_a \ - and @md.notes.prefix_a=~/\S+/ - txt=@md.notes.prefix_a - special_character_escape(txt) - @tp[:prefix_a_f],@tp[:prefix_a_i]='prefix_a, ',"'#{txt}', " - end - if defined? @md.notes.prefix_b \ - and @md.notes.prefix_b=~/\S+/ - txt=@md.notes.prefix_b - special_character_escape(txt) - @tp[:prefix_b_f],@tp[:prefix_b_i]='prefix_b, ',"'#{txt}', " - end - if defined? @md.fns \ - and @md.fns=~/\S+/ - txt=@md.fns - special_character_escape(txt) - @tp[:fns_f],@tp[:fns_i]="filename, ","'#{txt}', " - end - if @md.wc_words; txt=@md.wc_words - @tp[:wc_words_f],@tp[:wc_words_i]='wc_words, ',"'#{txt}', " - end - if defined? @md.dgst \ - and @md.dgst.class==Array - txt=@md.dgst[1] - @tp[:dgst_f],@tp[:dgst_i]='dgst, ',"'#{txt}', " - end - if @md.sc_date; txt=@md.sc_date - @tp[:sc_date_f],@tp[:sc_date_i]='sc_date, ',"'#{txt}', " - end - if @md.generated; txt=@md.generated - @tp[:generated_f],@tp[:generated_i]='generated, ',"'#{@txt}', " - end + ################ CLEAR ############## SiSU_DB_DBI::Test.new(self,@opt).verify #% import title names, filenames (tuple) - t=SiSU_DB_tuple::Load_metadata.new(@conn,@tp,@@id_t,@opt,@file) + t=SiSU_DB_tuple::Load_metadata.new(@conn,@@id_t,@md,@file) tuple=t.tuple tuple end @@ -482,13 +261,7 @@ module SiSU_DB_import and data.ln.inspect=~/[123]/ @col[:lev],txt,@col[:ocn],@col[:lev_an],@col[:ocnd],@col[:ocns],@col[:t_of],@col[:t_is],@col[:node],@col[:parent],@col[:digest_clean],@col[:digest_all]=data.ln,data.obj,data.ocn,data.lv,data.odv,data.osp,data.of,data.is,data.node,data.parent,'','' @col[:lid]+=1 - if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/ - endnotes(txt).range - @en << endnotes(txt).standard if txt =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/ - @en_ast << endnotes(txt).asterisk if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/ - @en_pls << endnotes(txt).plus if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_o]}/ - txt=endnotes(txt).clean_text - end + txt=endnotes(txt).extract_any @col[:body]=SiSU_Format_Shared::CSS_Format.new(@md,data).lev4_minus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup @@ -521,13 +294,7 @@ module SiSU_DB_import end @env=SiSU_Env::Info_env.new(@md.fns) @base_url="#{@env.url.root}/#{@md.fnb}/#{@hname}.html" - if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/ - endnotes(txt).range - @en << endnotes(txt).standard if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/ - @en_ast << endnotes(txt).asterisk if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/ - @en_pls << endnotes(txt).plus if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/ - txt=endnotes(txt).clean_text(@base_url) - end + txt=endnotes(txt).extract_any @col[:body]=SiSU_Format_Shared::CSS_Format.new(@md,data).lev4_plus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup @@ -553,13 +320,7 @@ module SiSU_DB_import end @env=SiSU_Env::Info_env.new(@md.fns) @base_url="#{@env.url.root}/#{@md.fnb}/#{@hname}.html" - if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/ - endnotes(txt).range - @en << endnotes(txt).standard if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/ - @en_ast << endnotes(txt).asterisk if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/ - @en_pls << endnotes(txt).plus if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/ - txt=endnotes(txt).clean_text(@base_url) - end + txt=endnotes(txt).extract_any @col[:body]=SiSU_Format_Shared::CSS_Format.new(@md,data).lev4_plus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup @@ -585,13 +346,7 @@ module SiSU_DB_import end @env=SiSU_Env::Info_env.new(@md.fns) @base_url="#{@env.url.root}/#{@md.fnb}/#{@hname}.html" - if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/ - endnotes(txt).range - @en << endnotes(txt).standard if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/ - @en_ast << endnotes(txt).asterisk if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/ - @en_pls << endnotes(txt).plus if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/ - txt=endnotes(txt).clean_text(@base_url) - end + txt=endnotes(txt).extract_any @col[:body]=SiSU_Format_Shared::CSS_Format.new(@md,data).lev4_plus special_character_escape(@col[:body]) @col[:plaintext]=@col[:body].dup @@ -613,15 +368,9 @@ module SiSU_DB_import end @env=SiSU_Env::Info_env.new(@md.fns) @base_url="#{@env.url.root}/#{@md.fnb}/#{@hname}.html" - if txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/ - endnotes(txt).range - @en << endnotes(txt).standard if txt =~ /#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/ - @en_ast << endnotes(txt).asterisk if txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/ - @en_pls << endnotes(txt).plus if txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_c]}/ - txt=endnotes(txt).clean_text(@base_url) - end + txt=endnotes(txt).extract_any if @sql_type=~/pg/ \ - and txt.size > (document_clean - 1) #% examine pg build & remove limitation + and txt.size > (SiSU_DB_columns::Column_size.new.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)}") @@ -660,7 +409,7 @@ module SiSU_DB_import #special_character_escape(body) #special_character_escape(txt) strip_markup(txt) - if txt.size > (endnote_clean - 1) + if txt.size > (SiSU_DB_columns::Column_size.new.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)}") @@ -698,7 +447,7 @@ module SiSU_DB_import special_character_escape(txt) body=SiSU_Format_Shared::CSS_Format.new(@md,data).endnote(nr,txt) strip_markup(txt) - if txt.size > (endnote_clean - 1) + if txt.size > (SiSU_DB_columns::Column_size.new.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)}") @@ -736,7 +485,7 @@ module SiSU_DB_import special_character_escape(txt) body=SiSU_Format_Shared::CSS_Format.new(@md,data).endnote(nr,txt) strip_markup(txt) - if txt.size > (endnote_clean - 1) + if txt.size > (SiSU_DB_columns::Column_size.new.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)}") @@ -772,6 +521,16 @@ module SiSU_DB_import end def endnotes(txt) @txt=txt + def extract_any + if @txt =~/(?:#{Mx[:en_a_o]}|#{Mx[:en_b_o]})[*+]?(\d+)\s+.+?(?:#{Mx[:en_a_c]}|#{Mx[:en_b_c]})/ + endnotes(@txt).range + @en << endnotes(@txt).standard if @txt =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/ + @en_ast << endnotes(@txt).asterisk if @txt =~/#{Mx[:en_b_o]}\*.+?#{Mx[:en_b_c]}/ + @en_pls << endnotes(@txt).plus if @txt =~/#{Mx[:en_b_o]}\+.+?#{Mx[:en_b_o]}/ + @txt=endnotes(@txt).clean_text + end + @txt + end def standard x=if @txt =~/#{Mx[:en_a_o]}.+?#{Mx[:en_a_c]}/; @txt.scan(/#{Mx[:en_a_o]}(\d+).+?#{Mx[:en_a_c]}/) else nil -- cgit v1.2.3