Word index links are to html versions of the text the segmented version followed by the scroll (single document) version.
[For segmented text references [T1], [T2] or [T3] appearing without a link, indicates that the word appears in a title (or subtitle) of the text (that is identifiable by the appended object citation number).]
(The word listing/index is Case sensitive: Capitalized words appear before lower case)
word (number of occurences)
linked references to word within document
[if number of occurences exceed number of references - word occurs more than once in at least one reference. Footnote/endnotes are either assigned to the paragraph from which they are referenced or ignored, so it is relevant to check the footnotes referenced from within a paragraph as well.]
(After the page is fully loaded) you can jump directly to a word by appending a hash (#) and the word to the url for this text, (do not forget that words are case sensitive, and may be listed twice (starting with and without an upper case letter)), #your_word # [ http://[web host]/#{@fnb}/concordance.html#your_word ]
WOK end end class Word @@word_previous='' def initialize(word,freq) @word,@freq=word,freq end def html w=if @word.capitalize==@@word_previous %{\n#@word
(#@freq)
\n\t} else n=@word.strip.gsub(/\s+/,'_') #also need to convert extended character set to html %{\n
(#@freq)
\n\t} end @@word_previous=@word.capitalize w end end class Words require "#{SiSU_lib}/defaults" include SiSU_Viz require "#{SiSU_lib}/html_format" include SiSU_HTML_Format require "#{SiSU_lib}/sysenv" include SiSU_Screen @@dp=nil def initialize(particulars) @particulars=particulars begin @vz=SiSU_Env::Get_init.instance.skin @env,@md,@dal_array=particulars.env,particulars.md,particulars.dal_array @path="#{@env.path.output}/#{@md.fnb}" @freq=Hash.new(0) @dp=@@dp ||=SiSU_Env::Info_env.new.digest.pattern @rxp_to=Regexp.new("#{Mx[:id_o]}~(\\d+);(?:[oh]|[0-6]:)\\d+;\\w\\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}|#{Mx[:id_o]}\S+?#{Mx[:id_c]}$") @rxp_lv1=/^#{Mx[:lv_o]}1:/ @rxp_lv2=/^#{Mx[:lv_o]}2:/ @rxp_lv3=/^#{Mx[:lv_o]}3:/ @rxp_seg=/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/ @rxp_title=Regexp.new("^#{Mx[:meta_o]}title#{Mx[:meta_c]}\s*(.+?)\s*$") @rxp_t1=Regexp.new('^T1') @rxp_t2=Regexp.new('^T2') @rxp_t3=Regexp.new('^T3') @rxp_excluded1=/(?:https?|file|ftp):\/\/\S+/ @rxp_excluded0=/^(?:#{Mx[:fa_bold_o]}|#{Mx[:fa_italics_o]})?(?:to\d+|\d+| |#{Mx[:br_endnotes]}|EOF|#{Mx[:br_eof]}|thumb_\S+|snap_\S+|_+|-+|[(]?(?:ii+|iv|vi+|ix|xi+|xiv|xv|xvi+|xix|xx)[).]?|\S+?_\S+|[\d_]+\w\S+|[\w\d]{1,2}|\d{1,3}\w?|#@dp|[0-9a-f]{16,64}|\d{2,3}x\d{2,3}|\S{0,2}sha\d|\S{0,3}\d{4}w\d\d|\b\w\d+|\d_all\b|e\.?g\.?)(?:#{Mx[:fa_bold_c]}|#{Mx[:fa_italics_c]})?$/mi #this regex causes and cures a stack dump in ruby 1.9 !!! @rgx_splitlist=%r{[—.,;:-]|#{Mx[:id_o]}\S+?#{Mx[:id_c]}}mi @rgx_scanlist=%r{#{Mx[:fa_italics_o]}[a-zA-Z0-9"\s]{2,12}#{Mx[:fa_italics_c]}|#{Mx[:fa_bold_o]}[a-zA-Z0-9"\s]{2,12}#{Mx[:fa_bold_c]}|(?:https?|file)://\S+|#{Mx[:gr_o]}code#{Mx[:gr_o]}.+?#{Mx[:gr_o]}code-end#{Mx[:gr_o]}|<\S+?>|\w+|[a-zA-Z]+}mi rescue; SiSU_Errors::Info_error.new($!,$@,@md.cmd,@md.fns).error end end def songsheet begin mkdir_p(@path) unless FileTest.directory?(@path) @file_index_all=File.open("#@path/#{@md.fn[:concordance]}",'w') map_para rescue; SiSU_Errors::Info_error.new($!,$@,@md.cmd,@md.fns).error ensure @file_index_all.close end end protected def location_scroll(wordlocation,show) @wordlocation=wordlocation %{#@wordlocation; } end def location_seg(wordlocation,show) @wordlocation,@show=wordlocation,show @sfx='.html' #used for hardlinks, previous setting @sfx='', web server takes care of suffix @word_location_seg=wordlocation.gsub(/(.+?)\#(\d+)/,"#{@md.fnl[:pre]}\\1#{@md.fnl[:mid]}#@sfx#{@md.fnl[:post]}#\\2") unless wordlocation.nil? case @wordlocation when @rxp_t1 %{[H]#@show, } when @rxp_t2 %{[H]#@show, } when @rxp_t3 %{[H]#@show, } else %{#@show, } end end def map_para @seg,toy=nil,nil @word_map={} @dal_array.each do |line| if line !~/#{Mx[:id_o]}~(\d+);[um]\d+;\w\d+#{Mx[:id_c]}#{Mx[:id_o]}#@dp:#@dp#{Mx[:id_c]}$/ #lines to ignore: # are added but not part of authors substantive text; 0 are mostly machine generated if line =~@rxp_seg; @seg=line[@rxp_seg,1] end if line =~@rxp_to; toy=line[@rxp_to,1] end if toy =~/\d+/ \ and toy !~/^0$/ line=line.split(@rgx_splitlist).join(' ') #%take in word or other match for word in line.scan(@rgx_scanlist) #%take in word or other match #word.gsub!(@rxp_clean,'') word.gsub!(/#{Mx[:lnk_o]}|#{Mx[:lnk_c]}(?:http)?/,'') word.gsub!(/#{Mx[:fa_o]}\S+?#{Mx[:fa_o_c]}/,'') word.gsub!(/#{Mx[:fa_c_o]}\S+?#{Mx[:fa_c]}/,'') word.gsub!(/#{Mx[:gl_o]}#[a-z]+#{Mx[:gl_c]}/,'') word.gsub!(/#{Mx[:gl_o]}#[0-9]+#{Mx[:gl_c]}/,'') word.gsub!(/^\S$/,'') word=nil if word.empty? word=nil if word =~@rxp_excluded0 #watch word=nil if word =~@rxp_excluded1 #watch word=nil if word =~/^\S$/ if word word.gsub!(/#{Mx[:br_nl]}|#{Mx[:br_line]}/,' ') word.gsub!(/#{Mx[:lv_o]}\d:\S*?#{Mx[:lv_c]}/,'') word.gsub!(/#{Mx[:pa_o]}:i\d#{Mx[:pa_c]}/,'') word.gsub!(/#{Mx[:id_o]}~\d+;\S+?#{Mx[:id_c]}/,'') word.gsub!(/#{Mx[:fa_o]}[a-z]{1,7}#{Mx[:fa_o_c]}|#{Mx[:fa_c_o]}[a-z]{1,7}#{Mx[:fa_c]}/,'') word.gsub!(/#{Mx[:mk_o]}(?:[0-9a-f]{32}:[0-9a-f]{32}|[0-9a-f]{64}:[0-9a-f]{64})#{Mx[:mk_c]}/,'') word.gsub!(/#{Mx[:mk_o]}(?:[0-9a-f]{32}|[0-9a-f]{64})#{Mx[:mk_c]}/,'') word.gsub!(/#{Mx[:en_a_o]}(?:\d|[*+])*|#{Mx[:en_b_o]}(?:\d|[*+])*|#{Mx[:en_a_c]}|#{Mx[:en_b_c]}/mi,'') word.gsub!(/#{Mx[:fa_o]}\S+?#{Mx[:fa_o_c]}/,''); word.gsub!(/#{Mx[:fa_c_o]}\S+?#{Mx[:fa_c]}/,'') #word.gsub!(/#{Mx[:fa_o]}\S+?#{Mx[:fa_c]}/,'') #watch word.gsub!(/<\/?\S+?>/,'') word.gsub!(/^\@+/,'') word.strip! word.gsub!(/#{Mx[:tc_p]}.+/,'') word.gsub!(/[\.,;:"]$/,'') word.gsub!(/["]/,'') word.gsub!(/^\s*[\(]/,'') word.gsub!(/[\(]\s*$/,'') word.gsub!(/^(?:See|e\.?g\.?).+/,'') word.gsub!(/^\s*[.,;:]\s*/,'') word.strip! word.gsub!(/^\(?[a-zA-Z]\)$/,'') word.gsub!(/^\d+(st|nd|rd|th)$/,'') word.gsub!(/^(\d+\.?)+$/, '') word.gsub!(/#{Mx[:mk_o]}|#{Mx[:mk_c]}/,'') word.gsub!(/:name#\S+/,'') word.gsub!(/^\S$/,'') word=nil if word =~/^\S$/ word=nil if word =~/^\s*$/ #watch if word unless word =~/[A-Z][A-Z]/ \ or word =~/\w+\s\w+/ word.capitalize! end #word.downcase! if word =~lesser #word.capitalize! if word =~greater @freq[word] +=1 @word_map[word] ||= [] if line !~@rxp_lv1 \ and line !~@rxp_lv2 \ and line !~@rxp_lv3 @word_map[word] << location_seg("#@seg\##{toy}",toy) else @word_map[word] << case line when @rxp_lv1; location_seg('T1',toy) when @rxp_lv2; location_seg('T2',toy) when @rxp_lv3; location_seg('T3',toy) end end end end end end end end scr=' scroll: doc# ' seg='' @file_index_all << SiSU_Concordance::Source::Doc_title.new(@particulars).create for word in @freq.keys.sort! {|a,b| a.downcase<=>b.downcase} keyword=SiSU_Concordance::Source::Word.new(word,@freq[word]).html if keyword !~ @rxp_excluded0 if @word_map[word][0] =~ /\d+/ wm=[] @file_index_all << %{#{keyword}#{seg}#{@word_map[word].uniq.compact.join}} end @file_index_all << '
' end # special cases endnotes and header levels 1 - 3 end credits=@vz.credits_sisu @file_index_all << %{