aboutsummaryrefslogtreecommitdiffhomepage
path: root/lib/sisu/xhtml_epub2_concordance.rb
diff options
context:
space:
mode:
Diffstat (limited to 'lib/sisu/xhtml_epub2_concordance.rb')
-rw-r--r--lib/sisu/xhtml_epub2_concordance.rb322
1 files changed, 322 insertions, 0 deletions
diff --git a/lib/sisu/xhtml_epub2_concordance.rb b/lib/sisu/xhtml_epub2_concordance.rb
new file mode 100644
index 00000000..ab50a7f8
--- /dev/null
+++ b/lib/sisu/xhtml_epub2_concordance.rb
@@ -0,0 +1,322 @@
+# encoding: utf-8
+=begin
+
+* Name: SiSU
+
+** Description: documents, structuring, processing, publishing, search
+*** epub concordance file (wordmap, linked index of words in document)
+
+** Author: Ralph Amissah
+ <ralph@amissah.com>
+ <ralph.amissah@gmail.com>
+
+** Copyright: (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+ 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015 Ralph Amissah,
+ All Rights Reserved.
+
+** License: GPL 3 or later:
+
+ SiSU, a framework for document structuring, publishing and search
+
+ Copyright (C) Ralph Amissah
+
+ 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 3 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, see <http://www.gnu.org/licenses/>.
+
+ If you have Internet connection, the latest version of the GPL should be
+ available at these locations:
+ <http://www.fsf.org/licensing/licenses/gpl.html>
+ <http://www.gnu.org/licenses/gpl.html>
+
+ <http://www.sisudoc.org/sisu/en/manifest/gpl.fsf.html>
+
+** SiSU uses:
+ * Standard SiSU markup syntax,
+ * Standard SiSU meta-markup syntax, and the
+ * Standard SiSU object citation numbering and system
+
+** Hompages:
+ <http://www.jus.uio.no/sisu>
+ <http://www.sisudoc.org>
+
+** Git
+ <http://git.sisudoc.org/gitweb/?p=code/sisu.git;a=summary>
+ <http://git.sisudoc.org/gitweb/?p=code/sisu.git;a=blob;f=lib/sisu/xhtml_epub2_concordance.rb;hb=HEAD>
+
+=end
+module SiSU_XHTML_EPUB2_Concordance
+ require_relative 'se_hub_particulars' # se_hub_particulars.rb
+ include SiSU_Particulars
+ require_relative 'se' # se.rb
+ include SiSU_Env
+ require_relative 'xhtml_parts' # xhtml_parts.rb
+ require_relative 'xhtml_epub2_format' # xhtml_epub2_format.rb
+ include SiSU_XHTML_EPUB2_Format
+ class Source
+ def initialize(opt)
+ @opt=opt
+ @particulars=SiSU_Particulars::CombinedSingleton.instance.get_all(opt)
+ end
+ def read
+ begin
+ @env,@md=@particulars.env,@particulars.md
+ wordmax=@env.concord_max
+ unless @md.wc_words.nil?
+ if @md.wc_words < wordmax
+ SiSU_XHTML_EPUB2_Concordance::Source::Words.new(@particulars).songsheet
+ else
+ SiSU_Screen::Ansi.new(
+ @md.opt.act[:color_state][:set],
+ "*WARN* concordance skipped, large document has over #{wordmax} words (#{@md.wc_words})"
+ ).warn unless @md.opt.act[:quiet][:set]==:on
+ end
+ else
+ SiSU_Screen::Ansi.new(
+ @md.opt.act[:color_state][:set],
+ "*WARN* wc (word count) is off, concordance will be processed for all files including those over the max set size of: #{wordmax} words"
+ ).warn unless @md.opt.act[:quiet][:set]==:on
+ SiSU_XHTML_EPUB2_Concordance::Source::Words.new(@particulars).songsheet
+ end
+ rescue
+ SiSU_Errors::Rescued.new($!,$@,@md.opt.selections.str,@md.fns).location do
+ __LINE__.to_s + ':' + __FILE__
+ end
+ ensure
+ end
+ end
+ private
+ class DocTitle
+ #revisit, both requires (html & xml_shared) needed for stand alone operation (sisu -w [filename])
+ require_relative 'xhtml_epub2' # xhtml_epub2.rb
+ def initialize(particulars)
+ @particulars,@md=particulars,particulars.md
+ @data=SiSU_XHTML_EPUB2::Source::XHTML_Environment.new(particulars).tuned_file_instructions
+ @fnb=@md.fnb
+ @lex_button=%{<a href="http://www.jus.uio.no/sisu/" target="_top"><img border="0" height="44" width="144" valign="center" src="../_sisu/image/sisu.png" alt="SiSU home"></a>}
+ @doc_details =<<WOK
+<table summary="links to text related to this rudimentary index" width="96%" border="0" bgcolor="white" cellpadding="0" align="center"><tr><td width="2%" align="right">#{$ep[:hsp]}</td><td width="94%" valign="top" align="justify"><h1 class="small"><a href="#{@md.file.base_filename.epub}"><b>#{@md.title.full}</b></a></h1><p class="bold">#{@md.creator.author}</p></td></tr></table>
+WOK
+ end
+ def create
+ @css=SiSU_Env::CSS_Stylesheet.new(@particulars.md)
+ format_head_toc=SiSU_XHTML_EPUB2_Format::HeadToc.new(@md)
+ dochead=format_head_toc.head
+ <<WOK
+#{dochead}
+<div class="content">
+ #{@doc_details}
+<p>Word index links are to html versions of the text the segmented version followed by the scroll (single document) version.<br />[For segmented text references [T1], [T2] or [T3] appearing without a link, indicates that the word appears in a title (or subtitle) of the text (that is identifiable by the appended object citation number).]</p>
+<p>(The word listing/index is Case sensitive: Capitalized words appear before lower case)</p>
+ <p>
+ <b>word</b> (number of occurences)<br />linked references to word within document <br />
+ [if number of occurences exceed number of references - word occurs more than once in at least one reference. Footnote/endnotes are either assigned to the paragraph from which they are referenced or ignored, so it is relevant to check the footnotes referenced from within a paragraph as well.]
+ </p>
+ <p>
+ (After the page is fully loaded) you can jump directly to a word by appending a hash (#) and the word to the url for this text, (do not forget that words are case sensitive, and may be listed twice (starting with and without an upper case letter)), #your_word # [#{$ep[:hsp]}http://[web host]/#{@fnb}/concordance.html#your_word#{$ep[:hsp]}]
+ </p>
+WOK
+ end
+ end
+ class Word
+ @@word_previous=''
+ def initialize(word,freq)
+ @word,@freq=word,freq
+ end
+ def html
+ w=if @word.capitalize==@@word_previous
+ %{\n<p class="concordance_word">#{@word}</p><p class="concordance_count">(#{@freq})</p>\n\t<p class="concordance_object"> }
+ else n=@word.strip.gsub(/\s+/,'_') #also need to convert extended character set to html
+ %{\n<p class="concordance_word"><a name="#{n}">#{@word}</a></p><p class="concordance_count">(#{@freq})</p>\n\t<p class="concordance_object"> }
+ end
+ @@word_previous=@word.capitalize
+ w
+ end
+ end
+ class Words
+ require_relative 'xhtml_epub2_format' # xhtml_epub2_format.rb
+ include SiSU_XHTML_EPUB2_Format
+ require_relative 'se' # se.rb
+ include SiSU_Screen
+ def initialize(particulars)
+ @particulars=particulars
+ begin
+ @env,@md,@ao_array=particulars.env,particulars.md,particulars.ao_array
+ @path="#{@env.processing_path.epub}"
+ @freq=Hash.new(0)
+ @rxp_lv0=/^#{Mx[:lv_o]}0:/
+ @rxp_lv1=/^#{Mx[:lv_o]}1:/
+ @rxp_lv2=/^#{Mx[:lv_o]}2:/
+ @rxp_lv3=/^#{Mx[:lv_o]}3:/
+ @rxp_seg=/^#{Mx[:lv_o]}4:(\S+?)#{Mx[:lv_c]}/
+ @rxp_title=Regexp.new("^#{Mx[:meta_o]}title#{Mx[:meta_c]}\s*(.+?)\s*$")
+ @rxp_t0=Regexp.new('^T0')
+ @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+|&nbsp;|#{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?|[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]})?$/mi #this regex causes and cures a stack dump in ruby 1.9 !!!
+ @rgx_splitlist=%r{[—.,;:-]+|#{Mx[:nbsp]}+}mi
+ @rgx_scanlist=%r{#{Mx[:fa_italics_o]}[a-zA-Z0-9"\s]{2,12}#{Mx[:fa_italics_c]}|#{Mx[:fa_bold_o]}[a-zA-Z0-9"\s]{2,12}#{Mx[:fa_bold_c]}|#{Mx[:url_o]}https?://\S+?#{Mx[:url_c]}|file://\S+|<\S+?>|\w+|[a-zA-Z]+}mi
+ rescue
+ SiSU_Errors::Rescued.new($!,$@,@md.opt.selections.str,@md.fns).location do
+ __LINE__.to_s + ':' + __FILE__
+ end
+ end
+ end
+ def songsheet
+ begin
+ #fix to use
+ p __LINE__.to_s + ':' + __FILE__
+ p "#{@path}/content/#{@md.fn[:epub_concord]}"
+ p "#{@md.file.output_path.epub.dir}/#{@md.file.base_filename.epub}"
+ @file_concordance=File.open("#{@path}/content/#{@md.fn[:epub_concord]}",'w')
+ map_para
+ rescue
+ SiSU_Errors::Rescued.new($!,$@,@md.opt.selections.str,@md.fns).location do
+ __LINE__.to_s + ':' + __FILE__
+ end
+ ensure
+ @file_concordance.close
+ end
+ end
+ protected
+ def location_scroll(wordlocation,show)
+ @wordlocation=wordlocation
+ %{<a href="doc#{Sfx[:epub_xhtml]}\##{@wordlocation}">#{@wordlocation}</a>; }
+ end
+ def location_seg(wordlocation,show)
+ @wordlocation,@show=wordlocation,show
+ @word_location_seg=wordlocation.gsub(/(.+?)\#(\d+)/,"\\1#{Sfx[:epub_xhtml]}#o\\2") unless wordlocation.nil?
+ case @wordlocation
+ when @rxp_t1
+ %{[<a href="doc#{Sfx[:epub_xhtml]}##{@show}">H</a>]#{@show}, }
+ when @rxp_t2
+ %{[<a href="doc#{Sfx[:epub_xhtml]}##{@show}">H</a>]#{@show}, }
+ when @rxp_t3
+ %{[<a href="doc#{Sfx[:epub_xhtml]}##{@show}">H</a>]#{@show}, }
+ else %{<a href="#{@word_location_seg}">#{@show}</a>, }
+ end
+ end
+ def map_para
+ @seg,toy=nil,nil
+ @word_map={}
+ @ao_array.each do |line|
+ if defined? line.ocn
+ if (line.is ==:heading \
+ || line.is ==:heading_insert) \
+ && line.ln==4
+ @seg=line.name
+ end
+ if line.ocn.to_s =~/\d+/ then toy=line.ocn.to_s
+ end
+ if toy =~/\d+/ \
+ and toy !~/^0$/
+ line.obj=line.obj.split(@rgx_splitlist).join(' ') #%take in word or other match
+ for word in line.obj.scan(@rgx_scanlist) #%take in word or other match
+ word=word.gsub(/#{Mx[:lnk_o]}|#{Mx[:lnk_c]}|#{Mx[:url_o]}|#{Mx[:url_c]}/,'').
+ gsub(/#{Mx[:fa_o]}\S+?#{Mx[:fa_o_c]}/,'').
+ gsub(/#{Mx[:fa_c_o]}\S+?#{Mx[:fa_c]}/,'').
+ gsub(/#{Mx[:gl_o]}#[a-z]+#{Mx[:gl_c]}/,'').
+ gsub(/#{Mx[:gl_o]}#[0-9]+#{Mx[:gl_c]}/,'').
+ 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=word.gsub(/#{Mx[:br_nl]}|#{Mx[:br_line]}/,' ').
+ gsub(/#{Mx[:fa_o]}[a-z]{1,7}#{Mx[:fa_o_c]}|#{Mx[:fa_c_o]}[a-z]{1,7}#{Mx[:fa_c]}/,'').
+ gsub(/#{Mx[:mk_o]}(?:[0-9a-f]{32}:[0-9a-f]{32}|[0-9a-f]{64}:[0-9a-f]{64})#{Mx[:mk_c]}/,'').
+ gsub(/#{Mx[:mk_o]}(?:[0-9a-f]{32}|[0-9a-f]{64})#{Mx[:mk_c]}/,'').
+ gsub(/#{Mx[:en_a_o]}(?:\d|[*+])*|#{Mx[:en_b_o]}(?:\d|[*+])*|#{Mx[:en_a_c]}|#{Mx[:en_b_c]}/mi,'').
+ gsub(/#{Mx[:fa_o]}\S+?#{Mx[:fa_o_c]}/,'').gsub(/#{Mx[:fa_c_o]}\S+?#{Mx[:fa_c]}/,'').
+ gsub(/<\/?\S+?>/,'').
+ gsub(/^\@+/,'').
+ strip.
+ gsub(/#{Mx[:tc_p]}.+/,'').
+ gsub(/[\.,;:"]$/,'').
+ gsub(/["]/,'').
+ gsub(/^\s*[\(]/,'').
+ gsub(/[\(]\s*$/,'').
+ gsub(/^(?:See|e\.?g\.?).+/,'').
+ gsub(/^\s*[.,;:]\s*/,'').
+ strip.
+ gsub(/^\(?[a-zA-Z]\)$/,'').
+ gsub(/^\d+(st|nd|rd|th)$/,'').
+ gsub(/^(\d+\.?)+$/, '').
+ gsub(/#{Mx[:mk_o]}|#{Mx[:mk_c]}/,'').
+ gsub(/:name#\S+/,'').
+ gsub(/^\S$/,'')
+ 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=word.capitalize
+ end
+ @freq[word] +=1
+ @word_map[word] ||= []
+ if line !~@rxp_lv0 \
+ and 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_lv0 then location_seg('T0',toy)
+ when @rxp_lv1 then location_seg('T1',toy)
+ when @rxp_lv2 then location_seg('T2',toy)
+ when @rxp_lv3 then location_seg('T3',toy)
+ end
+ end
+ end
+ end
+ end
+ end
+ end
+ end
+ seg=''
+ @file_concordance << SiSU_XHTML_EPUB2_Concordance::Source::DocTitle.new(@particulars).create
+ alph=%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]
+ @file_concordance << '<p>'
+ alph.each {|x| @file_concordance << %{<a href="##{x}">#{x}</a>,#{$ep[:hsp]}}}
+ @file_concordance << '</p>'
+ letter=alph.shift
+ @file_concordance << %{\n<p class="letter"><a name="A">A</a></p>}
+ for word in @freq.keys.sort! {|a,b| a.downcase<=>b.downcase}
+ f=/^(\S)/.match(word)[1]
+ if letter < f.upcase
+ while letter < f.upcase
+ if alph.length > 0
+ letter=alph.shift
+ @file_concordance << %{\n<p class="letter"><a name="#{letter}">#{letter}</a></p>}
+ else break
+ end
+ end
+ end
+ keyword=SiSU_XHTML_EPUB2_Concordance::Source::Word.new(word,@freq[word]).html
+ if keyword !~ @rxp_excluded0
+ if @word_map[word][0] =~ /\d+/
+ @file_concordance << %{#{keyword}#{seg}#{@word_map[word].uniq.compact.join}}
+ end
+ @file_concordance << '</p>'
+ end
+ # special cases endnotes and header levels 1 - 3
+ end
+ credits=SiSU_Proj_XHTML::Bits.new.credits_sisu_epub
+ @file_concordance << %{</div>>#{credits}</body>\n</html>} # footer
+ end
+ end
+ end
+end
+__END__