various small fixes

* html segments, name more accurately
* rough description of how book index markup works
* clean out book index from these outputs
* book markup sample, free as in freedom, start doing book index, only letter "A" done so far
* texpdf, url matching, special characters
* # Please enter the commit message for your changes.

5 files changed, 37 insertions, 13 deletions

diff --git a/lib/sisu/v0/dal_idx.rb b/lib/sisu/v0/dal_idx.rb
index a5806d06..c2bba846 100644
--- a/lib/sisu/v0/dal_idx.rb
+++ b/lib/sisu/v0/dal_idx.rb
@@ -288,8 +288,7 @@ module SiSU_book_index
         path="#{@env.path.output}/#{@md.fnb}"
         Dir.mkdir(path) unless FileTest.directory?(path)
         html_index_file=File.new("#{path}/#{@md.fn[:book_index]}",'w')
-        puts "#{path}/#{@md.fn[:book_index]}"
-        #html_file(the_idx)
+        #puts "#{path}/#{@md.fn[:book_index]}"
         html_idx.each {|x| html_index_file << x }
         html_index_file.close
       end
diff --git a/lib/sisu/v0/html_segments.rb b/lib/sisu/v0/html_segments.rb
index 796c3939..a280a8c8 100644
--- a/lib/sisu/v0/html_segments.rb
+++ b/lib/sisu/v0/html_segments.rb
@@ -63,18 +63,28 @@ module SiSU_HTML_seg
   require "#{SiSU_lib}/html"
   require "#{SiSU_lib}/html_promo"
   class Seg_output
-    def initialize(outputfile,seg,minitoc,type='')
-      @output_seg_file,@seg,@minitoc,@type=outputfile,seg,minitoc,type
+    def initialize(md,outputfile,seg,minitoc,type='')
+      @md,@output_seg_file,@seg,@minitoc,@type=md,outputfile,seg,minitoc,type
     end
     def output #CONSIDER
-      if @seg[:title] =~/\S/ #kludge (for exception file better.ways, how ironic) get a real ruby test, e.g. test that not array or...
+      if @seg[:title] =~/\S/
         filename_seg=[]
         filename_seg << @seg[:title] << @seg[:tocband_banner]
         if @type =~/endnote/
-#p  @seg[:headers] #FIX endnote header
+          @seg[:headers]=[]
+          format_head_seg=SiSU_HTML_Format::Head_seg.new(@md)
+          @seg[:headers] << format_head_seg.title_banner(@md.title,@md.subtitle,@dc_creator)
+          txt_obj={:txt =>'Endnotes',:ocn_display =>''}
+          format_seg=SiSU_HTML_Format::Format_seg.new(@md,txt_obj)
+          @seg[:headers] << format_seg.title_header1
           filename_seg << @seg[:header_endnotes] << @minitoc << @seg[:headers] << %{\n<div class="content">\n} << @seg[:endnote_all] << '</div>' # << '</div>'
         elsif @type =~/idx/
-#p  @seg[:headers] #FIX inserted index header
+          @seg[:headers]=[]
+          format_head_seg=SiSU_HTML_Format::Head_seg.new(@md)
+          @seg[:headers] << format_head_seg.title_banner(@md.title,@md.subtitle,@dc_creator)
+          txt_obj={:txt =>'Index',:ocn_display =>''}
+          format_seg=SiSU_HTML_Format::Format_seg.new(@md,txt_obj)
+          @seg[:headers] << format_seg.title_header1
           filename_seg << @seg[:header_idx] << @minitoc << @seg[:headers] << %{\n<div class="content">\n} << @seg[:idx] << '</div>' # << '</div>'
         else
           filename_seg << @minitoc <<  @seg[:headers] << @seg[:main] << "\n</div>\n"
@@ -191,11 +201,11 @@ module SiSU_HTML_seg
                 segfilename="#{@md.dir_out}/#{@md.fnl[:pre]}#{@@seg_name_html[tracking-1]}#{@md.fnl[:mid]}#@h_sfx#{@md.fnl[:post]}"
                 @output_seg_file=File.new(segfilename,'w') if @@seg_name_html[tracking-1]
                 if @@seg_name_html[tracking-1] !~/endnotes|idx/
-                  Seg_output.new(@output_seg_file,@@seg,@minitoc).output
+                  Seg_output.new(@md,@output_seg_file,@@seg,@minitoc).output
                 elsif @@seg_name_html[tracking-1] =~/endnotes/
-                  Seg_output.new(@output_seg_file,@@seg,@minitoc,'endnotes').output
+                  Seg_output.new(@md,@output_seg_file,@@seg,@minitoc,'endnotes').output
                 elsif @@seg_name_html[tracking-1] =~/idx/
-                  Seg_output.new(@output_seg_file,@@seg,@minitoc,'idx').output
+                  Seg_output.new(@md,@output_seg_file,@@seg,@minitoc,'idx').output
                 else p 'check'
                 end
                 Seg.new.reinitialise
diff --git a/lib/sisu/v0/manpage.rb b/lib/sisu/v0/manpage.rb
index 597099ed..ef9f6bab 100644
--- a/lib/sisu/v0/manpage.rb
+++ b/lib/sisu/v0/manpage.rb
@@ -266,6 +266,7 @@ WOK
         table_message='[table omitted, see other document formats]'
         fix=[]
         data.each do |para|
+          para.gsub!(/#{Mx[:id_o]}~0;0:0;x\d+#{Mx[:id_c]}/,'') # if book index? remove
           para.gsub!(/#{Mx[:gr_o]}Th?#{Mx[:tc_p]}.+/um,"#@br#{table_message}")
           para.gsub!(/.+?<-#>/,'')                                           # remove dummy headings (used by html) #check
           para.gsub!(/#{Mx[:gl_bullet]}\s*/,'* ')                                          # bullet markup, marked down
diff --git a/lib/sisu/v0/texinfo.rb b/lib/sisu/v0/texinfo.rb
index 3edf67e4..3ff5652c 100644
--- a/lib/sisu/v0/texinfo.rb
+++ b/lib/sisu/v0/texinfo.rb
@@ -267,6 +267,7 @@ module SiSU_TexInfo
       @submenu,@subsubmenu={},{}
       data.each do |para|
         para.gsub!(/\s*<:name#example>\s*/,' ')
+        para.gsub!(/#{Mx[:id_o]}~0;0:0;x\d+#{Mx[:id_c]}/,'') # if book index? remove
         if para =~ /^#{Mx[:lv_o]}[1-3]:\S*?#{Mx[:lv_c]}\s*(.+?)\s*$/
           txt_obj={:txt =>$1}
           toc=SiSU_Texinfo_format::Texinfo.new(@md,txt_obj)
diff --git a/lib/sisu/v0/texpdf_format.rb b/lib/sisu/v0/texpdf_format.rb
index 58a057d8..5c2b7ec5 100644
--- a/lib/sisu/v0/texpdf_format.rb
+++ b/lib/sisu/v0/texpdf_format.rb
@@ -1100,16 +1100,22 @@ WOK
       #string.gsub!(/<=lt>/,'\<')
       #string.gsub!(/<=gt>/,'\>')
       string.gsub!(/<=underscore>/,'\_')
-      string.gsub!(/((?:\\href|\\url)\{http:\/\/\S+?)(?:(?:<=tilde>)(\S+))+\}/,'\1\~\2}') #tildes in urls \href treated differently from text
+      while string =~/(http:\/\/\S+?)(?:<=tilde>\S+)+/ #tilde in urls \href treated differently from text
+        string.gsub!(/(http:\/\/\S+?)(?:<=tilde>(\S+))+/,'\1~\2')
+      end
       string.gsub!(/<=tilde>/,'{$\sim$}')
       string.gsub!(/<=pipe>/,'{\textbar}')
       string.gsub!(/<=caret>/,'{\^{~}}')
       #string.gsub!(/<=caret>/,'\^{}')
       string.gsub!(/<=exclaim>/,'\Verbatim{!}')
+      string.gsub!(/(http:\/\/\S+?)(?:(?:<=hash>)(\S+))+/,'\1#\2') #hash in urls \href treated differently from text
       string.gsub!(/<=hash>/,'{\#}')
       #string.gsub!(/<=hash>/,'{\UseTextSymbol{OT1}{#}}')
       #string.gsub!(/<=slash>/,'{\slash}')
       string.gsub!(/<=hardspace>/,'{~}') #changed ... 2005
+      while string =~/(http:\/\/\S+?)(?:<=amp>\S+)+/ #amp in urls \href treated differently from text
+        string.gsub!(/(http:\/\/\S+?)(?:<=amp>(\S+))+/,'\1&\2')
+      end
       string.gsub!(/<=amp>/,'{\\\&}') #changed ... 2005
       #string.gsub!(/<=amp>/,'{\UseTextSymbol{OT1}{&}}')
       string.gsub!(/<=slash>/,'{/}')
@@ -1202,7 +1208,8 @@ WOK
       elsif string=~/#{Mx[:gr_o]}code-end#{Mx[:gr_c]}/; @@flag_code=false
       end
       if @@flag_code; string.gsub!(/&/,'{\\\&}')
-      else string.gsub!(/(\s+&\s+)/,' and ')
+      else string.gsub!(/&/,'<=amp>')
+      #else string.gsub!(/(\s+&\s+)/,' and ')
       end
       string.gsub!(/§/u,'\S') #latex: space between next character not preserved? #string.gsub!(/§ /,'\S ')
       string.gsub!(/£/u,'\pounds')
@@ -1271,16 +1278,22 @@ WOK
       #string.gsub!(/<=lt>/,'\<')
       #string.gsub!(/<=gt>/,'\>')
       string.gsub!(/<=underscore>/,'\_')
-      string.gsub!(/((?:\\href|\\url)?\{http:\/\/\S+?)(?:(?:<=tilde>)(\S+))+\}/,'\1\~\2}') #tildes in urls \href treated differently from text
+      while string =~/(http:\/\/\S+?)(?:<=tilde>\S+)+/ #tilde in urls \href treated differently from text
+        string.gsub!(/(http:\/\/\S+?)(?:<=tilde>(\S+))+/,'\1~\2')
+      end
       string.gsub!(/<=tilde>/,'{$\sim$}')
       string.gsub!(/<=pipe>/,'{\textbar}')
       string.gsub!(/<=caret>/,'{\^{~}}')
       #string.gsub!(/<=caret>/,'\^{}')
       string.gsub!(/<=exclaim>/,'\Verbatim{!}')
+      string.gsub!(/(http:\/\/\S+?)(?:(?:<=hash>)(\S+))+/,'\1#\2') #hash in urls \href treated differently from text
       string.gsub!(/<=hash>/,'{\#}')
       #string.gsub!(/<=hash>/,'{\UseTextSymbol{OT1}{#}}')
       #string.gsub!(/<=slash>/,'{\slash}')
       string.gsub!(/<=hardspace>/,'{~}') #changed ... 2005
+      while string =~/(http:\/\/\S+?)(?:<=amp>\S+)+/ #amp in urls \href treated differently from text
+        string.gsub!(/(http:\/\/\S+?)(?:<=amp>(\S+))+/,'\1&\2')
+      end
       string.gsub!(/<=amp>/,'{\\\&}') #changed ... 2005
       #string.gsub!(/<=amp>/,'{\UseTextSymbol{OT1}{&}}')
       string.gsub!(/<=slash>/,'{/}')