special character exceptions, some fixes, primarily underscore

8 files changed, 24 insertions, 15 deletions

diff --git a/CHANGELOG b/CHANGELOG
index 47a68840..4dd3eccb 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -21,9 +21,12 @@ http://www.jus.uio.no/sisu/pkg/src/sisu_0.61.0.orig.tar.gz
     document, (rather than just e.g. the document title) [affects document
     objects and numbering where used, hence version number bump]
 
-  * html, pdf, text object switch off @markup: no_ocn (or command line flag
-    --no-ocn), in html objects are still named, (i.e. will still work with
-    searches though the relevance of the numbers returned is obscured)
+  * html, pdf, switch text object numbering off, may be set in: (a) document
+    header, @markup: no_ocn; (b) skin (for documents sharing that skin) "def
+    ocn_display_off" and set to true;  or (c) as a processing flag "sisu -hpv
+    --no-ocn [filename]". NOTE, now in html objects are still named, (i.e. will
+    still work with searches though the relevance of the numbers returned is
+    obscured)
 
   * shared markup source, composite documents, look to processing directory for
     both text (share source) and binary (sisupod (make))
@@ -35,8 +38,10 @@ http://www.jus.uio.no/sisu/pkg/src/sisu_0.61.0.orig.tar.gz
       dynamic building of some documents)
     * sysenv (default) replaced (obsoleted) -A with -a
 
-  * sisu manual, download info, change links to source to archive, rather than
-    transient repo
+  * sisu manual, manpage, download info, change links to source to archive,
+    rather than transient repo
+
+  * special character exceptions, some fixes
 
 %% sisu_0.60.1.orig.tar.gz (2007-10-07:40/7)
 http://www.jus.uio.no/sisu/pkg/src/sisu_0.60.1.orig.tar.gz
diff --git a/lib/sisu/v0/html_tune.rb b/lib/sisu/v0/html_tune.rb
index b98f19d8..82183a02 100644
--- a/lib/sisu/v0/html_tune.rb
+++ b/lib/sisu/v0/html_tune.rb
@@ -333,7 +333,7 @@ module SiSU_Tune
             end
             para.gsub!(/<a href="\.\.\//,%{<a href="#{@vz.url_site}/})
           end
-        else para.gsub!(/_</m,'&lt;'); para.gsub!(/_>/m,'&gt;') #code-block: angle brackets special characters
+        else para.gsub!(/(?=^|[^}])_</m,'&lt;'); para.gsub!(/(?=^|[^}])_>/m,'&gt;') #code-block: angle brackets special characters
         end
         @tuned_file << para
       end
diff --git a/lib/sisu/v0/manpage.rb b/lib/sisu/v0/manpage.rb
index 304bcda1..10480b90 100644
--- a/lib/sisu/v0/manpage.rb
+++ b/lib/sisu/v0/manpage.rb
@@ -338,8 +338,8 @@ WOK
           para.gsub!(/-/,'\-') #manpages use this
           para.gsub!(/&#126;/,'~') if para #manpages use this
           if para =~/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/
-            if para =~/<:code>/
-              para.gsub!(/_</,'<'); para.gsub!(/_>/m,'>') #code-block: angle brackets special characters
+            if para =~/<:code>/ #code-block: angle brackets special characters
+              para.gsub!(/(?=^|[^}])_</m,'<'); para.gsub!(/(?=^|[^}])_>/m,'>')
             end
             para.gsub!(/<br(?: \/)?>/,"\n\n.P\n\n")                                   # watch
             para.gsub!(/<:(?:group|verse|alt)(?:\\-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/,'')
diff --git a/lib/sisu/v0/odf.rb b/lib/sisu/v0/odf.rb
index 610a51aa..171372a9 100644
--- a/lib/sisu/v0/odf.rb
+++ b/lib/sisu/v0/odf.rb
@@ -473,8 +473,11 @@ module SiSU_ODF
             para=para_array.join(' ')
             para=para.strip
           end
-          para.gsub!(/_</m,'&lt;'); para.gsub!(/_>/m,'&gt;') #code-block: angle brackets special characters
-          #para.gsub!(/</,'&lt;'); para.gsub!(/>/,'&gt;')
+          if para =~/<:code>/ #code-block: angle brackets special characters
+            para.gsub!(/(?=^|[^}])_</m,'&lt;'); para.gsub!(/(?=^|[^}])_>/m,'&gt;')
+          end
+          ##para.gsub!(/_</m,'&lt;'); para.gsub!(/([^_])_>/m,'\1&gt;') #code-block: angle brackets special characters
+          #para.gsub!(/_</m,'&lt;'); para.gsub!(/_>/m,'&gt;') #code-block: angle brackets special characters
           para.gsub!(/^(<:i[1-9]>\s+)?_\*\s+/,'\1<draw:frame draw:style-name="gr1" text:anchor-type="as-char" svg:width="0.22cm" svg:height="0.22cm" draw:z-index="2"><draw:image xlink:href="Pictures/bullet_09.png" xlink:type="simple" xlink:show="embed" xlink:actuate="onLoad"/></draw:frame> ') # bullet_09.png
           #para.gsub!(/^(<:i[1-9]>\s+)?_\*\s+/,'\1<text:span text:style-name="T6">●</text:span> ')     #bullet
           #para.gsub!(/^(<:i[1-9]>\s+)?_\*\s+/,'\1● ') # bullet utf8, make smaller if used
diff --git a/lib/sisu/v0/plaintext.rb b/lib/sisu/v0/plaintext.rb
index c308dfb2..361624e1 100644
--- a/lib/sisu/v0/plaintext.rb
+++ b/lib/sisu/v0/plaintext.rb
@@ -335,8 +335,8 @@ WOK
             para.gsub!(/&#169;/,'©')
           end
           if para =~/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/
-            if para =~/<:code>/
-              para.gsub!(/_</,'<'); para.gsub!(/_>/m,'>') #code-block: angle brackets special characters
+            if para =~/<:code>/ #code-block: angle brackets special characters
+              para.gsub!(/(?=^|[^}])_</m,'<'); para.gsub!(/(?=^|[^}])_>/m,'>')
             end
             para.gsub!(/<br(?: \/)?>/,"\n")                                   # watch
             para.gsub!(/<:(?:group|verse|alt|code)(?:-end)?>(?:\s+<~(\d+);(?:\w|[0-6]:)\d+;\w\d+><#@dp:#@dp>)?/,'')
diff --git a/lib/sisu/v0/shared_html_lite.rb b/lib/sisu/v0/shared_html_lite.rb
index 85368a28..d63f4cef 100644
--- a/lib/sisu/v0/shared_html_lite.rb
+++ b/lib/sisu/v0/shared_html_lite.rb
@@ -133,7 +133,7 @@ module SiSU_Format_Shared
         para.gsub!(/\b[_\\]((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'<a href="\1" target="_top">\1</a>\2') #http ftp matches escaped, no decoration
         para.gsub!(/((?:^|\s)[}])((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?:\s|$))/,'\1<a href="\2" target="_top">\2</a>\3') #special case \{ e.g. \}http://url
         para.gsub!(/(^|\s)((?:https?|file|ftp):\/\/\S+?\.[^'"><\s]+?)([;.,]?(?=\s|$))/,%{\\1#{@url_brace.xml_open}<a href="\\2" target="_top">\\2</a>#{@url_brace.xml_close}\\3}) #http ftp matches with decoration
-      else para.gsub!(/_</m,'&lt;'); para.gsub!(/_>/m,'&gt;') #code-block: angle brackets special characters
+      else para.gsub!(/(?=^|[^}])_</m,'&lt;'); para.gsub!(/(?=^|[^}])_>/m,'&gt;') #code-block: angle brackets special characters
       end
       para
     end
diff --git a/lib/sisu/v0/shared_xml.rb b/lib/sisu/v0/shared_xml.rb
index da1891e5..62e8b5ca 100644
--- a/lib/sisu/v0/shared_xml.rb
+++ b/lib/sisu/v0/shared_xml.rb
@@ -365,7 +365,7 @@ module SiSU_XML_munge
         para.gsub!(/&nbsp;/,'&#160;')
         #para.gsub!(/&nbsp;/,' ') #clean
       else
-        para.gsub!(/_</m,'&lt;'); para.gsub!(/_>/m,'&gt;') #code-block: angle brackets special characters
+        para.gsub!(/(?=^|[^}])_</m,'&lt;'); para.gsub!(/(?=^|[^}])_>/m,'&gt;') #code-block: angle brackets special characters
         para.gsub!(/&nbsp;/,'&#160;')
       end
       para
@@ -391,7 +391,7 @@ module SiSU_XML_munge
     def markup_group(para='')
       para.gsub!(/</,'&lt;'); para.gsub!(/>/,'&gt;')
       para.gsub!(/&lt;:?br(?:\s+\/)?&gt;/,'<br />')
-      para.gsub!(/&lt;(link xmlns:xlink=".+?)"&gt;/,'<"\1">')
+      para.gsub!(/&lt;(link xmlns:xlink=".+?")&gt;/,'<\1>')
       para.gsub!(/&lt;(\/link)&gt;/,'<\1>')
       para.gsub!(/&lt;(\/?en)&gt;/,'<\1>')
       para
diff --git a/lib/sisu/v0/texpdf_format.rb b/lib/sisu/v0/texpdf_format.rb
index bf93ce9c..7798e886 100644
--- a/lib/sisu/v0/texpdf_format.rb
+++ b/lib/sisu/v0/texpdf_format.rb
@@ -519,6 +519,7 @@ WOK
       @string.gsub!(/<i>(.+?)<\/i>/,'\emph{\1}')
       @string.gsub!(/<italic>(.+?)<\/italic>/,'\emph{\1}')
       @string.gsub!(/<u>(.+?)<\/u>/,'\uline{\1}') # ulem
+      @string.gsub!(/<cite>(.+?)<\/cite>/,"``\\1''") # quote
       @string.gsub!(/<ins>(.+?)<\/ins>/,'\uline{\1}') # ulem
       @string.gsub!(/<del>(.+?)<\/del>/,'\sout{\1}') # ulem
       @string.gsub!(/<sub>(.+?)<\/sub>/,"\$_{\\textrm{\\1}}\$")