ydocx 1.0.1 → 1.0.2

data/History.txt

@@ -1,3 +1,11 @@
+=== 1.0.2 / 01.05.2012
+
+* Improved tab handling at line head
+
+=== 1.0.1 / 01.05.2012
+
+* Updated title chapter for frame
+
 === 1.0.0 / 01.05.2012
 
 * 1 major enhancement

data/README.txt

@@ -16,6 +16,6 @@
 * nokogiri
 * htmlentities
 
-== License GPLv2.1
+== License GPLv3.0
 
-* http://www.gnu.org/licenses/lgpl-2.1.html
+* http://www.gnu.org/licenses/gpl.html

data/lib/docx2html/lib/docx2html/parser.rb

@@ -8,12 +8,13 @@ require 'docx2html/lib/docx2html/html_methods'
 module Docx2html
   class Parser
     include HtmlMethods
-    attr_accessor :indecies, :result
+    attr_accessor :indecies, :result, :space
     def initialize(stream)
       @xml = Nokogiri::XML.parse(stream)
       @coder = HTMLEntities.new
       @indecies = []
       @result = []
+      @space = ' '
       init
       if block_given?
         yield self
@@ -73,7 +74,7 @@ module Docx2html
       nil # default no block element
     end
     def optional_escape(text)
-      return text = ' ' if text.empty?
+      return text = @space if text.empty?
       text.force_encoding('utf-8')
       # NOTE
       # :named only for escape at Builder
@@ -146,18 +147,23 @@ module Docx2html
     end
     def parse_paragraph(node)
       paragraph = tag :p
+      line_head = true
+      pos = 0
       node.xpath('w:r').each do |r|
         unless r.xpath('w:t').empty?
           paragraph[:content] << parse_text(r)
+          pos += 1
         else
           unless r.xpath('w:tab').empty?
-            if paragraph[:content].last != '&nbsp;' # as a space
+            if paragraph[:content].last != @space and pos != 0 # ignore tab at line head
               paragraph[:content] << optional_escape('')
+              pos += 1
             end
           end
           unless r.xpath('w:sym').empty?
             code = r.xpath('w:sym').first['char'].downcase # w:char
             paragraph[:content] << optional_replace(code)
+            pos += 1
           end
         end
       end
@@ -193,6 +199,7 @@ module Docx2html
           block
         else
           # inline tag
+          text = text.strip
           text = apply_align(rpr, text)
           unless rpr.xpath('w:u').empty?
             text = tag(:span, text, {:style => "text-decoration:underline;"})

data/lib/fachinfo.rb

@@ -6,21 +6,24 @@ require 'cgi'
 module Docx2html
   class Parser
     private
+    def escape(text)
+      CGI.escape(text.gsub(/&(.)uml;/, '\1').gsub(/\s*\/\s*|\/|\s+/, '_').downcase)
+    end
     def parse_as_block(r, text)
-      if r.parent.previous.nil?
+      if r.parent.previous.nil? and @indecies.empty?
         # The first line as package name
-        link = tag(:a, text, {:href => ''})
-        @indecies << tag(:h2, link)
-        return tag(:h2, text)
+        id = escape('titel')
+        @indecies << {:text => 'Titel', :id => id}
+        return tag(:h2, text, {:id => id})
       end
       text = text.strip
       # TODO
       # Franzoesisch
       chapters = {
-        'Dos./Anw.'       => /^Dosierung\s*\/\s*Anwendung/u, # 5
+        'Dos./Anw.'       => /^Dosierung\s*(\/|und)\s*Anwendung/u, # 5
         'Eigensch.'       => /^Eigenschaften\s*\/\s*Wirkungen($|\s*\(\s*(ATC\-Code|Wirkungsmechanismus|Pharmakodyamik|Klinische\s+Wirksamkeit)\s*\)\s*$)|^Propri.t.s/iu, # 13
-        'Galen.Form'      => /^Galenische\s+Form\s+und\s+Wirkstoffmenge\s+pro\s+Einheit$|^Forme\s*gal.nique/iu, # 3
-        'Ind./Anw.mögl.'  => /^Indikationen(\s+|\s*\/\s*)Anwendungsm&ouml;glichkeiten$|^Indications/u, # 4
+        'Galen.Form'      => /^Galenische\s+Form\s*(und|\/)\s*Wirkstoffmenge\s+pro\s+Einheit$|^Forme\s*gal.nique/iu, # 3
+        'Ind./Anw.mögl.'  => /^Indikationen(\s+|\s*(\/|und)\s*)Anwendungsm&ouml;glichkeiten$|^Indications/u, # 4
         'Interakt.'       => /^Interaktionen$|^Interactions/u, # 8
         'Kontraind.'      => /^Kontraindikationen($|\s*\(\s*absolute\s+Kontraindikationen\s*\)$)/u, # 6
         'Name'            => /^Name\s+des\s+Pr&auml;parates$/, # 1
@@ -28,7 +31,7 @@ module Docx2html
         'Präklin.'        => /^Pr&auml;klinische\s+Daten$/u, # 15
         'Pharm.kinetik'   =>  /^Pharmakokinetik($|\s*\((Absorption,\s*Distribution,\s*Metabolisms,\s*Elimination\s|Kinetik\s+spezieller\s+Patientengruppen)*\)$)|^Pharmacocin.tique?/iu, # 14
         'Sonstige H.'     => /^Sonstige\s*Hinweise($|\s*\(\s*(Inkompatibilit&auml;ten|Beeinflussung\s*diagnostischer\s*Methoden|Haltbarkeit|Besondere\s*Lagerungshinweise|Hinweise\s+f&uuml;r\s+die\s+Handhabung)\s*\)$)|^Remarques/u, # 16
-        'Schwangerschaft' => /^Schwangerschaft(,\s*|\s*\/\s*)Stillzeit$/u, # 9
+        'Schwangerschaft' => /^Schwangerschaft(,\s*|\s*\/\s*|\s+und\s+)Stillzeit$/u, # 9
         'Stand d. Info.'  => /^Stand\s+der\s+Information$|^Mise\s+.\s+jour$/iu, # 20
         'Unerw.Wirkungen' => /^Unerw&uuml;nschte\s+Wirkungen$/u, # 11
         'Überdos.'        => /^&Uuml;berdosierung$|^Surdosage$/u, # 12
@@ -40,7 +43,7 @@ module Docx2html
       }.each_pair do |chapter, regexp|
         if text =~ regexp
           next unless r.next.nil? # without line break
-          id = CGI.escape(text.gsub(/&(.)uml;/, '\1').gsub(/\s*\/\s*|\/|\s+/, '_').downcase)
+          id = escape(text)
           @indecies << {:text => chapter, :id => id}
           return tag(:h3, text, {:id => id})
         end
@@ -53,19 +56,13 @@ module Docx2html
       @container = tag(:div, [], {:id => 'container'})
     end
     private
-    def build_after_content
-      link = tag(:a, 'Top', {:href => ''})
-      tag(:div, link, {:id => 'footer'})
-    end
     def build_before_content
       if @indecies
         indices = []
-        if @indecies.first.has_key?(:tag) and @indecies.first[:tag] == :h2
-          indices << @indecies.shift
-        end
         @indecies.each do |index|
           if index.has_key?(:id)
-            indices << tag(:li, tag(:a, index[:text], {:href => "#" + index[:id]}))
+            link = tag(:a, index[:text], {:href => "#" + index[:id]})
+            indices << tag(:li, link)
           end
         end
         tag(:div, tag(:ul, indices), {:id => 'indecies'})
@@ -99,19 +96,13 @@ div#indecies {
 }
 div#indecies ul {
   margin:  0;
-  padding: 5px 0 0 25px;
+  padding: 25px 0 0 25px;
 }
 div#container {
   position: relative;
   padding:  5px 0 0 0;
   float:    top left;
   margin:   0 0 0 200px;
-}
-div#footer {
-  position:   relative;
-  float:      bottom right;
-  text-align: right;
-  padding:    0 25px 0 0;
 }
       CSS
       if @style == :frame
@@ -130,7 +121,7 @@ body{
 }
 div#indecies {
   position: absolute;
-  osition:  fixed;
+  padding:  0;
   height:   100%;
   left:     0;
   top:      0;
@@ -140,9 +131,6 @@ div#container {
   padding:  0;
   height:   100%;
   overflow: auto;
-}
-div#footer {
-  padding: 10px 30px 0 0;
 }
         FRAME
       end

data/lib/version.rb

@@ -2,5 +2,5 @@
 # encoding: utf-8
 
 module Docx2html
-  VERSION = "1.0.1"
+  VERSION = "1.0.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ydocx
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -13,7 +13,7 @@ date: 2012-05-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &23006340 !ruby/object:Gem::Requirement
+  requirement: &16773920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '3.10'
   type: :development
   prerelease: false
-  version_requirements: *23006340
+  version_requirements: *16773920
 - !ruby/object:Gem::Dependency
   name: hoe
-  requirement: &23005920 !ruby/object:Gem::Requirement
+  requirement: &16773500 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,7 +32,7 @@ dependencies:
         version: '2.13'
   type: :development
   prerelease: false
-  version_requirements: *23005920
+  version_requirements: *16773500
 description: ''
 email:
 - yasaka@ywesee.com,  zdavatz@ywesee.com