ydocx 1.0.0

data/History.txt

@@ -0,0 +1,6 @@
+=== 1.0.0 / 01.05.2012
+
+* 1 major enhancement
+
+  * Birthday!
+

data/Manifest.txt

@@ -0,0 +1,12 @@
+History.txt
+Manifest.txt
+README.txt
+Rakefile
+bin/docx2html
+lib/docx2html/bin/docx2html
+lib/docx2html/lib/docx2html.rb
+lib/docx2html/lib/docx2html/builder.rb
+lib/docx2html/lib/docx2html/document.rb
+lib/docx2html/lib/docx2html/html_methods.rb
+lib/docx2html/lib/docx2html/parser.rb
+lib/fachinfo.rb

data/README.txt

@@ -0,0 +1,21 @@
+== ydocx - © ywesee GmbH
+
+* https://github.com/zdavatz/ydocx
+* Parsing docx files with Ruby and output them as HTML.
+
+== Supports
+
+* Tables
+* Uppercase letters, numbers
+* Lowercase letters, numbers
+* Umlaute
+* bold, italic, underline
+
+== Using the great libraries
+
+* nokogiri
+* htmlentities
+
+== License GPLv2.1
+
+* http://www.gnu.org/licenses/lgpl-2.1.html

data/Rakefile

@@ -0,0 +1,17 @@
+# -*- ruby -*-
+
+require 'rubygems'
+require 'hoe'
+
+# Hoe.plugin :compiler
+# Hoe.plugin :gem_prelude_sucks
+# Hoe.plugin :inline
+# Hoe.plugin :minitest
+# Hoe.plugin :racc
+# Hoe.plugin :rubyforge
+
+Hoe.spec 'ydocx' do
+
+  developer('Yasuhiro Asaka, Zeno R.R. Davatz', 'yasaka@ywesee.com,  zdavatz@ywesee.com')
+
+end

data/bin/docx2html

@@ -0,0 +1,27 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+require 'pathname'
+
+VERSION = "1.0.0"
+
+root = Pathname.new(__FILE__).realpath.parent.parent
+%w(
+  lib/docx2html/lib
+  lib
+).each do |lib|
+  $:.unshift root.join(lib) if $0 == __FILE__
+end
+require 'docx2html'
+
+if file = ARGV.first
+  unless File.exist?(file)
+    exit
+  else
+    # TODO args handling
+    if true
+      require 'fachinfo'
+    end
+    Docx2html::Document.open(file).to_html file, :style => true
+  end
+end

data/lib/docx2html/bin/docx2html

@@ -0,0 +1,16 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+require 'pathname'
+
+root = Pathname.new(__FILE__).realpath.parent.parent
+$:.unshift root.join('lib/docx2html') if $0 == __FILE__
+require 'docx2html'
+
+if file = ARGV.first
+  unless File.exist?(file)
+    exit
+  else
+    Docx2html::Document.open(file).to_html file, :style => true
+  end
+end

data/lib/docx2html/lib/docx2html/builder.rb

@@ -0,0 +1,100 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require 'nokogiri'
+require 'docx2html/html_methods'
+
+module Docx2html
+  class Builder
+    include HtmlMethods
+    attr_accessor :body, :indecies, :style, :title
+    def initialize(body)
+      @body = body
+      @container = {}
+      @indecies = []
+      @style = false
+      @title = ''
+      init
+      if block_given?
+        yield self
+      end
+    end
+    def init
+    end
+    def build
+      if @container.has_key?(:content)
+        @container[:content] = @body
+        @body = [@container]
+      end
+      if before_content = build_before_content
+        @body.unshift before_content
+      end
+      if after_content = build_after_content
+        @body.push after_content
+      end
+      body = ''
+      @body.each do |e|
+        body << build_tag(e[:tag], e[:content], e[:attributes])
+      end
+      builder = Nokogiri::HTML::Builder.new do |doc|
+        doc.html {
+          doc.head {
+            doc.meta :charset => 'utf-8'
+            doc.title @title
+            doc.style { doc << style } if @style
+          }
+          doc.body { doc << body }
+        }
+      end
+      builder.to_html.gsub(/\n/, '')
+    end
+    private
+    def build_after_content
+      nil
+    end
+    def build_before_content
+      nil
+    end
+    def build_tag(tag, content, attributes)
+      return '' if content.empty?
+      _content = ''
+      if content.is_a? Array
+        content.each do |c|
+          next if c.nil? or c.empty?
+          if c.is_a? Hash
+            _content << build_tag(c[:tag], c[:content], c[:attributes])
+          elsif c.is_a? String
+            _content << c.chomp.to_s
+          end
+        end
+      elsif content.is_a? Hash
+        _content = build_tag(content[:tag], content[:content], content[:attributes])
+      elsif content.is_a? String
+        _content = content
+      end
+      _tag = tag.to_s
+      _attributes = ''
+      unless attributes.empty?
+        attributes.each_pair do |k, v|
+          _attributes << " #{k.to_s}=#{v.to_s}"
+        end
+      end
+      "<#{_tag}#{_attributes}>#{_content}</#{_tag}>"
+    end
+    def style
+      style = <<-CSS
+table, tr, td {
+  border-collapse: collapse;
+  border:          1px solid gray;
+}
+table {
+  margin: 5px 0 5px 0;
+}
+td {
+  padding: 5px 10px;
+}
+      CSS
+      style.gsub(/\s\s+|\n/, ' ')
+    end
+  end
+end

data/lib/docx2html/lib/docx2html/document.rb

@@ -0,0 +1,51 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require 'pathname'
+require 'zip/zip'
+require 'docx2html/parser'
+require 'docx2html/builder'
+
+module Docx2html
+  class Document
+    attr_reader :contents
+    def self.open(file)
+      self.new(file)
+    end
+    def initialize(file)
+      @contents = nil
+      @indecies = nil
+      read(file)
+    end
+    def to_html(file='', options={})
+      html = ''
+      Builder.new(@contents) do |builder|
+        builder.title = @path
+        builder.style = options[:style]
+        if @indecies
+          builder.indecies = @indecies
+        end
+        html = builder.build
+      end
+      unless file.empty?
+        path = Pathname.new(file).realpath.sub_ext('.html')
+        File.open(path, 'w:utf-8') do |f|
+          f.puts html
+        end
+      else
+        html
+      end
+    end
+    private
+    def read(file)
+      @path = File.expand_path(file)
+      @zip = Zip::ZipFile.open(@path)
+      stream = @zip.find_entry('word/document.xml').get_input_stream
+      Parser.new(stream) do |parser|
+        @contents = parser.parse
+        @indecies = parser.indecies
+      end
+      @zip.close
+    end
+  end
+end

data/lib/docx2html/lib/docx2html/html_methods.rb

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+module Docx2html
+  module HtmlMethods
+    def tag(tag, content = [], attributes = {})
+      tag_hash = {
+        :tag        => tag,
+        :content    => content,
+        :attributes => attributes
+      }
+      tag_hash
+    end
+  end
+end

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

@@ -0,0 +1,213 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require 'nokogiri'
+require 'htmlentities'
+require 'docx2html/html_methods'
+
+module Docx2html
+  class Parser
+    include HtmlMethods
+    attr_accessor :indecies, :result
+    def initialize(stream)
+      @xml = Nokogiri::XML.parse(stream)
+      @coder = HTMLEntities.new
+      @indecies = []
+      @result = []
+      init
+      if block_given?
+        yield self
+      end
+    end
+    def init
+    end
+    def parse
+      @xml.xpath('//w:document//w:body').children.map do |node|
+        case node.node_name
+        when 'text'
+          @result << parse_paragraph(node)
+        when 'tbl'
+          @result << parse_table(node)
+        when 'image'
+          # pending
+        when 'p'
+          @result << parse_paragraph(node)
+        else
+          # skip
+        end
+      end
+      @result
+    end
+    private
+    def apply_fonts(rpr, text)
+      symbol = false
+      unless rpr.xpath('w:rFonts').empty?
+        rpr.xpath('w:rFonts').each do |font|
+          if font.values.include? 'Symbol'
+            symbol = true
+          end
+          break if symbol
+        end
+      end
+      if symbol
+        _text = ''
+        text.unpack('U*').each do |char|
+          _text << optional_replace(char.to_s(16))
+        end
+        text = _text
+      end
+      text
+    end
+    def apply_align(rpr, text)
+      unless rpr.xpath('w:vertAlign').empty?
+        script = rpr.xpath('w:vertAlign').first['val'].to_sym
+        if script == :subscript
+          text = tag(:sub, text)
+        elsif script == :superscript
+          text = tag(:sup, text)
+        end
+      end
+      text
+    end
+    def parse_as_block(r, text)
+      nil # default no block element
+    end
+    def optional_escape(text)
+      return text = '&nbsp;' if text.empty?
+      text.force_encoding('utf-8')
+      # NOTE
+      # :named only for escape at Builder
+      text = @coder.encode(text, :named)
+      text
+    end
+    def optional_replace(code)
+      code = '0x' + code
+      # NOTE
+      # replace with rsemble html character ref
+      # Symbol Font to HTML Character named ref
+      case code
+      when '0xf020' # '61472'
+        ""
+      when '0xf025' # '61477'
+        "%"
+      when '0xf02b' # '61482'
+        "*"
+      when '0xf02b' # '61483'
+        "+"
+      when '0xf02d' # '61485'
+        "-"
+      when '0xf02f' # '61487'
+        "/"
+      when '0xf03c' # '61500'
+        "&lt;"
+      when '0xf03d' # '61501'
+        "="
+      when '0xf03e' # '61502'
+        "&gt;"
+      when '0xf040' # '61504'
+        "&cong;"
+      when '0xf068' # '61544'
+        "&eta;"
+      when '0xf071' # '61553'
+        "&theta;"
+      when '0xf06d' # '61549'
+        "&mu;"
+      when '0xf0a3' # '61603'
+        "&le;"
+      when '0xf0ab' # '61611'
+        "&harr;"
+      when '0xf0ac' # '61612'
+        "&larr;"
+      when '0xf0ad' # '61613'
+        "&uarr;"
+      when '0xf0ae' # '61614'
+        "&rarr;"
+      when '0xf0ad' # '61615'
+        "&darr;"
+      when '0xf0b1' # '61617'
+        "&plusmn;"
+      when '0xf0b2' # '61618'
+        "&Prime;"
+      when '0xf0b3' # '61619'
+        "&ge;"
+      when '0xf0b4' # '61620'
+        "&times;"
+      when '0xf0b7' # '61623'
+        "&sdot;"
+      else
+        #p "code : " + ("&#%s;" % code)
+        #p "hex  : " + code.hex.to_s
+        #p "char : " + @coder.decode("&#%s;" % code)
+        #@coder.decode("&#%s;" % code.hex.to_s)
+      end
+    end
+    def parse_image
+      # pending
+    end
+    def parse_paragraph(node)
+      paragraph = tag :p
+      node.xpath('w:r').each do |r|
+        unless r.xpath('w:t').empty?
+          paragraph[:content] << parse_text(r)
+        else
+          unless r.xpath('w:tab').empty?
+            if paragraph[:content].last != '&nbsp;' # as a space
+              paragraph[:content] << optional_escape('')
+            end
+          end
+          unless r.xpath('w:sym').empty?
+            code = r.xpath('w:sym').first['char'].downcase # w:char
+            paragraph[:content] << optional_replace(code)
+          end
+        end
+      end
+      paragraph
+    end
+    def parse_table(node)
+      table = tag :table
+      node.xpath('w:tr').each do |tr|
+        cells = tag :tr
+        tr.xpath('w:tc').each do |tc|
+          attributes = {}
+          tc.xpath('w:tcPr').each do |tcpr|
+            if span = tcpr.xpath('w:gridSpan') and !span.empty?
+              attributes[:colspan] = span.first['val'] # w:val
+            end
+          end
+          cell = tag :td, [], attributes
+          tc.xpath('w:p').each do |p|
+            cell[:content] << parse_paragraph(p)
+          end
+          cells[:content] << cell
+        end
+        table[:content] << cells
+      end
+      table
+    end
+    def parse_text(r)
+      text = r.xpath('w:t').map(&:text).join('')
+      text = optional_escape(text)
+      if rpr = r.xpath('w:rPr')
+        text = apply_fonts(rpr, text)
+        if block = parse_as_block(r, text)
+          block
+        else
+          # inline tag
+          text = apply_align(rpr, text)
+          unless rpr.xpath('w:u').empty?
+            text = tag(:span, text, {:style => "text-decoration:underline;"})
+          end
+          unless rpr.xpath('w:i').empty?
+            text = tag(:em, text) 
+          end
+          unless rpr.xpath('w:b').empty?
+            text = tag(:strong, text)
+          end
+          text
+        end
+      else
+        text
+      end
+    end
+  end
+end

data/lib/docx2html/lib/docx2html.rb

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require 'docx2html/document'
+
+module Docx2html
+end

data/lib/fachinfo.rb

@@ -0,0 +1,112 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require 'cgi'
+
+module Docx2html
+  class Parser
+    private
+    def parse_as_block(r, text)
+      if r.parent.previous.nil?
+        # first line is package name
+        return tag(:h2, text)
+      end
+      text = text.strip
+      # TODO
+      # Franzoesisch
+      chapters = {
+        'Dos./Anw.'       => /^Dosierung\s*\/\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*)Anwendungsmöglichkeiten$|^Indications/u, # 4
+        'Interakt.'       => /^Interaktionen$|^Interactions/u, # 8
+        'Kontraind.'      => /^Kontraindikationen($|\s*\(\s*absolute\s+Kontraindikationen\s*\)$)/u, # 6
+        'Name'            => /^Name\s+des\s+Präparates$/, # 1
+        'Packungen'       => /^Packungen($|\s*\(\s*mit\s+Angabe\s+der\s+Abgabekategorie\s*\)$)/u, # 18
+        'Präklin.'        => /^Präklinische\s+Daten$/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*\(\s*(Inkompatibilitäten|Beeinflussung\s*diagnostischer\s*Methoden|Haltbarkeit|Besondere\s*Lagerungshinweise|Hinweise\s+für\s+die\s+Handhabung)\s*\)$)|^Remarques/u, # 16
+        'Schwangerschaft' => /^Schwangerschaft(,\s*|\s*\/\s*)Stillzeit$/u, # 9
+        'Stand d. Info.'  => /^Stand\s+der\s+Information$|^Mise\s+.\s+jour$/iu, # 20
+        'Unerw.Wirkungen' => /^Unerwünschte\s+Wirkungen$/u, # 11
+        'Überdos.'        => /^Überdosierung$|^Surdosage$/u, # 12
+        'Warn.hinw.'      => /^Warnhinweise\s+und\s+Vorsichtsmassnahmen($|\s*\/\s*(relative\s+Kontraindikationen|Warnhinweise\s*und\s*Vorsichtsmassnahmen)$)/u, # 7
+        'Fahrtücht.'      => /^Wirkung\s+auf\s+die\s+Fahrtüchtigkeit\s+und\s+auf\s+das\s+Bedienen\s+von\s+Maschinen$/u, # 10
+        'Swissmedic-Nr.'  => /^Zulassungsnummer($|\s*\(\s*Swissmedic\s*\)$)/u, # 17
+        'Reg.Inhaber'     => /^Zulassungsinhaberin($|\s*\(\s*Firma\s+und\s+Sitz\s+gemäss\s*Handelsregisterauszug\s*\))/u, # 19
+        'Zusammens.'      => /^Zusammensetzung($|\s*\/\s*(Wirkstoffe|Hilsstoffe)$)/u, # 2
+      }.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)
+          @indecies << {:text => chapter, :id => id}
+          return tag(:h3, text, {:id => id})
+        end
+      end
+      nil
+    end
+  end
+  class Builder
+    def init
+      @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 = []
+        @indecies.each do |index|
+          indices << tag(:li, tag(:a, index[:text], {:href => "#" + index[:id]}))
+        end
+        tag(:div, tag(:ul, indices), {:id => 'indecies'})
+      end
+    end
+    def style
+      style = <<-CSS
+table, tr, td {
+  border-collapse: collapse;
+  border: 1px solid gray;
+}
+table {
+  margin: 5px 0 5px 0;
+}
+td {
+  padding: 5px 10px;
+}
+body {
+  position: relative;
+  padding:  0 0 20px 0;
+  margin:   0px;
+  width:    100%;
+  height:   auto;
+}
+div#indecies {
+  position: relative;
+  padding:  0px;
+  float:    left;
+  width:    200px;
+}
+div#indecies ul {
+  margin:  0;
+  padding: 0 0 0 25px;
+}
+div#container {
+  position:    relative;
+  padding:     0px;
+  float:       top left;
+  margin-left: 200px;
+}
+div#footer {
+  position:      relative;
+  float:         bottom right;
+  text-align:    right;
+  padding-right: 25px;
+}
+      CSS
+      style.gsub(/\s\s+|\n/, ' ')
+    end
+  end
+end

metadata

@@ -0,0 +1,85 @@
+--- !ruby/object:Gem::Specification
+name: ydocx
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+  prerelease: 
+platform: ruby
+authors:
+- Yasuhiro Asaka, Zeno R.R. Davatz
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-05-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: &21539280 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.10'
+  type: :development
+  prerelease: false
+  version_requirements: *21539280
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: &21538860 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.13'
+  type: :development
+  prerelease: false
+  version_requirements: *21538860
+description: ''
+email:
+- yasaka@ywesee.com,  zdavatz@ywesee.com
+executables:
+- docx2html
+extensions: []
+extra_rdoc_files:
+- History.txt
+- Manifest.txt
+- README.txt
+files:
+- History.txt
+- Manifest.txt
+- README.txt
+- Rakefile
+- bin/docx2html
+- lib/docx2html/bin/docx2html
+- lib/docx2html/lib/docx2html.rb
+- lib/docx2html/lib/docx2html/builder.rb
+- lib/docx2html/lib/docx2html/document.rb
+- lib/docx2html/lib/docx2html/html_methods.rb
+- lib/docx2html/lib/docx2html/parser.rb
+- lib/fachinfo.rb
+homepage: https://github.com/zdavatz/ydocx
+licenses: []
+post_install_message: 
+rdoc_options:
+- --main
+- README.txt
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: ydocx
+rubygems_version: 1.8.15
+signing_key: 
+specification_version: 3
+summary: ''
+test_files: []