doc2text 0.3.3 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: f2530e3597409c35637493d9d8e9842b2f70f005
-  data.tar.gz: 304eb91cfa9b109bfa853cbc7d9736a14b7817bd
+SHA256:
+  metadata.gz: 7b9b5aeaa63d276696f0f4f716242b181d8d3aef2e47861053c03f9623cdf498
+  data.tar.gz: a9ac2a3e0314334dda782f8ce8ef0d5a0691015ae70da0cc7a7fd79b2d6d7cd2
 SHA512:
-  metadata.gz: 9ff147cd7f87f233a6fbbc9270e682426ffc3b5df514a5b7ca2b16b0405a4048901cb53972d5264c853eabce7532b9bb386f97847e5b072189119ec616b2961f
-  data.tar.gz: f992a33120ae4273966a54a15e02768abf4baa16473808775e938fed21163882e46c46333dfa7ea9a63cf5bd9e4ef02de4bbb8f50b7d9ab86dbe5a4a8ee6d3cc
+  metadata.gz: 88fcdc3ade712a061c62641dd7713274c676f41d37c7020348ad401e0e7af3a86b07a3726a057870396ee68a290867fccf635d3191c8376b45850507e2f566e9
+  data.tar.gz: a96c1f4cbfbb42079f5e5d6eea757531d7d7e852e01724c40cc58f94ee5ebd27e700bdffc221cc7c7202a3686a6f3c40d8a5e153f07dcdca7aa4fd542b13eac9

data/bin/doc2text

@@ -0,0 +1,43 @@
+#!/usr/bin/env ruby
+
+$LOAD_PATH.unshift File.dirname(__FILE__) + '/../lib'
+require 'doc2text'
+require 'optparse'
+
+options = {}
+opt_parse = OptionParser.new do |opts|
+  opts.banner = "Usage: doc2text document.odt output.md
+  or:  doc2text [OPTION]... -s input[.odt] -o output[.md]\n\n"
+
+  opts.on('-s FILE', '--source FILE', 'Odt FILE document to be processed') do |file|
+    options[:source] = file
+  end
+
+  opts.on('-o FILE', '--output FILE', 'Output to markdown document FILE') do |file|
+    options[:output] = file
+  end
+
+  opts.on_tail('-h', '--help', 'Show this message') do
+    puts opts
+    exit
+  end
+end
+
+begin
+  opt_parse.parse!
+  if options.empty?
+    if ARGV.size == 2
+      options[:source], options[:output] = *ARGV
+    else
+      puts opt_parse
+      exit
+    end
+  end
+rescue OptionParser::InvalidOption, OptionParser::MissingArgument
+  puts $!.to_s
+  puts opt_parse
+  exit
+end
+
+
+Doc2Text::Resolution.parse_and_save options[:source], options[:output]

data/lib/doc2text.rb

@@ -2,11 +2,17 @@ require 'nokogiri'
 #require 'nokogiri/xml'
 require 'fileutils'
 
+require 'doc2text/xml_based_document_file'
+require 'doc2text/generic_xml_nodes'
 require 'doc2text/resolution'
-require 'doc2text/odt'
-require 'doc2text/odt_xml_node'
-require 'doc2text/odt_xml_namespaces'
-require 'doc2text/markdown_odt_parser'
 require 'doc2text/errors'
 
-require 'doc2text/styles_parser'
+require 'doc2text/odt/odt'
+require 'doc2text/odt/odt_xml_namespaces'
+require 'doc2text/odt/markdown_odt_parser'
+
+require 'doc2text/docx/docx'
+require 'doc2text/docx/markdown_docx_parser'
+require 'doc2text/docx/docx_xml_namespaces'
+
+require 'doc2text/styles_parser'

data/lib/doc2text/docx/docx.rb

@@ -0,0 +1,31 @@
+module Doc2Text
+  module Docx
+    class Document < XmlBasedDocument::DocumentFile
+
+      def self.parse_and_save(input, output_filename)
+        docx = new input
+        begin
+          docx.unpack
+          styles_xml_root = docx.parse_styles
+          output = File.open output_filename, 'w'
+          markdown = Markdown::DocxParser.new output, styles_xml_root
+          begin
+            docx.parse markdown
+          ensure
+            markdown.close
+          end
+        ensure
+          docx.clean
+        end
+      end
+
+      def contains_extracted_files?
+        File.exist? File.join(extract_path, '[Content_Types].xml')
+      end
+
+      def extract_extension
+        'unpacked_docx'
+      end
+    end
+  end
+end

data/lib/doc2text/docx/docx_xml_namespaces.rb

@@ -0,0 +1,55 @@
+module Doc2Text
+  module Docx
+    module XmlNodes
+      class Node < XmlBasedDocument::XmlNodes::Node
+        def self.create_node(prefix, name, parent = nil, attrs = [], markdown_odt_parser = nil)
+          begin
+            clazz = XmlNodes.const_get "#{prefix.capitalize}::W#{name}"
+          rescue NameError => e
+            # markdown_odt_parser.logger.warn "No such <#{prefix}:#{name}> found"
+            Generic.new(parent, attrs, prefix, name, markdown_odt_parser)
+          else
+            clazz.new(parent, attrs, prefix, name, markdown_odt_parser)
+          end
+        end
+
+        def body?
+          false
+        end
+      end
+
+      class PlainText < XmlBasedDocument::XmlNodes::PlainText
+        def body?
+          false
+        end
+      end
+
+      class Generic < Node
+      end
+
+      module W
+        class Wbody < Node
+          def body?
+            true
+          end
+        end
+
+        class Wbr < Node
+          def open
+            '<br/>'
+          end
+        end
+
+        class Wp < Node
+          def open
+            "\n"
+          end
+
+          def close
+            "\n"
+          end
+        end
+      end
+    end
+  end
+end

data/lib/doc2text/docx/markdown_docx_parser.rb

@@ -0,0 +1,81 @@
+require 'logger'
+
+module Doc2Text
+  module Markdown
+    class DocxParser < Nokogiri::XML::SAX::Document
+      def initialize(output, styles_xml_root = nil)
+        @styles_xml_root = styles_xml_root
+        @output = output
+        @automatic_styles = {}
+      end
+
+      def start_element_namespace(name ,attrs = [], prefix = nil, uri = nil, ns = [])
+        unless @xml_root
+          @xml_root = @current_node = Docx::XmlNodes::Node.create_node prefix, name, nil, attrs, self
+        else
+          new_node = Docx::XmlNodes::Node.create_node prefix, name, @current_node, attrs, self
+          @current_node.children << new_node
+          @current_node = new_node
+        end
+      end
+
+      def end_element_namespace(name, prefix = nil, uri = nil)
+        if @current_node.parent and @current_node.parent.body?
+          @output << @current_node.expand
+          @current_node.delete
+        end
+        @current_node = @current_node.parent
+      end
+
+      def characters(string)
+        unless string.strip.empty?
+          plain_text = Docx::XmlNodes::PlainText.new(string)
+          @current_node.children << plain_text
+        end
+      end
+
+      def close
+        @output.close
+      end
+
+      def print_tree(node)
+        puts node
+        node.children.each do |child|
+          print_tree child
+        end
+      end
+
+      # Select nodes xpath style
+      # - supports selecting from the root node
+      def xpath(string)
+        patterns = string.split '|'
+        raise Doc2Text::XmlError, 'it does not support this xpath syntax' if patterns.length == 0
+        result = []
+        patterns.each do |pattern|
+          if /^(\/[\w:\-]+)+$/ =~ pattern
+            path = pattern.scan /[\w:\-]+/
+            result += xpath_search_nodes(path, @xml_root)
+            result += xpath_search_nodes(path, @styles_xml_root) if @styles_xml_root
+          else
+            raise Doc2Text::XmlError, 'it does not support this xpath syntax'
+          end
+        end
+        result
+      end
+
+      def xpath_search_nodes(path, xml_root)
+        seek_nodes = [xml_root]
+        path.each_with_index do |xml_name, index|
+          seek_nodes.select! { |node| node.xml_name == xml_name }
+          seek_nodes = seek_nodes.map(&:children).flatten unless index == path.length - 1
+          break if seek_nodes.empty?
+        end
+        seek_nodes
+      end
+
+      def logger
+        @logger ||= Logger.new(STDOUT)
+      end
+    end
+  end
+end

data/lib/doc2text/{odt_xml_node.rb → generic_xml_nodes.rb}

@@ -1,25 +1,16 @@
 module Doc2Text
-  module Odt
+  module XmlBasedDocument
     module XmlNodes
-      module Node
+      class Node
         attr_reader :parent, :children, :attrs, :prefix, :name
         attr_accessor :text
 
-        def self.create_node(prefix, name, parent = nil, attrs = [], markdown_odt_parser = nil)
-          begin
-            clazz = XmlNodes.const_get "#{titleize prefix}::#{titleize name}"
-          rescue NameError => e
-            # markdown_odt_parser.logger.warn "No such <#{prefix}:#{name}> found"
-            Generic.new(parent, attrs, prefix, name, markdown_odt_parser)
-          else
-            clazz.new(parent, attrs, prefix, name, markdown_odt_parser)
+        def self.inherited(subclass)
+          def subclass.titleize(tag)
+            tag.split('-').map(&:capitalize).join
           end
         end
 
-        def self.titleize(tag)
-          tag.split('-').map(&:capitalize).join
-        end
-
         def initialize(parent = nil, attrs = [], prefix = nil, name = nil, markdown_odt_parser = nil)
           @parent, @attrs, @prefix, @name, @xml_parser = parent, attrs, prefix, name, markdown_odt_parser
           @children = []
@@ -42,10 +33,6 @@ module Doc2Text
           ''
         end
 
-        def office_text?
-          false
-        end
-
         def delete
           return true unless @children
           @children.each { |child| child.delete }
@@ -74,24 +61,16 @@ module Doc2Text
           delete
           expanded.clone
         end
+      end
 
-        def not_enclosing?
-          !root? && parent.class.not_enclosing_tags && parent.class.not_enclosing_tags.find do |tag|
-            @prefix == parent.prefix && @name == tag
-          end
-        end
+      class PlainText < Node
 
-        def self.included(base)
-          base.extend ClassMethods
-        end
+        attr_accessor :text
 
-        module ClassMethods
-          attr_reader :not_enclosing_tags
+        alias_method :expand, :text
 
-          def not_enclosing(tag)
-            @not_enclosing_tags ||= []
-            @not_enclosing_tags << tag
-          end
+        def initialize(text)
+          @text = text
         end
       end
     end

data/lib/doc2text/odt/odt.rb

@@ -0,0 +1,43 @@
+module Doc2Text
+  module Odt
+    class Document < XmlBasedDocument::DocumentFile
+
+      def extract_extension
+        'unpacked_odt'
+      end
+
+      def self.parse_and_save(input, output_filename)
+        odt = new input
+        begin
+          odt.unpack
+          styles_xml_root = odt.parse_styles
+          output = File.open output_filename, 'w'
+          markdown = Markdown::OdtParser.new output, styles_xml_root
+          begin
+            odt.parse markdown
+          ensure
+            markdown.close
+          end
+        ensure
+          odt.clean
+        end
+      end
+
+      def parse_styles
+        styles_parser = Doc2Text::Odt::StylesParser.new
+        xml = Nokogiri::XML::SAX::Parser.new(styles_parser)
+        xml.parse open 'styles.xml'
+        styles_parser.xml_root
+      end
+
+      def parse(markdown)
+        parser = Nokogiri::XML::SAX::Parser.new(markdown) # { |config| config.strict}
+        parser.parse open 'content.xml'
+      end
+
+      def contains_extracted_files?
+        [File.join(extract_path, 'content.xml'), File.join(extract_path, 'mimetype')].all? { |file| File.exist?(file) }
+      end
+    end
+  end
+end

data/lib/doc2text/{odt_xml_namespaces.rb → odt/odt_xml_namespaces.rb}

@@ -1,37 +1,40 @@
 module Doc2Text
   module Odt
     module XmlNodes
-      class PlainText
-        include Node
-
-        attr_accessor :text
-
-        alias_method :expand, :text
+      class Node < XmlBasedDocument::XmlNodes::Node
+        def self.create_node(prefix, name, parent = nil, attrs = [], markdown_odt_parser = nil)
+          begin
+            clazz = XmlNodes.const_get "#{titleize prefix}::#{titleize name}"
+          rescue NameError => e
+            # markdown_odt_parser.logger.warn "No such <#{prefix}:#{name}> found"
+            Generic.new(parent, attrs, prefix, name, markdown_odt_parser)
+          else
+            clazz.new(parent, attrs, prefix, name, markdown_odt_parser)
+          end
+        end
 
-        def initialize(text)
-          @text = text
+        def office_text?
+          false
         end
       end
 
-      class Generic
-        include Node
+      class PlainText < XmlBasedDocument::XmlNodes::PlainText
       end
 
+      class Generic < Node
+      end
       #
       # These are the namespaces available in the open document format
       # http://docs.oasis-open.org/office/v1.2/os/OpenDocument-v1.2-os.html
       #
       module Office
-        class AutomaticStyles
-          include Node
+        class AutomaticStyles < Node
         end
 
-        class DocumentContent
-          include Node
+        class DocumentContent < Node
         end
 
-        class Text
-          include Node
+        class Text < Node
 
           def office_text?
             true
@@ -52,8 +55,7 @@ module Doc2Text
       module Presentation; end
       module Script; end
       module Table
-        class TableRow
-          include Node
+        class TableRow < Node
 
           def expand
             header_delimiter = parent.children.count >= 2 && parent.children[1] == self ? "\n|---|---|" : ''
@@ -63,8 +65,7 @@ module Doc2Text
           end
         end
 
-        class TableCell
-          include Node
+        class TableCell < Node
 
           def open
             ' | '
@@ -72,12 +73,10 @@ module Doc2Text
         end
       end
       module Style
-        class Style
-          include Node
+        class Style < Node
         end
 
-        class TextProperties
-          include Node
+        class TextProperties < Node
         end
       end
       module XslFoCompatible; end
@@ -86,48 +85,73 @@ module Doc2Text
       module Of; end
 
       module Text
-        def initialize(parent = nil, attrs = [], prefix = nil, name = nil, markdown_odt_parser = nil)
-          super parent, attrs, prefix, name
-          @xml_parser = markdown_odt_parser
-          style_index = attrs.index { |attr| attr.prefix == 'text' && attr.localname == 'style-name' }
-          @enclosing_style = []
-          if style_index and fetch_style?
-            elem_style = find_style attrs[style_index].value
-            fetch_style elem_style
+          def initialize(parent = nil, attrs = [], prefix = nil, name = nil, markdown_odt_parser = nil)
+            super parent, attrs, prefix, name
+            @xml_parser = markdown_odt_parser
+            style_index = attrs.index { |attr| attr.prefix == 'text' && attr.localname == 'style-name' }
+            @enclosing_style = []
+            if style_index and fetch_style?
+              elem_style = find_style attrs[style_index].value
+              fetch_style elem_style
+            end
           end
-        end
 
-        def fetch_style?
-          true
-        end
+          def fetch_style?
+            true
+          end
 
-        def fetch_style(elem_style)
-          if elem_style
-            elem_style.children.select { |style_property| style_property.xml_name == 'style:text-properties' }.each { |text_property|
-              text_property.attrs.each { |attr|
-                if attr.prefix == 'style'
-                  if attr.localname == 'font-style-complex' && attr.value == 'italic'
-                    @enclosing_style << '_'
-                  elsif attr.localname == 'font-weight-complex' && attr.value == 'bold'
-                    @enclosing_style << '**'
+          def fetch_style(elem_style)
+            if elem_style
+              elem_style.children.select { |style_property| style_property.xml_name == 'style:text-properties' }.each { |text_property|
+                text_property.attrs.each { |attr|
+                  if attr.prefix == 'style'
+                    if attr.localname == 'font-style-complex' && attr.value == 'italic'
+                      @enclosing_style << '_'
+                    elsif attr.localname == 'font-weight-complex' && attr.value == 'bold'
+                      @enclosing_style << '**'
+                    end
                   end
-                end
+                }
               }
-            }
+            end
+          end
+
+          def find_style(style_name)
+            styles = @xml_parser.xpath '/office:document-content/office:automatic-styles/style:style'
+            styles.find { |style| style.attrs.index { |attr| attr.prefix == 'style' && attr.localname == 'family' } &&
+                style.attrs.index { |attr| attr.prefix == 'style' && attr.localname == 'name' && attr.value == style_name } }
           end
-        end
 
-        def find_style(style_name)
-          styles = @xml_parser.xpath '/office:document-content/office:automatic-styles/style:style'
-          styles.find { |style| style.attrs.index { |attr| attr.prefix == 'style' && attr.localname == 'family' } &&
-              style.attrs.index { |attr| attr.prefix == 'style' && attr.localname == 'name' && attr.value == style_name } }
+        # http://docs.oasis-open.org/office/v1.2/os/OpenDocument-v1.2-os-part1.html#__RefHeading__1419212_253892949
+        class H < Node
+          include Text
+          def initialize(parent = nil, attrs = [], prefix = nil, name = nil, markdown_odt_parser = nil)
+            super parent, attrs, prefix, name, markdown_odt_parser
+            outline_level_index = attrs.index { |attr| attr.prefix == 'text' && attr.localname == 'outline-level' }
+            if outline_level_index and fetch_style?
+              @elem_outline_level = attrs[outline_level_index].value.to_i
+            else
+              @elem_outline_level = 0
+            end
+
+          end
+
+          def self.style_family
+            'paragraph'
+          end
+
+          def open
+            "\n#{'#' * @elem_outline_level} "
+          end
+
+          def close
+            "\n\n"
+          end
         end
 
         # http://docs.oasis-open.org/office/v1.2/os/OpenDocument-v1.2-os-part1.html#__RefHeading__1419256_253892949
-        class P
-          include Node
+        class P < Node
           include Text
-
           def initialize(parent = nil, attrs = [], prefix = nil, name = nil, markdown_odt_parser = nil)
             super parent, attrs, prefix, name, markdown_odt_parser
           end
@@ -145,8 +169,7 @@ module Doc2Text
           end
         end
 
-        class LineBreak
-          include Node
+        class LineBreak < Node
 
           def open
             '<br/>'
@@ -154,8 +177,7 @@ module Doc2Text
         end
 
         # http://docs.oasis-open.org/office/v1.2/os/OpenDocument-v1.2-os-part1.html#__RefHeading__1419264_253892949
-        class Span
-          include Node
+        class Span < Node
           include Text
 
           def self.style_family
@@ -178,10 +200,8 @@ module Doc2Text
         end
 
         # http://docs.oasis-open.org/office/v1.2/os/OpenDocument-v1.2-os-part1.html#__RefHeading__1415154_253892949
-        class ListItem
-          include Node
+        class ListItem < Node
           include Text
-
           def expand
             result = "* #{@children.map(&:expand).join.strip.gsub /\n{2,}/, "\n"}\n"
             delete
@@ -193,8 +213,7 @@ module Doc2Text
           end
         end
 
-        class List
-          include Node
+        class List < Node
           include Text
 
           def open

data/lib/doc2text/resolution.rb

@@ -2,13 +2,8 @@ module Doc2Text
   class Resolution
     def self.parse_and_save(source, output)
       case File.extname source
-        when '.doc', '.docx'
-          mid_name = File.join(File.dirname(output),
-                               File.basename(source, File.extname(source)) + '.odt')
-          system "soffice --headless --convert-to odt #{source}  --outdir #{File.dirname output}"
-          source = mid_name
-          Doc2Text::Odt::Document.parse_and_save source, output
-          File.delete(mid_name)
+        when '.docx'
+          Doc2Text::Docx::Document.parse_and_save source, output
         else
           Doc2Text::Odt::Document.parse_and_save source, output
       end

data/lib/doc2text/styles_parser.rb

@@ -5,9 +5,9 @@ module Doc2Text
 
       def start_element_namespace(name ,attrs = [], prefix = nil, uri = nil, ns = [])
         unless @xml_root
-          @xml_root = @current_node = Odt::XmlNodes::Node.create_node prefix, name, nil, attrs, self
+          @xml_root = @current_node = Doc2Text::Odt::XmlNodes::Node.create_node prefix, name, nil, attrs, self
         else
-          new_node = Odt::XmlNodes::Node.create_node prefix, name, @current_node, attrs, self
+          new_node = Doc2Text::Odt::XmlNodes::Node.create_node prefix, name, @current_node, attrs, self
           @current_node.children << new_node
           @current_node = new_node
         end

data/lib/doc2text/xml_based_document_file.rb

@@ -0,0 +1,48 @@
+require 'zip'
+
+module Doc2Text
+  module XmlBasedDocument
+    class DocumentFile
+      def initialize(document_path)
+        @document_path = document_path
+      end
+
+      def unpack
+        Zip::File.open(@document_path) {
+            |zip_file|
+          Dir.mkdir(extract_path)
+          zip_file.each do |entry|
+            zipped_file_extract_path = File.join extract_path, entry.name
+            FileUtils.mkdir_p File.dirname(zipped_file_extract_path)
+            zip_file.extract entry, zipped_file_extract_path
+          end
+        }
+      end
+
+      def contains_extracted_files?
+        false
+      end
+
+      def clean
+        if File.exist?(extract_path) and contains_extracted_files?
+          FileUtils.rm_r extract_path
+        else
+          puts 'Failed to clean temp files'
+        end
+      end
+
+      # Open file from the current odt
+      def open(filename)
+        File.open File.join(extract_path, filename), 'r'
+      end
+
+      def extract_extension
+        'unpacked'
+      end
+
+      def extract_path
+        File.join File.dirname(@document_path), ".#{File.basename(@document_path)}_#{extract_extension}"
+      end
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: doc2text
 version: !ruby/object:Gem::Version
-  version: 0.3.3
+  version: 0.4.0
 platform: ruby
 authors:
 - Valentin Aitken
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-25 00:00:00.000000000 Z
+date: 2019-01-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -16,57 +16,62 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.8'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.3
+        version: 1.8.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.8'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.3
+        version: 1.8.2
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.1'
+        version: '1.2'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.1.6
+        version: 1.2.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.1'
+        version: '1.2'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.1.6
+        version: 1.2.2
 description: Parses odt to markdown
-email: bostko@gmail.com
+email: valentin@nalisbg.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- bin/doc2text
 - lib/doc2text.rb
+- lib/doc2text/docx/docx.rb
+- lib/doc2text/docx/docx_xml_namespaces.rb
+- lib/doc2text/docx/markdown_docx_parser.rb
 - lib/doc2text/errors.rb
-- lib/doc2text/markdown_odt_parser.rb
-- lib/doc2text/odt.rb
-- lib/doc2text/odt_xml_namespaces.rb
-- lib/doc2text/odt_xml_node.rb
+- lib/doc2text/generic_xml_nodes.rb
+- lib/doc2text/odt/markdown_odt_parser.rb
+- lib/doc2text/odt/odt.rb
+- lib/doc2text/odt/odt_xml_namespaces.rb
 - lib/doc2text/resolution.rb
 - lib/doc2text/styles_parser.rb
+- lib/doc2text/xml_based_document_file.rb
 homepage: http://doc2text.com
 licenses:
-- GPL
+- Apache-2.0
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -84,9 +89,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.7.8
 signing_key: 
 specification_version: 4
 summary: Translates odt to markdown
 test_files: []
-has_rdoc: 

data/lib/doc2text/odt.rb

@@ -1,80 +0,0 @@
-require 'zip'
-
-module Doc2Text
-  module Odt
-    class Document
-      EXTRACT_EXTENSION = 'unpacked_odt'
-
-      def self.parse_and_save(input, output_filename)
-        odt = new input
-        begin
-          odt.unpack
-          styles_xml_root = odt.parse_styles
-          output = File.open output_filename, 'w'
-          markdown = Markdown::OdtParser.new output, styles_xml_root
-          begin
-            odt.parse markdown
-          ensure
-            markdown.close
-          end
-        ensure
-          odt.clean
-        end
-      end
-
-      def parse_styles
-        styles_parser = Doc2Text::Odt::StylesParser.new
-        xml = Nokogiri::XML::SAX::Parser.new(styles_parser)
-        xml.parse open 'styles.xml'
-        styles_parser.xml_root
-      end
-
-      def parse(markdown)
-        parser = Nokogiri::XML::SAX::Parser.new(markdown) # { |config| config.strict}
-        parser.parse open 'content.xml'
-      end
-
-      def initialize(document_path)
-        @document_path = document_path
-      end
-
-      def unpack
-        Zip::File.open(@document_path) {
-            |zip_file|
-          Dir.mkdir(extract_path)
-          zip_file.each do |entry|
-            zipped_file_extract_path = File.join extract_path, entry.name
-            FileUtils.mkdir_p File.dirname(zipped_file_extract_path)
-            zip_file.extract entry, zipped_file_extract_path
-          end
-        }
-      end
-
-      def clean
-        if [extract_path, File.join(extract_path, 'content.xml'), File.join(extract_path, 'mimetype')].all? { |file| File.exist?(file) }
-          FileUtils.rm_r extract_path
-        end
-      end
-
-      # Open file from the current odt
-      def open(filename)
-        File.open File.join(extract_path, filename), 'r'
-      end
-
-      # Parse xml file from the current odt
-      def xml_file(filename, rood_node_name)
-        Nokogiri::XML::Document.parse(open(filename)) { |config| config.strict }
-        root_node = doc.root
-        if root_node.name != rood_node_name or root_node.namespace.prefix != 'office'
-          raise XmlError, 'Document does not have correct root element'
-        else
-          open(filename)
-        end
-      end
-
-      def extract_path
-        File.join File.dirname(@document_path), ".#{File.basename(@document_path)}_#{EXTRACT_EXTENSION}"
-      end
-    end
-  end
-end