swordfish 0.0.12 → 0.0.13

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    ODBlMzJjZjVkMmUxZTdlNmVmMTUxOTI1NjFiMTI3NmNjMGVmNWM5OQ==
+    MDZkZmUxZDg4NTE1Y2RmNzJiMWVkOTVmYTIyOGU5Yzk5NjQ0ODI5Yw==
   data.tar.gz: !binary |-
-    NWQ4ZDMxOTJkN2VmZThkMmM3MDNmYjM5OWZjMWZkYjcxMTBkNjdmNQ==
+    YzkzMmVhNzkzNTExMjI3YjUyMTVlYzMzNGVhMWU2N2VkZGFhMmMxZA==
 SHA512:
   metadata.gz: !binary |-
-    ZTc0NTZkNjExNGFkODBjZTBkZjk1YTJiNzliMGZjZmRhY2I0MzQyNjQzNTUw
-    MDQ4YWE2YTAwMTYzN2EzYjY1Mzk5YjhiOTZmOWRmOTE3OTQyMTkyZDRkMzNh
-    NDNjMzUwNjZhOTg1YzIzZWViODk5NDZmNTQyYjcwNzBkZDhmN2I=
+    MWE1NDQxNzJkMWJjMzY0MDQyOGViMmUxNTI3NzUyN2RlMzFmNWJhMzMzODRl
+    NzA1YjI4ZWMwMmJiMTVhMzk5MmVmNWY4M2E3ZTg1ZWI2MjEyNWZmODIzNjdl
+    NGE1OWIzMjc5Y2ZkNWI1NmQ3NmI4MTcyNDM3NGEwNmM2OGM4OTU=
   data.tar.gz: !binary |-
-    OGQzZThlMmIzNGNlNDBhY2QwNThiNzYyMmY4ZmZmNGQ3ZmJhZGYyZGEyYjFl
-    MDg1ZTQ4ZjllNGEyODU5NmYzMzUxMGNiODUzMzhlYjI3MTY0OTY2MDU2NTg1
-    YzY4MGU0ZWM0NjkyNmMzMmZlZTU0NTM5YTk5MDY5YWY5ZTM4ZjM=
+    N2UwNTRkYWIwNTA1NWNlNzgwMTJlNWE4N2FjODU0NzVhMWU1Y2FhNjI3MWY1
+    MmM1ZmUxMDIxZjczZWUxNDU3ODg0NGZmOGMwZmIzOTZhZTlhZDc0ZGU0ODIy
+    MjFiNjhkOWVjNDViMmMwNzQ3YThmZjg2YWVmYjY1YmE5NjdiMDA=

data/README.md

@@ -1,4 +1,54 @@
-swordfish
-=====
+![Swordfish](https://raw.githubusercontent.com/voikya/swordfish/master/swordfish.png)
 
-Document parser
+Swordfish is a simple document processing library for Ruby. It enables the conversion of Microsoft Word XML documents (.docx) into clean, semantic HTML5, without all the mess that normal export     tools or copy-and-paste would produce.
+
+Features
+-----
+
+Swordfish currently supports identifying the following features:
+
+- Paragraphs
+- Formatting: bold, italic, underline, superscript, subscript, strikethrough
+- Links
+- Lists (including nested lists)
+- Tables
+- Footnotes and Endnotes
+- Images (except for Word Drawings)
+
+Installation
+-----
+
+Swordfish is available through RubyGems, so you can install it with `gem install swordfish`.
+
+Converting a Document
+-----
+
+Converting a Word document into HTML just requires two calls: one to parse the document, and one to generate the markup:
+
+```ruby
+require 'swordfish'
+Swordfish.open('~/Documents/my_word_doc.docx').to_html
+```
+
+Additional configuration options may be provided by calling `settings` with a hash of parameters prior to generating the final markup. For instance, if you want to enable footnotes (appearing as a block at the end of the HTML document), enable the `footnotes` option:
+
+```ruby
+Swordfish.open('~/Documents/my_word_doc.docx').settings(:footnotes => true).to_html
+```
+
+The following settings are currently available (all are boolean, and default to `false`)
+
+- `guess_headers` — When true, attempt to identify headers within the text and assign them the appropriate `<h1>` through `<h6>` tags. When false, all text will be presented as normal paragraphs.
+- `footnotes` — When true, preserve footnote and endnote content in a block at the end of the generated HTML, including links back to the original reference points in the text. When false, footnotes will be ignored.
+- `smart_br` — When true, attempt to clean up unnecessary linebreaks often present in Word markup, such as at the very beginning or end of a paragraph. When false, linebreaks will be preserved exactly as in the original Word markup.
+- `full_document` — When true, the generated HTML will represent a complete HTML document, including a doctype and header. When false, the output will be an HTML fragment suitable for insertion into the DOM, for example.
+
+Images within the Word document are available after parsing by calling the `images` method, which returns a hash of file names and temporary files.
+
+```ruby
+# Print the file name and size of each image in a document
+doc = Swordfish.open('~/Documents/my_word_doc.docx')
+doc.images.each do |filename, tempfile|
+  puts "#{filename}: #{tempfile.size}"
+end
+```

data/lib/swordfish/formats/docx/document.rb

@@ -67,7 +67,9 @@ module Swordfish
         @xml.xpath('//w:body').children.each do |node|
           case node.name
             when 'p'
-              if node.xpath('.//w:numPr').length == 0 && (@buffer.is_a?(Swordfish::Node::List) ? node.xpath('.//w:ind[@w:left]').length.zero? : true)
+              no_numbering_prop = node.xpath('.//w:numPr').length.zero? || node.xpath('.//w:numPr/w:ilvl | .//w:numPr/w:numId').length.zero?
+              not_multiparagraph_list_item = (@buffer.is_a?(Swordfish::Node::List) ? node.xpath('.//w:ind[@w:left]').length.zero? : true)
+              if no_numbering_prop && not_multiparagraph_list_item
                 # Regular paragraph
                 # (The buffer check makes sure that this isn't an indented paragraph immediately after a list item,
                 # which means we're most likely dealing with a multi-paragraph list item)

data/lib/swordfish/formats/docx/parser.rb

@@ -53,7 +53,7 @@ module Swordfish
                     if instruction =~ /^\s*HYPERLINK/
                       # A hyperlink
                       complex_field = Swordfish::Node::Hyperlink.new
-                      complex_field.href = instruction.match(/^\s*HYPERLINK (?:\\l )?"([^"]+)"/).captures[0]
+                      complex_field.href = instruction.match(/^\s*HYPERLINK (?:"" )?(?:\\l )?"([^"]+)"/).captures[0]
                     else
                       # Anything else
                       complex_field = Swordfish::Node::Text.new
@@ -127,7 +127,7 @@ module Swordfish
         if node.xpath(".//w:numPr/w:ilvl").length.zero?
           para = Swordfish::Node::Paragraph.new
           _node_parse_runs(node).each {|r| para.append(r)}
-          @buffer.last_list_item(:recurse => true).wrap_children(Swordfish::Node::Text, Swordfish::Node::Paragraph)
+          @buffer.last_list_item(:recurse => true).wrap_children(Swordfish::Node::Inline, Swordfish::Node::Paragraph)
           @buffer.last_list_item(:recurse => true).append para
           return
         end

data/lib/swordfish/nodes/base.rb

@@ -85,6 +85,9 @@ module Swordfish
       end
     end
 
+    class Inline < Base
+    end
+
     class BadContentError < Exception
     end
   end

data/lib/swordfish/nodes/hyperlink.rb

@@ -2,7 +2,7 @@
 
 module Swordfish
   module Node
-    class Hyperlink < Base
+    class Hyperlink < Inline
 
       attr_accessor :href
 

data/lib/swordfish/nodes/text.rb

@@ -2,7 +2,7 @@
 
 module Swordfish
   module Node
-    class Text < Base
+    class Text < Inline
 
       # Override Base append because a text node should never have children
       def append(node)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: swordfish
 version: !ruby/object:Gem::Version
-  version: 0.0.12
+  version: 0.0.13
 platform: ruby
 authors:
 - Martin Posthumus
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-10 00:00:00.000000000 Z
+date: 2014-08-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler