Class: Docx::Document

Inherits:
Object
  • Object
show all
Includes:
SimpleInspect
Defined in:
lib/docx/document.rb

Overview

The Document class wraps around a docx file and provides methods to interface with it.

# get a Docx::Document for a docx file in the local directory
doc = Docx::Document.open("test.docx")

# get the text from the document
puts doc.text

# do the same thing in a block
Docx::Document.open("test.docx") do |d|
  puts d.text
end

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Methods included from SimpleInspect

#inspect

Constructor Details

#initialize(path_or_io, options = {}) ⇒ Document

Returns a new instance of Document.



27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
 
# File 'lib/docx/document.rb', line 27

def initialize(path_or_io, options = {})
  @replace = {}

  # if path-or_io is string && does not contain a null byte
  if (path_or_io.instance_of?(String) && !/\u0000/.match?(path_or_io))
    raise Errno::EIO.new('Invalid file format') if !File.extname(path_or_io).eql?('.docx')
    @zip = Zip::File.open(path_or_io)
  else
    @zip = Zip::File.open_buffer(path_or_io)
  end

  document = @zip.glob('word/document*.xml').first
  raise Errno::ENOENT if document.nil?

  @document_xml = document.get_input_stream.read
  @doc = Nokogiri::XML(@document_xml)
  load_styles
  yield(self) if block_given?
ensure
  @zip.close unless @zip.nil?
end

Instance Attribute Details

#doc ⇒ Object (readonly)

Returns the value of attribute doc.



25
26
27
 
# File 'lib/docx/document.rb', line 25

def doc
  @doc
end

#styles ⇒ Object (readonly)

Returns the value of attribute styles.



25
26
27
 
# File 'lib/docx/document.rb', line 25

def styles
  @styles
end

#xml ⇒ Object (readonly)

Returns the value of attribute xml.



25
26
27
 
# File 'lib/docx/document.rb', line 25

def xml
  @xml
end

#zip ⇒ Object (readonly)

Returns the value of attribute zip.



25
26
27
 
# File 'lib/docx/document.rb', line 25

def zip
  @zip
end

Class Method Details

.open(path, &block) ⇒ Object

With no associated block, Docx::Document.open is a synonym for Docx::Document.new. If the optional code block is given, it will be passed the opened docx file as an argument and the Docx::Document oject will automatically be closed when the block terminates. The values of the block will be returned from Docx::Document.open. call-seq:

open(filepath) => file
open(filepath) {|file| block } => obj



61
62
63
 
# File 'lib/docx/document.rb', line 61

def self.open(path, &block)
  new(path, &block)
end

Instance Method Details

#bookmarks ⇒ Object 



69
70
71
72
73
74
75
76
 
# File 'lib/docx/document.rb', line 69

def bookmarks
  bkmrks_hsh = {}
  bkmrks_ary = @doc.xpath('//w:bookmarkStart').map { |b_node| parse_bookmark_from b_node }
  # auto-generated by office 2010
  bkmrks_ary.reject! { |b| b.name == '_GoBack' }
  bkmrks_ary.each { |b| bkmrks_hsh[b.name] = b }
  bkmrks_hsh
end

#default_paragraph_style ⇒ Object 



174
175
176
 
# File 'lib/docx/document.rb', line 174

def default_paragraph_style
  @styles.at_xpath("w:styles/w:style[@w:type='paragraph' and @w:default='1']/w:name/@w:val").value
end

#document_properties ⇒ Object

This stores the current global document properties, for now



50
51
52
53
54
55
 
# File 'lib/docx/document.rb', line 50

def document_properties
  {
    font_size: font_size,
    hyperlinks: hyperlinks
  }
end

#each_paragraph ⇒ Object

Deprecated

Iterates over paragraphs within document call-seq:

each_paragraph => Enumerator



113
114
115
 
# File 'lib/docx/document.rb', line 113

def each_paragraph
  paragraphs.each { |p| yield(p) }
end

#font_size ⇒ Object

Some documents have this set, others don’t. Values are returned as half-points, so to get points, that’s why it’s divided by 2.



88
89
90
91
92
93
94
 
# File 'lib/docx/document.rb', line 88

def font_size
  size_value = @styles&.at_xpath('//w:docDefaults//w:rPrDefault//w:rPr//w:sz/@w:val')&.value

  return nil unless size_value

  size_value.to_i / 2
end

#hyperlink_relationships ⇒ Object 



103
104
105
 
# File 'lib/docx/document.rb', line 103

def hyperlink_relationships
  @rels.xpath("//xmlns:Relationship[contains(@Type,'hyperlink')]")
end

#hyperlinks ⇒ Object

Hyperlink targets are extracted from the document.xml.rels file



97
98
99
100
101
 
# File 'lib/docx/document.rb', line 97

def hyperlinks
  hyperlink_relationships.each_with_object({}) do |rel, hash|
    hash[rel.attributes['Id'].value] = rel.attributes['Target'].value
  end
end

#paragraphs ⇒ Object 



65
66
67
 
# File 'lib/docx/document.rb', line 65

def paragraphs
  @doc.xpath('//w:document//w:body/w:p').map { |p_node| parse_paragraph_from p_node }
end

#replace_entry(entry_path, file_contents) ⇒ Object 



170
171
172
 
# File 'lib/docx/document.rb', line 170

def replace_entry(entry_path, file_contents)
  @replace[entry_path] = file_contents
end

#save(path) ⇒ Object

Save document to provided path call-seq:

save(filepath) => void



131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
 
# File 'lib/docx/document.rb', line 131

def save(path)
  update
  Zip::OutputStream.open(path) do |out|
    zip.each do |entry|
      next unless entry.file?

      out.put_next_entry(entry.name)
      value = @replace[entry.name] || zip.read(entry.name)

      out.write(value)
    end

  end
  zip.close
end

#stream ⇒ Object

Output entire document as a StringIO object



148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'lib/docx/document.rb', line 148

def stream
  update
  stream = Zip::OutputStream.write_buffer do |out|
    zip.each do |entry|
      next unless entry.file?

      out.put_next_entry(entry.name)

      if @replace[entry.name]
        out.write(@replace[entry.name])
      else
        out.write(zip.read(entry.name))
      end
    end
  end

  stream.rewind
  stream
end

#style_name_of(style_id) ⇒ Object 



178
179
180
 
# File 'lib/docx/document.rb', line 178

def style_name_of(style_id)
  styles_configuration.style_of(style_id).name
end

#styles_configuration ⇒ Object 



182
183
184
 
# File 'lib/docx/document.rb', line 182

def styles_configuration
  @styles_configuration ||= Elements::Containers::StylesConfiguration.new(@styles.dup)
end

#tables ⇒ Object 



82
83
84
 
# File 'lib/docx/document.rb', line 82

def tables
  @doc.xpath('//w:document//w:body//w:tbl').map { |t_node| parse_table_from t_node }
end

#to_html ⇒ Object

Output entire document as a String HTML fragment



124
125
126
 
# File 'lib/docx/document.rb', line 124

def to_html
  paragraphs.map(&:to_html).join("\n")
end

#to_s ⇒ Object Also known as: text

call-seq:

to_s -> string



119
120
121
 
# File 'lib/docx/document.rb', line 119

def to_s
  paragraphs.map(&:to_s).join("\n")
end

#to_xml ⇒ Object 



78
79
80
 
# File 'lib/docx/document.rb', line 78

def to_xml
  Nokogiri::XML(@document_xml)
end