Class: MsDocx::Document

Inherits:
Object
  • Object
show all
Defined in:
lib/ms_docx/document.rb

Overview

Examples:

doc = MsDocx::Document.open('1.docx')

puts doc.paragraphs.first.text
# => 'some text'

Author:

  • Alex Mercury

Constant Summary collapse

CONTENT_ENTRY = 
'word/document.xml'

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(file_path, *args) ⇒ Document

Returns a new instance of Document.



24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
 
# File 'lib/ms_docx/document.rb', line 24

def initialize(file_path, *args)
  if File.exist? file_path
    @file_path = file_path
    @temp_file_path = file_path.sub(/\.docx/, '~temp.docx')
    @docx_zip = Zip::File.open(file_path)
  else
    raise MsDocx::Errors::FileNotExist, "File '#{file_path}' doesn't exist ❗"
  end

  @doc = @docx_zip.find_entry(CONTENT_ENTRY).get_input_stream.read

  @xml = Nokogiri::XML::Document.parse @doc

  @paragraphs = []

  @xml.xpath('//w:body//w:p').each do |w_p|
    @paragraphs << MsDocx::Paragraph.new(w_p)
  end


  # @xml.xpath('//w:p//w:r//w:t').each do |p|
  #
  #
  #   puts p.content
  #
  #
  #   p.content = 'test'
  #
  #
  # end
  #

  #
  #
  # File.open(new_file, 'wb') {|f| f.write(buffer.string) }
end

Class Method Details

.open(file_path) ⇒ MsDocx::Document

Open .docx file

Parameters:

  • file_path (String) —

    file path

Returns:



18
19
20
 
# File 'lib/ms_docx/document.rb', line 18

def open(file_path)
  MsDocx::Document.new(file_path)
end

Instance Method Details

#each_paragraph(&block) ⇒ Object 



65
66
67
68
69
70
71
72
73
74
75
76
77
78
 
# File 'lib/ms_docx/document.rb', line 65

def each_paragraph(&block)
  @paragraphs.each do |paragraph|
    block.call(paragraph)
  end






  # block.call(self)


end

#paragraphs ⇒ Object 



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

def paragraphs
  @paragraphs
end

#save_file(file_path) ⇒ Object 



99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
 
# File 'lib/ms_docx/document.rb', line 99

def save_file(file_path)

  @buffer = Zip::OutputStream.write_buffer do |out|
    @docx_zip.entries.each do |e|
      if e.name == CONTENT_ENTRY

        # doc = get_xml_doc_from_stream(e.get_input_stream.read)

        # doc.xpath('//w:body//w:p').each do |pt|

          # pt.xpath(pt.path + '//w:t').

          # p pt.to_xml

          # block.call(pt)

          # p pt.to_xml

          # w_r_list = pt.xpath(pt.path + '//w:r')

          # if w_r_list.length > 1
          #   w_r_list[1..-1].each{|pp| pp.remove }

            # p pt.to_xml
            # p w_r_list.to_xml
          # end

          # pt

          # p w_r_list.to_xml


          # w_r_list.first.xpath(w_r_list.first.path + '//w:t').map{|pp| block.call(pp)} if w_r_list.first


          # p nil
          # p nil
          # p nil


        # end


        # p doc.to_xml

        out.put_next_entry(CONTENT_ENTRY)
        out.write self.to_xml
      else
        out.put_next_entry(e.name)
        e.write_to_zip_output_stream out
      end
    end
  end


  File.open(file_path, 'wb') {|f| f.write(@buffer.string) }
end

#to_text ⇒ Object 



80
81
82
 
# File 'lib/ms_docx/document.rb', line 80

def to_text
  @paragraphs.map(&:text).join("\n")
end

#to_xml ⇒ Object 



84
85
86
87
88
89
90
91
92
93
94
95
96
97
 
# File 'lib/ms_docx/document.rb', line 84

def to_xml

  body = @xml.at('//w:body')

  body.children = ''

  @paragraphs.each do |paragraph|
    body.add_child(paragraph.to_xml)
  end

  @xml.at('//w:document').children = body

  @xml.to_xml
end