Class: BioInterchange::TextMining::PDFxXMLReader::MyListener

Inherits:
Object
  • Object
show all
Includes:
REXML::StreamListener
Defined in:
lib/biointerchange/textmining/pdfx_xml_reader.rb

Instance Method Summary collapse

Constructor Details

#initialize ⇒ MyListener

Returns a new instance of MyListener.



56
57
58
59
60
61
62
 
# File 'lib/biointerchange/textmining/pdfx_xml_reader.rb', line 56

def initialize
  @map = {}
  
  #sections can nest, so "stack" them
  @map['sec_s'] = []
  @map['sec_l'] = []
end

Instance Method Details

#document ⇒ Object 



158
159
160
 
# File 'lib/biointerchange/textmining/pdfx_xml_reader.rb', line 158

def document
  @doc
end

#tag_end(name) ⇒ Object

TODO add deal with <author> type tags



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
156
 
# File 'lib/biointerchange/textmining/pdfx_xml_reader.rb', line 121

def tag_end(name)
  #puts "tag_end: #{name}"
  if name =~ /^job$/
    @map['id'] = false
    @map['id_done'] = true
  elsif name =~ /^article-title$/
    @map['title'] = false
    dc = BioInterchange::TextMining::Content.new(@map['title_s'], @map['title_l'], BioInterchange::TextMining::Content::TITLE, @process)
    dc.setContext(@doc)
    @doc.add(dc)
    @map['title_done'] = true
  elsif name =~ /^abstract$/
    @map['abs'] = false
    dc = BioInterchange::TextMining::Content.new(@map['abs_s'], @map['abs_l'], BioInterchange::TextMining::Content::ABSTRACT, @process)
    dc.setContext(@doc)
    @doc.add(dc)
    @map['abs_done'] = true
  elsif name =~ /^body$/
    @map['body'] = false
    dc = BioInterchange::TextMining::Content.new(@map['body_s'], @map['body_l'], BioInterchange::TextMining::Content::SECTION, @process)
    dc.setContext(@doc)
    @doc.add(dc)
    @map['body_done'] = true
  elsif name =~ /^article$/
    @map['art'] = false
    dc = BioInterchange::TextMining::Content.new(@map['art_s'], @map['art_l'], BioInterchange::TextMining::Content::DOCUMENT, @process)
    dc.setContext(@doc)
    @doc.add(dc)
    @map['art_done'] = true
  elsif name =~ /^section$/
    raise 'Error with section stack, stacks not equal in size' unless  @map['sec_s'].size == @map['sec_l'].size
    dc = BioInterchange::TextMining::Content.new(@map['sec_s'].pop, @map['sec_l'].pop, BioInterchange::TextMining::Content::SECTION, @process)
    dc.setContext(@doc)
    @doc.add(dc)
  end
end

#tag_start(name, attr) ⇒ Object 



64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
 
# File 'lib/biointerchange/textmining/pdfx_xml_reader.rb', line 64

def tag_start(name, attr)
  #puts "tag_start: #{name}"
  if name =~ /^job$/
    raise BioInterchange::Exceptions::InputFormatError, 'Input document XML has multiple <job> tags, cannot parse multiple documents within a single file.' if @map['id_done']
    @map['id'] = true
  elsif name =~ /^article-title$/
    raise BioInterchange::Exceptions::InputFormatError, 'Input document XML has multiple <article-title> tags defined, cannot parse multiple documents within a single file.' if @map['title_done']
    @map['title'] = true
    @map['title_s'] = @map['art_l']
    @map['title_l'] = 0
  elsif name =~ /^abstract$/
    raise BioInterchange::Exceptions::InputFormatError, 'Input document XML has multiple <abstract> tags defined, cannot parse multiple documents within a single file.' if @map['abs_done']
    @map['abs'] = true
    @map['abs_s'] = @map['art_l']
    @map['abs_l'] = 0
  elsif name =~ /^body$/
    raise BioInterchange::Exceptions::InputFormatError, 'Input document XML has multiple <body> tags defined, cannot parse multiple documents within a single file.' if @map['body_done']
    @map['body'] = true
    @map['body_s'] = @map['art_l']
    @map['body_l'] = 0
  elsif name =~ /^article$/
    raise BioInterchange::Exceptions::InputFormatError, 'Input document XML has multiple <article> tags defined, cannot parse multiple documents within a single file.' if @map['art_done']
    @map['art'] = true
    @map['art_s'] = 0
    @map['art_l'] = 0
  elsif name =~ /^section$/
    raise BioInterchange::Exceptions::InputFormatError, 'Error with section stack, stacks not equal in size: Possibly not a well formed XML input file. Check <section> tags all match up and do not overlap (nesting is fine).' unless  @map['sec_s'].size == @map['sec_l'].size
    @map['sec_s'].push @map['art_l']
    @map['sec_l'].push 0
  end
end

#text(data) ⇒ Object 



96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
 
# File 'lib/biointerchange/textmining/pdfx_xml_reader.rb', line 96

def text(data)
  if @map['art']
    @map['art_l'] += data.length
  end
  
  if @map['id']
    @doc = BioInterchange::TextMining::Document.new("http://pdfx.cs.man.ac.uk/" + data)
  elsif @map['title']
    @map['title_l'] += data.length
  elsif @map['abs']
    @map['abs_l'] += data.length
  end
  if @map['body']
    @map['body_l'] += data.length
  end
  if @map['sec_l'].size != 0
    #add length to *all* current sections
    @map['sec_l'].size.times do |i|
      @map['sec_l'][i] += data.length
    end
  end
end