Class: Wp2txt::Runner

Inherits:
Object
  • Object
show all
Includes:
Wp2txt
Defined in:
lib/wp2txt.rb

Constant Summary

Constants included from Wp2txt

VERSION

Instance Method Summary collapse

Methods included from Wp2txt

#batch_file_mod, #chrref_to_utf!, #collect_files, #convert_characters!, #correct_inline_template!, #correct_separator, #decimal_format, #escape_nowiki!, #expand_template, #file_mod, #format_article!, #format_ref!, #format_wiki!, #make_reference!, #mndash!, #parse_wikitext, #post_request, #process_external_links!, #process_interwiki_links!, #process_nested_structure, #remove_directive!, #remove_emphasis!, #remove_hr!, #remove_inbetween!, #remove_table!, #remove_tag!, #remove_templates!, #rename, #sec_to_str, #special_chr!, #unescape_nowiki!

Constructor Details

#initialize(parent, input_file, output_dir = ".", tfile_size = 10, convert = true, strip_tmarker = false, limit_recur = 10) ⇒ Runner

Returns a new instance of Runner.



32
33
34
35
36
37
38
39
40
41
42
43
44
 
# File 'lib/wp2txt.rb', line 32

def initialize(parent, input_file, output_dir = ".", tfile_size = 10, convert = true, strip_tmarker = false, limit_recur = 10)
  @parent = parent
  @fp = nil
  
  @input_file = input_file
  @output_dir = output_dir
  @tfile_size = tfile_size
  @convert = convert
  @strip_tmarker = strip_tmarker
  
  #max number of recursive calls (global variable)
  $limit_recur = limit_recur
end

Instance Method Details

#extract ⇒ Object 



325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
 
# File 'lib/wp2txt.rb', line 325

def extract
  output_text = ""
  end_flag = false
  while text = get_newline
    @count ||= 0;@count += 1;
    @size_read ||=0;@size_read += text.bytesize
    @total_size += text.bytesize
    output_text << text
    end_flag = true if @total_size > (@tfile_size * 1024 * 1024)
    notify_parent
    # never close the file until the end of the page even if end_flag is on
    if end_flag && /<\/page/ =~ text 
      @fp.puts(output_text)
      output_text = ""
      @total_size = 0
      end_flag = false
      @fp.close
      @file_index += 1
      outfilename = File.join(@output_dir, @outfile_base + @file_index.to_s)
      @outfiles << outfilename
      @fp = File.open(outfilename, "w")
      next
    end
  end
  @fp.puts(output_text) if output_text != ""
  notify_parent(true)
  @parent.after
  @fp.close    
  rename(@outfiles)    
  @parent.msg("Processing finished", 1)
end

#extract_and_convert(&block) ⇒ Object 



235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
 
# File 'lib/wp2txt.rb', line 235

def extract_and_convert(&block)
  in_text = false
  in_message = false
  result_text = ""
  title = nil
  end_flag = false
  terminal_round = false
  output_text = ""

  while page = get_page
    xmlns = '<mediawiki xmlns="http://www.mediawiki.org/xml/export-0.5/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.mediawiki.org/xml/export-0.5/ http://www.mediawiki.org/xml/export-0.5.xsd" version="0.5" xml:lang="en">' + "\n"
    xml = xmlns + page + "</mediawiki>"

    input = Nokogiri::XML(xml, nil, 'UTF-8')
    page = input.xpath("//xmlns:text").first
    pp_title = page.parent.parent.at_css "title"
    title = pp_title.content
    next if /\:/ =~ title
    text = page.content

    # input = Oga.parse_xml(xml)
    # page = input.xpath("//xmlns:text").first
    # title = page.parent.parent.xpath("//xmlns:title").first.text
    # next if /\:/ =~ title
    # text = page.text

    # input = Ox.load(xml, :encoding => "UTF-8")
    # title = ""
    # text  = ""
    # input.nodes.first.nodes.each do |n|
    #   if n.name == "title"
    #     title = n.nodes.first
    #     if /\:/ =~ title
    #       title = ""
    #       break
    #     end
    #   elsif n.name == "revision"
    #     n.nodes.each do |o|
    #       if o.name == "text"
    #         text = o.nodes.first
    #         break
    #       end
    #     end
    #   end
    # end
    # next if title == "" || text == ""

    # remove all comment texts
    # and insert as many number of new line chars included in 
    # each comment instead
    text.gsub!(/\<\!\-\-(.*?)\-\-\>/m) do |content|
      num_of_newlines = content.count("\n")
      if num_of_newlines == 0
        ""
      else
        "\n" * num_of_newlines
      end
    end
    
    @count ||= 0;@count += 1;

    article = Article.new(text, title, @strip_tmarker)
    output_text += block.call(article)
    @total_size = output_text.bytesize

    # flagged when data exceeds the size of output file
    end_flag = true if @total_size > (@tfile_size * 1024 * 1024)

    #close the present file, then open a new one
    if end_flag
      @fp.puts(output_text)
      output_text = ""
      @total_size = 0
      end_flag = false
      @fp.close
      @file_index += 1
      outfilename = File.join(@output_dir, @outfile_base + @file_index.to_s)
      @outfiles << outfilename
      @fp = File.open(outfilename, "w")
      next
    end
  end
  @fp.puts(output_text) if output_text != ""
  notify_parent(true)
  @parent.after
  @fp.close    
  rename(@outfiles)    
  @parent.msg("Processing finished", 1)
end

#extract_text(&block) ⇒ Object

call this method to do the job



221
222
223
224
225
226
227
228
229
230
231
232
233
 
# File 'lib/wp2txt.rb', line 221

def extract_text(&block)
  prepare            
  if @convert
    if block
      extract_and_convert(&block)
    else
      extract_and_convert
    end
  else
    # output the original xml only split to files of the specified size
    extract
  end
end

#file_size(file) ⇒ Object 



46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
 
# File 'lib/wp2txt.rb', line 46

def file_size(file) 
  origin = Time.now
  size = 0;  unit = 10485760; star = 0; before = Time.now.to_f
  error_count = 10
  while true do
    begin
      a = file.read(unit)
    rescue => e
      a = nil
    end
    break unless a    

    present = Time.now.to_f
    size += a.size
    if present - before > 0.3
      star = 0 if star > 10
      star += 1
      before = present
    end    
  end
  time_elapsed = Time.now - origin
  size
end

#fill_buffer ⇒ Object

read text data from bz2 compressed file by 1 megabyte



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
 
# File 'lib/wp2txt.rb', line 149

def fill_buffer
  while true do
    begin
      new_lines = @file_pointer.read(10485760)
    rescue => e
      return nil
    end
    return nil unless new_lines

    # temp_buf is filled with text split by "\n"
    temp_buf = []
    ss = StringScanner.new(new_lines)
    while ss.scan(/.*?\n/m)             
      temp_buf << ss[0]
    end
    temp_buf << ss.rest unless ss.eos?

    new_first_line = temp_buf.shift
    if new_first_line[-1, 1] == "\n" # new_first_line.index("\n")
      @buffer.last <<  new_first_line
      @buffer << ""
    else
      @buffer.last << new_first_line
    end
    @buffer += temp_buf unless temp_buf.empty?
    if @buffer.last[-1, 1] == "\n" # @buffer.last.index("\n")
      @buffer << ""
    end
    break if @buffer.size > 1
  end
  return true
end

#get_newline ⇒ Object 



182
183
184
185
186
187
188
189
190
191
192
193
 
# File 'lib/wp2txt.rb', line 182

def get_newline
  @buffer ||= [""]   
  if @buffer.size == 1
    return nil unless fill_buffer
  end
  if @buffer.empty?
    return nil
  else 
    new_line = @buffer.shift
    return new_line
  end  
end

#get_page ⇒ Object 



195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
 
# File 'lib/wp2txt.rb', line 195

def get_page
  inside_page = false
  page = ""
  while line = get_newline
    notify_parent        
    @size_read ||=0; @size_read += line.bytesize
    
    if /<page>/ =~ line #
      page << line
      inside_page = true
      next
    elsif  /<\/page>/ =~ line #
      page << line
      inside_page = false
      break
    end
    page << line if inside_page
  end
  if page.empty?
    return false
  else
    return page.force_encoding("utf-8") rescue page
  end
end

#notify_parent(last = false) ⇒ Object

control the display of command line progressbar (or gui which is not available for now)



71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
 
# File 'lib/wp2txt.rb', line 71

def notify_parent(last = false)
  @last_time ||= Time.now.to_f
  @elapsed_sum ||= 0
  time_now = Time.now.to_f
  elapsed_from_last = (time_now - @last_time).to_i

  if elapsed_from_last > 0.3 || last

    @last_time = time_now        
    @elapsed_sum += elapsed_from_last
    gvalue = (@size_read.to_f / @infile_size.to_f * 100 * 100).to_i
    elt_str = sec_to_str(@elapsed_sum)
    if last
      eta_str = "00:00:00"
    else
      lines_persec = @size_read / @elapsed_sum if @elapsed_sum > 0
      eta_sec = (@infile_size - @size_read) / lines_persec
      eta_str = sec_to_str(eta_sec)
    end
    @parent.prg_update(gvalue, elt_str, eta_str)
  end
end

#prepare ⇒ Object

check the size of input file (bz2 or plain xml) when uncompressed



95
96
97
98
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
 
# File 'lib/wp2txt.rb', line 95

def prepare

  # if output_dir is not specified, output in the same directory
  # as the imput file
  if !@output_dir && @input_file
    @output_dir = File.dirname(@input_file)
  end

  # if input file is bz2 compressed, use bz2-ruby if available,
  # use command line bzip2 program otherwise.
  if /.bz2$/ =~ @input_file
    unless NO_BZ2
      file = Bzip2::Reader.new File.open(@input_file, "r:UTF-8")
      @parent.msg("Preparing ... This may take several minutes or more ", 0)         
      @infile_size = file_size(file)
      @parent.msg("... Done.", 1)
      file.close
      file = Bzip2::Reader.new File.open(@input_file, "r:UTF-8")
    else
      if RUBY_PLATFORM.index("win32")
        file = IO.popen("bunzip2.exe -c #{@input_file}")
      else
        file = IO.popen("bzip2 -c -d #{@input_file}") 
      end
      @parent.msg("Preparing ... This may take several minutes or more ", 0)         
      @infile_size = file_size(file)
      @parent.msg("... Done.", 1)
      file.close  # try to reopen since rewind method is unavailable
      if RUBY_PLATFORM.index("win32")
        file = IO.popen("bunzip2.exe -c #{@input_file}")
      else
        file = IO.popen("bzip2 -c -d #{@input_file}") 
      end
    end 
  else # meaning that it is a text file
    @infile_size = File.stat(@input_file).size
    file = open(@input_file)
  end

  #create basename of output file
  @outfile_base = File.basename(@input_file, ".*") + "-"            
  @total_size = 0
  @file_index = 1
  outfilename = File.join(@output_dir, @outfile_base + @file_index.to_s)
  @outfiles = []
  @outfiles << outfilename
  @fp = File.open(outfilename, "w")    
  @parent.before
  @parent.data_set(@input_file, 100 * 100)
  @file_pointer = file
  return true
end