Module: Wp2txt

Included in:
Article, Runner
Defined in:
lib/wp2txt/progressbar.rb,
lib/wp2txt.rb,
lib/wp2txt/utils.rb,
lib/wp2txt/mw_api.rb,
lib/wp2txt/article.rb,
lib/wp2txt/version.rb

Overview

Ruby/ProgressBar - a text progress bar library

Copyright © 2001-2005 Satoru Takabayashi <[email protected]>

All rights reserved.
This is free software with ABSOLUTELY NO WARRANTY.

You can redistribute it and/or modify it under the terms of Ruby’s license.

Defined Under Namespace

Classes: Article, CmdProgbar, NewProgressBar, ProgressBar, ReversedProgressBar, Runner

Constant Summary collapse

VERSION = 
"0.7.7"

Instance Method Summary collapse

Instance Method Details

#batch_file_mod(dir_path, &block) ⇒ Object

modify files under a directry (recursive)



370
371
372
373
374
375
376
377
378
 
# File 'lib/wp2txt/utils.rb', line 370

def batch_file_mod(dir_path, &block)
  if FileTest.directory?(dir_path)
    collect_files(dir_path).each do |file|
      yield file if FileTest.file?(file)
    end
  else   
    yield dir_path if FileTest.file?(dir_path)
  end
end

#chrref_to_utf!(num_str) ⇒ Object 



276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
 
# File 'lib/wp2txt/utils.rb', line 276

def chrref_to_utf!(num_str)
  begin
    num_str.gsub!($chrref_to_utf_regex) do
      if $1 == 'x'
        ch = $2.to_i(16)
      else
        ch = $2.to_i
      end
      hi = ch>>8
      lo = ch&0xff
      u = "\377\376" << lo.chr << hi.chr
      u.encode("UTF-8", "UTF-16")
    end
  rescue StandardError
    return nil
  end
  return true
end

#collect_files(str, regex = nil) ⇒ Object

collect filenames recursively



344
345
346
347
348
349
350
351
 
# File 'lib/wp2txt/utils.rb', line 344

def collect_files(str, regex = nil)
  regex ||= //
  text_array = Array.new
  Find.find(str) do |f|
    text_array << f if regex =~ f
  end
  text_array.sort
end

#convert_characters!(text, has_retried = false) ⇒ Object 



90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
 
# File 'lib/wp2txt/utils.rb', line 90

def convert_characters!(text, has_retried = false)
  begin 
    text << "" 
    chrref_to_utf!(text)
    special_chr!(text)
    
  rescue # detect invalid byte sequence in UTF-8

    if has_retried
      puts "invalid byte sequence detected"
      puts "******************************"
      File.open("error_log.txt", "w") do |f|
        f.write text
      end
      exit
    else
      text.encode!("UTF-16")
      text.encode!("UTF-8")
      convert_characters!(text, true)
    end
  end
end

#correct_inline_template!(str) ⇒ Object 



316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
 
# File 'lib/wp2txt/utils.rb', line 316

def correct_inline_template!(str)
  str.gsub!($remove_inline_regex) do
    key = $1
    if $onset_bar_regex =~ key
      result = key
    elsif
      info = key.split("|")
      type_code = info.first
      case type_code
      when $type_code_regex
        out = info[-1]
      else
        if $leave_template
          out = "{" + info.collect{|i|i.chomp}.join("|") + "}"
        else
          out = ""
        end
      end
      out
    else
      ""
    end
  end
end

#correct_separator(input) ⇒ Object

take care of difference of separators among environments



381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
 
# File 'lib/wp2txt/utils.rb', line 381

def correct_separator(input)
  if input.is_a?(String)
    ret_str = String.new
    if RUBY_PLATFORM.index("win32")
      ret_str = input.gsub("/", "\\")
    else
      ret_str = input.gsub("\\", "/")
    end
    return ret_str
  elsif input.is_a?(Array)
    ret_array = Array.new
    input.each do |item|
      ret_array << correct_separator(item)
    end
    return ret_array
  end
end

#decimal_format(i) ⇒ Object 



429
430
431
432
 
# File 'lib/wp2txt/utils.rb', line 429

def decimal_format(i)
  str = i.to_s.reverse
  return str.scan(/.?.?./).join(',').reverse
end

#escape_nowiki!(str) ⇒ Object

methods used from format_wiki ####################



184
185
186
187
188
189
190
191
192
193
194
195
196
 
# File 'lib/wp2txt/utils.rb', line 184

def escape_nowiki!(str)
  if @nowikis
    @nowikis.clear
  else
    @nowikis = {}
  end
  str.gsub!($escape_nowiki_regex) do
    nowiki = $1
    nowiki_id = nowiki.object_id
    @nowikis[nowiki_id] = nowiki
    "<nowiki-#{nowiki_id}>"
  end
end

#expand_template(uri, template, page) ⇒ Object 



22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
 
# File 'lib/wp2txt/mw_api.rb', line 22

def expand_template(uri, template, page)
  text = URI.escape(template)
  title = URI.escape(page)
  data = {"action" => "expandtemplates",
          "format" => "json",
          "text"   => text,
          "title"  => title}
  jsn = post_request(uri, data)
  hash = JSON.parse(jsn)
  begin
    result = hash["expandtemplates"]["*"]
    result = special_chr(result)
    return chrref_to_utf(result).gsub("{{", "&#123;&#123;").gsub("}}", "&#125;&#125;")
  rescue => e      
    puts "ERROR!"
    p e
    exit
    template
  end
end

#file_mod(file_path, backup = false, &block) ⇒ Object

modify a file using block/yield mechanism



354
355
356
357
358
359
360
361
362
363
364
365
366
367
 
# File 'lib/wp2txt/utils.rb', line 354

def file_mod(file_path, backup = false, &block)
  File.open(file_path, "r") do |fr|
    str = fr.read
    newstr = yield(str)
    str = newstr unless newstr == nil
    File.open("temp", "w") do |tf|
      tf.write(str)
    end
  end

  File.rename(file_path, file_path + ".bak")
  File.rename("temp", file_path)
  File.unlink(file_path + ".bak") unless backup
end

#format_article!(text) ⇒ Object 



121
122
123
124
125
126
127
128
129
130
131
132
133
 
# File 'lib/wp2txt/utils.rb', line 121

def format_article!(text)
  remove_directive!(text)
  remove_emphasis!(text)
  mndash!(text)
  make_reference!(text)
  format_ref!(text)
  remove_hr!(text)
  remove_tag!(text)
  convert_characters!(text)    
  correct_inline_template!(text) unless $leave_template
  remove_templates!(text) unless $leave_template
  remove_table!(text) unless $leave_table
end

#format_ref!(page) ⇒ Object 



310
311
312
313
314
 
# File 'lib/wp2txt/utils.rb', line 310

def format_ref!(page)
  ###### do nothing for now

  # page.gsub!($format_ref_regex) do

  # end

end

#format_wiki!(text, has_retried = false) ⇒ Object 



112
113
114
115
116
117
118
119
 
# File 'lib/wp2txt/utils.rb', line 112

def format_wiki!(text, has_retried = false)
  escape_nowiki!(text)

  process_interwiki_links!(text)
  process_external_links!(text)

  unescape_nowiki!(text)      
end

#make_reference!(str) ⇒ Object 



303
304
305
306
307
308
 
# File 'lib/wp2txt/utils.rb', line 303

def make_reference!(str)
  str.gsub!($make_reference_regex_a, "\n")
  str.gsub!($make_reference_regex_b, "")
  str.gsub!($make_reference_regex_c, "[ref]")
  str.gsub!($make_reference_regex_d, "[/ref]")
end

#mndash!(str) ⇒ Object 



295
296
297
 
# File 'lib/wp2txt/utils.rb', line 295

def mndash!(str)
  str.gsub!($mndash_regex, "–")
end

#parse_wikitext(uri, wikitext, page) ⇒ Object 



43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/wp2txt/mw_api.rb', line 43

def parse_wikitext(uri, wikitext, page)
  text = URI.escape(wikitext)
  title = URI.escape(page)
  data = {"action" => "parse",
          "format" => "json",
          "text"   => text,
          "title"  => title}
  jsn = post_request(uri, data)
  hash = JSON.parse(jsn)
  begin
    result = hash["parse"]["text"]["*"]
    result = special_chr(result)
    return chrref_to_utf(result).gsub("[[", "&#91;&#91;").gsub("]]", "&#93;&#93;")
  rescue => e      
    puts "ERROR!"
    p e
    exit
    template
  end
end

#post_request(uri_string, data = {}) ⇒ Object 



14
15
16
17
18
19
20
 
# File 'lib/wp2txt/mw_api.rb', line 14

def post_request(uri_string, data={})
  data = data.map{ |k, v| "#{k}=#{v}" }.join("&")
  uri = URI.parse(uri_string)
  uri.path = "/" if uri.path.empty?
  http = Net::HTTP.new(uri.host)
  return http.post(uri.path, data).body
end

#process_external_links!(str) ⇒ Object 



220
221
222
223
224
225
226
227
228
229
230
231
232
 
# File 'lib/wp2txt/utils.rb', line 220

def process_external_links!(str)
  scanner = StringScanner.new(str)
  result = process_nested_structure(scanner, "[", "]", $limit_recur) do |contents|
    parts = contents.split(" ", 2)
    case parts.size
    when 1
      parts.first || ""
    else
      parts.last || ""
    end
  end
  str.replace(result)
end

#process_interwiki_links!(str) ⇒ Object 



205
206
207
208
209
210
211
212
213
214
215
216
217
218
 
# File 'lib/wp2txt/utils.rb', line 205

def process_interwiki_links!(str)
  scanner = StringScanner.new(str)
  result = process_nested_structure(scanner, "[[", "]]", $limit_recur) do |contents|
    parts = contents.split("|")      
    case parts.size
    when 1
      parts.first || ""
    else
      parts.shift
      parts.join("|")
    end
  end
  str.replace(result)
end

#process_nested_structure(scanner, left, right, recur_count, &block) ⇒ Object

parser for nested structure ####################



137
138
139
140
141
142
143
144
145
146
147
148
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
181
 
# File 'lib/wp2txt/utils.rb', line 137

def process_nested_structure(scanner, left, right, recur_count, &block)
  buffer = ""
  begin
  if left == "[" && right == "]"
    regex = $single_square_bracket_regex
  elsif left == "[[" && right == "]]"
    regex = $double_square_bracket_regex
  elsif left == "{" && right == "}"
    regex = $single_curly_bracket_regex
  elsif left == "{{" && right == "}}"
    regex = $double_curly_bracket_regex
  elsif left == "{|" && right == "|}"
    regex = $curly_square_bracket_regex
  else
    regex = Regexp.new('(#{Regexp.escape(left)}|#{Regexp.escape(right)})', Regexp::MULTILINE)
  end
  while str = scanner.scan_until(regex)
    case scanner[1]
    when left
      buffer << str
      has_left = true
    when right
      if has_left
        buffer = buffer[0...-(left.size)]
        contents = block.call(str[0...-(left.size)])
        buffer << contents
        break
      else
        buffer << str
      end
    end
  end
  buffer << scanner.rest

  recur_count = recur_count - 1
  if recur_count < 0 || buffer == scanner.string
    return buffer
  else
    scanner.string = buffer
    return process_nested_structure(scanner, left, right, recur_count, &block) || ""
  end
  rescue => e
    return scanner.string
  end
end

#remove_directive!(str) ⇒ Object 



266
267
268
 
# File 'lib/wp2txt/utils.rb', line 266

def remove_directive!(str)
  str.gsub!($remove_directives_regex, "")
end

#remove_emphasis!(str) ⇒ Object 



270
271
272
273
274
 
# File 'lib/wp2txt/utils.rb', line 270

def remove_emphasis!(str)
  str.gsub!($remove_emphasis_regex) do
    $2
  end
end

#remove_hr!(page) ⇒ Object 



299
300
301
 
# File 'lib/wp2txt/utils.rb', line 299

def remove_hr!(page)
  page.gsub!($remove_hr_regex, "")
end

#remove_inbetween!(str, tagset = ['<', '>']) ⇒ Object 



256
257
258
259
260
 
# File 'lib/wp2txt/utils.rb', line 256

def remove_inbetween!(str, tagset = ['<', '>'])
  tagsets = Regexp.quote(tagset.uniq.join(""))
  regex = /#{Regexp.escape(tagset[0])}[^#{tagsets}]*#{Regexp.escape(tagset[1])}/
  str.gsub!(regex, "")
end

#remove_table!(str) ⇒ Object 



244
245
246
247
248
249
250
 
# File 'lib/wp2txt/utils.rb', line 244

def remove_table!(str)
  scanner = StringScanner.new(str)
  result = process_nested_structure(scanner, "{|", "|}", $limit_recur) do |contents|
    ""
  end
  str.replace(result)
end

#remove_tag!(str) ⇒ Object 



262
263
264
 
# File 'lib/wp2txt/utils.rb', line 262

def remove_tag!(str)
  str.gsub!($remove_tag_regex, "")
end

#remove_templates!(str) ⇒ Object

methods used from format_article ####################



236
237
238
239
240
241
242
 
# File 'lib/wp2txt/utils.rb', line 236

def remove_templates!(str)
  scanner = StringScanner.new(str)
  result = process_nested_structure(scanner, "{{", "}}", $limit_recur) do |contents|
    ""
  end
  str.replace(result)
end

#rename(files) ⇒ Object 



399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
 
# File 'lib/wp2txt/utils.rb', line 399

def rename(files)    
  # num of digits necessary to name the last file generated

  maxwidth = 0  

  files.each do |f|
    width = f.slice(/\-(\d+)\z/, 1).to_s.length.to_i
    maxwidth = width if maxwidth < width
  end

  files.each do |f|
    newname= f.sub(/\-(\d+)\z/) do
      "-" + sprintf("%0#{maxwidth}d", $1.to_i)
    end
    File.rename(f, newname + ".txt")
  end
end

#sec_to_str(int) ⇒ Object

convert int of seconds to string in the format 00:00:00



417
418
419
420
421
422
423
424
425
426
427
 
# File 'lib/wp2txt/utils.rb', line 417

def sec_to_str(int)
  unless int
    str = "--:--:--"
    return str
  end
  h = int / 3600
  m = (int - h * 3600) / 60
  s = int % 60
  str = sprintf("%02d:%02d:%02d", h, m, s)
  return str
end

#special_chr!(str) ⇒ Object 



252
253
254
 
# File 'lib/wp2txt/utils.rb', line 252

def special_chr!(str)
  str.replace $html_decoder.decode(str)
end

#unescape_nowiki!(str) ⇒ Object 



198
199
200
201
202
203
 
# File 'lib/wp2txt/utils.rb', line 198

def unescape_nowiki!(str)
  str.gsub!($unescape_nowiki_regex) do
    obj_id = $1.to_i
    @nowikis[obj_id]
  end
end