Class: Wikidotrb::Module::PageCollection

Inherits:
Array
  • Object
show all
Defined in:
lib/wikidotrb/module/page.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(site: nil, pages: []) ⇒ PageCollection

Returns a new instance of PageCollection.



78
79
80
81
 
# File 'lib/wikidotrb/module/page.rb', line 78

def initialize(site: nil, pages: [])
  super(pages)
  @site = site || pages.first&.site
end

Instance Attribute Details

#site

Returns the value of attribute site.



76
77
78
 
# File 'lib/wikidotrb/module/page.rb', line 76

def site
  @site
end

Class Method Details

.acquire_page_discuss(site, pages) 



338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
 
# File 'lib/wikidotrb/module/page.rb', line 338

def self.acquire_page_discuss(site, pages)
  target_pages = pages.reject(&:is_discuss_acquired?)
  return pages if target_pages.empty?

  responses = site.amc_request(
    bodies: target_pages.map do |page|
      {
        "action" => "ForumAction",
        "event" => "createPageDiscussionThread",
        "page_id" => page.id,
        "moduleName" => "Empty"
      }
    end
  )

  target_pages.each_with_index do |page, index|
    page.discuss = ForumThread.new(site, responses[index]["thread_id"], page: page)
  end
end

.acquire_page_ids(site, pages) 



233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
 
# File 'lib/wikidotrb/module/page.rb', line 233

def self.acquire_page_ids(site, pages)
  target_pages = pages.reject(&:is_id_acquired?)
  return pages if target_pages.empty?

  responses = Wikidotrb::Util::RequestUtil.request(
    client: site.client,
    method: "GET",
    urls: target_pages.map { |page| "#{page.get_url}/norender/true/noredirect/true" }
  )

  responses.each_with_index do |response, index|
    source = response.body.to_s # Convert to string if necessary

    id_match = source&.match(/WIKIREQUEST\.info\.pageId = (\d+);/)

    unless id_match
      raise Wikidotrb::Common::Exceptions::UnexpectedException,
            "Cannot find page id for: #{target_pages[index].fullname}, possibly an invalid response"
    end

    target_pages[index].id = id_match[1].to_i
  end

  pages
end

.acquire_page_revisions(site, pages) 



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
 
# File 'lib/wikidotrb/module/page.rb', line 259

def self.acquire_page_revisions(site, pages)
  return pages if pages.empty?

  responses = site.amc_request(
    bodies: pages.map do |page|
      {
        "moduleName" => "history/PageRevisionListModule",
        "page_id" => page.id,
        "options" => { "all" => true },
        "perpage" => 100_000_000 # Get all without using pager
      }
    end
  )

  responses.each_with_index do |response, index|
    body = response["body"]
    revs = []
    body_html = Nokogiri::HTML(body)

    body_html.css("table.page-history > tr[id^=revision-row-]").each do |rev_element|
      rev_id = rev_element["id"].gsub("revision-row-", "").to_i

      tds = rev_element.css("td")
      rev_no = tds[0].text.strip.gsub(".", "").to_i
      created_by = Wikidotrb::Util::Parser::UserParser.parse(site.client, tds[4].css("span.printuser").first)
      created_at = Wikidotrb::Util::Parser::ODateParser.parse(tds[5].css("span.odate").first)
      comment = tds[6].text.strip
      revs << PageRevision.new(
        page: pages[index],
        id: rev_id,
        rev_no: rev_no,
        created_by: created_by,
        created_at: created_at,
        comment: comment
      )
    end
    pages[index].revisions = revs
  end

  pages
end

.acquire_page_sources(site, pages) 



217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
 
# File 'lib/wikidotrb/module/page.rb', line 217

def self.acquire_page_sources(site, pages)
  return pages if pages.empty?

  responses = site.amc_request(
    bodies: pages.map { |page| { "moduleName" => "viewsource/ViewSourceModule", "page_id" => page.id } }
  )

  pages.each_with_index do |page, index|
    body = responses[index]["body"]
    source = Nokogiri::HTML(body).at_css("div.page-source").text.strip
    page.source = PageSource.new(page: page, wiki_text: source)
  end

  pages
end

.acquire_page_votes(site, pages) 



301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
 
# File 'lib/wikidotrb/module/page.rb', line 301

def self.acquire_page_votes(site, pages)
  return pages if pages.empty?

  responses = site.amc_request(
    bodies: pages.map { |page| { "moduleName" => "pagerate/WhoRatedPageModule", "pageId" => page.id } }
  )

  responses.each_with_index do |response, index|
    body = response["body"]
    html = Nokogiri::HTML(body)
    user_elems = html.css("span.printuser")
    value_elems = html.css('span[style^="color"]')

    if user_elems.size != value_elems.size
      raise Wikidotrb::Common::Exceptions::UnexpectedException,
            "User and value count mismatch"
    end

    users = user_elems.map { |user_elem| Wikidotrb::Util::Parser::UserParser.parse(site.client, user_elem) }
    values = value_elems.map do |value_elem|
      value = value_elem.text.strip
      if value == "+"
        1
      elsif value == "-"
        -1
      else
        value.to_i
      end
    end

    votes = users.zip(values).map { |user, vote| PageVote.new(page: pages[index], user: user, value: vote) }
    pages[index].votes = PageVoteCollection.new(page: pages[index], votes: votes)
  end

  pages
end

.parse(site, html_body) 



83
84
85
86
87
88
89
90
91
92
93
94
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
 
# File 'lib/wikidotrb/module/page.rb', line 83

def self.parse(site, html_body)
  pages = []

  html_body.css("div.page").each do |page_element|
    page_params = {}

    # Determine rating method
    is_5star_rating = !page_element.css("span.rating span.page-rate-list-pages-start").empty?

    # Get each value
    page_element.css("span.set").each do |set_element|
      key = set_element.css("span.name").text.strip
      value_element = set_element.css("span.value")

      value = if value_element.empty?
                nil
              elsif %w[created_at updated_at commented_at].include?(key)
                odate_element = value_element.css("span.odate")
                odate_element.empty? ? nil : Wikidotrb::Util::Parser::ODateParser.parse(odate_element)
              elsif %w[created_by_linked updated_by_linked commented_by_linked].include?(key)
                printuser_element = value_element.css("span.printuser")
                if printuser_element.empty?
                  nil
                else
                  Wikidotrb::Util::Parser::UserParser.parse(site.client,
                                                            printuser_element)
                end
              elsif %w[tags _tags].include?(key)
                value_element.text.split
              elsif %w[rating_votes comments size revisions].include?(key)
                value_element.text.strip.to_i
              elsif key == "rating"
                is_5star_rating ? value_element.text.strip.to_f : value_element.text.strip.to_i
              elsif key == "rating_percent"
                is_5star_rating ? value_element.text.strip.to_f / 100 : nil
              else
                value_element.text.strip
              end

      # Convert key
      key = key.gsub("_linked", "") if key.include?("_linked")
      key = "#{key}_count" if %w[comments children revisions].include?(key)
      key = "votes_count" if key == "rating_votes"

      page_params[key.to_sym] = value
    end

    # Integrate tag lists
    page_params[:tags] ||= []
    page_params[:tags] += page_params.delete(:_tags) || []

    # Create page object
    pages << Page.new(site: site, **page_params)
  end

  new(site: site, pages: pages)
end

.search_pages(site, query = SearchPagesQuery.new) 



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
182
183
184
185
186
187
188
189
190
191
192
193
194
 
# File 'lib/wikidotrb/module/page.rb', line 141

def self.search_pages(site, query = SearchPagesQuery.new)
  # Initialize query
  query_dict = query.to_h
  query_dict["moduleName"] = "list/ListPagesModule"
  query_dict["module_body"] = %([[div class="page"]]#{
    DEFAULT_MODULE_BODY.map do |key|
      <<~WIKIDOT.chomp
        [[span class="set #{key}"]]
          [[span class="name"]]#{key}[[/span]]
          [[span class="value"]]%%#{key}%%[[/span]]
        [[/span]]
      WIKIDOT
    end.join
  }[[/div]])

  begin
    # Initial request
    response_data = site.amc_request(bodies: [query_dict])[0]
  rescue Wikidotrb::Common::Exceptions::WikidotStatusCodeException => e
    raise Wikidotrb::Common::Exceptions::ForbiddenException, "Failed to get pages, target site may be private" if e.status_code == "not_ok"

    raise e
  end

  body = response_data["body"]
  first_page_html_body = Nokogiri::HTML(body)

  total = 1
  html_bodies = [first_page_html_body]

  # Check for pager existence
  pager_element = first_page_html_body.css("div.pager")
  unless pager_element.empty?
    # Get maximum page number
    total = pager_element.css("span.target")[-2].css("a").text.to_i
  end

  # If multiple pages exist, repeat requests
  if total > 1
    request_bodies = []
    (1...total).each do |i|
      _query_dict = query_dict.dup
      _query_dict["offset"] = i * query.perPage
      request_bodies << _query_dict
    end

    responses = site.amc_request(bodies: request_bodies)
    html_bodies.concat(responses.map { |response| Nokogiri::HTML(response["body"]) })
  end

  # Parse all HTML bodies and create page collection
  pages = html_bodies.flat_map { |html_body| parse(site, html_body) }
  new(site: site, pages: pages)
end

Instance Method Details

#get_page_discuss 



213
214
215
 
# File 'lib/wikidotrb/module/page.rb', line 213

def get_page_discuss
  PageCollection.acquire_page_discuss(@site, self)
end

#get_page_ids 



201
202
203
 
# File 'lib/wikidotrb/module/page.rb', line 201

def get_page_ids
  PageCollection.acquire_page_ids(@site, self)
end

#get_page_revisions 



205
206
207
 
# File 'lib/wikidotrb/module/page.rb', line 205

def get_page_revisions
  PageCollection.acquire_page_revisions(@site, self)
end

#get_page_sources

Modification of method definition part



197
198
199
 
# File 'lib/wikidotrb/module/page.rb', line 197

def get_page_sources
  PageCollection.acquire_page_sources(@site, self)
end

#get_page_votes 



209
210
211
 
# File 'lib/wikidotrb/module/page.rb', line 209

def get_page_votes
  PageCollection.acquire_page_votes(@site, self)
end