Class: Nokogiri::HTML4::Document::EncodingReader

Inherits:
Object
  • Object
show all
Defined in:
lib/nokogiri/html4/document.rb

Overview

:nodoc:

Since:

  • v1.12.0

Defined Under Namespace

Classes: JumpSAXHandler, SAXHandler

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(io) ⇒ EncodingReader

Returns a new instance of EncodingReader.

Since:

  • v1.12.0



282
283
284
285
286
 
# File 'lib/nokogiri/html4/document.rb', line 282

def initialize(io)
  @io = io
  @firstchunk = nil
  @encoding_found = nil
end

Instance Attribute Details

#encoding_found ⇒ Object (readonly)

This method is used by the C extension so that Nokogiri::HTML4::Document#read_io() does not leak memory when EncodingFound is raised.

Since:

  • v1.12.0



291
292
293
 
# File 'lib/nokogiri/html4/document.rb', line 291

def encoding_found
  @encoding_found
end

Class Method Details

.detect_encoding(chunk) ⇒ Object

Since:

  • v1.12.0



263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
 
# File 'lib/nokogiri/html4/document.rb', line 263

def self.detect_encoding(chunk)
  m = chunk.match(/\A(<\?xml[ \t\r\n]+[^>]*>)/) and
    return Nokogiri.XML(m[1]).encoding

  if Nokogiri.jruby?
    m = chunk.match(/(<meta\s)(.*)(charset\s*=\s*([\w-]+))(.*)/i) and
      return m[4]
    catch(:encoding_found) {
      Nokogiri::HTML4::SAX::Parser.new(JumpSAXHandler.new(:encoding_found)).parse(chunk)
      nil
    }
  else
    handler = SAXHandler.new
    parser = Nokogiri::HTML4::SAX::PushParser.new(handler)
    parser << chunk rescue Nokogiri::SyntaxError
    handler.encoding
  end
end

Instance Method Details

#read(len) ⇒ Object

Since:

  • v1.12.0



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
 
# File 'lib/nokogiri/html4/document.rb', line 293

def read(len)
  # no support for a call without len

  if !@firstchunk
    @firstchunk = @io.read(len) or return nil

    # This implementation expects that the first call from
    # htmlReadIO() is made with a length long enough (~1KB) to
    # achieve advanced encoding detection.
    if encoding = EncodingReader.detect_encoding(@firstchunk)
      # The first chunk is stored for the next read in retry.
      raise @encoding_found = EncodingFound.new(encoding)
    end
  end
  @encoding_found = nil

  ret = @firstchunk.slice!(0, len)
  if (len -= ret.length) > 0
    rest = @io.read(len) and ret << rest
  end
  if ret.empty?
    nil
  else
    ret
  end
end