Module: OpenURI::Meta

Defined in:
lib/open-uri.rb

Overview

Mixin for holding meta-information.

Constant Summary collapse

RE_LWS =

:stopdoc:

/[\r\n\t ]+/n
RE_TOKEN =
%r{[^\x00- ()<>@,;:\\"/\[\]?={}\x7f]+}n
RE_QUOTED_STRING =
%r{"(?:[\r\n\t !#-\[\]-~\x80-\xff]|\\[\x00-\x7f])*"}n
RE_PARAMETERS =
%r{(?:;#{RE_LWS}?#{RE_TOKEN}#{RE_LWS}?=#{RE_LWS}?(?:#{RE_TOKEN}|#{RE_QUOTED_STRING})#{RE_LWS}?)*}n

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Instance Attribute Details

#base_uriObject

returns a URI that is the base of relative URIs in the data. It may differ from the URI supplied by a user due to redirection.


425
426
427
# File 'lib/open-uri.rb', line 425

def base_uri
  @base_uri
end

#metaObject (readonly)

returns a Hash that represents header fields. The Hash keys are downcased for canonicalization. The Hash values are a field body. If there are multiple field with same field name, the field values are concatenated with a comma.


432
433
434
# File 'lib/open-uri.rb', line 432

def meta
  @meta
end

#metasObject (readonly)

returns a Hash that represents header fields. The Hash keys are downcased for canonicalization. The Hash value are an array of field values.


437
438
439
# File 'lib/open-uri.rb', line 437

def metas
  @metas
end

#statusObject

returns an Array that consists of status code and message.


421
422
423
# File 'lib/open-uri.rb', line 421

def status
  @status
end

Class Method Details

.init(obj, src = nil) ⇒ Object

:nodoc:


404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
# File 'lib/open-uri.rb', line 404

def Meta.init(obj, src=nil) # :nodoc:
  obj.extend Meta
  obj.instance_eval {
    @base_uri = nil
    @meta = {} # name to string.  legacy.
    @metas = {} # name to array of strings.
  }
  if src
    obj.status = src.status
    obj.base_uri = src.base_uri
    src.metas.each {|name, values|
      obj.meta_add_field2(name, values)
    }
  end
end

Instance Method Details

#charsetObject

returns a charset parameter in Content-Type field. It is downcased for canonicalization.

If charset parameter is not given but a block is given, the block is called and its result is returned. It can be used to guess charset.

If charset parameter and block is not given, nil is returned except text type in HTTP. In that case, “iso-8859-1” is returned as defined by RFC2616 3.7.1.


523
524
525
526
527
528
529
530
531
532
533
534
535
# File 'lib/open-uri.rb', line 523

def charset
  type, *parameters = content_type_parse
  if pair = parameters.assoc('charset')
    pair.last.downcase
  elsif block_given?
    yield
  elsif type && %r{\Atext/} =~ type &&
        @base_uri && /\Ahttp\z/i =~ @base_uri.scheme
    "iso-8859-1" # RFC2616 3.7.1
  else
    nil
  end
end

#content_encodingObject

Returns a list of encodings in Content-Encoding field as an array of strings.

The encodings are downcased for canonicalization.


541
542
543
544
545
546
547
548
# File 'lib/open-uri.rb', line 541

def content_encoding
  vs = @metas['content-encoding']
  if vs && %r{\A#{RE_LWS}?#{RE_TOKEN}#{RE_LWS}?(?:,#{RE_LWS}?#{RE_TOKEN}#{RE_LWS}?)*}o =~ (v = vs.join(', '))
    v.scan(RE_TOKEN).map {|content_coding| content_coding.downcase}
  else
    []
  end
end

#content_typeObject

returns “type/subtype” which is MIME Content-Type. It is downcased for canonicalization. Content-Type parameters are stripped.


508
509
510
511
# File 'lib/open-uri.rb', line 508

def content_type
  type, *_ = content_type_parse
  type || 'application/octet-stream'
end

#content_type_parseObject

:startdoc:


486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
# File 'lib/open-uri.rb', line 486

def content_type_parse # :nodoc:
  vs = @metas['content-type']
  # The last (?:;#{RE_LWS}?)? matches extra ";" which violates RFC2045.
  if vs && %r{\A#{RE_LWS}?(#{RE_TOKEN})#{RE_LWS}?/(#{RE_TOKEN})#{RE_LWS}?(#{RE_PARAMETERS})(?:;#{RE_LWS}?)?\z}no =~ vs.join(', ')
    type = $1.downcase
    subtype = $2.downcase
    parameters = []
    $3.scan(/;#{RE_LWS}?(#{RE_TOKEN})#{RE_LWS}?=#{RE_LWS}?(?:(#{RE_TOKEN})|(#{RE_QUOTED_STRING}))/no) {|att, val, qval|
      if qval
        val = qval[1...-1].gsub(/[\r\n\t !#-\[\]-~\x80-\xff]+|(\\[\x00-\x7f])/n) { $1 ? $1[1,1] : $& }
      end
      parameters << [att.downcase, val]
    }
    ["#{type}/#{subtype}", *parameters]
  else
    nil
  end
end

#last_modifiedObject

returns a Time that represents the Last-Modified field.


470
471
472
473
474
475
476
477
# File 'lib/open-uri.rb', line 470

def last_modified
  if vs = @metas['last-modified']
    v = vs.join(', ')
    Time.httpdate(v)
  else
    nil
  end
end

#meta_add_field(name, value) ⇒ Object

:nodoc:


465
466
467
# File 'lib/open-uri.rb', line 465

def meta_add_field(name, value) # :nodoc:
  meta_add_field2(name, [value])
end

#meta_add_field2(name, values) ⇒ Object

:nodoc:


458
459
460
461
462
463
# File 'lib/open-uri.rb', line 458

def meta_add_field2(name, values) # :nodoc:
  name = name.downcase
  @metas[name] = values
  @meta[name] = values.join(', ')
  meta_setup_encoding if name == 'content-type'
end

#meta_setup_encodingObject

:nodoc:


439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
# File 'lib/open-uri.rb', line 439

def meta_setup_encoding # :nodoc:
  charset = self.charset
  enc = nil
  if charset
    begin
      enc = Encoding.find(charset)
    rescue ArgumentError
    end
  end
  enc = Encoding::ASCII_8BIT unless enc
  if self.respond_to? :force_encoding
    self.force_encoding(enc)
  elsif self.respond_to? :string
    self.string.force_encoding(enc)
  else # Tempfile
    self.set_encoding enc
  end
end