module Mechanize::Parser

The parser module provides standard methods for accessing the headers and content of a response that are shared across pluggable parsers.

Constants

SPECIAL_FILENAMES: Special filenames that must be escaped

Attributes

code [RW]

The HTTP response code

header [RW]

The Mechanize::Headers for this file

response [RW]

The Mechanize::Headers for this file

uri [RW]

The URI this file was retrieved from

Public Instance Methods

[](header)

Source

# File lib/mechanize/parser.rb, line 65
def_delegator :header, :[], :[]

Access HTTP header by name

[]=(header, value)

Source

# File lib/mechanize/parser.rb, line 75
def_delegator :header, :[]=, :[]=

Set HTTP header to value

each ()

Source

# File lib/mechanize/parser.rb, line 92
def_delegator :header, :each, :each

Enumerate HTTP headers

ensure_within (directory, path)

Source

# File lib/mechanize/parser.rb, line 188
def ensure_within directory, path
  directory = File.join File.expand_path(directory), ''

  return if File.expand_path(path).start_with? directory

  raise Mechanize::Error, "refusing to save #{path} outside #{directory}"
end

Raises Mechanize::Error unless path is inside directory.

extract_filename (full_path = @full_path)

Source

# File lib/mechanize/parser.rb, line 107
def extract_filename full_path = @full_path
  handled = false

  if @uri then
    uri_path = remove_dot_segments @uri.path
    uri_path += 'index.html' if uri_path.end_with? '/'

    path     = uri_path.split(/\//)
    filename = path.pop || 'index.html'
  else
    path     = []
    filename = 'index.html'
  end

  # Set the filename
  if (disposition = @response['content-disposition'])
    content_disposition =
      Mechanize::HTTP::ContentDispositionParser.parse disposition

    if content_disposition && content_disposition.filename && content_disposition.filename != ''
      filename = content_disposition.filename
      filename = filename.rpartition(/[\\\/]/).last
      handled = true
    end
  end

  if not handled and @uri then
    filename << '.html' unless filename =~ /\./
    filename << "?#{@uri.query}" if @uri.query
  end

  if SPECIAL_FILENAMES =~ filename then
    filename = "_#{filename}"
  end

  filename = filename.tr "\x00-\x20<>:\"/\\|?*", '_'

  @filename = if full_path then
                File.join @uri.host, path, filename
              else
                filename
              end
end

Extracts the filename from a Content-Disposition header in the response or from the URI. If full_path is true the filename will include the host name and path to the resource, otherwise a filename in the current directory is given.

fill_header (response)

Source

# File lib/mechanize/parser.rb, line 156
def fill_header response
  @response = Mechanize::Headers.new

  response.each { |k,v|
    @response[k] = v
  } if response

  @response
end

Creates a Mechanize::Header from the Net::HTTPResponse response.

This allows the Net::HTTPResponse to be garbage collected sooner.

find_free_name (filename)

Source

# File lib/mechanize/parser.rb, line 199
def find_free_name filename
  base_filename = filename ||= @filename

  number = 1

  while File.exist? filename do
    filename = "#{base_filename}.#{number}"
    number += 1
  end

  filename
end

Finds a free filename based on filename, but is not race-free

key?(header)

Source

# File lib/mechanize/parser.rb, line 85
def_delegator :header, :key?, :key?

Is the named header present?

remove_dot_segments (path)

Source

# File lib/mechanize/parser.rb, line 170
def remove_dot_segments path
  segments = path.split '/', -1

  resolved = segments.each_with_object [] do |segment, result|
    case segment
    when '.'  then next
    when '..' then result.pop unless result == ['']
    else           result << segment
    end
  end

  resolved << '' if ['.', '..'].include? segments.last
  resolved.join '/'
end

Resolves “.” and “..” segments in the absolute path as RFC 3986 section 5.2.4 does, without reparsing it as a URI.