unicorn.git  about / heads / tags
Rack HTTP server for Unix and fast clients
blob ec215ae5593238cbd89f34c2d5380a2f4945a004 3346 bytes (raw)
$ git show v0.9.2:lib/unicorn/http_request.rb	# shows this blob on the CLI

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
require 'stringio'

# compiled extension
require 'unicorn_http'

module Unicorn
  class HttpRequest

    # default parameters we merge into the request env for Rack handlers
    DEFAULTS = {
      "rack.errors" => $stderr,
      "rack.multiprocess" => true,
      "rack.multithread" => false,
      "rack.run_once" => false,
      "rack.version" => [1, 0].freeze,
      "SCRIPT_NAME" => "".freeze,

      # this is not in the Rack spec, but some apps may rely on it
      "SERVER_SOFTWARE" => "Unicorn #{Const::UNICORN_VERSION}".freeze
    }

    NULL_IO = StringIO.new(Z)
    LOCALHOST = '127.0.0.1'.freeze

    def initialize
    end

    # Being explicitly single-threaded, we have certain advantages in
    # not having to worry about variables being clobbered :)
    BUFFER = ' ' * Const::CHUNK_SIZE # initial size, may grow
    BUFFER.force_encoding(Encoding::BINARY) if Z.respond_to?(:force_encoding)
    PARSER = HttpParser.new
    PARAMS = Hash.new

    # Does the majority of the IO processing.  It has been written in
    # Ruby using about 8 different IO processing strategies.
    #
    # It is currently carefully constructed to make sure that it gets
    # the best possible performance for the common case: GET requests
    # that are fully complete after a single read(2)
    #
    # Anyone who thinks they can make it faster is more than welcome to
    # take a crack at it.
    #
    # returns an environment hash suitable for Rack if successful
    # This does minimal exception trapping and it is up to the caller
    # to handle any socket errors (e.g. user aborted upload).
    def read(socket)
      PARAMS.clear
      PARSER.reset

      # From http://www.ietf.org/rfc/rfc3875:
      # "Script authors should be aware that the REMOTE_ADDR and
      #  REMOTE_HOST meta-variables (see sections 4.1.8 and 4.1.9)
      #  may not identify the ultimate source of the request.  They
      #  identify the client for the immediate request to the server;
      #  that client may be a proxy, gateway, or other intermediary
      #  acting on behalf of the actual source client."
      PARAMS[Const::REMOTE_ADDR] =
                    TCPSocket === socket ? socket.peeraddr.last : LOCALHOST

      # short circuit the common case with small GET requests first
      PARSER.execute(PARAMS, socket.readpartial(Const::CHUNK_SIZE, BUFFER)) and
          return handle_body(socket)

      data = BUFFER.dup # socket.readpartial will clobber BUFFER

      # Parser is not done, queue up more data to read and continue parsing
      # an Exception thrown from the PARSER will throw us out of the loop
      begin
        data << socket.readpartial(Const::CHUNK_SIZE, BUFFER)
        PARSER.execute(PARAMS, data) and return handle_body(socket)
      end while true
    end

    private

    # Handles dealing with the rest of the request
    # returns a Rack environment if successful
    def handle_body(socket)
      PARAMS[Const::RACK_INPUT] = if (body = PARAMS.delete(:http_body))
        length = PARAMS[Const::CONTENT_LENGTH].to_i

        if /\Achunked\z/i =~ PARAMS[Const::HTTP_TRANSFER_ENCODING]
          socket = ChunkedReader.new(PARAMS, socket, body)
          length = body = nil
        end

        TeeInput.new(socket, length, body)
      else
        NULL_IO
      end

      PARAMS.update(DEFAULTS)
    end

  end
end

git clone https://yhbt.net/unicorn.git