Class: Rack::Lint

Inherits:
Object
  • Object
show all
Includes:
Assertion
Defined in:
lib/rack/lint.rb

Overview

Rack::Lint validates your application and the requests and responses according to the Rack spec.

Defined Under Namespace

Modules: Assertion Classes: ErrorWrapper, HijackWrapper, InputWrapper, LintError

Instance Method Summary collapse

Methods included from Assertion

#assert

Constructor Details

#initialize(app) ⇒ Lint

Returns a new instance of Lint.



9
10
11
12
# File 'lib/rack/lint.rb', line 9

def initialize(app)
  @app = app
  @content_length = nil
end

Instance Method Details

#_call(env) ⇒ Object



40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
# File 'lib/rack/lint.rb', line 40

def _call(env)
  ## It takes exactly one argument, the *environment*
  assert("No env given") { env }
  check_env env

  env['rack.input'] = InputWrapper.new(env['rack.input'])
  env['rack.errors'] = ErrorWrapper.new(env['rack.errors'])

  ## and returns an Array of exactly three values:
  status, headers, @body = @app.call(env)
  ## The *status*,
  check_status status
  ## the *headers*,
  check_headers headers

  check_hijack_response headers, env

  ## and the *body*.
  check_content_type status, headers
  check_content_length status, headers
  @head_request = env[REQUEST_METHOD] == "HEAD"
  [status, headers, self]
end

#call(env = nil) ⇒ Object

A Rack application is a Ruby object (not a class) that responds to call.



36
37
38
# File 'lib/rack/lint.rb', line 36

def call(env=nil)
  dup._call(env)
end

#check_content_length(status, headers) ⇒ Object

The Content-Length



673
674
675
676
677
678
679
680
681
682
683
684
# File 'lib/rack/lint.rb', line 673

def check_content_length(status, headers)
  headers.each { |key, value|
    if key.downcase == 'content-length'
      ## There must not be a <tt>Content-Length</tt> header when the
      ## +Status+ is 1xx, 204, 205 or 304.
      assert("Content-Length header found in #{status} response, not allowed") {
        not Rack::Utils::STATUS_WITH_NO_ENTITY_BODY.include? status.to_i
      }
      @content_length = value
    end
  }
end

#check_content_type(status, headers) ⇒ Object

The Content-Type



659
660
661
662
663
664
665
666
667
668
669
670
# File 'lib/rack/lint.rb', line 659

def check_content_type(status, headers)
  headers.each { |key, value|
    ## There must not be a <tt>Content-Type</tt>, when the +Status+ is 1xx,
    ## 204, 205 or 304.
    if key.downcase == "content-type"
      assert("Content-Type header found in #{status} response, not allowed") {
        not Rack::Utils::STATUS_WITH_NO_ENTITY_BODY.include? status.to_i
      }
      return
    end
  }
end

#check_env(env) ⇒ Object

The Environment



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
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
140
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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
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
258
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
300
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
# File 'lib/rack/lint.rb', line 65

def check_env(env)
  ## The environment must be an instance of Hash that includes
  ## CGI-like headers.  The application is free to modify the
  ## environment.
  assert("env #{env.inspect} is not a Hash, but #{env.class}") {
    env.kind_of? Hash
  }

  ##
  ## The environment is required to include these variables
  ## (adopted from PEP333), except when they'd be empty, but see
  ## below.

  ## <tt>REQUEST_METHOD</tt>:: The HTTP request method, such as
  ##                           "GET" or "POST". This cannot ever
  ##                           be an empty string, and so is
  ##                           always required.

  ## <tt>SCRIPT_NAME</tt>:: The initial portion of the request
  ##                        URL's "path" that corresponds to the
  ##                        application object, so that the
  ##                        application knows its virtual
  ##                        "location". This may be an empty
  ##                        string, if the application corresponds
  ##                        to the "root" of the server.

  ## <tt>PATH_INFO</tt>:: The remainder of the request URL's
  ##                      "path", designating the virtual
  ##                      "location" of the request's target
  ##                      within the application. This may be an
  ##                      empty string, if the request URL targets
  ##                      the application root and does not have a
  ##                      trailing slash. This value may be
  ##                      percent-encoded when I originating from
  ##                      a URL.

  ## <tt>QUERY_STRING</tt>:: The portion of the request URL that
  ##                         follows the <tt>?</tt>, if any. May be
  ##                         empty, but is always required!

  ## <tt>SERVER_NAME</tt>, <tt>SERVER_PORT</tt>::
  ##                        When combined with <tt>SCRIPT_NAME</tt> and
  ##                        <tt>PATH_INFO</tt>, these variables can be
  ##                        used to complete the URL. Note, however,
  ##                        that <tt>HTTP_HOST</tt>, if present,
  ##                        should be used in preference to
  ##                        <tt>SERVER_NAME</tt> for reconstructing
  ##                        the request URL.
  ##                        <tt>SERVER_NAME</tt> and <tt>SERVER_PORT</tt>
  ##                        can never be empty strings, and so
  ##                        are always required.

  ## <tt>HTTP_</tt> Variables:: Variables corresponding to the
  ##                            client-supplied HTTP request
  ##                            headers (i.e., variables whose
  ##                            names begin with <tt>HTTP_</tt>). The
  ##                            presence or absence of these
  ##                            variables should correspond with
  ##                            the presence or absence of the
  ##                            appropriate HTTP header in the
  ##                            request. See
  ##                            <a href="https://tools.ietf.org/html/rfc3875#section-4.1.18">
  ##                            RFC3875 section 4.1.18</a> for
  ##                            specific behavior.

  ## In addition to this, the Rack environment must include these
  ## Rack-specific variables:

  ## <tt>rack.version</tt>:: The Array representing this version of Rack
  ##                         See Rack::VERSION, that corresponds to
  ##                         the version of this SPEC.

  ## <tt>rack.url_scheme</tt>:: +http+ or +https+, depending on the
  ##                            request URL.

  ## <tt>rack.input</tt>:: See below, the input stream.

  ## <tt>rack.errors</tt>:: See below, the error stream.

  ## <tt>rack.multithread</tt>:: true if the application object may be
  ##                             simultaneously invoked by another thread
  ##                             in the same process, false otherwise.

  ## <tt>rack.multiprocess</tt>:: true if an equivalent application object
  ##                              may be simultaneously invoked by another
  ##                              process, false otherwise.

  ## <tt>rack.run_once</tt>:: true if the server expects
  ##                          (but does not guarantee!) that the
  ##                          application will only be invoked this one
  ##                          time during the life of its containing
  ##                          process. Normally, this will only be true
  ##                          for a server based on CGI
  ##                          (or something similar).

  ## <tt>rack.hijack?</tt>:: present and true if the server supports
  ##                         connection hijacking. See below, hijacking.

  ## <tt>rack.hijack</tt>:: an object responding to #call that must be
  ##                        called at least once before using
  ##                        rack.hijack_io.
  ##                        It is recommended #call return rack.hijack_io
  ##                        as well as setting it in env if necessary.

  ## <tt>rack.hijack_io</tt>:: if rack.hijack? is true, and rack.hijack
  ##                           has received #call, this will contain
  ##                           an object resembling an IO. See hijacking.

  ## Additional environment specifications have approved to
  ## standardized middleware APIs.  None of these are required to
  ## be implemented by the server.

  ## <tt>rack.session</tt>:: A hash like interface for storing
  ##                         request session data.
  ##                         The store must implement:
  if session = env['rack.session']
    ##                         store(key, value)         (aliased as []=);
    assert("session #{session.inspect} must respond to store and []=") {
      session.respond_to?(:store) && session.respond_to?(:[]=)
    }

    ##                         fetch(key, default = nil) (aliased as []);
    assert("session #{session.inspect} must respond to fetch and []") {
      session.respond_to?(:fetch) && session.respond_to?(:[])
    }

    ##                         delete(key);
    assert("session #{session.inspect} must respond to delete") {
      session.respond_to?(:delete)
    }

    ##                         clear;
    assert("session #{session.inspect} must respond to clear") {
      session.respond_to?(:clear)
    }
  end

  ## <tt>rack.logger</tt>:: A common object interface for logging messages.
  ##                        The object must implement:
  if logger = env['rack.logger']
    ##                         info(message, &block)
    assert("logger #{logger.inspect} must respond to info") {
      logger.respond_to?(:info)
    }

    ##                         debug(message, &block)
    assert("logger #{logger.inspect} must respond to debug") {
      logger.respond_to?(:debug)
    }

    ##                         warn(message, &block)
    assert("logger #{logger.inspect} must respond to warn") {
      logger.respond_to?(:warn)
    }

    ##                         error(message, &block)
    assert("logger #{logger.inspect} must respond to error") {
      logger.respond_to?(:error)
    }

    ##                         fatal(message, &block)
    assert("logger #{logger.inspect} must respond to fatal") {
      logger.respond_to?(:fatal)
    }
  end

  ## <tt>rack.multipart.buffer_size</tt>:: An Integer hint to the multipart parser as to what chunk size to use for reads and writes.
  if bufsize = env['rack.multipart.buffer_size']
    assert("rack.multipart.buffer_size must be an Integer > 0 if specified") {
      bufsize.is_a?(Integer) && bufsize > 0
    }
  end

  ## <tt>rack.multipart.tempfile_factory</tt>:: An object responding to #call with two arguments, the filename and content_type given for the multipart form field, and returning an IO-like object that responds to #<< and optionally #rewind. This factory will be used to instantiate the tempfile for each multipart form file upload field, rather than the default class of Tempfile.
  if tempfile_factory = env['rack.multipart.tempfile_factory']
    assert("rack.multipart.tempfile_factory must respond to #call") { tempfile_factory.respond_to?(:call) }
    env['rack.multipart.tempfile_factory'] = lambda do |filename, content_type|
      io = tempfile_factory.call(filename, content_type)
      assert("rack.multipart.tempfile_factory return value must respond to #<<") { io.respond_to?(:<<) }
      io
    end
  end

  ## The server or the application can store their own data in the
  ## environment, too.  The keys must contain at least one dot,
  ## and should be prefixed uniquely.  The prefix <tt>rack.</tt>
  ## is reserved for use with the Rack core distribution and other
  ## accepted specifications and must not be used otherwise.
  ##

  %w[REQUEST_METHOD SERVER_NAME SERVER_PORT
     QUERY_STRING
     rack.version rack.input rack.errors
     rack.multithread rack.multiprocess rack.run_once].each { |header|
    assert("env missing required key #{header}") { env.include? header }
  }

  ## The environment must not contain the keys
  ## <tt>HTTP_CONTENT_TYPE</tt> or <tt>HTTP_CONTENT_LENGTH</tt>
  ## (use the versions without <tt>HTTP_</tt>).
  %w[HTTP_CONTENT_TYPE HTTP_CONTENT_LENGTH].each { |header|
    assert("env contains #{header}, must use #{header[5,-1]}") {
      not env.include? header
    }
  }

  ## The CGI keys (named without a period) must have String values.
  env.each { |key, value|
    next  if key.include? "."   # Skip extensions
    assert("env variable #{key} has non-string value #{value.inspect}") {
      value.kind_of? String
    }
  }

  ## There are the following restrictions:

  ## * <tt>rack.version</tt> must be an array of Integers.
  assert("rack.version must be an Array, was #{env["rack.version"].class}") {
    env["rack.version"].kind_of? Array
  }
  ## * <tt>rack.url_scheme</tt> must either be +http+ or +https+.
  assert("rack.url_scheme unknown: #{env["rack.url_scheme"].inspect}") {
    %w[http https].include? env["rack.url_scheme"]
  }

  ## * There must be a valid input stream in <tt>rack.input</tt>.
  check_input env["rack.input"]
  ## * There must be a valid error stream in <tt>rack.errors</tt>.
  check_error env["rack.errors"]
  ## * There may be a valid hijack stream in <tt>rack.hijack_io</tt>
  check_hijack env

  ## * The <tt>REQUEST_METHOD</tt> must be a valid token.
  assert("REQUEST_METHOD unknown: #{env[REQUEST_METHOD]}") {
    env["REQUEST_METHOD"] =~ /\A[0-9A-Za-z!\#$%&'*+.^_`|~-]+\z/
  }

  ## * The <tt>SCRIPT_NAME</tt>, if non-empty, must start with <tt>/</tt>
  assert("SCRIPT_NAME must start with /") {
    !env.include?("SCRIPT_NAME") ||
    env["SCRIPT_NAME"] == "" ||
    env["SCRIPT_NAME"] =~ /\A\//
  }
  ## * The <tt>PATH_INFO</tt>, if non-empty, must start with <tt>/</tt>
  assert("PATH_INFO must start with /") {
    !env.include?("PATH_INFO") ||
    env["PATH_INFO"] == "" ||
    env["PATH_INFO"] =~ /\A\//
  }
  ## * The <tt>CONTENT_LENGTH</tt>, if given, must consist of digits only.
  assert("Invalid CONTENT_LENGTH: #{env["CONTENT_LENGTH"]}") {
    !env.include?("CONTENT_LENGTH") || env["CONTENT_LENGTH"] =~ /\A\d+\z/
  }

  ## * One of <tt>SCRIPT_NAME</tt> or <tt>PATH_INFO</tt> must be
  ##   set.  <tt>PATH_INFO</tt> should be <tt>/</tt> if
  ##   <tt>SCRIPT_NAME</tt> is empty.
  assert("One of SCRIPT_NAME or PATH_INFO must be set (make PATH_INFO '/' if SCRIPT_NAME is empty)") {
    env["SCRIPT_NAME"] || env["PATH_INFO"]
  }
  ##   <tt>SCRIPT_NAME</tt> never should be <tt>/</tt>, but instead be empty.
  assert("SCRIPT_NAME cannot be '/', make it '' and PATH_INFO '/'") {
    env["SCRIPT_NAME"] != "/"
  }
end

#check_error(error) ⇒ Object

The Error Stream



455
456
457
458
459
460
461
462
# File 'lib/rack/lint.rb', line 455

def check_error(error)
  ## The error stream must respond to +puts+, +write+ and +flush+.
  [:puts, :write, :flush].each { |method|
    assert("rack.error #{error} does not respond to ##{method}") {
      error.respond_to? method
    }
  }
end

#check_headers(header) ⇒ Object

The Headers



624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
# File 'lib/rack/lint.rb', line 624

def check_headers(header)
  ## The header must respond to +each+, and yield values of key and value.
  assert("headers object should respond to #each, but doesn't (got #{header.class} as headers)") {
     header.respond_to? :each
  }
  header.each { |key, value|
    ## Special headers starting "rack." are for communicating with the
    ## server, and must not be sent back to the client.
    next if key =~ /^rack\..+$/

    ## The header keys must be Strings.
    assert("header key must be a string, was #{key.class}") {
      key.kind_of? String
    }
    ## The header must not contain a +Status+ key.
    assert("header must not contain Status") { key.downcase != "status" }
    ## The header must conform to RFC7230 token specification, i.e. cannot
    ## contain non-printable ASCII, DQUOTE or "(),/:;<=>?@[\]{}".
    assert("invalid header name: #{key}") { key !~ /[\(\),\/:;<=>\?@\[\\\]{}[:cntrl:]]/ }

    ## The values of the header must be Strings,
    assert("a header value must be a String, but the value of " +
      "'#{key}' is a #{value.class}") { value.kind_of? String }
    ## consisting of lines (for multiple header values, e.g. multiple
    ## <tt>Set-Cookie</tt> values) separated by "\\n".
    value.split("\n").each { |item|
      ## The lines must not contain characters below 037.
      assert("invalid header value #{key}: #{item.inspect}") {
        item !~ /[\000-\037]/
      }
    }
  }
end

#check_hijack(env) ⇒ Object

Hijacking

AUTHORS: n.b. The trailing whitespace between paragraphs is important and should not be removed. The whitespace creates paragraphs in the RDoc output.

Request (before status)



520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
# File 'lib/rack/lint.rb', line 520

def check_hijack(env)
  if env['rack.hijack?']
    ## If rack.hijack? is true then rack.hijack must respond to #call.
    original_hijack = env['rack.hijack']
    assert("rack.hijack must respond to call") { original_hijack.respond_to?(:call) }
    env['rack.hijack'] = proc do
      ## rack.hijack must return the io that will also be assigned (or is
      ## already present, in rack.hijack_io.
      io = original_hijack.call
      HijackWrapper.new(io)
      ##
      ## rack.hijack_io must respond to:
      ## <tt>read, write, read_nonblock, write_nonblock, flush, close,
      ## close_read, close_write, closed?</tt>
      ##
      ## The semantics of these IO methods must be a best effort match to
      ## those of a normal ruby IO or Socket object, using standard
      ## arguments and raising standard exceptions. Servers are encouraged
      ## to simply pass on real IO objects, although it is recognized that
      ## this approach is not directly compatible with SPDY and HTTP 2.0.
      ##
      ## IO provided in rack.hijack_io should preference the
      ## IO::WaitReadable and IO::WaitWritable APIs wherever supported.
      ##
      ## There is a deliberate lack of full specification around
      ## rack.hijack_io, as semantics will change from server to server.
      ## Users are encouraged to utilize this API with a knowledge of their
      ## server choice, and servers may extend the functionality of
      ## hijack_io to provide additional features to users. The purpose of
      ## rack.hijack is for Rack to "get out of the way", as such, Rack only
      ## provides the minimum of specification and support.
      env['rack.hijack_io'] = HijackWrapper.new(env['rack.hijack_io'])
      io
    end
  else
    ##
    ## If rack.hijack? is false, then rack.hijack should not be set.
    assert("rack.hijack? is false, but rack.hijack is present") { env['rack.hijack'].nil? }
    ##
    ## If rack.hijack? is false, then rack.hijack_io should not be set.
    assert("rack.hijack? is false, but rack.hijack_io is present") { env['rack.hijack_io'].nil? }
  end
end

#check_hijack_response(headers, env) ⇒ Object

Response (after headers)

It is also possible to hijack a response after the status and headers have been sent.



567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
# File 'lib/rack/lint.rb', line 567

def check_hijack_response(headers, env)

  # this check uses headers like a hash, but the spec only requires
  # headers respond to #each
  headers = Rack::Utils::HeaderHash.new(headers)

  ## In order to do this, an application may set the special header
  ## <tt>rack.hijack</tt> to an object that responds to <tt>call</tt>
  ## accepting an argument that conforms to the <tt>rack.hijack_io</tt>
  ## protocol.
  ##
  ## After the headers have been sent, and this hijack callback has been
  ## called, the application is now responsible for the remaining lifecycle
  ## of the IO. The application is also responsible for maintaining HTTP
  ## semantics. Of specific note, in almost all cases in the current SPEC,
  ## applications will have wanted to specify the header Connection:close in
  ## HTTP/1.1, and not Connection:keep-alive, as there is no protocol for
  ## returning hijacked sockets to the web server. For that purpose, use the
  ## body streaming API instead (progressively yielding strings via each).
  ##
  ## Servers must ignore the <tt>body</tt> part of the response tuple when
  ## the <tt>rack.hijack</tt> response API is in use.

  if env['rack.hijack?'] && headers['rack.hijack']
    assert('rack.hijack header must respond to #call') {
      headers['rack.hijack'].respond_to? :call
    }
    original_hijack = headers['rack.hijack']
    headers['rack.hijack'] = proc do |io|
      original_hijack.call HijackWrapper.new(io)
    end
  else
    ##
    ## The special response header <tt>rack.hijack</tt> must only be set
    ## if the request env has <tt>rack.hijack?</tt> <tt>true</tt>.
    assert('rack.hijack header must not be present if server does not support hijacking') {
      headers['rack.hijack'].nil?
    }
  end
end

#check_input(input) ⇒ Object

The Input Stream

The input stream is an IO-like object which contains the raw HTTP POST data.



335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
# File 'lib/rack/lint.rb', line 335

def check_input(input)
  ## When applicable, its external encoding must be "ASCII-8BIT" and it
  ## must be opened in binary mode, for Ruby 1.9 compatibility.
  assert("rack.input #{input} does not have ASCII-8BIT as its external encoding") {
    input.external_encoding.name == "ASCII-8BIT"
  } if input.respond_to?(:external_encoding)
  assert("rack.input #{input} is not opened in binary mode") {
    input.binmode?
  } if input.respond_to?(:binmode?)

  ## The input stream must respond to +gets+, +each+, +read+ and +rewind+.
  [:gets, :each, :read, :rewind].each { |method|
    assert("rack.input #{input} does not respond to ##{method}") {
      input.respond_to? method
    }
  }
end

#check_status(status) ⇒ Object

The Status



617
618
619
620
621
# File 'lib/rack/lint.rb', line 617

def check_status(status)
  ## This is an HTTP status. When parsed as integer (+to_i+), it must be
  ## greater than or equal to 100.
  assert("Status must be >=100 seen as integer") { status.to_i >= 100 }
end

#closeObject



746
747
748
749
# File 'lib/rack/lint.rb', line 746

def close
  @closed = true
  @body.close  if @body.respond_to?(:close)
end

#eachObject

The Body



699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
# File 'lib/rack/lint.rb', line 699

def each
  @closed = false
  bytes = 0

  ## The Body must respond to +each+
  assert("Response body must respond to each") do
    @body.respond_to?(:each)
  end

  @body.each { |part|
    ## and must only yield String values.
    assert("Body yielded non-string value #{part.inspect}") {
      part.kind_of? String
    }
    bytes += Rack::Utils.bytesize(part)
    yield part
  }
  verify_content_length(bytes)

  ##
  ## The Body itself should not be an instance of String, as this will
  ## break in Ruby 1.9.
  ##
  ## If the Body responds to +close+, it will be called after iteration. If
  ## the body is replaced by a middleware after action, the original body
  ## must be closed first, if it responds to close.
  # XXX howto: assert("Body has not been closed") { @closed }


  ##
  ## If the Body responds to +to_path+, it must return a String
  ## identifying the location of a file whose contents are identical
  ## to that produced by calling +each+; this may be used by the
  ## server as an alternative, possibly more efficient way to
  ## transport the response.

  if @body.respond_to?(:to_path)
    assert("The file identified by body.to_path does not exist") {
      ::File.exist? @body.to_path
    }
  end

  ##
  ## The Body commonly is an Array of Strings, the application
  ## instance itself, or a File-like object.
end

#verify_content_length(bytes) ⇒ Object



686
687
688
689
690
691
692
693
694
695
696
# File 'lib/rack/lint.rb', line 686

def verify_content_length(bytes)
  if @head_request
    assert("Response body was given for HEAD request, but should be empty") {
      bytes == 0
    }
  elsif @content_length
    assert("Content-Length header was #{@content_length}, but should be #{bytes}") {
      @content_length == bytes.to_s
    }
  end
end