net-http 0.1.1 → 0.3.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/dependabot.yml +6 -0
- data/.github/workflows/test.yml +3 -5
- data/.gitignore +0 -1
- data/Gemfile +1 -0
- data/README.md +1 -1
- data/Rakefile +1 -1
- data/doc/net-http/examples.rdoc +30 -0
- data/lib/net/http/backward.rb +26 -12
- data/lib/net/http/exceptions.rb +27 -26
- data/lib/net/http/generic_request.rb +6 -7
- data/lib/net/http/header.rb +473 -105
- data/lib/net/http/request.rb +27 -5
- data/lib/net/http/requests.rb +296 -24
- data/lib/net/http/response.rb +303 -12
- data/lib/net/http/responses.rb +638 -223
- data/lib/net/http.rb +681 -371
- data/net-http.gemspec +0 -2
- metadata +5 -18
- data/Gemfile.lock +0 -23
data/lib/net/http/response.rb
CHANGED
@@ -1,20 +1,136 @@
|
|
1
1
|
# frozen_string_literal: false
|
2
|
-
|
2
|
+
|
3
|
+
# This class is the base class for \Net::HTTP request classes.
|
4
|
+
#
|
5
|
+
# == About the Examples
|
6
|
+
#
|
7
|
+
# :include: doc/net-http/examples.rdoc
|
8
|
+
#
|
9
|
+
# == Returned Responses
|
10
|
+
#
|
11
|
+
# \Method Net::HTTP.get_response returns
|
12
|
+
# an instance of one of the subclasses of \Net::HTTPResponse:
|
13
|
+
#
|
14
|
+
# Net::HTTP.get_response(uri)
|
15
|
+
# # => #<Net::HTTPOK 200 OK readbody=true>
|
16
|
+
# Net::HTTP.get_response(hostname, '/nosuch')
|
17
|
+
# # => #<Net::HTTPNotFound 404 Not Found readbody=true>
|
18
|
+
#
|
19
|
+
# As does method Net::HTTP#request:
|
20
|
+
#
|
21
|
+
# req = Net::HTTP::Get.new(uri)
|
22
|
+
# Net::HTTP.start(hostname) do |http|
|
23
|
+
# http.request(req)
|
24
|
+
# end # => #<Net::HTTPOK 200 OK readbody=true>
|
25
|
+
#
|
26
|
+
# \Class \Net::HTTPResponse includes module Net::HTTPHeader,
|
27
|
+
# which provides access to response header values via (among others):
|
28
|
+
#
|
29
|
+
# - \Hash-like method <tt>[]</tt>.
|
30
|
+
# - Specific reader methods, such as +content_type+.
|
31
|
+
#
|
32
|
+
# Examples:
|
33
|
+
#
|
34
|
+
# res = Net::HTTP.get_response(uri) # => #<Net::HTTPOK 200 OK readbody=true>
|
35
|
+
# res['Content-Type'] # => "text/html; charset=UTF-8"
|
36
|
+
# res.content_type # => "text/html"
|
37
|
+
#
|
38
|
+
# == Response Subclasses
|
39
|
+
#
|
40
|
+
# \Class \Net::HTTPResponse has a subclass for each
|
41
|
+
# {HTTP status code}[https://en.wikipedia.org/wiki/List_of_HTTP_status_codes].
|
42
|
+
# You can look up the response class for a given code:
|
43
|
+
#
|
44
|
+
# Net::HTTPResponse::CODE_TO_OBJ['200'] # => Net::HTTPOK
|
45
|
+
# Net::HTTPResponse::CODE_TO_OBJ['400'] # => Net::HTTPBadRequest
|
46
|
+
# Net::HTTPResponse::CODE_TO_OBJ['404'] # => Net::HTTPNotFound
|
47
|
+
#
|
48
|
+
# And you can retrieve the status code for a response object:
|
49
|
+
#
|
50
|
+
# Net::HTTP.get_response(uri).code # => "200"
|
51
|
+
# Net::HTTP.get_response(hostname, '/nosuch').code # => "404"
|
3
52
|
#
|
4
|
-
#
|
5
|
-
# entity requested).
|
53
|
+
# The response subclasses (indentation shows class hierarchy):
|
6
54
|
#
|
7
|
-
#
|
8
|
-
# header values both via hash-like methods and via individual readers.
|
55
|
+
# - Net::HTTPUnknownResponse (for unhandled \HTTP extensions).
|
9
56
|
#
|
10
|
-
#
|
11
|
-
# HTTPResponse subclass. All classes are defined under the Net module.
|
12
|
-
# Indentation indicates inheritance. For a list of the classes see Net::HTTP.
|
57
|
+
# - Net::HTTPInformation:
|
13
58
|
#
|
14
|
-
#
|
15
|
-
#
|
59
|
+
# - Net::HTTPContinue (100)
|
60
|
+
# - Net::HTTPSwitchProtocol (101)
|
61
|
+
# - Net::HTTPProcessing (102)
|
62
|
+
# - Net::HTTPEarlyHints (103)
|
16
63
|
#
|
17
|
-
#
|
64
|
+
# - Net::HTTPSuccess:
|
65
|
+
#
|
66
|
+
# - Net::HTTPOK (200)
|
67
|
+
# - Net::HTTPCreated (201)
|
68
|
+
# - Net::HTTPAccepted (202)
|
69
|
+
# - Net::HTTPNonAuthoritativeInformation (203)
|
70
|
+
# - Net::HTTPNoContent (204)
|
71
|
+
# - Net::HTTPResetContent (205)
|
72
|
+
# - Net::HTTPPartialContent (206)
|
73
|
+
# - Net::HTTPMultiStatus (207)
|
74
|
+
# - Net::HTTPAlreadyReported (208)
|
75
|
+
# - Net::HTTPIMUsed (226)
|
76
|
+
#
|
77
|
+
# - Net::HTTPRedirection:
|
78
|
+
#
|
79
|
+
# - Net::HTTPMultipleChoices (300)
|
80
|
+
# - Net::HTTPMovedPermanently (301)
|
81
|
+
# - Net::HTTPFound (302)
|
82
|
+
# - Net::HTTPSeeOther (303)
|
83
|
+
# - Net::HTTPNotModified (304)
|
84
|
+
# - Net::HTTPUseProxy (305)
|
85
|
+
# - Net::HTTPTemporaryRedirect (307)
|
86
|
+
# - Net::HTTPPermanentRedirect (308)
|
87
|
+
#
|
88
|
+
# - Net::HTTPClientError:
|
89
|
+
#
|
90
|
+
# - Net::HTTPBadRequest (400)
|
91
|
+
# - Net::HTTPUnauthorized (401)
|
92
|
+
# - Net::HTTPPaymentRequired (402)
|
93
|
+
# - Net::HTTPForbidden (403)
|
94
|
+
# - Net::HTTPNotFound (404)
|
95
|
+
# - Net::HTTPMethodNotAllowed (405)
|
96
|
+
# - Net::HTTPNotAcceptable (406)
|
97
|
+
# - Net::HTTPProxyAuthenticationRequired (407)
|
98
|
+
# - Net::HTTPRequestTimeOut (408)
|
99
|
+
# - Net::HTTPConflict (409)
|
100
|
+
# - Net::HTTPGone (410)
|
101
|
+
# - Net::HTTPLengthRequired (411)
|
102
|
+
# - Net::HTTPPreconditionFailed (412)
|
103
|
+
# - Net::HTTPRequestEntityTooLarge (413)
|
104
|
+
# - Net::HTTPRequestURITooLong (414)
|
105
|
+
# - Net::HTTPUnsupportedMediaType (415)
|
106
|
+
# - Net::HTTPRequestedRangeNotSatisfiable (416)
|
107
|
+
# - Net::HTTPExpectationFailed (417)
|
108
|
+
# - Net::HTTPMisdirectedRequest (421)
|
109
|
+
# - Net::HTTPUnprocessableEntity (422)
|
110
|
+
# - Net::HTTPLocked (423)
|
111
|
+
# - Net::HTTPFailedDependency (424)
|
112
|
+
# - Net::HTTPUpgradeRequired (426)
|
113
|
+
# - Net::HTTPPreconditionRequired (428)
|
114
|
+
# - Net::HTTPTooManyRequests (429)
|
115
|
+
# - Net::HTTPRequestHeaderFieldsTooLarge (431)
|
116
|
+
# - Net::HTTPUnavailableForLegalReasons (451)
|
117
|
+
#
|
118
|
+
# - Net::HTTPServerError:
|
119
|
+
#
|
120
|
+
# - Net::HTTPInternalServerError (500)
|
121
|
+
# - Net::HTTPNotImplemented (501)
|
122
|
+
# - Net::HTTPBadGateway (502)
|
123
|
+
# - Net::HTTPServiceUnavailable (503)
|
124
|
+
# - Net::HTTPGatewayTimeOut (504)
|
125
|
+
# - Net::HTTPVersionNotSupported (505)
|
126
|
+
# - Net::HTTPVariantAlsoNegotiates (506)
|
127
|
+
# - Net::HTTPInsufficientStorage (507)
|
128
|
+
# - Net::HTTPLoopDetected (508)
|
129
|
+
# - Net::HTTPNotExtended (510)
|
130
|
+
# - Net::HTTPNetworkAuthenticationRequired (511)
|
131
|
+
#
|
132
|
+
# There is also the Net::HTTPBadResponse exception which is raised when
|
133
|
+
# there is a protocol error.
|
18
134
|
#
|
19
135
|
class Net::HTTPResponse
|
20
136
|
class << self
|
@@ -84,6 +200,8 @@ class Net::HTTPResponse
|
|
84
200
|
@read = false
|
85
201
|
@uri = nil
|
86
202
|
@decode_content = false
|
203
|
+
@body_encoding = false
|
204
|
+
@ignore_eof = true
|
87
205
|
end
|
88
206
|
|
89
207
|
# The HTTP version supported by the server.
|
@@ -106,6 +224,22 @@ class Net::HTTPResponse
|
|
106
224
|
# Accept-Encoding header from the user.
|
107
225
|
attr_accessor :decode_content
|
108
226
|
|
227
|
+
# The encoding to use for the response body. If Encoding, use that encoding.
|
228
|
+
# If other true value, attempt to detect the appropriate encoding, and use
|
229
|
+
# that.
|
230
|
+
attr_reader :body_encoding
|
231
|
+
|
232
|
+
# Set the encoding to use for the response body. If given a String, find
|
233
|
+
# the related Encoding.
|
234
|
+
def body_encoding=(value)
|
235
|
+
value = Encoding.find(value) if value.is_a?(String)
|
236
|
+
@body_encoding = value
|
237
|
+
end
|
238
|
+
|
239
|
+
# Whether to ignore EOF when reading bodies with a specified Content-Length
|
240
|
+
# header.
|
241
|
+
attr_accessor :ignore_eof
|
242
|
+
|
109
243
|
def inspect
|
110
244
|
"#<#{self.class} #{@code} #{@message} readbody=#{@read}>"
|
111
245
|
end
|
@@ -214,6 +348,17 @@ class Net::HTTPResponse
|
|
214
348
|
end
|
215
349
|
@read = true
|
216
350
|
|
351
|
+
case enc = @body_encoding
|
352
|
+
when Encoding, false, nil
|
353
|
+
# Encoding: force given encoding
|
354
|
+
# false/nil: do not force encoding
|
355
|
+
else
|
356
|
+
# other value: detect encoding from body
|
357
|
+
enc = detect_encoding(@body)
|
358
|
+
end
|
359
|
+
|
360
|
+
@body.force_encoding(enc) if enc
|
361
|
+
|
217
362
|
@body
|
218
363
|
end
|
219
364
|
|
@@ -245,6 +390,141 @@ class Net::HTTPResponse
|
|
245
390
|
|
246
391
|
private
|
247
392
|
|
393
|
+
# :nodoc:
|
394
|
+
def detect_encoding(str, encoding=nil)
|
395
|
+
if encoding
|
396
|
+
elsif encoding = type_params['charset']
|
397
|
+
elsif encoding = check_bom(str)
|
398
|
+
else
|
399
|
+
encoding = case content_type&.downcase
|
400
|
+
when %r{text/x(?:ht)?ml|application/(?:[^+]+\+)?xml}
|
401
|
+
/\A<xml[ \t\r\n]+
|
402
|
+
version[ \t\r\n]*=[ \t\r\n]*(?:"[0-9.]+"|'[0-9.]*')[ \t\r\n]+
|
403
|
+
encoding[ \t\r\n]*=[ \t\r\n]*
|
404
|
+
(?:"([A-Za-z][\-A-Za-z0-9._]*)"|'([A-Za-z][\-A-Za-z0-9._]*)')/x =~ str
|
405
|
+
encoding = $1 || $2 || Encoding::UTF_8
|
406
|
+
when %r{text/html.*}
|
407
|
+
sniff_encoding(str)
|
408
|
+
end
|
409
|
+
end
|
410
|
+
return encoding
|
411
|
+
end
|
412
|
+
|
413
|
+
# :nodoc:
|
414
|
+
def sniff_encoding(str, encoding=nil)
|
415
|
+
# the encoding sniffing algorithm
|
416
|
+
# http://www.w3.org/TR/html5/parsing.html#determining-the-character-encoding
|
417
|
+
if enc = scanning_meta(str)
|
418
|
+
enc
|
419
|
+
# 6. last visited page or something
|
420
|
+
# 7. frequency
|
421
|
+
elsif str.ascii_only?
|
422
|
+
Encoding::US_ASCII
|
423
|
+
elsif str.dup.force_encoding(Encoding::UTF_8).valid_encoding?
|
424
|
+
Encoding::UTF_8
|
425
|
+
end
|
426
|
+
# 8. implementation-defined or user-specified
|
427
|
+
end
|
428
|
+
|
429
|
+
# :nodoc:
|
430
|
+
def check_bom(str)
|
431
|
+
case str.byteslice(0, 2)
|
432
|
+
when "\xFE\xFF"
|
433
|
+
return Encoding::UTF_16BE
|
434
|
+
when "\xFF\xFE"
|
435
|
+
return Encoding::UTF_16LE
|
436
|
+
end
|
437
|
+
if "\xEF\xBB\xBF" == str.byteslice(0, 3)
|
438
|
+
return Encoding::UTF_8
|
439
|
+
end
|
440
|
+
nil
|
441
|
+
end
|
442
|
+
|
443
|
+
# :nodoc:
|
444
|
+
def scanning_meta(str)
|
445
|
+
require 'strscan'
|
446
|
+
ss = StringScanner.new(str)
|
447
|
+
if ss.scan_until(/<meta[\t\n\f\r ]*/)
|
448
|
+
attrs = {} # attribute_list
|
449
|
+
got_pragma = false
|
450
|
+
need_pragma = nil
|
451
|
+
charset = nil
|
452
|
+
|
453
|
+
# step: Attributes
|
454
|
+
while attr = get_attribute(ss)
|
455
|
+
name, value = *attr
|
456
|
+
next if attrs[name]
|
457
|
+
attrs[name] = true
|
458
|
+
case name
|
459
|
+
when 'http-equiv'
|
460
|
+
got_pragma = true if value == 'content-type'
|
461
|
+
when 'content'
|
462
|
+
encoding = extracting_encodings_from_meta_elements(value)
|
463
|
+
unless charset
|
464
|
+
charset = encoding
|
465
|
+
end
|
466
|
+
need_pragma = true
|
467
|
+
when 'charset'
|
468
|
+
need_pragma = false
|
469
|
+
charset = value
|
470
|
+
end
|
471
|
+
end
|
472
|
+
|
473
|
+
# step: Processing
|
474
|
+
return if need_pragma.nil?
|
475
|
+
return if need_pragma && !got_pragma
|
476
|
+
|
477
|
+
charset = Encoding.find(charset) rescue nil
|
478
|
+
return unless charset
|
479
|
+
charset = Encoding::UTF_8 if charset == Encoding::UTF_16
|
480
|
+
return charset # tentative
|
481
|
+
end
|
482
|
+
nil
|
483
|
+
end
|
484
|
+
|
485
|
+
def get_attribute(ss)
|
486
|
+
ss.scan(/[\t\n\f\r \/]*/)
|
487
|
+
if ss.peek(1) == '>'
|
488
|
+
ss.getch
|
489
|
+
return nil
|
490
|
+
end
|
491
|
+
name = ss.scan(/[^=\t\n\f\r \/>]*/)
|
492
|
+
name.downcase!
|
493
|
+
raise if name.empty?
|
494
|
+
ss.skip(/[\t\n\f\r ]*/)
|
495
|
+
if ss.getch != '='
|
496
|
+
value = ''
|
497
|
+
return [name, value]
|
498
|
+
end
|
499
|
+
ss.skip(/[\t\n\f\r ]*/)
|
500
|
+
case ss.peek(1)
|
501
|
+
when '"'
|
502
|
+
ss.getch
|
503
|
+
value = ss.scan(/[^"]+/)
|
504
|
+
value.downcase!
|
505
|
+
ss.getch
|
506
|
+
when "'"
|
507
|
+
ss.getch
|
508
|
+
value = ss.scan(/[^']+/)
|
509
|
+
value.downcase!
|
510
|
+
ss.getch
|
511
|
+
when '>'
|
512
|
+
value = ''
|
513
|
+
else
|
514
|
+
value = ss.scan(/[^\t\n\f\r >]+/)
|
515
|
+
value.downcase!
|
516
|
+
end
|
517
|
+
[name, value]
|
518
|
+
end
|
519
|
+
|
520
|
+
def extracting_encodings_from_meta_elements(value)
|
521
|
+
# http://dev.w3.org/html5/spec/fetching-resources.html#algorithm-for-extracting-an-encoding-from-a-meta-element
|
522
|
+
if /charset[\t\n\f\r ]*=(?:"([^"]*)"|'([^']*)'|["']|\z|([^\t\n\f\r ;]+))/i =~ value
|
523
|
+
return $1 || $2 || $3
|
524
|
+
end
|
525
|
+
return nil
|
526
|
+
end
|
527
|
+
|
248
528
|
##
|
249
529
|
# Checks for a supported Content-Encoding header and yields an Inflate
|
250
530
|
# wrapper for this response's socket when zlib is present. If the
|
@@ -272,6 +552,9 @@ class Net::HTTPResponse
|
|
272
552
|
ensure
|
273
553
|
begin
|
274
554
|
inflate_body_io.finish
|
555
|
+
if self['content-length']
|
556
|
+
self['content-length'] = inflate_body_io.bytes_inflated.to_s
|
557
|
+
end
|
275
558
|
rescue => err
|
276
559
|
# Ignore #finish's error if there is an exception from yield
|
277
560
|
raise err if success
|
@@ -297,7 +580,7 @@ class Net::HTTPResponse
|
|
297
580
|
|
298
581
|
clen = content_length()
|
299
582
|
if clen
|
300
|
-
@socket.read clen, dest,
|
583
|
+
@socket.read clen, dest, @ignore_eof
|
301
584
|
return
|
302
585
|
end
|
303
586
|
clen = range_length()
|
@@ -373,6 +656,14 @@ class Net::HTTPResponse
|
|
373
656
|
@inflate.finish
|
374
657
|
end
|
375
658
|
|
659
|
+
##
|
660
|
+
# The number of bytes inflated, used to update the Content-Length of
|
661
|
+
# the response.
|
662
|
+
|
663
|
+
def bytes_inflated
|
664
|
+
@inflate.total_out
|
665
|
+
end
|
666
|
+
|
376
667
|
##
|
377
668
|
# Returns a Net::ReadAdapter that inflates each read chunk into +dest+.
|
378
669
|
#
|