multipart-parser 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/LICENSE +21 -0
- data/README +17 -0
- data/lib/multipart_parser/parser.rb +246 -0
- data/lib/multipart_parser/reader.rb +152 -0
- data/lib/multipart_parser/version.rb +3 -0
- data/multipart-parser.gemspec +27 -0
- data/test/fixtures/multipart.rb +111 -0
- data/test/multipart_parser/parser_test.rb +97 -0
- data/test/multipart_parser/reader.rb +74 -0
- metadata +77 -0
data/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
Copyright (c) 2011,2012 Daniel Abrahamsson
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
21
|
+
|
data/README
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
multipart-parser is a simple parser for multipart MIME messages, written in Ruby, based on felixge/node-formidable's parser.
|
2
|
+
|
3
|
+
Some things to note:
|
4
|
+
|
5
|
+
* Pure Ruby
|
6
|
+
|
7
|
+
* Event-driven API
|
8
|
+
|
9
|
+
* Only supports one level of multipart parsing. Invoke another parser if you need to handle nested messages.
|
10
|
+
|
11
|
+
* Does not perform I/O.
|
12
|
+
|
13
|
+
* Does not depend on any other library.
|
14
|
+
|
15
|
+
Contributors:
|
16
|
+
Daniel Abrahamsson
|
17
|
+
Jérémy Bobbio
|
@@ -0,0 +1,246 @@
|
|
1
|
+
module MultipartParser
|
2
|
+
# A low level parser for multipart messages,
|
3
|
+
# based on the node-formidable parser.
|
4
|
+
class Parser
|
5
|
+
|
6
|
+
def initialize
|
7
|
+
@boundary = nil
|
8
|
+
@boundary_chars = nil
|
9
|
+
@lookbehind = nil
|
10
|
+
@state = :parser_uninitialized
|
11
|
+
@index = 0 # Index into boundary or header
|
12
|
+
@flags = {}
|
13
|
+
@marks = {} # Keep track of different parts
|
14
|
+
@callbacks = {}
|
15
|
+
end
|
16
|
+
|
17
|
+
# Initializes the parser, using the given boundary
|
18
|
+
def init_with_boundary(boundary)
|
19
|
+
@boundary = "\r\n--" + boundary
|
20
|
+
@lookbehind = "\0"*(@boundary.length + 8)
|
21
|
+
@state = :start
|
22
|
+
|
23
|
+
@boundary_chars = {}
|
24
|
+
@boundary.each_byte do |b|
|
25
|
+
@boundary_chars[b] = true
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
# Registers a callback to be called when the
|
30
|
+
# given event occurs. Each callback is expected to
|
31
|
+
# take three parameters: buffer, start_index, and end_index.
|
32
|
+
# All of these parameters may be null, depending on the callback.
|
33
|
+
# Valid callbacks are:
|
34
|
+
# :end
|
35
|
+
# :header_field
|
36
|
+
# :header_value
|
37
|
+
# :header_end
|
38
|
+
# :headers_end
|
39
|
+
# :part_begin
|
40
|
+
# :part_data
|
41
|
+
# :part_end
|
42
|
+
def on(event, &callback)
|
43
|
+
@callbacks[event] = callback
|
44
|
+
end
|
45
|
+
|
46
|
+
# Writes data to the parser.
|
47
|
+
# Returns the number of bytes parsed.
|
48
|
+
# In practise, this means that if the return value
|
49
|
+
# is less than the buffer length, a parse error occured.
|
50
|
+
def write(buffer)
|
51
|
+
i = 0
|
52
|
+
buffer_length = buffer.length
|
53
|
+
index = @index
|
54
|
+
flags = @flags.dup
|
55
|
+
state = @state
|
56
|
+
lookbehind = @lookbehind
|
57
|
+
boundary = @boundary
|
58
|
+
boundary_chars = @boundary_chars
|
59
|
+
boundary_length = @boundary.length
|
60
|
+
boundary_end = boundary_length - 1
|
61
|
+
|
62
|
+
while i < buffer_length
|
63
|
+
c = buffer[i, 1]
|
64
|
+
case state
|
65
|
+
when :parser_uninitialized
|
66
|
+
return i;
|
67
|
+
when :start
|
68
|
+
index = 0;
|
69
|
+
state = :start_boundary
|
70
|
+
when :start_boundary # Differs in that it has no preceeding \r\n
|
71
|
+
if index == boundary_length - 2
|
72
|
+
return i unless c == "\r"
|
73
|
+
index += 1
|
74
|
+
elsif index - 1 == boundary_length - 2
|
75
|
+
return i unless c == "\n"
|
76
|
+
# Boundary read successfully, begin next part
|
77
|
+
callback(:part_begin)
|
78
|
+
state = :header_field_start
|
79
|
+
else
|
80
|
+
return i unless c == boundary[index+2, 1] # Unexpected character
|
81
|
+
index += 1
|
82
|
+
end
|
83
|
+
i += 1
|
84
|
+
when :header_field_start
|
85
|
+
state = :header_field
|
86
|
+
@marks[:header_field] = i
|
87
|
+
index = 0
|
88
|
+
when :header_field
|
89
|
+
if c == "\r"
|
90
|
+
@marks.delete :header_field
|
91
|
+
state = :headers_almost_done
|
92
|
+
else
|
93
|
+
index += 1
|
94
|
+
unless c == "-" # Skip hyphens
|
95
|
+
if c == ":"
|
96
|
+
return i if index == 1 # Empty header field
|
97
|
+
data_callback(:header_field, buffer, i, :clear => true)
|
98
|
+
state = :header_value_start
|
99
|
+
else
|
100
|
+
cl = c.downcase
|
101
|
+
return i if cl < "a" || cl > "z"
|
102
|
+
end
|
103
|
+
end
|
104
|
+
end
|
105
|
+
i += 1
|
106
|
+
when :header_value_start
|
107
|
+
if c == " " # Skip spaces
|
108
|
+
i += 1
|
109
|
+
else
|
110
|
+
@marks[:header_value] = i
|
111
|
+
state = :header_value
|
112
|
+
end
|
113
|
+
when :header_value
|
114
|
+
if c == "\r"
|
115
|
+
data_callback(:header_value, buffer, i, :clear => true)
|
116
|
+
callback(:header_end)
|
117
|
+
state = :header_value_almost_done
|
118
|
+
end
|
119
|
+
i += 1
|
120
|
+
when :header_value_almost_done
|
121
|
+
return i unless c == "\n"
|
122
|
+
state = :header_field_start
|
123
|
+
i += 1
|
124
|
+
when :headers_almost_done
|
125
|
+
return i unless c == "\n"
|
126
|
+
callback(:headers_end)
|
127
|
+
state = :part_data_start
|
128
|
+
i += 1
|
129
|
+
when :part_data_start
|
130
|
+
state = :part_data
|
131
|
+
@marks[:part_data] = i
|
132
|
+
when :part_data
|
133
|
+
prev_index = index
|
134
|
+
|
135
|
+
if index == 0
|
136
|
+
# Boyer-Moore derived algorithm to safely skip non-boundary data
|
137
|
+
# See http://debuggable.com/posts/parsing-file-uploads-at-500-
|
138
|
+
# mb-s-with-node-js:4c03862e-351c-4faa-bb67-4365cbdd56cb
|
139
|
+
while i + boundary_length <= buffer_length
|
140
|
+
break if boundary_chars.has_key? buffer[i + boundary_end]
|
141
|
+
i += boundary_length
|
142
|
+
end
|
143
|
+
c = buffer[i, 1]
|
144
|
+
end
|
145
|
+
|
146
|
+
if index < boundary_length
|
147
|
+
if boundary[index, 1] == c
|
148
|
+
if index == 0
|
149
|
+
data_callback(:part_data, buffer, i, :clear => true)
|
150
|
+
end
|
151
|
+
index += 1
|
152
|
+
else # It was not the boundary we found, after all
|
153
|
+
index = 0
|
154
|
+
end
|
155
|
+
elsif index == boundary_length
|
156
|
+
index += 1
|
157
|
+
if c == "\r"
|
158
|
+
flags[:part_boundary] = true
|
159
|
+
elsif c == "-"
|
160
|
+
flags[:last_boundary] = true
|
161
|
+
else # We did not find a boundary after all
|
162
|
+
index = 0
|
163
|
+
end
|
164
|
+
elsif index - 1 == boundary_length
|
165
|
+
if flags[:part_boundary]
|
166
|
+
index = 0
|
167
|
+
if c == "\n"
|
168
|
+
flags.delete :part_boundary
|
169
|
+
callback(:part_end)
|
170
|
+
callback(:part_begin)
|
171
|
+
state = :header_field_start
|
172
|
+
i += 1
|
173
|
+
next # Ugly way to break out of the case statement
|
174
|
+
end
|
175
|
+
elsif flags[:last_boundary]
|
176
|
+
if c == "-"
|
177
|
+
callback(:part_end)
|
178
|
+
callback(:end)
|
179
|
+
state = :end
|
180
|
+
else
|
181
|
+
index = 0 # False alarm
|
182
|
+
end
|
183
|
+
else
|
184
|
+
index = 0
|
185
|
+
end
|
186
|
+
end
|
187
|
+
|
188
|
+
if index > 0
|
189
|
+
# When matching a possible boundary, keep a lookbehind
|
190
|
+
# reference in case it turns out to be a false lead
|
191
|
+
lookbehind[index-1] = c
|
192
|
+
elsif prev_index > 0
|
193
|
+
# If our boundary turns out to be rubbish,
|
194
|
+
# the captured lookbehind belongs to part_data
|
195
|
+
callback(:part_data, lookbehind, 0, prev_index)
|
196
|
+
@marks[:part_data] = i
|
197
|
+
|
198
|
+
# Reconsider the current character as it might be the
|
199
|
+
# beginning of a new sequence.
|
200
|
+
i -= 1
|
201
|
+
end
|
202
|
+
|
203
|
+
i += 1
|
204
|
+
when :end
|
205
|
+
i += 1
|
206
|
+
else
|
207
|
+
return i;
|
208
|
+
end
|
209
|
+
end
|
210
|
+
|
211
|
+
data_callback(:header_field, buffer, buffer_length)
|
212
|
+
data_callback(:header_value, buffer, buffer_length)
|
213
|
+
data_callback(:part_data, buffer, buffer_length)
|
214
|
+
|
215
|
+
@index = index
|
216
|
+
@state = state
|
217
|
+
@flags = flags
|
218
|
+
|
219
|
+
return buffer_length
|
220
|
+
end
|
221
|
+
|
222
|
+
private
|
223
|
+
|
224
|
+
# Issues a callback.
|
225
|
+
def callback(event, buffer = nil, start = nil, the_end = nil)
|
226
|
+
return if !start.nil? && start == the_end
|
227
|
+
if @callbacks.has_key? event
|
228
|
+
@callbacks[event].call(buffer, start, the_end)
|
229
|
+
end
|
230
|
+
end
|
231
|
+
|
232
|
+
# Issues a data callback,
|
233
|
+
# The only valid options is :clear,
|
234
|
+
# which, if true, will reset the appropriate mark to 0,
|
235
|
+
# If not specified, the mark will be removed.
|
236
|
+
def data_callback(data_type, buffer, the_end, options = {})
|
237
|
+
return unless @marks.has_key? data_type
|
238
|
+
callback(data_type, buffer, @marks[data_type], the_end)
|
239
|
+
unless options[:clear]
|
240
|
+
@marks[data_type] = 0
|
241
|
+
else
|
242
|
+
@marks.delete data_type
|
243
|
+
end
|
244
|
+
end
|
245
|
+
end
|
246
|
+
end
|
@@ -0,0 +1,152 @@
|
|
1
|
+
require File.expand_path('../parser', __FILE__)
|
2
|
+
|
3
|
+
module MultipartParser
|
4
|
+
class NotMultipartError < StandardError; end;
|
5
|
+
|
6
|
+
# A more high level interface to MultipartParser.
|
7
|
+
class Reader
|
8
|
+
|
9
|
+
# Initializes a MultipartReader, that will
|
10
|
+
# read a request with the given boundary value.
|
11
|
+
def initialize(boundary)
|
12
|
+
@parser = Parser.new
|
13
|
+
@parser.init_with_boundary(boundary)
|
14
|
+
@header_field = ''
|
15
|
+
@header_value = ''
|
16
|
+
@part = nil
|
17
|
+
@ended = false
|
18
|
+
@on_error = nil
|
19
|
+
@on_part = nil
|
20
|
+
|
21
|
+
init_parser_callbacks
|
22
|
+
end
|
23
|
+
|
24
|
+
# Returns true if the parser has finished parsing
|
25
|
+
def ended?
|
26
|
+
@ended
|
27
|
+
end
|
28
|
+
|
29
|
+
# Sets to a code block to call
|
30
|
+
# when part headers have been parsed.
|
31
|
+
def on_part(&callback)
|
32
|
+
@on_part = callback
|
33
|
+
end
|
34
|
+
|
35
|
+
# Sets a code block to call when
|
36
|
+
# a parser error occurs.
|
37
|
+
def on_error(&callback)
|
38
|
+
@on_error = callback
|
39
|
+
end
|
40
|
+
|
41
|
+
# Write data from the given buffer (String)
|
42
|
+
# into the reader.
|
43
|
+
def write(buffer)
|
44
|
+
bytes_parsed = @parser.write(buffer)
|
45
|
+
if bytes_parsed != buffer.size
|
46
|
+
msg = "Parser error, #{bytes_parsed} of #{buffer.length} bytes parsed"
|
47
|
+
@on_error.call(msg) unless @on_error.nil?
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
# Extracts a boundary value from a Content-Type header.
|
52
|
+
# Note that it is the header value you provide here.
|
53
|
+
# Raises NotMultipartError if content_type is invalid.
|
54
|
+
def self.extract_boundary_value(content_type)
|
55
|
+
if content_type =~ /multipart/i
|
56
|
+
if match = (content_type =~ /boundary=(?:"([^"]+)"|([^;]+))/i)
|
57
|
+
$1 || $2
|
58
|
+
else
|
59
|
+
raise NotMultipartError.new("No multipart boundary")
|
60
|
+
end
|
61
|
+
else
|
62
|
+
raise NotMultipartError.new("Not a multipart content type!")
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
class Part
|
67
|
+
attr_accessor :filename, :headers, :name, :mime
|
68
|
+
|
69
|
+
def initialize
|
70
|
+
@headers = {}
|
71
|
+
@data_callback = nil
|
72
|
+
@end_callback = nil
|
73
|
+
end
|
74
|
+
|
75
|
+
# Calls the data callback with the given data
|
76
|
+
def emit_data(data)
|
77
|
+
@data_callback.call(data) unless @data_callback.nil?
|
78
|
+
end
|
79
|
+
|
80
|
+
# Calls the end callback
|
81
|
+
def emit_end
|
82
|
+
@end_callback.call unless @end_callback.nil?
|
83
|
+
end
|
84
|
+
|
85
|
+
# Sets a block to be called when part data
|
86
|
+
# is read. The block should take one parameter,
|
87
|
+
# namely the read data.
|
88
|
+
def on_data(&callback)
|
89
|
+
@data_callback = callback
|
90
|
+
end
|
91
|
+
|
92
|
+
# Sets a block to be called when all data
|
93
|
+
# for the part has been read.
|
94
|
+
def on_end(&callback)
|
95
|
+
@end_callback = callback
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
private
|
100
|
+
|
101
|
+
def init_parser_callbacks
|
102
|
+
@parser.on(:part_begin) do
|
103
|
+
@part = Part.new
|
104
|
+
@header_field = ''
|
105
|
+
@header_value = ''
|
106
|
+
end
|
107
|
+
|
108
|
+
@parser.on(:header_field) do |b, start, the_end|
|
109
|
+
@header_field << b[start...the_end]
|
110
|
+
end
|
111
|
+
|
112
|
+
@parser.on(:header_value) do |b, start, the_end|
|
113
|
+
@header_value << b[start...the_end]
|
114
|
+
end
|
115
|
+
|
116
|
+
@parser.on(:header_end) do
|
117
|
+
@header_field.downcase!
|
118
|
+
@part.headers[@header_field] = @header_value
|
119
|
+
if @header_field == 'content-disposition'
|
120
|
+
if @header_value =~ /name="([^"]+)"/i
|
121
|
+
@part.name = $1
|
122
|
+
end
|
123
|
+
if @header_value =~ /filename="([^;]+)"/i
|
124
|
+
match = $1
|
125
|
+
start = (match.rindex("\\") || -1)+1
|
126
|
+
@part.filename = match[start...(match.length)]
|
127
|
+
end
|
128
|
+
elsif @header_field == 'content-type'
|
129
|
+
@part.mime = @header_value
|
130
|
+
end
|
131
|
+
@header_field = ''
|
132
|
+
@header_value = ''
|
133
|
+
end
|
134
|
+
|
135
|
+
@parser.on(:headers_end) do
|
136
|
+
@on_part.call(@part) unless @on_part.nil?
|
137
|
+
end
|
138
|
+
|
139
|
+
@parser.on(:part_data) do |b, start, the_end|
|
140
|
+
@part.emit_data b[start...the_end]
|
141
|
+
end
|
142
|
+
|
143
|
+
@parser.on(:part_end) do
|
144
|
+
@part.emit_end
|
145
|
+
end
|
146
|
+
|
147
|
+
@parser.on(:end) do
|
148
|
+
@ended = true
|
149
|
+
end
|
150
|
+
end
|
151
|
+
end
|
152
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
$:.push File.expand_path("../lib", __FILE__)
|
2
|
+
require 'multipart_parser/version'
|
3
|
+
|
4
|
+
Gem::Specification.new do |s|
|
5
|
+
s.name = 'multipart-parser'
|
6
|
+
s.version = MultipartParser::VERSION
|
7
|
+
s.authors = ['Daniel Abrahamsson']
|
8
|
+
s.email = ['hamsson@gmail.com']
|
9
|
+
s.homepage = 'https://github.com/danabr/multipart-parser'
|
10
|
+
s.summary = %q{simple parser for multipart MIME messages}
|
11
|
+
s.description = <<-DESCRIPTION.gsub(/^ */, '')
|
12
|
+
multipart-parser is a simple parser for multipart MIME messages, written in
|
13
|
+
Ruby, based on felixge/node-formidable's parser.
|
14
|
+
|
15
|
+
Some things to note:
|
16
|
+
- Pure Ruby
|
17
|
+
- Event-driven API
|
18
|
+
- Only supports one level of multipart parsing. Invoke another parser if
|
19
|
+
you need to handle nested messages.
|
20
|
+
- Does not perform I/O.
|
21
|
+
- Does not depend on any other library.
|
22
|
+
DESCRIPTION
|
23
|
+
|
24
|
+
s.files = `git ls-files`.split("\n")
|
25
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
26
|
+
s.require_paths = ['lib']
|
27
|
+
end
|
@@ -0,0 +1,111 @@
|
|
1
|
+
# Contains fixturues to
|
2
|
+
module MultipartParser::Fixtures
|
3
|
+
# Returns all fixtures in the module
|
4
|
+
def fixtures
|
5
|
+
[Rfc1867.new, NoTrailingCRLF.new, EmptyHeader.new]
|
6
|
+
end
|
7
|
+
extend self
|
8
|
+
|
9
|
+
class Rfc1867
|
10
|
+
def boundary
|
11
|
+
'AaB03x'
|
12
|
+
end
|
13
|
+
|
14
|
+
def expect_error
|
15
|
+
false
|
16
|
+
end
|
17
|
+
|
18
|
+
def parts
|
19
|
+
part1, part2 = {}, {}
|
20
|
+
part1[:headers] = {'content-disposition' => 'form-data; name="field1"'}
|
21
|
+
part1[:data] = "Joe Blow\r\nalmost tricked you!"
|
22
|
+
part2[:headers] = {}
|
23
|
+
part2[:headers]['content-disposition'] = 'form-data; name="pics"; ' +
|
24
|
+
'filename="file1.txt"'
|
25
|
+
part2[:headers]['Content-Type'] = 'text/plain'
|
26
|
+
part2[:data] = "... contents of file1.txt ...\r"
|
27
|
+
[part1, part2]
|
28
|
+
end
|
29
|
+
|
30
|
+
def raw
|
31
|
+
['--AaB03x',
|
32
|
+
'content-disposition: form-data; name="field1"',
|
33
|
+
'',
|
34
|
+
"Joe Blow\r\nalmost tricked you!",
|
35
|
+
'--AaB03x',
|
36
|
+
'content-disposition: form-data; name="pics"; filename="file1.txt"',
|
37
|
+
'Content-Type: text/plain',
|
38
|
+
'',
|
39
|
+
"... contents of file1.txt ...\r",
|
40
|
+
'--AaB03x--',
|
41
|
+
''
|
42
|
+
].join("\r\n")
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
class NoTrailingCRLF
|
47
|
+
def boundary
|
48
|
+
'AaB03x'
|
49
|
+
end
|
50
|
+
|
51
|
+
def expect_error
|
52
|
+
false
|
53
|
+
end
|
54
|
+
|
55
|
+
def parts
|
56
|
+
part1, part2 = {}, {}
|
57
|
+
part1[:headers] = {'content-disposition' => 'form-data; name="field1"'}
|
58
|
+
part1[:data] = "Joe Blow\r\nalmost tricked you!"
|
59
|
+
part2[:headers] = {}
|
60
|
+
part2[:headers]['content-disposition'] = 'form-data; name="pics"; ' +
|
61
|
+
'filename="file1.txt"'
|
62
|
+
part2[:headers]['Content-Type'] = 'text/plain'
|
63
|
+
part2[:data] = "... contents of file1.txt ...\r"
|
64
|
+
[part1, part2]
|
65
|
+
end
|
66
|
+
|
67
|
+
def raw
|
68
|
+
['--AaB03x',
|
69
|
+
'content-disposition: form-data; name="field1"',
|
70
|
+
'',
|
71
|
+
"Joe Blow\r\nalmost tricked you!",
|
72
|
+
'--AaB03x',
|
73
|
+
'content-disposition: form-data; name="pics"; filename="file1.txt"',
|
74
|
+
'Content-Type: text/plain',
|
75
|
+
'',
|
76
|
+
"... contents of file1.txt ...\r",
|
77
|
+
'--AaB03x--'
|
78
|
+
].join("\r\n")
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
class EmptyHeader
|
83
|
+
def boundary
|
84
|
+
'AaB03x'
|
85
|
+
end
|
86
|
+
|
87
|
+
def expect_error
|
88
|
+
true
|
89
|
+
end
|
90
|
+
|
91
|
+
def parts
|
92
|
+
[] # Should never be called
|
93
|
+
end
|
94
|
+
|
95
|
+
def raw
|
96
|
+
['--AaB03x',
|
97
|
+
'content-disposition: form-data; name="field1"',
|
98
|
+
': foo',
|
99
|
+
'',
|
100
|
+
"Joe Blow\r\nalmost tricked you!",
|
101
|
+
'--AaB03x',
|
102
|
+
'content-disposition: form-data; name="pics"; filename="file1.txt"',
|
103
|
+
'Content-Type: text/plain',
|
104
|
+
'',
|
105
|
+
"... contents of file1.txt ...\r",
|
106
|
+
'--AaB03x--',
|
107
|
+
''
|
108
|
+
].join("\r\n")
|
109
|
+
end
|
110
|
+
end
|
111
|
+
end
|
@@ -0,0 +1,97 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require File.dirname(__FILE__) + "/../../lib/multipart_parser/parser"
|
3
|
+
require File.dirname(__FILE__) + "/../fixtures/multipart"
|
4
|
+
|
5
|
+
module MultipartParser
|
6
|
+
class ParserTest < Test::Unit::TestCase
|
7
|
+
def test_init_with_boundary
|
8
|
+
parser = Parser.new
|
9
|
+
def parser.boundary; @boundary end
|
10
|
+
def parser.boundary_chars; @boundary_chars end
|
11
|
+
|
12
|
+
parser.init_with_boundary("abc")
|
13
|
+
assert_equal "\r\n--abc", parser.boundary
|
14
|
+
expected_bc = {13 => true, 10 => true, 45 => true, 97 => true,
|
15
|
+
98 => true, 99 => true}
|
16
|
+
assert_equal expected_bc, parser.boundary_chars
|
17
|
+
end
|
18
|
+
|
19
|
+
def test_parser_error
|
20
|
+
parser = Parser.new
|
21
|
+
parser.init_with_boundary("abc")
|
22
|
+
assert_equal 3, parser.write("--ad")
|
23
|
+
end
|
24
|
+
|
25
|
+
def test_fixtures
|
26
|
+
parser = Parser.new
|
27
|
+
chunk_length = 10
|
28
|
+
Fixtures.fixtures.each do |fixture|
|
29
|
+
buffer = fixture.raw
|
30
|
+
parts = []
|
31
|
+
part, header_field, header_value = nil, nil, nil
|
32
|
+
end_called = false
|
33
|
+
got_error = false
|
34
|
+
|
35
|
+
parser.init_with_boundary(fixture.boundary)
|
36
|
+
|
37
|
+
parser.on(:part_begin) do
|
38
|
+
part = {:headers => {}, :data => ''}
|
39
|
+
parts.push(part)
|
40
|
+
header_field = ''
|
41
|
+
header_value = ''
|
42
|
+
end
|
43
|
+
|
44
|
+
parser.on(:header_field) do |b, start, the_end|
|
45
|
+
header_field += b[start...the_end]
|
46
|
+
end
|
47
|
+
|
48
|
+
parser.on(:header_value) do |b, start, the_end|
|
49
|
+
header_value += b[start...the_end]
|
50
|
+
end
|
51
|
+
|
52
|
+
parser.on(:header_end) do
|
53
|
+
part[:headers][header_field] = header_value
|
54
|
+
header_field = ''
|
55
|
+
header_value = ''
|
56
|
+
end
|
57
|
+
|
58
|
+
parser.on(:part_data) do |b, start, the_end|
|
59
|
+
part[:data] += b[start...the_end]
|
60
|
+
end
|
61
|
+
|
62
|
+
parser.on(:end) do
|
63
|
+
end_called = true
|
64
|
+
end
|
65
|
+
|
66
|
+
offset = 0
|
67
|
+
while offset < buffer.length
|
68
|
+
if(offset + chunk_length < buffer.length)
|
69
|
+
chunk = buffer[offset, chunk_length]
|
70
|
+
else
|
71
|
+
chunk = buffer[offset...buffer.length]
|
72
|
+
end
|
73
|
+
offset += chunk_length
|
74
|
+
|
75
|
+
nparsed = parser.write(chunk)
|
76
|
+
if nparsed != chunk.length
|
77
|
+
unless fixture.expect_error
|
78
|
+
puts "--ERROR--"
|
79
|
+
puts chunk
|
80
|
+
flunk "#{fixture.class.name}: #{chunk.length} bytes written, " +
|
81
|
+
"but only #{nparsed} bytes parsed!"
|
82
|
+
else
|
83
|
+
got_error = true
|
84
|
+
end
|
85
|
+
end
|
86
|
+
end
|
87
|
+
unless got_error
|
88
|
+
assert true, end_called
|
89
|
+
assert_equal fixture.parts, parts
|
90
|
+
else
|
91
|
+
assert fixture.expect_error,
|
92
|
+
"#{fixture.class.name}: Expected parse error did not happen"
|
93
|
+
end
|
94
|
+
end
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end
|
@@ -0,0 +1,74 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require File.dirname(__FILE__) + "/../../lib/multipart_parser/reader"
|
3
|
+
require File.dirname(__FILE__) + "/../fixtures/multipart"
|
4
|
+
|
5
|
+
module MultipartParser
|
6
|
+
class ReaderTest < Test::Unit::TestCase
|
7
|
+
def test_extract_boundary_value
|
8
|
+
assert_raise(NotMultipartError) do
|
9
|
+
not_multipart = "text/plain"
|
10
|
+
Reader.extract_boundary_value(not_multipart)
|
11
|
+
end
|
12
|
+
|
13
|
+
assert_raise(NotMultipartError) do
|
14
|
+
no_boundary = "multipart/form-data"
|
15
|
+
Reader.extract_boundary_value(no_boundary)
|
16
|
+
end
|
17
|
+
|
18
|
+
valid_content_type = "multipart/form-data; boundary=9asdadsdfv"
|
19
|
+
boundary = Reader.extract_boundary_value(valid_content_type)
|
20
|
+
assert_equal "9asdadsdfv", boundary
|
21
|
+
end
|
22
|
+
|
23
|
+
def test_error_callback
|
24
|
+
on_error_called = false
|
25
|
+
reader = Reader.new("boundary")
|
26
|
+
reader.on_error do |err|
|
27
|
+
on_error_called = true
|
28
|
+
end
|
29
|
+
reader.write("not boundary atleast")
|
30
|
+
assert on_error_called
|
31
|
+
end
|
32
|
+
|
33
|
+
def test_success_scenario
|
34
|
+
fixture = Fixtures::Rfc1867.new
|
35
|
+
reader = Reader.new(fixture.boundary)
|
36
|
+
on_error_called = false
|
37
|
+
parts = {}
|
38
|
+
|
39
|
+
reader.on_error do |err|
|
40
|
+
on_error_called = true
|
41
|
+
end
|
42
|
+
|
43
|
+
reader.on_part do |part|
|
44
|
+
part_entry = {:part => part, :data => '', :ended => false}
|
45
|
+
parts[part.name] = part_entry
|
46
|
+
part.on_data do |data|
|
47
|
+
part_entry[:data] << data
|
48
|
+
end
|
49
|
+
part.on_end do
|
50
|
+
part_entry[:ended] = true
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
reader.write(fixture.raw)
|
55
|
+
|
56
|
+
assert !on_error_called
|
57
|
+
assert reader.ended?
|
58
|
+
|
59
|
+
assert_equal parts.size, fixture.parts.size
|
60
|
+
assert parts.all? {|k, v| v[:ended]}
|
61
|
+
|
62
|
+
field = parts['field1']
|
63
|
+
assert !field.nil?
|
64
|
+
assert_equal 'field1', field[:part].name
|
65
|
+
assert_equal fixture.parts.first[:data], field[:data]
|
66
|
+
|
67
|
+
file = parts['pics']
|
68
|
+
assert !file.nil?
|
69
|
+
assert_equal 'pics', file[:part].name
|
70
|
+
assert_equal 'file1.txt', file[:part].filename
|
71
|
+
assert_equal fixture.parts.last[:data], file[:data]
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
metadata
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: multipart-parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Daniel Abrahamsson
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-03-17 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: ! 'multipart-parser is a simple parser for multipart MIME messages, written
|
15
|
+
in
|
16
|
+
|
17
|
+
Ruby, based on felixge/node-formidable''s parser.
|
18
|
+
|
19
|
+
|
20
|
+
Some things to note:
|
21
|
+
|
22
|
+
- Pure Ruby
|
23
|
+
|
24
|
+
- Event-driven API
|
25
|
+
|
26
|
+
- Only supports one level of multipart parsing. Invoke another parser if
|
27
|
+
|
28
|
+
you need to handle nested messages.
|
29
|
+
|
30
|
+
- Does not perform I/O.
|
31
|
+
|
32
|
+
- Does not depend on any other library.
|
33
|
+
|
34
|
+
'
|
35
|
+
email:
|
36
|
+
- hamsson@gmail.com
|
37
|
+
executables: []
|
38
|
+
extensions: []
|
39
|
+
extra_rdoc_files: []
|
40
|
+
files:
|
41
|
+
- LICENSE
|
42
|
+
- README
|
43
|
+
- lib/multipart_parser/parser.rb
|
44
|
+
- lib/multipart_parser/reader.rb
|
45
|
+
- lib/multipart_parser/version.rb
|
46
|
+
- multipart-parser.gemspec
|
47
|
+
- test/fixtures/multipart.rb
|
48
|
+
- test/multipart_parser/parser_test.rb
|
49
|
+
- test/multipart_parser/reader.rb
|
50
|
+
homepage: https://github.com/danabr/multipart-parser
|
51
|
+
licenses: []
|
52
|
+
post_install_message:
|
53
|
+
rdoc_options: []
|
54
|
+
require_paths:
|
55
|
+
- lib
|
56
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
63
|
+
none: false
|
64
|
+
requirements:
|
65
|
+
- - ! '>='
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: '0'
|
68
|
+
requirements: []
|
69
|
+
rubyforge_project:
|
70
|
+
rubygems_version: 1.8.19
|
71
|
+
signing_key:
|
72
|
+
specification_version: 3
|
73
|
+
summary: simple parser for multipart MIME messages
|
74
|
+
test_files:
|
75
|
+
- test/fixtures/multipart.rb
|
76
|
+
- test/multipart_parser/parser_test.rb
|
77
|
+
- test/multipart_parser/reader.rb
|