rmail 0.17
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/NEWS +309 -0
- data/NOTES +14 -0
- data/README +83 -0
- data/THANKS +25 -0
- data/TODO +112 -0
- data/guide/Intro.txt +122 -0
- data/guide/MIME.txt +6 -0
- data/guide/TableOfContents.txt +13 -0
- data/install.rb +1023 -0
- data/lib/rmail.rb +50 -0
- data/lib/rmail/address.rb +829 -0
- data/lib/rmail/header.rb +987 -0
- data/lib/rmail/mailbox.rb +62 -0
- data/lib/rmail/mailbox/mboxreader.rb +182 -0
- data/lib/rmail/message.rb +201 -0
- data/lib/rmail/parser.rb +412 -0
- data/lib/rmail/parser/multipart.rb +217 -0
- data/lib/rmail/parser/pushbackreader.rb +173 -0
- data/lib/rmail/serialize.rb +190 -0
- data/lib/rmail/utils.rb +59 -0
- data/rmail.gemspec +17 -0
- data/tests/addrgrammar.txt +113 -0
- data/tests/data/mbox.odd +4 -0
- data/tests/data/mbox.simple +8 -0
- data/tests/data/multipart/data.1 +5 -0
- data/tests/data/multipart/data.10 +1 -0
- data/tests/data/multipart/data.11 +9 -0
- data/tests/data/multipart/data.12 +9 -0
- data/tests/data/multipart/data.13 +3 -0
- data/tests/data/multipart/data.14 +3 -0
- data/tests/data/multipart/data.15 +3 -0
- data/tests/data/multipart/data.16 +3 -0
- data/tests/data/multipart/data.17 +0 -0
- data/tests/data/multipart/data.2 +5 -0
- data/tests/data/multipart/data.3 +2 -0
- data/tests/data/multipart/data.4 +3 -0
- data/tests/data/multipart/data.5 +1 -0
- data/tests/data/multipart/data.6 +2 -0
- data/tests/data/multipart/data.7 +3 -0
- data/tests/data/multipart/data.8 +5 -0
- data/tests/data/multipart/data.9 +4 -0
- data/tests/data/parser.badmime1 +4 -0
- data/tests/data/parser.badmime2 +6 -0
- data/tests/data/parser.nested-multipart +75 -0
- data/tests/data/parser.nested-simple +12 -0
- data/tests/data/parser.nested-simple2 +16 -0
- data/tests/data/parser.nested-simple3 +21 -0
- data/tests/data/parser.rfc822 +65 -0
- data/tests/data/parser.simple-mime +24 -0
- data/tests/data/parser/multipart.1 +8 -0
- data/tests/data/parser/multipart.10 +4 -0
- data/tests/data/parser/multipart.11 +12 -0
- data/tests/data/parser/multipart.12 +12 -0
- data/tests/data/parser/multipart.13 +6 -0
- data/tests/data/parser/multipart.14 +6 -0
- data/tests/data/parser/multipart.15 +6 -0
- data/tests/data/parser/multipart.16 +6 -0
- data/tests/data/parser/multipart.2 +8 -0
- data/tests/data/parser/multipart.3 +5 -0
- data/tests/data/parser/multipart.4 +6 -0
- data/tests/data/parser/multipart.5 +4 -0
- data/tests/data/parser/multipart.6 +5 -0
- data/tests/data/parser/multipart.7 +6 -0
- data/tests/data/parser/multipart.8 +8 -0
- data/tests/data/parser/multipart.9 +7 -0
- data/tests/data/transparency/absolute.1 +5 -0
- data/tests/data/transparency/absolute.2 +1 -0
- data/tests/data/transparency/absolute.3 +2 -0
- data/tests/data/transparency/absolute.4 +3 -0
- data/tests/data/transparency/absolute.5 +4 -0
- data/tests/data/transparency/absolute.6 +49 -0
- data/tests/data/transparency/message.1 +73 -0
- data/tests/data/transparency/message.2 +34 -0
- data/tests/data/transparency/message.3 +63 -0
- data/tests/data/transparency/message.4 +5 -0
- data/tests/data/transparency/message.5 +15 -0
- data/tests/data/transparency/message.6 +1185 -0
- data/tests/runtests.rb +35 -0
- data/tests/testaddress.rb +1192 -0
- data/tests/testbase.rb +207 -0
- data/tests/testheader.rb +1207 -0
- data/tests/testmailbox.rb +47 -0
- data/tests/testmboxreader.rb +161 -0
- data/tests/testmessage.rb +257 -0
- data/tests/testparser.rb +634 -0
- data/tests/testparsermultipart.rb +205 -0
- data/tests/testpushbackreader.rb +40 -0
- data/tests/testserialize.rb +264 -0
- data/tests/testtestbase.rb +112 -0
- data/tests/testtranspparency.rb +105 -0
- metadata +143 -0
@@ -0,0 +1,62 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#--
|
3
|
+
# Copyright (c) 2002, 2003 Matt Armstrong. All rights reserved.
|
4
|
+
#
|
5
|
+
# Redistribution and use in source and binary forms, with or without
|
6
|
+
# modification, are permitted provided that the following conditions are met:
|
7
|
+
#
|
8
|
+
# 1. Redistributions of source code must retain the above copyright notice,
|
9
|
+
# this list of conditions and the following disclaimer.
|
10
|
+
# 2. Redistributions in binary form must reproduce the above copyright
|
11
|
+
# notice, this list of conditions and the following disclaimer in the
|
12
|
+
# documentation and/or other materials provided with the distribution.
|
13
|
+
# 3. The name of the author may not be used to endorse or promote products
|
14
|
+
# derived from this software without specific prior written permission.
|
15
|
+
#
|
16
|
+
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
17
|
+
# IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
18
|
+
# OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
|
19
|
+
# NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
20
|
+
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
21
|
+
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
22
|
+
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
23
|
+
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
24
|
+
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
25
|
+
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
26
|
+
#
|
27
|
+
#++
|
28
|
+
# Implements the RMail::Mailbox module.
|
29
|
+
|
30
|
+
module RMail
|
31
|
+
|
32
|
+
# The RMail::Mailbox module contains a few methods that are useful
|
33
|
+
# for working with mailboxes.
|
34
|
+
module Mailbox
|
35
|
+
|
36
|
+
class << self
|
37
|
+
|
38
|
+
# Parse a Unix mbox style mailbox. These mailboxes searate
|
39
|
+
# individual messages with a line beginning with the string
|
40
|
+
# "From ".
|
41
|
+
#
|
42
|
+
# If a block is given, yields to the block with the raw message
|
43
|
+
# (a string), otherwise an array of raw message strings is
|
44
|
+
# returned.
|
45
|
+
def parse_mbox(input, line_separator = $/)
|
46
|
+
require 'rmail/mailbox/mboxreader'
|
47
|
+
retval = []
|
48
|
+
RMail::Mailbox::MBoxReader.new(input, line_separator).each_message {
|
49
|
+
|reader|
|
50
|
+
raw_message = reader.read(nil)
|
51
|
+
if block_given?
|
52
|
+
yield raw_message
|
53
|
+
else
|
54
|
+
retval << raw_message
|
55
|
+
end
|
56
|
+
}
|
57
|
+
return block_given? ? nil : retval
|
58
|
+
end
|
59
|
+
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
@@ -0,0 +1,182 @@
|
|
1
|
+
#--
|
2
|
+
# Copyright (c) 2002, 2003 Matt Armstrong. All rights reserved.
|
3
|
+
#
|
4
|
+
# Redistribution and use in source and binary forms, with or without
|
5
|
+
# modification, are permitted provided that the following conditions are met:
|
6
|
+
#
|
7
|
+
# 1. Redistributions of source code must retain the above copyright notice,
|
8
|
+
# this list of conditions and the following disclaimer.
|
9
|
+
# 2. Redistributions in binary form must reproduce the above copyright
|
10
|
+
# notice, this list of conditions and the following disclaimer in the
|
11
|
+
# documentation and/or other materials provided with the distribution.
|
12
|
+
# 3. The name of the author may not be used to endorse or promote products
|
13
|
+
# derived from this software without specific prior written permission.
|
14
|
+
#
|
15
|
+
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
16
|
+
# IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
17
|
+
# OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
|
18
|
+
# NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
19
|
+
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
20
|
+
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
21
|
+
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
22
|
+
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
23
|
+
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
24
|
+
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
25
|
+
#
|
26
|
+
#++
|
27
|
+
# Implements the RMail::Mailbox::MBoxReader class.
|
28
|
+
|
29
|
+
require 'rmail/parser/pushbackreader'
|
30
|
+
|
31
|
+
module RMail
|
32
|
+
module Mailbox
|
33
|
+
|
34
|
+
# Class that can parse Unix mbox style mailboxes. These mailboxes
|
35
|
+
# separate individual messages with a line beginning with the
|
36
|
+
# string "From ".
|
37
|
+
#
|
38
|
+
# Typical usage:
|
39
|
+
#
|
40
|
+
# File.open("file.mbox") { |file|
|
41
|
+
# RMail::Mailbox::MBoxReader.new(file).each_message { |input|
|
42
|
+
# message = RMail::Parser.read(input)
|
43
|
+
# # do something with the message
|
44
|
+
# end
|
45
|
+
# }
|
46
|
+
#
|
47
|
+
# Or see RMail::Mailbox.parse_mbox for a more convenient
|
48
|
+
# interface.
|
49
|
+
#
|
50
|
+
class MBoxReader < RMail::Parser::PushbackReader
|
51
|
+
|
52
|
+
# Creates a new MBoxReader that reads from `input' with lines
|
53
|
+
# that end with `line_separator'.
|
54
|
+
#
|
55
|
+
# `input' can either be an IO source (an object that responds to
|
56
|
+
# the "read" method in the same way as a standard IO object) or
|
57
|
+
# a String.
|
58
|
+
#
|
59
|
+
# `line_separator' defaults to $/, and useful values are
|
60
|
+
# probably limited to "\n" (Unix) and "\r\n" (DOS/Windows).
|
61
|
+
def initialize(input, line_separator = $/)
|
62
|
+
super(input)
|
63
|
+
@end_of_message = false
|
64
|
+
@chunk_minsize = 0
|
65
|
+
@sep = line_separator
|
66
|
+
@tail = nil
|
67
|
+
|
68
|
+
# This regexp will match a From_ header, or some prefix.
|
69
|
+
re_string = RMail::Parser::PushbackReader.
|
70
|
+
maybe_contains_re("#{@sep}From ")
|
71
|
+
@partial_from_re = Regexp.new(re_string)
|
72
|
+
|
73
|
+
# This regexp will match an entire From_ header.
|
74
|
+
@entire_from_re = /\A#{@sep}From .*?#{@sep}/
|
75
|
+
end
|
76
|
+
|
77
|
+
alias_method :parent_read_chunk, :read_chunk
|
78
|
+
|
79
|
+
# Reads some data from the current message and returns it. The
|
80
|
+
# `size' argument is just a suggestion, and the returned string
|
81
|
+
# can be larger or smaller. When `size' is nil, then the entire
|
82
|
+
# message is returned.
|
83
|
+
#
|
84
|
+
# Once all data from the current message has been read, #read
|
85
|
+
# returns nil and #next must be called to begin reading from the
|
86
|
+
# next message. You can use #eof to tell if there is any more
|
87
|
+
# data to be read from the input source.
|
88
|
+
def read_chunk(size)
|
89
|
+
chunk = read_chunk_low(size)
|
90
|
+
if chunk
|
91
|
+
if chunk.length > @sep.length
|
92
|
+
@tail = chunk[-@sep.length .. -1]
|
93
|
+
else
|
94
|
+
@tail ||= ''
|
95
|
+
@tail << chunk
|
96
|
+
end
|
97
|
+
elsif @tail
|
98
|
+
if @tail[-@sep.length .. -1] != @sep
|
99
|
+
chunk = @sep
|
100
|
+
end
|
101
|
+
@tail = nil
|
102
|
+
end
|
103
|
+
chunk
|
104
|
+
end
|
105
|
+
|
106
|
+
# Advances to the next message to be read. Call this after
|
107
|
+
# #read returns nil.
|
108
|
+
#
|
109
|
+
# Note: Once #read returns nil, you can call #eof before or
|
110
|
+
# after calling #next to tell if there actually is a next
|
111
|
+
# message to read.
|
112
|
+
def next
|
113
|
+
@end_of_message = false
|
114
|
+
@tail = nil
|
115
|
+
end
|
116
|
+
|
117
|
+
alias_method :parent_eof, :eof
|
118
|
+
|
119
|
+
# Returns true if the next call to read_chunk will return nil.
|
120
|
+
def eof
|
121
|
+
parent_eof and @tail.nil?
|
122
|
+
end
|
123
|
+
|
124
|
+
# Yield self until eof, calling next after each yield.
|
125
|
+
#
|
126
|
+
# This method makes it simple to read messages successively out
|
127
|
+
# of the mailbox. See the class description for a code example.
|
128
|
+
def each_message
|
129
|
+
while !eof
|
130
|
+
yield self
|
131
|
+
self.next
|
132
|
+
end
|
133
|
+
end
|
134
|
+
|
135
|
+
private
|
136
|
+
|
137
|
+
def read_chunk_low(size)
|
138
|
+
return nil if @end_of_message
|
139
|
+
if chunk = parent_read_chunk(size)
|
140
|
+
# Read at least @chunk_minsize bytes.
|
141
|
+
while chunk.length < @chunk_minsize && more = parent_read_chunk(size)
|
142
|
+
chunk << more
|
143
|
+
end
|
144
|
+
if match = @partial_from_re.match(chunk)
|
145
|
+
# We matched what might be a From_ separator. Separate
|
146
|
+
# the chunk into what came before and what came after it.
|
147
|
+
mbegin = match.begin(0)
|
148
|
+
rest = chunk[mbegin .. -1]
|
149
|
+
|
150
|
+
if @entire_from_re =~ rest
|
151
|
+
# We've got a full From_ line, so set the end of message
|
152
|
+
# flag and get rid of the line separator present just
|
153
|
+
# before the From_.
|
154
|
+
@end_of_message = true
|
155
|
+
@chunk_minsize = 0
|
156
|
+
rest[0, @sep.length] = "" # painful
|
157
|
+
else
|
158
|
+
# Make sure that next time we read more than just the
|
159
|
+
# pushback.
|
160
|
+
@chunk_minsize = rest.length + 1
|
161
|
+
end
|
162
|
+
|
163
|
+
# Return the whole chunk with a partially matched From_
|
164
|
+
# when there is nothing further to read.
|
165
|
+
unless ! @end_of_message && parent_eof
|
166
|
+
# Otherwise, push back the From_ and return the
|
167
|
+
# pre-match.
|
168
|
+
pushback(rest)
|
169
|
+
if mbegin == 0 and @end_of_message
|
170
|
+
chunk = nil
|
171
|
+
else
|
172
|
+
chunk = chunk[0, mbegin]
|
173
|
+
end
|
174
|
+
end
|
175
|
+
|
176
|
+
end
|
177
|
+
end
|
178
|
+
return chunk
|
179
|
+
end
|
180
|
+
end
|
181
|
+
end
|
182
|
+
end
|
@@ -0,0 +1,201 @@
|
|
1
|
+
#--
|
2
|
+
# Copyright (C) 2001, 2002, 2003 Matt Armstrong. All rights
|
3
|
+
# reserved.
|
4
|
+
#
|
5
|
+
# Redistribution and use in source and binary forms, with or without
|
6
|
+
# modification, are permitted provided that the following conditions are met:
|
7
|
+
#
|
8
|
+
# 1. Redistributions of source code must retain the above copyright notice,
|
9
|
+
# this list of conditions and the following disclaimer.
|
10
|
+
# 2. Redistributions in binary form must reproduce the above copyright
|
11
|
+
# notice, this list of conditions and the following disclaimer in the
|
12
|
+
# documentation and/or other materials provided with the distribution.
|
13
|
+
# 3. The name of the author may not be used to endorse or promote products
|
14
|
+
# derived from this software without specific prior written permission.
|
15
|
+
#
|
16
|
+
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
17
|
+
# IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
18
|
+
# OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
|
19
|
+
# NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
20
|
+
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
21
|
+
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
22
|
+
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
23
|
+
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
24
|
+
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
25
|
+
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
26
|
+
#
|
27
|
+
#++
|
28
|
+
# Implements the RMail::Message class.
|
29
|
+
|
30
|
+
require 'rmail/header.rb'
|
31
|
+
|
32
|
+
module RMail
|
33
|
+
|
34
|
+
# The RMail::Message is an object representation of a standard
|
35
|
+
# Internet email message, including MIME multipart messages.
|
36
|
+
#
|
37
|
+
# An RMail::Message object represents a message header (held in the
|
38
|
+
# contained RMail::Header object) and a message body. The message
|
39
|
+
# body may either be a single String for single part messages or an
|
40
|
+
# Array of RMail::Message objects for MIME multipart messages.
|
41
|
+
class Message
|
42
|
+
|
43
|
+
# Create a new, empty, RMail::Message.
|
44
|
+
def initialize
|
45
|
+
@header = RMail::Header.new
|
46
|
+
@body = nil
|
47
|
+
@epilogue = nil
|
48
|
+
@preamble = nil
|
49
|
+
end
|
50
|
+
|
51
|
+
# Test if this message is structured exactly the same as the other
|
52
|
+
# message. This is useful mainly for testing.
|
53
|
+
def ==(other)
|
54
|
+
@preamble == other.preamble &&
|
55
|
+
@epilogue == other.epilogue &&
|
56
|
+
@header == other.header &&
|
57
|
+
@body == other.body
|
58
|
+
end
|
59
|
+
|
60
|
+
# Returns the body of the message as a String or Array.
|
61
|
+
#
|
62
|
+
# If #multipart? returns true, it will be an array of
|
63
|
+
# RMail::Message objects. Otherwise it will be a String.
|
64
|
+
#
|
65
|
+
# See also #header.
|
66
|
+
def body
|
67
|
+
return @body
|
68
|
+
end
|
69
|
+
|
70
|
+
# Sets the body of the message to the given value. It should
|
71
|
+
# either be a String or an Array of RMail:Message objects.
|
72
|
+
def body=(s)
|
73
|
+
@body = s
|
74
|
+
end
|
75
|
+
|
76
|
+
# Returns the RMail::Header object.
|
77
|
+
#
|
78
|
+
# See also #body.
|
79
|
+
def header()
|
80
|
+
return @header
|
81
|
+
end
|
82
|
+
|
83
|
+
# Return true if the message consists of multiple parts.
|
84
|
+
def multipart?
|
85
|
+
@body.is_a?(Array)
|
86
|
+
end
|
87
|
+
|
88
|
+
# Add a part to the message. After this message is called, the
|
89
|
+
# #multipart? method will return true and the #body method will
|
90
|
+
# #return an array of parts.
|
91
|
+
def add_part(part)
|
92
|
+
if @body.nil?
|
93
|
+
@body = [part]
|
94
|
+
elsif @body.is_a?(Array)
|
95
|
+
@body.push(part)
|
96
|
+
else
|
97
|
+
@body = [@body, part]
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
# Decode the body of this message.
|
102
|
+
#
|
103
|
+
# If the body of this message is encoded with
|
104
|
+
# <tt>quoted-printable</tt> or <tt>base64</tt>, this function will
|
105
|
+
# decode the data into its original form and return it as a
|
106
|
+
# String. If the body is not encoded, it is returned unaltered.
|
107
|
+
#
|
108
|
+
# This only works when the message is not a multipart. The
|
109
|
+
# <tt>Content-Transfer-Encoding:</tt> header field is consulted to
|
110
|
+
# determine the encoding of the body part.
|
111
|
+
def decode
|
112
|
+
raise TypeError, "Can not decode a multipart message." if multipart?
|
113
|
+
case header.fetch('content-transfer-encoding', '7bit').strip.downcase
|
114
|
+
when 'quoted-printable'
|
115
|
+
Utils.quoted_printable_decode(@body)
|
116
|
+
when 'base64'
|
117
|
+
Utils.base64_decode(@body)
|
118
|
+
else
|
119
|
+
@body
|
120
|
+
end
|
121
|
+
end
|
122
|
+
|
123
|
+
# Get the indicated part from a multipart message.
|
124
|
+
def part(i)
|
125
|
+
raise TypeError,
|
126
|
+
"Can not get part on a single part message." unless multipart?
|
127
|
+
@body[i]
|
128
|
+
end
|
129
|
+
|
130
|
+
# Access the epilogue string for this message. The epilogue
|
131
|
+
# string is relevant only for multipart messages. It is the text
|
132
|
+
# that occurs after all parts of the message and is generally nil.
|
133
|
+
attr :epilogue, true
|
134
|
+
|
135
|
+
# Access the preamble string for this message. The preamble
|
136
|
+
# string is relevant only for multipart messages. It is the text
|
137
|
+
# that occurs just before the first part of the message, and is
|
138
|
+
# generally nil or simple English text describing the nature of
|
139
|
+
# the message.
|
140
|
+
attr :preamble, true
|
141
|
+
|
142
|
+
# Returns the entire message in a single string. This uses the
|
143
|
+
# RMail::Serialize class.
|
144
|
+
def to_s()
|
145
|
+
require 'rmail/serialize'
|
146
|
+
RMail::Serialize.new('').serialize(self)
|
147
|
+
end
|
148
|
+
|
149
|
+
# Return each part of this message
|
150
|
+
#
|
151
|
+
# FIXME: not tested
|
152
|
+
def each_part
|
153
|
+
raise TypeError, "not a multipart message" unless multipart?
|
154
|
+
@body.each do |part|
|
155
|
+
yield part
|
156
|
+
end
|
157
|
+
end
|
158
|
+
|
159
|
+
# Call the supplied block for each line of the message. Each line
|
160
|
+
# will contain a trailing newline (<tt>\n</tt>).
|
161
|
+
def each()
|
162
|
+
# FIXME: this is incredibly inefficient! The only users of this
|
163
|
+
# is RMail::Deliver -- get them to use a RMail::Serialize object.
|
164
|
+
to_s.each("\n") { |line|
|
165
|
+
yield line
|
166
|
+
}
|
167
|
+
end
|
168
|
+
|
169
|
+
# This is used by the RMail::Parser to set the MIME multipart
|
170
|
+
# delimiter strings found in the message. These delimiters are
|
171
|
+
# then used when serializing the message again.
|
172
|
+
#
|
173
|
+
# Normal uses of RMail::Message will never use this method, and so
|
174
|
+
# it is left undocumented.
|
175
|
+
def set_delimiters(delimiters, boundary) # :nodoc:
|
176
|
+
raise TypeError, "not a multipart message" unless multipart?
|
177
|
+
raise ArgumentError, "delimiter array wrong size" unless
|
178
|
+
delimiters.length == @body.length + 1
|
179
|
+
@delimiters = delimiters.to_ary
|
180
|
+
@delimiters_boundary = boundary.to_str
|
181
|
+
end
|
182
|
+
|
183
|
+
# This is used by the serializing functions to retrieve the MIME
|
184
|
+
# multipart delimiter strings found while parsing the message.
|
185
|
+
# These delimiters are then used when serializing the message
|
186
|
+
# again.
|
187
|
+
#
|
188
|
+
# Normal uses of RMail::Message will never use this method, and so
|
189
|
+
# it is left undocumented.
|
190
|
+
def get_delimiters # :nodoc:
|
191
|
+
unless multipart? and @delimiters and @delimiters_boundary and
|
192
|
+
@delimiters.length == @body.length + 1 and
|
193
|
+
header.param('content-type', 'boundary') == @delimiters_boundary
|
194
|
+
@delimiters = nil
|
195
|
+
@delimiters_boundary = nil
|
196
|
+
end
|
197
|
+
[ @delimiters, @delimiters_boundary ]
|
198
|
+
end
|
199
|
+
|
200
|
+
end
|
201
|
+
end
|
data/lib/rmail/parser.rb
ADDED
@@ -0,0 +1,412 @@
|
|
1
|
+
#--
|
2
|
+
# Copyright (C) 2002, 2003, 2004 Matt Armstrong. All rights reserved.
|
3
|
+
#
|
4
|
+
# Redistribution and use in source and binary forms, with or without
|
5
|
+
# modification, are permitted provided that the following conditions are met:
|
6
|
+
#
|
7
|
+
# 1. Redistributions of source code must retain the above copyright notice,
|
8
|
+
# this list of conditions and the following disclaimer.
|
9
|
+
# 2. Redistributions in binary form must reproduce the above copyright
|
10
|
+
# notice, this list of conditions and the following disclaimer in the
|
11
|
+
# documentation and/or other materials provided with the distribution.
|
12
|
+
# 3. The name of the author may not be used to endorse or promote products
|
13
|
+
# derived from this software without specific prior written permission.
|
14
|
+
#
|
15
|
+
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
16
|
+
# IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
17
|
+
# OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
|
18
|
+
# NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
19
|
+
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
20
|
+
# TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
21
|
+
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
22
|
+
# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
23
|
+
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
24
|
+
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
25
|
+
#
|
26
|
+
#++
|
27
|
+
# Implements the RMail::Parser, RMail::StreamParser and
|
28
|
+
# RMail::StreamHandler classes.
|
29
|
+
|
30
|
+
require 'rmail/message'
|
31
|
+
require 'rmail/parser/multipart'
|
32
|
+
|
33
|
+
module RMail
|
34
|
+
|
35
|
+
# = Overview
|
36
|
+
#
|
37
|
+
# An RMail::StreamHandler documents the set of methods a
|
38
|
+
# RMail::StreamParser handler must implement. See
|
39
|
+
# RMail::StreamParser.parse. This is a low level interface to the
|
40
|
+
# RMail message parser.
|
41
|
+
#
|
42
|
+
# = Order of Method Calls (Grammar)
|
43
|
+
#
|
44
|
+
# Calls to the methods of this class follow a specific grammar,
|
45
|
+
# described informally below. The words in all caps are productions
|
46
|
+
# in the grammar, while the lower case words are method calls to
|
47
|
+
# this object.
|
48
|
+
#
|
49
|
+
# MESSAGE:: [ #mbox_from ] *( #header_field )
|
50
|
+
# ( BODY / MULTIPART_BODY )
|
51
|
+
#
|
52
|
+
# BODY:: *body_begin *( #body_chunk ) #body_end
|
53
|
+
#
|
54
|
+
# MULTIPART_BODY:: #multipart_body_begin
|
55
|
+
# *( #preamble_chunk )
|
56
|
+
# *( #part_begin MESSAGE #part_end)
|
57
|
+
# *( #epilogue_chunk )
|
58
|
+
# #multipart_body_end
|
59
|
+
#
|
60
|
+
# = Order of Method Calls (English)
|
61
|
+
#
|
62
|
+
# If the grammar above is not clear, here is a description in English.
|
63
|
+
#
|
64
|
+
# The parser begins calling #header_field, possibly calling
|
65
|
+
# #mbox_from for the first line. Then it determines if the message
|
66
|
+
# was a MIME multipart message.
|
67
|
+
#
|
68
|
+
# If the message is a not a MIME multipart, the parser calls
|
69
|
+
# #body_begin once, then #body_chunk any number of times, then
|
70
|
+
# #body_end.
|
71
|
+
#
|
72
|
+
# If the message header is a MIME multipart message, then
|
73
|
+
# #multipart_body_begin is called, followed by any number of calls
|
74
|
+
# to #preamble_chunk. Then for each part parsed, #part_begin is
|
75
|
+
# called, followed by a recursive set of calls described by the
|
76
|
+
# "MESSAGE" production above, and then #part_end. After all parts
|
77
|
+
# are parsed, any number of calls to #epilogue_chunk are followed by
|
78
|
+
# a single call to #multipart_body_end.
|
79
|
+
#
|
80
|
+
# The recursive nature of MIME multipart messages is represented by
|
81
|
+
# the recursive invocation of the "MESSAGE" production in the
|
82
|
+
# grammar above.
|
83
|
+
class StreamHandler
|
84
|
+
|
85
|
+
# This method is called for Unix MBOX "From " lines in the message
|
86
|
+
# header, it calls this method with the text.
|
87
|
+
def mbox_from(line)
|
88
|
+
end
|
89
|
+
|
90
|
+
# This method is called when a header field is parsed. The
|
91
|
+
# +field+ is the full text of the field, the +name+ is the name of
|
92
|
+
# the field and the +value+ is the field's value with leading and
|
93
|
+
# trailing whitespace removed. Note that both +field+ and +value+
|
94
|
+
# may be multi-line strings.
|
95
|
+
def header_field(field, name, value)
|
96
|
+
end
|
97
|
+
|
98
|
+
# This method is called before a non-multipart message body is
|
99
|
+
# about to be parsed.
|
100
|
+
def body_begin
|
101
|
+
end
|
102
|
+
|
103
|
+
# This method is called with a string chunk of data from a
|
104
|
+
# non-multipart message body. The string does not necessarily
|
105
|
+
# begin or end on any particular boundary.
|
106
|
+
def body_chunk(chunk)
|
107
|
+
end
|
108
|
+
|
109
|
+
# This method is called after all of the non-multipart message
|
110
|
+
# body has been parsed.
|
111
|
+
def body_end
|
112
|
+
end
|
113
|
+
|
114
|
+
# This method is called before a multipart message body is about
|
115
|
+
# to be parsed.
|
116
|
+
def multipart_body_begin
|
117
|
+
end
|
118
|
+
|
119
|
+
# This method is called with a chunk of data from a multipart
|
120
|
+
# message body's preamble. The preamble is any text that appears
|
121
|
+
# before the first part of the multipart message body.
|
122
|
+
def preamble_chunk(chunk)
|
123
|
+
end
|
124
|
+
|
125
|
+
# This method is called when a part of a multipart body begins.
|
126
|
+
def part_begin
|
127
|
+
end
|
128
|
+
|
129
|
+
# This method is called when a part of a multipart body ends.
|
130
|
+
def part_end
|
131
|
+
end
|
132
|
+
|
133
|
+
# This method is called with a chunk of data from a multipart
|
134
|
+
# message body's epilogue. The epilogue is any text that appears
|
135
|
+
# after the last part of the multipart message body.
|
136
|
+
def epilogue_chunk(chunk)
|
137
|
+
end
|
138
|
+
|
139
|
+
# This method is called after a multipart message body has been
|
140
|
+
# completely parsed.
|
141
|
+
#
|
142
|
+
# The +delimiters+ is an Array of strings, one for each boundary
|
143
|
+
# string found in the multipart body. The +boundary+ is the
|
144
|
+
# boundary string used to delimit each part in the multipart body.
|
145
|
+
# You can normally ignore both +delimiters+ and +boundary+ if you
|
146
|
+
# are concerned only about message content.
|
147
|
+
def multipart_body_end(delimiters, boundary)
|
148
|
+
end
|
149
|
+
end
|
150
|
+
|
151
|
+
# The RMail::StreamParser is a low level message parsing API. It is
|
152
|
+
# useful when you are interested in serially examining all message
|
153
|
+
# content but are not interested in a full object representation of
|
154
|
+
# the object. See StreamParser.parse.
|
155
|
+
class StreamParser
|
156
|
+
|
157
|
+
class << self
|
158
|
+
|
159
|
+
# Parse a message from an input source. This method returns
|
160
|
+
# nothing. Instead, the supplied +handler+ is expected to
|
161
|
+
# implement the same methods as RMail::StreamHandler. The
|
162
|
+
# message structure can be inferred from the methods called on
|
163
|
+
# the +handler+. The +input+ can be any Ruby IO source or a
|
164
|
+
# String.
|
165
|
+
#
|
166
|
+
# This is a low level parsing API. For a message parser that
|
167
|
+
# returns an RMail::Message object, see the RMail::Parser class.
|
168
|
+
# RMail::Parser is implemented using RMail::StreamParser.
|
169
|
+
def parse(input, handler)
|
170
|
+
RMail::StreamParser.new(input, handler).parse
|
171
|
+
end
|
172
|
+
end
|
173
|
+
|
174
|
+
def initialize(input, handler) # :nodoc:
|
175
|
+
@input = input
|
176
|
+
@handler = handler
|
177
|
+
@chunk_size = nil
|
178
|
+
end
|
179
|
+
|
180
|
+
def parse # :nodoc:
|
181
|
+
input = RMail::Parser::PushbackReader.new(@input)
|
182
|
+
input.chunk_size = @chunk_size if @chunk_size
|
183
|
+
parse_low(input, 0)
|
184
|
+
return nil
|
185
|
+
end
|
186
|
+
|
187
|
+
# Change the chunk size used to read the message. This is useful
|
188
|
+
# mostly for testing, so we don't document it.
|
189
|
+
attr_accessor :chunk_size # :nodoc:
|
190
|
+
|
191
|
+
private
|
192
|
+
|
193
|
+
def parse_low(input, depth)
|
194
|
+
multipart_boundary = parse_header(input, depth)
|
195
|
+
if multipart_boundary
|
196
|
+
parse_multipart_body(input, depth, multipart_boundary)
|
197
|
+
else
|
198
|
+
parse_singlepart_body(input, depth)
|
199
|
+
end
|
200
|
+
end
|
201
|
+
|
202
|
+
def parse_header(input, depth)
|
203
|
+
data = nil
|
204
|
+
header = nil
|
205
|
+
pushback = nil
|
206
|
+
boundary = nil
|
207
|
+
while chunk = input.read
|
208
|
+
data ||= ''
|
209
|
+
data << chunk
|
210
|
+
if data[0] == ?\n
|
211
|
+
# A leading newline in the message is seen when parsing the
|
212
|
+
# parts of a multipart message. It means there are no
|
213
|
+
# headers. The body part starts directly after this
|
214
|
+
# newline.
|
215
|
+
rest = data[1..-1]
|
216
|
+
else
|
217
|
+
header, rest = data.split(/\n\n/, 2)
|
218
|
+
end
|
219
|
+
break if rest
|
220
|
+
end
|
221
|
+
input.pushback(rest)
|
222
|
+
if header
|
223
|
+
mime = false
|
224
|
+
fields = header.split(/\n(?!\s)/)
|
225
|
+
if fields.first =~ /^From /
|
226
|
+
@handler.mbox_from(fields.first)
|
227
|
+
fields.shift
|
228
|
+
end
|
229
|
+
fields.each { |field|
|
230
|
+
if field =~ /^From /
|
231
|
+
@handler.mbox_from(field)
|
232
|
+
else
|
233
|
+
name, value = RMail::Header::Field.parse(field)
|
234
|
+
case name.downcase
|
235
|
+
when 'mime-version'
|
236
|
+
if value =~ /\b1\.0\b/
|
237
|
+
mime = true
|
238
|
+
end
|
239
|
+
when 'content-type'
|
240
|
+
# FIXME: would be nice to have a procedural equivalent
|
241
|
+
# to RMail::Header#param.
|
242
|
+
header = RMail::Header.new
|
243
|
+
header['content-type'] = value
|
244
|
+
boundary = header.param('content-type', 'boundary')
|
245
|
+
end
|
246
|
+
@handler.header_field(field, name, value)
|
247
|
+
end
|
248
|
+
}
|
249
|
+
unless mime or depth > 0
|
250
|
+
boundary = nil
|
251
|
+
end
|
252
|
+
end
|
253
|
+
return boundary
|
254
|
+
end
|
255
|
+
|
256
|
+
def parse_multipart_body(input, depth, boundary)
|
257
|
+
input = RMail::Parser::MultipartReader.new(input, boundary)
|
258
|
+
input.chunk_size = @chunk_size if @chunk_size
|
259
|
+
|
260
|
+
@handler.multipart_body_begin
|
261
|
+
|
262
|
+
# Reach each part, adding it to this entity as appropriate.
|
263
|
+
delimiters = []
|
264
|
+
while input.next_part
|
265
|
+
if input.preamble?
|
266
|
+
while chunk = input.read
|
267
|
+
@handler.preamble_chunk(chunk)
|
268
|
+
end
|
269
|
+
elsif input.epilogue?
|
270
|
+
while chunk = input.read
|
271
|
+
@handler.epilogue_chunk(chunk)
|
272
|
+
end
|
273
|
+
else
|
274
|
+
@handler.part_begin
|
275
|
+
parse_low(input, depth + 1)
|
276
|
+
@handler.part_end
|
277
|
+
end
|
278
|
+
delimiters << (input.delimiter || "") unless input.epilogue?
|
279
|
+
end
|
280
|
+
@handler.multipart_body_end(delimiters, boundary)
|
281
|
+
end
|
282
|
+
|
283
|
+
def parse_singlepart_body(input, depth)
|
284
|
+
@handler.body_begin
|
285
|
+
while chunk = input.read
|
286
|
+
@handler.body_chunk(chunk)
|
287
|
+
end
|
288
|
+
@handler.body_end
|
289
|
+
end
|
290
|
+
|
291
|
+
end
|
292
|
+
|
293
|
+
# The RMail::Parser class creates RMail::Message objects from Ruby
|
294
|
+
# IO objects or strings.
|
295
|
+
#
|
296
|
+
# To parse from a string:
|
297
|
+
# message = RMail::Parser.read(the_string)
|
298
|
+
#
|
299
|
+
# To parse from an IO object:
|
300
|
+
# message = File.open('my-message') { |f|
|
301
|
+
# RMail::Parser.read(f)
|
302
|
+
# }
|
303
|
+
#
|
304
|
+
# You can also parse from STDIN, etc.
|
305
|
+
# message = RMail::Parser.read(STDIN)
|
306
|
+
#
|
307
|
+
# In all cases, the parser consumes all input.
|
308
|
+
class Parser
|
309
|
+
|
310
|
+
# This exception class is thrown when the parser encounters an
|
311
|
+
# error.
|
312
|
+
#
|
313
|
+
# Note: the parser tries hard to never throw exceptions -- this
|
314
|
+
# error is thrown only when the API is used incorrectly and not on
|
315
|
+
# invalid input.
|
316
|
+
class Error < StandardError; end
|
317
|
+
|
318
|
+
# Creates a new parser. Messages of +message_class+ will be
|
319
|
+
# created by the parser. By default, the parser will create
|
320
|
+
# RMail::Message objects.
|
321
|
+
def initialize()
|
322
|
+
@chunk_size = nil
|
323
|
+
end
|
324
|
+
|
325
|
+
# Parse a message from the IO object +io+ and return a new
|
326
|
+
# message. The +io+ object can also be a string.
|
327
|
+
def parse(input)
|
328
|
+
handler = RMail::Parser::Handler.new
|
329
|
+
parser = RMail::StreamParser.new(input, handler)
|
330
|
+
parser.chunk_size = @chunk_size if @chunk_size
|
331
|
+
parser.parse
|
332
|
+
return handler.message
|
333
|
+
end
|
334
|
+
|
335
|
+
# Change the chunk size used to read the message. This is useful
|
336
|
+
# mostly for testing.
|
337
|
+
attr_accessor :chunk_size
|
338
|
+
|
339
|
+
# Parse a message from the IO object +io+ and return a new
|
340
|
+
# message. The +io+ object can also be a string. This is just
|
341
|
+
# shorthand for:
|
342
|
+
#
|
343
|
+
# RMail::Parser.new.parse(io)
|
344
|
+
def Parser.read(input)
|
345
|
+
Parser.new.parse(input)
|
346
|
+
end
|
347
|
+
|
348
|
+
class Handler < RMail::StreamHandler # :nodoc:
|
349
|
+
def initialize
|
350
|
+
@parts = [ RMail::Message.new ]
|
351
|
+
@preambles = []
|
352
|
+
@epilogues = []
|
353
|
+
end
|
354
|
+
def mbox_from(field)
|
355
|
+
@parts.last.header.mbox_from = field
|
356
|
+
end
|
357
|
+
def header_field(field, name, value)
|
358
|
+
@parts.last.header.add_raw(field)
|
359
|
+
end
|
360
|
+
def body_begin
|
361
|
+
@body = nil
|
362
|
+
end
|
363
|
+
def body_chunk(chunk)
|
364
|
+
if @body
|
365
|
+
@body << chunk
|
366
|
+
else
|
367
|
+
@body = chunk
|
368
|
+
end
|
369
|
+
end
|
370
|
+
def body_end
|
371
|
+
@parts.last.body = @body
|
372
|
+
end
|
373
|
+
def multipart_body_begin
|
374
|
+
@preambles.push(nil)
|
375
|
+
@epilogues.push(nil)
|
376
|
+
end
|
377
|
+
def preamble_chunk(chunk)
|
378
|
+
if @preambles.last
|
379
|
+
@preambles.last << chunk
|
380
|
+
else
|
381
|
+
@preambles[-1] = chunk
|
382
|
+
end
|
383
|
+
end
|
384
|
+
def epilogue_chunk(chunk)
|
385
|
+
if @epilogues.last
|
386
|
+
@epilogues.last << chunk
|
387
|
+
else
|
388
|
+
@epilogues[-1] = chunk
|
389
|
+
end
|
390
|
+
end
|
391
|
+
def multipart_body_end(delimiters, boundary)
|
392
|
+
@parts.last.preamble = @preambles.pop
|
393
|
+
@parts.last.epilogue = @epilogues.pop
|
394
|
+
if @parts.last.body.nil?
|
395
|
+
@parts.last.body = []
|
396
|
+
end
|
397
|
+
@parts.last.set_delimiters(delimiters, boundary)
|
398
|
+
end
|
399
|
+
def part_begin
|
400
|
+
@parts << RMail::Message.new
|
401
|
+
end
|
402
|
+
def part_end
|
403
|
+
part = @parts.pop
|
404
|
+
@parts.last.add_part(part)
|
405
|
+
end
|
406
|
+
def message
|
407
|
+
@parts.first
|
408
|
+
end
|
409
|
+
end
|
410
|
+
|
411
|
+
end
|
412
|
+
end
|