Class: LogStash::Inputs::IMAP

Inherits:
Base
  • Object
show all
Extended by:
PluginMixins::ValidatorSupport::FieldReferenceValidationAdapter
Defined in:
lib/logstash/inputs/imap.rb

Overview

Read mails from IMAP server

Periodically scan an IMAP folder (INBOX by default) and move any read messages to the trash.

Instance Method Summary collapse

Constructor Details

#initialize(*params) ⇒ IMAP

Returns a new instance of IMAP.



61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
 
# File 'lib/logstash/inputs/imap.rb', line 61

def initialize(*params)
  super

  if original_params.include?('headers_target')
    @headers_target = normalize_field_ref(headers_target)
  else
    # NOTE: user specified `headers_target => ''` means disable headers (@headers_target == nil)
    # unlike our default here (@headers_target == '') causes setting headers at top level ...
    @headers_target = ecs_compatibility != :disabled ? '[@metadata][input][imap][headers]' : ''
  end

  if original_params.include?('attachments_target')
    @attachments_target = normalize_field_ref(attachments_target)
  else
    @attachments_target = ecs_compatibility != :disabled ? '[@metadata][input][imap][attachments]' : '[attachments]'
  end
end

Instance Method Details

#check_mail(queue) ⇒ Object 



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
 
# File 'lib/logstash/inputs/imap.rb', line 140

def check_mail(queue)
  # TODO(sissel): handle exceptions happening during runtime:
  # EOFError, OpenSSL::SSL::SSLError
  imap = connect
  imap.select(@folder)
  if @uid_tracking && @uid_last_value
    # If there are no new messages, uid_search returns @uid_last_value
    # because it is the last message, so we need to delete it.
    ids = imap.uid_search(["UID", (@uid_last_value+1..-1)]).delete_if { |uid|
      uid <= @uid_last_value
    }
  else
    ids = imap.uid_search("NOT SEEN")
  end

  ids.each_slice(@fetch_count) do |id_set|
    items = imap.uid_fetch(id_set, ["BODY.PEEK[]", "UID"])
    items.each do |item|
      next unless item.attr.has_key?("BODY[]")
      mail = Mail.read_from_string(item.attr["BODY[]"])
      if @strip_attachments
        queue << parse_mail(mail.without_attachments!)
      else
        queue << parse_mail(mail)
      end
      # Mark message as processed
      @uid_last_value = item.attr["UID"]
      imap.uid_store(@uid_last_value, '+FLAGS', @delete || @expunge ? :Deleted : :Seen)

      # Stop message processing if it is requested
      break if stop?
    end

    # Expunge deleted messages
    imap.expunge() if @expunge

    # Stop message fetching if it is requested
    break if stop?
  end

rescue => e
  @logger.error("Encountered error #{e.class}", :message => e.message, :backtrace => e.backtrace)
  # Do not raise error, check_mail will be invoked in the next run time
ensure
  # Close the connection (and ignore errors)
  imap.close rescue nil
  imap.disconnect rescue nil

  # Always save @uid_last_value so when tracking is switched from
  # "NOT SEEN" to "UID" we will continue from first unprocessed message
  if @uid_last_value
    @logger.debug? && @logger.debug("Saving to sincedb", uid_last_value: @uid_last_value)
    File.write(@sincedb_path, @uid_last_value)
  end
end

#connect ⇒ Object

def register



123
124
125
126
127
128
129
130
131
 
# File 'lib/logstash/inputs/imap.rb', line 123

def connect
  sslopt = @secure
  if @secure and not @verify_cert
      sslopt = { :verify_mode => OpenSSL::SSL::VERIFY_NONE }
  end
  imap = Net::IMAP.new(@host, :port => @port, :ssl => sslopt)
  imap.(@user, @password.value)
  return imap
end

#encode_attachment_data(attachment) ⇒ Object

Re-applies the attachment's transfer encoding ourselves (via Mail::Encodings, the same encoders mail uses internally) instead of relying on Mail::Body#encoded, whose return value (encoded vs. already-decoded) has varied across mail gem versions. Note: 'binary' is the in-memory default the mail gem assigns to non-text attachments before they've been serialized/re-parsed, so it's treated like 'base64'.



213
214
215
216
217
218
219
220
221
222
 
# File 'lib/logstash/inputs/imap.rb', line 213

def encode_attachment_data(attachment)
  case attachment.content_transfer_encoding.to_s.downcase
  when 'base64', 'binary'
    Mail::Encodings::Base64.encode(attachment.body.decoded)
  when 'quoted-printable'
    Mail::Encodings::QuotedPrintable.encode(attachment.body.decoded)
  else
    attachment.body.decoded
  end
end

#parse_attachments(mail) ⇒ Object 



196
197
198
199
200
201
202
203
204
205
206
 
# File 'lib/logstash/inputs/imap.rb', line 196

def parse_attachments(mail)
  attachments = []
  mail.attachments.each do |attachment|
    if @save_attachments
      attachments << { "filename" => attachment.filename, "data" => encode_attachment_data(attachment) }
    else
      attachments << { "filename" => attachment.filename}
    end
  end
  return attachments
end

#parse_mail(mail) ⇒ Object 



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
 
# File 'lib/logstash/inputs/imap.rb', line 224

def parse_mail(mail)
  # Add a debug message so we can track what message might cause an error later
  @logger.debug? && @logger.debug("Processing mail", message_id: mail.message_id)

  # TODO(sissel): What should a multipart message look like as an event?
  # For now, just take the plain-text part and set it as the message.
  if mail.parts.count == 0
    # No multipart message, just use the body as the event text
    message = mail.body.decoded
  else
    # Multipart message; use the first text/plain part we find
    part = mail.parts.find { |p| p.content_type.match @content_type_re } || mail.parts.first
    message = part.decoded

    # Parse attachments
    attachments = parse_attachments(mail)
  end

  @codec.decode(message) do |event|
    # Use the 'Date' field as the timestamp
    event.timestamp = LogStash::Timestamp.new(mail.date.to_time)

    process_headers(mail, event) if @headers_target

    # Add attachments
    if attachments && attachments.length > 0 && @attachments_target
      event.set(@attachments_target, attachments)
    end

    decorate(event)
    event
  end
end

#process_headers(mail, event) ⇒ Object 



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
 
# File 'lib/logstash/inputs/imap.rb', line 258

def process_headers(mail, event)
  # Add fields: Add message.header_fields { |h| h.name=> h.value }
  mail.header_fields.each do |header|
    # 'header.name' can sometimes be a Mail::Multibyte::Chars, get it in String form
    name = header.name.to_s
    name = name.downcase if @lowercase_headers

    # Call .decoded on the header in case it's in encoded-word form.
    # Details at:
    #   https://github.com/mikel/mail/blob/master/README.md#encodings
    #   http://tools.ietf.org/html/rfc2047#section-2
    value = transcode_to_utf8(header.decoded)

    targeted_name = "#{@headers_target}[#{name}]"
    case (field = event.get(targeted_name))
    when String
      # promote string to array if a header appears multiple times (like 'received')
      event.set(targeted_name, [field, value])
    when Array
      field << value
      event.set(targeted_name, field)
    when nil
      event.set(targeted_name, value)
    end
  end
end

#register ⇒ Object 



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
 
# File 'lib/logstash/inputs/imap.rb', line 87

def register
  require "net/imap" # in stdlib
  require "mail" # gem 'mail'

  if @secure and not @verify_cert
    @logger.warn("Running IMAP without verifying the certificate may grant attackers unauthorized access to your mailbox or data")
  end

  if @port.nil?
    if @secure
      @port = 993
    else
      @port = 143
    end
  end

  # Load last processed IMAP uid from file if exists
  if @sincedb_path.nil?
    datapath = File.join(LogStash::SETTINGS.get_value("path.data"), "plugins", "inputs", "imap")
    # Ensure that the filepath exists before writing, since it's deeply nested.
    FileUtils::mkdir_p datapath
    @sincedb_path = File.join(datapath, ".sincedb_" + Digest::MD5.hexdigest("#{@user}_#{@host}_#{@port}_#{@folder}"))
    @logger.debug? && @logger.debug("Generated sincedb path", sincedb_path: @sincedb_path)
  end
  @logger.info("Using", sincedb_path: @sincedb_path)
  if File.exist?(@sincedb_path)
    if File.directory?(@sincedb_path)
      raise ArgumentError.new("The \"sincedb_path\" argument must point to a file, received a directory: \"#{@sincedb_path}\"")
    end
    @uid_last_value = File.read(@sincedb_path).to_i
    @logger.debug? && @logger.debug("Loaded from sincedb", uid_last_value: @uid_last_value)
  end

  @content_type_re = Regexp.new("^" + @content_type)
end

#run(queue) ⇒ Object 



133
134
135
136
137
138
 
# File 'lib/logstash/inputs/imap.rb', line 133

def run(queue)
  @run_thread = Thread.current
  Stud.interval(@check_interval) do
    check_mail(queue)
  end
end

#stop ⇒ Object 



285
286
287
 
# File 'lib/logstash/inputs/imap.rb', line 285

def stop
  Stud.stop!(@run_thread)
end