alarm.rb in ring-sqa-0.0.20

- old
+ new

@@ -1,11 +1,11 @@
 require_relative 'alarm/email'
 require_relative 'alarm/udp2irc'
 require_relative 'alarm/cfg'
+require_relative 'alarm/message'
 require_relative 'mtr'
 require_relative 'paste'
-require_relative 'nodes_json'
 
 module Ring
 class SQA
 
   class Alarm
@@ -28,23 +28,23 @@
       end
     end
 
     private
 
-    def initialize
+    def initialize nodes
+      @nodes    = nodes
       @methods  = []
       @methods  << Email.new   if CFG.email.to?
       @methods  << UDP2IRC.new if CFG.irc.password?
+      @hostname = Ring::SQA::CFG.host.name
       @alarm    = false
-      @hostname = (Socket.gethostname rescue 'anonymous')
     end
 
     def compose_message alarm_buffer
       exceeding_nodes = alarm_buffer.exceeding_nodes
       msg = {short: "#{@hostname}: raising alarm - #{exceeding_nodes.size} new nodes down"}
-      nodes_json = NodesJSON.new
-      exceeding_nodes = exceeding_nodes.map { |node| nodes_json.get node }
+      exceeding_nodes = exceeding_nodes.map { |node| @nodes.get node }
 
       nodes_list = ''
       exceeding_nodes.sort_by{ |node| node[:cc] }.each do |node|
         nodes_list << "- %-35s %15s  AS%-6s  %2s\n" % [node[:name], node[:ip], node[:as], node[:cc]]
       end
@@ -62,43 +62,10 @@
         buffer_list << "%2s min ago %3s measurements failed" % [time, ary.size/2]
         buffer_list << (time.to_i < 3 ? " (raised alarm)\n" : " (baseline)\n")
         time -= 1
       end
 
-      msg[:long] = <<EOF
-Regarding: #{hostname}
-
-This is an automated alert from the distributed partial outage
-monitoring system "RING SQA".
-
-At #{Time.now.utc} the following measurements were analysed
-as indicating that there is a high probability your NLNOG RING node
-cannot reach the entire internet. Possible causes could be an outage
-in your upstream's or peer's network.
-
-The following #{exceeding_nodes.size} nodes previously were reachable, but became unreachable
-over the course of the last 3 minutes:
-
-#{nodes_list}
-
-As a debug starting point 3 traceroutes were launched right after
-detecting the event, they might assist in pinpointing what broke:
-
-#{mtr_list}
-
-An alarm is raised under the following conditions: every 30 seconds
-your node pings all other nodes. The amount of nodes that cannot be
-reached is stored in a circular buffer, with each element representing
-a minute of measurements. In the event that the last three minutes are
-#{Ring::SQA::CFG.analyzer.tolerance} above the median of the previous 27 measurement slots, a partial
-outage is assumed. The ring buffer's output is as following:
-
-#{buffer_list}
-
-Kind regards,
-
-NLNOG RING
-EOF
+      msg[:long] = message nodes_list, mtr_list, buffer_list
       msg
     end
 
   end
 