#./storm jar $HOME/working/storm-starter/target/storm-starter-0.0.1-SNAPSHOT-standalone.jar storm.starter.ExclamationTopology exclamationTopology

def jar(jarfile, klass, *args):
    """Syntax: [storm jar topology-jar-path class ...]

    Runs the main method of class with the specified arguments. 
    The storm jars and configs in ~/.storm are put on the classpath. 
    The process is configured so that StormSubmitter 
    (http://nathanmarz.github.com/storm/doc/backtype/storm/StormSubmitter.html)
    will upload the jar at topology-jar-path when the topology is submitted.
    """
    exec_storm_class(
        klass,
        jvmtype="-client",
        extrajars=[jarfile, USER_CONF_DIR, STORM_DIR + "/bin"],
        args=args,
        jvmopts=["-Dstorm.jar=" + jarfile])

def exec_storm_class(klass, jvmtype="-server", jvmopts=[], 
              extrajars=[], args=[], fork=False):
    global CONFFILE
    all_args = [
        "java", jvmtype, get_config_opts(),
        "-Dstorm.home=" + STORM_DIR, 
        "-Djava.library.path=" + confvalue("java.library.path", extrajars),
        "-Dstorm.conf.file=" + CONFFILE,
        "-cp", get_classpath(extrajars),
    ] + jvmopts + [klass] + list(args)
    print "Running: " + " ".join(all_args)
    if fork:
        os.spawnvp(os.P_WAIT, "java", all_args)
    else:
        os.execvp("java", all_args) # replaces the current process and
        never returns

public static void main(String[] args) throws Exception {
    TopologyBuilder builder = new TopologyBuilder();

    builder.setSpout("spout", new RandomSentenceSpout(), 5);
    builder.setBolt("split", new SplitSentence(), 8).shuffleGrouping("spout");
    builder.setBolt("count", new WordCount(), 12).fieldsGrouping("split", new Fields("word"));

    Config conf = new Config();
    conf.setDebug(true);

    if (args != null && args.length > 0) {
      conf.setNumWorkers(3);

      StormSubmitter.submitTopology(args[0], conf, builder.createTopology());
    }
}

public static void submitTopology(String name, Map stormConf,
 StormTopology topology, SubmitOptions opts) 
throws AlreadyAliveException, InvalidTopologyException 
{
        if(!Utils.isValidConf(stormConf)) {
            throw new IllegalArgumentException("Storm conf is not valid. Must be json-serializable");
        }
        stormConf = new HashMap(stormConf);
        stormConf.putAll(Utils.readCommandLineOpts());
        Map conf = Utils.readStormConfig();
        conf.putAll(stormConf);
        try {
            String serConf = JSONValue.toJSONString(stormConf);
            if(localNimbus!=null) {
                LOG.info("Submitting topology " + name + " in local mode");
                localNimbus.submitTopology(name, null, serConf, topology);
            } else {
                NimbusClient client = NimbusClient.getConfiguredClient(conf);
                if(topologyNameExists(conf, name)) {
                    throw new RuntimeException("Topology with name `"
                    + name 
                    + "` already exists on cluster");
                }
                submitJar(conf);
                try {
                    LOG.info("Submitting topology " +  name 
                    + " in distributed mode with conf " + serConf);
                    if(opts!=null) {
                        client.getClient().submitTopologyWithOpts(name, submittedJar, serConf, topology, opts);                    
                    } else {
                        // this is for backwards compatibility
                        client.getClient().submitTopology(name, submittedJar, serConf, topology);                                            
                    }
                } catch(InvalidTopologyException e) {
                    LOG.warn("Topology submission exception", e);
                    throw e;
                } catch(AlreadyAliveException e) {
                    LOG.warn("Topology already alive exception", e);
                    throw e;
                } finally {
                    client.close();
                }
            }
            LOG.info("Finished submitting topology: " +  name);
        } catch(TException e) {
            throw new RuntimeException(e);
        }
    }

(^void submitTopologyWithOpts
        [this ^String storm-name ^String uploadedJarLocation ^String serializedConf ^StormTopology topology
         ^SubmitOptions submitOptions]
        (try
          (assert (not-nil? submitOptions))
          (validate-topology-name! storm-name)
          (check-storm-active! nimbus storm-name false)
          (.validate ^backtype.storm.nimbus.ITopologyValidator (:validator nimbus)
                     storm-name
                     (from-json serializedConf)
                     topology)
          (swap! (:submitted-count nimbus) inc)
          (let [storm-id (str storm-name "-" @(:submitted-count nimbus) "-" (current-time-secs))
                storm-conf (normalize-conf
                            conf
                            (-> serializedConf
                                from-json
                                (assoc STORM-ID storm-id)
                              (assoc TOPOLOGY-NAME storm-name))
                            topology)
                total-storm-conf (merge conf storm-conf)
                topology (normalize-topology total-storm-conf topology)
                topology (if (total-storm-conf TOPOLOGY-OPTIMIZE)
                           (optimize-topology topology)
                           topology)
                storm-cluster-state (:storm-cluster-state nimbus)]
            (system-topology! total-storm-conf topology) ;; this validates the structure of the topology
            (log-message "Received topology submission for " storm-name " with conf " storm-conf)
            ;; lock protects against multiple topologies being submitted at once and
            ;; cleanup thread killing topology in b/w assignment and starting the topology
            (locking (:submit-lock nimbus)
              (setup-storm-code conf storm-id uploadedJarLocation storm-conf topology)
              (.setup-heartbeats! storm-cluster-state storm-id)
              (let [thrift-status->kw-status {TopologyInitialStatus/INACTIVE :inactive
                                              TopologyInitialStatus/ACTIVE :active}]
                (start-storm nimbus storm-name storm-id (thrift-status->kw-status (.get_initial_status submitOptions))))
              (mk-assignments nimbus)))
          (catch Throwable e
            (log-warn-error e "Topology submission exception. (topology name='" storm-name "')")
            (throw e))))

(defn all-components [^StormTopology topology]
  (apply merge {}
         (for [f thrift/STORM-TOPOLOGY-FIELDS]
           (.getFieldValue topology f)
           )))

(doseq [[topology-id assignment] new-assignments
            :let [existing-assignment (get existing-assignments topology-id)
                  topology-details (.getById topologies topology-id)]]
      (if (= existing-assignment assignment)
        (log-debug "Assignment for " topology-id " hasn't changed")
        (do
          (log-message "Setting new assignment for topology id " topology-id ": " 
                  (pr-str assignment))
          (.set-assignment! storm-cluster-state topology-id assignment)
          )))

_ (.schedule (:scheduler nimbus) topologies cluster)
new-scheduler-assignments (.getAssignments cluster)
;; add more information to convert SchedulerAssignment to Assignment
new-topology->executor->node+port (compute-topology->executor->node+port new-scheduler-assignments)]

(defn mk-synchronize-supervisor [supervisor sync-processes event-manager processes-event-manager]
  (fn this []
    (let [conf (:conf supervisor)
          storm-cluster-state (:storm-cluster-state supervisor)
          ^ISupervisor isupervisor (:isupervisor supervisor)
          ^LocalState local-state (:local-state supervisor)
          sync-callback (fn [& ignored] (.add event-manager this))
          assignments-snapshot (assignments-snapshot storm-cluster-state sync-callback)
          storm-code-map (read-storm-code-locations assignments-snapshot)
          downloaded-storm-ids (set (read-downloaded-storm-ids conf))
          ;;read assignments from zookeeper
          all-assignment (read-assignments
                           assignments-snapshot
                           (:assignment-id supervisor))
          new-assignment (->> all-assignment
                              (filter-key #(.confirmAssigned isupervisor %)))
          ;;task鍦╝ssignment涓?
          assigned-storm-ids (assigned-storm-ids-from-port-assignments new-assignment)
          existing-assignment (.get local-state LS-LOCAL-ASSIGNMENTS)]
      (log-debug "Synchronizing supervisor")
      (log-debug "Storm code map: " storm-code-map)
      (log-debug "Downloaded storm ids: " downloaded-storm-ids)
      (log-debug "All assignment: " all-assignment)
      (log-debug "New assignment: " new-assignment)
      
      ;; download code first
      ;; This might take awhile
      ;;   - should this be done separately from usual monitoring?
      ;; should we only download when topology is assigned to this supervisor?
      (doseq [[storm-id master-code-dir] storm-code-map]
        (when (and (not (downloaded-storm-ids storm-id))
                   (assigned-storm-ids storm-id))
          (log-message "Downloading code for storm id "
             storm-id
             " from "
             master-code-dir)
          (download-storm-code conf storm-id master-code-dir)
          (log-message "Finished downloading code for storm id "
             storm-id
             " from "
             master-code-dir)
          ))

      (log-debug "Writing new assignment "
                 (pr-str new-assignment))
      (doseq [p (set/difference (set (keys existing-assignment))
                                (set (keys new-assignment)))]
        (.killedWorker isupervisor (int p)))
      (.assigned isupervisor (keys new-assignment))
      (.put local-state
            LS-LOCAL-ASSIGNMENTS
            new-assignment)
      (reset! (:curr-assignment supervisor) new-assignment)
      ;; remove any downloaded code that's no longer assigned or active
      ;; important that this happens after setting the local assignment so that
      ;; synchronize-supervisor doesn't try to launch workers for which the
      ;; resources don't exist
      (doseq [storm-id downloaded-storm-ids]
        (when-not (assigned-storm-ids storm-id)
          (log-message "Removing code for storm id "
                       storm-id)
          (rmr (supervisor-stormdist-root conf storm-id))
          ))
      (.add processes-event-manager sync-processes)
      )))

(defn mk-executor [worker executor-id]
 (let [executor-data (mk-executor-data worker executor-id)
   _ (log-message "Loading executor " (:component-id executor-data) ":" (pr-str executor-id))
   task-datas (->> executor-data
                   :task-ids
                   (map (fn [t] [t (task/mk-task executor-data t)]))
                   (into {})
                   (HashMap.))
   _ (log-message "Loaded executor tasks " (:component-id executor-data) ":" (pr-str executor-id))
   report-error-and-die (:report-error-and-die executor-data)
   component-id (:component-id executor-data)

   ;; starting the batch-transfer->worker ensures that anything publishing to that queue 
   ;; doesn't block (because it's a single threaded queue and the caching/consumer started
   ;; trick isn't thread-safe)
   system-threads [(start-batch-transfer->worker-handler! worker executor-data)]
   handlers (with-error-reaction report-error-and-die
              (mk-threads executor-data task-datas))
   threads (concat handlers system-threads)]    
    (setup-ticks! worker executor-data)

    (log-message "Finished loading executor " component-id ":" (pr-str executor-id))
    ;; TODO: add method here to get rendered stats... have worker call that when heartbeating
    (reify
      RunningExecutor
      (render-stats [this]
        (stats/render-stats! (:stats executor-data)))
      (get-executor-id [this]
        executor-id )
      Shutdownable
      (shutdown
        [this]
        (log-message "Shutting down executor " component-id ":" (pr-str executor-id))
        (disruptor/halt-with-interrupt! (:receive-queue executor-data))
        (disruptor/halt-with-interrupt! (:batch-transfer-queue executor-data))
        (doseq [t threads]
          (.interrupt t)
          (.join t))
        
        (doseq [user-context (map :user-context (vals task-datas))]
          (doseq [hook (.getHooks user-context)]
            (.cleanup hook)))
        (.disconnect (:storm-cluster-state executor-data))
        (when @(:open-or-prepare-was-called? executor-data)
          (doseq [obj (map :object (vals task-datas))]
            (close-component executor-data obj)))
        (log-message "Shut down executor " component-id ":" (pr-str executor-id)))
        )))

[(async-loop
      (fn []
        ;; If topology was started in inactive state, don't call (.open spout) until it's activated first.
        (while (not @(:storm-active-atom executor-data))
          (Thread/sleep 100))
        
        (log-message "Opening spout " component-id ":" (keys task-datas))
        (doseq [[task-id task-data] task-datas
                :let [^ISpout spout-obj (:object task-data)
                      tasks-fn (:tasks-fn task-data)
                      send-spout-msg (fn [out-stream-id values message-id out-task-id]
                                       (.increment emitted-count)
   (let [out-tasks (if out-task-id
                     (tasks-fn out-task-id out-stream-id values)
                     (tasks-fn out-stream-id values))
         rooted? (and message-id has-ackers?)
         root-id (if rooted? (MessageId/generateId rand))
         out-ids (fast-list-for [t out-tasks] (if rooted? (MessageId/generateId rand)))]
     (fast-list-iter [out-task out-tasks id out-ids]
                     (let [tuple-id (if rooted?
                                      (MessageId/makeRootId root-id id)
                                      (MessageId/makeUnanchored))
                           out-tuple (TupleImpl. worker-context
                                                 values
                                                 task-id
                                                 out-stream-id
                                                 tuple-id)]
                       (transfer-fn out-task
                                    out-tuple
                                    overflow-buffer)
                       ))
     (if rooted?
       (do
         (.put pending root-id [task-id
                                message-id
                                {:stream out-stream-id :values values}
                                (if (sampler) (System/currentTimeMillis))])
         (task/send-unanchored task-data
                               ACKER-INIT-STREAM-ID
                               [root-id (bit-xor-vals out-ids) task-id]
                               overflow-buffer))
       (when message-id
         (ack-spout-msg executor-data task-data message-id
                        {:stream out-stream-id :values values}
                        (if (sampler) 0))))
     (or out-tasks [])
     ))]]
          (builtin-metrics/register-all (:builtin-metrics task-data) storm-conf (:user-context task-data))
          (builtin-metrics/register-queue-metrics {:sendqueue (:batch-transfer-queue executor-data)
                                                   :receive receive-queue}
                                                  storm-conf (:user-context task-data))

          (.open spout-obj
                 storm-conf
                 (:user-context task-data)
                 (SpoutOutputCollector.
                  (reify ISpoutOutputCollector
                    (^List emit [this ^String stream-id ^List tuple ^Object message-id]
                      (send-spout-msg stream-id tuple message-id nil)
                      )
                    (^void emitDirect [this ^int out-task-id ^String stream-id
                                       ^List tuple ^Object message-id]
                      (send-spout-msg stream-id tuple message-id out-task-id)
                      )
                    (reportError [this error]
                      (report-error error)
                      )))))
        (reset! open-or-prepare-was-called? true) 
        (log-message "Opened spout " component-id ":" (keys task-datas))
        (setup-metrics! executor-data)
        
        (disruptor/consumer-started! (:receive-queue executor-data))
        (fn []
          ;; This design requires that spouts be non-blocking
          (disruptor/consume-batch receive-queue event-handler)
          
          ;; try to clear the overflow-buffer
          (try-cause
            (while (not (.isEmpty overflow-buffer))
              (let [[out-task out-tuple] (.peek overflow-buffer)]
                (transfer-fn out-task out-tuple false nil)
                (.removeFirst overflow-buffer)))
          (catch InsufficientCapacityException e
            ))
          
          (let [active? @(:storm-active-atom executor-data)
                curr-count (.get emitted-count)]
            (if (and (.isEmpty overflow-buffer)
                     (or (not max-spout-pending)
                         (< (.size pending) max-spout-pending)))
              (if active?
                (do
                  (when-not @last-active
                    (reset! last-active true)
                    (log-message "Activating spout " component-id ":" (keys task-datas))
                    (fast-list-iter [^ISpout spout spouts] (.activate spout)))
               
                  (fast-list-iter [^ISpout spout spouts] (.nextTuple spout)))
                (do
                  (when @last-active
                    (reset! last-active false)
                    (log-message "Deactivating spout " component-id ":" (keys task-datas))
                    (fast-list-iter [^ISpout spout spouts] (.deactivate spout)))
                  ;; TODO: log that it's getting throttled
                  (Time/sleep 100))))
            (if (and (= curr-count (.get emitted-count)) active?)
              (do (.increment empty-emit-streak)
                  (.emptyEmit spout-wait-strategy (.get empty-emit-streak)))
              (.set empty-emit-streak 0)
              ))           
          0))
      :kill-fn (:report-error-and-die executor-data)
      :factory? true
      :thread-name component-id)]))

(fn [task-id ^TupleImpl tuple]
  [stream-id (.getSourceStreamId tuple)]
 ondp = stream-id
 Constants/SYSTEM_TICK_STREAM_ID (.rotate pending)
 Constants/METRICS_TICK_STREAM_ID (metrics-tick executor-data task-datas tuple)
 (let [id (.getValue tuple 0)
       [stored-task-id spout-id tuple-finished-info start-time-ms] (.remove pending id)]
   (when spout-id
     (when-not (= stored-task-id task-id)
       (throw-runtime "Fatal error, mismatched task ids: " task-id " " stored-task-id))
     (let [time-delta (if start-time-ms (time-delta-ms start-time-ms))]
       (condp = stream-id
         ACKER-ACK-STREAM-ID (ack-spout-msg executor-data (get task-datas task-id)
                                            spout-id tuple-finished-info time-delta)
         ACKER-FAIL-STREAM-ID (fail-spout-msg executor-data (get task-datas task-id)
                                              spout-id tuple-finished-info time-delta)
         )))
   ;; TODO: on failure, emit tuple to failure stream
   ))))