Merge pull request #44 from clowder-framework/heartbeat

Ability to set heartbeat (fixes #42)

Author: robkooper

CHANGELOG.md

@@ -4,6 +4,14 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/) 
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
+## Unreleased
+
+### Added
+- ability to set the heartbeat for an extractractor [#42](https://github.com/clowder-framework/pyclowder/issues/42)
+
+### Changed
+- update wordcount extractor to not use docker image
+
 ## 2.4.1 - 2021-07-21
 
 ### Added

pyclowder/connectors.py

@@ -645,7 +645,7 @@ def __init__(self, extractor_name, extractor_info,
         self.consumer_tag = None
         self.worker = None
         self.announcer = None
-        self.heartbeat = heartbeat
+        self.heartbeat = float(heartbeat)
 
     def connect(self):
         """connect to rabbitmq using URL parameters"""

pyclowder/extractors.py

@@ -74,6 +74,7 @@ def __init__(self):
         if os.getenv('LOCAL_PROCESSING', "False").lower() == "true":
             connector_default = "Local"
         max_retry = os.getenv('CLOWDER_MAX_RETRY', 10)
+        heartbeat = os.getenv('HEARTBEAT', 5*60)
 
         # create the actual extractor
         self.parser = argparse.ArgumentParser(description=self.extractor_info['description'])
@@ -111,6 +112,8 @@ def __init__(self):
                                  help='instance will bind itself to RabbitMQ by name but NOT file type')
         self.parser.add_argument('--max-retry', dest='max_retry', default=max_retry,
                                  help='Maximum number of retries if an error happens in the extractor')
+        self.parser.add_argument('--heartbeat', dest='heartbeat', default=heartbeat,
+                                 help='Time in seconds between extractor heartbeats (default=%d)' % heartbeat)
 
     def setup(self):
         """Parse command line arguments and so some setup
@@ -165,7 +168,8 @@ def start(self):
                                               rabbitmq_queue=self.args.rabbitmq_queuename,
                                               mounted_paths=json.loads(self.args.mounted_paths),
                                               clowder_url=self.args.clowder_url,
-                                              max_retry=self.args.max_retry)
+                                              max_retry=self.args.max_retry,
+                                              heartbeat=self.args.heartbeat)
                 connector.connect()
                 connector.register_extractor(self.args.registration_endpoints)
                 threading.Thread(target=connector.listen, name="RabbitMQConnector").start()