start supporting kafka importers

A nice feature would be some/any log output as to progress.

2 files changed, 18 insertions, 1 deletions

diff --git a/python/fatcat_tools/importers/__init__.py b/python/fatcat_tools/importers/__init__.py
index 0f5fafb6..e6f081e5 100644
--- a/python/fatcat_tools/importers/__init__.py
+++ b/python/fatcat_tools/importers/__init__.py
@@ -1,5 +1,5 @@
 
-from .common import FatcatImporter
+from .common import FatcatImporter, make_kafka_consumer
 from .crossref import CrossrefImporter, CROSSREF_TYPE_MAP
 from .grobid_metadata import GrobidMetadataImporter
 from .issn import IssnImporter
diff --git a/python/fatcat_tools/importers/common.py b/python/fatcat_tools/importers/common.py
index 18594884..65976a21 100644
--- a/python/fatcat_tools/importers/common.py
+++ b/python/fatcat_tools/importers/common.py
@@ -5,16 +5,33 @@ import csv
 import json
 import itertools
 from collections import Counter
+import pykafka
 
 import fatcat_client
 from fatcat_client.rest import ApiException
 
+
 # from: https://docs.python.org/3/library/itertools.html
 def grouper(iterable, n, fillvalue=None):
     "Collect data into fixed-length chunks or blocks"
     args = [iter(iterable)] * n
     return itertools.zip_longest(*args, fillvalue=fillvalue)
 
+def make_kafka_consumer(hosts, env, topic_suffix, group):
+    topic_name = "fatcat-{}.{}".format(env, topic_suffix).encode('utf-8')
+    client = pykafka.KafkaClient(hosts=hosts, broker_version="1.0.0")
+    consume_topic = client.topics[topic_name]
+    print("Consuming from kafka topic {}, group {}".format(topic_name, group))
+
+    consumer = consume_topic.get_balanced_consumer(
+        consumer_group=group.encode('utf-8'),
+        managed=True,
+        auto_commit_enable=True,
+        auto_commit_interval_ms=30000, # 30 seconds
+        compacted_topic=True,
+    )
+    return consumer
+
 class FatcatImporter:
     """
     Base class for fatcat importers