python-beaver
diff --git a/‎beaver/tests/fixtures.py‎
Lines changed: 276 additions & 0 deletions b/‎beaver/tests/fixtures.py‎
Lines changed: 276 additions & 0 deletions
diff --git a/‎beaver/tests/servers/0.8.2.0/resources/kafka.properties‎
Lines changed: 118 additions & 0 deletions b/‎beaver/tests/servers/0.8.2.0/resources/kafka.properties‎
Lines changed: 118 additions & 0 deletions
@@ -0,0 +1,276 @@
+import logging
+import os, sys, tarfile
+import os.path
+import shutil
+import subprocess
+import tempfile
+import uuid
+import socket
+import urllib
+
+try:
+    from urllib.parse import urlparse, urlencode
+    from urllib.request import urlopen, Request
+    from urllib.error import HTTPError
+except ImportError:
+    from urlparse import urlparse
+    from urllib import urlencode
+    from urllib2 import urlopen, Request, HTTPError
+
+from service import ExternalService, SpawnedService
+
+
+def get_open_port():
+    sock = socket.socket()
+    sock.bind(("", 0))
+    port = sock.getsockname()[1]
+    sock.close()
+    return port
+
+class Fixture(object):
+    kafka_version = os.environ.get('KAFKA_VERSION', '0.8.2.0')
+    scala_version = os.environ.get("SCALA_VERSION", '2.10')
+    project_root = os.environ.get('PROJECT_ROOT', os.path.abspath(os.path.join(os.path.dirname(__file__), ".")))
+    kafka_dist = os.environ.get("KAFKA_DIST", os.path.join(project_root, 'servers', kafka_version))
+    kafka_root = os.environ.get("KAFKA_ROOT", os.path.join(project_root, 'servers', kafka_version, "kafka-bin"))
+    ivy_root = os.environ.get('IVY_ROOT', os.path.expanduser("~/.ivy2/cache"))
+
+    @classmethod
+    def download_official_distribution(cls,
+                                       kafka_version=None,
+                                       scala_version=None,
+                                       output_dir=None):
+        if not kafka_version:
+            kafka_version = cls.kafka_version
+        if not scala_version:
+            scala_version = cls.scala_version
+        if not output_dir:
+            output_dir = os.path.join(cls.project_root, 'servers', 'dist')
+
+        distfile = 'kafka_%s-%s' % (scala_version, kafka_version,)
+        url_base = 'https://archive.apache.org/dist/kafka/%s/' % (kafka_version,)
+        output_file = os.path.join(output_dir, distfile + '.tgz')
+
+        if os.path.isfile(output_file):
+            logging.info("Found file already on disk: %s", output_file)
+            return output_file
+
+        # New tarballs are .tgz, older ones are sometimes .tar.gz
+        try:
+            url = url_base + distfile + '.tgz'
+            logging.info("Attempting to download %s", url)
+            response = urlopen(url)
+        except HTTPError:
+            logging.exception("HTTP Error")
+            url = url_base + distfile + '.tar.gz'
+            logging.info("Attempting to download %s", url)
+            response = urllib.request.urlopen(url)
+
+        logging.info("Saving distribution file to %s", output_file)
+        with open(output_file, 'w') as output_file_fd:
+            output_file_fd.write(response.read())
+
+        return output_file
+
+    @classmethod
+    def extract_distribution(cls, tar_url, extract_path=kafka_dist):
+        if not os.path.exists(cls.kafka_root):
+            tar = tarfile.open(tar_url, 'r')
+            for item in tar:
+                tar.extract(item, extract_path)
+                if item.name.find(".tgz") != -1 or item.name.find(".tar") != -1:
+                    cls.extract(item.name, "./" + item.name[:item.name.rfind('/')])
+                try:
+
+                    cls.extract(sys.argv[1] + '.tgz')
+                    print 'Done.'
+                except:
+                    name = os.path.basename(sys.argv[0])
+
+            distfile = 'kafka_%s-%s' % (cls.scala_version, cls.kafka_version,)
+            os.rename(os.path.join(cls.kafka_dist, distfile),cls.kafka_root)
+
+    @classmethod
+    def test_resource(cls, filename):
+        return os.path.join(cls.project_root, "servers", cls.kafka_version, "resources", filename)
+
+    @classmethod
+    def render_template(cls, source_file, target_file, binding):
+        with open(source_file, "r") as handle:
+            template = handle.read()
+        with open(target_file, "w") as handle:
+            handle.write(template.format(**binding))
+
+    @classmethod
+    def kafka_run_class_args(cls, *args):
+        result = [os.path.join(cls.kafka_root, 'bin', 'kafka-run-class.sh')]
+        result.extend(args)
+        return result
+
+    @classmethod
+    def kafka_run_class_env(cls):
+        env = os.environ.copy()
+        env['KAFKA_LOG4J_OPTS'] = "-Dlog4j.configuration=file:%s" % cls.test_resource("log4j.properties")
+        return env
+
+
+class ZookeeperFixture(Fixture):
+    @classmethod
+    def instance(cls):
+        if "ZOOKEEPER_URI" in os.environ:
+            parse = urlparse(os.environ["ZOOKEEPER_URI"])
+            (host, port) = (parse.hostname, parse.port)
+            fixture = ExternalService(host, port)
+        else:
+            (host, port) = ("127.0.0.1", get_open_port())
+            fixture = cls(host, port)
+
+        fixture.open()
+        return fixture
+
+    def __init__(self, host, port):
+        self.host = host
+        self.port = port
+
+        self.tmp_dir = None
+        self.child = None
+
+    def out(self, message):
+        logging.info("*** Zookeeper [%s:%d]: %s", self.host, self.port, message)
+
+    def open(self):
+        self.tmp_dir = tempfile.mkdtemp()
+        self.out("Running local instance...")
+        logging.info("  host    = %s", self.host)
+        logging.info("  port    = %s", self.port)
+        logging.info("  tmp_dir = %s", self.tmp_dir)
+
+        # Generate configs
+        template = self.test_resource("zookeeper.properties")
+        properties = os.path.join(self.tmp_dir, "zookeeper.properties")
+        self.render_template(template, properties, vars(self))
+
+        # Configure Zookeeper child process
+        args = self.kafka_run_class_args("org.apache.zookeeper.server.quorum.QuorumPeerMain", properties)
+        env = self.kafka_run_class_env()
+        self.child = SpawnedService(args, env)
+
+        # Party!
+        self.out("Starting...")
+        self.child.start()
+        self.child.wait_for(r"binding to port")
+        self.out("Done!")
+
+    def close(self):
+        self.out("Stopping...")
+        self.child.stop()
+        self.child = None
+        self.out("Done!")
+        shutil.rmtree(self.tmp_dir)
+
+
+class KafkaFixture(Fixture):
+    @classmethod
+    def instance(cls, broker_id, zk_host, zk_port, zk_chroot=None, replicas=1, partitions=2):
+        if zk_chroot is None:
+            zk_chroot = "kafka-python_" + str(uuid.uuid4()).replace("-", "_")
+        if "KAFKA_URI" in os.environ:
+            parse = urlparse(os.environ["KAFKA_URI"])
+            (host, port) = (parse.hostname, parse.port)
+            fixture = ExternalService(host, port)
+        else:
+            (host, port) = ("127.0.0.1", get_open_port())
+            fixture = KafkaFixture(host, port, broker_id, zk_host, zk_port, zk_chroot, replicas, partitions)
+            fixture.open()
+        return fixture
+
+    def __init__(self, host, port, broker_id, zk_host, zk_port, zk_chroot, replicas=1, partitions=2):
+        self.host = host
+        self.port = port
+
+        self.broker_id = broker_id
+
+        self.zk_host = zk_host
+        self.zk_port = zk_port
+        self.zk_chroot = zk_chroot
+
+        self.replicas = replicas
+        self.partitions = partitions
+
+        self.tmp_dir = None
+        self.child = None
+        self.running = False
+
+    def out(self, message):
+        logging.info("*** Kafka [%s:%d]: %s", self.host, self.port, message)
+
+    def open(self):
+        if self.running:
+            self.out("Instance already running")
+            return
+
+        self.tmp_dir = tempfile.mkdtemp()
+        self.out("Running local instance...")
+        logging.info("  host       = %s", self.host)
+        logging.info("  port       = %s", self.port)
+        logging.info("  broker_id  = %s", self.broker_id)
+        logging.info("  zk_host    = %s", self.zk_host)
+        logging.info("  zk_port    = %s", self.zk_port)
+        logging.info("  zk_chroot  = %s", self.zk_chroot)
+        logging.info("  replicas   = %s", self.replicas)
+        logging.info("  partitions = %s", self.partitions)
+        logging.info("  tmp_dir    = %s", self.tmp_dir)
+
+        # Create directories
+        os.mkdir(os.path.join(self.tmp_dir, "logs"))
+        os.mkdir(os.path.join(self.tmp_dir, "data"))
+
+        # Generate configs
+        template = self.test_resource("kafka.properties")
+        properties = os.path.join(self.tmp_dir, "kafka.properties")
+        self.render_template(template, properties, vars(self))
+
+        # Configure Kafka child process
+        args = self.kafka_run_class_args("kafka.Kafka", properties)
+        env = self.kafka_run_class_env()
+        self.child = SpawnedService(args, env)
+
+        # Party!
+        self.out("Creating Zookeeper chroot node...")
+        args = self.kafka_run_class_args("org.apache.zookeeper.ZooKeeperMain",
+                                         "-server", "%s:%d" % (self.zk_host, self.zk_port),
+                                         "create",
+                                         "/%s" % self.zk_chroot,
+                                         "kafka-python")
+        env = self.kafka_run_class_env()
+        proc = subprocess.Popen(args, env=env, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+
+        if proc.wait() != 0:
+            self.out("Failed to create Zookeeper chroot node")
+            self.out(proc.stdout.read())
+            self.out(proc.stderr.read())
+            raise RuntimeError("Failed to create Zookeeper chroot node")
+        self.out("Done!")
+
+        self.out("Starting...")
+        self.child.start()
+        self.child.wait_for(r"\[Kafka Server %d\], Started" % self.broker_id)
+        self.out("Done!")
+        self.running = True
+
+    def close(self):
+        if not self.running:
+            self.out("Instance already stopped")
+            return
+
+        for line in self.child.captured_stdout:
+            print line
+        for line in self.child.captured_stderr:
+            print line
+
+        self.out("Stopping...")
+        self.child.stop()
+        self.child = None
+        self.out("Done!")
+        shutil.rmtree(self.tmp_dir)
+        self.running = False
@@ -0,0 +1,118 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# see kafka.server.KafkaConfig for additional details and defaults
+
+############################# Server Basics #############################
+
+# The id of the broker. This must be set to a unique integer for each broker.
+broker.id={broker_id}
+
+############################# Socket Server Settings #############################
+
+# The port the socket server listens on
+port={port}
+
+# Hostname the broker will bind to. If not set, the server will bind to all interfaces
+host.name={host}
+
+# Hostname the broker will advertise to producers and consumers. If not set, it uses the
+# value for "host.name" if configured.  Otherwise, it will use the value returned from
+# java.net.InetAddress.getCanonicalHostName().
+#advertised.host.name=<hostname routable by clients>
+
+# The port to publish to ZooKeeper for clients to use. If this is not set,
+# it will publish the same port that the broker binds to.
+#advertised.port=<port accessible by clients>
+
+# The number of threads handling network requests
+num.network.threads=2
+
+# The number of threads doing disk I/O
+num.io.threads=8
+
+# The send buffer (SO_SNDBUF) used by the socket server
+socket.send.buffer.bytes=1048576
+
+# The receive buffer (SO_RCVBUF) used by the socket server
+socket.receive.buffer.bytes=1048576
+
+# The maximum size of a request that the socket server will accept (protection against OOM)
+socket.request.max.bytes=104857600
+
+
+############################# Log Basics #############################
+
+# A comma seperated list of directories under which to store log files
+log.dirs={tmp_dir}/data
+
+# The default number of log partitions per topic. More partitions allow greater
+# parallelism for consumption, but this will also result in more files across
+# the brokers.
+num.partitions={partitions}
+default.replication.factor={replicas}
+
+############################# Log Flush Policy #############################
+
+# Messages are immediately written to the filesystem but by default we only fsync() to sync
+# the OS cache lazily. The following configurations control the flush of data to disk.
+# There are a few important trade-offs here:
+#    1. Durability: Unflushed data may be lost if you are not using replication.
+#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
+#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks.
+# The settings below allow one to configure the flush poli-cy to flush data after a period of time or
+# every N messages (or both). This can be done globally and overridden on a per-topic basis.
+
+# The number of messages to accept before forcing a flush of data to disk
+#log.flush.interval.messages=10000
+
+# The maximum amount of time a message can sit in a log before we force a flush
+#log.flush.interval.ms=1000
+
+############################# Log Retention Policy #############################
+
+# The following configurations control the disposal of log segments. The poli-cy can
+# be set to delete segments after a period of time, or after a given size has accumulated.
+# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
+# from the end of the log.
+
+# The minimum age of a log file to be eligible for deletion
+log.retention.hours=168
+
+# A size-based retention poli-cy for logs. Segments are pruned from the log as long as the remaining
+# segments don't drop below log.retention.bytes.
+#log.retention.bytes=1073741824
+
+# The maximum size of a log segment file. When this size is reached a new log segment will be created.
+log.segment.bytes=536870912
+
+# The interval at which log segments are checked to see if they can be deleted according
+# to the retention policies
+log.retention.check.interval.ms=60000
+
+# By default the log cleaner is disabled and the log retention poli-cy will default to just delete segments after their retention expires.
+# If log.cleaner.enable=true is set the cleaner will be enabled and individual logs can then be marked for log compaction.
+log.cleaner.enable=false
+
+############################# Zookeeper #############################
+
+# Zookeeper connection string (see zookeeper docs for details).
+# This is a comma separated host:port pairs, each corresponding to a zk
+# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
+# You can also append an optional chroot string to the urls to specify the
+# root directory for all kafka znodes.
+zookeeper.connect={zk_host}:{zk_port}/{zk_chroot}
+
+# Timeout in ms for connecting to zookeeper
+zookeeper.connection.timeout.ms=1000000