addition of python version to python branch

python/config.json

@@ -0,0 +1,23 @@
+{
+    "serializer": "json",
+    "topology_specs": "topologies/",
+    "virtualenv_specs": "virtualenvs/",
+    "envs": {
+        "prod": {
+            "user": "",
+            "ssh_password": "",
+            "nimbus": "sandbox.hortonworks.com",
+            "use_ssh_for_nimbus": false,
+            "workers": [
+                "sandbox.hortonworks.com"
+            ],
+            "log": {
+                "path": "/var/log/storm/streamparse",
+                "max_bytes": 1000000,
+                "backup_count": 10,
+                "level": "info"
+            },
+            "virtualenv_root": "/data/virtualenvs/"
+        }
+    }
+}

python/fabfile.py

@@ -0,0 +1,11 @@
+def pre_submit(topology_name, env_name, env_config):
+    """Override this function to perform custom actions prior to topology
+    submission. No SSH tunnels will be active when this function is called."""
+    pass
+
+
+def post_submit(topo_name, env_name, env_config):
+    """Override this function to perform custom actions after topology
+    submission. Note that the SSH tunnel to Nimbus will still be active
+    when this function is called."""
+    pass

python/postsetup.sh

@@ -0,0 +1,28 @@
+pip install --upgrade pip
+pip install --upgrade virtualenv
+
+mkdir -p $HOME/bin
+
+if [[ ":$PATH:" != *":$HOME/bin:"* ]]; then
+    PATH=$PATH:$HOME/bin
+    export PATH
+    echo "Added $HOME/bin to PATH"
+fi
+
+wget -O $HOME/bin/lein https://raw.githubusercontent.com/technomancy/leiningen/stable/bin/lein
+chmod a+x $HOME/bin/lein
+echo "#!/bin/bash
+export LEIN_ROOT=true" > /etc/profile.d/leinroot.sh
+export LEIN_ROOT=true
+lein
+
+mkdir -p /data/virtualenvs
+touch /root/.ssh/config
+
+echo "/opt/rh/python27/root/usr/lib64/" >> /etc/ld.so.conf.d/x86_64-linux-gnu.conf
+ldconfig
+
+mkdir -p /var/log/storm/streamparse
+chown -R storm:hadoop /var/log/storm/streamparse
+
+pip install git+https://github.com/srujun/streamparse.git

python/project.clj

@@ -0,0 +1,11 @@
+(defproject wordcount "0.0.1-SNAPSHOT"
+  :resource-paths ["_resources"]
+  :target-path "_build"
+  :min-lein-version "2.0.0"
+  :jvm-opts ["-client"]
+  :repositories { "HDP Releases" "http://repo.hortonworks.com/content/repositories/releases" }
+  :dependencies  [[org.apache.storm/storm-core "0.10.0.2.3.2.0-2950"]
+                  [org.apache.storm/flux-core "0.10.0.2.3.2.0-2950"]]
+  :jar-exclusions     [#"log4j\.properties" #"org\.apache\.storm\.(?!flux)" #"trident" #"META-INF" #"meta-inf" #"\.yaml"]
+  :uberjar-exclusions [#"log4j\.properties" #"org\.apache\.storm\.(?!flux)" #"trident" #"META-INF" #"meta-inf" #"\.yaml"]
+  )

python/pysetup.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+
+yum install -y nano centos-release-SCL zlib-devel \
+bzip2-devel openssl-devel ncurses-devel \
+sqlite-devel readline-devel tk-devel \
+gdbm-devel db4-devel libpcap-devel xz-devel \
+libpng-devel libjpg-devel atlas-devel
+
+yum groupinstall "Development tools" -y
+
+yum install -y python27
+
+echo "#!/bin/bash
+source /opt/rh/python27/enable" > /etc/profile.d/enablepython27.sh

python/src/bolts/NormalizerBolt.py

@@ -0,0 +1,21 @@
+from streamparse import Bolt
+
+class NormalizerBolt(Bolt):
+    outputs = ['word']
+
+    def initialize(self, storm_conf, context):
+        self.common_words = [
+            "the", "be", "a", "an", "and", "of", "to", "in", "am",
+            "is", "are", "at", "not", "that", "have", "i", "it",
+            "for", "on", "with", "he", "she", "as", "you", "do",
+            "this", "but", "his", "by", "from", "they", "we", "her",
+            "or", "will", "my", "one", "all", "s", "if", "any", "our",
+            "may", "your", "these", "d" , " ", "me" , "so" , "what" , "him"
+        ]
+
+    def process(self, tup):
+        # TODO:
+        # Task 1: make the words all lower case
+        # Task 2: remove the common words
+
+        pass

python/src/bolts/SplitSentenceBolt.py

@@ -0,0 +1,9 @@
+from streamparse import Bolt
+
+class SplitSentenceBolt(Bolt):
+    outputs = ['word']
+
+    def process(self, tup):
+        sentence = tup.values[0]
+        for word in sentence.split():
+            self.emit([word])