# Lets start to interact with workbench, please note there is NO specific client to workbench,
# Just use the ZeroRPC Python, Node.js, or CLI interfaces.
import zerorpc
c = zerorpc.Client()
c.connect("tcp://127.0.0.1:4242")

# I forgot what stuff I can do with workbench
print c.help()

# Now lets get infomation about the dynamically loaded workers (your site may have many more!)
# Next to each worker name is the list of dependences that worker has declared
print c.help_workers()

# Lets gets the infomation about the meta worker
print c.help_worker('meta')

# Okay lets load up a file, and see what this silly meta thing gives back
filename = '../data/pe/bad/9e42ff1e6f75ae3e60b24e48367c8f26'
with open(filename,'rb') as f:
    my_md5 = c.store_sample(f.read(), filename, 'exe')
output = c.work_request('meta', my_md5)
output

# Pfff... my meta data worker will be WAY better!
# Err.. okay I'll just copy the meta worker file and see what happens.
# Note: obviously you'd just go to the shell and cp meta.py my_meta.py
#       but since we're in IPython...
%cd /Users/briford/work/workbench/server/workers
%cp meta.py my_meta.py
%cd /Users/briford/work/workbench/notebooks

# Okay just cause I'm feeling crazy lets look at help_workers again
print c.help_workers()

# My mind must be playing tricks, lets see if I can run my worker
output = c.work_request('my_meta', my_md5)
output

# I've been around software... testing, server integration, test coverage all that stuff is
# a complete PITA, heck I spend half my time doing that.. there's no way all that just happened.
!./runtests

# You sir are on some sort of needle drug... so you're saying that all the new functionality
# that I just typed in is already available on the server? Help too? 
print c.help_worker('my_meta')
output = c.work_request('my_meta', my_md5)
output

# Run my new code
output = c.work_request('my_meta', my_md5)
output

# So lets do a more complicated worker just for hammering home what's happening..
# Workbench uses Directed Acyclic Graphs to pipeline workers together, it recursively
# satisfies dependencies with agressive caching, shallow memory copies and gevent based
# co-operative processes on the server side. Basicaly six slices of awesome...
output = c.work_request('view', my_md5)
output

# Yeah but I want to run my new worker on a LOTS of samples and I
# want to put the results into a Pandas dataframes and run some 
# statistics, and do some Machine Learning and kewl plots!

# This is just throwing files at Workbench (could be pdfs, swfs, pcap, memory_images, etc)
import os
file_list = [os.path.join('../data/pe/bad', child) for child in os.listdir('../data/pe/bad')]
working_set = []
for filename in file_list:
    with open(filename,'rb') as f:
        md5 = c.store_sample(f.read(), filename, 'exe')
        working_set.append(md5)

# Now just run a batch request against all the sample we just threw in
results = c.batch_work_request('my_meta', {'md5_list':working_set})
results

# Now toss that client-server generator into a dataframe (zero-copy and efficient)
import pandas as pd
df_meta = pd.DataFrame(results)
df_meta.head()

# Plotting defaults
import matplotlib.pyplot as plt
%matplotlib inline
plt.rcParams['font.size'] = 12.0
plt.rcParams['figure.figsize'] = 18.0, 8.0

# Plot stuff (yes this is a silly plot but it's just an example :)
df_meta.boxplot('entropy','packed')
plt.xlabel('Packed')
plt.ylabel('Entropy')
plt.title('Entropy of Sample')
plt.suptitle('')

# Groupby and Statistics (yes silly again but just an example)
df_meta.groupby('packed').describe()