"""Setting up a web service for sharing numerical data

This came up in the context of people doing quantified-self experiments
but I think it can be valuable in several contexts, if done well. General
principles:

(1) Data should be as self-documenting as possible, via semantic
markup or something similar.
(2) Simultaneously, there should be as few as possible a-priori
constraints on how data is formatted.
(3) Data should be human-readable, or easily rendered human-readable.
(4) There should be some provision for controlling access to data.

So I think it makes sense to offer data in a JSON format.

To support ease of understanding data semantically, data objects may
refer to a descriptor object. If they don't, they should contain their
own descriptive information.

To avoid confusion between different objects, every object with any
likelihood of persistence (the exception being a request template sent
to the web service) should include a randomly generated 128-bit UUID.

An alternative to the UUID would be a permanently-assigned URI, in
keeping with the Semantic Web way of doing things. It might make sense
that any object shared publicly would have a URI.

Privacy control can be done a few different ways. Obviously a server
could operate behind a firewall and the system could be set up to
prohibit data sharing beyond the firewall. But for data that can't
just live behind a firewall there should be some more nuanced
provision for controlling privacy.

A web service should allow users to:
(1) Post descriptor and data objects on the server.
(2) Specify who is allowed to fetch a particular object.
    (a) Create groups of the users on the system.
    (b) Use a set-union of groups and individual users to specify
        who is allowed to fetch an object. (See example below, where
        an individual is "Bob Smith" and a group is "weatherbuffs".)
(3) Fetch data and descriptor objects using a template.
"""

import json
import pprint
import datetime
import urllib

########### Some preliminaries ##########################
#
# As of this writing I don't yet have a server working.
# But the following shows how client code will access it
# when it exists.

SERVER_URL = 'http://127.0.0.1/data-server/'

def httpPostRequest(params):
    f = urllib.urlopen(SERVER_URL, urllib.urlencode(params))
    data = f.read()
    f.close()
    return json.loads(data)

def httpGetRequest(params):
    f = urllib.urlopen(SERVER_URL + '?' + urllib.urlencode(params))
    data = f.read()
    f.close()
    return json.loads(data)

HOUR = datetime.timedelta(hours=1)

########### Descriptors and data #####################

def generateId():
    import hashlib
    import random
    h = hashlib.sha1()
    h.update(repr(random.random()))
    return h.hexdigest()

descriptor = {
    'id': generateId(),  # a URI could also work here
    'summary': 'A sequence of temperature samples in time',
    'creator': 'Will Ware <[email protected]>',
    'format': {
        'units': 'fahrenheit',
        'period': 1,   # seconds
        },
}

now = datetime.datetime.now()   # how to handle time zones? UTC?

data = {
    'timestamp': now.strftime('%Y/%m/%d %H:%M:%S.%f'),
    'latitude': 42.0,
    'longitude': -71.0,
    'id': generateId(),
    'descriptor': descriptor['id'],
    'creator': 'Will Ware <[email protected]>',
    'experiment': 'Outdoor temperature near Will\'s house',
    'summary': 'Anything summary-wise more specific than the descriptor',
    'samples': [
        82.0, 85.0, 83.0, 84.0, 86.0
        ],
    'visible-to': [
        'Bob Smith', 'weatherbuffs'
        ]
}

pprint.pprint(descriptor)
print
pprint.pprint(data)

if False:
    # submit a descriptor object
    httpPostRequest(descriptor)

    # submit a data object
    httpPostRequest(data)


#################################################
# Here is a template for fetching all data objects less than two hours
# old, created by Will, and using the descriptor appearing above.

template = {
    'timestamp__gt':   # server will probably be written in Django
        (now - 2 * HOUR).strftime('%Y/%m/%d %H:%M:%S.%f'),
    'creator': 'Will Ware <[email protected]>',
    'descriptor': descriptor['id'],
}

print
pprint.pprint(template)

if False:
    print httpGetRequest(template)

import json
import pprint
import datetime
import urllib

########### Some preliminaries ##########################
#
# As of this writing I don't yet have a server working.
# But the following shows how client code will access it
# when it exists.

SERVER_URL = 'http://127.0.0.1/data-server/'

def httpPostRequest(params):
    f = urllib.urlopen(SERVER_URL, urllib.urlencode(params))
    data = f.read()
    f.close()
    return json.loads(data)

def httpGetRequest(params):
    f = urllib.urlopen(SERVER_URL + '?' + urllib.urlencode(params))
    data = f.read()
    f.close()
    return json.loads(data)

HOUR = datetime.timedelta(hours=1)

########### Descriptors and data #####################

def generateId():
    import hashlib
    import random
    h = hashlib.sha1()
    h.update(repr(random.random()))
    return h.hexdigest()

descriptor = {
    'id': generateId(),  # a URI could also work here
    'summary': 'A sequence of temperature samples in time',
    'creator': 'Will Ware <[email protected]>',
    'format': {
        'units': 'fahrenheit',
        'period': 1,   # seconds
        },
}

now = datetime.datetime.now()   # how to handle time zones? UTC?

data = {
    'timestamp': now.strftime('%Y/%m/%d %H:%M:%S.%f'),
    'latitude': 42.0,
    'longitude': -71.0,
    'id': generateId(),
    'descriptor': descriptor['id'],
    'creator': 'Will Ware <[email protected]>',
    'experiment': 'Outdoor temperature near Will\'s house',
    'summary': 'Anything summary-wise more specific than the descriptor',
    'samples': [
        82.0, 85.0, 83.0, 84.0, 86.0
        ],
    'visible-to': [
        'Bob Smith', 'weatherbuffs'
        ]
}

pprint.pprint(descriptor)
print
pprint.pprint(data)

if False:
    # submit a descriptor object
    httpPostRequest(descriptor)

    # submit a data object
    httpPostRequest(data)


#################################################
# Here is a template for fetching all data objects less than two hours
# old, created by Will, and using the descriptor appearing above.

template = {
    'timestamp__gt':   # server will probably be written in Django
        (now - 2 * HOUR).strftime('%Y/%m/%d %H:%M:%S.%f'),
    'creator': 'Will Ware <[email protected]>',
    'descriptor': descriptor['id'],
}

print
pprint.pprint(template)

if False:
    print httpGetRequest(template)

http://edison.thinktrylearn.com/experiments/show/198

Puttering with a proposal for a web API for numerical data sharing

Python