datasift 1.5.0 → 2.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +1 -0
- data/LICENSE +1 -1
- data/README.md +6 -4
- data/VERSION +1 -1
- data/config.yml +2 -2
- data/datasift.gemspec +11 -11
- data/examples/historics.sh +2 -0
- data/examples/historics/create-from-csdl.rb +71 -0
- data/examples/historics/create-from-hash.rb +65 -0
- data/examples/historics/delete.rb +30 -0
- data/examples/historics/env.rb +37 -0
- data/examples/historics/list.rb +30 -0
- data/examples/historics/start.rb +30 -0
- data/examples/historics/stop.rb +30 -0
- data/examples/historics/view.rb +28 -0
- data/examples/push.sh +2 -0
- data/examples/push/delete.rb +33 -0
- data/examples/push/env.rb +53 -0
- data/examples/push/list.rb +30 -0
- data/examples/push/pause.rb +33 -0
- data/examples/push/push-from-hash.rb +72 -0
- data/examples/push/push-historic-from-csdl.rb +98 -0
- data/examples/push/push-stream-from-csdl.rb +70 -0
- data/examples/push/resume.rb +33 -0
- data/examples/push/stop.rb +33 -0
- data/examples/push/view-log.rb +45 -0
- data/examples/push/view.rb +31 -0
- data/lib/DataSift/apiclient.rb +20 -25
- data/lib/DataSift/definition.rb +97 -57
- data/lib/DataSift/exceptions.rb +25 -8
- data/lib/DataSift/historic.rb +321 -0
- data/lib/DataSift/mockapiclient.rb +23 -34
- data/lib/DataSift/push_definition.rb +115 -0
- data/lib/DataSift/push_subscription.rb +330 -0
- data/lib/DataSift/stream_consumer.rb +53 -70
- data/lib/DataSift/stream_consumer_http.rb +11 -15
- data/lib/DataSift/user.rb +189 -61
- data/lib/datasift.rb +5 -10
- data/test/helper.rb +80 -6
- data/test/test_definition.rb +0 -9
- data/test/test_historics.rb +233 -0
- data/test/test_pushdefinition.rb +92 -0
- data/test/test_pushsubscription.rb +17 -0
- data/test/test_user.rb +0 -6
- data/test/testdata.yml +26 -0
- metadata +38 -23
- data/test/test_live_api.rb +0 -100
data/.gitignore
CHANGED
data/LICENSE
CHANGED
data/README.md
CHANGED
@@ -2,9 +2,9 @@ DataSift
|
|
2
2
|
========
|
3
3
|
|
4
4
|
The official Ruby library for accessing the DataSift API. See
|
5
|
-
http://datasift.
|
5
|
+
http://datasift.com/ for full details and to sign up for an account.
|
6
6
|
|
7
|
-
The examples
|
7
|
+
The examples use the username and API key in config.yml unless otherwise noted.
|
8
8
|
|
9
9
|
Install Instructions
|
10
10
|
--------------------
|
@@ -19,7 +19,7 @@ If you're using the source you'll need to install the dependencies.
|
|
19
19
|
sudo gem install yajl-ruby rest-client
|
20
20
|
|
21
21
|
The library will use SSL connections by default. While we recommend using SSL
|
22
|
-
you may disable it if
|
22
|
+
you may disable it if r§equired by passing false as the third parameter when
|
23
23
|
creating a user, or by calling user.enableSSL(false) on the user object.
|
24
24
|
|
25
25
|
Simple example
|
@@ -56,7 +56,9 @@ more details.
|
|
56
56
|
Changelog
|
57
57
|
---------
|
58
58
|
|
59
|
-
* v.
|
59
|
+
* v.2.0.0 Added support for Historics queries and Push delivery (2012-08-31)
|
60
|
+
|
61
|
+
* v.1.5.0 Added getBalance to the User class [joncooper](https://github.com/joncooper) (2012-05-24)
|
60
62
|
|
61
63
|
* v.1.4.1 Fixed a minor bug in the SSL support (2012-05-15)
|
62
64
|
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
|
1
|
+
2.0.0
|
data/config.yml
CHANGED
@@ -1,2 +1,2 @@
|
|
1
|
-
username:
|
2
|
-
api_key:
|
1
|
+
username: 3ft9
|
2
|
+
api_key: 584b068700b016093686a8d3f95696ac
|
data/datasift.gemspec
CHANGED
@@ -2,17 +2,17 @@
|
|
2
2
|
$:.push File.expand_path("../lib", __FILE__)
|
3
3
|
|
4
4
|
Gem::Specification.new do |s|
|
5
|
-
s.name
|
6
|
-
s.version
|
5
|
+
s.name = 'datasift'
|
6
|
+
s.version = File.open('VERSION').first
|
7
7
|
|
8
|
-
s.authors
|
9
|
-
s.email
|
10
|
-
s.description
|
11
|
-
s.summary
|
12
|
-
s.homepage
|
8
|
+
s.authors = ['DataSift']
|
9
|
+
s.email = ['support@datasift.net']
|
10
|
+
s.description = %q{The official Ruby library for accessing the DataSift API. See http://datasift.com/ for full details and to sign up for an account.}
|
11
|
+
s.summary = %q{DataSift is a simple wrapper for the DataSift API.}
|
12
|
+
s.homepage = 'http://github.com/datasift/datasift-ruby'
|
13
13
|
|
14
|
-
s.platform
|
15
|
-
s.rubygems_version
|
14
|
+
s.platform = Gem::Platform::RUBY
|
15
|
+
s.rubygems_version = %q{1.3.6}
|
16
16
|
s.required_rubygems_version = Gem::Requirement.new(">= 1.3.6") if s.respond_to? :required_rubygems_version=
|
17
17
|
|
18
18
|
s.add_runtime_dependency('rest-client', '~> 1.6.3')
|
@@ -21,7 +21,7 @@ Gem::Specification.new do |s|
|
|
21
21
|
s.add_development_dependency('shoulda', '~> 2.11.3')
|
22
22
|
s.add_development_dependency('rspec', '~> 2.6.0')
|
23
23
|
|
24
|
-
s.files
|
25
|
-
s.test_files
|
24
|
+
s.files = `git ls-files`.split("\n")
|
25
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
26
26
|
s.require_paths = ["lib"]
|
27
27
|
end
|
@@ -0,0 +1,71 @@
|
|
1
|
+
# This script creates a new Historics query from a file containing CSDL.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Function to display usage instructions with an optional error message.
|
10
|
+
def usage(message = '', end_of_story = true)
|
11
|
+
puts message + '\n' unless message.length() == 0
|
12
|
+
puts
|
13
|
+
puts 'Usage: create-from-csdl <username> <api_key> \\'
|
14
|
+
puts ' <csdl_filename> <start> <end> <sources> <name> <sample>'
|
15
|
+
puts
|
16
|
+
puts 'Where: csdl_filename = the stream hash the query should run'
|
17
|
+
puts ' start = the start date for the query (YYYYMMDDHHMMSS)'
|
18
|
+
puts ' end = the end date for the query (YYYYMMDDHHMMSS)'
|
19
|
+
puts ' sources = comma separated list of data sources (e.g. twitter)'
|
20
|
+
puts ' name = a friendly name for the query'
|
21
|
+
puts ' sample = the sample rate'
|
22
|
+
puts
|
23
|
+
puts 'Example'
|
24
|
+
puts ' create-from-csdl csdl.txt 20120101000000 20120101235959 \\'
|
25
|
+
puts ' twitter HistoricsQuery123 100'
|
26
|
+
puts
|
27
|
+
exit 1 unless not end_of_story
|
28
|
+
end
|
29
|
+
|
30
|
+
# Include the shared Env class
|
31
|
+
require File.dirname(__FILE__) + '/env'
|
32
|
+
|
33
|
+
# Create the env object. This reads the command line arguments, creates the
|
34
|
+
# user object, and provides access to both along with helper functions.
|
35
|
+
env = Env.new()
|
36
|
+
|
37
|
+
# Check that we have enough arguments
|
38
|
+
usage() unless env.args.size() == 6
|
39
|
+
|
40
|
+
# Read the arguments
|
41
|
+
csdl_filename = env.args[0]
|
42
|
+
start_date = env.args[1]
|
43
|
+
end_date = env.args[2]
|
44
|
+
sources = env.args[3].split(',')
|
45
|
+
name = env.args[4]
|
46
|
+
sample = env.args[5]
|
47
|
+
|
48
|
+
# Parse the dates
|
49
|
+
start_date = DateTime.strptime(start_date, '%Y%m%d%H%M%S')
|
50
|
+
end_date = DateTime.strptime(end_date, '%Y%m%d%H%M%S')
|
51
|
+
|
52
|
+
# Read the CSDL
|
53
|
+
csdl = File.open(csdl_filename, 'r').read
|
54
|
+
|
55
|
+
begin
|
56
|
+
# Create the definition
|
57
|
+
definition = env.user.createDefinition(csdl)
|
58
|
+
|
59
|
+
# Create the Historics query
|
60
|
+
historic = definition.createHistoric(start_date, end_date, sources, name, sample)
|
61
|
+
|
62
|
+
# Prepare the query
|
63
|
+
historic.prepare()
|
64
|
+
|
65
|
+
# Display the details
|
66
|
+
env.displayHistoricDetails(historic)
|
67
|
+
|
68
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
69
|
+
rescue DataSift::DataSiftError => err
|
70
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
71
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
# This script creates a new Historics query from a stream hash.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Function to display usage instructions with an optional error message.
|
10
|
+
def usage(message = '', end_of_story = true)
|
11
|
+
puts message + '\n' unless message.length() == 0
|
12
|
+
puts
|
13
|
+
puts 'Usage: create-from-hash \\'
|
14
|
+
puts ' <username> <api_key> <hash> <start> <end> <sources> <name> <sample>'
|
15
|
+
puts
|
16
|
+
puts 'Where: hash = the stream hash the query should run'
|
17
|
+
puts ' start = the start date for the query (YYYYMMDDHHMMSS)'
|
18
|
+
puts ' end = the end date for the query (YYYYMMDDHHMMSS)'
|
19
|
+
puts ' sources = comma separated list of data sources (e.g. twitter)'
|
20
|
+
puts ' name = a friendly name for the query'
|
21
|
+
puts ' sample = the sample rate'
|
22
|
+
puts
|
23
|
+
puts 'Example'
|
24
|
+
puts ' create-from-hash <hash> 20120101000000 20120101235959 \\'
|
25
|
+
puts ' twitter HistoricsQuery123 100'
|
26
|
+
puts
|
27
|
+
exit 1 unless not end_of_story
|
28
|
+
end
|
29
|
+
|
30
|
+
# Include the shared Env class
|
31
|
+
require File.dirname(__FILE__) + '/env'
|
32
|
+
|
33
|
+
# Create the env object. This reads the command line arguments, creates the
|
34
|
+
# user object, and provides access to both along with helper functions.
|
35
|
+
env = Env.new()
|
36
|
+
|
37
|
+
# Check that we have enough arguments
|
38
|
+
usage() unless env.args.size() == 6
|
39
|
+
|
40
|
+
# Read the arguments
|
41
|
+
stream_hash = env.args[0]
|
42
|
+
start_date = env.args[1]
|
43
|
+
end_date = env.args[2]
|
44
|
+
sources = env.args[3].split(',')
|
45
|
+
name = env.args[4]
|
46
|
+
sample = env.args[5]
|
47
|
+
|
48
|
+
# Parse the dates
|
49
|
+
start_date = DateTime.strptime(start_date, '%Y%m%d%H%M%S')
|
50
|
+
end_date = DateTime.strptime(end_date, '%Y%m%d%H%M%S')
|
51
|
+
|
52
|
+
begin
|
53
|
+
# Create the Historics query
|
54
|
+
historic = env.user.createHistoric(stream_hash, start_date, end_date, sources, name, sample)
|
55
|
+
|
56
|
+
# Prepare the query
|
57
|
+
historic.prepare()
|
58
|
+
|
59
|
+
# Display the details
|
60
|
+
env.displayHistoricDetails(historic)
|
61
|
+
|
62
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
63
|
+
rescue DataSift::DataSiftError => err
|
64
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
65
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# This script deletes Historics queries from your account.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Include the shared Env class
|
10
|
+
require File.dirname(__FILE__) + '/env'
|
11
|
+
|
12
|
+
# Create the env object. This reads the command line arguments, creates the
|
13
|
+
# user object, and provides access to both along with helper functions.
|
14
|
+
env = Env.new()
|
15
|
+
|
16
|
+
# Make sure we have something to do
|
17
|
+
abort('Please specify one or more playback IDs') unless env.args.size() > 0
|
18
|
+
|
19
|
+
begin
|
20
|
+
for playback_id in env.args
|
21
|
+
historic = env.user.getHistoric(playback_id)
|
22
|
+
print 'Deleting ' + playback_id + ', "' + historic.name + '"...'
|
23
|
+
historic.delete()
|
24
|
+
puts 'done'
|
25
|
+
end
|
26
|
+
|
27
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
28
|
+
rescue DataSift::DataSiftError => err
|
29
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
30
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
# This class is used by the Historics examples to remove the noise of
|
2
|
+
# dealing with command line arguments.
|
3
|
+
#
|
4
|
+
|
5
|
+
# Include the DataSift library
|
6
|
+
require File.dirname(__FILE__) + '/../../lib/datasift'
|
7
|
+
|
8
|
+
class Env
|
9
|
+
attr_reader :user, :args
|
10
|
+
|
11
|
+
def initialize(args = false)
|
12
|
+
if args === false
|
13
|
+
args = ARGV
|
14
|
+
end
|
15
|
+
|
16
|
+
abort('Please specify your DataSift username and API key as the first two command line arguments!') unless args.size() >= 2
|
17
|
+
|
18
|
+
username = args.shift
|
19
|
+
api_key = args.shift
|
20
|
+
@user = DataSift::User.new(username, api_key)
|
21
|
+
|
22
|
+
@args = args
|
23
|
+
end
|
24
|
+
|
25
|
+
def displayHistoricDetails(historic)
|
26
|
+
puts 'Playback ID: ' + historic.hash
|
27
|
+
puts 'Stream hash: ' + historic.stream_hash
|
28
|
+
puts 'Name: ' + historic.name
|
29
|
+
puts 'Start time: ' + historic.start_date.strftime('%Y-%m-%d %H:%M:%S')
|
30
|
+
puts 'End time: ' + historic.end_date.strftime('%Y-%m-%d %H:%M:%S')
|
31
|
+
puts 'Sources: ' + historic.sources.join(', ')
|
32
|
+
puts 'Sample: ' + String(historic.sample)
|
33
|
+
puts 'Created at: ' + (historic.created_at.nil? ? 'None' : historic.created_at.strftime('%Y-%m-%d %H:%M:%S'))
|
34
|
+
puts 'Status: ' + historic.status
|
35
|
+
puts '--'
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# This script lists Historics queries in your account.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Include the shared Env class
|
10
|
+
require File.dirname(__FILE__) + '/env'
|
11
|
+
|
12
|
+
# Create the env object. This reads the command line arguments, creates the
|
13
|
+
# user object, and provides access to both along with helper functions.
|
14
|
+
env = Env.new()
|
15
|
+
|
16
|
+
begin
|
17
|
+
historics = env.user.listHistorics()
|
18
|
+
|
19
|
+
if historics['historics'].size() == 0
|
20
|
+
puts 'No Historics queries exist in your account.'
|
21
|
+
else
|
22
|
+
for historic in historics['historics']
|
23
|
+
env.displayHistoricDetails(historic)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
28
|
+
rescue DataSift::DataSiftError => err
|
29
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
30
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# This script starts Historics queries in your account.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Include the shared Env class
|
10
|
+
require File.dirname(__FILE__) + '/env'
|
11
|
+
|
12
|
+
# Create the env object. This reads the command line arguments, creates the
|
13
|
+
# user object, and provides access to both along with helper functions.
|
14
|
+
env = Env.new()
|
15
|
+
|
16
|
+
# Make sure we have something to do
|
17
|
+
abort('Please specify one or more playback IDs') unless env.args.size() > 0
|
18
|
+
|
19
|
+
begin
|
20
|
+
for playback_id in env.args
|
21
|
+
historic = env.user.getHistoric(playback_id)
|
22
|
+
print 'Starting ' + playback_id + ', "' + historic.name + '"...'
|
23
|
+
historic.start()
|
24
|
+
puts 'done'
|
25
|
+
end
|
26
|
+
|
27
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
28
|
+
rescue DataSift::DataSiftError => err
|
29
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
30
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
# This script stops Historics queries in your account.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Include the shared Env class
|
10
|
+
require File.dirname(__FILE__) + '/env'
|
11
|
+
|
12
|
+
# Create the env object. This reads the command line arguments, creates the
|
13
|
+
# user object, and provides access to both along with helper functions.
|
14
|
+
env = Env.new()
|
15
|
+
|
16
|
+
# Make sure we have something to do
|
17
|
+
abort('Please specify one or more playback IDs') unless env.args.size() > 0
|
18
|
+
|
19
|
+
begin
|
20
|
+
for playback_id in env.args
|
21
|
+
historic = env.user.getHistoric(playback_id)
|
22
|
+
print 'Stopping ' + playback_id + ', "' + historic.name + '"...'
|
23
|
+
historic.stop()
|
24
|
+
puts 'done'
|
25
|
+
end
|
26
|
+
|
27
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
28
|
+
rescue DataSift::DataSiftError => err
|
29
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
30
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
# This script views Historics queries in your account.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Include the shared Env class
|
10
|
+
require File.dirname(__FILE__) + '/env'
|
11
|
+
|
12
|
+
# Create the env object. This reads the command line arguments, creates the
|
13
|
+
# user object, and provides access to both along with helper functions.
|
14
|
+
env = Env.new()
|
15
|
+
|
16
|
+
# Make sure we have something to do
|
17
|
+
abort('Please specify one or more playback IDs') unless env.args.size() > 0
|
18
|
+
|
19
|
+
begin
|
20
|
+
for playback_id in env.args
|
21
|
+
historic = env.user.getHistoric(playback_id)
|
22
|
+
env.displayHistoricDetails(historic)
|
23
|
+
end
|
24
|
+
|
25
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
26
|
+
rescue DataSift::DataSiftError => err
|
27
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
28
|
+
end
|
data/examples/push.sh
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
# This script deletes Push subscriptions from your account.
|
2
|
+
#
|
3
|
+
# NB: Most of the error handling (exception catching) has been removed for
|
4
|
+
# the sake of simplicity. Nearly everything in this library may throw
|
5
|
+
# exceptions, and production code should catch them. See the documentation
|
6
|
+
# for full details.
|
7
|
+
#
|
8
|
+
|
9
|
+
# Include the shared Env class
|
10
|
+
require File.dirname(__FILE__) + '/env'
|
11
|
+
|
12
|
+
# Create the env object. This reads the command line arguments, creates the
|
13
|
+
# user object, and provides access to both along with helper functions.
|
14
|
+
env = Env.new()
|
15
|
+
|
16
|
+
# Make sure we have something to do
|
17
|
+
abort('Please specify one or more subscription IDs') unless env.args.size() > 0
|
18
|
+
|
19
|
+
for sub_id in env.args
|
20
|
+
begin
|
21
|
+
sub = env.user.getPushSubscription(sub_id)
|
22
|
+
print 'Deleting ' + sub_id + ', "' + sub.name + '"...'
|
23
|
+
sub.delete()
|
24
|
+
rescue DataSift::DataSiftError => err
|
25
|
+
puts 'ERR: [' + err.class.name + '] ' + err.message
|
26
|
+
else
|
27
|
+
puts 'done'
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
if env.user.rate_limit_remaining != -1
|
32
|
+
puts 'Rate limit remainining: ' + String(env.user.rate_limit_remaining)
|
33
|
+
end
|