crocoduck 0.0.5
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/crocoduck/entry.rb +73 -0
- data/lib/crocoduck/job.rb +102 -0
- data/lib/crocoduck/logging.rb +25 -0
- data/lib/crocoduck/redis.rb +7 -0
- data/lib/crocoduck/resque.rb +8 -0
- data/lib/crocoduck/server.rb +19 -0
- data/lib/crocoduck/store.rb +84 -0
- metadata +142 -0
@@ -0,0 +1,73 @@
|
|
1
|
+
# The Entry object represents a document retrieved from
|
2
|
+
# the datastore. By default this is a MongoDB document.
|
3
|
+
require 'crocoduck/job'
|
4
|
+
require 'crocoduck/redis'
|
5
|
+
require 'crocoduck/resque'
|
6
|
+
require 'crocoduck/store'
|
7
|
+
|
8
|
+
module Crocoduck
|
9
|
+
class Entry
|
10
|
+
attr_accessor :entry_id, :entry, :store
|
11
|
+
|
12
|
+
def initialize(entry_id)
|
13
|
+
@entry_id = entry_id
|
14
|
+
end
|
15
|
+
|
16
|
+
# A quick way to start work on an Entry is to do something
|
17
|
+
# like the following
|
18
|
+
#
|
19
|
+
# >>> e = Entry.new(53029).schedule(ShortUrlJob)
|
20
|
+
def schedule(worker = Job)
|
21
|
+
Resque.enqueue worker, entry_id
|
22
|
+
end
|
23
|
+
|
24
|
+
# Rather than access ``Crocoduck::Entry.entry`` directly, one can do the
|
25
|
+
# following:
|
26
|
+
#
|
27
|
+
# :001 > e = Crocoduck::Entry.new(50039)
|
28
|
+
# => #<Crocoduck::Entry:0x101611938 @entry_id=50039>
|
29
|
+
# :002 > e["url"]
|
30
|
+
# => "/apple/news/2011/04/this-is-not-a-real-article.ars"
|
31
|
+
def [](key)
|
32
|
+
if entry.has_key? key
|
33
|
+
entry[key]
|
34
|
+
else
|
35
|
+
nil
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
# This hasn't been field tested yet, but ``update`` should be a
|
40
|
+
# convienance method to manipulate a field on the entry document
|
41
|
+
# stored here. If a job needed to store results or data on a
|
42
|
+
# different document, she could use the ``Crocoduck::Store.update`` method
|
43
|
+
# directly.
|
44
|
+
def update(field, value)
|
45
|
+
store.update entry_id, field, value
|
46
|
+
end
|
47
|
+
|
48
|
+
# Call this method on your entries to have them close their own
|
49
|
+
# store object.
|
50
|
+
def close
|
51
|
+
store.close
|
52
|
+
end
|
53
|
+
|
54
|
+
def setup?
|
55
|
+
store.setup? && !entry.nil?
|
56
|
+
end
|
57
|
+
|
58
|
+
private
|
59
|
+
|
60
|
+
# When the ``entry`` property of an Entry object is accessed
|
61
|
+
# we attempt to retrieve the document from the store, save it
|
62
|
+
# on our object, and then return it. Further accesses get the
|
63
|
+
# cached copy of the document.
|
64
|
+
def entry
|
65
|
+
@entry ||= store.get entry_id
|
66
|
+
end
|
67
|
+
|
68
|
+
# Accessing ``Crocoduck::Entry.store`` gets you a new store object to work with.
|
69
|
+
def store
|
70
|
+
@store ||= Store.new
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
@@ -0,0 +1,102 @@
|
|
1
|
+
# `Job` is a class that is intended to be extended to do meaningful work. A
|
2
|
+
# Crocoduck Job is simply a Resque style job that knows about its own
|
3
|
+
# datastore and an entry object (Mongo Document when using the supplied
|
4
|
+
# ``store`` class).
|
5
|
+
require 'crocoduck/logging'
|
6
|
+
require 'crocoduck/entry'
|
7
|
+
|
8
|
+
module Crocoduck
|
9
|
+
class Job
|
10
|
+
# Override the value of ``@queue`` to specify which resque workers will
|
11
|
+
# process this job.
|
12
|
+
@queue = :low
|
13
|
+
|
14
|
+
class << self
|
15
|
+
attr_accessor :description
|
16
|
+
end
|
17
|
+
|
18
|
+
# ``perform`` is the method called by Resque. A Crocoduck job only expects
|
19
|
+
# an ``entry_id`` corresponding to a record in your Mongo store. An
|
20
|
+
# ``Entry`` is instantiated with said ``entry_id`` and passed to a new
|
21
|
+
# instance of this job and run is called on it.
|
22
|
+
def self.perform(entry_id)
|
23
|
+
init_with_id(entry_id).run
|
24
|
+
end
|
25
|
+
|
26
|
+
# A convienance initializer that returns a Crocoduck::Job instance with
|
27
|
+
# its entry object ready to go.
|
28
|
+
def self.init_with_id(entry_id)
|
29
|
+
new(Entry.new entry_id)
|
30
|
+
end
|
31
|
+
|
32
|
+
include Logging
|
33
|
+
|
34
|
+
attr_accessor :entry
|
35
|
+
|
36
|
+
def initialize(entry)
|
37
|
+
@entry = entry
|
38
|
+
end
|
39
|
+
|
40
|
+
# The ``do_work`` method should be overridden to do some kind of work on
|
41
|
+
# the stored entry object.
|
42
|
+
def do_work
|
43
|
+
logger.info "Starting work"
|
44
|
+
# Do Something with entry
|
45
|
+
# entry.update "derp", "herp"
|
46
|
+
logger.info entry["url"]
|
47
|
+
# shorturl = shorturl.generate @entry.url
|
48
|
+
# store.update entry_id, 'shorturl', shorturl
|
49
|
+
# store.update entry_id, 'shorturl_status, job_status
|
50
|
+
logger.info "Ending work"
|
51
|
+
end
|
52
|
+
|
53
|
+
# If you job failed, you can do something interesting here. Generally
|
54
|
+
# you will want to ultimately raise the exception so Resque can track it.
|
55
|
+
def handle_exception(e)
|
56
|
+
raise e
|
57
|
+
end
|
58
|
+
|
59
|
+
# This method will be called immediately before sanity checks and before
|
60
|
+
# ``do_work`` is called.
|
61
|
+
def setup
|
62
|
+
logger.info "Job is setup"
|
63
|
+
end
|
64
|
+
|
65
|
+
# This method will be called once ``do_work`` has finished successfully.
|
66
|
+
# Do anything you'd need to do once the processing was finished
|
67
|
+
# properly (save out your entry, update stats, et cetera).
|
68
|
+
def finished
|
69
|
+
logger.info "Job finished successfully"
|
70
|
+
end
|
71
|
+
|
72
|
+
# This method will always be called, regardless of the failure or
|
73
|
+
# success of your job.
|
74
|
+
def cleanup
|
75
|
+
entry.close
|
76
|
+
logger.info "Job cleaned up"
|
77
|
+
end
|
78
|
+
|
79
|
+
# The ``run`` method is a thin wrapper around ``do_work`` which lets us
|
80
|
+
# do some setup, benchmark the work we'll do, cleanly handle exceptions if
|
81
|
+
# thrown by the ``do_work`` call, and clean up our store and entry on
|
82
|
+
# success.
|
83
|
+
def run
|
84
|
+
setup
|
85
|
+
# The job will not process anything unless our datastore has enough
|
86
|
+
# information to connect and if a valid entry object could be fetched
|
87
|
+
# from the store.
|
88
|
+
return unless entry.setup?
|
89
|
+
benchmark :info, "Running job" do
|
90
|
+
do_work
|
91
|
+
end
|
92
|
+
# Exception handling is parceled out to ``Job`` methods you can override
|
93
|
+
# to handle cleanup specific to your task.
|
94
|
+
rescue Exception => e
|
95
|
+
handle_exception e
|
96
|
+
else
|
97
|
+
finished
|
98
|
+
ensure
|
99
|
+
cleanup
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# Include Loggging into your class to get a logger and benchmark
|
2
|
+
# object for logging errors or information to stdout and for profiling
|
3
|
+
# interesting bits of code.
|
4
|
+
require 'benchmark'
|
5
|
+
require 'logger'
|
6
|
+
|
7
|
+
module Crocoduck
|
8
|
+
def self.logger
|
9
|
+
@logger ||= Logger.new($stderr)
|
10
|
+
end
|
11
|
+
|
12
|
+
module Logging
|
13
|
+
private
|
14
|
+
def logger
|
15
|
+
Crocoduck.logger
|
16
|
+
end
|
17
|
+
|
18
|
+
def benchmark(level, message)
|
19
|
+
result = nil
|
20
|
+
ms = Benchmark.realtime { result = yield }
|
21
|
+
logger.send(level, '%s (%.5fs)' % [ message, ms ])
|
22
|
+
result
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
require 'sinatra/base'
|
2
|
+
require 'crocoduck/entry'
|
3
|
+
|
4
|
+
module Crocoduck
|
5
|
+
class Server < Sinatra::Base
|
6
|
+
set :root, File.dirname(__FILE__)
|
7
|
+
|
8
|
+
get "/" do
|
9
|
+
erb :index
|
10
|
+
end
|
11
|
+
|
12
|
+
post "/" do
|
13
|
+
entry_id = params[:entry_id]
|
14
|
+
entry = Entry.new entry_id
|
15
|
+
entry.schedule
|
16
|
+
redirect "/"
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,84 @@
|
|
1
|
+
# The Crocoduck::Store object handles the concern of talking to your
|
2
|
+
# data storage layer. By default, we have implemented this on top
|
3
|
+
# of MongoDB, so it may be that many of the choices made here highly
|
4
|
+
# favor document-based databases.
|
5
|
+
require 'mongo'
|
6
|
+
require 'crocoduck/logging'
|
7
|
+
|
8
|
+
module Crocoduck
|
9
|
+
class Store
|
10
|
+
include Logging
|
11
|
+
# We have several class properties that defined how all Store
|
12
|
+
# objects will connect and query for information. As stated
|
13
|
+
# before, many of these will only make sense for MongoDB or
|
14
|
+
# other similar document-based databases.
|
15
|
+
@id_field = '_id'
|
16
|
+
@server_cluster = nil
|
17
|
+
@server_db = nil
|
18
|
+
@server_collection = nil
|
19
|
+
|
20
|
+
class << self
|
21
|
+
attr_accessor :id_field, :server_cluster, :server_db, :server_collection
|
22
|
+
end
|
23
|
+
|
24
|
+
attr_accessor :store, :database, :collection
|
25
|
+
|
26
|
+
# A nice method to determine if there is enough information
|
27
|
+
# to potentially connect to the backing database.
|
28
|
+
def setup?
|
29
|
+
Crocoduck::Store.server_cluster &&
|
30
|
+
Crocoduck::Store.server_db &&
|
31
|
+
Crocoduck::Store.server_collection
|
32
|
+
end
|
33
|
+
|
34
|
+
def close
|
35
|
+
store.close
|
36
|
+
end
|
37
|
+
|
38
|
+
# A simple convienance method to update a single
|
39
|
+
# document in your datastore.
|
40
|
+
def update(entry_id, field, value)
|
41
|
+
collection.update({
|
42
|
+
Crocoduck::Store.id_field => entry_id},
|
43
|
+
{'$set' => { field => value}
|
44
|
+
}, :safe => true)
|
45
|
+
end
|
46
|
+
|
47
|
+
# Returns a single document given its ID
|
48
|
+
def get(id)
|
49
|
+
collection.find_one({
|
50
|
+
Crocoduck::Store.id_field => id.to_i
|
51
|
+
})
|
52
|
+
end
|
53
|
+
|
54
|
+
# Use this method to remove documents from your datastore. Cares
|
55
|
+
# has been taken to prevent accidental database destruction. Only
|
56
|
+
# pass {} to this method if you are 100% sure you want to clear the
|
57
|
+
# database.
|
58
|
+
def remove(criteria=nil)
|
59
|
+
return if criteria.nil?
|
60
|
+
collection.remove criteria
|
61
|
+
end
|
62
|
+
|
63
|
+
# Inserts a brand new document into the database
|
64
|
+
def insert(document)
|
65
|
+
collection.insert document
|
66
|
+
end
|
67
|
+
|
68
|
+
private
|
69
|
+
|
70
|
+
# These methods create and cache objects that maintain the state and
|
71
|
+
# connectivity to the backend storage.
|
72
|
+
def collection
|
73
|
+
@collection ||= database.collection Crocoduck::Store.server_collection
|
74
|
+
end
|
75
|
+
|
76
|
+
def database
|
77
|
+
@database ||= store.db(Crocoduck::Store.server_db)
|
78
|
+
end
|
79
|
+
|
80
|
+
def store
|
81
|
+
@store ||= Mongo::ReplSetConnection.new(*Crocoduck::Store.server_cluster)
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
metadata
ADDED
@@ -0,0 +1,142 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: crocoduck
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 21
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 5
|
10
|
+
version: 0.0.5
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Clint Ecker
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2011-06-17 00:00:00 -05:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: redis
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 3
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
version: "0"
|
33
|
+
type: :runtime
|
34
|
+
version_requirements: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: resque
|
37
|
+
prerelease: false
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
hash: 3
|
44
|
+
segments:
|
45
|
+
- 0
|
46
|
+
version: "0"
|
47
|
+
type: :runtime
|
48
|
+
version_requirements: *id002
|
49
|
+
- !ruby/object:Gem::Dependency
|
50
|
+
name: sinatra
|
51
|
+
prerelease: false
|
52
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
54
|
+
requirements:
|
55
|
+
- - ">="
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
hash: 3
|
58
|
+
segments:
|
59
|
+
- 0
|
60
|
+
version: "0"
|
61
|
+
type: :runtime
|
62
|
+
version_requirements: *id003
|
63
|
+
- !ruby/object:Gem::Dependency
|
64
|
+
name: mongo
|
65
|
+
prerelease: false
|
66
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
67
|
+
none: false
|
68
|
+
requirements:
|
69
|
+
- - ">="
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
hash: 3
|
72
|
+
segments:
|
73
|
+
- 0
|
74
|
+
version: "0"
|
75
|
+
type: :runtime
|
76
|
+
version_requirements: *id004
|
77
|
+
- !ruby/object:Gem::Dependency
|
78
|
+
name: rdiscount
|
79
|
+
prerelease: false
|
80
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ">="
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
hash: 3
|
86
|
+
segments:
|
87
|
+
- 0
|
88
|
+
version: "0"
|
89
|
+
type: :development
|
90
|
+
version_requirements: *id005
|
91
|
+
description: " Crocoduck is a Resque job system that seeks to model the pattern of mutating MongoDB documents.\n"
|
92
|
+
email: me@clintecker.com
|
93
|
+
executables: []
|
94
|
+
|
95
|
+
extensions: []
|
96
|
+
|
97
|
+
extra_rdoc_files: []
|
98
|
+
|
99
|
+
files:
|
100
|
+
- lib/crocoduck/entry.rb
|
101
|
+
- lib/crocoduck/job.rb
|
102
|
+
- lib/crocoduck/logging.rb
|
103
|
+
- lib/crocoduck/redis.rb
|
104
|
+
- lib/crocoduck/resque.rb
|
105
|
+
- lib/crocoduck/server.rb
|
106
|
+
- lib/crocoduck/store.rb
|
107
|
+
has_rdoc: true
|
108
|
+
homepage: https://github.com/clintecker/crocoduck
|
109
|
+
licenses: []
|
110
|
+
|
111
|
+
post_install_message:
|
112
|
+
rdoc_options: []
|
113
|
+
|
114
|
+
require_paths:
|
115
|
+
- lib
|
116
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
117
|
+
none: false
|
118
|
+
requirements:
|
119
|
+
- - ">="
|
120
|
+
- !ruby/object:Gem::Version
|
121
|
+
hash: 3
|
122
|
+
segments:
|
123
|
+
- 0
|
124
|
+
version: "0"
|
125
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
126
|
+
none: false
|
127
|
+
requirements:
|
128
|
+
- - ">="
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
hash: 3
|
131
|
+
segments:
|
132
|
+
- 0
|
133
|
+
version: "0"
|
134
|
+
requirements: []
|
135
|
+
|
136
|
+
rubyforge_project:
|
137
|
+
rubygems_version: 1.4.1
|
138
|
+
signing_key:
|
139
|
+
specification_version: 3
|
140
|
+
summary: Resque Jobs working on MongoDB documents
|
141
|
+
test_files: []
|
142
|
+
|