typingpool 0.7.0 → 0.7.1
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +20 -0
- data/README.markdown +452 -0
- data/lib/typingpool/amazon/hit/assignment/empty.rb +19 -0
- data/lib/typingpool/amazon/hit/assignment.rb +43 -0
- data/lib/typingpool/amazon/hit/full/fromsearchhits.rb +44 -0
- data/lib/typingpool/amazon/hit/full.rb +105 -0
- data/lib/typingpool/amazon/hit.rb +458 -0
- data/lib/typingpool/amazon/question.rb +45 -0
- data/lib/typingpool/amazon.rb +3 -677
- data/lib/typingpool/app/cli/formatter.rb +16 -0
- data/lib/typingpool/app/cli.rb +64 -0
- data/lib/typingpool/app/friendlyexceptions.rb +34 -0
- data/lib/typingpool/app.rb +2 -97
- data/lib/typingpool/config/root.rb +114 -0
- data/lib/typingpool/config.rb +13 -119
- data/lib/typingpool/filer/audio.rb +84 -0
- data/lib/typingpool/filer/csv.rb +57 -0
- data/lib/typingpool/filer/dir.rb +76 -0
- data/lib/typingpool/filer/files/audio.rb +63 -0
- data/lib/typingpool/filer/files.rb +55 -0
- data/lib/typingpool/filer.rb +4 -313
- data/lib/typingpool/project/local.rb +117 -0
- data/lib/typingpool/project/remote/s3.rb +135 -0
- data/lib/typingpool/project/remote/sftp.rb +100 -0
- data/lib/typingpool/project/remote.rb +65 -0
- data/lib/typingpool/project.rb +2 -396
- data/lib/typingpool/template/assignment.rb +17 -0
- data/lib/typingpool/template/env.rb +77 -0
- data/lib/typingpool/template.rb +2 -87
- data/lib/typingpool/test/script.rb +310 -0
- data/lib/typingpool/test.rb +1 -306
- data/lib/typingpool/transcript/chunk.rb +129 -0
- data/lib/typingpool/transcript.rb +1 -125
- data/lib/typingpool/utility/castable.rb +65 -0
- data/lib/typingpool/utility.rb +1 -61
- data/test/test_integration_script_6_tp_finish.rb +1 -0
- metadata +135 -81
@@ -0,0 +1,135 @@
|
|
1
|
+
module Typingpool
|
2
|
+
class Project
|
3
|
+
class Remote
|
4
|
+
|
5
|
+
#Subclass for storing remote files on Amazon Simple Storage
|
6
|
+
#Service (S3)
|
7
|
+
class S3 < Remote
|
8
|
+
require 'aws/s3'
|
9
|
+
|
10
|
+
#An Amazon Web Services "Access Key ID." Set from the
|
11
|
+
#Config#amazon value passed to Project::Remote::S3.new, but
|
12
|
+
#changeable.
|
13
|
+
attr_accessor :key
|
14
|
+
|
15
|
+
#An Amazon Web Services "Secret Access Key." Set from the
|
16
|
+
#Config#amazon value passed to Project::Remote::S3.new, but
|
17
|
+
#changeable.
|
18
|
+
attr_accessor :secret
|
19
|
+
|
20
|
+
#The S3 "bucket" where uploads will be stores. Set from the
|
21
|
+
#Config#amazon value passed to Project::Remote::S3.new, but
|
22
|
+
#changeable.
|
23
|
+
attr_accessor :bucket
|
24
|
+
|
25
|
+
#Returns the base URL, which is prepended to the remote
|
26
|
+
#files. This is either the 'url' attribute of the
|
27
|
+
#Config#amazon value passed to Project::Remote::S3.new or, if
|
28
|
+
#that attribute is not set, the value returned by
|
29
|
+
#'default_url' (e.g. "https://bucketname.s3.amazonaws.com").
|
30
|
+
attr_reader :url
|
31
|
+
|
32
|
+
#Constructor. Takes the project name and the result of calling
|
33
|
+
#the 'amazon' method on a Config instance (i.e. the amazon
|
34
|
+
#section of a Config file).
|
35
|
+
def initialize(name, amazon_config)
|
36
|
+
@name = name
|
37
|
+
@config = amazon_config
|
38
|
+
@key = @config.key or raise Error::File::Remote::S3, "Missing Amazon key in config"
|
39
|
+
@secret = @config.secret or raise Error::File::Remote::S3, "Missing Amazon secret in config"
|
40
|
+
@bucket = @config.bucket or raise Error::File::Remote::S3, "Missing Amazon bucket in config"
|
41
|
+
@url = @config.url || default_url
|
42
|
+
end
|
43
|
+
|
44
|
+
#The remote host (server) name, parsed from #url
|
45
|
+
def host
|
46
|
+
URI.parse(@url).host
|
47
|
+
end
|
48
|
+
|
49
|
+
#The remote path (directory), pased from #url
|
50
|
+
def path
|
51
|
+
URI.parse(@url).path
|
52
|
+
end
|
53
|
+
|
54
|
+
#Upload files/strings to S3, optionally changing the names in the process.
|
55
|
+
# ==== Params
|
56
|
+
#[io_streams] Enumerable collection of IO objects, like a File
|
57
|
+
# or StringIO instance.
|
58
|
+
#[as] Optional if the io_streams are File instances. Array of
|
59
|
+
# file basenames, used to name the destination
|
60
|
+
# files. Default is the basename of the Files
|
61
|
+
# passed in as io_streams.
|
62
|
+
# ==== Returns
|
63
|
+
#Array of URLs corresponding to the uploaded files.
|
64
|
+
def put(io_streams, as=io_streams.map{|file| File.basename(file)})
|
65
|
+
batch(io_streams) do |stream, i|
|
66
|
+
dest = as[i]
|
67
|
+
yield(stream, dest) if block_given?
|
68
|
+
begin
|
69
|
+
AWS::S3::S3Object.store(dest, stream, @bucket, :access => :public_read)
|
70
|
+
rescue AWS::S3::NoSuchBucket
|
71
|
+
make_bucket
|
72
|
+
retry
|
73
|
+
end
|
74
|
+
file_to_url(dest)
|
75
|
+
end #batch
|
76
|
+
end
|
77
|
+
|
78
|
+
#Delete objects from S3.
|
79
|
+
# ==== Params
|
80
|
+
#[files] Enumerable collection of file names. Should NOT
|
81
|
+
# include the bucket name (path).
|
82
|
+
# ==== Returns
|
83
|
+
#Array of booleans corresponding to whether the delete call
|
84
|
+
#succeeded.
|
85
|
+
def remove(files)
|
86
|
+
batch(files) do |file, i|
|
87
|
+
yield(file) if block_given?
|
88
|
+
AWS::S3::S3Object.delete(file, @bucket)
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
protected
|
93
|
+
|
94
|
+
def batch(io_streams)
|
95
|
+
results = []
|
96
|
+
io_streams.each_with_index do |stream, i|
|
97
|
+
connect if i == 0
|
98
|
+
begin
|
99
|
+
results.push(yield(stream, i))
|
100
|
+
rescue AWS::S3::S3Exception => e
|
101
|
+
if e.message.match(/AWS::S3::SignatureDoesNotMatch/)
|
102
|
+
raise Error::File::Remote::S3::Credentials, "S3 operation failed with a signature error. This likely means your AWS key or secret is wrong. Error: #{e}"
|
103
|
+
else
|
104
|
+
raise Error::File::Remote::S3, "Your S3 operation failed with an Amazon error: #{e}"
|
105
|
+
end #if
|
106
|
+
end #begin
|
107
|
+
end #files.each
|
108
|
+
disconnect unless io_streams.empty?
|
109
|
+
results
|
110
|
+
end
|
111
|
+
|
112
|
+
def connect
|
113
|
+
AWS::S3::Base.establish_connection!(
|
114
|
+
:access_key_id => @key,
|
115
|
+
:secret_access_key => @secret,
|
116
|
+
:persistent => true,
|
117
|
+
:use_ssl => true
|
118
|
+
)
|
119
|
+
end
|
120
|
+
|
121
|
+
def disconnect
|
122
|
+
AWS::S3::Base.disconnect
|
123
|
+
end
|
124
|
+
|
125
|
+
def make_bucket
|
126
|
+
AWS::S3::Bucket.create(@bucket)
|
127
|
+
end
|
128
|
+
|
129
|
+
def default_url
|
130
|
+
"https://#{@bucket}.s3.amazonaws.com"
|
131
|
+
end
|
132
|
+
end #S3
|
133
|
+
end #Remote
|
134
|
+
end #Project
|
135
|
+
end #Typingpool
|
@@ -0,0 +1,100 @@
|
|
1
|
+
module Typingpool
|
2
|
+
class Project
|
3
|
+
class Remote
|
4
|
+
|
5
|
+
#Subclass for storing remote files on an SFTP server. Only
|
6
|
+
#public/private key authentication has been tested. There is not
|
7
|
+
#yet any provision for password-based authentication, though
|
8
|
+
#adding it should be trivial.
|
9
|
+
class SFTP < Remote
|
10
|
+
require 'net/sftp'
|
11
|
+
|
12
|
+
#Returns the remote host (server) name. This is set from
|
13
|
+
#Config#sftp#host.
|
14
|
+
attr_reader :host
|
15
|
+
|
16
|
+
#Returns the remote path (directory). This is set from
|
17
|
+
#Config#sftp#path.
|
18
|
+
attr_reader :path
|
19
|
+
|
20
|
+
#Returns the name of the user used to log in to the SFTP
|
21
|
+
#server. This is et from Config#sftp#user.
|
22
|
+
attr_reader :user
|
23
|
+
|
24
|
+
#Returns the base URL, which is prepended to the remote
|
25
|
+
#files. This is set from Config#sftp#url.
|
26
|
+
attr_reader :url
|
27
|
+
|
28
|
+
#Constructor. Takes the project name and a Config#sftp.
|
29
|
+
def initialize(name, sftp_config)
|
30
|
+
@name = name
|
31
|
+
@config = sftp_config
|
32
|
+
@user = @config.user or raise Error::File::Remote::SFTP, "No SFTP user specified in config"
|
33
|
+
@host = @config.host or raise Error::File::Remote::SFTP, "No SFTP host specified in config"
|
34
|
+
@url = @config.url or raise Error::File::Remote::SFTP, "No SFTP url specified in config"
|
35
|
+
@path = @config.path || ''
|
36
|
+
end
|
37
|
+
|
38
|
+
#See docs for Project::Remote::S3#put.
|
39
|
+
def put(io_streams, as=io_streams.map{|file| File.basename(file)})
|
40
|
+
begin
|
41
|
+
i = 0
|
42
|
+
batch(io_streams) do |stream, connection|
|
43
|
+
dest = as[i]
|
44
|
+
i += 1
|
45
|
+
yield(stream, dest) if block_given?
|
46
|
+
connection.upload(stream, join_with_path(dest))
|
47
|
+
file_to_url(dest)
|
48
|
+
end
|
49
|
+
rescue Net::SFTP::StatusException => e
|
50
|
+
raise Error::File::Remote::SFTP, "SFTP upload failed: #{e.description}"
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
#See docs for Project::Remote::S3#remove.
|
55
|
+
def remove(files)
|
56
|
+
requests = batch(files) do |file, connection|
|
57
|
+
yield(file) if block_given?
|
58
|
+
connection.remove(join_with_path(file))
|
59
|
+
end
|
60
|
+
failures = requests.reject{|request| request.response.ok?}
|
61
|
+
if not(failures.empty?)
|
62
|
+
summary = failures.map{|request| request.response.to_s}.join('; ')
|
63
|
+
raise Error::File::Remote::SFTP, "SFTP removal failed: #{summary}"
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
protected
|
68
|
+
|
69
|
+
def connection
|
70
|
+
begin
|
71
|
+
Net::SFTP.start(@host, @user) do |connection|
|
72
|
+
yield(connection)
|
73
|
+
connection.loop
|
74
|
+
end
|
75
|
+
rescue Net::SSH::AuthenticationFailed
|
76
|
+
raise Error::File::Remote::SFTP, "SFTP authentication failed: #{$?}"
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
def batch(files)
|
81
|
+
results = []
|
82
|
+
connection do |connection|
|
83
|
+
files.each do |file|
|
84
|
+
results.push(yield(file, connection))
|
85
|
+
end
|
86
|
+
end
|
87
|
+
return results
|
88
|
+
end
|
89
|
+
|
90
|
+
def join_with_path(file)
|
91
|
+
if @path
|
92
|
+
[@path, file].join('/')
|
93
|
+
else
|
94
|
+
file
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end #SFTP
|
98
|
+
end #Remote
|
99
|
+
end #Project
|
100
|
+
end #Typingpool
|
@@ -0,0 +1,65 @@
|
|
1
|
+
module Typingpool
|
2
|
+
class Project
|
3
|
+
#Representation of the Project instance on remote servers. This is
|
4
|
+
#basically a collection of audio files to be transcribed and HTML
|
5
|
+
#files containing instructions and a form for the
|
6
|
+
#transcribers. The backend can be Amazon S3 (the default) or an
|
7
|
+
#SFTP server. Each backend is encapsulated in its own subclass. A
|
8
|
+
#backend subclass must provide a 'put' method, which takes an
|
9
|
+
#array of IO streams and an optional array of remote file
|
10
|
+
#basenames; a 'remove' method, which takes an array of remote file
|
11
|
+
#basenames; and the methods 'host' and 'path', which return the
|
12
|
+
#location of the destination server and destination directory,
|
13
|
+
#respectively.
|
14
|
+
#
|
15
|
+
#Thus, there will always be 'put', 'remove', 'host' and 'path'
|
16
|
+
#methods available, in addition to the Project::Remote methods
|
17
|
+
#outlined below.
|
18
|
+
class Remote
|
19
|
+
require 'typingpool/project/remote/s3'
|
20
|
+
require 'typingpool/project/remote/sftp'
|
21
|
+
|
22
|
+
#The project name
|
23
|
+
attr_accessor :name
|
24
|
+
|
25
|
+
#Constructor. Takes the project name and a Config
|
26
|
+
#instance. Returns a Project::Remote::S3 or
|
27
|
+
#Project::Remote::SFTP instance, depending on the particulars of
|
28
|
+
#the Config. If there are sufficient config params to return
|
29
|
+
#EITHER an S3 or SFTP subclass, it will prefer the SFTP
|
30
|
+
#subclass.
|
31
|
+
def self.from_config(name, config)
|
32
|
+
if config.sftp
|
33
|
+
SFTP.new(name, config.sftp)
|
34
|
+
elsif config.amazon && config.amazon.bucket
|
35
|
+
S3.new(name, config.amazon)
|
36
|
+
else
|
37
|
+
raise Error, "No valid upload params found in config file (SFTP or Amazon info)"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
#Like project.remote.remove, except it takes an array of URLs
|
42
|
+
#instead an array of remote basenames, saving you from having to
|
43
|
+
#manually extract basenames from the URL.
|
44
|
+
def remove_urls(urls)
|
45
|
+
basenames = urls.map{|url| url_basename(url) }
|
46
|
+
remove(basenames){|file| yield(file) if block_given? }
|
47
|
+
end
|
48
|
+
|
49
|
+
#Given a file path, returns the URL to the file path were it to
|
50
|
+
#be uploaded by this instance.
|
51
|
+
def file_to_url(file)
|
52
|
+
"#{@url}/#{URI.escape(file)}"
|
53
|
+
end
|
54
|
+
|
55
|
+
#Given an URL, returns the file portion of the path, given the
|
56
|
+
#configuration of this instance.
|
57
|
+
def url_basename(url)
|
58
|
+
basename = url.split("#{self.url}/")[1] or raise Error, "Could not find base url '#{self.url}' within longer url '#{url}'"
|
59
|
+
URI.unescape(basename)
|
60
|
+
end
|
61
|
+
|
62
|
+
|
63
|
+
end #Remote
|
64
|
+
end #Project
|
65
|
+
end #Typingpool
|