datafile 0.1.1 → 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/datafile.rb +2 -3
- data/lib/datafile/datafile.rb +89 -5
- data/lib/datafile/datasets/dataset.rb +21 -6
- data/lib/datafile/version.rb +1 -1
- data/test/test_builder.rb +2 -0
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 26b6312f588cc22d664d552ca2f01e6e11482f3d
|
4
|
+
data.tar.gz: 3afcbe6af0340685f5358a9f0713a4631a59e5ee
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 78dddc2a46795eb19b25819c9cc95e3d5202b81dcd11851ddbce92ac7efd883815495a6224546baaa53fbefaeb944abbdc686645b16ac3c9464bec7ccb491f5c
|
7
|
+
data.tar.gz: 48ae309c57d5a09b77d81d40e9542473427928c26ffabb28b9e4e7f18af941de1196f0f17a43440d9456a155111ddec61c9dfef7ae1854a3e8cb2c25ecbbc30c
|
data/lib/datafile.rb
CHANGED
data/lib/datafile/datafile.rb
CHANGED
@@ -19,36 +19,120 @@ class Datafile
|
|
19
19
|
def self.load( code )
|
20
20
|
builder = Builder.new
|
21
21
|
builder.instance_eval( code )
|
22
|
-
|
22
|
+
|
23
|
+
# Note: return datafile (of course, NOT the builder)
|
24
|
+
# if you want a builder use Datafile::Builder ;-)
|
25
|
+
builder.datafile
|
23
26
|
end
|
24
27
|
|
25
28
|
|
26
|
-
def initialize
|
29
|
+
def initialize
|
27
30
|
@datasets = []
|
28
31
|
end
|
29
32
|
|
30
33
|
|
31
|
-
def run
|
34
|
+
def run
|
32
35
|
logger.info( "[datafile] begin - run" )
|
33
36
|
download() # step 1 - download zips for datasets
|
34
37
|
read() # step 2 - read in datasets from zips
|
35
38
|
logger.info( "[datafile] end - run" )
|
36
39
|
end
|
37
40
|
|
38
|
-
|
41
|
+
|
42
|
+
|
43
|
+
def download
|
39
44
|
logger.info( "[datafile] dowload" )
|
40
45
|
@datasets.each do |dataset|
|
41
46
|
dataset.download()
|
42
47
|
end
|
43
48
|
end
|
44
49
|
|
45
|
-
def
|
50
|
+
def download_world ## only dl world datasets (skip all others)
|
51
|
+
logger.info( "[datafile] dowload world datasets" )
|
52
|
+
@datasets.each do |dataset|
|
53
|
+
if dataset.kind_of? WorldDataset
|
54
|
+
dataset.download()
|
55
|
+
else
|
56
|
+
# skip all others
|
57
|
+
end
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def download_beer ## only dl beer datasets (skip all others)
|
62
|
+
logger.info( "[datafile] dowload beer datasets" )
|
63
|
+
@datasets.each do |dataset|
|
64
|
+
if dataset.kind_of? BeerDataset
|
65
|
+
dataset.download()
|
66
|
+
else
|
67
|
+
# skip all others
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
def download_football ## only dl football datasets (skip all others)
|
73
|
+
logger.info( "[datafile] dowload football datasets" )
|
74
|
+
@datasets.each do |dataset|
|
75
|
+
if dataset.kind_of? FootballDataset
|
76
|
+
dataset.download()
|
77
|
+
else
|
78
|
+
# skip all others
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
|
86
|
+
def read
|
46
87
|
logger.info( "[datafile] read" )
|
47
88
|
@datasets.each do |dataset|
|
48
89
|
dataset.read()
|
49
90
|
end
|
50
91
|
end
|
51
92
|
|
93
|
+
def read_world
|
94
|
+
logger.info( "[datafile] read world datasets" )
|
95
|
+
@datasets.each do |dataset|
|
96
|
+
if dataset.kind_of? WorldDataset
|
97
|
+
dataset.read()
|
98
|
+
else
|
99
|
+
# skip all others
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
def read_beer
|
105
|
+
logger.info( "[datafile] read beer datasets" )
|
106
|
+
@datasets.each do |dataset|
|
107
|
+
if dataset.kind_of? BeerDataset
|
108
|
+
dataset.read()
|
109
|
+
else
|
110
|
+
# skip all others
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
|
115
|
+
def read_football
|
116
|
+
logger.info( "[datafile] read football datasets" )
|
117
|
+
@datasets.each do |dataset|
|
118
|
+
if dataset.kind_of? FootballDataset
|
119
|
+
dataset.read()
|
120
|
+
else
|
121
|
+
# skip all others
|
122
|
+
end
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
|
127
|
+
def dump
|
128
|
+
## for debugging dump datasets (note: will/might also check if zip exits)
|
129
|
+
logger.info( "[datafile] dump datasets (for debugging)" )
|
130
|
+
@datasets.each do |dataset|
|
131
|
+
dataset.dump()
|
132
|
+
end
|
133
|
+
end
|
134
|
+
|
135
|
+
|
52
136
|
end # class Datafile
|
53
137
|
end # module Datafile
|
54
138
|
|
@@ -10,33 +10,34 @@ class Dataset
|
|
10
10
|
@opts = opts
|
11
11
|
end
|
12
12
|
|
13
|
-
|
13
|
+
|
14
|
+
def setup
|
14
15
|
value = @opts[:setup] || 'all'
|
15
16
|
"setups/#{value}"
|
16
17
|
end
|
17
18
|
|
18
|
-
def remote_zip_url
|
19
|
+
def remote_zip_url # remote zip url
|
19
20
|
### note: use http:// for now - lets us use (personal proxy NOT working w/ https) for now
|
20
21
|
## "https://github.com/#{@name}/archive/master.zip"
|
21
22
|
"http://github.com/#{@name}/archive/master.zip"
|
22
23
|
end
|
23
24
|
|
24
|
-
def local_zip_name
|
25
|
+
def local_zip_name
|
25
26
|
### note: replace / in name w/ --I--
|
26
27
|
## e.g. flatten the filename, that is, do NOT include any folders
|
27
28
|
@name.gsub('/', '--I--') # note: will NOT include/return .zip extension
|
28
29
|
end
|
29
30
|
|
30
|
-
def local_zip_root
|
31
|
+
def local_zip_root
|
31
32
|
"./tmp"
|
32
33
|
end
|
33
34
|
|
34
|
-
def local_zip_path
|
35
|
+
def local_zip_path # local zip path
|
35
36
|
"#{local_zip_root}/#{local_zip_name}.zip"
|
36
37
|
end
|
37
38
|
|
38
39
|
|
39
|
-
def download
|
40
|
+
def download
|
40
41
|
logger.info( "download dataset '#{@name}'" )
|
41
42
|
logger.info( " from '#{remote_zip_url}'" )
|
42
43
|
logger.info( " to '#{local_zip_path}'..." )
|
@@ -44,6 +45,20 @@ class Dataset
|
|
44
45
|
download_blob( remote_zip_url, local_zip_path )
|
45
46
|
end
|
46
47
|
|
48
|
+
|
49
|
+
def dump
|
50
|
+
## for debuggin dump dataset (also check if zip exits)
|
51
|
+
puts "dataset '#{@name}' opts=#{@opts.to_json}" ## use opts.inspect instead of to_json - why? why not?
|
52
|
+
puts " local '#{local_zip_name}' (#{local_zip_path})"
|
53
|
+
if File.exist?( local_zip_path )
|
54
|
+
puts " size: #{File.size(local_zip_path)} bytes"
|
55
|
+
else
|
56
|
+
puts " (file not found)"
|
57
|
+
end
|
58
|
+
puts " remote '#{remote_zip_url}'"
|
59
|
+
end
|
60
|
+
|
61
|
+
|
47
62
|
private
|
48
63
|
####
|
49
64
|
# download tasks for zips
|
data/lib/datafile/version.rb
CHANGED
data/test/test_builder.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: datafile
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Gerald Bauer
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-
|
11
|
+
date: 2014-12-29 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: logutils
|