mobilize-hdfs 1.0.06 → 1.0.07
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +6 -6
- data/lib/mobilize-hdfs/handlers/hdfs.rb +11 -8
- data/lib/mobilize-hdfs/version.rb +1 -1
- data/mobilize-hdfs.gemspec +2 -2
- data/test/hdfs_job_rows.yml +2 -2
- data/test/mobilize-hdfs_test.rb +2 -2
- metadata +5 -5
data/README.md
CHANGED
@@ -228,16 +228,16 @@ same cluster as your first.
|
|
228
228
|
Meta
|
229
229
|
----
|
230
230
|
|
231
|
-
* Code: `git clone git://github.com/
|
232
|
-
* Home: <https://github.com/
|
233
|
-
* Bugs: <https://github.com/
|
231
|
+
* Code: `git clone git://github.com/dena/mobilize-hdfs.git`
|
232
|
+
* Home: <https://github.com/dena/mobilize-hdfs>
|
233
|
+
* Bugs: <https://github.com/dena/mobilize-hdfs/issues>
|
234
234
|
* Gems: <http://rubygems.org/gems/mobilize-hdfs>
|
235
235
|
|
236
236
|
<a name='section_Author'></a>
|
237
237
|
Author
|
238
238
|
------
|
239
239
|
|
240
|
-
Cassio Paes-Leme :: cpaesleme@
|
240
|
+
Cassio Paes-Leme :: cpaesleme@dena.com :: @cpaesleme
|
241
241
|
|
242
|
-
[mobilize-base]: https://github.com/
|
243
|
-
[mobilize-ssh]: https://github.com/
|
242
|
+
[mobilize-base]: https://github.com/dena/mobilize-base
|
243
|
+
[mobilize-ssh]: https://github.com/dena/mobilize-ssh
|
@@ -37,7 +37,7 @@ module Mobilize
|
|
37
37
|
cluster, cluster_path = Hdfs.resolve_path(path)
|
38
38
|
gateway_node = Hadoop.gateway_node(cluster)
|
39
39
|
#need to direct stderr to dev null since hdfs throws errors at being headed off
|
40
|
-
command = "((#{Hadoop.exec_path(cluster)} fs -fs '#{Hdfs.
|
40
|
+
command = "((#{Hadoop.exec_path(cluster)} fs -fs '#{Hdfs.root(cluster)}' -cat '#{cluster_path}'"
|
41
41
|
command += " | head -c #{Hadoop.read_limit}) > out.txt 2> /dev/null) && cat out.txt"
|
42
42
|
response = Ssh.run(gateway_node,command,user)
|
43
43
|
if response.length==Hadoop.read_limit
|
@@ -53,7 +53,8 @@ module Mobilize
|
|
53
53
|
elsif Hadoop.clusters.keys.include?(path.split("/").first)
|
54
54
|
return path.split("/").ie{|p| [p.first,"/#{p[1..-1].join("/")}"]}
|
55
55
|
else
|
56
|
-
|
56
|
+
#default cluster, slash on the front
|
57
|
+
return [Hadoop.output_cluster,"/#{path.to_s}"]
|
57
58
|
end
|
58
59
|
end
|
59
60
|
|
@@ -111,18 +112,21 @@ module Mobilize
|
|
111
112
|
source_path = params['source']
|
112
113
|
target_path = params['target']
|
113
114
|
user = params['user']
|
114
|
-
|
115
|
-
|
116
|
-
if source_cluster.nil?
|
117
|
-
#not hdfs
|
115
|
+
begin
|
116
|
+
#check for source in gsheet format
|
118
117
|
gdrive_slot = Gdrive.slot_worker_by_path(stage_path)
|
119
118
|
#return blank response if there are no slots available
|
120
119
|
return nil unless gdrive_slot
|
121
120
|
source_dst = s.source_dsts(gdrive_slot).first
|
121
|
+
in_string = source_dst.read(user)
|
122
122
|
Gdrive.unslot_worker_by_path(stage_path)
|
123
|
-
|
123
|
+
rescue
|
124
|
+
#try hdfs
|
125
|
+
source_cluster, source_cluster_path = Hdfs.resolve_path(source_path)
|
124
126
|
source_path = "#{source_cluster}#{source_cluster_path}"
|
125
127
|
source_dst = Dataset.find_or_create_by_handler_and_path("hdfs",source_path)
|
128
|
+
in_string = source_dst.read(user)
|
129
|
+
raise "No data found at hdfs://#{source_path}" unless in_string.to_s.length>0
|
126
130
|
end
|
127
131
|
|
128
132
|
#determine cluster for target
|
@@ -137,7 +141,6 @@ module Mobilize
|
|
137
141
|
end
|
138
142
|
|
139
143
|
target_path = "#{target_cluster}#{target_cluster_path}"
|
140
|
-
in_string = source_dst.read(user)
|
141
144
|
out_string = Hdfs.write(target_path,in_string,user)
|
142
145
|
|
143
146
|
out_url = "hdfs://#{Hadoop.output_cluster}#{Hadoop.output_dir}hdfs/#{stage_path}/out"
|
data/mobilize-hdfs.gemspec
CHANGED
@@ -10,11 +10,11 @@ Gem::Specification.new do |gem|
|
|
10
10
|
gem.email = ["cpaesleme@ngmoco.com"]
|
11
11
|
gem.description = %q{Adds hdfs read, write, and copy support to mobilize-ssh}
|
12
12
|
gem.summary = %q{Adds hdfs read, write, and copy support to mobilize-ssh}
|
13
|
-
gem.homepage = "http://github.com/
|
13
|
+
gem.homepage = "http://github.com/dena/mobilize-hdfs"
|
14
14
|
|
15
15
|
gem.files = `git ls-files`.split($/)
|
16
16
|
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
17
|
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
18
|
gem.require_paths = ["lib"]
|
19
|
-
gem.add_runtime_dependency "mobilize-ssh","1.1.
|
19
|
+
gem.add_runtime_dependency "mobilize-ssh","1.1.07"
|
20
20
|
end
|
data/test/hdfs_job_rows.yml
CHANGED
@@ -5,7 +5,7 @@
|
|
5
5
|
stage1: hdfs.write target:"/user/mobilize/test/test_hdfs_1.out",
|
6
6
|
source:"Runner_mobilize(test)/test_hdfs_1.in"
|
7
7
|
stage2: hdfs.copy source:"/user/mobilize/test/test_hdfs_1.out",
|
8
|
-
target:"test_cluster_2/user/mobilize/test/
|
9
|
-
stage3: hdfs.read source:"/user/mobilize/test/test_hdfs_1_copy.out"
|
8
|
+
target:"test_cluster_2/user/mobilize/test/test_hdfs_1_copy.out",
|
9
|
+
stage3: hdfs.read source:"test_cluster_2/user/mobilize/test/test_hdfs_1_copy.out"
|
10
10
|
stage4: gsheet.write source:"hdfs://test_cluster_2/user/mobilize/test/test_hdfs_1_copy.out",
|
11
11
|
target:"Runner_mobilize(test)/test_hdfs_1_copy.out"
|
data/test/mobilize-hdfs_test.rb
CHANGED
@@ -22,7 +22,7 @@ describe "Mobilize" do
|
|
22
22
|
|
23
23
|
puts "add test_source data"
|
24
24
|
hdfs_1_sheet = Mobilize::Gsheet.find_or_create_by_path("#{r.path.split("/")[0..-2].join("/")}/test_hdfs_1.in",gdrive_slot)
|
25
|
-
hdfs_1_tsv = ([
|
25
|
+
hdfs_1_tsv = ([%w{test0 test1 test2 test3 test4 test5 test6 test7 test8 test9}.join("\t")]*10).join("\n")
|
26
26
|
hdfs_1_sheet.write(hdfs_1_tsv,u.name)
|
27
27
|
|
28
28
|
jobs_sheet = r.gsheet(gdrive_slot)
|
@@ -41,7 +41,7 @@ describe "Mobilize" do
|
|
41
41
|
puts "jobtracker posted data to test sheet"
|
42
42
|
test_destination_sheet = Mobilize::Gsheet.find_by_path("#{r.path.split("/")[0..-2].join("/")}/test_hdfs_1_copy.out",gdrive_slot)
|
43
43
|
|
44
|
-
assert test_destination_sheet.
|
44
|
+
assert test_destination_sheet.read(u.name).length == 599
|
45
45
|
end
|
46
46
|
|
47
47
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: mobilize-hdfs
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.07
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-02-
|
12
|
+
date: 2013-02-22 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: mobilize-ssh
|
@@ -18,7 +18,7 @@ dependencies:
|
|
18
18
|
requirements:
|
19
19
|
- - '='
|
20
20
|
- !ruby/object:Gem::Version
|
21
|
-
version: 1.1.
|
21
|
+
version: 1.1.07
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
24
|
version_requirements: !ruby/object:Gem::Requirement
|
@@ -26,7 +26,7 @@ dependencies:
|
|
26
26
|
requirements:
|
27
27
|
- - '='
|
28
28
|
- !ruby/object:Gem::Version
|
29
|
-
version: 1.1.
|
29
|
+
version: 1.1.07
|
30
30
|
description: Adds hdfs read, write, and copy support to mobilize-ssh
|
31
31
|
email:
|
32
32
|
- cpaesleme@ngmoco.com
|
@@ -50,7 +50,7 @@ files:
|
|
50
50
|
- test/mobilize-hdfs_test.rb
|
51
51
|
- test/redis-test.conf
|
52
52
|
- test/test_helper.rb
|
53
|
-
homepage: http://github.com/
|
53
|
+
homepage: http://github.com/dena/mobilize-hdfs
|
54
54
|
licenses: []
|
55
55
|
post_install_message:
|
56
56
|
rdoc_options: []
|