wukong 1.4.12 → 1.5.0
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/CHANGELOG.textile +20 -1
- data/bin/bootstrap.sh +32 -0
- data/bin/hdp-sort +3 -0
- data/bin/hdp-stream +3 -0
- data/docpages/README-elastic_map_reduce.textile +377 -0
- data/docpages/avro/avro_notes.textile +56 -0
- data/docpages/avro/tethering.textile +19 -0
- data/docpages/pig/commandline_params.txt +26 -0
- data/examples/emr/elastic_mapreduce_example.rb +35 -0
- data/lib/wukong/logger.rb +8 -1
- data/lib/wukong/script/avro_command.rb +5 -0
- data/lib/wukong/script/emr_command.rb +119 -0
- data/lib/wukong/script/hadoop_command.rb +72 -90
- data/lib/wukong/script/local_command.rb +18 -8
- data/lib/wukong/script.rb +87 -92
- data/wukong.gemspec +27 -18
- metadata +30 -21
data/wukong.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{wukong}
|
8
|
-
s.version = "1.
|
8
|
+
s.version = "1.5.0"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["Philip (flip) Kromer"]
|
12
|
-
s.date = %q{2010-08-
|
12
|
+
s.date = %q{2010-08-10}
|
13
13
|
s.description = %q{ Treat your dataset like a:
|
14
14
|
|
15
15
|
* stream of lines when it's efficient to process by lines
|
@@ -30,6 +30,7 @@ Gem::Specification.new do |s|
|
|
30
30
|
"LICENSE.textile",
|
31
31
|
"README.textile",
|
32
32
|
"TODO.textile",
|
33
|
+
"bin/bootstrap.sh",
|
33
34
|
"bin/cutc",
|
34
35
|
"bin/cuttab",
|
35
36
|
"bin/greptrue",
|
@@ -65,12 +66,15 @@ Gem::Specification.new do |s|
|
|
65
66
|
"bin/wu-sum",
|
66
67
|
"docpages/INSTALL.textile",
|
67
68
|
"docpages/LICENSE.textile",
|
69
|
+
"docpages/README-elastic_map_reduce.textile",
|
68
70
|
"docpages/README-performance.textile",
|
69
71
|
"docpages/README-wulign.textile",
|
70
72
|
"docpages/UsingWukong-part1-get_ready.textile",
|
71
73
|
"docpages/UsingWukong-part2-ThinkingBigData.textile",
|
72
74
|
"docpages/UsingWukong-part3-parsing.textile",
|
73
75
|
"docpages/_config.yml",
|
76
|
+
"docpages/avro/avro_notes.textile",
|
77
|
+
"docpages/avro/tethering.textile",
|
74
78
|
"docpages/bigdata-tips.textile",
|
75
79
|
"docpages/code/api_response_example.txt",
|
76
80
|
"docpages/code/parser_skeleton.rb",
|
@@ -84,6 +88,7 @@ Gem::Specification.new do |s|
|
|
84
88
|
"docpages/news.html",
|
85
89
|
"docpages/pig/PigLatinExpressionsList.txt",
|
86
90
|
"docpages/pig/PigLatinReferenceManual.txt",
|
91
|
+
"docpages/pig/commandline_params.txt",
|
87
92
|
"docpages/pig/cookbook.html",
|
88
93
|
"docpages/pig/images/hadoop-logo.jpg",
|
89
94
|
"docpages/pig/images/instruction_arrow.png",
|
@@ -132,6 +137,7 @@ Gem::Specification.new do |s|
|
|
132
137
|
"examples/corpus/words_to_bigrams.rb",
|
133
138
|
"examples/count_keys.rb",
|
134
139
|
"examples/count_keys_at_mapper.rb",
|
140
|
+
"examples/emr/elastic_mapreduce_example.rb",
|
135
141
|
"examples/keystore/cassandra_batch_test.rb",
|
136
142
|
"examples/keystore/conditional_outputter_example.rb",
|
137
143
|
"examples/network_graph/adjacency_list.rb",
|
@@ -193,6 +199,8 @@ Gem::Specification.new do |s|
|
|
193
199
|
"lib/wukong/rdf.rb",
|
194
200
|
"lib/wukong/schema.rb",
|
195
201
|
"lib/wukong/script.rb",
|
202
|
+
"lib/wukong/script/avro_command.rb",
|
203
|
+
"lib/wukong/script/emr_command.rb",
|
196
204
|
"lib/wukong/script/hadoop_command.rb",
|
197
205
|
"lib/wukong/script/local_command.rb",
|
198
206
|
"lib/wukong/store.rb",
|
@@ -245,31 +253,32 @@ Gem::Specification.new do |s|
|
|
245
253
|
"spec/spec_helper.rb",
|
246
254
|
"spec/wukong/encoding_spec.rb",
|
247
255
|
"spec/wukong/script_spec.rb",
|
256
|
+
"examples/binning_percentile_estimator.rb",
|
257
|
+
"examples/contrib/jeans/normalize.rb",
|
258
|
+
"examples/contrib/jeans/sizes.rb",
|
259
|
+
"examples/corpus/words_to_bigrams.rb",
|
260
|
+
"examples/count_keys.rb",
|
261
|
+
"examples/count_keys_at_mapper.rb",
|
262
|
+
"examples/emr/elastic_mapreduce_example.rb",
|
263
|
+
"examples/keystore/cassandra_batch_test.rb",
|
264
|
+
"examples/keystore/conditional_outputter_example.rb",
|
265
|
+
"examples/network_graph/adjacency_list.rb",
|
266
|
+
"examples/network_graph/breadth_first_search.rb",
|
267
|
+
"examples/network_graph/gen_2paths.rb",
|
268
|
+
"examples/network_graph/gen_multi_edge.rb",
|
269
|
+
"examples/network_graph/gen_symmetric_links.rb",
|
248
270
|
"examples/pagerank/pagerank.rb",
|
249
271
|
"examples/pagerank/pagerank_initialize.rb",
|
272
|
+
"examples/rank_and_bin.rb",
|
250
273
|
"examples/sample_records.rb",
|
251
274
|
"examples/server_logs/apache_log_parser.rb",
|
252
275
|
"examples/server_logs/breadcrumbs.rb",
|
253
276
|
"examples/server_logs/user_agent.rb",
|
254
|
-
"examples/corpus/words_to_bigrams.rb",
|
255
|
-
"examples/count_keys.rb",
|
256
|
-
"examples/rank_and_bin.rb",
|
257
|
-
"examples/binning_percentile_estimator.rb",
|
258
277
|
"examples/size.rb",
|
259
|
-
"examples/store/chunked_store_example.rb",
|
260
|
-
"examples/network_graph/breadth_first_search.rb",
|
261
|
-
"examples/network_graph/gen_symmetric_links.rb",
|
262
|
-
"examples/network_graph/gen_multi_edge.rb",
|
263
|
-
"examples/network_graph/adjacency_list.rb",
|
264
|
-
"examples/network_graph/gen_2paths.rb",
|
265
|
-
"examples/keystore/cassandra_batch_test.rb",
|
266
|
-
"examples/keystore/conditional_outputter_example.rb",
|
267
278
|
"examples/stats/avg_value_frequency.rb",
|
268
|
-
"examples/
|
269
|
-
"examples/contrib/jeans/normalize.rb",
|
270
|
-
"examples/word_count.rb",
|
279
|
+
"examples/store/chunked_store_example.rb",
|
271
280
|
"examples/stupidly_simple_filter.rb",
|
272
|
-
"examples/
|
281
|
+
"examples/word_count.rb"
|
273
282
|
]
|
274
283
|
|
275
284
|
if s.respond_to? :specification_version then
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wukong
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 3
|
5
5
|
prerelease: false
|
6
6
|
segments:
|
7
7
|
- 1
|
8
|
-
-
|
9
|
-
-
|
10
|
-
version: 1.
|
8
|
+
- 5
|
9
|
+
- 0
|
10
|
+
version: 1.5.0
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Philip (flip) Kromer
|
@@ -15,7 +15,7 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2010-08-
|
18
|
+
date: 2010-08-10 00:00:00 -05:00
|
19
19
|
default_executable:
|
20
20
|
dependencies:
|
21
21
|
- !ruby/object:Gem::Dependency
|
@@ -124,6 +124,7 @@ files:
|
|
124
124
|
- LICENSE.textile
|
125
125
|
- README.textile
|
126
126
|
- TODO.textile
|
127
|
+
- bin/bootstrap.sh
|
127
128
|
- bin/cutc
|
128
129
|
- bin/cuttab
|
129
130
|
- bin/greptrue
|
@@ -159,12 +160,15 @@ files:
|
|
159
160
|
- bin/wu-sum
|
160
161
|
- docpages/INSTALL.textile
|
161
162
|
- docpages/LICENSE.textile
|
163
|
+
- docpages/README-elastic_map_reduce.textile
|
162
164
|
- docpages/README-performance.textile
|
163
165
|
- docpages/README-wulign.textile
|
164
166
|
- docpages/UsingWukong-part1-get_ready.textile
|
165
167
|
- docpages/UsingWukong-part2-ThinkingBigData.textile
|
166
168
|
- docpages/UsingWukong-part3-parsing.textile
|
167
169
|
- docpages/_config.yml
|
170
|
+
- docpages/avro/avro_notes.textile
|
171
|
+
- docpages/avro/tethering.textile
|
168
172
|
- docpages/bigdata-tips.textile
|
169
173
|
- docpages/code/api_response_example.txt
|
170
174
|
- docpages/code/parser_skeleton.rb
|
@@ -178,6 +182,7 @@ files:
|
|
178
182
|
- docpages/news.html
|
179
183
|
- docpages/pig/PigLatinExpressionsList.txt
|
180
184
|
- docpages/pig/PigLatinReferenceManual.txt
|
185
|
+
- docpages/pig/commandline_params.txt
|
181
186
|
- docpages/pig/cookbook.html
|
182
187
|
- docpages/pig/images/hadoop-logo.jpg
|
183
188
|
- docpages/pig/images/instruction_arrow.png
|
@@ -226,6 +231,7 @@ files:
|
|
226
231
|
- examples/corpus/words_to_bigrams.rb
|
227
232
|
- examples/count_keys.rb
|
228
233
|
- examples/count_keys_at_mapper.rb
|
234
|
+
- examples/emr/elastic_mapreduce_example.rb
|
229
235
|
- examples/keystore/cassandra_batch_test.rb
|
230
236
|
- examples/keystore/conditional_outputter_example.rb
|
231
237
|
- examples/network_graph/adjacency_list.rb
|
@@ -287,6 +293,8 @@ files:
|
|
287
293
|
- lib/wukong/rdf.rb
|
288
294
|
- lib/wukong/schema.rb
|
289
295
|
- lib/wukong/script.rb
|
296
|
+
- lib/wukong/script/avro_command.rb
|
297
|
+
- lib/wukong/script/emr_command.rb
|
290
298
|
- lib/wukong/script/hadoop_command.rb
|
291
299
|
- lib/wukong/script/local_command.rb
|
292
300
|
- lib/wukong/store.rb
|
@@ -367,28 +375,29 @@ test_files:
|
|
367
375
|
- spec/spec_helper.rb
|
368
376
|
- spec/wukong/encoding_spec.rb
|
369
377
|
- spec/wukong/script_spec.rb
|
378
|
+
- examples/binning_percentile_estimator.rb
|
379
|
+
- examples/contrib/jeans/normalize.rb
|
380
|
+
- examples/contrib/jeans/sizes.rb
|
381
|
+
- examples/corpus/words_to_bigrams.rb
|
382
|
+
- examples/count_keys.rb
|
383
|
+
- examples/count_keys_at_mapper.rb
|
384
|
+
- examples/emr/elastic_mapreduce_example.rb
|
385
|
+
- examples/keystore/cassandra_batch_test.rb
|
386
|
+
- examples/keystore/conditional_outputter_example.rb
|
387
|
+
- examples/network_graph/adjacency_list.rb
|
388
|
+
- examples/network_graph/breadth_first_search.rb
|
389
|
+
- examples/network_graph/gen_2paths.rb
|
390
|
+
- examples/network_graph/gen_multi_edge.rb
|
391
|
+
- examples/network_graph/gen_symmetric_links.rb
|
370
392
|
- examples/pagerank/pagerank.rb
|
371
393
|
- examples/pagerank/pagerank_initialize.rb
|
394
|
+
- examples/rank_and_bin.rb
|
372
395
|
- examples/sample_records.rb
|
373
396
|
- examples/server_logs/apache_log_parser.rb
|
374
397
|
- examples/server_logs/breadcrumbs.rb
|
375
398
|
- examples/server_logs/user_agent.rb
|
376
|
-
- examples/corpus/words_to_bigrams.rb
|
377
|
-
- examples/count_keys.rb
|
378
|
-
- examples/rank_and_bin.rb
|
379
|
-
- examples/binning_percentile_estimator.rb
|
380
399
|
- examples/size.rb
|
381
|
-
- examples/store/chunked_store_example.rb
|
382
|
-
- examples/network_graph/breadth_first_search.rb
|
383
|
-
- examples/network_graph/gen_symmetric_links.rb
|
384
|
-
- examples/network_graph/gen_multi_edge.rb
|
385
|
-
- examples/network_graph/adjacency_list.rb
|
386
|
-
- examples/network_graph/gen_2paths.rb
|
387
|
-
- examples/keystore/cassandra_batch_test.rb
|
388
|
-
- examples/keystore/conditional_outputter_example.rb
|
389
400
|
- examples/stats/avg_value_frequency.rb
|
390
|
-
- examples/
|
391
|
-
- examples/contrib/jeans/normalize.rb
|
392
|
-
- examples/word_count.rb
|
401
|
+
- examples/store/chunked_store_example.rb
|
393
402
|
- examples/stupidly_simple_filter.rb
|
394
|
-
- examples/
|
403
|
+
- examples/word_count.rb
|