wukong 2.0.2 → 3.0.0.pre
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +46 -0
- data/.gitmodules +3 -0
- data/.rspec +2 -0
- data/.travis.yml +12 -0
- data/.yardopts +19 -0
- data/CHANGELOG.md +7 -0
- data/Gemfile +3 -0
- data/Guardfile +14 -0
- data/NOTES-travis.md +31 -0
- data/README.md +422 -0
- data/Rakefile +12 -0
- data/TODO.md +99 -0
- data/VERSION +1 -0
- data/bin/hdp-cp +0 -0
- data/bin/wu-flow +10 -0
- data/bin/wu-map +17 -0
- data/bin/wu-red +17 -0
- data/bin/wukong +17 -0
- data/data/CREDITS.md +355 -0
- data/data/graph/airfares.tsv +2174 -0
- data/data/text/gift_of_the_magi.txt +225 -0
- data/data/text/jabberwocky.txt +36 -0
- data/data/text/rectification_of_names.txt +33 -0
- data/{spec/data → data/twitter}/a_atsigns_b.tsv +0 -0
- data/{spec/data → data/twitter}/a_follows_b.tsv +0 -0
- data/{spec/data → data/twitter}/tweet.tsv +0 -0
- data/{spec/data → data/twitter}/twitter_user.tsv +0 -0
- data/data/wikipedia/dbpedia-sentences.tsv +1000 -0
- data/examples/dataflow.rb +28 -0
- data/examples/{server_logs/logline.rb → dataflow/apache_log_line.rb} +28 -18
- data/examples/dataflow/complex.rb +11 -0
- data/examples/dataflow/donuts.rb +13 -0
- data/examples/dataflow/parse_apache_logs.rb +16 -0
- data/examples/dataflow/pig_latinizer.rb +16 -0
- data/examples/dataflow/simple.rb +12 -0
- data/examples/dataflow/telegram.rb +45 -0
- data/examples/examples_helper.rb +9 -0
- data/examples/graph/minimum_spanning_tree.rb +73 -0
- data/examples/graph/union_find.rb +62 -0
- data/examples/text/latinize_text.rb +0 -0
- data/examples/text/pig_latin.rb +35 -0
- data/examples/tiny_count.rb +8 -0
- data/examples/tiny_count/jabberwocky_output.tsv +92 -0
- data/examples/twitter/locations.rb +29 -0
- data/examples/twitter/models.rb +24 -0
- data/examples/twitter/pt1-fiddle.pig +8 -0
- data/examples/twitter/pt2-simple_parse.pig +31 -0
- data/examples/twitter/pt2-simple_parse.rb +18 -0
- data/examples/twitter/pt3-join_on_zips.pig +39 -0
- data/examples/twitter/pt4-strong_links.rb +20 -0
- data/examples/twitter/pt5-lnglat_and_strong_links.pig +16 -0
- data/examples/twitter/states.tsv +50 -0
- data/examples/word_count.rb +36 -63
- data/examples/workflow/cherry_pie.md +104 -0
- data/examples/workflow/cherry_pie.rb +66 -0
- data/examples/workflow/fiddle.rb +24 -0
- data/examples/workflow/package_gem.rb +55 -0
- data/lib/{wukong/encoding.rb → away/escapement.rb} +0 -0
- data/lib/away/exe.rb +11 -0
- data/lib/away/experimental.rb +5 -0
- data/lib/away/from_file.rb +52 -0
- data/lib/away/job.rb +56 -0
- data/lib/away/job/rake_compat.rb +17 -0
- data/lib/away/registry.rb +79 -0
- data/lib/away/runner.rb +276 -0
- data/lib/away/runner/execute.rb +121 -0
- data/lib/away/script.rb +161 -0
- data/lib/away/script/hadoop_command.rb +240 -0
- data/lib/away/source/file_list_source.rb +15 -0
- data/lib/away/source/looper.rb +18 -0
- data/lib/away/task.rb +219 -0
- data/lib/hanuman.rb +9 -0
- data/lib/hanuman/action.rb +21 -0
- data/lib/hanuman/chain.rb +4 -0
- data/lib/hanuman/graph.rb +51 -0
- data/lib/hanuman/graphviz.rb +74 -0
- data/lib/hanuman/graphvizzer.rb +185 -0
- data/lib/hanuman/resource.rb +6 -0
- data/lib/hanuman/slot.rb +87 -0
- data/lib/hanuman/slottable.rb +220 -0
- data/lib/hanuman/stage.rb +51 -0
- data/lib/wukong.rb +31 -17
- data/lib/wukong/bad_record.rb +13 -16
- data/lib/wukong/dataflow.rb +103 -0
- data/lib/wukong/event.rb +44 -0
- data/lib/wukong/local_runner.rb +55 -0
- data/lib/wukong/mapred.rb +3 -0
- data/lib/wukong/model/faker.rb +136 -0
- data/lib/wukong/processor.rb +142 -0
- data/lib/wukong/settings.rb +0 -0
- data/lib/wukong/universe.rb +48 -0
- data/lib/wukong/version.rb +3 -0
- data/lib/wukong/widget/filter.rb +81 -0
- data/lib/wukong/widget/gibberish.rb +123 -0
- data/lib/wukong/widget/monitor.rb +26 -0
- data/lib/wukong/widget/reducer.rb +66 -0
- data/lib/wukong/widget/sink.rb +58 -0
- data/lib/wukong/widget/source.rb +120 -0
- data/lib/wukong/widget/stringifier.rb +50 -0
- data/lib/wukong/workflow.rb +22 -0
- data/lib/wukong/workflow/command.rb +42 -0
- data/old/config/emr-example.yaml +48 -0
- data/{examples → old/examples}/README.txt +0 -0
- data/{examples → old/examples}/contrib/jeans/README.markdown +0 -0
- data/{examples → old/examples}/contrib/jeans/data/normalized_sizes +0 -0
- data/{examples → old/examples}/contrib/jeans/data/orders.tsv +0 -0
- data/{examples → old/examples}/contrib/jeans/data/sizes +0 -0
- data/{examples → old/examples}/contrib/jeans/normalize.rb +0 -0
- data/{examples → old/examples}/contrib/jeans/sizes.rb +0 -0
- data/old/examples/corpus/bnc_word_freq.rb +44 -0
- data/{examples → old/examples}/corpus/bucket_counter.rb +0 -0
- data/{examples → old/examples}/corpus/dbpedia_abstract_to_sentences.rb +0 -0
- data/{examples → old/examples}/corpus/sentence_bigrams.rb +0 -0
- data/{examples → old/examples}/corpus/sentence_coocurrence.rb +0 -0
- data/old/examples/corpus/stopwords.rb +138 -0
- data/{examples → old/examples}/corpus/words_to_bigrams.rb +0 -0
- data/{examples → old/examples}/emr/README.textile +0 -0
- data/{examples → old/examples}/emr/dot_wukong_dir/credentials.json +0 -0
- data/{examples → old/examples}/emr/dot_wukong_dir/emr.yaml +0 -0
- data/{examples → old/examples}/emr/dot_wukong_dir/emr_bootstrap.sh +0 -0
- data/{examples → old/examples}/emr/elastic_mapreduce_example.rb +0 -0
- data/{examples → old/examples}/network_graph/adjacency_list.rb +0 -0
- data/{examples → old/examples}/network_graph/breadth_first_search.rb +0 -0
- data/{examples → old/examples}/network_graph/gen_2paths.rb +0 -0
- data/{examples → old/examples}/network_graph/gen_multi_edge.rb +0 -0
- data/{examples → old/examples}/network_graph/gen_symmetric_links.rb +0 -0
- data/{examples → old/examples}/pagerank/README.textile +0 -0
- data/{examples → old/examples}/pagerank/gen_initial_pagerank_graph.pig +0 -0
- data/{examples → old/examples}/pagerank/pagerank.rb +0 -0
- data/{examples → old/examples}/pagerank/pagerank_initialize.rb +0 -0
- data/{examples → old/examples}/pagerank/run_pagerank.sh +0 -0
- data/{examples → old/examples}/sample_records.rb +0 -0
- data/{examples → old/examples}/server_logs/apache_log_parser.rb +0 -4
- data/{examples → old/examples}/server_logs/breadcrumbs.rb +0 -0
- data/{examples → old/examples}/server_logs/nook.rb +0 -0
- data/{examples → old/examples}/server_logs/nook/faraday_dummy_adapter.rb +0 -0
- data/{examples → old/examples}/server_logs/user_agent.rb +0 -0
- data/{examples → old/examples}/simple_word_count.rb +0 -0
- data/{examples → old/examples}/size.rb +0 -0
- data/{examples → old/examples}/stats/avg_value_frequency.rb +0 -0
- data/{examples → old/examples}/stats/binning_percentile_estimator.rb +0 -0
- data/{examples → old/examples}/stats/data/avg_value_frequency.tsv +0 -0
- data/{examples → old/examples}/stats/rank_and_bin.rb +0 -0
- data/{examples → old/examples}/stupidly_simple_filter.rb +0 -0
- data/old/examples/word_count.rb +75 -0
- data/old/graph/graphviz_builder.rb +580 -0
- data/old/graph_easy/Attributes.pm +4181 -0
- data/old/graph_easy/Graphviz.pm +2232 -0
- data/old/wukong.rb +18 -0
- data/{lib → old}/wukong/and_pig.rb +0 -0
- data/old/wukong/bad_record.rb +18 -0
- data/{lib → old}/wukong/datatypes.rb +0 -0
- data/{lib → old}/wukong/datatypes/enum.rb +0 -0
- data/{lib → old}/wukong/datatypes/fake_types.rb +0 -0
- data/{lib → old}/wukong/decorator.rb +0 -0
- data/{lib → old}/wukong/encoding/asciize.rb +0 -0
- data/{lib → old}/wukong/extensions.rb +0 -0
- data/{lib → old}/wukong/extensions/array.rb +0 -0
- data/{lib → old}/wukong/extensions/blank.rb +0 -0
- data/{lib → old}/wukong/extensions/class.rb +0 -0
- data/{lib → old}/wukong/extensions/date_time.rb +0 -0
- data/{lib → old}/wukong/extensions/emittable.rb +0 -0
- data/{lib → old}/wukong/extensions/enumerable.rb +0 -0
- data/{lib → old}/wukong/extensions/hash.rb +0 -0
- data/{lib → old}/wukong/extensions/hash_keys.rb +0 -0
- data/{lib → old}/wukong/extensions/hash_like.rb +0 -0
- data/{lib → old}/wukong/extensions/hashlike_class.rb +0 -0
- data/{lib → old}/wukong/extensions/module.rb +0 -0
- data/{lib → old}/wukong/extensions/pathname.rb +0 -0
- data/{lib → old}/wukong/extensions/string.rb +0 -0
- data/{lib → old}/wukong/extensions/struct.rb +0 -0
- data/{lib → old}/wukong/extensions/symbol.rb +0 -0
- data/{lib → old}/wukong/filename_pattern.rb +0 -0
- data/old/wukong/helper.rb +7 -0
- data/old/wukong/helper/stopwords.rb +195 -0
- data/old/wukong/helper/tokenize.rb +35 -0
- data/{lib → old}/wukong/logger.rb +0 -0
- data/{lib → old}/wukong/periodic_monitor.rb +0 -0
- data/{lib → old}/wukong/schema.rb +0 -0
- data/{lib → old}/wukong/script.rb +0 -0
- data/{lib → old}/wukong/script/avro_command.rb +0 -0
- data/{lib → old}/wukong/script/cassandra_loader_script.rb +0 -0
- data/{lib → old}/wukong/script/emr_command.rb +0 -0
- data/{lib → old}/wukong/script/hadoop_command.rb +0 -0
- data/{lib → old}/wukong/script/local_command.rb +4 -1
- data/{lib → old}/wukong/store.rb +0 -0
- data/{lib → old}/wukong/store/base.rb +0 -0
- data/{lib → old}/wukong/store/cassandra.rb +0 -0
- data/{lib → old}/wukong/store/cassandra/streaming.rb +0 -0
- data/{lib → old}/wukong/store/cassandra/struct_loader.rb +0 -0
- data/{lib → old}/wukong/store/cassandra_model.rb +0 -0
- data/{lib → old}/wukong/store/chh_chunked_flat_file_store.rb +0 -0
- data/{lib → old}/wukong/store/chunked_flat_file_store.rb +0 -0
- data/{lib → old}/wukong/store/conditional_store.rb +0 -0
- data/{lib → old}/wukong/store/factory.rb +0 -0
- data/{lib → old}/wukong/store/flat_file_store.rb +0 -0
- data/{lib → old}/wukong/store/key_store.rb +0 -0
- data/{lib → old}/wukong/store/null_store.rb +0 -0
- data/{lib → old}/wukong/store/read_thru_store.rb +0 -0
- data/{lib → old}/wukong/store/tokyo_tdb_key_store.rb +0 -0
- data/{lib → old}/wukong/store/tyrant_rdb_key_store.rb +0 -0
- data/{lib → old}/wukong/store/tyrant_tdb_key_store.rb +0 -0
- data/{lib → old}/wukong/streamer.rb +8 -0
- data/{lib → old}/wukong/streamer/accumulating_reducer.rb +0 -0
- data/{lib → old}/wukong/streamer/base.rb +2 -1
- data/{lib → old}/wukong/streamer/counting_reducer.rb +0 -0
- data/{lib → old}/wukong/streamer/filter.rb +0 -0
- data/old/wukong/streamer/instance_streamer.rb +15 -0
- data/old/wukong/streamer/json_streamer.rb +21 -0
- data/{lib → old}/wukong/streamer/line_streamer.rb +0 -0
- data/{lib → old}/wukong/streamer/list_reducer.rb +0 -0
- data/{lib → old}/wukong/streamer/rank_and_bin_reducer.rb +0 -0
- data/{lib → old}/wukong/streamer/record_streamer.rb +0 -0
- data/{lib → old}/wukong/streamer/reducer.rb +0 -0
- data/{lib → old}/wukong/streamer/set_reducer.rb +0 -0
- data/{lib → old}/wukong/streamer/struct_streamer.rb +0 -0
- data/{lib → old}/wukong/streamer/summing_reducer.rb +0 -0
- data/{lib → old}/wukong/streamer/uniq_by_last_reducer.rb +0 -0
- data/{lib → old}/wukong/typed_struct.rb +0 -0
- data/spec/away/encoding_spec.rb +32 -0
- data/spec/away/exe_spec.rb +20 -0
- data/spec/away/flow_spec.rb +82 -0
- data/spec/away/graph_spec.rb +6 -0
- data/spec/away/job_spec.rb +15 -0
- data/spec/away/rake_compat_spec.rb +9 -0
- data/spec/away/script_spec.rb +81 -0
- data/spec/examples/dataflow/parse_apache_logs_spec.rb +8 -0
- data/spec/examples/dataflow/parsing_spec.rb +13 -0
- data/spec/examples/dataflow/simple_spec.rb +8 -0
- data/spec/examples/dataflow/telegram_spec.rb +43 -0
- data/spec/examples/graph/minimum_spanning_tree_spec.rb +35 -0
- data/spec/examples/text/pig_latin_spec.rb +21 -0
- data/spec/examples/workflow/cherry_pie_spec.rb +6 -0
- data/spec/hanuman/graph_spec.rb +17 -0
- data/spec/hanuman/graphviz_spec.rb +29 -0
- data/spec/hanuman/slot_spec.rb +2 -0
- data/spec/hanuman/stage_spec.rb +12 -0
- data/spec/spec_helper.rb +24 -6
- data/spec/support/examples_helper.rb +10 -0
- data/spec/support/hanuman_test_helpers.rb +90 -0
- data/spec/support/streamer_test_helpers.rb +6 -0
- data/spec/support/wukong_test_helpers.rb +43 -0
- data/spec/support/wukong_widget_helpers.rb +66 -0
- data/spec/wukong/dataflow_spec.rb +65 -0
- data/spec/wukong/local_runner_spec.rb +31 -0
- data/spec/wukong/model/faker_spec.rb +131 -0
- data/spec/wukong/processor_spec.rb +109 -0
- data/spec/wukong/runner_spec.rb +12 -0
- data/spec/wukong/widget/filter_spec.rb +99 -0
- data/spec/wukong/widget/sink_spec.rb +19 -0
- data/spec/wukong/widget/source_spec.rb +41 -0
- data/spec/wukong/widget/stringifier_spec.rb +51 -0
- data/spec/wukong/workflow/command_spec.rb +5 -0
- data/wukong.gemspec +36 -277
- metadata +421 -165
- data/CHANGELOG.textile +0 -106
- data/INSTALL.textile +0 -89
- data/README.textile +0 -274
- data/TODO.textile +0 -11
- data/examples/ignore_me/counting.rb +0 -55
- data/examples/ignore_me/grouper.rb +0 -71
- data/old/cassandra_streaming/berlitz_for_cassandra.textile +0 -22
- data/old/cassandra_streaming/client_interface_notes.textile +0 -200
- data/old/cassandra_streaming/client_schema.textile +0 -318
- data/old/cassandra_streaming/tuning.textile +0 -73
- data/spec/wukong/encoding_spec.rb +0 -36
- data/spec/wukong/script_spec.rb +0 -80
@@ -0,0 +1,121 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
#
|
4
|
+
# Taken from the [Aruba project](). Original license:
|
5
|
+
#
|
6
|
+
# Copyright (c) 2010 Aslak Hellesøy, David Chelimsky
|
7
|
+
#
|
8
|
+
# Permission is hereby granted, free of charge, to any person obtaining
|
9
|
+
# a copy of this software and associated documentation files (the
|
10
|
+
# "Software"), to deal in the Software without restriction, including
|
11
|
+
# without limitation the rights to use, copy, modify, merge, publish,
|
12
|
+
# distribute, sublicense, and/or sell copies of the Software, and to
|
13
|
+
# permit persons to whom the Software is furnished to do so, subject to
|
14
|
+
# the following conditions:
|
15
|
+
#
|
16
|
+
# The above copyright notice and this permission notice shall be
|
17
|
+
# included in all copies or substantial portions of the Software.
|
18
|
+
#
|
19
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
20
|
+
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
21
|
+
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
22
|
+
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
23
|
+
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
24
|
+
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
25
|
+
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
26
|
+
|
27
|
+
|
28
|
+
require 'childprocess'
|
29
|
+
require 'tempfile'
|
30
|
+
|
31
|
+
module Wukong
|
32
|
+
class Runner
|
33
|
+
|
34
|
+
class Process
|
35
|
+
attr_reader :keep_ansi
|
36
|
+
|
37
|
+
def initialize(cmd, exit_timeout=2.0, io_wait=2.0, keep_ansi=true)
|
38
|
+
@exit_timeout = exit_timeout
|
39
|
+
@io_wait = io_wait
|
40
|
+
@keep_ansi = true
|
41
|
+
|
42
|
+
@process = ChildProcess.build(*cmd)
|
43
|
+
@process.io.stdout = raw_out_io
|
44
|
+
@process.io.stderr = raw_err_io
|
45
|
+
@process.duplex = true
|
46
|
+
end
|
47
|
+
|
48
|
+
def raw_out_io
|
49
|
+
@raw_out_io ||= StringIO.new('', 'w')
|
50
|
+
end
|
51
|
+
|
52
|
+
def raw_err_io
|
53
|
+
@raw_err_io ||= StringIO.new('', 'w')
|
54
|
+
end
|
55
|
+
|
56
|
+
def run!(&block)
|
57
|
+
@process.start
|
58
|
+
yield self if block_given?
|
59
|
+
end
|
60
|
+
|
61
|
+
def stdin
|
62
|
+
wait_for_io do
|
63
|
+
@process.io.stdin.sync = true
|
64
|
+
@process.io.stdin
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
def output
|
69
|
+
stdout + stderr
|
70
|
+
end
|
71
|
+
|
72
|
+
def stdout
|
73
|
+
wait_for_io do
|
74
|
+
@raw_out_io.rewind
|
75
|
+
filter_ansi(@raw_out_io.read)
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
def stderr
|
80
|
+
wait_for_io do
|
81
|
+
@raw_err_io.rewind
|
82
|
+
filter_ansi(@raw_err_io.read)
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
def stop(reader)
|
87
|
+
return unless @process
|
88
|
+
unless @process.exited?
|
89
|
+
reader.stdout stdout
|
90
|
+
reader.stderr stderr
|
91
|
+
@process.poll_for_exit(@exit_timeout)
|
92
|
+
end
|
93
|
+
@process.exit_code
|
94
|
+
end
|
95
|
+
|
96
|
+
def terminate
|
97
|
+
if @process
|
98
|
+
flush
|
99
|
+
@process.stop
|
100
|
+
flush
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
def flush
|
105
|
+
stdout && stderr # flush output
|
106
|
+
end
|
107
|
+
|
108
|
+
private
|
109
|
+
|
110
|
+
def wait_for_io(&block)
|
111
|
+
sleep @io_wait if @process.alive?
|
112
|
+
yield
|
113
|
+
end
|
114
|
+
|
115
|
+
def filter_ansi(string)
|
116
|
+
keep_ansi ? string : string.gsub(/\e\[\d+(?>(;\d+)*)m/, '')
|
117
|
+
end
|
118
|
+
|
119
|
+
end
|
120
|
+
end
|
121
|
+
end
|
data/lib/away/script.rb
ADDED
@@ -0,0 +1,161 @@
|
|
1
|
+
require 'wukong'
|
2
|
+
require 'wukong/script/hadoop_command'
|
3
|
+
require 'wukong/experimental'
|
4
|
+
|
5
|
+
#
|
6
|
+
# Runner settings
|
7
|
+
#
|
8
|
+
|
9
|
+
Settings.define :mode, :type => Symbol, :default => :mapper, :env_var => 'WUKONG_MODE', :description => "run the script's workflow: Specify 'hadoop' to use hadoop streaming; 'local' to run your_script.rb --map | sort | your_script.rb --reduce; 'emr' to launch on the amazon cloud; 'mapper' or 'reducer' to run that phase.", :wukong => true
|
10
|
+
Settings.define :dry_run, :description => "echo the command that will be run, but don't run it", :wukong => true
|
11
|
+
Settings.define :rm, :description => "Recursively remove the destination directory. Only used in hadoop mode.", :wukong => true
|
12
|
+
Settings.define :script_file, :type => :filename, :description => "script file to execute, or give as first arg", :wukong => true
|
13
|
+
|
14
|
+
module Wukong
|
15
|
+
# adds ability to execute
|
16
|
+
extend Wukong::Mixin::FromFile
|
17
|
+
|
18
|
+
def self.from_file(filename)
|
19
|
+
filename = filename.to_s
|
20
|
+
filename += ".rb" if filename !~ /\.rb$/
|
21
|
+
super(filename)
|
22
|
+
end
|
23
|
+
|
24
|
+
def self.run(filename=nil)
|
25
|
+
if filename
|
26
|
+
self.from_file(filename)
|
27
|
+
else
|
28
|
+
Settings.resolve!
|
29
|
+
end
|
30
|
+
if @main_run then return false ; end
|
31
|
+
Wukong::Script.new(Settings).run
|
32
|
+
@main_run = true
|
33
|
+
end
|
34
|
+
|
35
|
+
#
|
36
|
+
# sources a script file,
|
37
|
+
#
|
38
|
+
class Script
|
39
|
+
attr_reader :settings # configliere hash of settings
|
40
|
+
attr_reader :script_file # File to execute
|
41
|
+
attr_reader :input_paths
|
42
|
+
attr_reader :output_path
|
43
|
+
|
44
|
+
include Wukong::Script::HadoopCommand
|
45
|
+
|
46
|
+
def initialize(settings)
|
47
|
+
@settings = settings
|
48
|
+
|
49
|
+
@output_path = settings.rest.pop
|
50
|
+
@input_paths = settings.rest.reject(&:blank?)
|
51
|
+
end
|
52
|
+
|
53
|
+
|
54
|
+
# Execute the script file in the context of the Wukong module
|
55
|
+
def run_flow
|
56
|
+
Log.debug( "Running #{script_file} with settings #{settings}")
|
57
|
+
script_file = settings.script_file
|
58
|
+
mode = settings.mode
|
59
|
+
Wukong.flow(mode).run
|
60
|
+
end
|
61
|
+
|
62
|
+
#
|
63
|
+
# In --run mode, use the framework (local, hadoop, emr, etc) to re-launch
|
64
|
+
# the script as mapper, reducer, etc.
|
65
|
+
# If --map or --reduce, dispatch to the mapper or reducer.
|
66
|
+
#
|
67
|
+
def run
|
68
|
+
case settings.mode
|
69
|
+
when :local then execute_local_workflow
|
70
|
+
when :hadoop, :mapred then execute_hadoop_workflow
|
71
|
+
else
|
72
|
+
run_flow
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
#
|
77
|
+
# Shell command for map phase. By default, calls the script in --map mode
|
78
|
+
# In hadoop mode, this is given to the hadoop streaming command.
|
79
|
+
# In local mode, it's given to the system() call
|
80
|
+
#
|
81
|
+
def mapper_commandline
|
82
|
+
"#{ruby_interpreter_path} #{this_script_filename} --mode=mapper " + non_wukong_params
|
83
|
+
end
|
84
|
+
|
85
|
+
#
|
86
|
+
# Shell command for reduce phase. By default, calls the script in --reduce mode
|
87
|
+
# In hadoop mode, this is given to the hadoop streaming command.
|
88
|
+
# In local mode, it's given to the system() call
|
89
|
+
#
|
90
|
+
def reducer_commandline
|
91
|
+
"#{ruby_interpreter_path} #{this_script_filename} --mode=reducer " + non_wukong_params
|
92
|
+
end
|
93
|
+
|
94
|
+
def job_name
|
95
|
+
settings[:job_name] ||
|
96
|
+
"#{File.basename(this_script_filename)}---#{input_paths}---#{output_path}".gsub(%r{[^\w/\.\-\+]+}, '')
|
97
|
+
end
|
98
|
+
|
99
|
+
# Wrapper for dangerous operations to catch errors
|
100
|
+
def safely action, &block
|
101
|
+
begin
|
102
|
+
block.call
|
103
|
+
rescue StandardError => e ; handle_error(action, e); end
|
104
|
+
end
|
105
|
+
|
106
|
+
protected
|
107
|
+
|
108
|
+
#
|
109
|
+
# Execute the runner phase:
|
110
|
+
# use the running framework to relaunch the script in map and in reduce mode
|
111
|
+
#
|
112
|
+
def execute_command! *args
|
113
|
+
command = args.flatten.reject(&:blank?).join(" \\\n ")
|
114
|
+
Log.info "Running\n\n#{command}\n"
|
115
|
+
if settings[:dry_run]
|
116
|
+
Log.info '== [Not running preceding command: dry run] =='
|
117
|
+
else
|
118
|
+
maybe_overwrite_output_paths! output_path
|
119
|
+
$stdout.puts `#{command}`
|
120
|
+
raise "Streaming command failed!" unless $?.success?
|
121
|
+
end
|
122
|
+
end
|
123
|
+
|
124
|
+
#
|
125
|
+
# In hadoop mode only, removes the destination path before launching
|
126
|
+
#
|
127
|
+
# To the panic-stricken: look in .Trash/current/path/to/accidentally_deleted_files
|
128
|
+
#
|
129
|
+
def maybe_overwrite_output_paths! output_path
|
130
|
+
if (settings.rm && (settings.mode == :hadoop))
|
131
|
+
cmd = %Q{#{hadoop_runner} fs -rmr '#{output_path}'}
|
132
|
+
Log.info "Removing output file #{output_path}: #{cmd}"
|
133
|
+
puts `#{cmd}`
|
134
|
+
end
|
135
|
+
end
|
136
|
+
|
137
|
+
# Reassemble all the non-internal-to-wukong settings into a command line for
|
138
|
+
# the map/reducer phase scripts
|
139
|
+
def non_wukong_params
|
140
|
+
settings.
|
141
|
+
reject{|param, val| settings.definition_of(param, :wukong) }.
|
142
|
+
reject{|param, val| param.to_s =~ /catalog_root/ }.
|
143
|
+
map{|param,val| "--#{param}=#{val}" }.
|
144
|
+
join(" ")
|
145
|
+
end
|
146
|
+
|
147
|
+
# the full, real path to the script file
|
148
|
+
def this_script_filename
|
149
|
+
Pathname.new($0).realpath
|
150
|
+
end
|
151
|
+
|
152
|
+
# use the full ruby interpreter path to run slave processes
|
153
|
+
def ruby_interpreter_path
|
154
|
+
Pathname.new(File.join(
|
155
|
+
Config::CONFIG["bindir"],
|
156
|
+
Config::CONFIG["RUBY_INSTALL_NAME"]+Config::CONFIG["EXEEXT"])).realpath
|
157
|
+
end
|
158
|
+
|
159
|
+
|
160
|
+
end
|
161
|
+
end
|
@@ -0,0 +1,240 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
module Wukong
|
3
|
+
class Script
|
4
|
+
module HadoopCommand
|
5
|
+
|
6
|
+
# ===========================================================================
|
7
|
+
#
|
8
|
+
# Hadoop Options
|
9
|
+
#
|
10
|
+
Settings.define :hadoop_home, :default => '/usr/lib/hadoop', :description => "Path to hadoop installation; ENV['HADOOP_HOME'] by default. HADOOP_HOME/bin/hadoop is used to run hadoop.", :env_var => 'HADOOP_HOME', :wukong => true
|
11
|
+
Settings.define :hadoop_runner, :description => "Path to hadoop script. Usually set --hadoop_home instead of this.", :wukong => true
|
12
|
+
|
13
|
+
#
|
14
|
+
# Translate simplified args to their hairy hadoop equivalents
|
15
|
+
#
|
16
|
+
Settings.define :io_sort_mb, :jobconf => true, :description => 'io.sort.mb', :wukong => true
|
17
|
+
Settings.define :io_sort_record_percent, :jobconf => true, :description => 'io.sort.record.percent', :wukong => true
|
18
|
+
Settings.define :job_name, :jobconf => true, :description => 'mapred.job.name', :wukong => true
|
19
|
+
Settings.define :key_field_separator, :jobconf => true, :description => 'map.output.key.field.separator', :wukong => true
|
20
|
+
Settings.define :map_speculative, :jobconf => true, :description => 'mapred.map.tasks.speculative.execution', :wukong => true
|
21
|
+
Settings.define :map_tasks, :jobconf => true, :description => 'mapred.map.tasks', :wukong => true
|
22
|
+
Settings.define :max_maps_per_cluster, :jobconf => true, :description => 'mapred.max.maps.per.cluster', :wukong => true
|
23
|
+
Settings.define :max_maps_per_node, :jobconf => true, :description => 'mapred.max.maps.per.node', :wukong => true
|
24
|
+
Settings.define :max_node_map_tasks, :jobconf => true, :description => 'mapred.tasktracker.map.tasks.maximum', :wukong => true
|
25
|
+
Settings.define :max_node_reduce_tasks, :jobconf => true, :description => 'mapred.tasktracker.reduce.tasks.maximum', :wukong => true
|
26
|
+
Settings.define :max_record_length, :jobconf => true, :description => 'mapred.linerecordreader.maxlength', :wukong => true # "Safeguards against corrupted data: lines longer than this (in bytes) are treated as bad records."
|
27
|
+
Settings.define :max_reduces_per_cluster,:jobconf => true, :description => 'mapred.max.reduces.per.cluster', :wukong => true
|
28
|
+
Settings.define :max_reduces_per_node, :jobconf => true, :description => 'mapred.max.reduces.per.node', :wukong => true
|
29
|
+
Settings.define :max_tracker_failures, :jobconf => true, :description => 'mapred.max.tracker.failures', :wukong => true
|
30
|
+
Settings.define :max_map_attempts, :jobconf => true, :description => 'mapred.map.max.attempts', :wukong => true
|
31
|
+
Settings.define :max_reduce_attempts, :jobconf => true, :description => 'mapred.reduce.max.attempts', :wukong => true
|
32
|
+
Settings.define :min_split_size, :jobconf => true, :description => 'mapred.min.split.size', :wukong => true
|
33
|
+
Settings.define :output_field_separator, :jobconf => true, :description => 'stream.map.output.field.separator', :wukong => true
|
34
|
+
Settings.define :partition_fields, :jobconf => true, :description => 'num.key.fields.for.partition', :wukong => true
|
35
|
+
Settings.define :reduce_tasks, :jobconf => true, :description => 'mapred.reduce.tasks', :wukong => true
|
36
|
+
Settings.define :respect_exit_status, :jobconf => true, :description => 'stream.non.zero.exit.is.failure', :wukong => true
|
37
|
+
Settings.define :reuse_jvms, :jobconf => true, :description => 'mapred.job.reuse.jvm.num.tasks', :wukong => true
|
38
|
+
Settings.define :sort_fields, :jobconf => true, :description => 'stream.num.map.output.key.fields', :wukong => true
|
39
|
+
Settings.define :timeout, :jobconf => true, :description => 'mapred.task.timeout', :wukong => true
|
40
|
+
Settings.define :noempty, :description => "don't create zero-byte reduce files (hadoop mode only)", :wukong => true
|
41
|
+
Settings.define :split_on_xml_tag, :description => "Parse XML document by specifying the tag name: 'anything found between <tag> and </tag> will be treated as one record for map tasks'", :wukong => true
|
42
|
+
|
43
|
+
# emit a -jobconf hadoop option if the simplified command line arg is present
|
44
|
+
# if not, the resulting nil will be elided later
|
45
|
+
def jobconf option
|
46
|
+
if settings[option]
|
47
|
+
# "-jobconf %s=%s" % [settings.definition_of(option, :description), settings[option]]
|
48
|
+
"-D %s=%s" % [settings.definition_of(option, :description), settings[option]]
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
#
|
53
|
+
# Assemble the hadoop command to execute
|
54
|
+
# and launch the hadoop runner to execute the script across all tasktrackers
|
55
|
+
#
|
56
|
+
# FIXME: Should add some simple logic to ensure that commands are in the
|
57
|
+
# right order or hadoop will complain. ie. -D settings MUST come before
|
58
|
+
# others
|
59
|
+
#
|
60
|
+
def execute_hadoop_workflow
|
61
|
+
# Input paths join by ','
|
62
|
+
input_paths = @input_paths.join(',')
|
63
|
+
#
|
64
|
+
# Use Settings[:hadoop_home] to set the path your config install.
|
65
|
+
hadoop_commandline = [
|
66
|
+
hadoop_runner,
|
67
|
+
"jar #{settings[:hadoop_home]}/contrib/streaming/hadoop-*streaming*.jar",
|
68
|
+
hadoop_jobconf_settings,
|
69
|
+
"-D mapred.job.name='#{job_name}'",
|
70
|
+
hadoop_other_args,
|
71
|
+
"-mapper '#{mapper_commandline}'",
|
72
|
+
"-reducer '#{reducer_commandline}'",
|
73
|
+
"-input '#{input_paths}'",
|
74
|
+
"-output '#{output_path}'",
|
75
|
+
"-file '#{this_script_filename}'",
|
76
|
+
hadoop_recycle_env,
|
77
|
+
].flatten.compact.join(" \t\\\n ")
|
78
|
+
Log.info " Launching hadoop!"
|
79
|
+
execute_command!(hadoop_commandline)
|
80
|
+
end
|
81
|
+
|
82
|
+
def hadoop_jobconf_settings
|
83
|
+
jobconf_settings = []
|
84
|
+
# Fixup these settings
|
85
|
+
settings[:reuse_jvms] = '-1' if (settings[:reuse_jvms] == true)
|
86
|
+
settings[:respect_exit_status] = 'false' if (settings[:ignore_exit_status] == true)
|
87
|
+
# If no reducer and no reduce_command, then skip the reduce phase
|
88
|
+
# FIXME: auto-detect nil reducer
|
89
|
+
# settings[:reduce_tasks] = 0 if (! reducer) && (! settings[:reduce_command]) && (! settings[:reduce_tasks])
|
90
|
+
# Fields hadoop should use to distribute records to reducers
|
91
|
+
unless settings[:partition_fields].blank?
|
92
|
+
jobconf_settings += [
|
93
|
+
jobconf(:partition_fields),
|
94
|
+
jobconf(:output_field_separator),
|
95
|
+
]
|
96
|
+
end
|
97
|
+
jobconf_settings += [
|
98
|
+
:io_sort_mb, :io_sort_record_percent,
|
99
|
+
:map_speculative, :map_tasks,
|
100
|
+
:max_maps_per_cluster, :max_maps_per_node,
|
101
|
+
:max_node_map_tasks, :max_node_reduce_tasks,
|
102
|
+
:max_reduces_per_cluster, :max_reduces_per_node,
|
103
|
+
:max_record_length, :min_split_size,
|
104
|
+
:output_field_separator, :key_field_separator,
|
105
|
+
:partition_fields, :sort_fields,
|
106
|
+
:reduce_tasks, :respect_exit_status,
|
107
|
+
:reuse_jvms, :timeout,
|
108
|
+
:max_tracker_failures, :max_map_attempts,
|
109
|
+
:max_reduce_attempts
|
110
|
+
].map{|opt| jobconf(opt)}
|
111
|
+
jobconf_settings.flatten.compact
|
112
|
+
end
|
113
|
+
|
114
|
+
def hadoop_other_args
|
115
|
+
extra_str_args = [ settings[:extra_args] ]
|
116
|
+
if settings.split_on_xml_tag
|
117
|
+
extra_str_args << %Q{-inputreader 'StreamXmlRecordReader,begin=<#{settings.split_on_xml_tag}>,end=</#{settings.split_on_xml_tag}>'}
|
118
|
+
end
|
119
|
+
extra_str_args << ' -lazyOutput' if settings[:noempty] # don't create reduce file if no records
|
120
|
+
extra_str_args << ' -partitioner org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner' unless settings[:partition_fields].blank?
|
121
|
+
extra_str_args
|
122
|
+
end
|
123
|
+
|
124
|
+
def hadoop_recycle_env
|
125
|
+
%w[RUBYLIB].map do |var|
|
126
|
+
%Q{-cmdenv '#{var}=#{ENV[var]}'} if ENV[var]
|
127
|
+
end.compact
|
128
|
+
end
|
129
|
+
|
130
|
+
# The path to the hadoop runner script
|
131
|
+
def hadoop_runner
|
132
|
+
settings[:hadoop_runner] || (settings[:hadoop_home]+'/bin/hadoop')
|
133
|
+
end
|
134
|
+
|
135
|
+
module ClassMethods
|
136
|
+
#
|
137
|
+
# Via @pskomoroch via @tlipcon,
|
138
|
+
#
|
139
|
+
# "there is a little known Hadoop Streaming trick buried in this Python
|
140
|
+
# script. You will notice that the date is not actually in the raw log
|
141
|
+
# data itself, but is part of the filename. It turns out that Hadoop makes
|
142
|
+
# job parameters you would fetch in Java with something like
|
143
|
+
# job.get("mapred.input.file") available as environment variables for
|
144
|
+
# streaming jobs, with periods replaced with underscores:
|
145
|
+
#
|
146
|
+
# filepath = os.environ["map_input_file"]
|
147
|
+
# filename = os.path.split(filepath)[-1]
|
148
|
+
# Thanks to Todd Lipcon for directing me to that hack.
|
149
|
+
#
|
150
|
+
|
151
|
+
# HDFS pathname to the input file currently being processed.
|
152
|
+
def input_file
|
153
|
+
ENV['map_input_file']
|
154
|
+
end
|
155
|
+
|
156
|
+
# Directory of the input file
|
157
|
+
def input_dir
|
158
|
+
ENV['mapred_input_dir']
|
159
|
+
end
|
160
|
+
|
161
|
+
# Offset of this chunk within the input file
|
162
|
+
def map_input_start_offset
|
163
|
+
ENV['map_input_start']
|
164
|
+
end
|
165
|
+
|
166
|
+
# length of the mapper's input chunk
|
167
|
+
def map_input_length
|
168
|
+
ENV['map_input_length']
|
169
|
+
end
|
170
|
+
|
171
|
+
def attempt_id
|
172
|
+
ENV['mapred_task_id']
|
173
|
+
end
|
174
|
+
def curr_task_id
|
175
|
+
ENV['mapred_tip_id']
|
176
|
+
end
|
177
|
+
|
178
|
+
def script_cmdline_urlenc
|
179
|
+
ENV['stream_map_streamprocessor']
|
180
|
+
end
|
181
|
+
end
|
182
|
+
|
183
|
+
# Standard ClassMethods-on-include trick
|
184
|
+
def self.included base
|
185
|
+
base.class_eval do
|
186
|
+
extend ClassMethods
|
187
|
+
end
|
188
|
+
end
|
189
|
+
end
|
190
|
+
end
|
191
|
+
end
|
192
|
+
|
193
|
+
# -partitioner org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner \
|
194
|
+
# -D mapred.output.key.comparator.class=org.apache.hadoop.mapred.lib.KeyFieldBasedComparator \
|
195
|
+
# -D mapred.text.key.comparator.options=-k2,2nr\
|
196
|
+
# -D mapred.text.key.partitioner.options=-k1,2\
|
197
|
+
# -D mapred.text.key.partitioner.options=\"-k1,$partfields\"
|
198
|
+
# -D stream.num.map.output.key.fields=\"$sortfields\"
|
199
|
+
#
|
200
|
+
# -D stream.map.output.field.separator=\"'/t'\"
|
201
|
+
# -D map.output.key.field.separator=. \
|
202
|
+
# -D mapred.data.field.separator=. \
|
203
|
+
# -D map.output.key.value.fields.spec=6,5,1-3:0- \
|
204
|
+
# -D reduce.output.key.value.fields.spec=0-2:5- \
|
205
|
+
|
206
|
+
# "HADOOP_HOME" =>"/usr/lib/hadoop-0.20/bin/..",
|
207
|
+
# "HADOOP_IDENT_STRING" =>"hadoop",
|
208
|
+
# "HADOOP_LOGFILE" =>"hadoop-hadoop-tasktracker-ip-10-242-14-223.log",
|
209
|
+
# "HADOOP_LOG_DIR" =>"/usr/lib/hadoop-0.20/bin/../logs",
|
210
|
+
# "HOME" =>"/var/run/hadoop-0.20",
|
211
|
+
# "JAVA_HOME" =>"/usr/lib/jvm/java-6-sun",
|
212
|
+
# "LD_LIBRARY_PATH" =>"/usr/lib/jvm/java-6-sun-1.6.0.10/jre/lib/i386/client:/usr/lib/jvm/java-6-sun-1.6.0.10/jre/lib/i386:/usr/lib/jvm/java-6-sun-1.6.0.10/jre/../lib/i386:/mnt/hadoop/mapred/local/taskTracker/jobcache/job_200910221152_0023/attempt_200910221152_0023_m_000000_0/work:/usr/lib/jvm/java-6-sun-1.6.0.10/jre/lib/i386/client:/usr/lib/jvm/java-6-sun-1.6.0.10/jre/lib/i386:/usr/lib/jvm/java-6-sun-1.6.0.10/jre/../lib/i386",
|
213
|
+
# "PATH" =>"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games",
|
214
|
+
# "USER" =>"hadoop",
|
215
|
+
#
|
216
|
+
# "dfs_block_size" =>"134217728",
|
217
|
+
# "map_input_start" =>"0",
|
218
|
+
# "map_input_length" =>"125726898",
|
219
|
+
# "mapred_output_key_class" =>"org.apache.hadoop.io.Text",
|
220
|
+
# "mapred_output_value_class" =>"org.apache.hadoop.io.Text",
|
221
|
+
# "mapred_output_format_class" =>"org.apache.hadoop.mapred.TextOutputFormat",
|
222
|
+
# "mapred_output_compression_codec" =>"org.apache.hadoop.io.compress.DefaultCodec",
|
223
|
+
# "mapred_output_compression_type" =>"BLOCK",
|
224
|
+
# "mapred_task_partition" =>"0",
|
225
|
+
# "mapred_tasktracker_map_tasks_maximum" =>"4",
|
226
|
+
# "mapred_tasktracker_reduce_tasks_maximum" =>"2",
|
227
|
+
# "mapred_tip_id" =>"task_200910221152_0023_m_000000",
|
228
|
+
# "mapred_task_id" =>"attempt_200910221152_0023_m_000000_0",
|
229
|
+
# "mapred_job_tracker" =>"ec2-174-129-141-78.compute-1.amazonaws.com:8021",
|
230
|
+
#
|
231
|
+
# "mapred_input_dir" =>"hdfs://ec2-174-129-141-78.compute-1.amazonaws.com/user/flip/ripd/com.tw/com.twitter.search/20090809",
|
232
|
+
# "map_input_file" =>"hdfs://ec2-174-129-141-78.compute-1.amazonaws.com/user/flip/ripd/com.tw/com.twitter.search/20090809/com.twitter.search+20090809233441-56735-womper.tsv.bz2",
|
233
|
+
# "mapred_working_dir" =>"hdfs://ec2-174-129-141-78.compute-1.amazonaws.com/user/flip",
|
234
|
+
# "mapred_work_output_dir" =>"hdfs://ec2-174-129-141-78.compute-1.amazonaws.com/user/flip/tmp/twsearch-20090809/_temporary/_attempt_200910221152_0023_m_000000_0",
|
235
|
+
# "mapred_output_dir" =>"hdfs://ec2-174-129-141-78.compute-1.amazonaws.com/user/flip/tmp/twsearch-20090809",
|
236
|
+
# "mapred_temp_dir" =>"/mnt/tmp/hadoop-hadoop/mapred/temp",
|
237
|
+
# "PWD" =>"/mnt/hadoop/mapred/local/taskTracker/jobcache/job_200910221152_0023/attempt_200910221152_0023_m_000000_0/work",
|
238
|
+
# "TMPDIR" =>"/mnt/hadoop/mapred/local/taskTracker/jobcache/job_200910221152_0023/attempt_200910221152_0023_m_000000_0/work/tmp",
|
239
|
+
# "stream_map_streamprocessor" =>"%2Fusr%2Fbin%2Fruby1.8+%2Fmnt%2Fhome%2Fflip%2Fics%2Fwuclan%2Fexamples%2Ftwitter%2Fparse%2Fparse_twitter_search_requests.rb+--map+--rm",
|
240
|
+
# "user_name" =>"flip",
|