Revision 29471
Added by Eri Katsari over 10 years ago
modules/dnet-openaire-stats-workflow/src/main/resources/eu/dnetlib/iis/core/examples/javamapreduce/stats/oozie_app/workflow.xml | ||
---|---|---|
1 |
<workflow-app name="test-core_examples_javamapreduce_stats" xmlns="uri:oozie:workflow:0.4"> |
|
2 |
<!-- map reduce job that exports hbase data and prepares them for import to the relation database used for statistics generation --> |
|
3 |
|
|
4 |
<global> |
|
5 |
<job-tracker>${jobTracker}</job-tracker> |
|
6 |
<name-node>${nameNode}</name-node> |
|
7 |
<configuration> |
|
8 |
<property> |
|
9 |
<name>mapred.job.queue.name</name> |
|
10 |
<value>${queueName}</value> |
|
11 |
</property> |
|
12 |
<property> |
|
13 |
<name>oozie.sqoop.log.level</name> |
|
14 |
<value>DEBUG</value> |
|
15 |
</property> |
|
16 |
</configuration> |
|
17 |
</global> |
|
18 |
<start to='get-scanner' /> |
|
19 |
<action name='get-scanner'> |
|
20 |
<java> |
|
21 |
<main-class>eu.dnetlib.iis.core.workflows.stats.HbaseScannerGenerator |
|
22 |
</main-class> |
|
23 |
<!-- column families: --> |
|
24 |
|
|
25 |
<arg> |
|
26 |
-f datasource |
|
27 |
<!-- , --> |
|
28 |
<!-- datasourceOrganization_provision_provides , --> |
|
29 |
<!-- organization, --> |
|
30 |
<!-- project, projectOrganization_participation_hasParticipant --> |
|
31 |
<!-- result,resultProject_outcome_produces, --> |
|
32 |
<!-- personResult_authorship_hasAuthor,resultResult_publicationDataset_isRelatedTo --> |
|
33 |
</arg> |
|
34 |
|
|
35 |
<capture-output /> |
|
36 |
</java> |
|
37 |
<ok to="mr_export" /> |
|
38 |
<error to="fail" /> |
|
39 |
</action> |
|
40 |
<action name="mr_export"> |
|
41 |
<map-reduce> |
|
42 |
|
|
43 |
<prepare> |
|
44 |
<delete path="${nameNode}${Stats_output_Path}" /> |
|
45 |
|
|
46 |
</prepare> |
|
47 |
<configuration> |
|
48 |
<property> |
|
49 |
<name>hbase.mapreduce.scan</name> |
|
50 |
<value>${wf:actionData('get-scanner')['scan']}</value> |
|
51 |
</property> |
|
52 |
<property> |
|
53 |
<name>hbase.rootdir</name> |
|
54 |
<value>hdfs://nmis-hadoop-cluster/hbase</value> |
|
55 |
</property> |
|
56 |
|
|
57 |
<property> |
|
58 |
<name>hbase.security.authentication</name> |
|
59 |
<value>simple</value> |
|
60 |
</property> |
|
61 |
<!-- ZOOKEEPER --> |
|
62 |
|
|
63 |
<property> |
|
64 |
<name>hbase.zookeeper.quorum</name> |
|
65 |
<value> |
|
66 |
quorum1.t.hadoop.research-infrastructures.eu,quorum2.t.hadoop.research-infrastructures.eu,quorum3.t.hadoop.research-infrastructures.eu,quorum4.t.hadoop.research-infrastructures.eu,jobtracker.t.hadoop.research-infrastructures.eu |
|
67 |
</value> |
|
68 |
</property> |
|
69 |
<property> |
|
70 |
<name>zookeeper.znode.rootserver</name> |
|
71 |
<value>root-region-server</value> |
|
72 |
</property> |
|
73 |
|
|
74 |
<property> |
|
75 |
<name>hbase.zookeeper.property.clientPort</name> |
|
76 |
<value>2182</value> |
|
77 |
</property> |
|
78 |
|
|
79 |
|
|
80 |
<!-- MR IO --> |
|
81 |
|
|
82 |
|
|
83 |
<property> |
|
84 |
<name>mapreduce.inputformat.class</name> |
|
85 |
<value>org.apache.hadoop.hbase.mapreduce.TableInputFormat</value> |
|
86 |
</property> |
|
87 |
|
|
88 |
<property> |
|
89 |
<name>mapred.mapoutput.key.class</name> |
|
90 |
<value>org.apache.hadoop.io.Text</value> |
|
91 |
</property> |
|
92 |
<property> |
|
93 |
<name>mapred.mapoutput.value.class</name> |
|
94 |
<value>org.apache.hadoop.hbase.io.ImmutableBytesWritable</value> |
|
95 |
</property> |
|
96 |
<property> |
|
97 |
<name>mapred.output.key.class</name> |
|
98 |
<value>org.apache.hadoop.io.Text</value> |
|
99 |
</property> |
|
100 |
<property> |
|
101 |
<name>mapred.output.value.class</name> |
|
102 |
<value>org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat |
|
103 |
</value> |
|
104 |
</property> |
|
105 |
|
|
106 |
<!-- ## This is required for new MapReduce API usage --> |
|
107 |
<property> |
|
108 |
<name>mapred.mapper.new-api</name> |
|
109 |
<value>true</value> |
|
110 |
</property> |
|
111 |
<property> |
|
112 |
<name>mapred.reducer.new-api</name> |
|
113 |
<value>true</value> |
|
114 |
</property> |
|
115 |
|
|
116 |
<!-- # Job-specific options --> |
|
117 |
<property> |
|
118 |
<name>dfs.blocksize</name> |
|
119 |
<value>32M</value> |
|
120 |
</property> |
|
121 |
<property> |
|
122 |
<name>mapred.output.compress</name> |
|
123 |
<value>false</value> |
|
124 |
</property> |
|
125 |
<property> |
|
126 |
<name>mapred.reduce.tasks.speculative.execution</name> |
|
127 |
<value>false</value> |
|
128 |
</property> |
|
129 |
<property> |
|
130 |
<name>mapred.reduce.tasks.speculative.execution</name> |
|
131 |
<value>false</value> |
|
132 |
</property> |
|
133 |
<property> |
|
134 |
<name>mapreduce.map.speculative</name> |
|
135 |
<value>false</value> |
|
136 |
</property> |
|
137 |
|
|
138 |
<!-- I/O FORMAT --> |
|
139 |
<!-- IMPORTANT: sets default delimeter used by text output writer. Required to fix issue with traling tab added between id and value in multiple outputs --> |
|
140 |
<property> |
|
141 |
<name>mapred.textoutputformat.separator</name> |
|
142 |
<value>${Stats_delim_Character}</value> |
|
143 |
</property> |
|
144 |
<!-- ## Names of all output ports --> |
|
145 |
|
|
146 |
<property> |
|
147 |
<name>mapreduce.multipleoutputs</name> |
|
148 |
|
|
149 |
<value>${out1} ${out2} ${out3} ${out4} ${out5} ${out6} ${out7} ${out8} ${out9} ${out10} ${out11} ${out12} ${out13} ${out14} ${out15} ${out16} ${out17} ${out18} ${out19} ${out20} |
|
150 |
</value> |
|
151 |
|
|
152 |
</property> |
|
153 |
<!-- datasource --> |
|
154 |
<property> |
|
155 |
<name>mapreduce.multipleoutputs.namedOutput.${out1}.key</name> |
|
156 |
<value>org.apache.hadoop.io.Text</value> |
|
157 |
</property> |
|
158 |
<property> |
|
159 |
<name>mapreduce.multipleoutputs.namedOutput.${out1}.value</name> |
|
160 |
<value>org.apache.hadoop.io.Text</value> |
|
161 |
</property> |
|
162 |
<property> |
|
163 |
<name>mapreduce.multipleoutputs.namedOutput.${out1}.format</name> |
|
164 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
165 |
</value> |
|
166 |
</property> |
|
167 |
<!-- datasourceLanguage --> |
|
168 |
<property> |
|
169 |
<name>mapreduce.multipleoutputs.namedOutput.${out2}.key</name> |
|
170 |
<value>org.apache.hadoop.io.Text</value> |
|
171 |
</property> |
|
172 |
<property> |
|
173 |
<name>mapreduce.multipleoutputs.namedOutput.${out2}.value</name> |
|
174 |
<value>org.apache.hadoop.io.Text</value> |
|
175 |
</property> |
|
176 |
<property> |
|
177 |
<name>mapreduce.multipleoutputs.namedOutput.${out2}.format</name> |
|
178 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
179 |
</value> |
|
180 |
</property> |
|
181 |
|
|
182 |
|
|
183 |
|
|
184 |
<!-- datasourceOrganization --> |
|
185 |
<property> |
|
186 |
<name>mapreduce.multipleoutputs.namedOutput.${out3}.key</name> |
|
187 |
<value>org.apache.hadoop.io.Text</value> |
|
188 |
</property> |
|
189 |
<property> |
|
190 |
<name>mapreduce.multipleoutputs.namedOutput.${out3}.value</name> |
|
191 |
<value>org.apache.hadoop.io.Text</value> |
|
192 |
</property> |
|
193 |
<property> |
|
194 |
<name>mapreduce.multipleoutputs.namedOutput.${out3}.format</name> |
|
195 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
196 |
</value> |
|
197 |
</property> |
|
198 |
|
|
199 |
<!-- datasourceTopic --> |
|
200 |
<property> |
|
201 |
<name>mapreduce.multipleoutputs.namedOutput.${out4}.key</name> |
|
202 |
<value>org.apache.hadoop.io.Text</value> |
|
203 |
</property> |
|
204 |
<property> |
|
205 |
<name>mapreduce.multipleoutputs.namedOutput.${out4}.value</name> |
|
206 |
<value>org.apache.hadoop.io.Text</value> |
|
207 |
</property> |
|
208 |
<property> |
|
209 |
<name>mapreduce.multipleoutputs.namedOutput.${out4}.format</name> |
|
210 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
211 |
</value> |
|
212 |
</property> |
|
213 |
|
|
214 |
<!-- resultDatasource --> |
|
215 |
<property> |
|
216 |
<name>mapreduce.multipleoutputs.namedOutput.${out5}.key</name> |
|
217 |
<value>org.apache.hadoop.io.Text</value> |
|
218 |
</property> |
|
219 |
<property> |
|
220 |
<name>mapreduce.multipleoutputs.namedOutput.${out5}.value</name> |
|
221 |
<value>org.apache.hadoop.io.Text</value> |
|
222 |
</property> |
|
223 |
<property> |
|
224 |
<name>mapreduce.multipleoutputs.namedOutput.${out5}.format</name> |
|
225 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
226 |
</value> |
|
227 |
</property> |
|
228 |
<!-- organization --> |
|
229 |
<property> |
|
230 |
<name>mapreduce.multipleoutputs.namedOutput.${out6}.key</name> |
|
231 |
<value>org.apache.hadoop.io.Text</value> |
|
232 |
</property> |
|
233 |
<property> |
|
234 |
<name>mapreduce.multipleoutputs.namedOutput.${out6}.value</name> |
|
235 |
<value>org.apache.hadoop.io.Text</value> |
|
236 |
</property> |
|
237 |
<property> |
|
238 |
<name>mapreduce.multipleoutputs.namedOutput.${out6}.format</name> |
|
239 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
240 |
</value> |
|
241 |
</property> |
|
242 |
|
|
243 |
<!-- projectOrganization --> |
|
244 |
<property> |
|
245 |
<name>mapreduce.multipleoutputs.namedOutput.${out7}.key</name> |
|
246 |
<value>org.apache.hadoop.io.Text</value> |
|
247 |
</property> |
|
248 |
<property> |
|
249 |
<name>mapreduce.multipleoutputs.namedOutput.${out7}.value</name> |
|
250 |
<value>org.apache.hadoop.io.Text</value> |
|
251 |
</property> |
|
252 |
<property> |
|
253 |
<name>mapreduce.multipleoutputs.namedOutput.${out7}.format</name> |
|
254 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
255 |
</value> |
|
256 |
</property> |
|
257 |
<!-- resultProject --> |
|
258 |
<property> |
|
259 |
<name>mapreduce.multipleoutputs.namedOutput.${out8}.key</name> |
|
260 |
<value>org.apache.hadoop.io.Text</value> |
|
261 |
</property> |
|
262 |
<property> |
|
263 |
<name>mapreduce.multipleoutputs.namedOutput.${out8}.value</name> |
|
264 |
<value>org.apache.hadoop.io.Text</value> |
|
265 |
</property> |
|
266 |
<property> |
|
267 |
<name>mapreduce.multipleoutputs.namedOutput.${out8}.format</name> |
|
268 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
269 |
</value> |
|
270 |
</property> |
|
271 |
|
|
272 |
<!-- project --> |
|
273 |
<property> |
|
274 |
<name>mapreduce.multipleoutputs.namedOutput.${out9}.key</name> |
|
275 |
<value>org.apache.hadoop.io.Text</value> |
|
276 |
</property> |
|
277 |
<property> |
|
278 |
<name>mapreduce.multipleoutputs.namedOutput.${out9}.value</name> |
|
279 |
<value>org.apache.hadoop.io.Text</value> |
|
280 |
</property> |
|
281 |
<property> |
|
282 |
<name>mapreduce.multipleoutputs.namedOutput.${out9}.format</name> |
|
283 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
284 |
</value> |
|
285 |
</property> |
|
286 |
|
|
287 |
<!-- resultConcept --> |
|
288 |
<property> |
|
289 |
<name>mapreduce.multipleoutputs.namedOutput.${out10}.key</name> |
|
290 |
<value>org.apache.hadoop.io.Text</value> |
|
291 |
</property> |
|
292 |
<property> |
|
293 |
<name>mapreduce.multipleoutputs.namedOutput.${out10}.value</name> |
|
294 |
<value>org.apache.hadoop.io.Text</value> |
|
295 |
</property> |
|
296 |
<property> |
|
297 |
<name>mapreduce.multipleoutputs.namedOutput.${out10}.format</name> |
|
298 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
299 |
</value> |
|
300 |
</property> |
|
301 |
|
|
302 |
<!-- resultClaim --> |
|
303 |
<property> |
|
304 |
<name>mapreduce.multipleoutputs.namedOutput.${out11}.key</name> |
|
305 |
<value>org.apache.hadoop.io.Text</value> |
|
306 |
</property> |
|
307 |
<property> |
|
308 |
<name>mapreduce.multipleoutputs.namedOutput.${out11}.value</name> |
|
309 |
<value>org.apache.hadoop.io.Text</value> |
|
310 |
</property> |
|
311 |
<property> |
|
312 |
<name>mapreduce.multipleoutputs.namedOutput.${out11}.format</name> |
|
313 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
314 |
</value> |
|
315 |
</property> |
|
316 |
|
|
317 |
<!-- resultClassification --> |
|
318 |
<property> |
|
319 |
<name>mapreduce.multipleoutputs.namedOutput.${out12}.key</name> |
|
320 |
<value>org.apache.hadoop.io.Text</value> |
|
321 |
</property> |
|
322 |
<property> |
|
323 |
<name>mapreduce.multipleoutputs.namedOutput.${out12}.value</name> |
|
324 |
<value>org.apache.hadoop.io.Text</value> |
|
325 |
</property> |
|
326 |
<property> |
|
327 |
<name>mapreduce.multipleoutputs.namedOutput.${out12}.format</name> |
|
328 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
329 |
</value> |
|
330 |
</property> |
|
331 |
|
|
332 |
<!-- resultLanguage --> |
|
333 |
<property> |
|
334 |
<name>mapreduce.multipleoutputs.namedOutput.${out13}.key</name> |
|
335 |
<value>org.apache.hadoop.io.Text</value> |
|
336 |
</property> |
|
337 |
<property> |
|
338 |
<name>mapreduce.multipleoutputs.namedOutput.${out13}.value</name> |
|
339 |
<value>org.apache.hadoop.io.Text</value> |
|
340 |
</property> |
|
341 |
<property> |
|
342 |
<name>mapreduce.multipleoutputs.namedOutput.${out13}.format</name> |
|
343 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
344 |
</value> |
|
345 |
</property> |
|
346 |
|
|
347 |
<!-- resultProject --> |
|
348 |
<property> |
|
349 |
<name>mapreduce.multipleoutputs.namedOutput.${out14}.key</name> |
|
350 |
<value>org.apache.hadoop.io.Text</value> |
|
351 |
</property> |
|
352 |
<property> |
|
353 |
<name>mapreduce.multipleoutputs.namedOutput.${out14}.value</name> |
|
354 |
<value>org.apache.hadoop.io.Text</value> |
|
355 |
</property> |
|
356 |
<property> |
|
357 |
<name>mapreduce.multipleoutputs.namedOutput.${out14}.format</name> |
|
358 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
359 |
</value> |
|
360 |
</property> |
|
361 |
<!-- resultResult --> |
|
362 |
<property> |
|
363 |
<name>mapreduce.multipleoutputs.namedOutput.${out15}.key</name> |
|
364 |
<value>org.apache.hadoop.io.Text</value> |
|
365 |
</property> |
|
366 |
<property> |
|
367 |
<name>mapreduce.multipleoutputs.namedOutput.${out15}.value</name> |
|
368 |
<value>org.apache.hadoop.io.Text</value> |
|
369 |
</property> |
|
370 |
<property> |
|
371 |
<name>mapreduce.multipleoutputs.namedOutput.${out15}.format</name> |
|
372 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
373 |
</value> |
|
374 |
</property> |
|
375 |
<!-- resultTopic --> |
|
376 |
<property> |
|
377 |
<name>mapreduce.multipleoutputs.namedOutput.${out16}.key</name> |
|
378 |
<value>org.apache.hadoop.io.Text</value> |
|
379 |
</property> |
|
380 |
<property> |
|
381 |
<name>mapreduce.multipleoutputs.namedOutput.${out16}.value</name> |
|
382 |
<value>org.apache.hadoop.io.Text</value> |
|
383 |
</property> |
|
384 |
<property> |
|
385 |
<name>mapreduce.multipleoutputs.namedOutput.${out16}.format</name> |
|
386 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
387 |
</value> |
|
388 |
</property> |
|
389 |
|
|
390 |
<!-- resultDatasource --> |
|
391 |
<property> |
|
392 |
<name>mapreduce.multipleoutputs.namedOutput.${out17}.key</name> |
|
393 |
<value>org.apache.hadoop.io.Text</value> |
|
394 |
</property> |
|
395 |
<property> |
|
396 |
<name>mapreduce.multipleoutputs.namedOutput.${out17}.value</name> |
|
397 |
<value>org.apache.hadoop.io.Text</value> |
|
398 |
</property> |
|
399 |
<property> |
|
400 |
<name>mapreduce.multipleoutputs.namedOutput.${out17}.format</name> |
|
401 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
402 |
</value> |
|
403 |
</property> |
|
404 |
|
|
405 |
|
|
406 |
|
|
407 |
<!-- result --> |
|
408 |
<property> |
|
409 |
<name>mapreduce.multipleoutputs.namedOutput.${out18}.key</name> |
|
410 |
<value>org.apache.hadoop.io.Text</value> |
|
411 |
</property> |
|
412 |
<property> |
|
413 |
<name>mapreduce.multipleoutputs.namedOutput.${out18}.value</name> |
|
414 |
<value>org.apache.hadoop.io.Text</value> |
|
415 |
</property> |
|
416 |
<property> |
|
417 |
<name>mapreduce.multipleoutputs.namedOutput.${out18}.format</name> |
|
418 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
419 |
</value> |
|
420 |
</property> |
|
421 |
|
|
422 |
<!-- claim --> |
|
423 |
<property> |
|
424 |
<name>mapreduce.multipleoutputs.namedOutput.${out19}.key</name> |
|
425 |
<value>org.apache.hadoop.io.Text</value> |
|
426 |
</property> |
|
427 |
<property> |
|
428 |
<name>mapreduce.multipleoutputs.namedOutput.${out19}.value</name> |
|
429 |
<value>org.apache.hadoop.io.Text</value> |
|
430 |
</property> |
|
431 |
<property> |
|
432 |
<name>mapreduce.multipleoutputs.namedOutput.${out19}.format</name> |
|
433 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
434 |
</value> |
|
435 |
</property> |
|
436 |
<!-- cncept --> |
|
437 |
<property> |
|
438 |
<name>mapreduce.multipleoutputs.namedOutput.${out20}.key</name> |
|
439 |
<value>org.apache.hadoop.io.Text</value> |
|
440 |
</property> |
|
441 |
<property> |
|
442 |
<name>mapreduce.multipleoutputs.namedOutput.${out20}.value</name> |
|
443 |
<value>org.apache.hadoop.io.Text</value> |
|
444 |
</property> |
|
445 |
<property> |
|
446 |
<name>mapreduce.multipleoutputs.namedOutput.${out20}.format</name> |
|
447 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
448 |
</value> |
|
449 |
</property> |
|
450 |
|
|
451 |
|
|
452 |
<!-- ## Classes of mapper and reducer --> |
|
453 |
|
|
454 |
<property> |
|
455 |
<name>mapreduce.map.class</name> |
|
456 |
<value>eu.dnetlib.data.mapreduce.hbase.statsExport.StatsMapper |
|
457 |
</value> |
|
458 |
</property> |
|
459 |
<property> |
|
460 |
<name>mapreduce.reduce.class</name> |
|
461 |
<value>eu.dnetlib.data.mapreduce.hbase.statsExport.StatsReducer |
|
462 |
</value> |
|
463 |
</property> |
|
464 |
<property> |
|
465 |
<name>io.serializations</name> |
|
466 |
<value>org.apache.hadoop.io.serializer.WritableSerialization |
|
467 |
</value> |
|
468 |
</property> |
|
469 |
<!-- ## Custom config --> |
|
470 |
|
|
471 |
<!--delim character used to seperate fields in hdfs dump files <property> --> |
|
472 |
<property> |
|
473 |
<name>stats.delim</name> |
|
474 |
<value>${Stats_delim_Character}</value> |
|
475 |
</property> |
|
476 |
<!--default string for Null String Values --> |
|
477 |
<property> |
|
478 |
<name>stats.nullString</name> |
|
479 |
<value>${Stats_null_String_Field}</value> |
|
480 |
</property> |
|
481 |
<!--default string for Null Numeric Values --> |
|
482 |
<property> |
|
483 |
<name>stats.nullNum</name> |
|
484 |
<value>${Stats_null_Numeric_Field}</value> |
|
485 |
</property> |
|
486 |
<property> |
|
487 |
<name>stats.enclChar</name> |
|
488 |
<value>${Stats_enclosing_Character}</value> |
|
489 |
</property> |
|
490 |
|
|
491 |
|
|
492 |
<!--source hbase table --> |
|
493 |
<property> |
|
494 |
<name>hbase.mapreduce.inputtable</name> |
|
495 |
<value>${Stats_Hbase_Source_Table}</value> |
|
496 |
</property> |
|
497 |
<property> |
|
498 |
<!-- mapping of protos entities to tables in the relDB --> |
|
499 |
<name>stats.dbTablesMap</name> |
|
500 |
<value>${Stats_db_table_map}</value> |
|
501 |
</property> |
|
502 |
|
|
503 |
<!-- This directory does not correspond to a data store. In fact, this directory only contains multiple data stores. It has to be set to the name of the workflow node. --> |
|
504 |
<property> |
|
505 |
<name>mapred.output.dir</name> |
|
506 |
<value>${Stats_output_Path}</value> |
|
507 |
</property> |
|
508 |
<property> |
|
509 |
<name>stats.indexConf</name> |
|
510 |
<value>${Stats_indexConf}</value> |
|
511 |
</property> |
|
512 |
<!-- ## Workflow node parameters --> |
|
513 |
<property> |
|
514 |
<name>mapred.reduce.tasks</name> |
|
515 |
<value>${numReducers}</value> |
|
516 |
</property> |
|
517 |
</configuration> |
|
518 |
</map-reduce> |
|
519 |
<ok to="exportContext" /> |
|
520 |
<error to="fail" /> |
|
521 |
</action> |
|
522 |
|
|
523 |
|
|
524 |
<action name="exportContext"> |
|
525 |
<java> |
|
526 |
|
|
527 |
<prepare> |
|
528 |
</prepare> |
|
529 |
<configuration> |
|
530 |
<property> |
|
531 |
<name>mapred.job.queue.name</name> |
|
532 |
<value>${queueName}</value> |
|
533 |
</property> |
|
534 |
</configuration> |
|
535 |
|
|
536 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
537 |
<arg>-SworkingDir=${workingDir}</arg> |
|
538 |
<arg>eu.dnetlib.iis.core.workflows.stats.ExportContextWrapper</arg> |
|
539 |
<arg>-PStats_output_Path=${Stats_output_Path}</arg> |
|
540 |
<arg>-PStats_ContextResourceXML=${ContextResourceXML}</arg> |
|
541 |
|
|
542 |
</java> |
|
543 |
<ok to="prepareDatabase" /> |
|
544 |
<error to="fail" /> |
|
545 |
</action> |
|
546 |
|
|
547 |
<action name="prepareDatabase"> |
|
548 |
<java> |
|
549 |
|
|
550 |
<prepare> |
|
551 |
</prepare> |
|
552 |
<configuration> |
|
553 |
<property> |
|
554 |
<name>mapred.job.queue.name</name> |
|
555 |
<value>${queueName}</value> |
|
556 |
</property> |
|
557 |
</configuration> |
|
558 |
|
|
559 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
560 |
<arg>-SworkingDir=${workingDir}</arg> |
|
561 |
<arg>eu.dnetlib.iis.core.workflows.stats.DBInitWrapper</arg> |
|
562 |
|
|
563 |
<arg>-PStats_db_Url=${Stats_db_Url}</arg> |
|
564 |
<arg>-PStats_db_User=${Stats_db_User}</arg> |
|
565 |
<arg>-PStats_db_Pass=${Stats_db_Pass}</arg> |
|
566 |
<arg>-PStats_db_Driver=${Stats_db_Driver}</arg> |
|
567 |
|
|
568 |
</java> |
|
569 |
<ok to="sqoopImport" /> |
|
570 |
<error to="fail" /> |
|
571 |
</action> |
|
572 |
|
|
573 |
<action name="sqoopImport"> |
|
574 |
<java> |
|
575 |
<prepare> |
|
576 |
</prepare> |
|
577 |
<configuration> |
|
578 |
<property> |
|
579 |
<name>mapred.job.queue.name</name> |
|
580 |
<value>${queueName}</value> |
|
581 |
</property> |
|
582 |
|
|
583 |
<property> |
|
584 |
<name>oozie.sqoop.log.level</name> |
|
585 |
<value>DEBUG</value> |
|
586 |
</property> |
|
587 |
|
|
588 |
</configuration> |
|
589 |
|
|
590 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
591 |
<arg>-SworkingDir=${workingDir}</arg> |
|
592 |
<arg>eu.dnetlib.iis.core.workflows.stats.SqoopWrapper</arg> |
|
593 |
|
|
594 |
<arg>-PStats_db_Url=${Stats_db_Url}</arg> |
|
595 |
<arg>-PStats_db_User=${Stats_db_User}</arg> |
|
596 |
<arg>-PStats_db_Pass=${Stats_db_Pass}</arg> |
|
597 |
|
|
598 |
<arg>-PStats_output_Path=${Stats_output_Path}</arg> |
|
599 |
<arg>-PStats_sqoop_RecsPerStatement=${Stats_sqoop_RecsPerStatement} |
|
600 |
</arg> |
|
601 |
<arg>-PStats_sqoop_ReducersCount=${Stats_sqoop_ReducersCount}</arg> |
|
602 |
<arg>-PStats_sqoop_StatementPerTrans=${Stats_sqoop_StatementPerTrans} |
|
603 |
</arg> |
|
604 |
<arg>-PStats_delim_Character=${Stats_delim_Character}</arg> |
|
605 |
<arg>-PStats_db_table_map=${Stats_db_table_map}</arg> |
|
606 |
<arg>-PStats_enclosing_Character=${Stats_enclosing_Character} </arg> |
|
607 |
|
|
608 |
</java> |
|
609 |
<ok to="finalizeDatabase" /> |
|
610 |
<error to="fail" /> |
|
611 |
</action> |
|
612 |
|
|
613 |
<action name="finalizeDatabase"> |
|
614 |
<java> |
|
615 |
|
|
616 |
<prepare> |
|
617 |
</prepare> |
|
618 |
<configuration> |
|
619 |
<property> |
|
620 |
<name>mapred.job.queue.name</name> |
|
621 |
<value>${queueName}</value> |
|
622 |
</property> |
|
623 |
</configuration> |
|
624 |
|
|
625 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
626 |
<arg>-SworkingDir=${workingDir}</arg> |
|
627 |
<arg>eu.dnetlib.iis.core.workflows.stats.DBFinalizeWrapper</arg> |
|
628 |
<arg>-PStats_db_Url=${Stats_db_Url}</arg> |
|
629 |
<arg>-PStats_db_User=${Stats_db_User}</arg> |
|
630 |
<arg>-PStats_db_Pass=${Stats_db_Pass}</arg> |
|
631 |
<arg>-PStats_db_Driver=${Stats_db_Driver}</arg> |
|
632 |
|
|
633 |
|
|
634 |
</java> |
|
635 |
<ok to="end" /> |
|
636 |
<error to="fail" /> |
|
637 |
</action> |
|
638 |
<kill name="fail"> |
|
639 |
<message> |
|
640 |
Unfortunately, the process failed -- error message: |
|
641 |
[${wf:errorMessage(wf:lastErrorNode())}] |
|
642 |
</message> |
|
643 |
</kill> |
|
644 |
<end name="end" /> |
|
645 |
</workflow-app> |
modules/dnet-openaire-stats-workflow/src/main/resources/eu/dnetlib/iis/core/examples/javamapreduce/stats/job.properties | ||
---|---|---|
1 |
oozieServiceLoc=http://oozie.t.hadoop.research-infrastructures.eu:11000/oozie |
|
2 |
nameNode=hdfs://nmis-hadoop-cluster |
|
3 |
jobTracker=nmis-hadoop-jt |
|
4 |
queueName=default |
|
5 |
user.name=eri.katsari |
|
6 |
numReducers=1 |
|
7 |
Stats_db_Url = jdbc:postgresql://duffy.di.uoa.gr:5432/test_stats |
|
8 |
Stats_db_User = sqoop |
|
9 |
Stats_db_Pass = sqoop |
|
10 |
Stats_db_Driver = org.postgresql.Driver |
|
11 |
Stats_sqoop_RecsPerStatement = 1000 |
|
12 |
Stats_sqoop_StatementPerTrans = 1000 |
|
13 |
Stats_sqoop_ReducersCount=4 |
|
14 |
Stats_Hbase_Source_Table=db_openaireplus_node6_t |
|
15 |
Stats_output_Path=/tmp/test_stats/ |
|
16 |
Stats_null_String_Field=NULL |
|
17 |
Stats_null_Numeric_Field=-1 |
|
18 |
Stats_delim_Character=! |
|
19 |
Stats_enclosing_Character=# |
|
20 |
Stats_db_table_map=datasourceLanguage=datasource_languages,datasource=datasource,project=project,result=result,organization=organization,datasourceOrganization=datasource_organizations,datasourceTopic=datasource_topics,projectOrganization=project_organizations,resultClaim=result_claims,resultClassification=result_classifications,resultConcept=result_concepts,resultLanguage=result_languages,resultOrganization=result_organizations,resultResult=result_results,resultProject=project_results,resultResult=result_results,resultTopic=result_topics,category=category,claim=claim,concept=concept,datasourceLanguage=datasource_languages,resultLanguage=result_languages,resultDatasource=result_datasources |
|
21 |
out1=datasource |
|
22 |
out2=project |
|
23 |
out3=organization |
|
24 |
out4=datasourceOrganization |
|
25 |
out5=datasourceTopic |
|
26 |
out6=datasourceLanguage |
|
27 |
out7=projectOrganization |
|
28 |
out8=resultClaim |
|
29 |
out9=resultClassification |
|
30 |
out10=resultConcept |
|
31 |
out11=resultLanguage |
|
32 |
out12=resultOrganization |
|
33 |
out13=resultResult |
|
34 |
out14=resultProject |
|
35 |
out15=resultTopic |
|
36 |
out16=resultDatasource |
|
37 |
out17=result |
|
38 |
out18=claim |
|
39 |
out19=concept |
|
40 |
out20=category |
|
41 |
Stats_indexConf=index.conf { result { dups = true, links = [{ relType = personResult_authorship_hasAuthor, targetEntity = person, expandAs = rel, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] }, { relType = resultResult_dedup_isMergedIn, targetEntity = result, expandAs = child, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] }, { relType = resultResult_dedup_merges, targetEntity = result, expandAs = child, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] }, { relType = resultResult_publicationDataset_isRelatedTo, targetEntity = result, expandAs = rel, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] },{ relType = resultResult_similarity_isAmongTopNSimilarDocuments, targetEntity = result, expandAs = rel, symmetric = false, fields = [title,dateofacceptance,publisher,resulttype,similarity,type] },{ relType = resultResult_similarity_hasAmongTopNSimilarDocuments, targetEntity = result, expandAs = rel, symmetric = false, fields = [title,dateofacceptance,publisher,resulttype,similarity,type] }]}, person { dups = false, links = [ { relType = personResult_authorship_isAuthorOf, targetEntity = result, expandAs = rel, symmetric = true, fields = [fullname,ranking] }, { relType = projectPerson_contactPerson_isContact, targetEntity = project, expandAs = rel, symmetric = true, fields = [fullname,email,fax,phone] } ]}, datasource { dups = false, links = [ { relType = datasourceOrganization_provision_provides, targetEntity = organization, expandAs = rel, symmetric = true, fields = [officialname,websiteurl,datasourcetype,aggregatortype] } ]},organization { dups = false, links = [{ relType = projectOrganization_participation_isParticipant, targetEntity = project, expandAs = rel, symmetric = true, fields = [legalname,legalshortname,websiteurl,country] }, { relType = datasourceOrganization_provision_isProvidedBy, targetEntity = datasource, expandAs = rel, symmetric = true, fields = [legalname,legalshortname,websiteurl,country] } ]}, project { dups = false, links = [ { relType = projectOrganization_participation_hasParticipant, targetEntity = organization, expandAs = rel, symmetric = true, fields = [code,acronym,title,websiteurl,contracttype,fundingtree] }, { relType = resultProject_outcome_produces, targetEntity = result, expandAs = rel, symmetric = true, fields = [code,acronym,title,websiteurl,contracttype,fundingtree] }, { relType = projectPerson_contactPerson_hasContact, targetEntity = person, expandAs = rel, symmetric = true, fields = [code,acronym,title,websiteurl,contracttype,fundingtree] } ]}} |
|
42 |
ContextResourceXML=<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="context.xsl"?><RESOURCE_PROFILE><HEADER><RESOURCE_IDENTIFIER value="1284f828-6c12-4905-a9c9-43f143b36e08_Q29udGV4dERTUmVzb3VyY2VzL0NvbnRleHREU1Jlc291cmNlVHlwZQ=="/><RESOURCE_TYPE value="ContextDSResourceType"/><RESOURCE_KIND value="ContextDSResources"/><RESOURCE_URI value=""/><DATE_OF_CREATION value=""/></HEADER><BODY><CONFIGURATION><context id="egi" type="community" label="EGI"><category claim="true" label="Scientific Disciplines" id="egi::classification"><concept label="Natural Sciences" claim="true" id="egi::classification::natsc"><param name="originalID">1</param><concept label="Mathematics" claim="true" id="egi::classification::natsc::math"><param name="originalID">1.1</param><concept label="Applied Mathematics" id="egi::classification::natsc::math::applied" claim="true"><param name="originalID">1.1.1</param></concept></concept></concept></category></context></CONFIGURATION><STATUS/><SECURITY_PARAMETERS/></BODY></RESOURCE_PROFILE> |
modules/dnet-openaire-stats-workflow/src/main/resources/eu/dnetlib/iis/core/examples/javamapreduce/stats/NewFile.xml | ||
---|---|---|
1 |
<?xml version="1.0" encoding="UTF-8"?> |
modules/dnet-openaire-stats-workflow/src/main/resources/eu/dnetlib/iis/core/javamapreduce/stats/job.properties | ||
---|---|---|
1 |
oozieServiceLoc=http://oozie.t.hadoop.research-infrastructures.eu:11000/oozie |
|
2 |
nameNode=hdfs://nmis-hadoop-cluster |
|
3 |
jobTracker=nmis-hadoop-jt |
|
4 |
queueName=default |
|
5 |
user.name=eri.katsari |
|
6 |
numReducers=1 |
|
7 |
Stats_db_Url = jdbc:postgresql://duffy.di.uoa.gr:5432/test_stats |
|
8 |
Stats_db_User = sqoop |
|
9 |
Stats_db_Pass = sqoop |
|
10 |
Stats_db_Driver = org.postgresql.Driver |
|
11 |
Stats_sqoop_RecsPerStatement = 1000 |
|
12 |
Stats_sqoop_StatementPerTrans = 1000 |
|
13 |
Stats_sqoop_ReducersCount=4 |
|
14 |
Stats_Hbase_Source_Table=db_openaireplus_node6_t |
|
15 |
Stats_output_Path=/tmp/test_stats/ |
|
16 |
Stats_null_String_Field=NULL |
|
17 |
Stats_null_Numeric_Field=-1 |
|
18 |
Stats_delim_Character=! |
|
19 |
Stats_enclosing_Character=# |
|
20 |
Stats_db_table_map=datasourceLanguage=datasource_languages,datasource=datasource,project=project,result=result,organization=organization,datasourceOrganization=datasource_organizations,datasourceTopic=datasource_topics,projectOrganization=project_organizations,resultClaim=result_claims,resultClassification=result_classifications,resultConcept=result_concepts,resultLanguage=result_languages,resultOrganization=result_organizations,resultResult=result_results,resultProject=project_results,resultResult=result_results,resultTopic=result_topics,category=category,claim=claim,concept=concept,datasourceLanguage=datasource_languages,resultLanguage=result_languages,resultDatasource=result_datasources |
|
21 |
out1=datasource |
|
22 |
out2=project |
|
23 |
out3=organization |
|
24 |
out4=datasourceOrganization |
|
25 |
out5=datasourceTopic |
|
26 |
out6=datasourceLanguage |
|
27 |
out7=projectOrganization |
|
28 |
out8=resultClaim |
|
29 |
out9=resultClassification |
|
30 |
out10=resultConcept |
|
31 |
out11=resultLanguage |
|
32 |
out12=resultOrganization |
|
33 |
out13=resultResult |
|
34 |
out14=resultProject |
|
35 |
out15=resultTopic |
|
36 |
out16=resultDatasource |
|
37 |
out17=result |
|
38 |
out18=claim |
|
39 |
out19=concept |
|
40 |
out20=category |
|
41 |
Stats_indexConf=index.conf { result { dups = true, links = [{ relType = personResult_authorship_hasAuthor, targetEntity = person, expandAs = rel, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] }, { relType = resultResult_dedup_isMergedIn, targetEntity = result, expandAs = child, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] }, { relType = resultResult_dedup_merges, targetEntity = result, expandAs = child, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] }, { relType = resultResult_publicationDataset_isRelatedTo, targetEntity = result, expandAs = rel, symmetric = true, fields = [title,dateofacceptance,publisher,resulttype] },{ relType = resultResult_similarity_isAmongTopNSimilarDocuments, targetEntity = result, expandAs = rel, symmetric = false, fields = [title,dateofacceptance,publisher,resulttype,similarity,type] },{ relType = resultResult_similarity_hasAmongTopNSimilarDocuments, targetEntity = result, expandAs = rel, symmetric = false, fields = [title,dateofacceptance,publisher,resulttype,similarity,type] }]}, person { dups = false, links = [ { relType = personResult_authorship_isAuthorOf, targetEntity = result, expandAs = rel, symmetric = true, fields = [fullname,ranking] }, { relType = projectPerson_contactPerson_isContact, targetEntity = project, expandAs = rel, symmetric = true, fields = [fullname,email,fax,phone] } ]}, datasource { dups = false, links = [ { relType = datasourceOrganization_provision_provides, targetEntity = organization, expandAs = rel, symmetric = true, fields = [officialname,websiteurl,datasourcetype,aggregatortype] } ]},organization { dups = false, links = [{ relType = projectOrganization_participation_isParticipant, targetEntity = project, expandAs = rel, symmetric = true, fields = [legalname,legalshortname,websiteurl,country] }, { relType = datasourceOrganization_provision_isProvidedBy, targetEntity = datasource, expandAs = rel, symmetric = true, fields = [legalname,legalshortname,websiteurl,country] } ]}, project { dups = false, links = [ { relType = projectOrganization_participation_hasParticipant, targetEntity = organization, expandAs = rel, symmetric = true, fields = [code,acronym,title,websiteurl,contracttype,fundingtree] }, { relType = resultProject_outcome_produces, targetEntity = result, expandAs = rel, symmetric = true, fields = [code,acronym,title,websiteurl,contracttype,fundingtree] }, { relType = projectPerson_contactPerson_hasContact, targetEntity = person, expandAs = rel, symmetric = true, fields = [code,acronym,title,websiteurl,contracttype,fundingtree] } ]}} |
|
42 |
ContextResourceXML=<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="context.xsl"?><RESOURCE_PROFILES><RESOURCE_PROFILE><HEADER><RESOURCE_IDENTIFIER value="1284f828-6c12-4905-a9c9-43f143b36e08_Q29udGV4dERTUmVzb3VyY2VzL0NvbnRleHREU1Jlc291cmNlVHlwZQ=="/><RESOURCE_TYPE value="ContextDSResourceType"/><RESOURCE_KIND value="ContextDSResources"/><RESOURCE_URI value=""/><DATE_OF_CREATION value=""/></HEADER><BODY><CONFIGURATION><context id="egi" type="community" label="EGI"><category claim="true" label="Scientific Disciplines" id="egi::classification"><concept label="Natural Sciences" claim="true" id="egi::classification::natsc"><param name="originalID">1</param><concept label="Mathematics" claim="true" id="egi::classification::natsc::math"><param name="originalID">1.1</param><concept label="Applied Mathematics" id="egi::classification::natsc::math::applied" claim="true"><param name="originalID">1.1.1</param></concept></concept></concept></category></context></CONFIGURATION><STATUS/><SECURITY_PARAMETERS/></BODY></RESOURCE_PROFILE></RESOURCE_PROFILES> |
modules/dnet-openaire-stats-workflow/src/main/resources/eu/dnetlib/iis/core/javamapreduce/stats/oozie_app/workflow.xml | ||
---|---|---|
1 |
<workflow-app name="test-core_examples_javamapreduce_stats" xmlns="uri:oozie:workflow:0.4"> |
|
2 |
<!-- map reduce job that exports hbase data and prepares them for import to the relation database used for statistics generation --> |
|
3 |
|
|
4 |
<global> |
|
5 |
<job-tracker>${jobTracker}</job-tracker> |
|
6 |
<name-node>${nameNode}</name-node> |
|
7 |
<configuration> |
|
8 |
<property> |
|
9 |
<name>mapred.job.queue.name</name> |
|
10 |
<value>${queueName}</value> |
|
11 |
</property> |
|
12 |
<property> |
|
13 |
<name>oozie.sqoop.log.level</name> |
|
14 |
<value>DEBUG</value> |
|
15 |
</property> |
|
16 |
</configuration> |
|
17 |
</global> |
|
18 |
<start to='get-scanner' /> |
|
19 |
<action name='get-scanner'> |
|
20 |
<java> |
|
21 |
<main-class>eu.dnetlib.iis.core.workflows.stats.HbaseScannerGenerator |
|
22 |
</main-class> |
|
23 |
<!-- column families: --> |
|
24 |
|
|
25 |
<arg> |
|
26 |
-f datasource |
|
27 |
<!-- , --> |
|
28 |
<!-- datasourceOrganization_provision_provides , --> |
|
29 |
<!-- organization, --> |
|
30 |
<!-- project, projectOrganization_participation_hasParticipant --> |
|
31 |
<!-- result,resultProject_outcome_produces, --> |
|
32 |
<!-- personResult_authorship_hasAuthor,resultResult_publicationDataset_isRelatedTo --> |
|
33 |
</arg> |
|
34 |
|
|
35 |
<capture-output /> |
|
36 |
</java> |
|
37 |
<ok to="mr_export" /> |
|
38 |
<error to="fail" /> |
|
39 |
</action> |
|
40 |
<action name="mr_export"> |
|
41 |
<map-reduce> |
|
42 |
|
|
43 |
<prepare> |
|
44 |
<delete path="${nameNode}${Stats_output_Path}" /> |
|
45 |
|
|
46 |
</prepare> |
|
47 |
<configuration> |
|
48 |
<property> |
|
49 |
<name>hbase.mapreduce.scan</name> |
|
50 |
<value>${wf:actionData('get-scanner')['scan']}</value> |
|
51 |
</property> |
|
52 |
<property> |
|
53 |
<name>hbase.rootdir</name> |
|
54 |
<value>hdfs://nmis-hadoop-cluster/hbase</value> |
|
55 |
</property> |
|
56 |
|
|
57 |
<property> |
|
58 |
<name>hbase.security.authentication</name> |
|
59 |
<value>simple</value> |
|
60 |
</property> |
|
61 |
<!-- ZOOKEEPER --> |
|
62 |
|
|
63 |
<property> |
|
64 |
<name>hbase.zookeeper.quorum</name> |
|
65 |
<value> |
|
66 |
quorum1.t.hadoop.research-infrastructures.eu,quorum2.t.hadoop.research-infrastructures.eu,quorum3.t.hadoop.research-infrastructures.eu,quorum4.t.hadoop.research-infrastructures.eu,jobtracker.t.hadoop.research-infrastructures.eu |
|
67 |
</value> |
|
68 |
</property> |
|
69 |
<property> |
|
70 |
<name>zookeeper.znode.rootserver</name> |
|
71 |
<value>root-region-server</value> |
|
72 |
</property> |
|
73 |
|
|
74 |
<property> |
|
75 |
<name>hbase.zookeeper.property.clientPort</name> |
|
76 |
<value>2182</value> |
|
77 |
</property> |
|
78 |
|
|
79 |
|
|
80 |
<!-- MR IO --> |
|
81 |
|
|
82 |
|
|
83 |
<property> |
|
84 |
<name>mapreduce.inputformat.class</name> |
|
85 |
<value>org.apache.hadoop.hbase.mapreduce.TableInputFormat</value> |
|
86 |
</property> |
|
87 |
|
|
88 |
<property> |
|
89 |
<name>mapred.mapoutput.key.class</name> |
|
90 |
<value>org.apache.hadoop.io.Text</value> |
|
91 |
</property> |
|
92 |
<property> |
|
93 |
<name>mapred.mapoutput.value.class</name> |
|
94 |
<value>org.apache.hadoop.hbase.io.ImmutableBytesWritable</value> |
|
95 |
</property> |
|
96 |
<property> |
|
97 |
<name>mapred.output.key.class</name> |
|
98 |
<value>org.apache.hadoop.io.Text</value> |
|
99 |
</property> |
|
100 |
<property> |
|
101 |
<name>mapred.output.value.class</name> |
|
102 |
<value>org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat |
|
103 |
</value> |
|
104 |
</property> |
|
105 |
|
|
106 |
<!-- ## This is required for new MapReduce API usage --> |
|
107 |
<property> |
|
108 |
<name>mapred.mapper.new-api</name> |
|
109 |
<value>true</value> |
|
110 |
</property> |
|
111 |
<property> |
|
112 |
<name>mapred.reducer.new-api</name> |
|
113 |
<value>true</value> |
|
114 |
</property> |
|
115 |
|
|
116 |
<!-- # Job-specific options --> |
|
117 |
<property> |
|
118 |
<name>dfs.blocksize</name> |
|
119 |
<value>32M</value> |
|
120 |
</property> |
|
121 |
<property> |
|
122 |
<name>mapred.output.compress</name> |
|
123 |
<value>false</value> |
|
124 |
</property> |
|
125 |
<property> |
|
126 |
<name>mapred.reduce.tasks.speculative.execution</name> |
|
127 |
<value>false</value> |
|
128 |
</property> |
|
129 |
<property> |
|
130 |
<name>mapred.reduce.tasks.speculative.execution</name> |
|
131 |
<value>false</value> |
|
132 |
</property> |
|
133 |
<property> |
|
134 |
<name>mapreduce.map.speculative</name> |
|
135 |
<value>false</value> |
|
136 |
</property> |
|
137 |
|
|
138 |
<!-- I/O FORMAT --> |
|
139 |
<!-- IMPORTANT: sets default delimeter used by text output writer. Required to fix issue with traling tab added between id and value in multiple outputs --> |
|
140 |
<property> |
|
141 |
<name>mapred.textoutputformat.separator</name> |
|
142 |
<value>${Stats_delim_Character}</value> |
|
143 |
</property> |
|
144 |
<!-- ## Names of all output ports --> |
|
145 |
|
|
146 |
<property> |
|
147 |
<name>mapreduce.multipleoutputs</name> |
|
148 |
|
|
149 |
<value>${out1} ${out2} ${out3} ${out4} ${out5} ${out6} ${out7} ${out8} ${out9} ${out10} ${out11} ${out12} ${out13} ${out14} ${out15} ${out16} ${out17} ${out18} ${out19} ${out20} |
|
150 |
</value> |
|
151 |
|
|
152 |
</property> |
|
153 |
<!-- datasource --> |
|
154 |
<property> |
|
155 |
<name>mapreduce.multipleoutputs.namedOutput.${out1}.key</name> |
|
156 |
<value>org.apache.hadoop.io.Text</value> |
|
157 |
</property> |
|
158 |
<property> |
|
159 |
<name>mapreduce.multipleoutputs.namedOutput.${out1}.value</name> |
|
160 |
<value>org.apache.hadoop.io.Text</value> |
|
161 |
</property> |
|
162 |
<property> |
|
163 |
<name>mapreduce.multipleoutputs.namedOutput.${out1}.format</name> |
|
164 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
165 |
</value> |
|
166 |
</property> |
|
167 |
<!-- datasourceLanguage --> |
|
168 |
<property> |
|
169 |
<name>mapreduce.multipleoutputs.namedOutput.${out2}.key</name> |
|
170 |
<value>org.apache.hadoop.io.Text</value> |
|
171 |
</property> |
|
172 |
<property> |
|
173 |
<name>mapreduce.multipleoutputs.namedOutput.${out2}.value</name> |
|
174 |
<value>org.apache.hadoop.io.Text</value> |
|
175 |
</property> |
|
176 |
<property> |
|
177 |
<name>mapreduce.multipleoutputs.namedOutput.${out2}.format</name> |
|
178 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
179 |
</value> |
|
180 |
</property> |
|
181 |
|
|
182 |
|
|
183 |
|
|
184 |
<!-- datasourceOrganization --> |
|
185 |
<property> |
|
186 |
<name>mapreduce.multipleoutputs.namedOutput.${out3}.key</name> |
|
187 |
<value>org.apache.hadoop.io.Text</value> |
|
188 |
</property> |
|
189 |
<property> |
|
190 |
<name>mapreduce.multipleoutputs.namedOutput.${out3}.value</name> |
|
191 |
<value>org.apache.hadoop.io.Text</value> |
|
192 |
</property> |
|
193 |
<property> |
|
194 |
<name>mapreduce.multipleoutputs.namedOutput.${out3}.format</name> |
|
195 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
196 |
</value> |
|
197 |
</property> |
|
198 |
|
|
199 |
<!-- datasourceTopic --> |
|
200 |
<property> |
|
201 |
<name>mapreduce.multipleoutputs.namedOutput.${out4}.key</name> |
|
202 |
<value>org.apache.hadoop.io.Text</value> |
|
203 |
</property> |
|
204 |
<property> |
|
205 |
<name>mapreduce.multipleoutputs.namedOutput.${out4}.value</name> |
|
206 |
<value>org.apache.hadoop.io.Text</value> |
|
207 |
</property> |
|
208 |
<property> |
|
209 |
<name>mapreduce.multipleoutputs.namedOutput.${out4}.format</name> |
|
210 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
211 |
</value> |
|
212 |
</property> |
|
213 |
|
|
214 |
<!-- resultDatasource --> |
|
215 |
<property> |
|
216 |
<name>mapreduce.multipleoutputs.namedOutput.${out5}.key</name> |
|
217 |
<value>org.apache.hadoop.io.Text</value> |
|
218 |
</property> |
|
219 |
<property> |
|
220 |
<name>mapreduce.multipleoutputs.namedOutput.${out5}.value</name> |
|
221 |
<value>org.apache.hadoop.io.Text</value> |
|
222 |
</property> |
|
223 |
<property> |
|
224 |
<name>mapreduce.multipleoutputs.namedOutput.${out5}.format</name> |
|
225 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
226 |
</value> |
|
227 |
</property> |
|
228 |
<!-- organization --> |
|
229 |
<property> |
|
230 |
<name>mapreduce.multipleoutputs.namedOutput.${out6}.key</name> |
|
231 |
<value>org.apache.hadoop.io.Text</value> |
|
232 |
</property> |
|
233 |
<property> |
|
234 |
<name>mapreduce.multipleoutputs.namedOutput.${out6}.value</name> |
|
235 |
<value>org.apache.hadoop.io.Text</value> |
|
236 |
</property> |
|
237 |
<property> |
|
238 |
<name>mapreduce.multipleoutputs.namedOutput.${out6}.format</name> |
|
239 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
240 |
</value> |
|
241 |
</property> |
|
242 |
|
|
243 |
<!-- projectOrganization --> |
|
244 |
<property> |
|
245 |
<name>mapreduce.multipleoutputs.namedOutput.${out7}.key</name> |
|
246 |
<value>org.apache.hadoop.io.Text</value> |
|
247 |
</property> |
|
248 |
<property> |
|
249 |
<name>mapreduce.multipleoutputs.namedOutput.${out7}.value</name> |
|
250 |
<value>org.apache.hadoop.io.Text</value> |
|
251 |
</property> |
|
252 |
<property> |
|
253 |
<name>mapreduce.multipleoutputs.namedOutput.${out7}.format</name> |
|
254 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
255 |
</value> |
|
256 |
</property> |
|
257 |
<!-- resultProject --> |
|
258 |
<property> |
|
259 |
<name>mapreduce.multipleoutputs.namedOutput.${out8}.key</name> |
|
260 |
<value>org.apache.hadoop.io.Text</value> |
|
261 |
</property> |
|
262 |
<property> |
|
263 |
<name>mapreduce.multipleoutputs.namedOutput.${out8}.value</name> |
|
264 |
<value>org.apache.hadoop.io.Text</value> |
|
265 |
</property> |
|
266 |
<property> |
|
267 |
<name>mapreduce.multipleoutputs.namedOutput.${out8}.format</name> |
|
268 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
269 |
</value> |
|
270 |
</property> |
|
271 |
|
|
272 |
<!-- project --> |
|
273 |
<property> |
|
274 |
<name>mapreduce.multipleoutputs.namedOutput.${out9}.key</name> |
|
275 |
<value>org.apache.hadoop.io.Text</value> |
|
276 |
</property> |
|
277 |
<property> |
|
278 |
<name>mapreduce.multipleoutputs.namedOutput.${out9}.value</name> |
|
279 |
<value>org.apache.hadoop.io.Text</value> |
|
280 |
</property> |
|
281 |
<property> |
|
282 |
<name>mapreduce.multipleoutputs.namedOutput.${out9}.format</name> |
|
283 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
284 |
</value> |
|
285 |
</property> |
|
286 |
|
|
287 |
<!-- resultConcept --> |
|
288 |
<property> |
|
289 |
<name>mapreduce.multipleoutputs.namedOutput.${out10}.key</name> |
|
290 |
<value>org.apache.hadoop.io.Text</value> |
|
291 |
</property> |
|
292 |
<property> |
|
293 |
<name>mapreduce.multipleoutputs.namedOutput.${out10}.value</name> |
|
294 |
<value>org.apache.hadoop.io.Text</value> |
|
295 |
</property> |
|
296 |
<property> |
|
297 |
<name>mapreduce.multipleoutputs.namedOutput.${out10}.format</name> |
|
298 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
299 |
</value> |
|
300 |
</property> |
|
301 |
|
|
302 |
<!-- resultClaim --> |
|
303 |
<property> |
|
304 |
<name>mapreduce.multipleoutputs.namedOutput.${out11}.key</name> |
|
305 |
<value>org.apache.hadoop.io.Text</value> |
|
306 |
</property> |
|
307 |
<property> |
|
308 |
<name>mapreduce.multipleoutputs.namedOutput.${out11}.value</name> |
|
309 |
<value>org.apache.hadoop.io.Text</value> |
|
310 |
</property> |
|
311 |
<property> |
|
312 |
<name>mapreduce.multipleoutputs.namedOutput.${out11}.format</name> |
|
313 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
314 |
</value> |
|
315 |
</property> |
|
316 |
|
|
317 |
<!-- resultClassification --> |
|
318 |
<property> |
|
319 |
<name>mapreduce.multipleoutputs.namedOutput.${out12}.key</name> |
|
320 |
<value>org.apache.hadoop.io.Text</value> |
|
321 |
</property> |
|
322 |
<property> |
|
323 |
<name>mapreduce.multipleoutputs.namedOutput.${out12}.value</name> |
|
324 |
<value>org.apache.hadoop.io.Text</value> |
|
325 |
</property> |
|
326 |
<property> |
|
327 |
<name>mapreduce.multipleoutputs.namedOutput.${out12}.format</name> |
|
328 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
329 |
</value> |
|
330 |
</property> |
|
331 |
|
|
332 |
<!-- resultLanguage --> |
|
333 |
<property> |
|
334 |
<name>mapreduce.multipleoutputs.namedOutput.${out13}.key</name> |
|
335 |
<value>org.apache.hadoop.io.Text</value> |
|
336 |
</property> |
|
337 |
<property> |
|
338 |
<name>mapreduce.multipleoutputs.namedOutput.${out13}.value</name> |
|
339 |
<value>org.apache.hadoop.io.Text</value> |
|
340 |
</property> |
|
341 |
<property> |
|
342 |
<name>mapreduce.multipleoutputs.namedOutput.${out13}.format</name> |
|
343 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
344 |
</value> |
|
345 |
</property> |
|
346 |
|
|
347 |
<!-- resultProject --> |
|
348 |
<property> |
|
349 |
<name>mapreduce.multipleoutputs.namedOutput.${out14}.key</name> |
|
350 |
<value>org.apache.hadoop.io.Text</value> |
|
351 |
</property> |
|
352 |
<property> |
|
353 |
<name>mapreduce.multipleoutputs.namedOutput.${out14}.value</name> |
|
354 |
<value>org.apache.hadoop.io.Text</value> |
|
355 |
</property> |
|
356 |
<property> |
|
357 |
<name>mapreduce.multipleoutputs.namedOutput.${out14}.format</name> |
|
358 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
359 |
</value> |
|
360 |
</property> |
|
361 |
<!-- resultResult --> |
|
362 |
<property> |
|
363 |
<name>mapreduce.multipleoutputs.namedOutput.${out15}.key</name> |
|
364 |
<value>org.apache.hadoop.io.Text</value> |
|
365 |
</property> |
|
366 |
<property> |
|
367 |
<name>mapreduce.multipleoutputs.namedOutput.${out15}.value</name> |
|
368 |
<value>org.apache.hadoop.io.Text</value> |
|
369 |
</property> |
|
370 |
<property> |
|
371 |
<name>mapreduce.multipleoutputs.namedOutput.${out15}.format</name> |
|
372 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
373 |
</value> |
|
374 |
</property> |
|
375 |
<!-- resultTopic --> |
|
376 |
<property> |
|
377 |
<name>mapreduce.multipleoutputs.namedOutput.${out16}.key</name> |
|
378 |
<value>org.apache.hadoop.io.Text</value> |
|
379 |
</property> |
|
380 |
<property> |
|
381 |
<name>mapreduce.multipleoutputs.namedOutput.${out16}.value</name> |
|
382 |
<value>org.apache.hadoop.io.Text</value> |
|
383 |
</property> |
|
384 |
<property> |
|
385 |
<name>mapreduce.multipleoutputs.namedOutput.${out16}.format</name> |
|
386 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
387 |
</value> |
|
388 |
</property> |
|
389 |
|
|
390 |
<!-- resultDatasource --> |
|
391 |
<property> |
|
392 |
<name>mapreduce.multipleoutputs.namedOutput.${out17}.key</name> |
|
393 |
<value>org.apache.hadoop.io.Text</value> |
|
394 |
</property> |
|
395 |
<property> |
|
396 |
<name>mapreduce.multipleoutputs.namedOutput.${out17}.value</name> |
|
397 |
<value>org.apache.hadoop.io.Text</value> |
|
398 |
</property> |
|
399 |
<property> |
|
400 |
<name>mapreduce.multipleoutputs.namedOutput.${out17}.format</name> |
|
401 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
402 |
</value> |
|
403 |
</property> |
|
404 |
|
|
405 |
|
|
406 |
|
|
407 |
<!-- result --> |
|
408 |
<property> |
|
409 |
<name>mapreduce.multipleoutputs.namedOutput.${out18}.key</name> |
|
410 |
<value>org.apache.hadoop.io.Text</value> |
|
411 |
</property> |
|
412 |
<property> |
|
413 |
<name>mapreduce.multipleoutputs.namedOutput.${out18}.value</name> |
|
414 |
<value>org.apache.hadoop.io.Text</value> |
|
415 |
</property> |
|
416 |
<property> |
|
417 |
<name>mapreduce.multipleoutputs.namedOutput.${out18}.format</name> |
|
418 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
419 |
</value> |
|
420 |
</property> |
|
421 |
|
|
422 |
<!-- claim --> |
|
423 |
<property> |
|
424 |
<name>mapreduce.multipleoutputs.namedOutput.${out19}.key</name> |
|
425 |
<value>org.apache.hadoop.io.Text</value> |
|
426 |
</property> |
|
427 |
<property> |
|
428 |
<name>mapreduce.multipleoutputs.namedOutput.${out19}.value</name> |
|
429 |
<value>org.apache.hadoop.io.Text</value> |
|
430 |
</property> |
|
431 |
<property> |
|
432 |
<name>mapreduce.multipleoutputs.namedOutput.${out19}.format</name> |
|
433 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
434 |
</value> |
|
435 |
</property> |
|
436 |
<!-- cncept --> |
|
437 |
<property> |
|
438 |
<name>mapreduce.multipleoutputs.namedOutput.${out20}.key</name> |
|
439 |
<value>org.apache.hadoop.io.Text</value> |
|
440 |
</property> |
|
441 |
<property> |
|
442 |
<name>mapreduce.multipleoutputs.namedOutput.${out20}.value</name> |
|
443 |
<value>org.apache.hadoop.io.Text</value> |
|
444 |
</property> |
|
445 |
<property> |
|
446 |
<name>mapreduce.multipleoutputs.namedOutput.${out20}.format</name> |
|
447 |
<value>org.apache.hadoop.mapreduce.lib.output.TextOutputFormat |
|
448 |
</value> |
|
449 |
</property> |
|
450 |
|
|
451 |
|
|
452 |
<!-- ## Classes of mapper and reducer --> |
|
453 |
|
|
454 |
<property> |
|
455 |
<name>mapreduce.map.class</name> |
|
456 |
<value>eu.dnetlib.data.mapreduce.hbase.statsExport.StatsMapper |
|
457 |
</value> |
|
458 |
</property> |
|
459 |
<property> |
|
460 |
<name>mapreduce.reduce.class</name> |
|
461 |
<value>eu.dnetlib.data.mapreduce.hbase.statsExport.StatsReducer |
|
462 |
</value> |
|
463 |
</property> |
|
464 |
<property> |
|
465 |
<name>io.serializations</name> |
|
466 |
<value>org.apache.hadoop.io.serializer.WritableSerialization |
|
467 |
</value> |
|
468 |
</property> |
|
469 |
<!-- ## Custom config --> |
|
470 |
|
|
471 |
<!--delim character used to seperate fields in hdfs dump files <property> --> |
|
472 |
<property> |
|
473 |
<name>stats.delim</name> |
|
474 |
<value>${Stats_delim_Character}</value> |
|
475 |
</property> |
|
476 |
<!--default string for Null String Values --> |
|
477 |
<property> |
|
478 |
<name>stats.nullString</name> |
|
479 |
<value>${Stats_null_String_Field}</value> |
|
480 |
</property> |
|
481 |
<!--default string for Null Numeric Values --> |
|
482 |
<property> |
|
483 |
<name>stats.nullNum</name> |
|
484 |
<value>${Stats_null_Numeric_Field}</value> |
|
485 |
</property> |
|
486 |
<property> |
|
487 |
<name>stats.enclChar</name> |
|
488 |
<value>${Stats_enclosing_Character}</value> |
|
489 |
</property> |
|
490 |
|
|
491 |
|
|
492 |
<!--source hbase table --> |
|
493 |
<property> |
|
494 |
<name>hbase.mapreduce.inputtable</name> |
|
495 |
<value>${Stats_Hbase_Source_Table}</value> |
|
496 |
</property> |
|
497 |
<property> |
|
498 |
<!-- mapping of protos entities to tables in the relDB --> |
|
499 |
<name>stats.dbTablesMap</name> |
|
500 |
<value>${Stats_db_table_map}</value> |
|
501 |
</property> |
|
502 |
|
|
503 |
<!-- This directory does not correspond to a data store. In fact, this directory only contains multiple data stores. It has to be set to the name of the workflow node. --> |
|
504 |
<property> |
|
505 |
<name>mapred.output.dir</name> |
|
506 |
<value>${Stats_output_Path}</value> |
|
507 |
</property> |
|
508 |
<property> |
|
509 |
<name>stats.indexConf</name> |
|
510 |
<value>${Stats_indexConf}</value> |
|
511 |
</property> |
|
512 |
<!-- ## Workflow node parameters --> |
|
513 |
<property> |
|
514 |
<name>mapred.reduce.tasks</name> |
|
515 |
<value>${numReducers}</value> |
|
516 |
</property> |
|
517 |
</configuration> |
|
518 |
</map-reduce> |
|
519 |
<ok to="exportContext" /> |
|
520 |
<error to="fail" /> |
|
521 |
</action> |
|
522 |
|
|
523 |
|
|
524 |
<action name="exportContext"> |
|
525 |
<java> |
|
526 |
|
|
527 |
<prepare> |
|
528 |
</prepare> |
|
529 |
<configuration> |
|
530 |
<property> |
|
531 |
<name>mapred.job.queue.name</name> |
|
532 |
<value>${queueName}</value> |
|
533 |
</property> |
|
534 |
</configuration> |
|
535 |
|
|
536 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
537 |
<arg>-SworkingDir=${workingDir}</arg> |
|
538 |
<arg>eu.dnetlib.iis.core.workflows.stats.ExportContextWrapper</arg> |
|
539 |
<arg>-PStats_output_Path=${Stats_output_Path}</arg> |
|
540 |
<arg>-PStats_ContextResourceXML=${ContextResourceXML}</arg> |
|
541 |
|
|
542 |
</java> |
|
543 |
<ok to="prepareDatabase" /> |
|
544 |
<error to="fail" /> |
|
545 |
</action> |
|
546 |
|
|
547 |
<action name="prepareDatabase"> |
|
548 |
<java> |
|
549 |
|
|
550 |
<prepare> |
|
551 |
</prepare> |
|
552 |
<configuration> |
|
553 |
<property> |
|
554 |
<name>mapred.job.queue.name</name> |
|
555 |
<value>${queueName}</value> |
|
556 |
</property> |
|
557 |
</configuration> |
|
558 |
|
|
559 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
560 |
<arg>-SworkingDir=${workingDir}</arg> |
|
561 |
<arg>eu.dnetlib.iis.core.workflows.stats.DBInitWrapper</arg> |
|
562 |
|
|
563 |
<arg>-PStats_db_Url=${Stats_db_Url}</arg> |
|
564 |
<arg>-PStats_db_User=${Stats_db_User}</arg> |
|
565 |
<arg>-PStats_db_Pass=${Stats_db_Pass}</arg> |
|
566 |
<arg>-PStats_db_Driver=${Stats_db_Driver}</arg> |
|
567 |
|
|
568 |
</java> |
|
569 |
<ok to="sqoopImport" /> |
|
570 |
<error to="fail" /> |
|
571 |
</action> |
|
572 |
|
|
573 |
<action name="sqoopImport"> |
|
574 |
<java> |
|
575 |
<prepare> |
|
576 |
</prepare> |
|
577 |
<configuration> |
|
578 |
<property> |
|
579 |
<name>mapred.job.queue.name</name> |
|
580 |
<value>${queueName}</value> |
|
581 |
</property> |
|
582 |
|
|
583 |
<property> |
|
584 |
<name>oozie.sqoop.log.level</name> |
|
585 |
<value>DEBUG</value> |
|
586 |
</property> |
|
587 |
|
|
588 |
</configuration> |
|
589 |
|
|
590 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
591 |
<arg>-SworkingDir=${workingDir}</arg> |
|
592 |
<arg>eu.dnetlib.iis.core.workflows.stats.SqoopWrapper</arg> |
|
593 |
|
|
594 |
<arg>-PStats_db_Url=${Stats_db_Url}</arg> |
|
595 |
<arg>-PStats_db_User=${Stats_db_User}</arg> |
|
596 |
<arg>-PStats_db_Pass=${Stats_db_Pass}</arg> |
|
597 |
|
|
598 |
<arg>-PStats_output_Path=${Stats_output_Path}</arg> |
|
599 |
<arg>-PStats_sqoop_RecsPerStatement=${Stats_sqoop_RecsPerStatement} |
|
600 |
</arg> |
|
601 |
<arg>-PStats_sqoop_ReducersCount=${Stats_sqoop_ReducersCount}</arg> |
|
602 |
<arg>-PStats_sqoop_StatementPerTrans=${Stats_sqoop_StatementPerTrans} |
|
603 |
</arg> |
|
604 |
<arg>-PStats_delim_Character=${Stats_delim_Character}</arg> |
|
605 |
<arg>-PStats_db_table_map=${Stats_db_table_map}</arg> |
|
606 |
<arg>-PStats_enclosing_Character=${Stats_enclosing_Character} </arg> |
|
607 |
|
|
608 |
</java> |
|
609 |
<ok to="finalizeDatabase" /> |
|
610 |
<error to="fail" /> |
|
611 |
</action> |
|
612 |
|
|
613 |
<action name="finalizeDatabase"> |
|
614 |
<java> |
|
615 |
|
|
616 |
<prepare> |
|
617 |
</prepare> |
|
618 |
<configuration> |
|
619 |
<property> |
|
620 |
<name>mapred.job.queue.name</name> |
|
621 |
<value>${queueName}</value> |
|
622 |
</property> |
|
623 |
</configuration> |
|
624 |
|
|
625 |
<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class> |
|
626 |
<arg>-SworkingDir=${workingDir}</arg> |
|
627 |
<arg>eu.dnetlib.iis.core.workflows.stats.DBFinalizeWrapper</arg> |
|
628 |
<arg>-PStats_db_Url=${Stats_db_Url}</arg> |
|
629 |
<arg>-PStats_db_User=${Stats_db_User}</arg> |
|
630 |
<arg>-PStats_db_Pass=${Stats_db_Pass}</arg> |
|
631 |
<arg>-PStats_db_Driver=${Stats_db_Driver}</arg> |
|
632 |
|
|
633 |
|
|
634 |
</java> |
|
635 |
<ok to="end" /> |
|
636 |
<error to="fail" /> |
|
637 |
</action> |
|
638 |
<kill name="fail"> |
|
639 |
<message> |
|
640 |
Unfortunately, the process failed -- error message: |
|
641 |
[${wf:errorMessage(wf:lastErrorNode())}] |
|
642 |
</message> |
|
643 |
</kill> |
|
644 |
<end name="end" /> |
|
645 |
</workflow-app> |
modules/dnet-openaire-stats-workflow/src/main/resources/eu/dnetlib/iis/core/examples/simpleTest/oozie_app/workflow.xml | ||
---|---|---|
1 |
<workflow-app name="test-core_examples_javamapreduce_stats" xmlns="uri:oozie:workflow:0.4"> |
|
2 |
<!-- map reduce job that exports hbase data and prepares them for import to the relation database used for statistics generation --> |
|
3 |
|
|
1 |
<workflow-app name="test " xmlns="uri:oozie:workflow:0.4"> |
|
2 |
|
|
4 | 3 |
<global> |
5 | 4 |
<job-tracker>${jobTracker}</job-tracker> |
6 | 5 |
<name-node>${nameNode}</name-node> |
... | ... | |
28 | 27 |
|
29 | 28 |
</java> |
30 | 29 |
</action> |
31 |
|
|
32 |
|
|
33 |
|
|
34 |
<action name='get-scanner'> |
|
35 |
<java> |
|
36 |
<main-class>eu.dnetlib.iis.core.workflows.stats.HbaseScannerGenerator |
|
37 |
</main-class> |
|
38 |
<!-- column families: --> |
|
39 |
|
|
40 |
<arg> |
|
41 |
-f datasource |
|
42 |
<!-- , datasourceOrganization_provision_provides ,organization, --> |
|
43 |
<!-- projectOrganization_participation_isParticipant, --> |
|
44 |
<!-- project --> |
|
45 |
<!-- ,projectOrganization_participation_hasParticipant --> |
|
46 |
<!-- , --> |
|
47 |
<!-- result --> |
|
48 |
<!-- , resultProject_outcome_produces, --> |
|
49 |
<!-- personResult_authorship_hasAuthor,resultResult_publicationDataset_isRelatedTo --> |
|
50 |
</arg> |
|
51 |
|
|
52 |
<capture-output /> |
|
53 |
</java> |
|
54 |
<ok to="mr_export" /> |
|
55 |
<error to="fail" /> |
|
56 |
</action> |
|
57 |
<action name="mr_export"> |
|
58 |
<map-reduce> |
|
59 |
|
|
60 |
<prepare> |
|
61 |
<delete path="${nameNode}${Stats_output_Path}" /> |
|
62 |
|
|
63 |
</prepare> |
|
64 |
<configuration> |
|
65 |
<property> |
|
66 |
<name>hbase.mapreduce.scan</name> |
|
67 |
<value>${wf:actionData('get-scanner')['scan']}</value> |
|
68 |
</property> |
|
69 |
<property> |
|
70 |
<name>hbase.rootdir</name> |
|
71 |
<value>hdfs://nmis-hadoop-cluster/hbase</value> |
|
72 |
</property> |
|
73 |
|
|
74 |
<property> |
|
75 |
<name>hbase.security.authentication</name> |
|
76 |
<value>simple</value> |
|
77 |
</property> |
|
78 |
<!-- ZOOKEEPER --> |
|
79 |
|
|
80 |
<property> |
|
81 |
<name>hbase.zookeeper.quorum</name> |
|
82 |
<value> |
|
83 |
quorum1.t.hadoop.research-infrastructures.eu,quorum2.t.hadoop.research-infrastructures.eu,quorum3.t.hadoop.research-infrastructures.eu,quorum4.t.hadoop.research-infrastructures.eu,jobtracker.t.hadoop.research-infrastructures.eu |
|
84 |
</value> |
|
85 |
</property> |
|
86 |
<property> |
|
87 |
<name>zookeeper.znode.rootserver</name> |
|
88 |
<value>root-region-server</value> |
|
89 |
</property> |
|
90 |
|
|
91 |
<property> |
|
92 |
<name>hbase.zookeeper.property.clientPort</name> |
|
93 |
<value>2182</value> |
|
94 |
</property> |
|
95 |
|
|
96 |
|
|
97 |
<!-- MR IO --> |
|
98 |
|
|
99 |
|
|
100 |
<property> |
|
101 |
<name>mapreduce.inputformat.class</name> |
|
102 |
<value>org.apache.hadoop.hbase.mapreduce.TableInputFormat</value> |
|
103 |
</property> |
|
104 |
|
|
105 |
<property> |
|
106 |
<name>mapred.mapoutput.key.class</name> |
|
107 |
<value>org.apache.hadoop.io.Text</value> |
|
108 |
</property> |
|
109 |
<property> |
|
110 |
<name>mapred.mapoutput.value.class</name> |
|
111 |
<value>org.apache.hadoop.hbase.io.ImmutableBytesWritable</value> |
Also available in: Unified diff