antonis.lempesis
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 1
Code Issues Pull Requests Projects Releases Wiki Activity

defaults fixed in the cleaning workflow forces result.publisher to NULL when result.publisher.value in empty

This commit is contained in:
Claudio Atzori 2020-07-30 17:03:53 +02:00
parent 4bbfcf1ac6
commit cd631bb5bc
3 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleanGraphSparkJob.java
View File

@ -173,6 +173,9 @@ public class CleanGraphSparkJob {
} else if (value instanceof Result) { } else if (value instanceof Result) {
Result r = (Result) value; Result r = (Result) value;
if (Objects.nonNull(r.getPublisher()) && StringUtils.isBlank(r.getPublisher().getValue())) {
r.setPublisher(null);
}
if (Objects.isNull(r.getLanguage()) || StringUtils.isBlank(r.getLanguage().getClassid())) { if (Objects.isNull(r.getLanguage()) || StringUtils.isBlank(r.getLanguage().getClassid())) {
r r
.setLanguage( .setLanguage(

3
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctionTest.java
View File

@ -66,6 +66,8 @@ public class CleaningFunctionTest {
assertNotNull(p_out); assertNotNull(p_out);
assertNotNull(p_out.getPublisher());
assertNull(p_out.getPublisher().getValue());
assertEquals("und", p_out.getLanguage().getClassid()); assertEquals("und", p_out.getLanguage().getClassid());
assertEquals("Undetermined", p_out.getLanguage().getClassname()); assertEquals("Undetermined", p_out.getLanguage().getClassname());
@ -88,6 +90,7 @@ public class CleaningFunctionTest {
Publication p_defaults = CleanGraphSparkJob.fixDefaults(p_out); Publication p_defaults = CleanGraphSparkJob.fixDefaults(p_out);
assertEquals("CLOSED", p_defaults.getBestaccessright().getClassid()); assertEquals("CLOSED", p_defaults.getBestaccessright().getClassid());
assertNull(p_out.getPublisher());
getAuthorPids(p_defaults).forEach(pid -> { getAuthorPids(p_defaults).forEach(pid -> {
System.out System.out

3
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/result.json
View File

@ -208,6 +208,9 @@
} }
], ],
"bestaccessright": null, "bestaccessright": null,
"publisher": {
"value": null
},
"collectedfrom": [ "collectedfrom": [
{ {
"key": "10|CSC_________::a2b9ce8435390bcbfc05f3cae3948747", "key": "10|CSC_________::a2b9ce8435390bcbfc05f3cae3948747",