Skip to content

Commit e024182

Browse files
authored
Merge pull request #1539 from alliance-genome/better_reporting
Added better reporting for counts on all the indexers
2 parents 76a40b7 + f55f0ac commit e024182

33 files changed

+103
-83
lines changed

agr_indexer/src/main/java/org/alliancegenome/indexer/config/IndexerConfig.java

Lines changed: 18 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -28,39 +28,41 @@
2828
public enum IndexerConfig {
2929

3030
// Neo Indexers
31-
ModelIndexer("model", ModelIndexer.class, 4, 1500, 1426, 4, 1, false),
31+
ModelIndexer("model", ModelIndexer.class, 4, 1500, 1426, 4, 1, true),
3232

3333
// Curation Indexers
3434

3535
// Run Parallelly
3636
ParalogyIndexer("paralogy", GeneToGeneParalogyIndexer.class, 4, 5000, 5000, 8, 1, true),
3737
GOSearchResultCurationIndexer("goSearchResult", GOSearchResultCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
38-
HTPDatasetSearchResultCurationIndexer("htpDatasetSearchResult", HTPDatasetSearchResultCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
39-
LiteratureIndexer("literature", LiteratureIndexer.class, 4, 5000, 5000, 1, 1, true),
40-
GeneGeneticInteractionIndexers("geneGeneticInteraction", GeneGeneticInteractionCurationIndexer.class, 4, 1500, 1500, 2, 1, true),
4138
AffectedGenomicModelIndexer("affectedGenomicModels", AffectedGenomicModelCurationIndexer.class, 4, 1500, 1500, 8, 1, true),
42-
DiseaseSummaryIndexer("diseaseSummary", DiseaseSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
43-
DiseaseSearchResultIndexer("diseaseSearchResult", DiseaseSearchResultCurationIndexer.class, 8, 50, 50, 4, 1, true),
4439

40+
GeneSearchResultCurationIndexer("geneSearchResult", GeneSearchResultCurationIndexer.class, 4, 1000, 1500, 4, 1, true),
41+
GeneSummaryIndexer("geneSummary", GeneSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
42+
43+
DiseaseSearchResultIndexer("diseaseSearchResult", DiseaseSearchResultCurationIndexer.class, 8, 50, 50, 4, 1, true),
44+
VariantSummaryIndexer("variantSummary", VariantSummaryCurationIndexer.class, 1, 3000, 1500, 8, 1, false),
45+
GeneGeneticInteractionIndexers("geneGeneticInteraction", GeneGeneticInteractionCurationIndexer.class, 4, 1500, 1500, 2, 1, true),
46+
HTPDatasetSearchResultCurationIndexer("htpDatasetSearchResult", HTPDatasetSearchResultCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
47+
LiteratureIndexer("literature", LiteratureIndexer.class, 4, 5000, 5000, 1, 1, true),
48+
GeneExpressionAnnotationIndexer("geneExpressionAnnotation", GeneExpressionAnnotationIndexer.class, 8, 125, 2000, 4, 1, true),
4549
SiteMapAccessionCurationIndexer("sitemap", SiteMapAccessionCurationIndexer.class, 4, 1500, 1500, 8, 1, true),
50+
DiseaseSummaryIndexer("diseaseSummary", DiseaseSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, true),
51+
// neo model indexer
52+
TransgenicAlleleIndexer("transgenicAlleles", TransgenicAlleleCurationIndexer.class, 1, 3000, 1500, 8, 1, true),
4653
GeneExpressionRibbonSummaryIndexer("geneExpressionRibbonSummary", GeneExpressionRibbonSummaryIndexer.class, 1, 1, 1, 1, 1, true),
4754
ReleaseInfoIndexer("release", ReleaseInfoIndexer.class, 1, 1, 1, 1, 1, true),
4855

49-
// Run Sequentially
56+
// Run Sequentially -- typically take a lot of RAM or do consolidation in memory
5057
AlleleSummaryIndexer("alleleSummary", AlleleSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, false),
51-
GeneSummaryIndexer("geneSummary", GeneSummaryCurationIndexer.class, 4, 1500, 1500, 4, 1, false),
5258
GeneToGeneOrthologyIndexer("geneToGeneOrthology", GeneToGeneOrthologyIndexer.class, 4, 2500, 2500, 8, 1, false),
5359

54-
GeneExpressionAnnotationIndexer("geneExpressionAnnotation", GeneExpressionAnnotationIndexer.class, 8, 125, 2000, 4, 1, false),
55-
56-
PhenotypeAnnotationIndexer("phenotypeAnnotation", PhenotypeAnnotationCurationIndexer.class, 4, 1500, 1500, 2, 1, false),
57-
TransgenicAlleleIndexer("transgenicAlleles", TransgenicAlleleCurationIndexer.class, 1, 3000, 1500, 8, 1, false),
5860
GeneMolecularInteractionIndexers("geneMolecularInteraction", GeneMolecularInteractionCurationIndexer.class, 4, 1500, 1500, 2, 1, false),
61+
62+
PhenotypeAnnotationIndexer("phenotypeAnnotation", PhenotypeAnnotationCurationIndexer.class, 4, 1500, 1500, 2, 1, false),
5963
DiseaseAnnotationIndexer("diseaseAnnotation", DiseaseAnnotationCurationIndexer.class, 1, 1500, 1500, 2, 1, false),
60-
VariantSummaryIndexer("variantSummary", VariantSummaryCurationIndexer.class, 1, 3000, 1500, 8, 1, false),
61-
62-
GeneSearchResultCurationIndexer("geneSearchResult", GeneSearchResultCurationIndexer.class, 4, 1000, 1500, 4, 1, false),
63-
64+
65+
6466
;
6567

6668

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/DatasetIndexer.java

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@
66
import org.alliancegenome.core.translators.document.HTPDatasetTranslator;
77
import org.alliancegenome.es.index.site.cache.DatasetDocumentCache;
88
import org.alliancegenome.es.index.site.document.SearchableItemDocument;
9+
import org.alliancegenome.es.util.ProcessDisplayHelper;
910
import org.alliancegenome.exceptional.client.ExceptionCatcher;
1011
import org.alliancegenome.indexer.config.IndexerConfig;
1112
import org.alliancegenome.neo4j.entity.node.HTPDataset;
@@ -24,7 +25,7 @@ public DatasetIndexer(IndexerConfig config) {
2425
}
2526

2627
@Override
27-
public void index() {
28+
public void index(ProcessDisplayHelper display) {
2829
try {
2930
repo = new DatasetIndexerRepository();
3031
cache = repo.getCache();

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/DiseaseIndexer.java

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@
77
import org.alliancegenome.core.translators.document.DiseaseTranslator;
88
import org.alliancegenome.es.index.site.cache.DiseaseDocumentCache;
99
import org.alliancegenome.es.index.site.document.SearchableItemDocument;
10+
import org.alliancegenome.es.util.ProcessDisplayHelper;
1011
import org.alliancegenome.exceptional.client.ExceptionCatcher;
1112
import org.alliancegenome.indexer.config.IndexerConfig;
1213
import org.alliancegenome.neo4j.entity.node.DOTerm;
@@ -25,7 +26,7 @@ public DiseaseIndexer(IndexerConfig config) {
2526
}
2627

2728
@Override
28-
public void index() {
29+
public void index(ProcessDisplayHelper display) {
2930
try {
3031
DiseaseIndexerRepository diseaseIndexerRepository = new DiseaseIndexerRepository();
3132
diseaseDocumentCache = diseaseIndexerRepository.getDiseaseDocumentCache();

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/GeneIndexer.java

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,6 +8,7 @@
88
import org.alliancegenome.core.translators.document.GeneTranslator;
99
import org.alliancegenome.es.index.site.cache.GeneDocumentCache;
1010
import org.alliancegenome.es.index.site.document.SearchableItemDocument;
11+
import org.alliancegenome.es.util.ProcessDisplayHelper;
1112
import org.alliancegenome.exceptional.client.ExceptionCatcher;
1213
import org.alliancegenome.indexer.config.IndexerConfig;
1314
import org.alliancegenome.neo4j.entity.node.Gene;
@@ -25,7 +26,7 @@ public GeneIndexer(IndexerConfig config) {
2526
}
2627

2728
@Override
28-
public void index() {
29+
public void index(ProcessDisplayHelper display) {
2930

3031
try {
3132
LinkedBlockingDeque<String> queue = new LinkedBlockingDeque<>();

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/GoIndexer.java

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,7 @@
44

55
import org.alliancegenome.core.translators.document.GoTranslator;
66
import org.alliancegenome.es.index.site.document.SearchableItemDocument;
7+
import org.alliancegenome.es.util.ProcessDisplayHelper;
78
import org.alliancegenome.indexer.config.IndexerConfig;
89
import org.alliancegenome.neo4j.entity.node.GOTerm;
910
import org.alliancegenome.neo4j.repository.GoRepository;
@@ -21,7 +22,7 @@ public GoIndexer(IndexerConfig config) {
2122
}
2223

2324
@Override
24-
public void index() {
25+
public void index(ProcessDisplayHelper display) {
2526

2627
goRepo = new GoRepository();
2728
goTrans = new GoTranslator();

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/Indexer.java

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -104,7 +104,7 @@ public void runIndex() {
104104
try {
105105
Instant start = Instant.now();
106106
display.startProcess(getClass().getSimpleName());
107-
index();
107+
index(display);
108108
log.info("Waiting for bulkProcessor to finish");
109109
bulkProcessor.flush();
110110
bulkProcessor.awaitClose(30L, TimeUnit.DAYS);
@@ -126,7 +126,7 @@ public void run() {
126126
try {
127127
Instant start = Instant.now();
128128
display.startProcess(getClass().getSimpleName());
129-
index();
129+
index(display);
130130
log.info("Waiting for bulkProcessor to finish");
131131
bulkProcessor.flush();
132132
bulkProcessor.awaitClose(30L, TimeUnit.DAYS);
@@ -213,7 +213,7 @@ protected <T> List<List<T>> partition(List<T> list, int size) {
213213
return parts;
214214
}
215215

216-
protected abstract void index();
216+
protected abstract void index(ProcessDisplayHelper display);
217217

218218
protected abstract void startSingleThread(LinkedBlockingDeque<String> queue);
219219

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/LiteratureIndexer.java

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@
77

88
import org.alliancegenome.api.entity.LiteratureSummaryDocument;
99
import org.alliancegenome.core.config.ConfigHelper;
10+
import org.alliancegenome.es.util.ProcessDisplayHelper;
1011
import org.alliancegenome.exceptional.client.ExceptionCatcher;
1112
import org.alliancegenome.indexer.config.IndexerConfig;
1213
import org.alliancegenome.indexer.indexers.curation.interfaces.ElasticSearchInterface;
@@ -27,7 +28,7 @@ public LiteratureIndexer(IndexerConfig indexerConfig) {
2728

2829
// with multiple thread
2930
@Override
30-
protected void index() {
31+
protected void index(ProcessDisplayHelper display) {
3132
log.info("IndexName: " + indexName);
3233
Map<String, Object> countObject = literatureESApi.count(indexName);
3334
try {

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/ModelIndexer.java

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@
66
import org.alliancegenome.core.translators.document.ModelTranslator;
77
import org.alliancegenome.es.index.site.cache.ModelDocumentCache;
88
import org.alliancegenome.es.index.site.document.SearchableItemDocument;
9+
import org.alliancegenome.es.util.ProcessDisplayHelper;
910
import org.alliancegenome.exceptional.client.ExceptionCatcher;
1011
import org.alliancegenome.indexer.config.IndexerConfig;
1112
import org.alliancegenome.neo4j.entity.node.AffectedGenomicModel;
@@ -24,13 +25,13 @@ public ModelIndexer(IndexerConfig config) {
2425
}
2526

2627
@Override
27-
protected void index() {
28+
protected void index(ProcessDisplayHelper display) {
2829
try {
2930
repo = new ModelIndexerRepository();
3031
cache = repo.getModelDocumentCache();
3132

3233
LinkedBlockingDeque<String> queue = new LinkedBlockingDeque<>(cache.getModelMap().keySet());
33-
34+
display.startProcess(queue.size());
3435
initiateThreading(queue);
3536
repo.close();
3637
} catch (Exception e) {

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/VariantIndexer.java

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@
77
import org.alliancegenome.core.translators.document.VariantTranslator;
88
import org.alliancegenome.es.index.site.cache.IndexerCache;
99
import org.alliancegenome.es.index.site.document.SearchableItemDocument;
10+
import org.alliancegenome.es.util.ProcessDisplayHelper;
1011
import org.alliancegenome.exceptional.client.ExceptionCatcher;
1112
import org.alliancegenome.indexer.config.IndexerConfig;
1213
import org.alliancegenome.neo4j.entity.node.Variant;
@@ -25,7 +26,7 @@ public VariantIndexer(IndexerConfig config) {
2526
}
2627

2728
@Override
28-
protected void index() {
29+
protected void index(ProcessDisplayHelper display) {
2930

3031
// for now, variants only get indexed if an additional flag is set
3132
if (!ConfigHelper.getIndexVariants()) {

agr_indexer/src/main/java/org/alliancegenome/indexer/indexers/curation/AffectedGenomicModelCurationIndexer.java

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -8,6 +8,7 @@
88
import org.alliancegenome.curation_api.model.document.es.AffectedGenomicModelDocument;
99
import org.alliancegenome.curation_api.response.SearchResponse;
1010
import org.alliancegenome.es.rest.RestConfig;
11+
import org.alliancegenome.es.util.ProcessDisplayHelper;
1112
import org.alliancegenome.exceptional.client.ExceptionCatcher;
1213
import org.alliancegenome.indexer.config.IndexerConfig;
1314
import org.alliancegenome.indexer.indexers.Indexer;
@@ -30,13 +31,13 @@ public AffectedGenomicModelCurationIndexer(IndexerConfig config) {
3031
}
3132

3233
@Override
33-
protected void index() {
34+
protected void index(ProcessDisplayHelper display) {
3435
try {
3536
log.info("Fetching all AGM IDs...");
3637
SearchResponse<Long> idsResponse = modelApi.getAllIds();
3738
List<Long> allIds = idsResponse.getResults();
3839
log.info("Fetched {} AGM IDs", allIds.size());
39-
40+
display.startProcess(allIds.size());
4041
idBatches = partition(allIds, indexerConfig.getBufferSize());
4142
log.info("Partitioned into {} batches of up to {}", idBatches.size(), indexerConfig.getBufferSize());
4243

0 commit comments

Comments
 (0)