Skip to content

FUS-1162: Emit multiple candidates per item #144

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

FUS-1162: Emit multiple candidates per item #144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
03d8c45
FUS-1162: Emit multiple candidates per item
mcondo Jun 21, 2022
5fe7e89
FUS-1162: Emit multiple candidates per item
mcondo Jun 22, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions ...tor/src/main/java/com/lucidworks/connector/plugins/random/config/RandomContentConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
import com.lucidworks.connector.plugins.random.config.RandomContentConfig.Properties;
import com.lucidworks.fusion.connector.plugin.api.config.ConnectorConfig;
import com.lucidworks.fusion.connector.plugin.api.config.ConnectorPluginProperties;
import com.lucidworks.fusion.schema.SchemaAnnotations.NumberSchema;
import com.lucidworks.fusion.schema.SchemaAnnotations.Property;
import com.lucidworks.fusion.schema.SchemaAnnotations.RootSchema;

Expand All @@ -30,5 +31,15 @@ interface Properties extends ConnectorPluginProperties {
description = "Random Content properties"
)
RandomContentProperties getRandomContentProperties();

@Property(
title = "Number of candidates per item",
description = "The number of candidates to emit per document generated",
order = 2
)
@NumberSchema(
defaultValue = 1
)
Integer numberOfCandidates();
}
}
41 changes: 31 additions & 10 deletions ...r/src/main/java/com/lucidworks/connector/plugins/random/fetcher/RandomContentFetcher.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,25 +8,28 @@
import com.lucidworks.fusion.connector.plugin.api.fetcher.result.FetchResult;
import com.lucidworks.fusion.connector.plugin.api.fetcher.type.content.ContentFetcher;
import com.lucidworks.fusion.connector.plugin.api.fetcher.type.content.FetchInput;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import javax.inject.Inject;
import java.time.Instant;
import java.time.LocalDateTime;
import java.util.stream.IntStream;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

public class RandomContentFetcher implements ContentFetcher {

private static final Logger logger = LoggerFactory.getLogger(RandomContentFetcher.class);

private static final String CONTENT_ID = "content-example";
private static final String ERROR_ID = "no-number-this-should-fail";
private static final String COUNTER_FIELD = "number";
private static final String CANDIDATE_NUMBER = "candidate-number";

private final RandomContentGenerator generator;
private final RandomContentProperties randomContentProperties;
private final String hostname;
private final long numberOfCandidates;

@Inject
public RandomContentFetcher(
Expand All @@ -37,6 +40,7 @@ public RandomContentFetcher(
this.randomContentProperties = randomContentConfig.properties().getRandomContentProperties();
this.generator = generator;
this.hostname = hostnameProvider.get();
this.numberOfCandidates = randomContentConfig.properties().numberOfCandidates();
}

@Override
Expand All @@ -48,11 +52,9 @@ public FetchResult fetch(FetchContext fetchContext) {
int totalNumberOfDocs = randomContentProperties.totalNumDocs();
IntStream.range(0, totalNumberOfDocs)
.asLongStream()
.forEach(i -> {
logger.info("Emitting candidate -> number {}", i);
fetchContext.newCandidate(String.valueOf(i))
.metadata(m -> m.setLong(COUNTER_FIELD, i))
.emit();
.forEach(index -> {
logger.info("Emitting candidate for item {}", index);
emitCandidate(fetchContext, index, 1);
});
// Simulating an error item here... because we're emitting an item without a "number",
// the fetch() call will attempt to convert the number into a long and throw an exception.
Expand All @@ -65,13 +67,32 @@ public FetchResult fetch(FetchContext fetchContext) {

if (CONTENT_ID.equals(fetchContext.getFetchInput().getId())) {
emitContent(fetchContext, input);
} else if (input.getMetadata().get(CANDIDATE_NUMBER) != null) {
long candidate = Integer.valueOf(input.getMetadata().get(CANDIDATE_NUMBER).toString()) + 1;
if (candidate <= numberOfCandidates) {
long num = (Long) input.getMetadata().get(COUNTER_FIELD);
emitCandidate(fetchContext, num, candidate);
return fetchContext.newResult();
}
emitDocument(fetchContext, input);
} else {
emitDocument(fetchContext, input);
}

return fetchContext.newResult();
}

private void emitCandidate(FetchContext fetchContext, long num, long candidate) {
boolean latestCandidate = candidate == numberOfCandidates;
fetchContext
.newCandidate(latestCandidate ? String.valueOf(num) : num + "-" + candidate)
.metadata(m -> {
m.setLong(COUNTER_FIELD, num);
m.setLong(CANDIDATE_NUMBER, candidate);
})
.withTransient(latestCandidate ? false : true) // not need to save candidates that will not be indexed
.emit();
}

private void emitDocument(FetchContext fetchContext, FetchInput input) {
try {
long num = (Long) input.getMetadata().get(COUNTER_FIELD);
Expand All @@ -80,7 +101,7 @@ private void emitDocument(FetchContext fetchContext, FetchInput input) {
.forEach(
(k, v) -> logger.info("Input [{}:{}[{}]]", k, v, v.getClass())
);
logger.info("Emitting Document -> number {}", num);
logger.info("Emitting Document -> id {} - {}", num, input.getMetadata());

int min = randomContentProperties.minimumNumberSentences();
int max = randomContentProperties.maximumNumberSentences();
Expand Down Expand Up @@ -121,7 +142,7 @@ private void emitContent(FetchContext fetchContext, FetchInput input) {
f.setLocalDateTime("crawl_date", LocalDateTime.now());
})
.emit();
} catch(ContentEmitException e) {
} catch (ContentEmitException e) {
logger.error("Failed to emit content", e);
fetchContext.newError(input.getId(), e.toString())
.emit();
Expand Down