Skip to content
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

Add filtering commands. #63

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+85 −19
Open

Add filtering commands. #63

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 12 additions & 2 deletions corpus_transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,12 +14,22 @@ def transform(text):
except ValueError:
continue

if doc["url"] == "":
url = doc["url"]
if url == "":
continue

filters = []
id_hash = hash(doc["url"])
if id_hash % 10 == 3:
filters.append("10%")
if id_hash % 100 == 42:
filters.append("1%")

doc_transformed = {
"id": doc["url"],
"id": url,
"text": transform(doc["body"])
}
if len(filters) > 0:
doc_transformed["filters"] = filters

print(json.dumps(doc_transformed))
31 changes: 21 additions & 10 deletions engines/lucene-10.0.0-bp/src/main/java/BuildIndex.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
Expand All @@ -26,7 +27,9 @@
import org.apache.lucene.util.ThreadInterruptedException;

import com.eclipsesource.json.Json;
import com.eclipsesource.json.JsonArray;
import com.eclipsesource.json.JsonObject;
import com.eclipsesource.json.JsonValue;

public class BuildIndex {

Expand All @@ -37,11 +40,11 @@ public static void main(String[] args) throws Exception {
final IndexWriterConfig config = new IndexWriterConfig(standardAnalyzer)
.setRAMBufferSizeMB(1024)
.setOpenMode(OpenMode.CREATE);
final BPIndexReorderer reorderer = new BPIndexReorderer();
reorderer.setRAMBudgetMB(256);
final BPReorderingMergePolicy mp = new BPReorderingMergePolicy(config.getMergePolicy(), reorderer);
mp.setMinNaturalMergeNumDocs(Integer.MAX_VALUE); // only reorder at force-merge time
config.setMergePolicy(mp);
final BPIndexReorderer reorderer = new BPIndexReorderer();
reorderer.setRAMBudgetMB(256);
final BPReorderingMergePolicy mp = new BPReorderingMergePolicy(config.getMergePolicy(), reorderer);
mp.setMinNaturalMergeNumDocs(Integer.MAX_VALUE); // only reorder at force-merge time
config.setMergePolicy(mp);

try (Directory dir = FSDirectory.open(outputPath);
IndexWriter writer = new IndexWriter(dir, config);
Expand All @@ -53,13 +56,9 @@ public static void main(String[] args) throws Exception {
final AtomicInteger indexed = new AtomicInteger();
for (int i = 0; i < threads.length; ++i) {

final Document document = new Document();
StoredField idField = new StoredField("id", "");
TextField textField = new TextField("text", "", Field.Store.NO);

document.add(idField);
document.add(textField);

threads[i] = new Thread(() -> {
while (true) {
String line;
Expand All @@ -83,13 +82,25 @@ public static void main(String[] args) throws Exception {
final JsonObject parsed_doc = Json.parse(line).asObject();
final String id = parsed_doc.get("id").asString();
final String text = parsed_doc.get("text").asString();
final JsonValue filters = parsed_doc.get("filters");
idField.setStringValue(id);
textField.setStringValue(text);

Document document = new Document();
document.add(idField);
document.add(textField);
if (filters != null) {
JsonArray filterArray = filters.asArray();
for (int j = 0; j < filterArray.size(); ++j) {
document.add(new StringField("filters", filterArray.get(j).asString(), Field.Store.NO));
}
}

try {
writer.addDocument(document);
final int numIndexed = indexed.getAndIncrement();
if (numIndexed % 100_000 == 0) {
System.out.println("Indexed: " + numIndexed);
System.out.println("Indexed: " + numIndexed);
}
} catch (IOException e) {
throw new UncheckedIOException(e);
Expand Down
19 changes: 18 additions & 1 deletion engines/lucene-10.0.0-bp/src/main/java/DoQuery.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,15 +8,23 @@
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopScoreDocCollectorManager;
import org.apache.lucene.search.similarities.BM25Similarity;
import org.apache.lucene.store.FSDirectory;

public class DoQuery {

private static final String TEN_PERCENT_FILTER = "_FILTER_10%";
private static final String ONE_PERCENT_FILTER = "_FILTER_1%";

public static void main(String[] args) throws IOException, ParseException {
final Path indexDir = Paths.get(args[0]);
try (IndexReader reader = DirectoryReader.open(FSDirectory.open(indexDir));
Expand All @@ -29,9 +37,18 @@ public static void main(String[] args) throws IOException, ParseException {
while ((line = bufferedReader.readLine()) != null) {
final String[] fields = line.trim().split("\t");
assert fields.length == 2;
final String command = fields[0];
String command = fields[0];
final String query_str = fields[1];
Query query = queryParser.parse(query_str);
if (command.endsWith(TEN_PERCENT_FILTER)) {
Query filter = new TermQuery(new Term("filters", "10%"));
command = command.substring(0, command.length() - TEN_PERCENT_FILTER.length());
query = new BooleanQuery.Builder().add(query, Occur.MUST).add(filter, Occur.FILTER).build();
} else if (command.endsWith(ONE_PERCENT_FILTER)) {
Query filter = new TermQuery(new Term("filters", "1%"));
command = command.substring(0, command.length() - ONE_PERCENT_FILTER.length());
query = new BooleanQuery.Builder().add(query, Occur.MUST).add(filter, Occur.FILTER).build();
}
final long count;
switch (command) {
case "COUNT":
Expand Down
21 changes: 16 additions & 5 deletions engines/lucene-10.0.0/src/main/java/BuildIndex.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
Expand All @@ -24,7 +25,9 @@
import org.apache.lucene.util.ThreadInterruptedException;

import com.eclipsesource.json.Json;
import com.eclipsesource.json.JsonArray;
import com.eclipsesource.json.JsonObject;
import com.eclipsesource.json.JsonValue;

public class BuildIndex {

Expand All @@ -46,13 +49,9 @@ public static void main(String[] args) throws Exception {
final AtomicInteger indexed = new AtomicInteger();
for (int i = 0; i < threads.length; ++i) {

final Document document = new Document();
StoredField idField = new StoredField("id", "");
TextField textField = new TextField("text", "", Field.Store.NO);

document.add(idField);
document.add(textField);

threads[i] = new Thread(() -> {
while (true) {
String line;
Expand All @@ -76,13 +75,25 @@ public static void main(String[] args) throws Exception {
final JsonObject parsed_doc = Json.parse(line).asObject();
final String id = parsed_doc.get("id").asString();
final String text = parsed_doc.get("text").asString();
final JsonValue filters = parsed_doc.get("filters");
idField.setStringValue(id);
textField.setStringValue(text);

Document document = new Document();
document.add(idField);
document.add(textField);
if (filters != null) {
JsonArray filterArray = filters.asArray();
for (int j = 0; j < filterArray.size(); ++j) {
document.add(new StringField("filters", filterArray.get(j).asString(), Field.Store.NO));
}
}

try {
writer.addDocument(document);
final int numIndexed = indexed.getAndIncrement();
if (numIndexed % 100_000 == 0) {
System.out.println("Indexed: " + numIndexed);
System.out.println("Indexed: " + numIndexed);
}
} catch (IOException e) {
throw new UncheckedIOException(e);
Expand Down
19 changes: 18 additions & 1 deletion engines/lucene-10.0.0/src/main/java/DoQuery.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,15 +8,23 @@
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopScoreDocCollectorManager;
import org.apache.lucene.search.similarities.BM25Similarity;
import org.apache.lucene.store.FSDirectory;

public class DoQuery {

private static final String TEN_PERCENT_FILTER = "_FILTER_10%";
private static final String ONE_PERCENT_FILTER = "_FILTER_1%";

public static void main(String[] args) throws IOException, ParseException {
final Path indexDir = Paths.get(args[0]);
try (IndexReader reader = DirectoryReader.open(FSDirectory.open(indexDir));
Expand All @@ -29,9 +37,18 @@ public static void main(String[] args) throws IOException, ParseException {
while ((line = bufferedReader.readLine()) != null) {
final String[] fields = line.trim().split("\t");
assert fields.length == 2;
final String command = fields[0];
String command = fields[0];
final String query_str = fields[1];
Query query = queryParser.parse(query_str);
if (command.endsWith(TEN_PERCENT_FILTER)) {
Query filter = new TermQuery(new Term("filters", "10%"));
command = command.substring(0, command.length() - TEN_PERCENT_FILTER.length());
query = new BooleanQuery.Builder().add(query, Occur.MUST).add(filter, Occur.FILTER).build();
} else if (command.endsWith(ONE_PERCENT_FILTER)) {
Query filter = new TermQuery(new Term("filters", "1%"));
command = command.substring(0, command.length() - ONE_PERCENT_FILTER.length());
query = new BooleanQuery.Builder().add(query, Occur.MUST).add(filter, Occur.FILTER).build();
}
final long count;
switch (command) {
case "COUNT":
Expand Down