Support indexing ClueWeb22 B

src/main/java/io/anserini/collection/ClueWeb12Collection.java

@@ -16,7 +16,6 @@
 
 package io.anserini.collection;
 
-import org.apache.commons.io.input.ReaderInputStream;
 import org.apache.logging.log4j.LogManager;
 
 import java.io.BufferedReader;

src/main/java/io/anserini/collection/ClueWeb22Collection.java

@@ -0,0 +1,165 @@
+/*
+ * Anserini: A Lucene toolkit for reproducible information retrieval research
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package io.anserini.collection;
+
+import com.fasterxml.jackson.databind.JsonNode;
+import com.fasterxml.jackson.databind.MappingIterator;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+
+import java.io.BufferedReader;
+import java.io.FileReader;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.nio.file.StandardOpenOption;
+import java.util.HashMap;
+import java.util.Map;
+import java.util.NoSuchElementException;
+import java.util.Set;
+import java.util.zip.GZIPInputStream;
+
+/**
+ * An instance of the <a href="https://www.lemurproject.org/clueweb22.php/">ClueWeb22-B collection</a>.
+ */
+public class ClueWeb22Collection extends DocumentCollection<ClueWeb22Collection.Document> {
+  private static final Logger LOG = LogManager.getLogger(ClueWeb22Collection.class);
+
+  public ClueWeb22Collection(Path path) {
+    this.path = path;
+    this.allowedFileSuffix = Set.of(".json.gz");
+  }
+
+  public ClueWeb22Collection() {
+  }
+
+  @Override
+  public FileSegment<ClueWeb22Collection.Document> createFileSegment(Path p) throws IOException {
+    return new Segment(p);
+  }
+
+  @Override
+  public FileSegment<ClueWeb22Collection.Document> createFileSegment(BufferedReader bufferedReader) throws IOException {
+    return new Segment(bufferedReader);
+  }
+
+  /**
+   * A file segment in the ClueWeb22-B collection.
+   */
+  public static class Segment extends FileSegment<ClueWeb22Collection.Document> {
+    private JsonNode node = null;
+    private MappingIterator<JsonNode> iterator;
+
+    public Segment(Path path) throws IOException {
+      super(path);
+
+      if (path.toString().endsWith(".gz")) {
+        InputStream stream = new GZIPInputStream(Files.newInputStream(path, StandardOpenOption.READ), BUFFER_SIZE);
+        bufferedReader = new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8));
+      } else {
+        bufferedReader = new BufferedReader(new FileReader(path.toString()));
+      }
+
+      ObjectMapper mapper = new ObjectMapper();
+      iterator = mapper.readerFor(JsonNode.class).readValues(bufferedReader);
+      if (iterator.hasNext()) {
+        node = iterator.next();
+      }
+    }
+
+    public Segment(BufferedReader bufferedReader) throws IOException {
+      super(bufferedReader);
+      ObjectMapper mapper = new ObjectMapper();
+      iterator = mapper.readerFor(JsonNode.class).readValues(bufferedReader);
+      if (iterator.hasNext()) {
+        node = iterator.next();
+      }
+    }
+
+    @Override
+    public void readNext() throws NoSuchElementException {
+      if (node == null) {
+        throw new NoSuchElementException("JsonNode is empty");
+      } else if (node.isObject()) {
+        bufferedRecord = new Document(node);
+        if (iterator.hasNext()) {
+          node = iterator.next();
+        } else {
+          atEOF = true;
+        }
+      } else {
+        LOG.error("Error: invalid JsonNode type");
+        throw new NoSuchElementException("Invalid JsonNode type");
+      }
+    }
+  }
+
+  /**
+   * A document in the ClueWeb22-B collection.
+   */
+  public static class Document implements SourceDocument {
+    private String id;
+    private String contents;
+    private String raw;
+    private Map<String, String> fields;
+
+    public Document(JsonNode json) {
+      this.raw = json.toString();
+      this.fields = new HashMap<>();
+
+      json.fields().forEachRemaining(e -> {
+        if ("ClueWeb22-ID".equals(e.getKey())) {
+          this.id = json.get("ClueWeb22-ID").asText();
+        } else if ("Clean-Text".equals(e.getKey())) {
+          this.contents = json.get("Clean-Text").asText();
+        } else {
+          this.fields.put(e.getKey(), e.getValue().asText());
+        }
+      });
+    }
+
+    @Override
+    public String id() {
+      if (id == null) {
+        throw new RuntimeException("Document does not have the required \"ClueWeb22-ID\" field!");
+      }
+      return id;
+    }
+
+    @Override
+    public String contents() {
+      if (contents == null) {
+        throw new RuntimeException("Document does not have the required \"Clean-Text\" field!");
+      }
+      return contents;
+    }
+
+    @Override
+    public String raw() {
+      return raw;
+    }
+
+    @Override
+    public boolean indexable() {
+      return true;
+    }
+  }
+}

src/test/java/io/anserini/collection/ClueWeb22CollectionTest.java

@@ -0,0 +1,53 @@
+/*
+ * Anserini: A Lucene toolkit for reproducible information retrieval research
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package io.anserini.collection;
+
+import org.junit.Before;
+
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.util.Map;
+
+public class ClueWeb22CollectionTest extends DocumentCollectionTest<ClueWeb22Collection.Document> {
+
+  @Before
+  public void setUp() throws Exception {
+    super.setUp();
+
+    collectionPath = Paths.get("src/test/resources/sample_docs/clueweb22/");
+    collection = new ClueWeb22Collection(collectionPath);
+
+    Path segment1 = Paths.get("src/test/resources/sample_docs/clueweb22/txt/en/en00/en0000/en0000-30.json.gz");
+
+    segmentPaths.add(segment1);
+    segmentDocCounts.put(segment1, 2);
+
+    totalSegments = 1;
+    totalDocs = 2;
+
+    expected.put("clueweb22-en0000-30-00000", Map.of("id", "clueweb22-en0000-30-00000"));
+    expected.put("clueweb22-en0000-30-00001", Map.of("id", "clueweb22-en0000-30-00001"));
+  }
+
+  @Override
+  void checkDocument(SourceDocument doc, Map<String, String> expected) {
+    assertTrue(doc.indexable());
+    assertEquals(expected.get("id"), doc.id());
+    assertNotNull(doc.contents());
+    assertTrue(doc.contents().length() > 0);
+  }
+}