add isfork() function

.project

@@ -16,12 +16,12 @@
 	</natures>
 	<filteredResources>
 		<filter>
-			<id>1625891463658</id>
+			<id>1700381053047</id>
 			<name></name>
 			<type>30</type>
 			<matcher>
 				<id>org.eclipse.core.resources.regexFilterMatcher</id>
-				<arguments>node_modules|.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__</arguments>
+				<arguments>node_modules|\.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__</arguments>
 			</matcher>
 		</filter>
 	</filteredResources>

src/java/boa/functions/BoaAstIntrinsics.java

@@ -1,7 +1,8 @@
 /*
- * Copyright 2017, Hridesh Rajan, Robert Dyer,
+ * Copyright 2023, Hridesh Rajan, Robert Dyer,
  *                 Iowa State University of Science and Technology
- *                 and Bowling Green State University
+ *                 Bowling Green State University
+ *                 and University of Nebraska Board of Regents
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -63,7 +64,7 @@
  */
 public class BoaAstIntrinsics {
 	@SuppressWarnings("rawtypes")
-	static Context context;
+	public static Context context;
 	private static MapFile.Reader map;
 	private static MapFile.Reader commentsMap;
 	private static MapFile.Reader issuesMap;

src/java/boa/functions/BoaIntrinsics.java

@@ -1,5 +1,5 @@
 /*
- * Copyright 2014-2021, Hridesh Rajan, Robert Dyer,
+ * Copyright 2014-2023, Hridesh Rajan, Robert Dyer,
  *                 Iowa State University of Science and Technology
  *                 and University of Nebraska Board of Regents
  *
@@ -17,6 +17,8 @@
  */
 package boa.functions;
 
+import java.io.BufferedInputStream;
+import java.io.ObjectInputStream;
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Collections;
@@ -29,6 +31,12 @@
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+
+import boa.datagen.DefaultProperties;
 import boa.types.Code.CodeRepository;
 import boa.types.Code.Revision;
 import boa.types.Diff.ChangedFile;
@@ -41,6 +49,43 @@
  * @author rdyer
  */
 public class BoaIntrinsics {
+	private static Set<Integer> forksData;
+
+	private static void loadForksData() {
+		try {
+			final Configuration conf = BoaAstIntrinsics.context.getConfiguration();
+			final FileSystem fs;
+			final Path p;
+			if (DefaultProperties.localDataPath != null) {
+				p = new Path(DefaultProperties.localDataPath, "forks.bin");
+				fs = FileSystem.getLocal(conf);
+			} else {
+				p = new Path(
+					BoaAstIntrinsics.context.getConfiguration().get("fs.default.name", "hdfs://boa-njt/"),
+					new Path(conf.get("boa.forks.file", conf.get("boa.ast.dir", conf.get("boa.input.dir", "")) + "/forks.bin"))
+				);
+				fs = FileSystem.get(conf);
+			}
+
+			try (final FSDataInputStream data = fs.open(p);
+				final BufferedInputStream bis = new BufferedInputStream(data);
+				final ObjectInputStream ois = new ObjectInputStream(bis)) {
+				forksData = (Set<Integer>)ois.readObject();
+			}
+		} catch (final Exception e) {
+			System.err.println("Error reading forks.bin: " + e.getMessage());
+			e.printStackTrace();
+			forksData = new HashSet<Integer>();
+		}
+	}
+
+	@FunctionSpec(name = "isfork", returnType = "bool", formalParameters = { "Project" })
+	public static boolean isfork(final Project p) {
+		if (forksData == null)
+			loadForksData();
+		return p.getForked() || forksData.contains(Integer.parseInt(p.getId()));
+	}
+
 	private final static String[] fixingRegex = {
 		"\\bfix(s|es|ing|ed)?\\b",
 		"\\b(error|bug|issue)(s)?\\b",

src/java/boa/runtime/BoaRunner.java

@@ -1,5 +1,5 @@
 /*
- * Copyright 2014-2021, Anthony Urso, Hridesh Rajan, Robert Dyer,
+ * Copyright 2014-2023, Anthony Urso, Hridesh Rajan, Robert Dyer,
  *                 Iowa State University of Science and Technology
  *                 and University of Nebraska Board of Regents
  *
@@ -121,6 +121,11 @@ public Job job(final Path[] ins, final Path out) throws IOException {
 										.hasArg()
 										.withArgName("INPUT")
 										.create("c"));
+		options.addOption(org.apache.commons.cli.OptionBuilder.withLongOpt("forks")
+										.withDescription("which INPUT to use for forks data")
+										.hasArg()
+										.withArgName("INPUT")
+										.create("f"));
 		options.addOption(org.apache.commons.cli.OptionBuilder.withLongOpt("splitsize")
 										.withDescription("split size in BYTES")
 										.hasArg()

templates/BoaJavaHadoop.stg

@@ -56,6 +56,8 @@ public class <name> extends boa.runtime.BoaRunner {
 			configuration.set("boa.ast.dir", line.getOptionValue("ast"));
 		if (line.hasOption("comments"))
 			configuration.set("boa.comments.dir", line.getOptionValue("comments"));
+		if (line.hasOption("forks"))
+			configuration.set("boa.forks.file", line.getOptionValue("forks"));
 
 		if (line.hasOption("splitsize"))
 			configuration.setInt("mapred.max.split.size", Integer.parseInt(line.getOptionValue("splitsize")));