Merge master and reconcile differences

build.sbt

@@ -1,16 +1,19 @@
 val scala211 = "2.11.12" // up to 2.11.12
-val scala212 = "2.12.17" // up to 2.12.18
-val scala213 = "2.13.10" // up to 2.13.11
+val scala212 = "2.12.18" // up to 2.12.18
+val scala213 = "2.13.12" // up to 2.13.12
 val scala30  = "3.0.2"   // up to 3.0.2
 val scala31  = "3.1.3"   // up to 3.1.3
-val scala32  = "3.2.1"   // up to 3.2.2
-val scala33  = "3.3.0"   // up to 3.3.0
+val scala32  = "3.2.2"   // up to 3.2.2
+val scala33  = "3.3.1"   // up to 3.3.1
+
+val scala3   = scala31
 
 // See https://www.scala-lang.org/blog/2022/08/17/long-term-compatibility-plans.html.
 // Scala30: "If you are maintaining a library, you should drop Scala 3.0."  Dropped.
-// Scala31: This is the current LTS (long term support) version and default Scala 3 release.
+// Scala31: This is a LTS (long term support) version before it was called that.
 // Scala32: This is for experimentation, as in Scala Next, and not for release.
-ThisBuild / crossScalaVersions := Seq(scala212, scala211, scala213, scala31)
+// Scala33: This is the first official LTS, but hold off until necessary.
+ThisBuild / crossScalaVersions := Seq(scala212, scala211, scala213, scala3)
 ThisBuild / scalaVersion := crossScalaVersions.value.head
 
 lazy val root = (project in file("."))

corenlp/src/main/scala/org/clulab/processors/TextLabelToCoNNLU.scala

@@ -1,13 +1,15 @@
 package org.clulab.processors
 
-import java.io.{File, FileFilter, PrintWriter}
 import org.clulab.processors.clu.BalaurProcessor
 import org.clulab.processors.fastnlp.FastNLPProcessor
+import org.clulab.struct.GraphMap
 import org.clulab.utils.{FileUtils, Sourcer, StringUtils}
 import org.slf4j.{Logger, LoggerFactory}
+
+import java.io.{File, FileFilter, PrintWriter}
+import scala.util.Using
+
 import TextLabelToCoNLLU._
-import org.clulab.struct.GraphMap
-import org.clulab.utils.Closer.AutoCloser
 
 /**
   * Processes raw text and saves the output in the CoNLL-U format
@@ -24,9 +26,9 @@ class TextLabelToCoNLLU(val proc:Processor, val isCoreNLP:Boolean) {
       try {
         val doc = parseFile(f)
         val ofn = s"$outDir/${f.getName.substring(0, f.getName.length - 4)}.conllu"
-        val pw = new PrintWriter(ofn)
-        toCoNLLU(doc, pw)
-        pw.close()
+        Using.resource(new PrintWriter(ofn)) { pw =>
+          toCoNLLU(doc, pw)
+        }
       } catch {
         case e:Exception => {
           logger.error(s"Parsing of file $f failed with error:")
@@ -77,7 +79,7 @@ class TextLabelToCoNLLU(val proc:Processor, val isCoreNLP:Boolean) {
 
   def parseFile(f:File):Document = {
     def option1(): Document = {
-      val tokens = Sourcer.sourceFromFile(f).autoClose { source =>
+      val tokens = Using.resource(Sourcer.sourceFromFile(f)) { source =>
         for (line <- source.getLines())
           yield line.split(' ').toSeq
       }.toSeq

corenlp/src/main/scala/org/clulab/processors/TextToCoNLLU.scala

@@ -1,13 +1,16 @@
 package org.clulab.processors
 
-import java.io.{File, FileFilter, PrintWriter}
 
 import org.clulab.processors.clu.BalaurProcessor
 import org.clulab.processors.fastnlp.FastNLPProcessor
+import org.clulab.struct.GraphMap
 import org.clulab.utils.StringUtils
 import org.slf4j.{Logger, LoggerFactory}
+
+import java.io.{File, FileFilter, PrintWriter}
+import scala.util.Using
+
 import TextToCoNLLU._
-import org.clulab.struct.GraphMap
 
 /**
   * Processes raw text and saves the output in the CoNLL-U format
@@ -24,9 +27,9 @@ class TextToCoNLLU(val proc:Processor, val isCoreNLP:Boolean) {
       try {
         val doc = parseFile(f)
         val ofn = s"$outDir/${f.getName.substring(0, f.getName.length - 4)}.conllu"
-        val pw = new PrintWriter(ofn)
-        toCoNLLU(doc, pw)
-        pw.close()
+        Using.resource(new PrintWriter(ofn)) { pw =>
+          toCoNLLU(doc, pw)
+        }
       } catch {
         case e:Exception => {
           logger.error(s"Parsing of file $f failed with error:")
@@ -65,13 +68,13 @@ class TextToCoNLLU(val proc:Processor, val isCoreNLP:Boolean) {
   }
 
   def parseFile(f:File):Document = {
-    val s = scala.io.Source.fromFile(f)
     val buffer = new StringBuilder
-    for(line <- s.getLines()) {
-      buffer.append(line)
-      buffer.append("\n")
+    Using.resource(scala.io.Source.fromFile(f)) { s =>
+      for (line <- s.getLines()) {
+        buffer.append(line)
+        buffer.append("\n")
+      }
     }
-    s.close()
 
     val doc = proc.mkDocument(buffer.toString())
     annotate(doc)

corenlp/src/main/scala/org/clulab/processors/corenlp/CoreNLPDocument.scala

@@ -14,14 +14,14 @@ class CoreNLPDocument(sentences: Array[Sentence]) extends Document(sentences) {
 
   var annotation:Option[Annotation] = None
 
-  def copy(document: CoreNLPDocument): CoreNLPDocument = {
-    super.copy(document)
+  def assimilate(document: CoreNLPDocument, textOpt: Option[String]): CoreNLPDocument = {
+    super.assimilate(document, textOpt)
     annotation = document.annotation
     this
   }
 
-  override def copy(sentences: Array[Sentence] = sentences): CoreNLPDocument =
-      new CoreNLPDocument(sentences).copy(this)
+  override def copy(sentences: Array[Sentence] = sentences, textOpt: Option[String] = text): CoreNLPDocument =
+      new CoreNLPDocument(sentences).assimilate(this, textOpt)
 
   override def clear(): Unit = {
     //println("Clearing state from document.")

corenlp/src/main/scala/org/clulab/processors/corenlp/chunker/TrainChunker.scala

@@ -1,11 +1,13 @@
 package org.clulab.processors.corenlp.chunker
 
+import edu.stanford.nlp.ling.{ CoreLabel, CoreAnnotations }
 import org.clulab.scala.WrappedArray._
+
 import java.io.FileInputStream
 import java.util.zip.GZIPInputStream
 import scala.collection.mutable
 import scala.io.Source
-import edu.stanford.nlp.ling.{ CoreLabel, CoreAnnotations }
+import scala.util.Using
 
 object TrainChunker extends App {
 
@@ -63,9 +65,9 @@ object TrainChunker extends App {
 
   def readData(path: String): Array[Array[CoreLabel]] = {
     val is = new GZIPInputStream(new FileInputStream(path))
-    val source = Source.fromInputStream(is)
-    val text = source.mkString
-    source.close()
+    val text = Using.resource(Source.fromInputStream(is)) { source =>
+      source.mkString
+    }
     // sentences are separated by an empty line
     val sentences = text.split("\n\n")
     sentences.map { sent =>

corenlp/src/main/scala/org/clulab/processors/examples/DocumentSerializerExample.scala

@@ -1,31 +1,32 @@
 package org.clulab.processors.examples
 
-import java.io.{BufferedReader, FileReader}
-
 import org.clulab.serialization.DocumentSerializer
 
+import java.io.{BufferedReader, FileReader}
+import scala.util.Using
+
 /**
  *
  * User: mihais
  * Date: 10/1/14
  */
 object DocumentSerializerExample {
   def main(args:Array[String]): Unit = {
-    val ds = new DocumentSerializer
-    val r = new BufferedReader(new FileReader(args(0)))
-    var done = false
     var count = 0
-    while(! done) {
-      val d = ds.load(r)
-      if(d == null) {
-        done = true
-      } else {
-        count += 1
-        if(count % 10 == 0)
-          println(s"Loaded $count documents...")
+    Using.resource(new BufferedReader(new FileReader(args(0)))) { r =>
+      val ds = new DocumentSerializer
+      var done = false
+      while (!done) {
+        val d = ds.load(r)
+        if (d == null) {
+          done = true
+        } else {
+          count += 1
+          if (count % 10 == 0)
+            println(s"Loaded $count documents...")
+        }
       }
     }
-    r.close()
     println(s"Done! Loaded $count documents.")
   }
 }

corenlp/src/main/scala/org/clulab/processors/examples/DocumentationExample.scala

@@ -8,7 +8,7 @@ import org.clulab.struct.DirectedGraphEdgeIterator
 
 object DocumentationExample extends App {
   // Create the processor.  Any processor works here!
-  // Try FastNLPProcessor or our own CluProcessor.
+  // Try FastNLPProcessor or our own BalaurProcessor.
   val proc: Processor = new CoreNLPProcessor()
 
   // val proc: Processor = new FastNLPProcessor()

corenlp/src/main/scala/org/clulab/processors/examples/InfiniteParallelProcessorExample.scala

@@ -4,17 +4,14 @@ import org.clulab.processors.Document
 import org.clulab.processors.Processor
 import org.clulab.processors.fastnlp.FastNLPProcessor
 import org.clulab.serialization.DocumentSerializer
-import org.clulab.utils.Closer.AutoCloser
-import org.clulab.utils.FileUtils
-import org.clulab.utils.ThreadUtils
-import org.clulab.utils.Timer
+import org.clulab.utils.{FileUtils, StringUtils, ThreadUtils, Timer}
 
 import java.io.BufferedOutputStream
 import java.io.File
 import java.io.FileOutputStream
 import java.io.PrintWriter
-import java.io.StringWriter
 import scala.collection.parallel.ParSeq
+import scala.util.Using
 
 object InfiniteParallelProcessorExample {
 
@@ -49,15 +46,8 @@ object InfiniteParallelProcessorExample {
         val text = FileUtils.getTextFromFile(file)
         val outputFile = new File(outputDir + "/" + file.getName)
         val document = processor.annotate(text)
-        val printedDocument = {
-          val stringWriter = new StringWriter
-
-          new PrintWriter(stringWriter).autoClose { printWriter =>
-            printDocument(document, printWriter)
-          }
-
-          val result = stringWriter.toString
-          result
+        val printedDocument = StringUtils.viaPrintWriter { printWriter =>
+          printDocument(document, printWriter)
         }
         val savedDocument = documentSerializer.save(document)
         val outputDocument = printedDocument + savedDocument
@@ -86,7 +76,7 @@ object InfiniteParallelProcessorExample {
   def run(args: Array[String]): Unit = {
 
     mainWithCallback(args) { case (file: File, contents: String) =>
-      new PrintWriter(new BufferedOutputStream(new FileOutputStream(file))).autoClose { printWriter =>
+      Using.resource(new PrintWriter(file)) { printWriter =>
         printWriter.println(contents)
       }
     }

corenlp/src/main/scala/org/clulab/processors/examples/ParallelProcessorExample.scala

@@ -1,19 +1,14 @@
 package org.clulab.processors.examples
 
-import java.io.BufferedOutputStream
-import java.io.File
-import java.io.FileOutputStream
-import java.io.PrintWriter
-import java.io.StringWriter
 import org.clulab.processors.Document
 import org.clulab.processors.Processor
 import org.clulab.processors.clu.BalaurProcessor
-import org.clulab.processors.fastnlp.FastNLPProcessor
 import org.clulab.serialization.DocumentSerializer
-import org.clulab.utils.Closer.AutoCloser
-import org.clulab.utils.FileUtils
-import org.clulab.utils.ThreadUtils
-import org.clulab.utils.Timer
+import org.clulab.utils.{FileUtils, StringUtils, ThreadUtils, Timer}
+
+import java.io.File
+import java.io.PrintWriter
+import scala.util.Using
 
 object ParallelProcessorExample {
 
@@ -25,7 +20,7 @@ object ParallelProcessorExample {
     val outputDir = args(1)
     val extension = args(2)
     val threads = args(3).toInt
-    val parallel = args.lift(4).exists(_ == "true")
+    val parallel = args.lift(4).contains("true")
 
     val files = FileUtils.findFiles(inputDir, extension)
     val serFiles = files.sortBy(-_.length)
@@ -60,15 +55,8 @@ object ParallelProcessorExample {
           println(s"Threw exception for ${file.getName}")
           throw throwable
       }
-      val printedDocument = {
-        val stringWriter = new StringWriter
-
-        new PrintWriter(stringWriter).autoClose { printWriter =>
-          printDocument(document, printWriter)
-        }
-
-        val result = stringWriter.toString
-        result
+      val printedDocument = StringUtils.viaPrintWriter { printWriter =>
+        printDocument(document, printWriter)
       }
       val savedDocument = documentSerializer.save(document)
       val outputDocument = printedDocument + savedDocument
@@ -83,7 +71,7 @@ object ParallelProcessorExample {
   def run(args: Array[String]): Unit = {
 
     mainWithCallback(args) { case (file: File, contents: String) =>
-      new PrintWriter(new BufferedOutputStream(new FileOutputStream(file))).autoClose { printWriter =>
+      Using.resource(new PrintWriter(file)) { printWriter =>
         printWriter.println(contents)
       }
     }

corenlp/src/main/scala/org/clulab/processors/examples/ProcessorExample.scala

@@ -26,7 +26,7 @@ object ProcessorExample {
 
     // other processors supported:
     // BioNLPProcessor, and FastBioNLPProcessor - for the biomedical domain
-    // CluProcessor - similar to FastNLPProcessor, but using tools licensed under the Apache license
+    // BalaurProcessor - similar to FastNLPProcessor, but using tools licensed under the Apache license
 
     // the actual work is done here
     val doc = proc.annotate("John Smith went to China. He visited Beijing, on January 10th, 2013.")

corenlp/src/test/scala/org/clulab/processors/TestOpenIE.scala

@@ -4,9 +4,7 @@ import org.clulab.processors.corenlp.CoreNLPProcessor
 import org.clulab.processors.fastnlp.FastNLPProcessor
 import org.clulab.processors.shallownlp.ShallowNLPProcessor
 import org.clulab.serialization.DocumentSerializer
-import org.clulab.utils.Test
-
-import java.io.{PrintWriter, StringWriter}
+import org.clulab.utils.{StringUtils, Test}
 
 import scala.collection.mutable
 
@@ -20,10 +18,9 @@ class TestOpenIE extends Test {
   private lazy val fastNLPDoc = fastNLP.annotate(text)
   private lazy val coreNLPDoc = coreNLP.annotate(text)
 
-  private val buffer = new StringWriter()
-  serializer.save(fastNLPDoc, new PrintWriter(buffer))
-  private val serialized = buffer.toString
-
+  private val serialized = StringUtils.viaPrintWriter { printWriter =>
+    serializer.save(fastNLPDoc, printWriter)
+  }
   private val deserializedDoc = serializer.load(serialized)
 
   def openIEBehavior(doc:Document): Unit = {

corenlp/src/test/scala/org/clulab/processors/TestParenthesesInCore.scala

@@ -13,7 +13,7 @@ import org.clulab.utils.Test
 class TestParenthesesInCore extends Test {
   val fast = new FastNLPProcessor()
 
-  "CluProcessor" should "tokenize, lemmatize, and POS tag parentheses correctly" in {
+  "Processor" should "tokenize, lemmatize, and POS tag parentheses correctly" in {
     val doc = fast.mkDocument("Moreover, in von Willebrand factor-stimulated platelets, the tyrosine phosphorylation of pp60(c-src) is closely associated with the activation of phosphatidylinositol 3-kinase (PIK), and two adhesion receptors, glycoprotein (Gp)Ib and GpIIb/IIIa(alpha-IIb-beta(3)), are involved. ")
     fast.tagPartsOfSpeech(doc)
     fast.lemmatize(doc)