Merge branch 'mainV9' into hexatags

Author: MihaiSurdeanu

.gitignore

@@ -23,6 +23,7 @@ lib_managed/
 src_managed/
 project/boot/
 project/plugins/project/
+main/project/
 
 # Scala-IDE specific
 .scala_dependencies

CHANGES.md

@@ -1,3 +1,4 @@
++ **9.0.0** - Replace CluProcessor with BalaurProcessor
 + **8.5.?** - Adjust processing of weeks as in "The first two weeks of the month"
 + **8.5.4** - Revise holiday normalization, downgrade JollyDay library, add jaxb-ri for Java 11+
 + **8.5.4** - Generate hugging face embeddings for potential use in grounding

build.sbt

@@ -1,9 +1,10 @@
 val scala211 = "2.11.12" // up to 2.11.12
 val scala212 = "2.12.18" // up to 2.12.18
-val scala213 = "2.13.11" // up to 2.13.11
+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  = "3.2.2"   // up to 3.2.2
+val scala33  = "3.3.1"   // up to 3.3.1
 
 val scala3   = scala31
 

corenlp/src/main/java/org/clulab/processors/ProcessorsJavaExample.java

@@ -1,7 +1,7 @@
 package org.clulab.processors;
 
 import com.typesafe.config.ConfigFactory;
-import org.clulab.processors.clu.CluProcessor;
+import org.clulab.processors.clu.BalaurProcessor;
 import org.clulab.processors.corenlp.CoreNLPProcessor;
 import org.clulab.processors.fastnlp.FastNLPProcessor;
 import org.clulab.sequences.LexiconNER;
@@ -17,20 +17,20 @@
 import java.util.Iterator;
 
 public class ProcessorsJavaExample {
-    // These are for the CluProcessor.
+    // These are for the BalaurProcessor.
     // final static Option<LexiconNER> noLexiconNER = Option.empty();
     // final static Option<String> noString = Option.empty();
     // final static Map<String, Object> emptyMap = new HashMap();
 
     public static void main(String [] args) throws Exception {
         // Create the processor.  Any processor works here!
-        // Try FastNLPProcessor or our own CluProcessor.
+        // Try FastNLPProcessor or our own BalaurProcessor.
         Processor proc = new CoreNLPProcessor(true, true, false, 0, 100);
 
         // Processor proc = new FastNLPProcessor(true, true, false, 0);
 
         // org.clulab.fatdynet.utils.Initializer.initialize(emptyMap);
-        // Processor proc = new CluProcessor(ConfigFactory.load("cluprocessor"), noLexiconNER, noString);
+        // Processor proc = new BalaurProcessor(ConfigFactory.load("balaurprocessor"), noLexiconNER, noString);
 
         // The actual work is done here.
         Document doc = proc.annotate("John Smith went to China. He visited Beijing on January 10th, 2013.", false);

corenlp/src/main/resources/org/clulab/processors/corenlp/chunker/chunker.crf.gz

@@ -1,9 +1,8 @@
 package org.clulab.processors
 
-import org.clulab.dynet.Utils
-import org.clulab.processors.clu.CluProcessor
+import org.clulab.processors.clu.BalaurProcessor
 import org.clulab.processors.corenlp.CoreNLPProcessor
-import org.clulab.processors.fastnlp.FastNLPProcessorWithSemanticRoles
+import org.clulab.processors.fastnlp.FastNLPProcessor
 import org.clulab.utils.CliReader
 import org.clulab.utils.ExitMenuItem
 import org.clulab.utils.HelpMenuItem
@@ -24,10 +23,10 @@ import java.io.PrintWriter
   */
 class ProcessorShell extends Shell {
   val core = new PromptedReloadableProcessor("(core)>>> ", () => new CoreNLPProcessor()) // this uses the slower constituent parser
-  val fast = new PromptedReloadableProcessor("(fast)>>> ", () => new FastNLPProcessorWithSemanticRoles()) // this uses the faster dependency parser
-  val clu = new PromptedReloadableProcessor("(clu)>>> ", () => new CluProcessor(), true)
+  val fast = new PromptedReloadableProcessor("(fast)>>> ", () => new FastNLPProcessor()) // this uses the faster dependency parser
+  val balaur = new PromptedReloadableProcessor("(balaur)>>> ", () => new BalaurProcessor(), true)
 
-  var proc = clu // Note that the initial proc does not get initialized.
+  var proc = balaur // Note that the initial proc does not get initialized.
 
   val lineReader = new CliReader(proc.prompt, "user.home", ".processorshellhistory")
   val printWriter = new PrintWriter(System.out)
@@ -44,7 +43,7 @@ class ProcessorShell extends Shell {
 
   def prepareFast(): Unit = prepareProcessor("Preparing FastNLPProcessor...", fast)
 
-  def prepareClu(): Unit = prepareProcessor("Preparing CluProcessor...", clu)
+  def prepareBalaur(): Unit = prepareProcessor("Preparing BalaurProcessor...", balaur)
 
   override def work(text: String): Unit = {
     val doc = proc.get.annotate(text)
@@ -63,7 +62,7 @@ class ProcessorShell extends Shell {
       new HelpMenuItem(":help", "show commands"),
       new SafeMainMenuItem(":core", "use CoreNLPProcessor", prepareCore),
       new SafeMainMenuItem(":fast", "use FastNLPProcessor", prepareFast),
-      new SafeMainMenuItem(":clu", "use CluProcessor", prepareClu),
+      new SafeMainMenuItem(":balaur", "use BalaurProcessor", prepareBalaur),
       // new SafeMainMenuItem(":reload", "reload rules for current processor from filesystem", reload),
       new ExitMenuItem(":exit", "exit system")
     )

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

@@ -1,9 +1,9 @@
 package org.clulab.processors
 
-import org.clulab.processors.clu.{CluProcessor, GivenConstEmbeddingsAttachment}
+import org.clulab.processors.clu.BalaurProcessor
 import org.clulab.processors.fastnlp.FastNLPProcessor
-import org.clulab.utils.{FileUtils, Sourcer, StringUtils}
 import org.clulab.struct.GraphMap
+import org.clulab.utils.{FileUtils, Sourcer, StringUtils}
 import org.slf4j.{Logger, LoggerFactory}
 
 import java.io.{File, FileFilter, PrintWriter}
@@ -103,12 +103,7 @@ class TextLabelToCoNLLU(val proc:Processor, val isCoreNLP:Boolean) {
       proc.lemmatize(doc)
       proc.parse(doc)
     } else {
-      GivenConstEmbeddingsAttachment(doc).perform {
-        proc.lemmatize(doc)
-        proc.tagPartsOfSpeech(doc)
-        proc.recognizeNamedEntities(doc)
-        proc.parse(doc)
-      }
+      proc.annotate(doc)
     }
     doc.clear()
   }
@@ -135,7 +130,7 @@ object TextLabelToCoNLLU {
 
     val proc =
       if (props.get("proc").exists(_ == "corenlp")) new FastNLPProcessor()
-      else new CluProcessor()
+      else new BalaurProcessor()
     val isCoreNLP = props.get("proc").exists(_ == "corenlp")
     val converter = new TextLabelToCoNLLU(proc, isCoreNLP)
 

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

@@ -1,7 +1,7 @@
 package org.clulab.processors
 
 
-import org.clulab.processors.clu.CluProcessor
+import org.clulab.processors.clu.BalaurProcessor
 import org.clulab.processors.fastnlp.FastNLPProcessor
 import org.clulab.struct.GraphMap
 import org.clulab.utils.StringUtils
@@ -115,7 +115,7 @@ object TextToCoNLLU {
 
     val proc =
       if (props.get("proc").exists(_ == "corenlp")) new FastNLPProcessor()
-      else new CluProcessor()
+      else new BalaurProcessor()
     val isCoreNLP = props.get("proc").exists(_ == "corenlp")
     val converter = new TextToCoNLLU(proc, isCoreNLP)
 

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

@@ -1,22 +1,19 @@
 package org.clulab.processors.examples
 
-import org.clulab.processors.clu.CluProcessor
+import org.clulab.processors.clu.BalaurProcessor
 import org.clulab.processors.corenlp.CoreNLPProcessor
 import org.clulab.processors.fastnlp.FastNLPProcessor
 import org.clulab.processors.{Document, Processor}
 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()
 
-  // val proc: Processor = new CluProcessor()
-
-  // org.clulab.dynet.Utils.initializeDyNet(mem = "1024,1024,1024,1024")
-  // val proc: Processor = new CluProcessor()
+  // val proc: Processor = new BalaurProcessor()
 
   // val proc = new CoreNLPProcessor(internStrings = false)
 

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

@@ -2,7 +2,7 @@ package org.clulab.processors.examples
 
 import org.clulab.processors.Document
 import org.clulab.processors.Processor
-import org.clulab.processors.fastnlp.FastNLPProcessorWithSemanticRoles
+import org.clulab.processors.fastnlp.FastNLPProcessor
 import org.clulab.serialization.DocumentSerializer
 import org.clulab.utils.{FileUtils, StringUtils, ThreadUtils, Timer}
 
@@ -17,12 +17,12 @@ object InfiniteParallelProcessorExample {
 
   class ProcessorProvider(reuseProcessor: Boolean) {
     protected val processorOpt: Option[Processor] =
-        if (reuseProcessor) Some(new FastNLPProcessorWithSemanticRoles())
+        if (reuseProcessor) Some(new FastNLPProcessor())
         else None
 
     def newOrReusedProcessor: Processor =
         if (reuseProcessor) processorOpt.get
-        else new FastNLPProcessorWithSemanticRoles()
+        else new FastNLPProcessor()
   }
 
   def mainWithCallback(args: Array[String])(callback: (File, String) => Unit): Unit = {
@@ -83,16 +83,12 @@ object InfiniteParallelProcessorExample {
   }
 
   def main(args: Array[String]): Unit = {
-    import org.clulab.fatdynet.utils.Utils
-
-    Utils.startup()
     run(Array(
       FileUtils.getSubprojectDir("./corenlp/src/test/resources/documents"),
       ".",
       "txt",
       "2",
       "false"
     ))
-    Utils.shutdown(true)
   }
 }