Update JuFiT to Version 1.2

* Update Semantic Groups from
https://metamap.nlm.nih.gov/Docs/SemGroups_2018.txt
* Removed an description error in Main.Java and the Readme file.

Author: chlor

.gitignore

@@ -5,3 +5,11 @@ target
 .project
 .classpath
 /.DS_Store
+*.gz
+*.txt
+*.sh
+*.RRF
+*.nlm
+*.CHK
+*.MD5
+*.zip

JenaUmlsFilter-1.1-jar-with-dependencies.jar

@@ -1,4 +1,4 @@
-Copyright (c) 2018, JULIE Lab
+Copyright (c) 2020, JULIE Lab
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

JenaUmlsFilter-1.2-jar-with-dependencies.jar

@@ -15,17 +15,15 @@ BSD license (2-clause).
 
 Please cite [JuFiT: A Configurable Rule Engine for Filtering and Generating New Multilingual UMLS Terms](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4765630/) when using JuFiT in your research.
 
-
 ## Usage
 ```
-java -jar <JUFIT-JAR> 
+java -jar <JuFiT-file.jar>
 ```
 followed by (on the same line)
 ```
- jufit <mrconso> <mrsty> <language> (--mrconso | --terms | --grounded | --complex) [--outFile=FILE] [--semanticGroup=GROUP]... [--rules=JSON] [--noFilter]
- jufit --help
- jufit --version
-
+ <mrconso> <mrsty> <language> (--mrconso | --terms | --grounded | --complex) [--outFile=FILE] [--semanticGroup=GROUP]  ...  [--rules=JSON] [--noFilter]
+ --help
+ --version
 Options:
 --help  Show this screen
 --version  Show the version number
@@ -44,3 +42,4 @@ We suggest updating your Java VM arguments to use at least 0.5GB of RAM, i.e., `
 
 ## Recent Changes:
   * 1.1 New output formats, new command line interface, change to license
+  * 1.2 Semantic Group definition (from https://metamap.nlm.nih.gov/Docs/SemGroups_2018.txt)

LICENSE

@@ -1,5 +1,8 @@
-<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+<project
+	xmlns="http://maven.apache.org/POM/4.0.0"
+	xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+
 	<properties>
 		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
 		<maven.compiler.source>1.8</maven.compiler.source>
@@ -14,7 +17,7 @@
 
 	<modelVersion>4.0.0</modelVersion>
 	<artifactId>JenaUmlsFilter</artifactId>
-	<version>1.1</version>
+	<version>1.2</version>
 	<dependencies>
 		<dependency>
 			<groupId>junit</groupId>

README.md

@@ -25,94 +25,31 @@
  *
  * First entry on each enum, i.e., short name, was then manually added
  *
- * @author hellrich
+ * Update from 04/27/2020:
+ * The definition of the Semantic Groups and the Semantic Types changed.
+ * We updated the Semantic Types of the Semantic Groups from
+ * https://metamap.nlm.nih.gov/Docs/SemGroups_2018.txt
+ *
+ * @author hellrich, chlor
  *
  */
+
 public enum SemanticGroup {
-	ACTI("Activities & Behaviors", "T052", "T053", "T056", "T051", "T064",
-			"T055", "T066", "T057", "T054"), ANAT("Anatomy", "T017", "T029",
-					"T023", "T030", "T031", "T022", "T025", "T026", "T018",
-					"T021", "T024"), CHEM("Chemicals & Drugs", "T116", "T195",
-							"T123", "T122", "T118", "T103", "T120", "T104",
-							"T200", "T111", "T196", "T126", "T131", "T125",
-							"T129", "T130", "T197", "T119", "T124", "T114",
-							"T109", "T115", "T121", "T192", "T110",
-							"T127"), CONC("Concepts & Ideas", "T185", "T077",
-									"T169", "T102", "T078", "T170", "T171",
-									"T080", "T081", "T089", "T082",
-									"T079"), DEVI("Devices", "T203", "T074",
-											"T075"), DISO("Disorders", "T020",
-													"T190", "T049", "T019",
-													"T047", "T050", "T033",
-													"T037", "T048", "T191",
-													"T046", "T184"), GENE(
-															"Genes & Molecular Sequences",
-															"T087", "T088",
-															"T028", "T085",
-															"T086"), GEOG(
-																	"Geographic Areas",
-																	"T083"), LIVB(
-																			"Living Beings",
-																			"T100",
-																			"T011",
-																			"T008",
-																			"T194",
-																			"T007",
-																			"T012",
-																			"T204",
-																			"T099",
-																			"T013",
-																			"T004",
-																			"T096",
-																			"T016",
-																			"T015",
-																			"T001",
-																			"T101",
-																			"T002",
-																			"T098",
-																			"T097",
-																			"T014",
-																			"T010",
-																			"T005"), OBJC(
-																					"Objects",
-																					"T071",
-																					"T168",
-																					"T073",
-																					"T072",
-																					"T167"), OCCU(
-																							"Occupations",
-																							"T091",
-																							"T090"), ORGA(
-																									"Organizations",
-																									"T093",
-																									"T092",
-																									"T094",
-																									"T095"), PHEN(
-																											"Phenomena",
-																											"T038",
-																											"T069",
-																											"T068",
-																											"T034",
-																											"T070",
-																											"T067"), PHYS(
-																													"Physiology",
-																													"T043",
-																													"T201",
-																													"T045",
-																													"T041",
-																													"T044",
-																													"T032",
-																													"T040",
-																													"T042",
-																													"T039"), PROC(
-																															"Procedures",
-																															"T060",
-																															"T065",
-																															"T058",
-																															"T059",
-																															"T063",
-																															"T062",
-																															"T061");
+	ACTI("Activities & Behaviors", "T052", "T053", "T056", "T051", "T064", "T055", "T066", "T057", "T054"),
+	ANAT("Anatomy", "T017", "T029", "T023", "T030", "T031", "T022", "T025", "T026", "T018",    "T021", "T024"),
+	CHEM("Chemicals & Drugs", "T116", "T195", "T123", "T122", "T118", "T103", "T120", "T104", "T200", "T111", "T196", "T126", "T131", "T125", "T129", "T130", "T197", "T119", "T124", "T114", "T109", "T115", "T121", "T192", "T110", "T127"),
+	CONC("Concepts & Ideas", "T185", "T077", "T169", "T102", "T078", "T170", "T171", "T080", "T081", "T089", "T082", "T079"),
+	DEVI("Devices", "T203", "T074", "T075"),
+	DISO("Disorders", "T020", "T190", "T049", "T019", "T047", "T050", "T033", "T037", "T048", "T191", "T046", "T184"),
+	GENE("Genes & Molecular Sequences", "T087", "T088", "T028", "T085", "T086"),
+	GEOG("Geographic Areas", "T083"),
+	LIVB("Living Beings", "T100", "T011", "T008", "T194", "T007", "T012", "T204", "T099", "T013", "T004", "T096", "T016", "T015", "T001", "T101", "T002", "T098", "T097", "T014", "T010", "T005"),
+	OBJC("Objects", "T071", "T168", "T073", "T072", "T167"),
+	OCCU("Occupations", "T091", "T090"),
+	ORGA("Organizations", "T093", "T092", "T094", "T095"),
+	PHEN("Phenomena", "T038", "T069", "T068", "T034", "T070", "T067"),
+	PHYS("Physiology", "T043", "T201", "T045", "T041", "T044", "T032", "T040", "T042", "T039"),
+	PROC("Procedures", "T060", "T065", "T058", "T059", "T063", "T062", "T061");
 
 	private final static Map<String, SemanticGroup> termId2group = new HashMap<>();
 
@@ -141,5 +78,4 @@ private SemanticGroup(final String... strings) {
 		termIds = ImmutableSet
 				.copyOf(Arrays.asList(strings).subList(1, strings.length));
 	}
-
-}
+}

dic-Submission-AMIA2020/JenaUmlsFilter-1.1-jar-with-dependencies.jar

@@ -30,11 +30,13 @@
 
 public class Main {
 
-	public static final String VERSION = "1.1";
+	public static final String VERSION = "1.2";
 
 	private static final String doc = "Usage:\n"
-			+ " jufit <mrconso> <mrsty> <language> (--mrconso | --terms | --grounded | --complex) [--outFile=FILE] [--semanticGroup=GROUP]... [--rules=JSON] [--noFilter]\n"
-			+ " jufit --help\n" + " jufit --version\n" + "\nOptions:\n"
+			+ " java -jar <JuFiT-file.jar> "
+			+ " followed by (on the same line)"
+			+ " <mrconso> <mrsty> <language> (--mrconso | --terms | --grounded | --complex) [--outFile=FILE] [--semanticGroup=GROUP]... [--rules=JSON] [--noFilter]\n"
+			+ " --help\n" + " jufit --version\n" + "\nOptions:\n"
 			+ "--help  Show this screen\n"
 			+ "--version  Show the version number\n"
 			+ "--mrconso  MRCONSO output format (one format must be chosen)\n"
@@ -49,67 +51,67 @@ public class Main {
 
 	@SuppressWarnings("unchecked")
 	public static void main(final String[] args) throws IOException {
-		final Map<String, Object> opts = new Docopt(doc).withVersion(VERSION)
-				.parse(args);
+		final Map<String, Object> opts = new Docopt(doc).withVersion(VERSION).parse(args);
 		final String pathToMRCONSO = (String) opts.get("<mrconso>");
 		final String pathToMRSTY = (String) opts.get("<mrsty>");
 		final String language = (String) opts.get("<language>");
+
 		if (language.length() != 3) {
-			System.err.println(
-					"Only 3 letter languages codes supported, e.g., ENG for English");
+			System.err.println("Only 3 letter languages codes supported, e.g., ENG for English");
 			System.exit(1);
 		}
-		final String jsonFile = (String) opts.get("--rules"); //may be null, respected later
 
+		final String jsonFile = (String) opts.get("--rules"); //may be null, respected later
 		final Set<SemanticGroup> onlyTheseSemanticGroups = new HashSet<>();
+
 		try {
 			((List<String>) opts.get("--semanticGroup")).stream()
 					.map(SemanticGroup::valueOf)
 					.forEach(onlyTheseSemanticGroups::add);
 		} catch (final IllegalArgumentException e) {
 			System.err.println(
 					"Only the following semantic group names are supported:\n"
-							+ SemanticGroup.getNames()
-									.collect(Collectors.joining(", ")));
+					+ SemanticGroup.getNames().collect(Collectors.joining(", ")));
 			System.exit(1);
 		}
 
 		OutputFormat outputFormat = null;
-		if ((boolean) opts.get("--mrconso"))
+		if ((boolean) opts.get("--mrconso")){
 			outputFormat = OutputFormat.MRCONSO;
-		else if ((boolean) opts.get("--terms"))
+		}
+		else if ((boolean) opts.get("--terms")){
 			outputFormat = OutputFormat.TERMS;
-		else if ((boolean) opts.get("--grounded"))
+		}
+		else if ((boolean) opts.get("--grounded")){
 			outputFormat = OutputFormat.GROUNDED_TERMS;
-		else if ((boolean) opts.get("--complex"))
+		}
+			else if ((boolean) opts.get("--complex")){
 			outputFormat = OutputFormat.COMPLEX;
-		if (outputFormat == null)
-			throw new IllegalArgumentException(
-					"No valid output format selected!");
+		}
+		if (outputFormat == null){
+			throw new IllegalArgumentException("No valid output format selected!");
+		}
 
 		final boolean applyFilters = !(boolean) opts.get("--noFilter");
-		if (!applyFilters && (OutputFormat.MRCONSO == outputFormat))
-			throw new IllegalArgumentException(
-					"Applying no filtering while producing MRCONSO format is pointless");
+		if (!applyFilters && (OutputFormat.MRCONSO == outputFormat)){
+			throw new IllegalArgumentException("Applying no filtering while producing MRCONSO format is pointless");
+		}
 
 		final String outFileName = (String) opts.get("--outFile"); //may be null, respected later
-		if(null != outFileName)
+		if(null != outFileName){
 			System.setOut(new PrintStream(new BufferedOutputStream(new FileOutputStream(outFileName)), true));
-		
+		}
+
 		//Iterate over UMLS to generate list of existing terms
 		//TODO Currently respects pre-existing terms of all semantic groups, even those later ignored. Trivial change, unsure what is expected behavior?
 		final Set<String> existingTerms = Streams
-				.stream(UMLSTermProvider.provideUMLSTerms(pathToMRCONSO,
-						pathToMRSTY, true, null, language))
-				.map(ProvidedTerm::getTerm).collect(Collectors.toSet());
+			.stream(UMLSTermProvider.provideUMLSTerms(pathToMRCONSO, pathToMRSTY, true, null, language))
+			.map(ProvidedTerm::getTerm).collect(Collectors.toSet());
 
 		//Prepare to iterate over UMLS again, this time respecting group restrictions (if any)
-		final Iterator<ProvidedTerm> iterator = UMLSTermProvider
-				.provideUMLSTerms(pathToMRCONSO, pathToMRSTY, true,
-						onlyTheseSemanticGroups, language);
-
-		Delemmatizer.delemmatize(iterator, outputFormat, existingTerms,
-				jsonFile, language, applyFilters);
+		final Iterator<ProvidedTerm> iterator =
+			UMLSTermProvider.provideUMLSTerms(pathToMRCONSO, pathToMRSTY, true, onlyTheseSemanticGroups, language);
 
+		Delemmatizer.delemmatize(iterator, outputFormat, existingTerms, jsonFile, language, applyFilters);
 	}
 }