Enhancement #240

codemeta.json

@@ -135,18 +135,18 @@
     "identifier" : "https://orcid.org/0000-0003-0765-7390"
   },
   "dateCreated" : "2018-02-22",
-  "dateModified" : "2025-09-10",
+  "dateModified" : "2025-10-01",
   "description" : "A heterogeneous data mapping language based on Shape Expressions",
   "developmentStatus" : "active",
   "downloadUrl" : "https://api.github.com/repos/herminiogg/ShExML/downloads",
-  "identifier" : "https://doi.org/10.5281/zenodo.17092549",
+  "identifier" : "https://doi.org/10.5281/zenodo.17250444",
   "license" : "https://api.github.com/licenses/mit",
   "name" : "ShExML",
   "programmingLanguage" : "Scala",
-  "releaseNotes" : "## What's Changed\r\n- Added a parellelisation option in the RDF conversion. You can decide which parts of the execution you want to run in parallel and the number of threads to be used (or let the engine decide based on you hardware specs).\r\n- Stdin can be used as input for the mapping rules or as a input source.\r\n- Some minor fixes and stability improvements.\r\n\r\n**Full Changelog**: https://github.com/herminiogg/ShExML/compare/v0.5.4...v0.6.0",
+  "releaseNotes" : "## What's Changed\r\n* Fixed a bug preventing the correct processing of CSV files through the stdin.",
   "runtimePlatform" : "JVM",
   "softwareRequirements" : [ "http://example.org/jena-shacl", "http://example.org/Saxon-HE", "http://example.org/logback-classic", "http://example.org/jena-core", "http://example.org/scala-compiler", "http://example.org/mysql-connector-java", "http://example.org/stringdistance_2.13", "http://example.org/rmlmapper", "http://example.org/jena-base", "http://example.org/srdf_3", "http://example.org/scala-parallel-collections_3", "http://example.org/mssql-jdbc", "http://example.org/json-path", "http://example.org/picocli", "http://example.org/postgresql", "http://example.org/scala3-library_3", "http://example.org/shex_3", "http://example.org/scala-logging_3", "http://example.org/jena-arq", "http://example.org/srdf4j_3", "http://example.org/slf4j-nop", "http://example.org/antlr4", "http://example.org/mariadb-java-client", "http://example.org/sqlite-jdbc", "http://example.org/scalatest_3", "http://example.org/scala-csv_2.13", "http://example.org/scala-reflect" ],
-  "version" : "0.6.0",
+  "version" : "0.6.1",
   "issueTracker" : "https://api.github.com/repos/herminiogg/ShExML/issues",
   "referencePublication" : "https://doi.org/10.7717/peerj-cs.318"
 }

films.shexml

@@ -1,8 +1,8 @@
 PREFIX : <http://example.com/>
 PREFIX dbr: <http://dbpedia.org/resource/>
 PREFIX schema: <http://schema.org/>
-SOURCE films_xml_file <http://shexml.herminiogarcia.com/files/films.xml>
-SOURCE films_json_file <http://shexml.herminiogarcia.com/files/films.json>
+SOURCE films_xml_file <https://shexml.herminiogarcia.com/files/films.xml>
+SOURCE films_json_file <https://shexml.herminiogarcia.com/files/films.json>
 ITERATOR film_xml <xpath: //film> {
     FIELD id <@id>
     FIELD name <name>

src/main/java/com/herminiogarcia/shexml/helper/LogRedErrorConverter.java

@@ -0,0 +1,18 @@
+package com.herminiogarcia.shexml.helper;
+
+import ch.qos.logback.classic.Level;
+import ch.qos.logback.classic.spi.ILoggingEvent;
+import ch.qos.logback.core.pattern.color.ANSIConstants;
+import ch.qos.logback.core.pattern.color.ForegroundCompositeConverterBase;
+
+public class LogRedErrorConverter extends ForegroundCompositeConverterBase<ILoggingEvent> {
+
+    @Override
+    protected String getForegroundColorCode(ILoggingEvent event) {
+        if (event.getLevel().equals(Level.ERROR)) {
+            return ANSIConstants.RED_FG;
+        }
+        return ANSIConstants.DEFAULT_FG; // default color for everything else
+    }
+
+}

src/main/resources/logback.xml

@@ -1,7 +1,10 @@
 <configuration>
+    <conversionRule conversionWord="errorsInRed"
+                    converterClass="com.herminiogarcia.shexml.helper.LogRedErrorConverter" />
+
     <appender name="STDOUT" class="ch.qos.logback.core.ConsoleAppender">
         <encoder>
-            <pattern>%d{HH:mm:ss.SSS} %-5level[%thread] [%class] - %msg%n</pattern>
+            <pattern>%errorsInRed(%d{HH:mm:ss.SSS} %-5level[%thread] [%class] - %msg%n)</pattern>
         </encoder>
     </appender>
     <root level="info">

src/main/scala/com/herminiogarcia/shexml/Main.scala

@@ -1,10 +1,11 @@
 package com.herminiogarcia.shexml
 
-import com.herminiogarcia.shexml.helper.{ParallelExecutionConfigurator, PicocliLeftAlignedLayout}
+import com.herminiogarcia.shexml.helper.{ParallelExecutionConfigurator, PicocliLeftAlignedLayout, ShExMLError}
+import com.typesafe.scalalogging.Logger
 import picocli.CommandLine
 import picocli.CommandLine.{ArgGroup, Command, Option}
 
-import java.io.{File, PrintWriter}
+import java.io.{File, PrintWriter, StringWriter}
 import java.util.concurrent.Callable
 
 /**
@@ -26,6 +27,8 @@ object Main {
   description = Array("Map and merge heterogeneous data sources with a Shape Expressions based syntax"))
 class Main extends Callable[Int] {
 
+  private val logger = Logger[MappingLauncher]
+
   @Option(names = Array("-m", "--mapping"), required = true, description = Array("Path to the file with the mappings. If '-' is provided as the path the engine will read from the standard input."))
   private var file: String = ""
 
@@ -43,8 +46,8 @@ class Main extends Callable[Int] {
     val parallelExecutionConfiguration =
       if(generalTransformationOptions.parallel) ParallelExecutionConfigurator(generalTransformationOptions.parallelAspects, generalTransformationOptions.numberOfThreads)
       else ParallelExecutionConfigurator.empty
+    val fileContent = fileHandler.mkString
     try {
-      val fileContent = fileHandler.mkString
       val mappingLauncher = new MappingLauncher(
         generalTransformationOptions.username,
         generalTransformationOptions.password,
@@ -76,6 +79,15 @@ class Main extends Callable[Int] {
         pw.close()
       }
       0 // well finished
+    } catch {
+      case e: ShExMLError =>
+        val sw = new StringWriter()
+        val pw = new PrintWriter(sw)
+        e.printStackTrace(pw)
+        val stackTrace = sw.toString
+        pw.close(); sw.close()
+        logger.error(s"${e.getEnrichedErrorMessage(fileContent)}\n$stackTrace")
+        1 // badly finished
     } finally { fileHandler.close() }
   }
 }

src/main/scala/com/herminiogarcia/shexml/MappingLauncher.scala

@@ -2,14 +2,15 @@ package com.herminiogarcia.shexml
 
 import com.herminiogarcia.shexml.antlr.{ShExMLLexer, ShExMLParser}
 import com.herminiogarcia.shexml.ast._
-import com.herminiogarcia.shexml.helper.{OrphanBNodeRemover, ParallelExecutionConfigurator, SourceHelper}
+import com.herminiogarcia.shexml.helper.{LexerErrorListener, OrphanBNodeRemover, ParallelExecutionConfigurator, ParserErrorListener, SourceHelper}
 import com.herminiogarcia.shexml.parser.ASTCreatorVisitor
 import com.herminiogarcia.shexml.shex._
-import com.herminiogarcia.shexml.visitor.{PushedOrPoppedValueSearchVisitor, RDFGeneratorVisitor, RMLGeneratorVisitor, VarTableBuilderVisitor}
+import com.herminiogarcia.shexml.visitor.{PushedOrPoppedValueSearchVisitor, RDFGeneratorVisitor, RMLGeneratorVisitor, SemanticCheckerVisitor, VarTableBuilderVisitor}
 import org.antlr.v4.runtime.{CharStreams, CommonTokenStream}
 import org.apache.jena.query.{Dataset, DatasetFactory}
 import org.apache.jena.riot.{RDFDataMgr, RDFFormat, RDFLanguages}
 import com.typesafe.scalalogging.Logger
+
 import java.io.ByteArrayOutputStream
 import scala.collection.JavaConverters._
 import java.util.concurrent.ConcurrentLinkedQueue
@@ -47,6 +48,7 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
     val parser = createParser(lexer)
     val ast = createAST(parser)
     val varTable = createVarTable(ast)
+    runSemanticAnalysis(ast, varTable)
     generateResultingRDF(ast, varTable)
   }
 
@@ -58,6 +60,7 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
     val ast = createAST(parser)
     val varTable = createVarTable(ast)
     val dataset = generateResultingRML(ast, varTable, prettify)
+    runSemanticAnalysis(ast, varTable)
     val outputStream = new ByteArrayOutputStream()
     if(prettify) new OrphanBNodeRemover().removeOrphanBNodes(dataset.getDefaultModel)
     RDFDataMgr.write(outputStream, dataset.getDefaultModel, RDFFormat.TURTLE_PRETTY)
@@ -71,6 +74,7 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
     val parser = createParser(lexer)
     val ast = createAST(parser)
     val varTable = createVarTable(ast)
+    runSemanticAnalysis(ast, varTable)
     val inferencesTable = new ConcurrentLinkedQueue[ShExMLInferredCardinalitiesAndDatatypes]()
     generateInferencesFromShExML(ast, varTable, inferencesTable)
     val shex = new ShExGeneratorVisitor(inferencesTable.asScala.toList).doVisit(ast, null)
@@ -84,6 +88,7 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
     val parser = createParser(lexer)
     val ast = createAST(parser)
     val varTable = createVarTable(ast)
+    runSemanticAnalysis(ast, varTable)
     val shapeMaps = generateShapeMaps(ast, varTable)
     new ShapeMapPrinter().print(shapeMaps)
   }
@@ -96,6 +101,7 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
     val ast = createAST(parser)
     val varTable = createVarTable(ast)
     val inferencesTable = new ConcurrentLinkedQueue[ShExMLInferredCardinalitiesAndDatatypes]()
+    runSemanticAnalysis(ast, varTable)
     generateInferencesFromShExML(ast, varTable, inferencesTable)
     logger.info(s"Executing ShEx extraction process as base for the SHACL conversion")
     val shex = new ShExGeneratorVisitor(inferencesTable.asScala.toList).doVisit(ast, null)
@@ -115,6 +121,8 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
       val lexer = createLexer(mappingCode)
       val parser = createParser(lexer)
       val ast = createAST(parser)
+      val varTable = createVarTable(ast)
+      runSemanticAnalysis(ast, varTable)
       precompiledMappingRules
     } catch {
       case e: Exception =>
@@ -126,12 +134,18 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
   private def createLexer(mappingCode: String): ShExMLLexer = {
     val finalMappingRules = resolveImports(mappingCode)
     logger.info("Applying lexer to tokenize input mapping rules")
-    new ShExMLLexer(CharStreams.fromString(finalMappingRules))
+    val lexer = new ShExMLLexer(CharStreams.fromString(finalMappingRules))
+    lexer.removeErrorListeners()
+    lexer.addErrorListener(new LexerErrorListener)
+    lexer
   }
 
   private def createParser(lexer: ShExMLLexer): ShExMLParser = {
     logger.info("Parsing tokens from the lexer")
-    new ShExMLParser(new CommonTokenStream(lexer))
+    val parser = new ShExMLParser(new CommonTokenStream(lexer))
+    parser.removeErrorListeners()
+    parser.addErrorListener(new ParserErrorListener)
+    parser
   }
 
   private def createAST(parser: ShExMLParser): AST = {
@@ -142,14 +156,20 @@ class MappingLauncher(val username: String = "", val password: String = "", driv
   private def createVarTable(ast: AST): mutable.HashMap[Variable, VarResult] = {
     logger.info(s"Building var table")
     val varTable = mutable.HashMap[Variable, VarResult]()
-    varTable += ((Var("rdf:"), URL("http://www.w3.org/1999/02/22-rdf-syntax-ns#")))
+    varTable += ((Var("rdf:"), URL("http://www.w3.org/1999/02/22-rdf-syntax-ns#", UnknownParserInfo)))
     val optionalArgument = Map("variable" -> "", "query" -> "")
     new VarTableBuilderVisitor(varTable).visit(ast, optionalArgument)
     logger.debug(s"Var table contents:")
     varTable.foreach {case (v, vr) => logger.debug(s"$v -> $vr")}
     varTable
   }
 
+  private def runSemanticAnalysis(ast: AST, varTable: mutable.HashMap[Variable, VarResult]): Unit = {
+    logger.info(s"Running semantic analysis")
+    new SemanticCheckerVisitor(varTable.toMap).doVisit(ast, null)
+    logger.debug(s"Semantic analysis completed satisfactorily")
+  }
+
   private def generateResultingRDF(ast: AST, varTable: mutable.HashMap[Variable, VarResult]): Dataset = {
 
     val dataset = DatasetFactory.create()