Resolution for #67: Added CLI options --limit and --paginate

Author: Aklakan

pom.xml

@@ -476,7 +476,7 @@
 				<plugin>
 					<groupId>com.google.cloud.tools</groupId>
 					<artifactId>jib-maven-plugin</artifactId>
-					<version>3.2.0</version>
+					<version>3.4.4</version>
 				</plugin>
 				<plugin>
 					<artifactId>jdeb</artifactId>

rdf-processing-toolkit-cli/src/main/java/org/aksw/sparql_integrate/cli/cmd/CmdSparqlIntegrateMain.java

@@ -11,6 +11,7 @@
 import java.util.concurrent.Callable;
 
 import org.aksw.jenax.arq.picocli.CmdMixinArq;
+import org.aksw.jenax.arq.picocli.CmdMixinSparqlPaginate;
 import org.aksw.rdf_processing_toolkit.cli.cmd.CmdCommonBase;
 import org.aksw.rdf_processing_toolkit.cli.cmd.VersionProviderRdfProcessingToolkit;
 import org.aksw.sparql_integrate.cli.main.SparqlIntegrateCmdImpls;
@@ -75,8 +76,6 @@ public class CmdSparqlIntegrateMain
     @Option(names = { "--cache-rewrite-groupby" }, description="Cache GROUP BY operations individually. Ignored if no cache engine is specified.") //, defaultValue = "false", fallbackValue = "true")
     public boolean cacheRewriteGroupBy = false;
 
-
-
     @Option(names = { "--tmpdir" }, description="Temporary directory")
     public String tempPath = StandardSystemProperty.JAVA_IO_TMPDIR.value();
 
@@ -96,6 +95,10 @@ public class CmdSparqlIntegrateMain
     @Mixin
     public CmdMixinArq arqConfig = new CmdMixinArq();
 
+    /** Mixin for result set limit and pagination */
+    @Mixin
+    public CmdMixinSparqlPaginate paginationConfig = new CmdMixinSparqlPaginate();
+
     @Option(names= {"--bnp", "--bnode-profile"}, description="Blank node profile, empty string ('') to disable; 'auto' to autodetect, defaults to ${DEFAULT-VALUE}", defaultValue = "")
     public String bnodeProfile = null;
 

rdf-processing-toolkit-cli/src/main/java/org/aksw/sparql_integrate/cli/main/SparqlIntegrateCmdImpls.java

@@ -484,6 +484,16 @@ public static int sparqlIntegrate(CmdSparqlIntegrateMain cmd) throws Exception {
             }
         }
 
+        Long resultSetPageSize = cmd.paginationConfig.queryPageSize;
+        if (resultSetPageSize != null && resultSetPageSize > 0) {
+            dataSourceTmp = RdfDataEngines.wrapWithDataSourceTransform(dataSourceTmp, ds -> RdfDataSources.withPagination(ds, resultSetPageSize));
+        }
+
+        Long queryLimit = cmd.paginationConfig.queryLimit;
+        if (queryLimit != null && queryLimit > 0) {
+            dataSourceTmp = RdfDataEngines.wrapWithDataSourceTransform(dataSourceTmp, ds -> RdfDataSources.withLimit(ds, queryLimit));
+        }
+
         dataSourceTmp = RdfDataEngines.wrapWithQueryTransform(dataSourceTmp, null, QueryExecs::withDetailedHttpMessages);
 
         if (cmd.cachePath != null) {
@@ -582,16 +592,19 @@ public static int sparqlIntegrate(CmdSparqlIntegrateMain cmd) throws Exception {
 
         // Load function macros (run sparql inferences first)
         Map<String, UserDefinedFunctionDefinition> udfRegistry = new LinkedHashMap<>();
+
+        // XXX There should be a separate registry for default macros to load.
+        loadMacros(macroProfiles, udfRegistry, "macros/ollama.ttl");
+
         for (String macroSource : cmd.macroSources) {
-            Model model = RDFDataMgr.loadModel(macroSource);
-            SparqlStmtMgr.execSparql(model, "udf-inferences.rq");
-            Map<String, UserDefinedFunctionDefinition> contrib = UserDefinedFunctions.load(model, macroProfiles);
-            udfRegistry.putAll(contrib);
+            loadMacros(macroProfiles, udfRegistry, macroSource);
         }
 
         if (!cmd.macroSources.isEmpty()) {
-            logger.info("Loaded functions: {}", udfRegistry.keySet());
-            logger.info("Loaded {} function definitions from  {} macro sources.", udfRegistry.size(), cmd.macroSources.size());
+            if (logger.isInfoEnabled()) {
+                logger.info("Loaded functions: {}", udfRegistry.keySet());
+                logger.info("Loaded {} function definitions from  {} macro sources.", udfRegistry.size(), cmd.macroSources.size());
+            }
             // ExprTransform eform = new ExprTransformExpand(udfRegistry);
             ExprTransform eform = new ExprTransformCopy() {
                 @Override
@@ -602,8 +615,6 @@ public Expr transform(ExprFunctionN func, ExprList args) {
             };
             SparqlStmtTransform stmtTransform = SparqlStmtTransforms.ofExprTransform(eform);
             dataSourceTmp = RdfDataEngines.wrapWithStmtTransform(dataSourceTmp, stmtTransform);
-            // QueryTransform qform = q -> QueryUtils.rewrite(q, op -> Transformer.transform(null, eform, op));
-            // dataSourceTmp = RdfDataEngines.wrapWithQueryTransform(dataSourceTmp, qform, null);
         }
 
         RdfDataEngine datasetAndDelete = dataSourceTmp;
@@ -848,10 +859,14 @@ public void afterExec() {
 
                 server.start();
 
+                // Try to get the host address from a network device (e.g. within a docker container)
                 String hostAddress;
                 try(final DatagramSocket socket = new DatagramSocket()){
                     socket.connect(InetAddress.getByName("1.1.1.1"), 53);
                     hostAddress = socket.getLocalAddress().getHostAddress();
+                } catch (Exception e) {
+                    // Fall back to localhost
+                    hostAddress = "localhost";
                 }
                 URI browseUri = new URI("http://"+hostAddress+":" + port + "/");
                 if (Desktop.isDesktopSupported()) {
@@ -928,6 +943,14 @@ public void afterExec() {
         return exitCode;
     }
 
+    private static void loadMacros(Set<String> macroProfiles, Map<String, UserDefinedFunctionDefinition> udfRegistry,
+            String macroSource) {
+        Model model = RDFDataMgr.loadModel(macroSource);
+        SparqlStmtMgr.execSparql(model, "udf-inferences.rq");
+        Map<String, UserDefinedFunctionDefinition> contrib = UserDefinedFunctions.load(model, macroProfiles);
+        udfRegistry.putAll(contrib);
+    }
+
     /** Be careful not to call within a read transaction! */
     public static void updateSpatialIndex(Dataset dataset) {
         Context cxt = dataset.getContext();