Upstream sync (#295)

Miscellaneous changes to sync upstream.
 
This pull request introduces several improvements and bug fixes to the
Python tensor analysis engine, focusing on error handling, code clarity,
and compatibility updates. The most significant changes include improved
exception handling for shape source operations, refactoring for better
code readability, and updates to project settings for enhanced
compatibility with Java and Eclipse.

## Error handling and robustness improvements

* Exception handling was added to shape source operations in
`PythonTensorAnalysisEngine.java` and `TensorType.java`, converting
previously ignored IO errors into runtime exceptions to ensure failures
are surfaced and handled appropriately.
* The `TensorType.shapeArg` method now throws `IOException`, propagating
errors up the call stack instead of silently ignoring them.

## Code clarity and refactoring

* Several code blocks were refactored for readability and
maintainability, such as removing unnecessary braces, improving variable
naming, and restructuring loops and conditional statements.
* Documentation was updated to clarify the behavior of dataset tensor
element checks and associated nodes.

## Project configuration and compatibility

* Project settings were updated to enable Java compiler release
compatibility and preview features, ensuring the codebase remains
up-to-date with the latest Java standards.
* Eclipse resource encoding settings were added for test directories to
ensure consistent file encoding across environments.
* A new Maven test launch configuration was added for easier test
execution within Eclipse.

Author: khatchad

Maven test.launch

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<launchConfiguration type="org.eclipse.m2e.Maven2LaunchConfigurationType">
+    <intAttribute key="M2_COLORS" value="0"/>
+    <booleanAttribute key="M2_DEBUG_OUTPUT" value="false"/>
+    <stringAttribute key="M2_GOALS" value="test"/>
+    <booleanAttribute key="M2_NON_RECURSIVE" value="false"/>
+    <booleanAttribute key="M2_OFFLINE" value="true"/>
+    <stringAttribute key="M2_PROFILES" value=""/>
+    <listAttribute key="M2_PROPERTIES"/>
+    <stringAttribute key="M2_RUNTIME" value="EMBEDDED"/>
+    <booleanAttribute key="M2_SKIP_TESTS" value="false"/>
+    <intAttribute key="M2_THREADS" value="1"/>
+    <booleanAttribute key="M2_UPDATE_SNAPSHOTS" value="true"/>
+    <stringAttribute key="M2_USER_SETTINGS" value=""/>
+    <booleanAttribute key="M2_WORKSPACE_RESOLUTION" value="true"/>
+    <booleanAttribute key="org.eclipse.debug.core.ATTR_FORCE_SYSTEM_CONSOLE_ENCODING" value="false"/>
+    <listAttribute key="org.eclipse.debug.ui.favoriteGroups">
+        <listEntry value="org.eclipse.debug.ui.launchGroup.run"/>
+    </listAttribute>
+    <booleanAttribute key="org.eclipse.jdt.launching.ATTR_ATTR_USE_ARGFILE" value="false"/>
+    <booleanAttribute key="org.eclipse.jdt.launching.ATTR_SHOW_CODEDETAILS_IN_EXCEPTION_MESSAGES" value="true"/>
+    <booleanAttribute key="org.eclipse.jdt.launching.ATTR_USE_CLASSPATH_ONLY_JAR" value="false"/>
+    <stringAttribute key="org.eclipse.jdt.launching.WORKING_DIRECTORY" value="${workspace_loc:/ml}"/>
+</launchConfiguration>

com.ibm.wala.cast.python.jython.test/.settings/org.eclipse.jdt.core.prefs

@@ -18,7 +18,7 @@ org.eclipse.jdt.core.compiler.problem.enablePreviewFeatures=disabled
 org.eclipse.jdt.core.compiler.problem.enumIdentifier=error
 org.eclipse.jdt.core.compiler.problem.forbiddenReference=warning
 org.eclipse.jdt.core.compiler.problem.reportPreviewFeatures=ignore
-org.eclipse.jdt.core.compiler.release=disabled
+org.eclipse.jdt.core.compiler.release=enabled
 org.eclipse.jdt.core.compiler.source=21
 org.eclipse.jdt.core.incompatibleJDKLevel=ignore
 org.eclipse.jdt.core.incompleteClasspath=error

com.ibm.wala.cast.python.ml/source/com/ibm/wala/cast/python/ml/client/PythonTensorAnalysisEngine.java

@@ -44,6 +44,7 @@
 import com.ibm.wala.util.graph.impl.SlowSparseNumberedGraph;
 import com.ibm.wala.util.intset.OrdinalSet;
 import java.io.File;
+import java.io.IOException;
 import java.util.Iterator;
 import java.util.List;
 import java.util.Map;
@@ -168,12 +169,12 @@ private static Set<PointsToSetVariable> getDataflowSources(
           int objectRef = propertyRead.getObjectRef();
           SSAInstruction def = du.getDef(objectRef);
 
-          if (def == null) {
+          if (def == null)
             // definition is unavailable from the local DefUse. Use interprocedural analysis using
             // the PA.
             processInstructionInterprocedurally(
                 propertyRead, objectRef, localPointerKeyNode, src, sources, pointerAnalysis);
-          } else if (def instanceof EachElementGetInstruction
+          else if (def instanceof EachElementGetInstruction
               || def instanceof PythonPropertyRead
               || def instanceof PythonInvokeInstruction) {
             boolean added = false;
@@ -408,7 +409,7 @@ private static boolean processInstructionInterprocedurally(
         IClass concreteType = asin.getConcreteType();
         TypeReference reference = concreteType.getReference();
 
-        if (reference.equals(DATASET) && isDatasetTensorElement(src, use, node, pointerAnalysis)) {
+        if (reference.equals(DATASET) && isDatasetTensorElement(src, use, pointerAnalysis)) {
           sources.add(src);
           logger.info("Added dataflow source from tensor dataset: " + src + ".");
           return true;
@@ -421,69 +422,71 @@ private static boolean processInstructionInterprocedurally(
 
   /**
    * Returns true iff the given {@link PointsToSetVariable} refers to a tensor dataset element of
-   * the dataset defined by the given value number in the given {@link CGNode}.
+   * the dataset defined by the given value number in the its associated {@link CGNode}.
    *
    * @param variable The {@link PointsToSetVariable} to consider.
    * @param val The value in the given {@link CGNode} representing the tensor dataset.
-   * @param node The {@link CGNode} containing the given {@link PointsToSetVariable} and value.
    * @param pointerAnalysis The {@link PointerAnalysis} that includes points-to information for the
    *     given {@link CGNode}.
    * @return True iff src refers to a tensor dataset element defined by the dataset represented by
-   *     val in node.
+   *     val in the node associated with src.
    */
   private static boolean isDatasetTensorElement(
-      PointsToSetVariable variable,
-      int val,
-      CGNode node,
-      PointerAnalysis<InstanceKey> pointerAnalysis) {
-    SSAInstruction def = node.getDU().getDef(val);
-
-    if (def instanceof PythonInvokeInstruction) {
-      PythonInvokeInstruction invokeInstruction = (PythonInvokeInstruction) def;
-
-      // Check whether we are calling enumerate(), as that returns a tuple.
-      // Get the invoked function.
-      int invocationUse = invokeInstruction.getUse(0);
-
-      PointerKey invocationUsePointerKey =
-          pointerAnalysis.getHeapModel().getPointerKeyForLocal(node, invocationUse);
-
-      for (InstanceKey functionInstance : pointerAnalysis.getPointsToSet(invocationUsePointerKey)) {
-        if (functionInstance instanceof ConcreteTypeKey) {
-          ConcreteTypeKey typeKey = (ConcreteTypeKey) functionInstance;
-          IClass type = typeKey.getType();
-          TypeReference typeReference = type.getReference();
-
-          if (typeReference.equals(ENUMERATE.getDeclaringClass())) {
-            // it's a call to enumerate(), where the returned value is an iterator over
-            // tuples. Each tuple consists of the enumeration number and the dataset
-            // element. Check that we are not looking at the enumeration number.
-
-            PythonPropertyRead srcDef =
-                (PythonPropertyRead)
-                    node.getDU()
-                        .getDef(((LocalPointerKey) variable.getPointerKey()).getValueNumber());
-
-            // What does the member reference point to?
-            PointerKey memberRefPointerKey =
-                pointerAnalysis.getHeapModel().getPointerKeyForLocal(node, srcDef.getMemberRef());
-
-            for (InstanceKey memberInstance : pointerAnalysis.getPointsToSet(memberRefPointerKey)) {
-              ConstantKey<?> constant = (ConstantKey<?>) memberInstance;
-              Object value = constant.getValue();
-
-              // if it's the first tuple element.
-              if (value.equals(0)) {
-                // Now that we know it's the first tuple element, we now need to know whether it's
-                // the first tuple, i.e., the one returned by enumerate.
-                // To do that, we examine the object being referenced on the RHS.
-
-                SSAInstruction objRefDef = node.getDU().getDef(srcDef.getObjectRef());
-
-                // If the object being read is that of the dataset, we know that this is the first
-                // tuple read of the result of enumerate() on the dataset.
-                if (objRefDef instanceof PythonPropertyRead
-                    && ((PythonPropertyRead) objRefDef).getObjectRef() == val) return false;
+      PointsToSetVariable variable, int val, PointerAnalysis<InstanceKey> pointerAnalysis) {
+    if (variable.getPointerKey() instanceof LocalPointerKey) {
+      LocalPointerKey localPointerKey = (LocalPointerKey) variable.getPointerKey();
+      CGNode node = localPointerKey.getNode();
+      SSAInstruction def = node.getDU().getDef(val);
+
+      if (def instanceof PythonInvokeInstruction) {
+        PythonInvokeInstruction invokeInstruction = (PythonInvokeInstruction) def;
+
+        // Check whether we are calling enumerate(), as that returns a tuple.
+        // Get the invoked function.
+        int invocationUse = invokeInstruction.getUse(0);
+
+        PointerKey invocationUsePointerKey =
+            pointerAnalysis.getHeapModel().getPointerKeyForLocal(node, invocationUse);
+
+        for (InstanceKey functionInstance :
+            pointerAnalysis.getPointsToSet(invocationUsePointerKey)) {
+          if (functionInstance instanceof ConcreteTypeKey) {
+            ConcreteTypeKey typeKey = (ConcreteTypeKey) functionInstance;
+            IClass type = typeKey.getType();
+            TypeReference typeReference = type.getReference();
+
+            if (typeReference.equals(ENUMERATE.getDeclaringClass())) {
+              // it's a call to enumerate(), where the returned value is an iterator over
+              // tuples. Each tuple consists of the enumeration number and the dataset
+              // element. Check that we are not looking at the enumeration number.
+
+              PythonPropertyRead srcDef =
+                  (PythonPropertyRead)
+                      node.getDU()
+                          .getDef(((LocalPointerKey) variable.getPointerKey()).getValueNumber());
+
+              // What does the member reference point to?
+              PointerKey memberRefPointerKey =
+                  pointerAnalysis.getHeapModel().getPointerKeyForLocal(node, srcDef.getMemberRef());
+
+              for (InstanceKey memberInstance :
+                  pointerAnalysis.getPointsToSet(memberRefPointerKey)) {
+                ConstantKey<?> constant = (ConstantKey<?>) memberInstance;
+                Object value = constant.getValue();
+
+                // if it's the first tuple element.
+                if (value.equals(0)) {
+                  // Now that we know it's the first tuple element, we now need to know whether it's
+                  // the first tuple, i.e., the one returned by enumerate.
+                  // To do that, we examine the object being referenced on the RHS.
+
+                  SSAInstruction objRefDef = node.getDU().getDef(srcDef.getObjectRef());
+
+                  // If the object being read is that of the dataset, we know that this is the first
+                  // tuple read of the result of enumerate() on the dataset.
+                  if (objRefDef instanceof PythonPropertyRead
+                      && ((PythonPropertyRead) objRefDef).getObjectRef() == val) return false;
+                }
               }
             }
           }
@@ -617,16 +620,19 @@ private Map<PointsToSetVariable, TensorType> getShapeSourceCalls(
         op,
         builder,
         (CGNode src, SSAAbstractInvokeInstruction call) -> {
-          if (call.getNumberOfUses() > param) {
-            targets.put(
-                builder
-                    .getPropagationSystem()
-                    .findOrCreatePointsToSet(
-                        builder
-                            .getPointerAnalysis()
-                            .getHeapModel()
-                            .getPointerKeyForLocal(src, call.getDef())),
-                TensorType.shapeArg(src, call.getUse(param)));
+          try {
+            if (call.getNumberOfUses() > param)
+              targets.put(
+                  builder
+                      .getPropagationSystem()
+                      .findOrCreatePointsToSet(
+                          builder
+                              .getPointerAnalysis()
+                              .getHeapModel()
+                              .getPointerKeyForLocal(src, call.getDef())),
+                  TensorType.shapeArg(src, call.getUse(param)));
+          } catch (IOException e) {
+            throw new RuntimeException("Error while processing shape source call: " + call, e);
           }
         });
     return targets;
@@ -663,34 +669,46 @@ public TensorTypeAnalysis performAnalysis(PropagationCallGraphBuilder builder)
 
     TensorType mnistData = TensorType.mnistInput();
     Map<PointsToSetVariable, TensorType> init = HashMapFactory.make();
-    for (PointsToSetVariable v : sources) {
-      init.put(v, mnistData);
+
+    for (PointsToSetVariable v : sources) init.put(v, mnistData);
+
+    Map<PointsToSetVariable, TensorType> placeholders = null;
+    try {
+      placeholders = handleShapeSourceOp(builder, dataflow, placeholder, 2);
+    } catch (IOException e) {
+      throw new RuntimeException("Error while processing placeholder calls.", e);
     }
+    logger.fine("Placeholders: " + placeholders);
 
-    Map<PointsToSetVariable, TensorType> placeholders =
-        handleShapeSourceOp(builder, dataflow, placeholder, 2);
-    logger.fine(() -> "Placeholders: " + placeholders);
-    for (Map.Entry<PointsToSetVariable, TensorType> e : placeholders.entrySet()) {
+    for (Map.Entry<PointsToSetVariable, TensorType> e : placeholders.entrySet())
       init.put(e.getKey(), e.getValue());
-    }
 
     Map<PointsToSetVariable, TensorType> setCalls = HashMapFactory.make();
     Map<PointsToSetVariable, TensorType> set_shapes = getShapeSourceCalls(set_shape, builder, 1);
+
     for (Map.Entry<PointsToSetVariable, TensorType> x : set_shapes.entrySet()) {
-      CGNode setNode = ((LocalPointerKey) x.getKey().getPointerKey()).getNode();
-      int defVn = ((LocalPointerKey) x.getKey().getPointerKey()).getValueNumber();
+      LocalPointerKey localPointerKey = (LocalPointerKey) x.getKey().getPointerKey();
+      CGNode setNode = localPointerKey.getNode();
+      int defVn = localPointerKey.getValueNumber();
       SSAInstruction read = setNode.getDU().getDef(defVn);
       SSAInstruction call = setNode.getDU().getDef(read.getUse(0));
+
       PointerKey setKey =
           builder
               .getPointerAnalysis()
               .getHeapModel()
               .getPointerKeyForLocal(setNode, call.getUse(0));
+
       setCalls.put(builder.getPropagationSystem().findOrCreatePointsToSet(setKey), x.getValue());
     }
 
     Map<PointsToSetVariable, TensorType> shapeOps = HashMapFactory.make();
-    shapeOps.putAll(handleShapeSourceOp(builder, dataflow, reshape, 2));
+
+    try {
+      shapeOps.putAll(handleShapeSourceOp(builder, dataflow, reshape, 2));
+    } catch (IOException e) {
+      throw new RuntimeException("Error while processing reshape calls.", e);
+    }
 
     Set<PointsToSetVariable> conv2ds = getKeysDefinedByCall(conv2d, builder);
 
@@ -708,7 +726,8 @@ private Map<PointsToSetVariable, TensorType> handleShapeSourceOp(
       PropagationCallGraphBuilder builder,
       Graph<PointsToSetVariable> dataflow,
       MethodReference op,
-      int shapeSrcOperand) {
+      int shapeSrcOperand)
+      throws IOException {
     Map<PointsToSetVariable, TensorType> reshapeTypes =
         getShapeSourceCalls(op, builder, shapeSrcOperand);
     for (PointsToSetVariable to : reshapeTypes.keySet()) {

com.ibm.wala.cast.python.ml/source/com/ibm/wala/cast/python/ml/types/TensorType.java

@@ -329,7 +329,7 @@ public static TensorType mnistInput() {
     return new TensorType("pixel", Arrays.asList(batch, vec));
   }
 
-  public static TensorType shapeArg(CGNode node, int literalVn) {
+  public static TensorType shapeArg(CGNode node, int literalVn) throws IOException {
     logger.fine(() -> node.getIR().toString());
     ArrayList<Dimension<?>> r = new ArrayList<>();
     DefUse du = node.getDU();
@@ -360,18 +360,13 @@ public static TensorType shapeArg(CGNode node, int literalVn) {
                   .debugInfo()
                   .getInstructionPosition(du.getDef(val).iIndex());
           System.err.println(p);
-          try {
-            SourceBuffer b = new SourceBuffer(p);
-            String expr = b.toString();
-            System.err.println(expr);
-            Integer ival = PythonInterpreter.interpretAsInt(expr);
-            if (ival != null) {
-              r.add(new NumericDim(ival));
-              continue;
-            }
-          } catch (IOException e) {
-            // TODO Auto-generated catch block
-            e.printStackTrace();
+          SourceBuffer b = new SourceBuffer(p);
+          String expr = b.toString();
+          System.err.println(expr);
+          Integer ival = PythonInterpreter.interpretAsInt(expr);
+          if (ival != null) {
+            r.add(new NumericDim(ival));
+            continue;
           }
         }
         r.add(new SymbolicDim("?"));

com.ibm.wala.cast.python/.settings/org.eclipse.core.resources.prefs

@@ -1,4 +1,6 @@
 eclipse.preferences.version=1
+encoding//src/test/java=UTF-8
+encoding//src/test/resources=UTF-8
 encoding/<project>=UTF-8
 encoding/data=UTF-8
 encoding/source=UTF-8