@eagleoutice/flowr 2.3.0 → 2.4.0

package/README.md

@@ -24,7 +24,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.2.16, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.3.0, R v4.5.0 (r-shell engine)
     R> :query @linter "read.csv(\"/root/x.txt\")"
     ```
     
@@ -33,17 +33,17 @@ It offers a wide variety of features, for example:
     
     
     ```text
-    Query: linter (2 ms)
+    Query: linter (3 ms)
        ╰ **Deprecated Functions** (deprecated-functions):
            ╰ _Metadata_: <code>{"totalDeprecatedCalls":0,"totalDeprecatedFunctionDefinitions":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **File Path Validity** (file-path-validity):
-           ╰ definitely:
+           ╰ certain:
                ╰ Path `/root/x.txt` at 1.1-23
            ╰ _Metadata_: <code>{"totalReads":1,"totalUnknown":0,"totalWritesBeforeAlways":0,"totalValid":0,"searchTimeMs":1,"processTimeMs":0}</code>
        ╰ **Seeded Randomness** (seeded-randomness):
            ╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Absolute Paths** (absolute-file-paths):
-           ╰ definitely:
+           ╰ certain:
                ╰ Path `/root/x.txt` at 1.1-23
            ╰ _Metadata_: <code>{"totalConsidered":1,"totalUnknown":0,"searchTimeMs":1,"processTimeMs":0}</code>
        ╰ **Unused Definitions** (unused-definitions):
@@ -52,7 +52,9 @@ It offers a wide variety of features, for example:
            ╰ _Metadata_: <code>{"numMatches":0,"numBreak":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Dataframe Access Validation** (dataframe-access-validation):
            ╰ _Metadata_: <code>{"numOperations":0,"numAccesses":0,"totalAccessed":0,"searchTimeMs":0,"processTimeMs":0}</code>
-    All queries together required ≈2 ms (1ms accuracy, total 7 ms)
+       ╰ **Dead Code** (dead-code):
+           ╰ _Metadata_: <code>{"consideredNodes":5,"searchTimeMs":1,"processTimeMs":0}</code>
+    All queries together required ≈3 ms (1ms accuracy, total 9 ms)
     ```
     
     
@@ -74,30 +76,32 @@ It offers a wide variety of features, for example:
     
     _Results (prettified and summarized):_
     
-    Query: **linter** (12 ms)\
+    Query: **linter** (14 ms)\
     &nbsp;&nbsp;&nbsp;╰ **Deprecated Functions** (deprecated-functions):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalDeprecatedCalls":0,"totalDeprecatedFunctionDefinitions":0,"searchTimeMs":1,"processTimeMs":0}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalDeprecatedCalls":0,"totalDeprecatedFunctionDefinitions":0,"searchTimeMs":2,"processTimeMs":0}</code>\
     &nbsp;&nbsp;&nbsp;╰ **File Path Validity** (file-path-validity):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ definitely:\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ certain:\
     &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ Path `/root/x.txt` at 1.1-23\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalReads":1,"totalUnknown":0,"totalWritesBeforeAlways":0,"totalValid":0,"searchTimeMs":3,"processTimeMs":1}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalReads":1,"totalUnknown":0,"totalWritesBeforeAlways":0,"totalValid":0,"searchTimeMs":4,"processTimeMs":1}</code>\
     &nbsp;&nbsp;&nbsp;╰ **Seeded Randomness** (seeded-randomness):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"searchTimeMs":1,"processTimeMs":0}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"searchTimeMs":0,"processTimeMs":1}</code>\
     &nbsp;&nbsp;&nbsp;╰ **Absolute Paths** (absolute-file-paths):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ definitely:\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ certain:\
     &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ Path `/root/x.txt` at 1.1-23\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalConsidered":1,"totalUnknown":0,"searchTimeMs":2,"processTimeMs":0}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalConsidered":1,"totalUnknown":0,"searchTimeMs":1,"processTimeMs":1}</code>\
     &nbsp;&nbsp;&nbsp;╰ **Unused Definitions** (unused-definitions):\
     &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalConsidered":0,"searchTimeMs":0,"processTimeMs":0}</code>\
     &nbsp;&nbsp;&nbsp;╰ **Naming Convention** (naming-convention):\
     &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"numMatches":0,"numBreak":0,"searchTimeMs":0,"processTimeMs":0}</code>\
     &nbsp;&nbsp;&nbsp;╰ **Dataframe Access Validation** (dataframe-access-validation):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"numOperations":0,"numAccesses":0,"totalAccessed":0,"searchTimeMs":0,"processTimeMs":3}</code>\
-    _All queries together required ≈13 ms (1ms accuracy, total 207 ms)_
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"numOperations":0,"numAccesses":0,"totalAccessed":0,"searchTimeMs":0,"processTimeMs":2}</code>\
+    &nbsp;&nbsp;&nbsp;╰ **Dead Code** (dead-code):\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"consideredNodes":5,"searchTimeMs":0,"processTimeMs":0}</code>\
+    _All queries together required ≈14 ms (1ms accuracy, total 214 ms)_
     
     <details> <summary style="color:gray">Show Detailed Results as Json</summary>
     
-    The analysis required _207.2 ms_ (including parsing and normalization and the query) within the generation environment.	
+    The analysis required _213.8 ms_ (including parsing and normalization and the query) within the generation environment.	
     
     In general, the JSON contains the Ids of the nodes in question as they are present in the normalized AST or the dataflow graph of flowR.
     Please consult the [Interface](https://github.com/flowr-analysis/flowr/wiki/Interface) wiki page for more information on how to get those.
@@ -114,7 +118,7 @@ It offers a wide variety of features, for example:
             ".meta": {
               "totalDeprecatedCalls": 0,
               "totalDeprecatedFunctionDefinitions": 0,
-              "searchTimeMs": 1,
+              "searchTimeMs": 2,
               "processTimeMs": 0
             }
           },
@@ -128,7 +132,7 @@ It offers a wide variety of features, for example:
                   23
                 ],
                 "filePath": "/root/x.txt",
-                "certainty": "definitely"
+                "certainty": "certain"
               }
             ],
             ".meta": {
@@ -136,7 +140,7 @@ It offers a wide variety of features, for example:
               "totalUnknown": 0,
               "totalWritesBeforeAlways": 0,
               "totalValid": 0,
-              "searchTimeMs": 3,
+              "searchTimeMs": 4,
               "processTimeMs": 1
             }
           },
@@ -147,14 +151,14 @@ It offers a wide variety of features, for example:
               "callsWithFunctionProducers": 0,
               "callsWithAssignmentProducers": 0,
               "callsWithNonConstantProducers": 0,
-              "searchTimeMs": 1,
-              "processTimeMs": 0
+              "searchTimeMs": 0,
+              "processTimeMs": 1
             }
           },
           "absolute-file-paths": {
             "results": [
               {
-                "certainty": "definitely",
+                "certainty": "certain",
                 "filePath": "/root/x.txt",
                 "range": [
                   1,
@@ -167,8 +171,8 @@ It offers a wide variety of features, for example:
             ".meta": {
               "totalConsidered": 1,
               "totalUnknown": 0,
-              "searchTimeMs": 2,
-              "processTimeMs": 0
+              "searchTimeMs": 1,
+              "processTimeMs": 1
             }
           },
           "unused-definitions": {
@@ -195,16 +199,24 @@ It offers a wide variety of features, for example:
               "numAccesses": 0,
               "totalAccessed": 0,
               "searchTimeMs": 0,
-              "processTimeMs": 3
+              "processTimeMs": 2
+            }
+          },
+          "dead-code": {
+            "results": [],
+            ".meta": {
+              "consideredNodes": 5,
+              "searchTimeMs": 0,
+              "processTimeMs": 0
             }
           }
         },
         ".meta": {
-          "timing": 12
+          "timing": 14
         }
       },
       ".meta": {
-        "timing": 13
+        "timing": 14
       }
     }
     ```
@@ -271,7 +283,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.2.16, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.3.0, R v4.5.0 (r-shell engine)
     R> :slicer test/testfiles/example.R --criterion "11@sum"
     ```
     
@@ -318,7 +330,7 @@ It offers a wide variety of features, for example:
         
 
 * 🚀 **fast data- and control-flow graphs**\
-  Within just <i><span title="This measurement is automatically fetched from the latest benchmark!">136.1 ms</span></i> (as of Jul 12, 2025), 
+  Within just <i><span title="This measurement is automatically fetched from the latest benchmark!">136.8 ms</span></i> (as of Jul 21, 2025), 
   _flowR_ can analyze the data- and control-flow of the average real-world R script. See the [benchmarks](https://flowr-analysis.github.io/flowr/wiki/stats/benchmark) for more information,
   and consult the [wiki pages](https://github.com/flowr-analysis/flowr/wiki/Dataflow-Graph) for more details on the dataflow graph.
 
@@ -354,7 +366,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.2.16, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.3.0, R v4.5.0 (r-shell engine)
     R> :dataflow* test/testfiles/example.R
     ```
     

package/abstract-interpretation/data-frame/absint-visitor.d.ts

@@ -47,9 +47,8 @@ export declare class DataFrameShapeInferenceVisitor<OtherInfo = NoInfo, ControlF
         source: NodeId | undefined;
         target: NodeId | undefined;
     }): void;
-    private processOperation;
-    private processDataFrameAssignment;
-    private processDataFrameExpression;
+    private applyDataFrameAssignment;
+    private applyDataFrameExpression;
     /** We only process vertices of leaf nodes and exit vertices (no entry nodes of complex nodes) */
     private shouldSkipVertex;
     /** Get all AST nodes for the predecessor vertices that are leaf nodes and exit vertices */

package/abstract-interpretation/data-frame/absint-visitor.js

@@ -31,7 +31,7 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
     }
     visitNode(nodeId) {
         const vertex = this.getCfgVertex(nodeId);
-        // skip vertices representing mid markers or entries of complex nodes
+        // skip vertices representing entries of complex nodes
         if (vertex === undefined || this.shouldSkipVertex(vertex)) {
             return true;
         }
@@ -40,7 +40,7 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
         this.onVisitNode(nodeId);
         const visitedCount = this.visited.get(vertex.id) ?? 0;
         this.visited.set(vertex.id, visitedCount + 1);
-        // only continue visitor if the node has not been visited before or the data frame value of the node changed
+        // only continue visiting if the node has not been visited before or the data frame value of the node changed
         return visitedCount === 0 || !(0, domain_1.equalDataFrameState)(this.oldDomain, this.newDomain);
     }
     visitDataflowNode(vertex) {
@@ -69,7 +69,7 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
         const sourceNode = this.getNormalizedAst(source);
         if (node !== undefined && (0, assignment_mapper_1.isAssignmentTarget)(targetNode) && sourceNode !== undefined) {
             node.info.dataFrame = (0, assignment_mapper_1.mapDataFrameVariableAssignment)(targetNode, sourceNode, this.config.dfg);
-            this.processOperation(node);
+            this.applyDataFrameAssignment(node);
             this.clearUnassignedInfo(targetNode);
         }
     }
@@ -77,14 +77,14 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
         const node = this.getNormalizedAst(call.id);
         if (node !== undefined) {
             node.info.dataFrame = (0, access_mapper_1.mapDataFrameAccess)(node, this.config.dfg);
-            this.processOperation(node);
+            this.applyDataFrameExpression(node);
         }
     }
     onDefaultFunctionCall({ call }) {
         const node = this.getNormalizedAst(call.id);
         if (node !== undefined) {
             node.info.dataFrame = (0, function_mapper_1.mapDataFrameFunctionCall)(node, this.config.dfg, this.config.flowrConfig);
-            this.processOperation(node);
+            this.applyDataFrameExpression(node);
         }
     }
     onReplacementCall({ call, source, target }) {
@@ -93,19 +93,14 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
         const sourceNode = this.getNormalizedAst(source);
         if (node !== undefined && targetNode !== undefined && sourceNode !== undefined) {
             node.info.dataFrame = (0, replacement_mapper_1.mapDataFrameReplacementFunction)(node, sourceNode, this.config.dfg);
-            this.processOperation(node);
+            this.applyDataFrameExpression(node);
             this.clearUnassignedInfo(targetNode);
         }
     }
-    processOperation(node) {
-        if ((0, absint_info_1.hasDataFrameAssignmentInfo)(node)) {
-            this.processDataFrameAssignment(node);
-        }
-        else if ((0, absint_info_1.hasDataFrameExpressionInfo)(node)) {
-            this.processDataFrameExpression(node);
+    applyDataFrameAssignment(node) {
+        if (!(0, absint_info_1.hasDataFrameAssignmentInfo)(node)) {
+            return;
         }
-    }
-    processDataFrameAssignment(node) {
         const value = (0, shape_inference_1.resolveIdToDataFrameShape)(node.info.dataFrame.expression, this.config.dfg, this.newDomain);
         if (value !== undefined) {
             this.newDomain.set(node.info.dataFrame.identifier, value);
@@ -116,11 +111,14 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
             }
         }
     }
-    processDataFrameExpression(node) {
+    applyDataFrameExpression(node) {
+        if (!(0, absint_info_1.hasDataFrameExpressionInfo)(node)) {
+            return;
+        }
         let value = domain_1.DataFrameTop;
         for (const { operation, operand, type, options, ...args } of node.info.dataFrame.operations) {
             const operandValue = operand !== undefined ? (0, shape_inference_1.resolveIdToDataFrameShape)(operand, this.config.dfg, this.newDomain) : value;
-            value = (0, semantics_1.applySemantics)(operation, operandValue ?? domain_1.DataFrameTop, args, options);
+            value = (0, semantics_1.applyDataFrameSemantics)(operation, operandValue ?? domain_1.DataFrameTop, args, options);
             const constraintType = type ?? (0, semantics_1.getConstraintType)(operation);
             if (operand !== undefined && constraintType === semantics_1.ConstraintType.OperandModification) {
                 this.newDomain.set(operand, value);

package/abstract-interpretation/data-frame/mappers/function-mapper.js

@@ -214,8 +214,8 @@ const DataFrameFunctionParamsMapper = {
         critical: [{ pos: -1, name: 'row.names' }]
     },
     'as.data.frame': {
-        critical: [],
-        dataFrame: { pos: 0, name: 'x' }
+        dataFrame: { pos: 0, name: 'x' },
+        critical: []
     },
     'read.table': {
         fileName: { pos: 0, name: 'file' },
@@ -1097,7 +1097,7 @@ function mapDataFrameUnknown(args, params, info) {
         return;
     }
     return [{
-            operation: 'identity',
+            operation: 'unknown',
             operand: dataFrame.value.info.id,
             ...(params.constraintType !== undefined ? { type: params.constraintType } : {})
         }];

package/abstract-interpretation/data-frame/semantics.d.ts

@@ -123,7 +123,7 @@ export type DataFrameOperationOptions<N extends DataFrameOperationName> = Parame
  * @returns The resulting new data frame shape constraints.
  * The semantic type of the resulting constraints depends on the {@link ConstraintType} of the abstract operation.
  */
-export declare function applySemantics<Name extends DataFrameOperationName>(operation: Name, value: DataFrameDomain, args: DataFrameOperationArgs<Name>, options?: DataFrameOperationOptions<Name>): DataFrameDomain;
+export declare function applyDataFrameSemantics<Name extends DataFrameOperationName>(operation: Name, value: DataFrameDomain, args: DataFrameOperationArgs<Name>, options?: DataFrameOperationOptions<Name>): DataFrameDomain;
 /**
  * Gets the default resulting constraint type for an abstract data frame operation.
  */

package/abstract-interpretation/data-frame/semantics.js

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.DataFrameOperationNames = exports.ConstraintType = void 0;
-exports.applySemantics = applySemantics;
+exports.applyDataFrameSemantics = applyDataFrameSemantics;
 exports.getConstraintType = getConstraintType;
 const assert_1 = require("../../util/assert");
 const domain_1 = require("./domain");
@@ -58,7 +58,7 @@ exports.DataFrameOperationNames = Object.keys(DataFrameSemanticsMapper);
  * @returns The resulting new data frame shape constraints.
  * The semantic type of the resulting constraints depends on the {@link ConstraintType} of the abstract operation.
  */
-function applySemantics(operation, value, args, options) {
+function applyDataFrameSemantics(operation, value, args, options) {
     const applier = DataFrameSemanticsMapper[operation];
     return applier.apply(value, args, options);
 }
@@ -266,14 +266,11 @@ function applyGroupBySemantics(value, { by }, options) {
         return {
             ...value,
             colnames: by.every(assert_1.isNotUndefined) ? (0, domain_1.joinColNames)(value.colnames, by) : domain_1.ColNamesTop,
-            cols: (0, domain_1.addInterval)(value.cols, [0, by.length]),
-            rows: (0, domain_1.extendIntervalToZero)(value.rows)
+            cols: (0, domain_1.addInterval)(value.cols, [0, by.length])
         };
     }
-    return {
-        ...value,
-        rows: (0, domain_1.extendIntervalToZero)(value.rows)
-    };
+    // Group by only marks columns as groups but does not change the shape itself
+    return value;
 }
 function applySummarizeSemantics(value, { colnames }) {
     const cols = colnames?.length;
@@ -281,7 +278,7 @@ function applySummarizeSemantics(value, { colnames }) {
         ...value,
         colnames: colnames?.every(assert_1.isNotUndefined) ? (0, domain_1.joinColNames)(value.colnames, colnames) : domain_1.ColNamesTop,
         cols: cols !== undefined ? (0, domain_1.minInterval)((0, domain_1.addInterval)(value.cols, [0, cols]), [cols, Infinity]) : (0, domain_1.extendIntervalToInfinity)(value.rows),
-        rows: (0, domain_1.maxInterval)((0, domain_1.minInterval)(value.rows, [1, Infinity]), [1, 1])
+        rows: (0, domain_1.maxInterval)((0, domain_1.minInterval)(value.rows, [1, Infinity]), [0, 1])
     };
 }
 function applyJoinSemantics(value, { other, by }, options) {
@@ -304,7 +301,7 @@ function applyJoinSemantics(value, { other, by }, options) {
         }
     };
     const commonCols = (0, domain_1.meetColNames)(value.colnames, other.colnames);
-    let duplicateCols; // whether columns may be renamed due to occurance in both data frames
+    let duplicateCols; // whether columns may be renamed due to occurrence in both data frames
     let productRows; // whether the resulting rows may be a Cartesian product of the rows of the data frames
     if (options?.natural) {
         duplicateCols = false;

package/abstract-interpretation/data-frame/shape-inference.js

@@ -76,10 +76,7 @@ function resolveIdToDataFrameShape(id, dfg, domain) {
         }
     }
     else if (node.type === type_1.RType.IfThenElse) {
-        if (node.otherwise === undefined) {
-            return resolveIdToDataFrameShape(node.then, dfg, domain) !== undefined ? domain_1.DataFrameTop : undefined;
-        }
-        else {
+        if (node.otherwise !== undefined) {
             const values = [node.then, node.otherwise].map(entry => resolveIdToDataFrameShape(entry, dfg, domain));
             if (values.length > 0 && values.every(assert_1.isNotUndefined)) {
                 return (0, domain_1.joinDataFrames)(...values);
@@ -87,10 +84,7 @@ function resolveIdToDataFrameShape(id, dfg, domain) {
         }
     }
     else if (origins.includes('builtin:if-then-else') && call?.args.every(arg => arg !== r_function_call_1.EmptyArgument)) {
-        if (call.args.length === 2) {
-            return resolveIdToDataFrameShape(call.args[1].nodeId, dfg, domain) !== undefined ? domain_1.DataFrameTop : undefined;
-        }
-        else if (call.args.length === 3) {
+        if (call.args.length === 3) {
             const values = call.args.slice(1, 3).map(entry => resolveIdToDataFrameShape(entry.nodeId, dfg, domain));
             if (values.length > 0 && values.every(assert_1.isNotUndefined)) {
                 return (0, domain_1.joinDataFrames)(...values);

package/benchmark/slicer.js

@@ -339,13 +339,15 @@ class BenchmarkSlicer {
             if (expression !== undefined) {
                 nodeStats.mappedOperations = expression.operations.map(op => op.operation);
                 stats.numberOfOperationNodes++;
+                if (value !== undefined) {
+                    nodeStats.inferredColNames = value.colnames === domain_1.ColNamesTop ? 'top' : value.colnames.length;
+                    nodeStats.inferredColCount = this.getInferredSize(value.cols);
+                    nodeStats.inferredRowCount = this.getInferredSize(value.rows);
+                    nodeStats.approxRangeColCount = value.cols === domain_1.IntervalBottom ? 0 : value.cols[1] - value.cols[0];
+                    nodeStats.approxRangeRowCount = value.rows === domain_1.IntervalBottom ? 0 : value.rows[1] - value.rows[0];
+                }
             }
             if (value !== undefined) {
-                nodeStats.inferredColNames = value.colnames === domain_1.ColNamesTop ? 'top' : value.colnames.length;
-                nodeStats.inferredColCount = this.getInferredSize(value.cols);
-                nodeStats.inferredRowCount = this.getInferredSize(value.rows);
-                nodeStats.approxRangeColCount = value.cols === domain_1.IntervalBottom ? 0 : value.cols[1] - value.cols[0];
-                nodeStats.approxRangeRowCount = value.rows === domain_1.IntervalBottom ? 0 : value.rows[1] - value.rows[0];
                 stats.numberOfValueNodes++;
             }
             stats.perNodeStats.set(node.info.id, nodeStats);

package/benchmark/summarizer/second-phase/graph.js

@@ -11,7 +11,7 @@ function writeGraphOutput(ultimate, outputGraphPath) {
     const data = [];
     for (const { name, measurements } of [{ name: 'per-file', measurements: ultimate.commonMeasurements }, { name: 'per-slice', measurements: ultimate.perSliceMeasurements }]) {
         for (const [point, measurement] of measurements) {
-            if (point === 'close R session' || point === 'initialize R session') {
+            if (point === 'close R session' || point === 'initialize R session' || !measurement?.mean || !measurement?.std) {
                 continue;
             }
             const pointName = point === 'total' ? `total ${name}` : point;

package/benchmark/summarizer/second-phase/process.js

@@ -152,7 +152,7 @@ function summarizeAllUltimateStats(stats) {
         failedToRepParse: Math.max(...stats.map(s => s.failedToRepParse)),
         timesHitThreshold: Math.max(...stats.map(s => s.timesHitThreshold)),
         // average out / summarize other measurements
-        commonMeasurements: new Map(stats_1.CommonSlicerMeasurements.map(m => [m, (0, process_1.summarizeSummarizedMeasurement)(stats.map(s => s.commonMeasurements.get(m)))])),
+        commonMeasurements: new Map(stats_1.CommonSlicerMeasurements.filter(m => stats.some(s => s.commonMeasurements.has(m))).map(m => [m, (0, process_1.summarizeSummarizedMeasurement)(stats.map(s => s.commonMeasurements.get(m)))])),
         perSliceMeasurements: new Map(stats_1.PerSliceMeasurements.map(m => [m, (0, process_1.summarizeSummarizedMeasurement)(stats.map(s => s.perSliceMeasurements.get(m)))])),
         sliceTimePerToken: (0, process_1.summarizeSummarizedTimePerToken)(stats.map(s => s.sliceTimePerToken)),
         reconstructTimePerToken: (0, process_1.summarizeSummarizedTimePerToken)(stats.map(s => s.reconstructTimePerToken)),

package/cli/benchmark-app.d.ts

@@ -16,4 +16,5 @@ export interface BenchmarkCliOptions {
     threshold?: number;
     'per-file-time-limit'?: number;
     'sampling-strategy': string;
+    cfg?: boolean;
 }

package/cli/benchmark-app.js

@@ -75,6 +75,7 @@ async function benchmark() {
         ...(options.threshold ? ['--threshold', `${options.threshold}`] : []),
         '--sampling-strategy', options['sampling-strategy'],
         ...(options.seed ? ['--seed', options.seed] : []),
+        ...(options.cfg ? ['--cfg'] : []),
     ]);
     const runs = options.runs ?? 1;
     for (let i = 1; i <= runs; i++) {

package/cli/benchmark-helper-app.d.ts

@@ -11,6 +11,7 @@ export interface SingleBenchmarkCliOptions {
     'dataframe-shape-inference': boolean;
     'enable-pointer-tracking': boolean;
     'max-slices': number;
+    'cfg': boolean;
     threshold?: number;
     'sampling-strategy': string;
     seed?: string;

package/cli/benchmark-helper-app.js

@@ -34,7 +34,7 @@ async function benchmark() {
     const prefix = `[${options.input}${options['file-id'] !== undefined ? ` (file ${options['file-id']}, run ${options['run-num']})` : ''}]`;
     console.log(`${prefix} Appending output to ${options.output}`);
     const directory = path_1.default.parse(options.output).dir;
-    // ensure the directory exists if path contains one
+    // ensure the directory exists if the path contains one
     if (directory !== '') {
         fs_1.default.mkdirSync(directory, { recursive: true });
     }
@@ -69,9 +69,10 @@ async function benchmark() {
             (0, assert_1.guard)(count >= 0, `Number of slices exceeded limit of ${maxSlices} with ${-count} slices, skipping in count`);
             (0, assert_1.guard)(count > 0, `No possible slices found for ${options.input}, skipping in count`);
         }
-        if (options['dataframe-shape-inference']) {
-            console.log(`${prefix} Extracting control flow graph for data frame shape inference`);
+        if (options['cfg'] || options['dataframe-shape-inference']) {
             slicer.extractCFG();
+        }
+        if (options['dataframe-shape-inference']) {
             console.log(`${prefix} Performing shape inference for data frames`);
             slicer.inferDataFrameShapes();
             console.log(`${prefix} Completed data frame shape inference`);

package/cli/common/options.js

@@ -28,6 +28,7 @@ exports.benchmarkOptions = [
     { name: 'threshold', alias: 't', type: Number, description: 'How many re-visits of the same node are ok?', defaultValue: undefined, typeLabel: '{underline number}' },
     { name: 'per-file-time-limit', type: Number, description: 'Time limit in milliseconds to process single file (disabled by default)', defaultValue: undefined, typeLabel: '{underline number}' },
     { name: 'sampling-strategy', type: String, description: 'Which strategy to use, when sampling is enabled', defaultValue: 'random', typeLabel: '{underline random/equidistant}' },
+    { name: 'cfg', alias: 'c', type: Boolean, description: 'Extract the control flow graph of the file (benchmark it too)' }
 ];
 exports.benchmarkHelperOptions = [
     { name: 'verbose', alias: 'v', type: Boolean, description: 'Run with verbose logging [do not use for the real benchmark as this affects the time measurements, but only to find errors]' },
@@ -36,6 +37,7 @@ exports.benchmarkHelperOptions = [
     { name: 'file-id', alias: 'd', type: Number, description: 'A numeric file id that can be used to match an input and run-num to a file' },
     { name: 'run-num', alias: 'r', type: Number, description: 'The n-th time that the file with the given file-id is being benchmarked' },
     { name: 'slice', alias: 's', type: String, description: 'Automatically slice for *all* variables (default) or *no* slicing and only parsing/dataflow construction. Numbers will indicate: sample X random slices from all.', defaultValue: 'all', typeLabel: '{underline all/no}' },
+    { name: 'cfg', alias: 'c', type: Boolean, description: 'Extract the control flow graph of the file (benchmark it too)' },
     { name: 'output', alias: 'o', type: String, description: 'File to write the measurements to (appends a single line in JSON format)', typeLabel: '{underline file}' },
     { name: 'parser', type: String, description: 'The parser to use for the benchmark', defaultValue: 'r-shell', typeLabel: '{underline parser}' },
     { name: 'dataframe-shape-inference', type: Boolean, description: 'Infer the shape of data frames using abstract interpretation (includes control flow graph extraction)', defaultValue: false },

package/cli/repl/commands/repl-query.js

@@ -59,7 +59,7 @@ async function processQueryArgs(line, parser, output, config) {
     }
     const processed = await getDataflow(config, parser, args.join(' '));
     return {
-        query: (0, query_1.executeQueries)({ dataflow: processed.dataflow, ast: processed.normalize, config: config }, parsedQuery),
+        query: await Promise.resolve((0, query_1.executeQueries)({ dataflow: processed.dataflow, ast: processed.normalize, config: config }, parsedQuery)),
         processed
     };
 }

package/cli/repl/server/connection.js

@@ -348,11 +348,20 @@ class FlowRServerConnection {
         const { dataflow: dfg, normalize: ast } = fileInformation.pipeline.getResults(true);
         (0, assert_1.guard)(dfg !== undefined, `Dataflow graph must be present (request: ${request.filetoken})`);
         (0, assert_1.guard)(ast !== undefined, `AST must be present (request: ${request.filetoken})`);
-        const results = (0, query_1.executeQueries)({ dataflow: dfg, ast, config: this.config }, request.query);
-        (0, send_1.sendMessage)(this.socket, {
-            type: 'response-query',
-            id: request.id,
-            results
+        void Promise.resolve((0, query_1.executeQueries)({ dataflow: dfg, ast, config: this.config }, request.query)).then(results => {
+            (0, send_1.sendMessage)(this.socket, {
+                type: 'response-query',
+                id: request.id,
+                results
+            });
+        }).catch(e => {
+            this.logger.error(`[${this.name}] Error while executing query: ${String(e)}`);
+            (0, send_1.sendMessage)(this.socket, {
+                id: request.id,
+                type: 'error',
+                fatal: false,
+                reason: `Error while executing query: ${String(e)}`
+            });
         });
     }
 }

package/control-flow/basic-cfg-guided-visitor.d.ts

@@ -1,4 +1,4 @@
-import type { CfgBasicBlockVertex, CfgEndMarkerVertex, CfgExpressionVertex, CfgMidMarkerVertex, CfgSimpleVertex, CfgStatementVertex, ControlFlowInformation } from './control-flow-graph';
+import type { CfgBasicBlockVertex, CfgEndMarkerVertex, CfgExpressionVertex, CfgSimpleVertex, CfgStatementVertex, ControlFlowInformation } from './control-flow-graph';
 import type { NodeId } from '../r-bridge/lang-4.x/ast/model/processing/node-id';
 export interface BasicCfgGuidedVisitorConfiguration<ControlFlow extends ControlFlowInformation = ControlFlowInformation> {
     readonly controlFlow: ControlFlow;
@@ -34,6 +34,5 @@ export declare class BasicCfgGuidedVisitor<ControlFlow extends ControlFlowInform
     protected onBasicBlockNode(node: CfgBasicBlockVertex): void;
     protected onStatementNode(_node: CfgStatementVertex): void;
     protected onExpressionNode(_node: CfgExpressionVertex): void;
-    protected onMidMarkerNode(_node: CfgMidMarkerVertex): void;
     protected onEndMarkerNode(_node: CfgEndMarkerVertex): void;
 }

package/control-flow/basic-cfg-guided-visitor.js

@@ -72,9 +72,6 @@ class BasicCfgGuidedVisitor {
             case control_flow_graph_1.CfgVertexType.Expression:
                 this.onExpressionNode(vertex);
                 break;
-            case control_flow_graph_1.CfgVertexType.MidMarker:
-                this.onMidMarkerNode(vertex);
-                break;
             case control_flow_graph_1.CfgVertexType.EndMarker:
                 this.onEndMarkerNode(vertex);
                 break;
@@ -103,9 +100,6 @@ class BasicCfgGuidedVisitor {
     onExpressionNode(_node) {
         /* does nothing by default */
     }
-    onMidMarkerNode(_node) {
-        /* does nothing by default */
-    }
     onEndMarkerNode(_node) {
         /* does nothing by default */
     }

package/control-flow/cfg-simplification.d.ts

@@ -1,6 +1,7 @@
 import type { ControlFlowInformation } from './control-flow-graph';
 import type { NormalizedAst } from '../r-bridge/lang-4.x/ast/model/processing/decorate';
 import type { DataflowGraph } from '../dataflow/graph/graph';
+import type { NodeId } from '../r-bridge/lang-4.x/ast/model/processing/node-id';
 import { cfgAnalyzeDeadCode } from './cfg-dead-code';
 import type { FlowrConfigOptions } from '../config';
 export interface CfgPassInfo {
@@ -28,4 +29,9 @@ export declare function simplifyControlFlowInformation(cfg: ControlFlowInformati
 declare function cfgRemoveDeadCode(cfg: ControlFlowInformation, _info?: CfgPassInfo): ControlFlowInformation;
 declare function uniqueControlFlowSets(cfg: ControlFlowInformation, _info?: CfgPassInfo): ControlFlowInformation;
 declare function toBasicBlocks(cfg: ControlFlowInformation, _info?: CfgPassInfo): ControlFlowInformation;
+/**
+ * Uses {@link visitCfgInOrder} to find all nodes that are reachable from the control flow graph's {@link ControlFlowInformation.entryPoints} and returns them as a set.
+ * @param cfg - The control flow graph whose reachable nodes to find.
+ */
+export declare function cfgFindAllReachable(cfg: ControlFlowInformation): Set<NodeId>;
 export {};