@eagleoutice/flowr 2.6.1 → 2.6.2

package/README.md

@@ -16,7 +16,7 @@ It offers a wide variety of features, for example:
    Analyze your R scripts for common issues and potential bugs (see the [wiki page](https://github.com/flowr-analysis/flowr/wiki/Linter) for more information on the currently supported linters).
 
 	    
-    <details><summary style="">Example: Linting code with flowR</summary>
+    <details><summary>Example: Linting code with flowR</summary>
     
     To lint your code, you can use the [REPL](https://github.com/flowr-analysis/flowr/wiki/Interface#using-the-repl) or the [Visual Studio Code extension](https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr) (see [vscode-flowr#283](https://github.com/flowr-analysis/vscode-flowr/pull/283)).
     	
@@ -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 v2.6.0, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.6.1, R v4.5.0 (r-shell engine)
     R> :query @linter "read.csv(\"/root/x.txt\")"
     ```
     
@@ -41,11 +41,11 @@ It offers a wide variety of features, for example:
                ╰ 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":1,"processTimeMs":0}</code>
+           ╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Absolute Paths** (absolute-file-paths):
            ╰ certain:
                ╰ Path `/root/x.txt` at 1.1-23
-           ╰ _Metadata_: <code>{"totalConsidered":1,"totalUnknown":0,"searchTimeMs":0,"processTimeMs":0}</code>
+           ╰ _Metadata_: <code>{"totalConsidered":1,"totalUnknown":0,"searchTimeMs":1,"processTimeMs":0}</code>
        ╰ **Unused Definitions** (unused-definitions):
            ╰ _Metadata_: <code>{"totalConsidered":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Naming Convention** (naming-convention):
@@ -53,7 +53,7 @@ It offers a wide variety of features, for example:
        ╰ **Network Functions** (network-functions):
            ╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Dataframe Access Validation** (dataframe-access-validation):
-           ╰ _Metadata_: <code>{"numOperations":0,"numAccesses":0,"totalAccessed":0,"searchTimeMs":1,"processTimeMs":0}</code>
+           ╰ _Metadata_: <code>{"numOperations":0,"numAccesses":0,"totalAccessed":0,"searchTimeMs":0,"processTimeMs":1}</code>
        ╰ **Dead Code** (dead-code):
            ╰ _Metadata_: <code>{"consideredNodes":5,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Useless Loops** (useless-loop):
@@ -80,36 +80,36 @@ It offers a wide variety of features, for example:
     
     _Results (prettified and summarized):_
     
-    Query: **linter** (213 ms)\
+    Query: **linter** (212 ms)\
     &nbsp;&nbsp;&nbsp;╰ **Deprecated Functions** (deprecated-functions):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":199,"processTimeMs":1}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":198,"processTimeMs":0}</code>\
     &nbsp;&nbsp;&nbsp;╰ **File Path Validity** (file-path-validity):\
     &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":4,"processTimeMs":1}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalReads":1,"totalUnknown":0,"totalWritesBeforeAlways":0,"totalValid":0,"searchTimeMs":5,"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":0,"processTimeMs":1}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"searchTimeMs":0,"processTimeMs":0}</code>\
     &nbsp;&nbsp;&nbsp;╰ **Absolute Paths** (absolute-file-paths):\
     &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":2,"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;╰ **Network Functions** (network-functions):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":1,"processTimeMs":0}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":0,"processTimeMs":1}</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>\
+    &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":1}</code>\
     &nbsp;&nbsp;&nbsp;╰ **Useless Loops** (useless-loop):\
     &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"numOfUselessLoops":0,"searchTimeMs":0,"processTimeMs":0}</code>\
-    _All queries together required ≈213 ms (1ms accuracy, total 214 ms)_
+    _All queries together required ≈213 ms (1ms accuracy, total 213 ms)_
     
     <details> <summary style="color:gray">Show Detailed Results as Json</summary>
     
-    The analysis required _214.2 ms_ (including parsing and normalization and the query) within the generation environment.	
+    The analysis required _213.3 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.
@@ -126,8 +126,8 @@ It offers a wide variety of features, for example:
             ".meta": {
               "totalCalls": 0,
               "totalFunctionDefinitions": 0,
-              "searchTimeMs": 199,
-              "processTimeMs": 1
+              "searchTimeMs": 198,
+              "processTimeMs": 0
             }
           },
           "file-path-validity": {
@@ -148,7 +148,7 @@ It offers a wide variety of features, for example:
               "totalUnknown": 0,
               "totalWritesBeforeAlways": 0,
               "totalValid": 0,
-              "searchTimeMs": 4,
+              "searchTimeMs": 5,
               "processTimeMs": 1
             }
           },
@@ -160,7 +160,7 @@ It offers a wide variety of features, for example:
               "callsWithAssignmentProducers": 0,
               "callsWithNonConstantProducers": 0,
               "searchTimeMs": 0,
-              "processTimeMs": 1
+              "processTimeMs": 0
             }
           },
           "absolute-file-paths": {
@@ -180,7 +180,7 @@ It offers a wide variety of features, for example:
               "totalConsidered": 1,
               "totalUnknown": 0,
               "searchTimeMs": 2,
-              "processTimeMs": 0
+              "processTimeMs": 1
             }
           },
           "unused-definitions": {
@@ -205,8 +205,8 @@ It offers a wide variety of features, for example:
             ".meta": {
               "totalCalls": 0,
               "totalFunctionDefinitions": 0,
-              "searchTimeMs": 1,
-              "processTimeMs": 0
+              "searchTimeMs": 0,
+              "processTimeMs": 1
             }
           },
           "dataframe-access-validation": {
@@ -216,7 +216,7 @@ It offers a wide variety of features, for example:
               "numAccesses": 0,
               "totalAccessed": 0,
               "searchTimeMs": 0,
-              "processTimeMs": 3
+              "processTimeMs": 2
             }
           },
           "dead-code": {
@@ -237,7 +237,7 @@ It offers a wide variety of features, for example:
           }
         },
         ".meta": {
-          "timing": 213
+          "timing": 212
         }
       },
       ".meta": {
@@ -272,7 +272,7 @@ It offers a wide variety of features, for example:
    for the computation of the point of interest.
 
     
-    <details><summary style="">Example: Slicing with flowR</summary>
+    <details><summary>Example: Slicing with flowR</summary>
     
     
     The simplest way to retrieve slices is with flowR's [Visual Studio Code extension](https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr). 
@@ -306,7 +306,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.6.0, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.6.1, R v4.5.0 (r-shell engine)
     R> :slicer test/testfiles/example.R --criterion "11@sum"
     ```
     
@@ -340,7 +340,7 @@ It offers a wide variety of features, for example:
   the data files it reads, the scripts it sources, and the data it outputs.
   
       
-    <details><summary style="">Example: Dependency Analysis with flowR</summary>
+    <details><summary>Example: Dependency Analysis with flowR</summary>
     
     
     The following showcases the dependency view of the [Visual Studio Code extension](https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr):
@@ -353,12 +353,12 @@ 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!">136.9 ms</span></i> (as of Oct 13, 2025), 
+  Within just <i><span title="This measurement is automatically fetched from the latest benchmark!">137.6 ms</span></i> (as of Oct 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.
 
     
-    <details><summary style="">Example: Generating a dataflow graph with flowR</summary>
+    <details><summary>Example: Generating a dataflow graph with flowR</summary>
     
     
     You can investigate flowR's analyses using the [REPL](https://github.com/flowr-analysis/flowr/wiki/Interface#using-the-repl).
@@ -389,7 +389,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.6.0, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.6.1, R v4.5.0 (r-shell engine)
     R> :dataflow* test/testfiles/example.R
     ```
     
@@ -694,7 +694,7 @@ It offers a wide variety of features, for example:
     ```
     
     	
-    (The analysis required _15.0 ms_ (including parse and normalize, using the [r-shell](https://github.com/flowr-analysis/flowr/wiki/Engines) engine) within the generation environment.)
+    (The analysis required _14.2 ms_ (including parse and normalize, using the [r-shell](https://github.com/flowr-analysis/flowr/wiki/Engines) engine) within the generation environment.)
     
     
     
@@ -752,6 +752,107 @@ If you want to use the same commands:
 For more details on how to use _flowR_ please refer to the [wiki pages](https://github.com/flowr-analysis/flowr/wiki),
 as well as the deployed [code documentation](https://flowr-analysis.github.io/flowr/doc/).
 
+## 📃 Publications on flowR
+
+If you are interested in the theoretical background of _flowR_,
+please check out the following publications (if you find that a paper is missing here, please open [a new issue](https://github.com/flowr-analysis/flowr/issues/new/choose)):
+
+* [Statically Analyzing the Dataflow of R Programs (OOPSLA '25)](https://doi.org/10.1145/3763087)  
+  Please cite this paper if you are using flowR in your research.
+  <details><summary>BibTeX</summary>
+  
+   
+   ```bibtex
+   @article{10.1145/3763087,
+   	author = {Sihler, Florian and Tichy, Matthias},
+   	title = {Statically Analyzing the Dataflow of R Programs},
+   	year = {2025},
+   	issue_date = {October 2025},
+   	publisher = {Association for Computing Machinery},
+   	address = {New York, NY, USA},
+   	volume = {9},
+   	number = {OOPSLA2},
+   	url = {https://doi.org/10.1145/3763087},
+   	doi = {10.1145/3763087},
+   	abstract = {The R programming language is primarily designed for statistical computing and mostly used by researchers without a background in computer science. R provides a wide range of dynamic features and peculiarities that are difficult to analyze statically like dynamic scoping and lazy evaluation with dynamic side effects. At the same time, the R ecosystem lacks sophisticated analysis tools that support researchers in understanding and improving their code.   In this paper, we present a novel static dataflow analysis framework for the R programming language that is capable of handling the dynamic nature of R programs and produces the dataflow graph of given R programs. This graph can be essential in a range of analyses, including program slicing, which we implement as a proof of concept. The core analysis works as a stateful fold over a normalized version of the abstract syntax tree of the R program, which tracks (re-)definitions, values, function calls, side effects, external files, and a dynamic control flow to produce one dataflow graph per program.   We evaluate the correctness of our analysis using output equivalence testing on a manually curated dataset of 779 sensible slicing points from executable real-world R scripts. Additionally, we use a set of systematic test cases based on the capabilities of the R language and the implementation of the R interpreter and measure the runtimes well as the memory consumption on a set of 4,230 real-world R scripts and 20,815 packages available on R’s package manager CRAN.   Furthermore, we evaluate the recall of our program slicer, its accuracy using shrinking, and its improvement over the state of the art. We correctly analyze almost all programs in our equivalence test suite, preserving the identical output for 99.7\% of the manually curated slicing points. On average, we require 576ms to analyze the dataflow and around 213kB to store the graph of a research script.   This shows that our analysis is capable of analyzing real-world sources quickly and correctly. Our slicer achieves an average reduction of 84.8\% of tokens indicating its potential to improve program comprehension.},
+   	journal = {Proc. ACM Program. Lang.},
+   	month = oct,
+   	articleno = {309},
+   	numpages = {29},
+   	keywords = {Dataflow Analysis, R Programming Language, Static Analysis}
+   }
+   ```
+   
+  
+  </details>
+
+* [flowR: A Static Program Slicer for R (ASE '24, Tool)](https://doi.org/10.1145/3691620.3695359)  
+  This refers to the tool-demonstration of the <a href="https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr">VS Code Extension</a>.
+  <details><summary>BibTeX</summary>
+  
+   
+   ```bibtex
+   @inproceedings{DBLP:conf/kbse/SihlerT24,
+     author       = {Florian Sihler and
+                     Matthias Tichy},
+     editor       = {Vladimir Filkov and
+                     Baishakhi Ray and
+                     Minghui Zhou},
+     title        = {flowR: {A} Static Program Slicer for {R}},
+     booktitle    = {Proceedings of the 39th {IEEE/ACM} International Conference on Automated
+                     Software Engineering, {ASE} 2024, Sacramento, CA, USA, October 27
+                     - November 1, 2024},
+     pages        = {2390--2393},
+     publisher    = {{ACM}},
+     year         = {2024},
+     url          = {https://doi.org/10.1145/3691620.3695359},
+     doi          = {10.1145/3691620.3695359},
+     timestamp    = {Mon, 03 Mar 2025 21:16:51 +0100},
+     biburl       = {https://dblp.org/rec/conf/kbse/SihlerT24.bib},
+     bibsource    = {dblp computer science bibliography, https://dblp.org}
+   }
+   ```
+   
+  
+  </details>
+
+* [On the Anatomy of Real-World R Code for Static Analysis (MSR '24)](https://doi.org/10.1145/3643991.3644911)  
+  This paper lays the foundation for flowR by analyzing the characteristics of real-world R code.
+  <details><summary>BibTeX</summary>
+  
+   
+   ```bibtex
+   @inproceedings{DBLP:conf/msr/SihlerPSTDD24,
+     author       = {Florian Sihler and
+                     Lukas Pietzschmann and
+                     Raphael Straub and
+                     Matthias Tichy and
+                     Andor Diera and
+                     Abdelhalim Hafedh Dahou},
+     editor       = {Diomidis Spinellis and
+                     Alberto Bacchelli and
+                     Eleni Constantinou},
+     title        = {On the Anatomy of Real-World {R} Code for Static Analysis},
+     booktitle    = {21st {IEEE/ACM} International Conference on Mining Software Repositories,
+                     {MSR} 2024, Lisbon, Portugal, April 15-16, 2024},
+     pages        = {619--630},
+     publisher    = {{ACM}},
+     year         = {2024},
+     url          = {https://doi.org/10.1145/3643991.3644911},
+     doi          = {10.1145/3643991.3644911},
+     timestamp    = {Sun, 19 Jan 2025 13:31:27 +0100},
+     biburl       = {https://dblp.org/rec/conf/msr/SihlerPSTDD24.bib},
+     bibsource    = {dblp computer science bibliography, https://dblp.org}
+   }
+   ```
+   
+  
+  </details>
+
+ Works using flowR include:
+[Computational Reproducibility of R Code Supplements on OSF](https://doi.org/10.36190/2025.49) and [Multi-View Structural Graph Summaries](https://doi.org/10.1109/WI-IAT62293.2024.00037).
+
+
 ## 🚀 Contributing
 
 We welcome every contribution! Please check out the [developer onboarding](https://github.com/flowr-analysis/flowr/wiki/Onboarding) section in the wiki for all the information you will need.

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

@@ -1,7 +1,7 @@
 import type { RNode } from '../../r-bridge/lang-4.x/ast/model/model';
 import type { ParentInformation } from '../../r-bridge/lang-4.x/ast/model/processing/decorate';
 import type { NodeId } from '../../r-bridge/lang-4.x/ast/model/processing/node-id';
-import type { DataFrameStateDomain } from './domain';
+import type { DataFrameStateDomain } from './dataframe-domain';
 import type { ConstraintType, DataFrameOperationArgs, DataFrameOperationName, DataFrameOperationOptions } from './semantics';
 /**
  * An abstract data frame operation without additional options.

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

@@ -1,6 +1,5 @@
-import type { CfgBasicBlockVertex, CfgSimpleVertex, ControlFlowInformation } from '../../control-flow/control-flow-graph';
-import type { SemanticCfgGuidedVisitorConfiguration } from '../../control-flow/semantic-cfg-guided-visitor';
-import { SemanticCfgGuidedVisitor } from '../../control-flow/semantic-cfg-guided-visitor';
+import { type CfgBasicBlockVertex, type CfgSimpleVertex, type ControlFlowInformation } from '../../control-flow/control-flow-graph';
+import { type SemanticCfgGuidedVisitorConfiguration, SemanticCfgGuidedVisitor } from '../../control-flow/semantic-cfg-guided-visitor';
 import type { DataflowGraph } from '../../dataflow/graph/graph';
 import type { DataflowGraphVertexFunctionCall, DataflowGraphVertexVariableDefinition } from '../../dataflow/graph/vertex';
 import type { NoInfo } from '../../r-bridge/lang-4.x/ast/model/model';

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

@@ -5,7 +5,7 @@ const control_flow_graph_1 = require("../../control-flow/control-flow-graph");
 const semantic_cfg_guided_visitor_1 = require("../../control-flow/semantic-cfg-guided-visitor");
 const assert_1 = require("../../util/assert");
 const absint_info_1 = require("./absint-info");
-const domain_1 = require("./domain");
+const dataframe_domain_1 = require("./dataframe-domain");
 const access_mapper_1 = require("./mappers/access-mapper");
 const assignment_mapper_1 = require("./mappers/assignment-mapper");
 const function_mapper_1 = require("./mappers/function-mapper");
@@ -20,12 +20,12 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
      * The old domain of an AST node before processing the node retrieved from the attached {@link AbstractInterpretationInfo}.
      * This is used to check whether the state has changed and successors should be visited again, and is also required for widening.
      */
-    oldDomain = new Map();
+    oldDomain = dataframe_domain_1.DataFrameStateDomain.bottom();
     /**
      * The new domain of an AST node during and after processing the node.
      * This information is stored in the {@link AbstractInterpretationInfo} afterward.
      */
-    newDomain = new Map();
+    newDomain = dataframe_domain_1.DataFrameStateDomain.bottom();
     constructor(config) {
         super({ ...config, defaultVisitingOrder: 'forward', defaultVisitingType: 'exit' });
     }
@@ -36,22 +36,26 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
             return true;
         }
         const predecessors = this.getPredecessorNodes(vertex.id);
-        this.newDomain = (0, domain_1.joinDataFrameStates)(...predecessors.map(node => node.info.dataFrame?.domain ?? new Map()));
+        const predecessorDomains = predecessors.map(node => node.info.dataFrame?.domain).filter(assert_1.isNotUndefined);
+        this.newDomain = dataframe_domain_1.DataFrameStateDomain.bottom().joinAll(predecessorDomains);
         this.onVisitNode(nodeId);
         const visitedCount = this.visited.get(vertex.id) ?? 0;
         this.visited.set(vertex.id, visitedCount + 1);
         // 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);
+        return visitedCount === 0 || !this.oldDomain.equals(this.newDomain);
     }
     visitDataflowNode(vertex) {
         const node = this.getNormalizedAst((0, control_flow_graph_1.getVertexRootId)(vertex));
         if (node === undefined) {
             return;
         }
-        this.oldDomain = node.info.dataFrame?.domain ?? new Map();
+        this.oldDomain = node.info.dataFrame?.domain ?? dataframe_domain_1.DataFrameStateDomain.bottom();
         super.visitDataflowNode(vertex);
+        if (this.config.dfg.unknownSideEffects.has((0, control_flow_graph_1.getVertexRootId)(vertex))) {
+            this.newDomain = this.newDomain.bottom();
+        }
         if (this.shouldWiden(vertex)) {
-            this.newDomain = (0, domain_1.wideningDataFrameStates)(this.oldDomain, this.newDomain);
+            this.newDomain = this.oldDomain.widen(this.newDomain);
         }
         node.info.dataFrame ??= {};
         node.info.dataFrame.domain = this.newDomain;
@@ -107,7 +111,7 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
             const identifier = this.getNormalizedAst(node.info.dataFrame.identifier);
             if (identifier !== undefined) {
                 identifier.info.dataFrame ??= {};
-                identifier.info.dataFrame.domain = new Map(this.newDomain);
+                identifier.info.dataFrame.domain = this.newDomain.create(this.newDomain.value);
             }
         }
     }
@@ -115,10 +119,11 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
         if (!(0, absint_info_1.hasDataFrameExpressionInfo)(node)) {
             return;
         }
-        let value = domain_1.DataFrameTop;
+        const maxColNames = this.config.flowrConfig.abstractInterpretation.dataFrame.maxColNames;
+        let value = dataframe_domain_1.DataFrameDomain.top(maxColNames);
         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.applyDataFrameSemantics)(operation, operandValue ?? domain_1.DataFrameTop, args, options);
+            value = (0, semantics_1.applyDataFrameSemantics)(operation, operandValue ?? dataframe_domain_1.DataFrameDomain.top(maxColNames), 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/dataframe-domain.d.ts

@@ -1,40 +1,46 @@
-import type { AbstractDomain } from '../domains/abstract-domain';
+import type { NodeId } from '../../r-bridge/lang-4.x/ast/model/processing/node-id';
+import type { AbstractDomainValue } from '../domains/abstract-domain';
 import { PosIntervalDomain } from '../domains/positive-interval-domain';
 import { ProductDomain } from '../domains/product-domain';
-import { SetBoundedSetDomain } from '../domains/set-bounded-set-domain';
+import { SetUpperBoundDomain } from '../domains/set-upper-bound-domain';
 import { StateAbstractDomain } from '../domains/state-abstract-domain';
 /** The type of the abstract product representing the shape of data frames */
 export type AbstractDataFrameShape = {
-    colnames: SetBoundedSetDomain<string>;
+    colnames: SetUpperBoundDomain<string>;
     cols: PosIntervalDomain;
     rows: PosIntervalDomain;
 };
-/** The type of abstract values of a sub abstract domain (shape property) of the data frame shape product */
-type DataFrameShapeProperty<Property extends keyof AbstractDataFrameShape> = AbstractDataFrameShape[Property] extends AbstractDomain<unknown, unknown, unknown, unknown, infer Lift> ? Lift : never;
+/** The type of abstract values of a sub abstract domain (shape property) of the data frame shape product domain */
+export type DataFrameShapeProperty<Property extends keyof AbstractDataFrameShape> = AbstractDomainValue<AbstractDataFrameShape[Property]>;
 /**
  * The data frame abstract domain as product domain of a column names domain, column count domain, and row count domain.
  */
 export declare class DataFrameDomain extends ProductDomain<AbstractDataFrameShape> {
     constructor(value: AbstractDataFrameShape, maxColNames?: number);
-    create(value: AbstractDataFrameShape, maxColNames?: number): DataFrameDomain;
+    create(value: AbstractDataFrameShape): this;
     /**
      * The current abstract value of the column names domain.
      */
-    get colnames(): DataFrameShapeProperty<'colnames'>;
+    get colnames(): AbstractDataFrameShape['colnames'];
     /**
      * The current abstract value of the column count domain.
      */
-    get cols(): DataFrameShapeProperty<'cols'>;
+    get cols(): AbstractDataFrameShape['cols'];
     /**
      * The current abstract value of the row count domain.
      */
-    get rows(): DataFrameShapeProperty<'rows'>;
+    get rows(): AbstractDataFrameShape['rows'];
+    /**
+     * The maximum number of inferred column names of the column names domain.
+     */
+    get maxColNames(): number;
     static bottom(maxColNames?: number): DataFrameDomain;
     static top(maxColNames?: number): DataFrameDomain;
 }
 /**
- * The data frame state abstract domain as state abstract domain mapping AST node IDs to inferred abstract data frame shapes.
+ * The data frame state abstract domain as state domain mapping AST node IDs to inferred abstract data frame shapes.
  */
-export declare class DateFrameStateDomain extends StateAbstractDomain<DataFrameDomain> {
+export declare class DataFrameStateDomain extends StateAbstractDomain<DataFrameDomain> {
+    create(value: ReadonlyMap<NodeId, DataFrameDomain>): this;
+    static bottom(): DataFrameStateDomain;
 }
-export {};

package/abstract-interpretation/data-frame/dataframe-domain.js

@@ -1,9 +1,9 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.DateFrameStateDomain = exports.DataFrameDomain = void 0;
+exports.DataFrameStateDomain = exports.DataFrameDomain = void 0;
 const positive_interval_domain_1 = require("../domains/positive-interval-domain");
 const product_domain_1 = require("../domains/product-domain");
-const set_bounded_set_domain_1 = require("../domains/set-bounded-set-domain");
+const set_upper_bound_domain_1 = require("../domains/set-upper-bound-domain");
 const state_abstract_domain_1 = require("../domains/state-abstract-domain");
 /**
  * The data frame abstract domain as product domain of a column names domain, column count domain, and row count domain.
@@ -11,42 +11,48 @@ const state_abstract_domain_1 = require("../domains/state-abstract-domain");
 class DataFrameDomain extends product_domain_1.ProductDomain {
     constructor(value, maxColNames) {
         super({
-            colnames: new set_bounded_set_domain_1.SetBoundedSetDomain(value.colnames.value, maxColNames),
+            colnames: new set_upper_bound_domain_1.SetUpperBoundDomain(value.colnames.value, maxColNames ?? value.colnames.limit),
             cols: new positive_interval_domain_1.PosIntervalDomain(value.cols.value),
             rows: new positive_interval_domain_1.PosIntervalDomain(value.rows.value)
         });
     }
-    create(value, maxColNames) {
-        return new DataFrameDomain(value, maxColNames);
+    create(value) {
+        return new DataFrameDomain(value, this.maxColNames);
     }
     /**
      * The current abstract value of the column names domain.
      */
     get colnames() {
-        return this.value.colnames.value;
+        return this.value.colnames;
     }
     /**
      * The current abstract value of the column count domain.
      */
     get cols() {
-        return this.value.cols.value;
+        return this.value.cols;
     }
     /**
      * The current abstract value of the row count domain.
      */
     get rows() {
-        return this.value.rows.value;
+        return this.value.rows;
+    }
+    /**
+     * The maximum number of inferred column names of the column names domain.
+     */
+    get maxColNames() {
+        return this.value.colnames.limit;
     }
     static bottom(maxColNames) {
         return new DataFrameDomain({
-            colnames: set_bounded_set_domain_1.SetBoundedSetDomain.bottom(maxColNames),
+            colnames: set_upper_bound_domain_1.SetUpperBoundDomain.bottom(maxColNames),
             cols: positive_interval_domain_1.PosIntervalDomain.bottom(),
             rows: positive_interval_domain_1.PosIntervalDomain.bottom()
         });
     }
     static top(maxColNames) {
         return new DataFrameDomain({
-            colnames: set_bounded_set_domain_1.SetBoundedSetDomain.top(maxColNames),
+            colnames: set_upper_bound_domain_1.SetUpperBoundDomain.top(maxColNames),
             cols: positive_interval_domain_1.PosIntervalDomain.top(),
             rows: positive_interval_domain_1.PosIntervalDomain.top()
         });
@@ -54,9 +60,15 @@ class DataFrameDomain extends product_domain_1.ProductDomain {
 }
 exports.DataFrameDomain = DataFrameDomain;
 /**
- * The data frame state abstract domain as state abstract domain mapping AST node IDs to inferred abstract data frame shapes.
+ * The data frame state abstract domain as state domain mapping AST node IDs to inferred abstract data frame shapes.
  */
-class DateFrameStateDomain extends state_abstract_domain_1.StateAbstractDomain {
+class DataFrameStateDomain extends state_abstract_domain_1.StateAbstractDomain {
+    create(value) {
+        return new DataFrameStateDomain(value);
+    }
+    static bottom() {
+        return new DataFrameStateDomain(new Map());
+    }
 }
-exports.DateFrameStateDomain = DateFrameStateDomain;
+exports.DataFrameStateDomain = DataFrameStateDomain;
 //# sourceMappingURL=dataframe-domain.js.map

package/abstract-interpretation/data-frame/mappers/access-mapper.d.ts

@@ -5,7 +5,6 @@ import type { ParentInformation } from '../../../r-bridge/lang-4.x/ast/model/pro
 import type { DataFrameExpressionInfo } from '../absint-info';
 /**
  * Maps a concrete data frame access to abstract data frame operations.
- *
  * @param node - The R node of the access
  * @param dfg  - The data flow graph for resolving the arguments
  * @returns Data frame expression info containing the mapped abstract data frame operations, or `undefined` if the node does not represent a data frame access

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

@@ -16,7 +16,6 @@ const SpecialAccessArgumentsMapper = {
 };
 /**
  * Maps a concrete data frame access to abstract data frame operations.
- *
  * @param node - The R node of the access
  * @param dfg  - The data flow graph for resolving the arguments
  * @returns Data frame expression info containing the mapped abstract data frame operations, or `undefined` if the node does not represent a data frame access