@eagleoutice/flowr 2.2.11 → 2.2.13

package/README.md

@@ -4,9 +4,12 @@
 [![Docker Image Version (latest semver)](https://img.shields.io/docker/v/eagleoutice/flowr?logo=docker&logoColor=white&label=dockerhub)](https://hub.docker.com/r/eagleoutice/flowr)
 [![latest tag](https://badgen.net/github/tag/flowr-analysis/flowr?label=latest&color=purple)](https://github.com/flowr-analysis/flowr/releases/latest)
 [![Marketplace](https://badgen.net/vs-marketplace/v/code-inspect.vscode-flowr)](https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr)
+[![Marketplace](https://badgen.net/open-vsx/version/code-inspect/vscode-flowr?label=Positron/Open%20VSX)](https://open-vsx.org/extension/code-inspect/vscode-flowr)
 [![DOI](https://zenodo.org/badge/624819038.svg)](https://zenodo.org/doi/10.5281/zenodo.13319290)
 
-_flowR_ is a sophisticated, static [dataflow analyzer](https://en.wikipedia.org/wiki/Data-flow_analysis) for the [R programming language](https://www.r-project.org/).
+_flowR_ is a sophisticated, static [dataflow analyzer](https://en.wikipedia.org/wiki/Data-flow_analysis) for the [R programming language](https://www.r-project.org/),
+available for [VSCode](https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr), [Positron](https://open-vsx.org/extension/code-inspect/vscode-flowr), [RStudio](https://github.com/flowr-analysis/rstudio-addin-flowr),
+and [Docker](https://hub.docker.com/r/eagleoutice/flowr).
 It offers a wide variety of features, for example:
 
 * 🍕 **program slicing**\
@@ -48,7 +51,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.2.10, R v4.4.0 (r-shell engine)
+    flowR repl using flowR v2.2.12, R v4.4.3 (r-shell engine)
     R> :slicer test/testfiles/example.R --criterion "11@sum"
     ```
     
@@ -95,7 +98,7 @@ 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!">119.1 ms</span></i> (as of Feb 23, 2025), 
+  Within just <i><span title="This measurement is automatically fetched from the latest benchmark!">124.8 ms</span></i> (as of Mar 17, 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.
 
@@ -104,7 +107,7 @@ It offers a wide variety of features, for example:
     
     
     You can investigate flowR's analyses using the [REPL](https://github.com/flowr-analysis/flowr/wiki/Interface#using-the-repl).
-    Commands like <span title="Description (Repl Command, starred version): Returns the URL to mermaid.live; Base Command: Get mermaid code for the dataflow graph of R code, start with 'file://' to indicate a file (aliases: :d*, :df*)">`:dataflow*`</span> allow you to view a dataflow graph for a given R script.
+    Commands like <span title="Description (Repl Command, starred version): Returns the URL to mermaid.live; Base Command: Get mermaid code for the dataflow graph, start with 'file://' to indicate a file (aliases: :d*, :df*)">`:dataflow*`</span> allow you to view a dataflow graph for a given R script.
     
     Let's have a look at the following example:
     
@@ -131,7 +134,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.2.10, R v4.4.0 (r-shell engine)
+    flowR repl using flowR v2.2.12, R v4.4.3 (r-shell engine)
     R> :dataflow* test/testfiles/example.R
     ```
     
@@ -140,7 +143,7 @@ It offers a wide variety of features, for example:
     
     
     ```text
-    https://mermaid.live/view#base64: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
+    https://mermaid.live/view#base64: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
     ```
     
     
@@ -162,6 +165,9 @@ It offers a wide variety of features, for example:
           (2)
           *1.1-8*
         (0, 1)`"]]
+        built-in:_-["`Built-In:
+    #60;#45;`"]
+        style built-in:_- stroke:gray,fill:lightgray,stroke-width:2px,opacity:.8;
         4{{"`#91;RNumber#93; 1
           (4)
           *2.12*`"}}
@@ -208,14 +214,23 @@ It offers a wide variety of features, for example:
           (18)
           *6.14-16*
         (16, 17)`"]]
+        built-in:-["`Built-In:
+    #45;`"]
+        style built-in:- stroke:gray,fill:lightgray,stroke-width:2px,opacity:.8;
         19[["`#91;RExpressionList#93; (
           (19)
           *6.13*
         (18)`"]]
+        built-in:_["`Built-In:
+    (`"]
+        style built-in:_ stroke:gray,fill:lightgray,stroke-width:2px,opacity:.8;
         20[["`#91;RBinaryOp#93; #58;
           (20)
           *6.11-17*
         (13, 19)`"]]
+        built-in::["`Built-In:
+    #58;`"]
+        style built-in:: stroke:gray,fill:lightgray,stroke-width:2px,opacity:.8;
         24(["`#91;RSymbol#93; sum
           (24, :may:36+)
           *7.10-12*`"])
@@ -265,12 +280,18 @@ It offers a wide variety of features, for example:
           (36)
           *6.1-9.1*
         (12, 20, 35)`"]]
+        built-in:for["`Built-In:
+    for`"]
+        style built-in:for stroke:gray,fill:lightgray,stroke-width:2px,opacity:.8;
         38{{"`#91;RString#93; #34;Sum#58;#34;
           (38)
           *11.5-10*`"}}
         40(["`#91;RSymbol#93; sum
           (40)
           *11.13-15*`"])
+        built-in:sum["`Built-In:
+    sum`"]
+        style built-in:sum stroke:gray,fill:lightgray,stroke-width:2px,opacity:.8;
         42{{"`#91;RString#93; #34;
     #34;
           (42)
@@ -279,6 +300,9 @@ It offers a wide variety of features, for example:
           (44)
           *11.1-22*
         (38, 40, 42)`"]]
+        built-in:cat["`Built-In:
+    cat`"]
+        style built-in:cat stroke:gray,fill:lightgray,stroke-width:2px,opacity:.8;
         46{{"`#91;RString#93; #34;Product#58;#34;
           (46)
           *12.5-14*`"}}
@@ -297,87 +321,121 @@ It offers a wide variety of features, for example:
         0 -->|"defined-by"| 2
         2 -->|"argument"| 1
         2 -->|"returns, argument"| 0
+        2 -.->|"reads, calls"| built-in:_-
+        linkStyle 4 stroke:gray;
         3 -->|"defined-by"| 4
         3 -->|"defined-by"| 5
         5 -->|"argument"| 4
         5 -->|"returns, argument"| 3
+        5 -.->|"reads, calls"| built-in:_-
+        linkStyle 9 stroke:gray;
         6 -->|"defined-by"| 7
         6 -->|"defined-by"| 8
         8 -->|"argument"| 7
         8 -->|"returns, argument"| 6
+        8 -.->|"reads, calls"| built-in:_-
+        linkStyle 14 stroke:gray;
         9 -->|"defined-by"| 10
         9 -->|"defined-by"| 11
         11 -->|"argument"| 10
         11 -->|"returns, argument"| 9
+        11 -.->|"reads, calls"| built-in:_-
+        linkStyle 19 stroke:gray;
         12 -->|"defined-by"| 20
         16 -->|"reads"| 9
         18 -->|"reads, argument"| 16
         18 -->|"reads, argument"| 17
+        18 -.->|"reads, calls"| built-in:-
+        linkStyle 24 stroke:gray;
         19 -->|"returns, argument"| 18
+        19 -.->|"reads"| built-in:_
+        linkStyle 26 stroke:gray;
         20 -->|"reads, argument"| 13
         20 -->|"reads, argument"| 19
+        20 -.->|"reads, calls"| built-in::
+        linkStyle 29 stroke:gray;
         24 -->|"reads"| 0
         24 -->|"reads"| 23
         24 -->|"CD-True"| 36
-        linkStyle 25 stroke:gray,color:gray;
+        linkStyle 32 stroke:gray,color:gray;
         25 -->|"reads"| 12
         25 -->|"CD-True"| 36
-        linkStyle 27 stroke:gray,color:gray;
+        linkStyle 34 stroke:gray,color:gray;
         26 -->|"reads, argument"| 24
         26 -->|"reads, argument"| 25
+        26 -.->|"reads, calls"| built-in:_
+        linkStyle 37 stroke:gray;
         26 -->|"CD-True"| 36
-        linkStyle 30 stroke:gray,color:gray;
+        linkStyle 38 stroke:gray,color:gray;
         27 -->|"reads"| 6
         27 -->|"CD-True"| 36
-        linkStyle 32 stroke:gray,color:gray;
+        linkStyle 40 stroke:gray,color:gray;
         28 -->|"reads, argument"| 26
         28 -->|"reads, argument"| 27
+        28 -.->|"reads, calls"| built-in:_
+        linkStyle 43 stroke:gray;
         28 -->|"CD-True"| 36
-        linkStyle 35 stroke:gray,color:gray;
+        linkStyle 44 stroke:gray,color:gray;
         23 -->|"defined-by"| 28
         23 -->|"defined-by"| 29
         29 -->|"argument"| 28
         29 -->|"returns, argument"| 23
+        29 -.->|"reads, calls"| built-in:_-
+        linkStyle 49 stroke:gray;
         29 -->|"CD-True"| 36
-        linkStyle 40 stroke:gray,color:gray;
+        linkStyle 50 stroke:gray,color:gray;
         31 -->|"reads"| 3
         31 -->|"reads"| 30
         31 -->|"CD-True"| 36
-        linkStyle 43 stroke:gray,color:gray;
+        linkStyle 53 stroke:gray,color:gray;
         32 -->|"reads"| 12
         32 -->|"CD-True"| 36
-        linkStyle 45 stroke:gray,color:gray;
+        linkStyle 55 stroke:gray,color:gray;
         33 -->|"reads, argument"| 31
         33 -->|"reads, argument"| 32
+        33 -.->|"reads, calls"| built-in:_
+        linkStyle 58 stroke:gray;
         33 -->|"CD-True"| 36
-        linkStyle 48 stroke:gray,color:gray;
+        linkStyle 59 stroke:gray,color:gray;
         30 -->|"defined-by"| 33
         30 -->|"defined-by"| 34
         34 -->|"argument"| 33
         34 -->|"returns, argument"| 30
+        34 -.->|"reads, calls"| built-in:_-
+        linkStyle 64 stroke:gray;
         34 -->|"CD-True"| 36
-        linkStyle 53 stroke:gray,color:gray;
+        linkStyle 65 stroke:gray,color:gray;
         35 -->|"argument"| 29
         35 -->|"returns, argument"| 34
+        35 -.->|"reads, calls"| built-in:_
+        linkStyle 68 stroke:gray;
         35 -->|"CD-True"| 36
-        linkStyle 56 stroke:gray,color:gray;
+        linkStyle 69 stroke:gray,color:gray;
         36 -->|"reads, argument"| 12
         36 -->|"reads, argument"| 20
         36 -->|"argument, non-standard-evaluation"| 35
+        36 -.->|"reads, calls"| built-in:for
+        linkStyle 73 stroke:gray;
         40 -->|"reads"| 0
         40 -->|"reads"| 23
+        40 -.->|"reads"| built-in:sum
+        linkStyle 76 stroke:gray;
         44 -->|"argument"| 38
         44 -->|"reads, argument"| 40
         44 -->|"argument"| 42
+        44 -.->|"reads, calls"| built-in:cat
+        linkStyle 80 stroke:gray;
         48 -->|"reads"| 3
         48 -->|"reads"| 30
         52 -->|"argument"| 46
         52 -->|"reads, argument"| 48
         52 -->|"argument"| 50
+        52 -.->|"reads, calls"| built-in:cat
+        linkStyle 86 stroke:gray;
     ```
     
     	
-    (The analysis required _21.37 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 _22.6 ms_ (including parse and normalize, using the [r-shell](https://github.com/flowr-analysis/flowr/wiki/Engines) engine) within the generation environment.)
     
     
     
@@ -392,12 +450,16 @@ It offers a wide variety of features, for example:
 
 If you want to use flowR and the features it provides, feel free to check out the:
 
-- [Visual Studio Code extension](https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr): provides access to flowR directly in VS Code (or [vscode.dev](https://vscode.dev/))
+- [Visual Studio Code](https://marketplace.visualstudio.com/items?itemName=code-inspect.vscode-flowr)/[Positron](https://open-vsx.org/extension/code-inspect/vscode-flowr): provides access to flowR directly in VS Code and Positron (or [vscode.dev](https://vscode.dev/))
 - [RStudio Addin](https://github.com/flowr-analysis/rstudio-addin-flowr): integrates flowR into [RStudio](https://posit.co/downloads/)
 - [R package](https://github.com/flowr-analysis/flowr-r-adapter): use flowR in your R scripts
 - [Docker image](https://hub.docker.com/r/eagleoutice/flowr): run flowR in a container, this also includes [flowR's server](https://github.com/flowr-analysis/flowr/wiki/Interface#communicating-with-the-server)
 - [NPM package](https://www.npmjs.com/package/@eagleoutice/flowr): include flowR in your TypeScript and JavaScript projects
  
+
+If you are already using flowR and want to give feedback, please consider filling out our [feedback form](https://docs.google.com/forms/d/e/1FAIpQLScKFhgnh9LGVU7QzqLvFwZe1oiv_5jNhkIO-G-zND0ppqsMxQ/viewform).
+
+ 
 ## ⭐ Getting Started
 
 To get started with _flowR_ and its features, please check out the [Overview](https://github.com/flowr-analysis/flowr/wiki/Overview) wiki page. 
@@ -427,7 +489,7 @@ as well as the deployed [code documentation](https://flowr-analysis.github.io/fl
 
 ## 🚀 Contributing
 
-We welcome every contribution! Please check out the [contributing guidelines](https://github.com/flowr-analysis/flowr/tree/main/.github/CONTRIBUTING.md) for more information.
+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.
 
 ### Contributors
 

package/benchmark/slicer.d.ts

@@ -43,6 +43,13 @@ export interface BenchmarkSingleSliceStats extends MergeableRecord {
     /** the final code, as the result of the 'reconstruct' step */
     code: ReconstructionResult;
 }
+/**
+ * The type of sampling strategy to use when slicing all possible variables.
+ *
+ * - `'random'`: Randomly select the given number of slicing criteria.
+ * - `'equidistant'`: Select the given number of slicing criteria in an equidistant manner.
+ */
+export type SamplingStrategy = 'random' | 'equidistant';
 export declare class BenchmarkSlicer {
     /** Measures all data recorded *once* per slicer (complete setup up to the dataflow graph creation) */
     private readonly commonMeasurements;
@@ -62,38 +69,58 @@ export declare class BenchmarkSlicer {
      * Initialize the slicer on the given request.
      * Can only be called once for each instance.
      */
-    init(request: RParseRequestFromFile | RParseRequestFromText, autoSelectIf?: AutoSelectPredicate): Promise<void>;
+    init(request: RParseRequestFromFile | RParseRequestFromText, autoSelectIf?: AutoSelectPredicate, threshold?: number): Promise<void>;
     private calculateStatsAfterInit;
     /**
-   * Slice for the given {@link SlicingCriteria}.
-   * @see SingleSlicingCriterion
-   *
-   * @returns The per slice stats retrieved for this slicing criteria
-   */
+     * Counts the number of stored indices in the dataflow graph created by the pointer analysis.
+     */
+    private countStoredVertexIndices;
+    /**
+     * Counts the number of stored indices in the dataflow graph created by the pointer analysis.
+     */
+    private countStoredEnvIndices;
+    /**
+     * Counts the number of stored indices in the passed definitions.
+     */
+    private countStoredIndices;
+    /**
+     * Recursively counts the number of indices and sub-indices in the given collection.
+     */
+    private countIndices;
+    /**
+     * Slice for the given {@link SlicingCriteria}.
+     * @see SingleSlicingCriterion
+     *
+     * @returns The per slice stats retrieved for this slicing criteria
+     */
     slice(...slicingCriteria: SlicingCriteria): Promise<BenchmarkSingleSliceStats>;
     /** Bridging the gap between the new internal and the old names for the benchmarking */
     private measureCommonStep;
     private measureSliceStep;
     private guardActive;
     /**
-   * Call {@link slice} for all slicing criteria that match the given filter.
-   * See {@link collectAllSlicingCriteria} for details.
-   * <p>
-   * the `report` function will be called *before* each *individual* slice is performed.
-   *
-   * @returns The number of slices that were produced
-   *
-   * @see collectAllSlicingCriteria
-   * @see SlicingCriteriaFilter
-   */
-    sliceForAll(filter: SlicingCriteriaFilter, report?: (current: number, total: number, allCriteria: SlicingCriteria[]) => void, sampleRandom?: number): Promise<number>;
+     * Call {@link slice} for all slicing criteria that match the given filter.
+     * See {@link collectAllSlicingCriteria} for details.
+     * <p>
+     * the `report` function will be called *before* each *individual* slice is performed.
+     *
+     * @returns The number of slices that were produced
+     *
+     * @see collectAllSlicingCriteria
+     * @see SlicingCriteriaFilter
+     */
+    sliceForAll(filter: SlicingCriteriaFilter, report?: (current: number, total: number, allCriteria: SlicingCriteria[]) => void, options?: {
+        sampleCount?: number;
+        maxSliceCount?: number;
+        sampleStrategy?: SamplingStrategy;
+    }): Promise<number>;
     /**
-   * Retrieves the final stats and closes the shell session.
-   * Can be called multiple times to retrieve the stored stats, but will only close the session once (the first time).
-   */
+     * Retrieves the final stats and closes the shell session.
+     * Can be called multiple times to retrieve the stored stats, but will only close the session once (the first time).
+     */
     finish(): BenchmarkSlicerStats;
     /**
-   * Only call in case of an error - if the session must be closed and the benchmark itself is to be considered failed/dead.
-   */
+     * Only call in case of an error - if the session must be closed and the benchmark itself is to be considered failed/dead.
+     */
     ensureSessionClosed(): void;
 }

package/benchmark/slicer.js

@@ -12,7 +12,7 @@ const stopwatch_1 = require("./stopwatch");
 const fs_1 = __importDefault(require("fs"));
 const log_1 = require("../util/log");
 const assert_1 = require("../util/assert");
-const strings_1 = require("../util/strings");
+const strings_1 = require("../util/text/strings");
 const default_pipelines_1 = require("../core/steps/pipeline/default-pipelines");
 const retriever_1 = require("../r-bridge/retriever");
 const collect_all_1 = require("../slicing/criterion/collect-all");
@@ -22,6 +22,8 @@ const size_of_1 = require("./stats/size-of");
 const shell_1 = require("../r-bridge/shell");
 const tree_sitter_types_1 = require("../r-bridge/lang-4.x/tree-sitter/tree-sitter-types");
 const tree_sitter_executor_1 = require("../r-bridge/lang-4.x/tree-sitter/tree-sitter-executor");
+const vertex_1 = require("../dataflow/graph/vertex");
+const arrays_1 = require("../util/collections/arrays");
 /**
  * The logger to be used for benchmarking as a global object.
  */
@@ -49,7 +51,7 @@ class BenchmarkSlicer {
      * Initialize the slicer on the given request.
      * Can only be called once for each instance.
      */
-    async init(request, autoSelectIf) {
+    async init(request, autoSelectIf, threshold) {
         (0, assert_1.guard)(this.stats === undefined, 'cannot initialize the slicer twice');
         // we know these are in sync so we just cast to one of them
         this.parser = await this.commonMeasurements.measure('initialize R session', async () => {
@@ -64,7 +66,8 @@ class BenchmarkSlicer {
         this.executor = (0, default_pipelines_1.createSlicePipeline)(this.parser, {
             request: { ...request },
             criterion: [],
-            autoSelectIf
+            autoSelectIf,
+            threshold,
         });
         this.loadedXml = (await this.measureCommonStep('parse', 'retrieve AST from R code')).parsed;
         this.normalizedAst = await this.measureCommonStep('normalize', 'normalize R AST');
@@ -127,6 +130,9 @@ class BenchmarkSlicer {
             }
             return false;
         });
+        const storedVertexIndices = this.countStoredVertexIndices();
+        const storedEnvIndices = this.countStoredEnvIndices();
+        const overwrittenIndices = storedVertexIndices - storedEnvIndices;
         const split = loadedContent.split('\n');
         const nonWhitespace = (0, strings_1.withoutWhitespace)(loadedContent).length;
         this.stats = {
@@ -150,7 +156,10 @@ class BenchmarkSlicer {
                 numberOfEdges: numberOfEdges,
                 numberOfCalls: numberOfCalls,
                 numberOfFunctionDefinitions: numberOfDefinitions,
-                sizeOfObject: (0, size_of_1.getSizeOfDfGraph)(this.dataflow.graph)
+                sizeOfObject: (0, size_of_1.getSizeOfDfGraph)(this.dataflow.graph),
+                storedVertexIndices: storedVertexIndices,
+                storedEnvIndices: storedEnvIndices,
+                overwrittenIndices: overwrittenIndices,
             },
             // these are all properly initialized in finish()
             commonMeasurements: new Map(),
@@ -161,11 +170,52 @@ class BenchmarkSlicer {
         };
     }
     /**
-   * Slice for the given {@link SlicingCriteria}.
-   * @see SingleSlicingCriterion
-   *
-   * @returns The per slice stats retrieved for this slicing criteria
-   */
+     * Counts the number of stored indices in the dataflow graph created by the pointer analysis.
+     */
+    countStoredVertexIndices() {
+        return this.countStoredIndices(this.dataflow?.out.map(ref => ref) ?? []);
+    }
+    /**
+     * Counts the number of stored indices in the dataflow graph created by the pointer analysis.
+     */
+    countStoredEnvIndices() {
+        return this.countStoredIndices(this.dataflow?.environment.current.memory.values()
+            ?.flatMap(def => def)
+            .map(def => def) ?? []);
+    }
+    /**
+     * Counts the number of stored indices in the passed definitions.
+     */
+    countStoredIndices(definitions) {
+        let numberOfIndices = 0;
+        for (const reference of definitions) {
+            if (reference.indicesCollection) {
+                numberOfIndices += this.countIndices(reference.indicesCollection);
+            }
+        }
+        return numberOfIndices;
+    }
+    /**
+     * Recursively counts the number of indices and sub-indices in the given collection.
+     */
+    countIndices(collection) {
+        let numberOfIndices = 0;
+        for (const indices of collection ?? []) {
+            for (const index of indices.indices) {
+                numberOfIndices++;
+                if ((0, vertex_1.isParentContainerIndex)(index)) {
+                    numberOfIndices += this.countIndices(index.subIndices);
+                }
+            }
+        }
+        return numberOfIndices;
+    }
+    /**
+     * Slice for the given {@link SlicingCriteria}.
+     * @see SingleSlicingCriterion
+     *
+     * @returns The per slice stats retrieved for this slicing criteria
+     */
     async slice(...slicingCriteria) {
         exports.benchmarkLogger.trace(`try to slice for criteria ${JSON.stringify(slicingCriteria)}`);
         this.guardActive();
@@ -227,23 +277,33 @@ class BenchmarkSlicer {
         (0, assert_1.guard)(this.stats !== undefined && !this.finished, 'need to call init before, and can not do after finish!');
     }
     /**
-   * Call {@link slice} for all slicing criteria that match the given filter.
-   * See {@link collectAllSlicingCriteria} for details.
-   * <p>
-   * the `report` function will be called *before* each *individual* slice is performed.
-   *
-   * @returns The number of slices that were produced
-   *
-   * @see collectAllSlicingCriteria
-   * @see SlicingCriteriaFilter
-   */
-    async sliceForAll(filter, report = () => { }, sampleRandom = -1) {
+     * Call {@link slice} for all slicing criteria that match the given filter.
+     * See {@link collectAllSlicingCriteria} for details.
+     * <p>
+     * the `report` function will be called *before* each *individual* slice is performed.
+     *
+     * @returns The number of slices that were produced
+     *
+     * @see collectAllSlicingCriteria
+     * @see SlicingCriteriaFilter
+     */
+    async sliceForAll(filter, report = () => { }, options = {}) {
+        const { sampleCount, maxSliceCount, sampleStrategy } = { sampleCount: -1, maxSliceCount: -1, sampleStrategy: 'random', ...options };
         this.guardActive();
         let count = 0;
-        const allCriteria = [...(0, collect_all_1.collectAllSlicingCriteria)(this.normalizedAst.ast, filter)];
-        if (sampleRandom > 0) {
-            allCriteria.sort(() => Math.random() - 0.5);
-            allCriteria.length = Math.min(allCriteria.length, sampleRandom);
+        let allCriteria = [...(0, collect_all_1.collectAllSlicingCriteria)(this.normalizedAst.ast, filter)];
+        // Cancel slicing if the number of slices exceeds the limit
+        if (maxSliceCount > 0 && allCriteria.length > maxSliceCount) {
+            return -allCriteria.length;
+        }
+        if (sampleCount > 0) {
+            if (sampleStrategy === 'equidistant') {
+                allCriteria = (0, arrays_1.equidistantSampling)(allCriteria, sampleCount, 'ceil');
+            }
+            else {
+                allCriteria.sort(() => Math.random() - 0.5);
+                allCriteria.length = Math.min(allCriteria.length, sampleCount);
+            }
         }
         for (const slicingCriteria of allCriteria) {
             report(count, allCriteria.length, allCriteria);
@@ -253,9 +313,9 @@ class BenchmarkSlicer {
         return count;
     }
     /**
-   * Retrieves the final stats and closes the shell session.
-   * Can be called multiple times to retrieve the stored stats, but will only close the session once (the first time).
-   */
+     * Retrieves the final stats and closes the shell session.
+     * Can be called multiple times to retrieve the stored stats, but will only close the session once (the first time).
+     */
     finish() {
         (0, assert_1.guard)(this.stats !== undefined, 'need to call init before finish');
         if (!this.finished) {
@@ -291,8 +351,8 @@ class BenchmarkSlicer {
         };
     }
     /**
-   * Only call in case of an error - if the session must be closed and the benchmark itself is to be considered failed/dead.
-   */
+     * Only call in case of an error - if the session must be closed and the benchmark itself is to be considered failed/dead.
+     */
     ensureSessionClosed() {
         this.parser?.close();
     }

package/benchmark/stats/print.js

@@ -140,11 +140,14 @@ Input:
   Normalized R tokens (w/o comments):  ${pad(stats.input.numberOfNormalizedTokensNoComments)}
 
 Dataflow:
-  Number of nodes:            ${pad(stats.dataflow.numberOfNodes)}
-  Number of edges:            ${pad(stats.dataflow.numberOfEdges)}
-  Number of calls:            ${pad(stats.dataflow.numberOfCalls)}
-  Number of function defs:    ${pad(stats.dataflow.numberOfFunctionDefinitions)}
-  Size of graph:              ${convertNumberToNiceBytes(stats.dataflow.sizeOfObject)}`;
+  Number of nodes:               ${pad(stats.dataflow.numberOfNodes)}
+  Number of edges:               ${pad(stats.dataflow.numberOfEdges)}
+  Number of calls:               ${pad(stats.dataflow.numberOfCalls)}
+  Number of function defs:       ${pad(stats.dataflow.numberOfFunctionDefinitions)}
+  Number of stored Vtx indices:  ${pad(stats.dataflow.storedVertexIndices)}
+  Number of stored Env indices:  ${pad(stats.dataflow.storedEnvIndices)}
+  Number of overwritten indices: ${pad(stats.dataflow.overwrittenIndices)}
+  Size of graph:                 ${convertNumberToNiceBytes(stats.dataflow.sizeOfObject)}`;
 }
 function ultimateStats2String(stats) {
     const slice = stats.totalSlices > 0 ? `Slice summary for:
@@ -195,11 +198,14 @@ Input:
   Normalized R tokens (w/o comments):  ${formatSummarizedMeasure(stats.input.numberOfNormalizedTokensNoComments)}
 
 Dataflow:
-  Number of nodes:            ${formatSummarizedMeasure(stats.dataflow.numberOfNodes)}
-  Number of edges:            ${formatSummarizedMeasure(stats.dataflow.numberOfEdges)}
-  Number of calls:            ${formatSummarizedMeasure(stats.dataflow.numberOfCalls)}
-  Number of function defs:    ${formatSummarizedMeasure(stats.dataflow.numberOfFunctionDefinitions)}
-  Size of graph:              ${formatSummarizedMeasure(stats.dataflow.sizeOfObject, convertNumberToNiceBytes)}
+  Number of nodes:               ${formatSummarizedMeasure(stats.dataflow.numberOfNodes)}
+  Number of edges:               ${formatSummarizedMeasure(stats.dataflow.numberOfEdges)}
+  Number of calls:               ${formatSummarizedMeasure(stats.dataflow.numberOfCalls)}
+  Number of function defs:       ${formatSummarizedMeasure(stats.dataflow.numberOfFunctionDefinitions)}
+  Number of stored Vtx indices:  ${formatSummarizedMeasure(stats.dataflow.storedVertexIndices)}
+  Number of stored Env indices:  ${formatSummarizedMeasure(stats.dataflow.storedEnvIndices)}
+  Number of overwritten indices: ${formatSummarizedMeasure(stats.dataflow.overwrittenIndices)}
+  Size of graph:                 ${formatSummarizedMeasure(stats.dataflow.sizeOfObject, convertNumberToNiceBytes)}
 `;
 }
 function reduction2String(title, reduction) {

package/benchmark/stats/size-of.js

@@ -65,6 +65,23 @@ function getSizeOfDfGraph(df) {
         });
         verts.push(vertex);
     }
-    return (0, object_sizeof_1.default)([...verts, ...df.edges()]);
+    return safeSizeOf([...verts, ...df.edges()]);
+}
+/**
+ * Calculates the size of an array in bytes.
+ *
+ * @param array - The array to calculate the size of.
+ * @returns The size of the array in bytes.
+ */
+function safeSizeOf(array) {
+    const size = (0, object_sizeof_1.default)(array);
+    if (typeof size === 'number') {
+        return size;
+    }
+    // the sizeOf method returns an error object, when the size could not be calculated
+    // in this case, we split the array in half and calculate the size of each half recursively
+    const chunkSize = Math.ceil(array.length / 2);
+    // subtract 1, because of the separate stringification of the array
+    return safeSizeOf(array.slice(0, chunkSize)) + safeSizeOf(array.slice(chunkSize)) - 1;
 }
 //# sourceMappingURL=size-of.js.map

package/benchmark/stats/stats.d.ts

@@ -37,6 +37,9 @@ export interface SlicerStatsDataflow<T = number> {
     numberOfCalls: T;
     numberOfFunctionDefinitions: T;
     sizeOfObject: T;
+    storedVertexIndices: T;
+    storedEnvIndices: T;
+    overwrittenIndices: T;
 }
 /**
  * Please note, that these measurement can be negative as there is no guarantee that the memory usage will increase

package/benchmark/summarizer/first-phase/input.js

@@ -9,7 +9,7 @@ const fs_1 = __importDefault(require("fs"));
 const process_1 = require("../second-phase/process");
 const process_2 = require("./process");
 const assert_1 = require("../../../util/assert");
-const ansi_1 = require("../../../util/ansi");
+const ansi_1 = require("../../../util/text/ansi");
 const json_1 = require("../../../util/json");
 const print_1 = require("../../stats/print");
 async function processRunMeasurement(line, fileNum, lineNum, textOutputAppendPath, rawOutputPath) {