@eagleoutice/flowr 2.6.2 → 2.6.3

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 v2.6.1, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.6.2, R grammar v14 (tree-sitter engine)
     R> :query @linter "read.csv(\"/root/x.txt\")"
     ```
     
@@ -33,19 +33,19 @@ It offers a wide variety of features, for example:
     
     
     ```text
-    Query: linter (6 ms)
+    Query: linter (3 ms)
        ╰ **Deprecated Functions** (deprecated-functions):
-           ╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":3,"processTimeMs":0}</code>
+           ╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":1,"processTimeMs":0}</code>
        ╰ **File Path Validity** (file-path-validity):
            ╰ certain:
                ╰ Path `/root/x.txt` at 1.1-23
-           ╰ _Metadata_: <code>{"totalReads":1,"totalUnknown":0,"totalWritesBeforeAlways":0,"totalValid":0,"searchTimeMs":1,"processTimeMs":0}</code>
+           ╰ _Metadata_: <code>{"totalReads":1,"totalUnknown":0,"totalWritesBeforeAlways":0,"totalValid":0,"searchTimeMs":0,"processTimeMs":1}</code>
        ╰ **Seeded Randomness** (seeded-randomness):
-           ╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"searchTimeMs":0,"processTimeMs":0}</code>
+           ╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"callsWithOtherBranchProducers":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":1,"processTimeMs":0}</code>
+           ╰ _Metadata_: <code>{"totalConsidered":1,"totalUnknown":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Unused Definitions** (unused-definitions):
            ╰ _Metadata_: <code>{"totalConsidered":0,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Naming Convention** (naming-convention):
@@ -58,7 +58,7 @@ It offers a wide variety of features, for example:
            ╰ _Metadata_: <code>{"consideredNodes":5,"searchTimeMs":0,"processTimeMs":0}</code>
        ╰ **Useless Loops** (useless-loop):
            ╰ _Metadata_: <code>{"numOfUselessLoops":0,"searchTimeMs":0,"processTimeMs":0}</code>
-    All queries together required ≈6 ms (1ms accuracy, total 9 ms)
+    All queries together required ≈3 ms (1ms accuracy, total 3 ms)
     ```
     
     
@@ -80,36 +80,36 @@ It offers a wide variety of features, for example:
     
     _Results (prettified and summarized):_
     
-    Query: **linter** (212 ms)\
+    Query: **linter** (3 ms)\
     &nbsp;&nbsp;&nbsp;╰ **Deprecated Functions** (deprecated-functions):\
-    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":198,"processTimeMs":0}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":0,"searchTimeMs":1,"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":5,"processTimeMs":1}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalReads":1,"totalUnknown":0,"totalWritesBeforeAlways":0,"totalValid":0,"searchTimeMs":1,"processTimeMs":0}</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":0}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"consumerCalls":0,"callsWithFunctionProducers":0,"callsWithAssignmentProducers":0,"callsWithNonConstantProducers":0,"callsWithOtherBranchProducers":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":1}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalConsidered":1,"totalUnknown":0,"searchTimeMs":1,"processTimeMs":0}</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":0,"processTimeMs":1}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"totalCalls":0,"totalFunctionDefinitions":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":2}</code>\
+    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"numOperations":0,"numAccesses":0,"totalAccessed":0,"searchTimeMs":0,"processTimeMs":0}</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;&nbsp;&nbsp;&nbsp;&nbsp;╰ _Metadata_: <code>{"consideredNodes":5,"searchTimeMs":0,"processTimeMs":0}</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 213 ms)_
+    _All queries together required ≈3 ms (1ms accuracy, total 4 ms)_
     
     <details> <summary style="color:gray">Show Detailed Results as Json</summary>
     
-    The analysis required _213.3 ms_ (including parsing and normalization and the query) within the generation environment.
+    The analysis required _3.7 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.
@@ -126,7 +126,7 @@ It offers a wide variety of features, for example:
             ".meta": {
               "totalCalls": 0,
               "totalFunctionDefinitions": 0,
-              "searchTimeMs": 198,
+              "searchTimeMs": 1,
               "processTimeMs": 0
             }
           },
@@ -148,8 +148,8 @@ It offers a wide variety of features, for example:
               "totalUnknown": 0,
               "totalWritesBeforeAlways": 0,
               "totalValid": 0,
-              "searchTimeMs": 5,
-              "processTimeMs": 1
+              "searchTimeMs": 1,
+              "processTimeMs": 0
             }
           },
           "seeded-randomness": {
@@ -159,6 +159,7 @@ It offers a wide variety of features, for example:
               "callsWithFunctionProducers": 0,
               "callsWithAssignmentProducers": 0,
               "callsWithNonConstantProducers": 0,
+              "callsWithOtherBranchProducers": 0,
               "searchTimeMs": 0,
               "processTimeMs": 0
             }
@@ -179,8 +180,8 @@ It offers a wide variety of features, for example:
             ".meta": {
               "totalConsidered": 1,
               "totalUnknown": 0,
-              "searchTimeMs": 2,
-              "processTimeMs": 1
+              "searchTimeMs": 1,
+              "processTimeMs": 0
             }
           },
           "unused-definitions": {
@@ -206,7 +207,7 @@ It offers a wide variety of features, for example:
               "totalCalls": 0,
               "totalFunctionDefinitions": 0,
               "searchTimeMs": 0,
-              "processTimeMs": 1
+              "processTimeMs": 0
             }
           },
           "dataframe-access-validation": {
@@ -216,7 +217,7 @@ It offers a wide variety of features, for example:
               "numAccesses": 0,
               "totalAccessed": 0,
               "searchTimeMs": 0,
-              "processTimeMs": 2
+              "processTimeMs": 0
             }
           },
           "dead-code": {
@@ -224,7 +225,7 @@ It offers a wide variety of features, for example:
             ".meta": {
               "consideredNodes": 5,
               "searchTimeMs": 0,
-              "processTimeMs": 1
+              "processTimeMs": 0
             }
           },
           "useless-loop": {
@@ -237,11 +238,11 @@ It offers a wide variety of features, for example:
           }
         },
         ".meta": {
-          "timing": 212
+          "timing": 3
         }
       },
       ".meta": {
-        "timing": 213
+        "timing": 3
       }
     }
     ```
@@ -306,8 +307,8 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.6.1, R v4.5.0 (r-shell engine)
-    R> :slicer test/testfiles/example.R --criterion "11@sum"
+    flowR repl using flowR v2.6.2, R grammar v14 (tree-sitter engine)
+    R> :query @static-slice (11@sum) file://test/testfiles/example.R
     ```
     
     <details>
@@ -320,6 +321,7 @@ It offers a wide variety of features, for example:
     N <- 10
     for(i in 1:(N-1)) sum <- sum + i + w
     sum
+    All queries together required ≈3 ms (1ms accuracy, total 4 ms)
     ```
     
     
@@ -353,7 +355,7 @@ 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!">137.6 ms</span></i> (as of Oct 21, 2025), 
+  Within just <i><span title="This measurement is automatically fetched from the latest benchmark!">138.7 ms</span></i> (as of Nov 9, 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.
 
@@ -389,7 +391,7 @@ It offers a wide variety of features, for example:
     
     ```shell
     $ docker run -it --rm eagleoutice/flowr # or npm run flowr 
-    flowR repl using flowR v2.6.1, R v4.5.0 (r-shell engine)
+    flowR repl using flowR v2.6.2, R grammar v14 (tree-sitter engine)
     R> :dataflow* test/testfiles/example.R
     ```
     
@@ -694,7 +696,7 @@ It offers a wide variety of features, for example:
     ```
     
     	
-    (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.)
+    (The analysis required _2.3 ms_ (including parse and normalize, using the [tree-sitter](https://github.com/flowr-analysis/flowr/wiki/Engines) engine) within the generation environment.)
     
     
     
@@ -873,6 +875,6 @@ It is partially supported by the German Research Foundation (DFG) under the gran
 
 ### Generation Notice
 
-Please notice that this file was generated automatically using the file [src/documentation/print-readme.ts](https://github.com/flowr-analysis/flowr/tree/main//src/documentation/print-readme.ts) as a source.\
+Please notice that this file was generated automatically using the file [src/documentation/doc-readme.ts](https://github.com/flowr-analysis/flowr/tree/main//src/documentation/doc-readme.ts) as a source.\
 If you want to make changes please edit the source file (the CI will take care of the rest).
-In fact, many files in the [wiki](https://github.com/flowr-analysis/flowr/wiki) are generated, so make sure to check for the source file if you want to make changes.
+In fact, many files in the [wiki](https://github.com/flowr-analysis/flowr/wiki) are generated, so make sure to check for the source file if you want to make changes.

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

@@ -87,7 +87,7 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
     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);
+            node.info.dataFrame = (0, function_mapper_1.mapDataFrameFunctionCall)(node, this.config.dfg, this.config.ctx);
             this.applyDataFrameExpression(node);
         }
     }
@@ -119,7 +119,7 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
         if (!(0, absint_info_1.hasDataFrameExpressionInfo)(node)) {
             return;
         }
-        const maxColNames = this.config.flowrConfig.abstractInterpretation.dataFrame.maxColNames;
+        const maxColNames = this.config.ctx.config.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;
@@ -159,7 +159,7 @@ class DataFrameShapeInferenceVisitor extends semantic_cfg_guided_visitor_1.Seman
             .toArray() ?? [];
     }
     shouldWiden(vertex) {
-        return (this.visited.get(vertex.id) ?? 0) >= this.config.flowrConfig.abstractInterpretation.dataFrame.wideningThreshold;
+        return (this.visited.get(vertex.id) ?? 0) >= this.config.ctx.config.abstractInterpretation.dataFrame.wideningThreshold;
     }
     clearUnassignedInfo(node) {
         if ((0, absint_info_1.hasDataFrameInfoMarker)(node, absint_info_1.DataFrameInfoMarker.Unassigned)) {

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

@@ -1,4 +1,3 @@
-import { type FlowrConfigOptions } from '../../../config';
 import { type ResolveInfo } from '../../../dataflow/eval/resolve/alias-tracking';
 import type { DataflowGraph } from '../../../dataflow/graph/graph';
 import type { RNode } from '../../../r-bridge/lang-4.x/ast/model/model';
@@ -6,6 +5,7 @@ import { type RFunctionArgument } from '../../../r-bridge/lang-4.x/ast/model/nod
 import type { ParentInformation } from '../../../r-bridge/lang-4.x/ast/model/processing/decorate';
 import type { DataFrameExpressionInfo, DataFrameOperation } from '../absint-info';
 import { type FunctionParameterLocation } from './arguments';
+import type { ReadOnlyFlowrAnalyzerContext } from '../../../project/context/flowr-analyzer-context';
 /**
  * Represents the different types of data frames in R
  */
@@ -179,12 +179,12 @@ declare const DataFrameFunctionMapper: {
 type DataFrameFunction = keyof typeof DataFrameFunctionMapper;
 /**
  * Maps a concrete data frame function call to abstract data frame operations.
- * @param node   - The R node of the function call
- * @param dfg    - The data flow graph for resolving the arguments
- * @param config - The flowR configuration to use
+ * @param node - The R node of the function call
+ * @param dfg  - The data flow graph for resolving the arguments
+ * @param ctx  - The current flowR analyzer context
  * @returns Data frame expression info containing the mapped abstract data frame operations, or `undefined` if the node does not represent a data frame function call
  */
-export declare function mapDataFrameFunctionCall<Name extends DataFrameFunction>(node: RNode<ParentInformation>, dfg: DataflowGraph, config: FlowrConfigOptions): DataFrameExpressionInfo | undefined;
+export declare function mapDataFrameFunctionCall<Name extends DataFrameFunction>(node: RNode<ParentInformation>, dfg: DataflowGraph, ctx: ReadOnlyFlowrAnalyzerContext): DataFrameExpressionInfo | undefined;
 declare function mapDataFrameCreate(args: readonly RFunctionArgument<ParentInformation>[], params: {
     checkNames: FunctionParameterLocation<boolean>;
     noDupNames: FunctionParameterLocation<boolean>;
@@ -204,7 +204,7 @@ declare function mapDataFrameRead(args: readonly RFunctionArgument<ParentInforma
     checkNames: FunctionParameterLocation<boolean>;
     noDupNames: FunctionParameterLocation<boolean>;
     noEmptyNames?: boolean;
-}, info: ResolveInfo, config: FlowrConfigOptions): DataFrameOperation[];
+}, info: ResolveInfo, ctx: ReadOnlyFlowrAnalyzerContext): DataFrameOperation[];
 declare function mapDataFrameColBind(args: readonly RFunctionArgument<ParentInformation>[], params: {
     special: string[];
 }, info: ResolveInfo): DataFrameOperation[] | undefined;
@@ -251,7 +251,7 @@ declare function mapDataFrameJoin(args: readonly RFunctionArgument<ParentInforma
     joinAll: FunctionParameterLocation<boolean>;
     joinLeft: FunctionParameterLocation<boolean>;
     joinRight: FunctionParameterLocation<boolean>;
-}, info: ResolveInfo, config: FlowrConfigOptions): DataFrameOperation[] | undefined;
+}, info: ResolveInfo, ctx: ReadOnlyFlowrAnalyzerContext): DataFrameOperation[] | undefined;
 declare function mapDataFrameIdentity(args: readonly RFunctionArgument<ParentInformation>[], params: {
     dataFrame: FunctionParameterLocation;
     special: string[];

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

@@ -519,12 +519,12 @@ const DataFrameFunctionParamsMapper = {
 };
 /**
  * Maps a concrete data frame function call to abstract data frame operations.
- * @param node   - The R node of the function call
- * @param dfg    - The data flow graph for resolving the arguments
- * @param config - The flowR configuration to use
+ * @param node - The R node of the function call
+ * @param dfg  - The data flow graph for resolving the arguments
+ * @param ctx  - The current flowR analyzer context
  * @returns Data frame expression info containing the mapped abstract data frame operations, or `undefined` if the node does not represent a data frame function call
  */
-function mapDataFrameFunctionCall(node, dfg, config) {
+function mapDataFrameFunctionCall(node, dfg, ctx) {
     if (node.type !== type_1.RType.FunctionCall || !node.named) {
         return;
     }
@@ -539,7 +539,7 @@ function mapDataFrameFunctionCall(node, dfg, config) {
             operations = [{ operation: 'unknown', operand: undefined }];
         }
         else {
-            operations = mapper(args, params, resolveInfo, config);
+            operations = mapper(args, params, resolveInfo, ctx);
         }
     }
     else {
@@ -605,10 +605,10 @@ function mapDataFrameConvert(args, params, info) {
             operand: dataFrame.value.info.id
         }];
 }
-function mapDataFrameRead(args, params, info, config) {
+function mapDataFrameRead(args, params, info, ctx) {
     const fileNameArg = (0, arguments_1.getFunctionArgument)(args, params.fileName, info);
     const textArg = params.text ? (0, arguments_1.getFunctionArgument)(args, params.text, info) : undefined;
-    const { source, request } = getRequestFromRead(fileNameArg, textArg, params, info, config);
+    const { source, request } = getRequestFromRead(fileNameArg, textArg, params, info, ctx);
     const header = (0, arguments_1.getArgumentValue)(args, params.header, info);
     const separator = (0, arguments_1.getArgumentValue)(args, params.separator, info);
     const quote = (0, arguments_1.getArgumentValue)(args, params.quote, info);
@@ -618,7 +618,7 @@ function mapDataFrameRead(args, params, info, config) {
     const noDupNames = (0, arguments_1.getArgumentValue)(args, params.noDupNames, info);
     const validArguments = typeof header === 'boolean' && typeof separator === 'string' && typeof quote === 'string' && typeof comment === 'string' &&
         typeof skipLines === 'number' && typeof checkNames === 'boolean' && typeof noDupNames === 'boolean';
-    if (request === undefined || !config.abstractInterpretation.dataFrame.readLoadedData.readExternalFiles || !validArguments) {
+    if (request === undefined || !ctx.config.abstractInterpretation.dataFrame.readLoadedData.readExternalFiles || !validArguments) {
         return [{
                 operation: 'read',
                 operand: undefined,
@@ -643,7 +643,7 @@ function mapDataFrameRead(args, params, info, config) {
             }
         }
     };
-    const allLines = parseRequestContent(request, parseLine, config.abstractInterpretation.dataFrame.readLoadedData.maxReadLines);
+    const allLines = parseRequestContent(request, parseLine, ctx.config.abstractInterpretation.dataFrame.readLoadedData.maxReadLines);
     let colnames;
     if (header) {
         colnames = (0, arguments_1.filterValidNames)(firstLine, checkNames, noDupNames, params.noEmptyNames);
@@ -1002,8 +1002,11 @@ function mapDataFrameSummarize(args, params, info) {
     }
     const result = [];
     const summarizeArgs = args.filter(arg => arg !== dataFrame);
-    const accessedNames = summarizeArgs.flatMap(arg => (0, arguments_1.getUnresolvedSymbolsInExpression)(arg, info.graph));
     const summarizedCols = summarizeArgs.map(arg => (0, resolve_args_1.resolveIdToArgName)(arg, info));
+    // only column names that are not created by summarize are preconditions on the operand
+    const accessedNames = summarizeArgs
+        .flatMap(arg => (0, arguments_1.getUnresolvedSymbolsInExpression)(arg, info.graph))
+        .filter(arg => !summarizedCols.includes(arg));
     if (accessedNames.length > 0) {
         result.push({
             operation: 'accessCols',
@@ -1018,7 +1021,7 @@ function mapDataFrameSummarize(args, params, info) {
     });
     return result;
 }
-function mapDataFrameJoin(args, params, info, config) {
+function mapDataFrameJoin(args, params, info, ctx) {
     const dataFrame = (0, arguments_1.getFunctionArgument)(args, params.dataFrame, info);
     const joinAll = (0, arguments_1.getArgumentValue)(args, params.joinAll, info);
     const joinLeft = (0, arguments_1.getArgumentValue)(args, params.joinLeft, info);
@@ -1035,7 +1038,7 @@ function mapDataFrameJoin(args, params, info, config) {
     const result = [];
     const otherArg = (0, arguments_1.getFunctionArgument)(args, params.otherDataFrame, info);
     const byArg = (0, arguments_1.getFunctionArgument)(args, params.by, info);
-    const otherDataFrame = (0, shape_inference_1.resolveIdToDataFrameShape)(otherArg, info.graph) ?? dataframe_domain_1.DataFrameDomain.top(config.abstractInterpretation.dataFrame.maxColNames);
+    const otherDataFrame = (0, shape_inference_1.resolveIdToDataFrameShape)(otherArg, info.graph) ?? dataframe_domain_1.DataFrameDomain.top(ctx.config.abstractInterpretation.dataFrame.maxColNames);
     let byCols;
     const joinType = getJoinType(joinAll, joinLeft, joinRight);
     if (byArg !== undefined) {
@@ -1101,19 +1104,19 @@ function mapDataFrameUnknown(args, params, info) {
             ...(params.constraintType !== undefined ? { type: params.constraintType } : {})
         }];
 }
-function getRequestFromRead(fileNameArg, textArg, params, info, config) {
+function getRequestFromRead(fileNameArg, textArg, params, info, ctx) {
     let source;
     let request;
     if (fileNameArg !== undefined && fileNameArg !== r_function_call_1.EmptyArgument) {
         const fileName = (0, resolve_args_1.resolveIdToArgValue)(fileNameArg, info);
         if (typeof fileName === 'string') {
             source = fileName;
-            const referenceChain = fileNameArg.info.file ? [(0, retriever_1.requestFromInput)(`file://${fileNameArg.info.file}`)] : [];
-            const sources = (0, built_in_source_1.findSource)(config.solver.resolveSource, fileName, { referenceChain });
+            const referenceChain = fileNameArg.info.file ? [fileNameArg.info.file] : [];
+            const sources = (0, built_in_source_1.findSource)(ctx.config.solver.resolveSource, fileName, { referenceChain, ctx });
             if (sources?.length === 1) {
                 source = sources[0];
                 // create request from resolved source file path
-                request = (0, built_in_source_1.getSourceProvider)().createRequest(source);
+                request = { request: 'file', content: sources[0] };
             }
             else if (params.text === undefined && (0, resolve_args_1.unescapeSpecialChars)(fileName).includes('\n')) {
                 // create request from string if file name argument contains newline
@@ -1128,6 +1131,7 @@ function getRequestFromRead(fileNameArg, textArg, params, info, config) {
             request = (0, retriever_1.requestFromInput)((0, resolve_args_1.unescapeSpecialChars)(text));
         }
     }
+    request = request ? ctx.files.resolveRequest(request).r : undefined;
     return { source, request };
 }
 function parseRequestContent(request, parser, maxLines) {

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

@@ -168,6 +168,14 @@ function applyAddColsSemantics(value, { colnames }) {
     });
 }
 function applyAddRowsSemantics(value, { rows }) {
+    if (value.cols.value !== lattice_1.Bottom && value.cols.value[0] === 0) {
+        return new dataframe_domain_1.DataFrameDomain({
+            ...value,
+            colnames: value.colnames.top(),
+            cols: rows !== undefined ? value.cols.add([1, 1]) : value.cols.top(),
+            rows: rows !== undefined ? value.rows.add([rows, rows]) : value.rows.extendUp()
+        });
+    }
     return new dataframe_domain_1.DataFrameDomain({
         colnames: value.colnames,
         cols: value.cols,

package/abstract-interpretation/data-frame/shape-inference.d.ts

@@ -1,4 +1,3 @@
-import type { FlowrConfigOptions } from '../../config';
 import { type ControlFlowInformation } from '../../control-flow/control-flow-graph';
 import type { DataflowGraph } from '../../dataflow/graph/graph';
 import type { RNode } from '../../r-bridge/lang-4.x/ast/model/model';
@@ -6,17 +5,18 @@ import type { NormalizedAst, ParentInformation } from '../../r-bridge/lang-4.x/a
 import type { NodeId } from '../../r-bridge/lang-4.x/ast/model/processing/node-id';
 import { type AbstractInterpretationInfo } from './absint-info';
 import { type DataFrameDomain, DataFrameStateDomain } from './dataframe-domain';
+import type { ReadOnlyFlowrAnalyzerContext } from '../../project/context/flowr-analyzer-context';
 /**
  * Infers the shape of data frames by performing abstract interpretation using the control flow graph of a program.
  * This directly attaches the inferred data frames shapes to the AST (see {@link AbstractInterpretationInfo}).
  * @param cfinfo - The control flow information containing the control flow graph
  * @param dfg    - The data flow graph to resolve variable origins and function arguments
  * @param ast    - The abstract syntax tree to resolve node IDs to AST nodes
- * @param config - The flowR configuration to use for the shape inference
+ * @param ctx    - The current flowr analyzer context
  * @returns The abstract data frame state at the exit node of the control flow graph (see {@link DataFrameStateDomain}).
  * The abstract data frame states for all other nodes are attached to the AST.
  */
-export declare function inferDataFrameShapes(cfinfo: ControlFlowInformation, dfg: DataflowGraph, ast: NormalizedAst<ParentInformation & AbstractInterpretationInfo>, config: FlowrConfigOptions): DataFrameStateDomain;
+export declare function inferDataFrameShapes(cfinfo: ControlFlowInformation, dfg: DataflowGraph, ast: NormalizedAst<ParentInformation & AbstractInterpretationInfo>, ctx: ReadOnlyFlowrAnalyzerContext): DataFrameStateDomain;
 /**
  * Resolves the abstract data frame shape of a node in the AST.
  * This requires that the data frame shape inference has been executed before using {@link inferDataFrameShapes}.

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

@@ -19,12 +19,12 @@ const dataframe_domain_1 = require("./dataframe-domain");
  * @param cfinfo - The control flow information containing the control flow graph
  * @param dfg    - The data flow graph to resolve variable origins and function arguments
  * @param ast    - The abstract syntax tree to resolve node IDs to AST nodes
- * @param config - The flowR configuration to use for the shape inference
+ * @param ctx    - The current flowr analyzer context
  * @returns The abstract data frame state at the exit node of the control flow graph (see {@link DataFrameStateDomain}).
  * The abstract data frame states for all other nodes are attached to the AST.
  */
-function inferDataFrameShapes(cfinfo, dfg, ast, config) {
-    const visitor = new absint_visitor_1.DataFrameShapeInferenceVisitor({ controlFlow: cfinfo, dfg: dfg, normalizedAst: ast, flowrConfig: config });
+function inferDataFrameShapes(cfinfo, dfg, ast, ctx) {
+    const visitor = new absint_visitor_1.DataFrameShapeInferenceVisitor({ controlFlow: cfinfo, dfg: dfg, normalizedAst: ast, ctx });
     visitor.start();
     const exitPoints = cfinfo.exitPoints.map(id => cfinfo.graph.getVertex(id)).filter(assert_1.isNotUndefined);
     const exitNodes = exitPoints.map(vertex => ast.idMap.get((0, control_flow_graph_1.getVertexRootId)(vertex))).filter(assert_1.isNotUndefined);

package/abstract-interpretation/normalized-ast-fold.d.ts

@@ -25,7 +25,7 @@ type FoldOfType<T extends RType, Returns = void, Info = NoInfo> = (node: Extract
     type: T;
 }>) => Returns;
 /** explicitly excludes types that are not visitable */
-export type FoldableRType = Exclude<RType, RType.Delimiter>;
+export type FoldableRType = Exclude<RType, RType.Delimiter | RType.Project>;
 /**
  * Describes the fold functions for each node type.
  */

package/benchmark/slicer.d.ts

@@ -58,6 +58,7 @@ export declare class BenchmarkSlicer {
     private readonly deltas;
     private readonly parserName;
     private config;
+    private context;
     private stats;
     private loadedXml;
     private dataflow;

package/benchmark/slicer.js

@@ -29,6 +29,7 @@ const extract_cfg_1 = require("../control-flow/extract-cfg");
 const absint_info_1 = require("../abstract-interpretation/data-frame/absint-info");
 const shape_inference_1 = require("../abstract-interpretation/data-frame/shape-inference");
 const fs_1 = __importDefault(require("fs"));
+const flowr_analyzer_context_1 = require("../project/context/flowr-analyzer-context");
 /**
  * The logger to be used for benchmarking as a global object.
  */
@@ -40,6 +41,7 @@ class BenchmarkSlicer {
     deltas = new Map();
     parserName;
     config;
+    context;
     stats;
     loadedXml;
     dataflow;
@@ -71,13 +73,14 @@ class BenchmarkSlicer {
                 return new tree_sitter_executor_1.TreeSitterExecutor();
             }
         });
+        this.context = (0, flowr_analyzer_context_1.contextFromInput)({ ...request }, config);
         this.executor = (0, default_pipelines_1.createSlicePipeline)(this.parser, {
-            request: { ...request },
+            context: this.context,
             criterion: [],
             autoSelectIf,
             threshold,
-        }, config);
-        this.loadedXml = (await this.measureCommonStep('parse', 'retrieve AST from R code')).parsed;
+        });
+        this.loadedXml = (await this.measureCommonStep('parse', 'retrieve AST from R code')).files.map(p => p.parsed);
         this.normalizedAst = await this.measureCommonStep('normalize', 'normalize R AST');
         this.dataflow = await this.measureCommonStep('dataflow', 'produce dataflow information');
         this.executor.switchToRequestStage();
@@ -100,9 +103,9 @@ class BenchmarkSlicer {
                 }
                 return ret;
             };
-            const root = this.loadedXml.rootNode;
-            numberOfRTokens = countChildren(root);
-            numberOfRTokensNoComments = countChildren(root, true);
+            const root = this.loadedXml.map(t => t.rootNode);
+            numberOfRTokens = root.map(r => countChildren(r)).reduce((a, b) => a + b, 0);
+            numberOfRTokensNoComments = root.map(r => countChildren(r, true)).reduce((a, b) => a + b, 0);
         }
         (0, assert_1.guard)(this.normalizedAst !== undefined, 'normalizedAst should be defined after initialization');
         (0, assert_1.guard)(this.dataflow !== undefined, 'dataflow should be defined after initialization');
@@ -125,7 +128,7 @@ class BenchmarkSlicer {
         let nodesNoComments = 0;
         let commentChars = 0;
         let commentCharsNoWhitespace = 0;
-        (0, visitor_1.visitAst)(this.normalizedAst.ast, t => {
+        (0, visitor_1.visitAst)(this.normalizedAst.ast.files.map(f => f.root), t => {
             nodes++;
             const comments = t.info.additionalTokens?.filter(t => t.type === type_1.RType.Comment);
             if (comments && comments.length > 0) {
@@ -274,8 +277,7 @@ class BenchmarkSlicer {
         (0, assert_1.guard)(this.config !== undefined, 'config should be defined for control flow extraction');
         const ast = this.normalizedAst;
         const dfg = this.dataflow.graph;
-        const config = this.config;
-        this.controlFlow = this.measureSimpleStep('extract control flow graph', () => (0, extract_cfg_1.extractCfg)(ast, config, dfg));
+        this.controlFlow = this.measureSimpleStep('extract control flow graph', () => (0, extract_cfg_1.extractCfg)(ast, this.context, dfg));
     }
     /**
      * Infer the shape of data frames using abstract interpretation with {@link inferDataFrameShapes}
@@ -291,7 +293,6 @@ class BenchmarkSlicer {
         const ast = this.normalizedAst;
         const dfg = this.dataflow.graph;
         const cfinfo = this.controlFlow;
-        const config = this.config;
         const stats = {
             numberOfDataFrameFiles: 0,
             numberOfNonDataFrameFiles: 0,
@@ -305,7 +306,7 @@ class BenchmarkSlicer {
             sizeOfInfo: 0,
             perNodeStats: new Map()
         };
-        const result = this.measureSimpleStep('infer data frame shapes', () => (0, shape_inference_1.inferDataFrameShapes)(cfinfo, dfg, ast, config));
+        const result = this.measureSimpleStep('infer data frame shapes', () => (0, shape_inference_1.inferDataFrameShapes)(cfinfo, dfg, ast, this.context));
         stats.numberOfResultConstraints = result.value.size;
         for (const value of result.value.values()) {
             if (value.isTop()) {
@@ -318,7 +319,7 @@ class BenchmarkSlicer {
                 stats.numberOfResultingValues++;
             }
         }
-        (0, visitor_1.visitAst)(this.normalizedAst.ast, (node) => {
+        (0, visitor_1.visitAst)(this.normalizedAst.ast.files.map(f => f.root), (node) => {
             if (node.info.dataFrame === undefined) {
                 return;
             }

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

@@ -159,7 +159,7 @@ async function summarizeSlicerStats(stats, report = () => {
             let numberOfNormalizedTokensNoComments = 0;
             let commentChars = 0;
             let commentCharsNoWhitespace = 0;
-            (0, visitor_1.visitAst)(reParsed.ast, t => {
+            (0, visitor_1.visitAst)(reParsed.ast.files.map(f => f.root), t => {
                 numberOfNormalizedTokens++;
                 const comments = t.info.additionalTokens?.filter(t => t.type === type_1.RType.Comment);
                 if (comments && comments.length > 0) {

package/benchmark/summarizer/second-phase/graph.d.ts

@@ -1,5 +1,7 @@
 import type { UltimateSlicerStats } from '../data';
 /**
- *
+ * Write the graph output for the ultimate slicer stats to a file
+ * @param ultimate - The ultimate slicer stats
+ * @param outputGraphPath - The path to write the graph output to
  */
 export declare function writeGraphOutput(ultimate: UltimateSlicerStats, outputGraphPath: string): void;

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

@@ -7,7 +7,9 @@ exports.writeGraphOutput = writeGraphOutput;
 const fs_1 = __importDefault(require("fs"));
 const json_1 = require("../../../util/json");
 /**
- *
+ * Write the graph output for the ultimate slicer stats to a file
+ * @param ultimate - The ultimate slicer stats
+ * @param outputGraphPath - The path to write the graph output to
  */
 function writeGraphOutput(ultimate, outputGraphPath) {
     console.log(`Producing benchmark graph data (${outputGraphPath})...`);

package/cli/export-quads-app.js

@@ -21,7 +21,7 @@ const options = (0, script_1.processCommandLineArgs)('export-quads', [], {
 const shell = new shell_1.RShell((0, config_1.getEngineConfig)((0, config_1.getConfig)(), 'r-shell'));
 async function writeQuadForSingleFile(request, output) {
     const normalized = await (0, retriever_1.retrieveNormalizedAstFromRCode)(request, shell);
-    const serialized = (0, quads_1.serialize2quads)(normalized.ast, { context: request.content });
+    const serialized = (0, quads_1.serialize2quads)(normalized.ast.files[0].root, { context: request.content });
     log_1.log.info(`Appending quads to ${output}`);
     fs_1.default.appendFileSync(output, serialized);
 }