[DF-Shape] Use a set range domain for the column names of data frames

src/abstract-interpretation/data-frame/absint-visitor.ts

@@ -1,12 +1,12 @@
-import { type CfgBasicBlockVertex, type CfgSimpleVertex, type ControlFlowInformation , CfgVertexType, getVertexRootId, isMarkerVertex } from '../../control-flow/control-flow-graph';
-import { type SemanticCfgGuidedVisitorConfiguration , SemanticCfgGuidedVisitor } from '../../control-flow/semantic-cfg-guided-visitor';
+import { type CfgBasicBlockVertex, type CfgSimpleVertex, type ControlFlowInformation, CfgVertexType, getVertexRootId, isMarkerVertex } 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, RNode } from '../../r-bridge/lang-4.x/ast/model/model';
 import type { NormalizedAst, 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 { isNotUndefined } from '../../util/assert';
-import { DataFrameInfoMarker, hasDataFrameAssignmentInfo, hasDataFrameExpressionInfo, hasDataFrameInfoMarker, type AbstractInterpretationInfo } from './absint-info';
+import { type AbstractInterpretationInfo, DataFrameInfoMarker, hasDataFrameAssignmentInfo, hasDataFrameExpressionInfo, hasDataFrameInfoMarker } from './absint-info';
 import { DataFrameDomain, DataFrameStateDomain } from './dataframe-domain';
 import { mapDataFrameAccess } from './mappers/access-mapper';
 import { isAssignmentTarget, mapDataFrameVariableAssignment } from './mappers/assignment-mapper';

src/abstract-interpretation/data-frame/dataframe-domain.ts

@@ -2,12 +2,13 @@ import type { NodeId } from '../../r-bridge/lang-4.x/ast/model/processing/node-i
 import type { AbstractDomainValue } from '../domains/abstract-domain';
 import { PosIntervalDomain } from '../domains/positive-interval-domain';
 import { ProductDomain } from '../domains/product-domain';
-import { SetUpperBoundDomain } from '../domains/set-upper-bound-domain';
+import type { SetRangeLimit } from '../domains/set-range-domain';
+import { SetRangeDomain } from '../domains/set-range-domain';
 import { StateAbstractDomain } from '../domains/state-abstract-domain';
 
 /** The type of the abstract product representing the shape of data frames */
 export type AbstractDataFrameShape = {
-	colnames: SetUpperBoundDomain<string>;
+	colnames: SetRangeDomain<string>;
 	cols:     PosIntervalDomain;
 	rows:     PosIntervalDomain;
 }
@@ -19,17 +20,17 @@ export type DataFrameShapeProperty<Property extends keyof AbstractDataFrameShape
  * The data frame abstract domain as product domain of a column names domain, column count domain, and row count domain.
  */
 export class DataFrameDomain extends ProductDomain<AbstractDataFrameShape> {
-	constructor(value: AbstractDataFrameShape, maxColNames?: number) {
+	constructor(value: AbstractDataFrameShape, maxColNames?: SetRangeLimit | number) {
 		super({
-			colnames: new SetUpperBoundDomain(value.colnames.value, maxColNames ?? value.colnames.limit),
+			colnames: new SetRangeDomain(value.colnames.value, maxColNames ?? value.colnames.limit),
 			cols:     new PosIntervalDomain(value.cols.value),
 			rows:     new PosIntervalDomain(value.rows.value)
 		});
 	}
 
 	public create(value: AbstractDataFrameShape): this;
 	public create(value: AbstractDataFrameShape): DataFrameDomain {
-		return new DataFrameDomain(value, this.maxColNames);
+		return new DataFrameDomain(value, this.colnames.limit);
 	}
 
 	/**
@@ -53,24 +54,17 @@ export class DataFrameDomain extends ProductDomain<AbstractDataFrameShape> {
 		return this.value.rows;
 	}
 
-	/**
-	 * The maximum number of inferred column names of the column names domain.
-	 */
-	public get maxColNames(): number {
-		return this.value.colnames.limit;
-	}
-
 	public static bottom(maxColNames?: number): DataFrameDomain {
 		return new DataFrameDomain({
-			colnames: SetUpperBoundDomain.bottom(maxColNames),
+			colnames: SetRangeDomain.bottom(maxColNames),
 			cols:     PosIntervalDomain.bottom(),
 			rows:     PosIntervalDomain.bottom()
 		});
 	}
 
 	public static top(maxColNames?: number): DataFrameDomain {
 		return new DataFrameDomain({
-			colnames: SetUpperBoundDomain.top(maxColNames),
+			colnames: SetRangeDomain.top(maxColNames),
 			cols:     PosIntervalDomain.top(),
 			rows:     PosIntervalDomain.top()
 		});

src/abstract-interpretation/data-frame/mappers/access-mapper.ts

@@ -3,7 +3,7 @@ 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';
 import type { RAccess, RIndexAccess, RNamedAccess } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-access';
-import { type RFunctionArgument , EmptyArgument } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-function-call';
+import { type RFunctionArgument, EmptyArgument } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-function-call';
 import type { ParentInformation } from '../../../r-bridge/lang-4.x/ast/model/processing/decorate';
 import { RType } from '../../../r-bridge/lang-4.x/ast/model/type';
 import type { DataFrameExpressionInfo, DataFrameOperation } from '../absint-info';

src/abstract-interpretation/data-frame/mappers/arguments.ts

@@ -4,15 +4,15 @@ import { isUseVertex, VertexType } from '../../../dataflow/graph/vertex';
 import { toUnnamedArgument } from '../../../dataflow/internal/process/functions/call/argument/make-argument';
 import type { RNode } from '../../../r-bridge/lang-4.x/ast/model/model';
 import type { RArgument } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-argument';
-import { type RFunctionArgument, type RFunctionCall , EmptyArgument } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-function-call';
+import { type RFunctionArgument, type RFunctionCall, EmptyArgument } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-function-call';
 import type { RSymbol } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-symbol';
 import type { ParentInformation } from '../../../r-bridge/lang-4.x/ast/model/processing/decorate';
+import { visitAst } from '../../../r-bridge/lang-4.x/ast/model/processing/visitor';
 import { RType } from '../../../r-bridge/lang-4.x/ast/model/type';
 import { RNull } from '../../../r-bridge/lang-4.x/convert-values';
 import type { AbstractInterpretationInfo } from '../absint-info';
-import { resolveIdToDataFrameShape } from '../shape-inference';
 import { resolveIdToArgName, resolveIdToArgValue, unquoteArgument } from '../resolve-args';
-import { visitAst } from '../../../r-bridge/lang-4.x/ast/model/processing/visitor';
+import { resolveIdToDataFrameShape } from '../shape-inference';
 
 /** Regular expression representing valid columns names, e.g. for `data.frame` */
 const ColNamesRegex = /^[A-Za-z.][A-Za-z0-9_.]*$/;

src/abstract-interpretation/data-frame/mappers/function-mapper.ts

@@ -1,22 +1,22 @@
-import {  VariableResolve } from '../../../config';
+import { VariableResolve } from '../../../config';
 import { type ResolveInfo } from '../../../dataflow/eval/resolve/alias-tracking';
 import type { DataflowGraph } from '../../../dataflow/graph/graph';
 import { toUnnamedArgument } from '../../../dataflow/internal/process/functions/call/argument/make-argument';
 import { findSource } from '../../../dataflow/internal/process/functions/call/built-in/built-in-source';
+import type { ReadOnlyFlowrAnalyzerContext } from '../../../project/context/flowr-analyzer-context';
 import type { RNode } from '../../../r-bridge/lang-4.x/ast/model/model';
-import { type RFunctionArgument , EmptyArgument } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-function-call';
+import { type RFunctionArgument, EmptyArgument } from '../../../r-bridge/lang-4.x/ast/model/nodes/r-function-call';
 import type { ParentInformation } from '../../../r-bridge/lang-4.x/ast/model/processing/decorate';
 import { RType } from '../../../r-bridge/lang-4.x/ast/model/type';
-import { type RParseRequest , requestFromInput } from '../../../r-bridge/retriever';
+import { type RParseRequest, requestFromInput } from '../../../r-bridge/retriever';
 import { assertUnreachable, isNotUndefined, isUndefined } from '../../../util/assert';
 import { readLineByLineSync } from '../../../util/files';
 import type { DataFrameExpressionInfo, DataFrameOperation } from '../absint-info';
 import { DataFrameDomain } from '../dataframe-domain';
 import { resolveIdToArgName, resolveIdToArgValue, resolveIdToArgValueSymbolName, resolveIdToArgVectorLength, unescapeSpecialChars } from '../resolve-args';
 import type { ConstraintType } from '../semantics';
 import { resolveIdToDataFrameShape } from '../shape-inference';
-import { type FunctionParameterLocation , escapeRegExp, filterValidNames, getArgumentValue, getEffectiveArgs, getFunctionArgument, getFunctionArguments, getUnresolvedSymbolsInExpression, hasCriticalArgument, isDataFrameArgument, isNamedArgument, isRNull } from './arguments';
-import type { ReadOnlyFlowrAnalyzerContext } from '../../../project/context/flowr-analyzer-context';
+import { type FunctionParameterLocation, escapeRegExp, filterValidNames, getArgumentValue, getEffectiveArgs, getFunctionArgument, getFunctionArguments, getUnresolvedSymbolsInExpression, hasCriticalArgument, isDataFrameArgument, isNamedArgument, isRNull } from './arguments';
 
 /**
  * Represents the different types of data frames in R
@@ -564,7 +564,7 @@ type OtherDataFrameFunctionMapping = OtherDataFrameEntryPoint | OtherDataFrameTr
  * - `args` contains the function call arguments
  * - `params` contains the expected argument location for each parameter of the function
  * - `info` contains the resolve information
- * - `ctx` access to the current flowR analyzer context
+ * - `ctx` contains the current flowR analyzer context
  */
 type DataFrameFunctionMapping<Params extends object> = (
     args: readonly RFunctionArgument<ParentInformation>[],
@@ -1127,20 +1127,20 @@ function mapDataFrameMutate(
 		});
 	}
 
-	if(deletedCols === undefined || deletedCols.length > 0) {
+	if(mutatedCols === undefined || mutatedCols.length > 0 || deletedCols?.length === 0) {
 		result.push({
-			operation: 'removeCols',
+			operation: 'mutateCols',
 			operand:   operand?.info.id,
-			colnames:  deletedCols,
-			options:   { maybe: true }
+			colnames:  mutatedCols
 		});
 		operand = undefined;
 	}
-	if(mutatedCols === undefined || mutatedCols.length > 0 || deletedCols?.length === 0) {
+	if(deletedCols === undefined || deletedCols.length > 0) {
 		result.push({
-			operation: 'mutateCols',
+			operation: 'removeCols',
 			operand:   operand?.info.id,
-			colnames:  mutatedCols
+			colnames:  deletedCols,
+			options:   { maybe: true }
 		});
 		operand = undefined;
 	}
@@ -1381,6 +1381,7 @@ function getRequestFromRead(
 		}
 	}
 	request = request ? ctx.files.resolveRequest(request).r : undefined;
+
 	return { source, request };
 }
 

src/abstract-interpretation/data-frame/resolve-args.ts

@@ -1,4 +1,4 @@
-import { type ResolveInfo , resolveIdToValue } from '../../dataflow/eval/resolve/alias-tracking';
+import { type ResolveInfo, resolveIdToValue } from '../../dataflow/eval/resolve/alias-tracking';
 import type { RArgument } from '../../r-bridge/lang-4.x/ast/model/nodes/r-argument';
 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';