[Analyzer] rda plugin

package.json

@@ -174,6 +174,7 @@
     "@types/command-line-usage": "^5.0.4",
     "@types/commonmark": "^0.27.10",
     "@types/dagre": "^0.7.53",
+    "@types/lzma-native": "^4.0.4",
     "@types/n-readlines": "^1.0.6",
     "@types/n3": "^1.26.0",
     "@types/object-hash": "^3.0.6",
@@ -200,6 +201,7 @@
     "@eagleoutice/tree-sitter-r": "^1.1.2",
     "@jupyterlab/nbformat": "^4.5.0",
     "@xmldom/xmldom": "^0.9.7",
+    "bzip2": "^0.1.1",
     "clipboardy": "^4.0.0",
     "command-line-args": "^6.0.1",
     "command-line-usage": "^7.0.3",
@@ -208,6 +210,8 @@
     "gray-matter": "^4.0.3",
     "joi": "^18.0.1",
     "lz-string": "^1.5.0",
+    "lzma-native": "^8.0.6",
+    "lzma1": "^0.3.0",
     "n-readlines": "^1.0.1",
     "n3": "^1.23.1",
     "object-hash": "^3.0.0",
@@ -222,5 +226,9 @@
     "web-tree-sitter": "^0.24.7",
     "ws": "^8.18.0",
     "xpath-ts2": "^1.4.2"
+  },
+  "main": "vitest.config.js",
+  "directories": {
+    "test": "test"
   }
 }

src/config.ts

@@ -97,6 +97,10 @@
 	 * Whether source calls should be ignored, causing {@link processSourceCall}'s behavior to be skipped
 	 */
 	readonly ignoreSourceCalls: boolean
+	/**
+	 * Whether load calls should be ignored, causing {@link processLoadCall}'s behavior to be skipped
+	 */
+	readonly ignoreLoadCalls:   boolean
 	/** Configure language semantics and how flowR handles them */
 	readonly semantics: {
 		/** Semantics regarding the handling of the environment */
@@ -110,13 +114,13 @@
 			}
 		}
 	}
-    /** Configuration options for the REPL */
-    readonly repl: {
-        /** Whether to show quick stats in the REPL after each evaluation */
-        quickStats:   boolean
-	    /** This instruments the dataflow processors to count how often each processor is called */
-	    dfProcessorHeat: boolean;
-    }
+	/** Configuration options for the REPL */
+	readonly repl: {
+		/** Whether to show quick stats in the REPL after each evaluation */
+		quickStats:   boolean
+		/** This instruments the dataflow processors to count how often each processor is called */
+		dfProcessorHeat: boolean;
+	}
 	readonly project: {
 		/** Whether to resolve unknown paths loaded by the r project disk when trying to source/analyze files */
 		resolveUnknownPathsOnDisk: boolean
@@ -243,6 +247,7 @@
 
 export const defaultConfigOptions: FlowrConfigOptions = {
 	ignoreSourceCalls: false,
+	ignoreLoadCalls:   false,
 	semantics:         {
 		environment: {
 			overwriteBuiltIns: {
@@ -292,6 +297,7 @@
 
 export const flowrConfigFileSchema = Joi.object({
 	ignoreSourceCalls: Joi.boolean().optional().description('Whether source calls should be ignored, causing {@link processSourceCall}\'s behavior to be skipped.'),
+	ignoreLoadCalls:   Joi.boolean().optional().description('Whether load calls should be ignored, causing {@link processLoadCall}\'s behavior to be skipped.'),
 	semantics:         Joi.object({
 		environment: Joi.object({
 			overwriteBuiltIns: Joi.object({
@@ -462,4 +468,4 @@
 
 	log.info(`Using default config ${JSON.stringify(defaultConfigOptions)}`);
 	return defaultConfigOptions;
-}
+}

src/control-flow/semantic-cfg-guided-visitor.ts

@@ -312,6 +312,8 @@
 			case BuiltInProcName.Function:
 			case BuiltInProcName.FunctionDefinition:
 				return this.onDefaultFunctionCall({ call });
+			case BuiltInProcName.Load:
+				return this.onLoadCall({call});
 			default:
 				assertUnreachable(origin);
 		}
@@ -687,4 +689,6 @@
 	 * @protected
 	 */
 	protected onReturnCall(_data: { call: DataflowGraphVertexFunctionCall }) {}
+
+	private onLoadCall(_param: { call: DataflowGraphVertexFunctionCall }) {}
 }

src/dataflow/environments/built-in.ts

@@ -53,6 +53,7 @@
 import { processRegisterHook } from '../internal/process/functions/call/built-in/built-in-register-hook';
 import { processLocal } from '../internal/process/functions/call/built-in/built-in-local';
 import { processS3Dispatch } from '../internal/process/functions/call/built-in/built-in-s-three-dispatch';
+import { processLoadCall } from '../internal/process/functions/call/built-in/built-in-load';
 
 export type BuiltIn = `built-in:${string}`;
 
@@ -224,6 +225,8 @@
 	Library             = 'builtin:library',
 	/** for `list` calls, see {@link processList} */
 	List                = 'builtin:list',
+	/** for 'load' calls see {@link processLoadCall} */
+	Load = 'builtin:load',
 	/** for `local` calls, see {@link processLocal} */
 	Local               = 'builtin:local',
 	/** for the pipe operators, see {@link processPipe} */
@@ -277,6 +280,7 @@
 	[BuiltInProcName.IfThenElse]:         processIfThenElse,
 	[BuiltInProcName.Library]:            processLibrary,
 	[BuiltInProcName.List]:               processList,
+	[BuiltInProcName.Load]:               processLoadCall,
 	[BuiltInProcName.Local]:              processLocal,
 	[BuiltInProcName.Pipe]:               processPipe,
 	[BuiltInProcName.Quote]:              processQuote,
@@ -336,8 +340,8 @@
 				type:      ReferenceType.BuiltInFunction,
 				definedAt: id,
 				cds:       undefined,
-				/* eslint-disable-next-line @typescript-eslint/no-explicit-any,@typescript-eslint/no-unsafe-argument */
+				/* eslint-disable-next-line @typescript-eslint/no-explicit-any */
 				processor: (name, args, rootId, data) => mappedProcessor(name, args, rootId, data, config as any),
 				config,
 				name,
 				nodeId:    id

src/dataflow/environments/default-builtin-config.ts

@@ -220,7 +220,8 @@ export const DefaultBuiltinConfig = [
 			}
 		}, assumePrimitive: true },
 	{ type: 'function', names: ['('],                                          processor: BuiltInProcName.Default,             config: { returnsNthArgument: 0 },                                                     assumePrimitive: true  },
-	{ type: 'function', names: ['load', 'load_all', 'setwd', 'set.seed'],      processor: BuiltInProcName.Default,             config: { hasUnknownSideEffects: true, forceArgs: [true] },                            assumePrimitive: false },
+	{ type: 'function', names: ['load'],      processor: BuiltInProcName.Load,             config: { hasUnknownSideEffects: true, forceArgs: [true] },                            assumePrimitive: false },
+	{ type: 'function', names: ['load_all', 'setwd', 'set.seed'],      processor: BuiltInProcName.Default,             config: { hasUnknownSideEffects: true, forceArgs: [true] },                            assumePrimitive: false },
 	{ type: 'function', names: ['body', 'formals', 'environment'],             processor: BuiltInProcName.Default,             config: { hasUnknownSideEffects: true, forceArgs: [true] },                            assumePrimitive: true },
 	{ type:      'function',
 		names:     ['.Call', '.External', '.C', '.Fortran'],

src/dataflow/info.ts

@@ -22,6 +22,8 @@ export interface ControlDependency {
 	readonly when?:        boolean
 	/** whether this control dependency was created due to iteration (e.g., a loop) */
 	readonly byIteration?: boolean
+	/** the filepath that caused this dependency (e.g., for load() calls where the file must exist) */
+	readonly file?:        string
 }
 
 /**