@eagleoutice/flowr 2.10.3 → 2.10.5

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eagleoutice/flowr",
-  "version": "2.10.3",
+  "version": "2.10.5",
   "description": "Static Dataflow Analyzer and Program Slicer for the R Programming Language",
   "types": "dist/src/index.d.ts",
   "repository": {
@@ -167,10 +167,10 @@
   "devDependencies": {
     "@commitlint/cli": "^20.5.0",
     "@commitlint/config-angular": "^20.5.0",
-    "@eagleoutice/eslint-config-flowr": "^1.0.36",
+    "@eagleoutice/eslint-config-flowr": "^1.0.40",
     "@eslint/eslintrc": "^3.3.3",
     "@eslint/js": "^9.39.2",
-    "@j-ulrich/release-it-regex-bumper": "^5.3.0",
+    "@j-ulrich/release-it-regex-bumper": "^5.4.0",
     "@types/command-line-args": "^5.2.3",
     "@types/command-line-usage": "^5.0.4",
     "@types/commonmark": "^0.27.10",
@@ -188,7 +188,7 @@
     "eslint": "^9.39.2",
     "license-checker-rseidelsohn": "^4.4.2",
     "npm-run-all": "^4.1.5",
-    "release-it": "^19.2.3",
+    "release-it": "^20.0.0",
     "ts-node": "^10.9.2",
     "typedoc": "^0.28.17",
     "typedoc-plugin-missing-exports": "^4.1.2",

package/project/flowr-analyzer-builder.d.ts

@@ -34,11 +34,12 @@ export declare class FlowrAnalyzerBuilder {
     private parser?;
     private input?;
     private readonly plugins;
+    private readonly withDefaultPlugins;
     /**
      * Creates a new builder for the {@link FlowrAnalyzer}.
-     * By default, the standard set of plugins as returned by {@link FlowrAnalyzerPluginDefaults} are registered.
+     * By default, the standard set of plugins as returned by {@link FlowrConfig#defaultPlugins} are registered.
      * @param withDefaultPlugins - Whether to register the default plugins upon creation. Default is `true`.
-     * @see {@link FlowrAnalyzerPluginDefaults} - for the default plugin set.
+     * @see {@link FlowrDefaultPlugins} - for the default plugin set.
      * @see {@link FlowrAnalyzerBuilder#registerPlugins} - to add more plugins.
      * @see {@link FlowrAnalyzerBuilder#unregisterPlugins} - to remove plugins.
      */
@@ -53,6 +54,8 @@ export declare class FlowrAnalyzerBuilder {
     amendConfig(func: (config: DeepWritable<FlowrConfig>) => FlowrConfig | void): this;
     /**
      * Overwrite the configuration used by the resulting analyzer.
+     * This also unloads all default plugins and reloads them as set in the new config
+     * if the withDefaultPlugins flag was set in the constructor
      * @param config - The new configuration.
      */
     setConfig(config: FlowrConfig): this;
@@ -78,7 +81,7 @@ export declare class FlowrAnalyzerBuilder {
     setInput(input: Omit<NormalizeRequiredInput, 'context'>): this;
     /**
      * Register one or multiple additional plugins.
-     * For the default plugin set, please refer to {@link FlowrAnalyzerPluginDefaults}, they can be registered
+     * For the default plugin set, please refer to {@link FlowrDefaultPlugins}, they can be registered
      * by passing `true` to the {@link FlowrAnalyzerBuilder} constructor.
      * @param plugin - One or multiple plugins to register.
      * @see {@link FlowrAnalyzerBuilder#unregisterPlugins} to remove plugins.

package/project/flowr-analyzer-builder.js

@@ -7,7 +7,6 @@ const engines_1 = require("../engines");
 const assert_1 = require("../util/assert");
 const flowr_analyzer_context_1 = require("./context/flowr-analyzer-context");
 const flowr_analyzer_cache_1 = require("./cache/flowr-analyzer-cache");
-const flowr_analyzer_plugin_defaults_1 = require("./plugins/flowr-analyzer-plugin-defaults");
 const plugin_registry_1 = require("./plugins/plugin-registry");
 /**
  * Builder for the {@link FlowrAnalyzer}, use it to configure all analysis aspects before creating the analyzer instance
@@ -37,17 +36,19 @@ class FlowrAnalyzerBuilder {
     parser;
     input;
     plugins = new Map();
+    withDefaultPlugins;
     /**
      * Creates a new builder for the {@link FlowrAnalyzer}.
-     * By default, the standard set of plugins as returned by {@link FlowrAnalyzerPluginDefaults} are registered.
+     * By default, the standard set of plugins as returned by {@link FlowrConfig#defaultPlugins} are registered.
      * @param withDefaultPlugins - Whether to register the default plugins upon creation. Default is `true`.
-     * @see {@link FlowrAnalyzerPluginDefaults} - for the default plugin set.
+     * @see {@link FlowrDefaultPlugins} - for the default plugin set.
      * @see {@link FlowrAnalyzerBuilder#registerPlugins} - to add more plugins.
      * @see {@link FlowrAnalyzerBuilder#unregisterPlugins} - to remove plugins.
      */
     constructor(withDefaultPlugins = true) {
+        this.withDefaultPlugins = withDefaultPlugins;
         if (withDefaultPlugins) {
-            this.registerPlugins(...(0, flowr_analyzer_plugin_defaults_1.FlowrAnalyzerPluginDefaults)());
+            this.registerPlugins(...this.flowrConfig.defaultPlugins);
         }
     }
     /**
@@ -64,9 +65,15 @@ class FlowrAnalyzerBuilder {
     }
     /**
      * Overwrite the configuration used by the resulting analyzer.
+     * This also unloads all default plugins and reloads them as set in the new config
+     * if the withDefaultPlugins flag was set in the constructor
      * @param config - The new configuration.
      */
     setConfig(config) {
+        if (this.withDefaultPlugins) {
+            this.unregisterPlugins(...this.flowrConfig.defaultPlugins.map(p => Array.isArray(p) ? p[0] : p));
+            this.registerPlugins(...config.defaultPlugins);
+        }
         this.flowrConfig = config;
         return this;
     }
@@ -104,7 +111,7 @@ class FlowrAnalyzerBuilder {
     }
     /**
      * Register one or multiple additional plugins.
-     * For the default plugin set, please refer to {@link FlowrAnalyzerPluginDefaults}, they can be registered
+     * For the default plugin set, please refer to {@link FlowrDefaultPlugins}, they can be registered
      * by passing `true` to the {@link FlowrAnalyzerBuilder} constructor.
      * @param plugin - One or multiple plugins to register.
      * @see {@link FlowrAnalyzerBuilder#unregisterPlugins} to remove plugins.

package/project/plugins/file-plugins/files/flowr-rmarkdown-file.d.ts

@@ -3,7 +3,7 @@ import { FlowrFile } from '../../../context/flowr-file';
 import { type Node } from 'commonmark';
 /**
  * This decorates a text file and parses its contents as a R Markdown file.
- * Finnaly, it provides access to the single cells, and all cells fused together as one R file.
+ * Finally, it provides access to the single cells, and all cells fused together as one R file.
  */
 export declare class FlowrRMarkdownFile extends FlowrFile<string> {
     private data?;
@@ -24,8 +24,9 @@ export declare class FlowrRMarkdownFile extends FlowrFile<string> {
     protected loadContent(): string;
     static from(file: FlowrFileProvider<string> | FlowrRMarkdownFile): FlowrRMarkdownFile;
 }
+export type CodeBlockOptions = Map<string, string>;
 export interface CodeBlock {
-    options: string;
+    options: CodeBlockOptions;
     code: string;
 }
 export type CodeBlockEx = CodeBlock & {
@@ -59,4 +60,4 @@ export declare function restoreBlocksWithoutMd(blocks: CodeBlockEx[], totalLines
 /**
  * Parses the options of an R code block from its header and content
  */
-export declare function parseCodeBlockOptions(header: string, content: string): string;
+export declare function parseCodeBlockOptions(header: string, content: string): CodeBlockOptions;

package/project/plugins/file-plugins/files/flowr-rmarkdown-file.js

@@ -15,7 +15,7 @@ const gray_matter_1 = __importDefault(require("gray-matter"));
 const log_1 = require("../../../../util/log");
 /**
  * This decorates a text file and parses its contents as a R Markdown file.
- * Finnaly, it provides access to the single cells, and all cells fused together as one R file.
+ * Finally, it provides access to the single cells, and all cells fused together as one R file.
  */
 class FlowrRMarkdownFile extends flowr_file_1.FlowrFile {
     data;
@@ -78,9 +78,14 @@ function parseRMarkdownFile(raw) {
         if (!isRCodeBlock(node)) {
             continue;
         }
+        const options = parseCodeBlockOptions(node.info, node.literal);
+        const engineOpt = options.get('engine');
+        if (engineOpt !== undefined && engineOpt.trim().toLowerCase() !== 'r') {
+            continue;
+        }
         blocks.push({
             code: node.literal,
-            options: parseCodeBlockOptions(node.info, node.literal),
+            options: options,
             startpos: { line: node.sourcepos[0][0] + 1, col: 0 }
         });
     }
@@ -91,6 +96,7 @@ function parseRMarkdownFile(raw) {
         options: frontmatter?.data ?? {}
     };
 }
+// We need the [\s,] part, otherwise {rust} would also match
 const RTagRegex = /{[rR](?:[\s,][^}]*)?}/;
 /**
  * Checks whether a CommonMark node is an R code block
@@ -123,6 +129,7 @@ function restoreBlocksWithoutMd(blocks, totalLines) {
     goToLine(totalLines + 1);
     return output;
 }
+const OptionsRegex = /([\w_.-]*)\s*[:=]\s*["']?([^,"']*)/g;
 /**
  * Parses the options of an R code block from its header and content
  */
@@ -135,9 +142,15 @@ function parseCodeBlockOptions(header, content) {
         if (!line.trim().startsWith('#|')) {
             break;
         }
-        const opt = line.substring(3);
+        const opt = line.substring(2).trim();
         opts += opts.length === 0 ? opt : `, ${opt}`;
     }
-    return opts;
+    const parsedOptions = new Map();
+    for (const match of opts.matchAll(OptionsRegex)) {
+        if (match[1] && match[2] !== undefined) { // key must not be empty, but value can be empty string for example
+            parsedOptions.set(match[1], match[2]);
+        }
+    }
+    return parsedOptions;
 }
 //# sourceMappingURL=flowr-rmarkdown-file.js.map

package/project/plugins/flowr-analyzer-plugin.d.ts

@@ -73,7 +73,7 @@ export interface FlowrAnalyzerPluginInterface<In = unknown, Out = In> {
  * For example, if you want to create a plugin that determines the loading order of files, extend {@link FlowrAnalyzerLoadingOrderPlugin} instead.
  * These classes also provide sensible overrides of {@link FlowrAnalyzerPlugin.defaultPlugin} to be used when no plugin of this type is registered or triggered.
  *
- * For a collection of default plugins, see {@link FlowrAnalyzerPluginDefaults}.
+ * For a collection of default plugins, see {@link FlowrDefaultPlugins}.
  */
 export declare abstract class FlowrAnalyzerPlugin<In = unknown, Out extends AsyncOrSync<unknown> = In> implements FlowrAnalyzerPluginInterface<In, Out> {
     abstract readonly name: string;

package/project/plugins/flowr-analyzer-plugin.js

@@ -53,7 +53,7 @@ const generalPluginLog = log_1.log.getSubLogger({ name: 'plugins' });
  * For example, if you want to create a plugin that determines the loading order of files, extend {@link FlowrAnalyzerLoadingOrderPlugin} instead.
  * These classes also provide sensible overrides of {@link FlowrAnalyzerPlugin.defaultPlugin} to be used when no plugin of this type is registered or triggered.
  *
- * For a collection of default plugins, see {@link FlowrAnalyzerPluginDefaults}.
+ * For a collection of default plugins, see {@link FlowrDefaultPlugins}.
  */
 class FlowrAnalyzerPlugin {
     /**

package/queries/catalog/call-context-query/call-context-query-executor.js

@@ -77,14 +77,14 @@ function promoteQueryCallNames(queries) {
                     ...q.fileFilter,
                     filter: promoteCallName(q.fileFilter.filter)
                 },
-                linkTo: Array.isArray(q.linkTo) ? q.linkTo.map(l => ({
+                linkTo: q.linkTo ? Array.isArray(q.linkTo) ? q.linkTo.map(l => ({
                     ...l,
                     callName: promoteCallName(l.callName)
                 })) : {
                     ...q.linkTo,
                     /* we have to add another promotion layer whenever we add something without this call name */
                     callName: promoteCallName(q.linkTo.callName)
-                }
+                } : undefined
             };
         }
         else {

package/queries/catalog/call-context-query/call-context-query-format.d.ts

@@ -88,7 +88,7 @@ export type LinkTo<CallName extends CallNameTypes = CallNameTypes, AttachLinkInf
     attachLinkInfo?: AttachLinkInfo;
 };
 export interface SubCallContextQueryFormat<CallName extends CallNameTypes = CallNameTypes, AttachLinkInfo = NoInfo> extends DefaultCallContextQueryFormat<CallName> {
-    readonly linkTo: LinkTo<CallName, AttachLinkInfo> | LinkTo<CallName, AttachLinkInfo>[];
+    readonly linkTo?: LinkTo<CallName, AttachLinkInfo> | LinkTo<CallName, AttachLinkInfo>[];
 }
 export interface CallContextQuerySubKindResult {
     /** The id of the call vertex identified within the supplied dataflow graph */

package/queries/catalog/call-context-query/call-context-query-format.js

@@ -29,8 +29,7 @@ exports.CallContextQueryDefinition = {
     executor: call_context_query_executor_1.executeCallContextQueries,
     asciiSummarizer: async (formatter, analyzer, queryResults, result) => {
         const out = queryResults;
-        result.push(`Query: ${(0, ansi_1.bold)('call-context', formatter)} (${(0, time_1.printAsMs)(out['.meta'].timing, 0)})`);
-        result.push((0, query_print_1.asciiCallContext)(formatter, out, (await analyzer.normalize()).idMap));
+        result.push(`Query: ${(0, ansi_1.bold)('call-context', formatter)} (${(0, time_1.printAsMs)(out['.meta'].timing, 0)})`, (0, query_print_1.asciiCallContext)(formatter, out, (await analyzer.normalize()).idMap));
         return true;
     },
     schema: joi_1.default.object({

package/queries/catalog/dependencies-query/function-info/read-functions.js

@@ -108,5 +108,11 @@ exports.ReadFunctions = [
     { package: 'rpolars', name: 'pl_scan_ipc', argIdx: 0, argName: 'source', resolveValue: true, ignoreIf: 'arg-missing' },
     { package: 'rpolars', name: 'pl_scan_ndjson', argIdx: 0, argName: 'source', resolveValue: true, ignoreIf: 'arg-missing' },
     { package: 'rpolars', name: 'pl_scan_parquet', argIdx: 0, argName: 'source', resolveValue: true, ignoreIf: 'arg-missing' },
+    { package: 'rio', name: 'import', argIdx: 0, argName: 'file', resolveValue: true },
+    { package: 'rio', name: 'import_list', argIdx: 0, argName: 'file', resolveValue: true },
+    { package: 'openxlsx', name: 'read.xlsx', argIdx: 0, argName: 'file', resolveValue: true },
+    { package: 'openxlsx', name: 'loadWorkbook', argIdx: 0, argName: 'file', resolveValue: true },
+    { package: 'readODS', name: 'read_ods', argIdx: 0, argName: 'path', resolveValue: true },
+    { package: 'vroom', name: 'vroom', argIdx: 0, argName: 'file', resolveValue: true },
 ];
 //# sourceMappingURL=read-functions.js.map

package/queries/catalog/dependencies-query/function-info/write-functions.js

@@ -115,6 +115,13 @@ exports.WriteFunctions = [
     { package: 'rpolars', name: 'write_csv', argIdx: 0, argName: 'file', resolveValue: true, ignoreIf: 'arg-missing' },
     { package: 'rpolars', name: 'write_ndjson', argIdx: 0, argName: 'file', resolveValue: true, ignoreIf: 'arg-missing' },
     { package: 'rpolars', name: 'write_parquet', argIdx: 0, argName: 'file', resolveValue: true, ignoreIf: 'arg-missing' },
+    { package: 'data.table', name: 'fwrite', argIdx: 1, argName: 'file', resolveValue: true },
+    { package: 'writexl', name: 'write_xlsx', argIdx: 1, argName: 'path', resolveValue: true },
+    { package: 'openxlsx', name: 'write.xlsx', argIdx: 1, argName: 'file', resolveValue: true },
+    { package: 'vroom', name: 'vroom_write', argIdx: 1, argName: 'file', resolveValue: true },
+    { package: 'vroom', name: 'vroom_write_lines', argIdx: 1, argName: 'file', resolveValue: true },
+    { package: 'rio', name: 'export', argIdx: 1, argName: 'file', resolveValue: true },
+    { package: 'rio', name: 'export_list', argIdx: 1, argName: 'file', resolveValue: true },
     { package: 'magick', name: 'image_write', argIdx: 1, argName: 'path', resolveValue: true, ignoreIf: 'arg-missing' },
 ];
 //# sourceMappingURL=write-functions.js.map

package/queries/catalog/input-sources-query/input-source-functions.d.ts

@@ -0,0 +1,6 @@
+import type { Identifier } from '../../../dataflow/environments/identifier';
+export declare const PureFunctions: Identifier[];
+export declare const SystemFunctions: Identifier[];
+export declare const FfiFunctions: Identifier[];
+export declare const LangFunctions: Identifier[];
+export declare const OptionsFunctions: Identifier[];

package/queries/catalog/input-sources-query/input-source-functions.js

@@ -0,0 +1,50 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.OptionsFunctions = exports.LangFunctions = exports.FfiFunctions = exports.SystemFunctions = exports.PureFunctions = void 0;
+exports.PureFunctions = [
+    'paste', 'paste0', 'parse', '+', '-', '*',
+    '/', '^', '%%', '%/%', '&', '|', '!', '&&', '||',
+    '<', '>', '<=', '>=', '==', '!=', ':',
+    'abs', 'sign', 'sqrt', 'exp', 'log', 'log10', 'log2',
+    'sin', 'cos', 'tan', 'asin', 'acos', 'atan',
+    'length', 'nchar', 'dim', 'nrow', 'ncol',
+    'c', 'list', 'data.frame',
+    'ifelse', 'switch', 'factor', 'as.factor',
+    'round', 'floor', 'ceiling', 'trunc',
+    'substr', 'substring', 'strsplit',
+    'min', 'max', 'range', 'sum', 'prod', 'mean', 'median', 'var', 'sd',
+    'head', 'tail', 'seq', 'rep',
+    'apply', 'lapply', 'sapply', 'vapply', 'tapply',
+    'matrix', 'array',
+    'rownames', 'colnames',
+    'list.files', 'tolower', 'toupper', 'printf',
+    '<-', '->', '=', '<<-', '->>', 'assign', 'get',
+    '[', '[[', '$', 'length<-', 'dim<-', 'names<-', 'colnames<-', 'rownames<-',
+    'as.character', 'as.numeric', 'as.logical', 'as.raw', 'as.list', 'as.data.frame', 'as.matrix', 'as.array',
+    'identity', 'invisible', 'return', 'force', 'missing',
+    'print', 'cat', 'message', 'warning', 'stop',
+    'format', 'sprintf', 'formatC',
+    'is.na', 'is.null', 'is.numeric', 'is.character',
+    'which', 'match', 'order', 'sort', 'unique', 'duplicated', 'na.omit',
+    'grep', 'grepl', 'sub', 'gsub', 'regexpr', 'gregexpr', 'regexec', 'regmatches',
+    'as.integer', 'as.double', 'as.complex',
+    'trimws', 'seq_len', 'seq_along', 'rep.int',
+    'pmin', 'pmax', 'cumsum', 'cumprod', 'cummax', 'cummin', 'diff', 'signif',
+    'table', 'prop.table', 'xtabs',
+    'rbind', 'cbind', 't', 'crossprod', 'tcrossprod',
+    'colSums', 'rowSums', 'colMeans', 'rowMeans',
+    'solve', 'det', 'eigen',
+    'is.factor', 'is.logical', 'is.vector', 'is.matrix', 'is.data.frame',
+];
+exports.SystemFunctions = ['system', 'system2', 'pipe', 'shell', 'shell.exec'];
+exports.FfiFunctions = ['.C', '.Call', '.Fortran', '.External', 'dyn.load', 'sourceCpp', 'getNativeSymbolInfo'];
+exports.LangFunctions = [
+    'substitute', 'quote', 'enquote', 'bquote',
+    'call', 'as.call', 'expression', 'as.expression', // 'str2lang', 'str2expression',
+    'as.name', 'as.symbol', 'alist', 'as.language', 'evalq',
+    'expr', 'exprs', 'enexpr', 'enexprs', 'inject',
+    'quo', 'quos', 'enquo', 'enquos', 'enquo0', 'enquos0',
+    'sym', 'syms', 'ensym', 'ensyms'
+];
+exports.OptionsFunctions = ['options', 'getOption', 'Sys.getenv'];
+//# sourceMappingURL=input-source-functions.js.map

package/queries/catalog/input-sources-query/input-sources-query-executor.d.ts

@@ -1,5 +1,5 @@
 import type { BasicQueryData } from '../../base-query-format';
-import type { InputSourcesQuery, InputSourcesQueryResult } from './input-sources-query-format';
+import { type InputSourcesQuery, type InputSourcesQueryResult } from './input-sources-query-format';
 /**
  * Execute an input sources query
  */

package/queries/catalog/input-sources-query/input-sources-query-executor.js

@@ -1,15 +1,15 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.executeInputSourcesQuery = executeInputSourcesQuery;
+const input_sources_query_format_1 = require("./input-sources-query-format");
 const log_1 = require("../../../util/log");
 const parse_1 = require("../../../slicing/criterion/parse");
 const r_function_definition_1 = require("../../../r-bridge/lang-4.x/ast/model/nodes/r-function-definition");
 const model_1 = require("../../../r-bridge/lang-4.x/ast/model/model");
 const df_helper_1 = require("../../../dataflow/graph/df-helper");
 const simple_input_classifier_1 = require("./simple-input-classifier");
-const network_functions_1 = require("../../../linter/rules/network-functions");
-const seeded_randomness_1 = require("../../../linter/rules/seeded-randomness");
-const read_functions_1 = require("../dependencies-query/function-info/read-functions");
+const flowr_search_executor_1 = require("../../../search/flowr-search-executor");
+const record_1 = require("../../../util/record");
 /**
  * Execute an input sources query
  */
@@ -18,6 +18,7 @@ async function executeInputSourcesQuery({ analyzer }, queries) {
     const results = {};
     const nast = await analyzer.normalize();
     const df = await analyzer.dataflow();
+    const defaultConfig = await resolveSearches(analyzer, input_sources_query_format_1.DefaultInputClassifierConfig);
     for (const query of queries) {
         const key = query.criterion;
         if (results[key]) {
@@ -27,34 +28,8 @@ async function executeInputSourcesQuery({ analyzer }, queries) {
         const provenanceNode = nast.idMap.get(criterionId);
         const fdef = r_function_definition_1.RFunctionDefinition.rootFunctionDefinition(provenanceNode, nast.idMap);
         const provenance = df_helper_1.Dataflow.provenanceGraph(criterionId, df.graph, fdef ? model_1.RNode.collectAllIds(fdef) : undefined);
-        results[key] = (0, simple_input_classifier_1.classifyInput)(criterionId, provenance, {
-            networkFns: query.config?.networkFns ?? network_functions_1.NETWORK_FUNCTIONS.info.defaultConfig.fns,
-            randomFns: query.config?.randomFns ?? seeded_randomness_1.SEEDED_RANDOMNESS.info.defaultConfig.randomnessConsumers,
-            pureFns: query.config?.pureFns ?? ['paste', 'paste0', 'parse', '+', '-', '*',
-                '/', '^', '%%', '%/%', '&', '|', '!', '&&', '||',
-                '<', '>', '<=', '>=', '==', '!=', ':',
-                'abs', 'sign', 'sqrt', 'exp', 'log', 'log10', 'log2',
-                'sin', 'cos', 'tan', 'asin', 'acos', 'atan',
-                'length', 'nchar', 'dim', 'nrow', 'ncol',
-                'c', 'list', 'data.frame',
-                'ifelse', 'switch', 'factor', 'as.factor',
-                'round', 'floor', 'ceiling', 'trunc',
-                'substr', 'substring', 'strsplit',
-                'min', 'max', 'range', 'sum', 'prod', 'mean', 'median', 'var', 'sd',
-                'head', 'tail', 'seq', 'rep',
-                'apply', 'lapply', 'sapply', 'vapply', 'tapply',
-                'matrix', 'array', 'substitute', 'quote', 'bquote', 'enquote', 'enexpr', 'enexprs', 'enquo', 'enquos',
-                'expression', 'call', 'as.call', 'as.expression',
-                'rownames', 'colnames',
-                'list.files', 'tolower', 'toupper', 'printf',
-                '<-', '->', '=', '<<-', '->>', 'assign', 'get',
-                '[', '[[', '$', 'length<-', 'dim<-', 'names<-', 'colnames<-', 'rownames<-',
-                'as.character', 'as.numeric', 'as.logical', 'as.list', 'as.data.frame', 'as.matrix', 'as.array',
-                'identity', 'invisible', 'return', 'force', 'missing',
-                'print', 'cat', 'message', 'warning', 'stop'
-            ],
-            readFileFns: query.config?.readFileFns ?? read_functions_1.ReadFunctions.map(f => f.name)
-        });
+        const config = { ...defaultConfig, ...(await resolveSearches(analyzer, query?.config ?? {})) };
+        results[key] = (0, simple_input_classifier_1.classifyInput)(criterionId, provenance, config, df.graph);
     }
     return {
         '.meta': {
@@ -63,4 +38,17 @@ async function executeInputSourcesQuery({ analyzer }, queries) {
         results
     };
 }
+async function resolveSearches(analyzer, config) {
+    const result = {};
+    for (const [key, value] of record_1.Record.entries(config)) {
+        if (value === undefined || Array.isArray(value)) {
+            result[key] = value;
+        }
+        else {
+            const searchResult = await (0, flowr_search_executor_1.runSearch)(value, analyzer);
+            result[key] = searchResult.getElements().map(element => element.node.info.id);
+        }
+    }
+    return result;
+}
 //# sourceMappingURL=input-sources-query-executor.js.map

package/queries/catalog/input-sources-query/input-sources-query-format.d.ts

@@ -3,7 +3,7 @@ import type { SlicingCriterion } from '../../../slicing/criterion/parse';
 import type { ParsedQueryLine } from '../../query';
 import Joi from 'joi';
 import type { NodeId } from '../../../r-bridge/lang-4.x/ast/model/processing/node-id';
-import type { InputClassifierConfig, InputSources } from './simple-input-classifier';
+import { type InputClassifierConfig, type InputSources } from './simple-input-classifier';
 import type { ReplOutput } from '../../../cli/repl/commands/repl-main';
 import type { FlowrConfig } from '../../../config';
 import { executeInputSourcesQuery } from './input-sources-query-executor';
@@ -21,6 +21,7 @@ export interface InputSourcesQuery extends BaseQueryFormat {
     readonly criterion: SlicingCriterion;
     readonly config?: InputSourcesQueryConfig;
 }
+export declare const DefaultInputClassifierConfig: InputClassifierConfig;
 export interface InputSourcesQueryResult extends BaseQueryResult {
     /** For each query key, a list of classified input sources (each with id and all traces) */
     results: Record<string, InputSources>;

package/queries/catalog/input-sources-query/input-sources-query-format.js

@@ -3,13 +3,27 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
     return (mod && mod.__esModule) ? mod : { "default": mod };
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.InputSourcesDefinition = void 0;
+exports.InputSourcesDefinition = exports.DefaultInputClassifierConfig = void 0;
 const ansi_1 = require("../../../util/text/ansi");
 const time_1 = require("../../../util/text/time");
 const joi_1 = __importDefault(require("joi"));
+const simple_input_classifier_1 = require("./simple-input-classifier");
 const slice_query_parser_1 = require("../../../cli/repl/parser/slice-query-parser");
 const input_sources_query_executor_1 = require("./input-sources-query-executor");
 const range_1 = require("../../../util/range");
+const flowr_search_builder_1 = require("../../../search/flowr-search-builder");
+const read_functions_1 = require("../dependencies-query/function-info/read-functions");
+const input_source_functions_1 = require("./input-source-functions");
+exports.DefaultInputClassifierConfig = {
+    [simple_input_classifier_1.InputTraceType.Pure]: input_source_functions_1.PureFunctions,
+    [simple_input_classifier_1.InputType.File]: read_functions_1.ReadFunctions.map(readFunction => readFunction.name),
+    [simple_input_classifier_1.InputType.Network]: flowr_search_builder_1.Q.fromQuery({ type: 'linter', rules: ['network-functions'] }),
+    [simple_input_classifier_1.InputType.Random]: flowr_search_builder_1.Q.fromQuery({ type: 'linter', rules: ['seeded-randomness'] }),
+    [simple_input_classifier_1.InputType.System]: input_source_functions_1.SystemFunctions,
+    [simple_input_classifier_1.InputType.Ffi]: input_source_functions_1.FfiFunctions,
+    [simple_input_classifier_1.InputType.Lang]: input_source_functions_1.LangFunctions,
+    [simple_input_classifier_1.InputType.Options]: input_source_functions_1.OptionsFunctions
+};
 function inputSourcesQueryLineParser(output, line, _config) {
     const criterion = (0, slice_query_parser_1.sliceCriteriaParser)(line[0]);
     if (!criterion || criterion.length !== 1) {
@@ -29,10 +43,11 @@ exports.InputSourcesDefinition = {
         const nast = (await analyzer.normalize()).idMap;
         for (const [key, sources] of Object.entries(out.results)) {
             result.push(`   ╰ Input Sources for ${key}`);
-            for (const { id, trace, type } of sources) {
+            for (const { id, trace, types, value } of sources) {
                 const kNode = nast.get(id);
                 const kLoc = kNode ? range_1.SourceLocation.format(range_1.SourceLocation.fromNode(kNode)) : 'unknown location';
-                result.push(`           ╰ ${kLoc} (id: ${id}), type: ${JSON.stringify(type)}, trace: ${trace}`);
+                const valueStr = value !== undefined ? `, value: ${JSON.stringify(value)}` : '';
+                result.push(`           ╰ ${kLoc} (id: ${id}), type: ${JSON.stringify(types)}, trace: ${trace}${valueStr}`);
             }
         }
         return true;
@@ -42,11 +57,14 @@ exports.InputSourcesDefinition = {
         type: joi_1.default.string().valid('input-sources').required().description('The type of the query.'),
         criterion: joi_1.default.string().required().description('The slicing criterion to use.'),
         config: joi_1.default.object({
-            networkFunctions: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that fetch data from the network.'),
-            randomnessConsumers: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that consume randomness.'),
-            randomnessProducers: joi_1.default.array().items(joi_1.default.object({ type: joi_1.default.string().valid('function', 'assignment'), name: joi_1.default.string().required() })).optional().description('Functions or assignments that produce randomness seeds.'),
-            configurableFunctions: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that read configuration (options/env).'),
-            pureFunctions: joi_1.default.array().items(joi_1.default.string()).optional().description('Deterministic functions that keep constant inputs constant.'),
+            [simple_input_classifier_1.InputTraceType.Pure]: joi_1.default.array().items(joi_1.default.string()).optional().description('Deterministic/pure functions: functions that preserve constantness of their inputs (e.g., arithmetic, parse).'),
+            [simple_input_classifier_1.InputType.File]: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that read from the filesystem and produce data (e.g., read.csv, readRDS).'),
+            [simple_input_classifier_1.InputType.Network]: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that fetch data from the network (e.g., download.file, url connections).'),
+            [simple_input_classifier_1.InputType.Random]: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that produce randomness (e.g., runif, rnorm).'),
+            [simple_input_classifier_1.InputType.System]: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that execute system commands (e.g., system, system2, shell, pipe).'),
+            [simple_input_classifier_1.InputType.Ffi]: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that call native code via the R FFI (.C, .Call, .Fortran, .External, dyn.load).'),
+            [simple_input_classifier_1.InputType.Lang]: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that produce language objects (e.g., substitute, quote, bquote, expression).'),
+            [simple_input_classifier_1.InputType.Options]: joi_1.default.array().items(joi_1.default.string()).optional().description('Functions that access or set global options (e.g., options, getOption).'),
         }).optional()
     }).description('Input Sources query definition'),
     flattenInvolvedNodes: (queryResults) => {