@eagleoutice/flowr 2.1.2 → 2.1.4

package/documentation/doc-util/doc-query.d.ts

@@ -5,8 +5,9 @@ import type { VirtualCompoundConstraint } from '../../queries/virtual-query/comp
 export interface ShowQueryOptions {
     readonly showCode?: boolean;
     readonly collapseResult?: boolean;
+    readonly collapseQuery?: boolean;
 }
-export declare function showQuery<Base extends SupportedQueryTypes, VirtualArguments extends VirtualCompoundConstraint<Base> = VirtualCompoundConstraint<Base>>(shell: RShell, code: string, queries: Queries<Base, VirtualArguments>, { showCode, collapseResult }?: ShowQueryOptions): Promise<string>;
+export declare function showQuery<Base extends SupportedQueryTypes, VirtualArguments extends VirtualCompoundConstraint<Base> = VirtualCompoundConstraint<Base>>(shell: RShell, code: string, queries: Queries<Base, VirtualArguments>, { showCode, collapseResult, collapseQuery }?: ShowQueryOptions): Promise<string>;
 export interface QueryDocumentation {
     readonly name: string;
     readonly type: 'virtual' | 'active';
@@ -20,5 +21,6 @@ export declare const RegisteredQueries: {
     virtual: Map<string, QueryDocumentation>;
 };
 export declare function registerQueryDocumentation(query: SupportedQueryTypes | SupportedVirtualQueryTypes, doc: QueryDocumentation): void;
+export declare function linkToQueryOfName(id: SupportedQueryTypes | SupportedVirtualQueryTypes): string;
 export declare function tocForQueryType(type: 'active' | 'virtual'): string;
 export declare function explainQueries(shell: RShell, type: 'active' | 'virtual'): Promise<string>;

package/documentation/doc-util/doc-query.js

@@ -3,6 +3,7 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.RegisteredQueries = void 0;
 exports.showQuery = showQuery;
 exports.registerQueryDocumentation = registerQueryDocumentation;
+exports.linkToQueryOfName = linkToQueryOfName;
 exports.tocForQueryType = tocForQueryType;
 exports.explainQueries = explainQueries;
 const query_1 = require("../../queries/query");
@@ -11,12 +12,12 @@ const default_pipelines_1 = require("../../core/steps/pipeline/default-pipelines
 const retriever_1 = require("../../r-bridge/retriever");
 const json_1 = require("../../util/json");
 const ansi_1 = require("../../util/ansi");
-const repl_query_1 = require("../../cli/repl/commands/repl-query");
 const doc_files_1 = require("./doc-files");
 const doc_dfg_1 = require("./doc-dfg");
 const doc_code_1 = require("./doc-code");
 const time_1 = require("../../util/time");
-async function showQuery(shell, code, queries, { showCode, collapseResult } = {}) {
+const query_print_1 = require("../../queries/query-print");
+async function showQuery(shell, code, queries, { showCode, collapseResult, collapseQuery } = {}) {
     const now = performance.now();
     const analysis = await new pipeline_executor_1.PipelineExecutor(default_pipelines_1.DEFAULT_DATAFLOW_PIPELINE, {
         shell,
@@ -27,17 +28,16 @@ async function showQuery(shell, code, queries, { showCode, collapseResult } = {}
     const metaInfo = `
 The analysis required _${(0, time_1.printAsMs)(duration)}_ (including parsing and normalization and the query) within the generation environment.
 	`.trim();
+    const str = JSON.stringify(queries, json_1.jsonReplacer, collapseQuery ? ' ' : 2);
     return `
 
-\`\`\`json
-${JSON.stringify(queries, json_1.jsonReplacer, 2)}
-\`\`\`
+${(0, doc_code_1.codeBlock)('json', collapseQuery ? str.split('\n').join(' ').replace(/([{[])\s{2,}/g, '$1 ').replace(/\s{2,}([\]}])/g, ' $1') : str)}
 
 ${collapseResult ? ' <details> <summary style="color:gray">Show Results</summary>' : ''}
 
 _Results (prettified and summarized):_
 
-${(0, repl_query_1.asciiSummaryOfQueryResult)(ansi_1.markdownFormatter, duration, results, analysis)}
+${(0, query_print_1.asciiSummaryOfQueryResult)(ansi_1.markdownFormatter, duration, results, analysis)}
 
 <details> <summary style="color:gray">Show Detailed Results as Json</summary>
 
@@ -76,6 +76,13 @@ function registerQueryDocumentation(query, doc) {
 function linkify(name) {
     return name.toLowerCase().replace(/ /g, '-');
 }
+function linkToQueryOfName(id) {
+    const query = exports.RegisteredQueries.active.get(id) ?? exports.RegisteredQueries.virtual.get(id);
+    if (!query) {
+        throw new Error(`Query ${id} not found`);
+    }
+    return `[${query.name}](#${linkify(query.name)})`;
+}
 function tocForQueryType(type) {
     const queries = [...exports.RegisteredQueries[type].entries()].sort(([, { name: a }], [, { name: b }]) => a.localeCompare(b));
     const result = [];
@@ -101,11 +108,11 @@ Responsible for the execution of the ${name} query is \`${functionName}\` in ${(
 `;
 }
 async function explainQueries(shell, type) {
-    const queries = exports.RegisteredQueries[type];
+    const queries = [...exports.RegisteredQueries[type].entries()].sort(([, { name: a }], [, { name: b }]) => a.localeCompare(b));
     const result = [];
-    for (const doc of queries.values()) {
+    for (const [, doc] of queries) {
         result.push(await explainQuery(shell, doc));
     }
-    return result.join('\n\n\n');
+    return result.join(`\n${'-'.repeat(5)}\n\n`);
 }
 //# sourceMappingURL=doc-query.js.map

package/documentation/doc-util/doc-repl.js

@@ -4,7 +4,7 @@ exports.printReplHelpAsMarkdownTable = printReplHelpAsMarkdownTable;
 exports.documentReplSession = documentReplSession;
 const repl_commands_1 = require("../../cli/repl/commands/repl-commands");
 const doc_cli_option_1 = require("./doc-cli-option");
-const doc_hover_over_1 = require("./doc-hover-over");
+const html_hover_over_1 = require("../../util/html-hover-over");
 const core_1 = require("../../cli/repl/core");
 const ansi_1 = require("../../util/ansi");
 const doc_docker_1 = require("./doc-docker");
@@ -19,7 +19,7 @@ function printHelpForScript(script, starredVersion) {
         return base;
     }
     const aliases = script[1].aliases;
-    return `${base} (alias${aliases.length > 1 ? 'es' : ''}: ${aliases.map(a => '**:' + (0, doc_hover_over_1.textWithTooltip)(a, `Alias of ':${script[0]}'. ${script[1].description}`) + '**').join(', ')}) |`;
+    return `${base} (alias${aliases.length > 1 ? 'es' : ''}: ${aliases.map(a => '**:' + (0, html_hover_over_1.textWithTooltip)(a, `Alias of ':${script[0]}'. ${script[1].description}`) + '**').join(', ')}) |`;
 }
 function printReplHelpAsMarkdownTable() {
     const scriptHelp = [];

package/documentation/print-dataflow-graph-wiki.js

@@ -807,7 +807,8 @@ ${(0, doc_types_1.printHierarchy)({ program: vertexType.program, hierarchy: vert
 Let's start by looking at the properties of the dataflow information object: ${Object.keys(result.dataflow).map(k => `\`${k}\``).join(', ')}.
 
 ${(() => {
-            (0, assert_1.guard)(Object.keys(result.dataflow).length === 7, () => 'Update Dataflow Documentation!');
+            /* this includes the meta field for timing */
+            (0, assert_1.guard)(Object.keys(result.dataflow).length === 8, () => 'Update Dataflow Documentation!');
             return '';
         })()}
 

package/documentation/print-interface-wiki.js

@@ -18,6 +18,7 @@ const ansi_1 = require("../util/ansi");
 const flowr_main_options_1 = require("../cli/flowr-main-options");
 const doc_issue_1 = require("./doc-util/doc-issue");
 const pipeline_executor_1 = require("../core/pipeline-executor");
+const doc_structure_1 = require("./doc-util/doc-structure");
 async function explainServer(shell) {
     (0, doc_data_server_messages_1.documentAllServerMessages)();
     return `
@@ -27,9 +28,13 @@ Additionally, the server is not well guarded against attacks (e.g., you can theo
 
 Every message has to be given in a single line (i.e., without a newline in-between) and end with a newline character. Nevertheless, we will pretty-print example given in the following segments for the ease of reading.
 
-> [!NOTE]
-> The default ${(0, doc_cli_option_1.getCliLongOptionOf)('flowr', 'server', false)} uses a simple [TCP](https://de.wikipedia.org/wiki/Transmission_Control_Protocol)
-> connection. If you want _flowR_ to expose a [WebSocket](https://de.wikipedia.org/wiki/WebSocket) server instead, add the ${(0, doc_cli_option_1.getCliLongOptionOf)('flowr', 'server', false)} flag (i.e., ${(0, doc_cli_option_1.multipleCliOptions)('flowr', 'server', 'ws')}) when starting _flowR_ from the command line.
+${(0, doc_structure_1.block)({
+        type: 'NOTE',
+        content: `
+The default ${(0, doc_cli_option_1.getCliLongOptionOf)('flowr', 'server', false)} uses a simple [TCP](https://de.wikipedia.org/wiki/Transmission_Control_Protocol)
+connection. If you want _flowR_ to expose a [WebSocket](https://de.wikipedia.org/wiki/WebSocket) server instead, add the ${(0, doc_cli_option_1.getCliLongOptionOf)('flowr', 'ws', false)} flag (i.e., ${(0, doc_cli_option_1.multipleCliOptions)('flowr', 'server', 'ws')}) when starting _flowR_ from the command line.
+			`
+    })}
 
 ${await (0, doc_server_message_1.printServerMessages)(shell)}
 

package/documentation/print-query-wiki.js

@@ -6,9 +6,7 @@ const log_1 = require("../../test/functionality/_helper/log");
 const query_1 = require("../queries/query");
 const doc_files_1 = require("./doc-util/doc-files");
 const doc_query_1 = require("./doc-util/doc-query");
-const call_context_query_format_1 = require("../queries/catalog/call-context-query/call-context-query-format");
 const schema_1 = require("../util/schema");
-const query_schema_1 = require("../queries/query-schema");
 const ansi_1 = require("../util/ansi");
 const call_context_query_executor_1 = require("../queries/catalog/call-context-query/call-context-query-executor");
 const compound_query_1 = require("../queries/virtual-query/compound-query");
@@ -21,6 +19,12 @@ const id_map_query_executor_1 = require("../queries/catalog/id-map-query/id-map-
 const normalized_ast_query_executor_1 = require("../queries/catalog/normalized-ast-query/normalized-ast-query-executor");
 const cluster_query_executor_1 = require("../queries/catalog/cluster-query/cluster-query-executor");
 const static_slice_query_executor_1 = require("../queries/catalog/static-slice-query/static-slice-query-executor");
+const lineage_query_executor_1 = require("../queries/catalog/lineage-query/lineage-query-executor");
+const dependencies_query_executor_1 = require("../queries/catalog/dependencies-query/dependencies-query-executor");
+const doc_cli_option_1 = require("./doc-util/doc-cli-option");
+const doc_issue_1 = require("./doc-util/doc-issue");
+const location_map_query_executor_1 = require("../queries/catalog/location-map-query/location-map-query-executor");
+const identify_link_to_last_call_relation_1 = require("../queries/catalog/call-context-query/identify-link-to-last-call-relation");
 (0, doc_query_1.registerQueryDocumentation)('call-context', {
     name: 'Call-Context Query',
     type: 'active',
@@ -53,7 +57,7 @@ ${await (0, doc_query_1.showQuery)(shell, example_query_code_1.exampleQueryCode,
                 callName: '^read_',
                 kind: 'input',
                 subkind: 'csv-file',
-                callTargets: call_context_query_format_1.CallTargets.OnlyGlobal
+                callTargets: identify_link_to_last_call_relation_1.CallTargets.OnlyGlobal
             },
             {
                 type: 'call-context',
@@ -66,7 +70,7 @@ ${await (0, doc_query_1.showQuery)(shell, example_query_code_1.exampleQueryCode,
 
 As you can see, all kinds and subkinds with the same name are grouped together.
 Yet, re-stating common arguments and kinds may be cumbersome (although you can already use clever regex patterns).
-See the [Compound Query](#compound-query) for a way to structure your queries more compactly if you think it gets too verbose. 
+See the ${(0, doc_query_1.linkToQueryOfName)('compound')} for a way to structure your queries more compactly if you think it gets too verbose. 
 
 ${await (async () => {
             const code = `
@@ -98,7 +102,7 @@ This query type does exactly that!
 Using the example code \`${exampleCode}\`, the following query returns the dataflow graph of the code:
 ${await (0, doc_query_1.showQuery)(shell, exampleCode, [{
                 type: 'dataflow'
-            }], { showCode: true })}
+            }], { showCode: true, collapseQuery: true })}
 		`;
     }
 });
@@ -117,7 +121,38 @@ This query type does exactly that!
 Using the example code \`${exampleCode}\`, the following query returns the normalized AST of the code:
 ${await (0, doc_query_1.showQuery)(shell, exampleCode, [{
                 type: 'normalized-ast'
-            }], { showCode: true })}
+            }], { showCode: true, collapseQuery: true })}
+		`;
+    }
+});
+(0, doc_query_1.registerQueryDocumentation)('lineage', {
+    name: 'Lineage Query',
+    type: 'active',
+    shortDescription: 'Returns lineage of a criteria.',
+    functionName: lineage_query_executor_1.executeLineageQuery.name,
+    functionFile: '../queries/catalog/lineage-query/lineage-query-executor.ts',
+    buildExplanation: async (shell) => {
+        const exampleCode = 'x <- 1\nx';
+        return `
+This query calculates the _lineage_ of a given slicing criterion. The lineage traces back all parts that the
+respective variables stems from given the reads, definitions, and returns in the dataflow graph.
+
+To understand this, let's start with a simple example query, to get the lineage of the second use of \`x\` in the following code:
+${(0, doc_code_1.codeBlock)('r', exampleCode)}
+ 
+For this, we use the criterion \`2@x\` (which is the first use of \`x\` in the second line).
+ 
+${await (0, doc_query_1.showQuery)(shell, exampleCode, [{
+                type: 'lineage',
+                criterion: '2@x'
+            }], { showCode: false })}
+
+In this simple scenario, the _lineage_ is equivalent to the slice (and in-fact the complete code). 
+In general the lineage is smaller and makes no executability guarantees. 
+It is just a quick and neither complete nor sound way to get information on where the variable originates from.
+
+This query replaces the old [\`request-lineage\`](${doc_files_1.FlowrWikiBaseRef}/Interface#message-request-lineage) message.
+
 		`;
     }
 });
@@ -144,7 +179,7 @@ ${(0, doc_structure_1.details)('Example <code>' + exampleB + '</code>', await (0
 Using the example code from above, the following query returns all clusters:
 ${await (0, doc_query_1.showQuery)(shell, example_query_code_1.exampleQueryCode, [{
                 type: 'dataflow-cluster'
-            }], { showCode: false })}
+            }], { showCode: false, collapseQuery: true })}
 		`;
     }
 });
@@ -162,7 +197,7 @@ This query provides access to all nodes in the [normalized AST](${doc_files_1.Fl
 Using the example code \`${exampleCode}\`, the following query returns all nodes from the code:
 ${await (0, doc_query_1.showQuery)(shell, exampleCode, [{
                 type: 'id-map'
-            }], { showCode: true })}
+            }], { showCode: true, collapseQuery: true })}
 		`;
     }
 });
@@ -208,10 +243,10 @@ want to resolve to a local definition:
 ${await (0, doc_query_1.showQuery)(shell, example_query_code_1.exampleQueryCode, [{
                 type: 'compound',
                 query: 'call-context',
-                commonArguments: { kind: 'visualize', subkind: 'text', callTargets: call_context_query_format_1.CallTargets.OnlyGlobal },
+                commonArguments: { kind: 'visualize', subkind: 'text', callTargets: identify_link_to_last_call_relation_1.CallTargets.OnlyGlobal },
                 arguments: [
                     { callName: '^mean$' },
-                    { callName: '^print$', callTargets: call_context_query_format_1.CallTargets.OnlyLocal }
+                    { callName: '^print$', callTargets: identify_link_to_last_call_relation_1.CallTargets.OnlyLocal }
                 ]
             }], { showCode: false })}
 
@@ -257,6 +292,85 @@ This query replaces the old [\`request-slice\`](${doc_files_1.FlowrWikiBaseRef}/
 		`;
     }
 });
+(0, doc_query_1.registerQueryDocumentation)('dependencies', {
+    name: 'Dependencies Query',
+    type: 'active',
+    shortDescription: 'Returns all direct dependencies (in- and outputs) of a given R script',
+    functionName: dependencies_query_executor_1.executeDependenciesQuery.name,
+    functionFile: '../queries/catalog/dependencies-query/dependencies-query-executor.ts',
+    buildExplanation: async (shell) => {
+        const exampleCode = 'library(x)';
+        const longerCode = `
+source("sample.R")
+foo <- loadNamespace("bar")
+
+data <- read.csv("data.csv")
+
+#' @importFrom ggplot2 ggplot geom_point aes
+ggplot(data, aes(x=x, y=y)) + geom_point()
+
+better::write.csv(data, "data2.csv")
+print("hello world!")
+		`;
+        return `
+This query extracts all dependencies from an R script, using a combination of a ${(0, doc_query_1.linkToQueryOfName)('call-context')}
+and more advanced tracking in the [Dataflow Graph](${doc_files_1.FlowrWikiBaseRef}/Dataflow%20Graph).  
+
+In other words, if you have a script simply reading: \`${exampleCode}\`, the following query returns the loaded library:
+${await (0, doc_query_1.showQuery)(shell, exampleCode, [{
+                type: 'dependencies'
+            }], { showCode: false, collapseQuery: true })}
+
+Of course, this works for more complicated scripts too. The query offers information on the loaded _libraries_, _sourced_ files, data which is _read_ and data which is _written_.
+For example, consider the following script:
+${(0, doc_code_1.codeBlock)('r', longerCode)}
+The following query returns the dependencies of the script.
+${await (0, doc_query_1.showQuery)(shell, longerCode, [{
+                type: 'dependencies'
+            }], { showCode: false, collapseQuery: true, collapseResult: true })}
+
+Currently the dependency extraction may fail as it is essentially a set of heuristics guessing the dependencies.
+We welcome any feedback on this (consider opening a [new issue](${doc_issue_1.NewIssueUrl})).
+
+In the meantime we offer several properties to overwrite the default behavior (e.g., function names that should be collected)
+
+${await (0, doc_query_1.showQuery)(shell, longerCode, [{
+                type: 'dependencies',
+                ignoreDefaultFunctions: true,
+                libraryFunctions: [{ name: 'print', argIdx: 0, argName: 'library' }],
+                sourceFunctions: [],
+                readFunctions: [],
+                writeFunctions: []
+            }], { showCode: false, collapseQuery: false, collapseResult: true })}
+
+		`;
+    }
+});
+(0, doc_query_1.registerQueryDocumentation)('location-map', {
+    name: 'Location Map Query',
+    type: 'active',
+    shortDescription: 'Returns a simple mapping of ids to their location in the source file',
+    functionName: location_map_query_executor_1.executeLocationMapQuery.name,
+    functionFile: '../queries/catalog/location-map-query/location-map-query-executor.ts',
+    buildExplanation: async (shell) => {
+        const exampleCode = 'x + 1\nx * 2';
+        return `
+A query like the ${(0, doc_query_1.linkToQueryOfName)('id-map')} query can return a really big result, especially for larger scripts.
+If you are not interested in all of the information contained within the full map, you can use the location map query to get a simple mapping of ids to their location in the source file.   
+
+Consider you have the following code:
+
+${(0, doc_code_1.codeBlock)('r', exampleCode)}
+
+The following query then gives you the aforementioned mapping:
+
+${await (0, doc_query_1.showQuery)(shell, exampleCode, [{
+                type: 'location-map'
+            }], { showCode: false, collapseQuery: true })}
+
+		`;
+    }
+});
 async function getText(shell) {
     const rversion = (await shell.usedRVersion())?.format() ?? 'unknown';
     return `${(0, doc_auto_gen_1.autoGenHeader)({ filename: module.filename, purpose: 'query API', rVersion: rversion })}
@@ -264,13 +378,22 @@ async function getText(shell) {
 This page briefly summarizes flowR's query API, represented by the ${query_1.executeQueries.name} function in ${(0, doc_files_1.getFilePathMd)('../queries/query.ts')}.
 Please see the [Interface](${doc_files_1.FlowrWikiBaseRef}/Interface) wiki page for more information on how to access this API.
 
+${(0, doc_structure_1.block)({
+        type: 'NOTE',
+        content: `
+There are many ways to query a dataflow graph created by flowR.
+For example, you can use the [\`request-query\`](${doc_files_1.FlowrWikiBaseRef}/Interface#message-request-query) message
+with a running flowR server, or the ${(0, doc_cli_option_1.getReplCommand)('query')} command in the flowR [REPL](${doc_files_1.FlowrWikiBaseRef}/Interface#repl).	
+			`.trim()
+    })}
+
 ## The Query Format
 
 Queries are JSON arrays of query objects, each of which uses a \`type\` property to specify the query type.
 In general, we separate two types of queries:
 
-1. **Active Queries**: Are exactly what you would expect from a query (e.g., the [Call-Context Query](#call-context-query)). They fetch information from the dataflow graph.
-2. **Virtual Queries**: Are used to structure your queries (e.g., the [Compound Query](#compound-query)). 
+1. **Active Queries**: Are exactly what you would expect from a query (e.g., the ${(0, doc_query_1.linkToQueryOfName)('call-context')}). They fetch information from the dataflow graph.
+2. **Virtual Queries**: Are used to structure your queries (e.g., the ${(0, doc_query_1.linkToQueryOfName)('compound')}). 
 
 We separate these from a concept perspective. 
 For now, we support the following **active** queries (which we will refer to simply as a \`query\`):
@@ -288,7 +411,7 @@ ${(0, doc_query_1.tocForQueryType)('virtual')}
 
 Although it is probably better to consult the detailed explanations below, if you want to have a look at the scehma, here is its description:
 
-${(0, schema_1.describeSchema)(query_schema_1.QueriesSchema, ansi_1.markdownFormatter)}
+${(0, schema_1.describeSchema)(query_1.QueriesSchema, ansi_1.markdownFormatter)}
 
 </details>
 
@@ -317,11 +440,11 @@ However, this fails to incorporate
 3. Context information (e.g., calls like \`points\` may link to the current plot)
 
 To solve this, flowR provides a query API which allows you to specify queries on the dataflow graph.
-For the specific use-case stated, you could use the [Call-Context Query](#call-context-query) to find all calls to \`read_csv\` which refer functions that are not overwritten.
+For the specific use-case stated, you could use the ${(0, doc_query_1.linkToQueryOfName)('call-context')} to find all calls to \`read_csv\` which refer functions that are not overwritten.
 
-Just as an example, the following [Call-Context Query](#call-context-query) finds all calls to \`read_csv\` that are not overwritten:
+Just as an example, the following ${(0, doc_query_1.linkToQueryOfName)('call-context')} finds all calls to \`read_csv\` that are not overwritten:
 
-${await (0, doc_query_1.showQuery)(shell, example_query_code_1.exampleQueryCode, [{ type: 'call-context', callName: '^read_csv$', callTargets: call_context_query_format_1.CallTargets.OnlyGlobal, kind: 'input', subkind: 'csv-file' }], { showCode: false })}
+${await (0, doc_query_1.showQuery)(shell, example_query_code_1.exampleQueryCode, [{ type: 'call-context', callName: '^read_csv$', callTargets: identify_link_to_last_call_relation_1.CallTargets.OnlyGlobal, kind: 'input', subkind: 'csv-file' }], { showCode: false })}
 
 ${await (0, doc_query_1.explainQueries)(shell, 'active')}
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eagleoutice/flowr",
-  "version": "2.1.2",
+  "version": "2.1.4",
   "description": "Static Dataflow Analyzer and Program Slicer for the R Programming Language",
   "types": "dist/src/index.d.ts",
   "repository": {
@@ -38,7 +38,8 @@
     "test": "nyc --no-clean mocha",
     "performance-test": "func() { cd test/performance/ && bash run-all-suites.sh $1 $2 $3; cd ../../; }; func",
     "test-full": "npm run test -- --test-installation",
-    "detect-circular-deps": "npx madge  --extensions ts,tsx --circular src/"
+    "detect-circular-deps": "npx madge  --extensions ts,tsx --circular src/",
+    "checkup": "npm run flowr -- --execute \":version\" && npm run lint && npm run test-full -- --forbid-only && docker build -t test-flowr -f scripts/Dockerfile . && npm run doc && npm-run-all wiki:*"
   },
   "keywords": [
     "static code analysis",

package/queries/base-query-format.d.ts

@@ -1,3 +1,5 @@
+import type { NormalizedAst } from '../r-bridge/lang-4.x/ast/model/processing/decorate';
+import type { DataflowGraph } from '../dataflow/graph/graph';
 export interface BaseQueryFormat {
     /** used to select the query type :) */
     readonly type: string;
@@ -9,3 +11,7 @@ export interface BaseQueryMeta {
 export interface BaseQueryResult {
     readonly '.meta': BaseQueryMeta;
 }
+export interface BasicQueryData {
+    readonly ast: NormalizedAst;
+    readonly graph: DataflowGraph;
+}

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

@@ -1,5 +1,5 @@
 import type { CallContextQuery, CallContextQueryResult } from './call-context-query-format';
-import type { BasicQueryData } from '../../query';
+import type { BasicQueryData } from '../../base-query-format';
 /**
  * Multi-stage call context query resolve.
  *

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

@@ -1,69 +1,13 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.executeCallContextQueries = executeCallContextQueries;
-const call_context_query_format_1 = require("./call-context-query-format");
 const node_id_1 = require("../../../r-bridge/lang-4.x/ast/model/processing/node-id");
 const vertex_1 = require("../../../dataflow/graph/vertex");
-const assert_1 = require("../../../util/assert");
 const edge_1 = require("../../../dataflow/graph/edge");
-const resolve_by_name_1 = require("../../../dataflow/environments/resolve-by-name");
-const built_in_1 = require("../../../dataflow/environments/built-in");
 const cfg_1 = require("../../../util/cfg/cfg");
 const two_layer_collector_1 = require("../../two-layer-collector");
 const objects_1 = require("../../../util/objects");
-const visitor_1 = require("../../../util/cfg/visitor");
-const identifier_1 = require("../../../dataflow/environments/identifier");
-function satisfiesCallTargets(id, graph, callTarget) {
-    const callVertex = graph.get(id);
-    if (callVertex === undefined || callVertex[0].tag !== vertex_1.VertexType.FunctionCall) {
-        return 'no';
-    }
-    const [info, outgoing] = callVertex;
-    const callTargets = [...outgoing]
-        .filter(([, e]) => (0, edge_1.edgeIncludesType)(e.types, edge_1.EdgeType.Calls))
-        .map(([t]) => t);
-    let builtIn = false;
-    if (info.environment === undefined) {
-        /* if we have a call with an unbound environment,
-         * this only happens if we are sure of built-in relations and want to save references
-         */
-        builtIn = true;
-    }
-    else {
-        /*
-         * for performance and scoping reasons, flowR will not identify the global linkage,
-         * including any potential built-in mapping.
-         */
-        const reResolved = (0, resolve_by_name_1.resolveByName)(info.name, info.environment, identifier_1.ReferenceType.Unknown);
-        if (reResolved?.some(t => t.definedAt === built_in_1.BuiltIn)) {
-            builtIn = true;
-        }
-    }
-    switch (callTarget) {
-        case call_context_query_format_1.CallTargets.Any:
-            return callTargets;
-        case call_context_query_format_1.CallTargets.OnlyGlobal:
-            if (callTargets.length === 0) {
-                return builtIn ? [built_in_1.BuiltIn] : [];
-            }
-            else {
-                return 'no';
-            }
-        case call_context_query_format_1.CallTargets.MustIncludeGlobal:
-            return builtIn || callTargets.length === 0 ? [...callTargets, built_in_1.BuiltIn] : 'no';
-        case call_context_query_format_1.CallTargets.OnlyLocal:
-            return !builtIn && callTargets.length > 0 ? callTargets : 'no';
-        case call_context_query_format_1.CallTargets.MustIncludeLocal:
-            if (callTargets.length > 0) {
-                return builtIn ? [...callTargets, built_in_1.BuiltIn] : callTargets;
-            }
-            else {
-                return 'no';
-            }
-        default:
-            (0, assert_1.assertUnreachable)(callTarget);
-    }
-}
+const identify_link_to_last_call_relation_1 = require("./identify-link-to-last-call-relation");
 /* if the node is effected by nse, we have an ingoing nse edge */
 function isQuoted(node, graph) {
     const vertex = graph.ingoingEdges(node);
@@ -77,6 +21,9 @@ function makeReport(collector) {
     for (const [kind, collected] of collector.store) {
         const subkinds = {};
         for (const [subkind, values] of collected) {
+            if (!Array.isArray(subkinds[subkind])) {
+                subkinds[subkind] = [];
+            }
             subkinds[subkind] ??= [];
             const collectIn = subkinds[subkind];
             for (const value of values) {
@@ -90,10 +37,10 @@ function makeReport(collector) {
     return result;
 }
 function isSubCallQuery(query) {
-    return 'linkTo' in query;
+    return 'linkTo' in query && query.linkTo !== undefined;
 }
 function exactCallNameRegex(name) {
-    return new RegExp(`^${name}$`);
+    return new RegExp(`^(${name})$`);
 }
 function promoteQueryCallNames(queries) {
     let requiresCfg = false;
@@ -121,24 +68,6 @@ function promoteQueryCallNames(queries) {
     });
     return { promotedQueries, requiresCfg };
 }
-function identifyLinkToLastCallRelation(from, cfg, graph, linkTo) {
-    const found = [];
-    (0, visitor_1.visitInReverseOrder)(cfg, from, node => {
-        /* we ignore the start id as it cannot be the last call */
-        if (node === from) {
-            return;
-        }
-        const vertex = graph.getVertex(node);
-        if (vertex === undefined || vertex.tag !== vertex_1.VertexType.FunctionCall) {
-            return;
-        }
-        if (linkTo.test(vertex.name)) {
-            found.push(node);
-            return true;
-        }
-    });
-    return found;
-}
 /* maybe we want to add caches to this */
 function retrieveAllCallAliases(nodeId, graph) {
     /* we want the names of all functions called at the source id, including synonyms and returns */
@@ -187,6 +116,22 @@ function retrieveAllCallAliases(nodeId, graph) {
     }
     return aliases;
 }
+function removeIdenticalDuplicates(collector) {
+    for (const [, collected] of collector.store) {
+        for (const [subkind, values] of collected) {
+            const seen = new Set();
+            const newValues = values.filter(v => {
+                const str = JSON.stringify(v);
+                if (seen.has(str)) {
+                    return false;
+                }
+                seen.add(str);
+                return true;
+            });
+            collected.set(subkind, newValues);
+        }
+    }
+}
 /**
  * Multi-stage call context query resolve.
  *
@@ -223,7 +168,7 @@ function executeCallContextQueries({ graph, ast }, queries) {
             for (const [l, ids] of targets.entries()) {
                 for (const query of queriesWhichWantAliases) {
                     if (query.callName.test(l)) {
-                        initialIdCollector.add(query.kind ?? '.', query.subkind ?? '.', (0, objects_1.compactRecord)({ id: nodeId, aliasRoots: ids }));
+                        initialIdCollector.add(query.kind ?? '.', query.subkind ?? '.', (0, objects_1.compactRecord)({ id: nodeId, name: info.name, aliasRoots: ids }));
                     }
                 }
             }
@@ -231,7 +176,7 @@ function executeCallContextQueries({ graph, ast }, queries) {
         for (const query of promotedQueries.filter(q => q.callName.test(info.name))) {
             let targets = undefined;
             if (query.callTargets) {
-                targets = satisfiesCallTargets(nodeId, graph, query.callTargets);
+                targets = (0, identify_link_to_last_call_relation_1.satisfiesCallTargets)(nodeId, graph, query.callTargets);
                 if (targets === 'no') {
                     continue;
                 }
@@ -243,14 +188,15 @@ function executeCallContextQueries({ graph, ast }, queries) {
             let linkedIds = undefined;
             if (cfg && isSubCallQuery(query)) {
                 /* if we have a linkTo query, we have to find the last call */
-                const lastCall = identifyLinkToLastCallRelation(nodeId, cfg.graph, graph, query.linkTo.callName);
+                const lastCall = (0, identify_link_to_last_call_relation_1.identifyLinkToLastCallRelation)(nodeId, cfg.graph, graph, query.linkTo.callName);
                 if (lastCall) {
                     linkedIds = lastCall;
                 }
             }
-            initialIdCollector.add(query.kind ?? '.', query.subkind ?? '.', (0, objects_1.compactRecord)({ id: nodeId, calls: targets, linkedIds }));
+            initialIdCollector.add(query.kind ?? '.', query.subkind ?? '.', (0, objects_1.compactRecord)({ id: nodeId, name: info.name, calls: targets, linkedIds }));
         }
     }
+    removeIdenticalDuplicates(initialIdCollector);
     return {
         '.meta': {
             timing: Date.now() - now,