@eagleoutice/flowr 1.3.11 → 1.3.13

package/util/summarizer/benchmark/benchmark-summarizer.js

@@ -1,208 +0,0 @@
-"use strict";
-var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    var desc = Object.getOwnPropertyDescriptor(m, k);
-    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-      desc = { enumerable: true, get: function() { return m[k]; } };
-    }
-    Object.defineProperty(o, k2, desc);
-}) : (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    o[k2] = m[k];
-}));
-var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
-    Object.defineProperty(o, "default", { enumerable: true, value: v });
-}) : function(o, v) {
-    o["default"] = v;
-});
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
-var __importDefault = (this && this.__importDefault) || function (mod) {
-    return (mod && mod.__esModule) ? mod : { "default": mod };
-};
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.summarizeSummarizedMeasurement = exports.summarizeMeasurement = exports.summarizeSlicerStats = void 0;
-const tmp = __importStar(require("tmp"));
-const assert_1 = require("../../assert");
-const log_1 = require("../../log");
-const defaultmap_1 = require("../../defaultmap");
-const r_bridge_1 = require("../../../r-bridge");
-const strings_1 = require("../../strings");
-const fs_1 = __importDefault(require("fs"));
-const arrays_1 = require("../../arrays");
-const tempfile = (() => {
-    let _tempfile = undefined;
-    return () => {
-        if (_tempfile === undefined) {
-            _tempfile = tmp.fileSync({ postfix: '.R', keep: false });
-            process.on('beforeExit', () => _tempfile?.removeCallback());
-        }
-        return _tempfile;
-    };
-})();
-function safeDivPercentage(a, b) {
-    if (isNaN(a) || isNaN(b)) {
-        return undefined;
-    }
-    else if (b === 0) {
-        return a === 0 ? 0 : undefined;
-    }
-    else {
-        const result = 1 - (a / b);
-        if (isNaN(result)) {
-            log_1.log.error(`NaN for ${a} and ${b}\n`);
-            return undefined;
-        }
-        else {
-            return result;
-        }
-    }
-}
-function calculateReductionForSlice(input, dataflow, perSlice) {
-    return {
-        numberOfLines: safeDivPercentage(perSlice.lines, input.numberOfLines),
-        numberOfLinesNoAutoSelection: safeDivPercentage(perSlice.lines - perSlice.autoSelected, input.numberOfLines),
-        numberOfCharacters: safeDivPercentage(perSlice.characters, input.numberOfCharacters),
-        numberOfNonWhitespaceCharacters: safeDivPercentage(perSlice.nonWhitespaceCharacters, input.numberOfNonWhitespaceCharacters),
-        numberOfRTokens: safeDivPercentage(perSlice.tokens, input.numberOfRTokens),
-        numberOfNormalizedTokens: safeDivPercentage(perSlice.normalizedTokens, input.numberOfNormalizedTokens),
-        numberOfDataflowNodes: safeDivPercentage(perSlice.dataflowNodes, dataflow.numberOfNodes)
-    };
-}
-/**
- * Summarizes the given stats by calculating the min, max, median, mean, and the standard deviation for each measurement.
- * @see Slicer
- */
-async function summarizeSlicerStats(stats, report = () => {
-}) {
-    const perSliceStats = stats.perSliceMeasurements;
-    const collect = new defaultmap_1.DefaultMap(() => []);
-    const sizeOfSliceCriteria = [];
-    const reParseShellSession = new r_bridge_1.RShell();
-    reParseShellSession.tryToInjectHomeLibPath();
-    const reductions = [];
-    let failedOutputs = 0;
-    const sliceSize = {
-        lines: [],
-        autoSelected: [],
-        characters: [],
-        nonWhitespaceCharacters: [],
-        tokens: [],
-        normalizedTokens: [],
-        dataflowNodes: []
-    };
-    let first = true;
-    let timesHitThreshold = 0;
-    for (const [criteria, perSliceStat] of perSliceStats) {
-        report(criteria, perSliceStat);
-        for (const measure of perSliceStat.measurements) {
-            collect.get(measure[0]).push(Number(measure[1]));
-        }
-        sizeOfSliceCriteria.push(perSliceStat.slicingCriteria.length);
-        timesHitThreshold += perSliceStat.timesHitThreshold > 0 ? 1 : 0;
-        const { code: output, autoSelected } = perSliceStat.reconstructedCode;
-        sliceSize.autoSelected.push(autoSelected);
-        const lines = output.split('\n').length;
-        sliceSize.lines.push(lines);
-        sliceSize.characters.push(output.length);
-        const nonWhitespace = (0, strings_1.withoutWhitespace)(output).length;
-        sliceSize.nonWhitespaceCharacters.push(nonWhitespace);
-        // reparse the output to get the number of tokens
-        try {
-            // there seem to be encoding issues, therefore, we dump to a temp file
-            fs_1.default.writeFileSync(tempfile().name, output);
-            const reParsed = await (0, r_bridge_1.retrieveNormalizedAstFromRCode)({ request: 'file', content: tempfile().name, ensurePackageInstalled: first }, reParseShellSession);
-            first = false;
-            let numberOfNormalizedTokens = 0;
-            (0, r_bridge_1.visitAst)(reParsed.ast, _ => {
-                numberOfNormalizedTokens++;
-                return false;
-            });
-            sliceSize.normalizedTokens.push(numberOfNormalizedTokens);
-            const numberOfRTokens = await (0, r_bridge_1.retrieveNumberOfRTokensOfLastParse)(reParseShellSession);
-            sliceSize.tokens.push(numberOfRTokens);
-            reductions.push(calculateReductionForSlice(stats.input, stats.dataflow, {
-                lines: lines,
-                characters: output.length,
-                nonWhitespaceCharacters: nonWhitespace,
-                autoSelected: autoSelected,
-                tokens: numberOfRTokens,
-                normalizedTokens: numberOfNormalizedTokens,
-                dataflowNodes: perSliceStat.numberOfDataflowNodesSliced
-            }));
-        }
-        catch (e) {
-            console.error(`    ! Failed to re-parse the output of the slicer for ${JSON.stringify(criteria)}`); //, e
-            console.error(`      Code: ${output}\n`);
-            failedOutputs++;
-        }
-        sliceSize.dataflowNodes.push(perSliceStat.numberOfDataflowNodesSliced);
-    }
-    // summarize all measurements:
-    const summarized = new Map();
-    for (const [criterion, measurements] of collect.entries()) {
-        summarized.set(criterion, summarizeMeasurement(measurements));
-    }
-    reParseShellSession.close();
-    return {
-        ...stats,
-        perSliceMeasurements: {
-            numberOfSlices: perSliceStats.size,
-            sliceCriteriaSizes: summarizeMeasurement(sizeOfSliceCriteria),
-            measurements: summarized,
-            failedToRepParse: failedOutputs,
-            timesHitThreshold,
-            reduction: {
-                numberOfLines: summarizeMeasurement(reductions.map(r => r.numberOfLines).filter(assert_1.isNotUndefined)),
-                numberOfLinesNoAutoSelection: summarizeMeasurement(reductions.map(r => r.numberOfLinesNoAutoSelection).filter(assert_1.isNotUndefined)),
-                numberOfCharacters: summarizeMeasurement(reductions.map(r => r.numberOfCharacters).filter(assert_1.isNotUndefined)),
-                numberOfNonWhitespaceCharacters: summarizeMeasurement(reductions.map(r => r.numberOfNonWhitespaceCharacters).filter(assert_1.isNotUndefined)),
-                numberOfRTokens: summarizeMeasurement(reductions.map(r => r.numberOfRTokens).filter(assert_1.isNotUndefined)),
-                numberOfNormalizedTokens: summarizeMeasurement(reductions.map(r => r.numberOfNormalizedTokens).filter(assert_1.isNotUndefined)),
-                numberOfDataflowNodes: summarizeMeasurement(reductions.map(r => r.numberOfDataflowNodes).filter(assert_1.isNotUndefined))
-            },
-            sliceSize: {
-                lines: summarizeMeasurement(sliceSize.lines),
-                characters: summarizeMeasurement(sliceSize.characters),
-                nonWhitespaceCharacters: summarizeMeasurement(sliceSize.nonWhitespaceCharacters),
-                autoSelected: summarizeMeasurement(sliceSize.autoSelected),
-                tokens: summarizeMeasurement(sliceSize.tokens),
-                normalizedTokens: summarizeMeasurement(sliceSize.normalizedTokens),
-                dataflowNodes: summarizeMeasurement(sliceSize.dataflowNodes)
-            }
-        }
-    };
-}
-exports.summarizeSlicerStats = summarizeSlicerStats;
-function summarizeMeasurement(data, totalNumberOfDataPoints) {
-    // just to avoid in-place modification
-    const sorted = [...data].sort((a, b) => a - b);
-    const min = sorted[0];
-    const max = sorted[sorted.length - 1];
-    const median = sorted[Math.floor(sorted.length / 2)];
-    const total = (0, arrays_1.sum)(sorted);
-    const length = totalNumberOfDataPoints ?? sorted.length;
-    const mean = total / length;
-    // sqrt(sum(x-mean)^2 / n)
-    const std = Math.sqrt(sorted.map(x => (x - mean) ** 2).reduce((a, b) => a + b, 0) / length);
-    return { min, max, median, mean, std, total };
-}
-exports.summarizeMeasurement = summarizeMeasurement;
-function summarizeSummarizedMeasurement(data) {
-    const min = data.map(d => d.min).filter(assert_1.isNotUndefined).reduce((a, b) => Math.min(a, b), Infinity);
-    const max = data.map(d => d.max).filter(assert_1.isNotUndefined).reduce((a, b) => Math.max(a, b), -Infinity);
-    // get most average
-    const median = data.map(d => d.median).filter(assert_1.isNotUndefined).reduce((a, b) => a + b, 0) / data.length;
-    const mean = data.map(d => d.mean).filter(assert_1.isNotUndefined).reduce((a, b) => a + b, 0) / data.length;
-    // Method 1 of https://www.statology.org/averaging-standard-deviations/
-    const std = Math.sqrt(data.map(d => d.std ** 2).filter(assert_1.isNotUndefined).reduce((a, b) => a + b, 0) / data.length);
-    const total = data.map(d => d.total).filter(assert_1.isNotUndefined).reduce((a, b) => a + b, 0);
-    return { min, max, median, mean, std, total };
-}
-exports.summarizeSummarizedMeasurement = summarizeSummarizedMeasurement;
-//# sourceMappingURL=benchmark-summarizer.js.map