synonym-optimizer - npm Package Compare versions

Comparing version 2.19.0 to 2.20.0

dist/index.d.ts

@@ -1,23 +0,1 @@
-export declare type Languages = 'en_US' | 'fr_FR' | 'de_DE' | 'it_IT' | 'es_ES' | string;
-export declare function getStandardStopWords(lang: Languages): string[];
-export declare function getStopWords(lang: Languages, stopWordsToAdd: string[], stopWordsToRemove: string[], stopWordsOverride: string[]): string[];
-export declare function extractWords(input: string, lang: Languages): string[];
-interface WordsWithPos {
-    [key: string]: number[];
-}
-export declare function getWordsWithPos(lang: Languages, words: string[], identicals: string[][], debugHolder: DebugHolder): WordsWithPos;
-export declare function getScore(wordsWithPos: WordsWithPos): number;
-interface IdenticalsMap {
-    [key: string]: string;
-}
-export interface DebugHolder {
-    filteredAlt?: string[];
-    identicals?: string[][];
-    identicalsMap?: IdenticalsMap;
-    wordsWithPos?: WordsWithPos;
-    score?: number;
-}
-export declare function getStemmedWords(text: string, stopwords: string[], lang: Languages): string[];
-export declare function scoreAlternative(lang: Languages, alternative: string, stopWordsToAdd: string[], stopWordsToRemove: string[], stopWordsOverride: string[], identicals: string[][], debugHolder: DebugHolder): number;
-export declare function getBest(lang: Languages, alternatives: string[], stopWordsToAdd: string[], stopWordsToRemove: string[], stopWordsOverride: string[], identicals: string[][]): number;
-export {};
+export { DebugHolder, SynOptimizer } from './SynOptimizer';

dist/index.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.getBest = exports.scoreAlternative = exports.getStemmedWords = exports.getScore = exports.getWordsWithPos = exports.extractWords = exports.getStopWords = exports.getStandardStopWords = void 0;
-const tokenizer = require("wink-tokenizer");
-const stopwordsFr = require("stopwords-fr");
-const stopwordsDe = require("stopwords-de");
-const stopwordsEn = require("stopwords-en");
-const stopwordsIt = require("stopwords-it");
-const stopwordsEs = require("stopwords-es");
-const englishStemmer = require("snowball-stemmer.jsx/dest/english-stemmer.common.js");
-const frenchStemmer = require("snowball-stemmer.jsx/dest/french-stemmer.common.js");
-const germanStemmer = require("snowball-stemmer.jsx/dest/german-stemmer.common.js");
-const italianStemmer = require("snowball-stemmer.jsx/dest/italian-stemmer.common.js");
-const spanishStemmer = require("snowball-stemmer.jsx/dest/spanish-stemmer.common.js");
-const rosaenlg_filter_1 = require("rosaenlg-filter");
-const fullySupportedLanguages = ['en_US', 'de_DE', 'fr_FR', 'it_IT', 'es_ES'];
-// exported for testing purposes
-function getStandardStopWords(lang) {
-    switch (lang) {
-        case 'en_US':
-            return stopwordsEn;
-        case 'fr_FR':
-            return stopwordsFr;
-        case 'de_DE':
-            return stopwordsDe;
-        case 'it_IT':
-            return stopwordsIt;
-        case 'es_ES':
-            return stopwordsEs;
-        default:
-            return [];
-    }
-}
-exports.getStandardStopWords = getStandardStopWords;
-function getStopWords(lang, stopWordsToAdd, stopWordsToRemove, stopWordsOverride) {
-    let baseList;
-    // the base list
-    if (stopWordsOverride) {
-        baseList = stopWordsOverride.slice(0);
-    }
-    else {
-        baseList = getStandardStopWords(lang);
-    }
-    // remove
-    if (stopWordsToRemove) {
-        baseList = baseList.filter(function (word) {
-            return !stopWordsToRemove.includes(word);
-        });
-    }
-    // and add
-    if (stopWordsToAdd) {
-        baseList = baseList.concat(stopWordsToAdd);
-    }
-    return baseList.map(function (alt) {
-        return alt.toLowerCase();
-    });
-}
-exports.getStopWords = getStopWords;
-function extractWords(input, lang) {
-    // console.log(`tokenizing: ${input}`);
-    const myTokenizer = new tokenizer();
-    myTokenizer.defineConfig({
-        currency: false,
-        number: false,
-        punctuation: false,
-        symbol: false,
-        time: false,
-    });
-    const tokenized = myTokenizer.tokenize(input);
-    // console.log(`tokenized: ${tokenized}`);
-    let res = [];
-    tokenized.forEach(function (elt) {
-        // no alien tags and no html elements
-        if (elt.tag != 'alien' && rosaenlg_filter_1.blockLevelHtmlElts.indexOf(elt.value) == -1 && rosaenlg_filter_1.inlineHtmlElts.indexOf(elt.value) == -1) {
-            res.push(elt.value);
-        }
-    });
-    if (lang == 'fr_FR') {
-        // we just leave [Pp]uisqu [Jj]usqu [Ll]orsqu as they are
-        const regexp = new RegExp("^(D|d|Q|q|L|l|S|s|J|j|T|t|M|m|N|n)'", 'g');
-        res = res.map((elt) => {
-            return elt.replace(regexp, '');
-        });
-        // sometimes it results in having empty elements
-        res = res.filter((elt) => elt.length > 0);
-    }
-    // console.log(`res: ${res}`);
-    return res;
-}
-exports.extractWords = extractWords;
-const stemmersCache = {};
-function stemWordForLang(word, lang) {
-    if (fullySupportedLanguages.includes(lang)) {
-        //console.log(`ok ${lang} is valid`);
-        if (!stemmersCache[lang]) {
-            switch (lang) {
-                case 'en_US':
-                    stemmersCache[lang] = new englishStemmer.EnglishStemmer();
-                    break;
-                case 'de_DE':
-                    stemmersCache[lang] = new germanStemmer.GermanStemmer();
-                    break;
-                case 'fr_FR':
-                    stemmersCache[lang] = new frenchStemmer.FrenchStemmer();
-                    break;
-                case 'it_IT':
-                    stemmersCache[lang] = new italianStemmer.ItalianStemmer();
-                    break;
-                case 'es_ES':
-                    stemmersCache[lang] = new spanishStemmer.SpanishStemmer();
-                    break;
-            }
-        }
-        //console.log(`orig: ${word}, stemmed: ${stemmersCache[lang].stemWord(word)}`);
-        return stemmersCache[lang].stemWord(word);
-    }
-    return word;
-}
-function getWordsWithPos(lang, words, identicals, debugHolder) {
-    const identicalsMap = {};
-    if (identicals) {
-        // check type
-        if (!Array.isArray(identicals)) {
-            const err = new Error();
-            err.name = 'InvalidArgumentError';
-            err.message = `identicals must be a string[][]`;
-            throw err;
-        }
-        else {
-            identicals.forEach(function (identicalList) {
-                if (!Array.isArray(identicalList)) {
-                    const err = new Error();
-                    err.name = 'InvalidArgumentError';
-                    err.message = `identicals must be a string[][]`;
-                    throw err;
-                }
-            });
-        }
-        if (debugHolder) {
-            debugHolder.identicals = identicals;
-        }
-        // do the job
-        identicals.forEach(function (identicalList) {
-            const mapTo = identicalList.join('_');
-            identicalList.forEach(function (identicalElt) {
-                identicalsMap[stemWordForLang(identicalElt, lang)] = mapTo;
-            });
-        });
-    }
-    if (debugHolder) {
-        debugHolder.identicalsMap = identicalsMap;
-    }
-    const wordsWithPos = {};
-    for (let j = 0; j < words.length; j++) {
-        const word = identicalsMap[words[j]] || words[j];
-        if (!wordsWithPos[word]) {
-            wordsWithPos[word] = [];
-        }
-        wordsWithPos[word].push(j);
-    }
-    return wordsWithPos;
-}
-exports.getWordsWithPos = getWordsWithPos;
-function getScore(wordsWithPos) {
-    let score = 0;
-    Object.keys(wordsWithPos).forEach(function (word) {
-        const positions = wordsWithPos[word];
-        for (let j = 1; j < positions.length; j++) {
-            score += 1 / (positions[j] - positions[j - 1]);
-        }
-    });
-    return score;
-}
-exports.getScore = getScore;
-function getStemmedWords(text, stopwords, lang) {
-    // console.log(`getStemmedWords: ${text}`);
-    const res = extractWords(text, lang)
-        .map(function (alt) {
-        return alt.toLowerCase();
-    })
-        .filter(function (alt) {
-        return !stopwords.includes(alt);
-    })
-        .map((elt) => {
-        return stemWordForLang(elt, lang);
-    });
-    // console.log(`getStemmedWords result: ${res}`);
-    return res;
-}
-exports.getStemmedWords = getStemmedWords;
-function scoreAlternative(lang, alternative, stopWordsToAdd, stopWordsToRemove, stopWordsOverride, identicals, debugHolder) {
-    // console.log(stemmer.stemWord("baby"));
-    // console.log(stopWordsToAdd);
-    const stopwords = getStopWords(lang, stopWordsToAdd, stopWordsToRemove, stopWordsOverride);
-    // console.log(stopwords);
-    const filteredAlt = getStemmedWords(alternative, stopwords, lang);
-    if (debugHolder) {
-        debugHolder.filteredAlt = filteredAlt;
-    }
-    const wordsWithPos = getWordsWithPos(lang, filteredAlt, identicals, debugHolder);
-    if (debugHolder) {
-        // only keep ones with > 1 for readability
-        debugHolder.wordsWithPos = {};
-        Object.keys(wordsWithPos).forEach(function (word) {
-            if (wordsWithPos[word].length > 1) {
-                debugHolder.wordsWithPos[word] = wordsWithPos[word];
-            }
-        });
-    }
-    // console.log(wordsWithPos);
-    // score
-    const score = getScore(wordsWithPos);
-    if (debugHolder) {
-        debugHolder.score = score;
-    }
-    return score;
-    // console.log(score);
-}
-exports.scoreAlternative = scoreAlternative;
-function getBest(lang, alternatives, stopWordsToAdd, stopWordsToRemove, stopWordsOverride, identicals) {
-    const scores = [];
-    alternatives.forEach(function (alt) {
-        scores.push(scoreAlternative(lang, alt, stopWordsToAdd, stopWordsToRemove, stopWordsOverride, identicals, null));
-    });
-    return scores.indexOf(Math.min(...scores));
-}
-exports.getBest = getBest;
+exports.SynOptimizer = void 0;
+var SynOptimizer_1 = require("./SynOptimizer");
+Object.defineProperty(exports, "SynOptimizer", { enumerable: true, get: function () { return SynOptimizer_1.SynOptimizer; } });
 //# sourceMappingURL=index.js.map

dist/stopWordsDoc.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 const fs = require("fs");
-const index_1 = require("./index");
+const helper_1 = require("./helper");
 function generateStopWordsDoc(dest) {
@@ -12,3 +12,4 @@ const stream = fs.createWriteStream(dest, 'utf-8');
         stream.write(`== ${language}\n\n`);
-        const stopWords = index_1.getStandardStopWords(language);
+        const languageSyn = helper_1.buildLanguageSyn(helper_1.getIso2fromLocale(language));
+        const stopWords = languageSyn.getStandardStopWords();
         stream.write(stopWords.join(' - '));
@@ -15,0 +16,0 @@ stream.write(`\n\n\n`);

package.json

 {
   "name": "synonym-optimizer",
-  "version": "2.19.0",
+  "version": "2.20.0",
   "description": "Finds the text which has the least number of repetitions",
@@ -11,3 +11,3 @@ "main": "dist/index.js",
     "tsc": "tsc",
-    "build": "tsc && node dist/stopWordsDoc.js"
+    "build": "tsc && node ./dist/stopWordsDoc.js"
   },
@@ -56,3 +56,3 @@ "nyc": {
     "@types/wink-tokenizer": "^4.0.1",
-    "rosaenlg-filter": "2.19.0",
+    "rosaenlg-filter": "2.20.0",
     "snowball-stemmer.jsx": "^0.2.3",
@@ -66,3 +66,3 @@ "stopwords-de": "^0.3.0",
   },
-  "gitHead": "ecf867234952618936b9710b363984bfe00632ba"
+  "gitHead": "9223cdd558d1775f866f99921e3391d5d7cdc4f2"
 }

No alert changes

Improved metrics

Total package byte prevSize

152945

increased by49.4%

Number of package files

56

increased by180%

Lines of code

934

increased by20.21%

Dependency changes

• + Addedenglish-a-an@0.12.0(transitive)

• + Addedenglish-a-an-list@0.12.0(transitive)

• + Addedfrench-contractions@2.20.0(transitive)

• + Addedrosaenlg-commons@0.4.0(transitive)

• + Addedrosaenlg-filter@2.20.0(transitive)

• - Removedenglish-a-an@0.11.0(transitive)

• - Removedenglish-a-an-list@0.11.0(transitive)

• - Removedfrench-contractions@2.19.0(transitive)

• - Removedrosaenlg-commons@0.3.0(transitive)

• - Removedrosaenlg-filter@2.19.0(transitive)

• Updatedrosaenlg-filter@2.20.0