External/fredy
1
0
Fork 0
mirror of https://github.com/orangecoding/fredy.git synced 2026-06-16 12:31:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

improve similarity cache. It now checks for similarities independend from jobs

Browse Source
This commit is contained in:
orangecoding
2025-09-07 22:15:14 +02:00
parent 7fa9a265ef
commit 09c6ce1d0b
6 changed files with 138 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
test/similarity/similarity.test.js
View File

@@ -1,40 +1,30 @@
import SimilarityCacheEntry from '../../lib/services/similarity-check/SimilarityCacheEntry.js';
import { expect } from 'chai';
import * as similarityCache from '../../lib/services/similarity-check/similarityCache.js';
describe('similarityCheck', () => {
describe('#similarityCheck()', () => {
it('should be false', () => {
const check = new SimilarityCacheEntry(0);
check.setCacheEntry('Hallo');
expect(check.hasSimilarEntries('Welt')).to.be.false;
});
it('should be true', () => {
const check = new SimilarityCacheEntry(0);
check.setCacheEntry('Hallo');
expect(check.hasSimilarEntries('hallo')).to.be.true;
});
it('should be true', () => {
const check = new SimilarityCacheEntry(0);
check.setCacheEntry('Selling an incredible house in san francisco');
expect(check.hasSimilarEntries('incredible house in san francisco for sale')).to.be.true;
});
it('should be true', () => {
const check = new SimilarityCacheEntry(0);
check.setCacheEntry('a');
check.setCacheEntry('b');
check.setCacheEntry('c');
check.setCacheEntry('d');
expect(check.hasSimilarEntries('b')).to.be.true;
});
it('should be false', () => {
const check = new SimilarityCacheEntry(0);
check.setCacheEntry(
'The index is known by several other names, especially Sørensen–Dice index,[3] Sørensen index and Dice\'s coefficient. Other variations include the "similarity coefficient" or "index", such as Dice similarity coefficient (DSC). Common alternate spellings for Sørensen are Sorenson, Soerenson and Sörenson, and all three can also be seen with the –sen ending.',
);
check.setCacheEntry(
'where |X| and |Y| are the cardinalities of the two sets (i.e. the number of elements in each set). The Sørensen index equals twice the number of elements common to both sets divided by the sum of the number of elements in each set.',
);
expect(check.hasSimilarEntries('unrelated text')).to.be.false;
});
it('should return true on duplicate', () => {
similarityCache.addCacheEntry('Hello World', 'Test');
expect(similarityCache.hasSimilarEntries('Hello World', 'Test')).to.be.true;
});
it('should return true even if one value is null', () => {
similarityCache.addCacheEntry('Hello World', null);
expect(similarityCache.hasSimilarEntries('Hello World', null)).to.be.true;
});
it('should return true even if one value is an obj', () => {
similarityCache.addCacheEntry('Hello World', [{ TR: 'OLOLO' }]);
expect(similarityCache.hasSimilarEntries('Hello World', [{ TR: 'OLOLO' }])).to.be.true;
});
it('should return false when no duplicate', () => {
similarityCache.addCacheEntry('Hello World__', 'Test');
expect(similarityCache.hasSimilarEntries('Hello World___', 'Test')).to.be.false;
});
it('should return false when no duplicate', () => {
expect(similarityCache.hasSimilarEntries('Hello World', 'Test')).to.be.true;
similarityCache.invalidateAllForTest();
expect(similarityCache.hasSimilarEntries('Hello World', 'Test')).to.be.false;
});
});