UML Diagram Draft 1

@startuml
' TODO: Discussion
' 1. Fingerprint: Pair<Int, Int>, or create a new Object of type Fingerprint and shinglesList: List<Fingerprint>


' Entities
entity Document {
'key
String url;

'The rest are values
' <shingle_hash, shingle_pos>
List<Integer, Integer> shinglesList;
Date publishDate;
}


' Controllers
class FingerprintController {

CrawlerService crawlerService;
FingerprintService fingerprintService;

' Endpoints -> Double represents similarity ratio
ResponseEntity<Double> checkURL(@PathVariable String url);
ResponseEntity<Double> compareURLs(@PathVariable String url1, @PathVariable String url2);
ResponseEntity<Double> checkText(@RequestBody String text);
ResponseEntity<Double> compareTexts(@RequestBody String text1, @RequestBody String text2);


}

' Services

class CrawlerService {
'from news-please import NewsPlease
NewsPlease newsPlease;
NewsPlease.Article crawl(String url);
}


class SimilarityService {

' Check to be in [0, 1]
Double computeSimilarity(List<Integer, Integer> fp1, List<Integer, Integer> fp2);
' <URL, Similarity>

}


class FingerprintService {

DocumentRepository documentRepository;
SimilarityService similarityService;

Pair<String, Double> findMaxSim(String URL);
List<Pair<String, Double>> findMaxKSims(String url, int k);




}

class CrawlerService

' Repositories -> what interacts with our database

interface DocumentRepository {

Document findById();
List<Document> findAll();
Document save(Document document);
}
@enduml