Examples with LevenshteinDistance org.apache.commons.text.similarity.LevenshteinDistance used on opensource projects

Example 6 with LevenshteinDistance

use of org.apache.commons.text.similarity.LevenshteinDistance in project drools by kiegroup.

the class KiePMMLTextIndexTest method evaluateLevenshteinDistanceBestHits.

@Test
public void evaluateLevenshteinDistanceBestHits() {
    // brown-foxy does not match
    String wordSeparatorCharacterRE = "\\s+";
    Pattern pattern = Pattern.compile(wordSeparatorCharacterRE);
    List<String> terms = KiePMMLTextIndex.splitText("The", pattern);
    List<String> texts = KiePMMLTextIndex.splitText(TEXT_0, pattern);
    LevenshteinDistance levenshteinDistance = new LevenshteinDistance(0);
    assertEquals(2, KiePMMLTextIndex.evaluateLevenshteinDistanceBestHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(1);
    assertEquals(2, KiePMMLTextIndex.evaluateLevenshteinDistanceBestHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(2);
    assertEquals(2, KiePMMLTextIndex.evaluateLevenshteinDistanceBestHits(levenshteinDistance, terms, texts));
    // ---
    // brown-foxy match
    wordSeparatorCharacterRE = "[\\s\\-]";
    pattern = Pattern.compile(wordSeparatorCharacterRE);
    terms = KiePMMLTextIndex.splitText("The", pattern);
    texts = KiePMMLTextIndex.splitText(TEXT_0, pattern);
    levenshteinDistance = new LevenshteinDistance(0);
    assertEquals(2, KiePMMLTextIndex.evaluateLevenshteinDistanceBestHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(1);
    assertEquals(2, KiePMMLTextIndex.evaluateLevenshteinDistanceBestHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(2);
    assertEquals(2, KiePMMLTextIndex.evaluateLevenshteinDistanceBestHits(levenshteinDistance, terms, texts));
}

Example 7 with LevenshteinDistance

use of org.apache.commons.text.similarity.LevenshteinDistance in project drools by kiegroup.

the class KiePMMLTextIndexTest method evaluateLevenshteinDistanceAllHits.

@Test
public void evaluateLevenshteinDistanceAllHits() {
    // brown-foxy does not match
    String wordSeparatorCharacterRE = "\\s+";
    Pattern pattern = Pattern.compile(wordSeparatorCharacterRE);
    List<String> terms = KiePMMLTextIndex.splitText(TERM_0, pattern);
    List<String> texts = KiePMMLTextIndex.splitText(TEXT_0, pattern);
    LevenshteinDistance levenshteinDistance = new LevenshteinDistance(0);
    assertEquals(1, KiePMMLTextIndex.evaluateLevenshteinDistanceAllHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(1);
    assertEquals(2, KiePMMLTextIndex.evaluateLevenshteinDistanceAllHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(2);
    assertEquals(3, KiePMMLTextIndex.evaluateLevenshteinDistanceAllHits(levenshteinDistance, terms, texts));
    // ---
    // brown-foxy match
    wordSeparatorCharacterRE = "[\\s\\-]";
    pattern = Pattern.compile(wordSeparatorCharacterRE);
    terms = KiePMMLTextIndex.splitText(TERM_0, pattern);
    texts = KiePMMLTextIndex.splitText(TEXT_0, pattern);
    levenshteinDistance = new LevenshteinDistance(0);
    assertEquals(1, KiePMMLTextIndex.evaluateLevenshteinDistanceAllHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(1);
    assertEquals(3, KiePMMLTextIndex.evaluateLevenshteinDistanceAllHits(levenshteinDistance, terms, texts));
    levenshteinDistance = new LevenshteinDistance(2);
    assertEquals(4, KiePMMLTextIndex.evaluateLevenshteinDistanceAllHits(levenshteinDistance, terms, texts));
}

Example 8 with LevenshteinDistance

use of org.apache.commons.text.similarity.LevenshteinDistance in project goci by EBISPOT.

the class PublicationController method matchPublication.

@RequestMapping(value = "/match", produces = MediaType.APPLICATION_JSON_VALUE, method = RequestMethod.POST)
@ResponseBody
public ResponseEntity<Map<String, Object>> matchPublication(Model model, @RequestBody String pubmedId) {
    Map<String, Object> results = new HashMap<>();
    CosineDistance cosScore = new CosineDistance();
    LevenshteinDistance levenshteinDistance = new LevenshteinDistance();
    JaroWinklerSimilarity jwDistance = new JaroWinklerSimilarity();
    EuropePMCData europePMCResult = europepmcPubMedSearchService.createStudyByPubmed(pubmedId);
    Map<String, String> searchProps = new HashMap<>();
    List<Map<String, String>> data = new ArrayList<>();
    if (!europePMCResult.getError()) {
        try {
            searchProps.put("pubMedID", europePMCResult.getPublication().getPubmedId());
            searchProps.put("author", europePMCResult.getFirstAuthor().getFullname());
            searchProps.put("title", europePMCResult.getPublication().getTitle());
            searchProps.put("doi", europePMCResult.getDoi());
            results.put("search", searchProps);
            String searchTitle = europePMCResult.getPublication().getTitle();
            String searchAuthor = europePMCResult.getFirstAuthor().getFullname();
            CharSequence searchString = buildSearch(searchAuthor, searchTitle);
            Map<String, Submission> submissionMap = submissionService.getSubmissionsBasic();
            for (Map.Entry<String, Submission> e : submissionMap.entrySet()) {
                Map<String, String> props = new HashMap<>();
                Submission submission = e.getValue();
                String matchTitle = submission.getTitle();
                String matchAuthor = submission.getAuthor();
                CharSequence matchString = buildSearch(matchAuthor, matchTitle);
                props.put("submissionID", submission.getId());
                props.put("pubMedID", submission.getPubMedID());
                props.put("author", submission.getAuthor());
                props.put("title", submission.getTitle());
                props.put("doi", submission.getDoi());
                if (matchString.equals("")) {
                    props.put("cosScore", new Integer(0).toString());
                    props.put("levDistance", new Integer(0).toString());
                    props.put("jwScore", new Integer(0).toString());
                } else {
                    Double score = cosScore.apply(searchString, matchString) * 100;
                    Integer ldScore = levenshteinDistance.apply(searchString, matchString);
                    Double jwScore = jwDistance.apply(searchString, matchString) * 100;
                    props.put("cosScore", normalizeScore(score.intValue()).toString());
                    props.put("levDistance", normalizeScore(ldScore).toString());
                    props.put("jwScore", new Integer(jwScore.intValue()).toString());
                }
                data.add(props);
            }
            data.sort((o1, o2) -> Integer.decode(o2.get("cosScore")).compareTo(Integer.decode(o1.get("cosScore"))));
        } catch (IOException e) {
            e.printStackTrace();
        }
    } else {
        results.put("error", "ID " + pubmedId + " not found");
    }
    results.put("data", data);
    model.addAttribute("baseUrl", depositionUiURL);
    HttpHeaders responseHeaders = new HttpHeaders();
    responseHeaders.add("Content-Type", "application/json; charset=utf-8");
    return new ResponseEntity<>(results, responseHeaders, HttpStatus.OK);
}