Examples with PlaceCandidate org.opensextant.extractors.geo.PlaceCandidate used on opensource projects

Example 11 with PlaceCandidate

use of org.opensextant.extractors.geo.PlaceCandidate in project Xponents by OpenSextant.

the class GeoTaggerMapper method match2JSON.

/**
     * Convert a TextMatch (Place, Taxon, Pattern, etc.) and convert to JSON.
     * This outputs only geocoding objects -- PlaceCandidate or GeocoordMatch. 
     * Attributes reported are gazetteer metadata, precision, country code, confidence of match, etc.
     * 
     * @param tm
     * @return
     */
public static final JSONObject match2JSON(TextMatch tm) {
    JSONObject j = prepareOutput(tm);
    if (tm instanceof PlaceCandidate) {
        PlaceCandidate candidate = (PlaceCandidate) tm;
        if (candidate.isCountry) {
            j.put("type", "country");
        } else {
            j.put("type", "place");
        }
        /* Geotagging can be noisy -- accept only highest confidence matches.
             * 
             */
        if (candidate.getFirstChoice() != null) {
            addPlaceData(candidate.getFirstChoice(), j);
            j.put("confidence", candidate.getConfidence());
            if (candidate.getSecondChoice() != null) {
                JSONObject alt = new JSONObject();
                addPlaceData(candidate.getSecondChoice(), alt);
                alt.put("score", candidate.getSecondChoice().getScore());
                j.put("alt-place", alt);
            }
        }
    } else if (tm instanceof GeocoordMatch) {
        /* Geocoding coordinates can also be noisy.  Accept only high precision matches.
             * E.g., +/- 10KM
             */
        GeocoordMatch geo = (GeocoordMatch) tm;
        addPlaceData(geo, j);
        j.put("type", "coordinate");
        j.put("method", geo.getMethod());
        j.put("confidence", geo.getConfidence());
        if (geo.getRelatedPlace() != null) {
            JSONObject alt = new JSONObject();
            addPlaceData(geo.getRelatedPlace(), alt);
            j.put("related-place", alt);
        }
    }
    return j;
}

Example 12 with PlaceCandidate

use of org.opensextant.extractors.geo.PlaceCandidate in project Xponents by OpenSextant.

the class TestGazMatcher method main.

/**
     * Do a basic test. Requirements include setting opensextant.solr to solr
     * core home. (Xponents/solr, by default) USAGE:
     * 
     * TestGazMatcher file
     * 
     * Prints: all matched, filtered place mentions distinct places distinct
     * countries
     */
public static void main(String[] args) throws Exception {
    GazetteerMatcher sm = new GazetteerMatcher(true);
    URL filterFile = TestGazMatcher.class.getResource("/test-filter.txt");
    if (filterFile == null) {
        System.err.println("This test requires a 'test-filter.txt' file with non-place names in it." + "\nThese filters should match up with your test documents");
    }
    MatchFilter filt = new MatchFilter(filterFile);
    sm.setMatchFilter(filt);
    try {
        String docContent = "We drove to Sin City. The we drove to -$IN ĆITŸ .";
        System.out.println(docContent);
        List<PlaceCandidate> matches = sm.tagText(docContent, "main-test");
        for (PlaceCandidate pc : matches) {
            printGeoTags(pc);
        }
        docContent = "Is there some city in 刘家埝 written in Chinese?";
        matches = sm.tagCJKText(docContent, "main-test");
        for (PlaceCandidate pc : matches) {
            printGeoTags(pc);
        }
        docContent = "Where is seoul?";
        matches = sm.tagText(docContent, "main-test");
        for (PlaceCandidate pc : matches) {
            printGeoTags(pc);
        }
        String buf = FileUtility.readFile(args[0]);
        matches = sm.tagText(buf, "main-test", true);
        summarizeFindings(copyFrom(matches));
    } catch (Exception err) {
        err.printStackTrace();
    } finally {
        sm.shutdown();
    }
}

Example 13 with PlaceCandidate

use of org.opensextant.extractors.geo.PlaceCandidate in project Xponents by OpenSextant.

the class TestPersonFilter method test.

@Test
public void test() {
    // Set classpath to point to ./gazetteer/conf
    URL p1 = PlaceGeocoder.class.getResource("/filters/person-name-filter.txt");
    URL p2 = PlaceGeocoder.class.getResource("/filters/person-title-filter.txt");
    URL p3 = PlaceGeocoder.class.getResource("/filters/person-suffix-filter.txt");
    try {
        PersonNameFilter filt = new PersonNameFilter(p1, p2, p3);
        PlaceCandidate p = new PlaceCandidate();
        p.setText("John Doe");
        p.setPrematchTokens(null);
        p.setPostmatchTokens(null);
        filt.evaluate(p, null);
        print(p.getText() + " pass? " + p.isFilteredOut());
        p.setPrematchTokens("             ".split(" "));
        p.setPostmatchTokens("             ".split(" "));
        filt.evaluate(p, null);
        print(p.getText() + " pass? " + p.isFilteredOut());
        p.setPrematchTokens("this is Mr. ".split(" "));
        p.setPostmatchTokens(null);
        filt.evaluate(p, null);
        print(p.getText() + " pass? " + p.isFilteredOut());
        p.setPrematchTokens("this is Mr. ".split(" "));
        p.setPostmatchTokens(" and his wife lives in the city...".split(" "));
        filt.evaluate(p, null);
        print(p.getText() + " pass? " + p.isFilteredOut());
    } catch (ConfigException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
        fail("Configuration problem -- set CLASSPATH to include ./conf");
    }
}