Examples with GeocoordMatch org.opensextant.extractors.xcoord.GeocoordMatch used on opensource projects

Example 1 with GeocoordMatch

use of org.opensextant.extractors.xcoord.GeocoordMatch in project Xponents by OpenSextant.

the class Transforms method parseAnnotation.

/**
	 * Convert JSON object for an annotation into a Xponents TextMatch instance.
	 * Parsing data from JSON/REST representations has very limited capability compared to
	 * using Java API for processing routines directly.
	 * 
	 * @param data
	 * @return
	 * @throws JSONException
	 */
public static TextMatch parseAnnotation(Object data) throws JSONException {
    if (!(data instanceof JSONObject)) {
        return null;
    }
    TextMatch m = null;
    JSONObject a = (JSONObject) data;
    TaxonMatch x = null;
    String typ = a.getString("type");
    String text = a.getString("matchtext");
    switch(typ) {
        case "place":
            PlaceCandidate placeMatch = new PlaceCandidate();
            Place geo = new Place();
            placeMatch.setText(text);
            Transforms.parseGeocoding(geo, a);
            placeMatch.setConfidence(a.optInt("confidence", -1));
            placeMatch.choose(geo);
            m = placeMatch;
            break;
        case "coordinate":
            GeocoordMatch coord = new GeocoordMatch();
            Place coordLoc = new Place();
            coord.setText(text);
            // How awful:.... need to parse Coord directly
            Transforms.parseGeocoding(coordLoc, a);
            coord.setLatLon(coordLoc);
            coord.setMethod(coordLoc.getMethod());
            /* TODO: GeocoordMatch needs to support setters for Geocoding here.
			 * missing reverse geo info
			 * 
			 *  cc, adm1
			 *  
			 */
            m = coord;
            break;
        case "country":
            PlaceCandidate countryMatch = new PlaceCandidate();
            Place cc = new Place();
            countryMatch.setText(text);
            cc.setName(text);
            countryMatch.setConfidence(a.optInt("confidence", -1));
            cc.setCountryCode(a.getString("cc"));
            countryMatch.isCountry = true;
            countryMatch.choose(cc);
            m = countryMatch;
            break;
        case "person":
            x = new TaxonMatch();
            Transforms.parseTaxon(x, "person", a);
            m = x;
            break;
        case "org":
            x = new TaxonMatch();
            Transforms.parseTaxon(x, "org", a);
            m = x;
            break;
        case "taxon":
            x = new TaxonMatch();
            Transforms.parseTaxon(x, "taxon", a);
            m = x;
            break;
        default:
            throw new JSONException("Unknown Annotation " + typ);
    }
    m.setType(typ);
    m.start = a.getInt("offset");
    m.end = m.start + a.getInt("length");
    return m;
}

Example 2 with GeocoordMatch

use of org.opensextant.extractors.xcoord.GeocoordMatch in project Xponents by OpenSextant.

the class XponentsGeotagger method format.

private Representation format(List<TextMatch> matches, RequestParameters jobParams) throws JSONException {
    Representation result = null;
    int tagCount = 0;
    JSONObject resultContent = new JSONObject();
    JSONObject resultMeta = new JSONObject();
    resultMeta.put("status", "ok");
    resultMeta.put("numfound", 0);
    JSONArray resultArray = new JSONArray();
    /*
		 * Super loop: Iterate through all found entities. record Taxons as
		 * person or orgs record Geo tags as country, place, or geo. geo =
		 * geocoded place or parsed coordinate (MGRS, DMS, etc)
		 * 
		 */
    for (TextMatch name : matches) {
        /*            
			 * ==========================
			 * ANNOTATIONS: non-geographic entities that are filtered out, but worth tracking
			 * ==========================             
			 */
        if (name instanceof TaxonMatch) {
            if (jobParams.output_taxons) {
                TaxonMatch match = (TaxonMatch) name;
                ++tagCount;
                for (Taxon n : match.getTaxons()) {
                    JSONObject node = populateMatch(name);
                    String t = "taxon";
                    String taxon_name = n.name.toLowerCase();
                    if (taxon_name.startsWith("org.")) {
                        t = "org";
                    } else if (taxon_name.startsWith("person.")) {
                        t = "person";
                    }
                    node.put("type", t);
                    // Name of taxon
                    node.put("taxon", n.name);
                    // Name of catalog or source
                    node.put("catalog", n.catalog);
                    // node.put("filtered-out", true);
                    resultArray.put(node);
                    break;
                }
            }
            continue;
        }
        // Ignore non-place tags
        if (name.isFilteredOut() || !(name instanceof PlaceCandidate || name instanceof GeocoordMatch)) {
            continue;
        }
        JSONObject node = populateMatch(name);
        /*
			 * ==========================
			 * ANNOTATIONS: coordinates
			 * ==========================
			 */
        if (name instanceof GeocoordMatch) {
            ++tagCount;
            GeocoordMatch geo = (GeocoordMatch) name;
            node.put("type", "coordinate");
            Transforms.createGeocoding(geo, node);
            resultArray.put(node);
            continue;
        }
        if (name.isFilteredOut()) {
            debug("Filtered out " + name.getText());
            continue;
        }
        PlaceCandidate place = (PlaceCandidate) name;
        Place resolvedPlace = place.getChosen();
        /*
			 * ==========================
			 * ANNOTATIONS: countries, places, etc.
			 * ==========================
			 */
        /*
			 * Accept all country names as potential geotags Else if name can be
			 * filtered out, do it now. Otherwise it is a valid place name to
			 * consider
			 */
        ++tagCount;
        if (place.isCountry) {
            node.put("name", resolvedPlace.getPlaceName());
            node.put("type", "country");
            node.put("cc", resolvedPlace.getCountryCode());
            node.put("confidence", place.getConfidence());
        } else {
            /*
				 * Conf = 20 or greater to be geocoded.
				 */
            Transforms.createGeocoding(resolvedPlace, node);
            node.put("name", resolvedPlace.getPlaceName());
            node.put("type", "place");
            node.put("confidence", place.getConfidence());
            if (place.getConfidence() <= 10) {
                node.put("filtered-out", true);
            }
        }
        resultArray.put(node);
    }
    resultMeta.put("numfound", tagCount);
    resultContent.put("response", resultMeta);
    resultContent.put("annotations", resultArray);
    result = new JsonRepresentation(resultContent.toString(2));
    result.setCharacterSet(CharacterSet.UTF_8);
    return result;
}

Example 3 with GeocoordMatch

use of org.opensextant.extractors.xcoord.GeocoordMatch in project Xponents by OpenSextant.

the class TestXCoordReporter method save_result.

/**
     * Coordinate Test/Eval format
     *
     *
     * Result ID, CCE family, pattern ID, status, message // Reason for failure
     * Result ID, CCE family, pattern ID, status, Match ID, matchtext, lat, lon
     * etc. // Success implied by match
     *
     * @TODO: use TestCase here or rely on truth evaluation in Python
     * GeocoderEval?
     * @param t
     * @param results
     * @throws IOException
     */
public void save_result(GeocoordTestCase t, TextMatchResult results) throws IOException {
    Map<String, Object> row = null;
    if (!results.matches.isEmpty()) {
        //
        for (TextMatch tm : results.matches) {
            GeocoordMatch m = (GeocoordMatch) tm;
            if (!full_report && (m.is_submatch || m.is_duplicate)) {
                // Ignore submatches and duplicates
                continue;
            }
            row = createTestCase(t);
            row.put(header[6], results.result_id);
            row.put(header[7], (full_report & m.is_submatch) ? "IGNORE" : "PASS");
            String msg = results.message;
            if (m.is_submatch) {
                msg += "; Is Submatch";
            }
            row.put(header[8], msg);
            row.put(header[9], XConstants.get_CCE_family(m.cce_family_id));
            row.put(header[10], m.pattern_id);
            row.put(header[11], m.getText());
            row.put(header[12], "" + m.formatLatitude());
            row.put(header[13], "" + m.formatLongitude());
            String mgrs = "";
            try {
                mgrs = m.toMGRS();
            } catch (Exception err) {
            }
            row.put(header[14], mgrs);
            row.put(header[15], m.formatPrecision());
            row.put(header[16], new Long(m.start));
            report.write(row, header, xcoordResultsSpec);
        }
    } else {
        row = createTestCase(t);
        row.put(header[6], results.result_id);
        boolean expected_failure = false;
        if (t != null) {
            expected_failure = !t.true_positive;
        } else {
            // If the match message contains a test payload from the test cases
            //
            String test_status = results.get_trace().toUpperCase();
            expected_failure = test_status.contains("FAIL");
        }
        // True Negative -- you ignored one correctly
        row.put(header[7], expected_failure ? "PASS" : "FAIL");
        row.put(header[8], results.get_trace());
        report.write(row, header, xcoordResultsSpec);
    }
}

Example 4 with GeocoordMatch

use of org.opensextant.extractors.xcoord.GeocoordMatch in project Xponents by OpenSextant.

the class TestGazMatcher method summarizeFindings.

public static void summarizeFindings(List<TextMatch> matches) {
    Set<String> placeNames = new TreeSet<>();
    Set<String> countryNames = new TreeSet<>();
    Set<String> coordinates = new TreeSet<>();
    System.out.println("MENTIONS ALL == " + matches.size());
    for (TextMatch tm : matches) {
        printGeoTags(tm);
        if (tm instanceof PlaceCandidate) {
            PlaceCandidate p = (PlaceCandidate) tm;
            if (tm.isFilteredOut()) {
                print("Filtered Out.  Rules = " + p.getRules());
                continue;
            }
            if (!p.getRules().isEmpty()) {
                print("Rules = " + p.getRules());
            }
            if (p.isCountry) {
                countryNames.add(p.getText());
            } else if (p.getChosen() != null) {
                print(String.format("\tgeocoded @ %s with conf=%d", p.getChosen(), p.getConfidence()));
                ScoredPlace alt = p.getSecondChoice();
                if (alt != null) {
                    print(String.format("\tgeocoded @ %s second place", alt));
                }
                placeNames.add(p.getText());
            } else {
                placeNames.add(p.getText());
            }
        } else if (tm.isFilteredOut()) {
            System.out.println("\t(filtered out: " + tm.getText() + ")");
            continue;
        }
        if (tm instanceof GeocoordMatch) {
            GeocoordMatch geo = (GeocoordMatch) tm;
            coordinates.add(geo.getText());
            if (geo.getRelatedPlace() != null) {
                System.out.println("Coordinate at place named " + geo.getRelatedPlace());
            }
        }
    }
    System.out.println("MENTIONS DISTINCT PLACES == " + placeNames.size());
    System.out.println(placeNames);
    System.out.println("MENTIONS COUNTRIES == " + countryNames.size());
    System.out.println(countryNames);
    System.out.println("MENTIONS COORDINATES == " + coordinates.size());
    System.out.println(coordinates);
}

Example 5 with GeocoordMatch

use of org.opensextant.extractors.xcoord.GeocoordMatch in project Xponents by OpenSextant.

the class PlaceGeocoder method evaluateCoordinate.

/**
     * A method to retrieve one or more distinct admin boundaries containing the
     * coordinate. This depends on resolution of gazetteer at hand.
     *
     * @param g
     *            geocoordinate found in text.
     * @return Place object near the geocoding.
     * @throws SolrServerException
     *             a query against the Solr index may throw a Solr error.
     */
public Place evaluateCoordinate(Geocoding g) throws SolrServerException {
    Place found = getGazetteer().placeAt(g, COORDINATE_PROXIMITY_CITY_THRESHOLD, "P");
    if (found != null) {
        if (g instanceof GeocoordMatch) {
            ((GeocoordMatch) g).setRelatedPlace(found);
        }
        return found;
    }
    found = getGazetteer().placeAt(g, COORDINATE_PROXIMITY_ADM1_THRESHOLD, "A");
    if (found != null) {
        if (g instanceof GeocoordMatch) {
            ((GeocoordMatch) g).setRelatedPlace(found);
        }
        return found;
    }
    return null;
}