sciname regex

Sciname.java

    static class Name {
        public int key;
        public int nameKey;
        public String rank;
        public String nameType;
        public String canonicalName;
        public String authorship;
        public String scientificName;
    }

    public void testRegex() throws Exception {
        final Pattern regex = Pattern.compile("^([A-Z][a-z][a-z-]+(:? [a-z][a-z]+)?(:? (:?[a-z]{1,5}\\.? )?[a-z][a-z-]+)?)\\b");
        String base = "http://api.gbif.org/v1/species/";

        Random rnd = new Random();
        ObjectMapper mapper = new ObjectMapper();
        mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);

        while (true) {
            int id = 100000000 + rnd.nextInt(20000000);
            try {
                URL url = new URL(base + id);
                Name name = mapper.readValue(url, Name.class);

                System.out.println(String.format("%12s %s", name.nameType, name.scientificName));
                Matcher m  = regex.matcher(name.scientificName);
                if (m.find()) {
                    String canonical = m.group();
                    if (!canonical.equalsIgnoreCase(name.canonicalName)) {
                        System.out.println("  -> " + m.group());
                    }
                } else {
                    System.out.println("  -> UNPARSABLE " + name.nameType);
                }
            } catch (IOException e) {
                // ignore
            }
        }
    }