public String encode()

in src/main/java/org/apache/commons/codec/language/bm/PhoneticEngine.java [377:458]
59 lines of code
11 McCabe index (conditional complexity)

    public String encode(String input, final Languages.LanguageSet languageSet) {
        final Map<String, List<Rule>> rules = Rule.getInstanceMap(this.nameType, RuleType.RULES, languageSet);
        // rules common across many (all) languages
        final Map<String, List<Rule>> finalRules1 = Rule.getInstanceMap(this.nameType, this.ruleType, "common");
        // rules that apply to a specific language that may be ambiguous or wrong if applied to other languages
        final Map<String, List<Rule>> finalRules2 = Rule.getInstanceMap(this.nameType, this.ruleType, languageSet);

        // tidy the input
        // lower case is a locale-dependent operation
        input = input.toLowerCase(Locale.ENGLISH).replace('-', ' ').trim();

        if (this.nameType == NameType.GENERIC) {
            if (input.startsWith("d'")) { // check for d'
                final String remainder = input.substring(2);
                final String combined = "d" + remainder;
                return "(" + encode(remainder) + ")-(" + encode(combined) + ")";
            }
            for (final String l : NAME_PREFIXES.get(this.nameType)) {
                // handle generic prefixes
                if (input.startsWith(l + " ")) {
                    // check for any prefix in the words list
                    final String remainder = input.substring(l.length() + 1); // input without the prefix
                    final String combined = l + remainder; // input with prefix without space
                    return "(" + encode(remainder) + ")-(" + encode(combined) + ")";
                }
            }
        }

        final List<String> words = Arrays.asList(input.split("\\s+"));
        final List<String> words2 = new ArrayList<>();

        // special-case handling of word prefixes based upon the name type
        switch (this.nameType) {
        case SEPHARDIC:
            words.forEach(aWord -> {
                final String[] parts = aWord.split("'");
                words2.add(parts[parts.length - 1]);
            });
            words2.removeAll(NAME_PREFIXES.get(this.nameType));
            break;
        case ASHKENAZI:
            words2.addAll(words);
            words2.removeAll(NAME_PREFIXES.get(this.nameType));
            break;
        case GENERIC:
            words2.addAll(words);
            break;
        default:
            throw new IllegalStateException("Unreachable case: " + this.nameType);
        }

        if (this.concat) {
            // concat mode enabled
            input = join(words2, " ");
        } else if (words2.size() == 1) {
            // not a multi-word name
            input = words.iterator().next();
        } else {
            // encode each word in a multi-word name separately (normally used for approx matches)
            final StringBuilder result = new StringBuilder();
            words2.forEach(word -> result.append("-").append(encode(word)));
            // return the result without the leading "-"
            return result.substring(1);
        }

        PhonemeBuilder phonemeBuilder = PhonemeBuilder.empty(languageSet);

        // loop over each char in the input - we will handle the increment manually
        for (int i = 0; i < input.length();) {
            final RulesApplication rulesApplication =
                    new RulesApplication(rules, input, phonemeBuilder, i, maxPhonemes).invoke();
            i = rulesApplication.getI();
            phonemeBuilder = rulesApplication.getPhonemeBuilder();
        }

        // Apply the general rules
        phonemeBuilder = applyFinalRules(phonemeBuilder, finalRules1);
        // Apply the language-specific rules
        phonemeBuilder = applyFinalRules(phonemeBuilder, finalRules2);

        return phonemeBuilder.makeString();
    }