Example usage for org.apache.lucene.analysis.miscellaneous WordDelimiterIterator getType

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.miscellaneous WordDelimiterIterator getType.

Prototype

public static byte getType(int ch) 

Source Link

Document

Computes the type of the given character

Usage

From source file:org.elasticsearch.analysis.common.WordDelimiterTokenFilterFactory.java

License:Apache License

/**
 * parses a list of MappingCharFilter style rules into a custom byte[] type table
 *//*from w  w  w  . ja  v  a2  s  .co  m*/
static byte[] parseTypes(Collection<String> rules) {
    SortedMap<Character, Byte> typeMap = new TreeMap<>();
    for (String rule : rules) {
        Matcher m = typePattern.matcher(rule);
        if (!m.find())
            throw new RuntimeException("Invalid Mapping Rule : [" + rule + "]");
        String lhs = parseString(m.group(1).trim());
        Byte rhs = parseType(m.group(2).trim());
        if (lhs.length() != 1)
            throw new RuntimeException(
                    "Invalid Mapping Rule : [" + rule + "]. Only a single character is allowed.");
        if (rhs == null)
            throw new RuntimeException("Invalid Mapping Rule : [" + rule + "]. Illegal type.");
        typeMap.put(lhs.charAt(0), rhs);
    }

    // ensure the table is always at least as big as DEFAULT_WORD_DELIM_TABLE for performance
    byte types[] = new byte[Math.max(typeMap.lastKey() + 1,
            WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE.length)];
    for (int i = 0; i < types.length; i++)
        types[i] = WordDelimiterIterator.getType(i);
    for (Map.Entry<Character, Byte> mapping : typeMap.entrySet())
        types[mapping.getKey()] = mapping.getValue();
    return types;
}

---

From source file:org.elasticsearch.index.analysis.WordDelimiterTokenFilterFactory.java

License:Apache License

/**
 * parses a list of MappingCharFilter style rules into a custom byte[] type table
 *//*from  www . j av  a  2 s .c om*/
private byte[] parseTypes(Collection<String> rules) {
    SortedMap<Character, Byte> typeMap = new TreeMap<Character, Byte>();
    for (String rule : rules) {
        Matcher m = typePattern.matcher(rule);
        if (!m.find())
            throw new RuntimeException("Invalid Mapping Rule : [" + rule + "]");
        String lhs = parseString(m.group(1).trim());
        Byte rhs = parseType(m.group(2).trim());
        if (lhs.length() != 1)
            throw new RuntimeException(
                    "Invalid Mapping Rule : [" + rule + "]. Only a single character is allowed.");
        if (rhs == null)
            throw new RuntimeException("Invalid Mapping Rule : [" + rule + "]. Illegal type.");
        typeMap.put(lhs.charAt(0), rhs);
    }

    // ensure the table is always at least as big as DEFAULT_WORD_DELIM_TABLE for performance
    byte types[] = new byte[Math.max(typeMap.lastKey() + 1,
            WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE.length)];
    for (int i = 0; i < types.length; i++)
        types[i] = WordDelimiterIterator.getType(i);
    for (Map.Entry<Character, Byte> mapping : typeMap.entrySet())
        types[mapping.getKey()] = mapping.getValue();
    return types;
}

---