You must specify the required {@link Version} - * compatibility when creating UAX29URLEmailTokenizer: - *
- * See Unicode Line Breaking Algorithm: http://www.unicode.org/reports/tr14/#SA
- * @deprecated use {@link #TOKEN_TYPES} instead
- */
- @Deprecated
- public static final String SOUTH_EAST_ASIAN_TYPE = TOKEN_TYPES[SOUTHEAST_ASIAN];
-
- /** @deprecated use {@link #TOKEN_TYPES} instead */
- @Deprecated
- public static final String IDEOGRAPHIC_TYPE = TOKEN_TYPES[IDEOGRAPHIC];
-
- /** @deprecated use {@link #TOKEN_TYPES} instead */
- @Deprecated
- public static final String HIRAGANA_TYPE = TOKEN_TYPES[HIRAGANA];
-
- /** @deprecated use {@link #TOKEN_TYPES} instead */
- @Deprecated
- public static final String KATAKANA_TYPE = TOKEN_TYPES[KATAKANA];
-
- /** @deprecated use {@link #TOKEN_TYPES} instead */
- @Deprecated
- public static final String HANGUL_TYPE = TOKEN_TYPES[HANGUL];
-
- private int maxTokenLength = StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH;
-
- /** Set the max allowed token length. Any token longer
- * than this is skipped. */
- public void setMaxTokenLength(int length) {
- this.maxTokenLength = length;
- }
-
- /** @see #setMaxTokenLength */
- public int getMaxTokenLength() {
- return maxTokenLength;
- }
-
- /** @deprecated use {@link #UAX29URLEmailTokenizer(Version, Reader)} instead. */
- @Deprecated
- public UAX29URLEmailTokenizer(Reader input) {
- this(Version.LUCENE_31, input);
- }
-
- /** @deprecated use {@link #UAX29URLEmailTokenizer(Version, Reader)} instead. */
- @Deprecated
- public UAX29URLEmailTokenizer(InputStream input) {
- this(Version.LUCENE_31, new InputStreamReader(input));
- }
-
- /** @deprecated use {@link #UAX29URLEmailTokenizer(Version, AttributeSource, Reader)} instead. */
- @Deprecated
- public UAX29URLEmailTokenizer(AttributeSource source, Reader input) {
- this(Version.LUCENE_31, source, input);
- }
-
- /** @deprecated use {@link #UAX29URLEmailTokenizer(Version, AttributeSource.AttributeFactory, Reader)} instead. */
- @Deprecated
- public UAX29URLEmailTokenizer(AttributeFactory factory, Reader input) {
- this(Version.LUCENE_31, factory, input);
- }
-
- /**
- * Creates a new instance of the UAX29URLEmailTokenizer. Attaches
- * the input to the newly created JFlex scanner.
- *
- * @param input The input reader
- */
- public UAX29URLEmailTokenizer(Version matchVersion, Reader input) {
- super(input);
- this.scanner = getScannerFor(matchVersion, input);
- }
-
- /**
- * Creates a new UAX29URLEmailTokenizer with a given {@link AttributeSource}.
- */
- public UAX29URLEmailTokenizer(Version matchVersion, AttributeSource source, Reader input) {
- super(source, input);
- this.scanner = getScannerFor(matchVersion, input);
- }
-
- /**
- * Creates a new UAX29URLEmailTokenizer with a given {@link AttributeFactory}
- */
- public UAX29URLEmailTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
- super(factory, input);
- this.scanner = getScannerFor(matchVersion, input);
- }
-
- private static StandardTokenizerInterface getScannerFor(Version matchVersion, Reader input) {
- if (matchVersion.onOrAfter(Version.LUCENE_34)) {
- return new UAX29URLEmailTokenizerImpl(input);
- } else {
- return new UAX29URLEmailTokenizerImpl31(input);
- }
- }
-
- // this tokenizer generates three attributes:
- // term offset, positionIncrement and type
- private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
- private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
- private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
- private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
-
- @Override
- public final boolean incrementToken() throws IOException {
- clearAttributes();
- int posIncr = 1;
-
- while(true) {
- int tokenType = scanner.getNextToken();
-
- if (tokenType == StandardTokenizerInterface.YYEOF) {
- return false;
- }
-
- if (scanner.yylength() <= maxTokenLength) {
- posIncrAtt.setPositionIncrement(posIncr);
- scanner.getText(termAtt);
- final int start = scanner.yychar();
- offsetAtt.setOffset(correctOffset(start), correctOffset(start+termAtt.length()));
- typeAtt.setType(TOKEN_TYPES[tokenType]);
- return true;
- } else
- // When we skip a too-long term, we still increment the
- // position increment
- posIncr++;
- }
- }
-
- @Override
- public final void end() {
- // set final offset
- int finalOffset = correctOffset(scanner.yychar() + scanner.yylength());
- offsetAtt.setOffset(finalOffset, finalOffset);
- }
-
- @Override
- public void reset(Reader reader) throws IOException {
- super.reset(reader);
- scanner.yyreset(reader);
- }
-}