本文整理汇总了Java中org.apache.lucene.analysis.core.LetterTokenizer类的典型用法代码示例。如果您正苦于以下问题:Java LetterTokenizer类的具体用法?Java LetterTokenizer怎么用?Java LetterTokenizer使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
LetterTokenizer类属于org.apache.lucene.analysis.core包,在下文中一共展示了LetterTokenizer类的10个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Java代码示例。
示例1: main
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
System.out.println(NumberUtils.isDigits("12345"));
System.out.println(NumberUtils.isDigits("12345.1"));
System.out.println(NumberUtils.isDigits("12345,2"));
System.out.println(NumberUtils.isNumber("12345"));
System.out.println(NumberUtils.isNumber("12345.1"));
System.out.println(NumberUtils.isNumber("12345,2".replace(",", ".")));
System.out.println(NumberUtils.isNumber("12345,2"));
StringReader input = new StringReader(
"Правя тест на класификатор и после др.Дулитъл, пада.br2n ще се оправя с данните! които,са много зле. Но това е по-добре. Но24"
.replaceAll("br2n", ""));
LetterTokenizer tokenizer = new LetterTokenizer();
tokenizer.setReader(input);
TokenFilter stopFilter = new StopFilter(tokenizer, BULGARIAN_STOP_WORDS_SET);
TokenFilter length = new LengthFilter(stopFilter, 3, 1000);
TokenFilter stemmer = new BulgarianStemFilter(length);
TokenFilter ngrams = new ShingleFilter(stemmer, 2, 2);
try (TokenFilter filter = ngrams) {
Attribute termAtt = filter.addAttribute(CharTermAttribute.class);
filter.reset();
while (filter.incrementToken()) {
String word = termAtt.toString().replaceAll(",", "\\.").replaceAll("\n|\r", "");
System.out.println(word);
}
}
}
开发者ID:mhardalov,项目名称:news-credibility,代码行数:32,代码来源:EgdeMain.java
示例2: testCrossPlaneNormalization
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
public void testCrossPlaneNormalization() throws IOException {
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader) {
@Override
protected int normalize(int c) {
if (c > 0xffff) {
return 'δ';
} else {
return c;
}
}
};
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
int num = 1000 * RANDOM_MULTIPLIER;
for (int i = 0; i < num; i++) {
String s = TestUtil.randomUnicodeString(random());
TokenStream ts = analyzer.tokenStream("foo", s);
try {
ts.reset();
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
while (ts.incrementToken()) {
String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
cp = highlightedText.codePointAt(j);
assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
}
}
ts.end();
} finally {
IOUtils.closeWhileHandlingException(ts);
}
}
// just for fun
checkRandomData(random(), analyzer, num);
}
开发者ID:europeana,项目名称:search,代码行数:40,代码来源:TestCharTokenizers.java
示例3: testCrossPlaneNormalization2
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
public void testCrossPlaneNormalization2() throws IOException {
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader) {
@Override
protected int normalize(int c) {
if (c <= 0xffff) {
return 0x1043C;
} else {
return c;
}
}
};
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
int num = 1000 * RANDOM_MULTIPLIER;
for (int i = 0; i < num; i++) {
String s = TestUtil.randomUnicodeString(random());
TokenStream ts = analyzer.tokenStream("foo", s);
try {
ts.reset();
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
while (ts.incrementToken()) {
String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
cp = highlightedText.codePointAt(j);
assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
}
}
ts.end();
} finally {
IOUtils.closeWhileHandlingException(ts);
}
}
// just for fun
checkRandomData(random(), analyzer, num);
}
开发者ID:europeana,项目名称:search,代码行数:40,代码来源:TestCharTokenizers.java
示例4: testCrossPlaneNormalization
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
public void testCrossPlaneNormalization() throws IOException {
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, reader) {
@Override
protected int normalize(int c) {
if (c > 0xffff) {
return 'δ';
} else {
return c;
}
}
};
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
int num = 1000 * RANDOM_MULTIPLIER;
for (int i = 0; i < num; i++) {
String s = _TestUtil.randomUnicodeString(random());
TokenStream ts = analyzer.tokenStream("foo", new StringReader(s));
ts.reset();
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
while (ts.incrementToken()) {
String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
cp = highlightedText.codePointAt(j);
assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
}
}
ts.end();
ts.close();
}
// just for fun
checkRandomData(random(), analyzer, num);
}
开发者ID:pkarmstr,项目名称:NYBC,代码行数:37,代码来源:TestCharTokenizers.java
示例5: testCrossPlaneNormalization2
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
public void testCrossPlaneNormalization2() throws IOException {
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, reader) {
@Override
protected int normalize(int c) {
if (c <= 0xffff) {
return 0x1043C;
} else {
return c;
}
}
};
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
int num = 1000 * RANDOM_MULTIPLIER;
for (int i = 0; i < num; i++) {
String s = _TestUtil.randomUnicodeString(random());
TokenStream ts = analyzer.tokenStream("foo", new StringReader(s));
ts.reset();
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
while (ts.incrementToken()) {
String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
cp = highlightedText.codePointAt(j);
assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
}
}
ts.end();
ts.close();
}
// just for fun
checkRandomData(random(), analyzer, num);
}
开发者ID:pkarmstr,项目名称:NYBC,代码行数:37,代码来源:TestCharTokenizers.java
示例6: testCrossPlaneNormalization
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
public void testCrossPlaneNormalization() throws IOException {
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, reader) {
@Override
protected int normalize(int c) {
if (c > 0xffff) {
return 'δ';
} else {
return c;
}
}
};
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
int num = 1000 * RANDOM_MULTIPLIER;
for (int i = 0; i < num; i++) {
String s = _TestUtil.randomUnicodeString(random());
TokenStream ts = analyzer.tokenStream("foo", s);
try {
ts.reset();
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
while (ts.incrementToken()) {
String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
cp = highlightedText.codePointAt(j);
assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
}
}
ts.end();
} finally {
IOUtils.closeWhileHandlingException(ts);
}
}
// just for fun
checkRandomData(random(), analyzer, num);
}
开发者ID:jimaguere,项目名称:Maskana-Gestor-de-Conocimiento,代码行数:40,代码来源:TestCharTokenizers.java
示例7: testCrossPlaneNormalization2
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
public void testCrossPlaneNormalization2() throws IOException {
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, reader) {
@Override
protected int normalize(int c) {
if (c <= 0xffff) {
return 0x1043C;
} else {
return c;
}
}
};
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
int num = 1000 * RANDOM_MULTIPLIER;
for (int i = 0; i < num; i++) {
String s = _TestUtil.randomUnicodeString(random());
TokenStream ts = analyzer.tokenStream("foo", s);
try {
ts.reset();
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
while (ts.incrementToken()) {
String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
cp = highlightedText.codePointAt(j);
assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
}
}
ts.end();
} finally {
IOUtils.closeWhileHandlingException(ts);
}
}
// just for fun
checkRandomData(random(), analyzer, num);
}
开发者ID:jimaguere,项目名称:Maskana-Gestor-de-Conocimiento,代码行数:40,代码来源:TestCharTokenizers.java
示例8: create
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
@Override
public Tokenizer create() {
return new LetterTokenizer();
}
开发者ID:justor,项目名称:elasticsearch_my,代码行数:5,代码来源:LetterTokenizerFactory.java
示例9: create
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
@Override
public LetterTokenizer create(Reader input) {
return new LetterTokenizer(luceneMatchVersion, input);
}
开发者ID:pkarmstr,项目名称:NYBC,代码行数:5,代码来源:LetterTokenizerFactory.java
示例10: tokenStream
import org.apache.lucene.analysis.core.LetterTokenizer; //导入依赖的package包/类
@Override
public TokenStream tokenStream(String fieldName, Reader reader) {
return new MetaphoneReplacementFilter(new LetterTokenizer(reader));
}
开发者ID:xuzhikethinker,项目名称:t4f-data,代码行数:5,代码来源:MetaphoneReplacementAnalyzer.java
注:本文中的org.apache.lucene.analysis.core.LetterTokenizer类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论