本文整理汇总了Java中org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents方法的典型用法代码示例。如果您正苦于以下问题：Java BaseTokenStreamTestCase.assertTokenStreamContents方法的具体用法？Java BaseTokenStreamTestCase.assertTokenStreamContents怎么用？Java BaseTokenStreamTestCase.assertTokenStreamContents使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.lucene.analysis.BaseTokenStreamTestCase的用法示例。
在下文中一共展示了BaseTokenStreamTestCase.assertTokenStreamContents方法的7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，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: testHugeDoc
import org.apache.lucene.analysis.BaseTokenStreamTestCase; //导入方法依赖的package包/类
public void testHugeDoc() throws IOException {
StringBuilder sb = new StringBuilder();
char whitespace[] = new char[4094];
Arrays.fill(whitespace, ' ');
sb.append(whitespace);
sb.append("testing 1234");
String input = sb.toString();
UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer(newAttributeFactory(), new StringReader(input));
BaseTokenStreamTestCase.assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" });
}
示例2: testHugeDoc
import org.apache.lucene.analysis.BaseTokenStreamTestCase; //导入方法依赖的package包/类
public void testHugeDoc() throws IOException {
StringBuilder sb = new StringBuilder();
char whitespace[] = new char[4094];
Arrays.fill(whitespace, ' ');
sb.append(whitespace);
sb.append("testing 1234");
String input = sb.toString();
StandardTokenizer tokenizer = new StandardTokenizer(new StringReader(input));
BaseTokenStreamTestCase.assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" });
}
示例3: testHugeDoc
import org.apache.lucene.analysis.BaseTokenStreamTestCase; //导入方法依赖的package包/类
public void testHugeDoc() throws IOException {
StringBuilder sb = new StringBuilder();
char whitespace[] = new char[4094];
Arrays.fill(whitespace, ' ');
sb.append(whitespace);
sb.append("testing 1234");
String input = sb.toString();
UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
BaseTokenStreamTestCase.assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" });
}
示例4: testHugeDoc
import org.apache.lucene.analysis.BaseTokenStreamTestCase; //导入方法依赖的package包/类
public void testHugeDoc() throws IOException {
StringBuilder sb = new StringBuilder();
char whitespace[] = new char[4094];
Arrays.fill(whitespace, ' ');
sb.append(whitespace);
sb.append("testing 1234");
String input = sb.toString();
StandardTokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
BaseTokenStreamTestCase.assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" });
}
示例5: testConsume2
import org.apache.lucene.analysis.BaseTokenStreamTestCase; //导入方法依赖的package包/类
public void testConsume2() throws IOException {
BaseTokenStreamTestCase.assertTokenStreamContents(new EmptyTokenStream(), new String[0]);
}
示例6: testCustomTypes
import org.apache.lucene.analysis.BaseTokenStreamTestCase; //导入方法依赖的package包/类
@Test
public void testCustomTypes() throws Exception {
String testText = "I borrowed $5,400.00 at 25% interest-rate";
ResourceLoader loader = new SolrResourceLoader("solr/collection1");
Map<String,String> args = new HashMap<>();
args.put("luceneMatchVersion", TEST_VERSION_CURRENT.toString());
args.put("generateWordParts", "1");
args.put("generateNumberParts", "1");
args.put("catenateWords", "1");
args.put("catenateNumbers", "1");
args.put("catenateAll", "0");
args.put("splitOnCaseChange", "1");
/* default behavior */
WordDelimiterFilterFactory factoryDefault = new WordDelimiterFilterFactory(args);
factoryDefault.inform(loader);
TokenStream ts = factoryDefault.create(
new MockTokenizer(new StringReader(testText), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "I", "borrowed", "5", "540000", "400", "00", "at", "25", "interest", "interestrate", "rate" });
ts = factoryDefault.create(
new MockTokenizer(new StringReader("foo\u200Dbar"), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "foo", "foobar", "bar" });
/* custom behavior */
args = new HashMap<>();
// use a custom type mapping
args.put("luceneMatchVersion", TEST_VERSION_CURRENT.toString());
args.put("generateWordParts", "1");
args.put("generateNumberParts", "1");
args.put("catenateWords", "1");
args.put("catenateNumbers", "1");
args.put("catenateAll", "0");
args.put("splitOnCaseChange", "1");
args.put("types", "wdftypes.txt");
WordDelimiterFilterFactory factoryCustom = new WordDelimiterFilterFactory(args);
factoryCustom.inform(loader);
ts = factoryCustom.create(
new MockTokenizer(new StringReader(testText), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "I", "borrowed", "$5,400.00", "at", "25%", "interest", "interestrate", "rate" });
/* test custom behavior with a char > 0x7F, because we had to make a larger byte[] */
ts = factoryCustom.create(
new MockTokenizer(new StringReader("foo\u200Dbar"), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "foo\u200Dbar" });
}
示例7: testCustomTypes
import org.apache.lucene.analysis.BaseTokenStreamTestCase; //导入方法依赖的package包/类
@Test
public void testCustomTypes() throws Exception {
String testText = "I borrowed $5,400.00 at 25% interest-rate";
WordDelimiterFilterFactory factoryDefault = new WordDelimiterFilterFactory();
ResourceLoader loader = new SolrResourceLoader("solr/collection1");
Map<String,String> args = new HashMap<String,String>();
args.put("generateWordParts", "1");
args.put("generateNumberParts", "1");
args.put("catenateWords", "1");
args.put("catenateNumbers", "1");
args.put("catenateAll", "0");
args.put("splitOnCaseChange", "1");
/* default behavior */
factoryDefault.init(args);
factoryDefault.inform(loader);
TokenStream ts = factoryDefault.create(
new MockTokenizer(new StringReader(testText), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "I", "borrowed", "5", "400", "00", "540000", "at", "25", "interest", "rate", "interestrate" });
ts = factoryDefault.create(
new MockTokenizer(new StringReader("foo\u200Dbar"), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "foo", "bar", "foobar" });
/* custom behavior */
WordDelimiterFilterFactory factoryCustom = new WordDelimiterFilterFactory();
// use a custom type mapping
args.put("types", "wdftypes.txt");
factoryCustom.init(args);
factoryCustom.inform(loader);
ts = factoryCustom.create(
new MockTokenizer(new StringReader(testText), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "I", "borrowed", "$5,400.00", "at", "25%", "interest", "rate", "interestrate" });
/* test custom behavior with a char > 0x7F, because we had to make a larger byte[] */
ts = factoryCustom.create(
new MockTokenizer(new StringReader("foo\u200Dbar"), MockTokenizer.WHITESPACE, false));
BaseTokenStreamTestCase.assertTokenStreamContents(ts,
new String[] { "foo\u200Dbar" });
}