Java IWiktionaryPage类代码示例

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
public void testWater() throws Exception {
	IWiktionaryPage page = parse("water.txt");
	IWiktionaryEntry entry;

	entry = page.getEntry(0);
	assertEquals(Language.ENGLISH, entry.getWordLanguage());
	assertEquals(PartOfSpeech.NOUN, entry.getPartOfSpeech());
	assertEquals("{{PIE root|en|wed}}\n" +
		"From {{etyl|enm|en}} {{m|enm|water|sc=Latn}}, from {{etyl|ang|en}} {{m|ang|wæter||water|sc=Latn}}, from " +
		"{{etyl|gem-pro|en}} {{m|gem-pro|*watōr||water}}, from {{etyl|ine-pro|en}} {{m|ine-pro|*wódr̥||water}}.\n" +
		"{{rel-top|cognates}}\n" +
		"Cognate with {{etyl|sco|-}} {{m|sco|wattir|sc=Latn}}, {{m|sco|watir||water|sc=Latn}}, " +
		"{{etyl|frr|-}} {{m|frr|weeter||water|sc=Latn}}, {{etyl|stq|-}} {{m|stq|woater||water|sc=Latn}}, " +
		"{{etyl|fy|-}} {{m|fy|wetter||water|sc=Latn}}, {{etyl|nl|-}} {{m|nl|water||water|sc=Latn}}, " +
		"{{etyl|nds|-}} {{m|nds|Water||water|sc=Latn}}, {{etyl|de|-}} {{m|de|Wasser|sc=Latn}}, {{etyl|sv|-}} " +
		"{{m|sv|vatten||water|sc=Latn}}, {{etyl|is|-}} {{m|is|vatn||water|sc=Latn}}, {{etyl|sga|-}} coin " +
		"{{m|sga|fodorne||otters|lit=water-dogs|sc=Latn}}, {{etyl|la|-}} {{m|la|unda||wave|sc=Latn}}, " +
		"{{etyl|lt|-}} {{m|lt|vanduõ||water|sc=Latn}}, {{etyl|ru|-}} {{m|ru|вода́||water}}, {{etyl|sq|-}} " +
		"{{m|sq|ujë||water|sc=Latn}}, {{etyl|grc|-}} {{m|grc|ὕδωρ||water}}, {{etyl|hy|-}} {{m|hy|գետ||river}}, " +
		"{{etyl|sa|-}} {{m|sa|उदन्|tr=udán||wave, water|sc=Deva}}, {{etyl|hit|-}} " +
		"{{m|hit|\uD808\uDE7F\uD808\uDC00\uD808\uDEFB|wa-a-tar|sc=Xsux}}.\n" +
		"{{rel-bottom}}",
		entry.getWordEtymology().getText());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
public void testIt_s() throws Exception {
	/*BufferedReader r = new BufferedReader(
			new InputStreamReader(new FileInputStream(
					new File("src/test/resources/articles-en/it_s.txt")), 
					"UTF-8"));
	String line;
	while ((line = r.readLine()) != null)
		System.out.println(line);
	r.close();
	System.out.println();
	System.out.println();*/
	
	IWiktionaryPage page = parse("it_s.txt");
	Iterator<? extends IWiktionaryEntry> entryIter = page.getEntries().iterator();
	assertEntry(Language.ENGLISH, PartOfSpeech.CONTRACTION, 2, entryIter.next());
	assertFalse(entryIter.hasNext());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
public void testGetExamples() throws Exception {
	IWiktionaryPage page = parse("cheio.txt");
	final IWiktionaryEntry entry = page.getEntry(0);

	final List<IWiktionaryExample> examples = entry.getExamples();
	assertEquals(4, examples.size());

	final IWiktionarySense senseFull = entry.getSense(1);
	final IWiktionarySense senseCovered = entry.getSense(2);
	final IWiktionarySense senseFedUp = entry.getSense(3);

	assertEquals(2, senseFull.getExamples().size());
	assertEquals(1, senseCovered.getExamples().size());
	assertEquals(1, senseFedUp.getExamples().size());

	assertEquals("{{usex|lang=pt|A rua está '''cheia''' de trânsito|The street is full of traffic.}}", senseFull.getExamples().get(0).getText());
	assertEquals("{{usex|lang=pt|Estou '''cheio'''.|I'm full (not hungry anymore).}}", senseFull.getExamples().get(1).getText());

	assertEquals("A rua está '''cheia''' de óleo.", senseCovered.getExamples().get(0).getText());
	assertEquals("The street is covered with oil.", senseCovered.getExamples().get(0).getTranslation().getText());
	assertEquals("{{usex|lang=pt|Estou '''cheio''' dele.|I'm fed up with him.}}", senseFedUp.getExamples().get(0).getText());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
public List<IWiktionarySense> getSensesForWord(final String word,
		final IWiktionarySenseFilter filter, boolean normalize) {
	ensureOpen();
	List<IWiktionarySense> result = new ArrayList<>();
	if (word == null || word.isEmpty())
		return result;
	
	List<IWiktionaryPage> pages = getPagesForWord(word, normalize);
	for (IWiktionaryPage page : pages)
		for (IWiktionaryEntry entry : page.getEntries())
			for (IWiktionarySense sense : entry.getSenses())
				if (filter == null || filter.accept(sense))
					result.add(sense);
	
	return result;
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
public void testKiefer() throws Exception {
	IWiktionaryPage page = parse("Kiefer.txt");
	IWiktionaryEntry entry = page.getEntry(0);
	Iterator<IWiktionaryWordForm> actualIter = entry.getWordForms().iterator();
	assertWordFormNoun("die Kiefer", GrammaticalCase.NOMINATIVE, GrammaticalNumber.SINGULAR, actualIter.next());
	assertWordFormNoun("die Kiefern", GrammaticalCase.NOMINATIVE, GrammaticalNumber.PLURAL, actualIter.next());
	assertWordFormNoun("der Kiefer", GrammaticalCase.GENITIVE, GrammaticalNumber.SINGULAR, actualIter.next());
	assertWordFormNoun("der Kiefern", GrammaticalCase.GENITIVE, GrammaticalNumber.PLURAL, actualIter.next());
	assertWordFormNoun("der Kiefer", GrammaticalCase.DATIVE, GrammaticalNumber.SINGULAR, actualIter.next());
	assertWordFormNoun("den Kiefern", GrammaticalCase.DATIVE, GrammaticalNumber.PLURAL, actualIter.next());
	assertWordFormNoun("die Kiefer", GrammaticalCase.ACCUSATIVE, GrammaticalNumber.SINGULAR, actualIter.next());
	assertWordFormNoun("die Kiefern", GrammaticalCase.ACCUSATIVE, GrammaticalNumber.PLURAL, actualIter.next());
	assertFalse(actualIter.hasNext());
	entry = page.getEntry(1);
	actualIter = entry.getWordForms().iterator();
	assertWordFormNoun("Kiefer", null, GrammaticalNumber.SINGULAR, actualIter.next());
	assertWordFormNoun("Kiefer", null, GrammaticalNumber.PLURAL, actualIter.next());
	assertFalse(actualIter.hasNext());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
	public void testPlant() throws Exception {
		IWiktionaryPage page = parse("plant.txt");
		IWiktionarySense sense = page.getEntry(1).getSense(3);
		Iterator<IQuotation> quotationIter = sense.getQuotations().iterator();
		IQuotation quotation = quotationIter.next();
//		assertEquals("{{quote-news|year=2011|date=January 15|author=Sam Sheringham|title=Chelsea 2 - 0 Blackburn Rovers|work=BBC|url=http://news.bbc.co.uk/sport2/hi/football/eng_prem/9358426.stm|page=|passage=First Anelka curled a shot wide from just outside the box, then Lampard '''planted''' a header over the bar from Bosingwa's cross. }}", quotation.getSource().getText());
		assertNull(quotation.getSource());
		assertEquals(1, quotation.getLines().size());
		assertEquals("{{quote-news |year=2011 |date=January 15 |author=Sam Sheringham |title=Chelsea 2 - 0 Blackburn Rovers |work=BBC |url=http://news.bbc.co.uk/sport2/hi/football/eng_prem/9358426.stm |page= |passage=First Anelka curled a shot wide from just outside the box, then Lampard '''planted''' a header over the bar from Bosingwa's cross. }}", quotation.getLines().get(0).getText());
		assertFalse(quotationIter.hasNext());
		
		sense = page.getEntry(1).getSense(4);
		quotationIter = sense.getQuotations().iterator();
		quotation = quotationIter.next();
		assertEquals("'''2007''', Richard Laymon, ''Savage'', page 118:", quotation.getSource().getText());
		assertEquals(1, quotation.getLines().size());
		assertEquals("Sarah, she kissed each of her grandparents on the forehead. They were '''planted''' in a graveyard behind the church.", quotation.getLines().get(0).getText());
		assertFalse(quotationIter.hasNext());
	}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
	public void testWomen() throws Exception {
		IWiktionaryPage page = parse("women.txt");
//		printPronunciations(page);
		Iterator<? extends IWiktionaryEntry> entryIter = page.getEntries().iterator();
		Iterator<IPronunciation> pronIter = entryIter.next().getPronunciations().iterator();		
		assertPronunciation(PronunciationType.IPA, "/ˈwɪmɪn/", "RP", pronIter.next());
		assertPronunciation(PronunciationType.IPA, "/ˈwɪmən/", "US", pronIter.next());
		assertPronunciation(PronunciationType.AUDIO, "en-uk-women.ogg", "Audio (UK)", pronIter.next());
		assertPronunciation(PronunciationType.RHYME, "ɪmɪn", "", pronIter.next());
		assertFalse(pronIter.hasNext());
		pronIter = entryIter.next().getPronunciations().iterator();
		assertPronunciation(PronunciationType.AUDIO, "zh-wǒmen.ogg", "audio", pronIter.next());
		assertPronunciation(PronunciationType.IPA, "[ wo˨˩mən ]", "", pronIter.next());
		assertFalse(pronIter.hasNext());
		assertFalse(entryIter.hasNext());
	}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
public void testSynonymsJanuar() throws Exception {
	IWiktionaryPage page = parse("Januar.txt");
	IWiktionaryEntry entry = page.getEntry(0);
	Set<String> expected = new HashSet<>();
	expected.add("Jänner");
	expected.add("Hartung");
	expected.add("Eismonat");
	expected.add("Wintermonat");
	expected.add("Schneemonat");
	expected.add("Wolfsmonat");
	List<IWiktionaryRelation> relations = entry.getSense(1).getRelations();
	relations.stream()
		.filter(relation -> RelationType.SYNONYM == relation.getRelationType())
		.forEach(relation -> assertTrue("Invalid relation: " + relation.getTarget(), expected.remove(relation.getTarget())));
	assertTrue("Relations missing: " + Arrays.toString(expected.toArray()), expected.isEmpty());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
public void testDerivedTermsKiefer() throws Exception {
	IWiktionaryPage page = parse("Kiefer.txt");
	IWiktionaryEntry entry = page.getEntry(1);
	Set<String> expected = new HashSet<>();
	expected.add("Kieferanomalie");
	expected.add("Kieferchirurgie");
	expected.add("Kiefergelenk");
	expected.add("Kieferhöhle");
	expected.add("Kieferklemme");
	expected.add("Kieferknochen");
	expected.add("Kieferorthopädie");
	expected.add("Kieferspalte");
	expected.add("Kiefersprerre");
	List<IWiktionaryRelation> relations = entry.getUnassignedSense().getRelations();
	relations.stream()
		.filter(relation -> RelationType.DERIVED_TERM == relation.getRelationType())
		.forEach(relation -> assertTrue(expected.remove(relation.getTarget())));
	assertTrue("Relations missing: " + Arrays.toString(expected.toArray()), expected.isEmpty());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
	public void testBass() throws Exception {
		IWiktionaryPage page = parse("bass.txt");
//		printPronunciations(page);
		Iterator<? extends IWiktionaryEntry> entryIter = page.getEntries().iterator();
		Iterator<IPronunciation> pronIter = entryIter.next().getPronunciations().iterator();		
		assertPronunciation(PronunciationType.IPA, "/beɪs/", "", pronIter.next());
		assertPronunciation(PronunciationType.SAMPA, "/beIs/", "", pronIter.next());
		assertPronunciation(PronunciationType.AUDIO, "en-us-bass-low.ogg", "Audio (US)", pronIter.next());
		assertFalse(pronIter.hasNext());
		pronIter = entryIter.next().getPronunciations().iterator();
		assertPronunciation(PronunciationType.IPA, "/beɪs/", "", pronIter.next());
		assertPronunciation(PronunciationType.SAMPA, "/beIs/", "", pronIter.next());
		assertPronunciation(PronunciationType.AUDIO, "en-us-bass-low.ogg", "Audio (US)", pronIter.next());
		assertFalse(pronIter.hasNext());
		pronIter = entryIter.next().getPronunciations().iterator();
//		assertPronunciation(PronunciationType.enPR, "/băs/", "", pronIter.next());
		assertPronunciation(PronunciationType.IPA, "/bæs/", "", pronIter.next());
		assertPronunciation(PronunciationType.SAMPA, "/b{s/", "", pronIter.next());
		assertPronunciation(PronunciationType.AUDIO, "en-us-bass.ogg", "Audio (US)", pronIter.next());
		assertFalse(pronIter.hasNext());
		assertNull(entryIter.next().getPronunciations());
		assertFalse(entryIter.hasNext());
	}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
public void testBass() throws Exception {
	IWiktionaryPage page = parse("bass.txt");
	IWiktionaryEntry entry = page.getEntry(0);
	Iterator<IWiktionaryWordForm> actualIter = entry.getWordForms().iterator();
	assertWordFormAdjective("bass", GrammaticalDegree.POSITIVE, actualIter.next());
	assertWordFormAdjective("more bass", GrammaticalDegree.COMPARATIVE, actualIter.next());
	assertWordFormAdjective("most bass", GrammaticalDegree.SUPERLATIVE, actualIter.next());
	assertFalse(actualIter.hasNext()); 
	
	entry = page.getEntry(1);
	actualIter = entry.getWordForms().iterator();
	assertWordFormNoun("basses", GrammaticalNumber.PLURAL, actualIter.next());
	assertFalse(actualIter.hasNext());

	entry = page.getEntry(2);
	actualIter = entry.getWordForms().iterator();
	assertWordFormNoun("bass", GrammaticalNumber.PLURAL, actualIter.next());
	assertWordFormNoun("basses", GrammaticalNumber.PLURAL, actualIter.next());
	assertFalse(actualIter.hasNext());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
protected IWiktionaryPage parse(final String fileName, final String title) throws IOException {
	StringBuilder text = new StringBuilder();
	BufferedReader reader = new BufferedReader(
			new InputStreamReader(new FileInputStream(
					new File("src/test/resources/articles-ru/" + fileName)), 
					"UTF-8"));
	String line;
	while ((line = reader.readLine()) != null)
		text.append(line).append("\n");
	reader.close();
	WiktionaryPage result = new WiktionaryPage();
	result.setTitle(title);
	WiktionaryEntryParser parser = new RUWiktionaryEntryParser();
	parser.parse(result, text.toString());
	return result;
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
protected IWiktionaryPage parse(final String fileName) throws IOException {
	StringBuilder text = new StringBuilder();
	BufferedReader reader = new BufferedReader(
			new InputStreamReader(new FileInputStream(
					new File("src/test/resources/articles-en/" + fileName)), 
					"UTF-8"));
	String line;
	while ((line = reader.readLine()) != null)
		text.append(line).append("\n");
	reader.close();
	WiktionaryPage result = new WiktionaryPage();
	result.setTitle(fileName.replace(".txt", ""));
	WiktionaryEntryParser parser = new ENWiktionaryEntryParser();
	parser.parse(result, text.toString());
	return result;
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
public void testSumo() throws Exception {
	// 5 entries with 4 different etymologies, last entry has empty one
	IWiktionaryPage page = parse("sumo.txt");
	assertEquals(5, page.getEntryCount());
	// adj, noun
	assertNotNull(page.getEntry(0).getWordEtymology());
	assertEquals(page.getEntry(1).getWordEtymology(), page.getEntry(0).getWordEtymology());
	// noun
	assertNotNull(page.getEntry(2).getWordEtymology());
	assertNotEquals(page.getEntry(2).getWordEtymology(), page.getEntry(1).getWordEtymology());
	// noun
	assertNotNull(page.getEntry(3).getWordEtymology());
	assertNotEquals(page.getEntry(3).getWordEtymology(), page.getEntry(2).getWordEtymology());
	// verb, no etymology set
	assertNull(page.getEntry(4).getWordEtymology());
}
 

import de.tudarmstadt.ukp.jwktl.api.IWiktionaryPage; //导入依赖的package包/类
/***/
public void testSynonymsRainCatsAndDogs() throws Exception {
	IWiktionaryPage page = parse("rain_cats_and_dogs.txt");
	IWiktionaryEntry entry = page.getEntry(0);
	Iterator<IWiktionaryRelation> iter = entry.getSense(1).getRelations(SYNONYM).iterator();
	assertRelation(SYNONYM, "bucket", iter.next());
	assertRelation(SYNONYM, "bucket down", iter.next());
	assertRelation(SYNONYM, "chuck it down", iter.next());
	assertRelation(SYNONYM, "rain buckets", iter.next());
	assertRelation(SYNONYM, "rain pitchforks", iter.next());
	assertRelation(SYNONYM, "pelt", iter.next());
	assertRelation(SYNONYM, "piss down", iter.next());
	assertRelation(SYNONYM, "pour", iter.next());
	assertRelation(SYNONYM, "stream", iter.next());
	assertRelation(SYNONYM, "teem", iter.next());
	assertFalse(iter.hasNext());
}