Java Strings类代码示例

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
/**
 * returns 
 * @param sentence
 * 			input sentence, space delimited
 * @param discardStopWords
 * 			true if stopwords are to be discarded from the sentence 			
 * @return
 * 		a pair containing <list of word-pos, remaining not-handled terms>  
 * 		
 */
public Pair<List<String>, List<String>> getStanfordSentence(String sentence)
{
	List<WordLemmaTag> wlts = SentenceProcessor.getInstance().processSentence(sentence, false);
	
	List<String> terms = null;
	StanfordSentence sSentence = StanfordSentence.fromLine(Strings.join(wlts," "));
	
	try
	{
		 terms = sSentence.getTerms(TAGS, 
				 Language.EN, 
				 null, 
				 MultiwordBelongingTo.WORDNET, 
				 CompoundingParameter.ALLOW_MULTIWORD_EXPRESSIONS,
				 CompoundingParameter.APPEND_POS);	 
	}
	catch(Exception e)
	{
		e.printStackTrace();
	}

	//discards OOVs, and tries to map incorrect pos-tags to the correct ones
	return fixTerms(terms, discardStopwords);
}
 

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
public void getConcepts() throws IOException
{
	int counter = 0;
	Timer timer = new Timer();
	for (String concept : concepts)
	{
		Set<List<String>> paths = kb.getAllPathsFrom(concept, maxSearchDepth);

		FileWriter writerFrom = dirManager.getFileWriter(concept+".txt");
		
		// saves the paths starting from the concept
		for (List<String> path : paths)
			writerFrom.write(Strings.join(path)+"\n");
		
		writerFrom.close();
		
		if ((counter%100)==0)
			timer.tick("\t[WORKER] " + id +
					   " TO CREATE INDEXABLE FILES FOR " + 
					   counter + " CONCEPTS SO FAR ... ");
		counter++;
	}
}
 

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
@Override
public String toString()
{
	return
		new StringBuffer().
				append(Strings.format(confidence)).append("_").
				append(numberOfTranslations).append("_").
				append(sampleSize).toString();
}
 

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
@Override
public String toString()
{
	return
		new StringBuffer().
			append(language).append("_").
			append(pointer.getSymbol()).append("_").
			append(target).append("_").
			append(Strings.format(weight)).append("_").
			append(Strings.format(normalizedWeight)).toString();
}
 

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
/**
 * Prints information about the degree of a {@link KnowledgeGraph} with a
 * specific scorer
 * 
 * @param simpleGraph
 * @param kb
 */
public static void printDegree(KnowledgeGraph simpleGraph, KnowledgeBase kb)
{
	StringBuffer buffer = new StringBuffer();
	Collection<String> concepts = simpleGraph.getConceptsForSourceWords();
	DirectedGraph<String, WeightedLabeledEdge> graph = simpleGraph.getGraph();

	for (String concept : concepts)
	{
		double weightedSum = 0.0;
		int degree = graph.outDegreeOf(concept);
		Multimap<IPointer, ScoredItem<String>> related = kb.getRelatedConceptsMap(concept);

		buffer.append("\n    OFFSET = ").append(concept).append(" SENSE = ").append(kb.conceptToString(concept)).append("\n\n      OUTGOING EDGES\n");

		for (WeightedLabeledEdge edge : graph.outgoingEdgesOf(concept))
		{
			weightedSum += edge.getWeight();

			String src = graph.getEdgeSource(edge);
			String target = graph.getEdgeTarget(edge);

			buffer.append("\n      ").append(kb.conceptToString(src)).append(":").append(edge.getLabel()).append("[").append(edge.getWeight()).append("]:").append(kb.conceptToString(target));
		}
		buffer.append("\n    ==============================");
		buffer.append("\n    DEGREE: ").append(degree).append("/").append(related.size()).append("=").append(Strings.format((double) degree / (double) related.size()))
				.append(" -- WEIGHTED SUM: ").append(Strings.format(weightedSum)).append("/").append(related.size()).append("=")
				.append(Strings.format((double) weightedSum / (double) related.size()));
		buffer.append("\n    ==============================");
	}

	log.info(buffer);
}
 

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
/**
 * Creates a new instance of {@link BabelImage}
 * 
 * @param imageName
 *            the MediaWiki page name for the image - something like
 *            "LANGUAGE:Image:..."
 */
public BabelImage(String imageName)
{
	boolean bSpecialImage = false;
	// identifies the language
	int colonIdx = imageName.indexOf(":");
	if (colonIdx == -1) 
		throw new RuntimeException("Invalid image name: " + imageName);
	Language language = Language.valueOf(imageName.substring(0, colonIdx));
	
	// removes trailing "File:" or "Image:"
	String cleanImageName = imageName.substring(colonIdx+1);
	colonIdx = cleanImageName.indexOf(":");
	if (colonIdx != -1) cleanImageName = cleanImageName.substring(colonIdx+1);
	//se è un'image particolare ha un tag in più
	if(cleanImageName.startsWith("MANUAL:"))
	{
		bSpecialImage = true;
		colonIdx = cleanImageName.indexOf(":");
		if (colonIdx != -1) cleanImageName = cleanImageName.substring(colonIdx+1);
		cleanImageName = Strings.forceFirstCharUppercase(cleanImageName);
	}
	else cleanImageName = Strings.forceFirstCharUppercase(cleanImageName);
	
	// e.g. "Paula_Radcliffe.jpg"
	this.name = cleanImageName.trim();
	//System.out.println("name "+name);
	this.badImage = BadImageList.getInstance().isBadImage(name);
	// Language.EN for instance
	this.language = language;
	
	if(bSpecialImage)
	{
		this.thumbUrl = cleanImageName;
		this.url = cleanImageName;
	}
	else
	{
		this.thumbUrl = createThumbURL(name);
		this.url = createURL(name);
	}
}
 

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
private String getValidatedURL(boolean isThumb)
{
	// try the "base" search first
	// otherwise check whether it's a redirection
	//
	// e.g. http://en.wikipedia.org/wiki/File:Cheese_07_bg_042906.jpg
	if (!isThumb)
		if (urlValidated != null) return urlValidated;
	else
		if (urlThumbValidated  != null) return urlThumbValidated;

	String url = null;
	int sizeSmall = 0;
	try
	{
		URI uri = new URI(
			"http", 
			    EN_WIKIPEDIA_HOST, 
			    EN_WIKIPEDIA_PATH+"File:"+name,
			    null);
		String wikiUrl = uri.toASCIIString();

		// get the page content
		ByteArrayOutputStream os = new ByteArrayOutputStream();
		WGet.wGet(wikiUrl, os);
		String content = os.toString();

		// check for a URL labeled as "canonical"
		Matcher matcher = CANONICAL_PATTERN.matcher(content);

		if (matcher.find())
		{
			// got it, e.g. File:Mozzarella_cheese.jpg
			String redirectedName = matcher.group(1);
			String cleanRedirectedName = redirectedName;
			int colonIdx = redirectedName.indexOf(":");
			if (colonIdx != -1) cleanRedirectedName = cleanRedirectedName.substring(colonIdx+1);
			cleanRedirectedName =
				Strings.forceFirstCharUppercase(cleanRedirectedName).trim();
				Pattern sizePatt  = Pattern.compile("=\"(//upload.wikimedia.org/wikipedia/(commons|"+this.language.toString().toLowerCase()+")/thumb/(?!archive).*?"+cleanRedirectedName+""+"/([0-9]*?)px-"+cleanRedirectedName+".*?)\"");
			Matcher matcherSize =  sizePatt.matcher(content);
			while (matcherSize.find())
			{
				//Se sono qui vuol dire che il thumb non è stato validato, 
				//prende l'indirizzo più piccolo vicino alla grandezza desiderata
				
				if(Integer.parseInt(matcherSize.group(3)) <= imageSize) 
					if (sizeSmall < Integer.parseInt(matcherSize.group(3))) {
						if(matcherSize.group(1).startsWith("//"))
							url = "http:"+matcherSize.group(1);
						else
							url = matcherSize.group(1);
						sizeSmall = Integer.parseInt(matcherSize.group(3));
					}
			}

			// create the redirection's URL and check it exists
				String redirectedURL = createURL(cleanRedirectedName);
			urlValidated = getValidatedURL(redirectedURL, language);
			
			//se non trova nulla imposta l'url originale validato
			if(url == null) url = urlValidated;

			// create the thumb URL 
			urlThumbValidated = url;

			// if validate thumbs
			if (!isThumb) return urlValidated;
			else return urlThumbValidated;
		}
		return null;
	}
	catch (URISyntaxException e)
	{
		return null;
	}
}
 

import it.uniroma1.lcl.jlt.util.Strings; //导入依赖的package包/类
@Override
public String toString()
{
	return "("+src+","+pointerSymbol+":"+Strings.format(weight)+","+target+")";
}