de.tudarmstadt.ukp.jwktl.parser.en.components.ENPronunciationHandler Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of dkpro-jwktl Show documentation

JWKTL (Java Wiktionary Library) is a Java-based API that enables efficient and structured access to the information encoded in the English and the German Wiktionary edition, including sense definitions, part of speech tags, etymology, example sentences, translations, semantic relations and many other lexical information types.

The newest version!

/*******************************************************************************
 * Copyright 2013
 * Ubiquitous Knowledge Processing (UKP) Lab
 * Technische Universität Darmstadt
 * 
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 * 
 *   http://www.apache.org/licenses/LICENSE-2.0
 * 
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 ******************************************************************************/
package de.tudarmstadt.ukp.jwktl.parser.en.components;

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import de.tudarmstadt.ukp.jwktl.api.IPronunciation;
import de.tudarmstadt.ukp.jwktl.api.IPronunciation.PronunciationType;
import de.tudarmstadt.ukp.jwktl.api.entry.Pronunciation;
import de.tudarmstadt.ukp.jwktl.api.util.TemplateParser;
import de.tudarmstadt.ukp.jwktl.parser.util.ParsingContext;
import de.tudarmstadt.ukp.jwktl.parser.util.StringUtils;

/**
 * Parser component for extracting pronunciations from the English Wiktionary. 
 * @author Christian M. Meyer
 */
public class ENPronunciationHandler extends ENBlockHandler {	
	
	protected static final Pattern PRONUNCIATION_CONTEXT = Pattern.compile("\\{\\{(?:a|sense)\\|([^\\}\\|]+?)\\}\\}");
	protected static final Pattern PRONUNCIATION = Pattern.compile("\\{\\{(?:IPA|SAMPA)\\|.+?\\}\\}");
	protected static final Pattern PRONUNCIATION_AUDIO = Pattern.compile("\\{\\{audio\\|([^\\}\\|]+?)(?:\\|([^\\}\\|]+?)(?:\\|lang=[^\\}\\|]+)?)?\\}\\}");
	protected static final Pattern PRONUNCIATION_RYHME = Pattern.compile("\\{\\{rhymes\\|([^\\}\\|]+?)\\}\\}");
	
	protected List pronunciations;

	public boolean canHandle(String blockHeader) {
		blockHeader = StringUtils.strip(blockHeader, "{}=: 1234567890").toLowerCase();
		if ("pronunciation".equals(blockHeader) || "pronuncaition".equals(blockHeader)
				|| "pronunceation".equals(blockHeader) || "pronunciaton".equals(blockHeader))
			return true;
		
		return false;
	}
	
	@Override
	public boolean processHead(final String textLine, final ParsingContext context) {
		pronunciations = new ArrayList<>();
		return super.processHead(textLine, context);
	}

	@Override
	public boolean processBody(final String textLine, final ParsingContext context) {
		final StringBuilder ctx = new StringBuilder();
		Matcher matcher = PRONUNCIATION_CONTEXT.matcher(textLine); 
		while (matcher.find())
			ctx.append(" ").append(matcher.group(1));

		final Matcher pronunMatcher = PRONUNCIATION.matcher(textLine);
		while (pronunMatcher.find()) {
			TemplateParser.parse(pronunMatcher.group(), template -> {
				final PronunciationType type = PronunciationType.valueOf(template.getName());
				for (int i = 0; i>>>" + textLine);
		for (Pronunciation p : pronunciations)
			System.out.println(p.getType() + ": " + p.getText() + " " + p.getNote());
		pronunciations.clear();*/
		
		return false;
	}
	
	public void fillContent(final ParsingContext context) {		
		// There is no PosEntry yet - store the pronunciations in the context
		// and add them later on (in ENWordLanguageHandler).
		context.setPronunciations(pronunciations);
	}

	/** Returns the list of all extracted pronunciations. */
	public List getPronunciations() {
		return pronunciations;
	}
	
}