001/** 002 * Copyright (c) 2011, The University of Southampton and the individual contributors. 003 * All rights reserved. 004 * 005 * Redistribution and use in source and binary forms, with or without modification, 006 * are permitted provided that the following conditions are met: 007 * 008 * * Redistributions of source code must retain the above copyright notice, 009 * this list of conditions and the following disclaimer. 010 * 011 * * Redistributions in binary form must reproduce the above copyright notice, 012 * this list of conditions and the following disclaimer in the documentation 013 * and/or other materials provided with the distribution. 014 * 015 * * Neither the name of the University of Southampton nor the names of its 016 * contributors may be used to endorse or promote products derived from this 017 * software without specific prior written permission. 018 * 019 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND 020 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED 021 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE 022 * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR 023 * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES 024 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 025 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON 026 * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 027 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 028 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 029 */ 030package org.openimaj.text.nlp.textpipe.annotations; 031 032import org.openimaj.text.nlp.textpipe.annotations.POSAnnotation.PartOfSpeech; 033import org.openimaj.text.nlp.textpipe.annotations.PhraseAnnotation.Phrase; 034import org.openimaj.text.nlp.textpipe.annotators.MissingRequiredAnnotationException; 035import org.openimaj.text.nlp.textpipe.annotators.OpenNLPPOSAnnotator; 036import org.openimaj.text.nlp.textpipe.annotators.OpenNLPPhraseChunkAnnotator; 037import org.openimaj.text.nlp.textpipe.annotators.OpenNLPSentenceAnnotator; 038import org.openimaj.text.nlp.textpipe.annotators.OpenNLPTokenAnnotator; 039import org.openimaj.text.nlp.textpipe.annotators.YagoNEAnnotator; 040 041/** 042 * Simple demo and play area. 043 * 044 * @author Laurence Willmore (lgw1e10@ecs.soton.ac.uk) 045 * 046 */ 047public class PipePlayground { 048 049 public static void main(String[] args) { 050 final RawTextAnnotation rta = new RawTextAnnotation( 051 "The tall curtains"); 052 053 // Set the properties 054 System.setProperty(OpenNLPTokenAnnotator.TOKEN_MODEL_PROP, "/org/openimaj/text/opennlp/models/en-token.bin"); 055 System.setProperty(OpenNLPSentenceAnnotator.SENTENCE_MODEL_PROP, "/org/openimaj/text/opennlp/models/en-sent.bin"); 056 System.setProperty(OpenNLPPOSAnnotator.POS_MODEL_PROP, "/org/openimaj/text/opennlp/models/en-pos-maxent.bin"); 057 System.setProperty(OpenNLPPhraseChunkAnnotator.PHRASE_MODEL_PROP, 058 "/org/openimaj/text/opennlp/models/en-chunker.bin"); 059 final OpenNLPTokenAnnotator ta = new OpenNLPTokenAnnotator(); 060 final OpenNLPSentenceAnnotator sa = new OpenNLPSentenceAnnotator(); 061 final OpenNLPPOSAnnotator pa = new OpenNLPPOSAnnotator(); 062 final OpenNLPPhraseChunkAnnotator pca = new OpenNLPPhraseChunkAnnotator(); 063 final YagoNEAnnotator yna = new YagoNEAnnotator(); 064 try { 065 sa.annotate(rta); 066 ta.annotate(rta); 067 pa.annotate(rta); 068 pca.annotate(rta); 069 yna.annotate(rta); 070 } catch (final MissingRequiredAnnotationException e1) { 071 // TODO Auto-generated catch block 072 e1.printStackTrace(); 073 } 074 for (final SentenceAnnotation sentence : rta 075 .getAnnotationsFor(SentenceAnnotation.class)) 076 { 077 System.out.println(sentence.text); 078 if (sentence.getAnnotationKeyList().contains(NamedEntityAnnotation.class)) 079 for (final NamedEntityAnnotation ne : sentence.getAnnotationsFor(NamedEntityAnnotation.class)) { 080 System.out.println(ne.namedEntity.rootName); 081 System.out.println(ne.namedEntity.type); 082 } 083 for (final TokenAnnotation token : sentence.getAnnotationsFor(TokenAnnotation.class)) { 084 final PartOfSpeech pos = token.getAnnotationsFor(POSAnnotation.class).get(0).pos; 085 final Phrase ph = token.getAnnotationsFor(PhraseAnnotation.class).get(0).phrase; 086 final String phraseOrder = token.getAnnotationsFor(PhraseAnnotation.class).get(0).getOrder(); 087 System.out.println(token.stringToken + " " + pos.toString() + " " + pos.DESCRIPTION + " " 088 + ph.toString() + "-" + phraseOrder); 089 System.out.println(sentence.text.substring(token.start, token.stop)); 090 System.out.println("|" + token.getRawString() + "|"); 091 final String fromRaw = rta.text.substring(sentence.start + token.start, sentence.start + token.stop); 092 System.out.print(fromRaw + "\n"); 093 } 094 } 095 } 096 097}