blob: f5d6b1fe9f9a224e169672eb22d2f0383e4934fc [file] [log] [blame]
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you 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 org.apache.uima.cas.test;
import org.apache.uima.analysis_component.JCasAnnotator_ImplBase;
import org.apache.uima.jcas.JCas;
public class SubiteratorAnnotator extends JCasAnnotator_ImplBase {
public SubiteratorAnnotator() {
super();
}
public void process(JCas jCas) {
String text = jCas.getDocumentText();
boolean isInToken = false;
int tokenStart = 0;
for (int i = 0; i < text.length(); i++) {
char c = text.charAt(i);
if (Character.isLetterOrDigit(c)) {
if (!isInToken) {
isInToken = true;
tokenStart = i;
}
} else {
if (isInToken) {
isInToken = false;
Token token = new Token(jCas);
token.setBegin(tokenStart);
token.setEnd(i);
token.addToIndexes();
}
}
}
if (isInToken) {
Token token = new Token(jCas);
token.setBegin(tokenStart);
token.setEnd(text.length());
token.addToIndexes();
}
int sentenceStart = 0;
for (int i = 0; i < text.length(); i++) {
if (text.charAt(i) == '.') {
Sentence sentence = new Sentence(jCas);
sentence.setBegin(sentenceStart);
sentence.setEnd(i+1);
sentence.addToIndexes();
sentenceStart = i + 1;
}
}
}
}