All Downloads are FREE. Search and download functionalities are using the official Maven repository.

src.it.unimi.dsi.parser.callback.TextExtractor Maven / Gradle / Ivy

Go to download

The DSI utilities are a mishmash of classes accumulated during the last twenty years in projects developed at the DSI (Dipartimento di Scienze dell'Informazione, i.e., Information Sciences Department), now DI (Dipartimento di Informatica, i.e., Informatics Department), of the Universita` degli Studi di Milano.

There is a newer version: 2.7.3
Show newest version
/*
 * DSI utilities
 *
 * Copyright (C) 2005-2020 Sebastiano Vigna
 *
 *  This library is free software; you can redistribute it and/or modify it
 *  under the terms of the GNU Lesser General Public License as published by the Free
 *  Software Foundation; either version 3 of the License, or (at your option)
 *  any later version.
 *
 *  This library is distributed in the hope that it will be useful, but
 *  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
 *  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public License
 *  for more details.
 *
 *  You should have received a copy of the GNU Lesser General Public License
 *  along with this program; if not, see .
 *
 */

package it.unimi.dsi.parser.callback;

import java.util.Map;

import it.unimi.dsi.lang.MutableString;
import it.unimi.dsi.parser.Attribute;
import it.unimi.dsi.parser.BulletParser;
import it.unimi.dsi.parser.Element;

/** A callback extracting text and titles.
 *
 * 

This callbacks extracts all text in the page, and the title. * The resulting * text is available through {@link #text}, and the title through {@link #title}. * *

Note that {@link #text} and {@link #title} are never trimmed. */ public class TextExtractor extends DefaultCallback { /** The text resulting from the parsing process. */ public final MutableString text = new MutableString(); /** The title resulting from the parsing process. */ public final MutableString title = new MutableString(); /** True if we are in the middle of the title. */ private boolean inTitle; /** * Configure the parser to parse text. */ @Override public void configure(final BulletParser parser) { parser.parseText(true); // To get the title. parser.parseTags(true); } @Override public void startDocument() { text.length(0); title.length(0); inTitle = false; } @Override public boolean characters(final char[] characters, final int offset, final int length, final boolean flowBroken) { text.append(characters, offset, length); if (inTitle) title.append(characters, offset, length); return true; } @Override public boolean endElement(final Element element) { // No element is allowed inside a title. inTitle = false; if (element.breaksFlow) { if (inTitle) title.append(' '); text.append(' '); } return true; } @Override public boolean startElement(final Element element, final Map attrMapUnused) { // No element is allowed inside a title. inTitle = element == Element.TITLE; if (element.breaksFlow) { if (inTitle) title.append(' '); text.append(' '); } return true; } }





© 2015 - 2024 Weber Informatics LLC | Privacy Policy