com.itextpdf.styledxmlparser.jsoup.nodes.TextNode Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of styled-xml-parser Show documentation
Styled XML parser is used by iText modules to parse HTML and XML
There is a newer version: 9.0.0
/*
    This file is part of the iText (R) project.
    Copyright (c) 1998-2024 Apryse Group NV
    Authors: Apryse Software.

    This program is offered under a commercial and under the AGPL license.
    For commercial licensing, contact us at https://itextpdf.com/sales.  For AGPL licensing, see below.

    AGPL licensing:
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU Affero General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    This program 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 Affero General Public License for more details.

    You should have received a copy of the GNU Affero General Public License
    along with this program.  If not, see .
 */
package com.itextpdf.styledxmlparser.jsoup.nodes;

import com.itextpdf.styledxmlparser.jsoup.internal.StringUtil;
import com.itextpdf.styledxmlparser.jsoup.helper.Validate;

import java.io.IOException;

/**
 A text node.
*/
public class TextNode extends LeafNode {
    /**
     Create a new TextNode representing the supplied (unencoded) text).

     @param text raw text
     @see #createFromEncoded(String)
     */
    public TextNode(String text) {
        value = text;
    }

	public String nodeName() {
        return "#text";
    }
    
    /**
     * Get the text content of this text node.
     * @return Unencoded, normalised text.
     * @see TextNode#getWholeText()
     */
    public String text() {
        return StringUtil.normaliseWhitespace(getWholeText());
    }
    
    /**
     * Set the text content of this text node.
     * @param text unencoded text
     * @return this, for chaining
     */
    public TextNode text(String text) {
        coreValue(text);
        return this;
    }

    /**
     Get the (unencoded) text of this text node, including any newlines and spaces present in the original.
     @return text
     */
    public String getWholeText() {
        return coreValue();
    }

    /**
     Test if this text node is blank -- that is, empty or only whitespace (including newlines).
     @return true if this document is empty or only whitespace, false if it contains any text content.
     */
    public boolean isBlank() {
        return StringUtil.isBlank(coreValue());
    }

    /**
     * Split this text node into two nodes at the specified string offset. After splitting, this node will contain the
     * original text up to the offset, and will have a new text node sibling containing the text after the offset.
     * @param offset string offset point to split node at.
     * @return the newly created text node containing the text after the offset.
     */
    public TextNode splitText(int offset) {
        final String text = coreValue();
        Validate.isTrue(offset >= 0, "Split offset must be not be negative");
        Validate.isTrue(offset < text.length(), "Split offset must not be greater than current text length");

        String head = text.substring(0, offset);
        String tail = text.substring(offset);
        text(head);
        TextNode tailNode = new TextNode(tail);
        if (parent() != null)
            parent().addChildren(siblingIndex()+1, tailNode);

        return tailNode;
    }

	void outerHtmlHead(Appendable accum, int depth, Document.OutputSettings out) throws IOException {
        final boolean prettyPrint = out.prettyPrint();
        if (prettyPrint && ((siblingIndex() == 0 && parentNode instanceof Element && ((Element) parentNode).tag().formatAsBlock() && !isBlank()) || (out.outline() && siblingNodes().size()>0 && !isBlank()) ))
            indent(accum, depth, out);

        final boolean normaliseWhite = prettyPrint && !Element.preserveWhitespace(parentNode);
        final boolean stripWhite = prettyPrint && parentNode instanceof Document;
        Entities.escape(accum, coreValue(), out, false, normaliseWhite, stripWhite);
    }

	void outerHtmlTail(Appendable accum, int depth, Document.OutputSettings out) {}

    @Override
    public String toString() {
        return outerHtml();
    }

    @Override
    public Object clone() {
        return (TextNode) super.clone();
    }

    /**
     * Create a new TextNode from HTML encoded (aka escaped) data.
     * @param encodedText Text containing encoded HTML (e.g. &lt;)
     * @return TextNode containing unencoded data (e.g. <)
     */
    public static TextNode createFromEncoded(String encodedText) {
        String text = Entities.unescape(encodedText);
        return new TextNode(text);
    }

    static String normaliseWhitespace(String text) {
        text = StringUtil.normaliseWhitespace(text);
        return text;
    }

    static String stripLeadingWhitespace(String text) {
        return text.replaceFirst("^\\s+", "");
    }

    static boolean lastCharIsWhitespace(StringBuilder sb) {
        return sb.length() != 0 && sb.charAt(sb.length() - 1) == ' ';
    }


}