List of usage examples for org.w3c.dom Text isElementContentWhitespace
public boolean isElementContentWhitespace();
From source file:Main.java
/** * Get the content of the first Text child element of the passed element. * * @param aStartNode// ww w .j a va 2 s. c o m * the element to scan for a TextNode child * @return <code>null</code> if the element contains no text node as child */ @Nullable public static String getFirstChildText(@Nullable final Node aStartNode) { if (aStartNode != null) { final NodeList aNodeList = aStartNode.getChildNodes(); final int nLen = aNodeList.getLength(); for (int i = 0; i < nLen; ++i) { final Node aNode = aNodeList.item(i); if (aNode instanceof Text) { final Text aText = (Text) aNode; // ignore whitespace-only content if (!aText.isElementContentWhitespace()) return aText.getData(); } } } return null; }
From source file:Main.java
/** * get the text string in an element (eg interspersed between child elements), * or "" if there is none or if the Element is null. * Tries to ignore white space text; but does not succeed. *//*from ww w . java 2 s. c o m*/ public static String getText(Element el) { String res = ""; if (el != null) try { el.normalize(); // does not help recognise white space NodeList nodes = el.getChildNodes(); for (int i = 0; i < nodes.getLength(); i++) if (nodes.item(i) instanceof Text) { Text text = (Text) nodes.item(i); // this filter seems to make no difference if (!text.isElementContentWhitespace()) { String tData = text.getData(); // this seems to be an effective way to catch pure white space StringTokenizer nonWhiteSpace = new StringTokenizer(tData, "\n \t"); if (nonWhiteSpace.countTokens() > 0) res = res + tData; } } } catch (Exception e) { System.out.println("Text failure: " + e.getMessage()); } return res; }