/** * Removes empty #text nodes from a document. From James Murty on this StackOverflow post: * http://stackoverflow.com/questions/978810/how-to-strip-whitespace-only-text-nodes-from-a-dom-before-serialization * * @param doc The document to remove empty text nodes from. */ private static void removeEmptyTextNodes(Document doc) { try { XPathFactory xpathFactory = XPathFactory.newInstance(); // XPath to find empty text nodes. XPathExpression xpathExp = xpathFactory.newXPath().compile("//text()[normalize-space(.) = '']"); NodeList emptyTextNodes = (NodeList) xpathExp.evaluate(doc, XPathConstants.NODESET); // Remove each empty text node from document. for (int i = 0; i < emptyTextNodes.getLength(); i++) { Node emptyTextNode = emptyTextNodes.item(i); emptyTextNode.getParentNode().removeChild(emptyTextNode); } } catch (Exception ex) { ex.printStackTrace(); } }
private NodeList findNodes(Document doc, Node operation) { List<Node> xpaths = getChildNodes(operation, "xpath"); if (xpaths.isEmpty()) { return null; } String xpathExpression = xpaths.get(0).getTextContent(); if (xpathExpression == null) { return null; } XPathFactory xPathfactory = XPathFactory.newInstance(); XPath xpath = xPathfactory.newXPath(); NodeList nl = null; try { XPathExpression expr = xpath.compile(xpathExpression); nl = (NodeList) expr.evaluate(doc, XPathConstants.NODESET); } catch (XPathExpressionException ex) { Utils.onError(new Error.WrongXpathExpression(xpathExpression)); } return nl; }