Re: [xwiki-devs] [xwiki-notifications] r17677 - in platform/core/trunk/xwiki-xml: . src/main/java/org/xwiki/xml/internal/html
Hi Asiri, On Mar 16, 2009, at 6:58 PM, asiri (SVN) wrote:
Author: asiri Date: 2009-03-16 18:58:57 +0100 (Mon, 16 Mar 2009) New Revision: 17677
Modified: platform/core/trunk/xwiki-xml/pom.xml platform/core/trunk/xwiki-xml/src/main/java/org/xwiki/xml/internal/ html/DefaultHTMLCleaner.java Log: XWIKI-3365: Get rid of jdom dependency in xwiki-xml module
* Fixed.
[snip]
+ } // Workaround HTML XML declaration bug. - fixCleanedNodeBug(cleanedNode); - - // Ideally following code should be enough. But SF's HTML Cleaner seems to omit the DocType declaration while - // serializing. - // See https://sourceforge.net/tracker/index.php?func=detail&aid=2062318&group_id=1... - // cleanedNode.setDocType(new DoctypeToken("html", "PUBLIC", "-//W3C//DTD XHTML 1.0 Strict//EN", - // "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd ")); - // try { - // result = new DomSerializer(cleanerProperties, false).createDOM(cleanedNode); - // } catch(ParserConfigurationException ex) { } - // As a workaround, we have go through JDOM so that we can set the DocType manually. - org.jdom.Document jdomDoc = null; - jdomDoc = new JDomSerializer(cleanerProperties, false).createJDom(cleanedNode); - jdomDoc.setDocType(new DocType("html", "-//W3C//DTD XHTML 1.0 Strict//EN", - "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd")); + fixCleanedNodeBug(cleanedNode); + // Serialize the cleanedNode TagNode into a w3c dom. try { - result = new DOMOutputter().output(jdomDoc); - } catch (JDOMException ex) { - throw new RuntimeException("Error while transforming jdom document into w3c document", ex); + Document tempDoc = new DomSerializer(cleanerProperties, false).createDOM(cleanedNode); + DOMImplementation domImpl = + DocumentBuilderFactory .newInstance().newDocumentBuilder().getDOMImplementation(); + DocumentType docType = + domImpl.createDocumentType(QUALIFIED_NAME_HTML, "-// W3C//DTD XHTML 1.0 Strict//EN", + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd "); + result = domImpl.createDocument(null, QUALIFIED_NAME_HTML, docType); + result.replaceChild(result.adoptNode(tempDoc.getDocumentElement()), result.getDocumentElement()); + } catch (ParserConfigurationException ex) { + throw new RuntimeException("Error while serializing TagNode into w3c dom.", ex);
cool but why have you removed the comment saying that there's a SF html cleaner bug? Can you put it back and instead add that this is workaround? Thanks -Vincent
On Tue, Mar 17, 2009 at 12:59 AM, Vincent Massol <[email protected]> wrote:
Hi Asiri,
On Mar 16, 2009, at 6:58 PM, asiri (SVN) wrote:
Author: asiri Date: 2009-03-16 18:58:57 +0100 (Mon, 16 Mar 2009) New Revision: 17677
Modified: platform/core/trunk/xwiki-xml/pom.xml platform/core/trunk/xwiki-xml/src/main/java/org/xwiki/xml/internal/ html/DefaultHTMLCleaner.java Log: XWIKI-3365: Get rid of jdom dependency in xwiki-xml module
* Fixed.
[snip]
+ } // Workaround HTML XML declaration bug. - fixCleanedNodeBug(cleanedNode); - - // Ideally following code should be enough. But SF's HTML Cleaner seems to omit the DocType declaration while - // serializing. - // See https://sourceforge.net/tracker/index.php?func=detail&aid=2062318&group_id=1... - // cleanedNode.setDocType(new DoctypeToken("html", "PUBLIC", "-//W3C//DTD XHTML 1.0 Strict//EN", - // "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd ")); - // try { - // result = new DomSerializer(cleanerProperties, false).createDOM(cleanedNode); - // } catch(ParserConfigurationException ex) { } - // As a workaround, we have go through JDOM so that we can set the DocType manually. - org.jdom.Document jdomDoc = null; - jdomDoc = new JDomSerializer(cleanerProperties, false).createJDom(cleanedNode); - jdomDoc.setDocType(new DocType("html", "-//W3C//DTD XHTML 1.0 Strict//EN", - "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd")); + fixCleanedNodeBug(cleanedNode); + // Serialize the cleanedNode TagNode into a w3c dom. try { - result = new DOMOutputter().output(jdomDoc); - } catch (JDOMException ex) { - throw new RuntimeException("Error while transforming jdom document into w3c document", ex); + Document tempDoc = new DomSerializer(cleanerProperties, false).createDOM(cleanedNode); + DOMImplementation domImpl = + DocumentBuilderFactory .newInstance().newDocumentBuilder().getDOMImplementation(); + DocumentType docType = + domImpl.createDocumentType(QUALIFIED_NAME_HTML, "-// W3C//DTD XHTML 1.0 Strict//EN", + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd "); + result = domImpl.createDocument(null, QUALIFIED_NAME_HTML, docType); + result.replaceChild(result.adoptNode(tempDoc.getDocumentElement()), result.getDocumentElement()); + } catch (ParserConfigurationException ex) { + throw new RuntimeException("Error while serializing TagNode into w3c dom.", ex);
cool but why have you removed the comment saying that there's a SF html cleaner bug? Can you put it back and instead add that this is workaround?
Fixed. Thanks. - Asiri
Thanks -Vincent _______________________________________________ devs mailing list [email protected] http://lists.xwiki.org/mailman/listinfo/devs
participants (2)
-
Asiri Rathnayake -
Vincent Massol