Author: asiri Date: 2009-01-02 07:04:20 +0100 (Fri, 02 Jan 2009) New Revision: 15010 Added: sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/AbstractHTMLCleanerTestCase.java sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/WysiwygDefaultHTMLCleanerTest.java Modified: sandbox/xwiki-officeimporter/pom.xml sandbox/xwiki-officeimporter/src/main/java/org/xwiki/ officeimporter/html/filter/TableFilter.java sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/OpenOfficeDefaultHTMLCleanerTest.java Log: * Added few more test cases. Modified: sandbox/xwiki-officeimporter/pom.xml =================================================================== --- sandbox/xwiki-officeimporter/pom.xml 2009-01-02 03:59:29 UTC (rev 15009) +++ sandbox/xwiki-officeimporter/pom.xml 2009-01-02 06:04:20 UTC (rev 15010) @@ -73,4 +73,17 @@ <scope>test</scope> </dependency> </dependencies> + <build> + <plugins> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-surefire-plugin</artifactId> + <configuration> + <excludes> + <exclude>**/Abstract*.java</exclude> + </excludes> + </configuration> + </plugin> + </plugins> + </build> </project> \ No newline at end of file Modified: sandbox/xwiki-officeimporter/src/main/java/org/xwiki/ officeimporter/html/filter/TableFilter.java =================================================================== --- sandbox/xwiki-officeimporter/src/main/java/org/xwiki/ officeimporter/html/filter/TableFilter.java 2009-01-02 03:59:29 UTC (rev 15009) +++ sandbox/xwiki-officeimporter/src/main/java/org/xwiki/ officeimporter/html/filter/TableFilter.java 2009-01-02 06:04:20 UTC (rev 15010) @@ -36,12 +36,12 @@ public class TableFilter implements HTMLFilter { /** - * Tags that need to be removed from cell items. + * Tags that need to be removed from cell items while preserving there children. */ private static final String[] filterTags = new String[] {"p"}; /** - * Tags that need to be removed from cell items. + * Tags that need to be completely removed from cell items. */ private static final String[] removeTags = new String[] {"br"}; @@ -54,7 +54,7 @@ for (int i = 0; i < cellItems.getLength(); i++) { Node cellItem = cellItems.item(i); cleanNode(cellItem); - // Workaround empty cells. + // Workaround empty cells. if (cellItem.getTextContent().equals("")) { boolean empty = true; for (int j = 0; j < cellItem.getChildNodes().getLength(); j++) { @@ -81,7 +81,13 @@ NodeList children = node.getChildNodes(); boolean removed = false; if (node.getNodeType() == Node.TEXT_NODE) { - node.setTextContent(node.getTextContent().trim()); + String trimmedContent = node.getTextContent().trim(); + if (trimmedContent.equals("")) { + parent.removeChild(node); + removed = true; + } else { + node.setTextContent(trimmedContent); + } } else if (Arrays.binarySearch(filterTags, node.getNodeName()) >= 0) { while (children.getLength() > 0) { Node child = children.item(0); @@ -95,7 +101,9 @@ removed = true; } else { for (int i = 0; i < children.getLength(); i++) { - i = cleanNode(children.item(i)) ? i-- : i; + if (cleanNode(children.item(i))) { + --i; + } } } return removed; Added: sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/AbstractHTMLCleanerTestCase.java =================================================================== --- sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/ AbstractHTMLCleanerTestCase.java (rev 0) +++ sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/AbstractHTMLCleanerTestCase.java 2009-01-02 06:04:20 UTC (rev 15010) @@ -0,0 +1,112 @@ +/* + * See the NOTICE file distributed with this work for additional + * information regarding copyright ownership. + * + * This 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 2.1 of + * the License, or (at your option) any later version. + * + * This software 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 software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.xwiki.officeimporter.html.cleaner; + +import java.io.StringReader; + +import org.w3c.dom.Document; +import org.w3c.dom.NodeList; +import org.xwiki.xml.html.HTMLCleaner; + +import com.xpn.xwiki.test.AbstractXWikiComponentTestCase; + +/** + * Abstract test case class for all HTMLCleaner tests. + * + * @version $Id$ + * @since 1.8M1 + */ +public class AbstractHTMLCleanerTestCase extends AbstractXWikiComponentTestCase +{ + /** + * Beginning of the test html document. + */ + protected String header = "<html><head><title>Title</title></ head><body>"; + + /** + * Beginning of the test html document, which has a {@code <style> tag.} + */ + protected String headerWithStyles = + "<html><head><style type=\"text/css\">h1 {color:red} p {color:blue} </style><title>Title</title></head><body>"; + + /** + * Ending of the test html document.. + */ + protected String footer = "</body></html>"; + + /** + * Test most basic cleaning. + */ + public void testBasicCleaning(HTMLCleaner cleaner) + { + String html = header + footer; + Document doc = cleaner.clean(new StringReader(html)); + assertNotNull(doc.getDoctype()); + } + + /** + * Test stripping of {@code <style>} and {@code <script>} tags. + */ + public void testTagStripping(HTMLCleaner cleaner) + { + String html = headerWithStyles + footer; + Document doc = cleaner.clean(new StringReader(html)); + NodeList nodes = doc.getElementsByTagName("style"); + assertEquals(0, nodes.getLength()); + html = + header + "<script type=\"text/javascript \">document.write(\"Hello World!\")</script>" + + footer; + doc = cleaner.clean(new StringReader(html)); + nodes = doc.getElementsByTagName("script"); + assertEquals(0, nodes.getLength()); + } + + /** + * Test stripping of redundant tags. + */ + public void testRedundancyFiltering(HTMLCleaner cleaner) + { + // <span> & <div> tags without attributes should be stripped off. + String htmlTemplate = header + "<p>Test%sRedundant %sFiltering<p>" + footer; + String[] attributeWiseFilteredTags = new String[] {"span", "div"}; + for (String tag : attributeWiseFilteredTags) { + String startTag = "<" + tag + ">"; + String endTag = "</" + tag + ">"; + String html = String.format(htmlTemplate, startTag, endTag); + Document doc = cleaner.clean(new StringReader(html)); + NodeList nodes = doc.getElementsByTagName(tag); + assertEquals(0, nodes.getLength()); + } + // Tags that usually contain textual information like <strong>, <code>, <em> etc. etc. + // should be filtered if they do not contain any textual content. + htmlTemplate = header + "<p>Test%sRedundant%s%s %sFiltering<p>" + footer; + String[] contentWiseFilteredTags = + new String[] {"em", "strong", "dfn", "code", "samp", "kbd", "var", "cite", "abbr", + "acronym", "address", "blockquote", "q", "pre", "h1", "h2", "h3", "h4", "h5", "h6"}; + for(String tag: contentWiseFilteredTags) { + String startTag = "<" + tag + ">"; + String endTag = "</" + tag + ">"; + String html = String.format(htmlTemplate, startTag, endTag, startTag, endTag); + Document doc = cleaner.clean(new StringReader(html)); + NodeList nodes = doc.getElementsByTagName(tag); + assertEquals(1, nodes.getLength()); + } + } +} Modified: sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/OpenOfficeDefaultHTMLCleanerTest.java =================================================================== --- sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/OpenOfficeDefaultHTMLCleanerTest.java 2009-01-02 03:59:29 UTC (rev 15009) +++ sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/OpenOfficeDefaultHTMLCleanerTest.java 2009-01-02 06:04:20 UTC (rev 15010) @@ -22,48 +22,135 @@ import java.io.StringReader; import org.w3c.dom.Document; +import org.w3c.dom.Element; +import org.w3c.dom.Node; +import org.w3c.dom.NodeList; import org.xwiki.xml.html.HTMLCleaner; -import com.xpn.xwiki.test.AbstractXWikiComponentTestCase; - /** * Test case for default open office html cleaner. - * + * * @version $Id$ * @since 1.8M1 */ -public class OpenOfficeDefaultHTMLCleanerTest extends AbstractXWikiComponentTestCase +public class OpenOfficeDefaultHTMLCleanerTest extends AbstractHTMLCleanerTestCase { /** - * Beginning of the test html document. - */ - private String header = "<html><head><title>Title</title></ head><body>"; - - /** - * Ending of the test html document.. - */ - private String footer = "</body></html>"; - - /** * Open office html cleaner. */ private HTMLCleaner cleaner; - + /** * {@inheritDoc} */ protected void setUp() throws Exception { super.setUp(); - cleaner = (HTMLCleaner) getComponentManager().lookup(HTMLCleaner.ROLE, "openoffice-default"); + cleaner = + (HTMLCleaner) getComponentManager().lookup(HTMLCleaner.ROLE, "openoffice-default"); } - + /** * Test most basic cleaning. */ - public void testBasicCleaning() { - String html = header + footer; + public void testBasicCleaning() + { + super.testBasicCleaning(cleaner); + } + + /** + * Test stripping of {@code <style>} and {@code <script>} tags. + */ + public void testTagStripping() + { + super.testTagStripping(cleaner); + } + + /** + * Test stripping of redundant tags. + */ + public void testRedundancyFiltering() + { + super.testRedundancyFiltering(cleaner); + } + + /** + * Test filtering of html links. + */ + public void testLinkFiltering() + { + String html = header + "<a href=\"http://www.xwiki.org \">xwiki</a>" + footer; Document doc = cleaner.clean(new StringReader(html)); - assertNotNull(doc.getDoctype()); + NodeList nodes = doc.getElementsByTagName("a"); + assertEquals(1, nodes.getLength()); + Node link = nodes.item(0); + Element span = (Element) link.getParentNode(); + assertEquals("span", span.getNodeName()); + assertEquals("wikiexternallink", span.getAttribute("class")); + Node startComment = span.getPreviousSibling(); + assertTrue(startComment.getNodeValue().startsWith("startwikilink")); + Node stopComment = span.getNextSibling(); + assertTrue(stopComment.getNodeValue().startsWith("stopwikilink")); } + + /** + * Test filtering of html lists. + */ + public void testListFiltering() + { + // Leading spaces inside list items are not allowed. + String html = header + "<ol><li> Test</li></ol>" + footer; + Document doc = cleaner.clean(new StringReader(html)); + NodeList nodes = doc.getElementsByTagName("li"); + Node listContent = nodes.item(0).getFirstChild(); + assertEquals(Node.TEXT_NODE, listContent.getNodeType()); + assertEquals("Test", listContent.getNodeValue()); + // Paragraphs inside list items are not allowed. + html = header + "<ol><li><p>Test</p></li></ol>" + footer; + doc = cleaner.clean(new StringReader(html)); + listContent = nodes.item(0).getFirstChild(); + assertEquals(Node.TEXT_NODE, listContent.getNodeType()); + assertEquals("Test", listContent.getNodeValue()); + // Leading space plus a starting paragraph. + html = header + "<ol><li> <p>Test</p></li></ol>" + footer; + doc = cleaner.clean(new StringReader(html)); + listContent = nodes.item(0).getFirstChild(); + assertEquals(Node.TEXT_NODE, listContent.getNodeType()); + assertEquals("Test", listContent.getNodeValue()); + } + + /** + * Test filtering of html tables. + */ + public void testTableFiltering() + { + // Leading or trailing spaces inside cell items are not allowed. + String html = header + "<table><tr><td> Test </td></tr></ table>" + footer; + Document doc = cleaner.clean(new StringReader(html)); + NodeList nodes = doc.getElementsByTagName("td"); + Node cellContent = nodes.item(0).getFirstChild(); + assertEquals(Node.TEXT_NODE, cellContent.getNodeType()); + assertEquals("Test", cellContent.getNodeValue()); + // Paragraphs are not allowed inside cell items. + html = header + "<table><tr><td> <p>Test</p> </td></tr></ table>" + footer; + doc = cleaner.clean(new StringReader(html)); + nodes = doc.getElementsByTagName("td"); + cellContent = nodes.item(0).getFirstChild(); + assertEquals(Node.TEXT_NODE, cellContent.getNodeType()); + assertEquals("Test", cellContent.getNodeValue()); + // Line breaks are not allowed inside cell items. + html = header + "<table><tr><td><br/><p><br/>Test</p> </ td></tr></table>" + footer; + doc = cleaner.clean(new StringReader(html)); + nodes = doc.getElementsByTagName("td"); + cellContent = nodes.item(0).getFirstChild(); + assertEquals(Node.TEXT_NODE, cellContent.getNodeType()); + assertEquals("Test", cellContent.getNodeValue()); + // Empty cells should be replaced by a '-' (this is temporary) + html = header + "<table><tr><td><br/><p><br/></p> </td></ tr></table>" + footer; + doc = cleaner.clean(new StringReader(html)); + nodes = doc.getElementsByTagName("td"); + cellContent = nodes.item(0).getFirstChild(); + assertEquals(Node.TEXT_NODE, cellContent.getNodeType()); + assertEquals("-", cellContent.getNodeValue()); + } } Added: sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/WysiwygDefaultHTMLCleanerTest.java =================================================================== --- sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/ WysiwygDefaultHTMLCleanerTest.java (rev 0) +++ sandbox/xwiki-officeimporter/src/test/java/org/xwiki/ officeimporter/html/cleaner/WysiwygDefaultHTMLCleanerTest.java 2009-01-02 06:04:20 UTC (rev 15010) @@ -0,0 +1,71 @@ +/* + * See the NOTICE file distributed with this work for additional + * information regarding copyright ownership. + * + * This 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 2.1 of + * the License, or (at your option) any later version. + * + * This software 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 software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.xwiki.officeimporter.html.cleaner; + +import org.xwiki.xml.html.HTMLCleaner; + +/** + * Test case for default wysiwyg html cleaner. + * + * @version $Id$ + * @since 1.8M1 + */ +public class WysiwygDefaultHTMLCleanerTest extends AbstractHTMLCleanerTestCase +{ + + /** + * Wysiwyg html cleaner. + */ + private HTMLCleaner cleaner; + + /** + * {@inheritDoc} + */ + protected void setUp() throws Exception + { + super.setUp(); + cleaner = + (HTMLCleaner) getComponentManager().lookup(HTMLCleaner.ROLE, "wysiwyg-default"); + } + + /** + * Test most basic cleaning. + */ + public void testBasicCleaning() + { + super.testBasicCleaning(cleaner); + } + + /** + * Test stripping of {@code <style>} and {@code <script>} tags. + */ + public void testTagStripping() + { + super.testTagStripping(cleaner); + } + + /** + * Test stripping of redundant tags. + */ + public void testRedundancyFiltering() + { + super.testRedundancyFiltering(cleaner); + } +}