Merge pull request #169 from pjfanning/namespaces

use namespace aware parsing/xpath resolution

src/main/java/com/monitorjbl/xlsx/StreamingReader.java

@@ -336,7 +336,7 @@ public StreamingReader read(File f) {
         }
 
         StylesTable styles = reader.getStylesTable();
-        NodeList workbookPr = searchForNodeList(document(reader.getWorkbookData()), "/workbook/workbookPr");
+        NodeList workbookPr = searchForNodeList(document(reader.getWorkbookData()), "/ss:workbook/ss:workbookPr");
         if (workbookPr.getLength() == 1) {
           final Node date1904 = workbookPr.item(0).getAttributes().getNamedItem("date1904");
           if (date1904 != null) {
@@ -369,7 +369,7 @@ private InputStream findSheet(XSSFReader reader) throws IOException, InvalidForm
       if(sheetName != null) {
         index = -1;
         //This file is separate from the worksheet data, and should be fairly small
-        NodeList nl = searchForNodeList(document(reader.getWorkbookData()), "/workbook/sheets/sheet");
+        NodeList nl = searchForNodeList(document(reader.getWorkbookData()), "/ss:workbook/ss:sheets/ss:sheet");
         for(int i = 0; i < nl.getLength(); i++) {
           if(Objects.equals(nl.item(i).getAttributes().getNamedItem("name").getTextContent(), sheetName)) {
             index = i;

src/main/java/com/monitorjbl/xlsx/XmlUtils.java

@@ -5,25 +5,29 @@
 import org.w3c.dom.NodeList;
 import org.xml.sax.SAXException;
 
+import javax.xml.XMLConstants;
+import javax.xml.namespace.NamespaceContext;
 import javax.xml.parsers.DocumentBuilderFactory;
 import javax.xml.parsers.ParserConfigurationException;
+import javax.xml.xpath.XPath;
 import javax.xml.xpath.XPathConstants;
 import javax.xml.xpath.XPathExpressionException;
 import javax.xml.xpath.XPathFactory;
 import java.io.IOException;
 import java.io.InputStream;
+import java.util.*;
 
 public class XmlUtils {
   public static Document document(InputStream is) {
     try {
       DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
-
+      factory.setNamespaceAware(true);
+      factory.setValidating(false);
       factory.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true);
       factory.setFeature("http://xml.org/sax/features/external-parameter-entities", false);
       factory.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
       factory.setExpandEntityReferences(false);
       factory.setXIncludeAware(false);
-
       return factory.newDocumentBuilder().parse(is);
     } catch(SAXException | IOException | ParserConfigurationException e) {
       throw new ParseException(e);
@@ -32,11 +36,59 @@ public static Document document(InputStream is) {
 
   public static NodeList searchForNodeList(Document document, String xpath) {
     try {
-      return (NodeList) XPathFactory.newInstance().newXPath().compile(xpath)
-          .evaluate(document, XPathConstants.NODESET);
+      XPath xp = XPathFactory.newInstance().newXPath();
+      NamespaceContextImpl nc = new NamespaceContextImpl();
+      nc.addNamespace("ss", "http://schemas.openxmlformats.org/spreadsheetml/2006/main");
+      xp.setNamespaceContext(nc);
+      return (NodeList)xp.compile(xpath)
+              .evaluate(document, XPathConstants.NODESET);
     } catch(XPathExpressionException e) {
       throw new ParseException(e);
     }
   }
 
+  private static class NamespaceContextImpl implements NamespaceContext {
+    private Map<String, String> urisByPrefix = new HashMap<String, String>();
+
+    private Map<String, Set> prefixesByURI = new HashMap<String, Set>();
+
+    public NamespaceContextImpl() {
+      addNamespace(XMLConstants.XML_NS_PREFIX, XMLConstants.XML_NS_URI);
+      addNamespace(XMLConstants.XMLNS_ATTRIBUTE, XMLConstants.XMLNS_ATTRIBUTE_NS_URI);
+    }
+
+    public void addNamespace(String prefix, String namespaceURI) {
+      urisByPrefix.put(prefix, namespaceURI);
+      if (prefixesByURI.containsKey(namespaceURI)) {
+        (prefixesByURI.get(namespaceURI)).add(prefix);
+      } else {
+        Set<String> set = new HashSet<String>();
+        set.add(prefix);
+        prefixesByURI.put(namespaceURI, set);
+      }
+    }
+
+    public String getNamespaceURI(String prefix) {
+      if (prefix == null)
+        throw new IllegalArgumentException("prefix cannot be null");
+      if (urisByPrefix.containsKey(prefix))
+        return (String) urisByPrefix.get(prefix);
+      else
+        return XMLConstants.NULL_NS_URI;
+    }
+
+    public String getPrefix(String namespaceURI) {
+      return (String) getPrefixes(namespaceURI).next();
+    }
+
+    public Iterator getPrefixes(String namespaceURI) {
+      if (namespaceURI == null)
+        throw new IllegalArgumentException("namespaceURI cannot be null");
+      if (prefixesByURI.containsKey(namespaceURI)) {
+        return ((Set) prefixesByURI.get(namespaceURI)).iterator();
+      } else {
+        return Collections.EMPTY_SET.iterator();
+      }
+    }
+  }
 }

src/main/java/com/monitorjbl/xlsx/impl/StreamingSheetReader.java

@@ -12,7 +12,6 @@
 import org.apache.poi.xssf.usermodel.XSSFRichTextString;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
-import org.xml.sax.SAXException;
 
 import javax.xml.namespace.QName;
 import javax.xml.stream.XMLEventReader;
@@ -72,7 +71,7 @@ private boolean getRow() {
       }
       rowCacheIterator = rowCache.iterator();
       return rowCacheIterator.hasNext();
-    } catch(XMLStreamException | SAXException e) {
+    } catch(XMLStreamException e) {
       throw new ParseException("Error reading XML stream", e);
     }
   }
@@ -100,9 +99,8 @@ private String[] splitCellRef(String ref) {
    * Handles a SAX event.
    *
    * @param event
-   * @throws SAXException
    */
-  private void handleEvent(XMLEvent event) throws SAXException {
+  private void handleEvent(XMLEvent event) {
     if(event.getEventType() == XMLStreamConstants.CHARACTERS) {
       Characters c = event.asCharacters();
       lastContents += c.getData();

src/main/java/com/monitorjbl/xlsx/impl/StreamingWorkbookReader.java

@@ -123,7 +123,7 @@ public void init(File f) {
       }
 
       StylesTable styles = reader.getStylesTable();
-      NodeList workbookPr = searchForNodeList(document(reader.getWorkbookData()), "/workbook/workbookPr");
+      NodeList workbookPr = searchForNodeList(document(reader.getWorkbookData()), "/ss:workbook/ss:workbookPr");
       if(workbookPr.getLength() == 1) {
         final Node date1904 = workbookPr.item(0).getAttributes().getNamedItem("date1904");
         if(date1904 != null) {
@@ -141,8 +141,8 @@ public void init(File f) {
     }
   }
 
-  void loadSheets(XSSFReader reader, SharedStringsTable sst, StylesTable stylesTable, int rowCacheSize) throws IOException, InvalidFormatException,
-      XMLStreamException {
+  void loadSheets(XSSFReader reader, SharedStringsTable sst, StylesTable stylesTable, int rowCacheSize)
+          throws IOException, InvalidFormatException, XMLStreamException {
     lookupSheetNames(reader);
 
     //Some workbooks have multiple references to the same sheet. Need to filter
@@ -165,7 +165,7 @@ void loadSheets(XSSFReader reader, SharedStringsTable sst, StylesTable stylesTab
 
   void lookupSheetNames(XSSFReader reader) throws IOException, InvalidFormatException {
     sheetProperties.clear();
-    NodeList nl = searchForNodeList(document(reader.getWorkbookData()), "/workbook/sheets/sheet");
+    NodeList nl = searchForNodeList(document(reader.getWorkbookData()), "/ss:workbook/ss:sheets/ss:sheet");
     for(int i = 0; i < nl.getLength(); i++) {
       Map<String, String> props = new HashMap<>();
       props.put("name", nl.item(i).getAttributes().getNamedItem("name").getTextContent());