Bug 64322: Optimize performance of reading ole2 files

Remember channel-size to no re-read it for every read-access,
but reset it if we extend the size of the file
profiling indicates Channel.size() sometimes has similar runtime
overhead as position() or read()!

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1877816 13f79535-47bb-0310-9956-ffa450edef68

src/java/org/apache/poi/poifs/nio/FileBackedDataSource.java

@@ -39,6 +39,8 @@ public class FileBackedDataSource extends DataSource {
     private final static POILogger logger = POILogFactory.getLogger(FileBackedDataSource.class);
 
     private final FileChannel channel;
+    private Long channelSize;
+
     private final boolean writable;
     // remember file base, which needs to be closed too
     private RandomAccessFile srcFile;
@@ -97,8 +99,9 @@ public class FileBackedDataSource extends DataSource {
             // remember this buffer for cleanup
             buffersToClean.put(dst,dst);
         } else {
-            // allocate the buffer on the heap if we cannot map the data in directly
             channel.position(position);
+
+            // allocate the buffer on the heap if we cannot map the data in directly
             dst = ByteBuffer.allocate(length);
 
             // Read the contents and check that we could read some data
@@ -118,6 +121,11 @@ public class FileBackedDataSource extends DataSource {
     @Override
     public void write(ByteBuffer src, long position) throws IOException {
         channel.write(src, position);
+
+        // we have to re-read size if we write "after" the recorded one
+        if(channelSize != null && position >= channelSize) {
+            channelSize = null;
+        }
     }
 
     @Override
@@ -131,7 +139,13 @@ public class FileBackedDataSource extends DataSource {
 
     @Override
     public long size() throws IOException {
-        return channel.size();
+        // this is called often and profiling showed that channel.size()
+        // was taking a large part of processing-time, so we only read it
+        // once
+        if(channelSize == null) {
+            channelSize = channel.size();
+        }
+        return channelSize;
     }
 
     public void releaseBuffer(ByteBuffer buffer) {

src/testcases/org/apache/poi/poifs/filesystem/TestPOIFSFileSystem.java

@@ -24,11 +24,18 @@ import static org.junit.Assert.fail;
 
 import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
+import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
+import java.io.UnsupportedEncodingException;
 import java.nio.ByteBuffer;
+import java.util.HashMap;
 
 import org.apache.poi.POIDataSamples;
+import org.apache.poi.hpsf.NoPropertySetStreamException;
+import org.apache.poi.hpsf.Property;
+import org.apache.poi.hpsf.PropertySet;
+import org.apache.poi.hpsf.Section;
 import org.apache.poi.hssf.HSSFTestDataSamples;
 import org.apache.poi.poifs.common.POIFSBigBlockSize;
 import org.apache.poi.poifs.common.POIFSConstants;
@@ -293,4 +300,66 @@ public final class TestPOIFSFileSystem {
 
 		assertEquals(FileMagic.UNKNOWN, FileMagic.valueOf("foobaa".getBytes(UTF_8)));
 	}
+
+	@Test
+	public void test64322() throws NoPropertySetStreamException, IOException {
+		try (POIFSFileSystem poiFS = new POIFSFileSystem(_samples.getFile("64322.ole2"))) {
+			int count = recurseDir(poiFS.getRoot());
+
+			assertEquals("Expecting a fixed number of entries being found in the test-document",
+					1285, count);
+		}
+	}
+
+	@Test
+	public void test64322a() throws NoPropertySetStreamException, IOException {
+		try (POIFSFileSystem poiFS = new POIFSFileSystem(_samples.openResourceAsStream("64322.ole2"))) {
+			int count = recurseDir(poiFS.getRoot());
+
+			assertEquals("Expecting a fixed number of entries being found in the test-document",
+					1285, count);
+		}
+	}
+
+	private static int recurseDir(DirectoryEntry dir) throws IOException, NoPropertySetStreamException {
+		int count = 0;
+		for (Entry entry : dir) {
+			count++;
+			if (entry instanceof DirectoryEntry) {
+				count += recurseDir((DirectoryEntry) entry);
+			}
+			if (entry instanceof DocumentEntry) {
+				DocumentEntry de = (DocumentEntry) entry;
+				HashMap<String, String> props = new HashMap<>();
+				try (DocumentInputStream dis = new DocumentInputStream(de)) {
+					props.put("name", de.getName());
+
+					if (PropertySet.isPropertySetStream(dis)) {
+						dis.mark(10000000);
+						PropertySet ps = null;
+						try {
+							ps = new PropertySet(dis);
+
+						} catch (UnsupportedEncodingException e) {
+							// ignore
+						}
+						if (ps != null) {
+							for (Section section : ps.getSections()) {
+								for (Property p : section.getProperties()) {
+									String prop = section.getDictionary() != null
+											? section.getDictionary().get(p.getID())
+											: String.valueOf(p.getID());
+									if (p.getValue() != null)
+										props.put("property_" + prop, p.getValue().toString());
+								}
+							}
+						}
+						dis.reset();
+					}
+				}
+				assertTrue(props.size() > 0);
+			}
+		}
+		return count;
+	}
 }