You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ju...@apache.org on 2010/09/06 22:36:18 UTC
svn commit: r993146 -
/tika/trunk/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
Author: jukka
Date: Mon Sep 6 20:36:18 2010
New Revision: 993146
URL: http://svn.apache.org/viewvc?rev=993146&view=rev
Log:
TIKA-153: Allow passing of files or memory buffers to parsers
Add support for accessing data from a database BLOB.
Modified:
tika/trunk/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
Modified: tika/trunk/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java?rev=993146&r1=993145&r2=993146&view=diff
==============================================================================
--- tika/trunk/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java (original)
+++ tika/trunk/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java Mon Sep 6 20:36:18 2010
@@ -29,6 +29,8 @@ import java.net.URI;
import java.net.URISyntaxException;
import java.net.URL;
import java.net.URLConnection;
+import java.sql.Blob;
+import java.sql.SQLException;
import org.apache.tika.metadata.Metadata;
@@ -144,6 +146,61 @@ public class TikaInputStream extends Pro
}
/**
+ * Creates a TikaInputStream from the given database BLOB.
+ * <p>
+ * Note that the result set containing the BLOB may need to be kept open
+ * until the returned TikaInputStream has been processed and closed.
+ *
+ * @param blob database BLOB
+ * @return a TikaInputStream instance
+ * @throws SQLException if BLOB data can not be accessed
+ */
+ public static TikaInputStream get(Blob blob) throws SQLException {
+ return get(blob, new Metadata());
+ }
+
+ /**
+ * Blob size threshold that limits the largest BLOB size to be
+ * buffered fully in memory by the {@link #get(Blob, Metadata)}
+ * method.
+ */
+ private static final int BLOB_SIZE_THRESHOLD = 1024 * 1024;
+
+ /**
+ * Creates a TikaInputStream from the given database BLOB. The BLOB
+ * length (if available) is stored as input metadata in the given
+ * metadata instance.
+ * <p>
+ * Note that the result set containing the BLOB may need to be kept open
+ * until the returned TikaInputStream has been processed and closed.
+ *
+ * @param blob database BLOB
+ * @param metadata metadata instance
+ * @return a TikaInputStream instance
+ * @throws SQLException if BLOB data can not be accessed
+ */
+ public static TikaInputStream get(Blob blob, Metadata metadata)
+ throws SQLException {
+ long length = -1;
+ try {
+ length = blob.length();
+ metadata.set(Metadata.CONTENT_LENGTH, Long.toString(length));
+ } catch (SQLException ignore) {
+ }
+
+ // Prefer an in-memory buffer for reasonably sized blobs to reduce
+ // the likelihood of problems caused by long-lived database accesses
+ if (0 <= length && length <= BLOB_SIZE_THRESHOLD) {
+ // the offset in Blob.getBytes() starts at 1
+ return get(blob.getBytes(1, (int) length), metadata);
+ } else {
+ return new TikaInputStream(
+ new BufferedInputStream(blob.getBinaryStream()),
+ null, length);
+ }
+ }
+
+ /**
* Creates a TikaInputStream from the resource at the given URI.
*
* @param uri resource URI