Author: nick
Date: Wed Oct 28 23:21:41 2015
New Revision: 1711162
URL: http://svn.apache.org/viewvc?rev=1711162&view=rev
Log:
Add Tika Facade parse methods for Path and File which take a Metadata object,
to mirror the existing InputStream one. This closes #60 from GitHub
Modified:
tika/trunk/CHANGES.txt
tika/trunk/tika-core/src/main/java/org/apache/tika/Tika.java
Modified: tika/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/tika/trunk/CHANGES.txt?rev=1711162&r1=1711161&r2=1711162&view=diff
==============================================================================
--- tika/trunk/CHANGES.txt (original)
+++ tika/trunk/CHANGES.txt Wed Oct 28 23:21:41 2015
@@ -5,6 +5,9 @@ Release 1.12 - Current Development
* Fix regression with spacing in PPT via Andreas Beeker (TIKA-1777).
+ * Tika Facade parse methods for Path and File added which take a
+ Metadata object, to mirror the existing InputStream one (GitHub-60)
+
Release 1.11 - 10/18/2015
Modified: tika/trunk/tika-core/src/main/java/org/apache/tika/Tika.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/java/org/apache/tika/Tika.java?rev=1711162&r1=1711161&r2=1711162&view=diff
==============================================================================
--- tika/trunk/tika-core/src/main/java/org/apache/tika/Tika.java (original)
+++ tika/trunk/tika-core/src/main/java/org/apache/tika/Tika.java Wed Oct 28
23:21:41 2015
@@ -283,7 +283,8 @@ public class Tika {
*/
public String detect(File file) throws IOException {
Metadata metadata = new Metadata();
- try (InputStream stream = TikaInputStream.get(file, metadata)) {
+ try (@SuppressWarnings("deprecation")
+ InputStream stream = TikaInputStream.get(file, metadata)) {
return detect(stream, metadata);
}
}
@@ -399,7 +400,7 @@ public class Tika {
* the time when the {@link Reader#close()} method is called.
*
* @param stream the document to be parsed
- * @param metadata document metadata
+ * @param metadata where document's metadata will be populated
* @return extracted text content
* @throws IOException if the document can not be read or parsed
*/
@@ -427,32 +428,62 @@ public class Tika {
/**
* Parses the file at the given path and returns the extracted text
content.
+ * <p>
+ * Metadata information extracted from the document is returned in
+ * the supplied metadata instance.
*
* @param path the path of the file to be parsed
+ * @param metadata where document's metadata will be populated
* @return extracted text content
* @throws IOException if the file can not be read or parsed
*/
- public Reader parse(Path path) throws IOException {
- Metadata metadata = new Metadata();
+ public Reader parse(Path path, Metadata metadata) throws IOException {
InputStream stream = TikaInputStream.get(path, metadata);
return parse(stream, metadata);
}
+
+ /**
+ * Parses the file at the given path and returns the extracted text
content.
+ *
+ * @param path the path of the file to be parsed
+ * @return extracted text content
+ * @throws IOException if the file can not be read or parsed
+ */
+ public Reader parse(Path path) throws IOException {
+ return parse(path, new Metadata());
+ }
/**
* Parses the given file and returns the extracted text content.
+ * <p>
+ * Metadata information extracted from the document is returned in
+ * the supplied metadata instance.
*
* @param file the file to be parsed
+ * @param metadata where document's metadata will be populated
* @return extracted text content
* @throws IOException if the file can not be read or parsed
* @see #parse(Path)
*/
- public Reader parse(File file) throws IOException {
- Metadata metadata = new Metadata();
+ public Reader parse(File file, Metadata metadata) throws IOException {
+ @SuppressWarnings("deprecation")
InputStream stream = TikaInputStream.get(file, metadata);
return parse(stream, metadata);
}
/**
+ * Parses the given file and returns the extracted text content.
+ *
+ * @param file the file to be parsed
+ * @return extracted text content
+ * @throws IOException if the file can not be read or parsed
+ * @see #parse(Path)
+ */
+ public Reader parse(File file) throws IOException {
+ return parse(file, new Metadata());
+ }
+
+ /**
* Parses the resource at the given URL and returns the extracted
* text content.
*
@@ -606,6 +637,7 @@ public class Tika {
*/
public String parseToString(File file) throws IOException, TikaException {
Metadata metadata = new Metadata();
+ @SuppressWarnings("deprecation")
InputStream stream = TikaInputStream.get(file, metadata);
return parseToString(stream, metadata);
}
