You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2017/01/24 19:04:27 UTC

[1/2] tika git commit: TIKA 2244 -- be more parsimonious with BufferedInputStream. AutoDetectReader

Repository: tika
Updated Branches:
  refs/heads/2.x bd667acde -> 4599374d6


TIKA 2244 --   be more parsimonious with BufferedInputStream.    AutoDetectReader


Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/985c1aef
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/985c1aef
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/985c1aef

Branch: refs/heads/2.x
Commit: 985c1aef89f280c3cdb5e63b01b8c2cc68c55dae
Parents: 7882817
Author: tballison <ta...@mitre.org>
Authored: Tue Jan 24 14:04:02 2017 -0500
Committer: tballison <ta...@mitre.org>
Committed: Tue Jan 24 14:04:02 2017 -0500

----------------------------------------------------------------------
 .../apache/tika/detect/AutoDetectReader.java    | 22 +++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/tika/blob/985c1aef/tika-core/src/main/java/org/apache/tika/detect/AutoDetectReader.java
----------------------------------------------------------------------
diff --git a/tika-core/src/main/java/org/apache/tika/detect/AutoDetectReader.java b/tika-core/src/main/java/org/apache/tika/detect/AutoDetectReader.java
index b498a17..2b2ff62 100644
--- a/tika-core/src/main/java/org/apache/tika/detect/AutoDetectReader.java
+++ b/tika-core/src/main/java/org/apache/tika/detect/AutoDetectReader.java
@@ -91,8 +91,17 @@ public class AutoDetectReader extends BufferedReader {
         }
     }
 
+    /**
+     *
+     * @param stream stream must support mark!
+     * @param metadata
+     * @param detectors
+     * @param handler
+     * @throws IOException
+     * @throws TikaException
+     */
     private AutoDetectReader(
-            BufferedInputStream stream, Metadata metadata,
+            InputStream stream, Metadata metadata,
             List<EncodingDetector> detectors, LoadErrorHandler handler)
             throws IOException, TikaException {
         this(stream, detect(stream, metadata, detectors, handler));
@@ -101,14 +110,21 @@ public class AutoDetectReader extends BufferedReader {
     public AutoDetectReader(
             InputStream stream, Metadata metadata,
             ServiceLoader loader) throws IOException, TikaException {
-        this(new BufferedInputStream(stream), metadata,
+        this(getBuffered(stream), metadata,
                 loader.loadServiceProviders(EncodingDetector.class),
                 loader.getLoadErrorHandler());
     }
 
+    private static InputStream getBuffered(InputStream stream) {
+        if (stream.markSupported()) {
+            return stream;
+        }
+        return new BufferedInputStream(stream);
+    }
+
     public AutoDetectReader(InputStream stream, Metadata metadata)
             throws IOException, TikaException {
-        this(new BufferedInputStream(stream), metadata, DEFAULT_LOADER);
+        this(stream, metadata, DEFAULT_LOADER);
     }
 
     public AutoDetectReader(InputStream stream)


[2/2] tika git commit: Merge remote-tracking branch 'origin/2.x' into 2.x

Posted by ta...@apache.org.
Merge remote-tracking branch 'origin/2.x' into 2.x


Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/4599374d
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/4599374d
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/4599374d

Branch: refs/heads/2.x
Commit: 4599374d623dc6e4e5c7f058f18dadeed46a591e
Parents: 985c1ae bd667ac
Author: tballison <ta...@mitre.org>
Authored: Tue Jan 24 14:04:19 2017 -0500
Committer: tballison <ta...@mitre.org>
Committed: Tue Jan 24 14:04:19 2017 -0500

----------------------------------------------------------------------
 CHANGES.txt                                     |  3 ++
 .../org/apache/tika/mime/TestMimeTypes.java     | 25 +++++-----
 .../tika/parser/AutoDetectParserTest.java       |  2 +-
 .../org/apache/tika/mime/tika-mimetypes.xml     | 52 ++++++++++++--------
 .../java/org/apache/tika/TikaDetectionTest.java |  6 ++-
 .../apache/tika/mime/MimeTypesReaderTest.java   |  2 +-
 .../apache/tika/parser/CompositeParserTest.java |  4 +-
 .../apache/tika/parser/image/ImageParser.java   | 16 +++---
 .../tika/parser/ocr/TesseractOCRParser.java     |  3 +-
 .../apache/tika/parser/pdf/PDFParserTest.java   |  2 +-
 .../tika/parser/microsoft/HSLFExtractor.java    |  4 +-
 .../AbstractPOIContainerExtractionTest.java     |  4 +-
 .../apache/tika/parser/rtf/RTFParserTest.java   |  4 +-
 .../apache/tika/server/TikaMimeTypesTest.java   | 13 ++---
 14 files changed, 79 insertions(+), 61 deletions(-)
----------------------------------------------------------------------