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 2017/01/10 17:46:49 UTC
[5/5] tika git commit: TIKA-2232 -- shorten one unit test and update
changes.
TIKA-2232 -- shorten one unit test and update changes.
Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/86dbde4e
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/86dbde4e
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/86dbde4e
Branch: refs/heads/master
Commit: 86dbde4ec93d4dc962d99349d23f08c326e607a3
Parents: 9fdf9a8
Author: tballison <ta...@mitre.org>
Authored: Tue Jan 10 12:46:22 2017 -0500
Committer: tballison <ta...@mitre.org>
Committed: Tue Jan 10 12:46:22 2017 -0500
----------------------------------------------------------------------
CHANGES.txt | 9 +++++++--
.../org/apache/tika/parser/pdf/PDFParserTest.java | 18 ++++--------------
2 files changed, 11 insertions(+), 16 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/tika/blob/86dbde4e/CHANGES.txt
----------------------------------------------------------------------
diff --git a/CHANGES.txt b/CHANGES.txt
index 630aa73..32caa4e 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,10 +1,14 @@
Release 1.15 - ??
+ * Add parsing of JBIG2 and extraction of JBIG2 from PDFs when
+ required dependencies are added to class path by user.
+ Contributed by Pascal Essiembre (TIKA-2232).
+
* Mime magic for the OneNote family (.one / .onetoc / .onepkg), no parser
(TIKA-2224).
* Add parsers for WordPerfect and QuattroPro (.qpw) files.
- Contributed by Pascal Essiembre (TIKA-1946).
+ Contributed by Pascal Essiembre (TIKA-1946 and TIKA-2228).
* Add configurability of "preserve-interword-spacing" to
TesseractOCRParser (TIKA-2190).
@@ -40,7 +44,8 @@ Release 1.15 - ??
* Allow configuration of timeout for ForkParser (TIKA-2170).
- * Add extraction of .jpx inline images from PDFs (TIKA-2175).
+ * Add extraction of .jpx inline images from PDFs when required
+ dependencies are added by user to class path (TIKA-2175).
* Add .jpx, .jp2, .ppm to formats handled by Tesseract (TIKA-2174).
http://git-wip-us.apache.org/repos/asf/tika/blob/86dbde4e/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
index 34c98f9..2d056c7 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -643,28 +643,18 @@ public class PDFParserTest extends TikaTest {
@Test // TIKA-2232
public void testEmbeddedJBIG2Image() throws Exception {
- String xml = getXML("/testPDF_JBIG2.pdf").xml;
- assertContains("test images compressed using JBIG2", xml);
-
- RecursiveParserWrapper p = new RecursiveParserWrapper(
- new AutoDetectParser(), new BasicContentHandlerFactory(
- BasicContentHandlerFactory.HANDLER_TYPE.IGNORE, -1));
+
ParseContext context = new ParseContext();
PDFParserConfig config = new PDFParserConfig();
config.setExtractInlineImages(true);
config.setExtractUniqueInlineImagesOnly(false);
context.set(PDFParserConfig.class, config);
- context.set(Parser.class, p);
- try (TikaInputStream tis = TikaInputStream.get(
- getResourceAsStream("/test-documents/testPDF_JBIG2.pdf"))) {
- p.parse(tis, new BodyContentHandler(-1), new Metadata(), context);
- }
-
- List<Metadata> metadatas = p.getMetadata();
+ List<Metadata> metadatas = getRecursiveMetadata("testPDF_JBIG2.pdf", context);
assertEquals(2, metadatas.size());
-
+ assertContains("test images compressed using JBIG2", metadatas.get(0).get(RecursiveParserWrapper.TIKA_CONTENT));
+
for (String key : metadatas.get(1).names()) {
if (key.startsWith("X-TIKA:EXCEPTION")) {
fail("Exception: " + metadatas.get(1).get(key));