Revision: 15057
http://gate.svn.sourceforge.net/gate/?rev=15057&view=rev
Author: markagreenwood
Date: 2012-01-16 10:35:29 +0000 (Mon, 16 Jan 2012)
Log Message:
-----------
five new tests to make sure that the tika parsers are loaded properly and that
we can use them to load documents with some content
Modified Paths:
--------------
gate/trunk/src/gate/TestGate.java
Added Paths:
-----------
gate/trunk/src/gate/corpora/TestTikaFormats.java
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.doc
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.docx
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.odt
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.pdf
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.rtf
Modified: gate/trunk/src/gate/TestGate.java
===================================================================
--- gate/trunk/src/gate/TestGate.java 2012-01-16 02:28:07 UTC (rev 15056)
+++ gate/trunk/src/gate/TestGate.java 2012-01-16 10:35:29 UTC (rev 15057)
@@ -22,6 +22,7 @@
import gate.corpora.TestDocument;
import gate.corpora.TestDocumentStaxUtils;
import gate.corpora.TestSerialCorpus;
+import gate.corpora.TestTikaFormats;
import gate.creole.TestControllers;
import gate.creole.TestCreole;
import gate.creole.TestCreoleAnnotationHandler;
@@ -265,6 +266,7 @@
// suite.addTest(TestJacl.suite());
suite.addTest(TestDocument.suite());
suite.addTest(TestDocumentStaxUtils.suite());
+ suite.addTest(TestTikaFormats.suite());
suite.addTest(TestRBTreeMap.suite());
suite.addTest(TestCorpus.suite());
suite.addTest(TestSerialCorpus.suite());
Added: gate/trunk/src/gate/corpora/TestTikaFormats.java
===================================================================
--- gate/trunk/src/gate/corpora/TestTikaFormats.java
(rev 0)
+++ gate/trunk/src/gate/corpora/TestTikaFormats.java 2012-01-16 10:35:29 UTC
(rev 15057)
@@ -0,0 +1,75 @@
+/*
+ * TestTikaFormats.java
+ *
+ * Copyright (c) 1995-2012, The University of Sheffield. See the file
+ * COPYRIGHT.txt in the software or at http://gate.ac.uk/gate/COPYRIGHT.txt
+ *
+ * This file is part of GATE (see http://gate.ac.uk/), and is free software,
+ * licenced under the GNU Library General Public License, Version 2, June 1991
+ * (in the distribution as file licence.html, and also available at
+ * http://gate.ac.uk/gate/licence.html).
+ *
+ * Mark A. Greenwood, 16/01/2012
+ *
+ * $Id$
+ */
+
+package gate.corpora;
+
+import gate.Document;
+import gate.Factory;
+import gate.Gate;
+import gate.util.GateException;
+
+import java.net.URL;
+
+import junit.framework.Test;
+import junit.framework.TestCase;
+import junit.framework.TestSuite;
+
+/**
+ * Tests to make sure the Tika format parsers work as expected
+ */
+public class TestTikaFormats extends TestCase {
+
+ public void setUp() throws GateException {
+ Gate.init();
+ }
+
+ private void doTest(String ext) throws Exception {
+ String base = Gate.getUrl().toExternalForm();
+
+ URL url = new URL(base + "tests/tika/tika-test." + ext);
+
+ Document doc = Factory.newDocument(url);
+
+ assertNotNull(doc);
+
+ assertTrue(doc.getContent().toString().indexOf("Testing Tika Format
Parsers") != -1);
+ }
+
+ public void testDOC() throws Exception {
+ doTest("doc");
+ }
+
+ public void testDOCX() throws Exception {
+ doTest("docx");
+ }
+
+ public void testODT() throws Exception {
+ doTest("odt");
+ }
+
+ public void testRTF() throws Exception {
+ doTest("rtf");
+ }
+
+ public void testPDF() throws Exception {
+ doTest("pdf");
+ }
+
+ /** Test suite routine for the test runner */
+ public static Test suite() {
+ return new TestSuite(TestTikaFormats.class);
+ }
+}
Property changes on: gate/trunk/src/gate/corpora/TestTikaFormats.java
___________________________________________________________________
Added: svn:keywords
+ Id
Added: svn:eol-style
+ native
Added: gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.doc
===================================================================
(Binary files differ)
Property changes on:
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.doc
___________________________________________________________________
Added: svn:mime-type
+ application/octet-stream
Added: gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.docx
===================================================================
(Binary files differ)
Property changes on:
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.docx
___________________________________________________________________
Added: svn:mime-type
+ application/octet-stream
Added: gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.odt
===================================================================
(Binary files differ)
Property changes on:
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.odt
___________________________________________________________________
Added: svn:mime-type
+ application/octet-stream
Added: gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.pdf
===================================================================
(Binary files differ)
Property changes on:
gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.pdf
___________________________________________________________________
Added: svn:mime-type
+ application/octet-stream
Added: gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.rtf
===================================================================
--- gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.rtf
(rev 0)
+++ gate/trunk/src/gate/resources/gate.ac.uk/tests/tika/tika-test.rtf
2012-01-16 10:35:29 UTC (rev 15057)
@@ -0,0 +1,34 @@
+{\rtf1\ansi\deff3\adeflang1025
+{\fonttbl{\f0\froman\fprq2\fcharset0 Times New
Roman;}{\f1\froman\fprq2\fcharset2 Symbol;}{\f2\fswiss\fprq2\fcharset0
Arial;}{\f3\froman\fprq2\fcharset128 Times New
Roman;}{\f4\fswiss\fprq2\fcharset128 Arial;}{\f5\fnil\fprq2\fcharset128 Droid
Sans Fallback;}{\f6\fnil\fprq2\fcharset128 Lohit
Hindi;}{\f7\fnil\fprq0\fcharset128 Lohit Hindi;}}
+{\colortbl;\red0\green0\blue0;\red255\green0\blue0;\red128\green128\blue128;}
+{\stylesheet{\s0\snext0\nowidctlpar{\*\hyphen2\hyphlead2\hyphtrail2\hyphmax0}\cf0\kerning1\hich\af5\langfe2052\dbch\af6\afs24\lang1081\loch\f3\fs24\lang2057
Normal;}
+{\s1\sbasedon15\snext16\ilvl0\outlinelevel0\sb240\sa120\keepn\b\hich\af5\dbch\af6\afs32\ab\loch\f4\fs32
Heading 1;}
+{\s15\sbasedon0\snext16\sb240\sa120\keepn\hich\af5\dbch\af6\afs28\loch\f4\fs28
Heading;}
+{\s16\sbasedon0\snext16\sb0\sa120 Text body;}
+{\s17\sbasedon16\snext17\sb0\sa120\dbch\af7 List;}
+{\s18\sbasedon0\snext18\sb120\sa120\noline\i\dbch\af7\afs24\ai\fs24 Caption;}
+{\s19\sbasedon0\snext19\noline\dbch\af7 Index;}
+}{\*\listtable{\list\listtemplateid1
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-432\li432}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-576\li576}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-720\li720}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-864\li864}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-1008\li1008}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-1152\li1152}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-1296\li1296}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-1440\li1440}
+{\listlevel\levelnfc0\leveljc0\levelstartat1\levelfollow0{\leveltext
\'00;}{\levelnumbers;}\fi-1584\li1584}\listid1}
+}{\listoverridetable{\listoverride\listid1\listoverridecount0\ls1}}{\info{\author
Mark Greenwood}{\creatim\yr2012\mo1\dy16\hr9\min45}{\author Mark
Greenwood}{\revtim\yr2012\mo1\dy16\hr9\min48}{\printim\yr0\mo0\dy0\hr0\min0}{\comment
LibreOffice}{\vern3300}}\deftab709
+
+{\*\pgdsctbl
+{\pgdsc0\pgdscuse195\pgwsxn11906\pghsxn16838\marglsxn1134\margrsxn1134\pgdscnxt0
Default;}}
+\formshade\paperh16838\paperw11906\margl1134\margr1134\margt1134\margb1134\sectd\sbknone\sectunlocked1\pgndec\pgwsxn11906\pghsxn16838\marglsxn1134\margrsxn1134\ftnbj\ftnstart1\ftnrstcont\ftnnar\aenddoc\aftnrstcont\aftnstart1\aftnnrlc
+\pgndec\pard\plain
\s1\ilvl0\outlinelevel0\sb240\sa120\keepn\b\hich\af5\dbch\af6\afs32\ab\loch\f4\fs32{\listtext\pard\plain
\tab}\ls1 \li432\ri0\lin432\rin0\fi-432\sb240\sa120{\rtlch \ltrch\loch
+Testing Tika Format Parsers}
+\par \pard\plain
\s0\nowidctlpar{\*\hyphen2\hyphlead2\hyphtrail2\hyphmax0}\cf0\kerning1\hich\af5\langfe2052\dbch\af6\afs24\lang1081\loch\f3\fs24\lang2057{\rtlch
\ltrch\loch
+This is a test document to ensure that we (naming no names) hasn't broken the
Tika format parser again. Strangely it seems that if Tika is broken then the
GATE document is created without }{\cf2\rtlch \ltrch\loch
+error}{\rtlch \ltrch\loch
+ but with no content which is a }{\i\ai\rtlch \ltrch\loch
+bit}{\rtlch \ltrch\loch
+ of a pain.}
+\par }
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
RSA(R) Conference 2012
Mar 27 - Feb 2
Save $400 by Jan. 27
Register now!
http://p.sf.net/sfu/rsa-sfdev2dev2
_______________________________________________
GATE-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gate-cvs