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 2017/02/02 16:10:02 UTC

[1/2] tika git commit: TIKA-2025 -- fix xls/x testBigIntegersWGeneralFormat to work in multiple locales. This closes #151

Repository: tika
Updated Branches:
  refs/heads/master 73a37a4c2 -> da8363fe6


TIKA-2025 -- fix xls/x testBigIntegersWGeneralFormat to work in multiple locales. This closes #151


Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/3c0cd647
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/3c0cd647
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/3c0cd647

Branch: refs/heads/master
Commit: 3c0cd647571d23665056de9adcaf5d58dc087fb9
Parents: 280ab87
Author: tballison <ta...@mitre.org>
Authored: Thu Feb 2 11:09:36 2017 -0500
Committer: tballison <ta...@mitre.org>
Committed: Thu Feb 2 11:09:36 2017 -0500

----------------------------------------------------------------------
 .../org/apache/tika/parser/microsoft/ExcelParserTest.java |  9 +++++++--
 .../tika/parser/microsoft/ooxml/OOXMLParserTest.java      | 10 +++++++---
 2 files changed, 14 insertions(+), 5 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/tika/blob/3c0cd647/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
index db137e0..17a0b30 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
@@ -21,9 +21,11 @@ import static org.junit.Assert.assertTrue;
 import static org.junit.Assert.fail;
 
 import java.io.InputStream;
+import java.text.DecimalFormatSymbols;
 import java.util.List;
 import java.util.Locale;
 
+import org.apache.poi.util.LocaleUtil;
 import org.apache.tika.TikaTest;
 import org.apache.tika.detect.DefaultDetector;
 import org.apache.tika.detect.Detector;
@@ -469,8 +471,11 @@ public class ExcelParserTest extends TikaTest {
         String xml = getXML("testEXCEL_big_numbers.xls").xml;
         assertContains("123456789012345", xml);//15 digit number
         assertContains("123456789012346", xml);//15 digit formula
-        assertContains("1.23456789012345E15", xml);//16 digit number is treated as scientific notation
-        assertContains("1.23456789012345E15", xml);//16 digit formula, ditto
+        Locale locale = LocaleUtil.getUserLocale();
+        DecimalFormatSymbols symbols = new DecimalFormatSymbols(locale);
+        //16 digit number is treated as scientific notation as is the 16 digit formula
+        assertContains("1"+symbols.getDecimalSeparator()+"23456789012345E15</td>\t"+
+                "<td>1"+symbols.getDecimalSeparator()+"23456789012345E15", xml);
     }
 
     @Test

http://git-wip-us.apache.org/repos/asf/tika/blob/3c0cd647/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
index 6464e79..25c0346 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
@@ -30,6 +30,7 @@ import java.io.File;
 import java.io.InputStream;
 import java.io.PrintStream;
 import java.io.StringWriter;
+import java.text.DecimalFormatSymbols;
 import java.util.Arrays;
 import java.util.Date;
 import java.util.HashMap;
@@ -37,6 +38,7 @@ import java.util.List;
 import java.util.Locale;
 import java.util.Map;
 
+import org.apache.poi.util.LocaleUtil;
 import org.apache.tika.TikaTest;
 import org.apache.tika.config.TikaConfig;
 import org.apache.tika.exception.EncryptedDocumentException;
@@ -1263,9 +1265,11 @@ public class OOXMLParserTest extends TikaTest {
         String xml = getXML("testEXCEL_big_numbers.xlsx").xml;
         assertContains("123456789012345", xml);//15 digit number
         assertContains("123456789012346", xml);//15 digit formula
-        assertContains("1.23456789012345E+15", xml);//16 digit number is treated as scientific notation
-        assertContains("1.23456789012345E+15", xml);//16 digit formula, ditto
-    }
+        Locale locale = LocaleUtil.getUserLocale();
+        DecimalFormatSymbols symbols = new DecimalFormatSymbols(locale);
+        //16 digit number is treated as scientific notation as is the 16 digit formula
+        assertContains("1"+symbols.getDecimalSeparator()+"23456789012345E+15</td>\t"+
+                "<td>1"+symbols.getDecimalSeparator()+"23456789012345E+15", xml);    }
 
     @Test
     public void testBoldHyperlink() throws Exception {


[2/2] tika git commit: Merge remote-tracking branch 'origin/master'

Posted by ta...@apache.org.
Merge remote-tracking branch 'origin/master'


Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/da8363fe
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/da8363fe
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/da8363fe

Branch: refs/heads/master
Commit: da8363fe62c490e6ec669e57ba19e9a49a9ddbcb
Parents: 3c0cd64 73a37a4
Author: tballison <ta...@mitre.org>
Authored: Thu Feb 2 11:09:56 2017 -0500
Committer: tballison <ta...@mitre.org>
Committed: Thu Feb 2 11:09:56 2017 -0500

----------------------------------------------------------------------
 .../org/apache/tika/mime/tika-mimetypes.xml     |  10 ++++++
 .../org/apache/tika/mime/TestMimeTypes.java     |  17 ++++++++++
 .../test/resources/test-documents/testSAS.sas   |  33 +++++++++++++++++++
 .../resources/test-documents/testSAS.sas7bdat   | Bin 0 -> 17408 bytes
 .../test/resources/test-documents/testSAS.sd2   | Bin 0 -> 16640 bytes
 .../test/resources/test-documents/testSAS.xpt   | Bin 0 -> 3360 bytes
 tika-server/pom.xml                             |  19 +++++++----
 7 files changed, 73 insertions(+), 6 deletions(-)
----------------------------------------------------------------------