Repository: tika Updated Branches: refs/heads/2.x 28010d90d -> 2d4889f44
TIKA 2025 -- fix xls/x testBigIntegersWGeneralFormat to work in multiple locales Project: http://git-wip-us.apache.org/repos/asf/tika/repo Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/2d4889f4 Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/2d4889f4 Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/2d4889f4 Branch: refs/heads/2.x Commit: 2d4889f44fce7795788d8446bc6a8091101b4a22 Parents: 28010d9 Author: tballison <talli...@mitre.org> Authored: Thu Feb 2 11:13:23 2017 -0500 Committer: tballison <talli...@mitre.org> Committed: Thu Feb 2 11:13:23 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/2d4889f4/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java b/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java index de65555..db78f13 100644 --- a/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java +++ b/tika-parser-modules/tika-parser-office-module/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; @@ -416,8 +418,11 @@ 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); } public void testMacros() throws Exception { http://git-wip-us.apache.org/repos/asf/tika/blob/2d4889f4/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java b/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java index eec9f89..fa92a7e 100644 --- a/tika-parser-modules/tika-parser-office-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java +++ b/tika-parser-modules/tika-parser-office-module/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; @@ -1247,9 +1249,11 @@ 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 {