Merge pull request #38 from spdx/longdashes

Add thin space unicode character (U+2009) to the space normalization

Author: goneall

pom.xml

@@ -4,7 +4,7 @@
 
     <groupId>org.spdx</groupId>
     <artifactId>java-spdx-library</artifactId>
-    <version>0.0.7</version>
+    <version>0.0.8-SNAPSHOT</version>
     <packaging>jar</packaging>
 
     <name>java-spdx-library</name>

src/main/java/org/spdx/utility/compare/LicenseCompareHelper.java

@@ -122,7 +122,7 @@ public class LicenseCompareHelper {
 
 
 	static final String DASHES_REGEX = "[\\u2012\\u2013\\u2014\\u2015]";
-	static final Pattern SPACE_PATTERN = Pattern.compile("[\\u202F\\u2007\\u2060]");
+	static final Pattern SPACE_PATTERN = Pattern.compile("[\\u202F\\u2007\\u2060\\u2009]");
 	static final Pattern PER_CENT_PATTERN = Pattern.compile("per cent", Pattern.CASE_INSENSITIVE);
 	static final Pattern COPYRIGHT_HOLDER_PATTERN = Pattern.compile("copyright holder", Pattern.CASE_INSENSITIVE);
 	static final Pattern COPYRIGHT_HOLDERS_PATTERN = Pattern.compile("copyright holders", Pattern.CASE_INSENSITIVE);

src/test/java/org/spdx/utility/compare/LicenseCompareHelperTest.java

@@ -632,10 +632,11 @@ public void regressionTestZpl21() throws IOException, InvalidSPDXAnalysisExcepti
 		DifferenceDescription result = LicenseCompareHelper.isTextStandardLicense(LicenseInfoFactory.getListedLicenseById("ZPL-2.1"), compareText);
 		assertFalse(result.isDifferenceFound());
 	}
+
 
 	public void testSpaceNormalization() {
-		String t1 = "This is a test of space";
-		String t2 = "This is\u2060a\u2007test\u202Fof space";
+		String t1 = "This is a test of space extra";
+		String t2 = "This is\u2060a\u2007test\u202Fof space\u2009extra";
 		assertTrue(LicenseCompareHelper.isLicenseTextEquivalent(t1, t2));
 	}