Revert "LANG-1269: Wrong name or result of StringUtils#getJaroWinklerDistance (closes #198)"
This reverts commit a40b2a907a69e51675d7d0502b2608833c4da343, because adding a new method StringUtils#getJaroWinklerSimilarity and immediately deprecating it makes not sense. Project: http://git-wip-us.apache.org/repos/asf/commons-lang/repo Commit: http://git-wip-us.apache.org/repos/asf/commons-lang/commit/f4ee399e Tree: http://git-wip-us.apache.org/repos/asf/commons-lang/tree/f4ee399e Diff: http://git-wip-us.apache.org/repos/asf/commons-lang/diff/f4ee399e Branch: refs/heads/release Commit: f4ee399e31eb61741f5f2167d6af8f49c0e991b6 Parents: 844cd42 Author: pascalschumacher <pascalschumac...@gmx.net> Authored: Sun Mar 19 14:25:20 2017 +0100 Committer: pascalschumacher <pascalschumac...@gmx.net> Committed: Sun Mar 19 14:25:20 2017 +0100 ---------------------------------------------------------------------- src/changes/changes.xml | 1 - .../org/apache/commons/lang3/StringUtils.java | 54 -------------------- .../apache/commons/lang3/StringUtilsTest.java | 28 ---------- 3 files changed, 83 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/commons-lang/blob/f4ee399e/src/changes/changes.xml ---------------------------------------------------------------------- diff --git a/src/changes/changes.xml b/src/changes/changes.xml index ee3097d..3edd5e6 100644 --- a/src/changes/changes.xml +++ b/src/changes/changes.xml @@ -54,7 +54,6 @@ The <action> type attribute can be add,update,fix,remove. <action issue="LANG-1287" type="fix" dev="pschumacher" due-to="Ivan Morozov">RandomStringUtils#random can enter infinite loop if end parameter is to small</action> <action issue="LANG-1285" type="fix" dev="pschumacher" due-to="Francesco Chicchiriccò">NullPointerException in FastDateParser$TimeZoneStrategy</action> <action issue="LANG-1281" type="fix" dev="pschumacher" due-to="Andreas Lundblad">Javadoc of StringUtils.ordinalIndexOf is contradictory.</action> - <action issue="LANG-1269" type="fix" dev="pschumacher">Wrong name or result of StringUtils#getJaroWinklerDistance</action> <action issue="LANG-1188" type="fix" dev="pschumacher">StringUtils#join(T...): warning: [unchecked] Possible heap pollution from parameterized vararg type T</action> <action issue="LANG-1144" type="fix" dev="ggregory" due-to="Waldemar Maier, Gary Gregory">Multiple calls of org.apache.commons.lang3.concurrent.LazyInitializer.initialize() are possible.</action> <action issue="LANG-1276" type="fix" dev="pschumacher" due-to="Andy Klimczak">StrBuilder#replaceAll ArrayIndexOutOfBoundsException</action> http://git-wip-us.apache.org/repos/asf/commons-lang/blob/f4ee399e/src/main/java/org/apache/commons/lang3/StringUtils.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/lang3/StringUtils.java b/src/main/java/org/apache/commons/lang3/StringUtils.java index 6e32a5c..26aea76 100644 --- a/src/main/java/org/apache/commons/lang3/StringUtils.java +++ b/src/main/java/org/apache/commons/lang3/StringUtils.java @@ -8213,7 +8213,6 @@ public class StringUtils { * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/similarity/JaroWinklerDistance.html"> * JaroWinklerDistance</a> instead */ - @Deprecated public static double getJaroWinklerDistance(final CharSequence first, final CharSequence second) { final double DEFAULT_SCALING_FACTOR = 0.1; @@ -8231,59 +8230,6 @@ public class StringUtils { return Math.round(jw * 100.0D) / 100.0D; } - /** - * <p>Find the Jaro Winkler Similarity which indicates the similarity score between two Strings.</p> - * - * <p>The Jaro measure is the weighted sum of percentage of matched characters from each file and transposed characters. - * Winkler increased this measure for matching initial characters.</p> - * - * <p>This implementation is based on the Jaro Winkler similarity algorithm - * from <a href="http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance">http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance</a>.</p> - * - * <pre> - * StringUtils.getJaroWinklerSimilarity(null, null) = IllegalArgumentException - * StringUtils.getJaroWinklerSimilarity("","") = 0.0 - * StringUtils.getJaroWinklerSimilarity("","a") = 0.0 - * StringUtils.getJaroWinklerSimilarity("aaapppp", "") = 0.0 - * StringUtils.getJaroWinklerSimilarity("frog", "fog") = 0.93 - * StringUtils.getJaroWinklerSimilarity("fly", "ant") = 0.0 - * StringUtils.getJaroWinklerSimilarity("elephant", "hippo") = 0.44 - * StringUtils.getJaroWinklerSimilarity("hippo", "elephant") = 0.44 - * StringUtils.getJaroWinklerSimilarity("hippo", "zzzzzzzz") = 0.0 - * StringUtils.getJaroWinklerSimilarity("hello", "hallo") = 0.88 - * StringUtils.getJaroWinklerSimilarity("ABC Corporation", "ABC Corp") = 0.93 - * StringUtils.getJaroWinklerSimilarity("D N H Enterprises Inc", "D & H Enterprises, Inc.") = 0.95 - * StringUtils.getJaroWinklerSimilarity("My Gym Children's Fitness Center", "My Gym. Childrens Fitness") = 0.92 - * StringUtils.getJaroWinklerSimilarity("PENNSYLVANIA", "PENNCISYLVNIA") = 0.88 - * </pre> - * - * @param first the first String, must not be null - * @param second the second String, must not be null - * @return result similarity - * @throws IllegalArgumentException if either String input {@code null} - * @since 3.6 - * @deprecated as of 3.6, use commons-text - * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/similarity/JaroWinklerDistance.html"> - * JaroWinklerDistance</a> instead - */ - @Deprecated - public static double getJaroWinklerSimilarity(final CharSequence first, final CharSequence second) { - final double DEFAULT_SCALING_FACTOR = 0.1; - - if (first == null || second == null) { - throw new IllegalArgumentException("Strings must not be null"); - } - - final int[] mtp = matches(first, second); - final double m = mtp[0]; - if (m == 0) { - return 0D; - } - final double j = ((m / first.length() + m / second.length() + (m - mtp[1]) / m)) / 3; - final double jw = j < 0.7D ? j : j + Math.min(DEFAULT_SCALING_FACTOR, 1D / mtp[3]) * mtp[2] * (1D - j); - return Math.round(jw * 100.0D) / 100.0D; - } - private static int[] matches(final CharSequence first, final CharSequence second) { CharSequence max, min; if (first.length() > second.length()) { http://git-wip-us.apache.org/repos/asf/commons-lang/blob/f4ee399e/src/test/java/org/apache/commons/lang3/StringUtilsTest.java ---------------------------------------------------------------------- diff --git a/src/test/java/org/apache/commons/lang3/StringUtilsTest.java b/src/test/java/org/apache/commons/lang3/StringUtilsTest.java index 8c76144..b776b3b 100644 --- a/src/test/java/org/apache/commons/lang3/StringUtilsTest.java +++ b/src/test/java/org/apache/commons/lang3/StringUtilsTest.java @@ -2507,34 +2507,6 @@ public class StringUtilsTest { } @Test - public void testGetJaroWinklerSimilarity_StringString() { - assertEquals(0.93d, StringUtils.getJaroWinklerSimilarity("frog", "fog"), 0.0d); - assertEquals(0.0d, StringUtils.getJaroWinklerSimilarity("fly", "ant"), 0.0d); - assertEquals(0.44d, StringUtils.getJaroWinklerSimilarity("elephant", "hippo"), 0.0d); - assertEquals(0.84d, StringUtils.getJaroWinklerSimilarity("dwayne", "duane"), 0.0d); - assertEquals(0.93d, StringUtils.getJaroWinklerSimilarity("ABC Corporation", "ABC Corp"), 0.0d); - assertEquals(0.95d, StringUtils.getJaroWinklerSimilarity("D N H Enterprises Inc", "D & H Enterprises, Inc."), 0.0d); - assertEquals(0.92d, StringUtils.getJaroWinklerSimilarity("My Gym Children's Fitness Center", "My Gym. Childrens Fitness"), 0.0d); - assertEquals(0.88d, StringUtils.getJaroWinklerSimilarity("PENNSYLVANIA", "PENNCISYLVNIA"), 0.0d); - assertEquals(0.63d, StringUtils.getJaroWinklerSimilarity("Haus Ingeborg", "Ingeborg Esser"), 0.0d); - } - - @Test(expected = IllegalArgumentException.class) - public void testGetJaroWinklerSimilarity_NullNull() throws Exception { - StringUtils.getJaroWinklerSimilarity(null, null); - } - - @Test(expected = IllegalArgumentException.class) - public void testGetJaroWinklerSimilarity_StringNull() throws Exception { - StringUtils.getJaroWinklerSimilarity(" ", null); - } - - @Test(expected = IllegalArgumentException.class) - public void testGetJaroWinklerSimilarity_NullString() throws Exception { - StringUtils.getJaroWinklerSimilarity(null, "clear"); - } - - @Test public void testGetFuzzyDistance() throws Exception { assertEquals(0, StringUtils.getFuzzyDistance("", "", Locale.ENGLISH)); assertEquals(0, StringUtils.getFuzzyDistance("Workshop", "b", Locale.ENGLISH));