ASCII digits only for versions

maven-resolver-util/src/main/java/org/eclipse/aether/util/version/GenericVersion.java

@@ -235,8 +235,8 @@ public boolean next() {
                     index++;
                     break;
                 } else {
-                    int digit = Character.digit(c, 10);
-                    if (digit >= 0) {
+                    if (c >= '0' && c <= '9') { // only ASCII digits
+                        int digit = c - '0';
                         if (state == -1) {
                             end = index;
                             terminatedByNumber = true;

maven-resolver-util/src/main/java/org/eclipse/aether/util/version/package-info.java

@@ -18,7 +18,7 @@
  * under the License.
  */
 /**
- * Ready-to-use version scheme for parsing/comparing versions and utility classes.
+ * Version scheme for parsing/comparing versions and utility classes.
  * <p>
  * Contains the "generic" scheme {@link org.eclipse.aether.util.version.GenericVersionScheme}
  * that serves the purpose of "factory" (and/or parser) for all corresponding elements (all those are package private).
@@ -28,12 +28,13 @@
  * <p>
  * Below is the <em>Generic Version Spec</em> described:
  * <p>
- * Version string is parsed into version according to these rules below:
+ * Version string is parsed into version according to these rules:
  * <ul>
  *     <li>The version string is parsed into segments, from left to right.</li>
- *     <li>Segments are explicitly delimited by single {@code "." (dot)}, {@code "-" (hyphen)} or {@code "_" (underscore)} character.</li>
- *     <li>Segments are implicitly delimited by transition between digits and non-digits.</li>
- *     <li>Segments are classified as numeric, string, qualifiers (special case of string) and min/max.</li>
+ *     <li>Segments are explicitly delimited by a single {@code "." (dot)}, {@code "-" (hyphen)}, or {@code "_" (underscore)} character.</li>
+ *     <li>Segments are implicitly delimited by a transition between ASCII digits and non-digits.</li>
+ *     <li>Segments are classified as numeric, string, qualifiers (special case of string), and min/max.</li>
+ *     <li>Numeric segments are composed of the ASCII digits 0-9. Non-ASCII digits are treated as letters.
  *     <li>Numeric segments are sorted numerically, ascending.</li>
  *     <li>Non-numeric segments may be qualifiers (predefined) or strings (non-empty letter sequence). All of them are interpreted as being case-insensitive in terms of the ROOT locale.</li>
  *     <li>Qualifier segments (strings listed below) and their sort order (ascending) are:
@@ -48,7 +49,7 @@
  *         </ul>
  *     </li>
  *     <li>String segments are sorted lexicographically and case-insensitively per ROOT locale, ascending.</li>
- *     <li>There are two special segments, {@code "min"} and {@code "max"}, they represent absolute minimum and absolute maximum in comparisons. They can be used only as trailing segment.</li>
+ *     <li>There are two special segments, {@code "min"} and {@code "max"} that represent absolute minimum and absolute maximum in comparisons. They can be used only as the trailing segment.</li>
  *     <li>As last step, trailing "zero segments" are trimmed. Similarly, "zero segments" positioned before numeric and non-numeric transitions (either explicitly or implicitly delimited) are trimmed.</li>
  *     <li>When trimming, "zero segments" are qualifiers {@code "ga"}, {@code "final"}, {@code "release"} only if being last (right-most) segment, empty string and "0" always.</li>
  *     <li>In comparison of same kind segments, the given type of segment determines comparison rules.</li>
@@ -57,11 +58,11 @@
  *     <li>It is common that a version identifier starts with numeric segment (consider this "best practice").</li>
  * </ul>
  * <p>
- * Note: this version spec does not document (nor cover) many corner cases, that we believe are "atypical" or not
+ * Note: this version spec does not document (or cover) many corner cases that we believe are "atypical" or not
  * used commonly. None of these are enforced, but in future implementations they probably will be. Some known examples are:
  * <ul>
- *     <li>Using "min" or "max" special segments as non-trailing segment. This yields in "undefined" behaviour and should be avoided.</li>
- *     <li>Having non-number as first segment of version. Versions are expected (but not enforced) to start with numbers.</li>
+ *     <li>Using "min" or "max" special segments as a non-trailing segment. This yields in "undefined" behaviour and should be avoided.</li>
+ *     <li>Having a non-number as the first segment of a version. Versions are expected (but not enforced) to start with numbers.</li>
  * </ul>
  *
  */

maven-resolver-util/src/test/java/org/eclipse/aether/util/version/GenericVersionTest.java

@@ -282,7 +282,7 @@ void testUnlimitedNumberOfDigitsInNumericComponent() {
     }
 
     @Test
-    void testTransitionFromDigitToLetterAndViceVersaIsEqualivantToDelimiter() {
+    void testTransitionFromDigitToLetterAndViceVersaIsEquivalentToDelimiter() {
         assertOrder(X_EQ_Y, "1alpha10", "1.alpha.10");
         assertOrder(X_EQ_Y, "1alpha10", "1-alpha-10");
 
@@ -495,8 +495,32 @@ void testMaximumSegment() {
         assertOrder(X_LT_Y, "1.max", "2.min");
     }
 
+    @Test
+    void testCompareLettersToNumbers() {
+        assertOrder(X_GT_Y, "1.7", "J");
+    }
+
+    @Test
+    void testCompareDigitToLetter() {
+        assertOrder(X_GT_Y, "7", "J");
+        assertOrder(X_GT_Y, "7", "c");
+    }
+
+    @Test
+    void testNonAsciiDigits() { // These should not be treated as digits.
+        String arabicEight = "\u0668";
+        assertOrder(X_GT_Y, "1", arabicEight);
+        assertOrder(X_GT_Y, "9", arabicEight);
+    }
+
+    @Test
+    void testLexicographicOrder() {
+        assertOrder(X_GT_Y, "zebra", "aardvark");
+        assertOrder(X_GT_Y, "ζέβρα", "zebra");
+    }
+
     /**
-     * UT for <a href="https://issues.apache.org/jira/browse/MRESOLVER-314">MRESOLVER-314</a>.
+     * Test for <a href="https://issues.apache.org/jira/browse/MRESOLVER-314">MRESOLVER-314</a>.
      *
      * Generates random UUID string based versions and tries to sort them. While this test is not as reliable
      * as {@link #testCompareUuidVersionStringStream()}, it covers broader range and in case it fails it records