Add constants for UUID lengths (elastic#112353)

Our UUID strings have fixed lengths (depending on the type of UUID).
Sometimes we might want code to rely on knowing these lengths rather
than doing some other string manipulations to look for a boundary. This
commit exposes constants for these things.

Author: DaveCTurner

server/src/main/java/org/elasticsearch/common/RandomBasedUUIDGenerator.java

@@ -56,8 +56,10 @@ public static String getBase64UUID(Random random) {
         return Base64.getUrlEncoder().withoutPadding().encodeToString(getUUIDBytes(random));
     }
 
+    static final int SIZE_IN_BYTES = 16;
+
     private static byte[] getUUIDBytes(Random random) {
-        final byte[] randomBytes = new byte[16];
+        final byte[] randomBytes = new byte[SIZE_IN_BYTES];
         random.nextBytes(randomBytes);
         /* Set the version to version 4 (see http://www.ietf.org/rfc/rfc4122.txt)
          * The randomly or pseudo-randomly generated version.

server/src/main/java/org/elasticsearch/common/TimeBasedUUIDGenerator.java

@@ -47,6 +47,8 @@ protected byte[] macAddress() {
         return SECURE_MUNGED_ADDRESS;
     }
 
+    static final int SIZE_IN_BYTES = 15;
+
     @Override
     public String getBase64UUID() {
         final int sequenceId = sequenceNumber.incrementAndGet() & 0xffffff;
@@ -61,7 +63,7 @@ public String getBase64UUID() {
             sequenceId == 0 ? (lastTimestamp, currentTimeMillis) -> Math.max(lastTimestamp, currentTimeMillis) + 1 : Math::max
         );
 
-        final byte[] uuidBytes = new byte[15];
+        final byte[] uuidBytes = new byte[SIZE_IN_BYTES];
         int i = 0;
 
         // We have auto-generated ids, which are usually used for append-only workloads.

server/src/main/java/org/elasticsearch/common/UUIDs.java

@@ -17,26 +17,50 @@ public class UUIDs {
     private static final RandomBasedUUIDGenerator RANDOM_UUID_GENERATOR = new RandomBasedUUIDGenerator();
     private static final UUIDGenerator TIME_UUID_GENERATOR = new TimeBasedUUIDGenerator();
 
-    /** Generates a time-based UUID (similar to Flake IDs), which is preferred when generating an ID to be indexed into a Lucene index as
-     *  primary key.  The id is opaque and the implementation is free to change at any time! */
+    /**
+     * The length of a UUID string generated by {@link #base64UUID}.
+     */
+    // A 15-byte time-based UUID is base64-encoded as 5 3-byte chunks (each becoming 4 chars after encoding).
+    public static final int TIME_BASED_UUID_STRING_LENGTH = 20;
+
+    /**
+     * Generates a time-based UUID (similar to Flake IDs), which is preferred when generating an ID to be indexed into a Lucene index as
+     * primary key. The id is opaque and the implementation is free to change at any time!
+     * The resulting string has length {@link #TIME_BASED_UUID_STRING_LENGTH}.
+     */
     public static String base64UUID() {
         return TIME_UUID_GENERATOR.getBase64UUID();
     }
 
-    /** Returns a Base64 encoded version of a Version 4.0 compatible UUID as defined here: http://www.ietf.org/rfc/rfc4122.txt, using the
-     *  provided {@code Random} instance */
+    /**
+     * The length of a UUID string generated by {@link #randomBase64UUID} and {@link #randomBase64UUIDSecureString}.
+     */
+    // A 16-byte v4 UUID is base64-encoded as 5 3-byte chunks (each becoming 4 chars after encoding) plus another byte (becomes 2 chars).
+    public static final int RANDOM_BASED_UUID_STRING_LENGTH = 22;
+
+    /**
+     * Returns a Base64 encoded string representing a <a href="http://www.ietf.org/rfc/rfc4122.txt">RFC4122 version 4 UUID</a>, using the
+     * provided {@code Random} instance.
+     * The resulting string has length {@link #RANDOM_BASED_UUID_STRING_LENGTH}.
+     */
     public static String randomBase64UUID(Random random) {
         return RandomBasedUUIDGenerator.getBase64UUID(random);
     }
 
-    /** Returns a Base64 encoded version of a Version 4.0 compatible UUID as defined here: http://www.ietf.org/rfc/rfc4122.txt, using a
-     *  private {@code SecureRandom} instance */
+    /**
+     * Returns a Base64 encoded string representing a <a href="http://www.ietf.org/rfc/rfc4122.txt">RFC4122 version 4 UUID</a>, using a
+     * private {@code SecureRandom} instance.
+     * The resulting string has length {@link #RANDOM_BASED_UUID_STRING_LENGTH}.
+     */
     public static String randomBase64UUID() {
         return RANDOM_UUID_GENERATOR.getBase64UUID();
     }
 
-    /** Returns a Base64 encoded {@link SecureString} of a Version 4.0 compatible UUID as defined here: http://www.ietf.org/rfc/rfc4122.txt,
-     *  using a private {@code SecureRandom} instance */
+    /**
+     * Returns a Base64 encoded {@link SecureString} representing a <a href="http://www.ietf.org/rfc/rfc4122.txt">RFC4122 version 4
+     * UUID</a>, using a private {@code SecureRandom} instance.
+     * The resulting string has length {@link #RANDOM_BASED_UUID_STRING_LENGTH}.
+     */
     public static SecureString randomBase64UUIDSecureString() {
         return RandomBasedUUIDGenerator.getBase64UUIDSecureString();
     }

server/src/test/java/org/elasticsearch/common/UUIDTests.java

@@ -176,4 +176,20 @@ protected byte[] macAddress() {
         );
         return bytesPerDoc;
     }
+
+    public void testStringLength() {
+        assertEquals(UUIDs.RANDOM_BASED_UUID_STRING_LENGTH, getUnpaddedBase64StringLength(RandomBasedUUIDGenerator.SIZE_IN_BYTES));
+        assertEquals(UUIDs.RANDOM_BASED_UUID_STRING_LENGTH, UUIDs.randomBase64UUID().length());
+        assertEquals(UUIDs.RANDOM_BASED_UUID_STRING_LENGTH, UUIDs.randomBase64UUID(random()).length());
+        try (var secureString = UUIDs.randomBase64UUIDSecureString()) {
+            assertEquals(UUIDs.RANDOM_BASED_UUID_STRING_LENGTH, secureString.toString().length());
+        }
+
+        assertEquals(UUIDs.TIME_BASED_UUID_STRING_LENGTH, getUnpaddedBase64StringLength(TimeBasedUUIDGenerator.SIZE_IN_BYTES));
+        assertEquals(UUIDs.TIME_BASED_UUID_STRING_LENGTH, UUIDs.base64UUID().length());
+    }
+
+    private static int getUnpaddedBase64StringLength(int sizeInBytes) {
+        return (int) Math.ceil(sizeInBytes * 4.0 / 3.0);
+    }
 }

test/framework/src/main/java/org/elasticsearch/repositories/blobstore/RepositoryFileType.java

@@ -9,6 +9,7 @@
 package org.elasticsearch.repositories.blobstore;
 
 import org.elasticsearch.common.Strings;
+import org.elasticsearch.common.UUIDs;
 
 import java.nio.file.Path;
 import java.util.regex.Pattern;
@@ -38,9 +39,9 @@ public enum RepositoryFileType {
                     // decimal numbers
                     .replace("NUM", "(0|[1-9][0-9]*)")
                     // 15-byte UUIDS from TimeBasedUUIDGenerator
-                    .replace("SHORTUUID", "[0-9a-zA-Z_-]{20}")
+                    .replace("SHORTUUID", "[0-9a-zA-Z_-]{" + UUIDs.TIME_BASED_UUID_STRING_LENGTH + "}")
                     // 16-byte UUIDs from RandomBasedUUIDGenerator
-                    .replace("UUID", "[0-9a-zA-Z_-]{22}")
+                    .replace("UUID", "[0-9a-zA-Z_-]{" + UUIDs.RANDOM_BASED_UUID_STRING_LENGTH + "}")
                 + ")$"
         );
     }