SegmentInfos header check requires 'segments' codec to be version 10 (Lucene v8.6.0) or older

Author: rahulgoswami

lucene/backward-codecs/src/test/org/apache/lucene/backward_index/TestAncientIndicesCompatibility.java

@@ -45,6 +45,7 @@
 import org.apache.lucene.tests.util.LuceneTestCase;
 import org.apache.lucene.tests.util.TestUtil;
 import org.apache.lucene.util.IOUtils;
+import org.apache.lucene.util.Version;
 
 public class TestAncientIndicesCompatibility extends LuceneTestCase {
   static final Set<String> UNSUPPORTED_INDEXES;
@@ -199,7 +200,7 @@ public void testUnsupportedOldIndexes() throws Exception {
       checker.setInfoStream(new PrintStream(bos, false, UTF_8));
       checker.setLevel(CheckIndex.Level.MIN_LEVEL_FOR_INTEGRITY_CHECKS);
       CheckIndex.Status indexStatus = checker.checkIndex();
-      if (version.startsWith("8.") || version.startsWith("9.")) {
+      if (getVersion(version).onOrAfter(Version.fromBits(8, 6, 0))) {
         assertTrue(indexStatus.clean);
       } else {
         assertFalse(indexStatus.clean);
@@ -217,6 +218,18 @@ public void testUnsupportedOldIndexes() throws Exception {
     }
   }
 
+  private Version getVersion(String version) {
+    if (version.startsWith("5x")) {
+      // couple of indices in unsupported_indices.txt start with "5x'
+      return Version.fromBits(5, 0, 0);
+    }
+    String[] versionBitsStr = version.split("[.\\-]");
+    return Version.fromBits(
+        Integer.parseInt(versionBitsStr[0]),
+        Integer.parseInt(versionBitsStr[1]),
+        Integer.parseInt(versionBitsStr[2]));
+  }
+
   // #12895: test on a carefully crafted 9.8.0 index (from a small contiguous subset
   // of wikibigall unique terms) that shows the read-time exception of
   // IntersectTermsEnum (used by WildcardQuery)

lucene/core/src/java/org/apache/lucene/index/SegmentInfos.java

@@ -328,7 +328,7 @@ public static final SegmentInfos readCommit(
         throw new IndexFormatTooOldException(
             input, magic, CodecUtil.CODEC_MAGIC, CodecUtil.CODEC_MAGIC);
       }
-      format = CodecUtil.checkHeaderNoMagic(input, "segments", VERSION_74, VERSION_CURRENT);
+      format = CodecUtil.checkHeaderNoMagic(input, "segments", VERSION_86, VERSION_CURRENT);
       byte[] id = new byte[StringHelper.ID_LENGTH];
       input.readBytes(id, 0, id.length);
       CodecUtil.checkIndexHeaderSuffix(input, Long.toString(generation, Character.MAX_RADIX));
@@ -394,33 +394,7 @@ private static void parseSegmentInfos(
       String segName = input.readString();
       byte[] segmentID = new byte[StringHelper.ID_LENGTH];
       input.readBytes(segmentID, 0, segmentID.length);
-      Codec codec = null;
-      try {
-        codec = readCodec(input);
-      } catch (IllegalArgumentException e) {
-        if (e.getMessage() != null && e.getMessage().contains("Could not load codec")) {
-          // maybe we tried loading an old default codec which isn't present in backward-codecs
-          // anymore.
-          // aka index is too old
-          throw new IndexFormatTooOldException(
-              input,
-              "Index has segments derived from Lucene version "
-                  + infos.indexCreatedVersionMajor
-                  + ".x and is not supported by Lucene "
-                  + Version.LATEST
-                  + ". This Lucene version only supports indexes with major version "
-                  + minSupportedMajorVersion
-                  + " or later (found: "
-                  + infos.indexCreatedVersionMajor
-                  + ", minimum supported: "
-                  + minSupportedMajorVersion
-                  + "). To resolve this issue re-index your data using Lucene "
-                  + minSupportedMajorVersion
-                  + ".x or later.");
-        } else {
-          throw e;
-        }
-      }
+      Codec codec = readCodec(input);
       SegmentInfo info =
           codec.segmentInfoFormat().read(directory, segName, segmentID, IOContext.READONCE);
       info.setCodec(codec);