Make type of logged values consistent for each logkey (delta-io#3883)

<!--
Thanks for sending a pull request!  Here are some tips for you:
1. If this is your first time, please read our contributor guidelines:
https://github.com/delta-io/delta/blob/master/CONTRIBUTING.md
2. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP]
Your PR title ...'.
  3. Be sure to keep the PR description updated to reflect all changes.
  4. Please write your PR title to summarize what this PR proposes.
5. If possible, provide a concise example to reproduce the issue for a
faster review.
6. If applicable, include the corresponding issue number in the PR title
and link it in the body.
-->

#### Which Delta project/connector is this regarding?
<!--
Please add the component selected below to the beginning of the pull
request title
For example: [Spark] Title of my pull request
-->

- [x] Spark
- [ ] Standalone
- [ ] Flink
- [ ] Kernel
- [ ] Other (fill in here)

## Description

Ensures that the types of logged values for each logkey are consistent.

## How was this patch tested?

Code compiles and existing tests pass.

## Does this PR introduce _any_ user-facing changes?

No

Signed-off-by: Michael Zhang <[email protected]>

Author: michaelzhan-db

spark/src/main/scala/org/apache/spark/sql/delta/MetadataCleanup.scala

@@ -128,8 +128,8 @@ trait MetadataCleanup extends DeltaLogging {
           sidecarDeletionMetrics)
         logInfo(log"Sidecar deletion metrics: ${MDC(DeltaLogKeys.METRICS, sidecarDeletionMetrics)}")
       }
-      logInfo(log"Deleted ${MDC(DeltaLogKeys.NUM_FILES, numDeleted)} log files and " +
-        log"${MDC(DeltaLogKeys.NUM_FILES2, numDeletedUnbackfilled)} unbackfilled commit " +
+      logInfo(log"Deleted ${MDC(DeltaLogKeys.NUM_FILES, numDeleted.toLong)} log files and " +
+        log"${MDC(DeltaLogKeys.NUM_FILES2, numDeletedUnbackfilled.toLong)} unbackfilled commit " +
         log"files older than ${MDC(DeltaLogKeys.DATE, formattedDate)}")
     }
   }

spark/src/main/scala/org/apache/spark/sql/delta/OptimisticTransaction.scala

@@ -1881,7 +1881,7 @@ trait OptimisticTransactionImpl extends TransactionalWrite
 
     logInfo(log"Committed delta #${MDC(DeltaLogKeys.VERSION, attemptVersion)} to " +
       log"${MDC(DeltaLogKeys.PATH, deltaLog.logPath)}. Wrote " +
-      log"${MDC(DeltaLogKeys.NUM_ACTIONS, commitSize)} actions.")
+      log"${MDC(DeltaLogKeys.NUM_ACTIONS, commitSize.toLong)} actions.")
 
     deltaLog.checkpoint(currentSnapshot)
     currentSnapshot
@@ -2044,7 +2044,7 @@ trait OptimisticTransactionImpl extends TransactionalWrite
              |Detected mismatch in partition values between AddFile and table metadata but
              |commit validation was turned off.
              |To turn it back on set
-             |${MDC(DeltaLogKeys.CONFIG_KEY, DeltaSQLConf.DELTA_COMMIT_VALIDATION_ENABLED)}
+             |${MDC(DeltaLogKeys.CONFIG_KEY, DeltaSQLConf.DELTA_COMMIT_VALIDATION_ENABLED.key)}
              |to "true"
           """.stripMargin)
         a
@@ -2284,7 +2284,7 @@ trait OptimisticTransactionImpl extends TransactionalWrite
     val actions = currentTransactionInfo.finalActionsToCommit
     logInfo(
       log"Attempting to commit version ${MDC(DeltaLogKeys.VERSION, attemptVersion)} with " +
-      log"${MDC(DeltaLogKeys.NUM_ACTIONS, actions.size)} actions with " +
+      log"${MDC(DeltaLogKeys.NUM_ACTIONS, actions.size.toLong)} actions with " +
       log"${MDC(DeltaLogKeys.ISOLATION_LEVEL, isolationLevel)} isolation level")
 
     if (readVersion > -1 && metadata.id != snapshot.metadata.id) {
@@ -2588,7 +2588,7 @@ trait OptimisticTransactionImpl extends TransactionalWrite
         log"${MDC(DeltaLogKeys.NUM_ACTIONS, adds)} adds, " +
         log"${MDC(DeltaLogKeys.NUM_ACTIONS2, removes)} removes, " +
         log"${MDC(DeltaLogKeys.NUM_PREDICATES, readPredicates.size)} read predicates, " +
-        log"${MDC(DeltaLogKeys.NUM_FILES, readFiles.size)} read files"
+        log"${MDC(DeltaLogKeys.NUM_FILES, readFiles.size.toLong)} read files"
       }
 
       logInfo(logPrefix +

spark/src/main/scala/org/apache/spark/sql/delta/commands/ConvertToDeltaCommand.scala

@@ -311,7 +311,8 @@ abstract class ConvertToDeltaCommandBase(
           _, txn.deltaLog.dataPath, fs, conf, Some(partitionSchema), deltaPath.isDefined))
       if (shouldCollectStats) {
         logInfo(
-          log"Collecting stats for a batch of ${MDC(DeltaLogKeys.NUM_FILES, batch.size)} files; " +
+          log"Collecting stats for a batch of " +
+          log"${MDC(DeltaLogKeys.NUM_FILES, batch.size.toLong)} files; " +
           log"finished ${MDC(DeltaLogKeys.NUM_FILES2, numFiles)} so far"
           )
         numFiles += statsBatchSize

spark/src/main/scala/org/apache/spark/sql/delta/commands/ReorgTableForUpgradeUniformHelper.scala

@@ -114,7 +114,7 @@ trait ReorgTableForUpgradeUniformHelper extends DeltaLogging {
       log"at version ${MDC(DeltaLogKeys.VERSION, snapshot.version)}, there are " +
       log"${MDC(DeltaLogKeys.NUM_FILES, numOfAddFiles)} addFiles, and " +
       log"${MDC(DeltaLogKeys.NUM_FILES2, numOfAddFilesWithTag)} addFiles with " +
-      log"ICEBERG_COMPAT_VERSION=${MDC(DeltaLogKeys.VERSION2, icebergCompatVersion)} tag.")
+      log"ICEBERG_COMPAT_VERSION=${MDC(DeltaLogKeys.VERSION2, icebergCompatVersion.toLong)} tag.")
     (numOfAddFiles, numOfAddFilesWithTag)
   }
 

spark/src/main/scala/org/apache/spark/sql/delta/commands/VacuumCommand.scala

@@ -423,10 +423,10 @@ object VacuumCommand extends VacuumCommandImpl with Serializable {
             )
 
             recordDeltaEvent(deltaLog, "delta.gc.stats", data = stats)
-            logInfo(log"Found ${MDC(DeltaLogKeys.NUM_FILES, numFiles)} files " +
+            logInfo(log"Found ${MDC(DeltaLogKeys.NUM_FILES, numFiles.toLong)} files " +
               log"(${MDC(DeltaLogKeys.NUM_BYTES, sizeOfDataToDelete)} bytes) and directories in " +
               log"a total of ${MDC(DeltaLogKeys.NUM_DIRS, dirCounts)} directories " +
-              log"that are safe to delete. Vacuum stats: ${MDC(DeltaLogKeys.STATS, stats)}")
+              log"that are safe to delete. Vacuum stats: ${MDC(DeltaLogKeys.VACUUM_STATS, stats)}")
 
             return diffFiles.map(f => urlEncodedStringToPath(f).toString).toDF("path")
           }

spark/src/main/scala/org/apache/spark/sql/delta/commands/backfill/BackfillBatch.scala

@@ -68,8 +68,8 @@ trait BackfillBatch extends DeltaLogging {
       )
     }
 
-    logInfo(log"Batch ${MDC(DeltaLogKeys.BATCH_ID, batchId)} starting, committing " +
-      log"${MDC(DeltaLogKeys.NUM_FILES, filesInBatch.size)} candidate files")
+    logInfo(log"Batch ${MDC(DeltaLogKeys.BATCH_ID, batchId.toLong)} starting, committing " +
+      log"${MDC(DeltaLogKeys.NUM_FILES, filesInBatch.size.toLong)} candidate files")
     // This step is necessary to mark all files in this batch as "read" in the
     // child transaction object `txn` and to set the read transactions ids to be the same as the
     // parent transaction object `origTxn`, for proper conflict checking.

spark/src/main/scala/org/apache/spark/sql/delta/hooks/GenerateSymlinkManifest.scala

@@ -337,7 +337,7 @@ trait GenerateSymlinkManifestImpl extends PostCommitHook with DeltaLogging with
     }
 
     logInfo(log"Deleted manifest partitions [" +
-      log"${MDC(DeltaLogKeys.NUM_FILES, partitionRelativePathsToDelete.size)}]:\n\t" +
+      log"${MDC(DeltaLogKeys.NUM_FILES, partitionRelativePathsToDelete.size.toLong)}]:\n\t" +
       log"${MDC(DeltaLogKeys.PATHS, partitionRelativePathsToDelete.mkString("\n\t"))}")
   }
 

spark/src/main/scala/org/apache/spark/sql/delta/sources/DeltaSink.scala

@@ -93,8 +93,8 @@ case class DeltaSink(
       logInfo(
         log"Committed transaction, batchId=${MDC(DeltaLogKeys.BATCH_ID, batchId)}, " +
         log"duration=${MDC(DeltaLogKeys.DURATION, durationMs)} ms, " +
-        log"added ${MDC(DeltaLogKeys.NUM_FILES, newFiles.size)} files, " +
-        log"removed ${MDC(DeltaLogKeys.NUM_FILES2, deletedFiles.size)} files.")
+        log"added ${MDC(DeltaLogKeys.NUM_FILES, newFiles.size.toLong)} files, " +
+        log"removed ${MDC(DeltaLogKeys.NUM_FILES2, deletedFiles.size.toLong)} files.")
       val executionId = sc.getLocalProperty(SQLExecution.EXECUTION_ID_KEY)
       SQLMetrics.postDriverMetricUpdates(sc, executionId, metrics.values.toSeq)
     }
@@ -153,8 +153,8 @@ case class DeltaSink(
     val totalSize = newFiles.map(_.getFileSize).sum
     val totalLogicalRecords = newFiles.map(_.numLogicalRecords.getOrElse(0L)).sum
     logInfo(
-      log"Wrote ${MDC(DeltaLogKeys.NUM_FILES, newFiles.size)} files, with total size " +
-      log"${MDC(DeltaLogKeys.NUM_BYTES, totalSize)}, " +
+      log"Wrote ${MDC(DeltaLogKeys.NUM_FILES, newFiles.size.toLong)} files, " +
+        log"with total size ${MDC(DeltaLogKeys.NUM_BYTES, totalSize)}, " +
       log"${MDC(DeltaLogKeys.NUM_RECORDS, totalLogicalRecords)} logical records, " +
       log"duration=${MDC(DeltaLogKeys.DURATION, writeFilesTimeMs)} ms.")
 

spark/src/main/scala/org/apache/spark/sql/delta/util/DeltaFileOperations.scala

@@ -128,7 +128,7 @@ object DeltaFileOperations extends DeltaLogging {
       base: Int = 100,
       jitter: Int = 1000): Unit = {
     val sleepTime = Random.nextInt(jitter) + base
-    logWarning(log"Sleeping for ${MDC(DeltaLogKeys.TIME_MS, sleepTime)} ms to rate limit " +
+    logWarning(log"Sleeping for ${MDC(DeltaLogKeys.TIME_MS, sleepTime.toLong)} ms to rate limit " +
       log"${MDC(DeltaLogKeys.OP_NAME, opName)}", t)
     Thread.sleep(sleepTime)
   }