karuppayya commented on code in PR #4652:
URL: https://github.com/apache/iceberg/pull/4652#discussion_r927881682


##########
spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/actions/DeleteOrphanFilesSparkAction.java:
##########
@@ -213,14 +239,8 @@ private DeleteOrphanFiles.Result doExecute() {
     Dataset<Row> validFileDF = validContentFileDF.union(validMetadataFileDF);
     Dataset<Row> actualFileDF = compareToFileList == null ? 
buildActualFileDF() : filteredCompareToFileList();
 
-    Column actualFileName = filenameUDF.apply(actualFileDF.col(FILE_PATH));
-    Column validFileName = filenameUDF.apply(validFileDF.col(FILE_PATH));
-    Column nameEqual = actualFileName.equalTo(validFileName);
-    Column actualContains = 
actualFileDF.col(FILE_PATH).contains(validFileDF.col(FILE_PATH));
-    Column joinCond = nameEqual.and(actualContains);
-    List<String> orphanFiles = actualFileDF.join(validFileDF, joinCond, 
"leftanti")
-        .as(Encoders.STRING())
-        .collectAsList();
+    List<String> orphanFiles = findOrphanFiles(spark(), actualFileDF, 
validFileDF,
+            equalSchemes, equalAuthorities, prefixMismatchMode);

Review Comment:
   Fixed the indentation



##########
spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/actions/DeleteOrphanFilesSparkAction.java:
##########
@@ -326,6 +346,96 @@ private static FlatMapFunction<Iterator<String>, String> 
listDirsRecursively(
     };
   }
 
+  @VisibleForTesting
+  static List<String> findOrphanFiles(
+          SparkSession spark, Dataset<Row> actualFileDF, Dataset<Row> 
validFileDF,
+          Map<String, String> equalSchemes, Map<String, String> 
equalAuthorities,
+          PrefixMismatchMode prefixMismatchMode) {
+    Dataset<FileMetadata> actualFileMetadataDS = actualFileDF.mapPartitions(
+        toFileMetadata(equalSchemes, equalAuthorities),
+        Encoders.bean(FileMetadata.class));
+    Dataset<FileMetadata> validFileMetadataDS = validFileDF.mapPartitions(
+        toFileMetadata(equalSchemes, equalAuthorities),
+        Encoders.bean(FileMetadata.class));
+
+    SetAccumulator<Pair<String, String>> conflicts = new SetAccumulator<>();
+    spark.sparkContext().register(conflicts);
+
+    Column joinCond = 
actualFileMetadataDS.col("path").equalTo(validFileMetadataDS.col("path"));
+
+    List<String> orphanFiles = 
actualFileMetadataDS.joinWith(validFileMetadataDS,
+            joinCond, "leftouter")
+        .mapPartitions(findOrphanFiles(prefixMismatchMode, conflicts), 
Encoders.STRING())
+        .collectAsList();
+
+    if (prefixMismatchMode == PrefixMismatchMode.ERROR && 
!conflicts.value().isEmpty()) {
+      throw new ValidationException("Unable to determine whether certain files 
are orphan. " +
+              "Metadata references files that match listed/provided files 
except for authority/scheme. " +

Review Comment:
   fixed



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to