nice overloads in Deletes

apache · Dec 10, 2024 · 1c03a14 · 1c03a14
1 parent 52dc58b
commit 1c03a14
Show file tree

Hide file tree

Showing 2 changed files with 42 additions and 3 deletions.
diff --git a/core/src/main/java/org/apache/iceberg/deletes/Deletes.java b/core/src/main/java/org/apache/iceberg/deletes/Deletes.java
@@ -36,6 +36,7 @@
 import org.apache.iceberg.relocated.com.google.common.collect.Lists;
 import org.apache.iceberg.types.Comparators;
 import org.apache.iceberg.types.Types;
+import org.apache.iceberg.util.CharSequenceMap;
 import org.apache.iceberg.util.Filter;
 import org.apache.iceberg.util.ParallelIterable;
 import org.apache.iceberg.util.PathMap;
@@ -124,11 +125,49 @@ public static StructLikeSet toEqualitySet(
     }
   }
 
-  public static <T extends StructLike> PathMap<PositionDeleteIndex> toPositionIndexes(
+  /**
+   * Builds a map of position delete indexes by path.
+   *
+   * @deprecated since 1.8.0, will be removed in 1.9.0. Use {@link #toPathPositionIndexes}.
+   */
+  @Deprecated
+  public static <T extends StructLike> CharSequenceMap<PositionDeleteIndex> toPositionIndexes(
       CloseableIterable<T> posDeletes) {
     return toPositionIndexes(posDeletes, null /* unknown delete file */);
   }
 
+  /**
+   * Builds a map of position delete indexes by path.
+   *
+   * <p>Unlike {@link #toPositionIndex(CharSequence, List)}, this method builds a position delete
+   * index for each referenced data file and does not filter deletes. This can be useful when the
+   * entire delete file content is needed (e.g. caching).
+   *
+   * @param posDeletes position deletes
+   * @param file the source delete file for the deletes
+   * @return the map of position delete indexes by path
+   * @deprecated since 1.8.0, will be removed in 1.9.0. Use {@link #toPathPositionIndexes}.
+   */
+  @Deprecated
+  public static <T extends StructLike> CharSequenceMap<PositionDeleteIndex> toPositionIndexes(
+      CloseableIterable<T> posDeletes, DeleteFile file) {
+    CharSequenceMap<PositionDeleteIndex> indexes = CharSequenceMap.create();
+
+    try (CloseableIterable<T> deletes = posDeletes) {
+      for (T delete : deletes) {
+        CharSequence filePath = (CharSequence) FILENAME_ACCESSOR.get(delete);
+        long position = (long) POSITION_ACCESSOR.get(delete);
+        PositionDeleteIndex index =
+            indexes.computeIfAbsent(filePath, () -> new BitmapPositionDeleteIndex(file));
+        index.delete(position);
+      }
+    } catch (IOException e) {
+      throw new UncheckedIOException("Failed to close position delete source", e);
+    }
+
+    return indexes;
+  }
+
   /**
    * Builds a map of position delete indexes by path.
    *
@@ -140,7 +179,7 @@ public static <T extends StructLike> PathMap<PositionDeleteIndex> toPositionInde
    * @param file the source delete file for the deletes
    * @return the map of position delete indexes by path
    */
-  public static <T extends StructLike> PathMap<PositionDeleteIndex> toPositionIndexes(
+  public static <T extends StructLike> PathMap<PositionDeleteIndex> toPathPositionIndexes(
       CloseableIterable<T> posDeletes, DeleteFile file) {
     PathMap<PositionDeleteIndex> indexes = PathMap.create();
 

diff --git a/data/src/main/java/org/apache/iceberg/data/BaseDeleteLoader.java b/data/src/main/java/org/apache/iceberg/data/BaseDeleteLoader.java
@@ -210,7 +210,7 @@ private PositionDeleteIndex getOrReadPosDeletes(DeleteFile deleteFile, CharSeque
 
   private PathMap<PositionDeleteIndex> readPosDeletes(DeleteFile deleteFile) {
     CloseableIterable<Record> deletes = openDeletes(deleteFile, POS_DELETE_SCHEMA);
-    return Deletes.toPositionIndexes(deletes, deleteFile);
+    return Deletes.toPathPositionIndexes(deletes, deleteFile);
   }
 
   private PositionDeleteIndex readPosDeletes(DeleteFile deleteFile, CharSequence filePath) {