drill-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] arina-ielchiieva commented on a change in pull request #1370: DRILL-5797: Use Parquet new reader in all non-complex column queries
Date Wed, 11 Jul 2018 12:53:26 GMT
arina-ielchiieva commented on a change in pull request #1370: DRILL-5797: Use Parquet new reader
in all non-complex column queries
URL: https://github.com/apache/drill/pull/1370#discussion_r201676485
 
 

 ##########
 File path: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/ParquetReaderUtility.java
 ##########
 @@ -140,15 +142,88 @@ public static int getIntFromLEBytes(byte[] input, int start) {
     return out;
   }
 
+  /**
+   * Map full schema paths in format `a`.`b`.`c` to respective SchemaElement objects.
+   *
+   * @param footer Parquet file metadata
+   * @return       schema full path to SchemaElement map
+   */
   public static Map<String, SchemaElement> getColNameToSchemaElementMapping(ParquetMetadata
footer) {
-    HashMap<String, SchemaElement> schemaElements = new HashMap<>();
+    Map<String, SchemaElement> schemaElements = new HashMap<>();
     FileMetaData fileMetaData = new ParquetMetadataConverter().toParquetMetadata(ParquetFileWriter.CURRENT_VERSION,
footer);
-    for (SchemaElement se : fileMetaData.getSchema()) {
-      schemaElements.put(se.getName(), se);
+
+    Iterator<SchemaElement> iter = fileMetaData.getSchema().iterator();
+
+    // First element in collection is default `root` element. We skip it to maintain key
in `a` format instead of `root`.`a`,
+    // and thus to avoid the need to cut it out again when comparing with SchemaPath string
representation
+    if (iter.hasNext()) {
+      iter.next();
+    }
+    while (iter.hasNext()) {
+      addSchemaElementMapping(iter, new StringBuilder(), schemaElements);
     }
     return schemaElements;
   }
 
+  /**
+   * Populate full path to SchemaElement map by recursively traversing schema elements referenced
by the given iterator
+   *
+   * @param iter file schema values iterator
+   * @param path parent schema element path
+   * @param schemaElements schema elements map to insert next iterator element into
+   */
+  private static void addSchemaElementMapping(Iterator<SchemaElement> iter, StringBuilder
path,
+      Map<String, SchemaElement> schemaElements) {
+    SchemaElement schemaElement = iter.next();
+    path.append('`').append(schemaElement.getName().toLowerCase()).append('`');
+    schemaElements.put(path.toString(), schemaElement);
+
+    int remainingChildren = schemaElement.getNum_children();
 
 Review comment:
   Please add comment why remaining children are important in while loop.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

Mime
View raw message