aokolnychyi commented on a change in pull request #398: Push down StringStartsWith in Spark IcebergSource URL: https://github.com/apache/incubator-iceberg/pull/398#discussion_r317269241
########## File path: api/src/main/java/org/apache/iceberg/expressions/InclusiveMetricsEvaluator.java ########## @@ -254,5 +258,43 @@ public Boolean or(Boolean leftResult, Boolean rightResult) { public <T> Boolean notIn(BoundReference<T> ref, Literal<T> lit) { return ROWS_MIGHT_MATCH; } + + @Override + public <T> Boolean startsWith(BoundReference<T> ref, Literal<T> lit) { + int id = ref.fieldId(); + + String prefix = (String) lit.value(); + ByteBuffer prefixAsBytes = ByteBuffer.wrap(prefix.getBytes(StandardCharsets.UTF_8)); + + Comparator<ByteBuffer> comparator = Comparators.unsignedBytes(); + + if (lowerBounds != null && lowerBounds.containsKey(id)) { + ByteBuffer lower = lowerBounds.get(id); + // take the same number of bytes from prefix and lower bound + int length = Math.min(prefixAsBytes.remaining(), lower.remaining()); + + int cmp = comparator.compare( + length < lower.remaining() ? BinaryUtil.truncateBinary(lower, length) : lower, Review comment: `BinaryUtil.truncateBinary` will complain if the length is lower than the number of remaining elements. I would probably change that to return the original value. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org