From e09cb7deeaa294053fd42652fada8a914afc4621 Mon Sep 17 00:00:00 2001 From: Marko Topolnik Date: Fri, 5 Jan 2024 23:03:28 +0100 Subject: Limit names to 100 bytes --- src/main/java/dev/morling/onebrc/CreateMeasurements3.java | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'src/main/java/dev/morling/onebrc') diff --git a/src/main/java/dev/morling/onebrc/CreateMeasurements3.java b/src/main/java/dev/morling/onebrc/CreateMeasurements3.java index 23b1b74..3910744 100644 --- a/src/main/java/dev/morling/onebrc/CreateMeasurements3.java +++ b/src/main/java/dev/morling/onebrc/CreateMeasurements3.java @@ -21,6 +21,7 @@ import java.io.FileReader; import java.io.FileWriter; import java.io.IOException; import java.io.StringReader; +import java.nio.charset.StandardCharsets; import java.util.ArrayList; import java.util.HashSet; import java.util.concurrent.ThreadLocalRandom; @@ -113,6 +114,9 @@ public class CreateMeasurements3 { while (names.contains(name)) { name = name.substring(1) + readNonSpace(nameSource); } + while (name.getBytes(StandardCharsets.UTF_8).length > 100) { + name = name.substring(0, name.length() - 1); + } if (name.indexOf(';') != -1) { throw new Exception("Station name contains a semicolon!"); } -- cgit v1.2.3