Use new parseHiveDate for OpenX reader to remove any characters after yyyy-mm-dd

Author: ljw9111

lib/trino-hive-formats/src/main/java/io/trino/hive/formats/HiveFormatUtils.java

@@ -71,7 +71,7 @@ public final class HiveFormatUtils
     private static final char TIMESTAMP_FORMATS_SEPARATOR = ',';
     private static final char TIMESTAMP_FORMATS_ESCAPE = '\\';
 
-    private static final DateTimeFormatter DATE_PARSER = new DateTimeFormatterBuilder()
+    public static final DateTimeFormatter DATE_PARSER = new DateTimeFormatterBuilder()
             .parseLenient()
             .appendValue(YEAR, 1, 10, SignStyle.NORMAL)
             .appendLiteral('-')

lib/trino-hive-formats/src/main/java/io/trino/hive/formats/line/openxjson/OpenXJsonDeserializer.java

@@ -43,6 +43,7 @@
 import java.io.IOException;
 import java.math.BigDecimal;
 import java.math.RoundingMode;
+import java.time.LocalDate;
 import java.time.ZoneOffset;
 import java.time.ZonedDateTime;
 import java.time.format.DateTimeFormatter;
@@ -62,7 +63,7 @@
 
 import static com.google.common.base.Preconditions.checkArgument;
 import static com.google.common.collect.ImmutableList.toImmutableList;
-import static io.trino.hive.formats.HiveFormatUtils.parseHiveDate;
+import static io.trino.hive.formats.HiveFormatUtils.DATE_PARSER;
 import static io.trino.hive.formats.HiveFormatUtils.parseHiveTimestamp;
 import static io.trino.hive.formats.HiveFormatUtils.scaleDecimal;
 import static io.trino.hive.formats.line.openxjson.JsonWriter.canonicalizeJsonString;
@@ -899,6 +900,32 @@ public static long parseDecimalHexOctalLong(String stringValue)
         return Long.parseLong(stringValue);
     }
 
+    /*
+    * The parseHiveDate method in HiveFormatUtils.java that the native OpenX reader was using only supported
+    * a space delimiter to remove any characters after 'yyyy-mm-dd'. As a result, while '2025-01-04 00:00:00.000Z'
+    * was correctly parsed as '2025-01-04', strings like '2025-01-04T00:00:00.000Z' or '2025-01-04AA00:00:00.000Z'
+    * were throwing exceptions and being parsed as null.
+    * This new parseHiveDate method removes any characters after 'yyyy-mm-dd', regardless of the delimiter.
+    */
+    private static LocalDate parseHiveDate(String value)
+    {
+        value = value.trim();
+        int length = value.length();
+        int endIndex = length;
+
+        // Find the first character that isn't a digit or hyphen
+        for (int i = 0; i < length; i++) {
+            char c = value.charAt(i);
+            if (c != '-' && (c < '0' || c > '9')) {
+                endIndex = i;
+                break;
+            }
+        }
+
+        String datePortion = value.substring(0, endIndex);
+        return LocalDate.parse(datePortion, DATE_PARSER);
+    }
+
     private static boolean isHex(String s)
     {
         // This does not allow for `0x-123`

lib/trino-hive-formats/src/test/java/io/trino/hive/formats/line/openxjson/TestOpenxJsonFormat.java

@@ -885,7 +885,11 @@ public void testDate()
         assertDate("\"1969-12-31\"", -1);
 
         // Hive ignores everything after the first space
-        assertDate("\"1986-01-01 anything is allowed here\"", LocalDate.of(1986, 1, 1).toEpochDay());
+        long day = LocalDate.of(1986, 1, 1).toEpochDay();
+        SqlDate sqlDate = new SqlDate((int) day);
+        assertDate("\"1986-01-01 anything is allowed here\"", day);
+        assertValueTrinoOnly(DATE, "\"1986-01-01T00:00:00.000Z\"", sqlDate);
+        assertValueTrinoOnly(DATE, "\"1986-01-01AA00:00:00.000Z\"", sqlDate);
 
         assertDate("\"1986-01-01\"", LocalDate.of(1986, 1, 1).toEpochDay());
         assertDate("\"1986-01-33\"", LocalDate.of(1986, 2, 2).toEpochDay());