Add JNI Support for Multi-line Delimiters and Include Test (#17139)

This PR introduces the necessary changes to the cuDF jni to support the issue described in [NVIDIA/spark-rapids#11554](NVIDIA/spark-rapids#11554). For further information, refer to the details in the [comment](NVIDIA/spark-rapids#11554 (comment)).

Issue #15961 adds support for handling multiple line delimiters. This PR extends that functionality to JNI, which was previously missing, and also includes a test to validate the changes.

Authors:
  - Suraj Aralihalli (https://github.com/SurajAralihalli)

Approvers:
  - MithunR (https://github.com/mythrocks)
  - Robert (Bobby) Evans (https://github.com/revans2)

URL: #17139

java/src/main/java/ai/rapids/cudf/RegexFlag.java

@@ -28,7 +28,16 @@ public enum RegexFlag {
   DEFAULT(0),   // default
   MULTILINE(8), // the '^' and '$' honor new-line characters
   DOTALL(16),   // the '.' matching includes new-line characters
-  ASCII(256);   // use only ASCII when matching built-in character classes
+  ASCII(256),   // use only ASCII when matching built-in character classes
+  /**
+   * EXT_NEWLINE(512): Extends line delimiters to include the following Unicode characters
+   * - NEXT_LINE ('\u0085')
+   * - LINE_SEPARATOR ('\u2028')
+   * - PARAGRAPH_SEPARATOR ('\u2029')
+   * - CARRIAGE_RETURN ('\r')
+   * - NEW_LINE ('\n')
+   */
+  EXT_NEWLINE(512);
 
   final int nativeId; // Native id, for use with libcudf.
   private RegexFlag(int nativeId) { // Only constant values should be used

java/src/test/java/ai/rapids/cudf/ColumnVectorTest.java

@@ -31,6 +31,7 @@
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Collections;
+import java.util.EnumSet;
 import java.util.List;
 import java.util.Optional;
 import java.util.concurrent.atomic.AtomicInteger;
@@ -3877,6 +3878,43 @@ void testExtractRe() {
     }
   }
 
+  @Test
+void testExtractReWithMultiLineDelimiters() {
+    String NEXT_LINE = "\u0085";
+    String LINE_SEPARATOR = "\u2028";
+    String PARAGRAPH_SEPARATOR = "\u2029";
+    String CARRIAGE_RETURN = "\r";
+    String NEW_LINE = "\n";
+
+    try (ColumnVector input = ColumnVector.fromStrings(
+            "boo:" + NEXT_LINE + "boo::" + LINE_SEPARATOR + "boo:::",
+            "boo:::" + LINE_SEPARATOR + "zzé" + CARRIAGE_RETURN + "lll",
+            "boo::",
+            "",
+            "boo::" + NEW_LINE,
+            "boo::" + CARRIAGE_RETURN,
+            "boo:" + NEXT_LINE + "boo::" + PARAGRAPH_SEPARATOR,
+            "boo:" + NEW_LINE + "boo::" + LINE_SEPARATOR,
+            "boo:" + NEXT_LINE + "boo::" + NEXT_LINE);
+         Table expected_ext_newline = new Table.TestBuilder()
+             .column("boo:::", null, "boo::", null, "boo::", "boo::", "boo::", "boo::", "boo::")
+             .build();
+         Table expected_default = new Table.TestBuilder()
+             .column("boo:::", null, "boo::", null, "boo::", null, null, null, null)
+             .build()) {
+
+        // Regex pattern to match 'boo:' followed by one or more colons at the end of the string
+        try (Table found = input.extractRe(new RegexProgram("(boo:+)$", EnumSet.of(RegexFlag.EXT_NEWLINE)))) {
+          assertColumnsAreEqual(expected_ext_newline.getColumns()[0], found.getColumns()[0]);
+        }
+
+        try (Table found = input.extractRe(new RegexProgram("(boo:+)$", EnumSet.of(RegexFlag.DEFAULT)))) {
+          assertColumnsAreEqual(expected_default.getColumns()[0], found.getColumns()[0]);
+        }
+    }
+  }
+
+
   @Test
   void testExtractAllRecord() {
     String pattern = "([ab])(\\d)";