[Java] Add recoverWithNull to JSONOptions and pass to Table.readJSON

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

@@ -1,6 +1,6 @@
 /*
  *
- *  Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ *  Copyright (c) 2019-2023, NVIDIA CORPORATION.
  *
  *  Licensed under the Apache License, Version 2.0 (the "License");
  *  you may not use this file except in compliance with the License.
@@ -29,11 +29,13 @@ public final class JSONOptions extends ColumnFilterOptions {
 
   private final boolean dayFirst;
   private final boolean lines;
+  private final boolean recoverWithNull;
 
   private JSONOptions(Builder builder) {
     super(builder);
     dayFirst = builder.dayFirst;
     lines = builder.lines;
+    recoverWithNull = builder.recoverWithNull;
   }
 
   public boolean isDayFirst() {
@@ -44,6 +46,11 @@ public boolean isLines() {
     return lines;
   }
 
+  /** Return the value of the recoverWithNull option */
+  public boolean isRecoverWithNull() {
+    return recoverWithNull;
+  }
+
   @Override
   String[] getIncludeColumnNames() {
     throw new UnsupportedOperationException("JSON reader didn't support column prune");
@@ -57,6 +64,8 @@ public static final class Builder  extends ColumnFilterOptions.Builder<JSONOptio
     private boolean dayFirst = false;
     private boolean lines = true;
 
+    private boolean recoverWithNull = false;
+
     /**
      * Whether to parse dates as DD/MM versus MM/DD
      * @param dayFirst true: DD/MM, false, MM/DD
@@ -78,6 +87,20 @@ public Builder withLines(boolean perLine) {
       return this;
     }
 
+    /**
+     * Specify how to handle invalid lines when parsing json. Setting
+     * recoverWithNull to true will cause null values to be returned
+     * for invalid lines. Setting recoverWithNull to false will cause
+     * the parsing to fail with an exception.
+     *
+     * @param recoverWithNull true: return nulls, false: throw exception
+     * @return builder for chaining
+     */
+    public Builder withRecoverWithNull(boolean recoverWithNull) {
+      this.recoverWithNull = recoverWithNull;
+      return this;
+    }
+
     @Override
     public Builder includeColumn(String... names) {
       throw new UnsupportedOperationException("JSON reader didn't support column prune");

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

@@ -241,10 +241,11 @@ private static native long[] readCSV(String[] columnNames,
   private static native long readJSON(String[] columnNames,
                                         int[] dTypeIds, int[] dTypeScales,
                                         String filePath, long address, long length,
-                                        boolean dayFirst, boolean lines) throws CudfException;
+                                        boolean dayFirst, boolean lines,
+                                        boolean recoverWithNulls) throws CudfException;
 
   private static native long readAndInferJSON(long address, long length,
-      boolean dayFirst, boolean lines) throws CudfException;
+      boolean dayFirst, boolean lines, boolean recoverWithNulls) throws CudfException;
 
   /**
    * Read in Parquet formatted data.
@@ -1047,7 +1048,7 @@ public static Table readJSON(Schema schema, JSONOptions opts, File path) {
             readJSON(schema.getColumnNames(), schema.getTypeIds(), schema.getTypeScales(),
                     path.getAbsolutePath(),
                     0, 0,
-                    opts.isDayFirst(), opts.isLines()))) {
+                    opts.isDayFirst(), opts.isLines(), opts.isRecoverWithNull()))) {
 
       return gatherJSONColumns(schema, twm);
     }
@@ -1099,7 +1100,7 @@ public static TableWithMeta readJSON(JSONOptions opts, HostMemoryBuffer buffer,
     assert len <= buffer.length - offset;
     assert offset >= 0 && offset < buffer.length;
     return new TableWithMeta(readAndInferJSON(buffer.getAddress() + offset, len,
-        opts.isDayFirst(), opts.isLines()));
+        opts.isDayFirst(), opts.isLines(), opts.isRecoverWithNull()));
   }
 
   /**
@@ -1121,7 +1122,8 @@ public static Table readJSON(Schema schema, JSONOptions opts, HostMemoryBuffer b
     assert offset >= 0 && offset < buffer.length;
     try (TableWithMeta twm = new TableWithMeta(readJSON(schema.getColumnNames(),
             schema.getTypeIds(), schema.getTypeScales(), null,
-            buffer.getAddress() + offset, len, opts.isDayFirst(), opts.isLines()))) {
+            buffer.getAddress() + offset, len, opts.isDayFirst(), opts.isLines(),
+            opts.isRecoverWithNull()))) {
       return gatherJSONColumns(schema, twm);
     }
   }

java/src/main/native/src/TableJni.cpp

@@ -1331,7 +1331,8 @@ JNIEXPORT void JNICALL Java_ai_rapids_cudf_Table_endWriteCSVToBuffer(JNIEnv *env
 }
 
 JNIEXPORT jlong JNICALL Java_ai_rapids_cudf_Table_readAndInferJSON(
-    JNIEnv *env, jclass, jlong buffer, jlong buffer_length, jboolean day_first, jboolean lines) {
+    JNIEnv *env, jclass, jlong buffer, jlong buffer_length, jboolean day_first, jboolean lines,
+    jboolean recover_with_null) {
 
   JNI_NULL_CHECK(env, buffer, "buffer cannot be null", 0);
   if (buffer_length <= 0) {
@@ -1344,9 +1345,13 @@ JNIEXPORT jlong JNICALL Java_ai_rapids_cudf_Table_readAndInferJSON(
     auto source = cudf::io::source_info{reinterpret_cast<char *>(buffer),
                                         static_cast<std::size_t>(buffer_length)};
 
+    auto const recovery_mode = recover_with_null ?
+                                   cudf::io::json_recovery_mode_t::RECOVER_WITH_NULL :
+                                   cudf::io::json_recovery_mode_t::FAIL;
     cudf::io::json_reader_options_builder opts = cudf::io::json_reader_options::builder(source)
                                                      .dayfirst(static_cast<bool>(day_first))
-                                                     .lines(static_cast<bool>(lines));
+                                                     .lines(static_cast<bool>(lines))
+                                                     .recovery_mode(recovery_mode);
 
     auto result =
         std::make_unique<cudf::io::table_with_metadata>(cudf::io::read_json(opts.build()));
@@ -1404,7 +1409,8 @@ JNIEXPORT jlongArray JNICALL Java_ai_rapids_cudf_TableWithMeta_releaseTable(JNIE
 
 JNIEXPORT jlong JNICALL Java_ai_rapids_cudf_Table_readJSON(
     JNIEnv *env, jclass, jobjectArray col_names, jintArray j_types, jintArray j_scales,
-    jstring inputfilepath, jlong buffer, jlong buffer_length, jboolean day_first, jboolean lines) {
+    jstring inputfilepath, jlong buffer, jlong buffer_length, jboolean day_first, jboolean lines,
+    jboolean recover_with_null) {
 
   bool read_buffer = true;
   if (buffer == 0) {
@@ -1448,9 +1454,13 @@ JNIEXPORT jlong JNICALL Java_ai_rapids_cudf_Table_readJSON(
                                                       static_cast<std::size_t>(buffer_length)} :
                                 cudf::io::source_info{filename.get()};
 
+    cudf::io::json_recovery_mode_t recovery_mode =
+        recover_with_null ? cudf::io::json_recovery_mode_t::RECOVER_WITH_NULL :
+                            cudf::io::json_recovery_mode_t::FAIL;
     cudf::io::json_reader_options_builder opts = cudf::io::json_reader_options::builder(source)
                                                      .dayfirst(static_cast<bool>(day_first))
-                                                     .lines(static_cast<bool>(lines));
+                                                     .lines(static_cast<bool>(lines))
+                                                     .recovery_mode(recovery_mode);
 
     if (!n_col_names.is_null() && data_types.size() > 0) {
       if (n_col_names.size() != n_types.size()) {

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

@@ -86,6 +86,7 @@ public class TableTest extends CudfTestBase {
   private static final File TEST_ALL_TYPES_PLAIN_AVRO_FILE = TestUtils.getResourceAsFile("alltypes_plain.avro");
   private static final File TEST_SIMPLE_CSV_FILE = TestUtils.getResourceAsFile("simple.csv");
   private static final File TEST_SIMPLE_JSON_FILE = TestUtils.getResourceAsFile("people.json");
+  private static final File TEST_JSON_ERROR_FILE = TestUtils.getResourceAsFile("people_with_invalid_lines.json");
 
   private static final Schema CSV_DATA_BUFFER_SCHEMA = Schema.builder()
       .column(DType.INT32, "A")
@@ -326,6 +327,39 @@ void testReadJSONFile() {
     }
   }
 
+  @Test
+  void testReadJSONFileWithInvalidLines() {
+    Schema schema = Schema.builder()
+            .column(DType.STRING, "name")
+            .column(DType.INT32, "age")
+            .build();
+
+    // test with recoverWithNulls=true
+    {
+      JSONOptions opts = JSONOptions.builder()
+              .withLines(true)
+              .withRecoverWithNull(true)
+              .build();
+      try (Table expected = new Table.TestBuilder()
+              .column("Michael", "Andy", null, "Justin")
+              .column(null, 30, null, 19)
+              .build();
+           Table table = Table.readJSON(schema, opts, TEST_JSON_ERROR_FILE)) {
+        assertTablesAreEqual(expected, table);
+      }
+    }
+
+    // test with recoverWithNulls=false
+    {
+      JSONOptions opts = JSONOptions.builder()
+              .withLines(true)
+              .withRecoverWithNull(false)
+              .build();
+      assertThrows(CudfException.class, () ->
+        Table.readJSON(schema, opts, TEST_JSON_ERROR_FILE));
+    }
+  }
+
   @Test
   void testReadJSONFileWithDifferentColumnOrder() {
     Schema schema = Schema.builder()

java/src/test/resources/people_with_invalid_lines.json

@@ -0,0 +1,4 @@
+{"name":"Michael"}
+{"name":"Andy", "age":30}
+this_line_is_not_valid
+{"name":"Justin", "age":19}