(hudi) branch master updated: [HUDI-8125] Update handling of non-string inputs for string fields in MercifulJsonConverter (#11825)

[yihua]

This is an automated email from the ASF dual-hosted git repository.

yihua pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git


The following commit(s) were added to refs/heads/master by this push:
     new f64ff333369 [HUDI-8125] Update handling of non-string inputs for 
string fields in MercifulJsonConverter (#11825)
f64ff333369 is described below

commit f64ff333369bb7de3a78afd28263f162262773c8
Author: Tim Brown <t...@onehouse.ai>
AuthorDate: Wed Sep 4 00:24:56 2024 -0500

    [HUDI-8125] Update handling of non-string inputs for string fields in 
MercifulJsonConverter (#11825)
---
 .../apache/hudi/avro/MercifulJsonConverter.java    | 24 ++++++++++++++++------
 .../hudi/avro/TestMercifulJsonConverter.java       | 19 +++++++++++++++++
 2 files changed, 37 insertions(+), 6 deletions(-)

diff --git 
a/hudi-common/src/main/java/org/apache/hudi/avro/MercifulJsonConverter.java 
b/hudi-common/src/main/java/org/apache/hudi/avro/MercifulJsonConverter.java
index 5219a389662..a6eabc547f4 100644
--- a/hudi-common/src/main/java/org/apache/hudi/avro/MercifulJsonConverter.java
+++ b/hudi-common/src/main/java/org/apache/hudi/avro/MercifulJsonConverter.java
@@ -460,13 +460,25 @@ public class MercifulJsonConverter {
     };
   }
 
-  protected JsonFieldProcessor generateStringTypeHandler() {
-    return new JsonFieldProcessor() {
-      @Override
-      public Pair<Boolean, Object> convert(Object value, String name, Schema 
schema) {
-        return Pair.of(true, value.toString());
+  private static JsonFieldProcessor generateStringTypeHandler() {
+    return new StringProcessor();
+  }
+
+  private static class StringProcessor extends JsonFieldProcessor {
+    private static final ObjectMapper STRING_MAPPER = new ObjectMapper();
+
+    @Override
+    public Pair<Boolean, Object> convert(Object value, String name, Schema 
schema) {
+      if (value instanceof String) {
+        return Pair.of(true, value);
+      } else {
+        try {
+          return Pair.of(true, STRING_MAPPER.writeValueAsString(value));
+        } catch (IOException ex) {
+          return Pair.of(false, null);
+        }
       }
-    };
+    }
   }
 
   protected JsonFieldProcessor generateBytesTypeHandler() {
diff --git 
a/hudi-common/src/test/java/org/apache/hudi/avro/TestMercifulJsonConverter.java 
b/hudi-common/src/test/java/org/apache/hudi/avro/TestMercifulJsonConverter.java
index 0c9be20570b..74a611ab245 100644
--- 
a/hudi-common/src/test/java/org/apache/hudi/avro/TestMercifulJsonConverter.java
+++ 
b/hudi-common/src/test/java/org/apache/hudi/avro/TestMercifulJsonConverter.java
@@ -32,6 +32,7 @@ import org.junit.jupiter.api.Test;
 import org.junit.jupiter.params.ParameterizedTest;
 import org.junit.jupiter.params.provider.Arguments;
 import org.junit.jupiter.params.provider.MethodSource;
+import org.junit.jupiter.params.provider.ValueSource;
 
 import java.io.IOException;
 import java.math.BigDecimal;
@@ -71,6 +72,24 @@ public class TestMercifulJsonConverter {
     Assertions.assertEquals(rec, CONVERTER.convert(json, simpleSchema));
   }
 
+  @ParameterizedTest
+  @ValueSource(strings = {
+      "{\"first\":\"John\",\"last\":\"Smith\"}",
+      "[{\"first\":\"John\",\"last\":\"Smith\"}]",
+      "{\"first\":\"John\",\"last\":\"Smith\",\"suffix\":3}",
+  })
+  void nestedJsonAsString(String nameInput) throws IOException {
+    Schema simpleSchema = SchemaTestUtil.getSimpleSchema();
+    String json = String.format("{\"name\": %s, \"favorite_number\": 1337, 
\"favorite_color\": 10}", nameInput);
+
+    GenericRecord rec = new GenericData.Record(simpleSchema);
+    rec.put("name", nameInput);
+    rec.put("favorite_number", 1337);
+    rec.put("favorite_color", "10");
+
+    Assertions.assertEquals(rec, CONVERTER.convert(json, simpleSchema));
+  }
+
   private static final String DECIMAL_AVRO_FILE_INVALID_PATH = 
"/decimal-logical-type-invalid.avsc";
   private static final String DECIMAL_AVRO_FILE_PATH = 
"/decimal-logical-type.avsc";
   private static final String DECIMAL_FIXED_AVRO_FILE_PATH = 
"/decimal-logical-type-fixed-type.avsc";