[SPARK-45225][SQL][FOLLOW-UP] XML: Fix nested XSD file path resolution

### What changes were proposed in this pull request? This PR adds support to correctly resolve the path of nested XSD provided with `rowValidationXSDPath` option and `XSDToSchema` API. ### Why are the changes needed? Nested XSD were not resolved correctly. ### Does this PR introduce _any_ user-facing change? Yes ### How was this patch tested? Added a new test ### Was this patch authored or co-authored using generative AI tooling? No Closes #46235 from sandip-db/xml_nested_xsd. Authored-by: Sandip Agarwala <[email protected]> Signed-off-by: Hyukjin Kwon <[email protected]>
apache · Apr 26, 2024 · e04ac56 · e04ac56
1 parent 3451e66
commit e04ac56
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 10 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/ValidatorUtil.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/ValidatorUtil.scala
@@ -42,7 +42,7 @@ object ValidatorUtil extends Logging {
         val in = openSchemaFile(new Path(key))
         try {
           val schemaFactory = SchemaFactory.newInstance(XMLConstants.W3C_XML_SCHEMA_NS_URI)
-          schemaFactory.newSchema(new StreamSource(in))
+          schemaFactory.newSchema(new StreamSource(in, key))
         } finally {
           in.close()
         }

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XSDToSchema.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XSDToSchema.scala
@@ -47,7 +47,7 @@ object XSDToSchema extends Logging{
   def read(xsdPath: Path): StructType = {
     val in = ValidatorUtil.openSchemaFile(xsdPath)
     val xmlSchemaCollection = new XmlSchemaCollection()
-    xmlSchemaCollection.setBaseUri(xsdPath.getParent.toString)
+    xmlSchemaCollection.setBaseUri(xsdPath.toString)
     val xmlSchema = xmlSchemaCollection.read(new InputStreamReader(in))
     getStructType(xmlSchema)
   }

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala
@@ -1206,14 +1206,16 @@ class XmlSuite
   }
 
   test("test XSD validation") {
-    val basketDF = spark.read
-      .option("rowTag", "basket")
-      .option("inferSchema", true)
-      .option("rowValidationXSDPath", getTestResourcePath(resDir + "basket.xsd")
-        .replace("file:/", "/"))
-      .xml(getTestResourcePath(resDir + "basket.xml"))
-    // Mostly checking it doesn't fail
-    assert(basketDF.selectExpr("entry[0].key").head().getLong(0) === 9027)
+    Seq("basket.xsd", "include-example/first.xsd").foreach { xsdFile =>
+      val basketDF = spark.read
+        .option("rowTag", "basket")
+        .option("inferSchema", true)
+        .option("rowValidationXSDPath", getTestResourcePath(resDir + xsdFile)
+          .replace("file:/", "/"))
+        .xml(getTestResourcePath(resDir + "basket.xml"))
+      // Mostly checking it doesn't fail
+      assert(basketDF.selectExpr("entry[0].key").head().getLong(0) === 9027)
+    }
   }
 
   test("test XSD validation with validation error") {