feat: support v3 column default values in UpdateSchema (3/4)

src/iceberg/schema_field.cc

@@ -22,18 +22,19 @@
 #include <format>
 #include <string_view>
 #include <utility>
+#include <variant>
 
 #include "iceberg/expression/literal.h"
 #include "iceberg/type.h"
+#include "iceberg/util/checked_cast.h"
 #include "iceberg/util/formatter.h"  // IWYU pragma: keep
 #include "iceberg/util/macros.h"
 
 namespace iceberg {
 
 namespace {
 
-// A null default value is modeled as the absence of a default (matching Java), so it is
-// not stored.
+// Treat null defaults as absent.
 std::shared_ptr<const Literal> DropNullDefault(std::shared_ptr<const Literal> value) {
   if (value != nullptr && value->IsNull()) {
     return nullptr;
@@ -65,6 +66,55 @@ SchemaField SchemaField::MakeRequired(int32_t field_id, std::string_view name,
   return {field_id, name, std::move(type), false, doc};
 }
 
+SchemaField SchemaField::WithName(std::string_view name) const {
+  return {field_id_, name, type_, optional_, doc_, initial_default_, write_default_};
+}
+
+SchemaField SchemaField::WithType(std::shared_ptr<Type> type) const {
+  return {field_id_,        name_,         std::move(type), optional_, doc_,
+          initial_default_, write_default_};
+}
+
+SchemaField SchemaField::WithDoc(std::string_view doc) const {
+  return {field_id_, name_, type_, optional_, doc, initial_default_, write_default_};
+}
+
+SchemaField SchemaField::WithInitialDefault(
+    std::shared_ptr<const Literal> initial_default) const {
+  return {field_id_,     name_, type_, optional_, doc_, std::move(initial_default),
+          write_default_};
+}
+
+SchemaField SchemaField::WithWriteDefault(
+    std::shared_ptr<const Literal> write_default) const {
+  return {field_id_,
+          name_,
+          type_,
+          optional_,
+          doc_,
+          initial_default_,
+          std::move(write_default)};
+}
+
+Result<Literal> SchemaField::CastDefaultValue(
+    const Literal& value, const std::shared_ptr<PrimitiveType>& target_type) {
+  if (target_type->type_id() == TypeId::kDecimal &&
+      std::holds_alternative<Decimal>(value.value())) {
+    const auto& source_type = internal::checked_cast<const DecimalType&>(*value.type());
+    const auto& decimal_type = internal::checked_cast<const DecimalType&>(*target_type);
+    if (source_type.scale() == decimal_type.scale()) {
+      const auto& decimal_value = std::get<Decimal>(value.value());
+      if (!decimal_value.FitsInPrecision(decimal_type.precision())) {
+        return InvalidArgument("Cannot cast default value to {}: {}", *target_type,
+                               value);
+      }
+      return Literal::Decimal(decimal_value.value(), decimal_type.precision(),
+                              decimal_type.scale());
+    }
+  }
+  return value.CastTo(target_type);
+}
+
 int32_t SchemaField::field_id() const { return field_id_; }
 
 std::string_view SchemaField::name() const { return name_; }
@@ -87,8 +137,7 @@ namespace {
 
 Status ValidateDefault(const SchemaField& field, const Literal& value,
                        std::string_view kind) {
-  // A null default is modeled as absence and dropped at construction, so it never reaches
-  // here; only the out-of-range cast sentinels need rejecting.
+  // Null defaults are dropped at construction.
   if (value.IsAboveMax() || value.IsBelowMin()) {
     return InvalidSchema("Invalid {} value for {}: value is out of range", kind,
                          field.name());
@@ -97,8 +146,7 @@ Status ValidateDefault(const SchemaField& field, const Literal& value,
     return InvalidSchema("Invalid {} value for {}: field has no type", kind,
                          field.name());
   }
-  // The spec requires unknown/variant/geometry/geography columns to default to null, so a
-  // non-null default on them is invalid (a null default was already dropped as absence).
+  // These types can only use null defaults.
   switch (field.type()->type_id()) {
     case TypeId::kUnknown:
     case TypeId::kVariant:
@@ -109,17 +157,13 @@ Status ValidateDefault(const SchemaField& field, const Literal& value,
     default:
       break;
   }
-  // Defaults are otherwise only supported on primitive fields. The spec also permits JSON
-  // single-value defaults for struct/list/map (e.g. an empty struct `{}` whose sub-field
-  // defaults live in field metadata); that matches the current Java model's gap and is
-  // left as a follow-up.
+  // Nested defaults are not supported yet.
   if (!field.type()->is_primitive()) {
     return InvalidSchema(
         "Invalid {} value for {}: default values are only supported for primitive types",
         kind, field.name());
   }
-  // Defaults are stored verbatim (no implicit cast), so a default whose literal type does
-  // not match the field type is invalid.
+  // Stored defaults must already match the field type.
   if (*value.type() != *field.type()) {
     return InvalidSchema("{} of field {} has type {} but expected {}", kind, field.name(),
                          *value.type(), *field.type());

src/iceberg/schema_field.h

@@ -46,10 +46,8 @@ class ICEBERG_EXPORT SchemaField : public iceberg::util::Formattable {
   /// \param[in] type The field type.
   /// \param[in] optional Whether values of this field are required or nullable.
   /// \param[in] doc Optional documentation string for the field.
-  /// \param[in] initial_default The v3 `initial-default` value, or null if absent. The
-  /// field shares ownership of the (immutable) value.
-  /// \param[in] write_default The v3 `write-default` value, or null if absent. The field
-  /// shares ownership of the (immutable) value.
+  /// \param[in] initial_default The v3 `initial-default`, or null if absent.
+  /// \param[in] write_default The v3 `write-default`, or null if absent.
   SchemaField(int32_t field_id, std::string_view name, std::shared_ptr<Type> type,
               bool optional, std::string_view doc = {},
               std::shared_ptr<const Literal> initial_default = nullptr,
@@ -62,30 +60,47 @@ class ICEBERG_EXPORT SchemaField : public iceberg::util::Formattable {
   static SchemaField MakeRequired(int32_t field_id, std::string_view name,
                                   std::shared_ptr<Type> type, std::string_view doc = {});
 
+  /// \brief Return a copy with a new name.
+  SchemaField WithName(std::string_view name) const;
+
+  /// \brief Return a copy with a new type.
+  SchemaField WithType(std::shared_ptr<Type> type) const;
+
+  /// \brief Return a copy with new documentation.
+  SchemaField WithDoc(std::string_view doc) const;
+
+  /// \brief Return a copy with a new `initial-default`.
+  SchemaField WithInitialDefault(std::shared_ptr<const Literal> initial_default) const;
+
+  /// \brief Return a copy with a new `write-default`.
+  SchemaField WithWriteDefault(std::shared_ptr<const Literal> write_default) const;
+
+  /// \brief Cast a default literal to a field type.
+  static Result<Literal> CastDefaultValue(
+      const Literal& value, const std::shared_ptr<PrimitiveType>& target_type);
+
   /// \brief Get the field ID.
-  [[nodiscard]] int32_t field_id() const;
+  int32_t field_id() const;
 
   /// \brief Get the field name.
-  [[nodiscard]] std::string_view name() const;
+  std::string_view name() const;
 
   /// \brief Get the field type.
-  [[nodiscard]] const std::shared_ptr<Type>& type() const;
+  const std::shared_ptr<Type>& type() const;
 
   /// \brief Get whether the field is optional.
   [[nodiscard]] bool optional() const;
 
   /// \brief Get the field documentation.
   std::string_view doc() const;
 
-  /// \brief Get the owning pointer to the default value for this field used when reading
-  /// rows written before the field existed (v3 `initial-default`), or null if absent.
+  /// \brief Get the v3 `initial-default`, or null if absent.
   const std::shared_ptr<const Literal>& initial_default() const;
 
-  /// \brief Get the owning pointer to the default value for this field used when a writer
-  /// does not supply a value (v3 `write-default`), or null if absent.
+  /// \brief Get the v3 `write-default`, or null if absent.
   const std::shared_ptr<const Literal>& write_default() const;
 
-  [[nodiscard]] std::string ToString() const override;
+  std::string ToString() const override;
 
   Status Validate() const;
 
@@ -107,14 +122,13 @@ class ICEBERG_EXPORT SchemaField : public iceberg::util::Formattable {
 
  private:
   /// \brief Compare two fields for equality.
-  [[nodiscard]] bool Equals(const SchemaField& other) const;
+  bool Equals(const SchemaField& other) const;
 
   int32_t field_id_;
   std::string name_;
   std::shared_ptr<Type> type_;
   bool optional_;
   std::string doc_;
-  // Immutable default values, shared (not deep-copied) across field copies, like `type_`.
   std::shared_ptr<const Literal> initial_default_;
   std::shared_ptr<const Literal> write_default_;
 };

src/iceberg/test/meson.build

@@ -59,6 +59,7 @@ iceberg_tests = {
             'table_requirements_test.cc',
             'table_test.cc',
             'table_update_test.cc',
+            'update_schema_test.cc',
         ),
     },
     'logging_test': {

src/iceberg/test/schema_field_test.cc

@@ -24,6 +24,7 @@
 
 #include <gtest/gtest.h>
 
+#include "iceberg/expression/literal.h"
 #include "iceberg/type.h"
 #include "iceberg/util/formatter.h"  // IWYU pragma: keep
 
@@ -107,4 +108,66 @@ TEST(SchemaFieldTest, WithDoc) {
   }
 }
 
+TEST(SchemaFieldTest, WithFieldMetadata) {
+  auto initial_default = std::make_shared<const Literal>(Literal::Int(1));
+  auto write_default = std::make_shared<const Literal>(Literal::Int(2));
+  SchemaField field(1, "foo", int32(), false, "doc", initial_default, write_default);
+
+  auto renamed = field.WithName("bar");
+  EXPECT_EQ(renamed.name(), "bar");
+  EXPECT_EQ(renamed.field_id(), field.field_id());
+  EXPECT_EQ(renamed.type(), field.type());
+  EXPECT_EQ(renamed.doc(), field.doc());
+  EXPECT_EQ(renamed.initial_default(), field.initial_default());
+  EXPECT_EQ(renamed.write_default(), field.write_default());
+
+  auto retyped = field.WithType(int64());
+  EXPECT_EQ(retyped.type(), int64());
+  EXPECT_EQ(retyped.name(), field.name());
+  EXPECT_EQ(retyped.initial_default(), field.initial_default());
+  EXPECT_EQ(retyped.write_default(), field.write_default());
+
+  auto documented = field.WithDoc("new doc");
+  EXPECT_EQ(documented.doc(), "new doc");
+  EXPECT_EQ(documented.name(), field.name());
+  EXPECT_EQ(documented.initial_default(), field.initial_default());
+  EXPECT_EQ(documented.write_default(), field.write_default());
+
+  auto new_initial = std::make_shared<const Literal>(Literal::Int(3));
+  auto with_initial = field.WithInitialDefault(new_initial);
+  EXPECT_EQ(with_initial.initial_default(), new_initial);
+  EXPECT_EQ(with_initial.write_default(), field.write_default());
+
+  auto new_write = std::make_shared<const Literal>(Literal::Int(4));
+  auto with_write = field.WithWriteDefault(new_write);
+  EXPECT_EQ(with_write.initial_default(), field.initial_default());
+  EXPECT_EQ(with_write.write_default(), new_write);
+  EXPECT_EQ(field.name(), "foo");
+  EXPECT_EQ(*field.write_default(), Literal::Int(2));
+}
+
+TEST(SchemaFieldTest, CastDefaultValue) {
+  {
+    auto result = SchemaField::CastDefaultValue(Literal::Int(5), int64());
+    ASSERT_TRUE(result.has_value());
+    EXPECT_EQ(result.value(), Literal::Long(5));
+  }
+  {
+    auto result =
+        SchemaField::CastDefaultValue(Literal::Decimal(1234, 9, 2), decimal(18, 2));
+    ASSERT_TRUE(result.has_value());
+    EXPECT_EQ(result.value(), Literal::Decimal(1234, 18, 2));
+  }
+  {
+    auto result =
+        SchemaField::CastDefaultValue(Literal::Decimal(1234, 9, 3), decimal(18, 2));
+    EXPECT_FALSE(result.has_value());
+  }
+  {
+    auto result =
+        SchemaField::CastDefaultValue(Literal::Decimal(1234567, 9, 2), decimal(4, 2));
+    EXPECT_FALSE(result.has_value());
+  }
+}
+
 }  // namespace iceberg