fix comments

Author: xiao.dong

src/iceberg/expression/literal.cc

@@ -179,9 +179,7 @@ std::strong_ordering CompareFloat(T lhs, T rhs) {
   return lhs_is_negative <=> rhs_is_negative;
 }
 
-bool Literal::operator==(const iceberg::Literal& other) const {
-  return (*this <=> other) == 0;
-}
+bool Literal::operator==(const Literal& other) const { return (*this <=> other) == 0; }
 
 // Three-way comparison operator
 std::partial_ordering Literal::operator<=>(const Literal& other) const {

src/iceberg/file_format.h

@@ -36,7 +36,6 @@ enum class ICEBERG_EXPORT FileFormatType {
   kAvro,
   kOrc,
   kPuffin,
-  kUnknown = 99
 };
 
 /// \brief Convert a FileFormatType to a string

src/iceberg/manifest_entry.cc

@@ -27,7 +27,7 @@
 
 namespace iceberg {
 
-bool ManifestEntry::operator==(const iceberg::ManifestEntry& other) const {
+bool ManifestEntry::operator==(const ManifestEntry& other) const {
   return status == other.status && snapshot_id == other.snapshot_id &&
              sequence_number == other.sequence_number &&
              file_sequence_number == other.file_sequence_number &&

src/iceberg/manifest_entry.h

@@ -74,7 +74,7 @@ struct ICEBERG_EXPORT DataFile {
   std::string file_path;
   /// Field id: 101
   /// File format type, avro, orc, parquet, or puffin
-  FileFormatType file_format = FileFormatType::kUnknown;
+  FileFormatType file_format = FileFormatType::kParquet;
   /// Field id: 102
   /// Partition data tuple, schema based on the partition spec output using partition
   /// field ids

src/iceberg/manifest_list.h

@@ -30,6 +30,8 @@
 #include "iceberg/iceberg_export.h"
 #include "iceberg/result.h"
 #include "iceberg/schema_field.h"
+#include "iceberg/snapshot.h"
+#include "iceberg/table_metadata.h"
 #include "iceberg/type.h"
 
 namespace iceberg {
@@ -40,7 +42,7 @@ namespace iceberg {
 struct ICEBERG_EXPORT PartitionFieldSummary {
   /// Field id: 509
   /// Whether the manifest contains at least one partition with a null value for the field
-  bool contains_null = false;
+  bool contains_null = true;
   /// Field id: 518
   /// Whether the manifest contains at least one partition with a NaN value for the field
   std::optional<bool> contains_nan;
@@ -97,14 +99,14 @@ struct ICEBERG_EXPORT ManifestFile {
   /// Field id: 515
   /// The sequence number when the manifest was added to the table; use 0 when reading v1
   /// manifest lists
-  int64_t sequence_number = 0;
+  int64_t sequence_number = TableMetadata::kInitialSequenceNumber;
   /// Field id: 516
   /// The minimum data sequence number of all live data or delete files in the manifest;
   /// use 0 when reading v1 manifest lists
-  int64_t min_sequence_number = 0;
+  int64_t min_sequence_number = TableMetadata::kInitialSequenceNumber;
   /// Field id: 503
   /// ID of the snapshot where the manifest file was added
-  int64_t added_snapshot_id = 0;
+  int64_t added_snapshot_id = Snapshot::kInvalidSnapshotId;
   /// Field id: 504
   /// Number of entries in the manifest that have status ADDED (1), when null this is
   /// assumed to be non-zero
@@ -139,7 +141,7 @@ struct ICEBERG_EXPORT ManifestFile {
   std::vector<uint8_t> key_metadata;
   /// Field id: 520
   /// The starting _row_id to assign to rows added by ADDED data files
-  int64_t first_row_id = 0;
+  std::optional<int64_t> first_row_id;
 
   /// \brief Checks if this manifest file contains entries with ADDED status.
   bool has_added_files() const { return added_files_count.value_or(1) > 0; }

test/manifest_list_reader_test.cc

@@ -42,7 +42,7 @@ class ManifestListReaderTest : public TempFileTestBase {
     file_io_ = std::make_shared<iceberg::arrow::ArrowFileSystemFileIO>(local_fs_);
   }
 
-  std::vector<ManifestFile> prepare_test_manifest_list() {
+  std::vector<ManifestFile> PrepareTestManifestList() {
     std::vector<ManifestFile> manifest_files;
     std::string test_dir_prefix = "/tmp/db/db/iceberg_test/metadata/";
     std::vector<std::string> paths = {"2bccd69e-d642-4816-bba0-261cd9bd0d93-m0.avro",
@@ -96,7 +96,7 @@ TEST_F(ManifestListReaderTest, BasicTest) {
   ASSERT_EQ(read_result.has_value(), true);
   ASSERT_EQ(read_result.value().size(), 4);
 
-  auto expected_manifest_list = prepare_test_manifest_list();
+  auto expected_manifest_list = PrepareTestManifestList();
   ASSERT_EQ(read_result.value(), expected_manifest_list);
 }