Fixes and cf

Author: Sandeep Gottimukkala

src/iceberg/catalog/rest/json_serde.cc

@@ -611,8 +611,8 @@ Result<FetchPlanningResultResponse> FetchPlanningResultResponseFromJson(
         partition_specs_by_id,
     const Schema& schema) {
   FetchPlanningResultResponse response;
-  ICEBERG_ASSIGN_OR_RAISE(auto status_str, GetJsonValue<std::string>(json, kPlanStatus));
-  response.plan_status = PlanStatus(PlanStatus::FromString(status_str));
+  ICEBERG_ASSIGN_OR_RAISE(response.plan_status,
+                          GetJsonValue<std::string>(json, kPlanStatus));
   ICEBERG_RETURN_UNEXPECTED(
       BaseScanTaskResponseFromJson(json, &response, partition_specs_by_id, schema));
   ICEBERG_RETURN_UNEXPECTED(response.Validate());

src/iceberg/catalog/rest/types.cc

@@ -154,8 +154,7 @@ bool PlanTableScanResponse::operator==(const PlanTableScanResponse& other) const
 
 bool FetchPlanningResultResponse::operator==(
     const FetchPlanningResultResponse& other) const {
-  return BaseScanTaskResponse::operator==(other) &&
-         plan_status.ToString() == other.plan_status.ToString();
+  return BaseScanTaskResponse::operator==(other) && plan_status == other.plan_status;
 }
 
 bool FetchScanTasksRequest::operator==(const FetchScanTasksRequest& other) const {
@@ -233,11 +232,10 @@ Status PlanTableScanResponse::Validate() const {
 }
 
 Status FetchPlanningResultResponse::Validate() const {
-  if (plan_status.ToString() == "unknown") {
+  if (plan_status.empty()) {
     return ValidationFailed("Invalid status: null");
   }
-  if (plan_status.ToString() != "completed" &&
-      (!plan_tasks.empty() || !file_scan_tasks.empty())) {
+  if (plan_status != "completed" && (!plan_tasks.empty() || !file_scan_tasks.empty())) {
     return ValidationFailed(
         "Invalid response: tasks can only be returned in a 'completed' status");
   }

src/iceberg/catalog/rest/types.h

@@ -343,7 +343,7 @@ struct ICEBERG_REST_EXPORT PlanTableScanResponse : BaseScanTaskResponse {
 /// \brief Response from polling an asynchronous scan plan, including current status and
 /// available scan tasks.
 struct ICEBERG_REST_EXPORT FetchPlanningResultResponse : BaseScanTaskResponse {
-  PlanStatus plan_status;
+  std::string plan_status;
   // TODO: Add credentials.
 
   Status Validate() const;

src/iceberg/json_serde.cc

@@ -1761,12 +1761,11 @@ Result<DataFile> DataFileFromJson(
   DataFile df;
 
   ICEBERG_ASSIGN_OR_RAISE(auto content_str, GetJsonValue<std::string>(json, kContent));
-  const auto upper_content = StringUtils::ToUpper(content_str);
-  if (upper_content == "DATA") {
+  if (content_str == ToString(DataFile::Content::kData)) {
     df.content = DataFile::Content::kData;
-  } else if (upper_content == "POSITION_DELETES") {
+  } else if (content_str == ToString(DataFile::Content::kPositionDeletes)) {
     df.content = DataFile::Content::kPositionDeletes;
-  } else if (upper_content == "EQUALITY_DELETES") {
+  } else if (content_str == ToString(DataFile::Content::kEqualityDeletes)) {
     df.content = DataFile::Content::kEqualityDeletes;
   } else {
     return JsonParseError("Unknown data file content: {}", content_str);
@@ -1835,7 +1834,7 @@ Result<DataFile> DataFileFromJson(
   ICEBERG_RETURN_UNEXPECTED(parse_int_map(kNullValueCounts, df.null_value_counts));
   ICEBERG_RETURN_UNEXPECTED(parse_int_map(kNanValueCounts, df.nan_value_counts));
 
-  // Parse BinaryMap: {"keys": [int, ...], "values": [base64 binary, ...]}
+  // Parse BinaryMap: {"keys": [int, ...], "values": [...]}
   auto parse_binary_map = [&](std::string_view key,
                               std::map<int32_t, std::vector<uint8_t>>& target) -> Status {
     if (!json.contains(key) || json.at(key).is_null()) return {};

src/iceberg/table_scan.h

@@ -34,47 +34,6 @@
 
 namespace iceberg {
 
-class ICEBERG_EXPORT PlanStatus {
- public:
-  enum class Status {
-    kCompleted,
-    kSubmitted,
-    kCancelled,
-    kFailed,
-    kUnknown
-  };
-
-  PlanStatus() : status_(Status::kUnknown) {}
-  explicit PlanStatus(Status status) : status_(status) {}
-
-  static Status FromString(std::string_view status_str) {
-    if (status_str == "completed") {
-      return Status::kCompleted;
-    } else if (status_str == "submitted") {
-      return Status::kSubmitted;
-    } else if (status_str == "cancelled") {
-      return Status::kCancelled;
-    } else if (status_str == "failed") {
-      return Status::kFailed;
-    }
-    return Status::kUnknown;
-  }
-
-  const std::string ToString() const {
-    switch (status_) {
-      case Status::kCompleted: return "completed";
-      case Status::kSubmitted: return "submitted";
-      case Status::kCancelled: return "cancelled";
-      case Status::kFailed: return "failed";
-      default: return "unknown";
-    }
-  }
-
- private:
-  Status status_;
-
-};
-
 /// \brief An abstract scan task.
 class ICEBERG_EXPORT ScanTask {
  public:

src/iceberg/test/json_serde_test.cc

@@ -779,7 +779,7 @@ TEST(TableRequirementJsonTest, TableRequirementUnknownType) {
 
 TEST(DataFileFromJsonTest, RequiredFieldsOnly) {
   auto json = R"({
-    "content": "DATA",
+    "content": "data",
     "file-path": "s3://bucket/data/file.parquet",
     "file-format": "PARQUET",
     "file-size-in-bytes": 12345,
@@ -799,8 +799,7 @@ TEST(DataFileFromJsonTest, RequiredFieldsOnly) {
   EXPECT_FALSE(df.partition_spec_id.has_value());
 }
 
-TEST(DataFileFromJsonTest, LowercaseContentAndFormat) {
-  // The REST API sends uppercase, but we should handle lowercase too.
+TEST(DataFileFromJsonTest, LowercaseFormat) {
   auto json = R"({
     "content": "data",
     "file-path": "s3://bucket/data/file.avro",
@@ -817,7 +816,7 @@ TEST(DataFileFromJsonTest, LowercaseContentAndFormat) {
 
 TEST(DataFileFromJsonTest, WithOptionalFields) {
   auto json = R"({
-    "content": "DATA",
+    "content": "data",
     "file-path": "s3://bucket/data/file.parquet",
     "file-format": "PARQUET",
     "spec-id": 1,
@@ -852,7 +851,7 @@ TEST(DataFileFromJsonTest, WithOptionalFields) {
 
 TEST(DataFileFromJsonTest, EqualityDeleteFile) {
   auto json = R"({
-    "content": "EQUALITY_DELETES",
+    "content": "equality_deletes",
     "file-path": "s3://bucket/deletes/eq_delete.parquet",
     "file-format": "PARQUET",
     "file-size-in-bytes": 5000,
@@ -871,7 +870,7 @@ TEST(DataFileFromJsonTest, EqualityDeleteFile) {
 
 TEST(DataFileFromJsonTest, PositionDeleteFileWithReferencedDataFile) {
   auto json = R"({
-    "content": "POSITION_DELETES",
+    "content": "position_deletes",
     "file-path": "s3://bucket/deletes/pos_delete.parquet",
     "file-format": "PARQUET",
     "file-size-in-bytes": 3000,
@@ -904,7 +903,7 @@ TEST(DataFileFromJsonTest, InvalidContentType) {
 TEST(DataFileFromJsonTest, MissingRequiredField) {
   // Missing "file-path"
   auto json = R"({
-    "content": "DATA",
+    "content": "data",
     "file-format": "PARQUET",
     "file-size-in-bytes": 100,
     "record-count": 10
@@ -931,7 +930,7 @@ TEST(FileScanTasksFromJsonTest, EmptyArray) {
 TEST(FileScanTasksFromJsonTest, SingleTaskNoDeleteFiles) {
   auto json = R"([{
     "data-file": {
-      "content": "DATA",
+      "content": "data",
       "file-path": "s3://bucket/data/file.parquet",
       "file-format": "PARQUET",
       "file-size-in-bytes": 12345,
@@ -959,7 +958,7 @@ TEST(FileScanTasksFromJsonTest, TaskWithDeleteFileReferences) {
 
   auto json = R"([{
     "data-file": {
-      "content": "DATA",
+      "content": "data",
       "file-path": "s3://bucket/data/file.parquet",
       "file-format": "PARQUET",
       "file-size-in-bytes": 12345,
@@ -973,14 +972,13 @@ TEST(FileScanTasksFromJsonTest, TaskWithDeleteFileReferences) {
   ASSERT_EQ(result.value().size(), 1U);
   const auto& task = result.value()[0];
   ASSERT_EQ(task.delete_files().size(), 1U);
-  EXPECT_EQ(task.delete_files()[0]->file_path,
-            "s3://bucket/deletes/pos_delete.parquet");
+  EXPECT_EQ(task.delete_files()[0]->file_path, "s3://bucket/deletes/pos_delete.parquet");
 }
 
 TEST(FileScanTasksFromJsonTest, DeleteFileReferenceOutOfRange) {
   auto json = R"([{
     "data-file": {
-      "content": "DATA",
+      "content": "data",
       "file-path": "s3://bucket/data/file.parquet",
       "file-format": "PARQUET",
       "file-size-in-bytes": 100,

src/iceberg/test/rest_json_serde_test.cc

@@ -1467,7 +1467,7 @@ TEST(FetchScanTasksResponseFromJsonTest, WithFileScanTasks) {
     "plan-tasks": [],
     "delete-files": [
       {
-        "content": "POSITION_DELETES",
+        "content": "position_deletes",
         "file-path": "s3://bucket/deletes/delete.parquet",
         "file-format": "PARQUET",
         "file-size-in-bytes": 512,
@@ -1477,7 +1477,7 @@ TEST(FetchScanTasksResponseFromJsonTest, WithFileScanTasks) {
     "file-scan-tasks": [
       {
         "data-file": {
-          "content": "DATA",
+          "content": "data",
           "file-path": "s3://bucket/data/file.parquet",
           "file-format": "PARQUET",
           "file-size-in-bytes": 12345,