fix: fix orc read timestamp under debian

cmake_modules/DefineOptions.cmake

@@ -99,7 +99,6 @@ if("${CMAKE_SOURCE_DIR}" STREQUAL "${CMAKE_CURRENT_SOURCE_DIR}")
     set_option_category("Test")
 
     define_option(PAIMON_BUILD_TESTS "Build the Paimon googletest unit tests" OFF)
-    define_option(PAIMON_BUILD_EXAMPLE "Build the Paimon example" OFF)
 
     if(PAIMON_BUILD_SHARED)
         set(PAIMON_TEST_LINKAGE_DEFAULT "shared")

src/paimon/core/global_index/indexed_split_test.cpp

@@ -131,6 +131,10 @@ TEST(IndexedSplitTest, TestIndexedSplitWithScore) {
         std::make_shared<IndexedSplitImpl>(expected_data_split, ranges, scores);
 
     ASSERT_EQ(*result_indexed_split, *expected_indexed_split) << result_indexed_split->ToString();
+    ASSERT_TRUE(
+        result_indexed_split->ToString().find(
+            "rowRanges=[[55, 56],[270, 270],[1001, 1002]], scores=[1.01,2.1,-1.32,4.23,50.74]") !=
+        std::string::npos);
     ASSERT_OK_AND_ASSIGN(std::string serialize_bytes, Split::Serialize(result_indexed_split, pool));
     ASSERT_EQ(serialize_bytes,
               std::string(reinterpret_cast<char*>(split_bytes.data()), split_bytes.size()));

src/paimon/format/orc/complex_predicate_test.cpp

@@ -122,7 +122,7 @@ class ComplexPredicateTest : public ::testing::Test {
 TEST_F(ComplexPredicateTest, TestSimple) {
     std::string file_name = paimon::test::GetDataDir() +
                             "/orc/append_complex_data.db/append_complex_data/f1=10/bucket-0/"
-                            "data-05b19a2d-18d8-4620-b8ab-cd8f862d96d1-0.orc";
+                            "data-14a30421-7650-486c-9876-66a1fa4356ff-0.orc";
     arrow::FieldVector fields = {
         arrow::field("f1", arrow::int32()),
         arrow::field("f2", arrow::int32()),

src/paimon/format/orc/orc_file_batch_reader.cpp

@@ -241,6 +241,9 @@ Result<::orc::RowReaderOptions> OrcFileBatchReader::CreateRowReaderOptions(
         include_fields.push_back(field_name);
     }
     row_reader_options.include(include_fields);
+    // In order to avoid issue like https://github.com/alibaba/paimon-cpp/issues/42, we explicitly
+    // set GMT timezone.
+    row_reader_options.setTimezoneName("GMT");
     row_reader_options.searchArgument(std::move(search_arg));
 
     PAIMON_ASSIGN_OR_RAISE(

src/paimon/format/orc/orc_file_batch_reader_test.cpp

@@ -484,7 +484,7 @@ TEST_F(OrcFileBatchReaderTest, TestNextBatchWithDictionary) {
 TEST_P(OrcFileBatchReaderTest, TestComplexType) {
     std::string file_name = paimon::test::GetDataDir() +
                             "/orc/append_complex_data.db/append_complex_data/f1=10/bucket-0/"
-                            "data-05b19a2d-18d8-4620-b8ab-cd8f862d96d1-0.orc";
+                            "data-14a30421-7650-486c-9876-66a1fa4356ff-0.orc";
     arrow::FieldVector fields = {arrow::field("f1", arrow::int32()),
                                  arrow::field("f2", arrow::int32()),
                                  arrow::field("f3", arrow::date32()),

src/paimon/format/orc/orc_format_writer.cpp

@@ -239,6 +239,9 @@ Result<::orc::WriterOptions> OrcFormatWriter::PrepareWriterOptions(
                            OptionsUtils::GetValueFromMap<size_t>(options, ORC_ROW_INDEX_STRIDE,
                                                                  DEFAULT_ROW_INDEX_STRIDE));
     writer_options.setRowIndexStride(row_index_stride);
+    // In order to avoid issue like https://github.com/alibaba/paimon-cpp/issues/42, we explicitly
+    // set GMT timezone.
+    writer_options.setTimezoneName("GMT");
     return writer_options;
 }
 

test/inte/global_index_test.cpp

@@ -551,6 +551,27 @@ TEST_P(GlobalIndexTest, TestScanIndex) {
         ASSERT_OK_AND_ASSIGN(auto index_result, evaluator->Evaluate(predicate));
         ASSERT_EQ(index_result.value()->ToString(), "{0,1,2,3,4,5,6,7}");
     }
+    {
+        // test greater or equal predicate which bitmap index is not support, will return all range
+        auto predicate = PredicateBuilder::GreaterOrEqual(/*field_index=*/1, /*field_name=*/"f1",
+                                                          FieldType::INT, Literal(10));
+        ASSERT_OK_AND_ASSIGN(auto index_result, evaluator->Evaluate(predicate));
+        ASSERT_EQ(index_result.value()->ToString(), "{0,1,2,3,4,5,6,7}");
+    }
+    {
+        // test less than predicate which bitmap index is not support, will return all range
+        auto predicate = PredicateBuilder::LessThan(/*field_index=*/1, /*field_name=*/"f1",
+                                                    FieldType::INT, Literal(10));
+        ASSERT_OK_AND_ASSIGN(auto index_result, evaluator->Evaluate(predicate));
+        ASSERT_EQ(index_result.value()->ToString(), "{0,1,2,3,4,5,6,7}");
+    }
+    {
+        // test less or equal predicate which bitmap index is not support, will return all range
+        auto predicate = PredicateBuilder::LessOrEqual(/*field_index=*/1, /*field_name=*/"f1",
+                                                       FieldType::INT, Literal(10));
+        ASSERT_OK_AND_ASSIGN(auto index_result, evaluator->Evaluate(predicate));
+        ASSERT_EQ(index_result.value()->ToString(), "{0,1,2,3,4,5,6,7}");
+    }
     {
         // test a predicate for field with no index
         auto f3_predicate = PredicateBuilder::Equal(/*field_index=*/3, /*field_name=*/"f3",

test/inte/read_inte_test.cpp

@@ -630,9 +630,9 @@ TEST_P(ReadInteTest, TestAppendReadWithComplexTypePredicate) {
     std::vector<std::string> file_list_1;
     std::vector<std::string> file_list_2;
     if (param.file_format == "orc") {
-        file_list_0 = {"data-05b19a2d-18d8-4620-b8ab-cd8f862d96d1-0.orc"};
-        file_list_1 = {"data-d336eb91-df17-4932-8206-4199579a2cbd-0.orc"};
-        file_list_2 = {"data-b35d2ec8-b4a5-4c23-9652-bd8d9fabdee0-0.orc"};
+        file_list_0 = {"data-14a30421-7650-486c-9876-66a1fa4356ff-0.orc"};
+        file_list_1 = {"data-d39c4ccc-6245-460c-bd70-632bd2b26234-0.orc"};
+        file_list_2 = {"data-b20718c4-b2e1-4928-b563-11539edc9572-0.orc"};
     } else if (param.file_format == "parquet") {
         file_list_0 = {"data-f8754699-0c43-4e53-be00-7e8af1754913-0.parquet"};
         file_list_1 = {"data-ac0894ca-fc13-49c8-bb22-4556c8ee416c-0.parquet"};
@@ -668,7 +668,7 @@ TEST_P(ReadInteTest, TestAppendReadWithComplexTypePredicate) {
                                                                          &expected_array);
     ASSERT_TRUE(array_status.ok());
     ASSERT_TRUE(result_array);
-    ASSERT_TRUE(result_array->Equals(*expected_array));
+    ASSERT_TRUE(result_array->Equals(*expected_array)) << result_array->ToString();
 }
 
 TEST_P(ReadInteTest, TestAppendReadWithPredicateOnlyPushdown) {

test/inte/scan_inte_test.cpp

@@ -1230,7 +1230,7 @@ TEST_F(ScanInteTest, TestScanAppendComplexDataWithSnapshot4WithPredicateFilter)
     // check data splits
     auto result_data_splits = CollectDataSplits(result_plan);
     auto meta = std::make_shared<DataFileMeta>(
-        "data-05b19a2d-18d8-4620-b8ab-cd8f862d96d1-0.orc", /*file_size=*/974, /*row_count=*/6,
+        "data-14a30421-7650-486c-9876-66a1fa4356ff-0.orc", /*file_size=*/1004, /*row_count=*/6,
         /*min_key=*/BinaryRow::EmptyRow(), /*max_key=*/BinaryRow::EmptyRow(),
         /*key_stats=*/SimpleStats::EmptyStats(),
         BinaryRowGenerator::GenerateStats(
@@ -1242,7 +1242,7 @@ TEST_F(ScanInteTest, TestScanAppendComplexDataWithSnapshot4WithPredicateFilter)
             {0, 0, 1, 0, 1, 1}, pool_.get()),
         /*min_sequence_number=*/0, /*max_sequence_number=*/5, /*schema_id=*/0,
         /*level=*/0, /*extra_files=*/std::vector<std::optional<std::string>>(),
-        /*creation_time=*/Timestamp(1729183876992ll, 0),
+        /*creation_time=*/Timestamp(1767506722625ll, 0),
         /*delete_row_count=*/0, /*embedded_index=*/nullptr, FileSource::Compact(),
         /*value_stats_cols=*/std::nullopt, /*external_path=*/std::nullopt,
         /*first_row_id=*/std::nullopt,
@@ -1296,7 +1296,7 @@ TEST_F(ScanInteTest, TestScanAppendComplexDataWithSnapshot4WithPredicateFilter2)
     }
 
     auto meta = std::make_shared<DataFileMeta>(
-        "data-05b19a2d-18d8-4620-b8ab-cd8f862d96d1-0.orc", /*file_size=*/974, /*row_count=*/6,
+        "data-14a30421-7650-486c-9876-66a1fa4356ff-0.orc", /*file_size=*/1004, /*row_count=*/6,
         /*min_key=*/BinaryRow::EmptyRow(), /*max_key=*/BinaryRow::EmptyRow(),
         /*key_stats=*/SimpleStats::EmptyStats(),
         BinaryRowGenerator::GenerateStats(
@@ -1308,7 +1308,7 @@ TEST_F(ScanInteTest, TestScanAppendComplexDataWithSnapshot4WithPredicateFilter2)
             {0, 0, 1, 0, 1, 1}, pool_.get()),
         /*min_sequence_number=*/0, /*max_sequence_number=*/5, /*schema_id=*/0,
         /*level=*/0, /*extra_files=*/std::vector<std::optional<std::string>>(),
-        /*creation_time=*/Timestamp(1729183876992ll, 0),
+        /*creation_time=*/Timestamp(1767506722625ll, 0),
         /*delete_row_count=*/0, /*embedded_index=*/nullptr, FileSource::Compact(),
         /*value_stats_cols=*/std::nullopt, /*external_path=*/std::nullopt,
         /*first_row_id=*/std::nullopt,

test/test_data/orc/append_complex_data.db/append_complex_data/schema/schema-0

@@ -35,5 +35,5 @@
     "manifest.format" : "orc",
     "file.format" : "orc"
   },
-  "timeMillis" : 1729155073912
+  "timeMillis" : 1767506720974
 }

test/test_data/orc/append_complex_data.db/append_complex_data/snapshot/snapshot-1

@@ -2,15 +2,18 @@
   "version" : 3,
   "id" : 1,
   "schemaId" : 0,
-  "baseManifestList" : "manifest-list-0e955494-20af-43ff-8886-4a738fd3d517-0",
-  "deltaManifestList" : "manifest-list-0e955494-20af-43ff-8886-4a738fd3d517-1",
+  "baseManifestList" : "manifest-list-5496fd48-8429-467e-b48d-0de24ec78a99-0",
+  "baseManifestListSize" : 392,
+  "deltaManifestList" : "manifest-list-5496fd48-8429-467e-b48d-0de24ec78a99-1",
+  "deltaManifestListSize" : 1535,
   "changelogManifestList" : null,
-  "commitUser" : "c83342c0-bb33-4282-bb8c-b07b3033b86e",
+  "commitUser" : "1a9b901a-ec8e-414b-b546-a26b3c0dcac1",
   "commitIdentifier" : 1,
   "commitKind" : "APPEND",
-  "timeMillis" : 1729155076102,
+  "timeMillis" : 1767506722258,
   "logOffsets" : { },
   "totalRecordCount" : 3,
   "deltaRecordCount" : 3,
-  "changelogRecordCount" : 0
+  "changelogRecordCount" : 0,
+  "nextRowId" : 0
 }

test/test_data/orc/append_complex_data.db/append_complex_data/snapshot/snapshot-2

@@ -2,15 +2,18 @@
   "version" : 3,
   "id" : 2,
   "schemaId" : 0,
-  "baseManifestList" : "manifest-list-dd8bb739-7944-4b9f-a146-30ed9f9e27d9-0",
-  "deltaManifestList" : "manifest-list-dd8bb739-7944-4b9f-a146-30ed9f9e27d9-1",
+  "baseManifestList" : "manifest-list-392fa32d-34bf-4eef-86be-b31ccf8b7dd5-0",
+  "baseManifestListSize" : 1535,
+  "deltaManifestList" : "manifest-list-392fa32d-34bf-4eef-86be-b31ccf8b7dd5-1",
+  "deltaManifestListSize" : 1548,
   "changelogManifestList" : null,
-  "commitUser" : "c83342c0-bb33-4282-bb8c-b07b3033b86e",
+  "commitUser" : "1a9b901a-ec8e-414b-b546-a26b3c0dcac1",
   "commitIdentifier" : 2,
   "commitKind" : "APPEND",
-  "timeMillis" : 1729155076912,
+  "timeMillis" : 1767506722553,
   "logOffsets" : { },
   "totalRecordCount" : 7,
   "deltaRecordCount" : 4,
-  "changelogRecordCount" : 0
+  "changelogRecordCount" : 0,
+  "nextRowId" : 0
 }

test/test_data/orc/append_complex_data.db/append_complex_data/snapshot/snapshot-3

@@ -2,15 +2,18 @@
   "version" : 3,
   "id" : 3,
   "schemaId" : 0,
-  "baseManifestList" : "manifest-list-7a1c859b-2bd3-4a85-895c-1e16dd63493b-0",
-  "deltaManifestList" : "manifest-list-7a1c859b-2bd3-4a85-895c-1e16dd63493b-1",
+  "baseManifestList" : "manifest-list-4e2ee2ad-4258-41ca-8648-60f7481a72e9-0",
+  "baseManifestListSize" : 1708,
+  "deltaManifestList" : "manifest-list-4e2ee2ad-4258-41ca-8648-60f7481a72e9-1",
+  "deltaManifestListSize" : 1551,
   "changelogManifestList" : null,
-  "commitUser" : "c83342c0-bb33-4282-bb8c-b07b3033b86e",
+  "commitUser" : "1a9b901a-ec8e-414b-b546-a26b3c0dcac1",
   "commitIdentifier" : 3,
   "commitKind" : "APPEND",
-  "timeMillis" : 1729155077514,
+  "timeMillis" : 1767506722711,
   "logOffsets" : { },
   "totalRecordCount" : 8,
   "deltaRecordCount" : 1,
-  "changelogRecordCount" : 0
+  "changelogRecordCount" : 0,
+  "nextRowId" : 0
 }

test/test_data/orc/append_complex_data.db/append_complex_data/snapshot/snapshot-4

@@ -2,15 +2,18 @@
   "version" : 3,
   "id" : 4,
   "schemaId" : 0,
-  "baseManifestList" : "manifest-list-7a1c859b-2bd3-4a85-895c-1e16dd63493b-2",
-  "deltaManifestList" : "manifest-list-7a1c859b-2bd3-4a85-895c-1e16dd63493b-3",
+  "baseManifestList" : "manifest-list-4e2ee2ad-4258-41ca-8648-60f7481a72e9-2",
+  "baseManifestListSize" : 1756,
+  "deltaManifestList" : "manifest-list-4e2ee2ad-4258-41ca-8648-60f7481a72e9-3",
+  "deltaManifestListSize" : 1547,
   "changelogManifestList" : null,
-  "commitUser" : "c83342c0-bb33-4282-bb8c-b07b3033b86e",
+  "commitUser" : "1a9b901a-ec8e-414b-b546-a26b3c0dcac1",
   "commitIdentifier" : 3,
   "commitKind" : "COMPACT",
-  "timeMillis" : 1729155077559,
+  "timeMillis" : 1767506722814,
   "logOffsets" : { },
   "totalRecordCount" : 8,
   "deltaRecordCount" : 0,
-  "changelogRecordCount" : 0
+  "changelogRecordCount" : 0,
+  "nextRowId" : 0
 }