From 10b36c09e9ffd96f53d2fdada725f9c999241dd1 Mon Sep 17 00:00:00 2001
From: kevinyhzou <kevinyunhe8@gmail.com>
Date: Fri, 26 Jul 2024 15:38:26 +0800
Subject: [PATCH] support set orc reader time zone name

---
 src/Core/Settings.h                                    |  2 +-
 src/Core/SettingsChangesHistory.cpp                    |  2 +-
 src/Formats/FormatFactory.cpp                          |  2 +-
 src/Formats/FormatSettings.h                           |  2 +-
 .../Formats/Impl/NativeORCBlockInputFormat.cpp         |  6 +-----
 tests/queries/0_stateless/03198_orc_read_time_zone.sh  | 10 +++++-----
 6 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/src/Core/Settings.h b/src/Core/Settings.h
index 2a665326afc..a5220c3017c 100644
--- a/src/Core/Settings.h
+++ b/src/Core/Settings.h
@@ -1073,7 +1073,7 @@ class IColumn;
     M(Bool, input_format_orc_allow_missing_columns, true, "Allow missing columns while reading ORC input formats", 0) \
     M(Bool, input_format_orc_use_fast_decoder, true, "Use a faster ORC decoder implementation.", 0) \
     M(Bool, input_format_orc_filter_push_down, true, "When reading ORC files, skip whole stripes or row groups based on the WHERE/PREWHERE expressions, min/max statistics or bloom filter in the ORC metadata.", 0) \
-    M(Bool, input_format_orc_read_use_writer_time_zone, false, "Whether use the writer's time zone in ORC stripe for ORC row reader, the default ORC row reader's time zone is GMT.", 0) \
+    M(String, input_format_orc_reader_time_zone_name, "GMT", "The time zone name for ORC row reader, the default ORC row reader's time zone is GMT.", 0) \
     M(Bool, input_format_parquet_allow_missing_columns, true, "Allow missing columns while reading Parquet input formats", 0) \
     M(UInt64, input_format_parquet_local_file_min_bytes_for_seek, 8192, "Min bytes required for local read (file) to do seek, instead of read with ignore in Parquet input format", 0) \
     M(Bool, input_format_arrow_allow_missing_columns, true, "Allow missing columns while reading Arrow input formats", 0) \
diff --git a/src/Core/SettingsChangesHistory.cpp b/src/Core/SettingsChangesHistory.cpp
index acd119c159b..457caa76bb6 100644
--- a/src/Core/SettingsChangesHistory.cpp
+++ b/src/Core/SettingsChangesHistory.cpp
@@ -69,7 +69,7 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
               {"dictionary_validate_primary_key_type", false, false, "Validate primary key type for dictionaries. By default id type for simple layouts will be implicitly converted to UInt64."},
               {"collect_hash_table_stats_during_joins", false, true, "New setting."},
               {"max_size_to_preallocate_for_joins", 0, 100'000'000, "New setting."},
-              {"input_format_orc_read_use_writer_time_zone", false, false, "Whether use the writer's time zone in ORC stripe for ORC row reader, the default ORC row reader's time zone is GMT."},
+              {"input_format_orc_reader_time_zone_name", "GMT", "GMT", "The time zone name for ORC row reader, the default ORC row reader's time zone is GMT."},
               {"lightweight_mutation_projection_mode", "throw", "throw", "When lightweight delete happens on a table with projection(s), the possible operations include throw the exception as projection exists, or drop all projection related to this table then do lightweight delete."},
               {"database_replicated_allow_heavy_create", true, false, "Long-running DDL queries (CREATE AS SELECT and POPULATE) for Replicated database engine was forbidden"},
               {"query_plan_merge_filters", false, false, "Allow to merge filters in the query plan"},
diff --git a/src/Formats/FormatFactory.cpp b/src/Formats/FormatFactory.cpp
index 1271cdfb7ad..e61bd16b537 100644
--- a/src/Formats/FormatFactory.cpp
+++ b/src/Formats/FormatFactory.cpp
@@ -244,7 +244,7 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
     format_settings.orc.output_row_index_stride = settings.output_format_orc_row_index_stride;
     format_settings.orc.use_fast_decoder = settings.input_format_orc_use_fast_decoder;
     format_settings.orc.filter_push_down = settings.input_format_orc_filter_push_down;
-    format_settings.orc.read_use_writer_time_zone = settings.input_format_orc_read_use_writer_time_zone;
+    format_settings.orc.reader_time_zone_name = settings.input_format_orc_reader_time_zone_name;
     format_settings.defaults_for_omitted_fields = settings.input_format_defaults_for_omitted_fields;
     format_settings.capn_proto.enum_comparing_mode = settings.format_capn_proto_enum_comparising_mode;
     format_settings.capn_proto.skip_fields_with_unsupported_types_in_schema_inference = settings.input_format_capn_proto_skip_fields_with_unsupported_types_in_schema_inference;
diff --git a/src/Formats/FormatSettings.h b/src/Formats/FormatSettings.h
index a736bb1a558..2df8c9ca171 100644
--- a/src/Formats/FormatSettings.h
+++ b/src/Formats/FormatSettings.h
@@ -409,7 +409,7 @@ struct FormatSettings
         bool use_fast_decoder = true;
         bool filter_push_down = true;
         UInt64 output_row_index_stride = 10'000;
-        bool read_use_writer_time_zone = false;
+        String reader_time_zone_name = "GMT";
     } orc{};
 
     /// For capnProto format we should determine how to
diff --git a/src/Processors/Formats/Impl/NativeORCBlockInputFormat.cpp b/src/Processors/Formats/Impl/NativeORCBlockInputFormat.cpp
index c10969b02b7..649721f28bf 100644
--- a/src/Processors/Formats/Impl/NativeORCBlockInputFormat.cpp
+++ b/src/Processors/Formats/Impl/NativeORCBlockInputFormat.cpp
@@ -900,11 +900,7 @@ bool NativeORCBlockInputFormat::prepareStripeReader()
 
     orc::RowReaderOptions row_reader_options;
     row_reader_options.includeTypes(include_indices);
-    if (format_settings.orc.read_use_writer_time_zone)
-    {
-        String writer_time_zone = current_stripe_info->getWriterTimezone();
-        row_reader_options.setTimezoneName(writer_time_zone);
-    }
+    row_reader_options.setTimezoneName(format_settings.orc.reader_time_zone_name);
     row_reader_options.range(current_stripe_info->getOffset(), current_stripe_info->getLength());
     if (format_settings.orc.filter_push_down && sarg)
     {
diff --git a/tests/queries/0_stateless/03198_orc_read_time_zone.sh b/tests/queries/0_stateless/03198_orc_read_time_zone.sh
index 27530c06237..7e931e16e48 100755
--- a/tests/queries/0_stateless/03198_orc_read_time_zone.sh
+++ b/tests/queries/0_stateless/03198_orc_read_time_zone.sh
@@ -5,8 +5,8 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
 # shellcheck source=../shell_config.sh
 . "$CURDIR"/../shell_config.sh
 
-$CLICKHOUSE_CLIENT -q "drop table if exists test"
-$CLICKHOUSE_CLIENT -q "create table test(id UInt64, t DateTime64) Engine=MergeTree order by id"
-$CLICKHOUSE_CLIENT -q "insert into test from infile '$CURDIR/data_orc/test_reader_time_zone.snappy.orc' SETTINGS input_format_orc_read_use_writer_time_zone=true FORMAT ORC"
-$CLICKHOUSE_CLIENT -q "select * from test SETTINGS session_timezone='Asia/Shanghai'"
-$CLICKHOUSE_CLIENT -q "drop table test"
\ No newline at end of file
+$CLICKHOUSE_CLIENT -q "drop table if exists test_orc_read_timezone"
+$CLICKHOUSE_CLIENT -q "create table test_orc_read_timezone(id UInt64, t DateTime64) Engine=MergeTree order by id"
+$CLICKHOUSE_CLIENT -q "insert into test_orc_read_timezone from infile '$CURDIR/data_orc/test_reader_time_zone.snappy.orc' SETTINGS input_format_orc_reader_time_zone_name='Asia/Shanghai' FORMAT ORC"
+$CLICKHOUSE_CLIENT -q "select * from test_orc_read_timezone"
+$CLICKHOUSE_CLIENT -q "drop table test_orc_read_timezone"
\ No newline at end of file