diff --git a/.editorconfig b/.editorconfig
index 8ac06debb5a..8ecaf9b0267 100644
--- a/.editorconfig
+++ b/.editorconfig
@@ -19,3 +19,7 @@ charset = utf-8
indent_style = space
indent_size = 4
trim_trailing_whitespace = true
+
+# Some SQL results have trailing whitespace which is removed by IDEs
+[tests/queries/**.reference]
+trim_trailing_whitespace = false
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 51a1a6e2df8..73b2155482e 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -48,19 +48,17 @@ At a minimum, the following information should be added (but add more as needed)
- [ ] Allow: Stateful tests
- [ ] Allow: Integration Tests
- [ ] Allow: Performance tests
+- [ ] Allow: Normal Builds
+- [ ] Allow: Special Builds
- [ ] Allow: All NOT Required Checks
- [ ] Allow: batch 1, 2 for multi-batch jobs
- [ ] Allow: batch 3, 4, 5, 6 for multi-batch jobs
---
- [ ] Exclude: Style check
- [ ] Exclude: Fast test
-- [ ] Exclude: Integration Tests
-- [ ] Exclude: Stateless tests
-- [ ] Exclude: Stateful tests
-- [ ] Exclude: Performance tests
- [ ] Exclude: All with ASAN
-- [ ] Exclude: All with Aarch64
- [ ] Exclude: All with TSAN, MSAN, UBSAN, Coverage
+- [ ] Exclude: All with aarch64, release, debug
---
- [ ] Do not test
- [ ] Upload binaries for special builds
diff --git a/contrib/cld2 b/contrib/cld2
index bc6d493a2f6..217ba8b8805 160000
--- a/contrib/cld2
+++ b/contrib/cld2
@@ -1 +1 @@
-Subproject commit bc6d493a2f64ed1fc1c4c4b4294a542a04e04217
+Subproject commit 217ba8b8805b41557faadaa47bb6e99f2242eea3
diff --git a/contrib/orc b/contrib/orc
index e24f2c2a3ca..947cebaf943 160000
--- a/contrib/orc
+++ b/contrib/orc
@@ -1 +1 @@
-Subproject commit e24f2c2a3ca0769c96704ab20ad6f512a83ea2ad
+Subproject commit 947cebaf9432d708253ac08dc3012daa6b4ede6f
diff --git a/docker/test/style/Dockerfile b/docker/test/style/Dockerfile
index cb29185f068..91768c8328d 100644
--- a/docker/test/style/Dockerfile
+++ b/docker/test/style/Dockerfile
@@ -30,6 +30,7 @@ RUN pip3 install \
mypy==1.8.0 \
pylint==3.1.0 \
python-magic==0.4.24 \
+ flake8==4.0.1 \
requests \
thefuzz \
types-requests \
diff --git a/docker/test/style/run.sh b/docker/test/style/run.sh
index cc6cb292b66..64803191532 100755
--- a/docker/test/style/run.sh
+++ b/docker/test/style/run.sh
@@ -9,6 +9,8 @@ echo "Check style" | ts
./check-style -n |& tee /test_output/style_output.txt
echo "Check python formatting with black" | ts
./check-black -n |& tee /test_output/black_output.txt
+echo "Check python with flake8" | ts
+./check-flake8 |& tee /test_output/flake8_output.txt
echo "Check python type hinting with mypy" | ts
./check-mypy -n |& tee /test_output/mypy_output.txt
echo "Check typos" | ts
diff --git a/docker/test/upgrade/run.sh b/docker/test/upgrade/run.sh
index 1f2cc9903b2..a4c4c75e5b3 100644
--- a/docker/test/upgrade/run.sh
+++ b/docker/test/upgrade/run.sh
@@ -25,7 +25,8 @@ azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
./setup_minio.sh stateless # to have a proper environment
echo "Get previous release tag"
-previous_release_tag=$(dpkg --info package_folder/clickhouse-client*.deb | grep "Version: " | awk '{print $2}' | cut -f1 -d'+' | get_previous_release_tag)
+# shellcheck disable=SC2016
+previous_release_tag=$(dpkg-deb --showformat='${Version}' --show package_folder/clickhouse-client*.deb | get_previous_release_tag)
echo $previous_release_tag
echo "Clone previous release repository"
diff --git a/docs/changelogs/v24.4.2.141-stable.md b/docs/changelogs/v24.4.2.141-stable.md
new file mode 100644
index 00000000000..656d0854392
--- /dev/null
+++ b/docs/changelogs/v24.4.2.141-stable.md
@@ -0,0 +1,101 @@
+---
+sidebar_position: 1
+sidebar_label: 2024
+---
+
+# 2024 Changelog
+
+### ClickHouse release v24.4.2.141-stable (9e23d27bd11) FIXME as compared to v24.4.1.2088-stable (6d4b31322d1)
+
+#### Improvement
+* Backported in [#63467](https://github.com/ClickHouse/ClickHouse/issues/63467): Make rabbitmq nack broken messages. Closes [#45350](https://github.com/ClickHouse/ClickHouse/issues/45350). [#60312](https://github.com/ClickHouse/ClickHouse/pull/60312) ([Kseniia Sumarokova](https://github.com/kssenii)).
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#63612](https://github.com/ClickHouse/ClickHouse/issues/63612): The Dockerfile is reviewed by the docker official library in https://github.com/docker-library/official-images/pull/15846. [#63400](https://github.com/ClickHouse/ClickHouse/pull/63400) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+
+* Backported in [#64279](https://github.com/ClickHouse/ClickHouse/issues/64279): Fix queries with FINAL give wrong result when table does not use adaptive granularity. [#62432](https://github.com/ClickHouse/ClickHouse/pull/62432) ([Duc Canh Le](https://github.com/canhld94)).
+* Backported in [#63295](https://github.com/ClickHouse/ClickHouse/issues/63295): Fix crash with untuple and unresolved lambda. [#63131](https://github.com/ClickHouse/ClickHouse/pull/63131) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#63978](https://github.com/ClickHouse/ClickHouse/issues/63978): Fix intersect parts when restart after drop range. [#63202](https://github.com/ClickHouse/ClickHouse/pull/63202) ([Han Fei](https://github.com/hanfei1991)).
+* Backported in [#63413](https://github.com/ClickHouse/ClickHouse/issues/63413): Fix a misbehavior when SQL security defaults don't load for old tables during server startup. [#63209](https://github.com/ClickHouse/ClickHouse/pull/63209) ([pufit](https://github.com/pufit)).
+* Backported in [#63388](https://github.com/ClickHouse/ClickHouse/issues/63388): JOIN filter push down filled join fix. Closes [#63228](https://github.com/ClickHouse/ClickHouse/issues/63228). [#63234](https://github.com/ClickHouse/ClickHouse/pull/63234) ([Maksim Kita](https://github.com/kitaisreal)).
+* Backported in [#63618](https://github.com/ClickHouse/ClickHouse/issues/63618): Fix bug which could potentially lead to rare LOGICAL_ERROR during SELECT query with message: `Unexpected return type from materialize. Expected type_XXX. Got type_YYY.` Introduced in [#59379](https://github.com/ClickHouse/ClickHouse/issues/59379). [#63353](https://github.com/ClickHouse/ClickHouse/pull/63353) ([alesapin](https://github.com/alesapin)).
+* Backported in [#63451](https://github.com/ClickHouse/ClickHouse/issues/63451): Fix `X-ClickHouse-Timezone` header returning wrong timezone when using `session_timezone` as query level setting. [#63377](https://github.com/ClickHouse/ClickHouse/pull/63377) ([Andrey Zvonov](https://github.com/zvonand)).
+* Backported in [#63605](https://github.com/ClickHouse/ClickHouse/issues/63605): Fix backup of projection part in case projection was removed from table metadata, but part still has projection. [#63426](https://github.com/ClickHouse/ClickHouse/pull/63426) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Backported in [#63510](https://github.com/ClickHouse/ClickHouse/issues/63510): Fix 'Every derived table must have its own alias' error for MYSQL dictionary source, close [#63341](https://github.com/ClickHouse/ClickHouse/issues/63341). [#63481](https://github.com/ClickHouse/ClickHouse/pull/63481) ([vdimir](https://github.com/vdimir)).
+* Backported in [#63592](https://github.com/ClickHouse/ClickHouse/issues/63592): Avoid segafult in `MergeTreePrefetchedReadPool` while fetching projection parts. [#63513](https://github.com/ClickHouse/ClickHouse/pull/63513) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#63750](https://github.com/ClickHouse/ClickHouse/issues/63750): Read only the necessary columns from VIEW (new analyzer). Closes [#62594](https://github.com/ClickHouse/ClickHouse/issues/62594). [#63688](https://github.com/ClickHouse/ClickHouse/pull/63688) ([Maksim Kita](https://github.com/kitaisreal)).
+* Backported in [#63772](https://github.com/ClickHouse/ClickHouse/issues/63772): Fix [#63539](https://github.com/ClickHouse/ClickHouse/issues/63539). Forbid WINDOW redefinition in new analyzer. [#63694](https://github.com/ClickHouse/ClickHouse/pull/63694) ([Dmitry Novik](https://github.com/novikd)).
+* Backported in [#63872](https://github.com/ClickHouse/ClickHouse/issues/63872): Flatten_nested is broken with replicated database. [#63695](https://github.com/ClickHouse/ClickHouse/pull/63695) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#63854](https://github.com/ClickHouse/ClickHouse/issues/63854): Fix `Not found column` and `CAST AS Map from array requires nested tuple of 2 elements` exceptions for distributed queries which use `Map(Nothing, Nothing)` type. Fixes [#63637](https://github.com/ClickHouse/ClickHouse/issues/63637). [#63753](https://github.com/ClickHouse/ClickHouse/pull/63753) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#63847](https://github.com/ClickHouse/ClickHouse/issues/63847): Fix possible `ILLEGAL_COLUMN` error in `partial_merge` join, close [#37928](https://github.com/ClickHouse/ClickHouse/issues/37928). [#63755](https://github.com/ClickHouse/ClickHouse/pull/63755) ([vdimir](https://github.com/vdimir)).
+* Backported in [#63908](https://github.com/ClickHouse/ClickHouse/issues/63908): `query_plan_remove_redundant_distinct` can break queries with WINDOW FUNCTIONS (with `allow_experimental_analyzer` is on). Fixes [#62820](https://github.com/ClickHouse/ClickHouse/issues/62820). [#63776](https://github.com/ClickHouse/ClickHouse/pull/63776) ([Igor Nikonov](https://github.com/devcrafter)).
+* Backported in [#63955](https://github.com/ClickHouse/ClickHouse/issues/63955): Fix possible crash with SYSTEM UNLOAD PRIMARY KEY. [#63778](https://github.com/ClickHouse/ClickHouse/pull/63778) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#63938](https://github.com/ClickHouse/ClickHouse/issues/63938): Allow JOIN filter push down to both streams if only single equivalent column is used in query. Closes [#63799](https://github.com/ClickHouse/ClickHouse/issues/63799). [#63819](https://github.com/ClickHouse/ClickHouse/pull/63819) ([Maksim Kita](https://github.com/kitaisreal)).
+* Backported in [#63991](https://github.com/ClickHouse/ClickHouse/issues/63991): Fix incorrect select query result when parallel replicas were used to read from a Materialized View. [#63861](https://github.com/ClickHouse/ClickHouse/pull/63861) ([Nikita Taranov](https://github.com/nickitat)).
+* Backported in [#64033](https://github.com/ClickHouse/ClickHouse/issues/64033): Fix a error `Database name is empty` for remote queries with lambdas over the cluster with modified default database. Fixes [#63471](https://github.com/ClickHouse/ClickHouse/issues/63471). [#63864](https://github.com/ClickHouse/ClickHouse/pull/63864) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#64561](https://github.com/ClickHouse/ClickHouse/issues/64561): Fix SIGSEGV due to CPU/Real (`query_profiler_real_time_period_ns`/`query_profiler_cpu_time_period_ns`) profiler (has been an issue since 2022, that leads to periodic server crashes, especially if you were using distributed engine). [#63865](https://github.com/ClickHouse/ClickHouse/pull/63865) ([Azat Khuzhin](https://github.com/azat)).
+* Backported in [#64011](https://github.com/ClickHouse/ClickHouse/issues/64011): Fix analyzer - IN function with arbitrary deep sub-selects in materialized view to use insertion block. [#63930](https://github.com/ClickHouse/ClickHouse/pull/63930) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Backported in [#64238](https://github.com/ClickHouse/ClickHouse/issues/64238): Fix resolve of unqualified COLUMNS matcher. Preserve the input columns order and forbid usage of unknown identifiers. [#63962](https://github.com/ClickHouse/ClickHouse/pull/63962) ([Dmitry Novik](https://github.com/novikd)).
+* Backported in [#64103](https://github.com/ClickHouse/ClickHouse/issues/64103): Deserialize untrusted binary inputs in a safer way. [#64024](https://github.com/ClickHouse/ClickHouse/pull/64024) ([Robert Schulze](https://github.com/rschu1ze)).
+* Backported in [#64170](https://github.com/ClickHouse/ClickHouse/issues/64170): Add missing settings to recoverLostReplica. [#64040](https://github.com/ClickHouse/ClickHouse/pull/64040) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#64322](https://github.com/ClickHouse/ClickHouse/issues/64322): This fix will use a proper redefined context with the correct definer for each individual view in the query pipeline Closes [#63777](https://github.com/ClickHouse/ClickHouse/issues/63777). [#64079](https://github.com/ClickHouse/ClickHouse/pull/64079) ([pufit](https://github.com/pufit)).
+* Backported in [#64382](https://github.com/ClickHouse/ClickHouse/issues/64382): Fix analyzer: "Not found column" error is fixed when using INTERPOLATE. [#64096](https://github.com/ClickHouse/ClickHouse/pull/64096) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Backported in [#64568](https://github.com/ClickHouse/ClickHouse/issues/64568): Fix creating backups to S3 buckets with different credentials from the disk containing the file. [#64153](https://github.com/ClickHouse/ClickHouse/pull/64153) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#64272](https://github.com/ClickHouse/ClickHouse/issues/64272): Prevent LOGICAL_ERROR on CREATE TABLE as MaterializedView. [#64174](https://github.com/ClickHouse/ClickHouse/pull/64174) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#64330](https://github.com/ClickHouse/ClickHouse/issues/64330): The query cache now considers two identical queries against different databases as different. The previous behavior could be used to bypass missing privileges to read from a table. [#64199](https://github.com/ClickHouse/ClickHouse/pull/64199) ([Robert Schulze](https://github.com/rschu1ze)).
+* Backported in [#64254](https://github.com/ClickHouse/ClickHouse/issues/64254): Ignore `text_log` config when using Keeper. [#64218](https://github.com/ClickHouse/ClickHouse/pull/64218) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#64690](https://github.com/ClickHouse/ClickHouse/issues/64690): Fix Query Tree size validation. Closes [#63701](https://github.com/ClickHouse/ClickHouse/issues/63701). [#64377](https://github.com/ClickHouse/ClickHouse/pull/64377) ([Dmitry Novik](https://github.com/novikd)).
+* Backported in [#64409](https://github.com/ClickHouse/ClickHouse/issues/64409): Fix `Logical error: Bad cast` for `Buffer` table with `PREWHERE`. Fixes [#64172](https://github.com/ClickHouse/ClickHouse/issues/64172). [#64388](https://github.com/ClickHouse/ClickHouse/pull/64388) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#64727](https://github.com/ClickHouse/ClickHouse/issues/64727): Fixed `CREATE TABLE AS` queries for tables with default expressions. [#64455](https://github.com/ClickHouse/ClickHouse/pull/64455) ([Anton Popov](https://github.com/CurtizJ)).
+* Backported in [#64623](https://github.com/ClickHouse/ClickHouse/issues/64623): Fix an error `Cannot find column` in distributed queries with constant CTE in the `GROUP BY` key. [#64519](https://github.com/ClickHouse/ClickHouse/pull/64519) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#64680](https://github.com/ClickHouse/ClickHouse/issues/64680): Fix [#64612](https://github.com/ClickHouse/ClickHouse/issues/64612). Do not rewrite aggregation if `-If` combinator is already used. [#64638](https://github.com/ClickHouse/ClickHouse/pull/64638) ([Dmitry Novik](https://github.com/novikd)).
+* Backported in [#64942](https://github.com/ClickHouse/ClickHouse/issues/64942): Fix OrderByLimitByDuplicateEliminationVisitor across subqueries. [#64766](https://github.com/ClickHouse/ClickHouse/pull/64766) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#64871](https://github.com/ClickHouse/ClickHouse/issues/64871): Fixed memory possible incorrect memory tracking in several kinds of queries: queries that read any data from S3, queries via http protocol, asynchronous inserts. [#64844](https://github.com/ClickHouse/ClickHouse/pull/64844) ([Anton Popov](https://github.com/CurtizJ)).
+
+#### CI Fix or Improvement (changelog entry is not required)
+
+* Backported in [#63364](https://github.com/ClickHouse/ClickHouse/issues/63364): Implement cumulative A Sync status. [#61464](https://github.com/ClickHouse/ClickHouse/pull/61464) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#63338](https://github.com/ClickHouse/ClickHouse/issues/63338): Use `/commit/` to have the URLs in [reports](https://play.clickhouse.com/play?user=play#c2VsZWN0IGRpc3RpbmN0IGNvbW1pdF91cmwgZnJvbSBjaGVja3Mgd2hlcmUgY2hlY2tfc3RhcnRfdGltZSA+PSBub3coKSAtIGludGVydmFsIDEgbW9udGggYW5kIHB1bGxfcmVxdWVzdF9udW1iZXI9NjA1MzI=) like https://github.com/ClickHouse/ClickHouse/commit/44f8bc5308b53797bec8cccc3bd29fab8a00235d and not like https://github.com/ClickHouse/ClickHouse/commits/44f8bc5308b53797bec8cccc3bd29fab8a00235d. [#63331](https://github.com/ClickHouse/ClickHouse/pull/63331) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#63376](https://github.com/ClickHouse/ClickHouse/issues/63376):. [#63366](https://github.com/ClickHouse/ClickHouse/pull/63366) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Backported in [#63571](https://github.com/ClickHouse/ClickHouse/issues/63571):. [#63551](https://github.com/ClickHouse/ClickHouse/pull/63551) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Backported in [#63651](https://github.com/ClickHouse/ClickHouse/issues/63651): Fix 02362_part_log_merge_algorithm flaky test. [#63635](https://github.com/ClickHouse/ClickHouse/pull/63635) ([Miсhael Stetsyuk](https://github.com/mstetsyuk)).
+* Backported in [#63828](https://github.com/ClickHouse/ClickHouse/issues/63828): Fix test_odbc_interaction from aarch64 [#61457](https://github.com/ClickHouse/ClickHouse/issues/61457). [#63787](https://github.com/ClickHouse/ClickHouse/pull/63787) ([alesapin](https://github.com/alesapin)).
+* Backported in [#63897](https://github.com/ClickHouse/ClickHouse/issues/63897): Fix test `test_catboost_evaluate` for aarch64. [#61457](https://github.com/ClickHouse/ClickHouse/issues/61457). [#63789](https://github.com/ClickHouse/ClickHouse/pull/63789) ([alesapin](https://github.com/alesapin)).
+* Backported in [#63889](https://github.com/ClickHouse/ClickHouse/issues/63889): Remove HDFS from disks config for one integration test for arm. [#61457](https://github.com/ClickHouse/ClickHouse/issues/61457). [#63832](https://github.com/ClickHouse/ClickHouse/pull/63832) ([alesapin](https://github.com/alesapin)).
+* Backported in [#63881](https://github.com/ClickHouse/ClickHouse/issues/63881): Bump version for old image in test_short_strings_aggregation to make it work on arm. [#61457](https://github.com/ClickHouse/ClickHouse/issues/61457). [#63836](https://github.com/ClickHouse/ClickHouse/pull/63836) ([alesapin](https://github.com/alesapin)).
+* Backported in [#63919](https://github.com/ClickHouse/ClickHouse/issues/63919): Disable test `test_non_default_compression/test.py::test_preconfigured_deflateqpl_codec` on arm. [#61457](https://github.com/ClickHouse/ClickHouse/issues/61457). [#63839](https://github.com/ClickHouse/ClickHouse/pull/63839) ([alesapin](https://github.com/alesapin)).
+* Backported in [#63971](https://github.com/ClickHouse/ClickHouse/issues/63971): Fix 02124_insert_deduplication_token_multiple_blocks. [#63950](https://github.com/ClickHouse/ClickHouse/pull/63950) ([Han Fei](https://github.com/hanfei1991)).
+* Backported in [#64049](https://github.com/ClickHouse/ClickHouse/issues/64049): Add `ClickHouseVersion.copy` method. Create a branch release in advance without spinning out the release to increase the stability. [#64039](https://github.com/ClickHouse/ClickHouse/pull/64039) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#64078](https://github.com/ClickHouse/ClickHouse/issues/64078): The mime type is not 100% reliable for Python and shell scripts without shebangs; add a check for file extension. [#64062](https://github.com/ClickHouse/ClickHouse/pull/64062) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+* Backported in [#64161](https://github.com/ClickHouse/ClickHouse/issues/64161): Add retries in git submodule update. [#64125](https://github.com/ClickHouse/ClickHouse/pull/64125) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### Critical Bug Fix (crash, LOGICAL_ERROR, data loss, RBAC)
+
+* Backported in [#64589](https://github.com/ClickHouse/ClickHouse/issues/64589): Disabled `enable_vertical_final` setting by default. This feature should not be used because it has a bug: [#64543](https://github.com/ClickHouse/ClickHouse/issues/64543). [#64544](https://github.com/ClickHouse/ClickHouse/pull/64544) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#64880](https://github.com/ClickHouse/ClickHouse/issues/64880): This PR fixes an error when a user in a specific situation can escalate their privileges on the default database without necessary grants. [#64769](https://github.com/ClickHouse/ClickHouse/pull/64769) ([pufit](https://github.com/pufit)).
+
+#### NO CL CATEGORY
+
+* Backported in [#63306](https://github.com/ClickHouse/ClickHouse/issues/63306):. [#63297](https://github.com/ClickHouse/ClickHouse/pull/63297) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Backported in [#63710](https://github.com/ClickHouse/ClickHouse/issues/63710):. [#63415](https://github.com/ClickHouse/ClickHouse/pull/63415) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+
+#### NO CL ENTRY
+
+* NO CL ENTRY: 'Revert "Backport [#64363](https://github.com/ClickHouse/ClickHouse/issues/64363) to 24.4: Split tests 03039_dynamic_all_merge_algorithms to avoid timeouts"'. [#64905](https://github.com/ClickHouse/ClickHouse/pull/64905) ([Raúl Marín](https://github.com/Algunenano)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* group_by_use_nulls strikes back [#62922](https://github.com/ClickHouse/ClickHouse/pull/62922) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Add `FROM` keyword to `TRUNCATE ALL TABLES` [#63241](https://github.com/ClickHouse/ClickHouse/pull/63241) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* More checks for concurrently deleted files and dirs in system.remote_data_paths [#63274](https://github.com/ClickHouse/ClickHouse/pull/63274) ([Alexander Gololobov](https://github.com/davenger)).
+* Try fix segfault in `MergeTreeReadPoolBase::createTask` [#63323](https://github.com/ClickHouse/ClickHouse/pull/63323) ([Antonio Andelic](https://github.com/antonio2368)).
+* Skip unaccessible table dirs in system.remote_data_paths [#63330](https://github.com/ClickHouse/ClickHouse/pull/63330) ([Alexander Gololobov](https://github.com/davenger)).
+* Workaround for `oklch()` inside canvas bug for firefox [#63404](https://github.com/ClickHouse/ClickHouse/pull/63404) ([Sergei Trifonov](https://github.com/serxa)).
+* Cancel S3 reads properly when parallel reads are used [#63687](https://github.com/ClickHouse/ClickHouse/pull/63687) ([Antonio Andelic](https://github.com/antonio2368)).
+* Userspace page cache: don't collect stats if cache is unused [#63730](https://github.com/ClickHouse/ClickHouse/pull/63730) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fix sanitizers [#64090](https://github.com/ClickHouse/ClickHouse/pull/64090) ([Azat Khuzhin](https://github.com/azat)).
+* Split tests 03039_dynamic_all_merge_algorithms to avoid timeouts [#64363](https://github.com/ClickHouse/ClickHouse/pull/64363) ([Kruglov Pavel](https://github.com/Avogar)).
+* CI: Critical bugfix category in PR template [#64480](https://github.com/ClickHouse/ClickHouse/pull/64480) ([Max K.](https://github.com/maxknv)).
+
diff --git a/docs/en/development/continuous-integration.md b/docs/en/development/continuous-integration.md
index c348eb5ca07..c283cfbf4c2 100644
--- a/docs/en/development/continuous-integration.md
+++ b/docs/en/development/continuous-integration.md
@@ -91,6 +91,9 @@ cd ./utils/check-style
# Check python type hinting with mypy
./check-mypy
+# Check python with flake8
+./check-flake8
+
# Check code with codespell
./check-typos
diff --git a/docs/en/engines/table-engines/integrations/azureBlobStorage.md b/docs/en/engines/table-engines/integrations/azureBlobStorage.md
index 0843ff1ac47..dfc27d6b8cf 100644
--- a/docs/en/engines/table-engines/integrations/azureBlobStorage.md
+++ b/docs/en/engines/table-engines/integrations/azureBlobStorage.md
@@ -54,6 +54,7 @@ SELECT * FROM test_table;
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## See also
diff --git a/docs/en/engines/table-engines/integrations/hdfs.md b/docs/en/engines/table-engines/integrations/hdfs.md
index 2749fa7e479..c9df713231a 100644
--- a/docs/en/engines/table-engines/integrations/hdfs.md
+++ b/docs/en/engines/table-engines/integrations/hdfs.md
@@ -235,6 +235,7 @@ libhdfs3 support HDFS namenode HA.
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Storage Settings {#storage-settings}
diff --git a/docs/en/engines/table-engines/integrations/s3.md b/docs/en/engines/table-engines/integrations/s3.md
index cb1da1c8e68..93f4a187656 100644
--- a/docs/en/engines/table-engines/integrations/s3.md
+++ b/docs/en/engines/table-engines/integrations/s3.md
@@ -53,14 +53,14 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
This example uses the [docker compose recipe](https://github.com/ClickHouse/examples/tree/5fdc6ff72f4e5137e23ea075c88d3f44b0202490/docker-compose-recipes/recipes/ch-and-minio-S3), which integrates ClickHouse and MinIO. You should be able to reproduce the same queries using S3 by replacing the endpoint and authentication values.
-Notice that the S3 endpoint in the `ENGINE` configuration uses the parameter token `{_partition_id}` as part of the S3 object (filename), and that the SELECT queries select against those resulting object names (e.g., `test_3.csv`).
+Notice that the S3 endpoint in the `ENGINE` configuration uses the parameter token `{_partition_id}` as part of the S3 object (filename), and that the SELECT queries select against those resulting object names (e.g., `test_3.csv`).
:::note
As shown in the example, querying from S3 tables that are partitioned is
not directly supported at this time, but can be accomplished by querying the individual partitions
using the S3 table function.
-The primary use-case for writing
+The primary use-case for writing
partitioned data in S3 is to enable transferring that data into another
ClickHouse system (for example, moving from on-prem systems to ClickHouse
Cloud). Because ClickHouse datasets are often very large, and network
@@ -78,9 +78,9 @@ CREATE TABLE p
)
ENGINE = S3(
# highlight-next-line
- 'http://minio:10000/clickhouse//test_{_partition_id}.csv',
- 'minioadmin',
- 'minioadminpassword',
+ 'http://minio:10000/clickhouse//test_{_partition_id}.csv',
+ 'minioadmin',
+ 'minioadminpassword',
'CSV')
PARTITION BY column3
```
@@ -145,6 +145,7 @@ Code: 48. DB::Exception: Received from localhost:9000. DB::Exception: Reading fr
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
For more information about virtual columns see [here](../../../engines/table-engines/index.md#table_engines-virtual_columns).
diff --git a/docs/en/engines/table-engines/integrations/s3queue.md b/docs/en/engines/table-engines/integrations/s3queue.md
index aa7fa512480..f930fab1805 100644
--- a/docs/en/engines/table-engines/integrations/s3queue.md
+++ b/docs/en/engines/table-engines/integrations/s3queue.md
@@ -267,7 +267,7 @@ For introspection use `system.s3queue` stateless table and `system.s3queue_log`
`exception` String
)
ENGINE = SystemS3Queue
-COMMENT 'SYSTEM TABLE is built on the fly.' │
+COMMENT 'Contains in-memory state of S3Queue metadata and currently processed rows per file.' │
└────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```
diff --git a/docs/en/engines/table-engines/mergetree-family/mergetree.md b/docs/en/engines/table-engines/mergetree-family/mergetree.md
index 803b753fe0a..f0c4e1b0e34 100644
--- a/docs/en/engines/table-engines/mergetree-family/mergetree.md
+++ b/docs/en/engines/table-engines/mergetree-family/mergetree.md
@@ -6,35 +6,26 @@ sidebar_label: MergeTree
# MergeTree
-The `MergeTree` engine and other engines of this family (`*MergeTree`) are the most commonly used and most robust ClickHouse table engines.
+The `MergeTree` engine and other engines of the `MergeTree` family (e.g. `ReplacingMergeTree`, `AggregatingMergeTree` ) are the most commonly used and most robust table engines in ClickHouse.
-Engines in the `MergeTree` family are designed for inserting a very large amount of data into a table. The data is quickly written to the table part by part, then rules are applied for merging the parts in the background. This method is much more efficient than continually rewriting the data in storage during insert.
+`MergeTree`-family table engines are designed for high data ingest rates and huge data volumes.
+Insert operations create table parts which are merged by a background process with other table parts.
-Main features:
+Main features of `MergeTree`-family table engines.
-- Stores data sorted by primary key.
+- The table's primary key determines the sort order within each table part (clustered index). The primary key also does not reference individual rows but blocks of 8192 rows called granules. This makes primary keys of huge data sets small enough to remain loaded in main memory, while still providing fast access to on-disk data.
- This allows you to create a small sparse index that helps find data faster.
+- Tables can be partitioned using an arbitrary partition expression. Partition pruning ensures partitions are omitted from reading when the query allows it.
-- Partitions can be used if the [partitioning key](/docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md) is specified.
+- Data can be replicated across multiple cluster nodes for high availability, failover, and zero downtime upgrades. See [Data replication](/docs/en/engines/table-engines/mergetree-family/replication.md).
- ClickHouse supports certain operations with partitions that are more efficient than general operations on the same data with the same result. ClickHouse also automatically cuts off the partition data where the partitioning key is specified in the query.
+- `MergeTree` table engines support various statistics kinds and sampling methods to help query optimization.
-- Data replication support.
-
- The family of `ReplicatedMergeTree` tables provides data replication. For more information, see [Data replication](/docs/en/engines/table-engines/mergetree-family/replication.md).
-
-- Data sampling support.
-
- If necessary, you can set the data sampling method in the table.
-
-:::info
-The [Merge](/docs/en/engines/table-engines/special/merge.md/#merge) engine does not belong to the `*MergeTree` family.
+:::note
+Despite a similar name, the [Merge](/docs/en/engines/table-engines/special/merge.md/#merge) engine is different from `*MergeTree` engines.
:::
-If you need to update rows frequently, we recommend using the [`ReplacingMergeTree`](/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md) table engine. Using `ALTER TABLE my_table UPDATE` to update rows triggers a mutation, which causes parts to be re-written and uses IO/resources. With `ReplacingMergeTree`, you can simply insert the updated rows and the old rows will be replaced according to the table sorting key.
-
-## Creating a Table {#table_engine-mergetree-creating-a-table}
+## Creating Tables {#table_engine-mergetree-creating-a-table}
``` sql
CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
@@ -59,23 +50,24 @@ ORDER BY expr
[SETTINGS name = value, ...]
```
-For a description of parameters, see the [CREATE query description](/docs/en/sql-reference/statements/create/table.md).
+For a detailed description of the parameters, see the [CREATE TABLE](/docs/en/sql-reference/statements/create/table.md) statement
### Query Clauses {#mergetree-query-clauses}
#### ENGINE
-`ENGINE` — Name and parameters of the engine. `ENGINE = MergeTree()`. The `MergeTree` engine does not have parameters.
+`ENGINE` — Name and parameters of the engine. `ENGINE = MergeTree()`. The `MergeTree` engine has no parameters.
#### ORDER_BY
`ORDER BY` — The sorting key.
-A tuple of column names or arbitrary expressions. Example: `ORDER BY (CounterID, EventDate)`.
+A tuple of column names or arbitrary expressions. Example: `ORDER BY (CounterID + 1, EventDate)`.
-ClickHouse uses the sorting key as a primary key if the primary key is not defined explicitly by the `PRIMARY KEY` clause.
+If no primary key is defined (i.e. `PRIMARY KEY` was not specified), ClickHouse uses the the sorting key as primary key.
-Use the `ORDER BY tuple()` syntax, if you do not need sorting, or set `create_table_empty_primary_key_by_default` to `true` to use the `ORDER BY tuple()` syntax by default. See [Selecting the Primary Key](#selecting-the-primary-key).
+If no sorting is required, you can use syntax `ORDER BY tuple()`.
+Alternatively, if setting `create_table_empty_primary_key_by_default` is enabled, `ORDER BY tuple()` is implicitly added to `CREATE TABLE` statements. See [Selecting a Primary Key](#selecting-a-primary-key).
#### PARTITION BY
@@ -87,100 +79,32 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
`PRIMARY KEY` — The primary key if it [differs from the sorting key](#choosing-a-primary-key-that-differs-from-the-sorting-key). Optional.
-By default the primary key is the same as the sorting key (which is specified by the `ORDER BY` clause). Thus in most cases it is unnecessary to specify a separate `PRIMARY KEY` clause.
+Specifying a sorting key (using `ORDER BY` clause) implicitly specifies a primary key.
+It is usually not necessary to specify the primary key in addition to the primary key.
#### SAMPLE BY
-`SAMPLE BY` — An expression for sampling. Optional.
+`SAMPLE BY` — A sampling expression. Optional.
-If a sampling expression is used, the primary key must contain it. The result of a sampling expression must be an unsigned integer. Example: `SAMPLE BY intHash32(UserID) ORDER BY (CounterID, EventDate, intHash32(UserID))`.
+If specified, it must be contained in the primary key.
+The sampling expression must result in an unsigned integer.
+
+Example: `SAMPLE BY intHash32(UserID) ORDER BY (CounterID, EventDate, intHash32(UserID))`.
#### TTL
-`TTL` — A list of rules specifying storage duration of rows and defining logic of automatic parts movement [between disks and volumes](#table_engine-mergetree-multiple-volumes). Optional.
+`TTL` — A list of rules that specify the storage duration of rows and the logic of automatic parts movement [between disks and volumes](#table_engine-mergetree-multiple-volumes). Optional.
-Expression must have one `Date` or `DateTime` column as a result. Example:
-```
-TTL date + INTERVAL 1 DAY
-```
+Expression must result in a `Date` or `DateTime`, e.g. `TTL date + INTERVAL 1 DAY`.
Type of the rule `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'|GROUP BY` specifies an action to be done with the part if the expression is satisfied (reaches current time): removal of expired rows, moving a part (if expression is satisfied for all rows in a part) to specified disk (`TO DISK 'xxx'`) or to volume (`TO VOLUME 'xxx'`), or aggregating values in expired rows. Default type of the rule is removal (`DELETE`). List of multiple rules can be specified, but there should be no more than one `DELETE` rule.
+
For more details, see [TTL for columns and tables](#table_engine-mergetree-ttl)
-### SETTINGS
-Additional parameters that control the behavior of the `MergeTree` (optional):
+#### SETTINGS
-#### index_granularity
-
-`index_granularity` — Maximum number of data rows between the marks of an index. Default value: 8192. See [Data Storage](#mergetree-data-storage).
-
-#### index_granularity_bytes
-
-`index_granularity_bytes` — Maximum size of data granules in bytes. Default value: 10Mb. To restrict the granule size only by number of rows, set to 0 (not recommended). See [Data Storage](#mergetree-data-storage).
-
-#### min_index_granularity_bytes
-
-`min_index_granularity_bytes` — Min allowed size of data granules in bytes. Default value: 1024b. To provide a safeguard against accidentally creating tables with very low index_granularity_bytes. See [Data Storage](#mergetree-data-storage).
-
-#### enable_mixed_granularity_parts
-
-`enable_mixed_granularity_parts` — Enables or disables transitioning to control the granule size with the `index_granularity_bytes` setting. Before version 19.11, there was only the `index_granularity` setting for restricting granule size. The `index_granularity_bytes` setting improves ClickHouse performance when selecting data from tables with big rows (tens and hundreds of megabytes). If you have tables with big rows, you can enable this setting for the tables to improve the efficiency of `SELECT` queries.
-
-#### use_minimalistic_part_header_in_zookeeper
-
-`use_minimalistic_part_header_in_zookeeper` — Storage method of the data parts headers in ZooKeeper. If `use_minimalistic_part_header_in_zookeeper=1`, then ZooKeeper stores less data. For more information, see the [setting description](/docs/en/operations/server-configuration-parameters/settings.md/#server-settings-use_minimalistic_part_header_in_zookeeper) in “Server configuration parameters”.
-
-#### min_merge_bytes_to_use_direct_io
-
-`min_merge_bytes_to_use_direct_io` — The minimum data volume for merge operation that is required for using direct I/O access to the storage disk. When merging data parts, ClickHouse calculates the total storage volume of all the data to be merged. If the volume exceeds `min_merge_bytes_to_use_direct_io` bytes, ClickHouse reads and writes the data to the storage disk using the direct I/O interface (`O_DIRECT` option). If `min_merge_bytes_to_use_direct_io = 0`, then direct I/O is disabled. Default value: `10 * 1024 * 1024 * 1024` bytes.
-
-#### merge_with_ttl_timeout
-
-`merge_with_ttl_timeout` — Minimum delay in seconds before repeating a merge with delete TTL. Default value: `14400` seconds (4 hours).
-#### merge_with_recompression_ttl_timeout
-
-`merge_with_recompression_ttl_timeout` — Minimum delay in seconds before repeating a merge with recompression TTL. Default value: `14400` seconds (4 hours).
-
-#### try_fetch_recompressed_part_timeout
-
-`try_fetch_recompressed_part_timeout` — Timeout (in seconds) before starting merge with recompression. During this time ClickHouse tries to fetch recompressed part from replica which assigned this merge with recompression. Default value: `7200` seconds (2 hours).
-
-#### write_final_mark
-
-`write_final_mark` — Enables or disables writing the final index mark at the end of data part (after the last byte). Default value: 1. Don’t turn it off.
-
-#### merge_max_block_size
-
-`merge_max_block_size` — Maximum number of rows in block for merge operations. Default value: 8192.
-
-#### storage_policy
-
-`storage_policy` — Storage policy. See [Using Multiple Block Devices for Data Storage](#table_engine-mergetree-multiple-volumes).
-
-#### min_bytes_for_wide_part
-
-`min_bytes_for_wide_part`, `min_rows_for_wide_part` — Minimum number of bytes/rows in a data part that can be stored in `Wide` format. You can set one, both or none of these settings. See [Data Storage](#mergetree-data-storage).
-
-#### max_parts_in_total
-
-`max_parts_in_total` — Maximum number of parts in all partitions.
-
-#### max_compress_block_size
-
-`max_compress_block_size` — Maximum size of blocks of uncompressed data before compressing for writing to a table. You can also specify this setting in the global settings (see [max_compress_block_size](/docs/en/operations/settings/settings.md/#max-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
-
-#### min_compress_block_size
-
-`min_compress_block_size` — Minimum size of blocks of uncompressed data required for compression when writing the next mark. You can also specify this setting in the global settings (see [min_compress_block_size](/docs/en/operations/settings/settings.md/#min-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
-
-#### max_partitions_to_read
-
-`max_partitions_to_read` — Limits the maximum number of partitions that can be accessed in one query. You can also specify setting [max_partitions_to_read](/docs/en/operations/settings/merge-tree-settings.md/#max-partitions-to-read) in the global setting.
-
-#### allow_experimental_optimized_row_order
-
-`allow_experimental_optimized_row_order` - Experimental. Enables the optimization of the row order during inserts to improve the compressability of the data for compression codecs (e.g. LZ4). Analyzes and reorders the data, and thus increases the CPU overhead of inserts.
+See [MergeTree Settings](../../../operations/settings/merge-tree-settings.md).
**Example of Sections Setting**
@@ -270,7 +194,7 @@ ClickHouse does not require a unique primary key. You can insert multiple rows w
You can use `Nullable`-typed expressions in the `PRIMARY KEY` and `ORDER BY` clauses but it is strongly discouraged. To allow this feature, turn on the [allow_nullable_key](/docs/en/operations/settings/settings.md/#allow-nullable-key) setting. The [NULLS_LAST](/docs/en/sql-reference/statements/select/order-by.md/#sorting-of-special-values) principle applies for `NULL` values in the `ORDER BY` clause.
-### Selecting the Primary Key {#selecting-the-primary-key}
+### Selecting a Primary Key {#selecting-a-primary-key}
The number of columns in the primary key is not explicitly limited. Depending on the data structure, you can include more or fewer columns in the primary key. This may:
diff --git a/docs/en/engines/table-engines/special/file.md b/docs/en/engines/table-engines/special/file.md
index 0d422f64762..957b18b5305 100644
--- a/docs/en/engines/table-engines/special/file.md
+++ b/docs/en/engines/table-engines/special/file.md
@@ -102,6 +102,7 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Settings {#settings}
diff --git a/docs/en/engines/table-engines/special/url.md b/docs/en/engines/table-engines/special/url.md
index f6183a779ae..c906830d0e9 100644
--- a/docs/en/engines/table-engines/special/url.md
+++ b/docs/en/engines/table-engines/special/url.md
@@ -108,6 +108,7 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
- `_path` — Path to the `URL`. Type: `LowCardinalty(String)`.
- `_file` — Resource name of the `URL`. Type: `LowCardinalty(String)`.
- `_size` — Size of the resource in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Storage Settings {#storage-settings}
diff --git a/docs/en/operations/analyzer.md b/docs/en/operations/analyzer.md
new file mode 100644
index 00000000000..298c6dacd06
--- /dev/null
+++ b/docs/en/operations/analyzer.md
@@ -0,0 +1,194 @@
+---
+slug: /en/operations/analyzer
+sidebar_label: Analyzer
+title: Analyzer
+description: Details about ClickHouse's query analyzer
+keywords: [analyzer]
+---
+
+# Analyzer
+
+
+
+## Known incompatibilities
+
+In ClickHouse version `24.3`, the new query analyzer was enabled by default.
+Despite fixing a large number of bugs and introducing new optimizations, it also introduces some breaking changes in ClickHouse behaviour. Please read the following changes to determine how to rewrite your queries for the new analyzer.
+
+### Invalid queries are no longer optimized
+
+The previous query planning infrastructure applied AST-level optimizations before the query validation step.
+Optimizations could rewrite the initial query so it becomes valid and can be executed.
+
+In the new analyzer, query validation takes place before the optimization step.
+This means that invalid queries that were possible to execute before are now unsupported.
+In such cases, the query must be fixed manually.
+
+**Example 1:**
+
+```sql
+SELECT number
+FROM numbers(1)
+GROUP BY toString(number)
+```
+
+The following query uses column `number` in the projection list when only `toString(number)` is available after the aggregation.
+In the old analyzer, `GROUP BY toString(number)` was optimized into `GROUP BY number,` making the query valid.
+
+**Example 2:**
+
+```sql
+SELECT
+ number % 2 AS n,
+ sum(number)
+FROM numbers(10)
+GROUP BY n
+HAVING number > 5
+```
+
+The same problem occurs in this query: column `number` is used after aggregation with another key.
+The previous query analyzer fixed this query by moving the `number > 5` filter from the `HAVING` clause to the `WHERE` clause.
+
+To fix the query, you should move all conditions that apply to non-aggregated columns to the `WHERE` section to conform to standard SQL syntax:
+```sql
+SELECT
+ number % 2 AS n,
+ sum(number)
+FROM numbers(10)
+WHERE number > 5
+GROUP BY n
+```
+
+### CREATE VIEW with invalid query
+
+The new analyzer always performs type-checking.
+Previously, it was possible to create a `VIEW` with an invalid `SELECT` query. It would then fail during the first `SELECT` or `INSERT` (in the case of `MATERIALIZED VIEW`).
+
+Now, it's not possible to create such `VIEW`s anymore.
+
+**Example:**
+
+```sql
+CREATE TABLE source (data String) ENGINE=MergeTree ORDER BY tuple();
+
+CREATE VIEW some_view
+AS SELECT JSONExtract(data, 'test', 'DateTime64(3)')
+FROM source;
+```
+
+### Known incompatibilities of the `JOIN` clause
+
+#### Join using column from projection
+
+Alias from the `SELECT` list can not be used as a `JOIN USING` key by default.
+
+A new setting, `analyzer_compatibility_join_using_top_level_identifier`, when enabled, alters the behavior of `JOIN USING` to prefer to resolve identifiers based on expressions from the projection list of the `SELECT` query, rather than using the columns from left table directly.
+
+**Example:**
+
+```sql
+SELECT a + 1 AS b, t2.s
+FROM Values('a UInt64, b UInt64', (1, 1)) AS t1
+JOIN Values('b UInt64, s String', (1, 'one'), (2, 'two')) t2
+USING (b);
+```
+
+With `analyzer_compatibility_join_using_top_level_identifier` set to `true`, the join condition is interpreted as `t1.a + 1 = t2.b`, matching the behavior of earlier versions. So, the result will be `2, 'two'`.
+When the setting is `false`, the join condition defaults to `t1.b = t2.b`, and the query will return `2, 'one'`.
+If `b` is not present in `t1`, the query will fail with an error.
+
+#### Changes in behavior with `JOIN USING` and `ALIAS`/`MATERIALIZED` columns
+
+In the new analyzer, using `*` in a `JOIN USING` query that involves `ALIAS` or `MATERIALIZED` columns will include those columns in the result set by default.
+
+**Example:**
+
+```sql
+CREATE TABLE t1 (id UInt64, payload ALIAS sipHash64(id)) ENGINE = MergeTree ORDER BY id;
+INSERT INTO t1 VALUES (1), (2);
+
+CREATE TABLE t2 (id UInt64, payload ALIAS sipHash64(id)) ENGINE = MergeTree ORDER BY id;
+INSERT INTO t2 VALUES (2), (3);
+
+SELECT * FROM t1
+FULL JOIN t2 USING (payload);
+```
+
+In the new analyzer, the result of this query will include the `payload` column along with `id` from both tables. In contrast, the previous analyzer would only include these `ALIAS` columns if specific settings (`asterisk_include_alias_columns` or `asterisk_include_materialized_columns`) were enabled, and the columns might appear in a different order.
+
+To ensure consistent and expected results, especially when migrating old queries to the new analyzer, it is advisable to specify columns explicitly in the `SELECT` clause rather than using `*`.
+
+#### Handling of Type Modifiers for columns in `USING` Clause
+
+In the new version of the analyzer, the rules for determining the common supertype for columns specified in the `USING` clause have been standardized to produce more predictable outcomes, especially when dealing with type modifiers like `LowCardinality` and `Nullable`.
+
+- `LowCardinality(T)` and `T`: When a column of type `LowCardinality(T)` is joined with a column of type `T`, the resulting common supertype will be `T`, effectively discarding the `LowCardinality` modifier.
+
+- `Nullable(T)` and `T`: When a column of type `Nullable(T)` is joined with a column of type `T`, the resulting common supertype will be `Nullable(T)`, ensuring that the nullable property is preserved.
+
+**Example:**
+
+```sql
+SELECT id, toTypeName(id) FROM Values('id LowCardinality(String)', ('a')) AS t1
+FULL OUTER JOIN Values('id String', ('b')) AS t2
+USING (id);
+```
+
+In this query, the common supertype for `id` is determined as `String`, discarding the `LowCardinality` modifier from `t1`.
+
+### Projection column names changes
+
+During projection names computation, aliases are not substituted.
+
+```sql
+SELECT
+ 1 + 1 AS x,
+ x + 1
+SETTINGS allow_experimental_analyzer = 0
+FORMAT PrettyCompact
+
+ ┌─x─┬─plus(plus(1, 1), 1)─┐
+1. │ 2 │ 3 │
+ └───┴─────────────────────┘
+
+SELECT
+ 1 + 1 AS x,
+ x + 1
+SETTINGS allow_experimental_analyzer = 1
+FORMAT PrettyCompact
+
+ ┌─x─┬─plus(x, 1)─┐
+1. │ 2 │ 3 │
+ └───┴────────────┘
+```
+
+### Incompatible function arguments types
+
+In the new analyzer, type inference happens during initial query analysis.
+This change means that type checks are done before short-circuit evaluation; thus, `if` function arguments must always have a common supertype.
+
+**Example:**
+
+The following query fails with `There is no supertype for types Array(UInt8), String because some of them are Array and some of them are not`:
+
+```sql
+SELECT toTypeName(if(0, [2, 3, 4], 'String'))
+```
+
+### Heterogeneous clusters
+
+The new analyzer significantly changed the communication protocol between servers in the cluster. Thus, it's impossible to run distributed queries on servers with different `allow_experimental_analyzer` setting values.
+
+### Mutations are interpreted by previous analyzer
+
+Mutations are still using the old analyzer.
+This means some new ClickHouse SQL features can't be used in mutations. For example, the `QUALIFY` clause.
+Status can be checked [here](https://github.com/ClickHouse/ClickHouse/issues/61563).
+
+### Unsupported features
+
+The list of features new analyzer currently doesn't support:
+
+- Annoy index.
+- Hypothesis index. Work in progress [here](https://github.com/ClickHouse/ClickHouse/pull/48381).
+- Window view is not supported. There are no plans to support it in the future.
diff --git a/docs/en/operations/named-collections.md b/docs/en/operations/named-collections.md
index c9d94dd95ee..1d261d935af 100644
--- a/docs/en/operations/named-collections.md
+++ b/docs/en/operations/named-collections.md
@@ -443,3 +443,59 @@ SELECT dictGet('dict', 'b', 1);
│ a │
└─────────────────────────┘
```
+
+## Named collections for accessing Kafka
+
+The description of parameters see [Kafka](../engines/table-engines/integrations/kafka.md).
+
+### DDL example
+
+```sql
+CREATE NAMED COLLECTION my_kafka_cluster AS
+kafka_broker_list = 'localhost:9092',
+kafka_topic_list = 'kafka_topic',
+kafka_group_name = 'consumer_group',
+kafka_format = 'JSONEachRow',
+kafka_max_block_size = '1048576';
+
+```
+### XML example
+
+```xml
+
+
+
+ localhost:9092
+ kafka_topic
+ consumer_group
+ JSONEachRow
+ 1048576
+
+
+
+```
+
+### Example of using named collections with a Kafka table
+
+Both of the following examples use the same named collection `my_kafka_cluster`:
+
+
+```sql
+CREATE TABLE queue
+(
+ timestamp UInt64,
+ level String,
+ message String
+)
+ENGINE = Kafka(my_kafka_cluster)
+
+CREATE TABLE queue
+(
+ timestamp UInt64,
+ level String,
+ message String
+)
+ENGINE = Kafka(my_kafka_cluster)
+SETTINGS kafka_num_consumers = 4,
+ kafka_thread_per_consumer = 1;
+```
diff --git a/docs/en/operations/settings/merge-tree-settings.md b/docs/en/operations/settings/merge-tree-settings.md
index c3f303dcd38..d791683ac2b 100644
--- a/docs/en/operations/settings/merge-tree-settings.md
+++ b/docs/en/operations/settings/merge-tree-settings.md
@@ -3,9 +3,126 @@ slug: /en/operations/settings/merge-tree-settings
title: "MergeTree tables settings"
---
-The values of `merge_tree` settings (for all MergeTree tables) can be viewed in the table `system.merge_tree_settings`, they can be overridden in `config.xml` in the `merge_tree` section, or set in the `SETTINGS` section of each table.
+System table `system.merge_tree_settings` shows the globally set MergeTree settings.
-These are example overrides for `max_suspicious_broken_parts`:
+MergeTree settings can be set in the `merge_tree` section of the server config file, or specified for each `MergeTree` table individually in
+the `SETTINGS` clause of the `CREATE TABLE` statement.
+
+Example for customizing setting `max_suspicious_broken_parts`:
+
+Configure the default for all `MergeTree` tables in the server configuration file:
+
+``` text
+
+ 5
+
+```
+
+Set for a particular table:
+
+``` sql
+CREATE TABLE tab
+(
+ `A` Int64
+)
+ENGINE = MergeTree
+ORDER BY tuple()
+SETTINGS max_suspicious_broken_parts = 500;
+```
+
+Change the settings for a particular table using `ALTER TABLE ... MODIFY SETTING`:
+
+```sql
+ALTER TABLE tab MODIFY SETTING max_suspicious_broken_parts = 100;
+
+-- reset to global default (value from system.merge_tree_settings)
+ALTER TABLE tab RESET SETTING max_suspicious_broken_parts;
+```
+
+## index_granularity
+
+Maximum number of data rows between the marks of an index.
+
+Default value: 8192.
+
+## index_granularity_bytes
+
+Maximum size of data granules in bytes.
+
+Default value: 10Mb.
+
+To restrict the granule size only by number of rows, set to 0 (not recommended).
+
+## min_index_granularity_bytes
+
+Min allowed size of data granules in bytes.
+
+Default value: 1024b.
+
+To provide a safeguard against accidentally creating tables with very low index_granularity_bytes.
+
+## enable_mixed_granularity_parts
+
+Enables or disables transitioning to control the granule size with the `index_granularity_bytes` setting. Before version 19.11, there was only the `index_granularity` setting for restricting granule size. The `index_granularity_bytes` setting improves ClickHouse performance when selecting data from tables with big rows (tens and hundreds of megabytes). If you have tables with big rows, you can enable this setting for the tables to improve the efficiency of `SELECT` queries.
+
+## use_minimalistic_part_header_in_zookeeper
+
+Storage method of the data parts headers in ZooKeeper. If enabled, ZooKeeper stores less data. For details, see [here](../server-configuration-parameters/settings.md/#server-settings-use_minimalistic_part_header_in_zookeeper).
+
+## min_merge_bytes_to_use_direct_io
+
+The minimum data volume for merge operation that is required for using direct I/O access to the storage disk.
+When merging data parts, ClickHouse calculates the total storage volume of all the data to be merged.
+If the volume exceeds `min_merge_bytes_to_use_direct_io` bytes, ClickHouse reads and writes the data to the storage disk using the direct I/O interface (`O_DIRECT` option).
+If `min_merge_bytes_to_use_direct_io = 0`, then direct I/O is disabled.
+
+Default value: `10 * 1024 * 1024 * 1024` bytes.
+
+## merge_with_ttl_timeout
+
+Minimum delay in seconds before repeating a merge with delete TTL.
+
+Default value: `14400` seconds (4 hours).
+
+## merge_with_recompression_ttl_timeout
+
+Minimum delay in seconds before repeating a merge with recompression TTL.
+
+Default value: `14400` seconds (4 hours).
+
+## write_final_mark
+
+Enables or disables writing the final index mark at the end of data part (after the last byte).
+
+Default value: 1.
+
+Don’t change or bad things will happen.
+
+## storage_policy
+
+Storage policy.
+
+## min_bytes_for_wide_part
+
+Minimum number of bytes/rows in a data part that can be stored in `Wide` format.
+You can set one, both or none of these settings.
+
+## max_compress_block_size
+
+Maximum size of blocks of uncompressed data before compressing for writing to a table.
+You can also specify this setting in the global settings (see [max_compress_block_size](/docs/en/operations/settings/settings.md/#max-compress-block-size) setting).
+The value specified when table is created overrides the global value for this setting.
+
+## min_compress_block_size
+
+Minimum size of blocks of uncompressed data required for compression when writing the next mark.
+You can also specify this setting in the global settings (see [min_compress_block_size](/docs/en/operations/settings/settings.md/#min-compress-block-size) setting).
+The value specified when table is created overrides the global value for this setting.
+
+## max_partitions_to_read
+
+Limits the maximum number of partitions that can be accessed in one query.
+You can also specify setting [max_partitions_to_read](/docs/en/operations/settings/merge-tree-settings.md/#max-partitions-to-read) in the global setting.
## max_suspicious_broken_parts
@@ -17,37 +134,6 @@ Possible values:
Default value: 100.
-Override example in `config.xml`:
-
-``` text
-
- 5
-
-```
-
-An example to set in `SETTINGS` for a particular table:
-
-``` sql
-CREATE TABLE foo
-(
- `A` Int64
-)
-ENGINE = MergeTree
-ORDER BY tuple()
-SETTINGS max_suspicious_broken_parts = 500;
-```
-
-An example of changing the settings for a specific table with the `ALTER TABLE ... MODIFY SETTING` command:
-
-``` sql
-ALTER TABLE foo
- MODIFY SETTING max_suspicious_broken_parts = 100;
-
--- reset to default (use value from system.merge_tree_settings)
-ALTER TABLE foo
- RESET SETTING max_suspicious_broken_parts;
-```
-
## parts_to_throw_insert {#parts-to-throw-insert}
If the number of active parts in a single partition exceeds the `parts_to_throw_insert` value, `INSERT` is interrupted with the `Too many parts (N). Merges are processing significantly slower than inserts` exception.
@@ -301,6 +387,8 @@ Default value: 10800
## try_fetch_recompressed_part_timeout
+Timeout (in seconds) before starting merge with recompression. During this time ClickHouse tries to fetch recompressed part from replica which assigned this merge with recompression.
+
Recompression works slow in most cases, so we don't start merge with recompression until this timeout and trying to fetch recompressed part from replica which assigned this merge with recompression.
Possible values:
diff --git a/docs/en/operations/settings/settings.md b/docs/en/operations/settings/settings.md
index ffaf53085c4..79d0ca4f151 100644
--- a/docs/en/operations/settings/settings.md
+++ b/docs/en/operations/settings/settings.md
@@ -1590,6 +1590,22 @@ Possible values:
Default value: `default`.
+## parallel_replicas_custom_key_range_lower {#parallel_replicas_custom_key_range_lower}
+
+Allows the filter type `range` to split the work evenly between replicas based on the custom range `[parallel_replicas_custom_key_range_lower, INT_MAX]`.
+
+When used in conjuction with [parallel_replicas_custom_key_range_upper](#parallel_replicas_custom_key_range_upper), it lets the filter evenly split the work over replicas for the range `[parallel_replicas_custom_key_range_lower, parallel_replicas_custom_key_range_upper]`.
+
+Note: This setting will not cause any additional data to be filtered during query processing, rather it changes the points at which the range filter breaks up the range `[0, INT_MAX]` for parallel processing.
+
+## parallel_replicas_custom_key_range_upper {#parallel_replicas_custom_key_range_upper}
+
+Allows the filter type `range` to split the work evenly between replicas based on the custom range `[0, parallel_replicas_custom_key_range_upper]`. A value of 0 disables the upper bound, setting it the max value of the custom key expression.
+
+When used in conjuction with [parallel_replicas_custom_key_range_lower](#parallel_replicas_custom_key_range_lower), it lets the filter evenly split the work over replicas for the range `[parallel_replicas_custom_key_range_lower, parallel_replicas_custom_key_range_upper]`.
+
+Note: This setting will not cause any additional data to be filtered during query processing, rather it changes the points at which the range filter breaks up the range `[0, INT_MAX]` for parallel processing.
+
## allow_experimental_parallel_reading_from_replicas
Enables or disables sending SELECT queries to all replicas of a table (up to `max_parallel_replicas`). Reading is parallelized and coordinated dynamically. It will work for any kind of MergeTree table.
@@ -3862,6 +3878,10 @@ Possible values:
Default value: 30.
+:::note
+It's applicable only to the default profile. A server reboot is required for the changes to take effect.
+:::
+
## http_receive_timeout {#http_receive_timeout}
HTTP receive timeout (in seconds).
diff --git a/docs/en/sql-reference/aggregate-functions/reference/largestTriangleThreeBuckets.md b/docs/en/sql-reference/aggregate-functions/reference/largestTriangleThreeBuckets.md
index 06443994dd9..4f73aadb8da 100644
--- a/docs/en/sql-reference/aggregate-functions/reference/largestTriangleThreeBuckets.md
+++ b/docs/en/sql-reference/aggregate-functions/reference/largestTriangleThreeBuckets.md
@@ -24,6 +24,8 @@ Alias: `lttb`.
- `x` — x coordinate. [Integer](../../../sql-reference/data-types/int-uint.md) , [Float](../../../sql-reference/data-types/float.md) , [Decimal](../../../sql-reference/data-types/decimal.md) , [Date](../../../sql-reference/data-types/date.md), [Date32](../../../sql-reference/data-types/date32.md), [DateTime](../../../sql-reference/data-types/datetime.md), [DateTime64](../../../sql-reference/data-types/datetime64.md).
- `y` — y coordinate. [Integer](../../../sql-reference/data-types/int-uint.md) , [Float](../../../sql-reference/data-types/float.md) , [Decimal](../../../sql-reference/data-types/decimal.md) , [Date](../../../sql-reference/data-types/date.md), [Date32](../../../sql-reference/data-types/date32.md), [DateTime](../../../sql-reference/data-types/datetime.md), [DateTime64](../../../sql-reference/data-types/datetime64.md).
+NaNs are ignored in the provided series, meaning that any NaN values will be excluded from the analysis. This ensures that the function operates only on valid numerical data.
+
**Parameters**
- `n` — number of points in the resulting series. [UInt64](../../../sql-reference/data-types/int-uint.md).
@@ -61,7 +63,7 @@ Result:
``` text
┌────────largestTriangleThreeBuckets(4)(x, y)───────────┐
-│ [(1,10),(3,15),(5,40),(10,70)] │
+│ [(1,10),(3,15),(9,55),(10,70)] │
└───────────────────────────────────────────────────────┘
```
diff --git a/docs/en/sql-reference/functions/geo/polygon.md b/docs/en/sql-reference/functions/geo/polygon.md
index c2572779ada..25a7a1fac8e 100644
--- a/docs/en/sql-reference/functions/geo/polygon.md
+++ b/docs/en/sql-reference/functions/geo/polygon.md
@@ -142,6 +142,34 @@ SELECT readWKTPoint('POINT (1.2 3.4)');
(1.2,3.4)
```
+## readWKTLineString
+
+Parses a Well-Known Text (WKT) representation of a LineString geometry and returns it in the internal ClickHouse format.
+
+### Syntax
+
+```sql
+readWKTLineString(wkt_string)
+```
+
+### Arguments
+
+- `wkt_string`: The input WKT string representing a LineString geometry.
+
+### Returned value
+
+The function returns a ClickHouse internal representation of the linestring geometry.
+
+### Example
+
+```sql
+SELECT readWKTLineString('LINESTRING (1 1, 2 2, 3 3, 1 1)');
+```
+
+```response
+[(1,1),(2,2),(3,3),(1,1)]
+```
+
## readWKTRing
Parses a Well-Known Text (WKT) representation of a Polygon geometry and returns a ring (closed linestring) in the internal ClickHouse format.
@@ -163,7 +191,7 @@ The function returns a ClickHouse internal representation of the ring (closed li
### Example
```sql
-SELECT readWKTRing('LINESTRING (1 1, 2 2, 3 3, 1 1)');
+SELECT readWKTRing('POLYGON ((1 1, 2 2, 3 3, 1 1))');
```
```response
diff --git a/docs/en/sql-reference/functions/other-functions.md b/docs/en/sql-reference/functions/other-functions.md
index 31df9e5627d..5e63d9824b4 100644
--- a/docs/en/sql-reference/functions/other-functions.md
+++ b/docs/en/sql-reference/functions/other-functions.md
@@ -212,7 +212,7 @@ toTypeName(x)
## blockSize {#blockSize}
-In ClickHouse, queries are processed in blocks (chunks).
+In ClickHouse, queries are processed in [blocks](../../development/architecture.md/#block-block) (chunks).
This function returns the size (row count) of the block the function is called on.
**Syntax**
@@ -221,6 +221,33 @@ This function returns the size (row count) of the block the function is called o
blockSize()
```
+**Example**
+
+Query:
+
+```sql
+DROP TABLE IF EXISTS test;
+CREATE TABLE test (n UInt8) ENGINE = Memory;
+
+INSERT INTO test
+SELECT * FROM system.numbers LIMIT 5;
+
+SELECT blockSize()
+FROM test;
+```
+
+Result:
+
+```response
+ ┌─blockSize()─┐
+1. │ 5 │
+2. │ 5 │
+3. │ 5 │
+4. │ 5 │
+5. │ 5 │
+ └─────────────┘
+```
+
## byteSize
Returns an estimation of uncompressed byte size of its arguments in memory.
@@ -3688,3 +3715,108 @@ Result:
```response
{'version':'1','serial_number':'2D9071D64530052D48308473922C7ADAFA85D6C5','signature_algo':'sha256WithRSAEncryption','issuer':'/CN=marsnet.local CA','not_before':'May 7 17:01:21 2024 GMT','not_after':'May 7 17:01:21 2025 GMT','subject':'/CN=chnode1','pkey_algo':'rsaEncryption'}
```
+
+## lowCardinalityIndices
+
+Returns the position of a value in the dictionary of a [LowCardinality](../data-types/lowcardinality.md) column. Positions start at 1. Since LowCardinality have per-part dictionaries, this function may return different positions for the same value in different parts.
+
+**Syntax**
+
+```sql
+lowCardinalityIndices(col)
+```
+
+**Arguments**
+
+- `col` — a low cardinality column. [LowCardinality](../data-types/lowcardinality.md).
+
+**Returned value**
+
+- The position of the value in the dictionary of the current part. [UInt64](../data-types/int-uint.md).
+
+**Example**
+
+Query:
+
+```sql
+DROP TABLE IF EXISTS test;
+CREATE TABLE test (s LowCardinality(String)) ENGINE = Memory;
+
+-- create two parts:
+
+INSERT INTO test VALUES ('ab'), ('cd'), ('ab'), ('ab'), ('df');
+INSERT INTO test VALUES ('ef'), ('cd'), ('ab'), ('cd'), ('ef');
+
+SELECT s, lowCardinalityIndices(s) FROM test;
+```
+
+Result:
+
+```response
+ ┌─s──┬─lowCardinalityIndices(s)─┐
+1. │ ab │ 1 │
+2. │ cd │ 2 │
+3. │ ab │ 1 │
+4. │ ab │ 1 │
+5. │ df │ 3 │
+ └────┴──────────────────────────┘
+ ┌─s──┬─lowCardinalityIndices(s)─┐
+ 6. │ ef │ 1 │
+ 7. │ cd │ 2 │
+ 8. │ ab │ 3 │
+ 9. │ cd │ 2 │
+10. │ ef │ 1 │
+ └────┴──────────────────────────┘
+```
+## lowCardinalityKeys
+
+Returns the dictionary values of a [LowCardinality](../data-types/lowcardinality.md) column. If the block is smaller or larger than the dictionary size, the result will be truncated or extended with default values. Since LowCardinality have per-part dictionaries, this function may return different dictionary values in different parts.
+
+**Syntax**
+
+```sql
+lowCardinalityIndices(col)
+```
+
+**Arguments**
+
+- `col` — a low cardinality column. [LowCardinality](../data-types/lowcardinality.md).
+
+**Returned value**
+
+- The dictionary keys. [UInt64](../data-types/int-uint.md).
+
+**Example**
+
+Query:
+
+```sql
+DROP TABLE IF EXISTS test;
+CREATE TABLE test (s LowCardinality(String)) ENGINE = Memory;
+
+-- create two parts:
+
+INSERT INTO test VALUES ('ab'), ('cd'), ('ab'), ('ab'), ('df');
+INSERT INTO test VALUES ('ef'), ('cd'), ('ab'), ('cd'), ('ef');
+
+SELECT s, lowCardinalityKeys(s) FROM test;
+```
+
+Result:
+
+```response
+ ┌─s──┬─lowCardinalityKeys(s)─┐
+1. │ ef │ │
+2. │ cd │ ef │
+3. │ ab │ cd │
+4. │ cd │ ab │
+5. │ ef │ │
+ └────┴───────────────────────┘
+ ┌─s──┬─lowCardinalityKeys(s)─┐
+ 6. │ ab │ │
+ 7. │ cd │ ab │
+ 8. │ ab │ cd │
+ 9. │ ab │ df │
+10. │ df │ │
+ └────┴───────────────────────┘
+```
diff --git a/docs/en/sql-reference/functions/rounding-functions.md b/docs/en/sql-reference/functions/rounding-functions.md
index d18185c5013..6495a43fc85 100644
--- a/docs/en/sql-reference/functions/rounding-functions.md
+++ b/docs/en/sql-reference/functions/rounding-functions.md
@@ -6,49 +6,90 @@ sidebar_label: Rounding
# Rounding Functions
-## floor(x\[, N\])
+## floor
-Returns the largest round number that is less than or equal to `x`. A round number is a multiple of 1/10N, or the nearest number of the appropriate data type if 1 / 10N isn’t exact.
-‘N’ is an integer constant, optional parameter. By default it is zero, which means to round to an integer.
-‘N’ may be negative.
+Returns the largest rounded number less than or equal `x`.
+A rounded number is a multiple of 1 / 10 * N, or the nearest number of the appropriate data type if 1 / 10 * N isn’t exact.
-Examples: `floor(123.45, 1) = 123.4, floor(123.45, -1) = 120.`
+Integer arguments may be rounded with negative `N` argument, with non-negative `N` the function returns `x`, i.e. does nothing.
-`x` is any numeric type. The result is a number of the same type.
-For integer arguments, it makes sense to round with a negative `N` value (for non-negative `N`, the function does not do anything).
-If rounding causes overflow (for example, floor(-128, -1)), an implementation-specific result is returned.
+If rounding causes an overflow (for example, `floor(-128, -1)`), the result is undefined.
-## ceil(x\[, N\]), ceiling(x\[, N\])
+**Syntax**
-Returns the smallest round number that is greater than or equal to `x`. In every other way, it is the same as the `floor` function (see above).
+``` sql
+floor(x[, N])
+```
-## trunc(x\[, N\]), truncate(x\[, N\])
+**Parameters**
-Returns the round number with largest absolute value that has an absolute value less than or equal to `x`‘s. In every other way, it is the same as the ’floor’ function (see above).
+- `x` - The value to round. [Float*](../data-types/float.md), [Decimal*](../data-types/decimal.md), or [(U)Int*](../data-types/int-uint.md).
+- `N` . [(U)Int*](../data-types/int-uint.md). The default is zero, which means rounding to an integer. Can be negative.
+
+**Returned value**
+
+A rounded number of the same type as `x`.
+
+**Examples**
+
+Query:
+
+```sql
+SELECT floor(123.45, 1) AS rounded
+```
+
+Result:
+
+```
+┌─rounded─┐
+│ 123.4 │
+└─────────┘
+```
+
+Query:
+
+```sql
+SELECT floor(123.45, -1)
+```
+
+Result:
+
+```
+┌─rounded─┐
+│ 120 │
+└─────────┘
+```
+
+## ceiling
+
+Like `floor` but returns the smallest rounded number greater than or equal `x`.
+
+**Syntax**
+
+``` sql
+ceiling(x[, N])
+```
+
+Alias: `ceil`
+
+## truncate
+
+Like `floor` but returns the rounded number with largest absolute value that has an absolute value less than or equal to `x`‘s.
**Syntax**
```sql
-trunc(input, precision)
+truncate(x[, N])
```
-Alias: `truncate`.
-
-**Parameters**
-
-- `input`: A numeric type ([Float](../data-types/float.md), [Decimal](../data-types/decimal.md) or [Integer](../data-types/int-uint.md)).
-- `precision`: An [Integer](../data-types/int-uint.md) type.
-
-**Returned value**
-
-- A data type of `input`.
+Alias: `trunc`.
**Example**
Query:
```sql
-SELECT trunc(123.499, 1) as res;
+SELECT truncate(123.499, 1) as res;
```
```response
@@ -57,37 +98,40 @@ SELECT trunc(123.499, 1) as res;
└───────┘
```
-## round(x\[, N\])
+## round
Rounds a value to a specified number of decimal places.
-The function returns the nearest number of the specified order. In case when given number has equal distance to surrounding numbers, the function uses banker’s rounding for float number types and rounds away from zero for the other number types (Decimal).
+The function returns the nearest number of the specified order.
+If the input value has equal distance to two neighboring numbers, the function uses banker’s rounding for [Float*](../data-types/float.md) inputs and rounds away from zero for the other number types ([Decimal*](../data-types/decimal.md).
+
+**Syntax**
``` sql
-round(expression [, decimal_places])
+round(x[, N])
```
**Arguments**
-- `expression` — A number to be rounded. Can be any [expression](../../sql-reference/syntax.md#syntax-expressions) returning the numeric [data type](../data-types/index.md#data_types).
-- `decimal-places` — An integer value.
- - If `decimal-places > 0` then the function rounds the value to the right of the decimal point.
- - If `decimal-places < 0` then the function rounds the value to the left of the decimal point.
- - If `decimal-places = 0` then the function rounds the value to integer. In this case the argument can be omitted.
+- `x` — A number to round. [Float*](../data-types/float.md), [Decimal*](../data-types/decimal.md), or [(U)Int*](../data-types/int-uint.md).
+- `N` — The number of decimal places to round to. Integer. Defaults to `0`.
+ - If `N > 0`, the function rounds to the right of the decimal point.
+ - If `N < 0`, the function rounds to the left of the decimal point.
+ - If `N = 0`, the function rounds to the next integer.
**Returned value:**
-The rounded number of the same type as the input number.
+A rounded number of the same type as `x`.
**Examples**
-Example of usage with Float:
+Example with `Float` inputs:
-``` sql
+```sql
SELECT number / 2 AS x, round(x) FROM system.numbers LIMIT 3;
```
-``` text
+```
┌───x─┬─round(divide(number, 2))─┐
│ 0 │ 0 │
│ 0.5 │ 0 │
@@ -95,13 +139,13 @@ SELECT number / 2 AS x, round(x) FROM system.numbers LIMIT 3;
└─────┴──────────────────────────┘
```
-Example of usage with Decimal:
+Example with `Decimal` inputs:
-``` sql
+```sql
SELECT cast(number / 2 AS Decimal(10,4)) AS x, round(x) FROM system.numbers LIMIT 3;
```
-``` text
+```
┌───x─┬─round(CAST(divide(number, 2), 'Decimal(10, 4)'))─┐
│ 0 │ 0 │
│ 0.5 │ 1 │
@@ -109,14 +153,14 @@ SELECT cast(number / 2 AS Decimal(10,4)) AS x, round(x) FROM system.numbers LIM
└─────┴──────────────────────────────────────────────────┘
```
-If you want to keep the trailing zeros, you need to enable `output_format_decimal_trailing_zeros`
+To retain trailing zeros, enable setting `output_format_decimal_trailing_zeros`:
-``` sql
+```sql
SELECT cast(number / 2 AS Decimal(10,4)) AS x, round(x) FROM system.numbers LIMIT 3 settings output_format_decimal_trailing_zeros=1;
```
-``` text
+```
┌──────x─┬─round(CAST(divide(number, 2), 'Decimal(10, 4)'))─┐
│ 0.0000 │ 0.0000 │
│ 0.5000 │ 1.0000 │
@@ -151,9 +195,15 @@ round(3.65, 1) = 3.6
Rounds a number to a specified decimal position.
-- If the rounding number is halfway between two numbers, the function uses banker’s rounding. Banker's rounding is a method of rounding fractional numbers. When the rounding number is halfway between two numbers, it's rounded to the nearest even digit at the specified decimal position. For example: 3.5 rounds up to 4, 2.5 rounds down to 2. It's the default rounding method for floating point numbers defined in [IEEE 754](https://en.wikipedia.org/wiki/IEEE_754#Roundings_to_nearest). The [round](#rounding_functions-round) function performs the same rounding for floating point numbers. The `roundBankers` function also rounds integers the same way, for example, `roundBankers(45, -1) = 40`.
+If the rounding number is halfway between two numbers, the function uses banker’s rounding.
+Banker's rounding is a method of rounding fractional numbers
+When the rounding number is halfway between two numbers, it's rounded to the nearest even digit at the specified decimal position.
+For example: 3.5 rounds up to 4, 2.5 rounds down to 2.
+It's the default rounding method for floating point numbers defined in [IEEE 754](https://en.wikipedia.org/wiki/IEEE_754#Roundings_to_nearest).
+The [round](#rounding_functions-round) function performs the same rounding for floating point numbers.
+The `roundBankers` function also rounds integers the same way, for example, `roundBankers(45, -1) = 40`.
-- In other cases, the function rounds numbers to the nearest integer.
+In other cases, the function rounds numbers to the nearest integer.
Using banker’s rounding, you can reduce the effect that rounding numbers has on the results of summing or subtracting these numbers.
@@ -166,16 +216,20 @@ For example, sum numbers 1.5, 2.5, 3.5, 4.5 with different rounding:
**Syntax**
``` sql
-roundBankers(expression [, decimal_places])
+roundBankers(x [, N])
```
**Arguments**
-- `expression` — A number to be rounded. Can be any [expression](../../sql-reference/syntax.md#syntax-expressions) returning the numeric [data type](../data-types/index.md#data_types).
-- `decimal-places` — Decimal places. An integer number.
- - `decimal-places > 0` — The function rounds the number to the given position right of the decimal point. Example: `roundBankers(3.55, 1) = 3.6`.
- - `decimal-places < 0` — The function rounds the number to the given position left of the decimal point. Example: `roundBankers(24.55, -1) = 20`.
- - `decimal-places = 0` — The function rounds the number to an integer. In this case the argument can be omitted. Example: `roundBankers(2.5) = 2`.
+ - `N > 0` — The function rounds the number to the given position right of the decimal point. Example: `roundBankers(3.55, 1) = 3.6`.
+ - `N < 0` — The function rounds the number to the given position left of the decimal point. Example: `roundBankers(24.55, -1) = 20`.
+ - `N = 0` — The function rounds the number to an integer. In this case the argument can be omitted. Example: `roundBankers(2.5) = 2`.
+
+- `x` — A number to round. [Float*](../data-types/float.md), [Decimal*](../data-types/decimal.md), or [(U)Int*](../data-types/int-uint.md).
+- `N` — The number of decimal places to round to. Integer. Defaults to `0`.
+ - If `N > 0`, the function rounds to the right of the decimal point.
+ - If `N < 0`, the function rounds to the left of the decimal point.
+ - If `N = 0`, the function rounds to the next integer.
**Returned value**
@@ -185,13 +239,13 @@ A value rounded by the banker’s rounding method.
Query:
-``` sql
+```sql
SELECT number / 2 AS x, roundBankers(x, 0) AS b fROM system.numbers limit 10
```
Result:
-``` text
+```
┌───x─┬─b─┐
│ 0 │ 0 │
│ 0.5 │ 0 │
@@ -208,7 +262,7 @@ Result:
Examples of Banker’s rounding:
-``` text
+```
roundBankers(0.4) = 0
roundBankers(-3.5) = -4
roundBankers(4.5) = 4
@@ -264,7 +318,7 @@ Result:
## roundDuration
-Accepts a number. If the number is less than one, it returns `0`. Otherwise, it rounds the number down to numbers from the set of commonly used durations: `1, 10, 30, 60, 120, 180, 240, 300, 600, 1200, 1800, 3600, 7200, 18000, 36000`.
+Accepts a number. If the number is less than one, it returns `0`. Otherwise, it rounds the number down to numbers from the set of commonly used durations: `1, 10, 30, 60, 120, 180, 240, 300, 600, 1200, 1800, 3600, 7200, 18000, 36000`.
**Syntax**
diff --git a/docs/en/sql-reference/functions/type-conversion-functions.md b/docs/en/sql-reference/functions/type-conversion-functions.md
index 5dd1d5ceebe..2ec51d43c59 100644
--- a/docs/en/sql-reference/functions/type-conversion-functions.md
+++ b/docs/en/sql-reference/functions/type-conversion-functions.md
@@ -2423,11 +2423,7 @@ Result:
## toUnixTimestamp64Milli
-## toUnixTimestamp64Micro
-
-## toUnixTimestamp64Nano
-
-Converts a `DateTime64` to a `Int64` value with fixed sub-second precision. Input value is scaled up or down appropriately depending on it precision.
+Converts a `DateTime64` to a `Int64` value with fixed millisecond precision. The input value is scaled up or down appropriately depending on its precision.
:::note
The output value is a timestamp in UTC, not in the timezone of `DateTime64`.
@@ -2437,24 +2433,22 @@ The output value is a timestamp in UTC, not in the timezone of `DateTime64`.
```sql
toUnixTimestamp64Milli(value)
-toUnixTimestamp64Micro(value)
-toUnixTimestamp64Nano(value)
```
**Arguments**
-- `value` — DateTime64 value with any precision.
+- `value` — DateTime64 value with any precision. [DateTime64](../data-types/datetime64.md).
**Returned value**
-- `value` converted to the `Int64` data type.
+- `value` converted to the `Int64` data type. [Int64](../data-types/int-uint.md).
-**Examples**
+**Example**
Query:
```sql
-WITH toDateTime64('2019-09-16 19:20:12.345678910', 6) AS dt64
+WITH toDateTime64('2009-02-13 23:31:31.011', 3, 'UTC') AS dt64
SELECT toUnixTimestamp64Milli(dt64);
```
@@ -2462,14 +2456,77 @@ Result:
```response
┌─toUnixTimestamp64Milli(dt64)─┐
-│ 1568650812345 │
+│ 1234567891011 │
└──────────────────────────────┘
```
+## toUnixTimestamp64Micro
+
+Converts a `DateTime64` to a `Int64` value with fixed microsecond precision. The input value is scaled up or down appropriately depending on its precision.
+
+:::note
+The output value is a timestamp in UTC, not in the timezone of `DateTime64`.
+:::
+
+**Syntax**
+
+```sql
+toUnixTimestamp64Micro(value)
+```
+
+**Arguments**
+
+- `value` — DateTime64 value with any precision. [DateTime64](../data-types/datetime64.md).
+
+**Returned value**
+
+- `value` converted to the `Int64` data type. [Int64](../data-types/int-uint.md).
+
+**Example**
+
Query:
-``` sql
-WITH toDateTime64('2019-09-16 19:20:12.345678910', 6) AS dt64
+```sql
+WITH toDateTime64('1970-01-15 06:56:07.891011', 6, 'UTC') AS dt64
+SELECT toUnixTimestamp64Micro(dt64);
+```
+
+Result:
+
+```response
+┌─toUnixTimestamp64Micro(dt64)─┐
+│ 1234567891011 │
+└──────────────────────────────┘
+```
+
+## toUnixTimestamp64Nano
+
+Converts a `DateTime64` to a `Int64` value with fixed nanosecond precision. The input value is scaled up or down appropriately depending on its precision.
+
+:::note
+The output value is a timestamp in UTC, not in the timezone of `DateTime64`.
+:::
+
+**Syntax**
+
+```sql
+toUnixTimestamp64Nano(value)
+```
+
+**Arguments**
+
+- `value` — DateTime64 value with any precision. [DateTime64](../data-types/datetime64.md).
+
+**Returned value**
+
+- `value` converted to the `Int64` data type. [Int64](../data-types/int-uint.md).
+
+**Example**
+
+Query:
+
+```sql
+WITH toDateTime64('1970-01-01 00:20:34.567891011', 9, 'UTC') AS dt64
SELECT toUnixTimestamp64Nano(dt64);
```
@@ -2477,34 +2534,32 @@ Result:
```response
┌─toUnixTimestamp64Nano(dt64)─┐
-│ 1568650812345678000 │
+│ 1234567891011 │
└─────────────────────────────┘
```
## fromUnixTimestamp64Milli
-## fromUnixTimestamp64Micro
+Converts an `Int64` to a `DateTime64` value with fixed millisecond precision and optional timezone. The input value is scaled up or down appropriately depending on its precision.
-## fromUnixTimestamp64Nano
-
-Converts an `Int64` to a `DateTime64` value with fixed sub-second precision and optional timezone. Input value is scaled up or down appropriately depending on it’s precision. Please note that input value is treated as UTC timestamp, not timestamp at given (or implicit) timezone.
+:::note
+Please note that input value is treated as a UTC timestamp, not timestamp at the given (or implicit) timezone.
+:::
**Syntax**
``` sql
fromUnixTimestamp64Milli(value[, timezone])
-fromUnixTimestamp64Micro(value[, timezone])
-fromUnixTimestamp64Nano(value[, timezone])
```
**Arguments**
-- `value` — `Int64` value with any precision.
-- `timezone` — `String` (optional) timezone name of the result.
+- `value` — value with any precision. [Int64](../data-types/int-uint.md).
+- `timezone` — (optional) timezone name of the result. [String](../data-types/string.md).
**Returned value**
-- `value` converted to the `DateTime64` data type.
+- `value` converted to DateTime64 with precision `3`. [DateTime64](../data-types/datetime64.md).
**Example**
@@ -2512,15 +2567,101 @@ Query:
``` sql
WITH CAST(1234567891011, 'Int64') AS i64
-SELECT fromUnixTimestamp64Milli(i64, 'UTC');
+SELECT
+ fromUnixTimestamp64Milli(i64, 'UTC') AS x,
+ toTypeName(x);
```
Result:
```response
-┌─fromUnixTimestamp64Milli(i64, 'UTC')─┐
-│ 2009-02-13 23:31:31.011 │
-└──────────────────────────────────────┘
+┌───────────────────────x─┬─toTypeName(x)────────┐
+│ 2009-02-13 23:31:31.011 │ DateTime64(3, 'UTC') │
+└─────────────────────────┴──────────────────────┘
+```
+
+## fromUnixTimestamp64Micro
+
+Converts an `Int64` to a `DateTime64` value with fixed microsecond precision and optional timezone. The input value is scaled up or down appropriately depending on its precision.
+
+:::note
+Please note that input value is treated as a UTC timestamp, not timestamp at the given (or implicit) timezone.
+:::
+
+**Syntax**
+
+``` sql
+fromUnixTimestamp64Micro(value[, timezone])
+```
+
+**Arguments**
+
+- `value` — value with any precision. [Int64](../data-types/int-uint.md).
+- `timezone` — (optional) timezone name of the result. [String](../data-types/string.md).
+
+**Returned value**
+
+- `value` converted to DateTime64 with precision `6`. [DateTime64](../data-types/datetime64.md).
+
+**Example**
+
+Query:
+
+``` sql
+WITH CAST(1234567891011, 'Int64') AS i64
+SELECT
+ fromUnixTimestamp64Micro(i64, 'UTC') AS x,
+ toTypeName(x);
+```
+
+Result:
+
+```response
+┌──────────────────────────x─┬─toTypeName(x)────────┐
+│ 1970-01-15 06:56:07.891011 │ DateTime64(6, 'UTC') │
+└────────────────────────────┴──────────────────────┘
+```
+
+## fromUnixTimestamp64Nano
+
+Converts an `Int64` to a `DateTime64` value with fixed nanosecond precision and optional timezone. The input value is scaled up or down appropriately depending on its precision.
+
+:::note
+Please note that input value is treated as a UTC timestamp, not timestamp at the given (or implicit) timezone.
+:::
+
+**Syntax**
+
+``` sql
+fromUnixTimestamp64Nano(value[, timezone])
+```
+
+**Arguments**
+
+- `value` — value with any precision. [Int64](../data-types/int-uint.md).
+- `timezone` — (optional) timezone name of the result. [String](../data-types/string.md).
+
+**Returned value**
+
+- `value` converted to DateTime64 with precision `9`. [DateTime64](../data-types/datetime64.md).
+
+**Example**
+
+Query:
+
+``` sql
+WITH CAST(1234567891011, 'Int64') AS i64
+SELECT
+ fromUnixTimestamp64Nano(i64, 'UTC') AS x,
+ toTypeName(x);
+```
+
+Result:
+
+```response
+┌─────────────────────────────x─┬─toTypeName(x)────────┐
+│ 1970-01-01 00:20:34.567891011 │ DateTime64(9, 'UTC') │
+└───────────────────────────────┴──────────────────────┘
```
## formatRow
diff --git a/docs/en/sql-reference/statements/alter/partition.md b/docs/en/sql-reference/statements/alter/partition.md
index ce5cecf6fd6..0ed1e523669 100644
--- a/docs/en/sql-reference/statements/alter/partition.md
+++ b/docs/en/sql-reference/statements/alter/partition.md
@@ -139,7 +139,7 @@ For the query to run successfully, the following conditions must be met:
ALTER TABLE table2 [ON CLUSTER cluster] REPLACE PARTITION partition_expr FROM table1
```
-This query copies the data partition from the `table1` to `table2` and replaces existing partition in the `table2`.
+This query copies the data partition from `table1` to `table2` and replaces the existing partition in `table2`. The operation is atomic.
Note that:
diff --git a/docs/en/sql-reference/table-functions/azureBlobStorage.md b/docs/en/sql-reference/table-functions/azureBlobStorage.md
index 1510489ce83..f59fedeb3a2 100644
--- a/docs/en/sql-reference/table-functions/azureBlobStorage.md
+++ b/docs/en/sql-reference/table-functions/azureBlobStorage.md
@@ -72,6 +72,7 @@ SELECT count(*) FROM azureBlobStorage('DefaultEndpointsProtocol=https;AccountNam
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the file size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
**See Also**
diff --git a/docs/en/sql-reference/table-functions/file.md b/docs/en/sql-reference/table-functions/file.md
index f66178afbb2..4fec772c373 100644
--- a/docs/en/sql-reference/table-functions/file.md
+++ b/docs/en/sql-reference/table-functions/file.md
@@ -196,6 +196,7 @@ SELECT count(*) FROM file('big_dir/**/file002', 'CSV', 'name String, value UInt3
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the file size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Settings {#settings}
diff --git a/docs/en/sql-reference/table-functions/hdfs.md b/docs/en/sql-reference/table-functions/hdfs.md
index d65615e7588..28cba5ccc6a 100644
--- a/docs/en/sql-reference/table-functions/hdfs.md
+++ b/docs/en/sql-reference/table-functions/hdfs.md
@@ -97,6 +97,7 @@ FROM hdfs('hdfs://hdfs1:9000/big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name Strin
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Storage Settings {#storage-settings}
diff --git a/docs/en/sql-reference/table-functions/s3.md b/docs/en/sql-reference/table-functions/s3.md
index cbef80371a3..1a7e2b8d66a 100644
--- a/docs/en/sql-reference/table-functions/s3.md
+++ b/docs/en/sql-reference/table-functions/s3.md
@@ -272,6 +272,7 @@ FROM s3(
- `_path` — Path to the file. Type: `LowCardinalty(String)`.
- `_file` — Name of the file. Type: `LowCardinalty(String)`.
- `_size` — Size of the file in bytes. Type: `Nullable(UInt64)`. If the file size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Storage Settings {#storage-settings}
diff --git a/docs/en/sql-reference/table-functions/url.md b/docs/en/sql-reference/table-functions/url.md
index 4dc6e435b50..3bb7aff53a7 100644
--- a/docs/en/sql-reference/table-functions/url.md
+++ b/docs/en/sql-reference/table-functions/url.md
@@ -53,6 +53,7 @@ Character `|` inside patterns is used to specify failover addresses. They are it
- `_path` — Path to the `URL`. Type: `LowCardinalty(String)`.
- `_file` — Resource name of the `URL`. Type: `LowCardinalty(String)`.
- `_size` — Size of the resource in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
+- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
## Storage Settings {#storage-settings}
diff --git a/docs/ru/sql-reference/functions/rounding-functions.md b/docs/ru/sql-reference/functions/rounding-functions.md
index cc939f69afc..f1dd57505ea 100644
--- a/docs/ru/sql-reference/functions/rounding-functions.md
+++ b/docs/ru/sql-reference/functions/rounding-functions.md
@@ -10,7 +10,7 @@ sidebar_label: "Функции округления"
Возвращает наибольшее круглое число, которое меньше или равно, чем x.
Круглым называется число, кратное 1 / 10N или ближайшее к нему число соответствующего типа данных, если 1 / 10N не представимо точно.
-N - целочисленная константа, не обязательный параметр. По умолчанию - ноль, что означает - округлять до целого числа.
+N - целочисленный аргумент, не обязательный параметр. По умолчанию - ноль, что означает - округлять до целого числа.
N может быть отрицательным.
Примеры: `floor(123.45, 1) = 123.4, floor(123.45, -1) = 120.`
diff --git a/programs/server/Server.cpp b/programs/server/Server.cpp
index 8fcb9d87a93..84ff0e94cef 100644
--- a/programs/server/Server.cpp
+++ b/programs/server/Server.cpp
@@ -773,7 +773,27 @@ try
LOG_INFO(log, "Available CPU instruction sets: {}", cpu_info);
#endif
- bool will_have_trace_collector = hasPHDRCache() && config().has("trace_log");
+ bool has_trace_collector = false;
+ /// Disable it if we collect test coverage information, because it will work extremely slow.
+#if !WITH_COVERAGE
+ /// Profilers cannot work reliably with any other libunwind or without PHDR cache.
+ has_trace_collector = hasPHDRCache() && config().has("trace_log");
+#endif
+
+ /// Describe multiple reasons when query profiler cannot work.
+
+#if WITH_COVERAGE
+ LOG_INFO(log, "Query Profiler and TraceCollector are disabled because they work extremely slow with test coverage.");
+#endif
+
+#if defined(SANITIZER)
+ LOG_INFO(log, "Query Profiler disabled because they cannot work under sanitizers"
+ " when two different stack unwinding methods will interfere with each other.");
+#endif
+
+ if (!hasPHDRCache())
+ LOG_INFO(log, "Query Profiler and TraceCollector are disabled because they require PHDR cache to be created"
+ " (otherwise the function 'dl_iterate_phdr' is not lock free and not async-signal safe).");
// Initialize global thread pool. Do it before we fetch configs from zookeeper
// nodes (`from_zk`), because ZooKeeper interface uses the pool. We will
@@ -782,8 +802,27 @@ try
server_settings.max_thread_pool_size,
server_settings.max_thread_pool_free_size,
server_settings.thread_pool_queue_size,
- will_have_trace_collector ? server_settings.global_profiler_real_time_period_ns : 0,
- will_have_trace_collector ? server_settings.global_profiler_cpu_time_period_ns : 0);
+ has_trace_collector ? server_settings.global_profiler_real_time_period_ns : 0,
+ has_trace_collector ? server_settings.global_profiler_cpu_time_period_ns : 0);
+
+ if (has_trace_collector)
+ {
+ global_context->createTraceCollector();
+
+ /// Set up server-wide memory profiler (for total memory tracker).
+ if (server_settings.total_memory_profiler_step)
+ total_memory_tracker.setProfilerStep(server_settings.total_memory_profiler_step);
+
+ if (server_settings.total_memory_tracker_sample_probability > 0.0)
+ total_memory_tracker.setSampleProbability(server_settings.total_memory_tracker_sample_probability);
+
+ if (server_settings.total_memory_profiler_sample_min_allocation_size)
+ total_memory_tracker.setSampleMinAllocationSize(server_settings.total_memory_profiler_sample_min_allocation_size);
+
+ if (server_settings.total_memory_profiler_sample_max_allocation_size)
+ total_memory_tracker.setSampleMaxAllocationSize(server_settings.total_memory_profiler_sample_max_allocation_size);
+ }
+
/// Wait for all threads to avoid possible use-after-free (for example logging objects can be already destroyed).
SCOPE_EXIT({
Stopwatch watch;
@@ -1950,52 +1989,9 @@ try
LOG_DEBUG(log, "Loaded metadata.");
- /// Init trace collector only after trace_log system table was created
- /// Disable it if we collect test coverage information, because it will work extremely slow.
-#if !WITH_COVERAGE
- /// Profilers cannot work reliably with any other libunwind or without PHDR cache.
- if (hasPHDRCache())
- {
+ if (has_trace_collector)
global_context->initializeTraceCollector();
- /// Set up server-wide memory profiler (for total memory tracker).
- if (server_settings.total_memory_profiler_step)
- {
- total_memory_tracker.setProfilerStep(server_settings.total_memory_profiler_step);
- }
-
- if (server_settings.total_memory_tracker_sample_probability > 0.0)
- {
- total_memory_tracker.setSampleProbability(server_settings.total_memory_tracker_sample_probability);
- }
-
- if (server_settings.total_memory_profiler_sample_min_allocation_size)
- {
- total_memory_tracker.setSampleMinAllocationSize(server_settings.total_memory_profiler_sample_min_allocation_size);
- }
-
- if (server_settings.total_memory_profiler_sample_max_allocation_size)
- {
- total_memory_tracker.setSampleMaxAllocationSize(server_settings.total_memory_profiler_sample_max_allocation_size);
- }
- }
-#endif
-
- /// Describe multiple reasons when query profiler cannot work.
-
-#if WITH_COVERAGE
- LOG_INFO(log, "Query Profiler and TraceCollector are disabled because they work extremely slow with test coverage.");
-#endif
-
-#if defined(SANITIZER)
- LOG_INFO(log, "Query Profiler disabled because they cannot work under sanitizers"
- " when two different stack unwinding methods will interfere with each other.");
-#endif
-
- if (!hasPHDRCache())
- LOG_INFO(log, "Query Profiler and TraceCollector are disabled because they require PHDR cache to be created"
- " (otherwise the function 'dl_iterate_phdr' is not lock free and not async-signal safe).");
-
#if defined(OS_LINUX)
auto tasks_stats_provider = TasksStatsCounters::findBestAvailableProvider();
if (tasks_stats_provider == TasksStatsCounters::MetricsProvider::None)
diff --git a/programs/server/config.xml b/programs/server/config.xml
index 4b3248d9d1c..b7a4b8dd0e9 100644
--- a/programs/server/config.xml
+++ b/programs/server/config.xml
@@ -1561,6 +1561,7 @@
8
+ DEBUG_LEVEL
2
diff --git a/src/Analyzer/ArrayJoinNode.cpp b/src/Analyzer/ArrayJoinNode.cpp
index 27d7229d46a..0cfb5d80b2a 100644
--- a/src/Analyzer/ArrayJoinNode.cpp
+++ b/src/Analyzer/ArrayJoinNode.cpp
@@ -1,5 +1,6 @@
#include
#include
+#include
#include
#include
#include
@@ -64,7 +65,12 @@ ASTPtr ArrayJoinNode::toASTImpl(const ConvertToASTOptions & options) const
auto * column_node = array_join_expression->as();
if (column_node && column_node->getExpression())
- array_join_expression_ast = column_node->getExpression()->toAST(options);
+ {
+ if (const auto * function_node = column_node->getExpression()->as(); function_node && function_node->getFunctionName() == "nested")
+ array_join_expression_ast = array_join_expression->toAST(options);
+ else
+ array_join_expression_ast = column_node->getExpression()->toAST(options);
+ }
else
array_join_expression_ast = array_join_expression->toAST(options);
diff --git a/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp b/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp
index 26ca5984b49..15919c4a2fe 100644
--- a/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp
+++ b/src/Analyzer/Passes/OrderByLimitByDuplicateEliminationPass.cpp
@@ -22,6 +22,7 @@ public:
if (query_node->hasOrderBy())
{
+ QueryTreeNodeConstRawPtrWithHashSet unique_expressions_nodes_set;
QueryTreeNodes result_nodes;
auto & query_order_by_nodes = query_node->getOrderBy().getNodes();
@@ -45,10 +46,9 @@ public:
query_order_by_nodes = std::move(result_nodes);
}
- unique_expressions_nodes_set.clear();
-
if (query_node->hasLimitBy())
{
+ QueryTreeNodeConstRawPtrWithHashSet unique_expressions_nodes_set;
QueryTreeNodes result_nodes;
auto & query_limit_by_nodes = query_node->getLimitBy().getNodes();
@@ -63,9 +63,6 @@ public:
query_limit_by_nodes = std::move(result_nodes);
}
}
-
-private:
- QueryTreeNodeConstRawPtrWithHashSet unique_expressions_nodes_set;
};
}
diff --git a/src/Backups/BackupIO_S3.cpp b/src/Backups/BackupIO_S3.cpp
index 92f086295a0..1ea59c1d38b 100644
--- a/src/Backups/BackupIO_S3.cpp
+++ b/src/Backups/BackupIO_S3.cpp
@@ -54,9 +54,9 @@ namespace
S3::PocoHTTPClientConfiguration client_configuration = S3::ClientFactory::instance().createClientConfiguration(
settings.auth_settings.region,
context->getRemoteHostFilter(),
- static_cast(global_settings.s3_max_redirects),
- static_cast(global_settings.s3_retry_attempts),
- global_settings.enable_s3_requests_logging,
+ static_cast(local_settings.s3_max_redirects),
+ static_cast(local_settings.backup_restore_s3_retry_attempts),
+ local_settings.enable_s3_requests_logging,
/* for_disk_s3 = */ false,
request_settings.get_request_throttler,
request_settings.put_request_throttler,
diff --git a/src/Columns/MaskOperations.cpp b/src/Columns/MaskOperations.cpp
index 1f5f94beee9..873a4060872 100644
--- a/src/Columns/MaskOperations.cpp
+++ b/src/Columns/MaskOperations.cpp
@@ -289,10 +289,14 @@ void executeColumnIfNeeded(ColumnWithTypeAndName & column, bool empty)
if (!column_function)
return;
+ size_t original_size = column.column->size();
+
if (!empty)
column = column_function->reduce();
else
- column.column = column_function->getResultType()->createColumn();
+ column.column = column_function->getResultType()->createColumnConstWithDefaultValue(original_size)->convertToFullColumnIfConst();
+
+ chassert(column.column->size() == original_size);
}
int checkShortCircuitArguments(const ColumnsWithTypeAndName & arguments)
diff --git a/src/Common/QueryProfiler.cpp b/src/Common/QueryProfiler.cpp
index c3affbdd968..746010b5462 100644
--- a/src/Common/QueryProfiler.cpp
+++ b/src/Common/QueryProfiler.cpp
@@ -228,9 +228,9 @@ void Timer::cleanup()
#endif
template
-QueryProfilerBase::QueryProfilerBase([[maybe_unused]] UInt64 thread_id, [[maybe_unused]] int clock_type, [[maybe_unused]] UInt32 period, [[maybe_unused]] int pause_signal_)
- : log(getLogger("QueryProfiler"))
- , pause_signal(pause_signal_)
+QueryProfilerBase::QueryProfilerBase(
+ [[maybe_unused]] UInt64 thread_id, [[maybe_unused]] int clock_type, [[maybe_unused]] UInt32 period, [[maybe_unused]] int pause_signal_)
+ : log(getLogger("QueryProfiler")), pause_signal(pause_signal_)
{
#if defined(SANITIZER)
throw Exception(ErrorCodes::NOT_IMPLEMENTED, "QueryProfiler disabled because they cannot work under sanitizers");
diff --git a/src/Common/StringUtils.h b/src/Common/StringUtils.h
index fe5fc3c058f..e4c7ab3e80c 100644
--- a/src/Common/StringUtils.h
+++ b/src/Common/StringUtils.h
@@ -140,6 +140,18 @@ inline bool isPrintableASCII(char c)
return uc >= 32 && uc <= 126; /// 127 is ASCII DEL.
}
+inline bool isCSIParameterByte(char c)
+{
+ uint8_t uc = c;
+ return uc >= 0x30 && uc <= 0x3F; /// ASCII 0–9:;<=>?
+}
+
+inline bool isCSIIntermediateByte(char c)
+{
+ uint8_t uc = c;
+ return uc >= 0x20 && uc <= 0x2F; /// ASCII !"#$%&'()*+,-./
+}
+
inline bool isCSIFinalByte(char c)
{
uint8_t uc = c;
diff --git a/src/Common/UTF8Helpers.cpp b/src/Common/UTF8Helpers.cpp
index 8c8c8e8327b..dd24cb20933 100644
--- a/src/Common/UTF8Helpers.cpp
+++ b/src/Common/UTF8Helpers.cpp
@@ -103,7 +103,7 @@ template
size_t computeWidthImpl(const UInt8 * data, size_t size, size_t prefix, size_t limit) noexcept
{
UTF8Decoder decoder;
- int isEscapeSequence = false;
+ bool is_escape_sequence = false;
size_t width = 0;
size_t rollback = 0;
for (size_t i = 0; i < size; ++i)
@@ -116,6 +116,9 @@ size_t computeWidthImpl(const UInt8 * data, size_t size, size_t prefix, size_t l
while (i + 15 < size)
{
+ if (is_escape_sequence)
+ break;
+
__m128i bytes = _mm_loadu_si128(reinterpret_cast(&data[i]));
const uint16_t non_regular_width_mask = _mm_movemask_epi8(
@@ -132,25 +135,28 @@ size_t computeWidthImpl(const UInt8 * data, size_t size, size_t prefix, size_t l
}
else
{
- if (isEscapeSequence)
- {
- break;
- }
- else
- {
- i += 16;
- width += 16;
- }
+ i += 16;
+ width += 16;
}
}
#endif
while (i < size && isPrintableASCII(data[i]))
{
- if (!isEscapeSequence)
+ bool ignore_width = is_escape_sequence && (isCSIParameterByte(data[i]) || isCSIIntermediateByte(data[i]));
+
+ if (ignore_width || (data[i] == '[' && is_escape_sequence))
+ {
+ /// don't count the width
+ }
+ else if (is_escape_sequence && isCSIFinalByte(data[i]))
+ {
+ is_escape_sequence = false;
+ }
+ else
+ {
++width;
- else if (isCSIFinalByte(data[i]) && data[i - 1] != '\x1b')
- isEscapeSequence = false; /// end of CSI escape sequence reached
+ }
++i;
}
@@ -178,7 +184,7 @@ size_t computeWidthImpl(const UInt8 * data, size_t size, size_t prefix, size_t l
// special treatment for '\t' and for ESC
size_t next_width = width;
if (decoder.codepoint == '\x1b')
- isEscapeSequence = true;
+ is_escape_sequence = true;
else if (decoder.codepoint == '\t')
next_width += 8 - (prefix + width) % 8;
else
diff --git a/src/Core/Settings.h b/src/Core/Settings.h
index 27ce54c03a7..6848dfb196e 100644
--- a/src/Core/Settings.h
+++ b/src/Core/Settings.h
@@ -202,6 +202,8 @@ class IColumn;
M(UInt64, parallel_replica_offset, 0, "This is internal setting that should not be used directly and represents an implementation detail of the 'parallel replicas' mode. This setting will be automatically set up by the initiator server for distributed queries to the index of the replica participating in query processing among parallel replicas.", 0) \
M(String, parallel_replicas_custom_key, "", "Custom key assigning work to replicas when parallel replicas are used.", 0) \
M(ParallelReplicasCustomKeyFilterType, parallel_replicas_custom_key_filter_type, ParallelReplicasCustomKeyFilterType::DEFAULT, "Type of filter to use with custom key for parallel replicas. default - use modulo operation on the custom key, range - use range filter on custom key using all possible values for the value type of custom key.", 0) \
+ M(UInt64, parallel_replicas_custom_key_range_lower, 0, "Lower bound for the universe that the parallel replicas custom range filter is calculated over", 0) \
+ M(UInt64, parallel_replicas_custom_key_range_upper, 0, "Upper bound for the universe that the parallel replicas custom range filter is calculated over. A value of 0 disables the upper bound, setting it to the max value of the custom key expression", 0) \
\
M(String, cluster_for_parallel_replicas, "", "Cluster for a shard in which current server is located", 0) \
M(UInt64, allow_experimental_parallel_reading_from_replicas, 0, "Use all the replicas from a shard for SELECT query execution. Reading is parallelized and coordinated dynamically. 0 - disabled, 1 - enabled, silently disable them in case of failure, 2 - enabled, throw an exception in case of failure", 0) \
@@ -515,6 +517,7 @@ class IColumn;
M(UInt64, backup_restore_keeper_value_max_size, 1048576, "Maximum size of data of a [Zoo]Keeper's node during backup", 0) \
M(UInt64, backup_restore_batch_size_for_keeper_multiread, 10000, "Maximum size of batch for multiread request to [Zoo]Keeper during backup or restore", 0) \
M(UInt64, backup_restore_batch_size_for_keeper_multi, 1000, "Maximum size of batch for multi request to [Zoo]Keeper during backup or restore", 0) \
+ M(UInt64, backup_restore_s3_retry_attempts, 1000, "Setting for Aws::Client::RetryStrategy, Aws::Client does retries itself, 0 means no retries. It takes place only for backup/restore.", 0) \
M(UInt64, max_backup_bandwidth, 0, "The maximum read speed in bytes per second for particular backup on server. Zero means unlimited.", 0) \
\
M(Bool, log_profile_events, true, "Log query performance statistics into the query_log, query_thread_log and query_views_log.", 0) \
diff --git a/src/Core/SettingsChangesHistory.h b/src/Core/SettingsChangesHistory.h
index f7423754fc2..6734c0dc525 100644
--- a/src/Core/SettingsChangesHistory.h
+++ b/src/Core/SettingsChangesHistory.h
@@ -83,7 +83,7 @@ namespace SettingsChangesHistory
/// For newly added setting choose the most appropriate previous_value (for example, if new setting
/// controls new feature and it's 'true' by default, use 'false' as previous_value).
/// It's used to implement `compatibility` setting (see https://github.com/ClickHouse/ClickHouse/issues/35972)
-static std::map settings_changes_history =
+static const std::map settings_changes_history =
{
{"24.6", {{"materialize_skip_indexes_on_insert", true, true, "Added new setting to allow to disable materialization of skip indexes on insert"},
{"materialize_statistics_on_insert", true, true, "Added new setting to allow to disable materialization of statistics on insert"},
@@ -100,7 +100,9 @@ static std::map sett
{"allow_statistic_optimize", false, false, "Old setting which popped up here being renamed."},
{"allow_experimental_statistic", false, false, "Old setting which popped up here being renamed."},
{"allow_statistics_optimize", false, false, "The setting was renamed. The previous name is `allow_statistic_optimize`."},
- {"allow_experimental_statistics", false, false, "The setting was renamed. The previous name is `allow_experimental_statistic`."}
+ {"allow_experimental_statistics", false, false, "The setting was renamed. The previous name is `allow_experimental_statistic`."},
+ {"parallel_replicas_custom_key_range_lower", 0, 0, "Add settings to control the range filter when using parallel replicas with dynamic shards"},
+ {"parallel_replicas_custom_key_range_upper", 0, 0, "Add settings to control the range filter when using parallel replicas with dynamic shards. A value of 0 disables the upper limit"},
}},
{"24.5", {{"allow_deprecated_error_prone_window_functions", true, false, "Allow usage of deprecated error prone window functions (neighbor, runningAccumulate, runningDifferenceStartingWithFirstValue, runningDifference)"},
{"allow_experimental_join_condition", false, false, "Support join with inequal conditions which involve columns from both left and right table. e.g. t1.y < t2.y."},
@@ -111,6 +113,7 @@ static std::map sett
{"http_max_chunk_size", 0, 0, "Internal limitation"},
{"prefer_external_sort_block_bytes", 0, DEFAULT_BLOCK_SIZE * 256, "Prefer maximum block bytes for external sort, reduce the memory usage during merging."},
{"input_format_force_null_for_omitted_fields", false, false, "Disable type-defaults for omitted fields when needed"},
+ {"backup_restore_s3_retry_attempts", 0, 1000, "A new setting."},
{"cast_string_to_dynamic_use_inference", false, false, "Add setting to allow converting String to Dynamic through parsing"},
{"allow_experimental_dynamic_type", false, false, "Add new experimental Dynamic type"},
{"azure_max_blocks_in_multipart_upload", 50000, 50000, "Maximum number of blocks in multipart upload for Azure."},
diff --git a/src/DataTypes/DataTypeCustomGeo.cpp b/src/DataTypes/DataTypeCustomGeo.cpp
index f7d05fa3be6..0736d837d46 100644
--- a/src/DataTypes/DataTypeCustomGeo.cpp
+++ b/src/DataTypes/DataTypeCustomGeo.cpp
@@ -17,6 +17,13 @@ void registerDataTypeDomainGeo(DataTypeFactory & factory)
std::make_unique(std::make_unique()));
});
+ // Custom type for simple line which consists from several segments.
+ factory.registerSimpleDataTypeCustom("LineString", []
+ {
+ return std::make_pair(DataTypeFactory::instance().get("Array(Point)"),
+ std::make_unique(std::make_unique()));
+ });
+
// Custom type for simple polygon without holes stored as Array(Point)
factory.registerSimpleDataTypeCustom("Ring", []
{
diff --git a/src/DataTypes/DataTypeCustomGeo.h b/src/DataTypes/DataTypeCustomGeo.h
index c2a83b3e577..0a1c83e4638 100644
--- a/src/DataTypes/DataTypeCustomGeo.h
+++ b/src/DataTypes/DataTypeCustomGeo.h
@@ -11,6 +11,12 @@ public:
DataTypePointName() : DataTypeCustomFixedName("Point") {}
};
+class DataTypeLineStringName : public DataTypeCustomFixedName
+{
+public:
+ DataTypeLineStringName() : DataTypeCustomFixedName("LineString") {}
+};
+
class DataTypeRingName : public DataTypeCustomFixedName
{
public:
diff --git a/src/DataTypes/IDataType.h b/src/DataTypes/IDataType.h
index 46c30240ef8..85fce671cbb 100644
--- a/src/DataTypes/IDataType.h
+++ b/src/DataTypes/IDataType.h
@@ -543,6 +543,7 @@ template constexpr bool IsDataTypeNumber = false;
template constexpr bool IsDataTypeDateOrDateTime = false;
template constexpr bool IsDataTypeDate = false;
template constexpr bool IsDataTypeEnum = false;
+template constexpr bool IsDataTypeStringOrFixedString = false;
template constexpr bool IsDataTypeDecimalOrNumber = IsDataTypeDecimal || IsDataTypeNumber;
@@ -556,6 +557,8 @@ class DataTypeDate;
class DataTypeDate32;
class DataTypeDateTime;
class DataTypeDateTime64;
+class DataTypeString;
+class DataTypeFixedString;
template constexpr bool IsDataTypeDecimal> = true;
@@ -572,6 +575,9 @@ template <> inline constexpr bool IsDataTypeDateOrDateTime = tru
template <> inline constexpr bool IsDataTypeDateOrDateTime = true;
template <> inline constexpr bool IsDataTypeDateOrDateTime = true;
+template <> inline constexpr bool IsDataTypeStringOrFixedString = true;
+template <> inline constexpr bool IsDataTypeStringOrFixedString = true;
+
template
class DataTypeEnum;
diff --git a/src/Databases/DatabaseAtomic.cpp b/src/Databases/DatabaseAtomic.cpp
index 8edc5b737a6..ccab72cfbae 100644
--- a/src/Databases/DatabaseAtomic.cpp
+++ b/src/Databases/DatabaseAtomic.cpp
@@ -1,20 +1,21 @@
+#include
#include
+#include
#include
#include
-#include
+#include
#include
#include
-#include
+#include
+#include
+#include
+#include
#include
+#include
+#include "Common/logger_useful.h"
#include
#include
#include
-#include
-#include
-#include
-#include
-#include
-#include
namespace fs = std::filesystem;
@@ -393,6 +394,7 @@ DatabaseAtomic::DetachedTables DatabaseAtomic::cleanupDetachedTables()
{
DetachedTables not_in_use;
auto it = detached_tables.begin();
+ LOG_DEBUG(log, "There are {} detached tables. Start searching non used tables.", detached_tables.size());
while (it != detached_tables.end())
{
if (it->second.unique())
@@ -403,6 +405,7 @@ DatabaseAtomic::DetachedTables DatabaseAtomic::cleanupDetachedTables()
else
++it;
}
+ LOG_DEBUG(log, "Found {} non used tables in detached tables.", not_in_use.size());
/// It should be destroyed in caller with released database mutex
return not_in_use;
}
diff --git a/src/Databases/DatabaseOnDisk.cpp b/src/Databases/DatabaseOnDisk.cpp
index 025ac585593..b8154372116 100644
--- a/src/Databases/DatabaseOnDisk.cpp
+++ b/src/Databases/DatabaseOnDisk.cpp
@@ -794,7 +794,7 @@ ASTPtr DatabaseOnDisk::getCreateQueryFromStorage(const String & table_name, cons
throw_on_error);
create_table_query->set(create_table_query->as()->comment,
- std::make_shared("SYSTEM TABLE is built on the fly."));
+ std::make_shared(storage->getInMemoryMetadata().comment));
return create_table_query;
}
diff --git a/src/Databases/DatabaseReplicated.cpp b/src/Databases/DatabaseReplicated.cpp
index b91596a555d..badfedeec9b 100644
--- a/src/Databases/DatabaseReplicated.cpp
+++ b/src/Databases/DatabaseReplicated.cpp
@@ -122,6 +122,13 @@ DatabaseReplicated::DatabaseReplicated(
fillClusterAuthInfo(db_settings.collection_name.value, context_->getConfigRef());
replica_group_name = context_->getConfigRef().getString("replica_group_name", "");
+
+ if (!replica_group_name.empty() && database_name.starts_with(DatabaseReplicated::ALL_GROUPS_CLUSTER_PREFIX))
+ {
+ context_->addWarningMessage(fmt::format("There's a Replicated database with a name starting from '{}', "
+ "and replica_group_name is configured. It may cause collisions in cluster names.",
+ ALL_GROUPS_CLUSTER_PREFIX));
+ }
}
String DatabaseReplicated::getFullReplicaName(const String & shard, const String & replica)
@@ -173,13 +180,40 @@ ClusterPtr DatabaseReplicated::tryGetCluster() const
return cluster;
}
-void DatabaseReplicated::setCluster(ClusterPtr && new_cluster)
+ClusterPtr DatabaseReplicated::tryGetAllGroupsCluster() const
{
std::lock_guard lock{mutex};
- cluster = std::move(new_cluster);
+ if (replica_group_name.empty())
+ return nullptr;
+
+ if (cluster_all_groups)
+ return cluster_all_groups;
+
+ /// Database is probably not created or not initialized yet, it's ok to return nullptr
+ if (is_readonly)
+ return cluster_all_groups;
+
+ try
+ {
+ cluster_all_groups = getClusterImpl(/*all_groups*/ true);
+ }
+ catch (...)
+ {
+ tryLogCurrentException(log);
+ }
+ return cluster_all_groups;
}
-ClusterPtr DatabaseReplicated::getClusterImpl() const
+void DatabaseReplicated::setCluster(ClusterPtr && new_cluster, bool all_groups)
+{
+ std::lock_guard lock{mutex};
+ if (all_groups)
+ cluster_all_groups = std::move(new_cluster);
+ else
+ cluster = std::move(new_cluster);
+}
+
+ClusterPtr DatabaseReplicated::getClusterImpl(bool all_groups) const
{
Strings unfiltered_hosts;
Strings hosts;
@@ -199,17 +233,24 @@ ClusterPtr DatabaseReplicated::getClusterImpl() const
"It's possible if the first replica is not fully created yet "
"or if the last replica was just dropped or due to logical error", zookeeper_path);
- hosts.clear();
- std::vector paths;
- for (const auto & host : unfiltered_hosts)
- paths.push_back(zookeeper_path + "/replicas/" + host + "/replica_group");
-
- auto replica_groups = zookeeper->tryGet(paths);
-
- for (size_t i = 0; i < paths.size(); ++i)
+ if (all_groups)
{
- if (replica_groups[i].data == replica_group_name)
- hosts.push_back(unfiltered_hosts[i]);
+ hosts = unfiltered_hosts;
+ }
+ else
+ {
+ hosts.clear();
+ std::vector paths;
+ for (const auto & host : unfiltered_hosts)
+ paths.push_back(zookeeper_path + "/replicas/" + host + "/replica_group");
+
+ auto replica_groups = zookeeper->tryGet(paths);
+
+ for (size_t i = 0; i < paths.size(); ++i)
+ {
+ if (replica_groups[i].data == replica_group_name)
+ hosts.push_back(unfiltered_hosts[i]);
+ }
}
Int32 cversion = stat.cversion;
@@ -274,6 +315,11 @@ ClusterPtr DatabaseReplicated::getClusterImpl() const
bool treat_local_as_remote = false;
bool treat_local_port_as_remote = getContext()->getApplicationType() == Context::ApplicationType::LOCAL;
+
+ String cluster_name = TSA_SUPPRESS_WARNING_FOR_READ(database_name); /// FIXME
+ if (all_groups)
+ cluster_name = ALL_GROUPS_CLUSTER_PREFIX + cluster_name;
+
ClusterConnectionParameters params{
cluster_auth_info.cluster_username,
cluster_auth_info.cluster_password,
@@ -282,7 +328,7 @@ ClusterPtr DatabaseReplicated::getClusterImpl() const
treat_local_port_as_remote,
cluster_auth_info.cluster_secure_connection,
Priority{1},
- TSA_SUPPRESS_WARNING_FOR_READ(database_name), /// FIXME
+ cluster_name,
cluster_auth_info.cluster_secret};
return std::make_shared(getContext()->getSettingsRef(), shards, params);
diff --git a/src/Databases/DatabaseReplicated.h b/src/Databases/DatabaseReplicated.h
index 55bcf963d37..761d6b4b503 100644
--- a/src/Databases/DatabaseReplicated.h
+++ b/src/Databases/DatabaseReplicated.h
@@ -20,6 +20,8 @@ using ClusterPtr = std::shared_ptr;
class DatabaseReplicated : public DatabaseAtomic
{
public:
+ static constexpr auto ALL_GROUPS_CLUSTER_PREFIX = "all_groups.";
+
DatabaseReplicated(const String & name_, const String & metadata_path_, UUID uuid,
const String & zookeeper_path_, const String & shard_name_, const String & replica_name_,
DatabaseReplicatedSettings db_settings_,
@@ -65,6 +67,7 @@ public:
/// Returns cluster consisting of database replicas
ClusterPtr tryGetCluster() const;
+ ClusterPtr tryGetAllGroupsCluster() const;
void drop(ContextPtr /*context*/) override;
@@ -113,8 +116,8 @@ private:
ASTPtr parseQueryFromMetadataInZooKeeper(const String & node_name, const String & query);
String readMetadataFile(const String & table_name) const;
- ClusterPtr getClusterImpl() const;
- void setCluster(ClusterPtr && new_cluster);
+ ClusterPtr getClusterImpl(bool all_groups = false) const;
+ void setCluster(ClusterPtr && new_cluster, bool all_groups = false);
void createEmptyLogEntry(const ZooKeeperPtr & current_zookeeper);
@@ -155,6 +158,7 @@ private:
UInt64 tables_metadata_digest TSA_GUARDED_BY(metadata_mutex);
mutable ClusterPtr cluster;
+ mutable ClusterPtr cluster_all_groups;
LoadTaskPtr startup_replicated_database_task TSA_GUARDED_BY(mutex);
};
diff --git a/src/Databases/DatabaseReplicatedWorker.cpp b/src/Databases/DatabaseReplicatedWorker.cpp
index 6e19a77c501..31d6f7876a8 100644
--- a/src/Databases/DatabaseReplicatedWorker.cpp
+++ b/src/Databases/DatabaseReplicatedWorker.cpp
@@ -421,6 +421,8 @@ DDLTaskPtr DatabaseReplicatedDDLWorker::initAndCheckTask(const String & entry_na
{
/// Some replica is added or removed, let's update cached cluster
database->setCluster(database->getClusterImpl());
+ if (!database->replica_group_name.empty())
+ database->setCluster(database->getClusterImpl(/*all_groups*/ true), /*all_groups*/ true);
out_reason = fmt::format("Entry {} is a dummy task", entry_name);
return {};
}
diff --git a/src/Disks/IO/WriteBufferFromAzureBlobStorage.cpp b/src/Disks/IO/WriteBufferFromAzureBlobStorage.cpp
index 2c90e3a9003..a2d21cf49c2 100644
--- a/src/Disks/IO/WriteBufferFromAzureBlobStorage.cpp
+++ b/src/Disks/IO/WriteBufferFromAzureBlobStorage.cpp
@@ -19,11 +19,15 @@ namespace ProfileEvents
namespace DB
{
+namespace ErrorCodes
+{
+ extern const int LOGICAL_ERROR;
+}
+
struct WriteBufferFromAzureBlobStorage::PartData
{
Memory<> memory;
size_t data_size = 0;
- std::string block_id;
};
BufferAllocationPolicyPtr createBufferAllocationPolicy(const AzureObjectStorageSettings & settings)
@@ -119,22 +123,30 @@ void WriteBufferFromAzureBlobStorage::preFinalize()
// This function should not be run again
is_prefinalized = true;
+ hidePartialData();
+
+ if (hidden_size > 0)
+ detachBuffer();
+
+ setFakeBufferWhenPreFinalized();
+
/// If there is only one block and size is less than or equal to max_single_part_upload_size
/// then we use single part upload instead of multi part upload
- if (buffer_allocation_policy->getBufferNumber() == 1)
+ if (block_ids.empty() && detached_part_data.size() == 1 && detached_part_data.front().data_size <= max_single_part_upload_size)
{
- size_t data_size = size_t(position() - memory.data());
- if (data_size <= max_single_part_upload_size)
- {
- auto block_blob_client = blob_container_client->GetBlockBlobClient(blob_path);
- Azure::Core::IO::MemoryBodyStream memory_stream(reinterpret_cast(memory.data()), data_size);
- execWithRetry([&](){ block_blob_client.Upload(memory_stream); }, max_unexpected_write_error_retries, data_size);
- LOG_TRACE(log, "Committed single block for blob `{}`", blob_path);
- return;
- }
- }
+ auto part_data = std::move(detached_part_data.front());
+ auto block_blob_client = blob_container_client->GetBlockBlobClient(blob_path);
+ Azure::Core::IO::MemoryBodyStream memory_stream(reinterpret_cast(part_data.memory.data()), part_data.data_size);
+ execWithRetry([&](){ block_blob_client.Upload(memory_stream); }, max_unexpected_write_error_retries, part_data.data_size);
+ LOG_TRACE(log, "Committed single block for blob `{}`", blob_path);
- writePart();
+ detached_part_data.pop_front();
+ return;
+ }
+ else
+ {
+ writeMultipartUpload();
+ }
}
void WriteBufferFromAzureBlobStorage::finalizeImpl()
@@ -144,9 +156,13 @@ void WriteBufferFromAzureBlobStorage::finalizeImpl()
if (!is_prefinalized)
preFinalize();
+ chassert(offset() == 0);
+ chassert(hidden_size == 0);
+
+ task_tracker->waitAll();
+
if (!block_ids.empty())
{
- task_tracker->waitAll();
auto block_blob_client = blob_container_client->GetBlockBlobClient(blob_path);
execWithRetry([&](){ block_blob_client.CommitBlockList(block_ids); }, max_unexpected_write_error_retries);
LOG_TRACE(log, "Committed {} blocks for blob `{}`", block_ids.size(), blob_path);
@@ -155,14 +171,66 @@ void WriteBufferFromAzureBlobStorage::finalizeImpl()
void WriteBufferFromAzureBlobStorage::nextImpl()
{
+ if (is_prefinalized)
+ throw Exception(
+ ErrorCodes::LOGICAL_ERROR,
+ "Cannot write to prefinalized buffer for Azure Blob Storage, the file could have been created");
+
task_tracker->waitIfAny();
- writePart();
+
+ hidePartialData();
+
+ reallocateFirstBuffer();
+
+ if (available() > 0)
+ return;
+
+ detachBuffer();
+
+ if (detached_part_data.size() > 1)
+ writeMultipartUpload();
+
allocateBuffer();
}
+void WriteBufferFromAzureBlobStorage::hidePartialData()
+{
+ if (write_settings.remote_throttler)
+ write_settings.remote_throttler->add(offset(), ProfileEvents::RemoteWriteThrottlerBytes, ProfileEvents::RemoteWriteThrottlerSleepMicroseconds);
+
+ chassert(memory.size() >= hidden_size + offset());
+
+ hidden_size += offset();
+ chassert(memory.data() + hidden_size == working_buffer.begin() + offset());
+ chassert(memory.data() + hidden_size == position());
+
+ WriteBuffer::set(memory.data() + hidden_size, memory.size() - hidden_size);
+ chassert(offset() == 0);
+}
+
+void WriteBufferFromAzureBlobStorage::reallocateFirstBuffer()
+{
+ chassert(offset() == 0);
+
+ if (buffer_allocation_policy->getBufferNumber() > 1 || available() > 0)
+ return;
+
+ const size_t max_first_buffer = buffer_allocation_policy->getBufferSize();
+ if (memory.size() == max_first_buffer)
+ return;
+
+ size_t size = std::min(memory.size() * 2, max_first_buffer);
+ memory.resize(size);
+
+ WriteBuffer::set(memory.data() + hidden_size, memory.size() - hidden_size);
+ chassert(offset() == 0);
+}
+
void WriteBufferFromAzureBlobStorage::allocateBuffer()
{
buffer_allocation_policy->nextBuffer();
+ chassert(0 == hidden_size);
+
auto size = buffer_allocation_policy->getBufferSize();
if (buffer_allocation_policy->getBufferNumber() == 1)
@@ -172,30 +240,56 @@ void WriteBufferFromAzureBlobStorage::allocateBuffer()
WriteBuffer::set(memory.data(), memory.size());
}
-void WriteBufferFromAzureBlobStorage::writePart()
+void WriteBufferFromAzureBlobStorage::detachBuffer()
{
- auto data_size = size_t(position() - memory.data());
+ size_t data_size = size_t(position() - memory.data());
if (data_size == 0)
return;
- const std::string & block_id = block_ids.emplace_back(getRandomASCIIString(64));
- std::shared_ptr part_data = std::make_shared(std::move(memory), data_size, block_id);
- WriteBuffer::set(nullptr, 0);
+ chassert(data_size == hidden_size);
- auto upload_worker = [this, part_data] ()
+ auto buf = std::move(memory);
+
+ WriteBuffer::set(nullptr, 0);
+ total_size += hidden_size;
+ hidden_size = 0;
+
+ detached_part_data.push_back({std::move(buf), data_size});
+ WriteBuffer::set(nullptr, 0);
+}
+
+void WriteBufferFromAzureBlobStorage::writePart(WriteBufferFromAzureBlobStorage::PartData && part_data)
+{
+ const std::string & block_id = block_ids.emplace_back(getRandomASCIIString(64));
+ auto worker_data = std::make_shared>(block_id, std::move(part_data));
+
+ auto upload_worker = [this, worker_data] ()
{
+ auto & data_size = std::get<1>(*worker_data).data_size;
+ auto & data_block_id = std::get<0>(*worker_data);
auto block_blob_client = blob_container_client->GetBlockBlobClient(blob_path);
- Azure::Core::IO::MemoryBodyStream memory_stream(reinterpret_cast(part_data->memory.data()), part_data->data_size);
- execWithRetry([&](){ block_blob_client.StageBlock(part_data->block_id, memory_stream); }, max_unexpected_write_error_retries, part_data->data_size);
-
- if (write_settings.remote_throttler)
- write_settings.remote_throttler->add(part_data->data_size, ProfileEvents::RemoteWriteThrottlerBytes, ProfileEvents::RemoteWriteThrottlerSleepMicroseconds);
+ Azure::Core::IO::MemoryBodyStream memory_stream(reinterpret_cast(std::get<1>(*worker_data).memory.data()), data_size);
+ execWithRetry([&](){ block_blob_client.StageBlock(data_block_id, memory_stream); }, max_unexpected_write_error_retries, data_size);
};
task_tracker->add(std::move(upload_worker));
}
+void WriteBufferFromAzureBlobStorage::setFakeBufferWhenPreFinalized()
+{
+ WriteBuffer::set(fake_buffer_when_prefinalized, sizeof(fake_buffer_when_prefinalized));
+}
+
+void WriteBufferFromAzureBlobStorage::writeMultipartUpload()
+{
+ while (!detached_part_data.empty())
+ {
+ writePart(std::move(detached_part_data.front()));
+ detached_part_data.pop_front();
+ }
+}
+
}
#endif
diff --git a/src/Disks/IO/WriteBufferFromAzureBlobStorage.h b/src/Disks/IO/WriteBufferFromAzureBlobStorage.h
index 3da6d843991..10fe871a727 100644
--- a/src/Disks/IO/WriteBufferFromAzureBlobStorage.h
+++ b/src/Disks/IO/WriteBufferFromAzureBlobStorage.h
@@ -48,8 +48,13 @@ public:
private:
struct PartData;
- void writePart();
+ void writeMultipartUpload();
+ void writePart(PartData && part_data);
+ void detachBuffer();
+ void reallocateFirstBuffer();
void allocateBuffer();
+ void hidePartialData();
+ void setFakeBufferWhenPreFinalized();
void finalizeImpl() override;
void execWithRetry(std::function func, size_t num_tries, size_t cost = 0);
@@ -77,9 +82,16 @@ private:
MemoryBufferPtr allocateBuffer() const;
+ char fake_buffer_when_prefinalized[1] = {};
+
bool first_buffer=true;
+ size_t total_size = 0;
+ size_t hidden_size = 0;
+
std::unique_ptr task_tracker;
+
+ std::deque detached_part_data;
};
}
diff --git a/src/Disks/ObjectStorages/AzureBlobStorage/AzureObjectStorage.h b/src/Disks/ObjectStorages/AzureBlobStorage/AzureObjectStorage.h
index 8ead696cf78..c342929d656 100644
--- a/src/Disks/ObjectStorages/AzureBlobStorage/AzureObjectStorage.h
+++ b/src/Disks/ObjectStorages/AzureBlobStorage/AzureObjectStorage.h
@@ -166,6 +166,8 @@ public:
return client.get();
}
+ bool supportParallelWrite() const override { return true; }
+
private:
using SharedAzureClientPtr = std::shared_ptr;
void removeObjectImpl(const StoredObject & object, const SharedAzureClientPtr & client_ptr, bool if_exists);
diff --git a/src/Functions/FunctionHelpers.cpp b/src/Functions/FunctionHelpers.cpp
index c7a0c3c58ca..593646240ca 100644
--- a/src/Functions/FunctionHelpers.cpp
+++ b/src/Functions/FunctionHelpers.cpp
@@ -314,7 +314,7 @@ void checkFunctionArgumentSizes(const ColumnsWithTypeAndName & arguments, size_t
if (current_size != input_rows_count)
throw Exception(
ErrorCodes::LOGICAL_ERROR,
- "Expected the argument nº#{} ('{}' of type {}) to have {} rows, but it has {}",
+ "Expected the argument №{} ('{}' of type {}) to have {} rows, but it has {}",
i + 1,
arguments[i].name,
arguments[i].type->getName(),
diff --git a/src/Functions/FunctionsConversion.cpp b/src/Functions/FunctionsConversion.cpp
index 44d0b750af9..2a0b2f1d075 100644
--- a/src/Functions/FunctionsConversion.cpp
+++ b/src/Functions/FunctionsConversion.cpp
@@ -709,7 +709,7 @@ bool tryParseImpl(typename DataType::FieldType & x, ReadBuffer & rb, const DateL
else
return tryReadFloatTextFast(x, rb);
}
- else /*if constexpr (is_integer_v)*/
+ else /*if constexpr (is_integral_v)*/
return tryReadIntText(x, rb);
}
@@ -814,6 +814,16 @@ enum class ConvertFromStringParsingMode : uint8_t
BestEffortUS
};
+struct AccurateConvertStrategyAdditions
+{
+ UInt32 scale { 0 };
+};
+
+struct AccurateOrNullConvertStrategyAdditions
+{
+ UInt32 scale { 0 };
+};
+
template
struct ConvertThroughParsing
@@ -1020,7 +1030,13 @@ struct ConvertThroughParsing
break;
}
}
- parseImpl(vec_to[i], read_buffer, local_time_zone, precise_float_parsing);
+ if constexpr (std::is_same_v)
+ {
+ if (!tryParseImpl(vec_to[i], read_buffer, local_time_zone, precise_float_parsing))
+ throw Exception(ErrorCodes::CANNOT_PARSE_TEXT, "Cannot parse string to type {}", TypeName);
+ }
+ else
+ parseImpl(vec_to[i], read_buffer, local_time_zone, precise_float_parsing);
} while (false);
}
}
@@ -1120,16 +1136,6 @@ struct ConvertThroughParsing
/// Function toUnixTimestamp has exactly the same implementation as toDateTime of String type.
struct NameToUnixTimestamp { static constexpr auto name = "toUnixTimestamp"; };
-struct AccurateConvertStrategyAdditions
-{
- UInt32 scale { 0 };
-};
-
-struct AccurateOrNullConvertStrategyAdditions
-{
- UInt32 scale { 0 };
-};
-
enum class BehaviourOnErrorFromString : uint8_t
{
ConvertDefaultBehaviorTag,
@@ -3174,8 +3180,11 @@ private:
{
TypeIndex from_type_index = from_type->getTypeId();
WhichDataType which(from_type_index);
+ TypeIndex to_type_index = to_type->getTypeId();
+ WhichDataType to(to_type_index);
bool can_apply_accurate_cast = (cast_type == CastType::accurate || cast_type == CastType::accurateOrNull)
&& (which.isInt() || which.isUInt() || which.isFloat());
+ can_apply_accurate_cast |= cast_type == CastType::accurate && which.isStringOrFixedString() && to.isNativeInteger();
FormatSettings::DateTimeOverflowBehavior date_time_overflow_behavior = default_date_time_overflow_behavior;
if (context)
@@ -3260,6 +3269,20 @@ private:
return true;
}
}
+ else if constexpr (IsDataTypeStringOrFixedString)
+ {
+ if constexpr (IsDataTypeNumber)
+ {
+ chassert(wrapper_cast_type == CastType::accurate);
+ result_column = ConvertImpl::execute(
+ arguments,
+ result_type,
+ input_rows_count,
+ BehaviourOnErrorFromString::ConvertDefaultBehaviorTag,
+ AccurateConvertStrategyAdditions());
+ }
+ return true;
+ }
return false;
});
diff --git a/src/Functions/FunctionsRound.h b/src/Functions/FunctionsRound.h
index d2dac467bff..08e257de8ac 100644
--- a/src/Functions/FunctionsRound.h
+++ b/src/Functions/FunctionsRound.h
@@ -31,7 +31,6 @@ namespace DB
namespace ErrorCodes
{
- extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
extern const int ARGUMENT_OUT_OF_BOUND;
extern const int ILLEGAL_COLUMN;
@@ -40,26 +39,22 @@ namespace ErrorCodes
}
-/** Rounding Functions:
- * round(x, N) - rounding to nearest (N = 0 by default). Use banker's rounding for floating point numbers.
- * roundBankers(x, N) - rounding to nearest (N = 0 by default). Use banker's rounding for all numbers.
- * floor(x, N) is the largest number <= x (N = 0 by default).
- * ceil(x, N) is the smallest number >= x (N = 0 by default).
- * trunc(x, N) - is the largest by absolute value number that is not greater than x by absolute value (N = 0 by default).
- *
- * The value of the parameter N (scale):
- * - N > 0: round to the number with N decimal places after the decimal point
- * - N < 0: round to an integer with N zero characters
- * - N = 0: round to an integer
- *
- * Type of the result is the type of argument.
- * For integer arguments, when passing negative scale, overflow can occur.
- * In that case, the behavior is implementation specific.
- */
+/// Rounding Functions:
+/// - round(x, N) - rounding to nearest (N = 0 by default). Use banker's rounding for floating point numbers.
+/// - roundBankers(x, N) - rounding to nearest (N = 0 by default). Use banker's rounding for all numbers.
+/// - floor(x, N) is the largest number <= x (N = 0 by default).
+/// - ceil(x, N) is the smallest number >= x (N = 0 by default).
+/// - trunc(x, N) - is the largest by absolute value number that is not greater than x by absolute value (N = 0 by default).
+/// The value of the parameter N (scale):
+/// - N > 0: round to the number with N decimal places after the decimal point
+/// - N < 0: round to an integer with N zero characters
+/// - N = 0: round to an integer
-/** This parameter controls the behavior of the rounding functions.
- */
+/// Type of the result is the type of argument.
+/// For integer arguments, when passing negative scale, overflow can occur. In that case, the behavior is undefined.
+
+/// Controls the behavior of the rounding functions.
enum class ScaleMode : uint8_t
{
Positive, // round to a number with N decimal places after the decimal point
@@ -75,7 +70,7 @@ enum class RoundingMode : uint8_t
Ceil = _MM_FROUND_TO_POS_INF | _MM_FROUND_NO_EXC,
Trunc = _MM_FROUND_TO_ZERO | _MM_FROUND_NO_EXC,
#else
- Round = 8, /// Values are correspond to above just in case.
+ Round = 8, /// Values correspond to above values, just in case.
Floor = 9,
Ceil = 10,
Trunc = 11,
@@ -84,16 +79,21 @@ enum class RoundingMode : uint8_t
enum class TieBreakingMode : uint8_t
{
- Auto, // use banker's rounding for floating point numbers, round up otherwise
- Bankers, // use banker's rounding
+ Auto, /// banker's rounding for floating point numbers, round up otherwise
+ Bankers, /// banker's rounding
+};
+
+enum class Vectorize : uint8_t
+{
+ No,
+ Yes
};
/// For N, no more than the number of digits in the largest type.
using Scale = Int16;
-/** Rounding functions for integer values.
- */
+/// Rounding functions for integer values.
template
struct IntegerRoundingComputation
{
@@ -149,6 +149,8 @@ struct IntegerRoundingComputation
return x;
}
}
+
+ std::unreachable();
}
static ALWAYS_INLINE T compute(T x, T scale)
@@ -161,9 +163,12 @@ struct IntegerRoundingComputation
case ScaleMode::Negative:
return computeImpl(x, scale);
}
+
+ std::unreachable();
}
- static ALWAYS_INLINE void compute(const T * __restrict in, size_t scale, T * __restrict out) requires std::integral
+ static ALWAYS_INLINE void compute(const T * __restrict in, size_t scale, T * __restrict out)
+ requires std::integral
{
if constexpr (sizeof(T) <= sizeof(scale) && scale_mode == ScaleMode::Negative)
{
@@ -176,20 +181,23 @@ struct IntegerRoundingComputation
*out = compute(*in, static_cast(scale));
}
- static ALWAYS_INLINE void compute(const T * __restrict in, T scale, T * __restrict out) requires(!std::integral)
+ static ALWAYS_INLINE void compute(const T * __restrict in, T scale, T * __restrict out)
+ requires(!std::integral)
{
*out = compute(*in, scale);
}
};
+template
+class FloatRoundingComputationBase;
+
#ifdef __SSE4_1__
-template
-class BaseFloatRoundingComputation;
+/// Vectorized implementation for x86.
template <>
-class BaseFloatRoundingComputation
+class FloatRoundingComputationBase
{
public:
using ScalarType = Float32;
@@ -210,7 +218,7 @@ public:
};
template <>
-class BaseFloatRoundingComputation
+class FloatRoundingComputationBase
{
public:
using ScalarType = Float64;
@@ -230,9 +238,9 @@ public:
}
};
-#else
+#endif
-/// Implementation for ARM. Not vectorized.
+/// Sequential implementation for ARM. Also used for scalar arguments.
inline float roundWithMode(float x, RoundingMode mode)
{
@@ -243,6 +251,8 @@ inline float roundWithMode(float x, RoundingMode mode)
case RoundingMode::Ceil: return ceilf(x);
case RoundingMode::Trunc: return truncf(x);
}
+
+ std::unreachable();
}
inline double roundWithMode(double x, RoundingMode mode)
@@ -254,10 +264,12 @@ inline double roundWithMode(double x, RoundingMode mode)
case RoundingMode::Ceil: return ceil(x);
case RoundingMode::Trunc: return trunc(x);
}
+
+ std::unreachable();
}
template
-class BaseFloatRoundingComputation
+class FloatRoundingComputationBase
{
public:
using ScalarType = T;
@@ -277,15 +289,13 @@ public:
}
};
-#endif
-
/** Implementation of low-level round-off functions for floating-point values.
*/
-template
-class FloatRoundingComputation : public BaseFloatRoundingComputation
+template
+class FloatRoundingComputation : public FloatRoundingComputationBase
{
- using Base = BaseFloatRoundingComputation;
+ using Base = FloatRoundingComputationBase;
public:
static void compute(const T * __restrict in, const typename Base::VectorType & scale, T * __restrict out)
@@ -317,15 +327,22 @@ struct FloatRoundingImpl
private:
static_assert(!is_decimal);
- using Op = FloatRoundingComputation;
- using Data = std::array;
+ template
+ using Op = FloatRoundingComputation;
+ using Data = std::array::data_count>;
using ColumnType = ColumnVector;
using Container = typename ColumnType::Container;
public:
static NO_INLINE void apply(const Container & in, size_t scale, Container & out)
{
- auto mm_scale = Op::prepare(scale);
+ auto mm_scale = Op<>::prepare(scale);
const size_t data_count = std::tuple_size();
@@ -337,7 +354,7 @@ public:
while (p_in < limit)
{
- Op::compute(p_in, mm_scale, p_out);
+ Op<>::compute(p_in, mm_scale, p_out);
p_in += data_count;
p_out += data_count;
}
@@ -350,10 +367,17 @@ public:
size_t tail_size_bytes = (end_in - p_in) * sizeof(*p_in);
memcpy(&tmp_src, p_in, tail_size_bytes);
- Op::compute(reinterpret_cast(&tmp_src), mm_scale, reinterpret_cast(&tmp_dst));
+ Op<>::compute(reinterpret_cast(&tmp_src), mm_scale, reinterpret_cast(&tmp_dst));
memcpy(p_out, &tmp_dst, tail_size_bytes);
}
}
+
+ static void applyOne(T in, size_t scale, T& out)
+ {
+ using ScalarOp = Op;
+ auto s = ScalarOp::prepare(scale);
+ ScalarOp::compute(&in, s, &out);
+ }
};
template
@@ -409,6 +433,11 @@ public:
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unexpected 'scale' parameter passed to function");
}
}
+
+ static void applyOne(T in, size_t scale, T& out)
+ {
+ Op::compute(&in, scale, &out);
+ }
};
@@ -444,11 +473,40 @@ public:
memcpy(out.data(), in.data(), in.size() * sizeof(T));
}
}
+
+ static void applyOne(NativeType in, UInt32 in_scale, NativeType& out, Scale scale_arg)
+ {
+ scale_arg = in_scale - scale_arg;
+ if (scale_arg > 0)
+ {
+ auto scale = intExp10OfSize(scale_arg);
+ Op::compute(&in, scale, &out);
+ }
+ else
+ {
+ memcpy(&out, &in, sizeof(T));
+ }
+ }
};
+/// Select the appropriate processing algorithm depending on the scale.
+inline void validateScale(Int64 scale64)
+{
+ if (scale64 > std::numeric_limits::max() || scale64 < std::numeric_limits::min())
+ throw Exception(ErrorCodes::ARGUMENT_OUT_OF_BOUND, "Scale argument for rounding function is too large");
+}
-/** Select the appropriate processing algorithm depending on the scale.
- */
+inline Scale getScaleArg(const ColumnConst* scale_col)
+{
+ const auto & scale_field = scale_col->getField();
+
+ Int64 scale64 = scale_field.get();
+ validateScale(scale64);
+
+ return scale64;
+}
+
+/// Generic dispatcher
template
struct Dispatcher
{
@@ -457,30 +515,65 @@ struct Dispatcher
FloatRoundingImpl,
IntegerRoundingImpl>;
- static ColumnPtr apply(const IColumn * col_general, Scale scale_arg)
+ template
+ static ColumnPtr apply(const IColumn * value_col, const IColumn * scale_col = nullptr)
{
- const auto & col = checkAndGetColumn>(*col_general);
+ const auto & value_col_typed = checkAndGetColumn>(*value_col);
auto col_res = ColumnVector::create();
typename ColumnVector::Container & vec_res = col_res->getData();
- vec_res.resize(col.getData().size());
+ vec_res.resize(value_col_typed.getData().size());
if (!vec_res.empty())
{
- if (scale_arg == 0)
+ if (scale_col == nullptr || isColumnConst(*scale_col))
{
- size_t scale = 1;
- FunctionRoundingImpl::apply(col.getData(), scale, vec_res);
+ auto scale_arg = (scale_col == nullptr) ? 0 : getScaleArg(checkAndGetColumnConst>(scale_col));
+ if (scale_arg == 0)
+ {
+ size_t scale = 1;
+ FunctionRoundingImpl::apply(value_col_typed.getData(), scale, vec_res);
+ }
+ else if (scale_arg > 0)
+ {
+ size_t scale = intExp10(scale_arg);
+ FunctionRoundingImpl::apply(value_col_typed.getData(), scale, vec_res);
+ }
+ else
+ {
+ size_t scale = intExp10(-scale_arg);
+ FunctionRoundingImpl::apply(value_col_typed.getData(), scale, vec_res);
+ }
}
- else if (scale_arg > 0)
+ /// Non-const scale argument:
+ else if (const auto * scale_col_typed = checkAndGetColumn>(scale_col))
{
- size_t scale = intExp10(scale_arg);
- FunctionRoundingImpl::apply(col.getData(), scale, vec_res);
- }
- else
- {
- size_t scale = intExp10(-scale_arg);
- FunctionRoundingImpl::apply(col.getData(), scale, vec_res);
+ const auto & value_data = value_col_typed.getData();
+ const auto & scale_data = scale_col_typed->getData();
+ const size_t rows = value_data.size();
+
+ for (size_t i = 0; i < rows; ++i)
+ {
+ Int64 scale64 = scale_data[i];
+ validateScale(scale64);
+ Scale raw_scale = scale64;
+
+ if (raw_scale == 0)
+ {
+ size_t scale = 1;
+ FunctionRoundingImpl::applyOne(value_data[i], scale, vec_res[i]);
+ }
+ else if (raw_scale > 0)
+ {
+ size_t scale = intExp10(raw_scale);
+ FunctionRoundingImpl::applyOne(value_data[i], scale, vec_res[i]);
+ }
+ else
+ {
+ size_t scale = intExp10(-raw_scale);
+ FunctionRoundingImpl::applyOne(value_data[i], scale, vec_res[i]);
+ }
+ }
}
}
@@ -488,28 +581,51 @@ struct Dispatcher
}
};
+/// Dispatcher for Decimal inputs
template
struct Dispatcher
{
public:
- static ColumnPtr apply(const IColumn * col_general, Scale scale_arg)
+ template
+ static ColumnPtr apply(const IColumn * value_col, const IColumn * scale_col = nullptr)
{
- const auto & col = checkAndGetColumn>(*col_general);
- const typename ColumnDecimal::Container & vec_src = col.getData();
+ const auto & value_col_typed = checkAndGetColumn>(*value_col);
+ const typename ColumnDecimal::Container & vec_src = value_col_typed.getData();
- auto col_res = ColumnDecimal::create(vec_src.size(), col.getScale());
+ auto col_res = ColumnDecimal::create(vec_src.size(), value_col_typed.getScale());
auto & vec_res = col_res->getData();
if (!vec_res.empty())
- DecimalRoundingImpl::apply(col.getData(), col.getScale(), vec_res, scale_arg);
+ {
+ if (scale_col == nullptr || isColumnConst(*scale_col))
+ {
+ auto scale_arg = scale_col == nullptr ? 0 : getScaleArg(checkAndGetColumnConst>(scale_col));
+ DecimalRoundingImpl::apply(value_col_typed.getData(), value_col_typed.getScale(), vec_res, scale_arg);
+ }
+ /// Non-const scale argument
+ else if (const auto * scale_col_typed = checkAndGetColumn>(scale_col))
+ {
+ const auto & scale = scale_col_typed->getData();
+ const size_t rows = vec_src.size();
+
+ for (size_t i = 0; i < rows; ++i)
+ {
+ Int64 scale64 = scale[i];
+ validateScale(scale64);
+ Scale raw_scale = scale64;
+
+ DecimalRoundingImpl::applyOne(value_col_typed.getElement(i), value_col_typed.getScale(),
+ reinterpret_cast::NativeT&>(col_res->getElement(i)), raw_scale);
+ }
+ }
+ }
return col_res;
}
};
-/** A template for functions that round the value of an input parameter of type
- * (U)Int8/16/32/64, Float32/64 or Decimal32/64/128, and accept an additional optional parameter (default is 0).
- */
+/// Functions that round the value of an input parameter of type (U)Int8/16/32/64, Float32/64 or Decimal32/64/128.
+/// Accept an additional optional parameter of type (U)Int8/16/32/64 (0 by default).
template
class FunctionRounding : public IFunction
{
@@ -517,75 +633,58 @@ public:
static constexpr auto name = Name::name;
static FunctionPtr create(ContextPtr) { return std::make_shared(); }
- String getName() const override
- {
- return name;
- }
-
+ String getName() const override { return name; }
bool isVariadic() const override { return true; }
size_t getNumberOfArguments() const override { return 0; }
bool isSuitableForShortCircuitArgumentsExecution(const DataTypesWithConstInfo & /*arguments*/) const override { return false; }
-
- /// Get result types by argument types. If the function does not apply to these arguments, throw an exception.
- DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override
- {
- if ((arguments.empty()) || (arguments.size() > 2))
- throw Exception(ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
- "Number of arguments for function {} doesn't match: passed {}, should be 1 or 2.",
- getName(), arguments.size());
-
- for (const auto & type : arguments)
- if (!isNumber(type))
- throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of argument of function {}",
- arguments[0]->getName(), getName());
-
- return arguments[0];
- }
-
- static Scale getScaleArg(const ColumnsWithTypeAndName & arguments)
- {
- if (arguments.size() == 2)
- {
- const IColumn & scale_column = *arguments[1].column;
- if (!isColumnConst(scale_column))
- throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Scale argument for rounding functions must be constant");
-
- Field scale_field = assert_cast(scale_column).getField();
- if (scale_field.getType() != Field::Types::UInt64
- && scale_field.getType() != Field::Types::Int64)
- throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Scale argument for rounding functions must have integer type");
-
- Int64 scale64 = scale_field.get();
- if (scale64 > std::numeric_limits::max()
- || scale64 < std::numeric_limits::min())
- throw Exception(ErrorCodes::ARGUMENT_OUT_OF_BOUND, "Scale argument for rounding function is too large");
-
- return scale64;
- }
- return 0;
- }
-
bool useDefaultImplementationForConstants() const override { return true; }
- ColumnNumbers getArgumentsThatAreAlwaysConstant() const override { return {1}; }
+
+ DataTypePtr getReturnTypeImpl(const ColumnsWithTypeAndName & arguments) const override
+ {
+ FunctionArgumentDescriptors mandatory_args{
+ {"x", static_cast(&isNumber), nullptr, "A number to round"},
+ };
+ FunctionArgumentDescriptors optional_args{
+ {"N", static_cast(&isNativeInteger), nullptr, "The number of decimal places to round to"},
+ };
+ validateFunctionArgumentTypes(*this, arguments, mandatory_args, optional_args);
+
+ return arguments[0].type;
+ }
ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
{
- const ColumnWithTypeAndName & column = arguments[0];
- Scale scale_arg = getScaleArg(arguments);
+ const ColumnWithTypeAndName & value_arg = arguments[0];
ColumnPtr res;
- auto call = [&](const auto & types) -> bool
+ auto call_data = [&](const auto & types) -> bool
{
using Types = std::decay_t;
- using DataType = typename Types::LeftType;
+ using DataType = typename Types::RightType;
- if constexpr (IsDataTypeNumber || IsDataTypeDecimal)
+ if (arguments.size() > 1)
{
- using FieldType = typename DataType::FieldType;
- res = Dispatcher::apply(column.column.get(), scale_arg);
+ const ColumnWithTypeAndName & scale_column = arguments[1];
+
+ auto call_scale = [&](const auto & scaleTypes) -> bool
+ {
+ using ScaleTypes = std::decay_t;
+ using ScaleType = typename ScaleTypes::RightType;
+
+ if (isColumnConst(*value_arg.column) && !isColumnConst(*scale_column.column))
+ throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Scale column must be const for const data column");
+
+ res = Dispatcher::template apply(value_arg.column.get(), scale_column.column.get());
+ return true;
+ };
+
+ TypeIndex right_index = scale_column.type->getTypeId();
+ if (!callOnBasicType(right_index, call_scale))
+ throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Scale argument for rounding functions must have integer type");
return true;
}
- return false;
+ res = Dispatcher::template apply(value_arg.column.get());
+ return true;
};
#if !defined(__SSE4_1__)
@@ -597,10 +696,9 @@ public:
throw Exception(ErrorCodes::CANNOT_SET_ROUNDING_MODE, "Cannot set floating point rounding mode");
#endif
- if (!callOnIndexAndDataType(column.type->getTypeId(), call))
- {
- throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of argument of function {}", column.name, getName());
- }
+ TypeIndex left_index = value_arg.type->getTypeId();
+ if (!callOnBasicType(left_index, call_data))
+ throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of argument of function {}", value_arg.name, getName());
return res;
}
@@ -617,9 +715,8 @@ public:
};
-/** Rounds down to a number within explicitly specified array.
- * If the value is less than the minimal bound - returns the minimal bound.
- */
+/// Rounds down to a number within explicitly specified array.
+/// If the value is less than the minimal bound - returns the minimal bound.
class FunctionRoundDown : public IFunction
{
public:
@@ -627,7 +724,6 @@ public:
static FunctionPtr create(ContextPtr) { return std::make_shared(); }
String getName() const override { return name; }
-
bool isVariadic() const override { return false; }
size_t getNumberOfArguments() const override { return 2; }
bool useDefaultImplementationForConstants() const override { return true; }
diff --git a/src/Functions/geometryConverters.h b/src/Functions/geometryConverters.h
index 97162fa9dd0..03831d37e0c 100644
--- a/src/Functions/geometryConverters.h
+++ b/src/Functions/geometryConverters.h
@@ -28,6 +28,9 @@ namespace ErrorCodes
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
}
+template
+using LineString = boost::geometry::model::linestring;
+
template
using Ring = boost::geometry::model::ring;
@@ -38,11 +41,13 @@ template
using MultiPolygon = boost::geometry::model::multi_polygon>;
using CartesianPoint = boost::geometry::model::d2::point_xy;
+using CartesianLineString = LineString;
using CartesianRing = Ring;
using CartesianPolygon = Polygon;
using CartesianMultiPolygon = MultiPolygon;
using SphericalPoint = boost::geometry::model::point>;
+using SphericalLineString = LineString;
using SphericalRing = Ring;
using SphericalPolygon = Polygon;
using SphericalMultiPolygon = MultiPolygon;
@@ -85,6 +90,29 @@ struct ColumnToPointsConverter
}
};
+
+/**
+ * Class which converts Column with type Array(Tuple(Float64, Float64)) to a vector of boost linestring type.
+*/
+template
+struct ColumnToLineStringsConverter
+{
+ static std::vector> convert(ColumnPtr col)
+ {
+ const IColumn::Offsets & offsets = typeid_cast(*col).getOffsets();
+ size_t prev_offset = 0;
+ std::vector> answer;
+ answer.reserve(offsets.size());
+ auto tmp = ColumnToPointsConverter::convert(typeid_cast(*col).getDataPtr());
+ for (size_t offset : offsets)
+ {
+ answer.emplace_back(tmp.begin() + prev_offset, tmp.begin() + offset);
+ prev_offset = offset;
+ }
+ return answer;
+ }
+};
+
/**
* Class which converts Column with type Array(Tuple(Float64, Float64)) to a vector of boost ring type.
*/
@@ -208,6 +236,39 @@ private:
ColumnFloat64::Container & second_container;
};
+/// Serialize Point, LineString as LineString
+template
+class LineStringSerializer
+{
+public:
+ LineStringSerializer()
+ : offsets(ColumnUInt64::create())
+ {}
+
+ explicit LineStringSerializer(size_t n)
+ : offsets(ColumnUInt64::create(n))
+ {}
+
+ void add(const LineString & ring)
+ {
+ size += ring.size();
+ offsets->insertValue(size);
+ for (const auto & point : ring)
+ point_serializer.add(point);
+ }
+
+ ColumnPtr finalize()
+ {
+ return ColumnArray::create(point_serializer.finalize(), std::move(offsets));
+ }
+
+private:
+ size_t size = 0;
+ PointSerializer point_serializer;
+ ColumnUInt64::MutablePtr offsets;
+};
+
+/// Almost the same as LineStringSerializer
/// Serialize Point, Ring as Ring
template
class RingSerializer
@@ -344,8 +405,16 @@ static void callOnGeometryDataType(DataTypePtr type, F && f)
/// There is no Point type, because for most of geometry functions it is useless.
if (factory.get("Point")->equals(*type))
return f(ConverterType>());
+
+ /// We should take the name into consideration to avoid ambiguity.
+ /// Because for example both Ring and LineString are resolved to Array(Tuple(Point)).
+ else if (factory.get("LineString")->equals(*type) && type->getCustomName() && type->getCustomName()->getName() == "LineString")
+ return f(ConverterType>());
+
+ /// For backward compatibility if we call this function not on a custom type, we will consider Array(Tuple(Point)) as type Ring.
else if (factory.get("Ring")->equals(*type))
return f(ConverterType>());
+
else if (factory.get("Polygon")->equals(*type))
return f(ConverterType>());
else if (factory.get("MultiPolygon")->equals(*type))
diff --git a/src/Functions/polygonsIntersection.cpp b/src/Functions/polygonsIntersection.cpp
index 77484e7e63c..329242e762e 100644
--- a/src/Functions/polygonsIntersection.cpp
+++ b/src/Functions/polygonsIntersection.cpp
@@ -73,6 +73,8 @@ public:
if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be Point", getName());
+ else if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
+ throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be LineString", getName());
else
{
auto first = LeftConverter::convert(arguments[0].column->convertToFullColumnIfConst());
diff --git a/src/Functions/polygonsSymDifference.cpp b/src/Functions/polygonsSymDifference.cpp
index 194b7f2cfd7..3c219d0facb 100644
--- a/src/Functions/polygonsSymDifference.cpp
+++ b/src/Functions/polygonsSymDifference.cpp
@@ -71,6 +71,8 @@ public:
if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be Point", getName());
+ else if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
+ throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be LineString", getName());
else
{
auto first = LeftConverter::convert(arguments[0].column->convertToFullColumnIfConst());
diff --git a/src/Functions/polygonsUnion.cpp b/src/Functions/polygonsUnion.cpp
index 37d865af50a..969eb2f78fb 100644
--- a/src/Functions/polygonsUnion.cpp
+++ b/src/Functions/polygonsUnion.cpp
@@ -71,6 +71,8 @@ public:
if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be Point", getName());
+ else if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
+ throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be LineString", getName());
else
{
auto first = LeftConverter::convert(arguments[0].column->convertToFullColumnIfConst());
diff --git a/src/Functions/polygonsWithin.cpp b/src/Functions/polygonsWithin.cpp
index 35a9e17cdfd..c63ad5ef868 100644
--- a/src/Functions/polygonsWithin.cpp
+++ b/src/Functions/polygonsWithin.cpp
@@ -75,6 +75,8 @@ public:
if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be Point", getName());
+ else if constexpr (std::is_same_v, LeftConverter> || std::is_same_v, RightConverter>)
+ throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Any argument of function {} must not be LineString", getName());
else
{
auto first = LeftConverter::convert(arguments[0].column->convertToFullColumnIfConst());
diff --git a/src/Functions/readWkt.cpp b/src/Functions/readWkt.cpp
index ddc847b1ca5..eb262777b0d 100644
--- a/src/Functions/readWkt.cpp
+++ b/src/Functions/readWkt.cpp
@@ -82,6 +82,11 @@ struct ReadWKTPointNameHolder
static constexpr const char * name = "readWKTPoint";
};
+struct ReadWKTLineStringNameHolder
+{
+ static constexpr const char * name = "readWKTLineString";
+};
+
struct ReadWKTRingNameHolder
{
static constexpr const char * name = "readWKTRing";
@@ -102,6 +107,30 @@ struct ReadWKTMultiPolygonNameHolder
REGISTER_FUNCTION(ReadWKT)
{
factory.registerFunction, ReadWKTPointNameHolder>>();
+ factory.registerFunction, ReadWKTLineStringNameHolder>>(FunctionDocumentation
+ {
+ .description=R"(
+Parses a Well-Known Text (WKT) representation of a LineString geometry and returns it in the internal ClickHouse format.
+)",
+ .syntax = "readWKTLineString(wkt_string)",
+ .arguments{
+ {"wkt_string", "The input WKT string representing a LineString geometry."}
+ },
+ .returned_value = "The function returns a ClickHouse internal representation of the linestring geometry.",
+ .examples{
+ {"first call", "SELECT readWKTLineString('LINESTRING (1 1, 2 2, 3 3, 1 1)');", R"(
+┌─readWKTLineString('LINESTRING (1 1, 2 2, 3 3, 1 1)')─┐
+│ [(1,1),(2,2),(3,3),(1,1)] │
+└──────────────────────────────────────────────────────┘
+ )"},
+ {"second call", "SELECT toTypeName(readWKTLineString('LINESTRING (1 1, 2 2, 3 3, 1 1)'));", R"(
+┌─toTypeName(readWKTLineString('LINESTRING (1 1, 2 2, 3 3, 1 1)'))─┐
+│ LineString │
+└──────────────────────────────────────────────────────────────────┘
+ )"},
+ },
+ .categories{"Unique identifiers"}
+ });
factory.registerFunction, ReadWKTRingNameHolder>>();
factory.registerFunction, ReadWKTPolygonNameHolder>>();
factory.registerFunction, ReadWKTMultiPolygonNameHolder>>();
diff --git a/src/Functions/tupleConcat.cpp b/src/Functions/tupleConcat.cpp
index c48e4d61463..c9cdae10bcf 100644
--- a/src/Functions/tupleConcat.cpp
+++ b/src/Functions/tupleConcat.cpp
@@ -61,7 +61,7 @@ public:
return std::make_shared(tuple_arg_types);
}
- ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t) const override
+ ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
{
const size_t num_arguments = arguments.size();
Columns columns;
@@ -92,6 +92,9 @@ public:
columns.push_back(inner_col);
}
+ if (columns.empty())
+ return ColumnTuple::create(input_rows_count);
+
return ColumnTuple::create(columns);
}
};
diff --git a/src/Functions/wkt.cpp b/src/Functions/wkt.cpp
index afcfabd0bf4..678ec02d229 100644
--- a/src/Functions/wkt.cpp
+++ b/src/Functions/wkt.cpp
@@ -41,6 +41,14 @@ public:
bool isSuitableForShortCircuitArgumentsExecution(const DataTypesWithConstInfo & /*arguments*/) const override { return true; }
+ /*
+ * Functions like recursiveRemoveLowCardinality don't pay enough attention to custom types and just erase
+ * the information about it during type conversions.
+ * While it is a big problem the quick solution would be just to disable default low cardinality implementation
+ * because it doesn't make a lot of sense for geo types.
+ */
+ bool useDefaultImplementationForLowCardinalityColumns() const override { return false; }
+
ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & /*result_type*/, size_t input_rows_count) const override
{
auto res_column = ColumnString::create();
diff --git a/src/IO/Archives/IArchiveReader.h b/src/IO/Archives/IArchiveReader.h
index ee516d2655b..d7758b9e401 100644
--- a/src/IO/Archives/IArchiveReader.h
+++ b/src/IO/Archives/IArchiveReader.h
@@ -5,6 +5,7 @@
#include
#include
+#include
namespace DB
{
@@ -25,6 +26,7 @@ public:
{
UInt64 uncompressed_size;
UInt64 compressed_size;
+ Poco::Timestamp last_modified;
bool is_encrypted;
};
diff --git a/src/IO/Archives/LibArchiveReader.cpp b/src/IO/Archives/LibArchiveReader.cpp
index bec7f587180..e3fe63fa40d 100644
--- a/src/IO/Archives/LibArchiveReader.cpp
+++ b/src/IO/Archives/LibArchiveReader.cpp
@@ -157,6 +157,7 @@ public:
file_info.emplace();
file_info->uncompressed_size = archive_entry_size(current_entry);
file_info->compressed_size = archive_entry_size(current_entry);
+ file_info->last_modified = archive_entry_mtime(current_entry);
file_info->is_encrypted = false;
}
diff --git a/src/IO/S3/Client.h b/src/IO/S3/Client.h
index bd281846343..1e90acb7f7b 100644
--- a/src/IO/S3/Client.h
+++ b/src/IO/S3/Client.h
@@ -162,7 +162,7 @@ public:
class RetryStrategy : public Aws::Client::RetryStrategy
{
public:
- explicit RetryStrategy(uint32_t maxRetries_ = 10, uint32_t scaleFactor_ = 25, uint32_t maxDelayMs_ = 90000);
+ explicit RetryStrategy(uint32_t maxRetries_ = 10, uint32_t scaleFactor_ = 25, uint32_t maxDelayMs_ = 5000);
/// NOLINTNEXTLINE(google-runtime-int)
bool ShouldRetry(const Aws::Client::AWSError& error, long attemptedRetries) const override;
diff --git a/src/Interpreters/ActionsDAG.cpp b/src/Interpreters/ActionsDAG.cpp
index cfccc835d29..54db8980e12 100644
--- a/src/Interpreters/ActionsDAG.cpp
+++ b/src/Interpreters/ActionsDAG.cpp
@@ -596,6 +596,34 @@ void ActionsDAG::removeUnusedActions(const std::unordered_set & us
std::erase_if(inputs, [&](const Node * node) { return !visited_nodes.contains(node); });
}
+
+void ActionsDAG::removeAliasesForFilter(const std::string & filter_name)
+{
+ const auto & filter_node = findInOutputs(filter_name);
+ std::stack stack;
+ stack.push(const_cast(&filter_node));
+
+ std::unordered_set visited;
+ visited.insert(stack.top());
+
+ while (!stack.empty())
+ {
+ auto * node = stack.top();
+ stack.pop();
+ for (auto & child : node->children)
+ {
+ while (child->type == ActionType::ALIAS)
+ child = child->children.front();
+
+ if (!visited.contains(child))
+ {
+ stack.push(const_cast(child));
+ visited.insert(child);
+ }
+ }
+ }
+}
+
ActionsDAGPtr ActionsDAG::cloneSubDAG(const NodeRawConstPtrs & outputs, bool remove_aliases)
{
auto actions = std::make_shared();
@@ -1704,7 +1732,7 @@ void ActionsDAG::mergeNodes(ActionsDAG && second, NodeRawConstPtrs * out_outputs
}
}
-ActionsDAG::SplitResult ActionsDAG::split(std::unordered_set split_nodes, bool create_split_nodes_mapping) const
+ActionsDAG::SplitResult ActionsDAG::split(std::unordered_set split_nodes, bool create_split_nodes_mapping, bool avoid_duplicate_inputs) const
{
/// Split DAG into two parts.
/// (first_nodes, first_outputs) is a part which will have split_list in result.
@@ -1718,6 +1746,14 @@ ActionsDAG::SplitResult ActionsDAG::split(std::unordered_set