thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-19 16:20:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'ClickHouse:master' into hive_partitioning_filtration

Browse Source
This commit is contained in:
Yarik Briukhovetskyi 2024-09-17 18:50:43 +02:00 committed by GitHub
commit f52cdfb795
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
834 changed files with 19064 additions and 5383 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
.github/actions/debug/action.yml vendored
View File

@ -4,15 +4,31 @@ description: Prints workflow debug info
runs:
using: "composite"
steps:
- name: Print envs
- name: Envs, event.json and contexts
shell: bash
run: |
echo "::group::Envs"
env
echo "::endgroup::"
- name: Print Event.json
shell: bash
run: |
echo "::group::Event.json"
echo '::group::Environment variables'
env | sort
echo '::endgroup::'
echo '::group::event.json'
python3 -m json.tool "$GITHUB_EVENT_PATH"
echo "::endgroup::"
echo '::endgroup::'
cat << 'EOF'
::group::github context
${{ toJSON(github) }}
::endgroup::
::group::env context
${{ toJSON(env) }}
::endgroup::
::group::runner context
${{ toJSON(runner) }}
::endgroup::
::group::job context
${{ toJSON(job) }}
::endgroup::
EOF

2
.github/workflows/backport_branches.yml vendored
View File

@ -27,6 +27,8 @@ jobs:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: Labels check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"

2
.github/workflows/cherry_pick.yml vendored
View File

@ -33,6 +33,8 @@ jobs:
clear-repository: true
token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
fetch-depth: 0
- name: Debug Info
uses: ./.github/actions/debug
- name: Cherry pick
run: |
cd "$GITHUB_WORKSPACE/tests/ci"

4
.github/workflows/create_release.yml vendored
View File

@ -56,13 +56,13 @@ jobs:
GH_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
runs-on: [self-hosted, release-maker]
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
fetch-depth: 0
- name: Debug Info
uses: ./.github/actions/debug
- name: Prepare Release Info
shell: bash
run: |

1
.github/workflows/docker_test_images.yml vendored
View File

@ -11,6 +11,7 @@ name: Build docker images
required: false
type: boolean
default: false
jobs:
DockerBuildAarch64:
runs-on: [self-hosted, style-checker-aarch64]

5
.github/workflows/jepsen.yml vendored
View File

@ -8,20 +8,21 @@ on: # yamllint disable-line rule:truthy
schedule:
- cron: '0 */6 * * *'
workflow_dispatch:
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: PrepareRunConfig
id: runconfig
run: |

4
.github/workflows/master.yml vendored
View File

@ -15,14 +15,14 @@ jobs:
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: Merge sync PR
run: |
cd "$GITHUB_WORKSPACE/tests/ci"

4
.github/workflows/merge_queue.yml vendored
View File

@ -14,14 +14,14 @@ jobs:
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get a version
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: Cancel PR workflow
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run

4
.github/workflows/nightly.yml vendored
View File

@ -15,14 +15,14 @@ jobs:
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: PrepareRunConfig
id: runconfig
run: |

4
.github/workflows/pull_request.yml vendored
View File

@ -25,14 +25,14 @@ jobs:
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get a version
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: Cancel previous Sync PR workflow
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run

2
.github/workflows/release_branches.yml vendored
View File

@ -24,6 +24,8 @@ jobs:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: Labels check
run: |
cd "$GITHUB_WORKSPACE/tests/ci"

4
.github/workflows/reusable_simple_job.yml vendored
View File

@ -62,8 +62,6 @@ jobs:
env:
GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
@ -72,6 +70,8 @@ jobs:
submodules: ${{inputs.submodules}}
fetch-depth: ${{inputs.checkout_depth}}
filter: tree:0
- name: Debug Info
uses: ./.github/actions/debug
- name: Set build envs
run: |
cat >> "$GITHUB_ENV" << 'EOF'

6
.gitmodules vendored
View File

@ -170,9 +170,6 @@
[submodule "contrib/fast_float"]
path = contrib/fast_float
url = https://github.com/fastfloat/fast_float
[submodule "contrib/libpq"]
path = contrib/libpq
url = https://github.com/ClickHouse/libpq
[submodule "contrib/NuRaft"]
path = contrib/NuRaft
url = https://github.com/ClickHouse/NuRaft
@ -369,3 +366,6 @@
[submodule "contrib/numactl"]
path = contrib/numactl
url = https://github.com/ClickHouse/numactl.git
[submodule "contrib/postgres"]
path = contrib/postgres
url = https://github.com/ClickHouse/postgres.git

31
CITATION.cff Normal file
View File

@ -0,0 +1,31 @@
# This CITATION.cff file was generated with cffinit.
cff-version: 1.2.0
title: "ClickHouse"
message: "If you use this software, please cite it as below."
type: software
authors:
- family-names: "Milovidov"
given-names: "Alexey"
repository-code: 'https://github.com/ClickHouse/ClickHouse'
url: 'https://clickhouse.com'
license: Apache-2.0
preferred-citation:
type: article
authors:
- family-names: "Schulze"
given-names: "Robert"
- family-names: "Schreiber"
given-names: "Tom"
- family-names: "Yatsishin"
given-names: "Ilya"
- family-names: "Dahimene"
given-names: "Ryadh"
- family-names: "Milovidov"
given-names: "Alexey"
journal: "Proceedings of the VLDB Endowment"
title: "ClickHouse - Lightning Fast Analytics for Everyone"
year: 2024
volume: 17
issue: 12
doi: 10.14778/3685800.3685802

18
README.md
View File

@ -42,21 +42,19 @@ Keep an eye out for upcoming meetups and events around the world. Somewhere else
The following upcoming meetups are featuring creator of ClickHouse & CTO, Alexey Milovidov:
* [ClickHouse Guangzhou User Group Meetup](https://mp.weixin.qq.com/s/GSvo-7xUoVzCsuUvlLTpCw) - August 25
* [San Francisco Meetup (Cloudflare)](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/302540575) - September 5
* [Raleigh Meetup (Deutsche Bank)](https://www.meetup.com/triangletechtalks/events/302723486/) - September 9
* [New York Meetup (Rokt)](https://www.meetup.com/clickhouse-new-york-user-group/events/302575342) - September 10
* [Chicago Meetup (Jump Capital)](https://lu.ma/43tvmrfw) - September 12
Other upcoming meetups
* [Seattle Meetup (Statsig)](https://www.meetup.com/clickhouse-seattle-user-group/events/302518075/) - August 27
* [Melbourne Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302732666/) - August 27
* [Sydney Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302862966/) - September 5
* [Zurich Meetup](https://www.meetup.com/clickhouse-switzerland-meetup-group/events/302267429/) - September 5
* [Toronto Meetup (Shopify)](https://www.meetup.com/clickhouse-toronto-user-group/events/301490855/) - September 10
* [Austin Meetup](https://www.meetup.com/clickhouse-austin-user-group/events/302558689/) - September 17
* [London Meetup](https://www.meetup.com/clickhouse-london-user-group/events/302977267) - September 17
* [Bangalore Meetup](https://www.meetup.com/clickhouse-bangalore-user-group/events/303208274/) - September 18
* [Tel Aviv Meetup](https://www.meetup.com/clickhouse-meetup-israel/events/303095121) - September 22
* [Jakarta Meetup](https://www.meetup.com/clickhouse-indonesia-user-group/events/303191359/) - October 1
* [Singapore Meetup](https://www.meetup.com/clickhouse-singapore-meetup-group/events/303212064/) - October 3
* [Madrid Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096564/) - October 22
* [Barcelona Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096876/) - October 29
* [Oslo Meetup](https://www.meetup.com/open-source-real-time-data-warehouse-real-time-analytics/events/302938622) - October 31
@ -64,7 +62,13 @@ Other upcoming meetups
* [Dubai Meetup](https://www.meetup.com/clickhouse-dubai-meetup-group/events/303096989/) - November 21
* [Paris Meetup](https://www.meetup.com/clickhouse-france-user-group/events/303096434) - November 26
Recently completed events
* [ClickHouse Guangzhou User Group Meetup](https://mp.weixin.qq.com/s/GSvo-7xUoVzCsuUvlLTpCw) - August 25
* [Seattle Meetup (Statsig)](https://www.meetup.com/clickhouse-seattle-user-group/events/302518075/) - August 27
* [Melbourne Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302732666/) - August 27
* [Sydney Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302862966/) - September 5
* [Zurich Meetup](https://www.meetup.com/clickhouse-switzerland-meetup-group/events/302267429/) - September 5
* [San Francisco Meetup (Cloudflare)](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/302540575) - September 5
## Recent Recordings
* **Recent Meetup Videos**: [Meetup Playlist](https://www.youtube.com/playlist?list=PL0Z2YDlm0b3iNDUzpY1S3L_iV4nARda_U) Whenever possible recordings of the ClickHouse Community Meetups are edited and presented as individual talks. Current featuring "Modern SQL in 2023", "Fast, Concurrent, and Consistent Asynchronous INSERTS in ClickHouse", and "Full-Text Indices: Design and Experiments"

15
base/harmful/harmful.c
View File

@ -66,13 +66,11 @@ TRAP(gethostbyname)
TRAP(gethostbyname2)
TRAP(gethostent)
TRAP(getlogin)
TRAP(getmntent)
TRAP(getnetbyaddr)
TRAP(getnetbyname)
TRAP(getnetent)
TRAP(getnetgrent)
TRAP(getnetgrent_r)
TRAP(getopt)
TRAP(getopt_long)
TRAP(getopt_long_only)
TRAP(getpass)
@ -133,7 +131,6 @@ TRAP(nrand48)
TRAP(__ppc_get_timebase_freq)
TRAP(ptsname)
TRAP(putchar_unlocked)
TRAP(putenv)
TRAP(pututline)
TRAP(pututxline)
TRAP(putwchar_unlocked)
@ -148,7 +145,6 @@ TRAP(sethostent)
TRAP(sethostid)
TRAP(setkey)
//TRAP(setlocale) // Used by replxx at startup
TRAP(setlogmask)
TRAP(setnetent)
TRAP(setnetgrent)
TRAP(setprotoent)
@ -203,7 +199,6 @@ TRAP(lgammal)
TRAP(nftw)
TRAP(nl_langinfo)
TRAP(putc_unlocked)
TRAP(rand)
/** In the current POSIX.1 specification (POSIX.1-2008), readdir() is not required to be thread-safe. However, in modern
* implementations (including the glibc implementation), concurrent calls to readdir() that specify different directory streams
* are thread-safe. In cases where multiple threads must read from the same directory stream, using readdir() with external
@ -288,4 +283,14 @@ TRAP(tss_get)
TRAP(tss_set)
TRAP(tss_delete)
#ifndef USE_MUSL
/// These produce duplicate symbol errors when statically linking with musl.
/// Maybe we can remove them from the musl fork.
TRAP(getopt)
TRAP(putenv)
TRAP(setlogmask)
TRAP(rand)
TRAP(getmntent)
#endif
#endif

19
base/poco/Crypto/include/Poco/Crypto/EVPPKey.h
View File

@ -188,8 +188,9 @@ namespace Crypto
pFile = fopen(keyFile.c_str(), "r");
if (pFile)
{
pem_password_cb * pCB = pass.empty() ? (pem_password_cb *)0 : &passCB;
void * pPassword = pass.empty() ? (void *)0 : (void *)pass.c_str();
pem_password_cb * pCB = &passCB;
static constexpr char * no_password = "";
void * pPassword = pass.empty() ? (void *)no_password : (void *)pass.c_str();
if (readFunc(pFile, &pKey, pCB, pPassword))
{
fclose(pFile);
@ -225,6 +226,13 @@ namespace Crypto
error:
if (pFile)
fclose(pFile);
if (*ppKey)
{
if constexpr (std::is_same_v<K, EVP_PKEY>)
EVP_PKEY_free(*ppKey);
else
EC_KEY_free(*ppKey);
}
throw OpenSSLException("EVPKey::loadKey(string)");
}
@ -286,6 +294,13 @@ namespace Crypto
error:
if (pBIO)
BIO_free(pBIO);
if (*ppKey)
{
if constexpr (std::is_same_v<K, EVP_PKEY>)
EVP_PKEY_free(*ppKey);
else
EC_KEY_free(*ppKey);
}
throw OpenSSLException("EVPKey::loadKey(stream)");
}

8
base/poco/Foundation/src/Path_UNIX.cpp
View File

@ -48,25 +48,17 @@ std::string PathImpl::currentImpl()
std::string PathImpl::homeImpl()
{
std::string path;
#if defined(_POSIX_C_SOURCE) || defined(_BSD_SOURCE) || defined(_POSIX_C_SOURCE)
size_t buf_size = 1024; // Same as glibc use for getpwuid
std::vector<char> buf(buf_size);
struct passwd res;
struct passwd* pwd = nullptr;
getpwuid_r(getuid(), &res, buf.data(), buf_size, &pwd);
#else
struct passwd* pwd = getpwuid(getuid());
#endif
if (pwd)
path = pwd->pw_dir;
else
{
#if defined(_POSIX_C_SOURCE) || defined(_BSD_SOURCE) || defined(_POSIX_C_SOURCE)
getpwuid_r(getuid(), &res, buf.data(), buf_size, &pwd);
#else
pwd = getpwuid(geteuid());
#endif
if (pwd)
path = pwd->pw_dir;
else

10
base/poco/NetSSL_OpenSSL/include/Poco/Net/Context.h
View File

@ -248,6 +248,9 @@ namespace Net
SSL_CTX * sslContext() const;
/// Returns the underlying OpenSSL SSL Context object.
SSL_CTX * takeSslContext();
/// Takes ownership of the underlying OpenSSL SSL Context object.
Usage usage() const;
/// Returns whether the context is for use by a client or by a server
/// and whether TLSv1 is required.
@ -401,6 +404,13 @@ namespace Net
return _pSSLContext;
}
inline SSL_CTX * Context::takeSslContext()
{
auto * result = _pSSLContext;
_pSSLContext = nullptr;
return result;
}
inline bool Context::extendedCertificateVerificationEnabled() const
{

5
base/poco/NetSSL_OpenSSL/src/Context.cpp
View File

@ -106,6 +106,11 @@ Context::Context(
Context::~Context()
{
if (_pSSLContext == nullptr)
{
return;
}
try
{
SSL_CTX_free(_pSSLContext);

2
base/poco/Util/CMakeLists.txt
View File

@ -18,4 +18,4 @@ target_compile_options (_poco_util
-Wno-zero-as-null-pointer-constant
)
target_include_directories (_poco_util SYSTEM PUBLIC "include")
target_link_libraries (_poco_util PUBLIC Poco::JSON Poco::XML)
target_link_libraries (_poco_util PUBLIC Poco::JSON Poco::XML Poco::Net)

37
base/poco/Util/include/Poco/Util/AbstractConfiguration.h
View File

@ -241,6 +241,20 @@ namespace Util
/// If the value contains references to other properties (${<property>}), these
/// are expanded.
std::string getHost(const std::string & key) const;
/// Returns the string value of the host property with the given name.
/// Throws a NotFoundException if the key does not exist.
/// Throws a SyntaxException if the property is not a valid host (IP address or domain).
/// If the value contains references to other properties (${<property>}), these
/// are expanded.
std::string getHost(const std::string & key, const std::string & defaultValue) const;
/// If a property with the given key exists, returns the host property's string value,
/// otherwise returns the given default value.
/// Throws a SyntaxException if the property is not a valid host (IP address or domain).
/// If the value contains references to other properties (${<property>}), these
/// are expanded.
virtual void setString(const std::string & key, const std::string & value);
/// Sets the property with the given key to the given value.
/// An already existing value for the key is overwritten.
@ -339,12 +353,35 @@ namespace Util
static bool parseBool(const std::string & value);
void setRawWithEvent(const std::string & key, std::string value);
static void checkHostValidity(const std::string & value);
/// Throws a SyntaxException if the value is not a valid host (IP address or domain).
virtual ~AbstractConfiguration();
private:
std::string internalExpand(const std::string & value) const;
std::string uncheckedExpand(const std::string & value) const;
static bool isValidIPv4Address(const std::string & value);
/// IPv4 address considered valid if it is "0.0.0.0" or one of those,
/// defined by inet_aton() or inet_addr()
static bool isValidIPv6Address(const std::string & value);
/// IPv6 address considered valid if it is "::" or one of those,
/// defined by inet_pton() with AF_INET6 flag
/// (in this case it may have scope id and may be surrounded by '[', ']')
static bool isValidDomainName(const std::string & value);
/// <domain> ::= <subdomain> [ "." ]
/// <subdomain> ::= <label> | <subdomain> "." <label>
/// <label> ::= <letter> [ [ <ldh-str> ] <let-dig> ]
/// <ldh-str> ::= <let-dig-hyp> | <let-dig-hyp> <ldh-str>
/// <let-dig-hyp> ::= <let-dig> | "-"
/// <let-dig> ::= <letter> | <digit>
/// <letter> ::= any one of the 52 alphabetic characters A through Z in
/// upper case and a through z in lower case
/// <digit> ::= any one of the ten digits 0 through 9
AbstractConfiguration(const AbstractConfiguration &);
AbstractConfiguration & operator=(const AbstractConfiguration &);

100
base/poco/Util/src/AbstractConfiguration.cpp
View File

@ -18,6 +18,7 @@
#include "Poco/NumberParser.h"
#include "Poco/NumberFormatter.h"
#include "Poco/String.h"
#include "Poco/Net/IPAddressImpl.h"
using Poco::Mutex;
@ -263,6 +264,41 @@ bool AbstractConfiguration::getBool(const std::string& key, bool defaultValue) c
}
std::string AbstractConfiguration::getHost(const std::string& key) const
{
Mutex::ScopedLock lock(_mutex);
std::string value;
if (getRaw(key, value))
{
std::string expandedValue = internalExpand(value);
checkHostValidity(expandedValue);
return expandedValue;
}
else
throw NotFoundException(key);
}
std::string AbstractConfiguration::getHost(const std::string& key, const std::string& defaultValue) const
{
Mutex::ScopedLock lock(_mutex);
std::string value;
if (getRaw(key, value))
{
std::string expandedValue = internalExpand(value);
checkHostValidity(expandedValue);
return expandedValue;
}
else
{
checkHostValidity(defaultValue);
return defaultValue;
}
}
void AbstractConfiguration::setString(const std::string& key, const std::string& value)
{
setRawWithEvent(key, value);
@ -529,4 +565,68 @@ void AbstractConfiguration::setRawWithEvent(const std::string& key, std::string
}
void AbstractConfiguration::checkHostValidity(const std::string& value)
{
if (!isValidIPv4Address(value) && !isValidIPv6Address(value) && !isValidDomainName(value))
{
throw SyntaxException("Property is not a valid host name", value);
}
}
bool AbstractConfiguration::isValidIPv4Address(const std::string& value)
{
using Poco::Net::Impl::IPv4AddressImpl;
IPv4AddressImpl empty4 = IPv4AddressImpl();
IPv4AddressImpl ipAddress = IPv4AddressImpl::parse(value);
return ipAddress != empty4 || value == "0.0.0.0";
}
bool AbstractConfiguration::isValidIPv6Address(const std::string& value)
{
#if defined(POCO_HAVE_IPv6)
using Poco::Net::Impl::IPv6AddressImpl;
IPv6AddressImpl empty6 = IPv6AddressImpl();
IPv6AddressImpl ipAddress = IPv6AddressImpl::parse(value);
return ipAddress != empty6 || value == "::";
#else
return false;
#endif
}
bool AbstractConfiguration::isValidDomainName(const std::string& value)
{
if (value.empty() || value == "." || value.length() > 253)
return false;
int labelLength = 0;
char oldChar = 0;
for (char ch : value)
{
if (ch == '.')
{
if (labelLength == 0 || labelLength > 63 || oldChar == '-')
return false;
labelLength = 0;
}
else if (isalnum(ch) || ch == '-')
{
if (labelLength == 0 && (ch == '-' || isdigit(ch)))
return false;
++labelLength;
}
else
{
return false;
}
oldChar = ch;
}
return oldChar == '.' || (labelLength > 0 && labelLength <= 63 && oldChar != '-');
}
} } // namespace Poco::Util

9
contrib/CMakeLists.txt vendored
View File

@ -145,8 +145,13 @@ add_contrib (isa-l-cmake isa-l)
add_contrib (libhdfs3-cmake libhdfs3) # requires: google-protobuf, krb5, isa-l
add_contrib (hive-metastore-cmake hive-metastore) # requires: thrift, avro, arrow, libhdfs3
add_contrib (cppkafka-cmake cppkafka)
add_contrib (libpqxx-cmake libpqxx)
add_contrib (libpq-cmake libpq)
option(ENABLE_LIBPQXX "Enable PostgreSQL" ${ENABLE_LIBRARIES})
if (ENABLE_LIBPQXX)
add_contrib (postgres-cmake postgres)
add_contrib (libpqxx-cmake libpqxx)
endif()
add_contrib (rocksdb-cmake rocksdb) # requires: jemalloc, snappy, zlib, lz4, zstd, liburing
add_contrib (nuraft-cmake NuRaft)
add_contrib (fast_float-cmake fast_float)

2
contrib/curl vendored

@ -1 +1 @@
Subproject commit de7b3e89218467159a7af72d58cea8425946e97d
Subproject commit 83bedbd730d62b83744cc26fa0433d3f6e2e4cd6

2
contrib/grpc vendored

@ -1 +1 @@
Subproject commit 1716359d2e28d304a250f9df0e6c0ccad03de8db
Subproject commit 7bc3abe952aba1dc7bce7f2f790dc781cb51a41e

746
contrib/icu-cmake/CMakeLists.txt
View File

@ -15,162 +15,64 @@ set(ICUDATA_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/icudata/")
# These lists of sources were generated from build log of the original ICU build system (configure + make).
set(ICUUC_SOURCES
"${ICU_SOURCE_DIR}/common/errorcode.cpp"
"${ICU_SOURCE_DIR}/common/putil.cpp"
"${ICU_SOURCE_DIR}/common/umath.cpp"
"${ICU_SOURCE_DIR}/common/utypes.cpp"
"${ICU_SOURCE_DIR}/common/uinvchar.cpp"
"${ICU_SOURCE_DIR}/common/umutex.cpp"
"${ICU_SOURCE_DIR}/common/ucln_cmn.cpp"
"${ICU_SOURCE_DIR}/common/uinit.cpp"
"${ICU_SOURCE_DIR}/common/uobject.cpp"
"${ICU_SOURCE_DIR}/common/cmemory.cpp"
"${ICU_SOURCE_DIR}/common/charstr.cpp"
"${ICU_SOURCE_DIR}/common/cstr.cpp"
"${ICU_SOURCE_DIR}/common/udata.cpp"
"${ICU_SOURCE_DIR}/common/ucmndata.cpp"
"${ICU_SOURCE_DIR}/common/udatamem.cpp"
"${ICU_SOURCE_DIR}/common/umapfile.cpp"
"${ICU_SOURCE_DIR}/common/udataswp.cpp"
"${ICU_SOURCE_DIR}/common/utrie_swap.cpp"
"${ICU_SOURCE_DIR}/common/ucol_swp.cpp"
"${ICU_SOURCE_DIR}/common/utrace.cpp"
"${ICU_SOURCE_DIR}/common/uhash.cpp"
"${ICU_SOURCE_DIR}/common/uhash_us.cpp"
"${ICU_SOURCE_DIR}/common/uenum.cpp"
"${ICU_SOURCE_DIR}/common/ustrenum.cpp"
"${ICU_SOURCE_DIR}/common/uvector.cpp"
"${ICU_SOURCE_DIR}/common/ustack.cpp"
"${ICU_SOURCE_DIR}/common/uvectr32.cpp"
"${ICU_SOURCE_DIR}/common/uvectr64.cpp"
"${ICU_SOURCE_DIR}/common/ucnv.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_bld.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_cnv.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_io.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_cb.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_err.cpp"
"${ICU_SOURCE_DIR}/common/ucnvlat1.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u7.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u8.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u16.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u32.cpp"
"${ICU_SOURCE_DIR}/common/ucnvscsu.cpp"
"${ICU_SOURCE_DIR}/common/ucnvbocu.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_ext.cpp"
"${ICU_SOURCE_DIR}/common/ucnvmbcs.cpp"
"${ICU_SOURCE_DIR}/common/ucnv2022.cpp"
"${ICU_SOURCE_DIR}/common/ucnvhz.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_lmb.cpp"
"${ICU_SOURCE_DIR}/common/ucnvisci.cpp"
"${ICU_SOURCE_DIR}/common/ucnvdisp.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_set.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_ct.cpp"
"${ICU_SOURCE_DIR}/common/resource.cpp"
"${ICU_SOURCE_DIR}/common/uresbund.cpp"
"${ICU_SOURCE_DIR}/common/ures_cnv.cpp"
"${ICU_SOURCE_DIR}/common/uresdata.cpp"
"${ICU_SOURCE_DIR}/common/resbund.cpp"
"${ICU_SOURCE_DIR}/common/resbund_cnv.cpp"
"${ICU_SOURCE_DIR}/common/ucurr.cpp"
"${ICU_SOURCE_DIR}/common/localebuilder.cpp"
"${ICU_SOURCE_DIR}/common/localeprioritylist.cpp"
"${ICU_SOURCE_DIR}/common/messagepattern.cpp"
"${ICU_SOURCE_DIR}/common/ucat.cpp"
"${ICU_SOURCE_DIR}/common/locmap.cpp"
"${ICU_SOURCE_DIR}/common/uloc.cpp"
"${ICU_SOURCE_DIR}/common/locid.cpp"
"${ICU_SOURCE_DIR}/common/locutil.cpp"
"${ICU_SOURCE_DIR}/common/locavailable.cpp"
"${ICU_SOURCE_DIR}/common/locdispnames.cpp"
"${ICU_SOURCE_DIR}/common/locdspnm.cpp"
"${ICU_SOURCE_DIR}/common/loclikely.cpp"
"${ICU_SOURCE_DIR}/common/locresdata.cpp"
"${ICU_SOURCE_DIR}/common/lsr.cpp"
"${ICU_SOURCE_DIR}/common/loclikelysubtags.cpp"
"${ICU_SOURCE_DIR}/common/locdistance.cpp"
"${ICU_SOURCE_DIR}/common/localematcher.cpp"
"${ICU_SOURCE_DIR}/common/bytestream.cpp"
"${ICU_SOURCE_DIR}/common/stringpiece.cpp"
"${ICU_SOURCE_DIR}/common/bytesinkutil.cpp"
"${ICU_SOURCE_DIR}/common/stringtriebuilder.cpp"
"${ICU_SOURCE_DIR}/common/bytestriebuilder.cpp"
"${ICU_SOURCE_DIR}/common/bytestrie.cpp"
"${ICU_SOURCE_DIR}/common/bytestrieiterator.cpp"
"${ICU_SOURCE_DIR}/common/ucharstrie.cpp"
"${ICU_SOURCE_DIR}/common/ucharstriebuilder.cpp"
"${ICU_SOURCE_DIR}/common/ucharstrieiterator.cpp"
"${ICU_SOURCE_DIR}/common/dictionarydata.cpp"
"${ICU_SOURCE_DIR}/common/edits.cpp"
"${ICU_SOURCE_DIR}/common/appendable.cpp"
"${ICU_SOURCE_DIR}/common/ustr_cnv.cpp"
"${ICU_SOURCE_DIR}/common/unistr_cnv.cpp"
"${ICU_SOURCE_DIR}/common/unistr.cpp"
"${ICU_SOURCE_DIR}/common/unistr_case.cpp"
"${ICU_SOURCE_DIR}/common/unistr_props.cpp"
"${ICU_SOURCE_DIR}/common/utf_impl.cpp"
"${ICU_SOURCE_DIR}/common/ustring.cpp"
"${ICU_SOURCE_DIR}/common/ustrcase.cpp"
"${ICU_SOURCE_DIR}/common/ucasemap.cpp"
"${ICU_SOURCE_DIR}/common/ucasemap_titlecase_brkiter.cpp"
"${ICU_SOURCE_DIR}/common/cstring.cpp"
"${ICU_SOURCE_DIR}/common/ustrfmt.cpp"
"${ICU_SOURCE_DIR}/common/ustrtrns.cpp"
"${ICU_SOURCE_DIR}/common/ustr_wcs.cpp"
"${ICU_SOURCE_DIR}/common/utext.cpp"
"${ICU_SOURCE_DIR}/common/unistr_case_locale.cpp"
"${ICU_SOURCE_DIR}/common/ustrcase_locale.cpp"
"${ICU_SOURCE_DIR}/common/unistr_titlecase_brkiter.cpp"
"${ICU_SOURCE_DIR}/common/ustr_titlecase_brkiter.cpp"
"${ICU_SOURCE_DIR}/common/normalizer2impl.cpp"
"${ICU_SOURCE_DIR}/common/normalizer2.cpp"
"${ICU_SOURCE_DIR}/common/filterednormalizer2.cpp"
"${ICU_SOURCE_DIR}/common/normlzr.cpp"
"${ICU_SOURCE_DIR}/common/unorm.cpp"
"${ICU_SOURCE_DIR}/common/unormcmp.cpp"
"${ICU_SOURCE_DIR}/common/loadednormalizer2impl.cpp"
"${ICU_SOURCE_DIR}/common/chariter.cpp"
"${ICU_SOURCE_DIR}/common/schriter.cpp"
"${ICU_SOURCE_DIR}/common/uchriter.cpp"
"${ICU_SOURCE_DIR}/common/uiter.cpp"
"${ICU_SOURCE_DIR}/common/patternprops.cpp"
"${ICU_SOURCE_DIR}/common/uchar.cpp"
"${ICU_SOURCE_DIR}/common/uprops.cpp"
"${ICU_SOURCE_DIR}/common/ucase.cpp"
"${ICU_SOURCE_DIR}/common/propname.cpp"
"${ICU_SOURCE_DIR}/common/ubidi_props.cpp"
"${ICU_SOURCE_DIR}/common/characterproperties.cpp"
"${ICU_SOURCE_DIR}/common/ubidi.cpp"
"${ICU_SOURCE_DIR}/common/ubidiwrt.cpp"
"${ICU_SOURCE_DIR}/common/ubidiln.cpp"
"${ICU_SOURCE_DIR}/common/ushape.cpp"
"${ICU_SOURCE_DIR}/common/uscript.cpp"
"${ICU_SOURCE_DIR}/common/uscript_props.cpp"
"${ICU_SOURCE_DIR}/common/usc_impl.cpp"
"${ICU_SOURCE_DIR}/common/unames.cpp"
"${ICU_SOURCE_DIR}/common/utrie.cpp"
"${ICU_SOURCE_DIR}/common/utrie2.cpp"
"${ICU_SOURCE_DIR}/common/utrie2_builder.cpp"
"${ICU_SOURCE_DIR}/common/ucptrie.cpp"
"${ICU_SOURCE_DIR}/common/umutablecptrie.cpp"
"${ICU_SOURCE_DIR}/common/bmpset.cpp"
"${ICU_SOURCE_DIR}/common/unisetspan.cpp"
"${ICU_SOURCE_DIR}/common/uset_props.cpp"
"${ICU_SOURCE_DIR}/common/uniset_props.cpp"
"${ICU_SOURCE_DIR}/common/uniset_closure.cpp"
"${ICU_SOURCE_DIR}/common/uset.cpp"
"${ICU_SOURCE_DIR}/common/uniset.cpp"
"${ICU_SOURCE_DIR}/common/usetiter.cpp"
"${ICU_SOURCE_DIR}/common/ruleiter.cpp"
"${ICU_SOURCE_DIR}/common/caniter.cpp"
"${ICU_SOURCE_DIR}/common/unifilt.cpp"
"${ICU_SOURCE_DIR}/common/unifunct.cpp"
"${ICU_SOURCE_DIR}/common/uarrsort.cpp"
"${ICU_SOURCE_DIR}/common/brkiter.cpp"
"${ICU_SOURCE_DIR}/common/ubrk.cpp"
"${ICU_SOURCE_DIR}/common/brkeng.cpp"
"${ICU_SOURCE_DIR}/common/brkiter.cpp"
"${ICU_SOURCE_DIR}/common/bytesinkutil.cpp"
"${ICU_SOURCE_DIR}/common/bytestream.cpp"
"${ICU_SOURCE_DIR}/common/bytestrie.cpp"
"${ICU_SOURCE_DIR}/common/bytestriebuilder.cpp"
"${ICU_SOURCE_DIR}/common/bytestrieiterator.cpp"
"${ICU_SOURCE_DIR}/common/caniter.cpp"
"${ICU_SOURCE_DIR}/common/characterproperties.cpp"
"${ICU_SOURCE_DIR}/common/chariter.cpp"
"${ICU_SOURCE_DIR}/common/charstr.cpp"
"${ICU_SOURCE_DIR}/common/cmemory.cpp"
"${ICU_SOURCE_DIR}/common/cstr.cpp"
"${ICU_SOURCE_DIR}/common/cstring.cpp"
"${ICU_SOURCE_DIR}/common/cwchar.cpp"
"${ICU_SOURCE_DIR}/common/dictbe.cpp"
"${ICU_SOURCE_DIR}/common/dictionarydata.cpp"
"${ICU_SOURCE_DIR}/common/dtintrv.cpp"
"${ICU_SOURCE_DIR}/common/edits.cpp"
"${ICU_SOURCE_DIR}/common/emojiprops.cpp"
"${ICU_SOURCE_DIR}/common/errorcode.cpp"
"${ICU_SOURCE_DIR}/common/filteredbrk.cpp"
"${ICU_SOURCE_DIR}/common/filterednormalizer2.cpp"
"${ICU_SOURCE_DIR}/common/icudataver.cpp"
"${ICU_SOURCE_DIR}/common/icuplug.cpp"
"${ICU_SOURCE_DIR}/common/loadednormalizer2impl.cpp"
"${ICU_SOURCE_DIR}/common/localebuilder.cpp"
"${ICU_SOURCE_DIR}/common/localematcher.cpp"
"${ICU_SOURCE_DIR}/common/localeprioritylist.cpp"
"${ICU_SOURCE_DIR}/common/locavailable.cpp"
"${ICU_SOURCE_DIR}/common/locbased.cpp"
"${ICU_SOURCE_DIR}/common/locdispnames.cpp"
"${ICU_SOURCE_DIR}/common/locdistance.cpp"
"${ICU_SOURCE_DIR}/common/locdspnm.cpp"
"${ICU_SOURCE_DIR}/common/locid.cpp"
"${ICU_SOURCE_DIR}/common/loclikely.cpp"
"${ICU_SOURCE_DIR}/common/loclikelysubtags.cpp"
"${ICU_SOURCE_DIR}/common/locmap.cpp"
"${ICU_SOURCE_DIR}/common/locresdata.cpp"
"${ICU_SOURCE_DIR}/common/locutil.cpp"
"${ICU_SOURCE_DIR}/common/lsr.cpp"
"${ICU_SOURCE_DIR}/common/lstmbe.cpp"
"${ICU_SOURCE_DIR}/common/messagepattern.cpp"
"${ICU_SOURCE_DIR}/common/mlbe.cpp"
"${ICU_SOURCE_DIR}/common/normalizer2.cpp"
"${ICU_SOURCE_DIR}/common/normalizer2impl.cpp"
"${ICU_SOURCE_DIR}/common/normlzr.cpp"
"${ICU_SOURCE_DIR}/common/parsepos.cpp"
"${ICU_SOURCE_DIR}/common/patternprops.cpp"
"${ICU_SOURCE_DIR}/common/pluralmap.cpp"
"${ICU_SOURCE_DIR}/common/propname.cpp"
"${ICU_SOURCE_DIR}/common/propsvec.cpp"
"${ICU_SOURCE_DIR}/common/punycode.cpp"
"${ICU_SOURCE_DIR}/common/putil.cpp"
"${ICU_SOURCE_DIR}/common/rbbi.cpp"
"${ICU_SOURCE_DIR}/common/rbbi_cache.cpp"
"${ICU_SOURCE_DIR}/common/rbbidata.cpp"
"${ICU_SOURCE_DIR}/common/rbbinode.cpp"
"${ICU_SOURCE_DIR}/common/rbbirb.cpp"
@ -178,166 +80,180 @@ set(ICUUC_SOURCES
"${ICU_SOURCE_DIR}/common/rbbisetb.cpp"
"${ICU_SOURCE_DIR}/common/rbbistbl.cpp"
"${ICU_SOURCE_DIR}/common/rbbitblb.cpp"
"${ICU_SOURCE_DIR}/common/rbbi_cache.cpp"
"${ICU_SOURCE_DIR}/common/resbund.cpp"
"${ICU_SOURCE_DIR}/common/resbund_cnv.cpp"
"${ICU_SOURCE_DIR}/common/resource.cpp"
"${ICU_SOURCE_DIR}/common/restrace.cpp"
"${ICU_SOURCE_DIR}/common/ruleiter.cpp"
"${ICU_SOURCE_DIR}/common/schriter.cpp"
"${ICU_SOURCE_DIR}/common/serv.cpp"
"${ICU_SOURCE_DIR}/common/servnotf.cpp"
"${ICU_SOURCE_DIR}/common/servls.cpp"
"${ICU_SOURCE_DIR}/common/servlk.cpp"
"${ICU_SOURCE_DIR}/common/servlkf.cpp"
"${ICU_SOURCE_DIR}/common/servls.cpp"
"${ICU_SOURCE_DIR}/common/servnotf.cpp"
"${ICU_SOURCE_DIR}/common/servrbf.cpp"
"${ICU_SOURCE_DIR}/common/servslkf.cpp"
"${ICU_SOURCE_DIR}/common/uidna.cpp"
"${ICU_SOURCE_DIR}/common/usprep.cpp"
"${ICU_SOURCE_DIR}/common/uts46.cpp"
"${ICU_SOURCE_DIR}/common/punycode.cpp"
"${ICU_SOURCE_DIR}/common/util.cpp"
"${ICU_SOURCE_DIR}/common/util_props.cpp"
"${ICU_SOURCE_DIR}/common/parsepos.cpp"
"${ICU_SOURCE_DIR}/common/locbased.cpp"
"${ICU_SOURCE_DIR}/common/cwchar.cpp"
"${ICU_SOURCE_DIR}/common/wintz.cpp"
"${ICU_SOURCE_DIR}/common/dtintrv.cpp"
"${ICU_SOURCE_DIR}/common/ucnvsel.cpp"
"${ICU_SOURCE_DIR}/common/propsvec.cpp"
"${ICU_SOURCE_DIR}/common/ulist.cpp"
"${ICU_SOURCE_DIR}/common/uloc_tag.cpp"
"${ICU_SOURCE_DIR}/common/icudataver.cpp"
"${ICU_SOURCE_DIR}/common/icuplug.cpp"
"${ICU_SOURCE_DIR}/common/sharedobject.cpp"
"${ICU_SOURCE_DIR}/common/simpleformatter.cpp"
"${ICU_SOURCE_DIR}/common/unifiedcache.cpp"
"${ICU_SOURCE_DIR}/common/uloc_keytype.cpp"
"${ICU_SOURCE_DIR}/common/ubiditransform.cpp"
"${ICU_SOURCE_DIR}/common/pluralmap.cpp"
"${ICU_SOURCE_DIR}/common/static_unicode_sets.cpp"
"${ICU_SOURCE_DIR}/common/restrace.cpp"
"${ICU_SOURCE_DIR}/common/emojiprops.cpp"
"${ICU_SOURCE_DIR}/common/lstmbe.cpp")
"${ICU_SOURCE_DIR}/common/stringpiece.cpp"
"${ICU_SOURCE_DIR}/common/stringtriebuilder.cpp"
"${ICU_SOURCE_DIR}/common/uarrsort.cpp"
"${ICU_SOURCE_DIR}/common/ubidi.cpp"
"${ICU_SOURCE_DIR}/common/ubidi_props.cpp"
"${ICU_SOURCE_DIR}/common/ubidiln.cpp"
"${ICU_SOURCE_DIR}/common/ubiditransform.cpp"
"${ICU_SOURCE_DIR}/common/ubidiwrt.cpp"
"${ICU_SOURCE_DIR}/common/ubrk.cpp"
"${ICU_SOURCE_DIR}/common/ucase.cpp"
"${ICU_SOURCE_DIR}/common/ucasemap.cpp"
"${ICU_SOURCE_DIR}/common/ucasemap_titlecase_brkiter.cpp"
"${ICU_SOURCE_DIR}/common/ucat.cpp"
"${ICU_SOURCE_DIR}/common/uchar.cpp"
"${ICU_SOURCE_DIR}/common/ucharstrie.cpp"
"${ICU_SOURCE_DIR}/common/ucharstriebuilder.cpp"
"${ICU_SOURCE_DIR}/common/ucharstrieiterator.cpp"
"${ICU_SOURCE_DIR}/common/uchriter.cpp"
"${ICU_SOURCE_DIR}/common/ucln_cmn.cpp"
"${ICU_SOURCE_DIR}/common/ucmndata.cpp"
"${ICU_SOURCE_DIR}/common/ucnv.cpp"
"${ICU_SOURCE_DIR}/common/ucnv2022.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_bld.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_cb.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_cnv.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_ct.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_err.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_ext.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_io.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_lmb.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_set.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u16.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u32.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u7.cpp"
"${ICU_SOURCE_DIR}/common/ucnv_u8.cpp"
"${ICU_SOURCE_DIR}/common/ucnvbocu.cpp"
"${ICU_SOURCE_DIR}/common/ucnvdisp.cpp"
"${ICU_SOURCE_DIR}/common/ucnvhz.cpp"
"${ICU_SOURCE_DIR}/common/ucnvisci.cpp"
"${ICU_SOURCE_DIR}/common/ucnvlat1.cpp"
"${ICU_SOURCE_DIR}/common/ucnvmbcs.cpp"
"${ICU_SOURCE_DIR}/common/ucnvscsu.cpp"
"${ICU_SOURCE_DIR}/common/ucnvsel.cpp"
"${ICU_SOURCE_DIR}/common/ucol_swp.cpp"
"${ICU_SOURCE_DIR}/common/ucptrie.cpp"
"${ICU_SOURCE_DIR}/common/ucurr.cpp"
"${ICU_SOURCE_DIR}/common/udata.cpp"
"${ICU_SOURCE_DIR}/common/udatamem.cpp"
"${ICU_SOURCE_DIR}/common/udataswp.cpp"
"${ICU_SOURCE_DIR}/common/uenum.cpp"
"${ICU_SOURCE_DIR}/common/uhash.cpp"
"${ICU_SOURCE_DIR}/common/uhash_us.cpp"
"${ICU_SOURCE_DIR}/common/uidna.cpp"
"${ICU_SOURCE_DIR}/common/uinit.cpp"
"${ICU_SOURCE_DIR}/common/uinvchar.cpp"
"${ICU_SOURCE_DIR}/common/uiter.cpp"
"${ICU_SOURCE_DIR}/common/ulist.cpp"
"${ICU_SOURCE_DIR}/common/uloc.cpp"
"${ICU_SOURCE_DIR}/common/uloc_keytype.cpp"
"${ICU_SOURCE_DIR}/common/uloc_tag.cpp"
"${ICU_SOURCE_DIR}/common/ulocale.cpp"
"${ICU_SOURCE_DIR}/common/ulocbuilder.cpp"
"${ICU_SOURCE_DIR}/common/umapfile.cpp"
"${ICU_SOURCE_DIR}/common/umath.cpp"
"${ICU_SOURCE_DIR}/common/umutablecptrie.cpp"
"${ICU_SOURCE_DIR}/common/umutex.cpp"
"${ICU_SOURCE_DIR}/common/unames.cpp"
"${ICU_SOURCE_DIR}/common/unifiedcache.cpp"
"${ICU_SOURCE_DIR}/common/unifilt.cpp"
"${ICU_SOURCE_DIR}/common/unifunct.cpp"
"${ICU_SOURCE_DIR}/common/uniset.cpp"
"${ICU_SOURCE_DIR}/common/uniset_closure.cpp"
"${ICU_SOURCE_DIR}/common/uniset_props.cpp"
"${ICU_SOURCE_DIR}/common/unisetspan.cpp"
"${ICU_SOURCE_DIR}/common/unistr.cpp"
"${ICU_SOURCE_DIR}/common/unistr_case.cpp"
"${ICU_SOURCE_DIR}/common/unistr_case_locale.cpp"
"${ICU_SOURCE_DIR}/common/unistr_cnv.cpp"
"${ICU_SOURCE_DIR}/common/unistr_props.cpp"
"${ICU_SOURCE_DIR}/common/unistr_titlecase_brkiter.cpp"
"${ICU_SOURCE_DIR}/common/unorm.cpp"
"${ICU_SOURCE_DIR}/common/unormcmp.cpp"
"${ICU_SOURCE_DIR}/common/uobject.cpp"
"${ICU_SOURCE_DIR}/common/uprops.cpp"
"${ICU_SOURCE_DIR}/common/ures_cnv.cpp"
"${ICU_SOURCE_DIR}/common/uresbund.cpp"
"${ICU_SOURCE_DIR}/common/uresdata.cpp"
"${ICU_SOURCE_DIR}/common/usc_impl.cpp"
"${ICU_SOURCE_DIR}/common/uscript.cpp"
"${ICU_SOURCE_DIR}/common/uscript_props.cpp"
"${ICU_SOURCE_DIR}/common/uset.cpp"
"${ICU_SOURCE_DIR}/common/uset_props.cpp"
"${ICU_SOURCE_DIR}/common/usetiter.cpp"
"${ICU_SOURCE_DIR}/common/ushape.cpp"
"${ICU_SOURCE_DIR}/common/usprep.cpp"
"${ICU_SOURCE_DIR}/common/ustack.cpp"
"${ICU_SOURCE_DIR}/common/ustr_cnv.cpp"
"${ICU_SOURCE_DIR}/common/ustr_titlecase_brkiter.cpp"
"${ICU_SOURCE_DIR}/common/ustr_wcs.cpp"
"${ICU_SOURCE_DIR}/common/ustrcase.cpp"
"${ICU_SOURCE_DIR}/common/ustrcase_locale.cpp"
"${ICU_SOURCE_DIR}/common/ustrenum.cpp"
"${ICU_SOURCE_DIR}/common/ustrfmt.cpp"
"${ICU_SOURCE_DIR}/common/ustring.cpp"
"${ICU_SOURCE_DIR}/common/ustrtrns.cpp"
"${ICU_SOURCE_DIR}/common/utext.cpp"
"${ICU_SOURCE_DIR}/common/utf_impl.cpp"
"${ICU_SOURCE_DIR}/common/util.cpp"
"${ICU_SOURCE_DIR}/common/util_props.cpp"
"${ICU_SOURCE_DIR}/common/utrace.cpp"
"${ICU_SOURCE_DIR}/common/utrie.cpp"
"${ICU_SOURCE_DIR}/common/utrie2.cpp"
"${ICU_SOURCE_DIR}/common/utrie2_builder.cpp"
"${ICU_SOURCE_DIR}/common/utrie_swap.cpp"
"${ICU_SOURCE_DIR}/common/uts46.cpp"
"${ICU_SOURCE_DIR}/common/utypes.cpp"
"${ICU_SOURCE_DIR}/common/uvector.cpp"
"${ICU_SOURCE_DIR}/common/uvectr32.cpp"
"${ICU_SOURCE_DIR}/common/uvectr64.cpp"
"${ICU_SOURCE_DIR}/common/wintz.cpp")
set(ICUI18N_SOURCES
"${ICU_SOURCE_DIR}/i18n/ucln_in.cpp"
"${ICU_SOURCE_DIR}/i18n/fmtable.cpp"
"${ICU_SOURCE_DIR}/i18n/format.cpp"
"${ICU_SOURCE_DIR}/i18n/msgfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/umsg.cpp"
"${ICU_SOURCE_DIR}/i18n/numfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/unum.cpp"
"${ICU_SOURCE_DIR}/i18n/decimfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/dcfmtsym.cpp"
"${ICU_SOURCE_DIR}/i18n/fmtable_cnv.cpp"
"${ICU_SOURCE_DIR}/i18n/choicfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/datefmt.cpp"
"${ICU_SOURCE_DIR}/i18n/smpdtfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/reldtfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/dtfmtsym.cpp"
"${ICU_SOURCE_DIR}/i18n/udat.cpp"
"${ICU_SOURCE_DIR}/i18n/dtptngen.cpp"
"${ICU_SOURCE_DIR}/i18n/udatpg.cpp"
"${ICU_SOURCE_DIR}/i18n/nfrs.cpp"
"${ICU_SOURCE_DIR}/i18n/nfrule.cpp"
"${ICU_SOURCE_DIR}/i18n/nfsubs.cpp"
"${ICU_SOURCE_DIR}/i18n/rbnf.cpp"
"${ICU_SOURCE_DIR}/i18n/numsys.cpp"
"${ICU_SOURCE_DIR}/i18n/unumsys.cpp"
"${ICU_SOURCE_DIR}/i18n/ucsdet.cpp"
"${ICU_SOURCE_DIR}/i18n/ucal.cpp"
"${ICU_SOURCE_DIR}/i18n/calendar.cpp"
"${ICU_SOURCE_DIR}/i18n/gregocal.cpp"
"${ICU_SOURCE_DIR}/i18n/timezone.cpp"
"${ICU_SOURCE_DIR}/i18n/simpletz.cpp"
"${ICU_SOURCE_DIR}/i18n/olsontz.cpp"
"${ICU_SOURCE_DIR}/i18n/alphaindex.cpp"
"${ICU_SOURCE_DIR}/i18n/anytrans.cpp"
"${ICU_SOURCE_DIR}/i18n/astro.cpp"
"${ICU_SOURCE_DIR}/i18n/taiwncal.cpp"
"${ICU_SOURCE_DIR}/i18n/basictz.cpp"
"${ICU_SOURCE_DIR}/i18n/bocsu.cpp"
"${ICU_SOURCE_DIR}/i18n/brktrans.cpp"
"${ICU_SOURCE_DIR}/i18n/buddhcal.cpp"
"${ICU_SOURCE_DIR}/i18n/persncal.cpp"
"${ICU_SOURCE_DIR}/i18n/islamcal.cpp"
"${ICU_SOURCE_DIR}/i18n/japancal.cpp"
"${ICU_SOURCE_DIR}/i18n/gregoimp.cpp"
"${ICU_SOURCE_DIR}/i18n/hebrwcal.cpp"
"${ICU_SOURCE_DIR}/i18n/indiancal.cpp"
"${ICU_SOURCE_DIR}/i18n/chnsecal.cpp"
"${ICU_SOURCE_DIR}/i18n/calendar.cpp"
"${ICU_SOURCE_DIR}/i18n/casetrn.cpp"
"${ICU_SOURCE_DIR}/i18n/cecal.cpp"
"${ICU_SOURCE_DIR}/i18n/coptccal.cpp"
"${ICU_SOURCE_DIR}/i18n/dangical.cpp"
"${ICU_SOURCE_DIR}/i18n/ethpccal.cpp"
"${ICU_SOURCE_DIR}/i18n/chnsecal.cpp"
"${ICU_SOURCE_DIR}/i18n/choicfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/coleitr.cpp"
"${ICU_SOURCE_DIR}/i18n/coll.cpp"
"${ICU_SOURCE_DIR}/i18n/sortkey.cpp"
"${ICU_SOURCE_DIR}/i18n/bocsu.cpp"
"${ICU_SOURCE_DIR}/i18n/ucoleitr.cpp"
"${ICU_SOURCE_DIR}/i18n/ucol.cpp"
"${ICU_SOURCE_DIR}/i18n/ucol_res.cpp"
"${ICU_SOURCE_DIR}/i18n/ucol_sit.cpp"
"${ICU_SOURCE_DIR}/i18n/collation.cpp"
"${ICU_SOURCE_DIR}/i18n/collationsettings.cpp"
"${ICU_SOURCE_DIR}/i18n/collationbuilder.cpp"
"${ICU_SOURCE_DIR}/i18n/collationcompare.cpp"
"${ICU_SOURCE_DIR}/i18n/collationdata.cpp"
"${ICU_SOURCE_DIR}/i18n/collationtailoring.cpp"
"${ICU_SOURCE_DIR}/i18n/collationdatabuilder.cpp"
"${ICU_SOURCE_DIR}/i18n/collationdatareader.cpp"
"${ICU_SOURCE_DIR}/i18n/collationdatawriter.cpp"
"${ICU_SOURCE_DIR}/i18n/collationfastlatin.cpp"
"${ICU_SOURCE_DIR}/i18n/collationfastlatinbuilder.cpp"
"${ICU_SOURCE_DIR}/i18n/collationfcd.cpp"
"${ICU_SOURCE_DIR}/i18n/collationiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/utf16collationiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/utf8collationiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/uitercollationiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/collationsets.cpp"
"${ICU_SOURCE_DIR}/i18n/collationcompare.cpp"
"${ICU_SOURCE_DIR}/i18n/collationfastlatin.cpp"
"${ICU_SOURCE_DIR}/i18n/collationkeys.cpp"
"${ICU_SOURCE_DIR}/i18n/rulebasedcollator.cpp"
"${ICU_SOURCE_DIR}/i18n/collationroot.cpp"
"${ICU_SOURCE_DIR}/i18n/collationrootelements.cpp"
"${ICU_SOURCE_DIR}/i18n/collationdatabuilder.cpp"
"${ICU_SOURCE_DIR}/i18n/collationweights.cpp"
"${ICU_SOURCE_DIR}/i18n/collationruleparser.cpp"
"${ICU_SOURCE_DIR}/i18n/collationbuilder.cpp"
"${ICU_SOURCE_DIR}/i18n/collationfastlatinbuilder.cpp"
"${ICU_SOURCE_DIR}/i18n/listformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/ulistformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/strmatch.cpp"
"${ICU_SOURCE_DIR}/i18n/usearch.cpp"
"${ICU_SOURCE_DIR}/i18n/search.cpp"
"${ICU_SOURCE_DIR}/i18n/stsearch.cpp"
"${ICU_SOURCE_DIR}/i18n/translit.cpp"
"${ICU_SOURCE_DIR}/i18n/utrans.cpp"
"${ICU_SOURCE_DIR}/i18n/esctrn.cpp"
"${ICU_SOURCE_DIR}/i18n/unesctrn.cpp"
"${ICU_SOURCE_DIR}/i18n/funcrepl.cpp"
"${ICU_SOURCE_DIR}/i18n/strrepl.cpp"
"${ICU_SOURCE_DIR}/i18n/tridpars.cpp"
"${ICU_SOURCE_DIR}/i18n/collationsets.cpp"
"${ICU_SOURCE_DIR}/i18n/collationsettings.cpp"
"${ICU_SOURCE_DIR}/i18n/collationtailoring.cpp"
"${ICU_SOURCE_DIR}/i18n/collationweights.cpp"
"${ICU_SOURCE_DIR}/i18n/compactdecimalformat.cpp"
"${ICU_SOURCE_DIR}/i18n/coptccal.cpp"
"${ICU_SOURCE_DIR}/i18n/cpdtrans.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_data.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_pars.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_rule.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_set.cpp"
"${ICU_SOURCE_DIR}/i18n/nultrans.cpp"
"${ICU_SOURCE_DIR}/i18n/remtrans.cpp"
"${ICU_SOURCE_DIR}/i18n/casetrn.cpp"
"${ICU_SOURCE_DIR}/i18n/titletrn.cpp"
"${ICU_SOURCE_DIR}/i18n/tolowtrn.cpp"
"${ICU_SOURCE_DIR}/i18n/toupptrn.cpp"
"${ICU_SOURCE_DIR}/i18n/anytrans.cpp"
"${ICU_SOURCE_DIR}/i18n/name2uni.cpp"
"${ICU_SOURCE_DIR}/i18n/uni2name.cpp"
"${ICU_SOURCE_DIR}/i18n/nortrans.cpp"
"${ICU_SOURCE_DIR}/i18n/quant.cpp"
"${ICU_SOURCE_DIR}/i18n/transreg.cpp"
"${ICU_SOURCE_DIR}/i18n/brktrans.cpp"
"${ICU_SOURCE_DIR}/i18n/regexcmp.cpp"
"${ICU_SOURCE_DIR}/i18n/rematch.cpp"
"${ICU_SOURCE_DIR}/i18n/repattrn.cpp"
"${ICU_SOURCE_DIR}/i18n/regexst.cpp"
"${ICU_SOURCE_DIR}/i18n/regextxt.cpp"
"${ICU_SOURCE_DIR}/i18n/regeximp.cpp"
"${ICU_SOURCE_DIR}/i18n/uregex.cpp"
"${ICU_SOURCE_DIR}/i18n/uregexc.cpp"
"${ICU_SOURCE_DIR}/i18n/ulocdata.cpp"
"${ICU_SOURCE_DIR}/i18n/measfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/currfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/curramt.cpp"
"${ICU_SOURCE_DIR}/i18n/currunit.cpp"
"${ICU_SOURCE_DIR}/i18n/measure.cpp"
"${ICU_SOURCE_DIR}/i18n/utmscale.cpp"
"${ICU_SOURCE_DIR}/i18n/csdetect.cpp"
"${ICU_SOURCE_DIR}/i18n/csmatch.cpp"
"${ICU_SOURCE_DIR}/i18n/csr2022.cpp"
@ -346,60 +262,80 @@ set(ICUI18N_SOURCES
"${ICU_SOURCE_DIR}/i18n/csrsbcs.cpp"
"${ICU_SOURCE_DIR}/i18n/csrucode.cpp"
"${ICU_SOURCE_DIR}/i18n/csrutf8.cpp"
"${ICU_SOURCE_DIR}/i18n/inputext.cpp"
"${ICU_SOURCE_DIR}/i18n/wintzimpl.cpp"
"${ICU_SOURCE_DIR}/i18n/windtfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/winnmfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/basictz.cpp"
"${ICU_SOURCE_DIR}/i18n/dtrule.cpp"
"${ICU_SOURCE_DIR}/i18n/rbtz.cpp"
"${ICU_SOURCE_DIR}/i18n/tzrule.cpp"
"${ICU_SOURCE_DIR}/i18n/tztrans.cpp"
"${ICU_SOURCE_DIR}/i18n/vtzone.cpp"
"${ICU_SOURCE_DIR}/i18n/zonemeta.cpp"
"${ICU_SOURCE_DIR}/i18n/standardplural.cpp"
"${ICU_SOURCE_DIR}/i18n/upluralrules.cpp"
"${ICU_SOURCE_DIR}/i18n/plurrule.cpp"
"${ICU_SOURCE_DIR}/i18n/plurfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/selfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/curramt.cpp"
"${ICU_SOURCE_DIR}/i18n/currfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/currpinf.cpp"
"${ICU_SOURCE_DIR}/i18n/currunit.cpp"
"${ICU_SOURCE_DIR}/i18n/dangical.cpp"
"${ICU_SOURCE_DIR}/i18n/datefmt.cpp"
"${ICU_SOURCE_DIR}/i18n/dayperiodrules.cpp"
"${ICU_SOURCE_DIR}/i18n/dcfmtsym.cpp"
"${ICU_SOURCE_DIR}/i18n/decContext.cpp"
"${ICU_SOURCE_DIR}/i18n/decNumber.cpp"
"${ICU_SOURCE_DIR}/i18n/decimfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/displayoptions.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-bignum-dtoa.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-bignum.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-cached-powers.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-double-to-string.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-fast-dtoa.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-string-to-double.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-strtod.cpp"
"${ICU_SOURCE_DIR}/i18n/dtfmtsym.cpp"
"${ICU_SOURCE_DIR}/i18n/dtitvfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/dtitvinf.cpp"
"${ICU_SOURCE_DIR}/i18n/udateintervalformat.cpp"
"${ICU_SOURCE_DIR}/i18n/tmunit.cpp"
"${ICU_SOURCE_DIR}/i18n/tmutamt.cpp"
"${ICU_SOURCE_DIR}/i18n/tmutfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/currpinf.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof_build.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof_conf.cpp"
"${ICU_SOURCE_DIR}/i18n/smpdtfst.cpp"
"${ICU_SOURCE_DIR}/i18n/ztrans.cpp"
"${ICU_SOURCE_DIR}/i18n/zrule.cpp"
"${ICU_SOURCE_DIR}/i18n/vzone.cpp"
"${ICU_SOURCE_DIR}/i18n/dtptngen.cpp"
"${ICU_SOURCE_DIR}/i18n/dtrule.cpp"
"${ICU_SOURCE_DIR}/i18n/erarules.cpp"
"${ICU_SOURCE_DIR}/i18n/esctrn.cpp"
"${ICU_SOURCE_DIR}/i18n/ethpccal.cpp"
"${ICU_SOURCE_DIR}/i18n/fmtable.cpp"
"${ICU_SOURCE_DIR}/i18n/fmtable_cnv.cpp"
"${ICU_SOURCE_DIR}/i18n/format.cpp"
"${ICU_SOURCE_DIR}/i18n/formatted_string_builder.cpp"
"${ICU_SOURCE_DIR}/i18n/formattedval_iterimpl.cpp"
"${ICU_SOURCE_DIR}/i18n/formattedval_sbimpl.cpp"
"${ICU_SOURCE_DIR}/i18n/formattedvalue.cpp"
"${ICU_SOURCE_DIR}/i18n/fphdlimp.cpp"
"${ICU_SOURCE_DIR}/i18n/fpositer.cpp"
"${ICU_SOURCE_DIR}/i18n/ufieldpositer.cpp"
"${ICU_SOURCE_DIR}/i18n/decNumber.cpp"
"${ICU_SOURCE_DIR}/i18n/decContext.cpp"
"${ICU_SOURCE_DIR}/i18n/alphaindex.cpp"
"${ICU_SOURCE_DIR}/i18n/tznames.cpp"
"${ICU_SOURCE_DIR}/i18n/tznames_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/tzgnames.cpp"
"${ICU_SOURCE_DIR}/i18n/tzfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/compactdecimalformat.cpp"
"${ICU_SOURCE_DIR}/i18n/funcrepl.cpp"
"${ICU_SOURCE_DIR}/i18n/gender.cpp"
"${ICU_SOURCE_DIR}/i18n/region.cpp"
"${ICU_SOURCE_DIR}/i18n/scriptset.cpp"
"${ICU_SOURCE_DIR}/i18n/uregion.cpp"
"${ICU_SOURCE_DIR}/i18n/reldatefmt.cpp"
"${ICU_SOURCE_DIR}/i18n/quantityformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/gregocal.cpp"
"${ICU_SOURCE_DIR}/i18n/gregoimp.cpp"
"${ICU_SOURCE_DIR}/i18n/hebrwcal.cpp"
"${ICU_SOURCE_DIR}/i18n/indiancal.cpp"
"${ICU_SOURCE_DIR}/i18n/inputext.cpp"
"${ICU_SOURCE_DIR}/i18n/islamcal.cpp"
"${ICU_SOURCE_DIR}/i18n/iso8601cal.cpp"
"${ICU_SOURCE_DIR}/i18n/japancal.cpp"
"${ICU_SOURCE_DIR}/i18n/listformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/measfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/measunit.cpp"
"${ICU_SOURCE_DIR}/i18n/sharedbreakiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/scientificnumberformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/dayperiodrules.cpp"
"${ICU_SOURCE_DIR}/i18n/measunit_extra.cpp"
"${ICU_SOURCE_DIR}/i18n/measure.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_arguments.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_checker.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_data_model.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_errors.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_evaluation.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_formattable.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_formatter.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_function_registry.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_parser.cpp"
"${ICU_SOURCE_DIR}/i18n/messageformat2_serializer.cpp"
"${ICU_SOURCE_DIR}/i18n/msgfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/name2uni.cpp"
"${ICU_SOURCE_DIR}/i18n/nfrs.cpp"
"${ICU_SOURCE_DIR}/i18n/nfrule.cpp"
"${ICU_SOURCE_DIR}/i18n/nfsubs.cpp"
"${ICU_SOURCE_DIR}/i18n/nortrans.cpp"
"${ICU_SOURCE_DIR}/i18n/nultrans.cpp"
"${ICU_SOURCE_DIR}/i18n/number_affixutils.cpp"
"${ICU_SOURCE_DIR}/i18n/number_asformat.cpp"
"${ICU_SOURCE_DIR}/i18n/number_capi.cpp"
"${ICU_SOURCE_DIR}/i18n/number_compact.cpp"
"${ICU_SOURCE_DIR}/i18n/number_currencysymbols.cpp"
"${ICU_SOURCE_DIR}/i18n/number_decimalquantity.cpp"
"${ICU_SOURCE_DIR}/i18n/number_decimfmtprops.cpp"
"${ICU_SOURCE_DIR}/i18n/number_fluent.cpp"
@ -407,7 +343,9 @@ set(ICUI18N_SOURCES
"${ICU_SOURCE_DIR}/i18n/number_grouping.cpp"
"${ICU_SOURCE_DIR}/i18n/number_integerwidth.cpp"
"${ICU_SOURCE_DIR}/i18n/number_longnames.cpp"
"${ICU_SOURCE_DIR}/i18n/number_mapper.cpp"
"${ICU_SOURCE_DIR}/i18n/number_modifiers.cpp"
"${ICU_SOURCE_DIR}/i18n/number_multiplier.cpp"
"${ICU_SOURCE_DIR}/i18n/number_notation.cpp"
"${ICU_SOURCE_DIR}/i18n/number_output.cpp"
"${ICU_SOURCE_DIR}/i18n/number_padding.cpp"
@ -415,46 +353,125 @@ set(ICUI18N_SOURCES
"${ICU_SOURCE_DIR}/i18n/number_patternstring.cpp"
"${ICU_SOURCE_DIR}/i18n/number_rounding.cpp"
"${ICU_SOURCE_DIR}/i18n/number_scientific.cpp"
"${ICU_SOURCE_DIR}/i18n/number_utils.cpp"
"${ICU_SOURCE_DIR}/i18n/number_asformat.cpp"
"${ICU_SOURCE_DIR}/i18n/number_mapper.cpp"
"${ICU_SOURCE_DIR}/i18n/number_multiplier.cpp"
"${ICU_SOURCE_DIR}/i18n/number_currencysymbols.cpp"
"${ICU_SOURCE_DIR}/i18n/number_simple.cpp"
"${ICU_SOURCE_DIR}/i18n/number_skeletons.cpp"
"${ICU_SOURCE_DIR}/i18n/number_capi.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-string-to-double.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-double-to-string.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-bignum-dtoa.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-bignum.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-cached-powers.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-fast-dtoa.cpp"
"${ICU_SOURCE_DIR}/i18n/double-conversion-strtod.cpp"
"${ICU_SOURCE_DIR}/i18n/string_segment.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_parsednumber.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_symbols.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_decimal.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_scientific.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_currency.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_affixes.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_compositions.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_validators.cpp"
"${ICU_SOURCE_DIR}/i18n/numrange_fluent.cpp"
"${ICU_SOURCE_DIR}/i18n/numrange_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/erarules.cpp"
"${ICU_SOURCE_DIR}/i18n/formattedvalue.cpp"
"${ICU_SOURCE_DIR}/i18n/formattedval_iterimpl.cpp"
"${ICU_SOURCE_DIR}/i18n/formattedval_sbimpl.cpp"
"${ICU_SOURCE_DIR}/i18n/formatted_string_builder.cpp"
"${ICU_SOURCE_DIR}/i18n/measunit_extra.cpp"
"${ICU_SOURCE_DIR}/i18n/number_symbolswrapper.cpp"
"${ICU_SOURCE_DIR}/i18n/number_usageprefs.cpp"
"${ICU_SOURCE_DIR}/i18n/number_utils.cpp"
"${ICU_SOURCE_DIR}/i18n/numfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_affixes.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_compositions.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_currency.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_decimal.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_parsednumber.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_scientific.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_symbols.cpp"
"${ICU_SOURCE_DIR}/i18n/numparse_validators.cpp"
"${ICU_SOURCE_DIR}/i18n/numrange_capi.cpp"
"${ICU_SOURCE_DIR}/i18n/numrange_fluent.cpp"
"${ICU_SOURCE_DIR}/i18n/numrange_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/numsys.cpp"
"${ICU_SOURCE_DIR}/i18n/olsontz.cpp"
"${ICU_SOURCE_DIR}/i18n/persncal.cpp"
"${ICU_SOURCE_DIR}/i18n/pluralranges.cpp"
"${ICU_SOURCE_DIR}/i18n/plurfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/plurrule.cpp"
"${ICU_SOURCE_DIR}/i18n/quant.cpp"
"${ICU_SOURCE_DIR}/i18n/quantityformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/rbnf.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_data.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_pars.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_rule.cpp"
"${ICU_SOURCE_DIR}/i18n/rbt_set.cpp"
"${ICU_SOURCE_DIR}/i18n/rbtz.cpp"
"${ICU_SOURCE_DIR}/i18n/regexcmp.cpp"
"${ICU_SOURCE_DIR}/i18n/regeximp.cpp"
"${ICU_SOURCE_DIR}/i18n/regexst.cpp"
"${ICU_SOURCE_DIR}/i18n/regextxt.cpp"
"${ICU_SOURCE_DIR}/i18n/region.cpp"
"${ICU_SOURCE_DIR}/i18n/reldatefmt.cpp"
"${ICU_SOURCE_DIR}/i18n/reldtfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/rematch.cpp"
"${ICU_SOURCE_DIR}/i18n/remtrans.cpp"
"${ICU_SOURCE_DIR}/i18n/repattrn.cpp"
"${ICU_SOURCE_DIR}/i18n/rulebasedcollator.cpp"
"${ICU_SOURCE_DIR}/i18n/scientificnumberformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/scriptset.cpp"
"${ICU_SOURCE_DIR}/i18n/search.cpp"
"${ICU_SOURCE_DIR}/i18n/selfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/sharedbreakiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/simpletz.cpp"
"${ICU_SOURCE_DIR}/i18n/smpdtfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/smpdtfst.cpp"
"${ICU_SOURCE_DIR}/i18n/sortkey.cpp"
"${ICU_SOURCE_DIR}/i18n/standardplural.cpp"
"${ICU_SOURCE_DIR}/i18n/string_segment.cpp"
"${ICU_SOURCE_DIR}/i18n/strmatch.cpp"
"${ICU_SOURCE_DIR}/i18n/strrepl.cpp"
"${ICU_SOURCE_DIR}/i18n/stsearch.cpp"
"${ICU_SOURCE_DIR}/i18n/taiwncal.cpp"
"${ICU_SOURCE_DIR}/i18n/timezone.cpp"
"${ICU_SOURCE_DIR}/i18n/titletrn.cpp"
"${ICU_SOURCE_DIR}/i18n/tmunit.cpp"
"${ICU_SOURCE_DIR}/i18n/tmutamt.cpp"
"${ICU_SOURCE_DIR}/i18n/tmutfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/tolowtrn.cpp"
"${ICU_SOURCE_DIR}/i18n/toupptrn.cpp"
"${ICU_SOURCE_DIR}/i18n/translit.cpp"
"${ICU_SOURCE_DIR}/i18n/transreg.cpp"
"${ICU_SOURCE_DIR}/i18n/tridpars.cpp"
"${ICU_SOURCE_DIR}/i18n/tzfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/tzgnames.cpp"
"${ICU_SOURCE_DIR}/i18n/tznames.cpp"
"${ICU_SOURCE_DIR}/i18n/tznames_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/tzrule.cpp"
"${ICU_SOURCE_DIR}/i18n/tztrans.cpp"
"${ICU_SOURCE_DIR}/i18n/ucal.cpp"
"${ICU_SOURCE_DIR}/i18n/ucln_in.cpp"
"${ICU_SOURCE_DIR}/i18n/ucol.cpp"
"${ICU_SOURCE_DIR}/i18n/ucol_res.cpp"
"${ICU_SOURCE_DIR}/i18n/ucol_sit.cpp"
"${ICU_SOURCE_DIR}/i18n/ucoleitr.cpp"
"${ICU_SOURCE_DIR}/i18n/ucsdet.cpp"
"${ICU_SOURCE_DIR}/i18n/udat.cpp"
"${ICU_SOURCE_DIR}/i18n/udateintervalformat.cpp"
"${ICU_SOURCE_DIR}/i18n/udatpg.cpp"
"${ICU_SOURCE_DIR}/i18n/ufieldpositer.cpp"
"${ICU_SOURCE_DIR}/i18n/uitercollationiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/ulistformatter.cpp"
"${ICU_SOURCE_DIR}/i18n/ulocdata.cpp"
"${ICU_SOURCE_DIR}/i18n/umsg.cpp"
"${ICU_SOURCE_DIR}/i18n/unesctrn.cpp"
"${ICU_SOURCE_DIR}/i18n/uni2name.cpp"
"${ICU_SOURCE_DIR}/i18n/units_complexconverter.cpp"
"${ICU_SOURCE_DIR}/i18n/units_converter.cpp"
"${ICU_SOURCE_DIR}/i18n/units_data.cpp"
"${ICU_SOURCE_DIR}/i18n/units_router.cpp")
"${ICU_SOURCE_DIR}/i18n/units_router.cpp"
"${ICU_SOURCE_DIR}/i18n/unum.cpp"
"${ICU_SOURCE_DIR}/i18n/unumsys.cpp"
"${ICU_SOURCE_DIR}/i18n/upluralrules.cpp"
"${ICU_SOURCE_DIR}/i18n/uregex.cpp"
"${ICU_SOURCE_DIR}/i18n/uregexc.cpp"
"${ICU_SOURCE_DIR}/i18n/uregion.cpp"
"${ICU_SOURCE_DIR}/i18n/usearch.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof_build.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof_conf.cpp"
"${ICU_SOURCE_DIR}/i18n/uspoof_impl.cpp"
"${ICU_SOURCE_DIR}/i18n/utf16collationiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/utf8collationiterator.cpp"
"${ICU_SOURCE_DIR}/i18n/utmscale.cpp"
"${ICU_SOURCE_DIR}/i18n/utrans.cpp"
"${ICU_SOURCE_DIR}/i18n/vtzone.cpp"
"${ICU_SOURCE_DIR}/i18n/vzone.cpp"
"${ICU_SOURCE_DIR}/i18n/windtfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/winnmfmt.cpp"
"${ICU_SOURCE_DIR}/i18n/wintzimpl.cpp"
"${ICU_SOURCE_DIR}/i18n/zonemeta.cpp"
"${ICU_SOURCE_DIR}/i18n/zrule.cpp"
"${ICU_SOURCE_DIR}/i18n/ztrans.cpp")
file(GENERATE OUTPUT "${CMAKE_CURRENT_BINARY_DIR}/empty.cpp" CONTENT " ")
enable_language(ASM)
@ -464,6 +481,11 @@ if (ARCH_S390X)
else()
set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt75l_dat.S" )
endif()
# ^^ you might be confused how for different little endian platforms (x86, ARM) the same assembly files can be used.
# These files are indeed assembly but they only contain data ('.long' directive), which makes them portable accross CPUs.
# Only the endianness and the character set (ASCII, EBCDIC) makes a difference, also see
# https://unicode-org.github.io/icu/userguide/icu_data/#sharing-icu-data-between-platforms, 'Sharing ICU Data Between Platforms')
# (and as an experiment, try re-generating the data files on x86 vs. ARM, ... you'll get exactly the same files)
set(ICUDATA_SOURCES
"${ICUDATA_SOURCE_FILE}"

2
contrib/libarchive vendored

@ -1 +1 @@
Subproject commit ee45796171324519f0c0bfd012018dd099296336
Subproject commit 313aa1fa10b657de791e3202c168a6c833bc3543

2
contrib/libarchive-cmake/CMakeLists.txt
View File

@ -157,7 +157,7 @@ if (TARGET ch_contrib::zlib)
endif()
if (TARGET ch_contrib::zstd)
target_compile_definitions(_libarchive PUBLIC HAVE_ZSTD_H=1 HAVE_LIBZSTD=1 HAVE_LIBZSTD_COMPRESSOR=1)
target_compile_definitions(_libarchive PUBLIC HAVE_ZSTD_H=1 HAVE_LIBZSTD=1 HAVE_ZSTD_compressStream=1)
target_link_libraries(_libarchive PRIVATE ch_contrib::zstd)
endif()

42
contrib/libarchive-cmake/config.h
View File

@ -334,13 +334,16 @@ typedef uint64_t uintmax_t;
/* #undef ARCHIVE_XATTR_LINUX */
/* Version number of bsdcpio */
#define BSDCPIO_VERSION_STRING "3.7.0"
#define BSDCPIO_VERSION_STRING "3.7.4"
/* Version number of bsdtar */
#define BSDTAR_VERSION_STRING "3.7.0"
#define BSDTAR_VERSION_STRING "3.7.4"
/* Version number of bsdcat */
#define BSDCAT_VERSION_STRING "3.7.0"
#define BSDCAT_VERSION_STRING "3.7.4"
/* Version number of bsdunzip */
#define BSDUNZIP_VERSION_STRING "3.7.4"
/* Define to 1 if you have the `acl_create_entry' function. */
/* #undef HAVE_ACL_CREATE_ENTRY */
@ -642,8 +645,8 @@ typedef uint64_t uintmax_t;
/* Define to 1 if you have the `getgrnam_r' function. */
#define HAVE_GETGRNAM_R 1
/* Define to 1 if platform uses `optreset` to reset `getopt` */
#define HAVE_GETOPT_OPTRESET 1
/* Define to 1 if you have the `getline' function. */
#define HAVE_GETLINE 1
/* Define to 1 if you have the `getpid' function. */
#define HAVE_GETPID 1
@ -750,6 +753,12 @@ typedef uint64_t uintmax_t;
/* Define to 1 if you have the `pcreposix' library (-lpcreposix). */
/* #undef HAVE_LIBPCREPOSIX */
/* Define to 1 if you have the `pcre2-8' library (-lpcre2-8). */
/* #undef HAVE_LIBPCRE2 */
/* Define to 1 if you have the `pcreposix' library (-lpcre2posix). */
/* #undef HAVE_LIBPCRE2POSIX */
/* Define to 1 if you have the `xml2' library (-lxml2). */
#define HAVE_LIBXML2 1
@ -765,9 +774,8 @@ typedef uint64_t uintmax_t;
/* Define to 1 if you have the `zstd' library (-lzstd). */
/* #undef HAVE_LIBZSTD */
/* Define to 1 if you have the `zstd' library (-lzstd) with compression
support. */
/* #undef HAVE_LIBZSTD_COMPRESSOR */
/* Define to 1 if you have the ZSTD_compressStream function. */
/* #undef HAVE_ZSTD_compressStream */
/* Define to 1 if you have the <limits.h> header file. */
#define HAVE_LIMITS_H 1
@ -923,6 +931,9 @@ typedef uint64_t uintmax_t;
/* Define to 1 if you have the <pcreposix.h> header file. */
/* #undef HAVE_PCREPOSIX_H */
/* Define to 1 if you have the <pcre2posix.h> header file. */
/* #undef HAVE_PCRE2POSIX_H */
/* Define to 1 if you have the `pipe' function. */
#define HAVE_PIPE 1
@ -1029,6 +1040,12 @@ typedef uint64_t uintmax_t;
/* Define to 1 if you have the `strrchr' function. */
#define HAVE_STRRCHR 1
/* Define to 1 if the system has the type `struct statfs'. */
/* #undef HAVE_STRUCT_STATFS */
/* Define to 1 if `f_iosize' is a member of `struct statfs'. */
/* #undef HAVE_STRUCT_STATFS_F_IOSIZE */
/* Define to 1 if `f_namemax' is a member of `struct statfs'. */
/* #undef HAVE_STRUCT_STATFS_F_NAMEMAX */
@ -1077,6 +1094,9 @@ typedef uint64_t uintmax_t;
/* Define to 1 if you have the `symlink' function. */
#define HAVE_SYMLINK 1
/* Define to 1 if you have the `sysconf' function. */
#define HAVE_SYSCONF 1
/* Define to 1 if you have the <sys/acl.h> header file. */
/* #undef HAVE_SYS_ACL_H */
@ -1276,10 +1296,10 @@ typedef uint64_t uintmax_t;
#define ICONV_CONST
/* Version number of libarchive as a single integer */
#define LIBARCHIVE_VERSION_NUMBER "3007000"
#define LIBARCHIVE_VERSION_NUMBER "3007004"
/* Version number of libarchive */
#define LIBARCHIVE_VERSION_STRING "3.7.0"
#define LIBARCHIVE_VERSION_STRING "3.7.4"
/* Define to 1 if `lstat' dereferences a symlink specified with a trailing
slash. */
@ -1333,7 +1353,7 @@ typedef uint64_t uintmax_t;
#endif /* SAFE_TO_DEFINE_EXTENSIONS */
/* Version number of package */
#define VERSION "3.7.0"
#define VERSION "3.7.4"
/* Number of bits in a file offset, on hosts where this is settable. */
/* #undef _FILE_OFFSET_BITS */

1
contrib/libpq vendored

@ -1 +0,0 @@
Subproject commit 2446f2c85650b56df9d4ebc4c2ea7f4b01beee57

78
contrib/libpq-cmake/CMakeLists.txt
View File

@ -1,78 +0,0 @@
if (NOT ENABLE_LIBPQXX)
return()
endif()
set(LIBPQ_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/libpq")
set(SRCS
"${LIBPQ_SOURCE_DIR}/fe-auth.c"
"${LIBPQ_SOURCE_DIR}/fe-auth-scram.c"
"${LIBPQ_SOURCE_DIR}/fe-connect.c"
"${LIBPQ_SOURCE_DIR}/fe-exec.c"
"${LIBPQ_SOURCE_DIR}/fe-lobj.c"
"${LIBPQ_SOURCE_DIR}/fe-misc.c"
"${LIBPQ_SOURCE_DIR}/fe-print.c"
"${LIBPQ_SOURCE_DIR}/fe-trace.c"
"${LIBPQ_SOURCE_DIR}/fe-protocol3.c"
"${LIBPQ_SOURCE_DIR}/fe-secure.c"
"${LIBPQ_SOURCE_DIR}/fe-secure-common.c"
"${LIBPQ_SOURCE_DIR}/fe-secure-openssl.c"
"${LIBPQ_SOURCE_DIR}/legacy-pqsignal.c"
"${LIBPQ_SOURCE_DIR}/libpq-events.c"
"${LIBPQ_SOURCE_DIR}/pqexpbuffer.c"
"${LIBPQ_SOURCE_DIR}/common/scram-common.c"
"${LIBPQ_SOURCE_DIR}/common/sha2.c"
"${LIBPQ_SOURCE_DIR}/common/sha1.c"
"${LIBPQ_SOURCE_DIR}/common/md5.c"
"${LIBPQ_SOURCE_DIR}/common/md5_common.c"
"${LIBPQ_SOURCE_DIR}/common/hmac_openssl.c"
"${LIBPQ_SOURCE_DIR}/common/cryptohash.c"
"${LIBPQ_SOURCE_DIR}/common/saslprep.c"
"${LIBPQ_SOURCE_DIR}/common/unicode_norm.c"
"${LIBPQ_SOURCE_DIR}/common/ip.c"
"${LIBPQ_SOURCE_DIR}/common/jsonapi.c"
"${LIBPQ_SOURCE_DIR}/common/wchar.c"
"${LIBPQ_SOURCE_DIR}/common/base64.c"
"${LIBPQ_SOURCE_DIR}/common/link-canary.c"
"${LIBPQ_SOURCE_DIR}/common/fe_memutils.c"
"${LIBPQ_SOURCE_DIR}/common/string.c"
"${LIBPQ_SOURCE_DIR}/common/pg_get_line.c"
"${LIBPQ_SOURCE_DIR}/common/stringinfo.c"
"${LIBPQ_SOURCE_DIR}/common/psprintf.c"
"${LIBPQ_SOURCE_DIR}/common/encnames.c"
"${LIBPQ_SOURCE_DIR}/common/logging.c"
"${LIBPQ_SOURCE_DIR}/port/snprintf.c"
"${LIBPQ_SOURCE_DIR}/port/strlcpy.c"
"${LIBPQ_SOURCE_DIR}/port/strerror.c"
"${LIBPQ_SOURCE_DIR}/port/inet_net_ntop.c"
"${LIBPQ_SOURCE_DIR}/port/getpeereid.c"
"${LIBPQ_SOURCE_DIR}/port/chklocale.c"
"${LIBPQ_SOURCE_DIR}/port/noblock.c"
"${LIBPQ_SOURCE_DIR}/port/pg_strong_random.c"
"${LIBPQ_SOURCE_DIR}/port/pgstrcasecmp.c"
"${LIBPQ_SOURCE_DIR}/port/thread.c"
"${LIBPQ_SOURCE_DIR}/port/path.c"
)
add_library(_libpq ${SRCS})
add_definitions(-DHAVE_BIO_METH_NEW)
add_definitions(-DHAVE_HMAC_CTX_NEW)
add_definitions(-DHAVE_HMAC_CTX_FREE)
target_include_directories (_libpq SYSTEM PUBLIC ${LIBPQ_SOURCE_DIR})
target_include_directories (_libpq SYSTEM PUBLIC "${LIBPQ_SOURCE_DIR}/include")
target_include_directories (_libpq SYSTEM PRIVATE "${LIBPQ_SOURCE_DIR}/configs")
# NOTE: this is a dirty hack to avoid and instead pg_config.h should be shipped
# for different OS'es like for jemalloc, not one generic for all OS'es like
# now.
if (OS_DARWIN OR OS_FREEBSD OR USE_MUSL)
target_compile_definitions(_libpq PRIVATE -DSTRERROR_R_INT=1)
endif()
target_link_libraries (_libpq PRIVATE OpenSSL::SSL)
add_library(ch_contrib::libpq ALIAS _libpq)

7
contrib/libpqxx-cmake/CMakeLists.txt
View File

@ -1,10 +1,3 @@
option(ENABLE_LIBPQXX "Enalbe libpqxx" ${ENABLE_LIBRARIES})
if (NOT ENABLE_LIBPQXX)
message(STATUS "Not using libpqxx")
return()
endif()
set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/libpqxx")
set (SRCS

2
contrib/libuv vendored

@ -1 +1 @@
Subproject commit 4482964660c77eec1166cd7d14fb915e3dbd774a
Subproject commit 714b58b9849568211ade86b44dd91d37f8a2175e

6
contrib/libuv-cmake/CMakeLists.txt
View File

@ -10,6 +10,7 @@ set(uv_sources
src/random.c
src/strscpy.c
src/strtok.c
src/thread-common.c
src/threadpool.c
src/timer.c
src/uv-common.c
@ -70,10 +71,7 @@ if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
list(APPEND uv_defines _GNU_SOURCE _POSIX_C_SOURCE=200112)
list(APPEND uv_libraries rt)
list(APPEND uv_sources
src/unix/epoll.c
src/unix/linux-core.c
src/unix/linux-inotify.c
src/unix/linux-syscalls.c
src/unix/linux.c
src/unix/procfs-exepath.c
src/unix/random-getrandom.c
src/unix/random-sysctl-linux.c)

6
contrib/llvm-project-cmake/CMakeLists.txt
View File

@ -140,6 +140,12 @@ if (CMAKE_CROSSCOMPILING)
message (STATUS "CROSS COMPILING SET LLVM HOST TRIPLE ${LLVM_HOST_TRIPLE}")
endif()
# llvm-project/llvm/cmake/config-ix.cmake does a weird thing: it defines _LARGEFILE64_SOURCE,
# then checks if lseek64() function exists, then undefines _LARGEFILE64_SOURCE.
# Then the actual code that uses this function *doesn't* define _LARGEFILE64_SOURCE, so lseek64()
# may not exist and compilation fails. This happens with musl.
add_compile_definitions("_LARGEFILE64_SOURCE")
add_subdirectory ("${LLVM_SOURCE_DIR}" "${LLVM_BINARY_DIR}")
set_directory_properties (PROPERTIES

2
contrib/openssl vendored

@ -1 +1 @@
Subproject commit 66deddc1e53cda8706604a019777259372d1bd62
Subproject commit b3e62c440f390e12e77c80675f883af82ad3d5ed

1
contrib/postgres vendored Submodule

@ -0,0 +1 @@
Subproject commit 665ff8c164d56d012e359735efe4d400c0564b44

78
contrib/postgres-cmake/CMakeLists.txt Normal file
View File

@ -0,0 +1,78 @@
# Build description for libpq which is part of the PostgreSQL sources
set(POSTGRES_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/postgres")
set(LIBPQ_SOURCE_DIR "${POSTGRES_SOURCE_DIR}/src/interfaces/libpq")
set(LIBPQ_CMAKE_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/postgres-cmake")
set(SRCS
"${LIBPQ_SOURCE_DIR}/fe-auth.c"
"${LIBPQ_SOURCE_DIR}/fe-auth-scram.c"
"${LIBPQ_SOURCE_DIR}/fe-connect.c"
"${LIBPQ_SOURCE_DIR}/fe-exec.c"
"${LIBPQ_SOURCE_DIR}/fe-lobj.c"
"${LIBPQ_SOURCE_DIR}/fe-misc.c"
"${LIBPQ_SOURCE_DIR}/fe-print.c"
"${LIBPQ_SOURCE_DIR}/fe-trace.c"
"${LIBPQ_SOURCE_DIR}/fe-protocol3.c"
"${LIBPQ_SOURCE_DIR}/fe-secure.c"
"${LIBPQ_SOURCE_DIR}/fe-secure-common.c"
"${LIBPQ_SOURCE_DIR}/fe-secure-openssl.c"
"${LIBPQ_SOURCE_DIR}/legacy-pqsignal.c"
"${LIBPQ_SOURCE_DIR}/libpq-events.c"
"${LIBPQ_SOURCE_DIR}/pqexpbuffer.c"
"${POSTGRES_SOURCE_DIR}/src/common/scram-common.c"
"${POSTGRES_SOURCE_DIR}/src/common/sha2.c"
"${POSTGRES_SOURCE_DIR}/src/common/sha1.c"
"${POSTGRES_SOURCE_DIR}/src/common/md5.c"
"${POSTGRES_SOURCE_DIR}/src/common/md5_common.c"
"${POSTGRES_SOURCE_DIR}/src/common/hmac_openssl.c"
"${POSTGRES_SOURCE_DIR}/src/common/cryptohash.c"
"${POSTGRES_SOURCE_DIR}/src/common/saslprep.c"
"${POSTGRES_SOURCE_DIR}/src/common/unicode_norm.c"
"${POSTGRES_SOURCE_DIR}/src/common/ip.c"
"${POSTGRES_SOURCE_DIR}/src/common/jsonapi.c"
"${POSTGRES_SOURCE_DIR}/src/common/wchar.c"
"${POSTGRES_SOURCE_DIR}/src/common/base64.c"
"${POSTGRES_SOURCE_DIR}/src/common/link-canary.c"
"${POSTGRES_SOURCE_DIR}/src/common/fe_memutils.c"
"${POSTGRES_SOURCE_DIR}/src/common/string.c"
"${POSTGRES_SOURCE_DIR}/src/common/pg_get_line.c"
"${POSTGRES_SOURCE_DIR}/src/common/stringinfo.c"
"${POSTGRES_SOURCE_DIR}/src/common/psprintf.c"
"${POSTGRES_SOURCE_DIR}/src/common/encnames.c"
"${POSTGRES_SOURCE_DIR}/src/common/logging.c"
"${POSTGRES_SOURCE_DIR}/src/port/snprintf.c"
"${POSTGRES_SOURCE_DIR}/src/port/strlcpy.c"
"${POSTGRES_SOURCE_DIR}/src/port/strerror.c"
"${POSTGRES_SOURCE_DIR}/src/port/inet_net_ntop.c"
"${POSTGRES_SOURCE_DIR}/src/port/getpeereid.c"
"${POSTGRES_SOURCE_DIR}/src/port/chklocale.c"
"${POSTGRES_SOURCE_DIR}/src/port/noblock.c"
"${POSTGRES_SOURCE_DIR}/src/port/pg_strong_random.c"
"${POSTGRES_SOURCE_DIR}/src/port/pgstrcasecmp.c"
"${POSTGRES_SOURCE_DIR}/src/port/thread.c"
"${POSTGRES_SOURCE_DIR}/src/port/path.c"
)
add_library(_libpq ${SRCS})
add_definitions(-DHAVE_BIO_METH_NEW)
add_definitions(-DHAVE_HMAC_CTX_NEW)
add_definitions(-DHAVE_HMAC_CTX_FREE)
target_include_directories (_libpq SYSTEM PUBLIC ${LIBPQ_SOURCE_DIR})
target_include_directories (_libpq SYSTEM PUBLIC "${POSTGRES_SOURCE_DIR}/src/include")
target_include_directories (_libpq SYSTEM PUBLIC "${LIBPQ_CMAKE_SOURCE_DIR}") # pre-generated headers
# NOTE: this is a dirty hack to avoid and instead pg_config.h should be shipped
# for different OS'es like for jemalloc, not one generic for all OS'es like
# now.
if (OS_DARWIN OR OS_FREEBSD OR USE_MUSL)
target_compile_definitions(_libpq PRIVATE -DSTRERROR_R_INT=1)
endif()
target_link_libraries (_libpq PRIVATE OpenSSL::SSL)
add_library(ch_contrib::libpq ALIAS _libpq)

941
contrib/postgres-cmake/pg_config.h Normal file
View File

@ -0,0 +1,941 @@
/* src/include/pg_config.h. Generated from pg_config.h.in by configure. */
/* src/include/pg_config.h.in. Generated from configure.in by autoheader. */
/* Define to the type of arg 1 of 'accept' */
#define ACCEPT_TYPE_ARG1 int
/* Define to the type of arg 2 of 'accept' */
#define ACCEPT_TYPE_ARG2 struct sockaddr *
/* Define to the type of arg 3 of 'accept' */
#define ACCEPT_TYPE_ARG3 size_t
/* Define to the return type of 'accept' */
#define ACCEPT_TYPE_RETURN int
/* Define if building universal (internal helper macro) */
/* #undef AC_APPLE_UNIVERSAL_BUILD */
/* The normal alignment of `double', in bytes. */
#define ALIGNOF_DOUBLE 4
/* The normal alignment of `int', in bytes. */
#define ALIGNOF_INT 4
/* The normal alignment of `long', in bytes. */
#define ALIGNOF_LONG 4
/* The normal alignment of `long long int', in bytes. */
#define ALIGNOF_LONG_LONG_INT 4
/* The normal alignment of `short', in bytes. */
#define ALIGNOF_SHORT 2
/* Size of a disk block --- this also limits the size of a tuple. You can set
it bigger if you need bigger tuples (although TOAST should reduce the need
to have large tuples, since fields can be spread across multiple tuples).
BLCKSZ must be a power of 2. The maximum possible value of BLCKSZ is
currently 2^15 (32768). This is determined by the 15-bit widths of the
lp_off and lp_len fields in ItemIdData (see include/storage/itemid.h).
Changing BLCKSZ requires an initdb. */
#define BLCKSZ 8192
/* Define to the default TCP port number on which the server listens and to
which clients will try to connect. This can be overridden at run-time, but
it's convenient if your clients have the right default compiled in.
(--with-pgport=PORTNUM) */
#define DEF_PGPORT 5432
/* Define to the default TCP port number as a string constant. */
#define DEF_PGPORT_STR "5432"
/* Define to build with GSSAPI support. (--with-gssapi) */
//#define ENABLE_GSS 0
/* Define to 1 if you want National Language Support. (--enable-nls) */
/* #undef ENABLE_NLS */
/* Define to 1 to build client libraries as thread-safe code.
(--enable-thread-safety) */
#define ENABLE_THREAD_SAFETY 1
/* Define to nothing if C supports flexible array members, and to 1 if it does
not. That way, with a declaration like `struct s { int n; double
d[FLEXIBLE_ARRAY_MEMBER]; };', the struct hack can be used with pre-C99
compilers. When computing the size of such an object, don't use 'sizeof
(struct s)' as it overestimates the size. Use 'offsetof (struct s, d)'
instead. Don't use 'offsetof (struct s, d[0])', as this doesn't work with
MSVC and with C++ compilers. */
#define FLEXIBLE_ARRAY_MEMBER /**/
/* float4 values are passed by value if 'true', by reference if 'false' */
#define FLOAT4PASSBYVAL true
/* float8, int8, and related values are passed by value if 'true', by
reference if 'false' */
#define FLOAT8PASSBYVAL false
/* Define to 1 if gettimeofday() takes only 1 argument. */
/* #undef GETTIMEOFDAY_1ARG */
#ifdef GETTIMEOFDAY_1ARG
# define gettimeofday(a,b) gettimeofday(a)
#endif
/* Define to 1 if you have the `append_history' function. */
/* #undef HAVE_APPEND_HISTORY */
/* Define to 1 if you want to use atomics if available. */
#define HAVE_ATOMICS 1
/* Define to 1 if you have the <atomic.h> header file. */
/* #undef HAVE_ATOMIC_H */
/* Define to 1 if you have the `cbrt' function. */
#define HAVE_CBRT 1
/* Define to 1 if you have the `class' function. */
/* #undef HAVE_CLASS */
/* Define to 1 if you have the <crtdefs.h> header file. */
/* #undef HAVE_CRTDEFS_H */
/* Define to 1 if you have the `crypt' function. */
#define HAVE_CRYPT 1
/* Define to 1 if you have the <crypt.h> header file. */
#define HAVE_CRYPT_H 1
/* Define to 1 if you have the declaration of `fdatasync', and to 0 if you
don't. */
#define HAVE_DECL_FDATASYNC 1
/* Define to 1 if you have the declaration of `F_FULLFSYNC', and to 0 if you
don't. */
#define HAVE_DECL_F_FULLFSYNC 0
/* Define to 1 if you have the declaration of `posix_fadvise', and to 0 if you
don't. */
#define HAVE_DECL_POSIX_FADVISE 1
/* Define to 1 if you have the declaration of `snprintf', and to 0 if you
don't. */
#define HAVE_DECL_SNPRINTF 1
/* Define to 1 if you have the declaration of `strlcat', and to 0 if you
don't. */
#if OS_DARWIN
#define HAVE_DECL_STRLCAT 1
#endif
/* Define to 1 if you have the declaration of `strlcpy', and to 0 if you
don't. */
#if OS_DARWIN
#define HAVE_DECL_STRLCPY 1
#endif
/* Define to 1 if you have the declaration of `sys_siglist', and to 0 if you
don't. */
#define HAVE_DECL_SYS_SIGLIST 1
/* Define to 1 if you have the declaration of `vsnprintf', and to 0 if you
don't. */
#define HAVE_DECL_VSNPRINTF 1
/* Define to 1 if you have the <dld.h> header file. */
/* #undef HAVE_DLD_H */
/* Define to 1 if you have the `dlopen' function. */
#define HAVE_DLOPEN 1
/* Define to 1 if you have the <editline/history.h> header file. */
/* #undef HAVE_EDITLINE_HISTORY_H */
/* Define to 1 if you have the <editline/readline.h> header file. */
#define HAVE_EDITLINE_READLINE_H 1
/* Define to 1 if you have the `fdatasync' function. */
#define HAVE_FDATASYNC 1
/* Define to 1 if you have the `fls' function. */
/* #undef HAVE_FLS */
/* Define to 1 if you have the `fpclass' function. */
/* #undef HAVE_FPCLASS */
/* Define to 1 if you have the `fp_class' function. */
/* #undef HAVE_FP_CLASS */
/* Define to 1 if you have the `fp_class_d' function. */
/* #undef HAVE_FP_CLASS_D */
/* Define to 1 if you have the <fp_class.h> header file. */
/* #undef HAVE_FP_CLASS_H */
/* Define to 1 if fseeko (and presumably ftello) exists and is declared. */
#define HAVE_FSEEKO 1
/* Define to 1 if your compiler understands __func__. */
#define HAVE_FUNCNAME__FUNC 1
/* Define to 1 if your compiler understands __FUNCTION__. */
/* #undef HAVE_FUNCNAME__FUNCTION */
/* Define to 1 if you have __atomic_compare_exchange_n(int *, int *, int). */
/* #undef HAVE_GCC__ATOMIC_INT32_CAS */
/* Define to 1 if you have __atomic_compare_exchange_n(int64 *, int *, int64).
*/
/* #undef HAVE_GCC__ATOMIC_INT64_CAS */
/* Define to 1 if you have __sync_lock_test_and_set(char *) and friends. */
#define HAVE_GCC__SYNC_CHAR_TAS 1
/* Define to 1 if you have __sync_compare_and_swap(int *, int, int). */
/* #undef HAVE_GCC__SYNC_INT32_CAS */
/* Define to 1 if you have __sync_lock_test_and_set(int *) and friends. */
#define HAVE_GCC__SYNC_INT32_TAS 1
/* Define to 1 if you have __sync_compare_and_swap(int64 *, int64, int64). */
/* #undef HAVE_GCC__SYNC_INT64_CAS */
/* Define to 1 if you have the `getaddrinfo' function. */
#define HAVE_GETADDRINFO 1
/* Define to 1 if you have the `gethostbyname_r' function. */
#define HAVE_GETHOSTBYNAME_R 1
/* Define to 1 if you have the `getifaddrs' function. */
#define HAVE_GETIFADDRS 1
/* Define to 1 if you have the `getopt' function. */
#define HAVE_GETOPT 1
/* Define to 1 if you have the <getopt.h> header file. */
#define HAVE_GETOPT_H 1
/* Define to 1 if you have the `getopt_long' function. */
#define HAVE_GETOPT_LONG 1
/* Define to 1 if you have the `getpeereid' function. */
/* #undef HAVE_GETPEEREID */
/* Define to 1 if you have the `getpeerucred' function. */
/* #undef HAVE_GETPEERUCRED */
/* Define to 1 if you have the `getpwuid_r' function. */
#define HAVE_GETPWUID_R 1
/* Define to 1 if you have the `getrlimit' function. */
#define HAVE_GETRLIMIT 1
/* Define to 1 if you have the `getrusage' function. */
#define HAVE_GETRUSAGE 1
/* Define to 1 if you have the `gettimeofday' function. */
/* #undef HAVE_GETTIMEOFDAY */
/* Define to 1 if you have the <gssapi/gssapi.h> header file. */
//#define HAVE_GSSAPI_GSSAPI_H 0
/* Define to 1 if you have the <gssapi.h> header file. */
/* #undef HAVE_GSSAPI_H */
/* Define to 1 if you have the <history.h> header file. */
/* #undef HAVE_HISTORY_H */
/* Define to 1 if you have the `history_truncate_file' function. */
#define HAVE_HISTORY_TRUNCATE_FILE 1
/* Define to 1 if you have the <ieeefp.h> header file. */
/* #undef HAVE_IEEEFP_H */
/* Define to 1 if you have the <ifaddrs.h> header file. */
#define HAVE_IFADDRS_H 1
/* Define to 1 if you have the `inet_aton' function. */
#define HAVE_INET_ATON 1
/* Define to 1 if the system has the type `int64'. */
/* #undef HAVE_INT64 */
/* Define to 1 if the system has the type `int8'. */
/* #undef HAVE_INT8 */
/* Define to 1 if the system has the type `intptr_t'. */
#define HAVE_INTPTR_T 1
/* Define to 1 if you have the <inttypes.h> header file. */
#define HAVE_INTTYPES_H 1
/* Define to 1 if you have the global variable 'int opterr'. */
#define HAVE_INT_OPTERR 1
/* Define to 1 if you have the global variable 'int optreset'. */
/* #undef HAVE_INT_OPTRESET */
/* Define to 1 if you have the global variable 'int timezone'. */
#define HAVE_INT_TIMEZONE 1
/* Define to 1 if you have support for IPv6. */
#define HAVE_IPV6 1
/* Define to 1 if you have isinf(). */
#define HAVE_ISINF 1
/* Define to 1 if you have the <langinfo.h> header file. */
#define HAVE_LANGINFO_H 1
/* Define to 1 if you have the <ldap.h> header file. */
//#define HAVE_LDAP_H 0
/* Define to 1 if you have the `crypto' library (-lcrypto). */
#define HAVE_LIBCRYPTO 1
/* Define to 1 if you have the `ldap' library (-lldap). */
//#define HAVE_LIBLDAP 0
/* Define to 1 if you have the `m' library (-lm). */
#define HAVE_LIBM 1
/* Define to 1 if you have the `pam' library (-lpam). */
#define HAVE_LIBPAM 1
/* Define if you have a function readline library */
#define HAVE_LIBREADLINE 1
/* Define to 1 if you have the `selinux' library (-lselinux). */
/* #undef HAVE_LIBSELINUX */
/* Define to 1 if you have the `ssl' library (-lssl). */
#define HAVE_LIBSSL 0
/* Define to 1 if you have the `wldap32' library (-lwldap32). */
/* #undef HAVE_LIBWLDAP32 */
/* Define to 1 if you have the `xml2' library (-lxml2). */
#define HAVE_LIBXML2 1
/* Define to 1 if you have the `xslt' library (-lxslt). */
#define HAVE_LIBXSLT 1
/* Define to 1 if you have the `z' library (-lz). */
#define HAVE_LIBZ 1
/* Define to 1 if constants of type 'long long int' should have the suffix LL.
*/
#define HAVE_LL_CONSTANTS 1
/* Define to 1 if the system has the type `locale_t'. */
#define HAVE_LOCALE_T 1
/* Define to 1 if `long int' works and is 64 bits. */
/* #undef HAVE_LONG_INT_64 */
/* Define to 1 if the system has the type `long long int'. */
#define HAVE_LONG_LONG_INT 1
/* Define to 1 if `long long int' works and is 64 bits. */
#define HAVE_LONG_LONG_INT_64 1
/* Define to 1 if you have the <mbarrier.h> header file. */
/* #undef HAVE_MBARRIER_H */
/* Define to 1 if you have the `mbstowcs_l' function. */
/* #undef HAVE_MBSTOWCS_L */
/* Define to 1 if you have the `memmove' function. */
#define HAVE_MEMMOVE 1
/* Define to 1 if you have the <memory.h> header file. */
#define HAVE_MEMORY_H 1
/* Define to 1 if the system has the type `MINIDUMP_TYPE'. */
/* #undef HAVE_MINIDUMP_TYPE */
/* Define to 1 if you have the `mkdtemp' function. */
#define HAVE_MKDTEMP 1
/* Define to 1 if you have the <netinet/in.h> header file. */
#define HAVE_NETINET_IN_H 1
/* Define to 1 if you have the <netinet/tcp.h> header file. */
#define HAVE_NETINET_TCP_H 1
/* Define to 1 if you have the <net/if.h> header file. */
#define HAVE_NET_IF_H 1
/* Define to 1 if you have the <ossp/uuid.h> header file. */
/* #undef HAVE_OSSP_UUID_H */
/* Define to 1 if you have the <pam/pam_appl.h> header file. */
/* #undef HAVE_PAM_PAM_APPL_H */
/* Define to 1 if you have the `poll' function. */
#define HAVE_POLL 1
/* Define to 1 if you have the <poll.h> header file. */
#define HAVE_POLL_H 1
/* Define to 1 if you have the `posix_fadvise' function. */
#define HAVE_POSIX_FADVISE 1
/* Define to 1 if you have the declaration of `preadv', and to 0 if you don't. */
/* #undef HAVE_DECL_PREADV */
/* Define to 1 if you have the declaration of `pwritev', and to 0 if you don't. */
/* #define HAVE_DECL_PWRITEV */
/* Define to 1 if you have the `X509_get_signature_info' function. */
/* #undef HAVE_X509_GET_SIGNATURE_INFO */
/* Define to 1 if you have the POSIX signal interface. */
#define HAVE_POSIX_SIGNALS 1
/* Define to 1 if the assembler supports PPC's LWARX mutex hint bit. */
/* #undef HAVE_PPC_LWARX_MUTEX_HINT */
/* Define to 1 if you have the `pstat' function. */
/* #undef HAVE_PSTAT */
/* Define to 1 if the PS_STRINGS thing exists. */
/* #undef HAVE_PS_STRINGS */
/* Define to 1 if you have the `pthread_is_threaded_np' function. */
/* #undef HAVE_PTHREAD_IS_THREADED_NP */
/* Define to 1 if you have the <pwd.h> header file. */
#define HAVE_PWD_H 1
/* Define to 1 if you have the `random' function. */
#define HAVE_RANDOM 1
/* Define to 1 if you have the <readline.h> header file. */
/* #undef HAVE_READLINE_H */
/* Define to 1 if you have the <readline/history.h> header file. */
#define HAVE_READLINE_HISTORY_H 1
/* Define to 1 if you have the <readline/readline.h> header file. */
/* #undef HAVE_READLINE_READLINE_H */
/* Define to 1 if you have the `readlink' function. */
#define HAVE_READLINK 1
/* Define to 1 if you have the `rint' function. */
#define HAVE_RINT 1
/* Define to 1 if you have the global variable
'rl_completion_append_character'. */
/* #undef HAVE_RL_COMPLETION_APPEND_CHARACTER */
/* Define to 1 if you have the `rl_completion_matches' function. */
#define HAVE_RL_COMPLETION_MATCHES 1
/* Define to 1 if you have the `rl_filename_completion_function' function. */
#define HAVE_RL_FILENAME_COMPLETION_FUNCTION 1
/* Define to 1 if you have the `rl_reset_screen_size' function. */
/* #undef HAVE_RL_RESET_SCREEN_SIZE */
/* Define to 1 if you have the <security/pam_appl.h> header file. */
#define HAVE_SECURITY_PAM_APPL_H 1
/* Define to 1 if you have the `setproctitle' function. */
/* #undef HAVE_SETPROCTITLE */
/* Define to 1 if you have the `setsid' function. */
#define HAVE_SETSID 1
/* Define to 1 if you have the `shm_open' function. */
#define HAVE_SHM_OPEN 1
/* Define to 1 if you have the `sigprocmask' function. */
#define HAVE_SIGPROCMASK 1
/* Define to 1 if you have sigsetjmp(). */
#define HAVE_SIGSETJMP 1
/* Define to 1 if the system has the type `sig_atomic_t'. */
#define HAVE_SIG_ATOMIC_T 1
/* Define to 1 if you have the `snprintf' function. */
#define HAVE_SNPRINTF 1
/* Define to 1 if you have spinlocks. */
#define HAVE_SPINLOCKS 1
/* Define to 1 if you have the `srandom' function. */
#define HAVE_SRANDOM 1
/* Define to 1 if you have the `SSL_CTX_set_num_tickets' function. */
/* #define HAVE_SSL_CTX_SET_NUM_TICKETS */
/* Define to 1 if you have the `SSL_get_current_compression' function. */
#define HAVE_SSL_GET_CURRENT_COMPRESSION 0
/* Define to 1 if you have the <stdint.h> header file. */
#define HAVE_STDINT_H 1
/* Define to 1 if you have the <stdlib.h> header file. */
#define HAVE_STDLIB_H 1
/* Define to 1 if you have the `strerror' function. */
#define HAVE_STRERROR 1
/* Define to 1 if you have the `strerror_r' function. */
#define HAVE_STRERROR_R 1
/* Define to 1 if you have the <strings.h> header file. */
//#define HAVE_STRINGS_H 1
/* Define to 1 if you have the <string.h> header file. */
#define HAVE_STRING_H 1
/* Define to 1 if you have the `strlcat' function. */
/* #undef HAVE_STRLCAT */
/* Define to 1 if you have the `strlcpy' function. */
/* #undef HAVE_STRLCPY */
/* Define to 1 if you have the `strtoll' function. */
#define HAVE_STRTOLL 1
#if (!OS_DARWIN)
#define HAVE_STRCHRNUL 1
#endif
/* Define to 1 if you have the `strtoq' function. */
/* #undef HAVE_STRTOQ */
/* Define to 1 if you have the `strtoull' function. */
#define HAVE_STRTOULL 1
/* Define to 1 if you have the `strtouq' function. */
/* #undef HAVE_STRTOUQ */
/* Define to 1 if the system has the type `struct addrinfo'. */
#define HAVE_STRUCT_ADDRINFO 1
/* Define to 1 if the system has the type `struct cmsgcred'. */
/* #undef HAVE_STRUCT_CMSGCRED */
/* Define to 1 if the system has the type `struct option'. */
#define HAVE_STRUCT_OPTION 1
/* Define to 1 if `sa_len' is a member of `struct sockaddr'. */
/* #undef HAVE_STRUCT_SOCKADDR_SA_LEN */
/* Define to 1 if the system has the type `struct sockaddr_storage'. */
#define HAVE_STRUCT_SOCKADDR_STORAGE 1
/* Define to 1 if `ss_family' is a member of `struct sockaddr_storage'. */
#define HAVE_STRUCT_SOCKADDR_STORAGE_SS_FAMILY 1
/* Define to 1 if `ss_len' is a member of `struct sockaddr_storage'. */
/* #undef HAVE_STRUCT_SOCKADDR_STORAGE_SS_LEN */
/* Define to 1 if `__ss_family' is a member of `struct sockaddr_storage'. */
/* #undef HAVE_STRUCT_SOCKADDR_STORAGE___SS_FAMILY */
/* Define to 1 if `__ss_len' is a member of `struct sockaddr_storage'. */
/* #undef HAVE_STRUCT_SOCKADDR_STORAGE___SS_LEN */
/* Define to 1 if `tm_zone' is a member of `struct tm'. */
#define HAVE_STRUCT_TM_TM_ZONE 1
/* Define to 1 if you have the `symlink' function. */
#define HAVE_SYMLINK 1
/* Define to 1 if you have the `sync_file_range' function. */
/* #undef HAVE_SYNC_FILE_RANGE */
/* Define to 1 if you have the syslog interface. */
#define HAVE_SYSLOG 1
/* Define to 1 if you have the <sys/ioctl.h> header file. */
#define HAVE_SYS_IOCTL_H 1
/* Define to 1 if you have the <sys/ipc.h> header file. */
#define HAVE_SYS_IPC_H 1
/* Define to 1 if you have the <sys/personality.h> header file. */
/* #undef HAVE_SYS_PERSONALITY_H */
/* Define to 1 if you have the <sys/poll.h> header file. */
#define HAVE_SYS_POLL_H 1
/* Define to 1 if you have the <sys/pstat.h> header file. */
/* #undef HAVE_SYS_PSTAT_H */
/* Define to 1 if you have the <sys/resource.h> header file. */
#define HAVE_SYS_RESOURCE_H 1
/* Define to 1 if you have the <sys/select.h> header file. */
#define HAVE_SYS_SELECT_H 1
/* Define to 1 if you have the <sys/sem.h> header file. */
#define HAVE_SYS_SEM_H 1
/* Define to 1 if you have the <sys/shm.h> header file. */
#define HAVE_SYS_SHM_H 1
/* Define to 1 if you have the <sys/signalfd.h> header file. */
/* #undef HAVE_SYS_SIGNALFD_H */
/* Define to 1 if you have the <sys/socket.h> header file. */
#define HAVE_SYS_SOCKET_H 1
/* Define to 1 if you have the <sys/sockio.h> header file. */
/* #undef HAVE_SYS_SOCKIO_H */
/* Define to 1 if you have the <sys/stat.h> header file. */
#define HAVE_SYS_STAT_H 1
/* Define to 1 if you have the <sys/tas.h> header file. */
/* #undef HAVE_SYS_TAS_H */
/* Define to 1 if you have the <sys/time.h> header file. */
#define HAVE_SYS_TIME_H 1
/* Define to 1 if you have the <sys/types.h> header file. */
#define HAVE_SYS_TYPES_H 1
/* Define to 1 if you have the <sys/ucred.h> header file. */
#if (OS_DARWIN || OS_FREEBSD)
#define HAVE_SYS_UCRED_H 1
#endif
/* Define to 1 if you have the <sys/un.h> header file. */
#define HAVE_SYS_UN_H 1
#define _GNU_SOURCE 1 /* Needed for glibc struct ucred */
/* Define to 1 if you have the <termios.h> header file. */
#define HAVE_TERMIOS_H 1
/* Define to 1 if your `struct tm' has `tm_zone'. Deprecated, use
`HAVE_STRUCT_TM_TM_ZONE' instead. */
#define HAVE_TM_ZONE 1
/* Define to 1 if you have the `towlower' function. */
#define HAVE_TOWLOWER 1
/* Define to 1 if you have the external array `tzname'. */
#define HAVE_TZNAME 1
/* Define to 1 if you have the <ucred.h> header file. */
/* #undef HAVE_UCRED_H */
/* Define to 1 if the system has the type `uint64'. */
/* #undef HAVE_UINT64 */
/* Define to 1 if the system has the type `uint8'. */
/* #undef HAVE_UINT8 */
/* Define to 1 if the system has the type `uintptr_t'. */
#define HAVE_UINTPTR_T 1
/* Define to 1 if the system has the type `union semun'. */
/* #undef HAVE_UNION_SEMUN */
/* Define to 1 if you have the <unistd.h> header file. */
#define HAVE_UNISTD_H 1
/* Define to 1 if you have unix sockets. */
#define HAVE_UNIX_SOCKETS 1
/* Define to 1 if you have the `unsetenv' function. */
#define HAVE_UNSETENV 1
/* Define to 1 if the system has the type `unsigned long long int'. */
#define HAVE_UNSIGNED_LONG_LONG_INT 1
/* Define to 1 if you have the `utime' function. */
#define HAVE_UTIME 1
/* Define to 1 if you have the `utimes' function. */
#define HAVE_UTIMES 1
/* Define to 1 if you have the <utime.h> header file. */
#define HAVE_UTIME_H 1
/* Define to 1 if you have BSD UUID support. */
/* #undef HAVE_UUID_BSD */
/* Define to 1 if you have E2FS UUID support. */
/* #undef HAVE_UUID_E2FS */
/* Define to 1 if you have the <uuid.h> header file. */
#define HAVE_UUID_H 1
/* Define to 1 if you have OSSP UUID support. */
#define HAVE_UUID_OSSP 1
/* Define to 1 if you have the <uuid/uuid.h> header file. */
/* #undef HAVE_UUID_UUID_H */
/* Define to 1 if you have the `vsnprintf' function. */
#define HAVE_VSNPRINTF 1
/* Define to 1 if you have the <wchar.h> header file. */
#define HAVE_WCHAR_H 1
/* Define to 1 if you have the `wcstombs' function. */
#define HAVE_WCSTOMBS 1
/* Define to 1 if you have the `wcstombs_l' function. */
/* #undef HAVE_WCSTOMBS_L */
/* Define to 1 if you have the <wctype.h> header file. */
#define HAVE_WCTYPE_H 1
/* Define to 1 if you have the <winldap.h> header file. */
/* #undef HAVE_WINLDAP_H */
/* Define to 1 if your compiler understands __builtin_bswap32. */
/* #undef HAVE__BUILTIN_BSWAP32 */
/* Define to 1 if your compiler understands __builtin_constant_p. */
#define HAVE__BUILTIN_CONSTANT_P 1
/* Define to 1 if your compiler understands __builtin_frame_address. */
/* #undef HAVE__BUILTIN_FRAME_ADDRESS */
/* Define to 1 if your compiler understands __builtin_types_compatible_p. */
#define HAVE__BUILTIN_TYPES_COMPATIBLE_P 1
/* Define to 1 if your compiler understands __builtin_unreachable. */
/* #undef HAVE__BUILTIN_UNREACHABLE */
/* Define to 1 if you have __cpuid. */
/* #undef HAVE__CPUID */
/* Define to 1 if you have __get_cpuid. */
/* #undef HAVE__GET_CPUID */
/* Define to 1 if your compiler understands _Static_assert. */
/* #undef HAVE__STATIC_ASSERT */
/* Define to 1 if your compiler understands __VA_ARGS__ in macros. */
#define HAVE__VA_ARGS 1
/* Define to the appropriate snprintf length modifier for 64-bit ints. */
#define INT64_MODIFIER "ll"
/* Define to 1 if `locale_t' requires <xlocale.h>. */
/* #undef LOCALE_T_IN_XLOCALE */
/* Define as the maximum alignment requirement of any C data type. */
#define MAXIMUM_ALIGNOF 4
/* Define bytes to use libc memset(). */
#define MEMSET_LOOP_LIMIT 1024
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT "pgsql-bugs@postgresql.org"
/* Define to the full name of this package. */
#define PACKAGE_NAME "PostgreSQL"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "PostgreSQL 9.5.4"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "postgresql"
/* Define to the home page for this package. */
#define PACKAGE_URL ""
/* Define to the version of this package. */
#define PACKAGE_VERSION "9.5.4"
/* Define to the name of a signed 128-bit integer type. */
/* #undef PG_INT128_TYPE */
/* Define to the name of a signed 64-bit integer type. */
#define PG_INT64_TYPE long long int
/* Define to the name of the default PostgreSQL service principal in Kerberos
(GSSAPI). (--with-krb-srvnam=NAME) */
#define PG_KRB_SRVNAM "postgres"
/* PostgreSQL major version as a string */
#define PG_MAJORVERSION "9.5"
/* Define to gnu_printf if compiler supports it, else printf. */
#define PG_PRINTF_ATTRIBUTE printf
/* Define to 1 if "static inline" works without unwanted warnings from
compilations where static inline functions are defined but not called. */
#define PG_USE_INLINE 1
/* PostgreSQL version as a string */
#define PG_VERSION "9.5.4"
/* PostgreSQL version as a number */
#define PG_VERSION_NUM 90504
/* A string containing the version number, platform, and C compiler */
#define PG_VERSION_STR "PostgreSQL 9.5.4 on i686-pc-linux-gnu, compiled by gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55), 32-bit"
/* Define to 1 to allow profiling output to be saved separately for each
process. */
/* #undef PROFILE_PID_DIR */
/* RELSEG_SIZE is the maximum number of blocks allowed in one disk file. Thus,
the maximum size of a single file is RELSEG_SIZE * BLCKSZ; relations bigger
than that are divided into multiple files. RELSEG_SIZE * BLCKSZ must be
less than your OS' limit on file size. This is often 2 GB or 4GB in a
32-bit operating system, unless you have large file support enabled. By
default, we make the limit 1 GB to avoid any possible integer-overflow
problems within the OS. A limit smaller than necessary only means we divide
a large relation into more chunks than necessary, so it seems best to err
in the direction of a small limit. A power-of-2 value is recommended to
save a few cycles in md.c, but is not absolutely required. Changing
RELSEG_SIZE requires an initdb. */
#define RELSEG_SIZE 131072
/* The size of `long', as computed by sizeof. */
#define SIZEOF_LONG 4
/* The size of `off_t', as computed by sizeof. */
#define SIZEOF_OFF_T 8
/* The size of `size_t', as computed by sizeof. */
#define SIZEOF_SIZE_T 4
/* The size of `void *', as computed by sizeof. */
#define SIZEOF_VOID_P 4
/* Define to 1 if you have the ANSI C header files. */
#define STDC_HEADERS 1
/* Define to 1 if strerror_r() returns a int. */
/* #undef STRERROR_R_INT */
/* Define to 1 if your <sys/time.h> declares `struct tm'. */
/* #undef TM_IN_SYS_TIME */
/* Define to 1 to build with assertion checks. (--enable-cassert) */
/* #undef USE_ASSERT_CHECKING */
/* Define to 1 to build with Bonjour support. (--with-bonjour) */
/* #undef USE_BONJOUR */
/* Define to 1 if you want float4 values to be passed by value.
(--enable-float4-byval) */
#define USE_FLOAT4_BYVAL 1
/* Define to 1 if you want float8, int8, etc values to be passed by value.
(--enable-float8-byval) */
/* #undef USE_FLOAT8_BYVAL */
/* Define to 1 if you want 64-bit integer timestamp and interval support.
(--enable-integer-datetimes) */
#define USE_INTEGER_DATETIMES 1
/* Define to 1 to build with LDAP support. (--with-ldap) */
//#define USE_LDAP 0
/* Define to 1 to build with XML support. (--with-libxml) */
#define USE_LIBXML 1
/* Define to 1 to use XSLT support when building contrib/xml2.
(--with-libxslt) */
#define USE_LIBXSLT 1
/* Define to select named POSIX semaphores. */
/* #undef USE_NAMED_POSIX_SEMAPHORES */
/* Define to build with OpenSSL support. (--with-openssl) */
#define USE_OPENSSL 0
#define USE_OPENSSL_RANDOM 0
#define FRONTEND 1
/* Define to 1 to build with PAM support. (--with-pam) */
#define USE_PAM 1
/* Use replacement snprintf() functions. */
/* #undef USE_REPL_SNPRINTF */
/* Define to 1 to use Intel SSE 4.2 CRC instructions with a runtime check. */
#define USE_SLICING_BY_8_CRC32C 1
/* Define to 1 use Intel SSE 4.2 CRC instructions. */
/* #undef USE_SSE42_CRC32C */
/* Define to 1 to use Intel SSSE 4.2 CRC instructions with a runtime check. */
/* #undef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK */
/* Define to select SysV-style semaphores. */
#define USE_SYSV_SEMAPHORES 1
/* Define to select SysV-style shared memory. */
#define USE_SYSV_SHARED_MEMORY 1
/* Define to select unnamed POSIX semaphores. */
/* #undef USE_UNNAMED_POSIX_SEMAPHORES */
/* Define to select Win32-style semaphores. */
/* #undef USE_WIN32_SEMAPHORES */
/* Define to select Win32-style shared memory. */
/* #undef USE_WIN32_SHARED_MEMORY */
/* Define to 1 if `wcstombs_l' requires <xlocale.h>. */
/* #undef WCSTOMBS_L_IN_XLOCALE */
/* Define WORDS_BIGENDIAN to 1 if your processor stores words with the most
significant byte first (like Motorola and SPARC, unlike Intel). */
#if defined AC_APPLE_UNIVERSAL_BUILD
# if defined __BIG_ENDIAN__
# define WORDS_BIGENDIAN 1
# endif
#else
# ifndef WORDS_BIGENDIAN
/* # undef WORDS_BIGENDIAN */
# endif
#endif
/* Size of a WAL file block. This need have no particular relation to BLCKSZ.
XLOG_BLCKSZ must be a power of 2, and if your system supports O_DIRECT I/O,
XLOG_BLCKSZ must be a multiple of the alignment requirement for direct-I/O
buffers, else direct I/O may fail. Changing XLOG_BLCKSZ requires an initdb.
*/
#define XLOG_BLCKSZ 8192
/* XLOG_SEG_SIZE is the size of a single WAL file. This must be a power of 2
and larger than XLOG_BLCKSZ (preferably, a great deal larger than
XLOG_BLCKSZ). Changing XLOG_SEG_SIZE requires an initdb. */
#define XLOG_SEG_SIZE (16 * 1024 * 1024)
/* Number of bits in a file offset, on hosts where this is settable. */
#define _FILE_OFFSET_BITS 64
/* Define to 1 to make fseeko visible on some hosts (e.g. glibc 2.2). */
/* #undef _LARGEFILE_SOURCE */
/* Define for large files, on AIX-style hosts. */
/* #undef _LARGE_FILES */
/* Define to `__inline__' or `__inline' if that's what the C compiler
calls it, or to nothing if 'inline' is not supported under any name. */
#ifndef __cplusplus
/* #undef inline */
#endif
/* Define to the type of a signed integer type wide enough to hold a pointer,
if such a type exists, and if the system does not define it. */
/* #undef intptr_t */
/* Define to empty if the C compiler does not understand signed types. */
/* #undef signed */
/* Define to the type of an unsigned integer type wide enough to hold a
pointer, if such a type exists, and if the system does not define it. */
/* #undef uintptr_t */

7
contrib/postgres-cmake/pg_config_ext.h Normal file
View File

@ -0,0 +1,7 @@
/*
* * src/include/pg_config_ext.h.in. This is generated manually, not by
* * autoheader, since we want to limit which symbols get defined here.
* */
/* Define to the name of a signed 64-bit integer type. */
#define PG_INT64_TYPE long long int

34
contrib/postgres-cmake/pg_config_os.h Normal file
View File

@ -0,0 +1,34 @@
#if defined(OS_DARWIN)
/* src/include/port/darwin.h */
#define __darwin__ 1
#if HAVE_DECL_F_FULLFSYNC /* not present before macOS 10.3 */
#define HAVE_FSYNC_WRITETHROUGH
#endif
#else
/* src/include/port/linux.h */
/*
* As of July 2007, all known versions of the Linux kernel will sometimes
* return EIDRM for a shmctl() operation when EINVAL is correct (it happens
* when the low-order 15 bits of the supplied shm ID match the slot number
* assigned to a newer shmem segment). We deal with this by assuming that
* EIDRM means EINVAL in PGSharedMemoryIsInUse(). This is reasonably safe
* since in fact Linux has no excuse for ever returning EIDRM; it doesn't
* track removed segments in a way that would allow distinguishing them from
* private ones. But someday that code might get upgraded, and we'd have
* to have a kernel version test here.
*/
#define HAVE_LINUX_EIDRM_BUG
/*
* Set the default wal_sync_method to fdatasync. With recent Linux versions,
* xlogdefs.h's normal rules will prefer open_datasync, which (a) doesn't
* perform better and (b) causes outright failures on ext4 data=journal
* filesystems, because those don't support O_DIRECT.
*/
#define PLATFORM_DEFAULT_SYNC_METHOD SYNC_METHOD_FDATASYNC
#endif

12
contrib/postgres-cmake/pg_config_paths.h Normal file
View File

@ -0,0 +1,12 @@
#define PGBINDIR "/bin"
#define PGSHAREDIR "/share"
#define SYSCONFDIR "/etc"
#define INCLUDEDIR "/include"
#define PKGINCLUDEDIR "/include"
#define INCLUDEDIRSERVER "/include/server"
#define LIBDIR "/lib"
#define PKGLIBDIR "/lib"
#define LOCALEDIR "/share/locale"
#define DOCDIR "/doc"
#define HTMLDIR "/doc"
#define MANDIR "/man"

0
contrib/postgres-cmake/utils/errcodes.h Normal file
View File

2
contrib/sysroot vendored

@ -1 +1 @@
Subproject commit cc385041b226d1fc28ead14dbab5d40a5f821dd8
Subproject commit 5be834147d5b5dd77ca2b821f356982029320513

2
docker/keeper/Dockerfile
View File

@ -34,7 +34,7 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="24.8.3.59"
ARG VERSION="24.8.4.13"
ARG PACKAGES="clickhouse-keeper"
ARG DIRECT_DOWNLOAD_URLS=""

2
docker/server/Dockerfile.alpine
View File

@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="24.8.3.59"
ARG VERSION="24.8.4.13"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
ARG DIRECT_DOWNLOAD_URLS=""

2
docker/server/Dockerfile.ubuntu
View File

@ -28,7 +28,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
ARG VERSION="24.8.3.59"
ARG VERSION="24.8.4.13"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
#docker-official-library:off

2
docker/server/entrypoint.sh
View File

@ -109,7 +109,7 @@ if [ -n "$CLICKHOUSE_USER" ] && [ "$CLICKHOUSE_USER" != "default" ] || [ -n "$CL
<networks>
<ip>::/0</ip>
</networks>
<password>${CLICKHOUSE_PASSWORD}</password>
<password><![CDATA[${CLICKHOUSE_PASSWORD//]]>/]]]]><![CDATA[>}]]></password>
<quota>default</quota>
<access_management>${CLICKHOUSE_ACCESS_MANAGEMENT}</access_management>
</${CLICKHOUSE_USER}>

14
docker/test/base/setup_export_logs.sh
View File

@ -124,6 +124,8 @@ function setup_logs_replication
check_logs_credentials || return 0
__set_connection_args
echo "My hostname is ${HOSTNAME}"
echo 'Create all configured system logs'
clickhouse-client --query "SYSTEM FLUSH LOGS"
@ -184,7 +186,17 @@ function setup_logs_replication
/^TTL /d
')
echo -e "Creating remote destination table ${table}_${hash} with statement:\n${statement}" >&2
echo -e "Creating remote destination table ${table}_${hash} with statement:" >&2
echo "::group::${table}"
# there's the only way big "$statement" can be printed without causing EAGAIN error
# cat: write error: Resource temporarily unavailable
statement_print="${statement}"
if [ "${#statement_print}" -gt 4000 ]; then
statement_print="${statement::1999}\n…\n${statement:${#statement}-1999}"
fi
echo -e "$statement_print"
echo "::endgroup::"
echo "$statement" | clickhouse-client --database_replicated_initial_query_timeout_sec=10 \
--distributed_ddl_task_timeout=30 --distributed_ddl_output_mode=throw_only_active \

4
docker/test/integration/helper_container/Dockerfile
View File

@ -3,6 +3,8 @@
FROM alpine:3.18
RUN apk add --no-cache -U iproute2 \
&& for bin in iptables iptables-restore iptables-save; \
&& for bin in \
iptables iptables-restore iptables-save \
ip6tables ip6tables-restore ip6tables-save; \
do ln -sf xtables-nft-multi "/sbin/$bin"; \
done

17
docs/changelogs/v24.3.11.7-lts.md Normal file
View File

@ -0,0 +1,17 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.3.11.7-lts (28795d0a47e) FIXME as compared to v24.3.10.33-lts (37b6502ebf0)
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#67479](https://github.com/ClickHouse/ClickHouse/issues/67479): In rare cases ClickHouse could consider parts as broken because of some unexpected projections on disk. Now it's fixed. [#66898](https://github.com/ClickHouse/ClickHouse/pull/66898) ([alesapin](https://github.com/alesapin)).
* Backported in [#69243](https://github.com/ClickHouse/ClickHouse/issues/69243): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Backported in [#69221](https://github.com/ClickHouse/ClickHouse/issues/69221): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).

18
docs/changelogs/v24.5.8.10-stable.md Normal file
View File

@ -0,0 +1,18 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.5.8.10-stable (f11729638ea) FIXME as compared to v24.5.7.31-stable (6c185e9aec1)
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#69295](https://github.com/ClickHouse/ClickHouse/issues/69295): TODO. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Backported in [#69245](https://github.com/ClickHouse/ClickHouse/issues/69245): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix crash when using `s3` table function with GLOB paths and filters. [#69176](https://github.com/ClickHouse/ClickHouse/pull/69176) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Backported in [#69223](https://github.com/ClickHouse/ClickHouse/issues/69223): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).

16
docs/changelogs/v24.6.6.6-stable.md Normal file
View File

@ -0,0 +1,16 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.6.6.6-stable (a4c4580e639) FIXME as compared to v24.6.5.30-stable (e6e196c92d6)
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#69197](https://github.com/ClickHouse/ClickHouse/issues/69197): TODO. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Backported in [#69225](https://github.com/ClickHouse/ClickHouse/issues/69225): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).

17
docs/changelogs/v24.7.6.8-stable.md Normal file
View File

@ -0,0 +1,17 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.7.6.8-stable (7779883593a) FIXME as compared to v24.7.5.37-stable (f2533ca97be)
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#69198](https://github.com/ClickHouse/ClickHouse/issues/69198): TODO. [#68744](https://github.com/ClickHouse/ClickHouse/pull/68744) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Backported in [#69249](https://github.com/ClickHouse/ClickHouse/issues/69249): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Backported in [#69227](https://github.com/ClickHouse/ClickHouse/issues/69227): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).

22
docs/changelogs/v24.8.4.13-lts.md Normal file
View File

@ -0,0 +1,22 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.8.4.13-lts (53195bc189b) FIXME as compared to v24.8.3.59-lts (e729b9fa40e)
#### Improvement
* Backported in [#68699](https://github.com/ClickHouse/ClickHouse/issues/68699): Delete old code of named collections from dictionaries and substitute it to the new, which allows to use DDL created named collections in dictionaries. Closes [#60936](https://github.com/ClickHouse/ClickHouse/issues/60936), closes [#36890](https://github.com/ClickHouse/ClickHouse/issues/36890). [#68412](https://github.com/ClickHouse/ClickHouse/pull/68412) ([Kseniia Sumarokova](https://github.com/kssenii)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Backported in [#69231](https://github.com/ClickHouse/ClickHouse/issues/69231): Fix parsing error when null should be inserted as default in some cases during JSON type parsing. [#68955](https://github.com/ClickHouse/ClickHouse/pull/68955) ([Kruglov Pavel](https://github.com/Avogar)).
* Backported in [#69251](https://github.com/ClickHouse/ClickHouse/issues/69251): `UNION` clause in subqueries wasn't handled correctly in queries with parallel replicas and lead to LOGICAL_ERROR `Duplicate announcement received for replica`. [#69146](https://github.com/ClickHouse/ClickHouse/pull/69146) ([Igor Nikonov](https://github.com/devcrafter)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Backported in [#69189](https://github.com/ClickHouse/ClickHouse/issues/69189): Don't create Object type if use_json_alias_for_old_object_type=1 but allow_experimental_object_type=0. [#69150](https://github.com/ClickHouse/ClickHouse/pull/69150) ([Kruglov Pavel](https://github.com/Avogar)).
* Backported in [#69229](https://github.com/ClickHouse/ClickHouse/issues/69229): Disable memory test with sanitizer. [#69193](https://github.com/ClickHouse/ClickHouse/pull/69193) ([alesapin](https://github.com/alesapin)).
* Backported in [#69219](https://github.com/ClickHouse/ClickHouse/issues/69219): Disable perf-like test with sanitizers. [#69194](https://github.com/ClickHouse/ClickHouse/pull/69194) ([alesapin](https://github.com/alesapin)).

9
docs/en/engines/database-engines/index.md
View File

@ -13,16 +13,17 @@ Here is a complete list of available database engines. Follow the links for more
- [Atomic](../../engines/database-engines/atomic.md)
- [MySQL](../../engines/database-engines/mysql.md)
- [Lazy](../../engines/database-engines/lazy.md)
- [MaterializedPostgreSQL](../../engines/database-engines/materialized-postgresql.md)
- [MaterializedMySQL](../../engines/database-engines/materialized-mysql.md)
- [Lazy](../../engines/database-engines/lazy.md)
- [MySQL](../../engines/database-engines/mysql.md)
- [PostgreSQL](../../engines/database-engines/postgresql.md)
- [MaterializedPostgreSQL](../../engines/database-engines/materialized-postgresql.md)
- [Replicated](../../engines/database-engines/replicated.md)
- [SQLite](../../engines/database-engines/sqlite.md)

6
docs/en/engines/database-engines/materialized-postgresql.md
View File

@ -155,6 +155,12 @@ Replication of [**TOAST**](https://www.postgresql.org/docs/9.5/storage-toast.htm
Sets a comma-separated list of PostgreSQL database tables, which will be replicated via [MaterializedPostgreSQL](../../engines/database-engines/materialized-postgresql.md) database engine.
Each table can have subset of replicated columns in brackets. If subset of columns is omitted, then all columns for table will be replicated.
``` sql
materialized_postgresql_tables_list = 'table1(co1, col2),table2,table3(co3, col5, col7)
```
Default value: empty list — means whole PostgreSQL database will be replicated.
### `materialized_postgresql_schema` {#materialized-postgresql-schema}

72
docs/en/engines/table-engines/integrations/azure-queue.md Normal file
View File

@ -0,0 +1,72 @@
---
slug: /en/engines/table-engines/integrations/azure-queue
sidebar_position: 181
sidebar_label: AzureQueue
---
# AzureQueue Table Engine
This engine provides an integration with [Azure Blob Storage](https://azure.microsoft.com/en-us/products/storage/blobs) ecosystem, allowing streaming data import.
## Create Table {#creating-a-table}
``` sql
CREATE TABLE test (name String, value UInt32)
ENGINE = AzureQueue(...)
[SETTINGS]
[mode = '',]
[after_processing = 'keep',]
[keeper_path = '',]
...
```
**Engine parameters**
`AzureQueue` parameters are the same as `AzureBlobStorage` table engine supports. See parameters section [here](../../../engines/table-engines/integrations/azureBlobStorage.md).
**Example**
```sql
CREATE TABLE azure_queue_engine_table (name String, value UInt32)
ENGINE=AzureQueue('DefaultEndpointsProtocol=http;AccountName=devstoreaccount1;AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;BlobEndpoint=http://azurite1:10000/devstoreaccount1/data/')
SETTINGS
mode = 'unordered'
```
## Settings {#settings}
The set of supported settings is the same as for `S3Queue` table engine, but without `s3queue_` prefix. See [full list of settings settings](../../../engines/table-engines/integrations/s3queue.md#settings).
## Description {#description}
`SELECT` is not particularly useful for streaming import (except for debugging), because each file can be imported only once. It is more practical to create real-time threads using [materialized views](../../../sql-reference/statements/create/view.md). To do this:
1. Use the engine to create a table for consuming from specified path in S3 and consider it a data stream.
2. Create a table with the desired structure.
3. Create a materialized view that converts data from the engine and puts it into a previously created table.
When the `MATERIALIZED VIEW` joins the engine, it starts collecting data in the background.
Example:
``` sql
CREATE TABLE azure_queue_engine_table (name String, value UInt32)
ENGINE=AzureQueue('<endpoint>', 'CSV', 'gzip')
SETTINGS
mode = 'unordered';
CREATE TABLE stats (name String, value UInt32)
ENGINE = MergeTree() ORDER BY name;
CREATE MATERIALIZED VIEW consumer TO stats
AS SELECT name, value FROM azure_queue_engine_table;
SELECT * FROM stats ORDER BY name;
```
## Virtual columns {#virtual-columns}
- `_path` — Path to the file.
- `_file` — Name of the file.
For more information about virtual columns see [here](../../../engines/table-engines/index.md#table_engines-virtual_columns).

4
docs/en/engines/table-engines/integrations/nats.md
View File

@ -112,7 +112,7 @@ Example:
```
The NATS server configuration can be added using the ClickHouse config file.
More specifically you can add Redis password for NATS engine:
More specifically you can add Redis password for NATS engine:
``` xml
<nats>
@ -167,7 +167,7 @@ If you want to change the target table by using `ALTER`, we recommend disabling
- `_subject` - NATS message subject. Data type: `String`.
Additional virtual columns when `kafka_handle_error_mode='stream'`:
Additional virtual columns when `nats_handle_error_mode='stream'`:
- `_raw_message` - Raw message that couldn't be parsed successfully. Data type: `Nullable(String)`.
- `_error` - Exception message happened during failed parsing. Data type: `Nullable(String)`.

2
docs/en/engines/table-engines/integrations/s3.md
View File

@ -35,7 +35,7 @@ CREATE TABLE s3_engine_table (name String, value UInt32)
[SETTINGS ...]
```
### Engine parameters
### Engine parameters {#parameters}
- `path` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings. For more information see [below](#wildcards-in-path).
- `NOSIGN` - If this keyword is provided in place of credentials, all the requests will not be signed.

31
docs/en/engines/table-engines/integrations/s3queue.md
View File

@ -5,6 +5,7 @@ sidebar_label: S3Queue
---
# S3Queue Table Engine
This engine provides integration with [Amazon S3](https://aws.amazon.com/s3/) ecosystem and allows streaming import. This engine is similar to the [Kafka](../../../engines/table-engines/integrations/kafka.md), [RabbitMQ](../../../engines/table-engines/integrations/rabbitmq.md) engines, but provides S3-specific features.
## Create Table {#creating-a-table}
@ -16,27 +17,25 @@ CREATE TABLE s3_queue_engine_table (name String, value UInt32)
[mode = '',]
[after_processing = 'keep',]
[keeper_path = '',]
[s3queue_loading_retries = 0,]
[s3queue_processing_threads_num = 1,]
[s3queue_enable_logging_to_s3queue_log = 0,]
[s3queue_polling_min_timeout_ms = 1000,]
[s3queue_polling_max_timeout_ms = 10000,]
[s3queue_polling_backoff_ms = 0,]
[s3queue_tracked_file_ttl_sec = 0,]
[s3queue_tracked_files_limit = 1000,]
[s3queue_cleanup_interval_min_ms = 10000,]
[s3queue_cleanup_interval_max_ms = 30000,]
[loading_retries = 0,]
[processing_threads_num = 1,]
[enable_logging_to_s3queue_log = 0,]
[polling_min_timeout_ms = 1000,]
[polling_max_timeout_ms = 10000,]
[polling_backoff_ms = 0,]
[tracked_file_ttl_sec = 0,]
[tracked_files_limit = 1000,]
[cleanup_interval_min_ms = 10000,]
[cleanup_interval_max_ms = 30000,]
```
Starting with `24.7` settings without `s3queue_` prefix are also supported.
:::warning
Before `24.7`, it is required to use `s3queue_` prefix for all settings apart from `mode`, `after_processing` and `keeper_path`.
:::
**Engine parameters**
- `path` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings. For more information see [below](#wildcards-in-path).
- `NOSIGN` - If this keyword is provided in place of credentials, all the requests will not be signed.
- `format` — The [format](../../../interfaces/formats.md#formats) of the file.
- `aws_access_key_id`, `aws_secret_access_key` - Long-term credentials for the [AWS](https://aws.amazon.com/) account user. You can use these to authenticate your requests. Parameter is optional. If credentials are not specified, they are used from the configuration file. For more information see [Using S3 for Data Storage](../mergetree-family/mergetree.md#table_engine-mergetree-s3).
- `compression` — Compression type. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. Parameter is optional. By default, it will autodetect compression by file extension.
`S3Queue` parameters are the same as `S3` table engine supports. See parameters section [here](../../../engines/table-engines/integrations/s3.md#parameters).
**Example**

21
docs/en/engines/table-engines/mergetree-family/annindexes.md
View File

@ -107,19 +107,24 @@ The vector similarity index currently does not work with per-table, non-default
[here](https://github.com/ClickHouse/ClickHouse/pull/51325#issuecomment-1605920475)). If necessary, the value must be changed in config.xml.
:::
Vector index creation is known to be slow. To speed the process up, index creation can be parallelized. The maximum number of threads can be
configured using server configuration
setting [max_build_vector_similarity_index_thread_pool_size](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters_max_build_vector_similarity_index_thread_pool_size).
ANN indexes are built during column insertion and merge. As a result, `INSERT` and `OPTIMIZE` statements will be slower than for ordinary
tables. ANNIndexes are ideally used only with immutable or rarely changed data, respectively when are far more read requests than write
requests.
ANN indexes support these queries:
ANN indexes support this type of query:
``` sql
SELECT *
FROM table
[WHERE ...]
ORDER BY Distance(vectors, Point)
LIMIT N
```
``` sql
WITH [...] AS reference_vector
SELECT *
FROM table
WHERE ... -- WHERE clause is optional
ORDER BY Distance(vectors, reference_vector)
LIMIT N
```
:::tip
To avoid writing out large vectors, you can use [query

39
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -989,19 +989,52 @@ ALTER TABLE tab DROP STATISTICS a;
These lightweight statistics aggregate information about distribution of values in columns. Statistics are stored in every part and updated when every insert comes.
They can be used for prewhere optimization only if we enable `set allow_statistics_optimize = 1`.
#### Available Types of Column Statistics {#available-types-of-column-statistics}
### Available Types of Column Statistics {#available-types-of-column-statistics}
- `MinMax`
The minimum and maximum column value which allows to estimate the selectivity of range filters on numeric columns.
Syntax: `minmax`
- `TDigest`
[TDigest](https://github.com/tdunning/t-digest) sketches which allow to compute approximate percentiles (e.g. the 90th percentile) for numeric columns.
Syntax: `tdigest`
- `Uniq`
[HyperLogLog](https://en.wikipedia.org/wiki/HyperLogLog) sketches which provide an estimation how many distinct values a column contains.
- `count_min`
Syntax: `uniq`
- `CountMin`
[CountMin](https://en.wikipedia.org/wiki/Count%E2%80%93min_sketch) sketches which provide an approximate count of the frequency of each value in a column.
Syntax `countmin`
### Supported Data Types {#supported-data-types}
| | (U)Int*, Float*, Decimal(*), Date*, Boolean, Enum* | String or FixedString |
|-----------|----------------------------------------------------|-----------------------|
| CountMin | ✔ | ✔ |
| MinMax | ✔ | ✗ |
| TDigest | ✔ | ✗ |
| Uniq | ✔ | ✔ |
### Supported Operations {#supported-operations}
| | Equality filters (==) | Range filters (>, >=, <, <=) |
|-----------|-----------------------|------------------------------|
| CountMin | ✔ | ✗ |
| MinMax | ✗ | ✔ |
| TDigest | ✗ | ✔ |
| Uniq | ✔ | ✗ |
[Count-min](https://en.wikipedia.org/wiki/Count%E2%80%93min_sketch) sketches which provide an approximate count of the frequency of each value in a column.
## Column-level Settings {#column-level-settings}

2
docs/en/engines/table-engines/special/filelog.md
View File

@ -97,7 +97,7 @@ If you want to change the target table by using `ALTER`, we recommend disabling
- `_filename` - Name of the log file. Data type: `LowCardinality(String)`.
- `_offset` - Offset in the log file. Data type: `UInt64`.
Additional virtual columns when `kafka_handle_error_mode='stream'`:
Additional virtual columns when `handle_error_mode='stream'`:
- `_raw_record` - Raw record that couldn't be parsed successfully. Data type: `Nullable(String)`.
- `_error` - Exception message happened during failed parsing. Data type: `Nullable(String)`.

90
docs/en/interfaces/formats.md
View File

@ -39,6 +39,7 @@ The supported formats are:
| [JSONCompact](#jsoncompact) | ✔ | ✔ |
| [JSONCompactStrings](#jsoncompactstrings) | ✗ | ✔ |
| [JSONCompactColumns](#jsoncompactcolumns) | ✔ | ✔ |
| [JSONCompactWithProgress](#jsoncompactwithprogress) | ✗ | ✔ |
| [JSONEachRow](#jsoneachrow) | ✔ | ✔ |
| [PrettyJSONEachRow](#prettyjsoneachrow) | ✗ | ✔ |
| [JSONEachRowWithProgress](#jsoneachrowwithprogress) | ✗ | ✔ |
@ -825,17 +826,17 @@ Result:
## JSONAsObject {#jsonasobject}
In this format, a single JSON object is interpreted as a single [Object('json')](/docs/en/sql-reference/data-types/json.md) value. If the input has several JSON objects (comma separated), they are interpreted as separate rows. If the input data is enclosed in square brackets, it is interpreted as an array of JSONs.
In this format, a single JSON object is interpreted as a single [JSON](/docs/en/sql-reference/data-types/newjson.md) value. If the input has several JSON objects (comma separated), they are interpreted as separate rows. If the input data is enclosed in square brackets, it is interpreted as an array of JSONs.
This format can only be parsed for a table with a single field of type [Object('json')](/docs/en/sql-reference/data-types/json.md). The remaining columns must be set to [DEFAULT](/docs/en/sql-reference/statements/create/table.md/#default) or [MATERIALIZED](/docs/en/sql-reference/statements/create/table.md/#materialized).
This format can only be parsed for a table with a single field of type [JSON](/docs/en/sql-reference/data-types/newjson.md). The remaining columns must be set to [DEFAULT](/docs/en/sql-reference/statements/create/table.md/#default) or [MATERIALIZED](/docs/en/sql-reference/statements/create/table.md/#materialized).
**Examples**
Query:
``` sql
SET allow_experimental_object_type = 1;
CREATE TABLE json_as_object (json Object('json')) ENGINE = Memory;
SET allow_experimental_json_type = 1;
CREATE TABLE json_as_object (json JSON) ENGINE = Memory;
INSERT INTO json_as_object (json) FORMAT JSONAsObject {"foo":{"bar":{"x":"y"},"baz":1}},{},{"any json stucture":1}
SELECT * FROM json_as_object FORMAT JSONEachRow;
```
@ -843,9 +844,9 @@ SELECT * FROM json_as_object FORMAT JSONEachRow;
Result:
``` response
{"json":{"any json stucture":0,"foo":{"bar":{"x":"y"},"baz":1}}}
{"json":{"any json stucture":0,"foo":{"bar":{"x":""},"baz":0}}}
{"json":{"any json stucture":1,"foo":{"bar":{"x":""},"baz":0}}}
{"json":{"foo":{"bar":{"x":"y"},"baz":"1"}}}
{"json":{}}
{"json":{"any json stucture":"1"}}
```
**An array of JSON objects**
@ -853,35 +854,34 @@ Result:
Query:
``` sql
SET allow_experimental_object_type = 1;
CREATE TABLE json_square_brackets (field Object('json')) ENGINE = Memory;
SET allow_experimental_json_type = 1;
CREATE TABLE json_square_brackets (field JSON) ENGINE = Memory;
INSERT INTO json_square_brackets FORMAT JSONAsObject [{"id": 1, "name": "name1"}, {"id": 2, "name": "name2"}];
SELECT * FROM json_square_brackets FORMAT JSONEachRow;
```
Result:
```response
{"field":{"id":1,"name":"name1"}}
{"field":{"id":2,"name":"name2"}}
{"field":{"id":"1","name":"name1"}}
{"field":{"id":"2","name":"name2"}}
```
**Columns with default values**
```sql
SET allow_experimental_object_type = 1;
CREATE TABLE json_as_object (json Object('json'), time DateTime MATERIALIZED now()) ENGINE = Memory;
SET allow_experimental_json_type = 1;
CREATE TABLE json_as_object (json JSON, time DateTime MATERIALIZED now()) ENGINE = Memory;
INSERT INTO json_as_object (json) FORMAT JSONAsObject {"foo":{"bar":{"x":"y"},"baz":1}};
INSERT INTO json_as_object (json) FORMAT JSONAsObject {};
INSERT INTO json_as_object (json) FORMAT JSONAsObject {"any json stucture":1}
SELECT * FROM json_as_object FORMAT JSONEachRow
SELECT time, json FROM json_as_object FORMAT JSONEachRow
```
```resonse
{"json":{"any json stucture":0,"foo":{"bar":{"x":"y"},"baz":1}},"time":"2024-07-25 17:02:45"}
{"json":{"any json stucture":0,"foo":{"bar":{"x":""},"baz":0}},"time":"2024-07-25 17:02:47"}
{"json":{"any json stucture":1,"foo":{"bar":{"x":""},"baz":0}},"time":"2024-07-25 17:02:50"}
{"time":"2024-09-16 12:18:10","json":{}}
{"time":"2024-09-16 12:18:13","json":{"any json stucture":"1"}}
{"time":"2024-09-16 12:18:08","json":{"foo":{"bar":{"x":"y"},"baz":"1"}}}
```
## JSONCompact {#jsoncompact}
@ -988,6 +988,59 @@ Example:
Columns that are not present in the block will be filled with default values (you can use [input_format_defaults_for_omitted_fields](/docs/en/operations/settings/settings-formats.md/#input_format_defaults_for_omitted_fields) setting here)
## JSONCompactWithProgress (#jsoncompactwithprogress)
In this format, ClickHouse outputs each row as a separated, newline-delimited JSON Object.
Each row is either a metadata object, data object, progress information or statistics object:
1. **Metadata Object (`meta`)**
- Describes the structure of the data rows.
- Fields: `name` (column name), `type` (data type, e.g., `UInt32`, `String`, etc.).
- Example: `{"meta": [{"name":"id", "type":"UInt32"}, {"name":"name", "type":"String"}]}`
- Appears before any data objects.
2. **Data Object (`data`)**
- Represents a row of query results.
- Fields: An array with values corresponding to the columns defined in the metadata.
- Example: `{"data":["1", "John Doe"]}`
- Appears after the metadata object, one per row.
3. **Progress Information Object (`progress`)**
- Provides real-time progress feedback during query execution.
- Fields: `read_rows`, `read_bytes`, `written_rows`, `written_bytes`, `total_rows_to_read`, `result_rows`, `result_bytes`, `elapsed_ns`.
- Example: `{"progress":{"read_rows":"8","read_bytes":"168"}}`
- May appear intermittently.
4. **Statistics Object (`statistics`)**
- Summarizes query execution statistics.
- Fields: `rows`, `rows_before_limit_at_least`, `elapsed`, `rows_read`, `bytes_read`.
- Example: `{"statistics": {"rows":2, "elapsed":0.001995, "rows_read":8}}`
- Appears at the end.
5. **Exception Object (`exception`)**
- Represents an error that occurred during query execution.
- Fields: A single text field containing the error message.
- Example: `{"exception": "Code: 395. DB::Exception: Value passed to 'throwIf' function is non-zero..."}`
- Appears when an error is encountered.
6. **Totals Object (`totals`)**
- Provides the totals for each numeric column in the result set.
- Fields: An array with total values corresponding to the columns defined in the metadata.
- Example: `{"totals": ["", "3"]}`
- Appears at the end of the data rows, if applicable.
Example:
```json
{"meta": [{"name":"id", "type":"UInt32"}, {"name":"name", "type":"String"}]}
{"progress":{"read_rows":"8","read_bytes":"168","written_rows":"0","written_bytes":"0","total_rows_to_read":"2","result_rows":"0","result_bytes":"0","elapsed_ns":"0"}}
{"data":["1", "John Doe"]}
{"data":["2", "Joe Doe"]}
{"statistics": {"rows":2, "rows_before_limit_at_least":8, "elapsed":0.001995, "rows_read":8, "bytes_read":168}}
```
## JSONEachRow {#jsoneachrow}
In this format, ClickHouse outputs each row as a separated, newline-delimited JSON Object.
@ -1342,6 +1395,7 @@ SELECT * FROM json_each_row_nested
- [input_format_json_ignore_unknown_keys_in_named_tuple](/docs/en/operations/settings/settings-formats.md/#input_format_json_ignore_unknown_keys_in_named_tuple) - ignore unknown keys in json object for named tuples. Default value - `false`.
- [input_format_json_compact_allow_variable_number_of_columns](/docs/en/operations/settings/settings-formats.md/#input_format_json_compact_allow_variable_number_of_columns) - allow variable number of columns in JSONCompact/JSONCompactEachRow format, ignore extra columns and use default values on missing columns. Default value - `false`.
- [input_format_json_throw_on_bad_escape_sequence](/docs/en/operations/settings/settings-formats.md/#input_format_json_throw_on_bad_escape_sequence) - throw an exception if JSON string contains bad escape sequence. If disabled, bad escape sequences will remain as is in the data. Default value - `true`.
- [input_format_json_empty_as_default](/docs/en/operations/settings/settings-formats.md/#input_format_json_empty_as_default) - treat empty fields in JSON input as default values. Default value - `false`. For complex default expressions [input_format_defaults_for_omitted_fields](/docs/en/operations/settings/settings-formats.md/#input_format_defaults_for_omitted_fields) must be enabled too.
- [output_format_json_quote_64bit_integers](/docs/en/operations/settings/settings-formats.md/#output_format_json_quote_64bit_integers) - controls quoting of 64-bit integers in JSON output format. Default value - `true`.
- [output_format_json_quote_64bit_floats](/docs/en/operations/settings/settings-formats.md/#output_format_json_quote_64bit_floats) - controls quoting of 64-bit floats in JSON output format. Default value - `false`.
- [output_format_json_quote_denormals](/docs/en/operations/settings/settings-formats.md/#output_format_json_quote_denormals) - enables '+nan', '-nan', '+inf', '-inf' outputs in JSON output format. Default value - `false`.

10
docs/en/interfaces/third-party/gui.md vendored
View File

@ -233,6 +233,16 @@ Features:
- Useful tools: Zookeeper data exploration, query EXPLAIN, kill queries, etc.
- Visualization metric charts: queries and resource usage, number of merges/mutation, merge performance, query performance, etc.
### CKibana {#ckibana}
[CKibana](https://github.com/TongchengOpenSource/ckibana) is a lightweight service that allows you to effortlessly search, explore, and visualize ClickHouse data using the native Kibana UI.
Features:
- Translates chart requests from the native Kibana UI into ClickHouse query syntax.
- Supports advanced features such as sampling and caching to enhance query performance.
- Minimizes the learning cost for users after migrating from ElasticSearch to ClickHouse.
## Commercial {#commercial}
### DataGrip {#datagrip}

8
docs/en/operations/external-authenticators/ssl-x509.md
View File

@ -6,7 +6,7 @@ import SelfManaged from '@site/docs/en/_snippets/_self_managed_only_no_roadmap.m
<SelfManaged />
[SSL 'strict' option](../server-configuration-parameters/settings.md#server_configuration_parameters-openssl) enables mandatory certificate validation for the incoming connections. In this case, only connections with trusted certificates can be established. Connections with untrusted certificates will be rejected. Thus, certificate validation allows to uniquely authenticate an incoming connection. `Common Name` or `subjectAltName extension` field of the certificate is used to identify the connected user. This allows to associate multiple certificates with the same user. Additionally, reissuing and revoking of the certificates does not affect the ClickHouse configuration.
[SSL 'strict' option](../server-configuration-parameters/settings.md#server_configuration_parameters-openssl) enables mandatory certificate validation for the incoming connections. In this case, only connections with trusted certificates can be established. Connections with untrusted certificates will be rejected. Thus, certificate validation allows to uniquely authenticate an incoming connection. `Common Name` or `subjectAltName extension` field of the certificate is used to identify the connected user. `subjectAltName extension` supports the usage of one wildcard '*' in the server configuration. This allows to associate multiple certificates with the same user. Additionally, reissuing and revoking of the certificates does not affect the ClickHouse configuration.
To enable SSL certificate authentication, a list of `Common Name`'s or `Subject Alt Name`'s for each ClickHouse user must be specified in the settings file `users.xml `:
@ -30,6 +30,12 @@ To enable SSL certificate authentication, a list of `Common Name`'s or `Subject
</ssl_certificates>
<!-- Other settings -->
</user_name_2>
<user_name_3>
<ssl_certificates>
<!-- Wildcard support -->
<subject_alt_name>URI:spiffe://foo.com/*/bar</subject_alt_name>
</ssl_certificates>
</user_name_3>
</users>
</clickhouse>
```

91
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -491,6 +491,14 @@ Type: Double
Default: 0.9
## max_build_vector_similarity_index_thread_pool_size {#server_configuration_parameters_max_build_vector_similarity_index_thread_pool_size}
The maximum number of threads to use for building vector indexes. 0 means all cores.
Type: UInt64
Default: 16
## cgroups_memory_usage_observer_wait_time
Interval in seconds during which the server's maximum allowed memory consumption is adjusted by the corresponding threshold in cgroups. (see
@ -1463,26 +1471,29 @@ Examples:
## logger {#logger}
Logging settings.
The location and format of log messages.
Keys:
- `level` – Logging level. Acceptable values: `trace`, `debug`, `information`, `warning`, `error`.
- `log` – The log file. Contains all the entries according to `level`.
- `errorlog` – Error log file.
- `size` – Size of the file. Applies to `log` and `errorlog`. Once the file reaches `size`, ClickHouse archives and renames it, and creates a new log file in its place.
- `count` – The number of archived log files that ClickHouse stores.
- `console` – Send `log` and `errorlog` to the console instead of file. To enable, set to `1` or `true`.
- `console_log_level` – Logging level for console. Default to `level`.
- `use_syslog` - Log to syslog as well.
- `syslog_level` - Logging level for logging to syslog.
- `stream_compress` – Compress `log` and `errorlog` with `lz4` stream compression. To enable, set to `1` or `true`.
- `formatting` – Specify log format to be printed in console log (currently only `json` supported).
- `level` – Log level. Acceptable values: `none` (turn logging off), `fatal`, `critical`, `error`, `warning`, `notice`, `information`,
`debug`, `trace`, `test`
- `log` – The path to the log file.
- `errorlog` – The path to the error log file.
- `size` – Rotation policy: Maximum size of the log files in bytes. Once the log file size exceeds this threshold, it is renamed and archived, and a new log file is created.
- `count` – Rotation policy: How many historical log files Clickhouse are kept at most.
- `stream_compress` – Compress log messages using LZ4. Set to `1` or `true` to enable.
- `console` – Do not write log messages to log files, instead print them in the console. Set to `1` or `true` to enable. Default is
`1` if Clickhouse does not run in daemon mode, `0` otherwise.
- `console_log_level` – Log level for console output. Defaults to `level`.
- `formatting` – Log format for console output. Currently, only `json` is supported).
- `use_syslog` - Also forward log output to syslog.
- `syslog_level` - Log level for logging to syslog.
Both log and error log file names (only file names, not directories) support date and time format specifiers.
**Log format specifiers**
**Format specifiers**
Using the following format specifiers, you can define a pattern for the resulting file name. “Example” column shows possible results for `2023-07-06 18:32:07`.
File names in `log` and `errorLog` paths support below format specifiers for the resulting file name (the directory part does not support them).
Column “Example” shows the output at `2023-07-06 18:32:07`.
| Specifier | Description | Example |
|-------------|---------------------------------------------------------------------------------------------------------------------|--------------------------|
@ -1537,18 +1548,37 @@ Using the following format specifiers, you can define a pattern for the resultin
</logger>
```
Writing to the console can be configured. Config example:
To print log messages only in the console:
``` xml
<logger>
<level>information</level>
<console>1</console>
<console>true</console>
</logger>
```
**Per-level Overrides**
The log level of individual log names can be overridden. For example, to mute all messages of loggers "Backup" and "RBAC".
```xml
<logger>
<levels>
<logger>
<name>Backup</name>
<level>none</level>
</logger>
<logger>
<name>RBAC</name>
<level>none</level>
</logger>
</levels>
</logger>
```
### syslog
Writing to the syslog is also supported. Config example:
To write log messages additionally to syslog:
``` xml
<logger>
@ -1562,14 +1592,12 @@ Writing to the syslog is also supported. Config example:
</logger>
```
Keys for syslog:
Keys for `<syslog>`:
- use_syslog — Required setting if you want to write to the syslog.
- address — The host\[:port\] of syslogd. If omitted, the local daemon is used.
- hostname — Optional. The name of the host that logs are sent from.
- facility — [The syslog facility keyword](https://en.wikipedia.org/wiki/Syslog#Facility) in uppercase letters with the “LOG_” prefix: (`LOG_USER`, `LOG_DAEMON`, `LOG_LOCAL3`, and so on).
Default value: `LOG_USER` if `address` is specified, `LOG_DAEMON` otherwise.
- format – Message format. Possible values: `bsd` and `syslog.`
- `address` — The address of syslog in format `host\[:port\]`. If omitted, the local daemon is used.
- `hostname` — The name of the host from which logs are send. Optional.
- `facility` — The syslog [facility keyword](https://en.wikipedia.org/wiki/Syslog#Facility). Must be specified uppercase with a “LOG_” prefix, e.g. `LOG_USER`, `LOG_DAEMON`, `LOG_LOCAL3`, etc. Default value: `LOG_USER` if `address` is specified, `LOG_DAEMON` otherwise.
- `format` – Log message format. Possible values: `bsd` and `syslog.`
### Log formats
@ -1588,6 +1616,7 @@ You can specify the log format that will be outputted in the console log. Curren
"source_line": "192"
}
```
To enable JSON logging support, use the following snippet:
```xml
@ -3121,3 +3150,15 @@ Default value: "default"
**See Also**
- [Workload Scheduling](/docs/en/operations/workload-scheduling.md)
## max_authentication_methods_per_user {#max_authentication_methods_per_user}
The maximum number of authentication methods a user can be created with or altered to.
Changing this setting does not affect existing users. Create/alter authentication-related queries will fail if they exceed the limit specified in this setting.
Non authentication create/alter queries will succeed.
Type: UInt64
Default value: 100
Zero means unlimited

11
docs/en/operations/settings/settings-formats.md
View File

@ -752,6 +752,17 @@ Possible values:
Default value: 0.
### input_format_json_empty_as_default {#input_format_json_empty_as_default}
When enabled, replace empty input fields in JSON with default values. For complex default expressions `input_format_defaults_for_omitted_fields` must be enabled too.
Possible values:
+ 0 — Disable.
+ 1 — Enable.
Default value: 0.
## TSV format settings {#tsv-format-settings}
### input_format_tsv_empty_as_default {#input_format_tsv_empty_as_default}

2
docs/en/operations/settings/settings.md
View File

@ -3226,7 +3226,7 @@ Default value: `0`.
## lightweight_deletes_sync {#lightweight_deletes_sync}
The same as 'mutation_sync', but controls only execution of lightweight deletes.
The same as [`mutations_sync`](#mutations_sync), but controls only execution of lightweight deletes.
Possible values:

2
docs/en/operations/storing-data.md
View File

@ -499,7 +499,7 @@ Required parameters:
- `type` — `encrypted`. Otherwise the encrypted disk is not created.
- `disk` — Type of disk for data storage.
- `key` — The key for encryption and decryption. Type: [Uint64](/docs/en/sql-reference/data-types/int-uint.md). You can use `key_hex` parameter to encode the key in hexadecimal form.
You can specify multiple keys using the `id` attribute (see example above).
You can specify multiple keys using the `id` attribute (see example below).
Optional parameters:

4
docs/en/operations/utilities/clickhouse-keeper-client.md
View File

@ -47,13 +47,15 @@ keeper foo bar
- `ls '[path]'` -- Lists the nodes for the given path (default: cwd)
- `cd '[path]'` -- Changes the working path (default `.`)
- `cp '<src>' '<dest>'` -- Copies 'src' node to 'dest' path
- `mv '<src>' '<dest>'` -- Moves 'src' node to the 'dest' path
- `exists '<path>'` -- Returns `1` if node exists, `0` otherwise
- `set '<path>' <value> [version]` -- Updates the node's value. Only updates if version matches (default: -1)
- `create '<path>' <value> [mode]` -- Creates new node with the set value
- `touch '<path>'` -- Creates new node with an empty string as value. Doesn't throw an exception if the node already exists
- `get '<path>'` -- Returns the node's value
- `rm '<path>' [version]` -- Removes the node only if version matches (default: -1)
- `rmr '<path>'` -- Recursively deletes path. Confirmation required
- `rmr '<path>' [limit]` -- Recursively deletes path if the subtree size is smaller than the limit. Confirmation required (default limit = 100)
- `flwc <command>` -- Executes four-letter-word command
- `help` -- Prints this message
- `get_direct_children_number '[path]'` -- Get numbers of direct children nodes under a specific path

44
docs/en/sql-reference/aggregate-functions/reference/distinctdynamictypes.md Normal file
View File

@ -0,0 +1,44 @@
---
slug: /en/sql-reference/aggregate-functions/reference/distinctdynamictypes
sidebar_position: 215
---
# distinctDynamicTypes
Calculates the list of distinct data types stored in [Dynamic](../../data-types/dynamic.md) column.
**Syntax**
```sql
distinctDynamicTypes(dynamic)
```
**Arguments**
- `dynamic` — [Dynamic](../../data-types/dynamic.md) column.
**Returned Value**
- The sorted list of data type names [Array(String)](../../data-types/array.md).
**Example**
Query:
```sql
DROP TABLE IF EXISTS test_dynamic;
CREATE TABLE test_dynamic(d Dynamic) ENGINE = Memory;
INSERT INTO test_dynamic VALUES (42), (NULL), ('Hello'), ([1, 2, 3]), ('2020-01-01'), (map(1, 2)), (43), ([4, 5]), (NULL), ('World'), (map(3, 4))
```
```sql
SELECT distinctDynamicTypes(d) FROM test_dynamic;
```
Result:
```reference
┌─distinctDynamicTypes(d)──────────────────────────────────────┐
│ ['Array(Int64)','Date','Int64','Map(UInt8, UInt8)','String'] │
└──────────────────────────────────────────────────────────────┘
```

125
docs/en/sql-reference/aggregate-functions/reference/distinctjsonpaths.md Normal file
View File

@ -0,0 +1,125 @@
---
slug: /en/sql-reference/aggregate-functions/reference/distinctjsonpaths
sidebar_position: 216
---
# distinctJSONPaths
Calculates the list of distinct paths stored in [JSON](../../data-types/newjson.md) column.
**Syntax**
```sql
distinctJSONPaths(json)
```
**Arguments**
- `json` — [JSON](../../data-types/newjson.md) column.
**Returned Value**
- The sorted list of paths [Array(String)](../../data-types/array.md).
**Example**
Query:
```sql
DROP TABLE IF EXISTS test_json;
CREATE TABLE test_json(json JSON) ENGINE = Memory;
INSERT INTO test_json VALUES ('{"a" : 42, "b" : "Hello"}'), ('{"b" : [1, 2, 3], "c" : {"d" : {"e" : "2020-01-01"}}}'), ('{"a" : 43, "c" : {"d" : {"f" : [{"g" : 42}]}}}')
```
```sql
SELECT distinctJSONPaths(json) FROM test_json;
```
Result:
```reference
┌─distinctJSONPaths(json)───┐
│ ['a','b','c.d.e','c.d.f'] │
└───────────────────────────┘
```
# distinctJSONPathsAndTypes
Calculates the list of distinct paths and their types stored in [JSON](../../data-types/newjson.md) column.
**Syntax**
```sql
distinctJSONPathsAndTypes(json)
```
**Arguments**
- `json` — [JSON](../../data-types/newjson.md) column.
**Returned Value**
- The sorted map of paths and types [Map(String, Array(String))](../../data-types/map.md).
**Example**
Query:
```sql
DROP TABLE IF EXISTS test_json;
CREATE TABLE test_json(json JSON) ENGINE = Memory;
INSERT INTO test_json VALUES ('{"a" : 42, "b" : "Hello"}'), ('{"b" : [1, 2, 3], "c" : {"d" : {"e" : "2020-01-01"}}}'), ('{"a" : 43, "c" : {"d" : {"f" : [{"g" : 42}]}}}')
```
```sql
SELECT distinctJSONPathsAndTypes(json) FROM test_json;
```
Result:
```reference
┌─distinctJSONPathsAndTypes(json)───────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ {'a':['Int64'],'b':['Array(Nullable(Int64))','String'],'c.d.e':['Date'],'c.d.f':['Array(JSON(max_dynamic_types=16, max_dynamic_paths=256))']} │
└───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```
**Note**
If JSON declaration contains paths with specified types, these paths will be always included in the result of `distinctJSONPaths/distinctJSONPathsAndTypes` functions even if input data didn't have values for these paths.
```sql
DROP TABLE IF EXISTS test_json;
CREATE TABLE test_json(json JSON(a UInt32)) ENGINE = Memory;
INSERT INTO test_json VALUES ('{"b" : "Hello"}'), ('{"b" : "World", "c" : [1, 2, 3]}');
```
```sql
SELECT json FROM test_json;
```
```text
┌─json──────────────────────────────────┐
│ {"a":0,"b":"Hello"} │
│ {"a":0,"b":"World","c":["1","2","3"]} │
└───────────────────────────────────────┘
```
```sql
SELECT distinctJSONPaths(json) FROM test_json;
```
```text
┌─distinctJSONPaths(json)─┐
│ ['a','b','c'] │
└─────────────────────────┘
```
```sql
SELECT distinctJSONPathsAndTypes(json) FROM test_json;
```
```text
┌─distinctJSONPathsAndTypes(json)────────────────────────────────┐
│ {'a':['UInt32'],'b':['String'],'c':['Array(Nullable(Int64))']} │
└────────────────────────────────────────────────────────────────┘
```

125
docs/en/sql-reference/data-types/newjson.md
View File

@ -505,7 +505,130 @@ As we can see, ClickHouse kept the most frequent paths `a`, `b` and `c` and move
## Introspection functions
There are several functions that can help to inspect the content of the JSON column: [JSONAllPaths](../functions/json-functions.md#jsonallpaths), [JSONAllPathsWithTypes](../functions/json-functions.md#jsonallpathswithtypes), [JSONDynamicPaths](../functions/json-functions.md#jsondynamicpaths), [JSONDynamicPathsWithTypes](../functions/json-functions.md#jsondynamicpathswithtypes), [JSONSharedDataPaths](../functions/json-functions.md#jsonshareddatapaths), [JSONSharedDataPathsWithTypes](../functions/json-functions.md#jsonshareddatapathswithtypes).
There are several functions that can help to inspect the content of the JSON column: [JSONAllPaths](../functions/json-functions.md#jsonallpaths), [JSONAllPathsWithTypes](../functions/json-functions.md#jsonallpathswithtypes), [JSONDynamicPaths](../functions/json-functions.md#jsondynamicpaths), [JSONDynamicPathsWithTypes](../functions/json-functions.md#jsondynamicpathswithtypes), [JSONSharedDataPaths](../functions/json-functions.md#jsonshareddatapaths), [JSONSharedDataPathsWithTypes](../functions/json-functions.md#jsonshareddatapathswithtypes), [distinctDynamicTypes](../aggregate-functions/reference/distinctdynamictypes.md), [distinctJSONPaths and distinctJSONPathsAndTypes](../aggregate-functions/reference/distinctjsonpaths.md)
**Examples**
Let's investigate the content of [GH Archive](https://www.gharchive.org/) dataset for `2020-01-01` date:
```sql
SELECT arrayJoin(distinctJSONPaths(json)) FROM s3('s3://clickhouse-public-datasets/gharchive/original/2020-01-01-*.json.gz', JSONAsObject)
```
```text
┌─arrayJoin(distinctJSONPaths(json))─────────────────────────┐
│ actor.avatar_url │
│ actor.display_login │
│ actor.gravatar_id │
│ actor.id │
│ actor.login │
│ actor.url │
│ created_at │
│ id │
│ org.avatar_url │
│ org.gravatar_id │
│ org.id │
│ org.login │
│ org.url │
│ payload.action │
│ payload.before │
│ payload.comment._links.html.href │
│ payload.comment._links.pull_request.href │
│ payload.comment._links.self.href │
│ payload.comment.author_association │
│ payload.comment.body │
│ payload.comment.commit_id │
│ payload.comment.created_at │
│ payload.comment.diff_hunk │
│ payload.comment.html_url │
│ payload.comment.id │
│ payload.comment.in_reply_to_id │
│ payload.comment.issue_url │
│ payload.comment.line │
│ payload.comment.node_id │
│ payload.comment.original_commit_id │
│ payload.comment.original_position │
│ payload.comment.path │
│ payload.comment.position │
│ payload.comment.pull_request_review_id │
...
│ payload.release.node_id │
│ payload.release.prerelease │
│ payload.release.published_at │
│ payload.release.tag_name │
│ payload.release.tarball_url │
│ payload.release.target_commitish │
│ payload.release.upload_url │
│ payload.release.url │
│ payload.release.zipball_url │
│ payload.size │
│ public │
│ repo.id │
│ repo.name │
│ repo.url │
│ type │
└─arrayJoin(distinctJSONPaths(json))─────────────────────────┘
```
```sql
SELECT arrayJoin(distinctJSONPathsAndTypes(json)) FROM s3('s3://clickhouse-public-datasets/gharchive/original/2020-01-01-*.json.gz', JSONAsObject) SETTINGS date_time_input_format='best_effort'
```
```text
┌─arrayJoin(distinctJSONPathsAndTypes(json))──────────────────┐
│ ('actor.avatar_url',['String']) │
│ ('actor.display_login',['String']) │
│ ('actor.gravatar_id',['String']) │
│ ('actor.id',['Int64']) │
│ ('actor.login',['String']) │
│ ('actor.url',['String']) │
│ ('created_at',['DateTime']) │
│ ('id',['String']) │
│ ('org.avatar_url',['String']) │
│ ('org.gravatar_id',['String']) │
│ ('org.id',['Int64']) │
│ ('org.login',['String']) │
│ ('org.url',['String']) │
│ ('payload.action',['String']) │
│ ('payload.before',['String']) │
│ ('payload.comment._links.html.href',['String']) │
│ ('payload.comment._links.pull_request.href',['String']) │
│ ('payload.comment._links.self.href',['String']) │
│ ('payload.comment.author_association',['String']) │
│ ('payload.comment.body',['String']) │
│ ('payload.comment.commit_id',['String']) │
│ ('payload.comment.created_at',['DateTime']) │
│ ('payload.comment.diff_hunk',['String']) │
│ ('payload.comment.html_url',['String']) │
│ ('payload.comment.id',['Int64']) │
│ ('payload.comment.in_reply_to_id',['Int64']) │
│ ('payload.comment.issue_url',['String']) │
│ ('payload.comment.line',['Int64']) │
│ ('payload.comment.node_id',['String']) │
│ ('payload.comment.original_commit_id',['String']) │
│ ('payload.comment.original_position',['Int64']) │
│ ('payload.comment.path',['String']) │
│ ('payload.comment.position',['Int64']) │
│ ('payload.comment.pull_request_review_id',['Int64']) │
...
│ ('payload.release.node_id',['String']) │
│ ('payload.release.prerelease',['Bool']) │
│ ('payload.release.published_at',['DateTime']) │
│ ('payload.release.tag_name',['String']) │
│ ('payload.release.tarball_url',['String']) │
│ ('payload.release.target_commitish',['String']) │
│ ('payload.release.upload_url',['String']) │
│ ('payload.release.url',['String']) │
│ ('payload.release.zipball_url',['String']) │
│ ('payload.size',['Int64']) │
│ ('public',['Bool']) │
│ ('repo.id',['Int64']) │
│ ('repo.name',['String']) │
│ ('repo.url',['String']) │
│ ('type',['String']) │
└─arrayJoin(distinctJSONPathsAndTypes(json))──────────────────┘
```
## Tips for better usage of the JSON type

38
docs/en/sql-reference/functions/array-functions.md
View File

@ -2035,6 +2035,7 @@ Query:
SELECT arrayZip(['a', 'b', 'c'], [5, 2, 1]);
```
Result:
``` text
@ -2043,6 +2044,43 @@ Result:
└──────────────────────────────────────┘
```
## arrayZipUnaligned
Combines multiple arrays into a single array, allowing for unaligned arrays. The resulting array contains the corresponding elements of the source arrays grouped into tuples in the listed order of arguments.
**Syntax**
``` sql
arrayZipUnaligned(arr1, arr2, ..., arrN)
```
**Arguments**
- `arrN` — [Array](../data-types/array.md).
The function can take any number of arrays of different types.
**Returned value**
- Array with elements from the source arrays grouped into [tuples](../data-types/tuple.md). Data types in the tuple are the same as types of the input arrays and in the same order as arrays are passed. [Array](../data-types/array.md). If the arrays have different sizes, the shorter arrays will be padded with `null` values.
**Example**
Query:
``` sql
SELECT arrayZipUnaligned(['a'], [1, 2, 3]);
```
Result:
``` text
┌─arrayZipUnaligned(['a'], [1, 2, 3])─┐
│ [('a',1),(NULL,2),(NULL,3)] │
└─────────────────────────────────────┘
```
## arrayAUC
Calculate AUC (Area Under the Curve, which is a concept in machine learning, see more details: <https://en.wikipedia.org/wiki/Receiver_operating_characteristic#Area_under_the_curve>).

335
docs/en/sql-reference/functions/date-time-functions.md
View File

@ -1617,45 +1617,348 @@ The calculation is performed relative to specific points in time:
If unit `WEEK` was specified, `toStartOfInterval` assumes that weeks start on Monday. Note that this behavior is different from that of function `toStartOfWeek` in which weeks start by default on Sunday.
**See Also**
**Syntax**
```sql
toStartOfInterval(value, INTERVAL x unit[, time_zone])
toStartOfInterval(value, INTERVAL x unit[, origin[, time_zone]])
```
The second overload emulates TimescaleDB's `time_bucket()` function, respectively PostgreSQL's `date_bin()` function, e.g.
``` SQL
SELECT toStartOfInterval(toDateTime('2023-01-01 14:45:00'), INTERVAL 1 MINUTE, toDateTime('2023-01-01 14:35:30'));
```
**See Also**
- [date_trunc](#date_trunc)
## toTime
Converts a date with time to a certain fixed date, while preserving the time.
**Syntax**
```sql
toTime(date[,timezone])
```
**Arguments**
- `date` — Date to convert to a time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
- `timezone` (optional) — Timezone for the returned value. [String](../data-types/string.md).
**Returned value**
- DateTime with date equated to `1970-01-02` while preserving the time. [DateTime](../data-types/datetime.md).
:::note
If the `date` input argument contained sub-second components,
they will be dropped in the returned `DateTime` value with second-accuracy.
:::
**Example**
Query:
```sql
SELECT toTime(toDateTime64('1970-12-10 01:20:30.3000',3)) AS result, toTypeName(result);
```
Result:
```response
┌──────────────result─┬─toTypeName(result)─┐
│ 1970-01-02 01:20:30 │ DateTime │
└─────────────────────┴────────────────────┘
```
## toRelativeYearNum
Converts a date, or date with time, to the number of the year, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of years elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeYearNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of years from a fixed reference point in the past. [UInt16](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeYearNum(toDate('2002-12-08')) AS y1,
toRelativeYearNum(toDate('2010-10-26')) AS y2
```
Result:
```response
┌───y1─┬───y2─┐
│ 2002 │ 2010 │
└──────┴──────┘
```
## toRelativeQuarterNum
Converts a date, or date with time, to the number of the quarter, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of quarters elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeQuarterNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of quarters from a fixed reference point in the past. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeQuarterNum(toDate('1993-11-25')) AS q1,
toRelativeQuarterNum(toDate('2005-01-05')) AS q2
```
Result:
```response
┌───q1─┬───q2─┐
│ 7975 │ 8020 │
└──────┴──────┘
```
## toRelativeMonthNum
Converts a date, or date with time, to the number of the month, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of months elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeMonthNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of months from a fixed reference point in the past. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeMonthNum(toDate('2001-04-25')) AS m1,
toRelativeMonthNum(toDate('2009-07-08')) AS m2
```
Result:
```response
┌────m1─┬────m2─┐
│ 24016 │ 24115 │
└───────┴───────┘
```
## toRelativeWeekNum
Converts a date, or date with time, to the number of the week, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of weeks elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeWeekNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of weeks from a fixed reference point in the past. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeWeekNum(toDate('2000-02-29')) AS w1,
toRelativeWeekNum(toDate('2001-01-12')) AS w2
```
Result:
```response
┌───w1─┬───w2─┐
│ 1574 │ 1619 │
└──────┴──────┘
```
## toRelativeDayNum
Converts a date, or date with time, to the number of the day, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of days elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeDayNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of days from a fixed reference point in the past. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeDayNum(toDate('1993-10-05')) AS d1,
toRelativeDayNum(toDate('2000-09-20')) AS d2
```
Result:
```response
┌───d1─┬────d2─┐
│ 8678 │ 11220 │
└──────┴───────┘
```
## toRelativeHourNum
Converts a date, or date with time, to the number of the hour, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of hours elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeHourNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of hours from a fixed reference point in the past. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeHourNum(toDateTime('1993-10-05 05:20:36')) AS h1,
toRelativeHourNum(toDateTime('2000-09-20 14:11:29')) AS h2
```
Result:
```response
┌─────h1─┬─────h2─┐
│ 208276 │ 269292 │
└────────┴────────┘
```
## toRelativeMinuteNum
Converts a date, or date with time, to the number of the minute, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of minutes elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeMinuteNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of minutes from a fixed reference point in the past. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeMinuteNum(toDateTime('1993-10-05 05:20:36')) AS m1,
toRelativeMinuteNum(toDateTime('2000-09-20 14:11:29')) AS m2
```
Result:
```response
┌───────m1─┬───────m2─┐
│ 12496580 │ 16157531 │
└──────────┴──────────┘
```
## toRelativeSecondNum
Converts a date, or date with time, to the number of the second, starting from a certain fixed point in the past.
Converts a date, or date with time, to the number of the seconds elapsed since a certain fixed point in the past.
**Syntax**
```sql
toRelativeSecondNum(date)
```
**Arguments**
- `date` — Date or date with time. [Date](../data-types/date.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Returned value**
- The number of seconds from a fixed reference point in the past. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
toRelativeSecondNum(toDateTime('1993-10-05 05:20:36')) AS s1,
toRelativeSecondNum(toDateTime('2000-09-20 14:11:29')) AS s2
```
Result:
```response
┌────────s1─┬────────s2─┐
│ 749794836 │ 969451889 │
└───────────┴───────────┘
```
## toISOYear
@ -3884,19 +4187,29 @@ Result:
└───────────────────────────────────────────────────────────────────────┘
```
## timeSlots(StartTime, Duration,\[, Size\])
## timeSlots
For a time interval starting at ‘StartTime’ and continuing for ‘Duration’ seconds, it returns an array of moments in time, consisting of points from this interval rounded down to the ‘Size’ in seconds. ‘Size’ is an optional parameter set to 1800 (30 minutes) by default.
This is necessary, for example, when searching for pageviews in the corresponding session.
Accepts DateTime and DateTime64 as ’StartTime’ argument. For DateTime, ’Duration’ and ’Size’ arguments must be `UInt32`. For ’DateTime64’ they must be `Decimal64`.
Returns an array of DateTime/DateTime64 (return type matches the type of ’StartTime’). For DateTime64, the return value's scale can differ from the scale of ’StartTime’ --- the highest scale among all given arguments is taken.
Example:
**Syntax**
```sql
timeSlots(StartTime, Duration,\[, Size\])
```
**Example**
```sql
SELECT timeSlots(toDateTime('2012-01-01 12:20:00'), toUInt32(600));
SELECT timeSlots(toDateTime('1980-12-12 21:01:02', 'UTC'), toUInt32(600), 299);
SELECT timeSlots(toDateTime64('1980-12-12 21:01:02.1234', 4, 'UTC'), toDecimal64(600.1, 1), toDecimal64(299, 0));
```
Result:
``` text
┌─timeSlots(toDateTime('2012-01-01 12:20:00'), toUInt32(600))─┐
│ ['2012-01-01 12:00:00','2012-01-01 12:30:00'] │

41
docs/en/sql-reference/functions/string-replace-functions.md
View File

@ -20,10 +20,10 @@ overlay(s, replace, offset[, length])
**Parameters**
- `input`: A string type [String](../data-types/string.md).
- `s`: A string type [String](../data-types/string.md).
- `replace`: A string type [String](../data-types/string.md).
- `offset`: An integer type [Int](../data-types/int-uint.md). If `offset` is negative, it is counted from the end of the `input` string.
- `length`: Optional. An integer type [Int](../data-types/int-uint.md). `length` specifies the length of the snippet within input to be replaced. If `length` is not specified, the number of bytes removed from `input` equals the length of `replace`; otherwise `length` bytes are removed.
- `offset`: An integer type [Int](../data-types/int-uint.md) (1-based). If `offset` is negative, it is counted from the end of the string `s`.
- `length`: Optional. An integer type [Int](../data-types/int-uint.md). `length` specifies the length of the snippet within the input string `s` to be replaced. If `length` is not specified, the number of bytes removed from `s` equals the length of `replace`; otherwise `length` bytes are removed.
**Returned value**
@ -32,22 +32,35 @@ overlay(s, replace, offset[, length])
**Example**
```sql
SELECT overlay('ClickHouse SQL', 'CORE', 12) AS res;
SELECT overlay('My father is from Mexico.', 'mother', 4) AS res;
```
Result:
```text
┌─res─────────────┐
│ ClickHouse CORE │
└─────────────────┘
┌─res──────────────────────┐
│ My mother is from Mexico.│
└──────────────────────────┘
```
```sql
SELECT overlay('My father is from Mexico.', 'dad', 4, 6) AS res;
```
Result:
```text
┌─res───────────────────┐
│ My dad is from Mexico.│
└───────────────────────┘
```
## overlayUTF8
Replace part of the string `input` with another string `replace`, starting at the 1-based index `offset`.
Assumes that the string contains valid UTF-8 encoded text. If this assumption is violated, no exception is thrown and the result is undefined.
Assumes that the string contains valid UTF-8 encoded text.
If this assumption is violated, no exception is thrown and the result is undefined.
**Syntax**
@ -59,8 +72,8 @@ overlayUTF8(s, replace, offset[, length])
- `s`: A string type [String](../data-types/string.md).
- `replace`: A string type [String](../data-types/string.md).
- `offset`: An integer type [Int](../data-types/int-uint.md). If `offset` is negative, it is counted from the end of the `input` string.
- `length`: Optional. An integer type [Int](../data-types/int-uint.md). `length` specifies the length of the snippet within input to be replaced. If `length` is not specified, the number of characters removed from `input` equals the length of `replace`; otherwise `length` characters are removed.
- `offset`: An integer type [Int](../data-types/int-uint.md) (1-based). If `offset` is negative, it is counted from the end of the input string `s`.
- `length`: Optional. An integer type [Int](../data-types/int-uint.md). `length` specifies the length of the snippet within the input string `s` to be replaced. If `length` is not specified, the number of characters removed from `s` equals the length of `replace`; otherwise `length` characters are removed.
**Returned value**
@ -69,15 +82,15 @@ overlayUTF8(s, replace, offset[, length])
**Example**
```sql
SELECT overlayUTF8('ClickHouse是一款OLAP数据库', '开源', 12, 2) AS res;
SELECT overlay('Mein Vater ist aus Österreich.', 'der Türkei', 20) AS res;
```
Result:
```text
┌─res────────────────────────┐
│ ClickHouse是开源OLAP数据库 │
└────────────────────────────┘
┌─res───────────────────────────┐
│ Mein Vater ist aus der Türkei.│
└───────────────────────────────┘
```
## replaceOne

131
docs/en/sql-reference/functions/type-conversion-functions.md
View File

@ -3906,7 +3906,7 @@ Result:
## toDateTime64
Converts the argument to the [DateTime64](../data-types/datetime64.md) data type.
Converts an input value to a value of type [DateTime64](../data-types/datetime64.md).
**Syntax**
@ -3918,7 +3918,7 @@ toDateTime64(expr, scale, [timezone])
- `expr` — The value. [String](../data-types/string.md), [UInt32](../data-types/int-uint.md), [Float](../data-types/float.md) or [DateTime](../data-types/datetime.md).
- `scale` - Tick size (precision): 10<sup>-precision</sup> seconds. Valid range: [ 0 : 9 ].
- `timezone` - Time zone of the specified datetime64 object.
- `timezone` (optional) - Time zone of the specified datetime64 object.
**Returned value**
@ -3977,10 +3977,137 @@ SELECT toDateTime64('2019-01-01 00:00:00', 3, 'Asia/Istanbul') AS value, toTypeN
## toDateTime64OrZero
Like [toDateTime64](#todatetime64), this function converts an input value to a value of type [DateTime64](../data-types/datetime64.md) but returns the min value of [DateTime64](../data-types/datetime64.md) if an invalid argument is received.
**Syntax**
``` sql
toDateTime64OrZero(expr, scale, [timezone])
```
**Arguments**
- `expr` — The value. [String](../data-types/string.md), [UInt32](../data-types/int-uint.md), [Float](../data-types/float.md) or [DateTime](../data-types/datetime.md).
- `scale` - Tick size (precision): 10<sup>-precision</sup> seconds. Valid range: [ 0 : 9 ].
- `timezone` (optional) - Time zone of the specified DateTime64 object.
**Returned value**
- A calendar date and time of day, with sub-second precision, otherwise the minimum value of `DateTime64`: `1970-01-01 01:00:00.000`. [DateTime64](../data-types/datetime64.md).
**Example**
Query:
```sql
SELECT toDateTime64OrZero('2008-10-12 00:00:00 00:30:30', 3) AS invalid_arg
```
Result:
```response
┌─────────────invalid_arg─┐
│ 1970-01-01 01:00:00.000 │
└─────────────────────────┘
```
**See also**
- [toDateTime64](#todatetime64).
- [toDateTime64OrNull](#todatetime64ornull).
- [toDateTime64OrDefault](#todatetime64ordefault).
## toDateTime64OrNull
Like [toDateTime64](#todatetime64), this function converts an input value to a value of type [DateTime64](../data-types/datetime64.md) but returns `NULL` if an invalid argument is received.
**Syntax**
``` sql
toDateTime64OrNull(expr, scale, [timezone])
```
**Arguments**
- `expr` — The value. [String](../data-types/string.md), [UInt32](../data-types/int-uint.md), [Float](../data-types/float.md) or [DateTime](../data-types/datetime.md).
- `scale` - Tick size (precision): 10<sup>-precision</sup> seconds. Valid range: [ 0 : 9 ].
- `timezone` (optional) - Time zone of the specified DateTime64 object.
**Returned value**
- A calendar date and time of day, with sub-second precision, otherwise `NULL`. [DateTime64](../data-types/datetime64.md)/[NULL](../data-types/nullable.md).
**Example**
Query:
```sql
SELECT
toDateTime64OrNull('1976-10-18 00:00:00.30', 3) AS valid_arg,
toDateTime64OrNull('1976-10-18 00:00:00 30', 3) AS invalid_arg
```
Result:
```response
┌───────────────valid_arg─┬─invalid_arg─┐
│ 1976-10-18 00:00:00.300 │ ᴺᵁᴸᴸ │
└─────────────────────────┴─────────────┘
```
**See also**
- [toDateTime64](#todatetime64).
- [toDateTime64OrZero](#todatetime64orzero).
- [toDateTime64OrDefault](#todatetime64ordefault).
## toDateTime64OrDefault
Like [toDateTime64](#todatetime64), this function converts an input value to a value of type [DateTime64](../data-types/datetime64.md),
but returns either the default value of [DateTime64](../data-types/datetime64.md)
or the provided default if an invalid argument is received.
**Syntax**
``` sql
toDateTime64OrNull(expr, scale, [timezone, default])
```
**Arguments**
- `expr` — The value. [String](../data-types/string.md), [UInt32](../data-types/int-uint.md), [Float](../data-types/float.md) or [DateTime](../data-types/datetime.md).
- `scale` - Tick size (precision): 10<sup>-precision</sup> seconds. Valid range: [ 0 : 9 ].
- `timezone` (optional) - Time zone of the specified DateTime64 object.
- `default` (optional) - Default value to return if an invalid argument is received. [DateTime64](../data-types/datetime64.md).
**Returned value**
- A calendar date and time of day, with sub-second precision, otherwise the minimum value of `DateTime64` or the `default` value if provided. [DateTime64](../data-types/datetime64.md).
**Example**
Query:
```sql
SELECT
toDateTime64OrDefault('1976-10-18 00:00:00 30', 3) AS invalid_arg,
toDateTime64OrDefault('1976-10-18 00:00:00 30', 3, 'UTC', toDateTime64('2001-01-01 00:00:00.00',3)) AS invalid_arg_with_default
```
Result:
```response
┌─────────────invalid_arg─┬─invalid_arg_with_default─┐
│ 1970-01-01 01:00:00.000 │ 2000-12-31 23:00:00.000 │
└─────────────────────────┴──────────────────────────┘
```
**See also**
- [toDateTime64](#todatetime64).
- [toDateTime64OrZero](#todatetime64orzero).
- [toDateTime64OrNull](#todatetime64ornull).
## toDecimal32
Converts an input value to a value of type [`Decimal(9, S)`](../data-types/decimal.md) with scale of `S`. Throws an exception in case of an error.

2
docs/en/sql-reference/operators/index.md
View File

@ -265,8 +265,6 @@ SELECT now() AS current_date_time, current_date_time + INTERVAL '4' day + INTERV
└─────────────────────┴────────────────────────────────────────────────────────────┘
```
You can work with dates without using `INTERVAL`, just by adding or subtracting seconds, minutes, and hours. For example, an interval of one day can be set by adding `60*60*24`.
:::note
The `INTERVAL` syntax or `addDays` function are always preferred. Simple addition or subtraction (syntax like `now() + ...`) doesn't consider time settings. For example, daylight saving time.
:::

2
docs/en/sql-reference/statements/alter/partition.md
View File

@ -351,7 +351,7 @@ ALTER TABLE mt DELETE IN PARTITION ID '2' WHERE p = 2;
You can specify the partition expression in `ALTER ... PARTITION` queries in different ways:
- As a value from the `partition` column of the `system.parts` table. For example, `ALTER TABLE visits DETACH PARTITION 201901`.
- Using the keyword `ALL`. It can be used only with DROP/DETACH/ATTACH. For example, `ALTER TABLE visits ATTACH PARTITION ALL`.
- Using the keyword `ALL`. It can be used only with DROP/DETACH/ATTACH/ATTACH FROM. For example, `ALTER TABLE visits ATTACH PARTITION ALL`.
- As a tuple of expressions or constants that matches (in types) the table partitioning keys tuple. In the case of a single element partitioning key, the expression should be wrapped in the `tuple (...)` function. For example, `ALTER TABLE visits DETACH PARTITION tuple(toYYYYMM(toDate('2019-01-25')))`.
- Using the partition ID. Partition ID is a string identifier of the partition (human-readable, if possible) that is used as the names of partitions in the file system and in ZooKeeper. The partition ID must be specified in the `PARTITION ID` clause, in a single quotes. For example, `ALTER TABLE visits DETACH PARTITION ID '201901'`.
- In the [ALTER ATTACH PART](#attach-partitionpart) and [DROP DETACHED PART](#drop-detached-partitionpart) query, to specify the name of a part, use string literal with a value from the `name` column of the [system.detached_parts](/docs/en/operations/system-tables/detached_parts.md/#system_tables-detached_parts) table. For example, `ALTER TABLE visits ATTACH PART '201901_1_1_0'`.

31
docs/en/sql-reference/statements/alter/user.md
View File

@ -12,9 +12,10 @@ Syntax:
``` sql
ALTER USER [IF EXISTS] name1 [ON CLUSTER cluster_name1] [RENAME TO new_name1]
[, name2 [ON CLUSTER cluster_name2] [RENAME TO new_name2] ...]
[NOT IDENTIFIED | IDENTIFIED {[WITH {no_password | plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name' | SAN 'TYPE:subject_alt_name'}]
[NOT IDENTIFIED | IDENTIFIED | ADD IDENTIFIED {[WITH {no_password | plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name' | SAN 'TYPE:subject_alt_name'}]
[[ADD | DROP] HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE]
[VALID UNTIL datetime]
[RESET AUTHENTICATION METHODS TO NEW]
[DEFAULT ROLE role [,...] | ALL | ALL EXCEPT role [,...] ]
[GRANTEES {user | role | ANY | NONE} [,...] [EXCEPT {user | role} [,...]]]
[SETTINGS variable [= value] [MIN [=] min_value] [MAX [=] max_value] [READONLY | WRITABLE] | PROFILE 'profile_name'] [,...]
@ -62,3 +63,31 @@ Allows the user with `john` account to grant his privileges to the user with `ja
``` sql
ALTER USER john GRANTEES jack;
```
Adds new authentication methods to the user while keeping the existing ones:
``` sql
ALTER USER user1 ADD IDENTIFIED WITH plaintext_password by '1', bcrypt_password by '2', plaintext_password by '3'
```
Notes:
1. Older versions of ClickHouse might not support the syntax of multiple authentication methods. Therefore, if the ClickHouse server contains such users and is downgraded to a version that does not support it, such users will become unusable and some user related operations will be broken. In order to downgrade gracefully, one must set all users to contain a single authentication method prior to downgrading. Alternatively, if the server was downgraded without the proper procedure, the faulty users should be dropped.
2. `no_password` can not co-exist with other authentication methods for security reasons.
Because of that, it is not possible to `ADD` a `no_password` authentication method. The below query will throw an error:
``` sql
ALTER USER user1 ADD IDENTIFIED WITH no_password
```
If you want to drop authentication methods for a user and rely on `no_password`, you must specify in the below replacing form.
Reset authentication methods and adds the ones specified in the query (effect of leading IDENTIFIED without the ADD keyword):
``` sql
ALTER USER user1 IDENTIFIED WITH plaintext_password by '1', bcrypt_password by '2', plaintext_password by '3'
```
Reset authentication methods and keep the most recent added one:
``` sql
ALTER USER user1 RESET AUTHENTICATION METHODS TO NEW
```

12
docs/en/sql-reference/statements/create/user.md
View File

@ -15,6 +15,7 @@ CREATE USER [IF NOT EXISTS | OR REPLACE] name1 [ON CLUSTER cluster_name1]
[NOT IDENTIFIED | IDENTIFIED {[WITH {no_password | plaintext_password | sha256_password | sha256_hash | double_sha1_password | double_sha1_hash}] BY {'password' | 'hash'}} | {WITH ldap SERVER 'server_name'} | {WITH kerberos [REALM 'realm']} | {WITH ssl_certificate CN 'common_name' | SAN 'TYPE:subject_alt_name'} | {WITH ssh_key BY KEY 'public_key' TYPE 'ssh-rsa|...'} | {WITH http SERVER 'server_name' [SCHEME 'Basic']}]
[HOST {LOCAL | NAME 'name' | REGEXP 'name_regexp' | IP 'address' | LIKE 'pattern'} [,...] | ANY | NONE]
[VALID UNTIL datetime]
[RESET AUTHENTICATION METHODS TO NEW]
[IN access_storage_type]
[DEFAULT ROLE role [,...]]
[DEFAULT DATABASE database | NONE]
@ -144,6 +145,17 @@ In ClickHouse Cloud, by default, passwords must meet the following complexity re
The available password types are: `plaintext_password`, `sha256_password`, `double_sha1_password`.
7. Multiple authentication methods can be specified:
```sql
CREATE USER user1 IDENTIFIED WITH plaintext_password by '1', bcrypt_password by '2', plaintext_password by '3''
```
Notes:
1. Older versions of ClickHouse might not support the syntax of multiple authentication methods. Therefore, if the ClickHouse server contains such users and is downgraded to a version that does not support it, such users will become unusable and some user related operations will be broken. In order to downgrade gracefully, one must set all users to contain a single authentication method prior to downgrading. Alternatively, if the server was downgraded without the proper procedure, the faulty users should be dropped.
2. `no_password` can not co-exist with other authentication methods for security reasons. Therefore, you can only specify
`no_password` if it is the only authentication method in the query.
## User Host
User host is a host from which a connection to ClickHouse server could be established. The host can be specified in the `HOST` query section in the following ways:

48
docs/en/sql-reference/statements/delete.md
View File

@ -13,7 +13,7 @@ The lightweight `DELETE` statement removes rows from the table `[db.]table` that
DELETE FROM [db.]table [ON CLUSTER cluster] [IN PARTITION partition_expr] WHERE expr;
```
It is called "lightweight `DELETE`" to contrast it to the [ALTER table DELETE](/en/sql-reference/statements/alter/delete) command, which is a heavyweight process.
It is called "lightweight `DELETE`" to contrast it to the [ALTER TABLE ... DELETE](/en/sql-reference/statements/alter/delete) command, which is a heavyweight process.
## Examples
@ -22,23 +22,27 @@ It is called "lightweight `DELETE`" to contrast it to the [ALTER table DELETE](/
DELETE FROM hits WHERE Title LIKE '%hello%';
```
## Lightweight `DELETE` does not delete data from storage immediately
## Lightweight `DELETE` does not delete data immediately
With lightweight `DELETE`, deleted rows are internally marked as deleted immediately and will be automatically filtered out of all subsequent queries. However, cleanup of data happens during the next merge. As a result, it is possible that for an unspecified period, data is not actually deleted from storage and is only marked as deleted.
Lightweight `DELETE` is implemented as a [mutation](/en/sql-reference/statements/alter#mutations) that marks rows as deleted but does not immediately physically delete them.
If you need to guarantee that your data is deleted from storage in a predictable time, consider using the [ALTER table DELETE](/en/sql-reference/statements/alter/delete) command. Note that deleting data using `ALTER table DELETE` may consume significant resources as it recreates all affected parts.
By default, `DELETE` statements wait until marking the rows as deleted is completed before returning. This can take a long time if the amount of data is large. Alternatively, you can run it asynchronously in the background using the setting [`lightweight_deletes_sync`](/en/operations/settings/settings#lightweight_deletes_sync). If disabled, the `DELETE` statement is going to return immediately, but the data can still be visible to queries until the background mutation is finished.
The mutation does not physically delete the rows that have been marked as deleted, this will only happen during the next merge. As a result, it is possible that for an unspecified period, data is not actually deleted from storage and is only marked as deleted.
If you need to guarantee that your data is deleted from storage in a predictable time, consider using the table setting [`min_age_to_force_merge_seconds`](https://clickhouse.com/docs/en/operations/settings/merge-tree-settings#min_age_to_force_merge_seconds). Or you can use the [ALTER TABLE ... DELETE](/en/sql-reference/statements/alter/delete) command. Note that deleting data using `ALTER TABLE ... DELETE` may consume significant resources as it recreates all affected parts.
## Deleting large amounts of data
Large deletes can negatively affect ClickHouse performance. If you are attempting to delete all rows from a table, consider using the [`TRUNCATE TABLE`](/en/sql-reference/statements/truncate) command.
If you anticipate frequent deletes, consider using a [custom partitioning key](/en/engines/table-engines/mergetree-family/custom-partitioning-key). You can then use the [`ALTER TABLE...DROP PARTITION`](/en/sql-reference/statements/alter/partition#drop-partitionpart) command to quickly drop all rows associated with that partition.
If you anticipate frequent deletes, consider using a [custom partitioning key](/en/engines/table-engines/mergetree-family/custom-partitioning-key). You can then use the [`ALTER TABLE ... DROP PARTITION`](/en/sql-reference/statements/alter/partition#drop-partitionpart) command to quickly drop all rows associated with that partition.
## Limitations of lightweight `DELETE`
### Lightweight `DELETE`s with projections
By default, `DELETE` does not work for tables with projections. This is because rows in a projection may be affected by a `DELETE` operation. But there is a [MergeTree setting](https://clickhouse.com/docs/en/operations/settings/merge-tree-settings) `lightweight_mutation_projection_mode` can change the behavior.
By default, `DELETE` does not work for tables with projections. This is because rows in a projection may be affected by a `DELETE` operation. But there is a [MergeTree setting](https://clickhouse.com/docs/en/operations/settings/merge-tree-settings) `lightweight_mutation_projection_mode` to change the behavior.
## Performance considerations when using lightweight `DELETE`
@ -48,7 +52,7 @@ The following can also negatively impact lightweight `DELETE` performance:
- A heavy `WHERE` condition in a `DELETE` query.
- If the mutations queue is filled with many other mutations, this can possibly lead to performance issues as all mutations on a table are executed sequentially.
- The affected table having a very large number of data parts.
- The affected table has a very large number of data parts.
- Having a lot of data in compact parts. In a Compact part, all columns are stored in one file.
## Delete permissions
@ -61,31 +65,31 @@ GRANT ALTER DELETE ON db.table to username;
## How lightweight DELETEs work internally in ClickHouse
1. A "mask" is applied to affected rows
1. **A "mask" is applied to affected rows**
When a `DELETE FROM table ...` query is executed, ClickHouse saves a mask where each row is marked as either “existing” or as “deleted”. Those “deleted” rows are omitted for subsequent queries. However, rows are actually only removed later by subsequent merges. Writing this mask is much more lightweight than what is done by an `ALTER table DELETE` query.
When a `DELETE FROM table ...` query is executed, ClickHouse saves a mask where each row is marked as either “existing” or as “deleted”. Those “deleted” rows are omitted for subsequent queries. However, rows are actually only removed later by subsequent merges. Writing this mask is much more lightweight than what is done by an `ALTER TABLE ... DELETE` query.
The mask is implemented as a hidden `_row_exists` system column that stores `True` for all visible rows and `False` for deleted ones. This column is only present in a part if some rows in the part were deleted. This column does not exist when a part has all values equal to `True`.
The mask is implemented as a hidden `_row_exists` system column that stores `True` for all visible rows and `False` for deleted ones. This column is only present in a part if some rows in the part were deleted. This column does not exist when a part has all values equal to `True`.
2. `SELECT` queries are transformed to include the mask
2. **`SELECT` queries are transformed to include the mask**
When a masked column is used in a query, the `SELECT ... FROM table WHERE condition` query internally is extended by the predicate on `_row_exists` and is transformed to:
```sql
SELECT ... FROM table PREWHERE _row_exists WHERE condition
```
At execution time, the column `_row_exists` is read to determine which rows should not be returned. If there are many deleted rows, ClickHouse can determine which granules can be fully skipped when reading the rest of the columns.
When a masked column is used in a query, the `SELECT ... FROM table WHERE condition` query internally is extended by the predicate on `_row_exists` and is transformed to:
```sql
SELECT ... FROM table PREWHERE _row_exists WHERE condition
```
At execution time, the column `_row_exists` is read to determine which rows should not be returned. If there are many deleted rows, ClickHouse can determine which granules can be fully skipped when reading the rest of the columns.
3. `DELETE` queries are transformed to `ALTER table UPDATE` queries
3. **`DELETE` queries are transformed to `ALTER TABLE ... UPDATE` queries**
The `DELETE FROM table WHERE condition` is translated into an `ALTER table UPDATE _row_exists = 0 WHERE condition` mutation.
The `DELETE FROM table WHERE condition` is translated into an `ALTER TABLE table UPDATE _row_exists = 0 WHERE condition` mutation.
Internally, this mutation is executed in two steps:
Internally, this mutation is executed in two steps:
1. A `SELECT count() FROM table WHERE condition` command is executed for each individual part to determine if the part is affected.
1. A `SELECT count() FROM table WHERE condition` command is executed for each individual part to determine if the part is affected.
2. Based on the commands above, affected parts are then mutated, and hardlinks are created for unaffected parts. In the case of wide parts, the `_row_exists` column for each row is updated and all other columns' files are hardlinked. For compact parts, all columns are re-written because they are all stored together in one file.
2. Based on the commands above, affected parts are then mutated, and hardlinks are created for unaffected parts. In the case of wide parts, the `_row_exists` column for each row is updated, and all other columns' files are hardlinked. For compact parts, all columns are re-written because they are all stored together in one file.
From the steps above, we can see that lightweight deletes using the masking technique improves performance over traditional `ALTER table DELETE` commands because `ALTER table DELETE` reads and re-writes all the columns' files for affected parts.
From the steps above, we can see that lightweight `DELETE` using the masking technique improves performance over traditional `ALTER TABLE ... DELETE` because it does not re-write all the columns' files for affected parts.
## Related content

15
docs/en/sql-reference/statements/select/from.md
View File

@ -15,7 +15,14 @@ The `FROM` clause specifies the source to read data from:
Subquery is another `SELECT` query that may be specified in parenthesis inside `FROM` clause.
`FROM` clause can contain multiple data sources, separated by commas, which is equivalent of performing [CROSS JOIN](../../../sql-reference/statements/select/join.md) on them.
The `FROM` can contain multiple data sources, separated by commas, which is equivalent of performing [CROSS JOIN](../../../sql-reference/statements/select/join.md) on them.
`FROM` can optionally appear before a `SELECT` clause. This is a ClickHouse-specific extension of standard SQL which makes `SELECT` statements easier to read. Example:
```sql
FROM table
SELECT *
```
## FINAL Modifier
@ -45,19 +52,19 @@ As an alternative to using `FINAL`, it is sometimes possible to use different qu
### Example Usage
**Using the `FINAL` keyword**
Using the `FINAL` keyword
```sql
SELECT x, y FROM mytable FINAL WHERE x > 1;
```
**Using `FINAL` as a query-level setting**
Using `FINAL` as a query-level setting
```sql
SELECT x, y FROM mytable WHERE x > 1 SETTINGS final = 1;
```
**Using `FINAL` as a session-level setting**
Using `FINAL` as a session-level setting
```sql
SET final = 1;

8
docs/en/sql-reference/transactions.md
View File

@ -8,14 +8,14 @@ slug: /en/guides/developer/transactional
This is transactional (ACID) if the inserted rows are packed and inserted as a single block (see Notes):
- Atomic: an INSERT succeeds or is rejected as a whole: if a confirmation is sent to the client, then all rows were inserted; if an error is sent to the client, then no rows were inserted.
- Consistent: if there are no table constraints violated, then all rows in an INSERT are inserted and the INSERT succeeds; if constraints are violated, then no rows are inserted.
- Isolated: concurrent clients observe a consistent snapshot of the table–the state of the table either as it was before the INSERT attempt, or after the successful INSERT; no partial state is seen
- Isolated: concurrent clients observe a consistent snapshot of the table–the state of the table either as it was before the INSERT attempt, or after the successful INSERT; no partial state is seen. Clients inside of another transaction have [snapshot isolation](https://en.wikipedia.org/wiki/Snapshot_isolation), while clients outside of a transaction have [read uncommitted](https://en.wikipedia.org/wiki/Isolation_(database_systems)#Read_uncommitted) isolation level.
- Durable: a successful INSERT is written to the filesystem before answering to the client, on a single replica or multiple replicas (controlled by the `insert_quorum` setting), and ClickHouse can ask the OS to sync the filesystem data on the storage media (controlled by the `fsync_after_insert` setting).
- INSERT into multiple tables with one statement is possible if materialized views are involved (the INSERT from the client is to a table which has associate materialized views).
## Case 2: INSERT into multiple partitions, of one table, of the MergeTree* family
Same as Case 1 above, with this detail:
- If table has many partitions and INSERT covers many partitions–then insertion into every partition is transactional on its own
- If table has many partitions and INSERT covers many partitions, then insertion into every partition is transactional on its own
## Case 3: INSERT into one distributed table of the MergeTree* family
@ -38,7 +38,7 @@ Same as Case 1 above, with this detail:
- the insert format is column-based (like Native, Parquet, ORC, etc) and the data contains only one block of data
- the size of the inserted block in general may depend on many settings (for example: `max_block_size`, `max_insert_block_size`, `min_insert_block_size_rows`, `min_insert_block_size_bytes`, `preferred_block_size_bytes`, etc)
- if the client did not receive an answer from the server, the client does not know if the transaction succeeded, and it can repeat the transaction, using exactly-once insertion properties
- ClickHouse is using MVCC with snapshot isolation internally
- ClickHouse is using [MVCC](https://en.wikipedia.org/wiki/Multiversion_concurrency_control) with [snapshot isolation](https://en.wikipedia.org/wiki/Snapshot_isolation) internally for concurrent transactions
- all ACID properties are valid even in the case of server kill/crash
- either insert_quorum into different AZ or fsync should be enabled to ensure durable inserts in the typical setup
- "consistency" in ACID terms does not cover the semantics of distributed systems, see https://jepsen.io/consistency which is controlled by different settings (select_sequential_consistency)
@ -260,7 +260,7 @@ FROM mergetree_table
### Transactions introspection
You can inspect transactions by querying the `system.transactions` table, but note that you cannot query that
table from a session that is in a transaction–open a second `clickhouse client` session to query that table.
table from a session that is in a transaction. Open a second `clickhouse client` session to query that table.
```sql
SELECT *

11
programs/keeper-client/Commands.cpp
View File

@ -506,14 +506,23 @@ bool RMRCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & nod
return false;
node->args.push_back(std::move(path));
ASTPtr remove_nodes_limit;
if (ParserUnsignedInteger{}.parse(pos, remove_nodes_limit, expected))
node->args.push_back(remove_nodes_limit->as<ASTLiteral &>().value);
else
node->args.push_back(UInt64(100));
return true;
}
void RMRCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) const
{
String path = client->getAbsolutePath(query->args[0].safeGet<String>());
UInt64 remove_nodes_limit = query->args[1].safeGet<UInt64>();
client->askConfirmation(
"You are going to recursively delete path " + path, [client, path] { client->zookeeper->removeRecursive(path); });
"You are going to recursively delete path " + path,
[client, path, remove_nodes_limit] { client->zookeeper->removeRecursive(path, static_cast<UInt32>(remove_nodes_limit)); });
}
bool ReconfigCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, DB::Expected & expected) const

2
programs/keeper-client/Commands.h
View File

@ -184,7 +184,7 @@ class RMRCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "{} <path> -- Recursively deletes path. Confirmation required"; }
String getHelpMessage() const override { return "{} <path> [limit] -- Recursively deletes path if the subtree size is smaller than the limit. Confirmation required (default limit = 100)"; }
};
class ReconfigCommand : public IKeeperClientCommand

10
programs/keeper/Keeper.cpp
View File

@ -11,6 +11,7 @@
#include <Core/ServerUUID.h>
#include <Common/logger_useful.h>
#include <Common/CgroupsMemoryUsageObserver.h>
#include <Common/MemoryWorker.h>
#include <Common/ErrorHandlers.h>
#include <Common/assertProcessUserMatchesDataOwner.h>
#include <Common/makeSocketAddress.h>
@ -384,6 +385,9 @@ try
LOG_INFO(log, "Background threads finished in {} ms", watch.elapsedMilliseconds());
});
MemoryWorker memory_worker(config().getUInt64("memory_worker_period_ms", 0));
memory_worker.start();
static ServerErrorHandler error_handler;
Poco::ErrorHandler::set(&error_handler);
@ -425,8 +429,9 @@ try
for (const auto & server : *servers)
metrics.emplace_back(ProtocolServerMetrics{server.getPortName(), server.currentThreads(), server.refusedConnections()});
return metrics;
}
);
},
/*update_jemalloc_epoch_=*/memory_worker.getSource() != MemoryWorker::MemoryUsageSource::Jemalloc,
/*update_rss_=*/memory_worker.getSource() == MemoryWorker::MemoryUsageSource::None);
std::vector<std::string> listen_hosts = DB::getMultipleValuesFromConfig(config(), "", "listen_host");
@ -655,7 +660,6 @@ try
GWPAsan::initFinished();
#endif
LOG_INFO(log, "Ready for connections.");
waitForTerminationRequest();

35
programs/server/Server.cpp
View File

@ -11,7 +11,6 @@
#include <Poco/Util/HelpFormatter.h>
#include <Poco/Environment.h>
#include <Poco/Config.h>
#include <Common/Jemalloc.h>
#include <Common/scope_guard_safe.h>
#include <Common/logger_useful.h>
#include <base/phdr_cache.h>
@ -25,6 +24,7 @@
#include <base/Numa.h>
#include <Common/PoolId.h>
#include <Common/MemoryTracker.h>
#include <Common/MemoryWorker.h>
#include <Common/ClickHouseRevision.h>
#include <Common/DNSResolver.h>
#include <Common/CgroupsMemoryUsageObserver.h>
@ -111,6 +111,8 @@
#include <filesystem>
#include <unordered_set>
#include <Common/Jemalloc.h>
#include "config.h"
#include <Common/config_version.h>
@ -449,9 +451,12 @@ void checkForUsersNotInMainConfig(
}
}
namespace
{
/// Unused in other builds
#if defined(OS_LINUX)
static String readLine(const String & path)
String readLine(const String & path)
{
ReadBufferFromFile in(path);
String contents;
@ -459,7 +464,7 @@ static String readLine(const String & path)
return contents;
}
static int readNumber(const String & path)
int readNumber(const String & path)
{
ReadBufferFromFile in(path);
int result;
@ -469,7 +474,7 @@ static int readNumber(const String & path)
#endif
static void sanityChecks(Server & server)
void sanityChecks(Server & server)
{
std::string data_path = getCanonicalPath(server.config().getString("path", DBMS_DEFAULT_PATH));
std::string logs_path = server.config().getString("logger.log", "");
@ -590,6 +595,8 @@ static void sanityChecks(Server & server)
}
}
}
void loadStartupScripts(const Poco::Util::AbstractConfiguration & config, ContextMutablePtr context, Poco::Logger * log)
{
try
@ -906,6 +913,8 @@ try
LOG_INFO(log, "Background threads finished in {} ms", watch.elapsedMilliseconds());
});
MemoryWorker memory_worker(global_context->getServerSettings().memory_worker_period_ms);
/// This object will periodically calculate some metrics.
ServerAsynchronousMetrics async_metrics(
global_context,
@ -924,8 +933,9 @@ try
for (const auto & server : servers)
metrics.emplace_back(ProtocolServerMetrics{server.getPortName(), server.currentThreads(), server.refusedConnections()});
return metrics;
}
);
},
/*update_jemalloc_epoch_=*/memory_worker.getSource() != MemoryWorker::MemoryUsageSource::Jemalloc,
/*update_rss_=*/memory_worker.getSource() == MemoryWorker::MemoryUsageSource::None);
/// NOTE: global context should be destroyed *before* GlobalThreadPool::shutdown()
/// Otherwise GlobalThreadPool::shutdown() will hang, since Context holds some threads.
@ -1204,6 +1214,8 @@ try
FailPointInjection::enableFromGlobalConfig(config());
memory_worker.start();
int default_oom_score = 0;
#if !defined(NDEBUG)
@ -1547,15 +1559,6 @@ try
total_memory_tracker.setDescription("(total)");
total_memory_tracker.setMetric(CurrentMetrics::MemoryTracking);
if (cgroups_memory_usage_observer)
{
double hard_limit_ratio = new_server_settings.cgroup_memory_watcher_hard_limit_ratio;
double soft_limit_ratio = new_server_settings.cgroup_memory_watcher_soft_limit_ratio;
cgroups_memory_usage_observer->setMemoryUsageLimits(
static_cast<uint64_t>(max_server_memory_usage * hard_limit_ratio),
static_cast<uint64_t>(max_server_memory_usage * soft_limit_ratio));
}
size_t merges_mutations_memory_usage_soft_limit = new_server_settings.merges_mutations_memory_usage_soft_limit;
size_t default_merges_mutations_server_memory_usage = static_cast<size_t>(current_physical_server_memory * new_server_settings.merges_mutations_memory_usage_to_ram_ratio);
@ -1584,8 +1587,6 @@ try
background_memory_tracker.setDescription("(background)");
background_memory_tracker.setMetric(CurrentMetrics::MergesMutationsMemoryTracking);
total_memory_tracker.setAllowUseJemallocMemory(new_server_settings.allow_use_jemalloc_memory);
auto * global_overcommit_tracker = global_context->getGlobalOvercommitTracker();
total_memory_tracker.setOvercommitTracker(global_overcommit_tracker);

2
src/Access/AccessEntityIO.cpp
View File

@ -82,7 +82,7 @@ AccessEntityPtr deserializeAccessEntityImpl(const String & definition)
if (res)
throw Exception(ErrorCodes::INCORRECT_ACCESS_ENTITY_DEFINITION, "Two access entities attached in the same file");
res = user = std::make_unique<User>();
InterpreterCreateUserQuery::updateUserFromQuery(*user, *create_user_query, /* allow_no_password = */ true, /* allow_plaintext_password = */ true);
InterpreterCreateUserQuery::updateUserFromQuery(*user, *create_user_query, /* allow_no_password = */ true, /* allow_plaintext_password = */ true, /* max_number_of_authentication_methods = zero is unlimited*/ 0);
}
else if (auto * create_role_query = query->as<ASTCreateRoleQuery>())
{

318
src/Access/Authentication.cpp
View File

@ -14,11 +14,6 @@
namespace DB
{
namespace ErrorCodes
{
extern const int NOT_IMPLEMENTED;
extern const int SUPPORT_IS_DISABLED;
}
namespace
{
@ -84,12 +79,140 @@ namespace
return false;
}
#endif
}
bool checkKerberosAuthentication(
const GSSAcceptorContext * gss_acceptor_context,
const AuthenticationData & authentication_method,
const ExternalAuthenticators & external_authenticators)
{
return authentication_method.getType() == AuthenticationType::KERBEROS
&& external_authenticators.checkKerberosCredentials(authentication_method.getKerberosRealm(), *gss_acceptor_context);
}
bool checkMySQLAuthentication(
const MySQLNative41Credentials * mysql_credentials,
const AuthenticationData & authentication_method)
{
switch (authentication_method.getType())
{
case AuthenticationType::PLAINTEXT_PASSWORD:
return checkPasswordPlainTextMySQL(
mysql_credentials->getScramble(),
mysql_credentials->getScrambledPassword(),
authentication_method.getPasswordHashBinary());
case AuthenticationType::DOUBLE_SHA1_PASSWORD:
return checkPasswordDoubleSHA1MySQL(
mysql_credentials->getScramble(),
mysql_credentials->getScrambledPassword(),
authentication_method.getPasswordHashBinary());
default:
return false;
}
}
bool checkBasicAuthentication(
const BasicCredentials * basic_credentials,
const AuthenticationData & authentication_method,
const ExternalAuthenticators & external_authenticators,
SettingsChanges & settings)
{
switch (authentication_method.getType())
{
case AuthenticationType::NO_PASSWORD:
{
return true; // N.B. even if the password is not empty!
}
case AuthenticationType::PLAINTEXT_PASSWORD:
{
return checkPasswordPlainText(basic_credentials->getPassword(), authentication_method.getPasswordHashBinary());
}
case AuthenticationType::SHA256_PASSWORD:
{
return checkPasswordSHA256(
basic_credentials->getPassword(), authentication_method.getPasswordHashBinary(), authentication_method.getSalt());
}
case AuthenticationType::DOUBLE_SHA1_PASSWORD:
{
return checkPasswordDoubleSHA1(basic_credentials->getPassword(), authentication_method.getPasswordHashBinary());
}
case AuthenticationType::LDAP:
{
return external_authenticators.checkLDAPCredentials(authentication_method.getLDAPServerName(), *basic_credentials);
}
case AuthenticationType::BCRYPT_PASSWORD:
{
return checkPasswordBcrypt(basic_credentials->getPassword(), authentication_method.getPasswordHashBinary());
}
case AuthenticationType::HTTP:
{
if (authentication_method.getHTTPAuthenticationScheme() == HTTPAuthenticationScheme::BASIC)
{
return external_authenticators.checkHTTPBasicCredentials(
authentication_method.getHTTPAuthenticationServerName(), *basic_credentials, settings);
}
break;
}
default:
break;
}
return false;
}
bool checkSSLCertificateAuthentication(
const SSLCertificateCredentials * ssl_certificate_credentials,
const AuthenticationData & authentication_method)
{
if (AuthenticationType::SSL_CERTIFICATE != authentication_method.getType())
{
return false;
}
for (SSLCertificateSubjects::Type type : {SSLCertificateSubjects::Type::CN, SSLCertificateSubjects::Type::SAN})
{
for (const auto & subject : authentication_method.getSSLCertificateSubjects().at(type))
{
if (ssl_certificate_credentials->getSSLCertificateSubjects().at(type).contains(subject))
return true;
// Wildcard support (1 only)
if (subject.contains('*'))
{
auto prefix = std::string_view(subject).substr(0, subject.find('*'));
auto suffix = std::string_view(subject).substr(subject.find('*') + 1);
auto slashes = std::count(subject.begin(), subject.end(), '/');
for (const auto & certificate_subject : ssl_certificate_credentials->getSSLCertificateSubjects().at(type))
{
bool matches_wildcard = certificate_subject.starts_with(prefix) && certificate_subject.ends_with(suffix);
// '*' must not represent a '/' in URI, so check if the number of '/' are equal
bool matches_slashes = slashes == count(certificate_subject.begin(), certificate_subject.end(), '/');
if (matches_wildcard && matches_slashes)
return true;
}
}
}
}
return false;
}
#if USE_SSH
bool checkSshAuthentication(
const SshCredentials * ssh_credentials,
const AuthenticationData & authentication_method)
{
return AuthenticationType::SSH_KEY == authentication_method.getType()
&& checkSshSignature(authentication_method.getSSHKeys(), ssh_credentials->getSignature(), ssh_credentials->getOriginal());
}
#endif
}
bool Authentication::areCredentialsValid(
const Credentials & credentials,
const AuthenticationData & auth_data,
const AuthenticationData & authentication_method,
const ExternalAuthenticators & external_authenticators,
SettingsChanges & settings)
{
@ -98,204 +221,35 @@ bool Authentication::areCredentialsValid(
if (const auto * gss_acceptor_context = typeid_cast<const GSSAcceptorContext *>(&credentials))
{
switch (auth_data.getType())
{
case AuthenticationType::NO_PASSWORD:
case AuthenticationType::PLAINTEXT_PASSWORD:
case AuthenticationType::SHA256_PASSWORD:
case AuthenticationType::DOUBLE_SHA1_PASSWORD:
case AuthenticationType::BCRYPT_PASSWORD:
case AuthenticationType::LDAP:
case AuthenticationType::HTTP:
throw Authentication::Require<BasicCredentials>("ClickHouse Basic Authentication");
case AuthenticationType::JWT:
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
case AuthenticationType::KERBEROS:
return external_authenticators.checkKerberosCredentials(auth_data.getKerberosRealm(), *gss_acceptor_context);
case AuthenticationType::SSL_CERTIFICATE:
throw Authentication::Require<BasicCredentials>("ClickHouse X.509 Authentication");
case AuthenticationType::SSH_KEY:
#if USE_SSH
throw Authentication::Require<SshCredentials>("SSH Keys Authentication");
#else
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "SSH is disabled, because ClickHouse is built without libssh");
#endif
case AuthenticationType::MAX:
break;
}
return checkKerberosAuthentication(gss_acceptor_context, authentication_method, external_authenticators);
}
if (const auto * mysql_credentials = typeid_cast<const MySQLNative41Credentials *>(&credentials))
{
switch (auth_data.getType())
{
case AuthenticationType::NO_PASSWORD:
return true; // N.B. even if the password is not empty!
case AuthenticationType::PLAINTEXT_PASSWORD:
return checkPasswordPlainTextMySQL(mysql_credentials->getScramble(), mysql_credentials->getScrambledPassword(), auth_data.getPasswordHashBinary());
case AuthenticationType::DOUBLE_SHA1_PASSWORD:
return checkPasswordDoubleSHA1MySQL(mysql_credentials->getScramble(), mysql_credentials->getScrambledPassword(), auth_data.getPasswordHashBinary());
case AuthenticationType::SHA256_PASSWORD:
case AuthenticationType::BCRYPT_PASSWORD:
case AuthenticationType::LDAP:
case AuthenticationType::KERBEROS:
case AuthenticationType::HTTP:
throw Authentication::Require<BasicCredentials>("ClickHouse Basic Authentication");
case AuthenticationType::SSL_CERTIFICATE:
throw Authentication::Require<BasicCredentials>("ClickHouse X.509 Authentication");
case AuthenticationType::JWT:
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
case AuthenticationType::SSH_KEY:
#if USE_SSH
throw Authentication::Require<SshCredentials>("SSH Keys Authentication");
#else
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "SSH is disabled, because ClickHouse is built without libssh");
#endif
case AuthenticationType::MAX:
break;
}
return checkMySQLAuthentication(mysql_credentials, authentication_method);
}
if (const auto * basic_credentials = typeid_cast<const BasicCredentials *>(&credentials))
{
switch (auth_data.getType())
{
case AuthenticationType::NO_PASSWORD:
return true; // N.B. even if the password is not empty!
case AuthenticationType::PLAINTEXT_PASSWORD:
return checkPasswordPlainText(basic_credentials->getPassword(), auth_data.getPasswordHashBinary());
case AuthenticationType::SHA256_PASSWORD:
return checkPasswordSHA256(basic_credentials->getPassword(), auth_data.getPasswordHashBinary(), auth_data.getSalt());
case AuthenticationType::DOUBLE_SHA1_PASSWORD:
return checkPasswordDoubleSHA1(basic_credentials->getPassword(), auth_data.getPasswordHashBinary());
case AuthenticationType::LDAP:
return external_authenticators.checkLDAPCredentials(auth_data.getLDAPServerName(), *basic_credentials);
case AuthenticationType::KERBEROS:
throw Authentication::Require<GSSAcceptorContext>(auth_data.getKerberosRealm());
case AuthenticationType::SSL_CERTIFICATE:
throw Authentication::Require<BasicCredentials>("ClickHouse X.509 Authentication");
case AuthenticationType::SSH_KEY:
#if USE_SSH
throw Authentication::Require<SshCredentials>("SSH Keys Authentication");
#else
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "SSH is disabled, because ClickHouse is built without libssh");
#endif
case AuthenticationType::JWT:
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
case AuthenticationType::BCRYPT_PASSWORD:
return checkPasswordBcrypt(basic_credentials->getPassword(), auth_data.getPasswordHashBinary());
case AuthenticationType::HTTP:
switch (auth_data.getHTTPAuthenticationScheme())
{
case HTTPAuthenticationScheme::BASIC:
return external_authenticators.checkHTTPBasicCredentials(
auth_data.getHTTPAuthenticationServerName(), *basic_credentials, settings);
}
case AuthenticationType::MAX:
break;
}
return checkBasicAuthentication(basic_credentials, authentication_method, external_authenticators, settings);
}
if (const auto * ssl_certificate_credentials = typeid_cast<const SSLCertificateCredentials *>(&credentials))
{
switch (auth_data.getType())
{
case AuthenticationType::NO_PASSWORD:
case AuthenticationType::PLAINTEXT_PASSWORD:
case AuthenticationType::SHA256_PASSWORD:
case AuthenticationType::DOUBLE_SHA1_PASSWORD:
case AuthenticationType::BCRYPT_PASSWORD:
case AuthenticationType::LDAP:
case AuthenticationType::HTTP:
throw Authentication::Require<BasicCredentials>("ClickHouse Basic Authentication");
case AuthenticationType::JWT:
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
case AuthenticationType::KERBEROS:
throw Authentication::Require<GSSAcceptorContext>(auth_data.getKerberosRealm());
case AuthenticationType::SSL_CERTIFICATE:
for (SSLCertificateSubjects::Type type : {SSLCertificateSubjects::Type::CN, SSLCertificateSubjects::Type::SAN})
{
for (const auto & subject : auth_data.getSSLCertificateSubjects().at(type))
{
if (ssl_certificate_credentials->getSSLCertificateSubjects().at(type).contains(subject))
return true;
}
}
return false;
case AuthenticationType::SSH_KEY:
#if USE_SSH
throw Authentication::Require<SshCredentials>("SSH Keys Authentication");
#else
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "SSH is disabled, because ClickHouse is built without libssh");
#endif
case AuthenticationType::MAX:
break;
}
return checkSSLCertificateAuthentication(ssl_certificate_credentials, authentication_method);
}
#if USE_SSH
if (const auto * ssh_credentials = typeid_cast<const SshCredentials *>(&credentials))
{
switch (auth_data.getType())
{
case AuthenticationType::NO_PASSWORD:
case AuthenticationType::PLAINTEXT_PASSWORD:
case AuthenticationType::SHA256_PASSWORD:
case AuthenticationType::DOUBLE_SHA1_PASSWORD:
case AuthenticationType::BCRYPT_PASSWORD:
case AuthenticationType::LDAP:
case AuthenticationType::HTTP:
throw Authentication::Require<BasicCredentials>("ClickHouse Basic Authentication");
case AuthenticationType::JWT:
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "JWT is available only in ClickHouse Cloud");
case AuthenticationType::KERBEROS:
throw Authentication::Require<GSSAcceptorContext>(auth_data.getKerberosRealm());
case AuthenticationType::SSL_CERTIFICATE:
throw Authentication::Require<SSLCertificateCredentials>("ClickHouse X.509 Authentication");
case AuthenticationType::SSH_KEY:
return checkSshSignature(auth_data.getSSHKeys(), ssh_credentials->getSignature(), ssh_credentials->getOriginal());
case AuthenticationType::MAX:
break;
}
return checkSshAuthentication(ssh_credentials, authentication_method);
}
#endif
if ([[maybe_unused]] const auto * always_allow_credentials = typeid_cast<const AlwaysAllowCredentials *>(&credentials))
return true;
throw Exception(ErrorCodes::NOT_IMPLEMENTED, "areCredentialsValid(): authentication type {} not supported", toString(auth_data.getType()));
return false;
}
}

2
src/Access/Authentication.h
View File

@ -24,7 +24,7 @@ struct Authentication
/// returned by the authentication server
static bool areCredentialsValid(
const Credentials & credentials,
const AuthenticationData & auth_data,
const AuthenticationData & authentication_method,
const ExternalAuthenticators & external_authenticators,
SettingsChanges & settings);

3
src/Access/AuthenticationData.cpp
View File

@ -375,7 +375,8 @@ std::shared_ptr<ASTAuthenticationData> AuthenticationData::toAST() const
break;
}
case AuthenticationType::NO_PASSWORD: [[fallthrough]];
case AuthenticationType::NO_PASSWORD:
break;
case AuthenticationType::MAX:
throw Exception(ErrorCodes::LOGICAL_ERROR, "AST: Unexpected authentication type {}", toString(auth_type));
}

50
src/Access/IAccessStorage.cpp
View File

@ -30,7 +30,6 @@ namespace ErrorCodes
extern const int IP_ADDRESS_NOT_ALLOWED;
extern const int LOGICAL_ERROR;
extern const int NOT_IMPLEMENTED;
extern const int AUTHENTICATION_FAILED;
}
@ -525,27 +524,45 @@ std::optional<AuthResult> IAccessStorage::authenticateImpl(
if (!isAddressAllowed(*user, address))
throwAddressNotAllowed(address);
auto auth_type = user->auth_data.getType();
bool skipped_not_allowed_authentication_methods = false;
for (const auto & auth_method : user->authentication_methods)
{
auto auth_type = auth_method.getType();
if (((auth_type == AuthenticationType::NO_PASSWORD) && !allow_no_password) ||
((auth_type == AuthenticationType::PLAINTEXT_PASSWORD) && !allow_plaintext_password))
throwAuthenticationTypeNotAllowed(auth_type);
if (!areCredentialsValid(*user, credentials, external_authenticators, auth_result.settings))
throwInvalidCredentials();
{
skipped_not_allowed_authentication_methods = true;
continue;
}
if (areCredentialsValid(user->getName(), user->valid_until, auth_method, credentials, external_authenticators, auth_result.settings))
{
auth_result.authentication_data = auth_method;
return auth_result;
}
}
if (skipped_not_allowed_authentication_methods)
{
LOG_INFO(log, "Skipped the check for not allowed authentication methods,"
"check allow_no_password and allow_plaintext_password settings in the server configuration");
}
throwInvalidCredentials();
}
}
if (throw_if_user_not_exists)
throwNotFound(AccessEntityType::USER, credentials.getUserName());
else
return std::nullopt;
}
bool IAccessStorage::areCredentialsValid(
const User & user,
const std::string & user_name,
time_t valid_until,
const AuthenticationData & authentication_method,
const Credentials & credentials,
const ExternalAuthenticators & external_authenticators,
SettingsChanges & settings) const
@ -553,21 +570,20 @@ bool IAccessStorage::areCredentialsValid(
if (!credentials.isReady())
return false;
if (credentials.getUserName() != user.getName())
if (credentials.getUserName() != user_name)
return false;
if (user.valid_until)
if (valid_until)
{
const time_t now = std::chrono::system_clock::to_time_t(std::chrono::system_clock::now());
if (now > user.valid_until)
if (now > valid_until)
return false;
}
return Authentication::areCredentialsValid(credentials, user.auth_data, external_authenticators, settings);
return Authentication::areCredentialsValid(credentials, authentication_method, external_authenticators, settings);
}
bool IAccessStorage::isAddressAllowed(const User & user, const Poco::Net::IPAddress & address) const
{
return user.allowed_client_hosts.contains(address);
@ -747,14 +763,6 @@ void IAccessStorage::throwAddressNotAllowed(const Poco::Net::IPAddress & address
throw Exception(ErrorCodes::IP_ADDRESS_NOT_ALLOWED, "Connections from {} are not allowed", address.toString());
}
void IAccessStorage::throwAuthenticationTypeNotAllowed(AuthenticationType auth_type)
{
throw Exception(
ErrorCodes::AUTHENTICATION_FAILED,
"Authentication type {} is not allowed, check the setting allow_{} in the server configuration",
toString(auth_type), AuthenticationTypeInfo::get(auth_type).name);
}
void IAccessStorage::throwInvalidCredentials()
{
throw Exception(ErrorCodes::WRONG_PASSWORD, "Invalid credentials");

7
src/Access/IAccessStorage.h
View File

@ -1,6 +1,7 @@
#pragma once
#include <Access/IAccessEntity.h>
#include <Access/AuthenticationData.h>
#include <Core/Types.h>
#include <Core/UUID.h>
#include <Parsers/IParser.h>
@ -34,6 +35,7 @@ struct AuthResult
UUID user_id;
/// Session settings received from authentication server (if any)
SettingsChanges settings{};
AuthenticationData authentication_data {};
};
/// Contains entities, i.e. instances of classes derived from IAccessEntity.
@ -227,7 +229,9 @@ protected:
bool allow_no_password,
bool allow_plaintext_password) const;
virtual bool areCredentialsValid(
const User & user,
const std::string & user_name,
time_t valid_until,
const AuthenticationData & authentication_method,
const Credentials & credentials,
const ExternalAuthenticators & external_authenticators,
SettingsChanges & settings) const;
@ -248,7 +252,6 @@ protected:
[[noreturn]] void throwReadonlyCannotRemove(AccessEntityType type, const String & name) const;
[[noreturn]] static void throwAddressNotAllowed(const Poco::Net::IPAddress & address);
[[noreturn]] static void throwInvalidCredentials();
[[noreturn]] static void throwAuthenticationTypeNotAllowed(AuthenticationType auth_type);
[[noreturn]] void throwBackupNotAllowed() const;
[[noreturn]] void throwRestoreNotAllowed() const;

6
src/Access/LDAPAccessStorage.cpp
View File

@ -468,8 +468,8 @@ std::optional<AuthResult> LDAPAccessStorage::authenticateImpl(
// User does not exist, so we create one, and will add it if authentication is successful.
new_user = std::make_shared<User>();
new_user->setName(credentials.getUserName());
new_user->auth_data = AuthenticationData(AuthenticationType::LDAP);
new_user->auth_data.setLDAPServerName(ldap_server_name);
new_user->authentication_methods.emplace_back(AuthenticationType::LDAP);
new_user->authentication_methods.back().setLDAPServerName(ldap_server_name);
user = new_user;
}
@ -504,7 +504,7 @@ std::optional<AuthResult> LDAPAccessStorage::authenticateImpl(
}
if (id)
return AuthResult{ .user_id = *id };
return AuthResult{ .user_id = *id, .authentication_data = AuthenticationData(AuthenticationType::LDAP) };
return std::nullopt;
}

3
src/Access/User.cpp
View File

@ -16,7 +16,8 @@ bool User::equal(const IAccessEntity & other) const
if (!IAccessEntity::equal(other))
return false;
const auto & other_user = typeid_cast<const User &>(other);
return (auth_data == other_user.auth_data) && (allowed_client_hosts == other_user.allowed_client_hosts)
return (authentication_methods == other_user.authentication_methods)
&& (allowed_client_hosts == other_user.allowed_client_hosts)
&& (access == other_user.access) && (granted_roles == other_user.granted_roles) && (default_roles == other_user.default_roles)
&& (settings == other_user.settings) && (grantees == other_user.grantees) && (default_database == other_user.default_database)
&& (valid_until == other_user.valid_until);

2
src/Access/User.h
View File

@ -15,7 +15,7 @@ namespace DB
*/
struct User : public IAccessEntity
{
AuthenticationData auth_data;
std::vector<AuthenticationData> authentication_methods;
AllowedClientHosts allowed_client_hosts = AllowedClientHosts::AnyHostTag{};
AccessRights access;
GrantedRoles granted_roles;

Some files were not shown because too many files have changed in this diff Show More