Merge branch 'ClickHouse:master' into add-alias

xiedeyantu · Jul 26, 2023 · 6bb1a30 · 6bb1a30
2 parents 265e143 + a4a8c73
commit 6bb1a30
Show file tree

Hide file tree

Showing 283 changed files with 3,669 additions and 1,836 deletions.
diff --git a/base/poco/Foundation/include/Poco/URI.h b/base/poco/Foundation/include/Poco/URI.h
@@ -57,7 +57,7 @@ class Foundation_API URI
     URI();
     /// Creates an empty URI.
 
-    explicit URI(const std::string & uri);
+    explicit URI(const std::string & uri, bool disable_url_encoding = false);
     /// Parses an URI from the given string. Throws a
     /// SyntaxException if the uri is not valid.
 
@@ -350,13 +350,19 @@ class Foundation_API URI
     static const std::string ILLEGAL;
 
 private:
+    void encodePath(std::string & encodedStr) const;
+    void decodePath(const std::string & encodedStr);
+
+
     std::string _scheme;
     std::string _userInfo;
     std::string _host;
     unsigned short _port;
     std::string _path;
     std::string _query;
     std::string _fragment;
+
+    bool _disable_url_encoding = false;
 };
 
 

diff --git a/base/poco/Foundation/src/URI.cpp b/base/poco/Foundation/src/URI.cpp
@@ -36,8 +36,8 @@ URI::URI():
 }
 
 
-URI::URI(const std::string& uri):
-	_port(0)
+URI::URI(const std::string& uri, bool decode_and_encode_path):
+	_port(0), _disable_url_encoding(decode_and_encode_path)
 {
 	parse(uri);
 }
@@ -107,7 +107,8 @@ URI::URI(const URI& uri):
 	_port(uri._port),
 	_path(uri._path),
 	_query(uri._query),
-	_fragment(uri._fragment)
+	_fragment(uri._fragment),
+    _disable_url_encoding(uri._disable_url_encoding)
 {
 }
 
@@ -119,7 +120,8 @@ URI::URI(const URI& baseURI, const std::string& relativeURI):
 	_port(baseURI._port),
 	_path(baseURI._path),
 	_query(baseURI._query),
-	_fragment(baseURI._fragment)
+	_fragment(baseURI._fragment),
+    _disable_url_encoding(baseURI._disable_url_encoding)
 {
 	resolve(relativeURI);
 }
@@ -151,6 +153,7 @@ URI& URI::operator = (const URI& uri)
 		_path     = uri._path;
 		_query    = uri._query;
 		_fragment = uri._fragment;
+        _disable_url_encoding = uri._disable_url_encoding;
 	}
 	return *this;
 }
@@ -181,6 +184,7 @@ void URI::swap(URI& uri)
 	std::swap(_path, uri._path);
 	std::swap(_query, uri._query);
 	std::swap(_fragment, uri._fragment);
+    std::swap(_disable_url_encoding, uri._disable_url_encoding);
 }
 
 
@@ -201,7 +205,7 @@ std::string URI::toString() const
 	std::string uri;
 	if (isRelative())
 	{
-		encode(_path, RESERVED_PATH, uri);
+		encodePath(uri);
 	}
 	else
 	{
@@ -217,7 +221,7 @@ std::string URI::toString() const
 		{
 			if (!auth.empty() && _path[0] != '/')
 				uri += '/';
-			encode(_path, RESERVED_PATH, uri);
+            encodePath(uri);
 		}
 		else if (!_query.empty() || !_fragment.empty())
 		{
@@ -313,7 +317,7 @@ void URI::setAuthority(const std::string& authority)
 void URI::setPath(const std::string& path)
 {
 	_path.clear();
-	decode(path, _path);
+    decodePath(path);
 }
 
 
@@ -418,7 +422,7 @@ void URI::setPathEtc(const std::string& pathEtc)
 std::string URI::getPathEtc() const
 {
 	std::string pathEtc;
-	encode(_path, RESERVED_PATH, pathEtc);
+	encodePath(pathEtc);
 	if (!_query.empty())
 	{
 		pathEtc += '?';
@@ -436,7 +440,7 @@ std::string URI::getPathEtc() const
 std::string URI::getPathAndQuery() const
 {
 	std::string pathAndQuery;
-	encode(_path, RESERVED_PATH, pathAndQuery);
+	encodePath(pathAndQuery);
 	if (!_query.empty())
 	{
 		pathAndQuery += '?';
@@ -681,6 +685,21 @@ void URI::decode(const std::string& str, std::string& decodedStr, bool plusAsSpa
 	}
 }
 
+void URI::encodePath(std::string & encodedStr) const
+{
+    if (_disable_url_encoding)
+        encodedStr = _path;
+    else
+        encode(_path, RESERVED_PATH, encodedStr);
+}
+
+void URI::decodePath(const std::string & encodedStr)
+{
+    if (_disable_url_encoding)
+        _path = encodedStr;
+    else
+        decode(encodedStr, _path);
+}
 
 bool URI::isWellKnownPort() const
 {
@@ -820,7 +839,7 @@ void URI::parsePath(std::string::const_iterator& it, const std::string::const_it
 {
 	std::string path;
 	while (it != end && *it != '?' && *it != '#') path += *it++;
-	decode(path, _path);
+    decodePath(path);
 }
 
 

diff --git a/contrib/idxd-config b/contrib/idxd-config
diff --git a/contrib/qpl b/contrib/qpl
diff --git a/docker/test/stress/run.sh b/docker/test/stress/run.sh
@@ -14,6 +14,7 @@ ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
 
 # Stress tests and upgrade check uses similar code that was placed
 # in a separate bash library. See tests/ci/stress_tests.lib
+source /usr/share/clickhouse-test/ci/attach_gdb.lib
 source /usr/share/clickhouse-test/ci/stress_tests.lib
 
 install_packages package_folder
@@ -52,7 +53,7 @@ azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
 
 start
 
-shellcheck disable=SC2086 # No quotes because I want to split it into words.
+# shellcheck disable=SC2086 # No quotes because I want to split it into words.
 /s3downloader --url-prefix "$S3_URL" --dataset-names $DATASETS
 chmod 777 -R /var/lib/clickhouse
 clickhouse-client --query "ATTACH DATABASE IF NOT EXISTS datasets ENGINE = Ordinary"

diff --git a/docker/test/upgrade/run.sh b/docker/test/upgrade/run.sh
@@ -16,6 +16,7 @@ ln -s /usr/share/clickhouse-test/ci/get_previous_release_tag.py /usr/bin/get_pre
 
 # Stress tests and upgrade check uses similar code that was placed
 # in a separate bash library. See tests/ci/stress_tests.lib
+source /usr/share/clickhouse-test/ci/attach_gdb.lib
 source /usr/share/clickhouse-test/ci/stress_tests.lib
 
 azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
@@ -61,6 +62,7 @@ configure
 
 # it contains some new settings, but we can safely remove it
 rm /etc/clickhouse-server/config.d/merge_tree.xml
+rm /etc/clickhouse-server/config.d/enable_wait_for_shutdown_replicated_tables.xml
 rm /etc/clickhouse-server/users.d/nonconst_timezone.xml
 
 start
@@ -90,6 +92,7 @@ sudo chgrp clickhouse /etc/clickhouse-server/config.d/s3_storage_policy_by_defau
 
 # it contains some new settings, but we can safely remove it
 rm /etc/clickhouse-server/config.d/merge_tree.xml
+rm /etc/clickhouse-server/config.d/enable_wait_for_shutdown_replicated_tables.xml
 rm /etc/clickhouse-server/users.d/nonconst_timezone.xml
 
 start

diff --git a/docs/en/development/building_and_benchmarking_deflate_qpl.md b/docs/en/development/building_and_benchmarking_deflate_qpl.md
@@ -7,12 +7,8 @@ description: How to build Clickhouse and run benchmark with DEFLATE_QPL Codec
 
 # Build Clickhouse with DEFLATE_QPL
 
-- Make sure your target machine meet the QPL required [prerequisites](https://intel.github.io/qpl/documentation/get_started_docs/installation.html#prerequisites)
-- Pass the following flag to CMake when building ClickHouse:
-
-``` bash
-cmake -DENABLE_QPL=1 ..
-```
+- Make sure your host machine meet the QPL required [prerequisites](https://intel.github.io/qpl/documentation/get_started_docs/installation.html#prerequisites)
+- deflate_qpl is enabled by default during cmake build. In case you accidentally change it, please double-check build flag: ENABLE_QPL=1
 
 - For generic requirements, please refer to Clickhouse generic [build instructions](/docs/en/development/build.md)
 

diff --git a/docs/en/engines/table-engines/integrations/s3.md b/docs/en/engines/table-engines/integrations/s3.md
@@ -57,7 +57,8 @@ Notice that the S3 endpoint in the `ENGINE` configuration uses the parameter tok
 
 :::note
 As shown in the example, querying from S3 tables that are partitioned is
-not directly supported at this time, but can be accomplished by querying the bucket contents with a wildcard.
+not directly supported at this time, but can be accomplished by querying the individual partitions
+using the S3 table function.
 
 The primary use-case for writing 
 partitioned data in S3 is to enable transferring that data into another
@@ -127,23 +128,7 @@ FROM s3('http://minio:10000/clickhouse//test_45.csv', 'minioadmin', 'minioadminp
 └────┴────┴────┘
 ```
 
-#### Select from all partitions
-
-```sql
-SELECT *
-FROM s3('http://minio:10000/clickhouse//**', 'minioadmin', 'minioadminpassword', 'CSV')
-```
-```response
-┌─c1─┬─c2─┬─c3─┐
-│  3 │  2 │  1 │
-└────┴────┴────┘
-┌─c1─┬─c2─┬─c3─┐
-│  1 │  2 │  3 │
-└────┴────┴────┘
-┌─c1─┬─c2─┬─c3─┐
-│ 78 │ 43 │ 45 │
-└────┴────┴────┘
-```
+#### Limitation
 
 You may naturally try to `Select * from p`, but as noted above, this query will fail; use the preceding query.
 

diff --git a/docs/en/engines/table-engines/special/url.md b/docs/en/engines/table-engines/special/url.md
@@ -106,3 +106,4 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
 ## Storage Settings {#storage-settings}
 
 - [engine_url_skip_empty_files](/docs/en/operations/settings/settings.md#engine_url_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
+- [disable_url_encoding](/docs/en/operations/settings/settings.md#disable_url_encoding) -allows to disable decoding/encoding path in uri. Disabled by default.
diff --git a/docs/en/interfaces/http.md b/docs/en/interfaces/http.md
@@ -56,7 +56,7 @@ Connection: Close
 Content-Type: text/tab-separated-values; charset=UTF-8
 X-ClickHouse-Server-Display-Name: clickhouse.ru-central1.internal
 X-ClickHouse-Query-Id: 5abe861c-239c-467f-b955-8a201abb8b7f
-X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0"}
+X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
 
 1
 ```
@@ -286,9 +286,9 @@ Similarly, you can use ClickHouse sessions in the HTTP protocol. To do this, you
 You can receive information about the progress of a query in `X-ClickHouse-Progress` response headers. To do this, enable [send_progress_in_http_headers](../operations/settings/settings.md#settings-send_progress_in_http_headers). Example of the header sequence:
 
 ``` text
-X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128"}
-X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128"}
-X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128"}
+X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","peak_memory_usage":"4371480"}
+X-ClickHouse-Progress: {"read_rows":"5439488","read_bytes":"482285394","total_rows_to_read":"8880128","peak_memory_usage":"13621616"}
+X-ClickHouse-Progress: {"read_rows":"8783786","read_bytes":"819092887","total_rows_to_read":"8880128","peak_memory_usage":"23155600"}
 ```
 
 Possible header fields:
@@ -416,7 +416,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
 < X-ClickHouse-Format: Template
 < X-ClickHouse-Timezone: Asia/Shanghai
 < Keep-Alive: timeout=3
-< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0"}
+< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
 <
 # HELP "Query" "Number of executing queries"
 # TYPE "Query" counter
@@ -581,7 +581,7 @@ $ curl -vv  -H 'XXX:xxx' 'http://localhost:8123/hi'
 < Content-Type: text/html; charset=UTF-8
 < Transfer-Encoding: chunked
 < Keep-Alive: timeout=3
-< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0"}
+< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
 <
 * Connection #0 to host localhost left intact
 Say Hi!%
@@ -621,7 +621,7 @@ $ curl -v  -H 'XXX:xxx' 'http://localhost:8123/get_config_static_handler'
 < Content-Type: text/plain; charset=UTF-8
 < Transfer-Encoding: chunked
 < Keep-Alive: timeout=3
-< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0"}
+< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
 <
 * Connection #0 to host localhost left intact
 <html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>%
@@ -673,7 +673,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_absolute_path_static_handler'
 < Content-Type: text/html; charset=UTF-8
 < Transfer-Encoding: chunked
 < Keep-Alive: timeout=3
-< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0"}
+< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
 <
 <html><body>Absolute Path File</body></html>
 * Connection #0 to host localhost left intact
@@ -692,7 +692,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_relative_path_static_handler'
 < Content-Type: text/html; charset=UTF-8
 < Transfer-Encoding: chunked
 < Keep-Alive: timeout=3
-< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0"}
+< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","peak_memory_usage":"0"}
 <
 <html><body>Relative Path File</body></html>
 * Connection #0 to host localhost left intact

diff --git a/docs/en/operations/configuration-files.md b/docs/en/operations/configuration-files.md
@@ -65,6 +65,40 @@ XML substitution example:
 
 Substitutions can also be performed from ZooKeeper. To do this, specify the attribute `from_zk = "/path/to/node"`. The element value is replaced with the contents of the node at `/path/to/node` in ZooKeeper. You can also put an entire XML subtree on the ZooKeeper node and it will be fully inserted into the source element.
 
+## Encrypting Configuration {#encryption}
+
+You can use symmetric encryption to encrypt a configuration element, for example, a password field. To do so, first configure the [encryption codec](../sql-reference/statements/create/table.md#encryption-codecs), then add attribute `encryption_codec` with the name of the encryption codec as value to the element to encrypt.
+
+Unlike attributes `from_zk`, `from_env` and `incl` (or element `include`), no substitution, i.e. decryption of the encrypted value, is performed in the preprocessed file. Decryption happens only at runtime in the server process.
+
+Example:
+
+```xml
+<clickhouse>
+    <encryption_codecs>
+        <aes_128_gcm_siv>
+            <key_hex>00112233445566778899aabbccddeeff</key_hex>
+        </aes_128_gcm_siv>
+    </encryption_codecs>
+    <interserver_http_credentials>
+        <user>admin</user>
+        <password encryption_codec="AES_128_GCM_SIV">961F000000040000000000EEDDEF4F453CFE6457C4234BD7C09258BD651D85</password>
+    </interserver_http_credentials>
+</clickhouse>
+```
+
+To get the encrypted value `encrypt_decrypt` example application may be used.
+
+Example:
+
+``` bash
+./encrypt_decrypt /etc/clickhouse-server/config.xml -e AES_128_GCM_SIV abcd
+```
+
+``` text
+961F000000040000000000EEDDEF4F453CFE6457C4234BD7C09258BD651D85
+```
+
 ## User Settings {#user-settings}
 
 The `config.xml` file can specify a separate config with user settings, profiles, and quotas. The relative path to this config is set in the `users_config` element. By default, it is `users.xml`. If `users_config` is omitted, the user settings, profiles, and quotas are specified directly in `config.xml`.

diff --git a/docs/en/operations/settings/settings.md b/docs/en/operations/settings/settings.md
@@ -3468,6 +3468,12 @@ Possible values:
 
 Default value: `0`.
 
+## disable_url_encoding {#disable_url_encoding}
+
+Allows to disable decoding/encoding path in uri in [URL](../../engines/table-engines/special/url.md) engine tables.
+
+Disabled by default.
+
 ## database_atomic_wait_for_drop_and_detach_synchronously {#database_atomic_wait_for_drop_and_detach_synchronously}
 
 Adds a modifier `SYNC` to all `DROP` and `DETACH` queries.

diff --git a/docs/en/sql-reference/aggregate-functions/reference/any.md b/docs/en/sql-reference/aggregate-functions/reference/any.md
@@ -12,3 +12,5 @@ To get a determinate result, you can use the ‘min’ or ‘max’ function ins
 In some cases, you can rely on the order of execution. This applies to cases when SELECT comes from a subquery that uses ORDER BY.
 
 When a `SELECT` query has the `GROUP BY` clause or at least one aggregate function, ClickHouse (in contrast to MySQL) requires that all expressions in the `SELECT`, `HAVING`, and `ORDER BY` clauses be calculated from keys or from aggregate functions. In other words, each column selected from the table must be used either in keys or inside aggregate functions. To get behavior like in MySQL, you can put the other columns in the `any` aggregate function.
+
+- Alias: `any_value`