mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-22 23:52:03 +00:00
Merge branch 'master' into fix-packager
This commit is contained in:
Mikhail f. Shiryaev
GitHub
commit
40cdfa2384
@ -8,6 +8,7 @@
|
||||
#include <functional>
|
||||
#include <iosfwd>
|
||||
|
||||
#include <base/defines.h>
|
||||
#include <base/types.h>
|
||||
#include <base/unaligned.h>
|
||||
|
||||
@ -274,6 +275,8 @@ struct CRC32Hash
|
||||
if (size == 0)
|
||||
return 0;
|
||||
|
||||
chassert(pos);
|
||||
|
||||
if (size < 8)
|
||||
{
|
||||
return static_cast<unsigned>(hashLessThan8(x.data, x.size));
|
||||
|
||||
@ -115,8 +115,15 @@
|
||||
/// because SIGABRT is easier to debug than SIGTRAP (the second one makes gdb crazy)
|
||||
#if !defined(chassert)
|
||||
#if defined(ABORT_ON_LOGICAL_ERROR)
|
||||
// clang-format off
|
||||
#include <base/types.h>
|
||||
namespace DB
|
||||
{
|
||||
void abortOnFailedAssertion(const String & description);
|
||||
}
|
||||
#define chassert(x) static_cast<bool>(x) ? void(0) : ::DB::abortOnFailedAssertion(#x)
|
||||
#define UNREACHABLE() abort()
|
||||
// clang-format off
|
||||
#else
|
||||
/// Here sizeof() trick is used to suppress unused warning for result,
|
||||
/// since simple "(void)x" will evaluate the expression, while
|
||||
|
||||
@ -57,7 +57,7 @@ public:
|
||||
URI();
|
||||
/// Creates an empty URI.
|
||||
|
||||
explicit URI(const std::string & uri, bool disable_url_encoding = false);
|
||||
explicit URI(const std::string & uri, bool enable_url_encoding = true);
|
||||
/// Parses an URI from the given string. Throws a
|
||||
/// SyntaxException if the uri is not valid.
|
||||
|
||||
@ -362,7 +362,7 @@ private:
|
||||
std::string _query;
|
||||
std::string _fragment;
|
||||
|
||||
bool _disable_url_encoding = false;
|
||||
bool _enable_url_encoding = true;
|
||||
};
|
||||
|
||||
|
||||
|
||||
@ -36,8 +36,8 @@ URI::URI():
|
||||
}
|
||||
|
||||
|
||||
URI::URI(const std::string& uri, bool decode_and_encode_path):
|
||||
_port(0), _disable_url_encoding(decode_and_encode_path)
|
||||
URI::URI(const std::string& uri, bool enable_url_encoding):
|
||||
_port(0), _enable_url_encoding(enable_url_encoding)
|
||||
{
|
||||
parse(uri);
|
||||
}
|
||||
@ -108,7 +108,7 @@ URI::URI(const URI& uri):
|
||||
_path(uri._path),
|
||||
_query(uri._query),
|
||||
_fragment(uri._fragment),
|
||||
_disable_url_encoding(uri._disable_url_encoding)
|
||||
_enable_url_encoding(uri._enable_url_encoding)
|
||||
{
|
||||
}
|
||||
|
||||
@ -121,7 +121,7 @@ URI::URI(const URI& baseURI, const std::string& relativeURI):
|
||||
_path(baseURI._path),
|
||||
_query(baseURI._query),
|
||||
_fragment(baseURI._fragment),
|
||||
_disable_url_encoding(baseURI._disable_url_encoding)
|
||||
_enable_url_encoding(baseURI._enable_url_encoding)
|
||||
{
|
||||
resolve(relativeURI);
|
||||
}
|
||||
@ -153,7 +153,7 @@ URI& URI::operator = (const URI& uri)
|
||||
_path = uri._path;
|
||||
_query = uri._query;
|
||||
_fragment = uri._fragment;
|
||||
_disable_url_encoding = uri._disable_url_encoding;
|
||||
_enable_url_encoding = uri._enable_url_encoding;
|
||||
}
|
||||
return *this;
|
||||
}
|
||||
@ -184,7 +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);
|
||||
std::swap(_enable_url_encoding, uri._enable_url_encoding);
|
||||
}
|
||||
|
||||
|
||||
@ -687,18 +687,18 @@ 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
|
||||
if (_enable_url_encoding)
|
||||
encode(_path, RESERVED_PATH, encodedStr);
|
||||
else
|
||||
encodedStr = _path;
|
||||
}
|
||||
|
||||
void URI::decodePath(const std::string & encodedStr)
|
||||
{
|
||||
if (_disable_url_encoding)
|
||||
_path = encodedStr;
|
||||
else
|
||||
if (_enable_url_encoding)
|
||||
decode(encodedStr, _path);
|
||||
else
|
||||
_path = encodedStr;
|
||||
}
|
||||
|
||||
bool URI::isWellKnownPort() const
|
||||
|
||||
@ -17,7 +17,8 @@
|
||||
#ifndef METROHASH_PLATFORM_H
|
||||
#define METROHASH_PLATFORM_H
|
||||
|
||||
#include <stdint.h>
|
||||
#include <bit>
|
||||
#include <cstdint>
|
||||
#include <cstring>
|
||||
|
||||
// rotate right idiom recognized by most compilers
|
||||
@ -33,6 +34,11 @@ inline static uint64_t read_u64(const void * const ptr)
|
||||
// so we use memcpy() which is the most portable. clang & gcc usually translates `memcpy()` into a single `load` instruction
|
||||
// when hardware supports it, so using memcpy() is efficient too.
|
||||
memcpy(&result, ptr, sizeof(result));
|
||||
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
result = std::byteswap(result);
|
||||
#endif
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -40,6 +46,11 @@ inline static uint64_t read_u32(const void * const ptr)
|
||||
{
|
||||
uint32_t result;
|
||||
memcpy(&result, ptr, sizeof(result));
|
||||
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
result = std::byteswap(result);
|
||||
#endif
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
@ -47,6 +58,11 @@ inline static uint64_t read_u16(const void * const ptr)
|
||||
{
|
||||
uint16_t result;
|
||||
memcpy(&result, ptr, sizeof(result));
|
||||
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
result = std::byteswap(result);
|
||||
#endif
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
|
||||
@ -95,6 +95,7 @@ RUN python3 -m pip install --no-cache-dir \
|
||||
pytest-timeout \
|
||||
pytest-xdist \
|
||||
pytz \
|
||||
pyyaml==5.3.1 \
|
||||
redis \
|
||||
requests-kerberos \
|
||||
tzlocal==2.1 \
|
||||
|
||||
@ -106,4 +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.
|
||||
- [enable_url_encoding](/docs/en/operations/settings/settings.md#enable_url_encoding) - allows to enable/disable decoding/encoding path in uri. Enabled by default.
|
||||
|
||||
@ -1723,6 +1723,34 @@ You can select data from a ClickHouse table and save them into some file in the
|
||||
``` bash
|
||||
$ clickhouse-client --query = "SELECT * FROM test.hits FORMAT CapnProto SETTINGS format_schema = 'schema:Message'"
|
||||
```
|
||||
|
||||
### Using autogenerated schema {#using-autogenerated-capn-proto-schema}
|
||||
|
||||
If you don't have an external CapnProto schema for your data, you can still output/input data in CapnProto format using autogenerated schema.
|
||||
For example:
|
||||
|
||||
```sql
|
||||
SELECT * FROM test.hits format CapnProto SETTINGS format_capn_proto_use_autogenerated_schema=1
|
||||
```
|
||||
|
||||
In this case ClickHouse will autogenerate CapnProto schema according to the table structure using function [structureToCapnProtoSchema](../sql-reference/functions/other-functions.md#structure_to_capn_proto_schema) and will use this schema to serialize data in CapnProto format.
|
||||
|
||||
You can also read CapnProto file with autogenerated schema (in this case the file must be created using the same schema):
|
||||
|
||||
```bash
|
||||
$ cat hits.bin | clickhouse-client --query "INSERT INTO test.hits SETTINGS format_capn_proto_use_autogenerated_schema=1 FORMAT CapnProto"
|
||||
```
|
||||
|
||||
The setting [format_capn_proto_use_autogenerated_schema](../operations/settings/settings-formats.md#format_capn_proto_use_autogenerated_schema) is enabled by default and applies if [format_schema](../operations/settings/settings-formats.md#formatschema-format-schema) is not set.
|
||||
|
||||
You can also save autogenerated schema in the file during input/output using setting [output_format_schema](../operations/settings/settings-formats.md#outputformatschema-output-format-schema). For example:
|
||||
|
||||
```sql
|
||||
SELECT * FROM test.hits format CapnProto SETTINGS format_capn_proto_use_autogenerated_schema=1, output_format_schema='path/to/schema/schema.capnp'
|
||||
```
|
||||
|
||||
In this case autogenerated CapnProto schema will be saved in file `path/to/schema/schema.capnp`.
|
||||
|
||||
## Prometheus {#prometheus}
|
||||
|
||||
Expose metrics in [Prometheus text-based exposition format](https://prometheus.io/docs/instrumenting/exposition_formats/#text-based-format).
|
||||
@ -1861,6 +1889,33 @@ ClickHouse inputs and outputs protobuf messages in the `length-delimited` format
|
||||
It means before every message should be written its length as a [varint](https://developers.google.com/protocol-buffers/docs/encoding#varints).
|
||||
See also [how to read/write length-delimited protobuf messages in popular languages](https://cwiki.apache.org/confluence/display/GEODE/Delimiting+Protobuf+Messages).
|
||||
|
||||
### Using autogenerated schema {#using-autogenerated-protobuf-schema}
|
||||
|
||||
If you don't have an external Protobuf schema for your data, you can still output/input data in Protobuf format using autogenerated schema.
|
||||
For example:
|
||||
|
||||
```sql
|
||||
SELECT * FROM test.hits format Protobuf SETTINGS format_protobuf_use_autogenerated_schema=1
|
||||
```
|
||||
|
||||
In this case ClickHouse will autogenerate Protobuf schema according to the table structure using function [structureToProtobufSchema](../sql-reference/functions/other-functions.md#structure_to_protobuf_schema) and will use this schema to serialize data in Protobuf format.
|
||||
|
||||
You can also read Protobuf file with autogenerated schema (in this case the file must be created using the same schema):
|
||||
|
||||
```bash
|
||||
$ cat hits.bin | clickhouse-client --query "INSERT INTO test.hits SETTINGS format_protobuf_use_autogenerated_schema=1 FORMAT Protobuf"
|
||||
```
|
||||
|
||||
The setting [format_protobuf_use_autogenerated_schema](../operations/settings/settings-formats.md#format_protobuf_use_autogenerated_schema) is enabled by default and applies if [format_schema](../operations/settings/settings-formats.md#formatschema-format-schema) is not set.
|
||||
|
||||
You can also save autogenerated schema in the file during input/output using setting [output_format_schema](../operations/settings/settings-formats.md#outputformatschema-output-format-schema). For example:
|
||||
|
||||
```sql
|
||||
SELECT * FROM test.hits format Protobuf SETTINGS format_protobuf_use_autogenerated_schema=1, output_format_schema='path/to/schema/schema.proto'
|
||||
```
|
||||
|
||||
In this case autogenerated Protobuf schema will be saved in file `path/to/schema/schema.capnp`.
|
||||
|
||||
## ProtobufSingle {#protobufsingle}
|
||||
|
||||
Same as [Protobuf](#protobuf) but for storing/parsing single Protobuf message without length delimiters.
|
||||
|
||||
@ -0,0 +1,26 @@
|
||||
---
|
||||
slug: /en/operations/optimizing-performance/profile-guided-optimization
|
||||
sidebar_position: 54
|
||||
sidebar_label: Profile Guided Optimization (PGO)
|
||||
---
|
||||
import SelfManaged from '@site/docs/en/_snippets/_self_managed_only_no_roadmap.md';
|
||||
|
||||
# Profile Guided Optimization
|
||||
|
||||
Profile-Guided Optimization (PGO) is a compiler optimization technique where a program is optimized based on the runtime profile.
|
||||
|
||||
According to the tests, PGO helps with achieving better performance for ClickHouse. According to the tests, we see improvements up to 15% in QPS on the ClickBench test suite. The more detailed results are available [here](https://pastebin.com/xbue3HMU). The performance benefits depend on your typical workload - you can get better or worse results.
|
||||
|
||||
More information about PGO in ClickHouse you can read in the corresponding GitHub [issue](https://github.com/ClickHouse/ClickHouse/issues/44567).
|
||||
|
||||
## How to build ClickHouse with PGO?
|
||||
|
||||
There are two major kinds of PGO: [Instrumentation](https://clang.llvm.org/docs/UsersManual.html#using-sampling-profilers) and [Sampling](https://clang.llvm.org/docs/UsersManual.html#using-sampling-profilers) (also known as AutoFDO). In this guide is described the Instrumentation PGO with ClickHouse.
|
||||
|
||||
1. Build ClickHouse in Instrumented mode. In Clang it can be done via passing `-fprofile-instr-generate` option to `CXXFLAGS`.
|
||||
2. Run instrumented ClickHouse on a sample workload. Here you need to use your usual workload. One of the approaches could be using [ClickBench](https://github.com/ClickHouse/ClickBench) as a sample workload. ClickHouse in the instrumentation mode could work slowly so be ready for that and do not run instrumented ClickHouse in performance-critical environments.
|
||||
3. Recompile ClickHouse once again with `-fprofile-instr-use` compiler flags and profiles that are collected from the previous step.
|
||||
|
||||
A more detailed guide on how to apply PGO is in the Clang [documentation](https://clang.llvm.org/docs/UsersManual.html#profile-guided-optimization).
|
||||
|
||||
If you are going to collect a sample workload directly from a production environment, we recommend trying to use Sampling PGO.
|
||||
@ -321,6 +321,10 @@ If both `input_format_allow_errors_num` and `input_format_allow_errors_ratio` ar
|
||||
|
||||
This parameter is useful when you are using formats that require a schema definition, such as [Cap’n Proto](https://capnproto.org/) or [Protobuf](https://developers.google.com/protocol-buffers/). The value depends on the format.
|
||||
|
||||
## output_format_schema {#output-format-schema}
|
||||
|
||||
The path to the file where the automatically generated schema will be saved in [Cap’n Proto](../../interfaces/formats.md#capnproto-capnproto) or [Protobuf](../../interfaces/formats.md#protobuf-protobuf) formats.
|
||||
|
||||
## output_format_enable_streaming {#output_format_enable_streaming}
|
||||
|
||||
Enable streaming in output formats that support it.
|
||||
@ -1330,6 +1334,11 @@ When serializing Nullable columns with Google wrappers, serialize default values
|
||||
|
||||
Disabled by default.
|
||||
|
||||
### format_protobuf_use_autogenerated_schema {#format_capn_proto_use_autogenerated_schema}
|
||||
|
||||
Use autogenerated Protobuf schema when [format_schema](#formatschema-format-schema) is not set.
|
||||
The schema is generated from ClickHouse table structure using function [structureToProtobufSchema](../../sql-reference/functions/other-functions.md#structure_to_protobuf_schema)
|
||||
|
||||
## Avro format settings {#avro-format-settings}
|
||||
|
||||
### input_format_avro_allow_missing_fields {#input_format_avro_allow_missing_fields}
|
||||
@ -1626,6 +1635,11 @@ Possible values:
|
||||
|
||||
Default value: `'by_values'`.
|
||||
|
||||
### format_capn_proto_use_autogenerated_schema {#format_capn_proto_use_autogenerated_schema}
|
||||
|
||||
Use autogenerated CapnProto schema when [format_schema](#formatschema-format-schema) is not set.
|
||||
The schema is generated from ClickHouse table structure using function [structureToCapnProtoSchema](../../sql-reference/functions/other-functions.md#structure_to_capnproto_schema)
|
||||
|
||||
## MySQLDump format settings {#musqldump-format-settings}
|
||||
|
||||
### input_format_mysql_dump_table_name (#input_format_mysql_dump_table_name)
|
||||
|
||||
@ -3468,11 +3468,11 @@ Possible values:
|
||||
|
||||
Default value: `0`.
|
||||
|
||||
## disable_url_encoding {#disable_url_encoding}
|
||||
## enable_url_encoding {#enable_url_encoding}
|
||||
|
||||
Allows to disable decoding/encoding path in uri in [URL](../../engines/table-engines/special/url.md) engine tables.
|
||||
Allows to enable/disable decoding/encoding path in uri in [URL](../../engines/table-engines/special/url.md) engine tables.
|
||||
|
||||
Disabled by default.
|
||||
Enabled by default.
|
||||
|
||||
## database_atomic_wait_for_drop_and_detach_synchronously {#database_atomic_wait_for_drop_and_detach_synchronously}
|
||||
|
||||
@ -4578,3 +4578,28 @@ Type: Int64
|
||||
|
||||
Default: 0
|
||||
|
||||
## precise_float_parsing {#precise_float_parsing}
|
||||
|
||||
Switches [Float32/Float64](../../sql-reference/data-types/float.md) parsing algorithms:
|
||||
* If the value is `1`, then precise method is used. It is slower than fast method, but it always returns a number that is the closest machine representable number to the input.
|
||||
* Otherwise, fast method is used (default). It usually returns the same value as precise, but in rare cases result may differ by one or two least significant digits.
|
||||
|
||||
Possible values: `0`, `1`.
|
||||
|
||||
Default value: `0`.
|
||||
|
||||
Example:
|
||||
|
||||
```sql
|
||||
SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 0;
|
||||
|
||||
┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
|
||||
│ 1.7090999999999998 │ 15008753.000000002 │
|
||||
└─────────────────────┴──────────────────────────┘
|
||||
|
||||
SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 1;
|
||||
|
||||
┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
|
||||
│ 1.7091 │ 15008753 │
|
||||
└─────────────────────┴──────────────────────────┘
|
||||
```
|
||||
|
||||
@ -48,7 +48,7 @@ Columns:
|
||||
- `read_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Total number of rows read from all tables and table functions participated in query. It includes usual subqueries, subqueries for `IN` and `JOIN`. For distributed queries `read_rows` includes the total number of rows read at all replicas. Each replica sends it’s `read_rows` value, and the server-initiator of the query summarizes all received and local values. The cache volumes do not affect this value.
|
||||
- `read_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Total number of bytes read from all tables and table functions participated in query. It includes usual subqueries, subqueries for `IN` and `JOIN`. For distributed queries `read_bytes` includes the total number of rows read at all replicas. Each replica sends it’s `read_bytes` value, and the server-initiator of the query summarizes all received and local values. The cache volumes do not affect this value.
|
||||
- `written_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written rows. For other queries, the column value is 0.
|
||||
- `written_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written bytes. For other queries, the column value is 0.
|
||||
- `written_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written bytes (uncompressed). For other queries, the column value is 0.
|
||||
- `result_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of rows in a result of the `SELECT` query, or a number of rows in the `INSERT` query.
|
||||
- `result_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — RAM volume in bytes used to store a query result.
|
||||
- `memory_usage` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Memory consumption by the query.
|
||||
|
||||
@ -51,3 +51,7 @@ keeper foo bar
|
||||
- `rmr <path>` -- Recursively deletes path. Confirmation required
|
||||
- `flwc <command>` -- Executes four-letter-word command
|
||||
- `help` -- Prints this message
|
||||
- `get_stat [path]` -- Returns the node's stat (default `.`)
|
||||
- `find_super_nodes <threshold> [path]` -- Finds nodes with number of children larger than some threshold for the given path (default `.`)
|
||||
- `delete_stable_backups` -- Deletes ClickHouse nodes used for backups that are now inactive
|
||||
- `find_big_family [path] [n]` -- Returns the top n nodes with the biggest family in the subtree (default path = `.` and n = 10)
|
||||
|
||||
@ -2552,3 +2552,187 @@ Result:
|
||||
|
||||
This function can be used together with [generateRandom](../../sql-reference/table-functions/generate.md) to generate completely random tables.
|
||||
|
||||
## structureToCapnProtoSchema {#structure_to_capn_proto_schema}
|
||||
|
||||
Converts ClickHouse table structure to CapnProto schema.
|
||||
|
||||
**Syntax**
|
||||
|
||||
``` sql
|
||||
structureToCapnProtoSchema(structure)
|
||||
```
|
||||
|
||||
**Arguments**
|
||||
|
||||
- `structure` — Table structure in a format `column1_name column1_type, column2_name column2_type, ...`.
|
||||
- `root_struct_name` — Name for root struct in CapnProto schema. Default value - `Message`;
|
||||
|
||||
**Returned value**
|
||||
|
||||
- CapnProto schema
|
||||
|
||||
Type: [String](../../sql-reference/data-types/string.md).
|
||||
|
||||
**Examples**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT structureToCapnProtoSchema('column1 String, column2 UInt32, column3 Array(String)') FORMAT RawBLOB
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
@0xf96402dd754d0eb7;
|
||||
|
||||
struct Message
|
||||
{
|
||||
column1 @0 : Data;
|
||||
column2 @1 : UInt32;
|
||||
column3 @2 : List(Data);
|
||||
}
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT structureToCapnProtoSchema('column1 Nullable(String), column2 Tuple(element1 UInt32, element2 Array(String)), column3 Map(String, String)') FORMAT RawBLOB
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
@0xd1c8320fecad2b7f;
|
||||
|
||||
struct Message
|
||||
{
|
||||
struct Column1
|
||||
{
|
||||
union
|
||||
{
|
||||
value @0 : Data;
|
||||
null @1 : Void;
|
||||
}
|
||||
}
|
||||
column1 @0 : Column1;
|
||||
struct Column2
|
||||
{
|
||||
element1 @0 : UInt32;
|
||||
element2 @1 : List(Data);
|
||||
}
|
||||
column2 @1 : Column2;
|
||||
struct Column3
|
||||
{
|
||||
struct Entry
|
||||
{
|
||||
key @0 : Data;
|
||||
value @1 : Data;
|
||||
}
|
||||
entries @0 : List(Entry);
|
||||
}
|
||||
column3 @2 : Column3;
|
||||
}
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT structureToCapnProtoSchema('column1 String, column2 UInt32', 'Root') FORMAT RawBLOB
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
@0x96ab2d4ab133c6e1;
|
||||
|
||||
struct Root
|
||||
{
|
||||
column1 @0 : Data;
|
||||
column2 @1 : UInt32;
|
||||
}
|
||||
```
|
||||
|
||||
## structureToProtobufSchema {#structure_to_protobuf_schema}
|
||||
|
||||
Converts ClickHouse table structure to Protobuf schema.
|
||||
|
||||
**Syntax**
|
||||
|
||||
``` sql
|
||||
structureToProtobufSchema(structure)
|
||||
```
|
||||
|
||||
**Arguments**
|
||||
|
||||
- `structure` — Table structure in a format `column1_name column1_type, column2_name column2_type, ...`.
|
||||
- `root_message_name` — Name for root message in Protobuf schema. Default value - `Message`;
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Protobuf schema
|
||||
|
||||
Type: [String](../../sql-reference/data-types/string.md).
|
||||
|
||||
**Examples**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT structureToProtobufSchema('column1 String, column2 UInt32, column3 Array(String)') FORMAT RawBLOB
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
syntax = "proto3";
|
||||
|
||||
message Message
|
||||
{
|
||||
bytes column1 = 1;
|
||||
uint32 column2 = 2;
|
||||
repeated bytes column3 = 3;
|
||||
}
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT structureToProtobufSchema('column1 Nullable(String), column2 Tuple(element1 UInt32, element2 Array(String)), column3 Map(String, String)') FORMAT RawBLOB
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
syntax = "proto3";
|
||||
|
||||
message Message
|
||||
{
|
||||
bytes column1 = 1;
|
||||
message Column2
|
||||
{
|
||||
uint32 element1 = 1;
|
||||
repeated bytes element2 = 2;
|
||||
}
|
||||
Column2 column2 = 2;
|
||||
map<string, bytes> column3 = 3;
|
||||
}
|
||||
```
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT structureToProtobufSchema('column1 String, column2 UInt32', 'Root') FORMAT RawBLOB
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
syntax = "proto3";
|
||||
|
||||
message Root
|
||||
{
|
||||
bytes column1 = 1;
|
||||
uint32 column2 = 2;
|
||||
}
|
||||
```
|
||||
|
||||
@ -56,7 +56,7 @@ Character `|` inside patterns is used to specify failover addresses. They are it
|
||||
## 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.
|
||||
- [enable_url_encoding](/docs/en/operations/settings/settings.md#enable_url_encoding) - allows to enable/disable decoding/encoding path in uri. Enabled by default.
|
||||
|
||||
**See Also**
|
||||
|
||||
|
||||
@ -4213,3 +4213,29 @@ SELECT *, timezone() FROM test_tz WHERE d = '2000-01-01 00:00:00' SETTINGS sessi
|
||||
- Запрос: `SELECT * FROM file('sample.csv')`
|
||||
|
||||
Если чтение и обработка `sample.csv` прошли успешно, файл будет переименован в `processed_sample_1683473210851438.csv`.
|
||||
|
||||
## precise_float_parsing {#precise_float_parsing}
|
||||
|
||||
Позволяет выбрать алгоритм, используемый при парсинге [Float32/Float64](../../sql-reference/data-types/float.md):
|
||||
* Если установлено значение `1`, то используется точный метод. Он более медленный, но всегда возвращает число, наиболее близкое к входному значению.
|
||||
* В противном случае используется быстрый метод (поведение по умолчанию). Обычно результат его работы совпадает с результатом, полученным точным методом, однако в редких случаях он может отличаться на 1 или 2 наименее значимых цифры.
|
||||
|
||||
Возможные значения: `0`, `1`.
|
||||
|
||||
Значение по умолчанию: `0`.
|
||||
|
||||
Пример:
|
||||
|
||||
```sql
|
||||
SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 0;
|
||||
|
||||
┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
|
||||
│ 1.7090999999999998 │ 15008753.000000002 │
|
||||
└─────────────────────┴──────────────────────────┘
|
||||
|
||||
SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 1;
|
||||
|
||||
┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
|
||||
│ 1.7091 │ 15008753 │
|
||||
└─────────────────────┴──────────────────────────┘
|
||||
```
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
|
||||
#include "Commands.h"
|
||||
#include <queue>
|
||||
#include "KeeperClient.h"
|
||||
|
||||
|
||||
@ -24,8 +25,18 @@ void LSCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) con
|
||||
else
|
||||
path = client->cwd;
|
||||
|
||||
for (const auto & child : client->zookeeper->getChildren(path))
|
||||
std::cout << child << " ";
|
||||
auto children = client->zookeeper->getChildren(path);
|
||||
std::sort(children.begin(), children.end());
|
||||
|
||||
bool need_space = false;
|
||||
for (const auto & child : children)
|
||||
{
|
||||
if (std::exchange(need_space, true))
|
||||
std::cout << " ";
|
||||
|
||||
std::cout << child;
|
||||
}
|
||||
|
||||
std::cout << "\n";
|
||||
}
|
||||
|
||||
@ -130,6 +141,173 @@ void GetCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) co
|
||||
std::cout << client->zookeeper->get(client->getAbsolutePath(query->args[0].safeGet<String>())) << "\n";
|
||||
}
|
||||
|
||||
bool GetStatCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
|
||||
{
|
||||
String arg;
|
||||
if (!parseKeeperPath(pos, expected, arg))
|
||||
return true;
|
||||
|
||||
node->args.push_back(std::move(arg));
|
||||
return true;
|
||||
}
|
||||
|
||||
void GetStatCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) const
|
||||
{
|
||||
Coordination::Stat stat;
|
||||
String path;
|
||||
if (!query->args.empty())
|
||||
path = client->getAbsolutePath(query->args[0].safeGet<String>());
|
||||
else
|
||||
path = client->cwd;
|
||||
|
||||
client->zookeeper->get(path, &stat);
|
||||
|
||||
std::cout << "cZxid = " << stat.czxid << "\n";
|
||||
std::cout << "mZxid = " << stat.mzxid << "\n";
|
||||
std::cout << "pZxid = " << stat.pzxid << "\n";
|
||||
std::cout << "ctime = " << stat.ctime << "\n";
|
||||
std::cout << "mtime = " << stat.mtime << "\n";
|
||||
std::cout << "version = " << stat.version << "\n";
|
||||
std::cout << "cversion = " << stat.cversion << "\n";
|
||||
std::cout << "aversion = " << stat.aversion << "\n";
|
||||
std::cout << "ephemeralOwner = " << stat.ephemeralOwner << "\n";
|
||||
std::cout << "dataLength = " << stat.dataLength << "\n";
|
||||
std::cout << "numChildren = " << stat.numChildren << "\n";
|
||||
}
|
||||
|
||||
bool FindSuperNodes::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
|
||||
{
|
||||
ASTPtr threshold;
|
||||
if (!ParserUnsignedInteger{}.parse(pos, threshold, expected))
|
||||
return false;
|
||||
|
||||
node->args.push_back(threshold->as<ASTLiteral &>().value);
|
||||
|
||||
String path;
|
||||
if (!parseKeeperPath(pos, expected, path))
|
||||
path = ".";
|
||||
|
||||
node->args.push_back(std::move(path));
|
||||
return true;
|
||||
}
|
||||
|
||||
void FindSuperNodes::execute(const ASTKeeperQuery * query, KeeperClient * client) const
|
||||
{
|
||||
auto threshold = query->args[0].safeGet<UInt64>();
|
||||
auto path = client->getAbsolutePath(query->args[1].safeGet<String>());
|
||||
|
||||
Coordination::Stat stat;
|
||||
client->zookeeper->get(path, &stat);
|
||||
|
||||
if (stat.numChildren >= static_cast<Int32>(threshold))
|
||||
{
|
||||
std::cout << static_cast<String>(path) << "\t" << stat.numChildren << "\n";
|
||||
return;
|
||||
}
|
||||
|
||||
auto children = client->zookeeper->getChildren(path);
|
||||
std::sort(children.begin(), children.end());
|
||||
for (const auto & child : children)
|
||||
{
|
||||
auto next_query = *query;
|
||||
next_query.args[1] = DB::Field(path / child);
|
||||
execute(&next_query, client);
|
||||
}
|
||||
}
|
||||
|
||||
bool DeleteStableBackups::parse(IParser::Pos & /* pos */, std::shared_ptr<ASTKeeperQuery> & /* node */, Expected & /* expected */) const
|
||||
{
|
||||
return true;
|
||||
}
|
||||
|
||||
void DeleteStableBackups::execute(const ASTKeeperQuery * /* query */, KeeperClient * client) const
|
||||
{
|
||||
client->askConfirmation(
|
||||
"You are going to delete all inactive backups in /clickhouse/backups.",
|
||||
[client]
|
||||
{
|
||||
fs::path backup_root = "/clickhouse/backups";
|
||||
auto backups = client->zookeeper->getChildren(backup_root);
|
||||
std::sort(backups.begin(), backups.end());
|
||||
|
||||
for (const auto & child : backups)
|
||||
{
|
||||
auto backup_path = backup_root / child;
|
||||
std::cout << "Found backup " << backup_path << ", checking if it's active\n";
|
||||
|
||||
String stage_path = backup_path / "stage";
|
||||
auto stages = client->zookeeper->getChildren(stage_path);
|
||||
|
||||
bool is_active = false;
|
||||
for (const auto & stage : stages)
|
||||
{
|
||||
if (startsWith(stage, "alive"))
|
||||
{
|
||||
is_active = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (is_active)
|
||||
{
|
||||
std::cout << "Backup " << backup_path << " is active, not going to delete\n";
|
||||
continue;
|
||||
}
|
||||
|
||||
std::cout << "Backup " << backup_path << " is not active, deleting it\n";
|
||||
client->zookeeper->removeRecursive(backup_path);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
bool FindBigFamily::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
|
||||
{
|
||||
String path;
|
||||
if (!parseKeeperPath(pos, expected, path))
|
||||
path = ".";
|
||||
|
||||
node->args.push_back(std::move(path));
|
||||
|
||||
ASTPtr count;
|
||||
if (ParserUnsignedInteger{}.parse(pos, count, expected))
|
||||
node->args.push_back(count->as<ASTLiteral &>().value);
|
||||
else
|
||||
node->args.push_back(UInt64(10));
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
void FindBigFamily::execute(const ASTKeeperQuery * query, KeeperClient * client) const
|
||||
{
|
||||
auto path = client->getAbsolutePath(query->args[0].safeGet<String>());
|
||||
auto n = query->args[1].safeGet<UInt64>();
|
||||
|
||||
std::vector<std::tuple<Int32, String>> result;
|
||||
|
||||
std::queue<fs::path> queue;
|
||||
queue.push(path);
|
||||
while (!queue.empty())
|
||||
{
|
||||
auto next_path = queue.front();
|
||||
queue.pop();
|
||||
|
||||
auto children = client->zookeeper->getChildren(next_path);
|
||||
std::transform(children.cbegin(), children.cend(), children.begin(), [&](const String & child) { return next_path / child; });
|
||||
|
||||
auto response = client->zookeeper->get(children);
|
||||
|
||||
for (size_t i = 0; i < response.size(); ++i)
|
||||
{
|
||||
result.emplace_back(response[i].stat.numChildren, children[i]);
|
||||
queue.push(children[i]);
|
||||
}
|
||||
}
|
||||
|
||||
std::sort(result.begin(), result.end(), std::greater());
|
||||
for (UInt64 i = 0; i < std::min(result.size(), static_cast<size_t>(n)); ++i)
|
||||
std::cout << std::get<1>(result[i]) << "\t" << std::get<0>(result[i]) << "\n";
|
||||
}
|
||||
|
||||
bool RMCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
|
||||
{
|
||||
String arg;
|
||||
@ -170,7 +348,7 @@ bool HelpCommand::parse(IParser::Pos & /* pos */, std::shared_ptr<ASTKeeperQuery
|
||||
void HelpCommand::execute(const ASTKeeperQuery * /* query */, KeeperClient * /* client */) const
|
||||
{
|
||||
for (const auto & pair : KeeperClient::commands)
|
||||
std::cout << pair.second->getHelpMessage() << "\n";
|
||||
std::cout << pair.second->generateHelpString() << "\n";
|
||||
}
|
||||
|
||||
bool FourLetterWordCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
|
||||
|
||||
@ -21,6 +21,12 @@ public:
|
||||
virtual String getName() const = 0;
|
||||
|
||||
virtual ~IKeeperClientCommand() = default;
|
||||
|
||||
String generateHelpString() const
|
||||
{
|
||||
return fmt::vformat(getHelpMessage(), fmt::make_format_args(getName()));
|
||||
}
|
||||
|
||||
};
|
||||
|
||||
using Command = std::shared_ptr<IKeeperClientCommand>;
|
||||
@ -34,7 +40,7 @@ class LSCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "ls [path] -- Lists the nodes for the given path (default: cwd)"; }
|
||||
String getHelpMessage() const override { return "{} [path] -- Lists the nodes for the given path (default: cwd)"; }
|
||||
};
|
||||
|
||||
class CDCommand : public IKeeperClientCommand
|
||||
@ -45,7 +51,7 @@ class CDCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "cd [path] -- Change the working path (default `.`)"; }
|
||||
String getHelpMessage() const override { return "{} [path] -- Change the working path (default `.`)"; }
|
||||
};
|
||||
|
||||
class SetCommand : public IKeeperClientCommand
|
||||
@ -58,7 +64,7 @@ class SetCommand : public IKeeperClientCommand
|
||||
|
||||
String getHelpMessage() const override
|
||||
{
|
||||
return "set <path> <value> [version] -- Updates the node's value. Only update if version matches (default: -1)";
|
||||
return "{} <path> <value> [version] -- Updates the node's value. Only update if version matches (default: -1)";
|
||||
}
|
||||
};
|
||||
|
||||
@ -70,7 +76,7 @@ class CreateCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "create <path> <value> -- Creates new node"; }
|
||||
String getHelpMessage() const override { return "{} <path> <value> -- Creates new node"; }
|
||||
};
|
||||
|
||||
class GetCommand : public IKeeperClientCommand
|
||||
@ -81,9 +87,63 @@ class GetCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "get <path> -- Returns the node's value"; }
|
||||
String getHelpMessage() const override { return "{} <path> -- Returns the node's value"; }
|
||||
};
|
||||
|
||||
class GetStatCommand : public IKeeperClientCommand
|
||||
{
|
||||
String getName() const override { return "get_stat"; }
|
||||
|
||||
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "{} [path] -- Returns the node's stat (default `.`)"; }
|
||||
};
|
||||
|
||||
class FindSuperNodes : public IKeeperClientCommand
|
||||
{
|
||||
String getName() const override { return "find_super_nodes"; }
|
||||
|
||||
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override
|
||||
{
|
||||
return "{} <threshold> [path] -- Finds nodes with number of children larger than some threshold for the given path (default `.`)";
|
||||
}
|
||||
};
|
||||
|
||||
class DeleteStableBackups : public IKeeperClientCommand
|
||||
{
|
||||
String getName() const override { return "delete_stable_backups"; }
|
||||
|
||||
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override
|
||||
{
|
||||
return "{} -- Deletes ClickHouse nodes used for backups that are now inactive";
|
||||
}
|
||||
};
|
||||
|
||||
class FindBigFamily : public IKeeperClientCommand
|
||||
{
|
||||
String getName() const override { return "find_big_family"; }
|
||||
|
||||
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override
|
||||
{
|
||||
return "{} [path] [n] -- Returns the top n nodes with the biggest family in the subtree (default path = `.` and n = 10)";
|
||||
}
|
||||
};
|
||||
|
||||
|
||||
class RMCommand : public IKeeperClientCommand
|
||||
{
|
||||
String getName() const override { return "rm"; }
|
||||
@ -92,7 +152,7 @@ class RMCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "remove <path> -- Remove the node"; }
|
||||
String getHelpMessage() const override { return "{} <path> -- Remove the node"; }
|
||||
};
|
||||
|
||||
class RMRCommand : public IKeeperClientCommand
|
||||
@ -103,7 +163,7 @@ class RMRCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "rmr <path> -- Recursively deletes path. Confirmation required"; }
|
||||
String getHelpMessage() const override { return "{} <path> -- Recursively deletes path. Confirmation required"; }
|
||||
};
|
||||
|
||||
class HelpCommand : public IKeeperClientCommand
|
||||
@ -114,7 +174,7 @@ class HelpCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "help -- Prints this message"; }
|
||||
String getHelpMessage() const override { return "{} -- Prints this message"; }
|
||||
};
|
||||
|
||||
class FourLetterWordCommand : public IKeeperClientCommand
|
||||
@ -125,7 +185,7 @@ class FourLetterWordCommand : public IKeeperClientCommand
|
||||
|
||||
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
|
||||
|
||||
String getHelpMessage() const override { return "flwc <command> -- Executes four-letter-word command"; }
|
||||
String getHelpMessage() const override { return "{} <command> -- Executes four-letter-word command"; }
|
||||
};
|
||||
|
||||
}
|
||||
|
||||
@ -177,6 +177,10 @@ void KeeperClient::initialize(Poco::Util::Application & /* self */)
|
||||
std::make_shared<SetCommand>(),
|
||||
std::make_shared<CreateCommand>(),
|
||||
std::make_shared<GetCommand>(),
|
||||
std::make_shared<GetStatCommand>(),
|
||||
std::make_shared<FindSuperNodes>(),
|
||||
std::make_shared<DeleteStableBackups>(),
|
||||
std::make_shared<FindBigFamily>(),
|
||||
std::make_shared<RMCommand>(),
|
||||
std::make_shared<RMRCommand>(),
|
||||
std::make_shared<HelpCommand>(),
|
||||
|
||||
@ -58,6 +58,7 @@ bool KeeperParser::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
|
||||
return false;
|
||||
|
||||
String command_name(pos->begin, pos->end);
|
||||
std::transform(command_name.begin(), command_name.end(), command_name.begin(), [](unsigned char c) { return std::tolower(c); });
|
||||
Command command;
|
||||
|
||||
auto iter = KeeperClient::commands.find(command_name);
|
||||
|
||||
@ -0,0 +1,221 @@
|
||||
#include <Analyzer/Passes/OptimizeDateOrDateTimeConverterWithPreimagePass.h>
|
||||
|
||||
#include <Functions/FunctionFactory.h>
|
||||
|
||||
#include <Analyzer/InDepthQueryTreeVisitor.h>
|
||||
#include <Analyzer/ColumnNode.h>
|
||||
#include <Analyzer/ConstantNode.h>
|
||||
#include <Analyzer/FunctionNode.h>
|
||||
#include <Common/DateLUT.h>
|
||||
#include <Common/DateLUTImpl.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int LOGICAL_ERROR;
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
|
||||
class OptimizeDateOrDateTimeConverterWithPreimageVisitor : public InDepthQueryTreeVisitorWithContext<OptimizeDateOrDateTimeConverterWithPreimageVisitor>
|
||||
{
|
||||
public:
|
||||
using Base = InDepthQueryTreeVisitorWithContext<OptimizeDateOrDateTimeConverterWithPreimageVisitor>;
|
||||
|
||||
explicit OptimizeDateOrDateTimeConverterWithPreimageVisitor(ContextPtr context)
|
||||
: Base(std::move(context))
|
||||
{}
|
||||
|
||||
static bool needChildVisit(QueryTreeNodePtr & node, QueryTreeNodePtr & /*child*/)
|
||||
{
|
||||
const static std::unordered_set<String> relations = {
|
||||
"equals",
|
||||
"notEquals",
|
||||
"less",
|
||||
"greater",
|
||||
"lessOrEquals",
|
||||
"greaterOrEquals",
|
||||
};
|
||||
|
||||
if (const auto * function = node->as<FunctionNode>())
|
||||
{
|
||||
return !relations.contains(function->getFunctionName());
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
void enterImpl(QueryTreeNodePtr & node) const
|
||||
{
|
||||
const static std::unordered_map<String, String> swap_relations = {
|
||||
{"equals", "equals"},
|
||||
{"notEquals", "notEquals"},
|
||||
{"less", "greater"},
|
||||
{"greater", "less"},
|
||||
{"lessOrEquals", "greaterOrEquals"},
|
||||
{"greaterOrEquals", "lessOrEquals"},
|
||||
};
|
||||
|
||||
const auto * function = node->as<FunctionNode>();
|
||||
|
||||
if (!function || !swap_relations.contains(function->getFunctionName())) return;
|
||||
|
||||
if (function->getArguments().getNodes().size() != 2) return;
|
||||
|
||||
size_t func_id = function->getArguments().getNodes().size();
|
||||
|
||||
for (size_t i = 0; i < function->getArguments().getNodes().size(); i++)
|
||||
{
|
||||
if (const auto * func = function->getArguments().getNodes()[i]->as<FunctionNode>())
|
||||
{
|
||||
func_id = i;
|
||||
}
|
||||
}
|
||||
|
||||
if (func_id == function->getArguments().getNodes().size()) return;
|
||||
|
||||
size_t literal_id = 1 - func_id;
|
||||
const auto * literal = function->getArguments().getNodes()[literal_id]->as<ConstantNode>();
|
||||
|
||||
if (!literal || literal->getValue().getType() != Field::Types::UInt64) return;
|
||||
|
||||
String comparator = literal_id > func_id ? function->getFunctionName(): swap_relations.at(function->getFunctionName());
|
||||
|
||||
const auto * func_node = function->getArguments().getNodes()[func_id]->as<FunctionNode>();
|
||||
/// Currently we only handle single-argument functions.
|
||||
if (!func_node || func_node->getArguments().getNodes().size() != 1) return;
|
||||
|
||||
const auto * column_id = func_node->getArguments().getNodes()[0]->as<ColumnNode>();
|
||||
if (!column_id) return;
|
||||
|
||||
const auto * column_type = column_id->getColumnType().get();
|
||||
if (!isDateOrDate32(column_type) && !isDateTime(column_type) && !isDateTime64(column_type)) return;
|
||||
|
||||
const auto & converter = FunctionFactory::instance().tryGet(func_node->getFunctionName(), getContext());
|
||||
if (!converter) return;
|
||||
|
||||
ColumnsWithTypeAndName args;
|
||||
args.emplace_back(column_id->getColumnType(), "tmp");
|
||||
auto converter_base = converter->build(args);
|
||||
if (!converter_base || !converter_base->hasInformationAboutPreimage()) return;
|
||||
|
||||
auto preimage_range = converter_base->getPreimage(*(column_id->getColumnType()), literal->getValue());
|
||||
if (!preimage_range) return;
|
||||
|
||||
const auto new_node = generateOptimizedDateFilter(comparator, *column_id, *preimage_range);
|
||||
|
||||
if (!new_node) return;
|
||||
|
||||
node = new_node;
|
||||
}
|
||||
|
||||
private:
|
||||
QueryTreeNodePtr generateOptimizedDateFilter(const String & comparator, const ColumnNode & column_node, const std::pair<Field, Field>& range) const
|
||||
{
|
||||
const DateLUTImpl & date_lut = DateLUT::instance("UTC");
|
||||
|
||||
String start_date_or_date_time;
|
||||
String end_date_or_date_time;
|
||||
|
||||
if (isDateOrDate32(column_node.getColumnType().get()))
|
||||
{
|
||||
start_date_or_date_time = date_lut.dateToString(range.first.get<DateLUTImpl::Time>());
|
||||
end_date_or_date_time = date_lut.dateToString(range.second.get<DateLUTImpl::Time>());
|
||||
}
|
||||
else if (isDateTime(column_node.getColumnType().get()) || isDateTime64(column_node.getColumnType().get()))
|
||||
{
|
||||
start_date_or_date_time = date_lut.timeToString(range.first.get<DateLUTImpl::Time>());
|
||||
end_date_or_date_time = date_lut.timeToString(range.second.get<DateLUTImpl::Time>());
|
||||
}
|
||||
else [[unlikely]] return {};
|
||||
|
||||
if (comparator == "equals")
|
||||
{
|
||||
const auto lhs = std::make_shared<FunctionNode>("greaterOrEquals");
|
||||
lhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
|
||||
lhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(start_date_or_date_time));
|
||||
resolveOrdinaryFunctionNode(*lhs, lhs->getFunctionName());
|
||||
|
||||
const auto rhs = std::make_shared<FunctionNode>("less");
|
||||
rhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
|
||||
rhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
|
||||
resolveOrdinaryFunctionNode(*rhs, rhs->getFunctionName());
|
||||
|
||||
const auto new_date_filter = std::make_shared<FunctionNode>("and");
|
||||
new_date_filter->getArguments().getNodes() = {lhs, rhs};
|
||||
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
|
||||
|
||||
return new_date_filter;
|
||||
}
|
||||
else if (comparator == "notEquals")
|
||||
{
|
||||
const auto lhs = std::make_shared<FunctionNode>("less");
|
||||
lhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
|
||||
lhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(start_date_or_date_time));
|
||||
resolveOrdinaryFunctionNode(*lhs, lhs->getFunctionName());
|
||||
|
||||
const auto rhs = std::make_shared<FunctionNode>("greaterOrEquals");
|
||||
rhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
|
||||
rhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
|
||||
resolveOrdinaryFunctionNode(*rhs, rhs->getFunctionName());
|
||||
|
||||
const auto new_date_filter = std::make_shared<FunctionNode>("or");
|
||||
new_date_filter->getArguments().getNodes() = {lhs, rhs};
|
||||
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
|
||||
|
||||
return new_date_filter;
|
||||
}
|
||||
else if (comparator == "greater")
|
||||
{
|
||||
const auto new_date_filter = std::make_shared<FunctionNode>("greaterOrEquals");
|
||||
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
|
||||
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
|
||||
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
|
||||
|
||||
return new_date_filter;
|
||||
}
|
||||
else if (comparator == "lessOrEquals")
|
||||
{
|
||||
const auto new_date_filter = std::make_shared<FunctionNode>("less");
|
||||
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
|
||||
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
|
||||
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
|
||||
|
||||
return new_date_filter;
|
||||
}
|
||||
else if (comparator == "less" || comparator == "greaterOrEquals")
|
||||
{
|
||||
const auto new_date_filter = std::make_shared<FunctionNode>(comparator);
|
||||
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
|
||||
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(start_date_or_date_time));
|
||||
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
|
||||
|
||||
return new_date_filter;
|
||||
}
|
||||
else [[unlikely]]
|
||||
{
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR,
|
||||
"Expected equals, notEquals, less, lessOrEquals, greater, greaterOrEquals. Actual {}",
|
||||
comparator);
|
||||
}
|
||||
}
|
||||
|
||||
void resolveOrdinaryFunctionNode(FunctionNode & function_node, const String & function_name) const
|
||||
{
|
||||
auto function = FunctionFactory::instance().get(function_name, getContext());
|
||||
function_node.resolveAsFunction(function->build(function_node.getArgumentColumns()));
|
||||
}
|
||||
};
|
||||
|
||||
}
|
||||
|
||||
void OptimizeDateOrDateTimeConverterWithPreimagePass::run(QueryTreeNodePtr query_tree_node, ContextPtr context)
|
||||
{
|
||||
OptimizeDateOrDateTimeConverterWithPreimageVisitor visitor(std::move(context));
|
||||
visitor.visit(query_tree_node);
|
||||
}
|
||||
|
||||
}
|
||||
@ -0,0 +1,24 @@
|
||||
#pragma once
|
||||
|
||||
#include <Analyzer/IQueryTreePass.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
/** Replace predicate having Date/DateTime converters with their preimages to improve performance.
|
||||
* Given a Date column c, toYear(c) = 2023 -> c >= '2023-01-01' AND c < '2024-01-01'
|
||||
* Or if c is a DateTime column, toYear(c) = 2023 -> c >= '2023-01-01 00:00:00' AND c < '2024-01-01 00:00:00'.
|
||||
* The similar optimization also applies to other converters.
|
||||
*/
|
||||
class OptimizeDateOrDateTimeConverterWithPreimagePass final : public IQueryTreePass
|
||||
{
|
||||
public:
|
||||
String getName() override { return "OptimizeDateOrDateTimeConverterWithPreimagePass"; }
|
||||
|
||||
String getDescription() override { return "Replace predicate having Date/DateTime converters with their preimages"; }
|
||||
|
||||
void run(QueryTreeNodePtr query_tree_node, ContextPtr context) override;
|
||||
|
||||
};
|
||||
|
||||
}
|
||||
@ -42,6 +42,7 @@
|
||||
#include <Analyzer/Passes/CrossToInnerJoinPass.h>
|
||||
#include <Analyzer/Passes/ShardNumColumnToFunctionPass.h>
|
||||
#include <Analyzer/Passes/ConvertQueryToCNFPass.h>
|
||||
#include <Analyzer/Passes/OptimizeDateOrDateTimeConverterWithPreimagePass.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -278,6 +279,7 @@ void addQueryTreePasses(QueryTreePassManager & manager)
|
||||
manager.addPass(std::make_unique<AutoFinalOnQueryPass>());
|
||||
manager.addPass(std::make_unique<CrossToInnerJoinPass>());
|
||||
manager.addPass(std::make_unique<ShardNumColumnToFunctionPass>());
|
||||
manager.addPass(std::make_unique<OptimizeDateOrDateTimeConverterWithPreimagePass>());
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@ -564,15 +564,22 @@ void ColumnNullable::updatePermutationImpl(IColumn::PermutationSortDirection dir
|
||||
else
|
||||
getNestedColumn().updatePermutation(direction, stability, limit, null_direction_hint, res, new_ranges);
|
||||
|
||||
equal_ranges = std::move(new_ranges);
|
||||
|
||||
if (unlikely(stability == PermutationSortStability::Stable))
|
||||
{
|
||||
for (auto & null_range : null_ranges)
|
||||
::sort(res.begin() + null_range.first, res.begin() + null_range.second);
|
||||
}
|
||||
|
||||
std::move(null_ranges.begin(), null_ranges.end(), std::back_inserter(equal_ranges));
|
||||
if (is_nulls_last || null_ranges.empty())
|
||||
{
|
||||
equal_ranges = std::move(new_ranges);
|
||||
std::move(null_ranges.begin(), null_ranges.end(), std::back_inserter(equal_ranges));
|
||||
}
|
||||
else
|
||||
{
|
||||
equal_ranges = std::move(null_ranges);
|
||||
std::move(new_ranges.begin(), new_ranges.end(), std::back_inserter(equal_ranges));
|
||||
}
|
||||
}
|
||||
|
||||
void ColumnNullable::getPermutation(IColumn::PermutationSortDirection direction, IColumn::PermutationSortStability stability,
|
||||
|
||||
@ -439,7 +439,7 @@ void ColumnSparse::compareColumn(const IColumn & rhs, size_t rhs_row_num,
|
||||
PaddedPODArray<UInt64> * row_indexes, PaddedPODArray<Int8> & compare_results,
|
||||
int direction, int nan_direction_hint) const
|
||||
{
|
||||
if (row_indexes)
|
||||
if (row_indexes || !typeid_cast<const ColumnSparse *>(&rhs))
|
||||
{
|
||||
/// TODO: implement without conversion to full column.
|
||||
auto this_full = convertToFullColumnIfSparse();
|
||||
|
||||
@ -45,6 +45,25 @@ size_t shortest_literal_length(const Literals & literals)
|
||||
return shortest;
|
||||
}
|
||||
|
||||
const char * skipNameCapturingGroup(const char * pos, size_t offset, const char * end)
|
||||
{
|
||||
const char special = *(pos + offset) == '<' ? '>' : '\'';
|
||||
offset ++;
|
||||
while (pos + offset < end)
|
||||
{
|
||||
const char cur = *(pos + offset);
|
||||
if (cur == special)
|
||||
{
|
||||
return pos + offset;
|
||||
}
|
||||
if (('0' <= cur && cur <= '9') || ('a' <= cur && cur <= 'z') || ('A' <= cur && cur <= 'Z'))
|
||||
offset ++;
|
||||
else
|
||||
return pos;
|
||||
}
|
||||
return pos;
|
||||
}
|
||||
|
||||
const char * analyzeImpl(
|
||||
std::string_view regexp,
|
||||
const char * pos,
|
||||
@ -247,10 +266,15 @@ const char * analyzeImpl(
|
||||
break;
|
||||
}
|
||||
}
|
||||
/// (?:regex) means non-capturing parentheses group
|
||||
if (pos + 2 < end && pos[1] == '?' && pos[2] == ':')
|
||||
{
|
||||
pos += 2;
|
||||
}
|
||||
if (pos + 3 < end && pos[1] == '?' && (pos[2] == '<' || pos[2] == '\'' || (pos[2] == 'P' && pos[3] == '<')))
|
||||
{
|
||||
pos = skipNameCapturingGroup(pos, pos[2] == 'P' ? 3: 2, end);
|
||||
}
|
||||
Literal group_required_substr;
|
||||
bool group_is_trival = true;
|
||||
Literals group_alters;
|
||||
|
||||
@ -47,4 +47,8 @@ TEST(OptimizeRE, analyze)
|
||||
test_f("abc|(:?xx|yy|zz|x?)def", "", {"abc", "def"});
|
||||
test_f("abc|(:?xx|yy|zz|x?){1,2}def", "", {"abc", "def"});
|
||||
test_f(R"(\\A(?:(?:[-0-9_a-z]+(?:\\.[-0-9_a-z]+)*)/k8s1)\\z)", "/k8s1");
|
||||
test_f("[a-zA-Z]+(?P<num>\\d+)", "");
|
||||
test_f("[a-zA-Z]+(?<num>\\d+)", "");
|
||||
test_f("[a-zA-Z]+(?'num'\\d+)", "");
|
||||
test_f("[a-zA-Z]+(?x<num>\\d+)", "x<num>");
|
||||
}
|
||||
|
||||
@ -626,7 +626,7 @@ class IColumn;
|
||||
M(Bool, engine_file_allow_create_multiple_files, false, "Enables or disables creating a new file on each insert in file engine tables if format has suffix.", 0) \
|
||||
M(Bool, engine_file_skip_empty_files, false, "Allows to skip empty files in file table engine", 0) \
|
||||
M(Bool, engine_url_skip_empty_files, false, "Allows to skip empty files in url table engine", 0) \
|
||||
M(Bool, disable_url_encoding, false, " Allows to disable decoding/encoding path in uri in URL table engine", 0) \
|
||||
M(Bool, enable_url_encoding, true, " Allows to enable/disable decoding/encoding path in uri in URL table engine", 0) \
|
||||
M(Bool, allow_experimental_database_replicated, false, "Allow to create databases with Replicated engine", 0) \
|
||||
M(UInt64, database_replicated_initial_query_timeout_sec, 300, "How long initial DDL query should wait for Replicated database to precess previous DDL queue entries", 0) \
|
||||
M(Bool, database_replicated_enforce_synchronous_settings, false, "Enforces synchronous waiting for some queries (see also database_atomic_wait_for_drop_and_detach_synchronously, mutation_sync, alter_sync). Not recommended to enable these settings.", 0) \
|
||||
@ -1011,6 +1011,10 @@ class IColumn;
|
||||
\
|
||||
M(CapnProtoEnumComparingMode, format_capn_proto_enum_comparising_mode, FormatSettings::CapnProtoEnumComparingMode::BY_VALUES, "How to map ClickHouse Enum and CapnProto Enum", 0) \
|
||||
\
|
||||
M(Bool, format_capn_proto_use_autogenerated_schema, true, "Use autogenerated CapnProto schema when format_schema is not set", 0) \
|
||||
M(Bool, format_protobuf_use_autogenerated_schema, true, "Use autogenerated Protobuf when format_schema is not set", 0) \
|
||||
M(String, output_format_schema, "", "The path to the file where the automatically generated schema will be saved", 0) \
|
||||
\
|
||||
M(String, input_format_mysql_dump_table_name, "", "Name of the table in MySQL dump from which to read data", 0) \
|
||||
M(Bool, input_format_mysql_dump_map_column_names, true, "Match columns from table in MySQL dump and columns from ClickHouse table by names", 0) \
|
||||
\
|
||||
@ -1027,7 +1031,8 @@ class IColumn;
|
||||
M(Bool, regexp_dict_allow_hyperscan, true, "Allow regexp_tree dictionary using Hyperscan library.", 0) \
|
||||
\
|
||||
M(Bool, dictionary_use_async_executor, false, "Execute a pipeline for reading from a dictionary with several threads. It's supported only by DIRECT dictionary with CLICKHOUSE source.", 0) \
|
||||
M(Bool, input_format_csv_allow_variable_number_of_columns, false, "Ignore extra columns in CSV input (if file has more columns than expected) and treat missing fields in CSV input as default values", 0) \
|
||||
M(Bool, input_format_csv_allow_variable_number_of_columns, false, "Ignore extra columns in CSV input (if file has more columns than expected) and treat missing fields in CSV input as default values", 0) \
|
||||
M(Bool, precise_float_parsing, false, "Prefer more precise (but slower) float parsing algorithm", 0) \
|
||||
|
||||
// End of FORMAT_FACTORY_SETTINGS
|
||||
// Please add settings non-related to formats into the COMMON_SETTINGS above.
|
||||
|
||||
@ -14,7 +14,7 @@ namespace ErrorCodes
|
||||
}
|
||||
|
||||
WriteBufferFromTemporaryFile::WriteBufferFromTemporaryFile(TemporaryFileOnDiskHolder && tmp_file_)
|
||||
: WriteBufferFromFile(tmp_file_->getPath(), DBMS_DEFAULT_BUFFER_SIZE, O_RDWR | O_TRUNC | O_CREAT, /* throttler= */ {}, 0600)
|
||||
: WriteBufferFromFile(tmp_file_->getAbsolutePath(), DBMS_DEFAULT_BUFFER_SIZE, O_RDWR | O_TRUNC | O_CREAT, /* throttler= */ {}, 0600)
|
||||
, tmp_file(std::move(tmp_file_))
|
||||
{
|
||||
}
|
||||
|
||||
@ -54,7 +54,7 @@ TemporaryFileOnDisk::TemporaryFileOnDisk(const DiskPtr & disk_, const String & p
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Temporary file name is empty");
|
||||
}
|
||||
|
||||
String TemporaryFileOnDisk::getPath() const
|
||||
String TemporaryFileOnDisk::getAbsolutePath() const
|
||||
{
|
||||
return std::filesystem::path(disk->getPath()) / relative_path;
|
||||
}
|
||||
|
||||
@ -22,7 +22,10 @@ public:
|
||||
~TemporaryFileOnDisk();
|
||||
|
||||
DiskPtr getDisk() const { return disk; }
|
||||
String getPath() const;
|
||||
/// Return absolute path (disk + relative_path)
|
||||
String getAbsolutePath() const;
|
||||
/// Return relative path (without disk)
|
||||
const String & getRelativePath() const { return relative_path; }
|
||||
|
||||
private:
|
||||
DiskPtr disk;
|
||||
|
||||
@ -143,12 +143,14 @@ FormatSettings getFormatSettings(ContextPtr context, const Settings & settings)
|
||||
format_settings.protobuf.input_flatten_google_wrappers = settings.input_format_protobuf_flatten_google_wrappers;
|
||||
format_settings.protobuf.output_nullables_with_google_wrappers = settings.output_format_protobuf_nullables_with_google_wrappers;
|
||||
format_settings.protobuf.skip_fields_with_unsupported_types_in_schema_inference = settings.input_format_protobuf_skip_fields_with_unsupported_types_in_schema_inference;
|
||||
format_settings.protobuf.use_autogenerated_schema = settings.format_protobuf_use_autogenerated_schema;
|
||||
format_settings.regexp.escaping_rule = settings.format_regexp_escaping_rule;
|
||||
format_settings.regexp.regexp = settings.format_regexp;
|
||||
format_settings.regexp.skip_unmatched = settings.format_regexp_skip_unmatched;
|
||||
format_settings.schema.format_schema = settings.format_schema;
|
||||
format_settings.schema.format_schema_path = context->getFormatSchemaPath();
|
||||
format_settings.schema.is_server = context->hasGlobalContext() && (context->getGlobalContext()->getApplicationType() == Context::ApplicationType::SERVER);
|
||||
format_settings.schema.output_format_schema = settings.output_format_schema;
|
||||
format_settings.skip_unknown_fields = settings.input_format_skip_unknown_fields;
|
||||
format_settings.template_settings.resultset_format = settings.format_template_resultset;
|
||||
format_settings.template_settings.row_between_delimiter = settings.format_template_rows_between_delimiter;
|
||||
@ -190,6 +192,7 @@ FormatSettings getFormatSettings(ContextPtr context, const Settings & settings)
|
||||
format_settings.defaults_for_omitted_fields = settings.input_format_defaults_for_omitted_fields;
|
||||
format_settings.capn_proto.enum_comparing_mode = settings.format_capn_proto_enum_comparising_mode;
|
||||
format_settings.capn_proto.skip_fields_with_unsupported_types_in_schema_inference = settings.input_format_capn_proto_skip_fields_with_unsupported_types_in_schema_inference;
|
||||
format_settings.capn_proto.use_autogenerated_schema = settings.format_capn_proto_use_autogenerated_schema;
|
||||
format_settings.seekable_read = settings.input_format_allow_seeks;
|
||||
format_settings.msgpack.number_of_columns = settings.input_format_msgpack_number_of_columns;
|
||||
format_settings.msgpack.output_uuid_representation = settings.output_format_msgpack_uuid_representation;
|
||||
|
||||
@ -1,6 +1,8 @@
|
||||
#include <Formats/FormatSchemaInfo.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Common/Exception.h>
|
||||
#include <Common/filesystemHelpers.h>
|
||||
#include <Disks/IO/WriteBufferFromTemporaryFile.h>
|
||||
#include <filesystem>
|
||||
|
||||
|
||||
@ -105,4 +107,84 @@ FormatSchemaInfo::FormatSchemaInfo(const FormatSettings & settings, const String
|
||||
{
|
||||
}
|
||||
|
||||
template <typename SchemaGenerator>
|
||||
MaybeAutogeneratedFormatSchemaInfo<SchemaGenerator>::MaybeAutogeneratedFormatSchemaInfo(
|
||||
const FormatSettings & settings, const String & format, const Block & header, bool use_autogenerated_schema)
|
||||
{
|
||||
if (!use_autogenerated_schema || !settings.schema.format_schema.empty())
|
||||
{
|
||||
schema_info = std::make_unique<FormatSchemaInfo>(settings, format, true);
|
||||
return;
|
||||
}
|
||||
|
||||
String schema_path;
|
||||
fs::path default_schema_directory_path(fs::canonical(settings.schema.format_schema_path) / "");
|
||||
fs::path path;
|
||||
if (!settings.schema.output_format_schema.empty())
|
||||
{
|
||||
schema_path = settings.schema.output_format_schema;
|
||||
path = schema_path;
|
||||
if (path.is_absolute())
|
||||
{
|
||||
if (settings.schema.is_server)
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Absolute path in the 'output_format_schema' setting is prohibited: {}", path.string());
|
||||
}
|
||||
else if (path.has_parent_path() && !fs::weakly_canonical(default_schema_directory_path / path).string().starts_with(fs::weakly_canonical(default_schema_directory_path).string()))
|
||||
{
|
||||
if (settings.schema.is_server)
|
||||
throw Exception(
|
||||
ErrorCodes::BAD_ARGUMENTS,
|
||||
"Path in the 'format_schema' setting shouldn't go outside the 'format_schema_path' directory: {} ({} not in {})",
|
||||
default_schema_directory_path.string(),
|
||||
path.string(),
|
||||
default_schema_directory_path.string());
|
||||
path = default_schema_directory_path / path;
|
||||
}
|
||||
else
|
||||
{
|
||||
path = default_schema_directory_path / path;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
if (settings.schema.is_server)
|
||||
{
|
||||
tmp_file_path = PocoTemporaryFile::tempName(default_schema_directory_path.string()) + '.' + getFormatSchemaDefaultFileExtension(format);
|
||||
schema_path = fs::path(tmp_file_path).filename();
|
||||
}
|
||||
else
|
||||
{
|
||||
tmp_file_path = PocoTemporaryFile::tempName() + '.' + getFormatSchemaDefaultFileExtension(format);
|
||||
schema_path = tmp_file_path;
|
||||
}
|
||||
|
||||
path = tmp_file_path;
|
||||
}
|
||||
|
||||
WriteBufferFromFile buf(path.string());
|
||||
SchemaGenerator::writeSchema(buf, "Message", header.getNamesAndTypesList());
|
||||
buf.finalize();
|
||||
|
||||
schema_info = std::make_unique<FormatSchemaInfo>(schema_path + ":Message", format, true, settings.schema.is_server, settings.schema.format_schema_path);
|
||||
}
|
||||
|
||||
template <typename SchemaGenerator>
|
||||
MaybeAutogeneratedFormatSchemaInfo<SchemaGenerator>::~MaybeAutogeneratedFormatSchemaInfo()
|
||||
{
|
||||
if (!tmp_file_path.empty())
|
||||
{
|
||||
try
|
||||
{
|
||||
fs::remove(tmp_file_path);
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
tryLogCurrentException("MaybeAutogeneratedFormatSchemaInfo", "Cannot delete temporary schema file");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
template class MaybeAutogeneratedFormatSchemaInfo<StructureToCapnProtoSchema>;
|
||||
template class MaybeAutogeneratedFormatSchemaInfo<StructureToProtobufSchema>;
|
||||
|
||||
}
|
||||
|
||||
@ -2,6 +2,8 @@
|
||||
|
||||
#include <base/types.h>
|
||||
#include <Formats/FormatSettings.h>
|
||||
#include <Formats/StructureToCapnProtoSchema.h>
|
||||
#include <Formats/StructureToProtobufSchema.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -30,4 +32,23 @@ private:
|
||||
String message_name;
|
||||
};
|
||||
|
||||
|
||||
template <typename SchemaGenerator>
|
||||
class MaybeAutogeneratedFormatSchemaInfo
|
||||
{
|
||||
public:
|
||||
MaybeAutogeneratedFormatSchemaInfo(const FormatSettings & settings, const String & format, const Block & header, bool use_autogenerated_schema);
|
||||
|
||||
~MaybeAutogeneratedFormatSchemaInfo();
|
||||
|
||||
const FormatSchemaInfo & getSchemaInfo() const { return *schema_info; }
|
||||
private:
|
||||
|
||||
std::unique_ptr<FormatSchemaInfo> schema_info;
|
||||
String tmp_file_path;
|
||||
};
|
||||
|
||||
using CapnProtoSchemaInfo = MaybeAutogeneratedFormatSchemaInfo<StructureToCapnProtoSchema>;
|
||||
using ProtobufSchemaInfo = MaybeAutogeneratedFormatSchemaInfo<StructureToProtobufSchema>;
|
||||
|
||||
}
|
||||
|
||||
@ -276,6 +276,7 @@ struct FormatSettings
|
||||
*/
|
||||
bool allow_multiple_rows_without_delimiter = false;
|
||||
bool skip_fields_with_unsupported_types_in_schema_inference = false;
|
||||
bool use_autogenerated_schema = true;
|
||||
} protobuf;
|
||||
|
||||
struct
|
||||
@ -297,6 +298,7 @@ struct FormatSettings
|
||||
std::string format_schema;
|
||||
std::string format_schema_path;
|
||||
bool is_server = false;
|
||||
std::string output_format_schema;
|
||||
} schema;
|
||||
|
||||
struct
|
||||
@ -359,6 +361,7 @@ struct FormatSettings
|
||||
{
|
||||
CapnProtoEnumComparingMode enum_comparing_mode = CapnProtoEnumComparingMode::BY_VALUES;
|
||||
bool skip_fields_with_unsupported_types_in_schema_inference = false;
|
||||
bool use_autogenerated_schema = true;
|
||||
} capn_proto;
|
||||
|
||||
enum class MsgPackUUIDRepresentation
|
||||
|
||||
@ -3029,7 +3029,7 @@ namespace
|
||||
if (!message_serializer)
|
||||
{
|
||||
throw Exception(ErrorCodes::NO_COLUMNS_SERIALIZED_TO_PROTOBUF_FIELDS,
|
||||
"Not found matches between the names of the columns {{}} and the fields {{}} of the message {} in the protobuf schema",
|
||||
"Not found matches between the names of the columns ({}) and the fields ({}) of the message {} in the protobuf schema",
|
||||
boost::algorithm::join(column_names, ", "), boost::algorithm::join(getFieldNames(message_descriptor), ", "),
|
||||
quoteString(message_descriptor.full_name()));
|
||||
}
|
||||
@ -3647,7 +3647,7 @@ namespace
|
||||
if (!message_serializer)
|
||||
{
|
||||
throw Exception(ErrorCodes::NO_COLUMNS_SERIALIZED_TO_PROTOBUF_FIELDS,
|
||||
"Not found matches between the names of the tuple's elements {{}} and the fields {{}} "
|
||||
"Not found matches between the names of the tuple's elements ({}) and the fields ({}) "
|
||||
"of the message {} in the protobuf schema",
|
||||
boost::algorithm::join(tuple_data_type.getElementNames(), ", "),
|
||||
boost::algorithm::join(getFieldNames(*field_descriptor.message_type()), ", "),
|
||||
|
||||
236
src/Formats/StructureToCapnProtoSchema.cpp
Normal file
236
src/Formats/StructureToCapnProtoSchema.cpp
Normal file
@ -0,0 +1,236 @@
|
||||
#include <Formats/StructureToCapnProtoSchema.h>
|
||||
#include <Formats/StructureToFormatSchemaUtils.h>
|
||||
#include <Columns/ColumnString.h>
|
||||
#include <DataTypes/DataTypeNullable.h>
|
||||
#include <DataTypes/DataTypeLowCardinality.h>
|
||||
#include <DataTypes/DataTypeArray.h>
|
||||
#include <DataTypes/DataTypeMap.h>
|
||||
#include <DataTypes/DataTypeTuple.h>
|
||||
#include <DataTypes/DataTypeEnum.h>
|
||||
#include <Common/StringUtils/StringUtils.h>
|
||||
#include <Common/randomSeed.h>
|
||||
#include <pcg_random.hpp>
|
||||
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
using namespace StructureToFormatSchemaUtils;
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int BAD_ARGUMENTS;
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
|
||||
const std::unordered_map<TypeIndex, String> capn_proto_simple_type_names =
|
||||
{
|
||||
{TypeIndex::Int8, "Int8"},
|
||||
{TypeIndex::UInt8, "UInt8"},
|
||||
{TypeIndex::Int16, "Int16"},
|
||||
{TypeIndex::UInt16, "UInt16"},
|
||||
{TypeIndex::Int32, "Int32"},
|
||||
{TypeIndex::UInt32, "UInt32"},
|
||||
{TypeIndex::Int64, "Int64"},
|
||||
{TypeIndex::UInt64, "UInt64"},
|
||||
{TypeIndex::Int128, "Data"},
|
||||
{TypeIndex::UInt128, "Data"},
|
||||
{TypeIndex::Int256, "Data"},
|
||||
{TypeIndex::UInt256, "Data"},
|
||||
{TypeIndex::Float32, "Float32"},
|
||||
{TypeIndex::Float64, "Float64"},
|
||||
{TypeIndex::Decimal32, "Int32"},
|
||||
{TypeIndex::Decimal64, "Int64"},
|
||||
{TypeIndex::Decimal128, "Data"},
|
||||
{TypeIndex::Decimal256, "Data"},
|
||||
{TypeIndex::String, "Data"},
|
||||
{TypeIndex::FixedString, "Data"},
|
||||
{TypeIndex::UUID, "Data"},
|
||||
{TypeIndex::Date, "UInt16"},
|
||||
{TypeIndex::Date32, "Int32"},
|
||||
{TypeIndex::DateTime, "UInt32"},
|
||||
{TypeIndex::DateTime64, "Int64"},
|
||||
{TypeIndex::IPv4, "UInt32"},
|
||||
{TypeIndex::IPv6, "Data"},
|
||||
};
|
||||
|
||||
void writeCapnProtoHeader(WriteBuffer & buf)
|
||||
{
|
||||
pcg64 rng(randomSeed());
|
||||
size_t id = rng() | (1ull << 63); /// First bit should be 1
|
||||
writeString(fmt::format("@0x{};\n\n", getHexUIntLowercase(id)), buf);
|
||||
}
|
||||
|
||||
void writeFieldDefinition(WriteBuffer & buf, const String & type_name, const String & column_name, size_t & field_index, size_t indent)
|
||||
{
|
||||
writeIndent(buf, indent);
|
||||
writeString(fmt::format("{} @{} : {};\n", getSchemaFieldName(column_name), field_index++, type_name), buf);
|
||||
}
|
||||
|
||||
void startEnum(WriteBuffer & buf, const String & enum_name, size_t indent)
|
||||
{
|
||||
startNested(buf, enum_name, "enum", indent);
|
||||
}
|
||||
|
||||
void startUnion(WriteBuffer & buf, size_t indent)
|
||||
{
|
||||
startNested(buf, "", "union", indent);
|
||||
}
|
||||
|
||||
void startStruct(WriteBuffer & buf, const String & struct_name, size_t indent)
|
||||
{
|
||||
startNested(buf, struct_name, "struct", indent);
|
||||
}
|
||||
|
||||
String prepareAndGetCapnProtoTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent);
|
||||
|
||||
void writeField(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t & field_index, size_t indent)
|
||||
{
|
||||
auto field_type_name = prepareAndGetCapnProtoTypeName(buf, data_type, column_name, indent);
|
||||
writeFieldDefinition(buf, field_type_name, column_name, field_index, indent);
|
||||
}
|
||||
|
||||
String prepareArrayAndGetCapnProtoTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
const auto & nested_type = assert_cast<const DataTypeArray &>(*data_type).getNestedType();
|
||||
auto nested_type_name = prepareAndGetCapnProtoTypeName(buf, nested_type, column_name, indent);
|
||||
return "List(" + nested_type_name + ")";
|
||||
}
|
||||
|
||||
String prepareNullableAndGetCapnProtoTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
/// Nullable is represented as a struct with union with 2 fields:
|
||||
///
|
||||
/// struct Nullable
|
||||
/// {
|
||||
/// union
|
||||
/// {
|
||||
/// value @0 : Value;
|
||||
/// null @1 : Void;
|
||||
/// }
|
||||
/// }
|
||||
auto struct_name = getSchemaMessageName(column_name);
|
||||
startStruct(buf, struct_name, indent);
|
||||
auto nested_type_name = prepareAndGetCapnProtoTypeName(buf, assert_cast<const DataTypeNullable &>(*data_type).getNestedType(), column_name, indent);
|
||||
startUnion(buf, indent + 1);
|
||||
size_t field_index = 0;
|
||||
writeFieldDefinition(buf, nested_type_name, "value", field_index, indent + 2);
|
||||
writeFieldDefinition(buf, "Void", "null", field_index, indent + 2);
|
||||
endNested(buf, indent + 1);
|
||||
endNested(buf, indent);
|
||||
return struct_name;
|
||||
}
|
||||
|
||||
String prepareTupleAndGetCapnProtoTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
const auto & tuple_type = assert_cast<const DataTypeTuple &>(*data_type);
|
||||
auto nested_names_and_types = getCollectedTupleElements(tuple_type);
|
||||
|
||||
String struct_name = getSchemaMessageName(column_name);
|
||||
startStruct(buf, struct_name, indent);
|
||||
size_t nested_field_index = 0;
|
||||
for (const auto & [name, type] : nested_names_and_types)
|
||||
writeField(buf, type, name, nested_field_index, indent + 1);
|
||||
endNested(buf, indent);
|
||||
return struct_name;
|
||||
}
|
||||
|
||||
String prepareMapAndGetCapnProtoTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
/// We output/input Map type as follow CapnProto schema
|
||||
///
|
||||
/// struct Map
|
||||
/// {
|
||||
/// struct Entry
|
||||
/// {
|
||||
/// key @0: Key;
|
||||
/// value @1: Value;
|
||||
/// }
|
||||
/// entries @0 :List(Entry);
|
||||
/// }
|
||||
const auto & map_type = assert_cast<const DataTypeMap &>(*data_type);
|
||||
const auto & key_type = map_type.getKeyType();
|
||||
const auto & value_type = map_type.getValueType();
|
||||
|
||||
String struct_name = getSchemaMessageName(column_name);
|
||||
startStruct(buf, struct_name, indent);
|
||||
startStruct(buf, "Entry", indent + 1);
|
||||
auto key_type_name = prepareAndGetCapnProtoTypeName(buf, key_type, "key", indent + 2);
|
||||
auto value_type_name = prepareAndGetCapnProtoTypeName(buf, value_type, "value", indent + 2);
|
||||
size_t field_index = 0;
|
||||
writeFieldDefinition(buf, key_type_name, "key", field_index, indent + 2);
|
||||
writeFieldDefinition(buf, value_type_name, "value", field_index, indent + 2);
|
||||
endNested(buf, indent + 1);
|
||||
field_index = 0;
|
||||
writeFieldDefinition(buf, "List(Entry)", "entries", field_index, indent + 1);
|
||||
endNested(buf, indent);
|
||||
return struct_name;
|
||||
}
|
||||
|
||||
template <typename EnumType>
|
||||
String prepareEnumAndGetCapnProtoTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
const auto & enum_type = assert_cast<const DataTypeEnum<EnumType> &>(*data_type);
|
||||
String enum_name = getSchemaMessageName(column_name);
|
||||
startEnum(buf, enum_name, indent);
|
||||
const auto & names = enum_type.getAllRegisteredNames();
|
||||
for (size_t i = 0; i != names.size(); ++i)
|
||||
{
|
||||
writeIndent(buf, indent + 1);
|
||||
writeString(fmt::format("{} @{};\n", names[i], std::to_string(i)), buf);
|
||||
}
|
||||
endNested(buf, indent);
|
||||
return enum_name;
|
||||
}
|
||||
|
||||
String prepareAndGetCapnProtoTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
TypeIndex type_id = data_type->getTypeId();
|
||||
|
||||
switch (data_type->getTypeId())
|
||||
{
|
||||
case TypeIndex::Nullable:
|
||||
return prepareNullableAndGetCapnProtoTypeName(buf, data_type, column_name, indent);
|
||||
case TypeIndex::LowCardinality:
|
||||
return prepareAndGetCapnProtoTypeName(buf, assert_cast<const DataTypeLowCardinality &>(*data_type).getDictionaryType(), column_name, indent);
|
||||
case TypeIndex::Array:
|
||||
return prepareArrayAndGetCapnProtoTypeName(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Tuple:
|
||||
return prepareTupleAndGetCapnProtoTypeName(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Map:
|
||||
return prepareMapAndGetCapnProtoTypeName(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Enum8:
|
||||
return prepareEnumAndGetCapnProtoTypeName<Int8>(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Enum16:
|
||||
return prepareEnumAndGetCapnProtoTypeName<Int16>(buf, data_type, column_name, indent);
|
||||
default:
|
||||
{
|
||||
if (isBool(data_type))
|
||||
return "Bool";
|
||||
|
||||
auto it = capn_proto_simple_type_names.find(type_id);
|
||||
if (it == capn_proto_simple_type_names.end())
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "CapnProto type name is not found for type {}", data_type->getName());
|
||||
return it->second;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
void StructureToCapnProtoSchema::writeSchema(WriteBuffer & buf, const String & message_name, const NamesAndTypesList & names_and_types_)
|
||||
{
|
||||
auto names_and_types = collectNested(names_and_types_);
|
||||
writeCapnProtoHeader(buf);
|
||||
startStruct(buf, getSchemaMessageName(message_name), 0);
|
||||
|
||||
size_t field_index = 0;
|
||||
for (const auto & [column_name, data_type] : names_and_types)
|
||||
writeField(buf, data_type, column_name, field_index, 1);
|
||||
|
||||
endNested(buf, 0);
|
||||
}
|
||||
|
||||
}
|
||||
16
src/Formats/StructureToCapnProtoSchema.h
Normal file
16
src/Formats/StructureToCapnProtoSchema.h
Normal file
@ -0,0 +1,16 @@
|
||||
#pragma once
|
||||
|
||||
#include <IO/WriteBuffer.h>
|
||||
#include <Core/NamesAndTypes.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
struct StructureToCapnProtoSchema
|
||||
{
|
||||
static constexpr auto name = "structureToCapnProtoSchema";
|
||||
|
||||
static void writeSchema(WriteBuffer & buf, const String & message_name, const NamesAndTypesList & names_and_types_);
|
||||
};
|
||||
|
||||
}
|
||||
117
src/Formats/StructureToFormatSchemaUtils.cpp
Normal file
117
src/Formats/StructureToFormatSchemaUtils.cpp
Normal file
@ -0,0 +1,117 @@
|
||||
#include <Formats/StructureToFormatSchemaUtils.h>
|
||||
#include <IO/WriteHelpers.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
namespace StructureToFormatSchemaUtils
|
||||
{
|
||||
|
||||
void writeIndent(WriteBuffer & buf, size_t indent)
|
||||
{
|
||||
writeChar(' ', indent * 4, buf);
|
||||
}
|
||||
|
||||
void startNested(WriteBuffer & buf, const String & nested_name, const String & nested_type, size_t indent)
|
||||
{
|
||||
writeIndent(buf, indent);
|
||||
writeString(nested_type, buf);
|
||||
if (!nested_name.empty())
|
||||
{
|
||||
writeChar(' ', buf);
|
||||
writeString(nested_name, buf);
|
||||
}
|
||||
writeChar('\n', buf);
|
||||
writeIndent(buf, indent);
|
||||
writeCString("{\n", buf);
|
||||
}
|
||||
|
||||
void endNested(WriteBuffer & buf, size_t indent)
|
||||
{
|
||||
writeIndent(buf, indent);
|
||||
writeCString("}\n", buf);
|
||||
}
|
||||
|
||||
String getSchemaFieldName(const String & column_name)
|
||||
{
|
||||
String result = column_name;
|
||||
/// Replace all first uppercase letters to lower-case,
|
||||
/// because fields in CapnProto schema must begin with a lower-case letter.
|
||||
/// Don't replace all letters to lower-case to remain camelCase field names.
|
||||
for (auto & symbol : result)
|
||||
{
|
||||
if (islower(symbol))
|
||||
break;
|
||||
symbol = tolower(symbol);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
String getSchemaMessageName(const String & column_name)
|
||||
{
|
||||
String result = column_name;
|
||||
if (!column_name.empty() && isalpha(column_name[0]))
|
||||
result[0] = toupper(column_name[0]);
|
||||
return result;
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
std::pair<String, String> splitName(const String & name)
|
||||
{
|
||||
const auto * begin = name.data();
|
||||
const auto * end = name.data() + name.size();
|
||||
const auto * it = find_first_symbols<'_', '.'>(begin, end);
|
||||
String first = String(begin, it);
|
||||
String second = it == end ? "" : String(it + 1, end);
|
||||
return {std::move(first), std::move(second)};
|
||||
}
|
||||
}
|
||||
|
||||
NamesAndTypesList collectNested(const NamesAndTypesList & names_and_types)
|
||||
{
|
||||
/// Find all columns with dots '.' or underscores '_' and move them into a tuple.
|
||||
/// For example if we have columns 'a.b UInt32, a.c UInt32, x_y String' we will
|
||||
/// change it to 'a Tuple(b UInt32, c UInt32), x Tuple(y String)'
|
||||
NamesAndTypesList result;
|
||||
std::unordered_map<String, NamesAndTypesList> nested;
|
||||
for (const auto & [name, type] : names_and_types)
|
||||
{
|
||||
auto [field_name, nested_name] = splitName(name);
|
||||
if (nested_name.empty())
|
||||
result.emplace_back(name, type);
|
||||
else
|
||||
nested[field_name].emplace_back(nested_name, type);
|
||||
}
|
||||
|
||||
for (const auto & [field_name, elements]: nested)
|
||||
result.emplace_back(field_name, std::make_shared<DataTypeTuple>(elements.getTypes(), elements.getNames()));
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
NamesAndTypesList getCollectedTupleElements(const DataTypeTuple & tuple_type)
|
||||
{
|
||||
const auto & nested_types = tuple_type.getElements();
|
||||
Names nested_names;
|
||||
if (tuple_type.haveExplicitNames())
|
||||
{
|
||||
nested_names = tuple_type.getElementNames();
|
||||
}
|
||||
else
|
||||
{
|
||||
nested_names.reserve(nested_types.size());
|
||||
for (size_t i = 0; i != nested_types.size(); ++i)
|
||||
nested_names.push_back("e" + std::to_string(i + 1));
|
||||
}
|
||||
|
||||
NamesAndTypesList result;
|
||||
for (size_t i = 0; i != nested_names.size(); ++i)
|
||||
result.emplace_back(nested_names[i], nested_types[i]);
|
||||
|
||||
return collectNested(result);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
27
src/Formats/StructureToFormatSchemaUtils.h
Normal file
27
src/Formats/StructureToFormatSchemaUtils.h
Normal file
@ -0,0 +1,27 @@
|
||||
#pragma once
|
||||
|
||||
#include <Core/NamesAndTypes.h>
|
||||
#include <DataTypes/NestedUtils.h>
|
||||
#include <DataTypes/DataTypeTuple.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
namespace StructureToFormatSchemaUtils
|
||||
{
|
||||
void writeIndent(WriteBuffer & buf, size_t indent);
|
||||
|
||||
void startNested(WriteBuffer & buf, const String & nested_name, const String & nested_type, size_t indent);
|
||||
|
||||
void endNested(WriteBuffer & buf, size_t indent);
|
||||
|
||||
String getSchemaFieldName(const String & column_name);
|
||||
|
||||
String getSchemaMessageName(const String & column_name);
|
||||
|
||||
NamesAndTypesList collectNested(const NamesAndTypesList & names_and_types);
|
||||
|
||||
NamesAndTypesList getCollectedTupleElements(const DataTypeTuple & tuple_type);
|
||||
}
|
||||
|
||||
}
|
||||
214
src/Formats/StructureToProtobufSchema.cpp
Normal file
214
src/Formats/StructureToProtobufSchema.cpp
Normal file
@ -0,0 +1,214 @@
|
||||
#include <Formats/StructureToProtobufSchema.h>
|
||||
#include <Formats/StructureToFormatSchemaUtils.h>
|
||||
#include <Columns/ColumnString.h>
|
||||
#include <DataTypes/DataTypeNullable.h>
|
||||
#include <DataTypes/DataTypeLowCardinality.h>
|
||||
#include <DataTypes/DataTypeArray.h>
|
||||
#include <DataTypes/DataTypeMap.h>
|
||||
#include <DataTypes/DataTypeTuple.h>
|
||||
#include <DataTypes/DataTypeEnum.h>
|
||||
#include <Common/StringUtils/StringUtils.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
using namespace StructureToFormatSchemaUtils;
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int BAD_ARGUMENTS;
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
|
||||
const std::unordered_map<TypeIndex, String> protobuf_simple_type_names =
|
||||
{
|
||||
{TypeIndex::Int8, "int32"},
|
||||
{TypeIndex::UInt8, "uint32"},
|
||||
{TypeIndex::Int16, "int32"},
|
||||
{TypeIndex::UInt16, "uint32"},
|
||||
{TypeIndex::Int32, "int32"},
|
||||
{TypeIndex::UInt32, "uint32"},
|
||||
{TypeIndex::Int64, "int64"},
|
||||
{TypeIndex::UInt64, "uint64"},
|
||||
{TypeIndex::Int128, "bytes"},
|
||||
{TypeIndex::UInt128, "bytes"},
|
||||
{TypeIndex::Int256, "bytes"},
|
||||
{TypeIndex::UInt256, "bytes"},
|
||||
{TypeIndex::Float32, "float"},
|
||||
{TypeIndex::Float64, "double"},
|
||||
{TypeIndex::Decimal32, "bytes"},
|
||||
{TypeIndex::Decimal64, "bytes"},
|
||||
{TypeIndex::Decimal128, "bytes"},
|
||||
{TypeIndex::Decimal256, "bytes"},
|
||||
{TypeIndex::String, "bytes"},
|
||||
{TypeIndex::FixedString, "bytes"},
|
||||
{TypeIndex::UUID, "bytes"},
|
||||
{TypeIndex::Date, "uint32"},
|
||||
{TypeIndex::Date32, "int32"},
|
||||
{TypeIndex::DateTime, "uint32"},
|
||||
{TypeIndex::DateTime64, "uint64"},
|
||||
{TypeIndex::IPv4, "uint32"},
|
||||
{TypeIndex::IPv6, "bytes"},
|
||||
};
|
||||
|
||||
void writeProtobufHeader(WriteBuffer & buf)
|
||||
{
|
||||
writeCString("syntax = \"proto3\";\n\n", buf);
|
||||
}
|
||||
|
||||
void startEnum(WriteBuffer & buf, const String & enum_name, size_t indent)
|
||||
{
|
||||
startNested(buf, enum_name, "enum", indent);
|
||||
}
|
||||
|
||||
void startMessage(WriteBuffer & buf, const String & message_name, size_t indent)
|
||||
{
|
||||
startNested(buf, message_name, "message", indent);
|
||||
}
|
||||
|
||||
void writeFieldDefinition(WriteBuffer & buf, const String & type_name, const String & column_name, size_t & field_index, size_t indent)
|
||||
{
|
||||
writeIndent(buf, indent);
|
||||
writeString(fmt::format("{} {} = {};\n", type_name, getSchemaFieldName(column_name), field_index++), buf);
|
||||
}
|
||||
|
||||
String prepareAndGetProtobufTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent);
|
||||
|
||||
void writeProtobufField(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t & field_index, size_t indent)
|
||||
{
|
||||
auto field_type_name = prepareAndGetProtobufTypeName(buf, data_type, column_name, indent);
|
||||
writeFieldDefinition(buf, field_type_name, column_name, field_index, indent);
|
||||
}
|
||||
|
||||
String prepareArrayAndGetProtobufTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
const auto & nested_type = assert_cast<const DataTypeArray &>(*data_type).getNestedType();
|
||||
/// Simple case when we can just use 'repeated <nested_type>'.
|
||||
if (!isArray(nested_type) && !isMap(nested_type))
|
||||
{
|
||||
auto nested_type_name = prepareAndGetProtobufTypeName(buf, nested_type, column_name, indent);
|
||||
return "repeated " + nested_type_name;
|
||||
}
|
||||
|
||||
/// Protobuf doesn't support multidimensional repeated fields and repeated maps.
|
||||
/// When we have Array(Array(...)) or Array(Map(...)) we should place nested type into a nested Message with one field.
|
||||
String message_name = getSchemaMessageName(column_name);
|
||||
startMessage(buf, message_name, indent);
|
||||
size_t nested_field_index = 1;
|
||||
writeProtobufField(buf, nested_type, column_name, nested_field_index, indent + 1);
|
||||
endNested(buf, indent);
|
||||
return "repeated " + message_name;
|
||||
}
|
||||
|
||||
String prepareTupleAndGetProtobufTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
const auto & tuple_type = assert_cast<const DataTypeTuple &>(*data_type);
|
||||
auto nested_names_and_types = getCollectedTupleElements(tuple_type);
|
||||
|
||||
String message_name = getSchemaMessageName(column_name);
|
||||
startMessage(buf, message_name, indent);
|
||||
size_t nested_field_index = 1;
|
||||
for (const auto & [name, type] : nested_names_and_types)
|
||||
writeProtobufField(buf, type, name, nested_field_index, indent + 1);
|
||||
endNested(buf, indent);
|
||||
return message_name;
|
||||
}
|
||||
|
||||
String prepareMapAndGetProtobufTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
const auto & map_type = assert_cast<const DataTypeMap &>(*data_type);
|
||||
const auto & key_type = map_type.getKeyType();
|
||||
const auto & value_type = map_type.getValueType();
|
||||
auto it = protobuf_simple_type_names.find(key_type->getTypeId());
|
||||
if (it == protobuf_simple_type_names.end())
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Type {} is not supported for conversion into Map key in Protobuf schema", data_type->getName());
|
||||
auto key_type_name = it->second;
|
||||
/// Protobuf map type doesn't support "bytes" type as a key. Change it to "string"
|
||||
if (key_type_name == "bytes")
|
||||
key_type_name = "string";
|
||||
|
||||
/// Special cases when value type is Array or Map, because Protobuf
|
||||
/// doesn't support syntax "map<Key, repeated Value>" and "map<Key, map<..., ...>>"
|
||||
/// In this case we should place it into a nested Message with one field.
|
||||
String value_type_name;
|
||||
if (isArray(value_type) || isMap(value_type))
|
||||
{
|
||||
value_type_name = getSchemaMessageName(column_name) + "Value";
|
||||
startMessage(buf, value_type_name, indent);
|
||||
size_t nested_field_index = 1;
|
||||
writeProtobufField(buf, value_type, column_name + "Value", nested_field_index, indent + 1);
|
||||
endNested(buf, indent);
|
||||
}
|
||||
else
|
||||
{
|
||||
value_type_name = prepareAndGetProtobufTypeName(buf, value_type, column_name + "Value", indent);
|
||||
}
|
||||
|
||||
return fmt::format("map<{}, {}>", key_type_name, value_type_name);
|
||||
}
|
||||
|
||||
template <typename EnumType>
|
||||
String prepareEnumAndGetProtobufTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
const auto & enum_type = assert_cast<const DataTypeEnum<EnumType> &>(*data_type);
|
||||
String enum_name = getSchemaMessageName(column_name);
|
||||
startEnum(buf, enum_name, indent);
|
||||
const auto & names = enum_type.getAllRegisteredNames();
|
||||
for (size_t i = 0; i != names.size(); ++i)
|
||||
{
|
||||
writeIndent(buf, indent + 1);
|
||||
writeString(fmt::format("{} = {};\n", names[i], std::to_string(i)), buf);
|
||||
}
|
||||
endNested(buf, indent);
|
||||
return enum_name;
|
||||
}
|
||||
|
||||
String prepareAndGetProtobufTypeName(WriteBuffer & buf, const DataTypePtr & data_type, const String & column_name, size_t indent)
|
||||
{
|
||||
TypeIndex type_id = data_type->getTypeId();
|
||||
|
||||
switch (data_type->getTypeId())
|
||||
{
|
||||
case TypeIndex::Nullable:
|
||||
return prepareAndGetProtobufTypeName(buf, assert_cast<const DataTypeNullable &>(*data_type).getNestedType(), column_name, indent);
|
||||
case TypeIndex::LowCardinality:
|
||||
return prepareAndGetProtobufTypeName(buf, assert_cast<const DataTypeLowCardinality &>(*data_type).getDictionaryType(), column_name, indent);
|
||||
case TypeIndex::Array:
|
||||
return prepareArrayAndGetProtobufTypeName(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Tuple:
|
||||
return prepareTupleAndGetProtobufTypeName(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Map:
|
||||
return prepareMapAndGetProtobufTypeName(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Enum8:
|
||||
return prepareEnumAndGetProtobufTypeName<Int8>(buf, data_type, column_name, indent);
|
||||
case TypeIndex::Enum16:
|
||||
return prepareEnumAndGetProtobufTypeName<Int16>(buf, data_type, column_name, indent);
|
||||
default:
|
||||
{
|
||||
if (isBool(data_type))
|
||||
return "bool";
|
||||
|
||||
auto it = protobuf_simple_type_names.find(type_id);
|
||||
if (it == protobuf_simple_type_names.end())
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Type {} is not supported for conversion into Protobuf schema", data_type->getName());
|
||||
return it->second;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
void StructureToProtobufSchema::writeSchema(WriteBuffer & buf, const String & message_name, const NamesAndTypesList & names_and_types_)
|
||||
{
|
||||
auto names_and_types = collectNested(names_and_types_);
|
||||
writeProtobufHeader(buf);
|
||||
startMessage(buf, getSchemaMessageName(message_name), 0);
|
||||
size_t field_index = 1;
|
||||
for (const auto & [column_name, data_type] : names_and_types)
|
||||
writeProtobufField(buf, data_type, column_name, field_index, 1);
|
||||
endNested(buf, 0);
|
||||
}
|
||||
|
||||
}
|
||||
16
src/Formats/StructureToProtobufSchema.h
Normal file
16
src/Formats/StructureToProtobufSchema.h
Normal file
@ -0,0 +1,16 @@
|
||||
#pragma once
|
||||
|
||||
#include <IO/WriteBuffer.h>
|
||||
#include <Core/NamesAndTypes.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
struct StructureToProtobufSchema
|
||||
{
|
||||
static constexpr auto name = "structureToProtobufSchema";
|
||||
|
||||
static void writeSchema(WriteBuffer & buf, const String & message_name, const NamesAndTypesList & names_and_types_);
|
||||
};
|
||||
|
||||
}
|
||||
@ -1040,13 +1040,21 @@ inline void convertFromTime<DataTypeDateTime>(DataTypeDateTime::FieldType & x, t
|
||||
/** Conversion of strings to numbers, dates, datetimes: through parsing.
|
||||
*/
|
||||
template <typename DataType>
|
||||
void parseImpl(typename DataType::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
void parseImpl(typename DataType::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool precise_float_parsing)
|
||||
{
|
||||
readText(x, rb);
|
||||
if constexpr (std::is_floating_point_v<typename DataType::FieldType>)
|
||||
{
|
||||
if (precise_float_parsing)
|
||||
readFloatTextPrecise(x, rb);
|
||||
else
|
||||
readFloatTextFast(x, rb);
|
||||
}
|
||||
else
|
||||
readText(x, rb);
|
||||
}
|
||||
|
||||
template <>
|
||||
inline void parseImpl<DataTypeDate>(DataTypeDate::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone)
|
||||
inline void parseImpl<DataTypeDate>(DataTypeDate::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone, bool)
|
||||
{
|
||||
DayNum tmp(0);
|
||||
readDateText(tmp, rb, *time_zone);
|
||||
@ -1054,7 +1062,7 @@ inline void parseImpl<DataTypeDate>(DataTypeDate::FieldType & x, ReadBuffer & rb
|
||||
}
|
||||
|
||||
template <>
|
||||
inline void parseImpl<DataTypeDate32>(DataTypeDate32::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone)
|
||||
inline void parseImpl<DataTypeDate32>(DataTypeDate32::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone, bool)
|
||||
{
|
||||
ExtendedDayNum tmp(0);
|
||||
readDateText(tmp, rb, *time_zone);
|
||||
@ -1064,7 +1072,7 @@ inline void parseImpl<DataTypeDate32>(DataTypeDate32::FieldType & x, ReadBuffer
|
||||
|
||||
// NOTE: no need of extra overload of DateTime64, since readDateTimeText64 has different signature and that case is explicitly handled in the calling code.
|
||||
template <>
|
||||
inline void parseImpl<DataTypeDateTime>(DataTypeDateTime::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone)
|
||||
inline void parseImpl<DataTypeDateTime>(DataTypeDateTime::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone, bool)
|
||||
{
|
||||
time_t time = 0;
|
||||
readDateTimeText(time, rb, *time_zone);
|
||||
@ -1072,7 +1080,7 @@ inline void parseImpl<DataTypeDateTime>(DataTypeDateTime::FieldType & x, ReadBuf
|
||||
}
|
||||
|
||||
template <>
|
||||
inline void parseImpl<DataTypeUUID>(DataTypeUUID::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
inline void parseImpl<DataTypeUUID>(DataTypeUUID::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool)
|
||||
{
|
||||
UUID tmp;
|
||||
readUUIDText(tmp, rb);
|
||||
@ -1080,7 +1088,7 @@ inline void parseImpl<DataTypeUUID>(DataTypeUUID::FieldType & x, ReadBuffer & rb
|
||||
}
|
||||
|
||||
template <>
|
||||
inline void parseImpl<DataTypeIPv4>(DataTypeIPv4::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
inline void parseImpl<DataTypeIPv4>(DataTypeIPv4::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool)
|
||||
{
|
||||
IPv4 tmp;
|
||||
readIPv4Text(tmp, rb);
|
||||
@ -1088,7 +1096,7 @@ inline void parseImpl<DataTypeIPv4>(DataTypeIPv4::FieldType & x, ReadBuffer & rb
|
||||
}
|
||||
|
||||
template <>
|
||||
inline void parseImpl<DataTypeIPv6>(DataTypeIPv6::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
inline void parseImpl<DataTypeIPv6>(DataTypeIPv6::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool)
|
||||
{
|
||||
IPv6 tmp;
|
||||
readIPv6Text(tmp, rb);
|
||||
@ -1096,16 +1104,21 @@ inline void parseImpl<DataTypeIPv6>(DataTypeIPv6::FieldType & x, ReadBuffer & rb
|
||||
}
|
||||
|
||||
template <typename DataType>
|
||||
bool tryParseImpl(typename DataType::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
bool tryParseImpl(typename DataType::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool precise_float_parsing)
|
||||
{
|
||||
if constexpr (std::is_floating_point_v<typename DataType::FieldType>)
|
||||
return tryReadFloatText(x, rb);
|
||||
{
|
||||
if (precise_float_parsing)
|
||||
return tryReadFloatTextPrecise(x, rb);
|
||||
else
|
||||
return tryReadFloatTextFast(x, rb);
|
||||
}
|
||||
else /*if constexpr (is_integer_v<typename DataType::FieldType>)*/
|
||||
return tryReadIntText(x, rb);
|
||||
}
|
||||
|
||||
template <>
|
||||
inline bool tryParseImpl<DataTypeDate>(DataTypeDate::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone)
|
||||
inline bool tryParseImpl<DataTypeDate>(DataTypeDate::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone, bool)
|
||||
{
|
||||
DayNum tmp(0);
|
||||
if (!tryReadDateText(tmp, rb, *time_zone))
|
||||
@ -1115,7 +1128,7 @@ inline bool tryParseImpl<DataTypeDate>(DataTypeDate::FieldType & x, ReadBuffer &
|
||||
}
|
||||
|
||||
template <>
|
||||
inline bool tryParseImpl<DataTypeDate32>(DataTypeDate32::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone)
|
||||
inline bool tryParseImpl<DataTypeDate32>(DataTypeDate32::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone, bool)
|
||||
{
|
||||
ExtendedDayNum tmp(0);
|
||||
if (!tryReadDateText(tmp, rb, *time_zone))
|
||||
@ -1125,7 +1138,7 @@ inline bool tryParseImpl<DataTypeDate32>(DataTypeDate32::FieldType & x, ReadBuff
|
||||
}
|
||||
|
||||
template <>
|
||||
inline bool tryParseImpl<DataTypeDateTime>(DataTypeDateTime::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone)
|
||||
inline bool tryParseImpl<DataTypeDateTime>(DataTypeDateTime::FieldType & x, ReadBuffer & rb, const DateLUTImpl * time_zone, bool)
|
||||
{
|
||||
time_t tmp = 0;
|
||||
if (!tryReadDateTimeText(tmp, rb, *time_zone))
|
||||
@ -1135,7 +1148,7 @@ inline bool tryParseImpl<DataTypeDateTime>(DataTypeDateTime::FieldType & x, Read
|
||||
}
|
||||
|
||||
template <>
|
||||
inline bool tryParseImpl<DataTypeUUID>(DataTypeUUID::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
inline bool tryParseImpl<DataTypeUUID>(DataTypeUUID::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool)
|
||||
{
|
||||
UUID tmp;
|
||||
if (!tryReadUUIDText(tmp, rb))
|
||||
@ -1146,7 +1159,7 @@ inline bool tryParseImpl<DataTypeUUID>(DataTypeUUID::FieldType & x, ReadBuffer &
|
||||
}
|
||||
|
||||
template <>
|
||||
inline bool tryParseImpl<DataTypeIPv4>(DataTypeIPv4::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
inline bool tryParseImpl<DataTypeIPv4>(DataTypeIPv4::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool)
|
||||
{
|
||||
IPv4 tmp;
|
||||
if (!tryReadIPv4Text(tmp, rb))
|
||||
@ -1157,7 +1170,7 @@ inline bool tryParseImpl<DataTypeIPv4>(DataTypeIPv4::FieldType & x, ReadBuffer &
|
||||
}
|
||||
|
||||
template <>
|
||||
inline bool tryParseImpl<DataTypeIPv6>(DataTypeIPv6::FieldType & x, ReadBuffer & rb, const DateLUTImpl *)
|
||||
inline bool tryParseImpl<DataTypeIPv6>(DataTypeIPv6::FieldType & x, ReadBuffer & rb, const DateLUTImpl *, bool)
|
||||
{
|
||||
IPv6 tmp;
|
||||
if (!tryReadIPv6Text(tmp, rb))
|
||||
@ -1336,6 +1349,16 @@ struct ConvertThroughParsing
|
||||
|
||||
size_t current_offset = 0;
|
||||
|
||||
bool precise_float_parsing = false;
|
||||
|
||||
if (DB::CurrentThread::isInitialized())
|
||||
{
|
||||
const DB::ContextPtr query_context = DB::CurrentThread::get().getQueryContext();
|
||||
|
||||
if (query_context)
|
||||
precise_float_parsing = query_context->getSettingsRef().precise_float_parsing;
|
||||
}
|
||||
|
||||
for (size_t i = 0; i < size; ++i)
|
||||
{
|
||||
size_t next_offset = std::is_same_v<FromDataType, DataTypeString> ? (*offsets)[i] : (current_offset + fixed_string_size);
|
||||
@ -1402,7 +1425,7 @@ struct ConvertThroughParsing
|
||||
}
|
||||
}
|
||||
|
||||
parseImpl<ToDataType>(vec_to[i], read_buffer, local_time_zone);
|
||||
parseImpl<ToDataType>(vec_to[i], read_buffer, local_time_zone, precise_float_parsing);
|
||||
} while (false);
|
||||
}
|
||||
}
|
||||
@ -1472,7 +1495,7 @@ struct ConvertThroughParsing
|
||||
}
|
||||
}
|
||||
|
||||
parsed = tryParseImpl<ToDataType>(vec_to[i], read_buffer, local_time_zone);
|
||||
parsed = tryParseImpl<ToDataType>(vec_to[i], read_buffer, local_time_zone, precise_float_parsing);
|
||||
} while (false);
|
||||
}
|
||||
}
|
||||
|
||||
@ -153,15 +153,10 @@ struct IntHash64Impl
|
||||
template<typename T, typename HashFunction>
|
||||
T combineHashesFunc(T t1, T t2)
|
||||
{
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
T tmp;
|
||||
reverseMemcpy(&tmp, &t1, sizeof(T));
|
||||
t1 = tmp;
|
||||
reverseMemcpy(&tmp, &t2, sizeof(T));
|
||||
t2 = tmp;
|
||||
#endif
|
||||
T hashes[] = {t1, t2};
|
||||
return HashFunction::apply(reinterpret_cast<const char *>(hashes), 2 * sizeof(T));
|
||||
transformEndianness<std::endian::little>(t1);
|
||||
transformEndianness<std::endian::little>(t2);
|
||||
const T hashes[] {t1, t2};
|
||||
return HashFunction::apply(reinterpret_cast<const char *>(hashes), sizeof(hashes));
|
||||
}
|
||||
|
||||
|
||||
@ -184,21 +179,14 @@ struct HalfMD5Impl
|
||||
MD5_Update(&ctx, reinterpret_cast<const unsigned char *>(begin), size);
|
||||
MD5_Final(buf.char_data, &ctx);
|
||||
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
return buf.uint64_data; /// No need to flip bytes on big endian machines
|
||||
#else
|
||||
return std::byteswap(buf.uint64_data); /// Compatibility with existing code. Cast need for old poco AND macos where UInt64 != uint64_t
|
||||
#endif
|
||||
/// Compatibility with existing code. Cast need for old poco AND macos where UInt64 != uint64_t
|
||||
transformEndianness<std::endian::big>(buf.uint64_data);
|
||||
return buf.uint64_data;
|
||||
}
|
||||
|
||||
static UInt64 combineHashes(UInt64 h1, UInt64 h2)
|
||||
{
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
h1 = std::byteswap(h1);
|
||||
h2 = std::byteswap(h2);
|
||||
#endif
|
||||
UInt64 hashes[] = {h1, h2};
|
||||
return apply(reinterpret_cast<const char *>(hashes), 16);
|
||||
return combineHashesFunc<UInt64, HalfMD5Impl>(h1, h2);
|
||||
}
|
||||
|
||||
/// If true, it will use intHash32 or intHash64 to hash POD types. This behaviour is intended for better performance of some functions.
|
||||
@ -311,15 +299,8 @@ struct SipHash64Impl
|
||||
static constexpr auto name = "sipHash64";
|
||||
using ReturnType = UInt64;
|
||||
|
||||
static UInt64 apply(const char * begin, size_t size)
|
||||
{
|
||||
return sipHash64(begin, size);
|
||||
}
|
||||
|
||||
static UInt64 combineHashes(UInt64 h1, UInt64 h2)
|
||||
{
|
||||
return combineHashesFunc<UInt64, SipHash64Impl>(h1, h2);
|
||||
}
|
||||
static UInt64 apply(const char * begin, size_t size) { return sipHash64(begin, size); }
|
||||
static UInt64 combineHashes(UInt64 h1, UInt64 h2) { return combineHashesFunc<UInt64, SipHash64Impl>(h1, h2); }
|
||||
|
||||
static constexpr bool use_int_hash_for_pods = false;
|
||||
};
|
||||
@ -336,12 +317,10 @@ struct SipHash64KeyedImpl
|
||||
|
||||
static UInt64 combineHashesKeyed(const Key & key, UInt64 h1, UInt64 h2)
|
||||
{
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
h1 = std::byteswap(h1);
|
||||
h2 = std::byteswap(h2);
|
||||
#endif
|
||||
UInt64 hashes[] = {h1, h2};
|
||||
return applyKeyed(key, reinterpret_cast<const char *>(hashes), 2 * sizeof(UInt64));
|
||||
transformEndianness<std::endian::little>(h1);
|
||||
transformEndianness<std::endian::little>(h2);
|
||||
const UInt64 hashes[]{h1, h2};
|
||||
return applyKeyed(key, reinterpret_cast<const char *>(hashes), sizeof(hashes));
|
||||
}
|
||||
|
||||
static constexpr bool use_int_hash_for_pods = false;
|
||||
@ -353,15 +332,8 @@ struct SipHash128Impl
|
||||
|
||||
using ReturnType = UInt128;
|
||||
|
||||
static UInt128 combineHashes(UInt128 h1, UInt128 h2)
|
||||
{
|
||||
return combineHashesFunc<UInt128, SipHash128Impl>(h1, h2);
|
||||
}
|
||||
|
||||
static UInt128 apply(const char * data, const size_t size)
|
||||
{
|
||||
return sipHash128(data, size);
|
||||
}
|
||||
static UInt128 combineHashes(UInt128 h1, UInt128 h2) { return combineHashesFunc<UInt128, SipHash128Impl>(h1, h2); }
|
||||
static UInt128 apply(const char * data, const size_t size) { return sipHash128(data, size); }
|
||||
|
||||
static constexpr bool use_int_hash_for_pods = false;
|
||||
};
|
||||
@ -378,15 +350,10 @@ struct SipHash128KeyedImpl
|
||||
|
||||
static UInt128 combineHashesKeyed(const Key & key, UInt128 h1, UInt128 h2)
|
||||
{
|
||||
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
|
||||
UInt128 tmp;
|
||||
reverseMemcpy(&tmp, &h1, sizeof(UInt128));
|
||||
h1 = tmp;
|
||||
reverseMemcpy(&tmp, &h2, sizeof(UInt128));
|
||||
h2 = tmp;
|
||||
#endif
|
||||
UInt128 hashes[] = {h1, h2};
|
||||
return applyKeyed(key, reinterpret_cast<const char *>(hashes), 2 * sizeof(UInt128));
|
||||
transformEndianness<std::endian::little>(h1);
|
||||
transformEndianness<std::endian::little>(h2);
|
||||
const UInt128 hashes[]{h1, h2};
|
||||
return applyKeyed(key, reinterpret_cast<const char *>(hashes), sizeof(hashes));
|
||||
}
|
||||
|
||||
static constexpr bool use_int_hash_for_pods = false;
|
||||
@ -531,10 +498,7 @@ struct MurmurHash3Impl64
|
||||
return h[0] ^ h[1];
|
||||
}
|
||||
|
||||
static UInt64 combineHashes(UInt64 h1, UInt64 h2)
|
||||
{
|
||||
return IntHash64Impl::apply(h1) ^ h2;
|
||||
}
|
||||
static UInt64 combineHashes(UInt64 h1, UInt64 h2) { return IntHash64Impl::apply(h1) ^ h2; }
|
||||
|
||||
static constexpr bool use_int_hash_for_pods = false;
|
||||
};
|
||||
@ -552,10 +516,7 @@ struct MurmurHash3Impl128
|
||||
return *reinterpret_cast<UInt128 *>(bytes);
|
||||
}
|
||||
|
||||
static UInt128 combineHashes(UInt128 h1, UInt128 h2)
|
||||
{
|
||||
return combineHashesFunc<UInt128, MurmurHash3Impl128>(h1, h2);
|
||||
}
|
||||
static UInt128 combineHashes(UInt128 h1, UInt128 h2) { return combineHashesFunc<UInt128, MurmurHash3Impl128>(h1, h2); }
|
||||
|
||||
static constexpr bool use_int_hash_for_pods = false;
|
||||
};
|
||||
@ -1040,11 +1001,10 @@ private:
|
||||
if (const ColVecType * col_from = checkAndGetColumn<ColVecType>(column))
|
||||
{
|
||||
const typename ColVecType::Container & vec_from = col_from->getData();
|
||||
size_t size = vec_from.size();
|
||||
const size_t size = vec_from.size();
|
||||
for (size_t i = 0; i < size; ++i)
|
||||
{
|
||||
ToType hash;
|
||||
|
||||
if constexpr (Impl::use_int_hash_for_pods)
|
||||
{
|
||||
if constexpr (std::is_same_v<ToType, UInt64>)
|
||||
@ -1058,13 +1018,8 @@ private:
|
||||
hash = JavaHashImpl::apply(vec_from[i]);
|
||||
else
|
||||
{
|
||||
FromType value = vec_from[i];
|
||||
if constexpr (std::endian::native == std::endian::big)
|
||||
{
|
||||
FromType value_reversed;
|
||||
reverseMemcpy(&value_reversed, &value, sizeof(value));
|
||||
value = value_reversed;
|
||||
}
|
||||
auto value = vec_from[i];
|
||||
transformEndianness<std::endian::little>(value);
|
||||
hash = apply(key, reinterpret_cast<const char *>(&value), sizeof(value));
|
||||
}
|
||||
}
|
||||
@ -1078,8 +1033,8 @@ private:
|
||||
else if (auto col_from_const = checkAndGetColumnConst<ColVecType>(column))
|
||||
{
|
||||
auto value = col_from_const->template getValue<FromType>();
|
||||
ToType hash;
|
||||
|
||||
ToType hash;
|
||||
if constexpr (Impl::use_int_hash_for_pods)
|
||||
{
|
||||
if constexpr (std::is_same_v<ToType, UInt64>)
|
||||
@ -1093,17 +1048,12 @@ private:
|
||||
hash = JavaHashImpl::apply(value);
|
||||
else
|
||||
{
|
||||
if constexpr (std::endian::native == std::endian::big)
|
||||
{
|
||||
FromType value_reversed;
|
||||
reverseMemcpy(&value_reversed, &value, sizeof(value));
|
||||
value = value_reversed;
|
||||
}
|
||||
transformEndianness<std::endian::little>(value);
|
||||
hash = apply(key, reinterpret_cast<const char *>(&value), sizeof(value));
|
||||
}
|
||||
}
|
||||
|
||||
size_t size = vec_to.size();
|
||||
const size_t size = vec_to.size();
|
||||
if constexpr (first)
|
||||
vec_to.assign(size, hash);
|
||||
else
|
||||
@ -1120,6 +1070,16 @@ private:
|
||||
{
|
||||
using ColVecType = ColumnVectorOrDecimal<FromType>;
|
||||
|
||||
static const auto to_little_endian = [](auto & value)
|
||||
{
|
||||
// IPv6 addresses are parsed into four 32-bit components in big-endian ordering on both platforms, so no change is necessary.
|
||||
// Reference: `parseIPv6orIPv4` in src/Common/formatIPv6.h.
|
||||
if constexpr (std::endian::native == std::endian::big && std::is_same_v<std::remove_reference_t<decltype(value)>, IPv6>)
|
||||
return;
|
||||
|
||||
transformEndianness<std::endian::little>(value);
|
||||
};
|
||||
|
||||
if (const ColVecType * col_from = checkAndGetColumn<ColVecType>(column))
|
||||
{
|
||||
const typename ColVecType::Container & vec_from = col_from->getData();
|
||||
@ -1131,9 +1091,10 @@ private:
|
||||
hash = apply(key, reinterpret_cast<const char *>(&vec_from[i]), sizeof(vec_from[i]));
|
||||
else
|
||||
{
|
||||
char tmp_buffer[sizeof(vec_from[i])];
|
||||
reverseMemcpy(tmp_buffer, &vec_from[i], sizeof(vec_from[i]));
|
||||
hash = apply(key, reinterpret_cast<const char *>(tmp_buffer), sizeof(vec_from[i]));
|
||||
auto value = vec_from[i];
|
||||
to_little_endian(value);
|
||||
|
||||
hash = apply(key, reinterpret_cast<const char *>(&value), sizeof(value));
|
||||
}
|
||||
if constexpr (first)
|
||||
vec_to[i] = hash;
|
||||
@ -1144,17 +1105,10 @@ private:
|
||||
else if (auto col_from_const = checkAndGetColumnConst<ColVecType>(column))
|
||||
{
|
||||
auto value = col_from_const->template getValue<FromType>();
|
||||
to_little_endian(value);
|
||||
|
||||
ToType hash;
|
||||
if constexpr (std::endian::native == std::endian::little)
|
||||
hash = apply(key, reinterpret_cast<const char *>(&value), sizeof(value));
|
||||
else
|
||||
{
|
||||
char tmp_buffer[sizeof(value)];
|
||||
reverseMemcpy(tmp_buffer, &value, sizeof(value));
|
||||
hash = apply(key, reinterpret_cast<const char *>(tmp_buffer), sizeof(value));
|
||||
}
|
||||
size_t size = vec_to.size();
|
||||
const auto hash = apply(key, reinterpret_cast<const char *>(&value), sizeof(value));
|
||||
const size_t size = vec_to.size();
|
||||
if constexpr (first)
|
||||
vec_to.assign(size, hash);
|
||||
else
|
||||
@ -1423,6 +1377,9 @@ public:
|
||||
|
||||
if constexpr (std::is_same_v<ToType, UInt128>) /// backward-compatible
|
||||
{
|
||||
if (std::endian::native == std::endian::big)
|
||||
std::ranges::for_each(col_to->getData(), transformEndianness<std::endian::little, ToType>);
|
||||
|
||||
auto col_to_fixed_string = ColumnFixedString::create(sizeof(UInt128));
|
||||
const auto & data = col_to->getData();
|
||||
auto & chars = col_to_fixed_string->getChars();
|
||||
@ -1676,21 +1633,8 @@ struct ImplWyHash64
|
||||
static constexpr auto name = "wyHash64";
|
||||
using ReturnType = UInt64;
|
||||
|
||||
static UInt64 apply(const char * s, const size_t len)
|
||||
{
|
||||
return wyhash(s, len, 0, _wyp);
|
||||
}
|
||||
static UInt64 combineHashes(UInt64 h1, UInt64 h2)
|
||||
{
|
||||
union
|
||||
{
|
||||
UInt64 u64[2];
|
||||
char chars[16];
|
||||
};
|
||||
u64[0] = h1;
|
||||
u64[1] = h2;
|
||||
return apply(chars, 16);
|
||||
}
|
||||
static UInt64 apply(const char * s, const size_t len) { return wyhash(s, len, 0, _wyp); }
|
||||
static UInt64 combineHashes(UInt64 h1, UInt64 h2) { return combineHashesFunc<UInt64, ImplWyHash64>(h1, h2); }
|
||||
|
||||
static constexpr bool use_int_hash_for_pods = false;
|
||||
};
|
||||
|
||||
145
src/Functions/structureToFormatSchema.cpp
Normal file
145
src/Functions/structureToFormatSchema.cpp
Normal file
@ -0,0 +1,145 @@
|
||||
#include <Columns/ColumnString.h>
|
||||
#include <DataTypes/DataTypeString.h>
|
||||
#include <DataTypes/DataTypeEnum.h>
|
||||
#include <Functions/FunctionFactory.h>
|
||||
#include <Functions/IFunction.h>
|
||||
#include <Interpreters/parseColumnsListForTableFunction.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <IO/WriteBufferFromVector.h>
|
||||
#include <Formats/StructureToCapnProtoSchema.h>
|
||||
#include <Formats/StructureToProtobufSchema.h>
|
||||
|
||||
#include <Common/randomSeed.h>
|
||||
|
||||
|
||||
namespace DB
|
||||
{
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
|
||||
extern const int ILLEGAL_TYPE_OF_ARGUMENT;
|
||||
}
|
||||
|
||||
template <class Impl>
|
||||
class FunctionStructureToFormatSchema : public IFunction
|
||||
{
|
||||
public:
|
||||
|
||||
static constexpr auto name = Impl::name;
|
||||
explicit FunctionStructureToFormatSchema(ContextPtr context_) : context(std::move(context_))
|
||||
{
|
||||
}
|
||||
|
||||
static FunctionPtr create(ContextPtr ctx)
|
||||
{
|
||||
return std::make_shared<FunctionStructureToFormatSchema>(std::move(ctx));
|
||||
}
|
||||
|
||||
String getName() const override { return name; }
|
||||
|
||||
size_t getNumberOfArguments() const override { return 0; }
|
||||
bool isVariadic() const override { return true; }
|
||||
|
||||
bool isSuitableForShortCircuitArgumentsExecution(const DataTypesWithConstInfo & /*arguments*/) const override { return false; }
|
||||
ColumnNumbers getArgumentsThatAreAlwaysConstant() const override { return {0, 1}; }
|
||||
bool useDefaultImplementationForConstants() const override { return false; }
|
||||
bool useDefaultImplementationForNulls() const override { return false; }
|
||||
|
||||
DataTypePtr getReturnTypeImpl(const DataTypes & arguments) const override
|
||||
{
|
||||
if (arguments.empty() || arguments.size() > 2)
|
||||
throw Exception(
|
||||
ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
|
||||
"Number of arguments for function {} doesn't match: passed {}, expected 1 or 2",
|
||||
getName(), arguments.size());
|
||||
|
||||
if (!isString(arguments[0]))
|
||||
{
|
||||
throw Exception(
|
||||
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
|
||||
"Illegal type {} of the first argument of function {}, expected constant string",
|
||||
arguments[0]->getName(),
|
||||
getName());
|
||||
}
|
||||
|
||||
if (arguments.size() > 1 && !isString(arguments[1]))
|
||||
{
|
||||
throw Exception(
|
||||
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT,
|
||||
"Illegal type {} of the second argument of function {}, expected constant string",
|
||||
arguments[1]->getName(),
|
||||
getName());
|
||||
}
|
||||
|
||||
return std::make_shared<DataTypeString>();
|
||||
}
|
||||
|
||||
ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
|
||||
{
|
||||
if (arguments.empty() || arguments.size() > 2)
|
||||
throw Exception(
|
||||
ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH,
|
||||
"Number of arguments for function {} doesn't match: passed {}, expected 1 or 2",
|
||||
getName(), arguments.size());
|
||||
|
||||
String structure = arguments[0].column->getDataAt(0).toString();
|
||||
String message_name = arguments.size() == 2 ? arguments[1].column->getDataAt(0).toString() : "Message";
|
||||
auto columns_list = parseColumnsListFromString(structure, context);
|
||||
auto col_res = ColumnString::create();
|
||||
auto & data = assert_cast<ColumnString &>(*col_res).getChars();
|
||||
WriteBufferFromVector buf(data);
|
||||
Impl::writeSchema(buf, message_name, columns_list.getAll());
|
||||
buf.finalize();
|
||||
auto & offsets = assert_cast<ColumnString &>(*col_res).getOffsets();
|
||||
offsets.push_back(data.size());
|
||||
return ColumnConst::create(std::move(col_res), input_rows_count);
|
||||
}
|
||||
|
||||
private:
|
||||
ContextPtr context;
|
||||
};
|
||||
|
||||
|
||||
REGISTER_FUNCTION(StructureToCapnProtoSchema)
|
||||
{
|
||||
factory.registerFunction<FunctionStructureToFormatSchema<StructureToCapnProtoSchema>>(FunctionDocumentation
|
||||
{
|
||||
.description=R"(
|
||||
Function that converts ClickHouse table structure to CapnProto format schema
|
||||
)",
|
||||
.examples{
|
||||
{"random", "SELECT structureToCapnProtoSchema('s String, x UInt32', 'MessageName') format TSVRaw", "struct MessageName\n"
|
||||
"{\n"
|
||||
" s @0 : Data;\n"
|
||||
" x @1 : UInt32;\n"
|
||||
"}"},
|
||||
},
|
||||
.categories{"Other"}
|
||||
},
|
||||
FunctionFactory::CaseSensitive);
|
||||
}
|
||||
|
||||
|
||||
REGISTER_FUNCTION(StructureToProtobufSchema)
|
||||
{
|
||||
factory.registerFunction<FunctionStructureToFormatSchema<StructureToProtobufSchema>>(FunctionDocumentation
|
||||
{
|
||||
.description=R"(
|
||||
Function that converts ClickHouse table structure to Protobuf format schema
|
||||
)",
|
||||
.examples{
|
||||
{"random", "SELECT structureToCapnProtoSchema('s String, x UInt32', 'MessageName') format TSVRaw", "syntax = \"proto3\";\n"
|
||||
"\n"
|
||||
"message MessageName\n"
|
||||
"{\n"
|
||||
" bytes s = 1;\n"
|
||||
" uint32 x = 2;\n"
|
||||
"}"},
|
||||
},
|
||||
.categories{"Other"}
|
||||
},
|
||||
FunctionFactory::CaseSensitive);
|
||||
}
|
||||
|
||||
}
|
||||
@ -529,6 +529,11 @@ void tryReadIntTextUnsafe(T & x, ReadBuffer & buf)
|
||||
template <typename T> void readFloatText(T & x, ReadBuffer & in);
|
||||
template <typename T> bool tryReadFloatText(T & x, ReadBuffer & in);
|
||||
|
||||
template <typename T> void readFloatTextPrecise(T & x, ReadBuffer & in);
|
||||
template <typename T> bool tryReadFloatTextPrecise(T & x, ReadBuffer & in);
|
||||
template <typename T> void readFloatTextFast(T & x, ReadBuffer & in);
|
||||
template <typename T> bool tryReadFloatTextFast(T & x, ReadBuffer & in);
|
||||
|
||||
|
||||
/// simple: all until '\n' or '\t'
|
||||
void readString(String & s, ReadBuffer & buf);
|
||||
|
||||
@ -764,7 +764,7 @@ InterpreterCreateQuery::TableProperties InterpreterCreateQuery::getTableProperti
|
||||
/// Table function without columns list.
|
||||
auto table_function_ast = create.as_table_function->ptr();
|
||||
auto table_function = TableFunctionFactory::instance().get(table_function_ast, getContext());
|
||||
properties.columns = table_function->getActualTableStructure(getContext());
|
||||
properties.columns = table_function->getActualTableStructure(getContext(), /*is_insert_query*/ true);
|
||||
}
|
||||
else if (create.is_dictionary)
|
||||
{
|
||||
|
||||
@ -96,7 +96,7 @@ BlockIO InterpreterDescribeQuery::execute()
|
||||
else if (table_expression.table_function)
|
||||
{
|
||||
TableFunctionPtr table_function_ptr = TableFunctionFactory::instance().get(table_expression.table_function, getContext());
|
||||
auto table_function_column_descriptions = table_function_ptr->getActualTableStructure(getContext());
|
||||
auto table_function_column_descriptions = table_function_ptr->getActualTableStructure(getContext(), /*is_insert_query*/ true);
|
||||
for (const auto & table_function_column_description : table_function_column_descriptions)
|
||||
columns.emplace_back(table_function_column_description);
|
||||
}
|
||||
|
||||
@ -1034,7 +1034,7 @@ std::shared_ptr<Block> MergeJoin::loadRightBlock(size_t pos) const
|
||||
{
|
||||
auto load_func = [&]() -> std::shared_ptr<Block>
|
||||
{
|
||||
TemporaryFileStreamLegacy input(flushed_right_blocks[pos]->getPath(), materializeBlock(right_sample_block));
|
||||
TemporaryFileStreamLegacy input(flushed_right_blocks[pos]->getAbsolutePath(), materializeBlock(right_sample_block));
|
||||
return std::make_shared<Block>(input.block_in->read());
|
||||
};
|
||||
|
||||
|
||||
@ -39,7 +39,7 @@ namespace
|
||||
TemporaryFileOnDiskHolder flushToFile(const DiskPtr & disk, const Block & header, QueryPipelineBuilder pipeline, const String & codec)
|
||||
{
|
||||
auto tmp_file = std::make_unique<TemporaryFileOnDisk>(disk, CurrentMetrics::TemporaryFilesForJoin);
|
||||
auto write_stat = TemporaryFileStreamLegacy::write(tmp_file->getPath(), header, std::move(pipeline), codec);
|
||||
auto write_stat = TemporaryFileStreamLegacy::write(tmp_file->getAbsolutePath(), header, std::move(pipeline), codec);
|
||||
|
||||
ProfileEvents::increment(ProfileEvents::ExternalProcessingCompressedBytesTotal, write_stat.compressed_bytes);
|
||||
ProfileEvents::increment(ProfileEvents::ExternalProcessingUncompressedBytesTotal, write_stat.uncompressed_bytes);
|
||||
@ -267,7 +267,7 @@ SortedBlocksWriter::SortedFiles SortedBlocksWriter::finishMerge(std::function<vo
|
||||
|
||||
Pipe SortedBlocksWriter::streamFromFile(const TmpFilePtr & file) const
|
||||
{
|
||||
return Pipe(std::make_shared<TemporaryFileLazySource>(file->getPath(), materializeBlock(sample_block)));
|
||||
return Pipe(std::make_shared<TemporaryFileLazySource>(file->getAbsolutePath(), materializeBlock(sample_block)));
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -235,9 +235,9 @@ TemporaryFileStream::TemporaryFileStream(TemporaryFileOnDiskHolder file_, const
|
||||
: parent(parent_)
|
||||
, header(header_)
|
||||
, file(std::move(file_))
|
||||
, out_writer(std::make_unique<OutputWriter>(std::make_unique<WriteBufferFromFile>(file->getPath()), header))
|
||||
, out_writer(std::make_unique<OutputWriter>(std::make_unique<WriteBufferFromFile>(file->getAbsolutePath()), header))
|
||||
{
|
||||
LOG_TEST(&Poco::Logger::get("TemporaryFileStream"), "Writing to temporary file {}", file->getPath());
|
||||
LOG_TEST(&Poco::Logger::get("TemporaryFileStream"), "Writing to temporary file {}", file->getAbsolutePath());
|
||||
}
|
||||
|
||||
TemporaryFileStream::TemporaryFileStream(FileSegmentsHolderPtr segments_, const Block & header_, TemporaryDataOnDisk * parent_)
|
||||
@ -365,7 +365,7 @@ void TemporaryFileStream::release()
|
||||
String TemporaryFileStream::getPath() const
|
||||
{
|
||||
if (file)
|
||||
return file->getPath();
|
||||
return file->getAbsolutePath();
|
||||
if (segment_holder && !segment_holder->empty())
|
||||
return segment_holder->front().getPathInLocalCache();
|
||||
|
||||
|
||||
@ -17,12 +17,12 @@ namespace ErrorCodes
|
||||
extern const int INCORRECT_DATA;
|
||||
}
|
||||
|
||||
CapnProtoRowInputFormat::CapnProtoRowInputFormat(ReadBuffer & in_, Block header_, Params params_, const FormatSchemaInfo & info, const FormatSettings & format_settings)
|
||||
CapnProtoRowInputFormat::CapnProtoRowInputFormat(ReadBuffer & in_, Block header_, Params params_, const CapnProtoSchemaInfo & info, const FormatSettings & format_settings)
|
||||
: IRowInputFormat(std::move(header_), in_, std::move(params_))
|
||||
, parser(std::make_shared<CapnProtoSchemaParser>())
|
||||
{
|
||||
// Parse the schema and fetch the root object
|
||||
schema = parser->getMessageSchema(info);
|
||||
schema = parser->getMessageSchema(info.getSchemaInfo());
|
||||
const auto & header = getPort().getHeader();
|
||||
serializer = std::make_unique<CapnProtoSerializer>(header.getDataTypes(), header.getNames(), schema, format_settings.capn_proto);
|
||||
}
|
||||
@ -106,8 +106,12 @@ void registerInputFormatCapnProto(FormatFactory & factory)
|
||||
"CapnProto",
|
||||
[](ReadBuffer & buf, const Block & sample, IRowInputFormat::Params params, const FormatSettings & settings)
|
||||
{
|
||||
return std::make_shared<CapnProtoRowInputFormat>(buf, sample, std::move(params),
|
||||
FormatSchemaInfo(settings, "CapnProto", true), settings);
|
||||
return std::make_shared<CapnProtoRowInputFormat>(
|
||||
buf,
|
||||
sample,
|
||||
std::move(params),
|
||||
CapnProtoSchemaInfo(settings, "CapnProto", sample, settings.capn_proto.use_autogenerated_schema),
|
||||
settings);
|
||||
});
|
||||
factory.markFormatSupportsSubsetOfColumns("CapnProto");
|
||||
factory.registerFileExtension("capnp", "CapnProto");
|
||||
|
||||
@ -24,7 +24,7 @@ class ReadBuffer;
|
||||
class CapnProtoRowInputFormat final : public IRowInputFormat
|
||||
{
|
||||
public:
|
||||
CapnProtoRowInputFormat(ReadBuffer & in_, Block header, Params params_, const FormatSchemaInfo & info, const FormatSettings & format_settings_);
|
||||
CapnProtoRowInputFormat(ReadBuffer & in_, Block header, Params params_, const CapnProtoSchemaInfo & info, const FormatSettings & format_settings);
|
||||
|
||||
String getName() const override { return "CapnProtoRowInputFormat"; }
|
||||
|
||||
|
||||
@ -23,14 +23,14 @@ void CapnProtoOutputStream::write(const void * buffer, size_t size)
|
||||
CapnProtoRowOutputFormat::CapnProtoRowOutputFormat(
|
||||
WriteBuffer & out_,
|
||||
const Block & header_,
|
||||
const FormatSchemaInfo & info,
|
||||
const CapnProtoSchemaInfo & info,
|
||||
const FormatSettings & format_settings)
|
||||
: IRowOutputFormat(header_, out_)
|
||||
, column_names(header_.getNames())
|
||||
, column_types(header_.getDataTypes())
|
||||
, output_stream(std::make_unique<CapnProtoOutputStream>(out_))
|
||||
{
|
||||
schema = schema_parser.getMessageSchema(info);
|
||||
schema = schema_parser.getMessageSchema(info.getSchemaInfo());
|
||||
const auto & header = getPort(PortKind::Main).getHeader();
|
||||
serializer = std::make_unique<CapnProtoSerializer>(header.getDataTypes(), header.getNames(), schema, format_settings.capn_proto);
|
||||
capnp::MallocMessageBuilder message;
|
||||
@ -52,7 +52,11 @@ void registerOutputFormatCapnProto(FormatFactory & factory)
|
||||
const Block & sample,
|
||||
const FormatSettings & format_settings)
|
||||
{
|
||||
return std::make_shared<CapnProtoRowOutputFormat>(buf, sample, FormatSchemaInfo(format_settings, "CapnProto", true), format_settings);
|
||||
return std::make_shared<CapnProtoRowOutputFormat>(
|
||||
buf,
|
||||
sample,
|
||||
CapnProtoSchemaInfo(format_settings, "CapnProto", sample, format_settings.capn_proto.use_autogenerated_schema),
|
||||
format_settings);
|
||||
});
|
||||
}
|
||||
|
||||
|
||||
@ -31,8 +31,8 @@ public:
|
||||
CapnProtoRowOutputFormat(
|
||||
WriteBuffer & out_,
|
||||
const Block & header_,
|
||||
const FormatSchemaInfo & info,
|
||||
const FormatSettings & format_settings_);
|
||||
const CapnProtoSchemaInfo & info,
|
||||
const FormatSettings & format_settings);
|
||||
|
||||
String getName() const override { return "CapnProtoRowOutputFormat"; }
|
||||
|
||||
|
||||
@ -14,7 +14,7 @@ ProtobufListInputFormat::ProtobufListInputFormat(
|
||||
ReadBuffer & in_,
|
||||
const Block & header_,
|
||||
const Params & params_,
|
||||
const FormatSchemaInfo & schema_info_,
|
||||
const ProtobufSchemaInfo & schema_info_,
|
||||
bool flatten_google_wrappers_)
|
||||
: IRowInputFormat(header_, in_, params_)
|
||||
, reader(std::make_unique<ProtobufReader>(in_))
|
||||
@ -22,7 +22,7 @@ ProtobufListInputFormat::ProtobufListInputFormat(
|
||||
header_.getNames(),
|
||||
header_.getDataTypes(),
|
||||
missing_column_indices,
|
||||
*ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_, ProtobufSchemas::WithEnvelope::Yes),
|
||||
*ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_.getSchemaInfo(), ProtobufSchemas::WithEnvelope::Yes),
|
||||
/* with_length_delimiter = */ true,
|
||||
/* with_envelope = */ true,
|
||||
flatten_google_wrappers_,
|
||||
@ -84,7 +84,7 @@ void registerInputFormatProtobufList(FormatFactory & factory)
|
||||
const FormatSettings & settings)
|
||||
{
|
||||
return std::make_shared<ProtobufListInputFormat>(buf, sample, std::move(params),
|
||||
FormatSchemaInfo(settings, "Protobuf", true), settings.protobuf.input_flatten_google_wrappers);
|
||||
ProtobufSchemaInfo(settings, "Protobuf", sample, settings.protobuf.use_autogenerated_schema), settings.protobuf.input_flatten_google_wrappers);
|
||||
});
|
||||
factory.markFormatSupportsSubsetOfColumns("ProtobufList");
|
||||
factory.registerAdditionalInfoForSchemaCacheGetter(
|
||||
|
||||
@ -28,7 +28,7 @@ public:
|
||||
ReadBuffer & in_,
|
||||
const Block & header_,
|
||||
const Params & params_,
|
||||
const FormatSchemaInfo & schema_info_,
|
||||
const ProtobufSchemaInfo & schema_info_,
|
||||
bool flatten_google_wrappers_);
|
||||
|
||||
String getName() const override { return "ProtobufListInputFormat"; }
|
||||
|
||||
@ -2,7 +2,6 @@
|
||||
|
||||
#if USE_PROTOBUF
|
||||
# include <Formats/FormatFactory.h>
|
||||
# include <Formats/FormatSchemaInfo.h>
|
||||
# include <Formats/ProtobufWriter.h>
|
||||
# include <Formats/ProtobufSerializer.h>
|
||||
# include <Formats/ProtobufSchemas.h>
|
||||
@ -13,14 +12,14 @@ namespace DB
|
||||
ProtobufListOutputFormat::ProtobufListOutputFormat(
|
||||
WriteBuffer & out_,
|
||||
const Block & header_,
|
||||
const FormatSchemaInfo & schema_info_,
|
||||
const ProtobufSchemaInfo & schema_info_,
|
||||
bool defaults_for_nullable_google_wrappers_)
|
||||
: IRowOutputFormat(header_, out_)
|
||||
, writer(std::make_unique<ProtobufWriter>(out))
|
||||
, serializer(ProtobufSerializer::create(
|
||||
header_.getNames(),
|
||||
header_.getDataTypes(),
|
||||
*ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_, ProtobufSchemas::WithEnvelope::Yes),
|
||||
*ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_.getSchemaInfo(), ProtobufSchemas::WithEnvelope::Yes),
|
||||
/* with_length_delimiter = */ true,
|
||||
/* with_envelope = */ true,
|
||||
defaults_for_nullable_google_wrappers_,
|
||||
@ -55,7 +54,7 @@ void registerOutputFormatProtobufList(FormatFactory & factory)
|
||||
const FormatSettings & settings)
|
||||
{
|
||||
return std::make_shared<ProtobufListOutputFormat>(
|
||||
buf, header, FormatSchemaInfo(settings, "Protobuf", true),
|
||||
buf, header, ProtobufSchemaInfo(settings, "Protobuf", header, settings.protobuf.use_autogenerated_schema),
|
||||
settings.protobuf.output_nullables_with_google_wrappers);
|
||||
});
|
||||
}
|
||||
|
||||
@ -4,10 +4,10 @@
|
||||
|
||||
#if USE_PROTOBUF
|
||||
# include <Processors/Formats/IRowOutputFormat.h>
|
||||
# include <Formats/FormatSchemaInfo.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
class FormatSchemaInfo;
|
||||
class ProtobufWriter;
|
||||
class ProtobufSerializer;
|
||||
|
||||
@ -26,7 +26,7 @@ public:
|
||||
ProtobufListOutputFormat(
|
||||
WriteBuffer & out_,
|
||||
const Block & header_,
|
||||
const FormatSchemaInfo & schema_info_,
|
||||
const ProtobufSchemaInfo & schema_info_,
|
||||
bool defaults_for_nullable_google_wrappers_);
|
||||
|
||||
String getName() const override { return "ProtobufListOutputFormat"; }
|
||||
|
||||
@ -11,9 +11,9 @@ namespace DB
|
||||
{
|
||||
|
||||
ProtobufRowInputFormat::ProtobufRowInputFormat(ReadBuffer & in_, const Block & header_, const Params & params_,
|
||||
const FormatSchemaInfo & schema_info_, bool with_length_delimiter_, bool flatten_google_wrappers_)
|
||||
const ProtobufSchemaInfo & schema_info_, bool with_length_delimiter_, bool flatten_google_wrappers_)
|
||||
: IRowInputFormat(header_, in_, params_)
|
||||
, message_descriptor(ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_, ProtobufSchemas::WithEnvelope::No))
|
||||
, message_descriptor(ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_.getSchemaInfo(), ProtobufSchemas::WithEnvelope::No))
|
||||
, with_length_delimiter(with_length_delimiter_)
|
||||
, flatten_google_wrappers(flatten_google_wrappers_)
|
||||
{
|
||||
@ -89,7 +89,7 @@ void registerInputFormatProtobuf(FormatFactory & factory)
|
||||
const FormatSettings & settings)
|
||||
{
|
||||
return std::make_shared<ProtobufRowInputFormat>(buf, sample, std::move(params),
|
||||
FormatSchemaInfo(settings, "Protobuf", true),
|
||||
ProtobufSchemaInfo(settings, "Protobuf", sample, settings.protobuf.use_autogenerated_schema),
|
||||
with_length_delimiter,
|
||||
settings.protobuf.input_flatten_google_wrappers);
|
||||
});
|
||||
|
||||
@ -33,7 +33,7 @@ public:
|
||||
ReadBuffer & in_,
|
||||
const Block & header_,
|
||||
const Params & params_,
|
||||
const FormatSchemaInfo & schema_info_,
|
||||
const ProtobufSchemaInfo & schema_info_,
|
||||
bool with_length_delimiter_,
|
||||
bool flatten_google_wrappers_);
|
||||
|
||||
|
||||
@ -3,7 +3,6 @@
|
||||
#if USE_PROTOBUF
|
||||
# include <Formats/FormatFactory.h>
|
||||
# include <Core/Block.h>
|
||||
# include <Formats/FormatSchemaInfo.h>
|
||||
# include <Formats/FormatSettings.h>
|
||||
# include <Formats/ProtobufSchemas.h>
|
||||
# include <Formats/ProtobufSerializer.h>
|
||||
@ -20,7 +19,7 @@ namespace ErrorCodes
|
||||
ProtobufRowOutputFormat::ProtobufRowOutputFormat(
|
||||
WriteBuffer & out_,
|
||||
const Block & header_,
|
||||
const FormatSchemaInfo & schema_info_,
|
||||
const ProtobufSchemaInfo & schema_info_,
|
||||
const FormatSettings & settings_,
|
||||
bool with_length_delimiter_)
|
||||
: IRowOutputFormat(header_, out_)
|
||||
@ -28,7 +27,7 @@ ProtobufRowOutputFormat::ProtobufRowOutputFormat(
|
||||
, serializer(ProtobufSerializer::create(
|
||||
header_.getNames(),
|
||||
header_.getDataTypes(),
|
||||
*ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_, ProtobufSchemas::WithEnvelope::No),
|
||||
*ProtobufSchemas::instance().getMessageTypeForFormatSchema(schema_info_.getSchemaInfo(), ProtobufSchemas::WithEnvelope::No),
|
||||
with_length_delimiter_,
|
||||
/* with_envelope = */ false,
|
||||
settings_.protobuf.output_nullables_with_google_wrappers,
|
||||
@ -61,7 +60,7 @@ void registerOutputFormatProtobuf(FormatFactory & factory)
|
||||
const FormatSettings & settings)
|
||||
{
|
||||
return std::make_shared<ProtobufRowOutputFormat>(
|
||||
buf, header, FormatSchemaInfo(settings, "Protobuf", true),
|
||||
buf, header, ProtobufSchemaInfo(settings, "Protobuf", header, settings.protobuf.use_autogenerated_schema),
|
||||
settings, with_length_delimiter);
|
||||
});
|
||||
}
|
||||
|
||||
@ -4,11 +4,11 @@
|
||||
|
||||
#if USE_PROTOBUF
|
||||
# include <Processors/Formats/IRowOutputFormat.h>
|
||||
# include <Formats/FormatSchemaInfo.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
class DB;
|
||||
class FormatSchemaInfo;
|
||||
class ProtobufSerializer;
|
||||
class ProtobufWriter;
|
||||
class WriteBuffer;
|
||||
@ -30,7 +30,7 @@ public:
|
||||
ProtobufRowOutputFormat(
|
||||
WriteBuffer & out_,
|
||||
const Block & header_,
|
||||
const FormatSchemaInfo & schema_info_,
|
||||
const ProtobufSchemaInfo & schema_info_,
|
||||
const FormatSettings & settings_,
|
||||
bool with_length_delimiter_);
|
||||
|
||||
|
||||
@ -5,6 +5,7 @@ namespace DB
|
||||
|
||||
namespace ErrorCodes
|
||||
{
|
||||
extern const int LOGICAL_ERROR;
|
||||
extern const int SET_SIZE_LIMIT_EXCEEDED;
|
||||
}
|
||||
|
||||
@ -126,9 +127,20 @@ bool DistinctSortedChunkTransform::isKey(const size_t key_pos, const size_t row_
|
||||
|
||||
bool DistinctSortedChunkTransform::isLatestKeyFromPrevChunk(const size_t row_pos) const
|
||||
{
|
||||
for (size_t i = 0; i < sorted_columns.size(); ++i)
|
||||
for (size_t i = 0, s = sorted_columns.size(); i < s; ++i)
|
||||
{
|
||||
const int res = prev_chunk_latest_key[i]->compareAt(0, row_pos, *sorted_columns[i], sorted_columns_descr[i].nulls_direction);
|
||||
const auto & sorted_column = *sorted_columns[i];
|
||||
/// temporary hardening due to suspious crashes in sqlancer tests
|
||||
if (unlikely(sorted_column.size() <= row_pos))
|
||||
throw Exception(
|
||||
ErrorCodes::LOGICAL_ERROR,
|
||||
"Unexpected size of a sorted column: size {}, row_pos {}, column position {}, type {}",
|
||||
sorted_column.size(),
|
||||
row_pos,
|
||||
i,
|
||||
sorted_column.getFamilyName());
|
||||
|
||||
const int res = prev_chunk_latest_key[i]->compareAt(0, row_pos, sorted_column, sorted_columns_descr[i].nulls_direction);
|
||||
if (res != 0)
|
||||
return false;
|
||||
}
|
||||
|
||||
@ -159,7 +159,7 @@ void PartialSortingTransform::transform(Chunk & chunk)
|
||||
{
|
||||
MutableColumnPtr sort_description_threshold_column_updated = raw_block_columns[i]->cloneEmpty();
|
||||
sort_description_threshold_column_updated->insertFrom(*raw_block_columns[i], min_row_to_compare);
|
||||
sort_description_threshold_columns_updated[i] = std::move(sort_description_threshold_column_updated);
|
||||
sort_description_threshold_columns_updated[i] = sort_description_threshold_column_updated->convertToFullColumnIfSparse();
|
||||
}
|
||||
|
||||
sort_description_threshold_columns = std::move(sort_description_threshold_columns_updated);
|
||||
|
||||
@ -175,10 +175,13 @@ struct SocketInterruptablePollWrapper
|
||||
}
|
||||
while (rc < 0 && errno == POCO_EINTR);
|
||||
|
||||
if (rc >= 1 && poll_buf[0].revents & POLLIN)
|
||||
socket_ready = true;
|
||||
if (rc >= 2 && poll_buf[1].revents & POLLIN)
|
||||
fd_ready = true;
|
||||
if (rc >= 1)
|
||||
{
|
||||
if (poll_buf[0].revents & POLLIN)
|
||||
socket_ready = true;
|
||||
if (poll_buf[1].revents & POLLIN)
|
||||
fd_ready = true;
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
@ -250,15 +250,16 @@ StorageKafka::StorageKafka(
|
||||
: IStorage(table_id_)
|
||||
, WithContext(context_->getGlobalContext())
|
||||
, kafka_settings(std::move(kafka_settings_))
|
||||
, topics(parseTopics(getContext()->getMacros()->expand(kafka_settings->kafka_topic_list.value)))
|
||||
, brokers(getContext()->getMacros()->expand(kafka_settings->kafka_broker_list.value))
|
||||
, group(getContext()->getMacros()->expand(kafka_settings->kafka_group_name.value))
|
||||
, macros_info{.table_id = table_id_}
|
||||
, topics(parseTopics(getContext()->getMacros()->expand(kafka_settings->kafka_topic_list.value, macros_info)))
|
||||
, brokers(getContext()->getMacros()->expand(kafka_settings->kafka_broker_list.value, macros_info))
|
||||
, group(getContext()->getMacros()->expand(kafka_settings->kafka_group_name.value, macros_info))
|
||||
, client_id(
|
||||
kafka_settings->kafka_client_id.value.empty() ? getDefaultClientId(table_id_)
|
||||
: getContext()->getMacros()->expand(kafka_settings->kafka_client_id.value))
|
||||
: getContext()->getMacros()->expand(kafka_settings->kafka_client_id.value, macros_info))
|
||||
, format_name(getContext()->getMacros()->expand(kafka_settings->kafka_format.value))
|
||||
, max_rows_per_message(kafka_settings->kafka_max_rows_per_message.value)
|
||||
, schema_name(getContext()->getMacros()->expand(kafka_settings->kafka_schema.value))
|
||||
, schema_name(getContext()->getMacros()->expand(kafka_settings->kafka_schema.value, macros_info))
|
||||
, num_consumers(kafka_settings->kafka_num_consumers.value)
|
||||
, log(&Poco::Logger::get("StorageKafka (" + table_id_.table_name + ")"))
|
||||
, semaphore(0, static_cast<int>(num_consumers))
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
#pragma once
|
||||
|
||||
#include <Common/Macros.h>
|
||||
#include <Core/BackgroundSchedulePool.h>
|
||||
#include <Storages/IStorage.h>
|
||||
#include <Storages/Kafka/KafkaConsumer.h>
|
||||
@ -79,6 +80,7 @@ public:
|
||||
private:
|
||||
// Configuration and state
|
||||
std::unique_ptr<KafkaSettings> kafka_settings;
|
||||
Macros::MacroExpansionInfo macros_info;
|
||||
const Names topics;
|
||||
const String brokers;
|
||||
const String group;
|
||||
|
||||
@ -350,7 +350,7 @@ void DataPartStorageOnDiskBase::backup(
|
||||
temp_dir_it = temp_dirs->emplace(disk, std::make_shared<TemporaryFileOnDisk>(disk, "tmp/")).first;
|
||||
|
||||
temp_dir_owner = temp_dir_it->second;
|
||||
fs::path temp_dir = temp_dir_owner->getPath();
|
||||
fs::path temp_dir = temp_dir_owner->getRelativePath();
|
||||
temp_part_dir = temp_dir / part_path_in_backup.relative_path();
|
||||
disk->createDirectories(temp_part_dir);
|
||||
}
|
||||
|
||||
@ -5266,7 +5266,7 @@ public:
|
||||
auto it = temp_dirs.find(disk);
|
||||
if (it == temp_dirs.end())
|
||||
it = temp_dirs.emplace(disk, std::make_shared<TemporaryFileOnDisk>(disk, "tmp/")).first;
|
||||
return it->second->getPath();
|
||||
return it->second->getRelativePath();
|
||||
}
|
||||
|
||||
private:
|
||||
|
||||
@ -86,7 +86,7 @@ const std::unordered_set<std::string_view> optional_configuration_keys = {
|
||||
|
||||
bool isConnectionString(const std::string & candidate)
|
||||
{
|
||||
return candidate.starts_with("DefaultEndpointsProtocol");
|
||||
return !candidate.starts_with("http");
|
||||
}
|
||||
|
||||
}
|
||||
@ -257,7 +257,7 @@ void registerStorageAzureBlob(StorageFactory & factory)
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "External data source must have arguments");
|
||||
|
||||
auto configuration = StorageAzureBlob::getConfiguration(engine_args, args.getLocalContext());
|
||||
auto client = StorageAzureBlob::createClient(configuration);
|
||||
auto client = StorageAzureBlob::createClient(configuration, /* is_read_only */ false);
|
||||
// Use format settings from global server context + settings from
|
||||
// the SETTINGS clause of the create query. Settings from current
|
||||
// session and user are ignored.
|
||||
@ -309,58 +309,113 @@ void registerStorageAzureBlob(StorageFactory & factory)
|
||||
});
|
||||
}
|
||||
|
||||
AzureClientPtr StorageAzureBlob::createClient(StorageAzureBlob::Configuration configuration)
|
||||
static bool containerExists(std::unique_ptr<BlobServiceClient> &blob_service_client, std::string container_name)
|
||||
{
|
||||
Azure::Storage::Blobs::ListBlobContainersOptions options;
|
||||
options.Prefix = container_name;
|
||||
options.PageSizeHint = 1;
|
||||
|
||||
auto containers_list_response = blob_service_client->ListBlobContainers(options);
|
||||
auto containers_list = containers_list_response.BlobContainers;
|
||||
|
||||
for (const auto & container : containers_list)
|
||||
{
|
||||
if (container_name == container.Name)
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
AzureClientPtr StorageAzureBlob::createClient(StorageAzureBlob::Configuration configuration, bool is_read_only)
|
||||
{
|
||||
AzureClientPtr result;
|
||||
|
||||
if (configuration.is_connection_string)
|
||||
{
|
||||
std::unique_ptr<BlobServiceClient> blob_service_client = std::make_unique<BlobServiceClient>(BlobServiceClient::CreateFromConnectionString(configuration.connection_url));
|
||||
result = std::make_unique<BlobContainerClient>(BlobContainerClient::CreateFromConnectionString(configuration.connection_url, configuration.container));
|
||||
result->CreateIfNotExists();
|
||||
}
|
||||
else
|
||||
{
|
||||
if (configuration.account_name.has_value() && configuration.account_key.has_value())
|
||||
bool container_exists = containerExists(blob_service_client,configuration.container);
|
||||
|
||||
if (!container_exists)
|
||||
{
|
||||
auto storage_shared_key_credential = std::make_shared<Azure::Storage::StorageSharedKeyCredential>(*configuration.account_name, *configuration.account_key);
|
||||
auto blob_service_client = std::make_unique<BlobServiceClient>(configuration.connection_url, storage_shared_key_credential);
|
||||
if (is_read_only)
|
||||
throw Exception(
|
||||
ErrorCodes::DATABASE_ACCESS_DENIED,
|
||||
"AzureBlobStorage container does not exist '{}'",
|
||||
configuration.container);
|
||||
|
||||
try
|
||||
{
|
||||
result = std::make_unique<BlobContainerClient>(blob_service_client->CreateBlobContainer(configuration.container).Value);
|
||||
}
|
||||
catch (const Azure::Storage::StorageException & e)
|
||||
result->CreateIfNotExists();
|
||||
} catch (const Azure::Storage::StorageException & e)
|
||||
{
|
||||
if (e.StatusCode == Azure::Core::Http::HttpStatusCode::Conflict)
|
||||
{
|
||||
auto final_url = configuration.connection_url
|
||||
+ (configuration.connection_url.back() == '/' ? "" : "/")
|
||||
+ configuration.container;
|
||||
|
||||
result = std::make_unique<BlobContainerClient>(final_url, storage_shared_key_credential);
|
||||
}
|
||||
else
|
||||
if (!(e.StatusCode == Azure::Core::Http::HttpStatusCode::Conflict
|
||||
&& e.ReasonPhrase == "The specified container already exists."))
|
||||
{
|
||||
throw;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
std::shared_ptr<Azure::Storage::StorageSharedKeyCredential> storage_shared_key_credential;
|
||||
if (configuration.account_name.has_value() && configuration.account_key.has_value())
|
||||
{
|
||||
storage_shared_key_credential
|
||||
= std::make_shared<Azure::Storage::StorageSharedKeyCredential>(*configuration.account_name, *configuration.account_key);
|
||||
}
|
||||
|
||||
std::unique_ptr<BlobServiceClient> blob_service_client;
|
||||
if (storage_shared_key_credential)
|
||||
{
|
||||
blob_service_client = std::make_unique<BlobServiceClient>(configuration.connection_url, storage_shared_key_credential);
|
||||
}
|
||||
else
|
||||
{
|
||||
auto managed_identity_credential = std::make_shared<Azure::Identity::ManagedIdentityCredential>();
|
||||
auto blob_service_client = std::make_unique<BlobServiceClient>(configuration.connection_url, managed_identity_credential);
|
||||
blob_service_client = std::make_unique<BlobServiceClient>(configuration.connection_url);
|
||||
}
|
||||
|
||||
bool container_exists = containerExists(blob_service_client,configuration.container);
|
||||
|
||||
std::string final_url;
|
||||
size_t pos = configuration.connection_url.find('?');
|
||||
if (pos != std::string::npos)
|
||||
{
|
||||
auto url_without_sas = configuration.connection_url.substr(0, pos);
|
||||
final_url = url_without_sas + (url_without_sas.back() == '/' ? "" : "/") + configuration.container
|
||||
+ configuration.connection_url.substr(pos);
|
||||
}
|
||||
else
|
||||
final_url
|
||||
= configuration.connection_url + (configuration.connection_url.back() == '/' ? "" : "/") + configuration.container;
|
||||
|
||||
if (container_exists)
|
||||
{
|
||||
if (storage_shared_key_credential)
|
||||
result = std::make_unique<BlobContainerClient>(final_url, storage_shared_key_credential);
|
||||
else
|
||||
result = std::make_unique<BlobContainerClient>(final_url);
|
||||
}
|
||||
else
|
||||
{
|
||||
if (is_read_only)
|
||||
throw Exception(
|
||||
ErrorCodes::DATABASE_ACCESS_DENIED,
|
||||
"AzureBlobStorage container does not exist '{}'",
|
||||
configuration.container);
|
||||
try
|
||||
{
|
||||
result = std::make_unique<BlobContainerClient>(blob_service_client->CreateBlobContainer(configuration.container).Value);
|
||||
}
|
||||
catch (const Azure::Storage::StorageException & e)
|
||||
} catch (const Azure::Storage::StorageException & e)
|
||||
{
|
||||
if (e.StatusCode == Azure::Core::Http::HttpStatusCode::Conflict)
|
||||
if (e.StatusCode == Azure::Core::Http::HttpStatusCode::Conflict
|
||||
&& e.ReasonPhrase == "The specified container already exists.")
|
||||
{
|
||||
auto final_url = configuration.connection_url
|
||||
+ (configuration.connection_url.back() == '/' ? "" : "/")
|
||||
+ configuration.container;
|
||||
|
||||
result = std::make_unique<BlobContainerClient>(final_url, managed_identity_credential);
|
||||
if (storage_shared_key_credential)
|
||||
result = std::make_unique<BlobContainerClient>(final_url, storage_shared_key_credential);
|
||||
else
|
||||
result = std::make_unique<BlobContainerClient>(final_url);
|
||||
}
|
||||
else
|
||||
{
|
||||
@ -438,7 +493,7 @@ void StorageAzureBlob::truncate(const ASTPtr &, const StorageMetadataPtr &, Cont
|
||||
{
|
||||
throw Exception(
|
||||
ErrorCodes::DATABASE_ACCESS_DENIED,
|
||||
"S3 key '{}' contains globs, so the table is in readonly mode",
|
||||
"AzureBlobStorage key '{}' contains globs, so the table is in readonly mode",
|
||||
configuration.blob_path);
|
||||
}
|
||||
|
||||
@ -1203,7 +1258,7 @@ ColumnsDescription StorageAzureBlob::getTableStructureFromData(
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
/// S3 file iterator could get new keys after new iteration, check them in schema cache.
|
||||
///AzureBlobStorage file iterator could get new keys after new iteration, check them in schema cache.
|
||||
if (ctx->getSettingsRef().schema_inference_use_cache_for_azure && read_keys.size() > prev_read_keys_size)
|
||||
{
|
||||
columns_from_cache = tryGetColumnsFromCache(read_keys.begin() + prev_read_keys_size, read_keys.end(), configuration, format_settings, ctx);
|
||||
|
||||
@ -65,7 +65,7 @@ public:
|
||||
ASTPtr partition_by_);
|
||||
|
||||
static StorageAzureBlob::Configuration getConfiguration(ASTs & engine_args, ContextPtr local_context);
|
||||
static AzureClientPtr createClient(StorageAzureBlob::Configuration configuration);
|
||||
static AzureClientPtr createClient(StorageAzureBlob::Configuration configuration, bool is_read_only);
|
||||
|
||||
static AzureObjectStorage::SettingsPtr createSettings(ContextPtr local_context);
|
||||
|
||||
|
||||
@ -946,7 +946,7 @@ void StorageLog::backupData(BackupEntriesCollector & backup_entries_collector, c
|
||||
|
||||
fs::path data_path_in_backup_fs = data_path_in_backup;
|
||||
auto temp_dir_owner = std::make_shared<TemporaryFileOnDisk>(disk, "tmp/");
|
||||
fs::path temp_dir = temp_dir_owner->getPath();
|
||||
fs::path temp_dir = temp_dir_owner->getRelativePath();
|
||||
disk->createDirectories(temp_dir);
|
||||
|
||||
bool copy_encrypted = !backup_entries_collector.getBackupSettings().decrypt_files_from_encrypted_disks;
|
||||
|
||||
@ -314,7 +314,7 @@ namespace
|
||||
backup_entries.resize(file_paths.size());
|
||||
|
||||
temp_dir_owner.emplace(temp_disk);
|
||||
fs::path temp_dir = temp_dir_owner->getPath();
|
||||
fs::path temp_dir = temp_dir_owner->getRelativePath();
|
||||
temp_disk->createDirectories(temp_dir);
|
||||
|
||||
/// Writing data.bin
|
||||
@ -453,10 +453,10 @@ void StorageMemory::restoreDataImpl(const BackupPtr & backup, const String & dat
|
||||
if (!dynamic_cast<ReadBufferFromFileBase *>(in.get()))
|
||||
{
|
||||
temp_data_file.emplace(temporary_disk);
|
||||
auto out = std::make_unique<WriteBufferFromFile>(temp_data_file->getPath());
|
||||
auto out = std::make_unique<WriteBufferFromFile>(temp_data_file->getAbsolutePath());
|
||||
copyData(*in, *out);
|
||||
out.reset();
|
||||
in = createReadBufferFromFileBase(temp_data_file->getPath(), {});
|
||||
in = createReadBufferFromFileBase(temp_data_file->getAbsolutePath(), {});
|
||||
}
|
||||
std::unique_ptr<ReadBufferFromFileBase> in_from_file{static_cast<ReadBufferFromFileBase *>(in.release())};
|
||||
CompressedReadBufferFromFile compressed_in{std::move(in_from_file)};
|
||||
|
||||
@ -544,7 +544,7 @@ void StorageStripeLog::backupData(BackupEntriesCollector & backup_entries_collec
|
||||
|
||||
fs::path data_path_in_backup_fs = data_path_in_backup;
|
||||
auto temp_dir_owner = std::make_shared<TemporaryFileOnDisk>(disk, "tmp/");
|
||||
fs::path temp_dir = temp_dir_owner->getPath();
|
||||
fs::path temp_dir = temp_dir_owner->getRelativePath();
|
||||
disk->createDirectories(temp_dir);
|
||||
|
||||
bool copy_encrypted = !backup_entries_collector.getBackupSettings().decrypt_files_from_encrypted_disks;
|
||||
|
||||
@ -371,7 +371,7 @@ std::pair<Poco::URI, std::unique_ptr<ReadWriteBufferFromHTTP>> StorageURLSource:
|
||||
for (; option != end; ++option)
|
||||
{
|
||||
bool skip_url_not_found_error = glob_url && read_settings.http_skip_not_found_url_for_globs && option == std::prev(end);
|
||||
auto request_uri = Poco::URI(*option, context->getSettingsRef().disable_url_encoding);
|
||||
auto request_uri = Poco::URI(*option, context->getSettingsRef().enable_url_encoding);
|
||||
|
||||
for (const auto & [param, value] : params)
|
||||
request_uri.addQueryParameter(param, value);
|
||||
|
||||
@ -38,7 +38,7 @@ ColumnsDescription getStructureOfRemoteTableInShard(
|
||||
if (shard_info.isLocal())
|
||||
{
|
||||
TableFunctionPtr table_function_ptr = TableFunctionFactory::instance().get(table_func_ptr, context);
|
||||
return table_function_ptr->getActualTableStructure(context);
|
||||
return table_function_ptr->getActualTableStructure(context, /*is_insert_query*/ true);
|
||||
}
|
||||
|
||||
auto table_func_name = queryToString(table_func_ptr);
|
||||
|
||||
@ -49,13 +49,14 @@ namespace DB
|
||||
actual_columns = parseColumnsListFromString(table_structure, context_);
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionHive::getActualTableStructure(ContextPtr /*context_*/) const { return actual_columns; }
|
||||
ColumnsDescription TableFunctionHive::getActualTableStructure(ContextPtr /*context_*/, bool /*is_insert_query*/) const { return actual_columns; }
|
||||
|
||||
StoragePtr TableFunctionHive::executeImpl(
|
||||
const ASTPtr & /*ast_function_*/,
|
||||
ContextPtr context_,
|
||||
const std::string & table_name_,
|
||||
ColumnsDescription /*cached_columns_*/) const
|
||||
ColumnsDescription /*cached_columns_*/,
|
||||
bool /*is_insert_query*/) const
|
||||
{
|
||||
const Settings & settings = context_->getSettings();
|
||||
ParserExpression partition_by_parser;
|
||||
|
||||
@ -17,10 +17,10 @@ public:
|
||||
bool hasStaticStructure() const override { return true; }
|
||||
|
||||
StoragePtr executeImpl(
|
||||
const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns) const override;
|
||||
const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
|
||||
|
||||
const char * getStorageTypeName() const override { return storage_type_name; }
|
||||
ColumnsDescription getActualTableStructure(ContextPtr) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr, bool is_insert_query) const override;
|
||||
void parseArguments(const ASTPtr & ast_function_, ContextPtr context_) override;
|
||||
|
||||
private:
|
||||
|
||||
@ -34,15 +34,15 @@ StoragePtr ITableFunction::execute(const ASTPtr & ast_function, ContextPtr conte
|
||||
auto context_to_use = use_global_context ? context->getGlobalContext() : context;
|
||||
|
||||
if (cached_columns.empty())
|
||||
return executeImpl(ast_function, context, table_name, std::move(cached_columns));
|
||||
return executeImpl(ast_function, context, table_name, std::move(cached_columns), is_insert_query);
|
||||
|
||||
if (hasStaticStructure() && cached_columns == getActualTableStructure(context))
|
||||
return executeImpl(ast_function, context_to_use, table_name, std::move(cached_columns));
|
||||
if (hasStaticStructure() && cached_columns == getActualTableStructure(context,is_insert_query))
|
||||
return executeImpl(ast_function, context_to_use, table_name, std::move(cached_columns), is_insert_query);
|
||||
|
||||
auto this_table_function = shared_from_this();
|
||||
auto get_storage = [=]() -> StoragePtr
|
||||
{
|
||||
return this_table_function->executeImpl(ast_function, context_to_use, table_name, cached_columns);
|
||||
return this_table_function->executeImpl(ast_function, context_to_use, table_name, cached_columns, is_insert_query);
|
||||
};
|
||||
|
||||
/// It will request actual table structure and create underlying storage lazily
|
||||
|
||||
@ -58,7 +58,7 @@ public:
|
||||
virtual void parseArguments(const ASTPtr & /*ast_function*/, ContextPtr /*context*/) {}
|
||||
|
||||
/// Returns actual table structure probably requested from remote server, may fail
|
||||
virtual ColumnsDescription getActualTableStructure(ContextPtr /*context*/) const = 0;
|
||||
virtual ColumnsDescription getActualTableStructure(ContextPtr /*context*/, bool is_insert_query) const = 0;
|
||||
|
||||
/// Check if table function needs a structure hint from SELECT query in case of
|
||||
/// INSERT INTO FUNCTION ... SELECT ... and INSERT INTO ... SELECT ... FROM table_function(...)
|
||||
@ -89,7 +89,7 @@ protected:
|
||||
|
||||
private:
|
||||
virtual StoragePtr executeImpl(
|
||||
const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns) const = 0;
|
||||
const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const = 0;
|
||||
|
||||
virtual const char * getStorageTypeName() const = 0;
|
||||
};
|
||||
|
||||
@ -26,7 +26,8 @@ protected:
|
||||
const ASTPtr & /*ast_function*/,
|
||||
ContextPtr context,
|
||||
const std::string & table_name,
|
||||
ColumnsDescription /*cached_columns*/) const override
|
||||
ColumnsDescription /*cached_columns*/,
|
||||
bool /*is_insert_query*/) const override
|
||||
{
|
||||
ColumnsDescription columns;
|
||||
if (TableFunction::configuration.structure != "auto")
|
||||
@ -42,7 +43,7 @@ protected:
|
||||
|
||||
const char * getStorageTypeName() const override { return Storage::name; }
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const override
|
||||
{
|
||||
if (TableFunction::configuration.structure == "auto")
|
||||
{
|
||||
|
||||
@ -110,7 +110,7 @@ void ITableFunctionFileLike::addColumnsStructureToArguments(ASTs & args, const S
|
||||
}
|
||||
}
|
||||
|
||||
StoragePtr ITableFunctionFileLike::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/) const
|
||||
StoragePtr ITableFunctionFileLike::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/, bool /*is_insert_query*/) const
|
||||
{
|
||||
ColumnsDescription columns;
|
||||
if (structure != "auto")
|
||||
|
||||
@ -48,7 +48,7 @@ protected:
|
||||
ColumnsDescription structure_hint;
|
||||
|
||||
private:
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns) const override;
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
|
||||
|
||||
virtual StoragePtr getStorage(
|
||||
const String & source, const String & format, const ColumnsDescription & columns, ContextPtr global_context,
|
||||
|
||||
@ -61,7 +61,7 @@ void ITableFunctionXDBC::startBridgeIfNot(ContextPtr context) const
|
||||
}
|
||||
}
|
||||
|
||||
ColumnsDescription ITableFunctionXDBC::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription ITableFunctionXDBC::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
|
||||
{
|
||||
startBridgeIfNot(context);
|
||||
|
||||
@ -92,10 +92,10 @@ ColumnsDescription ITableFunctionXDBC::getActualTableStructure(ContextPtr contex
|
||||
return ColumnsDescription{columns};
|
||||
}
|
||||
|
||||
StoragePtr ITableFunctionXDBC::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/) const
|
||||
StoragePtr ITableFunctionXDBC::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/, bool is_insert_query) const
|
||||
{
|
||||
startBridgeIfNot(context);
|
||||
auto columns = getActualTableStructure(context);
|
||||
auto columns = getActualTableStructure(context, is_insert_query);
|
||||
auto result = std::make_shared<StorageXDBC>(
|
||||
StorageID(getDatabaseName(), table_name), schema_name, remote_table_name, columns, ConstraintsDescription{}, String{}, context, helper);
|
||||
result->startup();
|
||||
|
||||
@ -16,7 +16,7 @@ namespace DB
|
||||
class ITableFunctionXDBC : public ITableFunction
|
||||
{
|
||||
private:
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns) const override;
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
|
||||
|
||||
/* A factory method to create bridge helper, that will assist in remote interaction */
|
||||
virtual BridgeHelperPtr createBridgeHelper(ContextPtr context,
|
||||
@ -24,7 +24,7 @@ private:
|
||||
const std::string & connection_string_,
|
||||
bool use_connection_pooling_) const = 0;
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
|
||||
void parseArguments(const ASTPtr & ast_function, ContextPtr context) override;
|
||||
|
||||
|
||||
@ -39,7 +39,7 @@ namespace
|
||||
|
||||
bool isConnectionString(const std::string & candidate)
|
||||
{
|
||||
return candidate.starts_with("DefaultEndpointsProtocol");
|
||||
return !candidate.starts_with("http");
|
||||
}
|
||||
|
||||
}
|
||||
@ -193,12 +193,12 @@ void TableFunctionAzureBlobStorage::parseArguments(const ASTPtr & ast_function,
|
||||
configuration = parseArgumentsImpl(args, context);
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionAzureBlobStorage::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription TableFunctionAzureBlobStorage::getActualTableStructure(ContextPtr context, bool is_insert_query) const
|
||||
{
|
||||
if (configuration.structure == "auto")
|
||||
{
|
||||
context->checkAccess(getSourceAccessType());
|
||||
auto client = StorageAzureBlob::createClient(configuration);
|
||||
auto client = StorageAzureBlob::createClient(configuration, !is_insert_query);
|
||||
auto settings = StorageAzureBlob::createSettings(context);
|
||||
|
||||
auto object_storage = std::make_unique<AzureObjectStorage>("AzureBlobStorageTableFunction", std::move(client), std::move(settings));
|
||||
@ -213,9 +213,9 @@ bool TableFunctionAzureBlobStorage::supportsReadingSubsetOfColumns()
|
||||
return FormatFactory::instance().checkIfFormatSupportsSubsetOfColumns(configuration.format);
|
||||
}
|
||||
|
||||
StoragePtr TableFunctionAzureBlobStorage::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/) const
|
||||
StoragePtr TableFunctionAzureBlobStorage::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/, bool is_insert_query) const
|
||||
{
|
||||
auto client = StorageAzureBlob::createClient(configuration);
|
||||
auto client = StorageAzureBlob::createClient(configuration, !is_insert_query);
|
||||
auto settings = StorageAzureBlob::createSettings(context);
|
||||
|
||||
ColumnsDescription columns;
|
||||
|
||||
@ -54,11 +54,12 @@ protected:
|
||||
const ASTPtr & ast_function,
|
||||
ContextPtr context,
|
||||
const std::string & table_name,
|
||||
ColumnsDescription cached_columns) const override;
|
||||
ColumnsDescription cached_columns,
|
||||
bool is_insert_query) const override;
|
||||
|
||||
const char * getStorageTypeName() const override { return "Azure"; }
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
void parseArguments(const ASTPtr & ast_function, ContextPtr context) override;
|
||||
|
||||
mutable StorageAzureBlob::Configuration configuration;
|
||||
|
||||
@ -43,7 +43,7 @@ void TableFunctionDictionary::parseArguments(const ASTPtr & ast_function, Contex
|
||||
dictionary_name = checkAndGetLiteralArgument<String>(args[0], "dictionary_name");
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionDictionary::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription TableFunctionDictionary::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
|
||||
{
|
||||
const ExternalDictionariesLoader & external_loader = context->getExternalDictionariesLoader();
|
||||
std::string resolved_name = external_loader.resolveDictionaryName(dictionary_name, context->getCurrentDatabase());
|
||||
@ -76,10 +76,10 @@ ColumnsDescription TableFunctionDictionary::getActualTableStructure(ContextPtr c
|
||||
}
|
||||
|
||||
StoragePtr TableFunctionDictionary::executeImpl(
|
||||
const ASTPtr &, ContextPtr context, const std::string & table_name, ColumnsDescription) const
|
||||
const ASTPtr &, ContextPtr context, const std::string & table_name, ColumnsDescription, bool is_insert_query) const
|
||||
{
|
||||
StorageID dict_id(getDatabaseName(), table_name);
|
||||
auto dictionary_table_structure = getActualTableStructure(context);
|
||||
auto dictionary_table_structure = getActualTableStructure(context, is_insert_query);
|
||||
|
||||
auto result = std::make_shared<StorageDictionary>(
|
||||
dict_id, dictionary_name, std::move(dictionary_table_structure), String{}, StorageDictionary::Location::Custom, context);
|
||||
|
||||
@ -18,9 +18,9 @@ public:
|
||||
|
||||
void parseArguments(const ASTPtr & ast_function, ContextPtr context) override;
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription) const override;
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription, bool is_insert_query) const override;
|
||||
|
||||
const char * getStorageTypeName() const override { return "Dictionary"; }
|
||||
|
||||
|
||||
@ -120,12 +120,12 @@ void TableFunctionExecutable::parseArguments(const ASTPtr & ast_function, Contex
|
||||
}
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionExecutable::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription TableFunctionExecutable::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
|
||||
{
|
||||
return parseColumnsListFromString(structure, context);
|
||||
}
|
||||
|
||||
StoragePtr TableFunctionExecutable::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/) const
|
||||
StoragePtr TableFunctionExecutable::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/, bool is_insert_query) const
|
||||
{
|
||||
auto storage_id = StorageID(getDatabaseName(), table_name);
|
||||
auto global_context = context->getGlobalContext();
|
||||
@ -135,7 +135,7 @@ StoragePtr TableFunctionExecutable::executeImpl(const ASTPtr & /*ast_function*/,
|
||||
if (settings_query != nullptr)
|
||||
settings.applyChanges(settings_query->as<ASTSetQuery>()->changes);
|
||||
|
||||
auto storage = std::make_shared<StorageExecutable>(storage_id, format, settings, input_queries, getActualTableStructure(context), ConstraintsDescription{});
|
||||
auto storage = std::make_shared<StorageExecutable>(storage_id, format, settings, input_queries, getActualTableStructure(context, is_insert_query), ConstraintsDescription{});
|
||||
storage->startup();
|
||||
return storage;
|
||||
}
|
||||
|
||||
@ -24,11 +24,11 @@ public:
|
||||
bool hasStaticStructure() const override { return true; }
|
||||
|
||||
private:
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns) const override;
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
|
||||
|
||||
const char * getStorageTypeName() const override { return "Executable"; }
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
|
||||
std::vector<size_t> skipAnalysisForArguments(const QueryTreeNodePtr & query_node_table_function, ContextPtr context) const override;
|
||||
|
||||
|
||||
@ -91,7 +91,7 @@ void TableFunctionExplain::parseArguments(const ASTPtr & ast_function, ContextPt
|
||||
query = std::move(explain_query);
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionExplain::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription TableFunctionExplain::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
|
||||
{
|
||||
Block sample_block = getInterpreter(context).getSampleBlock(query->as<ASTExplainQuery>()->getKind());
|
||||
ColumnsDescription columns_description;
|
||||
@ -123,7 +123,7 @@ static Block executeMonoBlock(QueryPipeline & pipeline)
|
||||
}
|
||||
|
||||
StoragePtr TableFunctionExplain::executeImpl(
|
||||
const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/) const
|
||||
const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/, bool is_insert_query) const
|
||||
{
|
||||
/// To support settings inside explain subquery.
|
||||
auto mutable_context = Context::createCopy(context);
|
||||
@ -132,7 +132,7 @@ StoragePtr TableFunctionExplain::executeImpl(
|
||||
Block block = executeMonoBlock(blockio.pipeline);
|
||||
|
||||
StorageID storage_id(getDatabaseName(), table_name);
|
||||
auto storage = std::make_shared<StorageValues>(storage_id, getActualTableStructure(context), std::move(block));
|
||||
auto storage = std::make_shared<StorageValues>(storage_id, getActualTableStructure(context, is_insert_query), std::move(block));
|
||||
storage->startup();
|
||||
return storage;
|
||||
}
|
||||
|
||||
@ -17,7 +17,7 @@ public:
|
||||
std::string getName() const override { return name; }
|
||||
|
||||
private:
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const String & table_name, ColumnsDescription cached_columns) const override;
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const String & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
|
||||
|
||||
const char * getStorageTypeName() const override { return "Explain"; }
|
||||
|
||||
@ -25,7 +25,7 @@ private:
|
||||
|
||||
void parseArguments(const ASTPtr & ast_function, ContextPtr context) override;
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
|
||||
InterpreterExplainQuery getInterpreter(ContextPtr context) const;
|
||||
|
||||
|
||||
@ -83,7 +83,7 @@ StoragePtr TableFunctionFile::getStorage(const String & source,
|
||||
return std::make_shared<StorageFile>(source, global_context->getUserFilesPath(), args);
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionFile::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription TableFunctionFile::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
|
||||
{
|
||||
if (structure == "auto")
|
||||
{
|
||||
|
||||
@ -20,7 +20,7 @@ public:
|
||||
return name;
|
||||
}
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
|
||||
std::unordered_set<String> getVirtualsToCheckBeforeUsingStructureHint() const override
|
||||
{
|
||||
|
||||
@ -52,7 +52,7 @@ void TableFunctionFormat::parseArguments(const ASTPtr & ast_function, ContextPtr
|
||||
structure = checkAndGetLiteralArgument<String>(args[1], "structure");
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionFormat::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription TableFunctionFormat::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
|
||||
{
|
||||
if (structure == "auto")
|
||||
{
|
||||
@ -98,9 +98,9 @@ Block TableFunctionFormat::parseData(ColumnsDescription columns, ContextPtr cont
|
||||
return concatenateBlocks(blocks);
|
||||
}
|
||||
|
||||
StoragePtr TableFunctionFormat::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/) const
|
||||
StoragePtr TableFunctionFormat::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/, bool is_insert_query) const
|
||||
{
|
||||
auto columns = getActualTableStructure(context);
|
||||
auto columns = getActualTableStructure(context, is_insert_query);
|
||||
Block res_block = parseData(columns, context);
|
||||
auto res = std::make_shared<StorageValues>(StorageID(getDatabaseName(), table_name), columns, res_block);
|
||||
res->startup();
|
||||
|
||||
@ -18,10 +18,10 @@ public:
|
||||
bool hasStaticStructure() const override { return false; }
|
||||
|
||||
private:
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns) const override;
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
|
||||
const char * getStorageTypeName() const override { return "Values"; }
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
void parseArguments(const ASTPtr & ast_function, ContextPtr context) override;
|
||||
|
||||
Block parseData(ColumnsDescription columns, ContextPtr context) const;
|
||||
|
||||
@ -97,7 +97,7 @@ void TableFunctionGenerateRandom::parseArguments(const ASTPtr & ast_function, Co
|
||||
}
|
||||
}
|
||||
|
||||
ColumnsDescription TableFunctionGenerateRandom::getActualTableStructure(ContextPtr context) const
|
||||
ColumnsDescription TableFunctionGenerateRandom::getActualTableStructure(ContextPtr context, bool /*is_insert_query*/) const
|
||||
{
|
||||
if (structure == "auto")
|
||||
{
|
||||
@ -113,9 +113,9 @@ ColumnsDescription TableFunctionGenerateRandom::getActualTableStructure(ContextP
|
||||
return parseColumnsListFromString(structure, context);
|
||||
}
|
||||
|
||||
StoragePtr TableFunctionGenerateRandom::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/) const
|
||||
StoragePtr TableFunctionGenerateRandom::executeImpl(const ASTPtr & /*ast_function*/, ContextPtr context, const std::string & table_name, ColumnsDescription /*cached_columns*/, bool is_insert_query) const
|
||||
{
|
||||
ColumnsDescription columns = getActualTableStructure(context);
|
||||
ColumnsDescription columns = getActualTableStructure(context, is_insert_query);
|
||||
auto res = std::make_shared<StorageGenerateRandom>(
|
||||
StorageID(getDatabaseName(), table_name), columns, String{}, max_array_length, max_string_length, random_seed);
|
||||
res->startup();
|
||||
|
||||
@ -19,10 +19,10 @@ public:
|
||||
void setStructureHint(const ColumnsDescription & structure_hint_) override { structure_hint = structure_hint_; }
|
||||
|
||||
private:
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns) const override;
|
||||
StoragePtr executeImpl(const ASTPtr & ast_function, ContextPtr context, const std::string & table_name, ColumnsDescription cached_columns, bool is_insert_query) const override;
|
||||
const char * getStorageTypeName() const override { return "GenerateRandom"; }
|
||||
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context) const override;
|
||||
ColumnsDescription getActualTableStructure(ContextPtr context, bool is_insert_query) const override;
|
||||
void parseArguments(const ASTPtr & ast_function, ContextPtr context) override;
|
||||
|
||||
String structure = "auto";
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user