@@ -358,11 +358,8 @@ struct Settings : public SettingsCollection<Settings>
M(SettingBool, enable_unaligned_array_join, false, "Allow ARRAY JOIN with multiple arrays that have different sizes. When this settings is enabled, arrays will be resized to the longest one.", 0) \
M(SettingBool, optimize_read_in_order, true, "Enable ORDER BY optimization for reading data in corresponding order in MergeTree tables.", 0) \
M(SettingBool, low_cardinality_allow_in_native_format, true, "Use LowCardinality type in Native format. Otherwise, convert LowCardinality columns to ordinary for select query, and convert ordinary columns to required LowCardinality for insert query.", 0) \
M(SettingBool, allow_experimental_multiple_joins_emulation, true, "Emulate multiple joins using subselects", 0) \
M(SettingBool, allow_experimental_cross_to_join_conversion, true, "Convert CROSS JOIN to INNER JOIN if possible", 0) \
M(SettingBool, cancel_http_readonly_queries_on_client_close, false, "Cancel HTTP readonly queries when a client closes the connection without waiting for response.", 0) \
M(SettingBool, external_table_functions_use_nulls, true, "If it is set to true, external table functions will implicitly use Nullable type if needed. Otherwise NULLs will be substituted with default values. Currently supported only by 'mysql' and 'odbc' table functions.", 0) \
M(SettingBool, allow_experimental_data_skipping_indices, false, "If it is set to true, data skipping indices can be used in CREATE TABLE/ALTER TABLE queries.", 0) \
<create_query>DROP TABLE IF EXISTS test_bf</create_query>
<create_query>CREATE TABLE test_bf (`id` int, `ary` Array(String), INDEX idx_ary ary TYPE bloom_filter(0.01) GRANULARITY 8192) ENGINE = MergeTree() ORDER BY id</create_query>
<query>SYSTEM STOP MERGES</query>
<query>INSERT INTO test_bf SELECT number AS id, [CAST(id, 'String'), CAST(id + 1, 'String'), CAST(id + 2, 'String')] FROM system.numbers LIMIT 3000000</query>
<query>SYSTEM START MERGES</query>
<drop_query>DROP TABLE IF EXISTS test_bf</drop_query>
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nCROSS JOIN t2_00826\nWHERE a = t2_00826.a
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nALL INNER JOIN t2_00826 ON a = t2_00826.a\nWHERE a = t2_00826.a
cross nullable
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\n, t2_00826\nWHERE a = t2_00826.a
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nALL INNER JOIN t2_00826 ON a = t2_00826.a\nWHERE a = t2_00826.a
cross nullable vs not nullable
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nCROSS JOIN t2_00826\nWHERE a = t2_00826.b
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nALL INNER JOIN t2_00826 ON a = t2_00826.b\nWHERE a = t2_00826.b
cross self
SELECT \n a, \n b, \n y.a, \n y.b\nFROM t1_00826 AS x\nCROSS JOIN t1_00826 AS y\nWHERE (a = y.a) AND (b = y.b)
SELECT \n a, \n b, \n y.a, \n y.b\nFROM t1_00826 AS x\nALL INNER JOIN t1_00826 AS y ON (a = y.a) AND (b = y.b)\nWHERE (a = y.a) AND (b = y.b)
cross one table expr
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nCROSS JOIN t2_00826\nWHERE a = b
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nCROSS JOIN t2_00826\nWHERE a = b
cross multiple ands
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nCROSS JOIN t2_00826\nWHERE (a = t2_00826.a) AND (b = t2_00826.b)
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nALL INNER JOIN t2_00826 ON (a = t2_00826.a) AND (b = t2_00826.b)\nWHERE (a = t2_00826.a) AND (b = t2_00826.b)
cross and inside and
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nCROSS JOIN t2_00826\nWHERE (a = t2_00826.a) AND ((a = t2_00826.a) AND ((a = t2_00826.a) AND (b = t2_00826.b)))
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nALL INNER JOIN t2_00826 ON (a = t2_00826.a) AND (a = t2_00826.a) AND (a = t2_00826.a) AND (b = t2_00826.b)\nWHERE (a = t2_00826.a) AND ((a = t2_00826.a) AND ((a = t2_00826.a) AND (b = t2_00826.b)))
cross split conjunction
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nCROSS JOIN t2_00826\nWHERE (a = t2_00826.a) AND (b = t2_00826.b) AND (a >= 1) AND (t2_00826.b > 0)
SELECT \n a, \n b, \n t2_00826.a, \n t2_00826.b\nFROM t1_00826\nALL INNER JOIN t2_00826 ON (a = t2_00826.a) AND (b = t2_00826.b)\nWHERE (a = t2_00826.a) AND (b = t2_00826.b) AND (a >= 1) AND (t2_00826.b > 0)
--SELECT * FROM t1_00826 cross join t2_00826 where t1_00826.a = t2_00826.a and t1_00826.a = t2_00826.a and t1_00826.b = t2_00826.b and t1_00826.a = t2_00826.a;
--SELECT * FROM t1_00826 cross join t2_00826 where t1_00826.a = t2_00826.a and (t1_00826.a = t2_00826.a and (t1_00826.a = t2_00826.a and t1_00826.b = t2_00826.b));
--SELECT * FROM t1_00826 x cross join t2_00826 y where t1_00826.a = t2_00826.a and (t1_00826.b = t2_00826.b and (x.a = y.a and x.b = y.b));
right/clickhouse local--file"$test_name-raw.tsv"--structure'query text, run int, version UInt32, time float'--query"$(cat$script_dir/eqmed.sql)">"$test_name-report.tsv"
done
}
run_tests
# Analyze results
result_structure="fail int, left float, right float, diff float, rd Array(float), query text"
result_structure="left float, right float, diff float, rd Array(float), query text"
right/clickhouse local--file'*-report.tsv'-S"$result_structure"--query"select * from table where rd[3] > 0.05 order by rd[3] desc"> flap-prone.tsv
right/clickhouse local--file'*-report.tsv'-S"$result_structure"--query"select * from table where diff > 0.05 and diff > rd[3] order by diff desc"> failed.tsv
right/clickhouse local--file'*-report.tsv'-S"$result_structure"--query"select * from table where diff > 0.05 and diff > rd[3] order by diff desc"> bad-perf.tsv
@@ -21,4 +21,36 @@ If you use Oracle through the ODBC driver as a source of external dictionaries,
NLS_LANG=RUSSIAN_RUSSIA.UTF8
```
## How to export data from ClickHouse to the file?
### Using INTO OUTFILE Clause
Add [INTO OUTFILE](../query_language/select/#into-outfile-clause) clause to your query.
For example:
```sql
SELECT*FROMtableINTOOUTFILE'file'
```
By default, ClickHouse uses the [TabSeparated](../interfaces/formats.md#tabseparated) format for output data. To select the [data format](../interfaces/formats.md), use the [FORMAT clause](../query_language/select/#format-clause).
For example:
```sql
SELECT*FROMtableINTOOUTFILE'file'FORMATCSV
```
### Using File-engine Table
See [File](../operations/table_engines/file.md).
### Using Command-line Redirection
```sql
$clickhouse-client--query "SELECT * from table" > result.txt
@@ -954,16 +955,57 @@ Data types of a ClickHouse table columns can differ from the corresponding field
You can insert Parquet data from a file into ClickHouse table by the following command:
```bash
cat{filename} | clickhouse-client --query="INSERT INTO {some_table} FORMAT Parquet"
$ cat{filename} | clickhouse-client --query="INSERT INTO {some_table} FORMAT Parquet"
```
You can select data from a ClickHouse table and save them into some file in the Parquet format by the following command:
```sql
clickhouse-client--query="SELECT * FROM {some_table} FORMAT Parquet" > {some_file.pq}
```bash
$ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Parquet">{some_file.pq}
```
To exchange data with Hadoop, you can use [HDFS table engine](../operations/table_engines/hdfs.md).
## ORC {#data-format-orc}
[Apache ORC](https://orc.apache.org/) is a columnar storage format widespread in the Hadoop ecosystem. ClickHouse supports only read operations for this format.
### Data Types Matching
The table below shows supported data types and how they match ClickHouse [data types](../data_types/index.md) in `INSERT` queries.
| ORC data type (`INSERT`) | ClickHouse data type |
ClickHouse supports configurable precision of `Decimal` type. The `INSERT` query treats the ORC `DECIMAL` type as the ClickHouse `Decimal128` type.
Unsupported ORC data types: `DATE32`, `TIME32`, `FIXED_SIZE_BINARY`, `JSON`, `UUID`, `ENUM`.
Data types of a ClickHouse table columns can differ from the corresponding fields of the ORC data inserted. When inserting data, ClickHouse interprets data types according to the table above and then [cast](../query_language/functions/type_conversion_functions/#type_conversion_function-cast) the data to that data type which is set for the ClickHouse table column.
### Inserting Data
You can insert Parquet data from a file into ClickHouse table by the following command:
```bash
$ cat{filename} | clickhouse-client --query="INSERT INTO {some_table} FORMAT ORC"
```
To exchange data with the Hadoop, you can use [HDFS table engine](../operations/table_engines/hdfs.md).
To exchange data with Hadoop, you can use [HDFS table engine](../operations/table_engines/hdfs.md).
@@ -1120,7 +1120,7 @@ The structure of results (the number and type of columns) must match for the que
Queries that are parts of UNION ALL can't be enclosed in brackets. ORDER BY and LIMIT are applied to separate queries, not to the final result. If you need to apply a conversion to the final result, you can put all the queries with UNION ALL in a subquery in the FROM clause.
### INTO OUTFILE Clause
### INTO OUTFILE Clause {#into-outfile-clause}
Add the `INTO OUTFILE filename` clause (where filename is a string literal) to redirect query output to the specified file.
In contrast to MySQL, the file is created on the client side. The query will fail if a file with the same filename already exists.
...
...
@@ -1128,7 +1128,7 @@ This functionality is available in the command-line client and clickhouse-local
The default output format is TabSeparated (the same as in the command-line client batch mode).
### FORMAT Clause
### FORMAT Clause {#format-clause}
Specify 'FORMAT format' to get data in any specified format.
You can use this for convenience, or for creating dumps.