دوال البحث في السلاسل

SELECT countMatches('hello 123 world 456 test', '[0-9]+')

┌─countMatches('hello 123 world 456 test', '[0-9]+')─┐
│                                                  2 │
└────────────────────────────────────────────────────┘

SELECT countMatchesCaseInsensitive('Hello HELLO world', 'hello')

┌─countMatchesCaseInsensitive('Hello HELLO world', 'hello')─┐
│                                                         2 │
└───────────────────────────────────────────────────────────┘

SELECT countSubstrings('aaaa', 'aa');

┌─countSubstrings('aaaa', 'aa')─┐
│                             2 │
└───────────────────────────────┘

SELECT countSubstrings('abc___abc', 'abc', 4);

┌─countSubstrings('abc___abc', 'abc', 4)─┐
│                                      1 │
└────────────────────────────────────────┘

SELECT countSubstringsCaseInsensitive('AAAA', 'aa');

┌─countSubstringsCaseInsensitive('AAAA', 'aa')─┐
│                                            2 │
└──────────────────────────────────────────────┘

SELECT countSubstringsCaseInsensitive('abc___ABC___abc', 'abc', 4);

┌─countSubstringsCaseInsensitive('abc___ABC___abc', 'abc', 4)─┐
│                                                           2 │
└─────────────────────────────────────────────────────────────┘

SELECT countSubstringsCaseInsensitiveUTF8('ложка, кошка, картошка', 'КА');

┌─countSubstringsCaseInsensitiveUTF8('ложка, кошка, картошка', 'КА')─┐
│                                                                  4 │
└────────────────────────────────────────────────────────────────────┘

SELECT countSubstringsCaseInsensitiveUTF8('ложка, кошка, картошка', 'КА', 13);

┌─countSubstringsCaseInsensitiveUTF8('ложка, кошка, картошка', 'КА', 13)─┐
│                                                                      2 │
└────────────────────────────────────────────────────────────────────────┘

SELECT extract('test@clickhouse.com', '.*@(.*)$')

┌─extract('test@clickhouse.com', '.*@(.*)$')─┐
│ clickhouse.com                             │
└────────────────────────────────────────────┘

SELECT extract('test@clickhouse.com', 'no_match')

┌─extract('test@clickhouse.com', 'no_match')─┐
│                                            │
└────────────────────────────────────────────┘

SELECT extractAll('hello 123 world 456', '[0-9]+')

┌─extractAll('hello 123 world 456', '[0-9]+')─┐
│ ['123','456']                               │
└─────────────────────────────────────────────┘

SELECT extractAll('test@example.com, user@domain.org', '([a-zA-Z0-9]+)@')

┌─extractAll('test@example.com, user@domain.org', '([a-zA-Z0-9]+)@')─┐
│ ['test','user']                                                    │
└────────────────────────────────────────────────────────────────────┘

WITH '< Server: nginx
< Date: Tue, 22 Jan 2019 00:26:14 GMT
< Content-Type: text/html; charset=UTF-8
< Connection: keep-alive
' AS s
SELECT extractAllGroupsHorizontal(s, '< ([\\w\\-]+): ([^\\r\\n]+)');

[['Server','Date','Content-Type','Connection'],['nginx','Tue, 22 Jan 2019 00:26:14 GMT','text/html; charset=UTF-8','keep-alive']]

WITH '< Server: nginx
< Date: Tue, 22 Jan 2019 00:26:14 GMT
< Content-Type: text/html; charset=UTF-8
< Connection: keep-alive
' AS s
SELECT extractGroups(s, '< ([\\w\\-]+): ([^\\r\\n]+)');

['Server','nginx']

DROP TABLE IF EXISTS doc;

CREATE TABLE doc (
    id UInt32,
    msg String,
    INDEX idx(msg) TYPE text(tokenizer = splitByString(['()', '\\']))
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO doc VALUES (1, '()a,\\bc()d'), (2, '()\\a()bc\\d'), (3, ',()a\\,bc,(),d,');

SELECT count() FROM doc WHERE hasAllTokens(msg, 'a\\d()');

┌─count()─┐
│       1 │
└─────────┘

DROP TABLE IF EXISTS doc;

CREATE TABLE doc (
    id UInt32,
    msg String,
    INDEX idx(msg) TYPE text(tokenizer = splitByString(['()', '\\']))
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO doc VALUES (1, '()a,\\bc()d'), (2, '()\\a()bc\\d'), (3, ',()a\\,bc,(),d,');

SELECT count() FROM doc WHERE hasAllTokens(msg, ['a', 'd']);

┌─count()─┐
│       1 │
└─────────┘

DROP TABLE IF EXISTS doc;

CREATE TABLE doc (
    id UInt32,
    msg String,
    INDEX idx(msg) TYPE text(tokenizer = splitByString(['()', '\\']))
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO doc VALUES (1, '()a,\\bc()d'), (2, '()\\a()bc\\d'), (3, ',()a\\,bc,(),d,');

SELECT count() FROM doc WHERE hasAllTokens(msg, tokens('a()d', 'splitByString', ['()', '\\']));

┌─count()─┐
│       1 │
└─────────┘

SELECT hasAllTokens('abcdef', 'abc', 'ngrams(3)');

┌─hasAllTokens('abcdef', 'abc', 'ngrams(3)')─┐
│                                          1 │
└────────────────────────────────────────────┘

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

SELECT count() FROM log WHERE hasAllTokens(tags, 'clickhouse');

┌─count()─┐
│       1 │
└─────────┘

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

SELECT count() FROM log WHERE hasAllTokens(mapKeys(attributes), ['address', 'log_level']);

┌─count()─┐
│       1 │
└─────────┘

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

SELECT count() FROM log WHERE hasAllTokens(mapValues(attributes), ['192.0.0.1', 'DEBUG']);

┌─count()─┐
│       0 │
└─────────┘

DROP TABLE IF EXISTS doc;

CREATE TABLE doc (
    id UInt32,
    msg String,
    INDEX idx(msg) TYPE text(tokenizer = splitByString(['()', '\\']))
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO doc VALUES (1, '()a,\\bc()d'), (2, '()\\a()bc\\d'), (3, ',()a\\,bc,(),d,');

SELECT count() FROM doc WHERE hasAnyTokens(msg, 'a\\d()');

┌─count()─┐
│       3 │
└─────────┘

DROP TABLE IF EXISTS doc;

CREATE TABLE doc (
    id UInt32,
    msg String,
    INDEX idx(msg) TYPE text(tokenizer = splitByString(['()', '\\']))
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO doc VALUES (1, '()a,\\bc()d'), (2, '()\\a()bc\\d'), (3, ',()a\\,bc,(),d,');

SELECT count() FROM doc WHERE hasAnyTokens(msg, ['a', 'd']);

┌─count()─┐
│       3 │
└─────────┘

DROP TABLE IF EXISTS doc;

CREATE TABLE doc (
    id UInt32,
    msg String,
    INDEX idx(msg) TYPE text(tokenizer = splitByString(['()', '\\']))
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO doc VALUES (1, '()a,\\bc()d'), (2, '()\\a()bc\\d'), (3, ',()a\\,bc,(),d,');

SELECT count() FROM doc WHERE hasAnyTokens(msg, tokens('a()d', 'splitByString', ['()', '\\']));

┌─count()─┐
│       3 │
└─────────┘

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

SELECT count() FROM log WHERE hasAnyTokens(tags, 'clickhouse');

┌─count()─┐
│       1 │
└─────────┘

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

SELECT count() FROM log WHERE hasAnyTokens(mapKeys(attributes), ['address', 'log_level']);

┌─count()─┐
│       2 │
└─────────┘

DROP TABLE IF EXISTS log;

CREATE TABLE log (
    id UInt32,
    tags Array(String),
    attributes Map(String, String),
    INDEX idx_tags (tags) TYPE text(tokenizer = splitByNonAlpha),
    INDEX idx_attributes_keys mapKeys(attributes) TYPE text(tokenizer = array),
    INDEX idx_attributes_vals mapValues(attributes) TYPE text(tokenizer = array)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO log VALUES
    (1, ['clickhouse', 'clickhouse cloud'], {'address': '192.0.0.1', 'log_level': 'INFO'}),
    (2, ['chdb'], {'embedded': 'true', 'log_level': 'DEBUG'});

SELECT count() FROM log WHERE hasAnyTokens(mapValues(attributes), ['192.0.0.1', 'DEBUG']);

┌─count()─┐
│       2 │
└─────────┘

SELECT hasPhrase('the quick brown fox jumps', 'quick brown')

┌─hasPhrase('the quick brown fox jumps', 'quick brown')─┐
│                                                     1 │
└───────────────────────────────────────────────────────┘

SELECT hasPhrase('the quick brown fox jumps', 'quick fox')

┌─hasPhrase('the quick brown fox jumps', 'quick fox')─┐
│                                                   0 │
└─────────────────────────────────────────────────────┘

SELECT hasSubsequence('Hello World', 'HlWrd')

┌─hasSubsequence('Hello World', 'HlWrd')─┐
│                                      1 │
└────────────────────────────────────────┘

SELECT hasSubsequence('Hello World', 'xyz')

┌─hasSubsequence('Hello World', 'xyz')─┐
│                                    0 │
└──────────────────────────────────────┘

SELECT hasSubsequenceCaseInsensitive('garbage', 'ARG');

┌─hasSubsequenceCaseInsensitive('garbage', 'ARG')─┐
│                                               1 │
└─────────────────────────────────────────────────┘

SELECT hasSubsequenceCaseInsensitiveUTF8('ClickHouse - столбцовая система управления базами данных', 'СИСТЕМА');

┌─hasSubsequenceCaseInsensitiveUTF8('ClickHouse - столбцовая система управления базами данных', 'СИСТЕМА')─┐
│                                                                                                        1 │
└──────────────────────────────────────────────────────────────────────────────────────────────────────────┘

SELECT hasSubsequenceUTF8('картошка', 'кошка');

┌─hasSubsequenceUTF8('картошка', 'кошка')─┐
│                                       1 │
└─────────────────────────────────────────┘

SELECT hasSubsequenceUTF8('картошка', 'апельсин');

┌─hasSubsequenceUTF8('картошка', 'апельсин')─┐
│                                          0 │
└────────────────────────────────────────────┘

SELECT hasToken('clickhouse test', 'test')

┌─hasToken('clickhouse test', 'test')─┐
│                                   1 │
└─────────────────────────────────────┘

SELECT hasTokenOrNull('apple banana cherry', 'ban ana');

┌─hasTokenOrNull('apple banana cherry', 'ban ana')─┐
│                                             ᴺᵁᴸᴸ │
└──────────────────────────────────────────────────┘

SELECT highlight('The quick brown fox', ['quick', 'fox'])

┌─highlight('The quick brown fox', ['quick', 'fox'])─┐
│ The <em>quick</em> brown <em>fox</em>              │
└────────────────────────────────────────────────────┘

SELECT highlight('Hello World', ['hello'], '<b>', '</b>')

┌─highlight('Hello World', ['hello'], '<b>', '</b>')─┐
│ <b>Hello</b> World                                 │
└────────────────────────────────────────────────────┘

SELECT ilike('ClickHouse', '%house%');

┌─ilike('ClickHouse', '%house%')─┐
│                              1 │
└────────────────────────────────┘

SELECT like('ClickHouse', '%House');

┌─like('ClickHouse', '%House')─┐
│                            1 │
└──────────────────────────────┘

SELECT like('ClickHouse', 'Click_ouse');

┌─like('ClickHouse', 'Click_ouse')─┐
│                                1 │
└──────────────────────────────────┘

SELECT like('ClickHouse', '%SQL%');

┌─like('ClickHouse', '%SQL%')─┐
│                           0 │
└─────────────────────────────┘

SELECT '50%off' LIKE '50#%off' ESCAPE '#';

┌─like('50%off', '50#%off', '#')─┐
│                              1 │
└────────────────────────────────┘

SELECT locate('ca', 'abcabc')

┌─locate('ca', 'abcabc')─┐
│                      3 │
└────────────────────────┘

SELECT match('Hello World', 'Hello.*')

┌─match('Hello World', 'Hello.*')─┐
│                               1 │
└─────────────────────────────────┘

SELECT match('Hello World', 'goodbye.*')

┌─match('Hello World', 'goodbye.*')─┐
│                                 0 │
└───────────────────────────────────┘

SELECT match('abcde', 'b.*d'), match('abcde', '^b.*d$')

┌─match('abcde', 'b.*d')─┬─match('abcde', '^b.*d$')─┐
│                      1 │                        0 │
└────────────────────────┴──────────────────────────┘

SELECT matchCaseInsensitive('Hello World', 'hello.*'), 'Hello World' ~* 'HELLO.*'

┌─matchCaseInsensitive('Hello World', 'hello.*')─┬─matchCaseInsensitive('Hello World', 'HELLO.*')─┐
│                                              1 │                                              1 │
└────────────────────────────────────────────────┴────────────────────────────────────────────────┘

SELECT multiFuzzyMatchAllIndices('ClickHouse', 2, ['ClickHouse', 'ClckHouse', 'ClickHose', 'House']);

┌─multiFuzzyMatchAllIndices('ClickHouse', 2, ['ClickHouse', 'ClckHouse', 'ClickHose', 'House'])─┐
│ [3,1,4,2]                                                                                     │
└───────────────────────────────────────────────────────────────────────────────────────────────┘

SELECT multiFuzzyMatchAny('ClickHouse', 2, ['ClickHouse', 'ClckHouse', 'ClickHose']);

┌─multiFuzzyMatchAny('ClickHouse', 2, ['ClickHouse', 'ClckHouse', 'ClickHose'])─┐
│                                                                             1 │
└───────────────────────────────────────────────────────────────────────────────┘

SELECT multiFuzzyMatchAnyIndex('ClickHouse', 2, ['ClckHouse', 'ClickHose', 'ClickHouse']);

┌─multiFuzzyMatchAnyIndex('ClickHouse', 2, ['ClckHouse', 'ClickHose', 'ClickHouse'])─┐
│                                                                                  2 │
└────────────────────────────────────────────────────────────────────────────────────┘

SELECT multiMatchAllIndices('ClickHouse', ['[0-9]', 'House', 'Click', 'ouse']);

┌─multiMatchAllIndices('ClickHouse', ['[0-9]', 'House', 'Click', 'ouse'])─┐
│ [3,2,4]                                                                 │
└─────────────────────────────────────────────────────────────────────────┘

SELECT multiMatchAny('Hello World', ['Hello.*', 'foo.*'])

┌─multiMatchAny('Hello World', ['Hello.*', 'foo.*'])─┐
│                                                  1 │
└────────────────────────────────────────────────────┘

SELECT multiMatchAny('Hello World', ['goodbye.*', 'foo.*'])

┌─multiMatchAny('Hello World', ['goodbye.*', 'foo.*'])─┐
│                                                    0 │
└──────────────────────────────────────────────────────┘

SELECT multiMatchAnyIndex('ClickHouse', ['[0-9]', 'House', 'Click']);

┌─multiMatchAnyIndex('ClickHouse', ['[0-9]', 'House', 'Click'])─┐
│                                                             3 │
└───────────────────────────────────────────────────────────────┘

SELECT multiSearchAllPositions('Hello, World!', ['hello', '!', 'world'])

┌─multiSearchAllPositions('Hello, World!', ['hello', '!', 'world'])─┐
│ [0,13,0]                                                          │
└───────────────────────────────────────────────────────────────────┘

SELECT multiSearchAllPositionsCaseInsensitive('ClickHouse',['c','h'])

┌─multiSearchAllPositionsCaseInsensitive('ClickHouse', ['c', 'h'])─┐
│ [1,6]                                                            │
└──────────────────────────────────────────────────────────────────┘

SELECT multiSearchAllPositionsCaseInsensitiveUTF8('Здравствуй, мир!', ['здравствуй', 'МИР']);

┌─multiSearchAllPositionsCaseInsensitiveUTF8('Здравствуй, мир!', ['здравствуй', 'МИР'])─┐
│ [1,13]                                                                                │
└───────────────────────────────────────────────────────────────────────────────────────┘

SELECT multiSearchAllPositionsUTF8('ClickHouse',['C','H'])

┌─multiSearchAllPositionsUTF8('ClickHouse', ['C', 'H'])─┐
│ [1,6]                                                 │
└───────────────────────────────────────────────────────┘

SELECT multiSearchAny('ClickHouse',['C','H'])

┌─multiSearchAny('ClickHouse', ['C', 'H'])─┐
│                                        1 │
└──────────────────────────────────────────┘

SELECT multiSearchAnyCaseInsensitive('ClickHouse',['c','h'])

┌─multiSearchAnyCaseInsensitive('ClickHouse', ['c', 'h'])─┐
│                                                       1 │
└─────────────────────────────────────────────────────────┘

SELECT multiSearchAnyCaseInsensitiveUTF8('Здравствуйте',['з'])

┌─multiSearchAnyCaseInsensitiveUTF8('Здравствуйте', ['з'])─┐
│                                                        1 │
└──────────────────────────────────────────────────────────┘

SELECT multiSearchAnyUTF8('你好，世界', ['你', '界']) AS result

┌─result─┐
│      1 │
└────────┘