使用文本索引进行全文搜索

1: The cat likes mice.
2: Mice are afraid of dogs.
3: I have two dogs and a cat.

1: The, cat, likes, mice
2: Mice, are, afraid, of, dogs
3: I, have, two, dogs, and, a, cat

1: the, cat, likes, mice
2: mice, are, afraid, of, dogs
3: i, have, two, dogs, and, a, cat

1: cat, likes, mice
2: mice, afraid, dogs
3: have, two, dogs, cat

afraid : [2]
cat    : [1, 3]
dogs   : [2, 3]
have   : [3]
likes  : [1]
mice   : [1]
two    : [3]

CREATE TABLE table
(
    str String,
    INDEX idx(str) TYPE text(
        tokenizer = 'splitByNonAlpha',
        postprocessor = if(str IN ('the', 'a', 'an', 'of', 'in', 'is', 'it'), '', str)
    )
)
ENGINE = MergeTree
ORDER BY tuple();

-- Log lines: '2024-01-15T10:23:45 ERROR connection failed'
-- The splitByString tokenizer (default: whitespace) keeps the full timestamp as one token.
-- parseDateTimeOrNull detects and drops it; non-timestamp words are kept.
CREATE TABLE logs
(
    id   UInt64,
    line String,
    INDEX idx(line) TYPE text(
        tokenizer    = 'splitByString',
        postprocessor = if(isNull(parseDateTimeOrNull(line, '%Y-%m-%dT%H:%i:%S')), line, '')
    )
)
ENGINE = MergeTree ORDER BY id;

-- Only message-level words are indexed; timestamp tokens are not stored.
SELECT count() FROM logs WHERE hasAllTokens(line, ['ERROR']);       -- fast index lookup
SELECT count() FROM logs WHERE hasAllTokens(line, ['2024-01-15T10:23:45']);  -- returns 0: token was never indexed

-- The preprocessor strips the ISO timestamp prefix before tokenization.
-- Any tokenizer can be used; timestamp characters are never seen by the tokenizer.
CREATE TABLE logs
(
    id   UInt64,
    line String,
    INDEX idx(line) TYPE text(
        tokenizer   = 'splitByNonAlpha',
        preprocessor = replaceRegexpAll(line, '^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2} ', '')
    )
)
ENGINE = MergeTree ORDER BY id;

-- Preprocessor strips the timestamp, then lowercases the remainder.
-- Postprocessor drops the severity word (error, info, warn, debug) after tokenization.
-- Result: only substantive message words are stored in the index.
CREATE TABLE logs
(
    id   UInt64,
    line String,
    INDEX idx(line) TYPE text(
        tokenizer    = 'splitByNonAlpha',
        preprocessor = lower(replaceRegexpAll(line, '^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2} ', '')),
        postprocessor = if(line IN ('error', 'info', 'warn', 'warning', 'debug', 'critical'), '', line)
    )
)
ENGINE = MergeTree ORDER BY id;

-- Example log line: '2024-01-15T10:23:45 ERROR connection failed'
-- After preprocessor:  'error connection failed'
-- After tokenization:  ['error', 'connection', 'failed']
-- After postprocessor: ['connection', 'failed']   ← 'error' dropped as severity word
SELECT count() FROM logs WHERE hasAllTokens(line, ['connection']);

CREATE TABLE table
(
    str String,
    INDEX idx(str) TYPE text(
        tokenizer = 'splitByNonAlpha',
        postprocessor = stem(str, 'en')
    )
)
ENGINE = MergeTree
ORDER BY tuple();

-- The query token 'running' is stemmed to 'run' before the lookup,
-- matching rows that contain 'run', 'runs', 'ran', 'running', etc.
SELECT count() FROM table WHERE hasAllTokens(str, ['running']);

SELECT [...]
FROM [...]
WHERE string_search_function(column_with_text_index)

SELECT * from table WHERE str = 'Hello';

SELECT * from table WHERE str IN ('Hello', 'World');

SELECT count() FROM table WHERE comment LIKE 'support%';

SELECT count() FROM table WHERE comment LIKE ' support %'; -- 或 `% support %`

SELECT count() FROM table WHERE multiSearchAny(comment, ['clickhouse', 'support']);

SELECT count() FROM table WHERE multiSearchAny(comment, [' clickhouse ', ' support ']);

SELECT count() FROM table WHERE startsWith(comment, 'clickhouse support');

startsWith(comment, 'clickhouse supports ')`

SELECT count() FROM table WHERE endsWith(comment, ' olap engine');

SELECT count() FROM table WHERE hasToken(comment, 'clickhouse');

-- 以字符串参数传入搜索标记
SELECT count() FROM table WHERE hasAnyTokens(comment, 'clickhouse olap');
SELECT count() FROM table WHERE hasAllTokens(comment, 'clickhouse olap');

-- 以 Array(String) 传入搜索标记
SELECT count() FROM table WHERE hasAnyTokens(comment, ['clickhouse', 'olap']);
SELECT count() FROM table WHERE hasAllTokens(comment, ['clickhouse', 'olap']);

-- Matches: 'clickhouse' and 'olap' must appear consecutively in that order
SELECT count() FROM table WHERE hasPhrase(comment, 'clickhouse olap');

-- Does NOT match a row containing 'olap clickhouse' (wrong order)
-- Does NOT match a row containing 'clickhouse fast olap' (non-consecutive)

SELECT count() FROM table WHERE has(array, 'clickhouse');

SELECT count() FROM table WHERE hasAny(tags, ['clickhouse', 'olap']);
SELECT count() FROM table WHERE hasAll(tags, ['clickhouse', 'olap']);

SELECT count() FROM table WHERE mapContainsKey(map, 'clickhouse');
-- 或
SELECT count() FROM table WHERE mapContains(map, 'clickhouse');

SELECT count() FROM table WHERE mapContainsValue(map, 'clickhouse');

SELECT count() FROM table WHERE mapContainsKeyLike(map, '% clickhouse %');
SELECT count() FROM table WHERE mapContainsValueLike(map, '% clickhouse %');

SELECT count() FROM table WHERE map['engine'] = 'clickhouse';

CREATE TABLE posts
(
    post_id UInt64,
    title String,
    content String,
    keywords Array(String)
)
ENGINE = MergeTree
ORDER BY (post_id);

SELECT count() FROM posts WHERE has(keywords, 'clickhouse'); -- 全表扫描，速度较慢——需检查每篇文章中的每个关键词

ALTER TABLE posts ADD INDEX keywords_idx(keywords) TYPE text(tokenizer = splitByNonAlpha);
ALTER TABLE posts MATERIALIZE INDEX keywords_idx; -- 别忘了为现有数据重建索引

CREATE TABLE logs
(
    id UInt64,
    timestamp DateTime,
    message String,
    attributes Map(String, String)
)
ENGINE = MergeTree
ORDER BY (timestamp);

-- 查找所有包含限流数据的日志：
SELECT * FROM logs WHERE has(mapKeys(attributes), 'rate_limit'); -- 全表扫描，速度较慢

-- 查找所有来自特定 IP 的日志：
SELECT * FROM logs WHERE has(mapValues(attributes), '192.168.1.1'); -- 全表扫描，速度较慢

ALTER TABLE logs ADD INDEX attributes_keys_idx mapKeys(attributes) TYPE text(tokenizer = array);
ALTER TABLE posts MATERIALIZE INDEX attributes_keys_idx;

ALTER TABLE logs ADD INDEX attributes_vals_idx mapValues(attributes) TYPE text(tokenizer = array);
ALTER TABLE posts MATERIALIZE INDEX attributes_vals_idx;

-- 查找所有受速率限制的请求：
SELECT * FROM logs WHERE mapContainsKey(attributes, 'rate_limit'); -- fast

-- 查找来自特定 IP 的所有日志：
SELECT * FROM logs WHERE has(mapValues(attributes), '192.168.1.1'); -- fast

-- 查找任意属性值包含错误信息的所有日志：
SELECT * FROM logs WHERE mapContainsValueLike(attributes, '% error %'); -- fast

CREATE TABLE events
(
    id UInt64,
    data JSON,
    INDEX json_idx JSONAllValues(data) TYPE text(tokenizer = splitByNonAlpha)
)
ENGINE = MergeTree
ORDER BY id;

SELECT * FROM events WHERE data.user_name = 'alice';
SELECT * FROM events WHERE data.message LIKE '% error %';
SELECT * FROM events WHERE startsWith(data.status, 'fail');
SELECT * FROM events WHERE hasToken(data.title, 'clickhouse');

SELECT * FROM events WHERE hasAllTokens(data.message::String, 'connection timeout');
SELECT * FROM events WHERE data.status_code::UInt64 = 404;
SELECT * FROM events WHERE has(data.tags::Array(String), 'bug')

SELECT * FROM events WHERE data.level IN ('error', 'critical');

SELECT *
FROM tab
WHERE hasAllTokens(col, 'weather in Tokyo')

SELECT *
FROM tab
WHERE hasPhrase(col, 'weather in Tokyo')

CREATE TABLE tab (
    id UInt32,
    text String,
    INDEX idx text TYPE text(tokenizer = splitByNonAlpha)
)
ENGINE = MergeTree
ORDER BY id;

INSERT INTO tab VALUES
    (1, 'weather in New York'),
    (2, 'New weather in York'),
    (3, 'weather in New Orleans');

SELECT column_a, column_b, ...
FROM [...]
WHERE string_search_function(column_with_text_index)

EXPLAIN PLAN actions = 1
SELECT count()
FROM table
WHERE hasToken(col, 'some_token')
SETTINGS query_plan_direct_read_from_text_index = 0, -- 禁用直接读取

[...]
Filter ((WHERE + Change column names to column identifiers))
Filter column: hasToken(__table1.col, 'some_token'_String) (removed)
Actions: INPUT : 0 -> col String : 0
         COLUMN Const(String) -> 'some_token'_String String : 1
         FUNCTION hasToken(col :: 0, 'some_token'_String :: 1) -> hasToken(__table1.col, 'some_token'_String) UInt8 : 2
[...]

EXPLAIN PLAN actions = 1
SELECT count()
FROM table
WHERE hasToken(col, 'some_token')
SETTINGS query_plan_direct_read_from_text_index = 1, -- 启用直接读取

[...]
Expression (Before GROUP BY)
Positions:
  Filter
  Filter column: __text_index_idx_hasToken_94cc2a813036b453d84b6fb344a63ad3 (removed)
  Actions: INPUT :: 0 -> __text_index_idx_hasToken_94cc2a813036b453d84b6fb344a63ad3 UInt8 : 0
[...]

EXPLAIN actions = 1
SELECT count()
FROM table
WHERE (col LIKE '%some-token%') AND (d >= today())
SETTINGS query_plan_text_index_add_hint = 0
FORMAT TSV

[...]
Prewhere filter column: and(like(__table1.col, \'%some-token%\'_String), greaterOrEquals(__table1.d, _CAST(20440_Date, \'Date\'_String))) (removed)
[...]

EXPLAIN actions = 1
SELECT count()
FROM table
WHERE col LIKE '%some-token%'
SETTINGS query_plan_text_index_add_hint = 1

[...]
Prewhere filter column: and(__text_index_idx_col_like_d306f7c9c95238594618ac23eb7a3f74, like(__table1.col, \'%some-token%\'_String), greaterOrEquals(__table1.d, _CAST(20440_Date, \'Date\'_String))) (removed)
[...]

CREATE TABLE hackernews (
    id UInt64,
    deleted UInt8,
    type String,
    author String,
    timestamp DateTime,
    comment String,
    dead UInt8,
    parent UInt64,
    poll UInt64,
    children Array(UInt32),
    url String,
    score UInt32,
    title String,
    parts Array(UInt32),
    descendants UInt32
)
ENGINE = MergeTree
ORDER BY (type, author);

INSERT INTO hackernews
    SELECT * FROM s3Cluster(
        'default',
        'https://datasets-documentation.s3.eu-west-3.amazonaws.com/hackernews/hacknernews.parquet',
        'Parquet',
        '
    id UInt64,
    deleted UInt8,
    type String,
    by String,
    time DateTime,
    text String,
    dead UInt8,
    parent UInt64,
    poll UInt64,
    kids Array(UInt32),
    url String,
    score UInt32,
    title String,
    parts Array(UInt32),
    descendants UInt32');

-- Add the index
ALTER TABLE hackernews ADD INDEX comment_idx comment TYPE text(tokenizer = splitByNonAlpha);

-- Materialize the index for existing data
ALTER TABLE hackernews MATERIALIZE INDEX comment_idx SETTINGS mutations_sync = 2;

SELECT count()
FROM hackernews
WHERE hasToken(comment, 'ClickHouse')
SETTINGS query_plan_direct_read_from_text_index = 0;

┌─count()─┐
│     516 │
└─────────┘

1 row in set. Elapsed: 0.362 sec. Processed 24.90 million rows, 9.51 GB

SELECT count()
FROM hackernews
WHERE hasToken(comment, 'ClickHouse')
SETTINGS query_plan_direct_read_from_text_index = 1;

┌─count()─┐
│     516 │
└─────────┘

1 row in set. Elapsed: 0.008 sec. Processed 3.15 million rows, 3.15 MB

SELECT count()
FROM hackernews
WHERE hasAnyTokens(comment, 'love ClickHouse')
SETTINGS query_plan_direct_read_from_text_index = 0;

┌─count()─┐
│  408426 │
└─────────┘

1 row in set. Elapsed: 1.329 sec. Processed 28.74 million rows, 9.72 GB

SELECT count()
FROM hackernews
WHERE hasAnyTokens(comment, 'love ClickHouse')
SETTINGS query_plan_direct_read_from_text_index = 1;

┌─count()─┐
│  408426 │
└─────────┘

1 row in set. Elapsed: 0.015 sec. Processed 27.99 million rows, 27.99 MB

SELECT count()
FROM hackernews
WHERE hasAllTokens(comment, 'love ClickHouse')
SETTINGS query_plan_direct_read_from_text_index = 0;

┌─count()─┐
│      11 │
└─────────┘

1 row in set. Elapsed: 0.184 sec. Processed 147.46 thousand rows, 57.03 MB

SELECT count()
FROM hackernews
WHERE hasAllTokens(comment, 'love ClickHouse')
SETTINGS query_plan_direct_read_from_text_index = 1;

┌─count()─┐
│      11 │
└─────────┘

1 row in set. Elapsed: 0.007 sec. Processed 147.46 thousand rows, 147.46 KB

SELECT count()
FROM hackernews
WHERE hasToken(comment, 'ClickHouse') OR hasToken(comment, 'clickhouse')
SETTINGS query_plan_direct_read_from_text_index = 0;

┌─count()─┐
│     769 │
└─────────┘

1 row in set. Elapsed: 0.450 sec. Processed 25.87 million rows, 9.58 GB

SELECT count()
FROM hackernews
WHERE hasToken(comment, 'ClickHouse') OR hasToken(comment, 'clickhouse')
SETTINGS query_plan_direct_read_from_text_index = 1;

┌─count()─┐
│     769 │
└─────────┘

1 row in set. Elapsed: 0.013 sec. Processed 25.87 million rows, 51.73 MB