chdb_hook 模块参考文档

# LOAD 'chdb_hook';
LOAD

# CREATE TABLE times (
    id     INT NOT NULL,
    months INT NOT NULL,
    days   INT NOT NULL
);
CREATE TABLE

# COPY times FROM 's3://datasets-documentation/my-test-bucket-768/{some,another}_prefix/some_file_{1..3}.csv';
COPY 18

CREATE TABLE times (
    id     INT PRIMARY KEY,
    months INT NOT NULL,
    days   INT NOT NULL
);

COPY times FROM 's3://datasets-documentation/my-test-bucket-768/some_prefix/some_file_1.csv';

file:///tmp/users.parquet

https://datasets-documentation.s3.eu-west-3.amazonaws.com/my-test-bucket-768/some_prefix/some_file_1.csv

s3://{bucket}/{path}

s3://{bucket}.s3.{region}.amazonaws.com/{path}

gs://storage.googleapis.com/{bucket}/{path}

gs://{bucket}/{path}

az://{account}.blob.core.windows.net/{container}/{blob}

az://{host}/{container}/{blob}

abfs://{container}@{account}.dfs.core.windows.net/{blob}

hdfs://{host}/{path}
hdfs://{host}:{port}/{path}

CREATE TABLE times (
    id     INT NOT NULL,
    months INT NOT NULL,
    days   INT NOT NULL
);

COPY times FROM 's3://datasets-documentation/my-test-bucket-768/{some,another}_prefix/some_file_{1..3}.csv';

COPY users TO 'file:///tmp/users.parquet' (
    structure 'id Int64, name String, age Nullable(UInt8), attributes JSON'
);

ERROR:  chdb: error executing chDB query
DETAIL:  Code: 53. DB::Exception: Requested type of column p doesn't match parquet schema
CONTEXT:  query: SELECT * FROM file({path:String}, {format:String}, {structure:String})
STATEMENT:  COPY "users" FROM 'file:///tmp/users.data' (format 'Parquet');

2026-08-08 09:41:06.842 EDT [59940] LOG:  executing chDB query
2026-08-08 09:41:06.842 EDT [59940] DETAIL:  query: SELECT * FROM file({path:String}, {format:String}, {structure:String})
2026-08-08 09:41:06.842 EDT [59940] CONTEXT:  params: { path: "/tmp/users.data", format: "Parquet", structure: "user_id Nullable(Int64), username Nullable(String), password Nullable(String)" }
2026-08-08 09:41:06.842 EDT [59940] STATEMENT:  COPY "users" FROM 'file:///tmp/users.data' (format 'Parquet');

CREATE TABLE reviews () WITH (
    structure_from = 's3://datasets-documentation/amazon_reviews/amazon_reviews_2015.snappy.parquet'
);

CREATE TABLE reviews () WITH (
    copy_from = 's3://datasets-documentation/amazon_reviews/amazon_reviews_2015.snappy.parquet'
);

CREATE TABLE times (
    id     INT NOT NULL,
    months INT NOT NULL,
    days   INT NOT NULL
) WITH (copy_from = 's3://datasets-documentation/my-test-bucket-768/some_prefix/some_file_1.csv');

CREATE TABLE users () WITH (
    copy_from     = 's3://my-bucket/users.csv',
    access_key    = 'AKIAIOSFODNN7EXAMPLE',
    access_secret = 'wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY',
    format        = 'CSVWithNames',
    fillfactor    = 90
);

ERROR:  invalid byte sequence for encoding "UTF8": 0x00

CREATE TABLE logs (id bigint, payload bytea) WITH (
    copy_from = 's3://my-bucket/logs.parquet'
);

SET chdb_hook.max_memory = '1 GB';

SET chdb_hook.max_threads = 4;

SET chdb_hook.max_parsing_threads = 2;

SELECT version FROM pg_get_loaded_modules() WHERE module_name = 'chdb_hook';