その他のJSONフォーマットの扱い

SELECT *
FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/pypi/json/*.json.gz', JSONEachRow)
LIMIT 5

┌───────date─┬─country_code─┬─project────────────┬─type────────┬─installer────┬─python_minor─┬─system─┬─version─┐
│ 2022-11-15 │ CN           │ clickhouse-connect │ bdist_wheel │ bandersnatch │              │        │ 0.2.8   │
│ 2022-11-15 │ CN           │ clickhouse-connect │ bdist_wheel │ bandersnatch │              │        │ 0.2.8   │
│ 2022-11-15 │ CN           │ clickhouse-connect │ bdist_wheel │ bandersnatch │              │        │ 0.2.8   │
│ 2022-11-15 │ CN           │ clickhouse-connect │ bdist_wheel │ bandersnatch │              │        │ 0.2.8   │
│ 2022-11-15 │ CN           │ clickhouse-connect │ bdist_wheel │ bandersnatch │              │        │ 0.2.8   │
└────────────┴──────────────┴────────────────────┴─────────────┴──────────────┴──────────────┴────────┴─────────┘

5 rows in set. Elapsed: 0.449 sec.

SELECT *
FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/pypi/json/*.json.gz', JSONAsObject)
LIMIT 5

┌─json─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ {"country_code":"CN","date":"2022-11-15","installer":"bandersnatch","project":"clickhouse-connect","python_minor":"","system":"","type":"bdist_wheel","version":"0.2.8"} │
│ {"country_code":"CN","date":"2022-11-15","installer":"bandersnatch","project":"clickhouse-connect","python_minor":"","system":"","type":"bdist_wheel","version":"0.2.8"} │
│ {"country_code":"CN","date":"2022-11-15","installer":"bandersnatch","project":"clickhouse-connect","python_minor":"","system":"","type":"bdist_wheel","version":"0.2.8"} │
│ {"country_code":"CN","date":"2022-11-15","installer":"bandersnatch","project":"clickhouse-connect","python_minor":"","system":"","type":"bdist_wheel","version":"0.2.8"} │
│ {"country_code":"CN","date":"2022-11-15","installer":"bandersnatch","project":"clickhouse-connect","python_minor":"","system":"","type":"bdist_wheel","version":"0.2.8"} │
└──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘

5 rows in set. Elapsed: 0.338 sec.

CREATE TABLE pypi
(
    `json` JSON
)
ENGINE = MergeTree
ORDER BY tuple();

INSERT INTO pypi SELECT *
FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/pypi/json/*.json.gz', JSONAsObject)
LIMIT 5;

SELECT *
FROM pypi
LIMIT 2;

┌─json─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ {"country_code":"CN","date":"2022-11-15","installer":"bandersnatch","project":"clickhouse-connect","python_minor":"","system":"","type":"bdist_wheel","version":"0.2.8"} │
│ {"country_code":"CN","date":"2022-11-15","installer":"bandersnatch","project":"clickhouse-connect","python_minor":"","system":"","type":"bdist_wheel","version":"0.2.8"} │
└──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘

2 rows in set. Elapsed: 0.003 sec.

SELECT count()
FROM s3('https://clickhouse-public-datasets.s3.amazonaws.com/bluesky/file_0001.json.gz', 'JSONEachRow')

Elapsed: 1.198 sec.

Received exception from server (version 24.12.1):
Code: 636. DB::Exception: Received from sql-clickhouse.clickhouse.com:9440. DB::Exception: The table structure cannot be extracted from a JSONEachRow format file. Error:
Code: 117. DB::Exception: JSON objects have ambiguous data: in some objects path 'record.subject' has type 'String' and in some - 'Tuple(`$type` String, cid String, uri String)'. You can enable setting input_format_json_use_string_type_for_ambiguous_paths_in_named_tuples_inference_from_objects to use String type for path 'record.subject'. (INCORRECT_DATA) (version 24.12.1.18239 (official build))
To increase the maximum number of rows/bytes to read for structure determination, use setting input_format_max_rows_to_read_for_schema_inference/input_format_max_bytes_to_read_for_schema_inference.
You can specify the structure manually: (in file/uri bluesky/file_0001.json.gz). (CANNOT_EXTRACT_TABLE_STRUCTURE)

SELECT count()
FROM s3('https://clickhouse-public-datasets.s3.amazonaws.com/bluesky/file_0001.json.gz', 'JSONAsObject')

┌─count()─┐
│ 1000000 │
└─────────┘

1 row in set. Elapsed: 0.480 sec. Processed 1.00 million rows, 256.00 B (2.08 million rows/s., 533.76 B/s.)

> cat list.json
[
  {
    "path": "Akiba_Hebrew_Academy",
    "month": "2017-08-01",
    "hits": 241
  },
  {
    "path": "Aegithina_tiphia",
    "month": "2018-02-01",
    "hits": 34
  },
  ...
]

CREATE TABLE sometable
(
    `path` String,
    `month` Date,
    `hits` UInt32
)
ENGINE = MergeTree
ORDER BY tuple(month, path)

INSERT INTO sometable
FROM INFILE 'list.json'
FORMAT JSONEachRow

SELECT *
FROM sometable

┌─path──────────────────────┬──────month─┬─hits─┐
│ 1971-72_Utah_Stars_season │ 2016-10-01 │    1 │
│ Akiba_Hebrew_Academy      │ 2017-08-01 │  241 │
│ Aegithina_tiphia          │ 2018-02-01 │   34 │
└───────────────────────────┴────────────┴──────┘

cat objects.json

{
  "a": {
    "path":"April_25,_2017",
    "month":"2018-01-01",
    "hits":2
  },
  "b": {
    "path":"Akahori_Station",
    "month":"2016-06-01",
    "hits":11
  },
  ...
}

INSERT INTO sometable FROM INFILE 'objects.json' FORMAT JSONObjectEachRow;
SELECT * FROM sometable;

┌─path────────────┬──────month─┬─hits─┐
│ Abducens_palsy  │ 2016-05-01 │   28 │
│ Akahori_Station │ 2016-06-01 │   11 │
│ April_25,_2017  │ 2018-01-01 │    2 │
└─────────────────┴────────────┴──────┘

SET format_json_object_each_row_column_for_object_name = 'id'

SELECT * FROM file('objects.json', JSONObjectEachRow)

┌─id─┬─path────────────┬──────month─┬─hits─┐
│ a  │ April_25,_2017  │ 2018-01-01 │    2 │
│ b  │ Akahori_Station │ 2016-06-01 │   11 │
│ c  │ Abducens_palsy  │ 2016-05-01 │   28 │
└────┴─────────────────┴────────────┴──────┘

cat arrays.json

["Akiba_Hebrew_Academy", "2017-08-01", 241],
["Aegithina_tiphia", "2018-02-01", 34],
["1971-72_Utah_Stars_season", "2016-10-01", 1]

SELECT * FROM sometable

┌─c1────────────────────────┬─────────c2─┬──c3─┐
│ Akiba_Hebrew_Academy      │ 2017-08-01 │ 241 │
│ Aegithina_tiphia          │ 2018-02-01 │  34 │
│ 1971-72_Utah_Stars_season │ 2016-10-01 │   1 │
└───────────────────────────┴────────────┴─────┘

cat columns.json

{
  "path": ["2007_Copa_America", "Car_dealerships_in_the_USA", "Dihydromyricetin_reductase"],
  "month": ["2016-07-01", "2015-07-01", "2015-07-01"],
  "hits": [178, 11, 1]
}

SELECT * FROM file('columns.json', JSONColumns)

┌─path───────────────────────┬──────month─┬─hits─┐
│ 2007_Copa_America          │ 2016-07-01 │  178 │
│ Car_dealerships_in_the_USA │ 2015-07-01 │   11 │
│ Dihydromyricetin_reductase │ 2015-07-01 │    1 │
└────────────────────────────┴────────────┴──────┘

SELECT * FROM file('columns-array.json', JSONCompactColumns)

┌─c1──────────────┬─────────c2─┬─c3─┐
│ Heidenrod       │ 2017-01-01 │ 10 │
│ Arthur_Henrique │ 2016-11-01 │ 12 │
│ Alan_Ebnother   │ 2015-11-01 │ 66 │
└─────────────────┴────────────┴────┘

cat custom.json

[
  {"name": "Joe", "age": 99, "type": "person"},
  {"url": "/my.post.MD", "hits": 1263, "type": "post"},
  {"message": "Warning on disk usage", "type": "log"}
]

CREATE TABLE events
(
    `data` String
)
ENGINE = MergeTree
ORDER BY ()

INSERT INTO events (data)
FROM INFILE 'custom.json'
FORMAT JSONAsString

SELECT
    JSONExtractString(data, 'type') AS type,
    data
FROM events

┌─type───┬─data─────────────────────────────────────────────────┐
│ person │ {"name": "Joe", "age": 99, "type": "person"}         │
│ post   │ {"url": "/my.post.MD", "hits": 1263, "type": "post"} │
│ log    │ {"message": "Warning on disk usage", "type": "log"}  │
└────────┴──────────────────────────────────────────────────────┘

SELECT *
FROM file('list-nested.json', JSONEachRow, 'page Tuple(path String, title String, owner_id UInt16), month Date, hits UInt32')
LIMIT 1

┌─page───────────────────────────────────────────────┬──────month─┬─hits─┐
│ ('Akiba_Hebrew_Academy','Akiba Hebrew Academy',12) │ 2017-08-01 │  241 │
└────────────────────────────────────────────────────┴────────────┴──────┘

SET input_format_import_nested_json = 1

SELECT *
FROM file('list-nested.json', JSONEachRow, '`page.owner_id` UInt32, `page.title` String, month Date, hits UInt32')
LIMIT 1

┌─page.owner_id─┬─page.title───────────┬──────month─┬─hits─┐
│            12 │ Akiba Hebrew Academy │ 2017-08-01 │  241 │
└───────────────┴──────────────────────┴────────────┴──────┘

CREATE TABLE shorttable
(
    `path` String,
    `hits` UInt32
)
ENGINE = MergeTree
ORDER BY path

INSERT INTO shorttable FROM INFILE 'list.json' FORMAT JSONEachRow;
SELECT * FROM shorttable

┌─path──────────────────────┬─hits─┐
│ 1971-72_Utah_Stars_season │    1 │
│ Aegithina_tiphia          │   34 │
│ Akiba_Hebrew_Academy      │  241 │
└───────────────────────────┴──────┘

SET input_format_skip_unknown_fields = 0;
INSERT INTO shorttable FROM INFILE 'list.json' FORMAT JSONEachRow;

Ok.
Exception on client:
Code: 117. DB::Exception: Unknown field found while parsing JSONEachRow format: month: (in file/uri /data/clickhouse/user_files/list.json): (at row 1)

SELECT * FROM file('data.bson', BSONEachRow)

┌─path──────────────────────┬─month─┬─hits─┐
│ Bob_Dolman                │ 17106 │  245 │
│ 1-krona                   │ 17167 │    4 │
│ Ahmadabad-e_Kalij-e_Sofla │ 17167 │    3 │
└───────────────────────────┴───────┴──────┘

SELECT *
FROM sometable
INTO OUTFILE 'out.bson'
FORMAT BSONEachRow