Read a file's schema and metadata

CREATE TABLE orders AS SELECT * FROM (VALUES
  (1,  'Alice Ng',      'north', DATE '2026-01-03', 120.00, 'widget', 'a|b',   '{"channel":"web","items":[1,2]}'),
  (2,  'alice ng',      'north', DATE '2026-01-05',  80.50, 'gadget', 'b',     '{"channel":"shop","items":[3]}'),
  (3,  'Bob  Okafor',   'south', DATE '2026-01-05', 300.00, 'widget', 'a|c',   '{"channel":"web","items":[4,5,6]}'),
  (4,  'Carla Díaz',    'east',  DATE '2026-01-09',  NULL,  'gizmo',  NULL,    '{"channel":"web","items":[]}'),
  (5,  'Bob Okafor',    'south', DATE '2026-01-12',  45.25, 'gadget', 'c',     '{"channel":"phone","items":[7]}'),
  (6,  'Dev Patel',     'west',  DATE '2026-01-12', 510.00, 'widget', 'a',     '{"channel":"web","items":[8,9]}'),
  (7,  'Carla Diaz',    'east',  DATE '2026-01-20',  99.99, 'gizmo',  'b|c',   '{"channel":"shop","items":[10]}'),
  (8,  'Dev Patel',     'west',  DATE '2026-02-02', 510.00, 'widget', 'a',     '{"channel":"web","items":[8,9]}'),
  (9,  'Eve Larsen',    NULL,    DATE '2026-02-03',  15.00, 'gadget', NULL,    '{"channel":"web","items":[11]}'),
  (10, 'Alice Ng',      'north', DATE '2026-02-10', 220.00, 'gizmo',  'a|b|c', '{"channel":"phone","items":[12,13]}')
) t(order_id, customer, region, order_date, amount, product, tags, meta);

-- 5000 rows written as three row groups of at most 2048 rows
COPY (SELECT i AS id, 'row ' || i AS label FROM range(5000) t(i)) TO '<your_scratch_dir>/inspect_many.parquet' (FORMAT parquet, ROW_GROUP_SIZE 2048);
COPY (SELECT order_id, customer, order_date, amount FROM orders) TO '<your_scratch_dir>/inspect_orders.csv' (HEADER);
CREATE TEMP TABLE file_schema AS SELECT name, duckdb_type FROM parquet_schema('<your_scratch_dir>/inspect_many.parquet') WHERE num_children IS NULL;
CREATE TEMP TABLE file_info AS SELECT num_rows, num_row_groups FROM parquet_file_metadata('<your_scratch_dir>/inspect_many.parquet');
CREATE TEMP TABLE row_groups AS
SELECT row_group_id, stats_min::BIGINT AS id_min, stats_max::BIGINT AS id_max, num_values
FROM parquet_metadata('<your_scratch_dir>/inspect_many.parquet') WHERE path_in_schema = 'id';
CREATE TEMP TABLE csv_format AS
SELECT "Delimiter" AS delimiter, "HasHeader" AS has_header, [c.name FOR c IN "Columns"] AS column_names, [c.type FOR c IN "Columns"] AS column_types
FROM sniff_csv('<your_scratch_dir>/inspect_orders.csv');
SELECT * FROM file_schema;
SELECT * FROM file_info;
SELECT * FROM row_groups ORDER BY row_group_id;
SELECT * FROM csv_format;
SELECT CASE WHEN ((SELECT list((name, duckdb_type) ORDER BY name) FROM file_schema) = [('id', 'BIGINT'), ('label', 'VARCHAR')] AND (SELECT (num_rows, num_row_groups) FROM file_info) = (5000, 3) AND (SELECT list((id_min, id_max, num_values) ORDER BY row_group_id) FROM row_groups) = [(0, 2047, 2048), (2048, 4095, 2048), (4096, 4999, 904)] AND (SELECT (delimiter, has_header) FROM csv_format) = (',', true) AND (SELECT column_names FROM csv_format) = ['order_id', 'customer', 'order_date', 'amount'] AND (SELECT column_types FROM csv_format) = ['BIGINT', 'VARCHAR', 'DATE', 'DOUBLE']) THEN 'as expected' ELSE error('the Parquet footer was not 3 row groups over 5000 rows with their id ranges, or the CSV was not detected as comma-separated with a header and four typed columns') END AS verdict;