Tsurugi DBからデータを出力する

> cat select.sql
select * from test_table;
> tgsql  -c ipc://tsurugi --script select.sql
[main] INFO com.tsurugidb.tgsql.core.TgsqlRunner - establishing connection: ipc://tsurugi
[main] INFO com.tsurugidb.tgsql.core.TgsqlRunner - start processing script
// {"columns":[{"name":"id","label":"id","type":"INT4","dimension":0}]}
{"id":1}
{"id":2}
{"id":3}
{"id":4}

> mkdir result
> tgdump test_table --to result --connection ipc://tsurugi
> ls result/test_table/
d1735190942_0_0.parquet  d1735190942_1_0.parquet

> cat look.py
import sys
import pyarrow.parquet as pq

if len(sys.argv) < 2:
    print("Usage: python script.py <folder_path>")
    sys.exit(1)

folder_path = sys.argv[1]

if not os.path.exists(folder_path):
    print(f"Error: The folder '{folder_path}' does not exist.")
    sys.exit(1)

parquet_files = [os.path.join(folder_path, file) for file in os.listdir(folder_path) if file.endswith(".parquet")]

if not parquet_files:
    print(f"No .parquet files found in folder: {folder_path}")
    sys.exit(0)

for file in parquet_files:
    print(f"Reading: {file}")
    table = pq.read_table(file)
    print(table)

> python3 look.py result/test_table
Reading: result/test_table/d1735190942_0_0.parquet
pyarrow.Table
id: int32
----
id: [[1,2,3]]
Reading: result/test_table/d1735190942_1_0.parquet
pyarrow.Table
id: int32
----
id: [[4]]

> export emb_ver=0.11.5
> curl -L https://github.com/embulk/embulk/releases/download/v${emb_ver}/embulk-${emb_ver}.jar -o embulk-${emb_ver}.jar
> java -jar embulk-${emb_ver}.jar install io.github.hishidama.embulk:embulk-input-tsurugidb:1.1.0
> cat 2.yml
in:
  type:
    source: maven
    group: io.github.hishidama.embulk
    name: tsurugidb
    version: 1.1.0
  endpoint: ipc://tsurugi
  query: select * from test_table
out:
  type: stdout
>  java  -jar embulk-${emb_ver}.jar run 2.yml

3
4
1
2