summaryrefslogtreecommitdiffstats
path: root/tests/dataframe/unit/test_dataframe_writer.py
blob: 042b9152c4fd6559b3b7f01f1c902c500885df2f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
from unittest import mock

import sqlglot
from sqlglot.schema import MappingSchema
from tests.dataframe.unit.dataframe_sql_validator import DataFrameSQLValidator


class TestDataFrameWriter(DataFrameSQLValidator):
    maxDiff = None

    def test_insertInto_full_path(self):
        df = self.df_employee.write.insertInto("catalog.db.table_name")
        expected = "INSERT INTO catalog.db.table_name SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_insertInto_db_table(self):
        df = self.df_employee.write.insertInto("db.table_name")
        expected = "INSERT INTO db.table_name SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_insertInto_table(self):
        df = self.df_employee.write.insertInto("table_name")
        expected = "INSERT INTO table_name SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_insertInto_overwrite(self):
        df = self.df_employee.write.insertInto("table_name", overwrite=True)
        expected = "INSERT OVERWRITE TABLE table_name SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    @mock.patch("sqlglot.schema", MappingSchema())
    def test_insertInto_byName(self):
        sqlglot.schema.add_table("table_name", {"employee_id": "INT"})
        df = self.df_employee.write.byName.insertInto("table_name")
        expected = "INSERT INTO table_name SELECT `a1`.`employee_id` AS `employee_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_insertInto_cache(self):
        df = self.df_employee.cache().write.insertInto("table_name")
        expected_statements = [
            "DROP VIEW IF EXISTS t12441",
            "CACHE LAZY TABLE t12441 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)",
            "INSERT INTO table_name SELECT `t12441`.`employee_id` AS `employee_id`, `t12441`.`fname` AS `fname`, `t12441`.`lname` AS `lname`, `t12441`.`age` AS `age`, `t12441`.`store_id` AS `store_id` FROM `t12441` AS `t12441`",
        ]
        self.compare_sql(df, expected_statements)

    def test_saveAsTable_format(self):
        with self.assertRaises(NotImplementedError):
            self.df_employee.write.saveAsTable("table_name", format="parquet").sql(pretty=False)[0]

    def test_saveAsTable_append(self):
        df = self.df_employee.write.saveAsTable("table_name", mode="append")
        expected = "INSERT INTO table_name SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_saveAsTable_overwrite(self):
        df = self.df_employee.write.saveAsTable("table_name", mode="overwrite")
        expected = "CREATE OR REPLACE TABLE table_name AS SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_saveAsTable_error(self):
        df = self.df_employee.write.saveAsTable("table_name", mode="error")
        expected = "CREATE TABLE table_name AS SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_saveAsTable_ignore(self):
        df = self.df_employee.write.saveAsTable("table_name", mode="ignore")
        expected = "CREATE TABLE IF NOT EXISTS table_name AS SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_mode_standalone(self):
        df = self.df_employee.write.mode("ignore").saveAsTable("table_name")
        expected = "CREATE TABLE IF NOT EXISTS table_name AS SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_mode_override(self):
        df = self.df_employee.write.mode("ignore").saveAsTable("table_name", mode="overwrite")
        expected = "CREATE OR REPLACE TABLE table_name AS SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)"
        self.compare_sql(df, expected)

    def test_saveAsTable_cache(self):
        df = self.df_employee.cache().write.saveAsTable("table_name")
        expected_statements = [
            "DROP VIEW IF EXISTS t12441",
            "CACHE LAZY TABLE t12441 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT `a1`.`employee_id` AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, `a1`.`age` AS `age`, `a1`.`store_id` AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)",
            "CREATE TABLE table_name AS SELECT `t12441`.`employee_id` AS `employee_id`, `t12441`.`fname` AS `fname`, `t12441`.`lname` AS `lname`, `t12441`.`age` AS `age`, `t12441`.`store_id` AS `store_id` FROM `t12441` AS `t12441`",
        ]
        self.compare_sql(df, expected_statements)