summaryrefslogtreecommitdiffstats
path: root/tests/dataframe/unit
diff options
context:
space:
mode:
Diffstat (limited to 'tests/dataframe/unit')
-rw-r--r--tests/dataframe/unit/test_dataframe.py20
-rw-r--r--tests/dataframe/unit/test_dataframe_writer.py36
-rw-r--r--tests/dataframe/unit/test_session.py17
3 files changed, 39 insertions, 34 deletions
diff --git a/tests/dataframe/unit/test_dataframe.py b/tests/dataframe/unit/test_dataframe.py
index e36667b..24850bc 100644
--- a/tests/dataframe/unit/test_dataframe.py
+++ b/tests/dataframe/unit/test_dataframe.py
@@ -4,6 +4,8 @@ from tests.dataframe.unit.dataframe_sql_validator import DataFrameSQLValidator
class TestDataframe(DataFrameSQLValidator):
+ maxDiff = None
+
def test_hash_select_expression(self):
expression = exp.select("cola").from_("table")
self.assertEqual("t17051", DataFrame._create_hash_from_expression(expression))
@@ -16,26 +18,26 @@ class TestDataframe(DataFrameSQLValidator):
def test_cache(self):
df = self.df_employee.select("fname").cache()
expected_statements = [
- "DROP VIEW IF EXISTS t11623",
- "CACHE LAZY TABLE t11623 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT CAST(`a1`.`fname` AS string) AS `fname` 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`)",
- "SELECT `t11623`.`fname` AS `fname` FROM `t11623` AS `t11623`",
+ "DROP VIEW IF EXISTS t31563",
+ "CACHE LAZY TABLE t31563 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT CAST(`a1`.`fname` AS STRING) AS `fname` 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`)",
+ "SELECT `t31563`.`fname` AS `fname` FROM `t31563` AS `t31563`",
]
self.compare_sql(df, expected_statements)
def test_persist_default(self):
df = self.df_employee.select("fname").persist()
expected_statements = [
- "DROP VIEW IF EXISTS t11623",
- "CACHE LAZY TABLE t11623 OPTIONS('storageLevel' = 'MEMORY_AND_DISK_SER') AS SELECT CAST(`a1`.`fname` AS string) AS `fname` 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`)",
- "SELECT `t11623`.`fname` AS `fname` FROM `t11623` AS `t11623`",
+ "DROP VIEW IF EXISTS t31563",
+ "CACHE LAZY TABLE t31563 OPTIONS('storageLevel' = 'MEMORY_AND_DISK_SER') AS SELECT CAST(`a1`.`fname` AS STRING) AS `fname` 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`)",
+ "SELECT `t31563`.`fname` AS `fname` FROM `t31563` AS `t31563`",
]
self.compare_sql(df, expected_statements)
def test_persist_storagelevel(self):
df = self.df_employee.select("fname").persist("DISK_ONLY_2")
expected_statements = [
- "DROP VIEW IF EXISTS t11623",
- "CACHE LAZY TABLE t11623 OPTIONS('storageLevel' = 'DISK_ONLY_2') AS SELECT CAST(`a1`.`fname` AS string) AS `fname` 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`)",
- "SELECT `t11623`.`fname` AS `fname` FROM `t11623` AS `t11623`",
+ "DROP VIEW IF EXISTS t31563",
+ "CACHE LAZY TABLE t31563 OPTIONS('storageLevel' = 'DISK_ONLY_2') AS SELECT CAST(`a1`.`fname` AS STRING) AS `fname` 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`)",
+ "SELECT `t31563`.`fname` AS `fname` FROM `t31563` AS `t31563`",
]
self.compare_sql(df, expected_statements)
diff --git a/tests/dataframe/unit/test_dataframe_writer.py b/tests/dataframe/unit/test_dataframe_writer.py
index 14b4a0a..7c646f5 100644
--- a/tests/dataframe/unit/test_dataframe_writer.py
+++ b/tests/dataframe/unit/test_dataframe_writer.py
@@ -6,39 +6,41 @@ 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "INSERT INTO catalog.db.table_name SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "INSERT INTO db.table_name SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "INSERT INTO table_name SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "INSERT OVERWRITE TABLE table_name SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) 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`)"
+ expected = "INSERT INTO table_name SELECT CAST(`a1`.`employee_id` AS INT) 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 t35612",
- "CACHE LAZY TABLE t35612 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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 `t35612`.`employee_id` AS `employee_id`, `t35612`.`fname` AS `fname`, `t35612`.`lname` AS `lname`, `t35612`.`age` AS `age`, `t35612`.`store_id` AS `store_id` FROM `t35612` AS `t35612`",
+ "DROP VIEW IF EXISTS t37164",
+ "CACHE LAZY TABLE t37164 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 `t37164`.`employee_id` AS `employee_id`, `t37164`.`fname` AS `fname`, `t37164`.`lname` AS `lname`, `t37164`.`age` AS `age`, `t37164`.`store_id` AS `store_id` FROM `t37164` AS `t37164`",
]
self.compare_sql(df, expected_statements)
@@ -48,39 +50,39 @@ class TestDataFrameWriter(DataFrameSQLValidator):
def test_saveAsTable_append(self):
df = self.df_employee.write.saveAsTable("table_name", mode="append")
- expected = "INSERT INTO table_name SELECT CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "INSERT INTO table_name SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "CREATE OR REPLACE TABLE table_name AS SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "CREATE TABLE table_name AS SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "CREATE TABLE IF NOT EXISTS table_name AS SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "CREATE TABLE IF NOT EXISTS table_name AS SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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`)"
+ expected = "CREATE OR REPLACE TABLE table_name AS SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 t35612",
- "CACHE LAZY TABLE t35612 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT CAST(`a1`.`employee_id` AS int) AS `employee_id`, CAST(`a1`.`fname` AS string) AS `fname`, CAST(`a1`.`lname` AS string) AS `lname`, CAST(`a1`.`age` AS int) AS `age`, CAST(`a1`.`store_id` AS int) 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 `t35612`.`employee_id` AS `employee_id`, `t35612`.`fname` AS `fname`, `t35612`.`lname` AS `lname`, `t35612`.`age` AS `age`, `t35612`.`store_id` AS `store_id` FROM `t35612` AS `t35612`",
+ "DROP VIEW IF EXISTS t37164",
+ "CACHE LAZY TABLE t37164 OPTIONS('storageLevel' = 'MEMORY_AND_DISK') AS SELECT CAST(`a1`.`employee_id` AS INT) AS `employee_id`, CAST(`a1`.`fname` AS STRING) AS `fname`, CAST(`a1`.`lname` AS STRING) AS `lname`, CAST(`a1`.`age` AS INT) AS `age`, CAST(`a1`.`store_id` AS INT) 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 `t37164`.`employee_id` AS `employee_id`, `t37164`.`fname` AS `fname`, `t37164`.`lname` AS `lname`, `t37164`.`age` AS `age`, `t37164`.`store_id` AS `store_id` FROM `t37164` AS `t37164`",
]
self.compare_sql(df, expected_statements)
diff --git a/tests/dataframe/unit/test_session.py b/tests/dataframe/unit/test_session.py
index 7e8bfad..55aa547 100644
--- a/tests/dataframe/unit/test_session.py
+++ b/tests/dataframe/unit/test_session.py
@@ -11,32 +11,32 @@ from tests.dataframe.unit.dataframe_sql_validator import DataFrameSQLValidator
class TestDataframeSession(DataFrameSQLValidator):
def test_cdf_one_row(self):
df = self.spark.createDataFrame([[1, 2]], ["cola", "colb"])
- expected = "SELECT `a2`.`cola` AS `cola`, `a2`.`colb` AS `colb` FROM (VALUES (1, 2)) AS `a2`(`cola`, `colb`)"
+ expected = "SELECT `a2`.`cola` AS `cola`, `a2`.`colb` AS `colb` FROM VALUES (1, 2) AS `a2`(`cola`, `colb`)"
self.compare_sql(df, expected)
def test_cdf_multiple_rows(self):
df = self.spark.createDataFrame([[1, 2], [3, 4], [None, 6]], ["cola", "colb"])
- expected = "SELECT `a2`.`cola` AS `cola`, `a2`.`colb` AS `colb` FROM (VALUES (1, 2), (3, 4), (NULL, 6)) AS `a2`(`cola`, `colb`)"
+ expected = "SELECT `a2`.`cola` AS `cola`, `a2`.`colb` AS `colb` FROM VALUES (1, 2), (3, 4), (NULL, 6) AS `a2`(`cola`, `colb`)"
self.compare_sql(df, expected)
def test_cdf_no_schema(self):
df = self.spark.createDataFrame([[1, 2], [3, 4], [None, 6]])
- expected = "SELECT `a2`.`_1` AS `_1`, `a2`.`_2` AS `_2` FROM (VALUES (1, 2), (3, 4), (NULL, 6)) AS `a2`(`_1`, `_2`)"
+ expected = "SELECT `a2`.`_1` AS `_1`, `a2`.`_2` AS `_2` FROM VALUES (1, 2), (3, 4), (NULL, 6) AS `a2`(`_1`, `_2`)"
self.compare_sql(df, expected)
def test_cdf_row_mixed_primitives(self):
df = self.spark.createDataFrame([[1, 10.1, "test", False, None]])
- expected = "SELECT `a2`.`_1` AS `_1`, `a2`.`_2` AS `_2`, `a2`.`_3` AS `_3`, `a2`.`_4` AS `_4`, `a2`.`_5` AS `_5` FROM (VALUES (1, 10.1, 'test', FALSE, NULL)) AS `a2`(`_1`, `_2`, `_3`, `_4`, `_5`)"
+ expected = "SELECT `a2`.`_1` AS `_1`, `a2`.`_2` AS `_2`, `a2`.`_3` AS `_3`, `a2`.`_4` AS `_4`, `a2`.`_5` AS `_5` FROM VALUES (1, 10.1, 'test', FALSE, NULL) AS `a2`(`_1`, `_2`, `_3`, `_4`, `_5`)"
self.compare_sql(df, expected)
def test_cdf_dict_rows(self):
df = self.spark.createDataFrame([{"cola": 1, "colb": "test"}, {"cola": 2, "colb": "test2"}])
- expected = "SELECT `a2`.`cola` AS `cola`, `a2`.`colb` AS `colb` FROM (VALUES (1, 'test'), (2, 'test2')) AS `a2`(`cola`, `colb`)"
+ expected = "SELECT `a2`.`cola` AS `cola`, `a2`.`colb` AS `colb` FROM VALUES (1, 'test'), (2, 'test2') AS `a2`(`cola`, `colb`)"
self.compare_sql(df, expected)
def test_cdf_str_schema(self):
df = self.spark.createDataFrame([[1, "test"]], "cola: INT, colb: STRING")
- expected = "SELECT CAST(`a2`.`cola` AS INT) AS `cola`, CAST(`a2`.`colb` AS STRING) AS `colb` FROM (VALUES (1, 'test')) AS `a2`(`cola`, `colb`)"
+ expected = "SELECT CAST(`a2`.`cola` AS INT) AS `cola`, CAST(`a2`.`colb` AS STRING) AS `colb` FROM VALUES (1, 'test') AS `a2`(`cola`, `colb`)"
self.compare_sql(df, expected)
def test_typed_schema_basic(self):
@@ -47,7 +47,7 @@ class TestDataframeSession(DataFrameSQLValidator):
]
)
df = self.spark.createDataFrame([[1, "test"]], schema)
- expected = "SELECT CAST(`a2`.`cola` AS int) AS `cola`, CAST(`a2`.`colb` AS string) AS `colb` FROM (VALUES (1, 'test')) AS `a2`(`cola`, `colb`)"
+ expected = "SELECT CAST(`a2`.`cola` AS INT) AS `cola`, CAST(`a2`.`colb` AS STRING) AS `colb` FROM VALUES (1, 'test') AS `a2`(`cola`, `colb`)"
self.compare_sql(df, expected)
def test_typed_schema_nested(self):
@@ -65,7 +65,8 @@ class TestDataframeSession(DataFrameSQLValidator):
]
)
df = self.spark.createDataFrame([[{"sub_cola": 1, "sub_colb": "test"}]], schema)
- expected = "SELECT CAST(`a2`.`cola` AS struct<sub_cola:int, sub_colb:string>) AS `cola` FROM (VALUES (STRUCT(1 AS `sub_cola`, 'test' AS `sub_colb`))) AS `a2`(`cola`)"
+ expected = "SELECT CAST(`a2`.`cola` AS STRUCT<`sub_cola`: INT, `sub_colb`: STRING>) AS `cola` FROM VALUES (STRUCT(1 AS `sub_cola`, 'test' AS `sub_colb`)) AS `a2`(`cola`)"
+
self.compare_sql(df, expected)
@mock.patch("sqlglot.schema", MappingSchema())
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-19 19:39:15 +0000