Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update regular expressions to make up to date with pymysql. #167

Merged
merged 2 commits into from
Apr 17, 2017
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions aiomysql/cursors.py
Original file line number Diff line number Diff line change
Expand Up @@ -11,21 +11,22 @@
from .utils import PY_35, create_future


# https://github.com/PyMySQL/PyMySQL/blob/master/pymysql/cursors.py#L11-L15
# https://github.com/PyMySQL/PyMySQL/blob/master/pymysql/cursors.py#L11-L18

#: Regular expression for :meth:`Cursor.executemany`.
#: executemany only suports simple bulk insert.
#: You can use it to load large dataset.
RE_INSERT_VALUES = re.compile(
r"""(INSERT\s.+\sVALUES\s+)(\(\s*%s\s*(?:,\s*%s\s*)*\))""" +
"""(\s*(?:ON DUPLICATE.*)?)\Z""",
r"\s*((?:INSERT|REPLACE)\s.+\sVALUES?\s+)" +
r"(\(\s*(?:%s|%\(.+\)s)\s*(?:,\s*(?:%s|%\(.+\)s)\s*)*\))" +
r"(\s*(?:ON DUPLICATE.*)?);?\s*\Z",
re.IGNORECASE | re.DOTALL)


class Cursor:
"""Cursor is used to interact with the database."""

#: Max stetement size which :meth:`executemany` generates.
#: Max statement size which :meth:`executemany` generates.
#:
#: Max size of allowed statement is max_allowed_packet -
# packet_header_size.
Expand Down Expand Up @@ -260,8 +261,8 @@ def executemany(self, query, args):
stmt = "INSERT INTO employees (name, phone) VALUES ('%s','%s')"
yield from cursor.executemany(stmt, data)

INSERT statements are optimized by batching the data, that is
using the MySQL multiple rows syntax.
INSERT or REPLACE statements are optimized by batching the data,
that is using the MySQL multiple rows syntax.

:param query: `str`, sql statement
:param args: ``tuple`` or ``list`` of arguments for sql query
Expand Down
89 changes: 89 additions & 0 deletions tests/test_bulk_inserts.py
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,20 @@ def f(data):
return f


@pytest.fixture
def assert_dict_records(connection):
@asyncio.coroutine
def f(data):
cursor = yield from connection.cursor(DictCursor)
yield from cursor.execute(
"SELECT id, name, age, height FROM bulkinsert")
result = yield from cursor.fetchall()
yield from cursor.execute('COMMIT')
assert sorted(data, key=lambda k: k['id']) == \
sorted(result, key=lambda k: k['id'])
return f


@pytest.mark.run_loop
def test_bulk_insert(cursor, table, assert_records):
data = [(0, "bob", 21, 123), (1, "jim", 56, 45), (2, "fred", 100, 180)]
Expand Down Expand Up @@ -101,3 +115,78 @@ def test_insert_on_duplicate_key_update(cursor, table, assert_records):
age = values(age)""")
yield from cursor.execute('COMMIT')
yield from assert_records(data)


@pytest.mark.run_loop
def test_bulk_insert_with_params_as_dict(cursor, table, assert_dict_records):
data = [
{
'id': 0,
'name': "bob",
'age': 21,
'height': 123
},
{
'id': 1,
'name': "jim",
'age': 56,
'height': 45
},
{
'id': 2,
'name': "fred",
'age': 100,
'height': 180
},
]
yield from cursor.executemany(
"INSERT INTO bulkinsert (id, name, age, height) "
"VALUES (%(id)s,%(name)s,%(age)s,%(height)s)", data)
expected = bytearray(b"INSERT INTO bulkinsert (id, name, age, height) "
b"VALUES (0,'bob',21,123),(1,'jim',56,45),"
b"(2,'fred',100,180)")
assert cursor._last_executed == expected
yield from cursor.execute('commit')
yield from assert_dict_records(data)


@pytest.mark.run_loop
def test_bulk_insert_with_precedence_spaces(cursor, table, assert_records):
data = [(0, "bob", 21, 123), (1, "jim", 56, 45)]
yield from cursor.executemany("""
INSERT INTO bulkinsert (id, name, age, height)
VALUES (%s,%s,%s,%s)
""", data)
expected = bytearray(b"INSERT INTO bulkinsert (id, name, age, height)"
b"\n VALUES (0,\'bob\',21,123),"
b"(1,\'jim\',56,45)\n ")
assert cursor._last_executed == expected
yield from cursor.execute('commit')
yield from assert_records(data)


@pytest.mark.run_loop
def test_bulk_replace(cursor, table, assert_records):
data = [(0, "bob", 21, 123), (0, "jim", 56, 45)]
sql = ("REPLACE INTO bulkinsert (id, name, age, height) " +
"VALUES (%s,%s,%s,%s)")
yield from cursor.executemany(sql, data)
assert cursor._last_executed.strip() == bytearray(
b"REPLACE INTO bulkinsert (id, name, age, height) " +
b"VALUES (0,'bob',21,123),(0,'jim',56,45)"
)
yield from cursor.execute('COMMIT')
yield from assert_records([(0, "jim", 56, 45)])


@pytest.mark.run_loop
def test_bulk_insert_with_semicolon_at_the_end(cursor, table, assert_records):
data = [(0, "bob", 21, 123), (1, "jim", 56, 45)]
yield from cursor.executemany(
"INSERT INTO bulkinsert (id, name, age, height) "
"VALUES (%s,%s,%s,%s);", data)
expected = bytearray(b"INSERT INTO bulkinsert (id, name, age, height) "
b"VALUES (0,'bob',21,123),(1,'jim',56,45)")
assert cursor._last_executed == expected
yield from cursor.execute('commit')
yield from assert_records(data)