diff options
Diffstat (limited to 'lib/sqlalchemy')
| -rw-r--r-- | lib/sqlalchemy/dialects/mysql/base.py | 61 | ||||
| -rw-r--r-- | lib/sqlalchemy/dialects/mysql/mysqldb.py | 10 | ||||
| -rw-r--r-- | lib/sqlalchemy/testing/provision.py | 12 | ||||
| -rw-r--r-- | lib/sqlalchemy/testing/schema.py | 3 | ||||
| -rw-r--r-- | lib/sqlalchemy/testing/suite/test_reflection.py | 4 |
5 files changed, 40 insertions, 50 deletions
diff --git a/lib/sqlalchemy/dialects/mysql/base.py b/lib/sqlalchemy/dialects/mysql/base.py index 62753e1a5..3aede4a05 100644 --- a/lib/sqlalchemy/dialects/mysql/base.py +++ b/lib/sqlalchemy/dialects/mysql/base.py @@ -54,13 +54,13 @@ including ``ENGINE``, ``CHARSET``, ``MAX_ROWS``, ``ROW_FORMAT``, ``INSERT_METHOD``, and many more. To accommodate the rendering of these arguments, specify the form ``mysql_argument_name="value"``. For example, to specify a table with -``ENGINE`` of ``InnoDB``, ``CHARSET`` of ``utf8``, and ``KEY_BLOCK_SIZE`` +``ENGINE`` of ``InnoDB``, ``CHARSET`` of ``utf8mb4``, and ``KEY_BLOCK_SIZE`` of ``1024``:: Table('mytable', metadata, Column('data', String(32)), mysql_engine='InnoDB', - mysql_charset='utf8', + mysql_charset='utf8mb4', mysql_key_block_size="1024" ) @@ -213,7 +213,7 @@ a connection. This is typically delivered using the ``charset`` parameter in the URL, such as:: e = create_engine( - "mysql+pymysql://scott:tiger@localhost/test?charset=utf8") + "mysql+pymysql://scott:tiger@localhost/test?charset=utf8mb4") This charset is the **client character set** for the connection. Some MySQL DBAPIs will default this to a value such as ``latin1``, and some @@ -223,8 +223,10 @@ for specific behavior. The encoding used for Unicode has traditionally been ``'utf8'``. However, for MySQL versions 5.5.3 on forward, a new MySQL-specific encoding -``'utf8mb4'`` has been introduced. The rationale for this new encoding -is due to the fact that MySQL's utf-8 encoding only supports +``'utf8mb4'`` has been introduced, and as of MySQL 8.0 a warning is emitted +by the server if plain ``utf8`` is specified within any server-side +directives, replaced with ``utf8mb3``. The rationale for this new encoding +is due to the fact that MySQL's legacy utf-8 encoding only supports codepoints up to three bytes instead of four. Therefore, when communicating with a MySQL database that includes codepoints more than three bytes in size, @@ -234,12 +236,11 @@ as the client DBAPI, as in:: e = create_engine( "mysql+pymysql://scott:tiger@localhost/test?charset=utf8mb4") -At the moment, up-to-date versions of MySQLdb and PyMySQL support the -``utf8mb4`` charset. Other DBAPIs such as MySQL-Connector and OurSQL -may **not** support it as of yet. +All modern DBAPIs should support the ``utf8mb4`` charset. -In order to use ``utf8mb4`` encoding, changes to -the MySQL schema and/or server configuration may be required. +In order to use ``utf8mb4`` encoding for a schema that was created with legacy +``utf8``, changes to the MySQL schema and/or server configuration may be +required. .. seealso:: @@ -252,38 +253,16 @@ Unicode Encoding / Decoding All modern MySQL DBAPIs all offer the service of handling the encoding and decoding of unicode data between the Python application space and the database. -As this was not always the case, SQLAlchemy also includes a comprehensive system -of performing the encode/decode task as well. As only one of these systems -should be in use at at time, SQLAlchemy has long included functionality -to automatically detect upon first connection whether or not the DBAPI is -automatically handling unicode. - -Whether or not the MySQL DBAPI will handle encoding can usually be configured -using a DBAPI flag ``use_unicode``, which is known to be supported at least -by MySQLdb, PyMySQL, and MySQL-Connector. Setting this value to ``0`` -in the "connect args" or query string will have the effect of disabling the -DBAPI's handling of unicode, such that it instead will return data of the -``str`` type or ``bytes`` type, with data in the configured charset:: - - # connect while disabling the DBAPI's unicode encoding/decoding +As this was not always the case, SQLAlchemy also includes a comprehensive +system of performing the encode/decode task as well, which for MySQL dialects +can be enabled by passing the flag ``use_unicode=0`` onto the query string, as +in:: + e = create_engine( - "mysql+mysqldb://scott:tiger@localhost/test?charset=utf8&use_unicode=0") - -Current recommendations for modern DBAPIs are as follows: - -* It is generally always safe to leave the ``use_unicode`` flag set at - its default; that is, don't use it at all. -* Under Python 3, the ``use_unicode=0`` flag should **never be used**. - SQLAlchemy under Python 3 generally assumes the DBAPI receives and returns - string values as Python 3 strings, which are inherently unicode objects. -* Under Python 2 with MySQLdb, the ``use_unicode=0`` flag will **offer - superior performance**, as MySQLdb's unicode converters under Python 2 only - have been observed to have unusually slow performance compared to SQLAlchemy's - fast C-based encoders/decoders. - -In short: don't specify ``use_unicode`` *at all*, with the possible -exception of ``use_unicode=0`` on MySQLdb with Python 2 **only** for a -potential performance gain. + "mysql+mysqldb://scott:tiger@localhost/test?charset=utf8mb4&use_unicode=0") + +Current recommendations are to **not** use this flag. All modern MySQL DBAPIs +handle unicode natively as is required on Python 3 in any case. Ansi Quoting Style ------------------ diff --git a/lib/sqlalchemy/dialects/mysql/mysqldb.py b/lib/sqlalchemy/dialects/mysql/mysqldb.py index 3da64a491..535c8ec52 100644 --- a/lib/sqlalchemy/dialects/mysql/mysqldb.py +++ b/lib/sqlalchemy/dialects/mysql/mysqldb.py @@ -109,21 +109,21 @@ class MySQLDialect_mysqldb(MySQLDialect): def _check_unicode_returns(self, connection): # work around issue fixed in # https://github.com/farcepest/MySQLdb1/commit/cd44524fef63bd3fcb71947392326e9742d520e8 - # specific issue w/ the utf8_bin collation and unicode returns + # specific issue w/ the utf8mb4_bin collation and unicode returns - has_utf8_bin = self.server_version_info > (5, ) and \ + has_utf8mb4_bin = self.server_version_info > (5, ) and \ connection.scalar( - "show collation where %s = 'utf8' and %s = 'utf8_bin'" + "show collation where %s = 'utf8mb4' and %s = 'utf8mb4_bin'" % ( self.identifier_preparer.quote("Charset"), self.identifier_preparer.quote("Collation") )) - if has_utf8_bin: + if has_utf8mb4_bin: additional_tests = [ sql.collate(sql.cast( sql.literal_column( "'test collated returns'"), - TEXT(charset='utf8')), "utf8_bin") + TEXT(charset='utf8mb4')), "utf8mb4_bin") ] else: additional_tests = [] diff --git a/lib/sqlalchemy/testing/provision.py b/lib/sqlalchemy/testing/provision.py index 687f84b18..8abfa3301 100644 --- a/lib/sqlalchemy/testing/provision.py +++ b/lib/sqlalchemy/testing/provision.py @@ -194,9 +194,15 @@ def _mysql_create_db(cfg, eng, ident): _mysql_drop_db(cfg, conn, ident) except Exception: pass - conn.execute("CREATE DATABASE %s" % ident) - conn.execute("CREATE DATABASE %s_test_schema" % ident) - conn.execute("CREATE DATABASE %s_test_schema_2" % ident) + + # using utf8mb4 we are getting collation errors on UNIONS: + # test/orm/inheritance/test_polymorphic_rel.py" + # 1271, u"Illegal mix of collations for operation 'UNION'" + conn.execute("CREATE DATABASE %s CHARACTER SET utf8mb3" % ident) + conn.execute( + "CREATE DATABASE %s_test_schema CHARACTER SET utf8mb3" % ident) + conn.execute( + "CREATE DATABASE %s_test_schema_2 CHARACTER SET utf8mb3" % ident) @_configure_follower.for_db("mysql") diff --git a/lib/sqlalchemy/testing/schema.py b/lib/sqlalchemy/testing/schema.py index 3ca91b901..401c8cbb7 100644 --- a/lib/sqlalchemy/testing/schema.py +++ b/lib/sqlalchemy/testing/schema.py @@ -22,7 +22,8 @@ def Table(*args, **kw): kw.update(table_options) if exclusions.against(config._current, 'mysql'): - if 'mysql_engine' not in kw and 'mysql_type' not in kw: + if 'mysql_engine' not in kw and 'mysql_type' not in kw and \ + "autoload_with" not in kw: if 'test_needs_fk' in test_opts or 'test_needs_acid' in test_opts: kw['mysql_engine'] = 'InnoDB' else: diff --git a/lib/sqlalchemy/testing/suite/test_reflection.py b/lib/sqlalchemy/testing/suite/test_reflection.py index 70a2f3f4f..00a5aac01 100644 --- a/lib/sqlalchemy/testing/suite/test_reflection.py +++ b/lib/sqlalchemy/testing/suite/test_reflection.py @@ -153,14 +153,18 @@ class ComponentReflectionTest(fixtures.TablesTest): cls.define_index(metadata, users) if not schema: + # test_needs_fk is at the moment to force MySQL InnoDB noncol_idx_test_nopk = Table( 'noncol_idx_test_nopk', metadata, Column('q', sa.String(5)), + test_needs_fk=True, ) + noncol_idx_test_pk = Table( 'noncol_idx_test_pk', metadata, Column('id', sa.Integer, primary_key=True), Column('q', sa.String(5)), + test_needs_fk=True, ) Index('noncol_idx_nopk', noncol_idx_test_nopk.c.q.desc()) Index('noncol_idx_pk', noncol_idx_test_pk.c.q.desc()) |