Log Message:
py-alembic: updated to 1.4.2

1.4.2:
bug

[bug] [tests]

Fixed an issue that prevented the test suite from running with the recently \ 
released py.test 5.4.0.

[bug] [autogenerate] [mysql]

Fixed more false-positive failures produced by the new “compare type” logic \ 
first added in 605, particularly impacting MySQL string types regarding flags \ 
such as “charset” and “collation”.

[bug] [op directives] [oracle]

Fixed issue in Oracle backend where a table RENAME with a schema-qualified name \ 
would include the schema in the “to” portion, which is rejected by Oracle.

usecase

[usecase] [autogenerate]

Adjusted autogen comparison to accommodate for backends that support computed \ 
column reflection, dependent on SQLAlchemy version 1.3.16 or higher. This emits \ 
a warning if the SQL expression inside of a Computed value changes between the \ 
metadata and the database, as these expressions can’t be changed without \ 
dropping and recreating the column.

1.4.1
bug

[bug] [autogenerate]

Fixed regression caused by the new “type comparison” logic introduced in 1.4 \ 
as part of 605 where comparisons of MySQL “unsigned integer” datatypes would \ 
produce false positives, as the regular expression logic was not correctly \ 
parsing the “unsigned” token when MySQL’s default display width would be \ 
returned by the database. Pull request courtesy Paul Becotte.

[bug] [environment]

Error message for “path doesn’t exist” when loading up script environment \ 
now displays the absolute path. Pull request courtesy Rowan Hart.

[bug] [autogenerate]

Fixed regression in 1.4.0 due to 647 where unique constraint comparison with \ 
mixed case constraint names while not using a naming convention would produce \ 
false positives during autogenerate.

[bug] [environment]

The check for matched rowcount when the alembic_version table is updated or \ 
deleted from is now conditional based on whether or not the dialect supports the \ 
concept of “rowcount” for UPDATE or DELETE rows matched. Some third party \ 
dialects do not support this concept. Pull request courtesy Ke Zhu.

[bug] [operations]

Fixed long-standing bug where an inline column CHECK constraint would not be \ 
rendered within an “ADD COLUMN” operation. The DDL compiler is now consulted \ 
for inline constraints within the Operations.add_column() method as is done for \ 
regular CREATE TABLE operations.