From: Mike Bayer Date: Fri, 11 Sep 2020 14:50:57 +0000 (-0400) Subject: - 1.4.3 X-Git-Tag: rel_1_4_3 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=b8f60b6c3fe9f250d8439048aece62452eaf08b8;p=thirdparty%2Fsqlalchemy%2Falembic.git - 1.4.3 --- diff --git a/docs/build/changelog.rst b/docs/build/changelog.rst index 1950c5a5..087abbe2 100644 --- a/docs/build/changelog.rst +++ b/docs/build/changelog.rst @@ -5,7 +5,64 @@ Changelog .. changelog:: :version: 1.4.3 - :include_notes_from: unreleased + :released: September 11, 2020 + + .. change:: + :tags: bug, sqlite, batch + :tickets: 711 + + Added support to drop named CHECK constraints that are specified as part of + a column, rather than table wide. Previously, only constraints associated + with the table were considered. + + .. change:: + :tags: bug, ops, mysql + :tickets: 736 + + Fixed issue where the MySQL dialect would not correctly render the server + default of a column in an alter operation, if the operation were + programmatically generated from an autogenerate pass as it would not + accommodate for the full structure of the DefaultClause construct. + + .. change:: + :tags: bug, sqlite, batch + :tickets: 697 + + Fixed issue where the CAST applied to a JSON column when copying a SQLite + table during batch mode would cause the data to be lost, as SQLite's CAST + with JSON appears to convert the data to the value "0". The CAST is now + skipped in a dialect-specific manner, including for JSON columns on SQLite. + Pull request courtesy Sebastián Ramírez. + + .. change:: + :tags: bug, commands + :tickets: 694 + + The ``alembic current`` command no longer creates an ``alembic_version`` + table in the database if one does not exist already, returning no version + as the current version. This allows checking for migrations in parallel + without introducing race conditions. Pull request courtesy Nikolay + Edigaryev. + + + .. change:: + :tags: bug, batch + + Fixed issue where columns in a foreign-key referenced table would be + replaced with null-type columns during a batch operation; while this did + not generally have any side effects, it could theoretically impact a batch + operation that also targets that table directly and also would interfere + with future changes to the ``.append_column()`` method to disallow implicit + replacement of columns. + + .. change:: + :tags: bug, mssql + :tickets: 716 + + Fixed issue where the ``mssql_drop_foreign_key=True`` flag on + ``op.drop_column`` would lead to incorrect syntax error due to a typo in the + SQL emitted, same typo was present in the test as well so it was not + detected. Pull request courtesy Oleg Shigorin. .. changelog:: :version: 1.4.2 diff --git a/docs/build/conf.py b/docs/build/conf.py index f633f613..d7f1a77e 100644 --- a/docs/build/conf.py +++ b/docs/build/conf.py @@ -85,8 +85,8 @@ copyright = u"2010-2020, Mike Bayer" # noqa # The short X.Y version. version = alembic.__version__ # The full version, including alpha/beta/rc tags. -release = "1.4.2" -release_date = "March 19, 2020" +release = "1.4.3" +release_date = "September 11, 2020" # The language for content autogenerated by Sphinx. Refer to documentation diff --git a/docs/build/unreleased/694.rst b/docs/build/unreleased/694.rst deleted file mode 100644 index 0d62b28f..00000000 --- a/docs/build/unreleased/694.rst +++ /dev/null @@ -1,10 +0,0 @@ -.. change:: - :tags: bug, commands - :tickets: 694 - - The ``alembic current`` command no longer creates an ``alembic_version`` - table in the database if one does not exist already, returning no version - as the current version. This allows checking for migrations in parallel - without introducing race conditions. Pull request courtesy Nikolay - Edigaryev. - diff --git a/docs/build/unreleased/697.rst b/docs/build/unreleased/697.rst deleted file mode 100644 index 0eff4a0e..00000000 --- a/docs/build/unreleased/697.rst +++ /dev/null @@ -1,9 +0,0 @@ -.. change:: - :tags: bug, sqlite, batch - :tickets: 697 - - Fixed issue where the CAST applied to a JSON column when copying a SQLite - table during batch mode would cause the data to be lost, as SQLite's CAST - with JSON appears to convert the data to the value "0". The CAST is now - skipped in a dialect-specific manner, including for JSON columns on SQLite. - Pull request courtesy Sebastián Ramírez. diff --git a/docs/build/unreleased/711.rst b/docs/build/unreleased/711.rst deleted file mode 100644 index 4117a3a9..00000000 --- a/docs/build/unreleased/711.rst +++ /dev/null @@ -1,7 +0,0 @@ -.. change:: - :tags: bug, sqlite, batch - :tickets: 711 - - Added support to drop named CHECK constraints that are specified as part of - a column, rather than table wide. Previously, only constraints associated - with the table were considered. diff --git a/docs/build/unreleased/716.rst b/docs/build/unreleased/716.rst deleted file mode 100644 index dd490edf..00000000 --- a/docs/build/unreleased/716.rst +++ /dev/null @@ -1,8 +0,0 @@ -.. change:: - :tags: bug, mssql - :tickets: 716 - - Fixed issue where the ``mssql_drop_foreign_key=True`` flag on - ``op.drop_column`` would lead to incorrect syntax error due to a typo in the - SQL emitted, same typo was present in the test as well so it was not - detected. Pull request courtesy Oleg Shigorin. diff --git a/docs/build/unreleased/736.rst b/docs/build/unreleased/736.rst deleted file mode 100644 index ce166c79..00000000 --- a/docs/build/unreleased/736.rst +++ /dev/null @@ -1,8 +0,0 @@ -.. change:: - :tags: bug, ops, mysql - :tickets: 736 - - Fixed issue where the MySQL dialect would not correctly render the server - default of a column in an alter operation, if the operation were - programmatically generated from an autogenerate pass as it would not - accommodate for the full structure of the DefaultClause construct. diff --git a/docs/build/unreleased/add_column.rst b/docs/build/unreleased/add_column.rst deleted file mode 100644 index 1e3c8a69..00000000 --- a/docs/build/unreleased/add_column.rst +++ /dev/null @@ -1,9 +0,0 @@ -.. change:: - :tags: bug, batch - - Fixed issue where columns in a foreign-key referenced table would be - replaced with null-type columns during a batch operation; while this did - not generally have any side effects, it could theoretically impact a batch - operation that also targets that table directly and also would interfere - with future changes to the ``.append_column()`` method to disallow implicit - replacement of columns. \ No newline at end of file