Issue 180: when deserializing objects, the context class loader is used instead of the default class loader if the system property "h2.useThreadContextClassLoader" is set. Thanks a lot to Noah Fontes for the patch!

Issue 326: improved support for case sensitive (mixed case) identifiers without quotes when using DATABASE_TO_UPPER=FALSE.

The optimization for "group by" was not working correctly if the group by column was aliased in the select list.

--no commit message

Issue 351: MySQL mode: can not create a table with the column "KEY", and can not open databases where such a table already exists. (KEY is _not_ a keyword.)

Issue 351: MySQL mode: can not create a table with the column "KEY", and can not open databases where such a table already exists. (KEY is now a keyword.)

TCP server: when using the trace option ("-trace"), the trace output contained unnecessary stack traces when stopping the server.

Issue 354: when using the multi-threaded kernel option, and multiple threads concurrently prepared SQL statements that use the same view or the same index of a view, then in some cases an infinite loop could occur.

Issue 354: when using the multi-threaded kernel option, and multiple threads concurrently prepared SQL statements that use the same view or the same index of a view, then in some cases an infinite loop could occur.

Issue 356: for Blob objects, InputStream.skip() returned 0, causing EOFException in Blob.getBytes(.., ..).

Updateable result sets: if the value is not set when inserting a new row, the default value is now used (the same behavior as MySQL, PostgreSQL, and Apache Derby) instead of NULL.

Conditions of the form IN(SELECT ...) where slow and increased the database size if the subquery result size was larger then the configured MAX_MEMORY_ROWS.