Change Log

Next Version (unreleased)

• Improve error message for METHOD_NOT_FOUND_1/90087
• CLOB and BLOB objects of removed rows were sometimes kept in the database file.
• Server mode: executing "shutdown" left a thread on the server.
• The condition "in(select...)" did not work correctly in some cases if the subquery had an "order by".
• Issue #184: The Platform-independent zip had Windows line endings in Linux scripts.
• Issue #186: The "script" command did not include sequences of temporary tables.
• Issue #115: to_char fails with pattern FM0D099

Version 1.4.190 Beta (2015-10-11)

• Pull request #183: optimizer hints (so far without special SQL syntax).
• Issue #180: In MVCC mode, executing UPDATE and SELECT ... FOR UPDATE simultaneously silently can drop rows.
• PageStore storage: the cooperative file locking mechanism did not always work as expected (with very slow computers).
• Temporary CLOB and BLOB objects are now removed while the database is open (and not just when closing the database).
• MVStore CLOB and BLOB larger than about 25 MB: An exception could be thrown when using the MVStore storage.
• Add FILE_WRITE function. Patch provided by Nicolas Fortin (Lab-STICC - CNRS UMR 6285 and Ecole Centrale de Nantes)

Version 1.4.189 Beta (2015-09-13)

• Add support for dropping multiple columns in ALTER TABLE DROP COLUMN...
• Fix bug in XA management when doing rollback after prepare. Patch by Stephane Lacoin.
• MVStore CLOB and BLOB: An exception with the message "Block not found" could be thrown when using the MVStore storage, when copying LOB objects (for example due to "alter table" on a table with a LOB object), and then re-opening the database.
• Fix for issue #171: Broken QueryStatisticsData duration data when trace level smaller than TraceSystem.INFO
• Pull request #170: Added SET QUERY_STATISTICS_MAX_ENTRIES
• Pull request #165: Fix compatibility postgresql function string_agg
• Pull request #163: improved performance when not using the default timezone.
• Local temporary tables with many rows did not work correctly due to automatic analyze.
• Server mode: concurrently using the same connection could throw an exception "Connection is broken: unexpected status".
• Performance improvement for metadata queries that join against the COLUMNS metadata table.
• An ArrayIndexOutOfBoundsException was thrown in some cases when opening an old version 1.3 database, or an 1.4 database with both "mv_store=false" and the system property "h2.storeLocalTime" set to false. It mainly showed up with an index on a time, date, or timestamp column. The system property "h2.storeLocalTime" is no longer supported (MVStore databases always store local time, and PageStore now databases never do).

Version 1.4.188 Beta (2015-08-01)

• Server mode: CLOB processing for texts larger than about 1 MB sometimes did not work.
• Server mode: BLOB processing for binaries larger than 2 GB did not work.
• Multi-threaded processing: concurrent deleting the same row could throw the exception "Row not found when trying to delete".
• MVStore transactions: a thread could see a change of a different thread within a different map. Pull request #153.
• H2 Console: improved IBM DB2 compatibility.
• A thread deadlock detector (disabled by default) can help detect and analyze Java level deadlocks. To enable, set the system property "h2.threadDeadlockDetector" to true.
• Performance improvement for metadata queries that join against the COLUMNS metadata table.
• MVStore: power failure could corrupt the store, if writes were re-ordered.
• For compatibility with other databases, support for (double and float) -0.0 has been removed. 0.0 is used instead.
• Fix for #134, Column name with a # character. Patch by bradmesserle.
• In version 1.4.186, "order by" was broken in some cases due to the change "Make the planner use indexes for sorting when doing a GROUP BY". The change was reverted.
• Pull request #146: Improved CompareMode.
• Fix for #144, JdbcResultSet.setFetchDirection() throws "Feature not supported".
• Fix for issue #143, deadlock between two sessions hitting the same sequence on a column.
• Pull request #137: SourceCompiler should not throw a syntax error on javac warning.
• MVStore: out of memory while storing could corrupt the store (theoretically, a rollback would be possible, but this case is not yet implemented).
• The compressed in-memory file systems (memLZF:) could not be used in the MVStore.
• The in-memory file systems (memFS: and memLZF:) did not support files larger than 2 GB due to an integer overflow.
• Pull request #138: Added the simple Oracle function: ORA_HASH (+ tests) #138
• Timestamps in the trace log follow the format (yyyy-MM-dd HH:mm:ss) instead of the old format (MM-dd HH:mm:ss). Patch by Richard Bull.
• Pull request #125: Improved Oracle compatibility with "truncate" with timestamps and dates.
• Pull request #127: Linked tables now support geometry columns.
• ABS(CAST(0.0 AS DOUBLE)) returned -0.0 instead of 0.0.
• BNF auto-completion failed with unquoted identifiers.
• Oracle compatibility: empty strings were not converted to NULL when using prepared statements.
• PostgreSQL compatibility: new syntax "create index ... using ...".
• There was a bug in DataType.convertToValue when reading a ResultSet from a ResultSet.
• Pull request #116: Improved concurrency in the trace system.
• Issue 609: the spatial index did not support NULL.
• Granting a schema is now supported.
• Linked tables did not work when a function-based index is present (Oracle).
• Creating a user with a null password, salt, or hash threw a NullPointerException.
• Foreign key: don't add a single column index if column is leading key of existing index.
• Pull request #4: Creating and removing temporary tables was getting slower and slower over time, because an internal object id was allocated but never de-allocated.
• Issue 609: the spatial index did not support NULL with update and delete operations.
• Pull request #2: Add external metadata type support (table type "external")
• MS SQL Server: the CONVERT method did not work in views and derived tables.
• Java 8 compatibility for "regexp_replace".
• When in cluster mode, and one of the nodes goes down, we need to log the problem with priority "error", not "debug"

Version 1.4.187 Beta (2015-04-10)

• MVStore: concurrent changes to the same row could result in the exception "The transaction log might be corrupt for key ...". This could only be reproduced with 3 or more threads.
• Results with CLOB or BLOB data are no longer reused.
• References to BLOB and CLOB objects now have a timeout. The configuration setting is LOB_TIMEOUT (default 5 minutes). This should avoid growing the database file if there are many queries that return BLOB or CLOB objects, and the database is not closed for a longer time.
• MVStore: when committing a session that removed LOB values, changes were flushed unnecessarily.
• Issue 610: possible integer overflow in WriteBuffer.grow().
• Issue 609: the spatial index did not support NULL (ClassCastException).
• MVStore: in some cases, CLOB/BLOB data blocks were removed incorrectly when opening a database.
• MVStore: updates that affected many rows were were slow in some cases if there was a secondary index.
• Using "runscript" with autocommit disabled could result in a lock timeout on the internal table "SYS".
• Issue 603: there was a memory leak when using H2 in a web application. Apache Tomcat logged an error message: "The web application ... created a ThreadLocal with key of type [org.h2.util.DateTimeUtils$1]".
• When using the MVStore, running a SQL script generate by the Recover tool from a PageStore file failed with a strange error message (NullPointerException), now a clear error message is shown.
• Issue 605: with version 1.4.186, opening a database could result in an endless loop in LobStorageMap.init.
• Queries that use the same table alias multiple times now work. Before, the select expression list was expanded incorrectly. Example: "select * from a as x, b as x".
• The MySQL compatibility feature "insert ... on duplicate key update" did not work with a non-default schema.
• Issue 599: the condition "in(x, y)" could not be used in the select list when using "group by".
• The LIRS cache could grow larger than the allocated memory.
• A new file system implementation that re-opens the file if it was closed due to the application calling Thread.interrupt(). File name prefix "retry:". Please note it is strongly recommended to avoid calling Thread.interrupt; this is a problem for various libraries, including Apache Lucene.
• MVStore: use RandomAccessFile file system if the file name starts with "file:".
• Allow DATEADD to take a long value for count when manipulating milliseconds.
• When using MV_STORE=TRUE and the SET CACHE_SIZE setting, the cache size was incorrectly set, so that it was effectively 1024 times smaller than it should be.
• Concurrent CREATE TABLE... IF NOT EXISTS in the presence of MULTI_THREAD=TRUE could throw an exception.
• Fix bug in MVStore when creating lots of temporary tables, where we could run out of transaction IDs.
• Add support for PostgreSQL STRING_AGG function. Patch by Fred Aquiles.
• Fix bug in "jdbc:h2:nioMemFS" isRoot() function. Also, the page size was increased to 64 KB.

Version 1.4.186 Beta (2015-03-02)

• The Servlet API 3.0.1 is now used, instead of 2.4.
• MVStore: old chunks no longer removed in append-only mode.
• MVStore: the cache for page references could grow far too big, resulting in out of memory in some cases.
• MVStore: orphaned lob objects were not correctly removed in some cases, making the database grow unnecessarily.
• MVStore: the maximum cache size was artificially limited to 2 GB (due to an integer overflow).
• MVStore / TransactionStore: concurrent updates could result in a "Too many open transactions" exception.
• StringUtils.toUpperEnglish now has a small cache. This should speed up reading from a ResultSet when using the column name.
• MVStore: up to 65535 open transactions are now supported. Previously, the limit was at most 65535 transactions between the oldest open and the newest open transaction (which was quite a strange limit).
• The default limit for in-place LOB objects was changed from 128 to 256 bytes. This is because each read creates a reference to a LOB, and maintaining the references is a big overhead. With the higher limit, less references are needed.
• Tables without columns didn't work. (The use case for such tables is testing.)
• The LIRS cache now resizes the table automatically in all cases and no longer needs the averageMemory configuration.
• Creating a linked table from an MVStore database to a non-MVStore database created a second (non-MVStore) database file.
• In version 1.4.184, a bug was introduced that broke queries that have both joins and wildcards, for example: select * from dual join(select x from dual) on 1=1
• Issue 598: parser fails on timestamp "24:00:00.1234" - prevent the creation of out-of-range time values.
• Allow declaring triggers as source code (like functions). Patch by Sylvain Cuaz.
• Make the planner use indexes for sorting when doing a GROUP BY where all of the GROUP BY columns are not mentioned in the select. Patch by Frederico (zepfred).
• PostgreSQL compatibility: generate_series (as an alias for system_range). Patch by litailang.
• Fix missing "column" type in right-hand parameter in ConditionIn. Patch by Arnaud Thimel.

Version 1.4.185 Beta (2015-01-16)

• In version 1.4.184, "group by" ignored the table name, and could pick a select column by mistake. Example: select 0 as x from system_range(1, 2) d group by d.x;
• New connection setting "REUSE_SPACE" (default: true). If disabled, all changes are appended to the database file, and existing content is never overwritten. This allows to rollback to a previous state of the database by truncating the database file.
• Issue 587: MVStore: concurrent compaction and store operations could result in an IllegalStateException.
• Issue 594: Profiler.copyInThread does not work properly.
• Script tool: Now, SCRIPT ... TO is always used (for higher speed and lower disk space usage).
• Script tool: Fix parsing of BLOCKSIZE parameter, original patch by Ken Jorissen.
• Fix bug in PageStore#commit method - when the ignoreBigLog flag was set, the logic that cleared the flag could never be reached, resulting in performance degradation. Reported by Alexander Nesterov.
• Issue 552: Implement BIT_AND and BIT_OR aggregate functions.

Version 1.4.184 Beta (2014-12-19)

• In version 1.3.183, indexes were not used if the table contains columns with a default value generated by a sequence. This includes tables with identity and auto-increment columns. This bug was introduced by supporting "rownum" in views and derived tables.
• MVStore: imported BLOB and CLOB data sometimes disappeared. This was caused by a bug in the ObjectDataType comparison.
• Reading from a StreamStore now throws an IOException if the underlying data doesn't exist.
• MVStore: if there is an exception while saving, the store is now in all cases immediately closed.
• MVStore: the dump tool could go into an endless loop for some files.
• MVStore: recovery for a database with many CLOB or BLOB entries is now much faster.
• Group by with a quoted select column name alias didn't work. Example: select 1 "a" from dual group by "a"
• Auto-server mode: the host name is now stored in the .lock.db file.

Version 1.4.183 Beta (2014-12-13)

• MVStore: the default auto-commit buffer size is now about twice as big. This should reduce the database file size after inserting a lot of data.
• The built-in functions "power" and "radians" now always return a double.
• Using "row_number" or "rownum" in views or derived tables had unexpected results if the outer query contained constraints for the given view. Example: select b.nr, b.id from (select row_number() over() as nr, a.id as id from (select id from test order by name) as a) as b where b.id = 1
• MVStore: the Recover tool can now deal with more types of corruption in the file.
• MVStore: the TransactionStore now first needs to be initialized before it can be used.
• Views and derived tables with equality and range conditions on the same columns did not work properly. example: select x from (select x from (select 1 as x) where x > 0 and x < 2) where x = 1
• The database URL setting PAGE_SIZE setting is now also used for the MVStore.
• MVStore: the default page split size for persistent stores is now 4096 (it was 16 KB so far). This should reduce the database file size for most situations (in some cases, less than half the size of the previous version).
• With query literals disabled, auto-analyze of a table with CLOB or BLOB did not work.
• MVStore: use a mark and sweep GC algorithm instead of reference counting, to ensure used chunks are never overwrite, even if the reference counting algorithm does not work properly.
• In the multi-threaded mode, updating the column selectivity ("analyze") in the background sometimes did not work.
• In the multi-threaded mode, database metadata operations did sometimes not work if the schema was changed at the same time (for example, if tables were dropped).
• Some CLOB and BLOB values could no longer be read when the original row was removed (even when using the MVCC mode).
• The MVStoreTool could throw an IllegalArgumentException.
• Improved performance for some date / time / timestamp conversion operations. Thanks to Sergey Evdokimov for reporting the problem.
• H2 Console: the built-in web server did not work properly if an unknown file was requested.
• MVStore: the jar file is renamed to "h2-mvstore-*.jar" and is deployed to Maven separately.
• MVStore: support for concurrent reads and writes is now enabled by default.
• Server mode: the transfer buffer size has been changed from 16 KB to 64 KB, after it was found that this improves performance on Linux quite a lot.
• H2 Console and server mode: SSL is now disabled and TLS is used to protect against the Poodle SSLv3 vulnerability. The system property to disable secure anonymous connections is now "h2.enableAnonymousTLS". The default certificate is still self-signed, so you need to manually install another one if you want to avoid man in the middle attacks.
• MVStore: the R-tree did not correctly measure the memory usage.
• MVStore: compacting a store with an R-tree did not always work.
• Issue 581: When running in LOCK_MODE=0, JdbcDatabaseMetaData#supportsTransactionIsolationLevel(TRANSACTION_READ_UNCOMMITTED) should return false
• Fix bug which could generate deadlocks when multiple connections accessed the same table.
• Some places in the code were not respecting the value set in the "SET MAX_MEMORY_ROWS x" command
• Fix bug which could generate a NegativeArraySizeException when performing large (>40M) row union operations
• Fix "USE schema" command for MySQL compatibility, patch by mfulton
• Parse and ignore the ROW_FORMAT=DYNAMIC MySQL syntax, patch by mfulton

Version 1.4.182 Beta (2014-10-17)

• MVStore: improved error messages and logging; improved behavior if there is an error when serializing objects.
• OSGi: the MVStore packages are now exported.
• With the MVStore option, when using multiple threads that concurrently create indexes or tables, it was relatively easy to get a lock timeout on the "SYS" table.
• When using the multi-threaded option, the exception "Unexpected code path" could be thrown, specially if the option "analyze_auto" was set to a low value.
• In the server mode, when reading from a CLOB or BLOB, if the connection was closed, a NullPointerException could be thrown instead of an exception saying the connection is closed.
• DatabaseMetaData.getProcedures and getProcedureColumns could throw an exception if a user defined class is not available.
• Issue 584: the error message for a wrong sequence definition was wrong.
• CSV tool: the rowSeparator option is no longer supported, as the same can be achieved with the lineSeparator.
• Descending indexes on MVStore tables did not work properly.
• Issue 579: Conditions on the "_rowid_" pseudo-column didn't use an index when using the MVStore.
• Fixed documentation that "offset" and "fetch" are also keywords since version 1.4.x.
• The Long.MIN_VALUE could not be parsed for auto-increment (identity) columns.
• Issue 573: Add implementation for Methods "isWrapperFor()" and "unwrap()" in other JDBC classes.
• Issue 572: MySQL compatibility for "order by" in update statements.
• The change in JDBC escape processing in version 1.4.181 affects both the parser (which is running on the server) and the JDBC API (which is running on the client). If you (or a tool you use) use the syntax "{t 'time}", or "{ts 'timestamp'}", or "{d 'data'}", then both the client and the server need to be upgraded to version 1.4.181 or later.

Version 1.4.181 Beta (2014-08-06)

• Improved MySQL compatibility by supporting "use schema". Thanks a lot to Karl Pietrzak for the patch!
• Writing to the trace file is now faster, specially with the debug level.
• The database option "defrag_always=true" did not work with the MVStore.
• The JDBC escape syntax {ts 'value'} did not interpret the value as a timestamp. The same for {d 'value'} (for date) and {t 'value'} (for time). Thanks to Lukas Eder for reporting the issue. The following problem was detected after version 1.4.181 was released: The change in JDBC escape processing affects both the parser (which is running on the server) and the JDBC API (which is running on the client). If you (or a tool you use) use the syntax {t 'time'}, or {ts 'timestamp'}, or {d 'date'}, then both the client and the server need to be upgraded to version 1.4.181 or later.
• File system abstraction: support replacing existing files using move (currently not for Windows).
• The statement "shutdown defrag" now compresses the database (with the MVStore). This command can greatly reduce the file size, and is relatively fast, but is not incremental.
• The MVStore now automatically compacts the store in the background if there is no read or write activity, which should (after some time; sometimes about one minute) reduce the file size. This is still work in progress, feedback is welcome!
• Change default value of PAGE_SIZE from 2048 to 4096 to more closely match most file systems block size (PageStore only; the MVStore already used 4096).
• Auto-scale MAX_MEMORY_ROWS and CACHE_SIZE settings by the amount of available RAM. Gives a better out of box experience for people with more powerful machines.
• Handle tabs like 4 spaces in web console, patch by Martin Grajcar.
• Issue 573: Add implementation for Methods "isWrapperFor()" and "unwrap()" in JdbcConnection.java, patch by BigMichi1.

Version 1.4.180 Beta (2014-07-13)

• MVStore: the store is now auto-compacted automatically up to some point, to avoid very large file sizes. This area is still work in progress.
• Sequences of temporary tables (auto-increment or identity columns) were persisted unnecessarily in the database file, and were not removed when re-opening the database.
• MVStore: an IndexOutOfBoundsException could sometimes occur MVMap.openVersion when concurrently accessing the store.
• The LIRS cache now re-sizes the internal hash map if needed.
• Optionally persist session history in the H2 console. (patch from Martin Grajcar)
• Add client-info property to get the number of servers currently in the cluster and which servers that are available. (patch from Nikolaj Fogh)
• Fix bug in changing encrypted DB password that kept the file handle open when the wrong password was supplied. (test case from Jens Hohmuth).
• Issue 567: H2 hangs for a long time then (sometimes) recovers. Introduce a queue when doing table locking to prevent session starvation.

Version 1.4.179 Beta (2014-06-23)

• The license was changed to MPL 2.0 (from 1.0) and EPL 1.0.
• Issue 565: MVStore: concurrently adding LOB objects (with MULTI_THREADED option) resulted in a NullPointerException.
• MVStore: reduced dependencies to other H2 classes.
• There was a way to prevent a database from being re-opened, by creating a column constraint that references a table with a higher id, for example with "check" constraints that contains queries. This is now detected, and creating the table is prohibited. In future versions of H2, most likely creating references to other tables will no longer be supported because of such problems.
• MVStore: descending indexes with "nulls first" did not work as expected (null was ordered last).
• Large result sets now always create temporary tables instead of temporary files.
• When using the PageStore, opening a database failed in some cases with a NullPointerException if temporary tables were used (explicitly, or implicitly when using large result sets).
• If a database file in the PageStore file format exists, this file and this mode is now used, even if the database URL does not contain "MV_STORE=FALSE". If a MVStore file exists, it is used.
• Databases created with version 1.3.175 and earlier that contained foreign keys in combination with multi-column indexes could not be opened in some cases. This was due to a bugfix in version 1.3.176: Referential integrity constraints sometimes used the wrong index.
• MVStore: the ObjectDataType comparison method was incorrect if one key was Serializable and the other was of a common class.
• Recursive queries with many result rows (more than the setting "max_memory_rows") did not work correctly.
• The license has changed to MPL 2.0 + EPL 1.0.
• MVStore: temporary tables from result sets could survive re-opening a database, which could result in a ClassCastException.
• Issue 566: MVStore: unique indexes that were created later on did not work correctly if there were over 5000 rows in the table. Existing databases need to be re-created (at least the broken index need to be re-built).
• MVStore: creating secondary indexes on large tables results in missing rows in the index.
• Metadata: the password of linked tables is now only visible for admin users.
• For Windows, database URLs of the form "jdbc:h2:/test" where considered relative and did not work unless the system property "h2.implicitRelativePath" was used.
• Windows: using a base directory of "C:/" and similar did not work as expected.
• Follow JDBC specification on Procedures MetaData, use P0 as return type of procedure.
• Issue 531: IDENTITY ignored for added column.
• FileSystem: improve exception throwing compatibility with JDK
• Spatial Index: adjust costs so we do not use the spatial index if the query does not contain an intersects operator.
• Fix multi-threaded deadlock when using a View that includes a TableFunction.
• Fix bug in dividing very-small BigDecimal numbers.

Version 1.4.178 Beta (2014-05-02)

• Issue 559: Make dependency on org.osgi.service.jdbc optional.
• Improve error message when the user specifies an unsupported combination of database settings.
• MVStore: in the multi-threaded mode, NullPointerException and other exceptions could occur.
• MVStore: some database file could not be compacted due to a bug in the bookkeeping of the fill rate. Also, database file were compacted quite slowly. This has been improved; but more changes in this area are expected.
• MVStore: support for volatile maps (that don't store changes).
• MVStore mode: in-memory databases now also use the MVStore.
• In server mode, appending ";autocommit=false" to the database URL was working, but the return value of Connection.getAutoCommit() was wrong.
• Issue 561: OSGi: the import package declaration of org.h2 excluded version 1.4.
• Issue 558: with the MVStore, a NullPointerException could occur when using LOBs at session commit (LobStorageMap.removeLob).
• Remove the "h2.MAX_MEMORY_ROWS_DISTINCT" system property to reduce confusion. We already have the MAX_MEMORY_ROWS setting which does a very similar thing, and is better documented.
• Issue 554: Web Console in an IFrame was not fully supported.

Version 1.4.177 Beta (2014-04-12)

• By default, the MV_STORE option is enabled, so it is using the new MVStore storage. The MVCC setting is by default set to the same values as the MV_STORE setting, so it is also enabled by default. For testing, both settings can be disabled by appending ";MV_STORE=FALSE" and/or ";MVCC=FALSE" to the database URL.
• The file locking method 'serialized' is no longer supported. This mode might return in a future version, however this is not clear right now. A new implementation and new tests would be needed.
• Enable the new storage format for dates (system property "h2.storeLocalTime"). For the MVStore mode, this is always enabled, but with version 1.4 this is even enabled in the PageStore mode.
• Implicit relative paths are disabled (system property "h2.implicitRelativePath"), so that the database URL jdbc:h2:test now needs to be written as jdbc:h2:./test.
• "select ... fetch first 1 row only" is supported with the regular mode. This was disabled so far because "fetch" and "offset" are now keywords. See also Mode.supportOffsetFetch.
• Byte arrays are now sorted in unsigned mode (x'99' is larger than x'09'). (System property "h2.sortBinaryUnsigned", Mode.binaryUnsigned, setting "binary_collation").
• Csv.getInstance will be removed in future versions of 1.4. Use the public constructor instead.
• Remove support for the limited old-style outer join syntax using "(+)". Use "outer join" instead. System property "h2.oldStyleOuterJoin".
• Support the data type "DATETIME2" as an alias for "DATETIME", for MS SQL Server compatibility.
• Add Oracle-compatible TRANSLATE function, patch by Eric Chatellier.

Version 1.3.176 (2014-04-05)

• The file locking method 'serialized' is no longer documented, as it will not be available in version 1.4.
• The static method Csv.getInstance() was removed. Use the public constructor instead.
• The default user name for the Script, RunScript, Shell, and CreateCluster tools are no longer "sa" but an empty string.
• The stack trace of the exception "The object is already closed" is no longer logged by default.
• If a value of a result set was itself a result set, the result could only be read once.
• Column constraints are also visible in views (patch from Nicolas Fortin for H2GIS).
• Granting a additional right to a role that already had a right for that table was not working.
• Spatial index: a few bugs have been fixed (using spatial constraints in views, transferring geometry objects over TCP/IP, the returned geometry object is copied when needed).
• Issue 551: the datatype documentation was incorrect (found by Bernd Eckenfels).
• Issue 368: ON DUPLICATE KEY UPDATE did not work for multi-row inserts. Test case from Angus Macdonald.
• OSGi: the package javax.tools is now imported (as an optional).
• H2 Console: auto-complete is now disabled by default, but there is a hot-key (Ctrl+Space).
• H2 Console: auto-complete did not work with multi-line statements.
• CLOB and BLOB data was not immediately removed after a rollback.
• There is a new Aggregate API that supports the internal H2 data types (GEOMETRY for example). Thanks a lot to Nicolas Fortin for the patch!
• Referential integrity constraints sometimes used the wrong index, such that updating a row in the referenced table incorrectly failed with a constraint violation.
• The Polish translation was completed and corrected by Wojtek Jurczyk. Thanks a lot!
• Issue 545: Unnecessary duplicate code was removed.
• The profiler tool can now process files with full thread dumps.
• MVStore: the file format was changed slightly.
• MVStore mode: the CLOB and BLOB storage was re-implemented and is now much faster than with the PageStore (which is still the default storage).
• MVStore mode: creating indexes is now much faster (in many cases faster than with the default PageStore).
• Various bugs in the MVStore storage and have been fixed, including a bug in the R-tree implementation. The database could get corrupt if there were transient IO exceptions while storing.
• The method org.h2.expression.Function.getCost could throw a NullPointException.
• Storing LOBs in separate files (outside of the main database file) is no longer supported for new databases.
• Lucene 2 is no longer supported.
• Fix bug in calculating default MIN and MAX values for SEQUENCE.
• Fix bug in performing IN queries with multiple values when IGNORECASE=TRUE
• Add entry-point to org.h2.tools.Shell so it can be called from inside an application. patch by Thomas Gillet.
• Fix bug that prevented the PgServer from being stopped and started multiple times.
• Support some more DDL syntax for MySQL, patch from Peter Jentsch.
• Issue 548: TO_CHAR does not format MM and DD correctly when the month or day of the month is 1 digit, patch from "the.tucc"
• Fix bug in varargs support in ALIAS's, patch from Nicolas Fortin