JaQu: the plan is to support natural (pure Java) conditions such as (id == 1 && name.equals("Test")). A proof of concept decompiler is now included (it doesn't work yet).
Better support GaeVFS (Google App Engine Virtual File System).
@changelog_1003_li
Various bugfixes and improvements in the page store mechanism (still experimental).
JaQu: the plan is to support natural (pure Java) conditions such as (id == 1 && name.equals("Test")). A proof of concept decompiler is now included (it doesn't work yet).
@changelog_1004_li
PreparedStatement.setObject now converts a java.lang.Character to a string.
Various bugfixes and improvements in the page store mechanism (still experimental).
@changelog_1005_li
H2 Console: PierPaolo Ucchino has completed the Italian translation. Thanks a lot!
PreparedStatement.setObject now converts a java.lang.Character to a string.
@changelog_1006_li
Various tools now use Java 5 var-args, such as main the methods and SimpleResultSet.addRow.
H2 Console: PierPaolo Ucchino has completed the Italian translation. Thanks a lot!
@changelog_1007_li
H2 Console: indexes of tables of non-default schemas are now also listed.
Various tools now use Java 5 var-args, such as main the methods and SimpleResultSet.addRow.
@changelog_1008_li
Issue 111: Multi-version concurrency / duplicate primary key after rollback.
H2 Console: indexes of tables of non-default schemas are now also listed.
@changelog_1009_li
Issue 110: Multi-version concurrency / wrong exception is thrown.
Issue 111: Multi-version concurrency / duplicate primary key after rollback.
@changelog_1010_li
Parser: sequenceName.NEXTVAL and CURRVAL did not respect the schema search path.
Issue 110: Multi-version concurrency / wrong exception is thrown.
@changelog_1011_li
The following sequence could throw the exception "Row not found when trying to delete": start a transaction, insert many rows, delete many rows, rollback. The number of rows depends on the cache size.
Parser: sequenceName.NEXTVAL and CURRVAL did not respect the schema search path.
@changelog_1012_li
The stack trace of very common exceptions is no longer written to the .trace.db file by default.
Issue 101: The following sequence could throw the exception "Row not found when trying to delete": start a transaction, insert many rows, delete many rows, rollback. The number of rows depends on the cache size.
@changelog_1013_li
An optimization for OR is implemented, but disabled by default. Expressions of the type X=1 OR X=2 are converted to X IN(1, 2). To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver.
The stack trace of very common exceptions is no longer written to the .trace.db file by default.
@changelog_1014_li
An optimization for OR is implemented, but disabled by default. Expressions of the type X=1 OR X=2 are converted to X IN(1, 2). To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver.
@changelog_1015_li
An optimization for IN(..) and IN(SELECT...) is implemented, but disabled by default. To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver. If enabled, this overrides h2.optimizeIn and h2.optimizeInJoin. Unlike now, this optimization will also speed up updates and deletes.
@changelog_1015_h2
@changelog_1016_h2
Version 1.1.117 (2009-08-09)
@changelog_1016_li
@changelog_1017_li
New committer: Sam Van Oort has been contributing to H2 since quite some time in many ways (on the mailing list, documentation, and in the form of patches). He is now a committer.
@changelog_1017_li
@changelog_1018_li
JaQu: the order of the fields in the database no longer needs to match the order in the database.
@changelog_1018_li
@changelog_1019_li
Issue 103: MVCC: the setting MAX_MEMORY_UNDO can currently not be supported when using multi-version concurrency, that means the complete undo log must fit in memory.
@changelog_1019_li
@changelog_1020_li
LIKE: the escape mechanism can now be disable using ESCAPE ''. The default escape character can be changed using the system property h2.defaultEscape. The default is still '\' (as in MySQL and PostgreSQL).
@changelog_1020_li
@changelog_1021_li
Views using functions were not re-evaluated when necessary.
@changelog_1021_li
@changelog_1022_li
Improved MySQL compatibility for SHOW COLUMNS.
@changelog_1022_li
@changelog_1023_li
Improved PostgreSQL compatibility for timestamp literals with timezone.
@changelog_1023_li
@changelog_1024_li
Sergi Vladykin translated the error messages to Russian. Thanks a lot!
@changelog_1024_li
@changelog_1025_li
Support for Java 6 DatabaseMetaData.getTables, getColumns, getProcedures, and getProcedureColumns.
@changelog_1025_li
@changelog_1026_li
Issue 101: Rollback of a large transaction (more than 100000 rows) could fail.
@changelog_1026_li
@changelog_1027_li
Various bugfixes and improvements in the page store mechanism (still experimental).
@changelog_1027_li
@changelog_1028_li
The functions LENGTH, OCTET_LENGTH, and BIT_LENGTH now return BIGINT.
@changelog_1028_li
@changelog_1029_li
Data types CLOB and BLOB: the maximum precision was Integer.MAX_VALUE, it is now Long.MAX_VALUE.
@changelog_1029_li
@changelog_1030_li
Multi-threaded kernel: creating and dropping temporary database objects and the potentially free pages list was not correctly synchronized. Thanks a lot to Eric Faulhaber for the test case and patch!
@changelog_1030_li
@changelog_1031_li
Parsing SQL script files is now faster.
@changelog_1031_li
@changelog_1032_li
CSV reading is now faster.
@changelog_1032_li
@changelog_1033_li
SimpleResultSet.newInstance(SimpleRowSource rs) did not work.
@changelog_1033_h2
@changelog_1034_h2
Version 1.1.116 (2009-07-18)
@changelog_1034_li
@changelog_1035_li
Server-less multi-connection mode: more bugs are fixed.
@changelog_1035_li
@changelog_1036_li
The built-in help (INFORMATION_SCHEMA.HELP) is smaller, shrinking the jar file size a bit.
@changelog_1036_li
@changelog_1037_li
H2 Console: column of tables of non-default schemas are now also listed, except for schemas starting with 'INFO'.
@changelog_1037_li
@changelog_1038_li
ALTER TABLE: removing an auto-increment or identity column didn't remove the sequence.
@changelog_1038_li
@changelog_1039_li
Creating indexes is now a bit faster.
@changelog_1039_li
@changelog_1040_li
PG Server: new system property h2.pgClientEncoding to explicitly set the encoding for clients that don't send the encoding (the default encoding is UTF-8). Thanks a lot to Sergi Vladykin for the patch!
@changelog_1040_li
@changelog_1041_li
PG Server: improved compatibility by using the type ids of the PostgreSQL driver. Thanks a lot to Sergi Vladykin for the patch!
@changelog_1041_li
@changelog_1042_li
H2 Console: Oracle system tables are no longer listed, improving performance.
@changelog_1042_li
@changelog_1043_li
Result sets are now read-only except if the statement or prepared statement was created with the concurrency ResultSet.CONCUR_UPDATABLE. This change is required because the old behavior (all result set are updatable) violated the JDBC spec. For backward compatibility, use the system property h2.defaultResultSetConcurrency.
@changelog_1043_li
@changelog_1044_li
New system property h2.defaultResultSetConcurrency to change the default result set concurrency.
@changelog_1044_li
@changelog_1045_li
JDBC: using an invalid result set type or concurrency now throws an exception.
@changelog_1045_li
@changelog_1046_li
If a pooled connection was not closed but garbage collected, a NullPointerException could occur.
@changelog_1046_li
@changelog_1047_li
Fulltext search: a NullPointerException was thrown when updating a value that was NULL previously.
@changelog_1047_li
@changelog_1048_li
The Recover tool did not work with .data.db files of the wrong size.
@changelog_1048_li
@changelog_1049_li
Triggers: if there was an exception when initializing a trigger, this exception could be hidden, and in some cases (specially when using the Lucene fulltext index mechanism) a NullPointerException was thrown later on. Now the exception that occurred on init is thrown when changing data.
@changelog_1049_li
@changelog_1050_li
The soft-references cache (CACHE_TYPE=SOFT_LRU) could throw a NullPointerException.
@changelog_1050_li
@changelog_1051_li
To enable the new page store mechanism, append ;PAGE_STORE=TRUE to the database URL. or set the system property h2.pageStore to true. This mechanism is still experimental, and the file format will change, but it is quite stable now.
@changelog_1051_h2
@changelog_1052_h2
Version 1.1.115 (2009-06-21)
@changelog_1052_li
@changelog_1053_li
The new storage mechanism is now alpha quality. To try it out, set the system property "h2.pageStore" to "true" (java -Dh2.pageStore=true). There are still bugs to be found and fixed, for example inserting many rows references a lot of main memory. Performance is currently about the same as with the regular storage mechanism, but the database file size is smaller. The file format is not stable yet.
@changelog_1053_li
@changelog_1054_li
ALTER TABLE could throw an exception "object already exists" in some cases.
@changelog_1054_li
@changelog_1055_li
Views: in some situations, an ArrayIndexOutOfBoundsException was thrown when using the same view concurrently.
@changelog_1055_li
@changelog_1056_li
java.util.UUID is now supported in PreparedStatement.setObject and user defined Java functions. ResultSet.getObject() returns a java.util.UUID when using the UUID data type.
@changelog_1056_li
@changelog_1057_li
H2 Console: the language was reset to the browser language when disconnecting.
@changelog_1057_li
@changelog_1058_li
H2 Console: improved Polish translation.
@changelog_1058_li
@changelog_1059_li
Server-less multi-connection mode: more bugs are fixed.
@changelog_1059_li
@changelog_1060_li
The download page now included the SHA1 checksums.
@changelog_1060_li
@changelog_1061_li
Shell tool: the file encoding workaround is now documented if you run java org.h2.tools.Shell -?.
@changelog_1061_li
@changelog_1062_li
The RunScript tool and SQL statement did not work with the compression method LZF.
@changelog_1062_li
@changelog_1063_li
Fulltext search: searching for NULL or an empty string threw an exception.
@changelog_1063_li
@changelog_1064_li
Lucene fulltext search: FTL_DROP_ALL did not drop the triggers.
@changelog_1064_li
@changelog_1065_li
Backup: if the database contained CLOB or BLOB data, the backup included a file entry for the LOB directory. This caused the restore to fail.
@changelog_1065_li
@changelog_1066_li
Data types: LONG is now an alias for BIGINT.
@changelog_1066_h2
@changelog_1067_h2
Version 1.1.114 (2009-06-01)
@changelog_1067_li
@changelog_1068_li
ResultSetMetaData.getColumnClassName returned the wrong class for CLOB and BLOB columns.
@changelog_1068_li
@changelog_1069_li
Fulltext search: data is no longer deleted and re-inserted if the indexed columns didn't change.
@changelog_1069_li
@changelog_1070_li
In some situations, an ArrayIndexOutOfBoundsException was thrown when adding rows. This was caused by a bug in the b-tree code.
@changelog_1070_li
@changelog_1071_li
Microsoft Windows Vista: when using the the installer, Vista wrote "This program may not have installed correctly." This message should no longer appear (in the h2.nsi file, the line 'RequestExecutionLevel highest' was added).
@changelog_1071_li
@changelog_1072_li
The Recover tool did not always work when the database contains referential integrity constraints.
@changelog_1072_li
@changelog_1073_li
Java 1.5 is now required to run H2. If required, Retrotranslator can be used to create a Java 1.4 version (http://retrotranslator.sourceforge.net/).
@changelog_1073_h2
@changelog_1074_h2
Version 1.1.113 (2009-05-21)
@changelog_1074_li
@changelog_1075_li
Shell tool: the built-in commands EXIT, HELP, ?, LIST, and so on didn't work with a semicolon at the end.
@changelog_1075_li
@changelog_1076_li
JDK 1.5 is now required to build the jar file. However it is still possible to create a jar file for Java 1.4. For details, see buildRelease.sh and buildRelease.bat. As an alternative, compile using JDK 1.5 or 1.6 and use Retrotranslator to create a Java 1.4 version (http://retrotranslator.sourceforge.net/).
@changelog_1076_li
@changelog_1077_li
When deleting or updating many rows in a table, the space in the index file was not re-used in the default mode (persistent database, b-tree index, LOG=1). This caused the index file to grow over time. Workarounds were to delete and re-created the index file, alter the table (add a remove a column), or append ;LOG=2 to the database URL. To disable the change, set the system property h2.reuseSpaceBtreeIndex to false.
@changelog_1077_li
@changelog_1078_li
Identifiers with a digit and then a dollar sign didn't work. Example: A1$B.
@changelog_1078_li
@changelog_1079_li
MS SQL Server compatibility: support for linked tables with NVARCHAR, NCHAR, NCLOB, and LONGNVARCHAR.
@changelog_1079_li
@changelog_1080_li
Android: workaround for a problem when using read-only databases in zip files (skip seems to be implemented incorrectly on the Android system).
@changelog_1080_li
@changelog_1081_li
Calling execute() or prepareStatement() with null as the SQL statement now throws an exception.
@changelog_1081_li
@changelog_1082_li
Benchmark: the number of executed statements was incorrect. The H2 database was loaded at the beginning of the test to collect results, now it is loaded at the very end. Thanks to Fred Toussi from HSQLDB for reporting those problems. However the changed do not affect the relative performance.
@changelog_1082_li
@changelog_1083_li
H2 Console: command line settings are no longer stored in the properties file. They are now only used for the current process, except if they are explicitly saved.
@changelog_1083_li
@changelog_1084_li
Cache: support for a second level soft-references cache. To enable it, append ;CACHE_TYPE=SOFT_LRU (or SOFT_TQ) to the database URL, or set the system property h2.cacheTypeDefault to "SOFT_LRU" / "SOFT_TQ". Enabling the second level cache reduces performance for small databases, but speeds up large databases. It makes sense to use it if the available memory size is unknown. Thanks a lot to Jan Kotek!
@changelog_1084_h2
@changelog_1085_h2
Version 1.1.112 (2009-05-01)
@changelog_1085_li
@changelog_1086_li
JdbcPreparedStatement.toString() could throw a NullPointerException.
@changelog_1086_li
@changelog_1087_li
EclipseLink: added H2Platform.supportsIdentity().
@changelog_1087_li
@changelog_1088_li
Connection pool: the default login timeout is now 5 minutes.
@changelog_1088_li
@changelog_1089_li
After truncating tables, opening large databases could become slow because indexes were always re-built unnecessarily when opening.
@changelog_1089_li
@changelog_1090_li
More bugs in the server-less multi-connection mode have been fixed: Sometimes parameters of prepared statements were lost when a reconnecting. Concurrent read operations were slow. To improve performance, executeQuery(..) must be used for queries (execute(..) switches to the write mode, which is slow).
@changelog_1090_li
@changelog_1091_li
GROUP BY queries with a self-join (join to the same table) that were grouped by columns with indexes returned the wrong result in some cases.
@changelog_1091_li
@changelog_1092_li
Improved error message when the .lock.db file modification time is in the future.
@changelog_1092_li
@changelog_1093_li
The MERGE statement now returns 0 as the generated key if the row was updated.
@changelog_1093_li
@changelog_1094_li
Running code coverage is now automated.
@changelog_1094_li
@changelog_1095_li
A file system implementation can now be registered using FileSystem.register.
@changelog_1095_li
@changelog_1096_li
The database file system is no longer included in the jar file, it moved to the test section.
@changelog_1096_h2
@changelog_1097_h2
Version 1.1.111 (2009-04-10)
@changelog_1097_li
@changelog_1098_li
In-memory databases can now run inside the Google App Engine.
@changelog_1098_li
@changelog_1099_li
Queries that are ordered by an indexed column returned no rows in certain cases (if all rows were deleted from the table previously, and there is a low number of rows in the table, and when not using other conditions, and when using the default b tree index).
@changelog_1099_li
@changelog_1100_li
The wrong exception was thrown when using unquoted text for the SQL statements COMMENT, ALTER USER, and SET PASSWORD.
@changelog_1100_li
@changelog_1101_li
The built-in connection pool did not roll back transactions and enable autocommit enabled after closing a connection.
@changelog_1101_li
@changelog_1102_li
Sometimes a StackOverflow occurred when checking for deadlock. See also http://code.google.com/p/h2database/issues/detail?id=61
@changelog_1102_li
@changelog_1103_li
The Shell tool no longer truncates results with only one column, and displays a message if data was truncated.
@changelog_1103_h2
@changelog_1104_h2
Version 1.1.110 (2009-04-03)
@changelog_1104_li
@changelog_1105_li
Support for not persistent in-memory tables in regular (persistent) databases using CREATE MEMORY TABLE(..) NOT PERSISTENT. Thanks a lot to Sergi Vladykin for the patch!
@changelog_1105_li
@changelog_1106_li
The H2 Console trimmed the password (removed leading and trailing spaces). This is no longer the case, to support encrypted H2 database with an empty user password.
@changelog_1106_li
@changelog_1107_li
The data type of a SUBSTRING method was wrong.
@changelog_1107_li
@changelog_1108_li
ResultSet.findColumn and get methods with column label parameters now also check for matching column names (like most databases except MySQL).
@changelog_1108_li
@changelog_1109_li
H2 Console: the browser system property now supports a list of arguments. Example: java -Dh2.browser="open,-a,Safari,%url" ...
@changelog_1109_li
@changelog_1110_li
Improved Javadoc navigation (similar to Scaladoc).
@changelog_1110_li
@changelog_1111_li
H2 Console: auto-complete of identifiers did not work correctly for H2 databases in MySQL mode.
@changelog_1111_li
@changelog_1112_li
DISTINCT and GROUP BY on a CLOB column was broken.
@changelog_1112_li
@changelog_1113_li
The FTP server moved to the tools section and is no longer included in the h2*.jar file.
@changelog_1113_li
@changelog_1114_li
Improved error message for unsupported features: now the message says what exactly is not supported.
@changelog_1114_li
@changelog_1115_li
Improved OSGi support.
@changelog_1115_li
@changelog_1116_li
Some internal caches did not use the LRU mechanism. Fixed (LOB file list, optimizer cost cache, trace system, view indexes, collection keys, compressed in-memory file system).
@changelog_1116_li
@changelog_1117_li
The API of the tools changed a bit (each tool now returns an exit code).
@changelog_1117_li
@changelog_1118_li
Command line help of the tools now match the javadocs. The build converts the javadocs to a resource that is read by the tool at runtime. This should not have an effect on using the database, but it reduces duplicate and out-of-sync documentation.
@changelog_1118_li
@changelog_1119_li
CREATE TABLE: improved compatibility (support for UNIQUE NOT NULL).
@changelog_1119_li
@changelog_1120_li
DatabaseMetaData.getSQLKeywords now returns the correct list.
@changelog_1120_li
@changelog_1121_li
Deterministic user defined functions did not work when the parameter was a column. Fixed.
@changelog_1121_li
@changelog_1122_li
JdbcConnectionPool.setLoginTimeout with 0 now uses the default timeout.
@changelog_1122_li
@changelog_1123_li
Creating a JdbcConnectionPool has been simplified a bit.
@changelog_1123_li
@changelog_1124_li
The built-in connection pool did not re-use connections. Getting a connection using the built-in JdbcConnectionPool is now about 70 times faster than opening connections using DriverManager.getConnection.
@changelog_1124_li
@changelog_1125_li
More bugs in the server-less multi-connection mode have been fixed: If a process terminated while writing, other open connections were blocked. If two processes were writing to the database, sometimes the database was corrupt after closing.
@changelog_1125_li
@changelog_1126_li
Linked tables to SQLite database can now be created.
@changelog_1126_li
@changelog_1127_li
Nested IN(IN(...)) didn't work.
@changelog_1127_li
@changelog_1128_li
NIO storage: the nio: prefix was using memory mapped files instead of FileChannel.
@changelog_1128_h2
@changelog_1129_h2
Version 1.1.109 (2009-03-14)
@changelog_1129_li
@changelog_1130_li
The optimization for IN(...) is now only used if comparing a column with an index.
@changelog_1130_li
@changelog_1131_li
User defined functions can now be deterministic (see CREATE ALIAS documentation).
@changelog_1131_li
@changelog_1132_li
Multiple nested queries in the FROM clause with parameters did not always work.
@changelog_1132_li
@changelog_1133_li
When converting CLOB to BINARY, each character resulted in one byte. Now, the text is parsed as a hex as when converting VARCHAR.
@changelog_1133_li
@changelog_1134_li
New experimental NIO storage mechanism with both FileChannel and memory mapped files. To use it, use the file name prefix nio: or nioMapped: as in jdbc:h2:nio:~/test. So far it looks like NIO storage is faster on Mac OS but slower on some Windows systems. Thanks a lot to Jan Kotek for the patch!
@changelog_1134_li
@changelog_1135_li
The functions BITOR, BITAND, BITXOR, and MOD now accept and return BIGINT instead of INT.
@changelog_1135_li
@changelog_1136_li
Could not use the same linked table multiple times in the same query.
@changelog_1136_li
@changelog_1137_li
Bugs in the server-less multi-connection mode have been fixed.
@changelog_1137_li
@changelog_1138_li
Column names could not be named "UNIQUE" (with the quotes).
@changelog_1138_li
@changelog_1139_li
New system function TRANSACTION_ID() to get the current transaction identifier for a session.
@changelog_1139_h2
@changelog_1140_h2
Version 1.1.108 (2009-02-28)
@changelog_1140_li
@changelog_1141_li
When the shutdown hook closed the database, the last log file was deleted too early. This could cause uncommitted changes to be persisted. In some cases, this could cause data corruption.
@changelog_1141_li
@changelog_1142_li
JdbcConnectionPool: it was possible to set a negative connection pool size.
@changelog_1142_li
@changelog_1143_li
Fulltext search did not support table names with a backslash.
@changelog_1143_li
@changelog_1144_li
The internal IntArray class did not work correctly when initialized with a zero length array.
@changelog_1144_li
@changelog_1145_li
The H2 Console web application (war file) did only support ASCII characters. Now UTF-8 is supported.
@changelog_1145_li
@changelog_1146_li
DATEADD does no longer require that the argument is a timestamp.
@changelog_1146_li
@changelog_1147_li
The database file locking mechanism didn't work correctly on Mac OS.
@changelog_1147_li
@changelog_1148_li
Some built-in functions reported the wrong precision, scale, and display size.
@changelog_1148_li
@changelog_1149_li
MySQL compatibility for CREATE TABLE is improved (UNSIGNED, KEY).
@changelog_1149_li
@changelog_1150_li
Recovery did not work if there were more than 255 lobs stored as files.
@changelog_1150_li
@changelog_1151_li
New experimental mode to support multiple read-write connections without starting a server. To enable this mode, append ;FILE_LOCK=SERIALIZED;OPEN_NEW=TRUE to the database URL. Don't expect high performance when multiple concurrent writers.
@changelog_1151_li
@changelog_1152_li
In a web application, the database classes are not unloaded if a connection is open. This may cause out of memory when re-deploying a web application. The DbStarter is changed to close all connections to the configured database (by executing SHUTDOWN).
@changelog_1152_li
@changelog_1153_li
The WebServlet did not close the database when un-deploying the web application.
@changelog_1153_li
@changelog_1154_li
The exception message of failed INSERT or MERGE statements now includes all values and the row number.
@changelog_1154_li
@changelog_1155_li
If opening a database failed with an out of memory exception, some files were not closed.
@changelog_1155_li
@changelog_1156_li
Optimizer: the expected runtime calculation was incorrect. The fixed calculation should give slightly better query plans when using many joins.
@changelog_1156_li
@changelog_1157_li
Improved exception message when connecting to a just started server fails.
@changelog_1157_li
@changelog_1158_li
Connection.isValid is a bit faster.
@changelog_1158_li
@changelog_1159_li
H2 Console: the autocomplete feature has been improved a bit. It can now better parse conditions.
@changelog_1159_li
@changelog_1160_li
When restarting a web application in Tomcat, an exception was thrown sometimes. In most cases this was a NullPointerException. A workaround in H2 has been implemented. The root cause of the problem is now documented in the FAQ: Tomcat sets all static fields (final or non-final) to null when unloading a web application. A workaround is to put the h2.jar in the lib directory, or set the system property org.apache.catalina.loader.WebappClassLoader.ENABLE_CLEAR_REFERENCES to false.
@changelog_1160_h2
@changelog_1161_h2
Version 1.1.107 (2009-01-24)
@changelog_1161_li
@changelog_1162_li
Some DatabaseMetaData operations did not work for non-admin users for versions 1.1.x.
@changelog_1162_li
@changelog_1163_li
The MySQL compatibility extension fromUnixTime now used the English locale.
@changelog_1163_li
@changelog_1164_li
When using LOG=2 and repeatedly updating the last row rows of a table, the index file grew quickly.
@changelog_1164_li
@changelog_1165_li
In versions 1.1.105 and 1.1.106, encrypted script files of earlier versions could not be processed. This is now again possible. The problem was that such script files were stored in a special format (STORAGE=TEXT) but support for this format was removed in version 1.1.105.
@changelog_1165_li
@changelog_1166_li
Enabling the trace mechanism by creating a specially named file is no longer supported.
@changelog_1166_h2
@changelog_1167_h2
Version 1.1.106 (2009-01-04)
@changelog_1167_li
@changelog_1168_li
Statement.setQueryTimeout did not work correctly for some statements.
@changelog_1168_li
@changelog_1169_li
CREATE DOMAIN: built-in data types can now only be changed if no tables exist.
@changelog_1169_li
@changelog_1170_li
Linked tables: a workaround for Oracle DATE columns has been implemented.
@changelog_1170_li
@changelog_1171_li
DatabaseMetaData.getPrimaryKeys: the column PK_NAME now contains the constraint name instead of the index name (compatibility for PostgreSQL and Derby).
@changelog_1171_li
@changelog_1172_li
Using IN(..) inside a IN(SELECT..) did not always work.
@changelog_1172_li
@changelog_1173_li
Views with IN(..) that used a view itself did not work.
@changelog_1173_li
@changelog_1174_li
Union queries with LIMIT or ORDER BY that are used in a view or subquery did not work.
@changelog_1174_li
@changelog_1175_li
The license change a bit: so far the license was modified to say 'Swiss law'. This is now changed back to the original 'US law'. This was requested by a user, and I don't see a problem.
@changelog_1175_li
@changelog_1176_li
Constraints for local temporary tables now session scoped. So far they were global. Thanks a lot to Eric Faulhaber for finding and fixing this problem!
@changelog_1176_li
@changelog_1177_li
When using the auto-server mode, and if the lock file was modified in the future, the wrong exception was thrown ('Connection is broken' instead of 'Error opening database: lock file modified in the future').
@changelog_1177_h2
@changelog_1178_h2
Version 1.1.105 (2008-12-19)
@changelog_1178_li
@changelog_1179_li
The setting STORAGE=TEXT is no longer supported.
@changelog_1179_li
@changelog_1180_li
Deleting a database using the tool DeleteDbFiles deleted LOB files of other databases in the same directory.
@changelog_1180_li
@changelog_1181_li
When used in a subquery, LIKE and IN(..) did not work correctly sometimes.
@changelog_1181_li
@changelog_1182_li
The fulltext search documentation has been improved.
@changelog_1182_li
@changelog_1183_li
ARRAY_GET returned the wrong data type (ARRAY). Now it returns VARCHAR.
@changelog_1183_li
@changelog_1184_li
Natural join: the joined columns are not repeated any more when using SELECT *.
@changelog_1184_li
@changelog_1185_li
User defined aggregate functions: the method getType expected internal data types instead of SQL types.
@changelog_1185_li
@changelog_1186_li
User defined aggregate functions did not work if there was no group by expression.
@changelog_1186_li
@changelog_1187_li
MySQL compatibility: support for := assignment as in @sum:=@sum+x
@changelog_1187_li
@changelog_1188_li
INSERT INTO TEST(SELECT * FROM TEST) is now supported.
@changelog_1188_li
@changelog_1189_li
Each session threw an invisible exception when garbage collected.
@changelog_1189_li
@changelog_1190_li
Foreign key constraints that refer to a quoted column did not work.
@changelog_1190_li
@changelog_1191_li
New meta data column INFORMATION_SCHEMA.TABLES.LAST_MODIFICATION to get the table modification counter.
@changelog_1191_li
@changelog_1192_li
Shell: line comments didn't work correctly.
@changelog_1192_li
@changelog_1193_li
H2 Console: columns are now listed for up to 500 tables instead of 100.
@changelog_1193_li
@changelog_1194_li
H2 Console: Cmd+Enter executes the current statement, Alt+Space for autocomplete.
@changelog_1194_li
@changelog_1195_li
JaQu: the maximum length of a column can now be defined using maxLength. For an example, see Product.java (maxLength(category, 255)).
@changelog_1195_li
@changelog_1196_li
R&\#305;dvan A&\#287;ar has completed the Turkish translation of the H2 Console. Thanks a lot!
@changelog_1196_h2
@changelog_1197_h2
Version 1.1.104 (2008-11-28)
@changelog_1197_li
@changelog_1198_li
If a query that was used like a table contained group by and was ordered by an expression that is not in the column list, an exception was thrown.
@changelog_1198_li
@changelog_1199_li
JaQu: tables are now auto-created when running a query.
@changelog_1199_li
@changelog_1200_li
The optimizer had problems with function tables (for example CSVREAD and FTL_SEARCH). A new system property h2.estimatedFunctionTableRows (default 1000) defines how many rows can be expected in the table.
@changelog_1200_li
@changelog_1201_li
The function SUM could overflow when using large values. It returns now a data type that is safe.
@changelog_1201_li
@changelog_1202_li
The function AVG could overflow when using large values. Fixed.
@changelog_1202_li
@changelog_1203_li
The emergency reserve file has been removed. It didn't provide an appropriate solution for the problem. It is still possible for an application to detect and deal with the low disk space problem (deleting temporary files for example) using DatabaseEventListener.diskSpaceIsLow, but this method is now always called with stillAvailable=0.
@changelog_1203_li
@changelog_1204_li
Build: JAVA_HOME is now automatically detected on Mac OS X.
@changelog_1204_li
@changelog_1205_li
Testing for local connections was very slow on some systems.
@changelog_1205_li
@changelog_1206_li
The cache memory usage calculation is more conservative.
@changelog_1206_li
@changelog_1207_li
Allocating space got slower and slower the larger the database.
@changelog_1207_li
@changelog_1208_li
ALTER TABLE ALTER COLUMN could throw the wrong exception in the last version (Table not found).
@changelog_1208_li
@changelog_1209_li
Updatable result sets: the key columns can now be updated.
@changelog_1209_li
@changelog_1210_li
The H2DatabaseProvider for ActiveObjects is now included in the tools section.
@changelog_1210_li
@changelog_1211_li
The H2Platform for Oracle Toplink Essential has been improved a bit.
@changelog_1211_li
@changelog_1212_li
The Windows service to start H2 didn't work in version 1.1.
@changelog_1212_li
@changelog_1213_li
File systems with a maximum file size (for example FAT) are now supported using the file prefix 'split:'. In this case the files are split in parts of 1 GB. Example URL: jdbc:h2:split:~/db/test. If you want to split into parts of 1 MB, use jdbc:h2:split:20:~/db/test (the part size is 1 << x, the default is 30 meaning 1 GB).
@changelog_1213_li
@changelog_1214_li
The database now tries to detect if the classloader or virtual machine has almost shut down by checking if static final variables are set to null. This should help reduce exceptions when stopping the web application.
@changelog_1214_li
@changelog_1215_li
Compatibility for MS SQL Server DATEDIFF(YYYY, .., ..)
@changelog_1215_li
@changelog_1216_li
ResultSet.getObject for CLOB or BLOB will return a java.sql.Clob / java.sql.Blob object instead of a java.io.Reader / java.io.InputStream as in version 1.0. This behavior can be changed using the system property h2.returnLobObjects (true by default for version 1.1).
@changelog_1216_li
@changelog_1217_li
The interface CloseListener has a new method 'remove' that is called when the trigger is dropped.
@changelog_1217_li
@changelog_1218_li
Fulltext search: there was a memory leak when creating and dropping fulltext indexes in a loop.
@changelog_1218_h2
@changelog_1219_h2
Version 1.1.103 (2008-11-07)
@changelog_1219_li
@changelog_1220_li
Could not order by a formula when the formula was in the group by list but not in the select list.
@changelog_1220_li
@changelog_1221_li
Date values that match the daylight saving time end were not allowed in times zones were the daylight saving time ends at midnight, for years larger than 2037. Example: timezone Brasilia, date 2042-10-12. This is a problem of Java, however a workaround is implemented in H2 that solves most problems (except the problems of java.util.Date itself).
@changelog_1221_li
@changelog_1222_li
ALTER TABLE used a lot of memory when using multi-version concurrency.
@changelog_1222_li
@changelog_1223_li
Referential integrity for in-memory databases didn't work in some cases in version 1.1.102.
@changelog_1223_li
@changelog_1224_li
New column INFORMATION_SCHEMA.COLUMNS.SEQUENCE_NAME to get the name of the sequence for auto-increment columns.
@changelog_1224_li
@changelog_1225_li
Aliases for built-in data types (such as MEDIUMBLOB which is an alias for BLOB) can now be re-mapped to another data type using CREATE DOMAIN. However main built-in data types (such as INTEGER) can not be re-mapped.
@changelog_1225_li
@changelog_1226_li
The Japanese translation has been completed by Masahiro Ikemoto. Thanks a lot!
@changelog_1226_li
@changelog_1227_li
Improved PostgreSQL compatibility for NEXTVAL and CURRVAL.
@changelog_1227_li
@changelog_1228_li
Less heap memory is needed when multiple databases are open at the same time: the memory reserve (used to rollback after out of memory) is now global and no longer allocated for each database separately.
@changelog_1228_li
@changelog_1229_li
New system property h2.browser to set the browser to use.
@changelog_1229_li
@changelog_1230_li
To start the browser, java.awt.Desktop.browse is now used if available.
@changelog_1230_h2
@changelog_1231_h2
Version 1.1.102 (2008-10-24)
@changelog_1231_li
@changelog_1232_li
The French translation of the H2 Console has been improved by Olivier Parent. Thanks a lot!
@changelog_1232_li
@changelog_1233_li
There was a memory leak when creating and dropping tables and indexes in a loop (persistent database only).
@changelog_1233_li
@changelog_1234_li
SET LOG 2 was not effective if executed after opening the database.
@changelog_1234_li
@changelog_1235_li
Translating the H2 Console is now simpler.
@changelog_1235_li
@changelog_1236_li
Common exception (error code 23*) are no longer written to the .trace.db file by default.
@changelog_1236_li
@changelog_1237_li
In-memory databases don't write LOBs to files any longer.
@changelog_1237_li
@changelog_1238_li
Self referencing constraints didn't restrict deleting rows that reference itself if there is another row that references it.
@changelog_1238_li
@changelog_1239_li
ResultSetMetaData.getColumnName now returns the alias name except for columns.
@changelog_1239_li
@changelog_1240_li
Temporary files are now deleted when the database is closed, even if they were not garbage collected so far.
@changelog_1240_h2
@changelog_1241_h2
Version 1.1.101 (2008-10-17)
@changelog_1241_li
@changelog_1242_li
Errors with code 42000 - 42999 are no longer written to the trace file by default.
@changelog_1242_li
@changelog_1243_li
Queries with more than 10 tables are now faster.
@changelog_1243_li
@changelog_1244_li
Opening a connection with AUTO_SERVER=TRUE is now fast when the database is already open in another process (less than 0.01 seconds instead of 2 seconds).
@changelog_1244_li
@changelog_1245_li
IF [NOT] EXISTS is supported for named constraints in ALTER TABLE ... ADD/DROP CONSTRAINT.
@changelog_1245_li
@changelog_1246_li
The error messages have been translated to Spanish by Dario V. Fassi. Thanks a lot!
@changelog_1246_li
@changelog_1247_li
Linked tables: the automatic connection sharing didn't work. Actually the system property h2.shareLinkedConnections was working in the opposite direction: it was disabled when set to true. Now it works as expected.
@changelog_1247_li
@changelog_1248_li
Opening large database is now faster.
@changelog_1248_li
@changelog_1249_li
New system property h2.socketConnectTimeout, the timeout in milliseconds to connect to a server. The default is 2000 (2 seconds).
@changelog_1249_li
@changelog_1250_li
The wrong parameters were bound to subqueries with parameters, specially when using IN(SELECT ...) and IN(...).
@changelog_1250_li
@changelog_1251_li
Unset parameters were not detected when the query was re-compiled.
@changelog_1251_li
@changelog_1252_li
New functions ISO_YEAR, ISO_WEEK, ISO_DAY_OF_WEEK. Thanks a lot to Robert Rathsack for implementing those!
@changelog_1252_li
@changelog_1253_li
The date functions DAYOFYEAR, DAYOFMONTH, DAYOFWEEK are now called DAY_OF_YEAR, DAY_OF_MONTH, DAY_OF_WEEK (the old names still work).
@changelog_1253_li
@changelog_1254_li
An out of memory error while deleting or updating many rows could result in a strange exception.
@changelog_1254_li
@changelog_1255_li
Linked tables: compatibility with MS SQL Server has been improved.
@changelog_1255_li
@changelog_1256_li
Renaming tables that have foreign keys with cascade didn't work correctly.
@changelog_1256_li
@changelog_1257_li
The auto-reconnect feature didn't work when using the auto-server mode. Fixed.
@changelog_1257_li
@changelog_1258_li
Fulltext search: new method FT_DROP_INDEX.
@changelog_1258_li
@changelog_1259_li
The optimization to group using an index didn't work in some cases in version 1.1 (see also system property h2.optimizeGroupSorted).
@changelog_1259_li
@changelog_1260_li
OSGi meta data is included in the manifest file. An OSGi BundleActivator is included: it loads the database driver when starting the bundle, and unloads it when stopping the bundle.
@changelog_1260_li
@changelog_1261_li
The default value for MAX_MEMORY_UNDO is now 50000.
@changelog_1261_li
@changelog_1262_li
For alias columns, ResultSetMetaData.getTableName() and getColumnName() now return the real table and column name in the default mode.
@changelog_1262_li
@changelog_1263_li
In SQL scripts created with SCRIPT TO, schemas are now only created if they don't exist yet.
@changelog_1263_li
@changelog_1264_li
After re-connecting to a database, the database event listener (if set) is informed about it.
@changelog_1264_li
@changelog_1265_li
Local temporary tables now support indexes. Thanks a lot to Matt Roy!
@changelog_1265_li
@changelog_1266_li
RUNSCRIPT no longer uses a temporary file.
@changelog_1266_li
@changelog_1267_li
New system table INFORMATION_SCHEMA.SESSION_STATE containing the SQL statements that make up the session state. The list currently contains variables (SET @..) and local temporary tables (without data).
@changelog_1267_li
@changelog_1268_li
After an automatic re-connect, part of the session state stays (the part that is stored in the SESSION_STATE table).
@changelog_1268_li
@changelog_1269_li
The build didn't work if the directory temp didn't exist before.
@changelog_1269_li
@changelog_1270_li
New system property h2.maxReconnect (default 3) to limit the number of re-connects for the same SQL statement (this is usually only important for SHUTDOWN).
@changelog_1270_li
@changelog_1271_li
WHERE .. IN (SELECT ...) could throw a NullPointerException.
@changelog_1271_li
@changelog_1272_li
Improved Glassfish / Toplink support in H2Platform thanks to Marcio Borges from Brazil. Thanks a lot!
@changelog_1272_h2
@changelog_1273_h2
Version 1.1.100 (2008-10-04)
@changelog_1273_li
@changelog_1274_li
In version 1.1, the following system properties are now enabled by default: h2.lobFilesInDirectories, h2.optimizeGroupSorted, h2.optimizeInJoin, h2.shareLinkedConnections
@changelog_1274_li
@changelog_1275_li
The H2 Console tool now works with the JDBC-ODBC bridge.
@changelog_1275_li
@changelog_1276_li
The H2 Console tool now supports command line options to start things separately.
@changelog_1276_li
@changelog_1277_li
Large objects did not work for in-memory databases in server mode in Linux.
@changelog_1277_li
@changelog_1278_li
Connections from a local address other than 'localhost' were not allowed if remote connections were disabled. This was always a problem, but only got visible in the last release because the server no longer connects to 'localhost' if networked.
@changelog_1278_li
@changelog_1279_li
The h2console.war can now be built using the Java build.
@changelog_1279_li
@changelog_1280_li
By default, databases are shared in the same process. For read-only databases this causes unnecessary synchronization, but safes memory. If you want that each connection opens its own database, append ;OPEN_NEW=TRUE to the database URL.
@changelog_1280_li
@changelog_1281_li
New auto-reconnect feature will cause the JDBC driver to reconnect to the database if the connection is lost. To enable, append ;AUTO_RECONNECT=TRUE to the database URL. This is specially helpful when using AUTO_SERVER. AUTO_SERVER automatically uses auto-reconnect.
@changelog_1281_li
@changelog_1282_li
CreateCluster: the property 'serverlist' is now called 'serverList'.
@changelog_1282_li
@changelog_1283_li
The ConvertTraceFile tool could not parse some files because the trace mechanism did not encode prepared statement parameters.
@changelog_1283_li
@changelog_1284_li
Databases names can now be one character long (the minimum size used to be 2 characters).
@changelog_1284_h2
@changelog_1285_h2
Version 1.0.79 (2008-09-26)
@changelog_1285_li
@changelog_1286_li
Linked tables that point to the same database can now share the connection within the same database. Access to the same connection is serialized. To enable this feature, set the system property h2.shareLinkedConnections to true.
@changelog_1286_li
@changelog_1287_li
Multiple processes can now access the same database without having to explicitly start the server. To do that, append ;AUTO_SERVER=TRUE to the database URL. In this case, the server is started automatically if the connection is in embedded mode, and the server mode is used if a server is running. If the process that opened the first connection is closed, the other client need to reconnect (there is no automatic re-connect so far). Remote connections are allowed, but only to this database.
@changelog_1287_li
@changelog_1288_li
The server tool now displays the correct IP address if networked.
@changelog_1288_li
@changelog_1289_li
Can now start a TCP server with port 0 (automatically select a port).
@changelog_1289_li
@changelog_1290_li
Result sets with just a unique index can now be updated (previously a primary key was required).
@changelog_1290_li
@changelog_1291_li
LINKED TABLE: the schema name can now be set. When multiple tables exist in different schema, and the schema name is not set, an exception is thrown.
@changelog_1291_li
@changelog_1292_li
LINKED TABLE: worked around a bug in Oracle with the CHAR data type.
@changelog_1292_li
@changelog_1293_li
Faster hash code calculation for large binary arrays.
@changelog_1293_li
@changelog_1294_li
Faster storage re-use algorithm thanks to Greg Dhuse from cleversafe.com.
@changelog_1294_li
@changelog_1295_li
The database supports the SHOW command for better MySQL and PostgreSQL compatibility.
@changelog_1295_li
@changelog_1296_li
The H2 Console now abbreviates large texts in results.
@changelog_1296_li
@changelog_1297_li
Multiple UNION queries could not be used in derived tables.
@changelog_1297_li
@changelog_1298_li
Linked tables can now be read-only.
@changelog_1298_li
@changelog_1299_li
Temporary linked tables are now supported.
@changelog_1299_li
@changelog_1300_li
It was possible to create tables in read-only databases.
@changelog_1300_li
@changelog_1301_li
SET SCHEMA_SEARCH_PATH is now documented.
@changelog_1301_li
@changelog_1302_li
SET SCHEMA did not work for views.
@changelog_1302_li
@changelog_1303_li
Row level locking for MVCC is now enabled. The exception 'Concurrent update in table ...' is still thrown, but only after the lock timeout.
@changelog_1303_li
@changelog_1304_li
The maximum log file size setting was ignored for large databases.
@changelog_1304_li
@changelog_1305_li
Multi-Version Concurrency (MVCC) may no longer be used when using the multi-threaded kernel feature (MULTI_THREADED). An exception is thrown when trying to connect with both settings. Additional synchronization is required before those features can be used together.
@changelog_1305_li
@changelog_1306_li
The data type JAVA_OBJECT could not be used in updatable result sets.
@changelog_1306_li
@changelog_1307_li
The system property h2.optimizeInJoin did not work correctly.
@changelog_1307_li
@changelog_1308_li
Conditions such as ID=? AND ID>? were slow.
@changelog_1308_h2
@changelog_1309_h2
Version 1.0.78 (2008-08-28)
@changelog_1309_li
@changelog_1310_li
The documentation no longer uses a frameset (except the Javadocs).
@changelog_1310_li
@changelog_1311_li
When using DB_CLOSE_DELAY, sometimes a NullPointerException is thrown when the database is opened almost at the same time as it is closed automatically. Thanks a lot to Dmitry Pekar for finding this!
@changelog_1311_li
@changelog_1312_li
Java methods with variable number of parameters can now be used (for Java 1.5 or newer).
@changelog_1312_li
@changelog_1313_li
The Japanese translation has been improved by Masahiro Ikemoto. Thanks a lot!
@changelog_1313_li
@changelog_1314_li
The H2 Console replaced an empty user name with a single space.
@changelog_1314_li
@changelog_1315_li
The build target 'build jarSmall' now includes the embedded database.
@changelog_1315_li
@changelog_1316_li
JdbcDataSource now keeps the password in a char array where possible.
@changelog_1316_li
@changelog_1317_li
ResultSet.absolute did not always work with large result sets.
@changelog_1317_li
@changelog_1318_li
Column aliases can now be used in GROUP BY and HAVING.
@changelog_1318_li
@changelog_1319_li
Jason Brittain has contributed MySQL date functions. Thanks a lot! They are not in the h2.jar file currently, but in src/tools/org/h2/mode/FunctionsMySQL.java. To install, add this class to the classpath and call FunctionsMySQL.register(conn) in the Java code.
@changelog_1319_h2
@changelog_1320_h2
Version 1.0.77 (2008-08-16)
@changelog_1320_li
@changelog_1321_li
JaQu is now using prepared statements and supports Date, Time, Timestamp.
@changelog_1321_li
@changelog_1322_li
When using remote in-memory databases, large LOB objects did not work.
@changelog_1322_li
@changelog_1323_li
Timestamp columns such as TIMESTAMP(6) were not compatible to other database.
@changelog_1323_li
@changelog_1324_li
Opening a large database was slow if there was a problem opening the previous time.
@changelog_1324_li
@changelog_1325_li
NOT IN(SELECT ...) was incorrect if the subquery returns no rows.
@changelog_1325_li
@changelog_1326_li
CREATE TABLE AS SELECT did not work correctly in the multi-version concurrency mode.
@changelog_1326_li
@changelog_1327_li
Support a comma before closing a list, as in: create table test(id int,)
@changelog_1327_li
@changelog_1328_li
MySQL compatibility: linked tables had lower case column names on some systems.
@changelog_1328_li
@changelog_1329_li
DB2 compatibility: the DB2 fetch-first-clause is supported.
@changelog_1329_li
@changelog_1330_li
Oracle compatibility: old style outer join syntax using (+) did work correctly sometimes.
@changelog_1330_li
@changelog_1331_li
ResultSet.setFetchSize is now supported.
@changelog_1331_li
@changelog_1332_li
It has been reported that when using Install4j on some Linux systems and enabling the 'pack200' option, the h2.jar becomes corrupted by the install process, causing application failure. A workaround is to add an empty file h2.jar.nopack next to the h2.jar file. The reason for this problem is not known.
@changelog_1332_h2
@changelog_1333_h2
Version 1.0.76 (2008-07-27)
@changelog_1333_li
@changelog_1334_li
The comment of a domain (user defined data type) is now used as the default column comment when creating a column with this domain.
@changelog_1334_li
@changelog_1335_li
Invalid database names are now detected and a better error message is thrown.
@changelog_1335_li
@changelog_1336_li
ResultSetMetaData.getColumnClassName now returns the correct class name for BLOB and CLOB.
@changelog_1336_li
@changelog_1337_li
Fixed the Oracle mode: Oracle allows multiple rows only where all columns of the unique index are NULL.
@changelog_1337_li
@changelog_1338_li
There is a problem with Hibernate when using Boolean columns. A patch for Hibernate has been submitted at http://opensource.atlassian.com/projects/hibernate/browse/HHH-3401
@changelog_1338_li
@changelog_1339_li
ORDER BY on tableName.columnName didn't work correctly if the column name was also used as an alias.
@changelog_1339_li
@changelog_1340_li
H2 Console: the progress display when opening a database has been improved.
@changelog_1340_li
@changelog_1341_li
The error message when the server doesn't start has been improved.
@changelog_1341_li
@changelog_1342_li
Key values can now be changed in updatable result sets.
@changelog_1342_li
@changelog_1343_li
Changes in updatable result sets are now visible even when resetting the result set.
@changelog_1343_li
@changelog_1344_li
Temporary files were sometimes deleted too late when executing large insert, update, or delete operations.
@changelog_1344_li
@changelog_1345_li
The database file was growing after deleting many rows, and after large update operations.
@download_1000_h1
...
...
@@ -7433,96 +7436,123 @@ The generated file <code>test.sql</code> will contain the SQL statements as well
Database Performance Tuning
@performance_1402_h3
Virus Scanners
Use a Modern JVM
@performance_1403_p
Some virus scanners scan files every time they are accessed. It is very important for performance that database files are not scanned for viruses. The database engine does never interprets the data stored in the files as programs, that means even if somebody would store a virus in a database file, this would be harmless (when the virus does not run, it cannot spread). Some virus scanners allow to exclude files by suffix. Make sure files ending with .db are not scanned.
Newer JVMs are faster. Upgrading to the latest version of your JVM can provide a "free" boost to performance. On the Windows platform, switching from the default Client JVM to the Server JVM using the <code>-server</code> command-line option improves performance at the cost of a slight increase in start-up time.
@performance_1404_h3
Using the Trace Options
Virus Scanners
@performance_1405_p
If the main performance hot spots are in the database engine, in many cases the performance can be optimized by creating additional indexes, or changing the schema. Sometimes the application does not directly generate the SQL statements, for example if an O/R mapping tool is used. To view the SQL statements and JDBC API calls, you can use the trace options. For more information, see <a href="features.html#trace_options">Using the Trace Options</a> .
Some virus scanners scan files every time they are accessed. It is very important for performance that database files are not scanned for viruses. The database engine does never interprets the data stored in the files as programs, that means even if somebody would store a virus in a database file, this would be harmless (when the virus does not run, it cannot spread). Some virus scanners allow to exclude files by suffix. Make sure files ending with .db are not scanned.
@performance_1406_h3
Index Usage
Using the Trace Options
@performance_1407_p
This database uses indexes to improve the performance of SELECT, UPDATE and DELETE statements. If a column is used in the WHERE clause of a query, and if an index exists on this column, then the index can be used. Multi-column indexes are used if all or the first columns of the index are used. Both equality lookup and range scans are supported. Indexes are used to order result sets, but only if the condition uses the same index or no index at all. The results are sorted in memory if required. Indexes are created automatically for primary key and unique constraints. Indexes are also created for foreign key constraints, if required. For other columns, indexes need to be created manually using the CREATE INDEX statement.
If the main performance hot spots are in the database engine, in many cases the performance can be optimized by creating additional indexes, or changing the schema. Sometimes the application does not directly generate the SQL statements, for example if an O/R mapping tool is used. To view the SQL statements and JDBC API calls, you can use the trace options. For more information, see <a href="features.html#trace_options">Using the Trace Options</a> .
@performance_1408_h3
Optimizer
Index Usage
@performance_1409_p
This database uses a cost based optimizer. For simple and queries and queries with medium complexity (less than 7 tables in the join), the expected cost (running time) of all possible plans is calculated, and the plan with the lowest cost is used. For more complex queries, the algorithm first tries all possible combinations for the first few tables, and the remaining tables added using a greedy algorithm (this works well for most joins). Afterwards a genetic algorithm is used to test at most 2000 distinct plans. Only left-deep plans are evaluated.
This database uses indexes to improve the performance of SELECT, UPDATE and DELETE statements. If a column is used in the WHERE clause of a query, and if an index exists on this column, then the index can be used. Multi-column indexes are used if all or the first columns of the index are used. Both equality lookup and range scans are supported. Indexes are used to order result sets, but only if the condition uses the same index or no index at all. The results are sorted in memory if required. Indexes are created automatically for primary key and unique constraints. Indexes are also created for foreign key constraints, if required. For other columns, indexes need to be created manually using the CREATE INDEX statement.
@performance_1410_h3
Expression Optimization
Optimizer
@performance_1411_p
After the statement is parsed, all expressions are simplified automatically if possible. Operations are evaluated only once if all parameters are constant. Functions are also optimized, but only if the function is constant (always returns the same result for the same parameter values). If the WHERE clause is always false, then the table is not accessed at all.
This database uses a cost based optimizer. For simple and queries and queries with medium complexity (less than 7 tables in the join), the expected cost (running time) of all possible plans is calculated, and the plan with the lowest cost is used. For more complex queries, the algorithm first tries all possible combinations for the first few tables, and the remaining tables added using a greedy algorithm (this works well for most joins). Afterwards a genetic algorithm is used to test at most 2000 distinct plans. Only left-deep plans are evaluated.
@performance_1412_h3
COUNT(*) Optimization
Expression Optimization
@performance_1413_p
If the query only counts all rows of a table, then the data is not accessed. However, this is only possible if no WHERE clause is used, that means it only works for queries of the form SELECT COUNT(*) FROM table.
After the statement is parsed, all expressions are simplified automatically if possible. Operations are evaluated only once if all parameters are constant. Functions are also optimized, but only if the function is constant (always returns the same result for the same parameter values). If the WHERE clause is always false, then the table is not accessed at all.
If the query only counts all rows of a table, then the data is not accessed. However, this is only possible if no WHERE clause is used, that means it only works for queries of the form SELECT COUNT(*) FROM table.
When executing a query, at most one index per joined table can be used. If the same table is joined multiple times, for each join only one index is used. Example: for the query SELECT * FROM TEST T1, TEST T2 WHERE T1.NAME='A' AND T2.ID=T1.ID, two index can be used, in this case the index on NAME for T1 and the index on ID for T2.
@performance_1416_p
@performance_1418_p
If a table has multiple indexes, sometimes more than one index could be used. Example: if there is a table TEST(ID, NAME, FIRSTNAME) and an index on each column, then two indexes could be used for the query SELECT * FROM TEST WHERE NAME='A' AND FIRSTNAME='B', the index on NAME or the index on FIRSTNAME. It is not possible to use both indexes at the same time. Which index is used depends on the selectivity of the column. The selectivity describes the 'uniqueness' of values in a column. A selectivity of 100 means each value appears only once, and a selectivity of 1 means the same value appears in many or most rows. For the query above, the index on NAME should be used if the table contains more distinct names than first names.
@performance_1417_p
@performance_1419_p
The SQL statement ANALYZE can be used to automatically estimate the selectivity of the columns in the tables. This command should be run from time to time to improve the query plans generated by the optimizer.
@performance_1418_h3
@performance_1420_h3
In-Memory (Hash) Indexes
@performance_1419_p
@performance_1421_p
Using in-memory indexes, specially in-memory hash indexes, can speed up queries and data manipulation.
@performance_1420_p
@performance_1422_p
In-memory indexes are automatically used for in-memory databases, but can also be created for persistent databases using <code>CREATE MEMORY TABLE</code> . In many cases, the rows itself will also be kept in-memory. Please note this may cause memory problems for large tables.
@performance_1421_p
@performance_1423_p
In-memory hash indexes are backed by a hash table and are usually faster than regular indexes. However, hash indexes only supports direct lookup (WHERE ID = ?) but not range scan (WHERE ID < ?). To use hash indexes, use HASH as in: <code>CREATE UNIQUE HASH INDEX</code> and <code>CREATE TABLE ...(ID INT PRIMARY KEY HASH,...)</code> .
@performance_1422_h3
@performance_1424_h3
Optimization Examples
@performance_1423_p
@performance_1425_p
See <code>src/test/org/h2/samples/optimizations.sql</code> for a few examples of queries that benefit from special optimizations built into the database.
@performance_1424_h3
@performance_1426_h3
Cache Size and Type
@performance_1425_p
@performance_1427_p
By default the cache size of H2 is quite small. Consider using a larger cache size, or enable the second level soft reference cache. See also <a href="features.html#cache_settings">Cache Settings</a> .
@performance_1426_h2
@performance_1428_h3
Data Types
@performance_1429_p
Each data type has different storage and performance characteristics:
@performance_1430_li
The DECIMAL/NUMERIC type is slower and requires more storage than the REAL and DOUBLE types.
@performance_1431_li
Text types are slower to read, write, and compare than numeric types and generally require more storage.
@performance_1432_li
See <a href="advanced.html#large_objects">Large Objects</a> for information on BINARY vs. BLOB and VARCHAR vs. CLOB performance.
@performance_1433_li
Parsing and formatting takes longer for the TIME, DATE, and TIMESTAMP types than the numeric types.
@performance_1434_li
SMALLINT/TINYINT/BOOLEAN are not significantly smaller or faster to work with than INTEGER in most modes.
@performance_1435_h2
Fast Database Import
@performance_1427_p
@performance_1436_p
To speed up large imports, consider using the following options temporarily:
@performance_1428_li
@performance_1437_li
SET CACHE_SIZE (a large cache is faster)
@performance_1429_li
@performance_1438_li
SET LOCK_MODE 0 (disable locking)
@performance_1430_li
@performance_1439_li
SET LOG 0 (disable the transaction log)
@performance_1431_li
@performance_1440_li
SET UNDO_LOG 0 (disable the session undo log)
@performance_1432_p
@performance_1441_p
These options can be set in the database URL: <code>jdbc:h2:~/test;CACHE_SIZE=65536;LOCK_MODE=0;LOG=0;UNDO_LOG=0</code> . Most of those options are not recommended for regular use, that means you need to reset them after use.
#JaQu: the plan is to support natural (pure Java) conditions such as (id == 1 && name.equals("Test")). A proof of concept decompiler is now included (it doesn't work yet).
#Better support GaeVFS (Google App Engine Virtual File System).
@changelog_1003_li
#Various bugfixes and improvements in the page store mechanism (still experimental).
#JaQu: the plan is to support natural (pure Java) conditions such as (id == 1 && name.equals("Test")). A proof of concept decompiler is now included (it doesn't work yet).
@changelog_1004_li
#PreparedStatement.setObject now converts a java.lang.Character to a string.
#Various bugfixes and improvements in the page store mechanism (still experimental).
@changelog_1005_li
#H2 Console: PierPaolo Ucchino has completed the Italian translation. Thanks a lot!
#PreparedStatement.setObject now converts a java.lang.Character to a string.
@changelog_1006_li
#Various tools now use Java 5 var-args, such as main the methods and SimpleResultSet.addRow.
#H2 Console: PierPaolo Ucchino has completed the Italian translation. Thanks a lot!
@changelog_1007_li
#H2 Console: indexes of tables of non-default schemas are now also listed.
#Various tools now use Java 5 var-args, such as main the methods and SimpleResultSet.addRow.
@changelog_1008_li
#Issue 111: Multi-version concurrency / duplicate primary key after rollback.
#H2 Console: indexes of tables of non-default schemas are now also listed.
@changelog_1009_li
#Issue 110: Multi-version concurrency / wrong exception is thrown.
#Issue 111: Multi-version concurrency / duplicate primary key after rollback.
@changelog_1010_li
#Parser: sequenceName.NEXTVAL and CURRVAL did not respect the schema search path.
#Issue 110: Multi-version concurrency / wrong exception is thrown.
@changelog_1011_li
#The following sequence could throw the exception "Row not found when trying to delete": start a transaction, insert many rows, delete many rows, rollback. The number of rows depends on the cache size.
#Parser: sequenceName.NEXTVAL and CURRVAL did not respect the schema search path.
@changelog_1012_li
#The stack trace of very common exceptions is no longer written to the .trace.db file by default.
#Issue 101: The following sequence could throw the exception "Row not found when trying to delete": start a transaction, insert many rows, delete many rows, rollback. The number of rows depends on the cache size.
@changelog_1013_li
#An optimization for OR is implemented, but disabled by default. Expressions of the type X=1 OR X=2 are converted to X IN(1, 2). To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver.
#The stack trace of very common exceptions is no longer written to the .trace.db file by default.
@changelog_1014_li
#An optimization for OR is implemented, but disabled by default. Expressions of the type X=1 OR X=2 are converted to X IN(1, 2). To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver.
@changelog_1015_li
#An optimization for IN(..) and IN(SELECT...) is implemented, but disabled by default. To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver. If enabled, this overrides h2.optimizeIn and h2.optimizeInJoin. Unlike now, this optimization will also speed up updates and deletes.
@changelog_1015_h2
@changelog_1016_h2
#Version 1.1.117 (2009-08-09)
@changelog_1016_li
@changelog_1017_li
#New committer: Sam Van Oort has been contributing to H2 since quite some time in many ways (on the mailing list, documentation, and in the form of patches). He is now a committer.
@changelog_1017_li
@changelog_1018_li
#JaQu: the order of the fields in the database no longer needs to match the order in the database.
@changelog_1018_li
@changelog_1019_li
#Issue 103: MVCC: the setting MAX_MEMORY_UNDO can currently not be supported when using multi-version concurrency, that means the complete undo log must fit in memory.
@changelog_1019_li
@changelog_1020_li
#LIKE: the escape mechanism can now be disable using ESCAPE ''. The default escape character can be changed using the system property h2.defaultEscape. The default is still '\' (as in MySQL and PostgreSQL).
@changelog_1020_li
@changelog_1021_li
#Views using functions were not re-evaluated when necessary.
@changelog_1021_li
@changelog_1022_li
#Improved MySQL compatibility for SHOW COLUMNS.
@changelog_1022_li
@changelog_1023_li
#Improved PostgreSQL compatibility for timestamp literals with timezone.
@changelog_1023_li
@changelog_1024_li
#Sergi Vladykin translated the error messages to Russian. Thanks a lot!
@changelog_1024_li
@changelog_1025_li
#Support for Java 6 DatabaseMetaData.getTables, getColumns, getProcedures, and getProcedureColumns.
@changelog_1025_li
@changelog_1026_li
#Issue 101: Rollback of a large transaction (more than 100000 rows) could fail.
@changelog_1026_li
@changelog_1027_li
#Various bugfixes and improvements in the page store mechanism (still experimental).
@changelog_1027_li
@changelog_1028_li
#The functions LENGTH, OCTET_LENGTH, and BIT_LENGTH now return BIGINT.
@changelog_1028_li
@changelog_1029_li
#Data types CLOB and BLOB: the maximum precision was Integer.MAX_VALUE, it is now Long.MAX_VALUE.
@changelog_1029_li
@changelog_1030_li
#Multi-threaded kernel: creating and dropping temporary database objects and the potentially free pages list was not correctly synchronized. Thanks a lot to Eric Faulhaber for the test case and patch!
@changelog_1030_li
@changelog_1031_li
#Parsing SQL script files is now faster.
@changelog_1031_li
@changelog_1032_li
#CSV reading is now faster.
@changelog_1032_li
@changelog_1033_li
#SimpleResultSet.newInstance(SimpleRowSource rs) did not work.
@changelog_1033_h2
@changelog_1034_h2
#Version 1.1.116 (2009-07-18)
@changelog_1034_li
@changelog_1035_li
#Server-less multi-connection mode: more bugs are fixed.
@changelog_1035_li
@changelog_1036_li
#The built-in help (INFORMATION_SCHEMA.HELP) is smaller, shrinking the jar file size a bit.
@changelog_1036_li
@changelog_1037_li
#H2 Console: column of tables of non-default schemas are now also listed, except for schemas starting with 'INFO'.
@changelog_1037_li
@changelog_1038_li
#ALTER TABLE: removing an auto-increment or identity column didn't remove the sequence.
@changelog_1038_li
@changelog_1039_li
#Creating indexes is now a bit faster.
@changelog_1039_li
@changelog_1040_li
#PG Server: new system property h2.pgClientEncoding to explicitly set the encoding for clients that don't send the encoding (the default encoding is UTF-8). Thanks a lot to Sergi Vladykin for the patch!
@changelog_1040_li
@changelog_1041_li
#PG Server: improved compatibility by using the type ids of the PostgreSQL driver. Thanks a lot to Sergi Vladykin for the patch!
@changelog_1041_li
@changelog_1042_li
#H2 Console: Oracle system tables are no longer listed, improving performance.
@changelog_1042_li
@changelog_1043_li
#Result sets are now read-only except if the statement or prepared statement was created with the concurrency ResultSet.CONCUR_UPDATABLE. This change is required because the old behavior (all result set are updatable) violated the JDBC spec. For backward compatibility, use the system property h2.defaultResultSetConcurrency.
@changelog_1043_li
@changelog_1044_li
#New system property h2.defaultResultSetConcurrency to change the default result set concurrency.
@changelog_1044_li
@changelog_1045_li
#JDBC: using an invalid result set type or concurrency now throws an exception.
@changelog_1045_li
@changelog_1046_li
#If a pooled connection was not closed but garbage collected, a NullPointerException could occur.
@changelog_1046_li
@changelog_1047_li
#Fulltext search: a NullPointerException was thrown when updating a value that was NULL previously.
@changelog_1047_li
@changelog_1048_li
#The Recover tool did not work with .data.db files of the wrong size.
@changelog_1048_li
@changelog_1049_li
#Triggers: if there was an exception when initializing a trigger, this exception could be hidden, and in some cases (specially when using the Lucene fulltext index mechanism) a NullPointerException was thrown later on. Now the exception that occurred on init is thrown when changing data.
@changelog_1049_li
@changelog_1050_li
#The soft-references cache (CACHE_TYPE=SOFT_LRU) could throw a NullPointerException.
@changelog_1050_li
@changelog_1051_li
#To enable the new page store mechanism, append ;PAGE_STORE=TRUE to the database URL. or set the system property h2.pageStore to true. This mechanism is still experimental, and the file format will change, but it is quite stable now.
@changelog_1051_h2
@changelog_1052_h2
#Version 1.1.115 (2009-06-21)
@changelog_1052_li
@changelog_1053_li
#The new storage mechanism is now alpha quality. To try it out, set the system property "h2.pageStore" to "true" (java -Dh2.pageStore=true). There are still bugs to be found and fixed, for example inserting many rows references a lot of main memory. Performance is currently about the same as with the regular storage mechanism, but the database file size is smaller. The file format is not stable yet.
@changelog_1053_li
@changelog_1054_li
#ALTER TABLE could throw an exception "object already exists" in some cases.
@changelog_1054_li
@changelog_1055_li
#Views: in some situations, an ArrayIndexOutOfBoundsException was thrown when using the same view concurrently.
@changelog_1055_li
@changelog_1056_li
#java.util.UUID is now supported in PreparedStatement.setObject and user defined Java functions. ResultSet.getObject() returns a java.util.UUID when using the UUID data type.
@changelog_1056_li
@changelog_1057_li
#H2 Console: the language was reset to the browser language when disconnecting.
@changelog_1057_li
@changelog_1058_li
#H2 Console: improved Polish translation.
@changelog_1058_li
@changelog_1059_li
#Server-less multi-connection mode: more bugs are fixed.
@changelog_1059_li
@changelog_1060_li
#The download page now included the SHA1 checksums.
@changelog_1060_li
@changelog_1061_li
#Shell tool: the file encoding workaround is now documented if you run java org.h2.tools.Shell -?.
@changelog_1061_li
@changelog_1062_li
#The RunScript tool and SQL statement did not work with the compression method LZF.
@changelog_1062_li
@changelog_1063_li
#Fulltext search: searching for NULL or an empty string threw an exception.
@changelog_1063_li
@changelog_1064_li
#Lucene fulltext search: FTL_DROP_ALL did not drop the triggers.
@changelog_1064_li
@changelog_1065_li
#Backup: if the database contained CLOB or BLOB data, the backup included a file entry for the LOB directory. This caused the restore to fail.
@changelog_1065_li
@changelog_1066_li
#Data types: LONG is now an alias for BIGINT.
@changelog_1066_h2
@changelog_1067_h2
#Version 1.1.114 (2009-06-01)
@changelog_1067_li
@changelog_1068_li
#ResultSetMetaData.getColumnClassName returned the wrong class for CLOB and BLOB columns.
@changelog_1068_li
@changelog_1069_li
#Fulltext search: data is no longer deleted and re-inserted if the indexed columns didn't change.
@changelog_1069_li
@changelog_1070_li
#In some situations, an ArrayIndexOutOfBoundsException was thrown when adding rows. This was caused by a bug in the b-tree code.
@changelog_1070_li
@changelog_1071_li
#Microsoft Windows Vista: when using the the installer, Vista wrote "This program may not have installed correctly." This message should no longer appear (in the h2.nsi file, the line 'RequestExecutionLevel highest' was added).
@changelog_1071_li
@changelog_1072_li
#The Recover tool did not always work when the database contains referential integrity constraints.
@changelog_1072_li
@changelog_1073_li
#Java 1.5 is now required to run H2. If required, Retrotranslator can be used to create a Java 1.4 version (http://retrotranslator.sourceforge.net/).
@changelog_1073_h2
@changelog_1074_h2
#Version 1.1.113 (2009-05-21)
@changelog_1074_li
@changelog_1075_li
#Shell tool: the built-in commands EXIT, HELP, ?, LIST, and so on didn't work with a semicolon at the end.
@changelog_1075_li
@changelog_1076_li
#JDK 1.5 is now required to build the jar file. However it is still possible to create a jar file for Java 1.4. For details, see buildRelease.sh and buildRelease.bat. As an alternative, compile using JDK 1.5 or 1.6 and use Retrotranslator to create a Java 1.4 version (http://retrotranslator.sourceforge.net/).
@changelog_1076_li
@changelog_1077_li
#When deleting or updating many rows in a table, the space in the index file was not re-used in the default mode (persistent database, b-tree index, LOG=1). This caused the index file to grow over time. Workarounds were to delete and re-created the index file, alter the table (add a remove a column), or append ;LOG=2 to the database URL. To disable the change, set the system property h2.reuseSpaceBtreeIndex to false.
@changelog_1077_li
@changelog_1078_li
#Identifiers with a digit and then a dollar sign didn't work. Example: A1$B.
@changelog_1078_li
@changelog_1079_li
#MS SQL Server compatibility: support for linked tables with NVARCHAR, NCHAR, NCLOB, and LONGNVARCHAR.
@changelog_1079_li
@changelog_1080_li
#Android: workaround for a problem when using read-only databases in zip files (skip seems to be implemented incorrectly on the Android system).
@changelog_1080_li
@changelog_1081_li
#Calling execute() or prepareStatement() with null as the SQL statement now throws an exception.
@changelog_1081_li
@changelog_1082_li
#Benchmark: the number of executed statements was incorrect. The H2 database was loaded at the beginning of the test to collect results, now it is loaded at the very end. Thanks to Fred Toussi from HSQLDB for reporting those problems. However the changed do not affect the relative performance.
@changelog_1082_li
@changelog_1083_li
#H2 Console: command line settings are no longer stored in the properties file. They are now only used for the current process, except if they are explicitly saved.
@changelog_1083_li
@changelog_1084_li
#Cache: support for a second level soft-references cache. To enable it, append ;CACHE_TYPE=SOFT_LRU (or SOFT_TQ) to the database URL, or set the system property h2.cacheTypeDefault to "SOFT_LRU" / "SOFT_TQ". Enabling the second level cache reduces performance for small databases, but speeds up large databases. It makes sense to use it if the available memory size is unknown. Thanks a lot to Jan Kotek!
@changelog_1084_h2
@changelog_1085_h2
#Version 1.1.112 (2009-05-01)
@changelog_1085_li
@changelog_1086_li
#JdbcPreparedStatement.toString() could throw a NullPointerException.
#Connection pool: the default login timeout is now 5 minutes.
@changelog_1088_li
@changelog_1089_li
#After truncating tables, opening large databases could become slow because indexes were always re-built unnecessarily when opening.
@changelog_1089_li
@changelog_1090_li
#More bugs in the server-less multi-connection mode have been fixed: Sometimes parameters of prepared statements were lost when a reconnecting. Concurrent read operations were slow. To improve performance, executeQuery(..) must be used for queries (execute(..) switches to the write mode, which is slow).
@changelog_1090_li
@changelog_1091_li
#GROUP BY queries with a self-join (join to the same table) that were grouped by columns with indexes returned the wrong result in some cases.
@changelog_1091_li
@changelog_1092_li
#Improved error message when the .lock.db file modification time is in the future.
@changelog_1092_li
@changelog_1093_li
#The MERGE statement now returns 0 as the generated key if the row was updated.
@changelog_1093_li
@changelog_1094_li
#Running code coverage is now automated.
@changelog_1094_li
@changelog_1095_li
#A file system implementation can now be registered using FileSystem.register.
@changelog_1095_li
@changelog_1096_li
#The database file system is no longer included in the jar file, it moved to the test section.
@changelog_1096_h2
@changelog_1097_h2
#Version 1.1.111 (2009-04-10)
@changelog_1097_li
@changelog_1098_li
#In-memory databases can now run inside the Google App Engine.
@changelog_1098_li
@changelog_1099_li
#Queries that are ordered by an indexed column returned no rows in certain cases (if all rows were deleted from the table previously, and there is a low number of rows in the table, and when not using other conditions, and when using the default b tree index).
@changelog_1099_li
@changelog_1100_li
#The wrong exception was thrown when using unquoted text for the SQL statements COMMENT, ALTER USER, and SET PASSWORD.
@changelog_1100_li
@changelog_1101_li
#The built-in connection pool did not roll back transactions and enable autocommit enabled after closing a connection.
@changelog_1101_li
@changelog_1102_li
#Sometimes a StackOverflow occurred when checking for deadlock. See also http://code.google.com/p/h2database/issues/detail?id=61
@changelog_1102_li
@changelog_1103_li
#The Shell tool no longer truncates results with only one column, and displays a message if data was truncated.
@changelog_1103_h2
@changelog_1104_h2
#Version 1.1.110 (2009-04-03)
@changelog_1104_li
@changelog_1105_li
#Support for not persistent in-memory tables in regular (persistent) databases using CREATE MEMORY TABLE(..) NOT PERSISTENT. Thanks a lot to Sergi Vladykin for the patch!
@changelog_1105_li
@changelog_1106_li
#The H2 Console trimmed the password (removed leading and trailing spaces). This is no longer the case, to support encrypted H2 database with an empty user password.
@changelog_1106_li
@changelog_1107_li
#The data type of a SUBSTRING method was wrong.
@changelog_1107_li
@changelog_1108_li
#ResultSet.findColumn and get methods with column label parameters now also check for matching column names (like most databases except MySQL).
@changelog_1108_li
@changelog_1109_li
#H2 Console: the browser system property now supports a list of arguments. Example: java -Dh2.browser="open,-a,Safari,%url" ...
@changelog_1109_li
@changelog_1110_li
#Improved Javadoc navigation (similar to Scaladoc).
@changelog_1110_li
@changelog_1111_li
#H2 Console: auto-complete of identifiers did not work correctly for H2 databases in MySQL mode.
@changelog_1111_li
@changelog_1112_li
#DISTINCT and GROUP BY on a CLOB column was broken.
@changelog_1112_li
@changelog_1113_li
#The FTP server moved to the tools section and is no longer included in the h2*.jar file.
@changelog_1113_li
@changelog_1114_li
#Improved error message for unsupported features: now the message says what exactly is not supported.
@changelog_1114_li
@changelog_1115_li
#Improved OSGi support.
@changelog_1115_li
@changelog_1116_li
#Some internal caches did not use the LRU mechanism. Fixed (LOB file list, optimizer cost cache, trace system, view indexes, collection keys, compressed in-memory file system).
@changelog_1116_li
@changelog_1117_li
#The API of the tools changed a bit (each tool now returns an exit code).
@changelog_1117_li
@changelog_1118_li
#Command line help of the tools now match the javadocs. The build converts the javadocs to a resource that is read by the tool at runtime. This should not have an effect on using the database, but it reduces duplicate and out-of-sync documentation.
@changelog_1118_li
@changelog_1119_li
#CREATE TABLE: improved compatibility (support for UNIQUE NOT NULL).
@changelog_1119_li
@changelog_1120_li
#DatabaseMetaData.getSQLKeywords now returns the correct list.
@changelog_1120_li
@changelog_1121_li
#Deterministic user defined functions did not work when the parameter was a column. Fixed.
@changelog_1121_li
@changelog_1122_li
#JdbcConnectionPool.setLoginTimeout with 0 now uses the default timeout.
@changelog_1122_li
@changelog_1123_li
#Creating a JdbcConnectionPool has been simplified a bit.
@changelog_1123_li
@changelog_1124_li
#The built-in connection pool did not re-use connections. Getting a connection using the built-in JdbcConnectionPool is now about 70 times faster than opening connections using DriverManager.getConnection.
@changelog_1124_li
@changelog_1125_li
#More bugs in the server-less multi-connection mode have been fixed: If a process terminated while writing, other open connections were blocked. If two processes were writing to the database, sometimes the database was corrupt after closing.
@changelog_1125_li
@changelog_1126_li
#Linked tables to SQLite database can now be created.
@changelog_1126_li
@changelog_1127_li
#Nested IN(IN(...)) didn't work.
@changelog_1127_li
@changelog_1128_li
#NIO storage: the nio: prefix was using memory mapped files instead of FileChannel.
@changelog_1128_h2
@changelog_1129_h2
#Version 1.1.109 (2009-03-14)
@changelog_1129_li
@changelog_1130_li
#The optimization for IN(...) is now only used if comparing a column with an index.
@changelog_1130_li
@changelog_1131_li
#User defined functions can now be deterministic (see CREATE ALIAS documentation).
@changelog_1131_li
@changelog_1132_li
#Multiple nested queries in the FROM clause with parameters did not always work.
@changelog_1132_li
@changelog_1133_li
#When converting CLOB to BINARY, each character resulted in one byte. Now, the text is parsed as a hex as when converting VARCHAR.
@changelog_1133_li
@changelog_1134_li
#New experimental NIO storage mechanism with both FileChannel and memory mapped files. To use it, use the file name prefix nio: or nioMapped: as in jdbc:h2:nio:~/test. So far it looks like NIO storage is faster on Mac OS but slower on some Windows systems. Thanks a lot to Jan Kotek for the patch!
@changelog_1134_li
@changelog_1135_li
#The functions BITOR, BITAND, BITXOR, and MOD now accept and return BIGINT instead of INT.
@changelog_1135_li
@changelog_1136_li
#Could not use the same linked table multiple times in the same query.
@changelog_1136_li
@changelog_1137_li
#Bugs in the server-less multi-connection mode have been fixed.
@changelog_1137_li
@changelog_1138_li
#Column names could not be named "UNIQUE" (with the quotes).
@changelog_1138_li
@changelog_1139_li
#New system function TRANSACTION_ID() to get the current transaction identifier for a session.
@changelog_1139_h2
@changelog_1140_h2
#Version 1.1.108 (2009-02-28)
@changelog_1140_li
@changelog_1141_li
#When the shutdown hook closed the database, the last log file was deleted too early. This could cause uncommitted changes to be persisted. In some cases, this could cause data corruption.
@changelog_1141_li
@changelog_1142_li
#JdbcConnectionPool: it was possible to set a negative connection pool size.
@changelog_1142_li
@changelog_1143_li
#Fulltext search did not support table names with a backslash.
@changelog_1143_li
@changelog_1144_li
#The internal IntArray class did not work correctly when initialized with a zero length array.
@changelog_1144_li
@changelog_1145_li
#The H2 Console web application (war file) did only support ASCII characters. Now UTF-8 is supported.
@changelog_1145_li
@changelog_1146_li
#DATEADD does no longer require that the argument is a timestamp.
@changelog_1146_li
@changelog_1147_li
#The database file locking mechanism didn't work correctly on Mac OS.
@changelog_1147_li
@changelog_1148_li
#Some built-in functions reported the wrong precision, scale, and display size.
@changelog_1148_li
@changelog_1149_li
#MySQL compatibility for CREATE TABLE is improved (UNSIGNED, KEY).
@changelog_1149_li
@changelog_1150_li
#Recovery did not work if there were more than 255 lobs stored as files.
@changelog_1150_li
@changelog_1151_li
#New experimental mode to support multiple read-write connections without starting a server. To enable this mode, append ;FILE_LOCK=SERIALIZED;OPEN_NEW=TRUE to the database URL. Don't expect high performance when multiple concurrent writers.
@changelog_1151_li
@changelog_1152_li
#In a web application, the database classes are not unloaded if a connection is open. This may cause out of memory when re-deploying a web application. The DbStarter is changed to close all connections to the configured database (by executing SHUTDOWN).
@changelog_1152_li
@changelog_1153_li
#The WebServlet did not close the database when un-deploying the web application.
@changelog_1153_li
@changelog_1154_li
#The exception message of failed INSERT or MERGE statements now includes all values and the row number.
@changelog_1154_li
@changelog_1155_li
#If opening a database failed with an out of memory exception, some files were not closed.
@changelog_1155_li
@changelog_1156_li
#Optimizer: the expected runtime calculation was incorrect. The fixed calculation should give slightly better query plans when using many joins.
@changelog_1156_li
@changelog_1157_li
#Improved exception message when connecting to a just started server fails.
@changelog_1157_li
@changelog_1158_li
#Connection.isValid is a bit faster.
@changelog_1158_li
@changelog_1159_li
#H2 Console: the autocomplete feature has been improved a bit. It can now better parse conditions.
@changelog_1159_li
@changelog_1160_li
#When restarting a web application in Tomcat, an exception was thrown sometimes. In most cases this was a NullPointerException. A workaround in H2 has been implemented. The root cause of the problem is now documented in the FAQ: Tomcat sets all static fields (final or non-final) to null when unloading a web application. A workaround is to put the h2.jar in the lib directory, or set the system property org.apache.catalina.loader.WebappClassLoader.ENABLE_CLEAR_REFERENCES to false.
@changelog_1160_h2
@changelog_1161_h2
#Version 1.1.107 (2009-01-24)
@changelog_1161_li
@changelog_1162_li
#Some DatabaseMetaData operations did not work for non-admin users for versions 1.1.x.
@changelog_1162_li
@changelog_1163_li
#The MySQL compatibility extension fromUnixTime now used the English locale.
@changelog_1163_li
@changelog_1164_li
#When using LOG=2 and repeatedly updating the last row rows of a table, the index file grew quickly.
@changelog_1164_li
@changelog_1165_li
#In versions 1.1.105 and 1.1.106, encrypted script files of earlier versions could not be processed. This is now again possible. The problem was that such script files were stored in a special format (STORAGE=TEXT) but support for this format was removed in version 1.1.105.
@changelog_1165_li
@changelog_1166_li
#Enabling the trace mechanism by creating a specially named file is no longer supported.
@changelog_1166_h2
@changelog_1167_h2
#Version 1.1.106 (2009-01-04)
@changelog_1167_li
@changelog_1168_li
#Statement.setQueryTimeout did not work correctly for some statements.
@changelog_1168_li
@changelog_1169_li
#CREATE DOMAIN: built-in data types can now only be changed if no tables exist.
@changelog_1169_li
@changelog_1170_li
#Linked tables: a workaround for Oracle DATE columns has been implemented.
@changelog_1170_li
@changelog_1171_li
#DatabaseMetaData.getPrimaryKeys: the column PK_NAME now contains the constraint name instead of the index name (compatibility for PostgreSQL and Derby).
@changelog_1171_li
@changelog_1172_li
#Using IN(..) inside a IN(SELECT..) did not always work.
@changelog_1172_li
@changelog_1173_li
#Views with IN(..) that used a view itself did not work.
@changelog_1173_li
@changelog_1174_li
#Union queries with LIMIT or ORDER BY that are used in a view or subquery did not work.
@changelog_1174_li
@changelog_1175_li
#The license change a bit: so far the license was modified to say 'Swiss law'. This is now changed back to the original 'US law'. This was requested by a user, and I don't see a problem.
@changelog_1175_li
@changelog_1176_li
#Constraints for local temporary tables now session scoped. So far they were global. Thanks a lot to Eric Faulhaber for finding and fixing this problem!
@changelog_1176_li
@changelog_1177_li
#When using the auto-server mode, and if the lock file was modified in the future, the wrong exception was thrown ('Connection is broken' instead of 'Error opening database: lock file modified in the future').
@changelog_1177_h2
@changelog_1178_h2
#Version 1.1.105 (2008-12-19)
@changelog_1178_li
@changelog_1179_li
#The setting STORAGE=TEXT is no longer supported.
@changelog_1179_li
@changelog_1180_li
#Deleting a database using the tool DeleteDbFiles deleted LOB files of other databases in the same directory.
@changelog_1180_li
@changelog_1181_li
#When used in a subquery, LIKE and IN(..) did not work correctly sometimes.
@changelog_1181_li
@changelog_1182_li
#The fulltext search documentation has been improved.
@changelog_1182_li
@changelog_1183_li
#ARRAY_GET returned the wrong data type (ARRAY). Now it returns VARCHAR.
@changelog_1183_li
@changelog_1184_li
#Natural join: the joined columns are not repeated any more when using SELECT *.
@changelog_1184_li
@changelog_1185_li
#User defined aggregate functions: the method getType expected internal data types instead of SQL types.
@changelog_1185_li
@changelog_1186_li
#User defined aggregate functions did not work if there was no group by expression.
@changelog_1186_li
@changelog_1187_li
#MySQL compatibility: support for := assignment as in @sum:=@sum+x
@changelog_1187_li
@changelog_1188_li
#INSERT INTO TEST(SELECT * FROM TEST) is now supported.
@changelog_1188_li
@changelog_1189_li
#Each session threw an invisible exception when garbage collected.
@changelog_1189_li
@changelog_1190_li
#Foreign key constraints that refer to a quoted column did not work.
@changelog_1190_li
@changelog_1191_li
#New meta data column INFORMATION_SCHEMA.TABLES.LAST_MODIFICATION to get the table modification counter.
@changelog_1191_li
@changelog_1192_li
#Shell: line comments didn't work correctly.
@changelog_1192_li
@changelog_1193_li
#H2 Console: columns are now listed for up to 500 tables instead of 100.
@changelog_1193_li
@changelog_1194_li
#H2 Console: Cmd+Enter executes the current statement, Alt+Space for autocomplete.
@changelog_1194_li
@changelog_1195_li
#JaQu: the maximum length of a column can now be defined using maxLength. For an example, see Product.java (maxLength(category, 255)).
@changelog_1195_li
@changelog_1196_li
#R&\#305;dvan A&\#287;ar has completed the Turkish translation of the H2 Console. Thanks a lot!
@changelog_1196_h2
@changelog_1197_h2
#Version 1.1.104 (2008-11-28)
@changelog_1197_li
@changelog_1198_li
#If a query that was used like a table contained group by and was ordered by an expression that is not in the column list, an exception was thrown.
@changelog_1198_li
@changelog_1199_li
#JaQu: tables are now auto-created when running a query.
@changelog_1199_li
@changelog_1200_li
#The optimizer had problems with function tables (for example CSVREAD and FTL_SEARCH). A new system property h2.estimatedFunctionTableRows (default 1000) defines how many rows can be expected in the table.
@changelog_1200_li
@changelog_1201_li
#The function SUM could overflow when using large values. It returns now a data type that is safe.
@changelog_1201_li
@changelog_1202_li
#The function AVG could overflow when using large values. Fixed.
@changelog_1202_li
@changelog_1203_li
#The emergency reserve file has been removed. It didn't provide an appropriate solution for the problem. It is still possible for an application to detect and deal with the low disk space problem (deleting temporary files for example) using DatabaseEventListener.diskSpaceIsLow, but this method is now always called with stillAvailable=0.
@changelog_1203_li
@changelog_1204_li
#Build: JAVA_HOME is now automatically detected on Mac OS X.
@changelog_1204_li
@changelog_1205_li
#Testing for local connections was very slow on some systems.
@changelog_1205_li
@changelog_1206_li
#The cache memory usage calculation is more conservative.
@changelog_1206_li
@changelog_1207_li
#Allocating space got slower and slower the larger the database.
@changelog_1207_li
@changelog_1208_li
#ALTER TABLE ALTER COLUMN could throw the wrong exception in the last version (Table not found).
@changelog_1208_li
@changelog_1209_li
#Updatable result sets: the key columns can now be updated.
@changelog_1209_li
@changelog_1210_li
#The H2DatabaseProvider for ActiveObjects is now included in the tools section.
@changelog_1210_li
@changelog_1211_li
#The H2Platform for Oracle Toplink Essential has been improved a bit.
@changelog_1211_li
@changelog_1212_li
#The Windows service to start H2 didn't work in version 1.1.
@changelog_1212_li
@changelog_1213_li
#File systems with a maximum file size (for example FAT) are now supported using the file prefix 'split:'. In this case the files are split in parts of 1 GB. Example URL: jdbc:h2:split:~/db/test. If you want to split into parts of 1 MB, use jdbc:h2:split:20:~/db/test (the part size is 1 << x, the default is 30 meaning 1 GB).
@changelog_1213_li
@changelog_1214_li
#The database now tries to detect if the classloader or virtual machine has almost shut down by checking if static final variables are set to null. This should help reduce exceptions when stopping the web application.
@changelog_1214_li
@changelog_1215_li
#Compatibility for MS SQL Server DATEDIFF(YYYY, .., ..)
@changelog_1215_li
@changelog_1216_li
#ResultSet.getObject for CLOB or BLOB will return a java.sql.Clob / java.sql.Blob object instead of a java.io.Reader / java.io.InputStream as in version 1.0. This behavior can be changed using the system property h2.returnLobObjects (true by default for version 1.1).
@changelog_1216_li
@changelog_1217_li
#The interface CloseListener has a new method 'remove' that is called when the trigger is dropped.
@changelog_1217_li
@changelog_1218_li
#Fulltext search: there was a memory leak when creating and dropping fulltext indexes in a loop.
@changelog_1218_h2
@changelog_1219_h2
#Version 1.1.103 (2008-11-07)
@changelog_1219_li
#Could not order by a formula when the formula was in the group by list but not in the select list.
@changelog_1220_li
#Date values that match the daylight saving time end were not allowed in times zones were the daylight saving time ends at midnight, for years larger than 2037. Example: timezone Brasilia, date 2042-10-12. This is a problem of Java, however a workaround is implemented in H2 that solves most problems (except the problems of java.util.Date itself).
#Could not order by a formula when the formula was in the group by list but not in the select list.
@changelog_1221_li
#ALTER TABLE used a lot of memory when using multi-version concurrency.
#Date values that match the daylight saving time end were not allowed in times zones were the daylight saving time ends at midnight, for years larger than 2037. Example: timezone Brasilia, date 2042-10-12. This is a problem of Java, however a workaround is implemented in H2 that solves most problems (except the problems of java.util.Date itself).
@changelog_1222_li
#Referential integrity for in-memory databases didn't work in some cases in version 1.1.102.
#ALTER TABLE used a lot of memory when using multi-version concurrency.
@changelog_1223_li
#New column INFORMATION_SCHEMA.COLUMNS.SEQUENCE_NAME to get the name of the sequence for auto-increment columns.
#Referential integrity for in-memory databases didn't work in some cases in version 1.1.102.
@changelog_1224_li
#Aliases for built-in data types (such as MEDIUMBLOB which is an alias for BLOB) can now be re-mapped to another data type using CREATE DOMAIN. However main built-in data types (such as INTEGER) can not be re-mapped.
#New column INFORMATION_SCHEMA.COLUMNS.SEQUENCE_NAME to get the name of the sequence for auto-increment columns.
@changelog_1225_li
#The Japanese translation has been completed by Masahiro Ikemoto. Thanks a lot!
#Aliases for built-in data types (such as MEDIUMBLOB which is an alias for BLOB) can now be re-mapped to another data type using CREATE DOMAIN. However main built-in data types (such as INTEGER) can not be re-mapped.
@changelog_1226_li
#Improved PostgreSQL compatibility for NEXTVAL and CURRVAL.
#The Japanese translation has been completed by Masahiro Ikemoto. Thanks a lot!
@changelog_1227_li
#Less heap memory is needed when multiple databases are open at the same time: the memory reserve (used to rollback after out of memory) is now global and no longer allocated for each database separately.
#Improved PostgreSQL compatibility for NEXTVAL and CURRVAL.
@changelog_1228_li
#New system property h2.browser to set the browser to use.
#Less heap memory is needed when multiple databases are open at the same time: the memory reserve (used to rollback after out of memory) is now global and no longer allocated for each database separately.
@changelog_1229_li
#New system property h2.browser to set the browser to use.
@changelog_1230_li
#To start the browser, java.awt.Desktop.browse is now used if available.
@changelog_1230_h2
@changelog_1231_h2
#Version 1.1.102 (2008-10-24)
@changelog_1231_li
@changelog_1232_li
#The French translation of the H2 Console has been improved by Olivier Parent. Thanks a lot!
@changelog_1232_li
@changelog_1233_li
#There was a memory leak when creating and dropping tables and indexes in a loop (persistent database only).
@changelog_1233_li
@changelog_1234_li
#SET LOG 2 was not effective if executed after opening the database.
@changelog_1234_li
@changelog_1235_li
#Translating the H2 Console is now simpler.
@changelog_1235_li
@changelog_1236_li
#Common exception (error code 23*) are no longer written to the .trace.db file by default.
@changelog_1236_li
@changelog_1237_li
#In-memory databases don't write LOBs to files any longer.
@changelog_1237_li
@changelog_1238_li
#Self referencing constraints didn't restrict deleting rows that reference itself if there is another row that references it.
@changelog_1238_li
@changelog_1239_li
#ResultSetMetaData.getColumnName now returns the alias name except for columns.
@changelog_1239_li
@changelog_1240_li
#Temporary files are now deleted when the database is closed, even if they were not garbage collected so far.
@changelog_1240_h2
@changelog_1241_h2
#Version 1.1.101 (2008-10-17)
@changelog_1241_li
@changelog_1242_li
#Errors with code 42000 - 42999 are no longer written to the trace file by default.
@changelog_1242_li
@changelog_1243_li
#Queries with more than 10 tables are now faster.
@changelog_1243_li
@changelog_1244_li
#Opening a connection with AUTO_SERVER=TRUE is now fast when the database is already open in another process (less than 0.01 seconds instead of 2 seconds).
@changelog_1244_li
@changelog_1245_li
#IF [NOT] EXISTS is supported for named constraints in ALTER TABLE ... ADD/DROP CONSTRAINT.
@changelog_1245_li
@changelog_1246_li
#The error messages have been translated to Spanish by Dario V. Fassi. Thanks a lot!
@changelog_1246_li
@changelog_1247_li
#Linked tables: the automatic connection sharing didn't work. Actually the system property h2.shareLinkedConnections was working in the opposite direction: it was disabled when set to true. Now it works as expected.
@changelog_1247_li
@changelog_1248_li
#Opening large database is now faster.
@changelog_1248_li
@changelog_1249_li
#New system property h2.socketConnectTimeout, the timeout in milliseconds to connect to a server. The default is 2000 (2 seconds).
@changelog_1249_li
@changelog_1250_li
#The wrong parameters were bound to subqueries with parameters, specially when using IN(SELECT ...) and IN(...).
@changelog_1250_li
@changelog_1251_li
#Unset parameters were not detected when the query was re-compiled.
@changelog_1251_li
@changelog_1252_li
#New functions ISO_YEAR, ISO_WEEK, ISO_DAY_OF_WEEK. Thanks a lot to Robert Rathsack for implementing those!
@changelog_1252_li
@changelog_1253_li
#The date functions DAYOFYEAR, DAYOFMONTH, DAYOFWEEK are now called DAY_OF_YEAR, DAY_OF_MONTH, DAY_OF_WEEK (the old names still work).
@changelog_1253_li
@changelog_1254_li
#An out of memory error while deleting or updating many rows could result in a strange exception.
@changelog_1254_li
@changelog_1255_li
#Linked tables: compatibility with MS SQL Server has been improved.
@changelog_1255_li
@changelog_1256_li
#Renaming tables that have foreign keys with cascade didn't work correctly.
@changelog_1256_li
@changelog_1257_li
#The auto-reconnect feature didn't work when using the auto-server mode. Fixed.
@changelog_1257_li
@changelog_1258_li
#Fulltext search: new method FT_DROP_INDEX.
@changelog_1258_li
@changelog_1259_li
#The optimization to group using an index didn't work in some cases in version 1.1 (see also system property h2.optimizeGroupSorted).
@changelog_1259_li
@changelog_1260_li
#OSGi meta data is included in the manifest file. An OSGi BundleActivator is included: it loads the database driver when starting the bundle, and unloads it when stopping the bundle.
@changelog_1260_li
@changelog_1261_li
#The default value for MAX_MEMORY_UNDO is now 50000.
@changelog_1261_li
@changelog_1262_li
#For alias columns, ResultSetMetaData.getTableName() and getColumnName() now return the real table and column name in the default mode.
@changelog_1262_li
@changelog_1263_li
#In SQL scripts created with SCRIPT TO, schemas are now only created if they don't exist yet.
@changelog_1263_li
@changelog_1264_li
#After re-connecting to a database, the database event listener (if set) is informed about it.
@changelog_1264_li
@changelog_1265_li
#Local temporary tables now support indexes. Thanks a lot to Matt Roy!
@changelog_1265_li
@changelog_1266_li
#RUNSCRIPT no longer uses a temporary file.
@changelog_1266_li
@changelog_1267_li
#New system table INFORMATION_SCHEMA.SESSION_STATE containing the SQL statements that make up the session state. The list currently contains variables (SET @..) and local temporary tables (without data).
@changelog_1267_li
@changelog_1268_li
#After an automatic re-connect, part of the session state stays (the part that is stored in the SESSION_STATE table).
@changelog_1268_li
@changelog_1269_li
#The build didn't work if the directory temp didn't exist before.
@changelog_1269_li
@changelog_1270_li
#New system property h2.maxReconnect (default 3) to limit the number of re-connects for the same SQL statement (this is usually only important for SHUTDOWN).
@changelog_1270_li
@changelog_1271_li
#WHERE .. IN (SELECT ...) could throw a NullPointerException.
@changelog_1271_li
@changelog_1272_li
#Improved Glassfish / Toplink support in H2Platform thanks to Marcio Borges from Brazil. Thanks a lot!
@changelog_1272_h2
@changelog_1273_h2
#Version 1.1.100 (2008-10-04)
@changelog_1273_li
@changelog_1274_li
#In version 1.1, the following system properties are now enabled by default: h2.lobFilesInDirectories, h2.optimizeGroupSorted, h2.optimizeInJoin, h2.shareLinkedConnections
@changelog_1274_li
@changelog_1275_li
#The H2 Console tool now works with the JDBC-ODBC bridge.
@changelog_1275_li
@changelog_1276_li
#The H2 Console tool now supports command line options to start things separately.
@changelog_1276_li
@changelog_1277_li
#Large objects did not work for in-memory databases in server mode in Linux.
@changelog_1277_li
@changelog_1278_li
#Connections from a local address other than 'localhost' were not allowed if remote connections were disabled. This was always a problem, but only got visible in the last release because the server no longer connects to 'localhost' if networked.
@changelog_1278_li
@changelog_1279_li
#The h2console.war can now be built using the Java build.
@changelog_1279_li
@changelog_1280_li
#By default, databases are shared in the same process. For read-only databases this causes unnecessary synchronization, but safes memory. If you want that each connection opens its own database, append ;OPEN_NEW=TRUE to the database URL.
@changelog_1280_li
@changelog_1281_li
#New auto-reconnect feature will cause the JDBC driver to reconnect to the database if the connection is lost. To enable, append ;AUTO_RECONNECT=TRUE to the database URL. This is specially helpful when using AUTO_SERVER. AUTO_SERVER automatically uses auto-reconnect.
@changelog_1281_li
@changelog_1282_li
#CreateCluster: the property 'serverlist' is now called 'serverList'.
@changelog_1282_li
@changelog_1283_li
#The ConvertTraceFile tool could not parse some files because the trace mechanism did not encode prepared statement parameters.
@changelog_1283_li
@changelog_1284_li
#Databases names can now be one character long (the minimum size used to be 2 characters).
@changelog_1284_h2
@changelog_1285_h2
#Version 1.0.79 (2008-09-26)
@changelog_1285_li
@changelog_1286_li
#Linked tables that point to the same database can now share the connection within the same database. Access to the same connection is serialized. To enable this feature, set the system property h2.shareLinkedConnections to true.
@changelog_1286_li
@changelog_1287_li
#Multiple processes can now access the same database without having to explicitly start the server. To do that, append ;AUTO_SERVER=TRUE to the database URL. In this case, the server is started automatically if the connection is in embedded mode, and the server mode is used if a server is running. If the process that opened the first connection is closed, the other client need to reconnect (there is no automatic re-connect so far). Remote connections are allowed, but only to this database.
@changelog_1287_li
@changelog_1288_li
#The server tool now displays the correct IP address if networked.
@changelog_1288_li
@changelog_1289_li
#Can now start a TCP server with port 0 (automatically select a port).
@changelog_1289_li
@changelog_1290_li
#Result sets with just a unique index can now be updated (previously a primary key was required).
@changelog_1290_li
@changelog_1291_li
#LINKED TABLE: the schema name can now be set. When multiple tables exist in different schema, and the schema name is not set, an exception is thrown.
@changelog_1291_li
@changelog_1292_li
#LINKED TABLE: worked around a bug in Oracle with the CHAR data type.
@changelog_1292_li
@changelog_1293_li
#Faster hash code calculation for large binary arrays.
@changelog_1293_li
@changelog_1294_li
#Faster storage re-use algorithm thanks to Greg Dhuse from cleversafe.com.
@changelog_1294_li
@changelog_1295_li
#The database supports the SHOW command for better MySQL and PostgreSQL compatibility.
@changelog_1295_li
@changelog_1296_li
#The H2 Console now abbreviates large texts in results.
@changelog_1296_li
@changelog_1297_li
#Multiple UNION queries could not be used in derived tables.
@changelog_1297_li
@changelog_1298_li
#Linked tables can now be read-only.
@changelog_1298_li
@changelog_1299_li
#Temporary linked tables are now supported.
@changelog_1299_li
@changelog_1300_li
#It was possible to create tables in read-only databases.
@changelog_1300_li
@changelog_1301_li
#SET SCHEMA_SEARCH_PATH is now documented.
@changelog_1301_li
@changelog_1302_li
#SET SCHEMA did not work for views.
@changelog_1302_li
@changelog_1303_li
#Row level locking for MVCC is now enabled. The exception 'Concurrent update in table ...' is still thrown, but only after the lock timeout.
@changelog_1303_li
@changelog_1304_li
#The maximum log file size setting was ignored for large databases.
@changelog_1304_li
@changelog_1305_li
#Multi-Version Concurrency (MVCC) may no longer be used when using the multi-threaded kernel feature (MULTI_THREADED). An exception is thrown when trying to connect with both settings. Additional synchronization is required before those features can be used together.
@changelog_1305_li
@changelog_1306_li
#The data type JAVA_OBJECT could not be used in updatable result sets.
@changelog_1306_li
@changelog_1307_li
#The system property h2.optimizeInJoin did not work correctly.
@changelog_1307_li
@changelog_1308_li
#Conditions such as ID=? AND ID>? were slow.
@changelog_1308_h2
@changelog_1309_h2
#Version 1.0.78 (2008-08-28)
@changelog_1309_li
@changelog_1310_li
#The documentation no longer uses a frameset (except the Javadocs).
@changelog_1310_li
@changelog_1311_li
#When using DB_CLOSE_DELAY, sometimes a NullPointerException is thrown when the database is opened almost at the same time as it is closed automatically. Thanks a lot to Dmitry Pekar for finding this!
@changelog_1311_li
@changelog_1312_li
#Java methods with variable number of parameters can now be used (for Java 1.5 or newer).
@changelog_1312_li
@changelog_1313_li
#The Japanese translation has been improved by Masahiro Ikemoto. Thanks a lot!
@changelog_1313_li
@changelog_1314_li
#The H2 Console replaced an empty user name with a single space.
@changelog_1314_li
@changelog_1315_li
#The build target 'build jarSmall' now includes the embedded database.
@changelog_1315_li
@changelog_1316_li
#JdbcDataSource now keeps the password in a char array where possible.
@changelog_1316_li
@changelog_1317_li
#ResultSet.absolute did not always work with large result sets.
@changelog_1317_li
@changelog_1318_li
#Column aliases can now be used in GROUP BY and HAVING.
@changelog_1318_li
@changelog_1319_li
#Jason Brittain has contributed MySQL date functions. Thanks a lot! They are not in the h2.jar file currently, but in src/tools/org/h2/mode/FunctionsMySQL.java. To install, add this class to the classpath and call FunctionsMySQL.register(conn) in the Java code.
@changelog_1319_h2
@changelog_1320_h2
#Version 1.0.77 (2008-08-16)
@changelog_1320_li
@changelog_1321_li
#JaQu is now using prepared statements and supports Date, Time, Timestamp.
@changelog_1321_li
@changelog_1322_li
#When using remote in-memory databases, large LOB objects did not work.
@changelog_1322_li
@changelog_1323_li
#Timestamp columns such as TIMESTAMP(6) were not compatible to other database.
@changelog_1323_li
@changelog_1324_li
#Opening a large database was slow if there was a problem opening the previous time.
@changelog_1324_li
@changelog_1325_li
#NOT IN(SELECT ...) was incorrect if the subquery returns no rows.
@changelog_1325_li
@changelog_1326_li
#CREATE TABLE AS SELECT did not work correctly in the multi-version concurrency mode.
@changelog_1326_li
@changelog_1327_li
#Support a comma before closing a list, as in: create table test(id int,)
@changelog_1327_li
@changelog_1328_li
#MySQL compatibility: linked tables had lower case column names on some systems.
@changelog_1328_li
@changelog_1329_li
#DB2 compatibility: the DB2 fetch-first-clause is supported.
@changelog_1329_li
@changelog_1330_li
#Oracle compatibility: old style outer join syntax using (+) did work correctly sometimes.
@changelog_1330_li
@changelog_1331_li
#ResultSet.setFetchSize is now supported.
@changelog_1331_li
@changelog_1332_li
#It has been reported that when using Install4j on some Linux systems and enabling the 'pack200' option, the h2.jar becomes corrupted by the install process, causing application failure. A workaround is to add an empty file h2.jar.nopack next to the h2.jar file. The reason for this problem is not known.
@changelog_1332_h2
@changelog_1333_h2
#Version 1.0.76 (2008-07-27)
@changelog_1333_li
@changelog_1334_li
#The comment of a domain (user defined data type) is now used as the default column comment when creating a column with this domain.
@changelog_1334_li
@changelog_1335_li
#Invalid database names are now detected and a better error message is thrown.
@changelog_1335_li
@changelog_1336_li
#ResultSetMetaData.getColumnClassName now returns the correct class name for BLOB and CLOB.
@changelog_1336_li
@changelog_1337_li
#Fixed the Oracle mode: Oracle allows multiple rows only where all columns of the unique index are NULL.
@changelog_1337_li
@changelog_1338_li
#There is a problem with Hibernate when using Boolean columns. A patch for Hibernate has been submitted at http://opensource.atlassian.com/projects/hibernate/browse/HHH-3401
@changelog_1338_li
@changelog_1339_li
#ORDER BY on tableName.columnName didn't work correctly if the column name was also used as an alias.
@changelog_1339_li
@changelog_1340_li
#H2 Console: the progress display when opening a database has been improved.
@changelog_1340_li
@changelog_1341_li
#The error message when the server doesn't start has been improved.
@changelog_1341_li
@changelog_1342_li
#Key values can now be changed in updatable result sets.
@changelog_1342_li
@changelog_1343_li
#Changes in updatable result sets are now visible even when resetting the result set.
@changelog_1343_li
@changelog_1344_li
#Temporary files were sometimes deleted too late when executing large insert, update, or delete operations.
@changelog_1344_li
@changelog_1345_li
#The database file was growing after deleting many rows, and after large update operations.
@download_1000_h1
...
...
@@ -7433,96 +7436,123 @@ MySQL
#Database Performance Tuning
@performance_1402_h3
#Virus Scanners
#Use a Modern JVM
@performance_1403_p
#Some virus scanners scan files every time they are accessed. It is very important for performance that database files are not scanned for viruses. The database engine does never interprets the data stored in the files as programs, that means even if somebody would store a virus in a database file, this would be harmless (when the virus does not run, it cannot spread). Some virus scanners allow to exclude files by suffix. Make sure files ending with .db are not scanned.
#Newer JVMs are faster. Upgrading to the latest version of your JVM can provide a "free" boost to performance. On the Windows platform, switching from the default Client JVM to the Server JVM using the <code>-server</code> command-line option improves performance at the cost of a slight increase in start-up time.
@performance_1404_h3
トレースオプションを使用する
#Virus Scanners #トレースオプションを使用する
@performance_1405_p
#If the main performance hot spots are in the database engine, in many cases the performance can be optimized by creating additional indexes, or changing the schema. Sometimes the application does not directly generate the SQL statements, for example if an O/R mapping tool is used. To view the SQL statements and JDBC API calls, you can use the trace options. For more information, see <a href="features.html#trace_options">Using the Trace Options</a> .
#Some virus scanners scan files every time they are accessed. It is very important for performance that database files are not scanned for viruses. The database engine does never interprets the data stored in the files as programs, that means even if somebody would store a virus in a database file, this would be harmless (when the virus does not run, it cannot spread). Some virus scanners allow to exclude files by suffix. Make sure files ending with .db are not scanned.
@performance_1406_h3
#Index Usage
トレースオプションを使用する
@performance_1407_p
#This database uses indexes to improve the performance of SELECT, UPDATE and DELETE statements. If a column is used in the WHERE clause of a query, and if an index exists on this column, then the index can be used. Multi-column indexes are used if all or the first columns of the index are used. Both equality lookup and range scans are supported. Indexes are used to order result sets, but only if the condition uses the same index or no index at all. The results are sorted in memory if required. Indexes are created automatically for primary key and unique constraints. Indexes are also created for foreign key constraints, if required. For other columns, indexes need to be created manually using the CREATE INDEX statement.
#If the main performance hot spots are in the database engine, in many cases the performance can be optimized by creating additional indexes, or changing the schema. Sometimes the application does not directly generate the SQL statements, for example if an O/R mapping tool is used. To view the SQL statements and JDBC API calls, you can use the trace options. For more information, see <a href="features.html#trace_options">Using the Trace Options</a> .
@performance_1408_h3
#Optimizer
#Index Usage
@performance_1409_p
#This database uses a cost based optimizer. For simple and queries and queries with medium complexity (less than 7 tables in the join), the expected cost (running time) of all possible plans is calculated, and the plan with the lowest cost is used. For more complex queries, the algorithm first tries all possible combinations for the first few tables, and the remaining tables added using a greedy algorithm (this works well for most joins). Afterwards a genetic algorithm is used to test at most 2000 distinct plans. Only left-deep plans are evaluated.
#This database uses indexes to improve the performance of SELECT, UPDATE and DELETE statements. If a column is used in the WHERE clause of a query, and if an index exists on this column, then the index can be used. Multi-column indexes are used if all or the first columns of the index are used. Both equality lookup and range scans are supported. Indexes are used to order result sets, but only if the condition uses the same index or no index at all. The results are sorted in memory if required. Indexes are created automatically for primary key and unique constraints. Indexes are also created for foreign key constraints, if required. For other columns, indexes need to be created manually using the CREATE INDEX statement.
@performance_1410_h3
#Expression Optimization
#Optimizer
@performance_1411_p
#After the statement is parsed, all expressions are simplified automatically if possible. Operations are evaluated only once if all parameters are constant. Functions are also optimized, but only if the function is constant (always returns the same result for the same parameter values). If the WHERE clause is always false, then the table is not accessed at all.
#This database uses a cost based optimizer. For simple and queries and queries with medium complexity (less than 7 tables in the join), the expected cost (running time) of all possible plans is calculated, and the plan with the lowest cost is used. For more complex queries, the algorithm first tries all possible combinations for the first few tables, and the remaining tables added using a greedy algorithm (this works well for most joins). Afterwards a genetic algorithm is used to test at most 2000 distinct plans. Only left-deep plans are evaluated.
@performance_1412_h3
#COUNT(*) Optimization
#Expression Optimization
@performance_1413_p
#If the query only counts all rows of a table, then the data is not accessed. However, this is only possible if no WHERE clause is used, that means it only works for queries of the form SELECT COUNT(*) FROM table.
#After the statement is parsed, all expressions are simplified automatically if possible. Operations are evaluated only once if all parameters are constant. Functions are also optimized, but only if the function is constant (always returns the same result for the same parameter values). If the WHERE clause is always false, then the table is not accessed at all.
#If the query only counts all rows of a table, then the data is not accessed. However, this is only possible if no WHERE clause is used, that means it only works for queries of the form SELECT COUNT(*) FROM table.
#When executing a query, at most one index per joined table can be used. If the same table is joined multiple times, for each join only one index is used. Example: for the query SELECT * FROM TEST T1, TEST T2 WHERE T1.NAME='A' AND T2.ID=T1.ID, two index can be used, in this case the index on NAME for T1 and the index on ID for T2.
@performance_1416_p
@performance_1418_p
#If a table has multiple indexes, sometimes more than one index could be used. Example: if there is a table TEST(ID, NAME, FIRSTNAME) and an index on each column, then two indexes could be used for the query SELECT * FROM TEST WHERE NAME='A' AND FIRSTNAME='B', the index on NAME or the index on FIRSTNAME. It is not possible to use both indexes at the same time. Which index is used depends on the selectivity of the column. The selectivity describes the 'uniqueness' of values in a column. A selectivity of 100 means each value appears only once, and a selectivity of 1 means the same value appears in many or most rows. For the query above, the index on NAME should be used if the table contains more distinct names than first names.
@performance_1417_p
@performance_1419_p
#The SQL statement ANALYZE can be used to automatically estimate the selectivity of the columns in the tables. This command should be run from time to time to improve the query plans generated by the optimizer.
@performance_1418_h3
@performance_1420_h3
#In-Memory (Hash) Indexes
@performance_1419_p
@performance_1421_p
#Using in-memory indexes, specially in-memory hash indexes, can speed up queries and data manipulation.
@performance_1420_p
@performance_1422_p
#In-memory indexes are automatically used for in-memory databases, but can also be created for persistent databases using <code>CREATE MEMORY TABLE</code> . In many cases, the rows itself will also be kept in-memory. Please note this may cause memory problems for large tables.
@performance_1421_p
@performance_1423_p
#In-memory hash indexes are backed by a hash table and are usually faster than regular indexes. However, hash indexes only supports direct lookup (WHERE ID = ?) but not range scan (WHERE ID < ?). To use hash indexes, use HASH as in: <code>CREATE UNIQUE HASH INDEX</code> and <code>CREATE TABLE ...(ID INT PRIMARY KEY HASH,...)</code> .
@performance_1422_h3
@performance_1424_h3
#Optimization Examples
@performance_1423_p
@performance_1425_p
#See <code>src/test/org/h2/samples/optimizations.sql</code> for a few examples of queries that benefit from special optimizations built into the database.
@performance_1424_h3
@performance_1426_h3
#Cache Size and Type
@performance_1425_p
@performance_1427_p
#By default the cache size of H2 is quite small. Consider using a larger cache size, or enable the second level soft reference cache. See also <a href="features.html#cache_settings">Cache Settings</a> .
@performance_1426_h2
@performance_1428_h3
データ型
@performance_1429_p
#Each data type has different storage and performance characteristics:
@performance_1430_li
#The DECIMAL/NUMERIC type is slower and requires more storage than the REAL and DOUBLE types.
@performance_1431_li
#Text types are slower to read, write, and compare than numeric types and generally require more storage.
@performance_1432_li
#See <a href="advanced.html#large_objects">Large Objects</a> for information on BINARY vs. BLOB and VARCHAR vs. CLOB performance.
@performance_1433_li
#Parsing and formatting takes longer for the TIME, DATE, and TIMESTAMP types than the numeric types.
@performance_1434_li
#SMALLINT/TINYINT/BOOLEAN are not significantly smaller or faster to work with than INTEGER in most modes.
@performance_1435_h2
#Fast Database Import
@performance_1427_p
@performance_1436_p
#To speed up large imports, consider using the following options temporarily:
@performance_1428_li
@performance_1437_li
#SET CACHE_SIZE (a large cache is faster)
@performance_1429_li
@performance_1438_li
#SET LOCK_MODE 0 (disable locking)
@performance_1430_li
@performance_1439_li
#SET LOG 0 (disable the transaction log)
@performance_1431_li
@performance_1440_li
#SET UNDO_LOG 0 (disable the session undo log)
@performance_1432_p
@performance_1441_p
#These options can be set in the database URL: <code>jdbc:h2:~/test;CACHE_SIZE=65536;LOCK_MODE=0;LOG=0;UNDO_LOG=0</code> . Most of those options are not recommended for regular use, that means you need to reset them after use.
changelog_1002_li=JaQu\:the plan is to support natural (pure Java) conditions such as (id \=\=1 && name.equals("Test")). A proof of concept decompiler is now included (it doesn't work yet).
changelog_1003_li=Various bugfixes and improvements in the page store mechanism (still experimental).
changelog_1004_li=PreparedStatement.setObject now converts a java.lang.Character to a string.
changelog_1005_li=H2 Console\:PierPaolo Ucchino has completed the Italian translation. Thanks a lot\!
changelog_1006_li=Various tools now use Java 5 var-args, such as main the methods and SimpleResultSet.addRow.
changelog_1007_li=H2 Console\:indexes of tables of non-default schemas are now also listed.
changelog_1008_li=Issue 111\:Multi-version concurrency / duplicate primary key after rollback.
changelog_1009_li=Issue 110\:Multi-version concurrency / wrong exception is thrown.
changelog_1010_li=Parser\:sequenceName.NEXTVAL and CURRVAL did not respect the schema search path.
changelog_1011_li=The following sequence could throw the exception "Row not found when trying to delete"\:start a transaction, insert many rows, delete many rows, rollback. The number of rows depends on the cache size.
changelog_1012_li=The stack trace of very common exceptions is no longer written to the .trace.db file by default.
changelog_1013_li=An optimization for OR is implemented, but disabled by default. Expressions of the type X\=1 OR X\=2 are converted to X IN(1, 2). To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver.
changelog_1014_li=An optimization for IN(..) and IN(SELECT...) is implemented, but disabled by default. To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver. If enabled, this overrides h2.optimizeIn and h2.optimizeInJoin. Unlike now, this optimization will also speed up updates and deletes.
changelog_1015_h2=Version 1.1.117 (2009-08-09)
changelog_1016_li=New committer\:Sam Van Oort has been contributing to H2 since quite some time in many ways (on the mailing list, documentation, and in the form of patches). He is now a committer.
changelog_1017_li=JaQu\:the order of the fields in the database no longer needs to match the order in the database.
changelog_1018_li=Issue 103\:MVCC\:the setting MAX_MEMORY_UNDO can currently not be supported when using multi-version concurrency, that means the complete undo log must fit in memory.
changelog_1019_li=LIKE\:the escape mechanism can now be disable using ESCAPE ''. The default escape character can be changed using the system property h2.defaultEscape. The default is still '\\' (as in MySQL and PostgreSQL).
changelog_1020_li=Views using functions were not re-evaluated when necessary.
changelog_1021_li=Improved MySQL compatibility for SHOW COLUMNS.
changelog_1022_li=Improved PostgreSQL compatibility for timestamp literals with timezone.
changelog_1023_li=Sergi Vladykin translated the error messages to Russian. Thanks a lot\!
changelog_1024_li=Support for Java 6 DatabaseMetaData.getTables, getColumns, getProcedures, and getProcedureColumns.
changelog_1025_li=Issue 101\:Rollback of a large transaction (more than 100000 rows) could fail.
changelog_1026_li=Various bugfixes and improvements in the page store mechanism (still experimental).
changelog_1027_li=The functions LENGTH, OCTET_LENGTH, and BIT_LENGTH now return BIGINT.
changelog_1028_li=Data types CLOB and BLOB\:the maximum precision was Integer.MAX_VALUE, it is now Long.MAX_VALUE.
changelog_1029_li=Multi-threaded kernel\:creating and dropping temporary database objects and the potentially free pages list was not correctly synchronized. Thanks a lot to Eric Faulhaber for the test case and patch\!
changelog_1030_li=Parsing SQL script files is now faster.
changelog_1031_li=CSV reading is now faster.
changelog_1032_li=SimpleResultSet.newInstance(SimpleRowSource rs) did not work.
changelog_1033_h2=Version 1.1.116 (2009-07-18)
changelog_1034_li=Server-less multi-connection mode\:more bugs are fixed.
changelog_1035_li=The built-in help (INFORMATION_SCHEMA.HELP) is smaller, shrinking the jar file size a bit.
changelog_1036_li=H2 Console\:column of tables of non-default schemas are now also listed, except for schemas starting with 'INFO'.
changelog_1037_li=ALTER TABLE\:removing an auto-increment or identity column didn't remove the sequence.
changelog_1038_li=Creating indexes is now a bit faster.
changelog_1039_li=PG Server\:new system property h2.pgClientEncoding to explicitly set the encoding for clients that don't send the encoding (the default encoding is UTF-8). Thanks a lot to Sergi Vladykin for the patch\!
changelog_1040_li=PG Server\:improved compatibility by using the type ids of the PostgreSQL driver. Thanks a lot to Sergi Vladykin for the patch\!
changelog_1041_li=H2 Console\:Oracle system tables are no longer listed, improving performance.
changelog_1042_li=Result sets are now read-only except if the statement or prepared statement was created with the concurrency ResultSet.CONCUR_UPDATABLE. This change is required because the old behavior (all result set are updatable) violated the JDBC spec. For backward compatibility, use the system property h2.defaultResultSetConcurrency.
changelog_1043_li=New system property h2.defaultResultSetConcurrency to change the default result set concurrency.
changelog_1044_li=JDBC\:using an invalid result set type or concurrency now throws an exception.
changelog_1045_li=If a pooled connection was not closed but garbage collected, a NullPointerException could occur.
changelog_1046_li=Fulltext search\:a NullPointerException was thrown when updating a value that was NULL previously.
changelog_1047_li=The Recover tool did not work with .data.db files of the wrong size.
changelog_1048_li=Triggers\:if there was an exception when initializing a trigger, this exception could be hidden, and in some cases (specially when using the Lucene fulltext index mechanism) a NullPointerException was thrown later on. Now the exception that occurred on init is thrown when changing data.
changelog_1049_li=The soft-references cache (CACHE_TYPE\=SOFT_LRU) could throw a NullPointerException.
changelog_1050_li=To enable the new page store mechanism, append ;PAGE_STORE\=TRUE to the database URL. or set the system property h2.pageStore to true. This mechanism is still experimental, and the file format will change, but it is quite stable now.
changelog_1051_h2=Version 1.1.115 (2009-06-21)
changelog_1052_li=The new storage mechanism is now alpha quality. To try it out, set the system property "h2.pageStore" to "true" (java -Dh2.pageStore\=true). There are still bugs to be found and fixed, for example inserting many rows references a lot of main memory. Performance is currently about the same as with the regular storage mechanism, but the database file size is smaller. The file format is not stable yet.
changelog_1053_li=ALTER TABLE could throw an exception "object already exists" in some cases.
changelog_1054_li=Views\:in some situations, an ArrayIndexOutOfBoundsException was thrown when using the same view concurrently.
changelog_1055_li=java.util.UUID is now supported in PreparedStatement.setObject and user defined Java functions. ResultSet.getObject() returns a java.util.UUID when using the UUID data type.
changelog_1056_li=H2 Console\:the language was reset to the browser language when disconnecting.
changelog_1058_li=Server-less multi-connection mode\:more bugs are fixed.
changelog_1059_li=The download page now included the SHA1 checksums.
changelog_1060_li=Shell tool\:the file encoding workaround is now documented if you run java org.h2.tools.Shell -?.
changelog_1061_li=The RunScript tool and SQL statement did not work with the compression method LZF.
changelog_1062_li=Fulltext search\:searching for NULL or an empty string threw an exception.
changelog_1063_li=Lucene fulltext search\:FTL_DROP_ALL did not drop the triggers.
changelog_1064_li=Backup\:if the database contained CLOB or BLOB data, the backup included a file entry for the LOB directory. This caused the restore to fail.
changelog_1065_li=Data types\:LONG is now an alias for BIGINT.
changelog_1066_h2=Version 1.1.114 (2009-06-01)
changelog_1067_li=ResultSetMetaData.getColumnClassName returned the wrong class for CLOB and BLOB columns.
changelog_1068_li=Fulltext search\:data is no longer deleted and re-inserted if the indexed columns didn't change.
changelog_1069_li=In some situations, an ArrayIndexOutOfBoundsException was thrown when adding rows. This was caused by a bug in the b-tree code.
changelog_1070_li=Microsoft Windows Vista\:when using the the installer, Vista wrote "This program may not have installed correctly." This message should no longer appear (in the h2.nsi file, the line 'RequestExecutionLevel highest' was added).
changelog_1071_li=The Recover tool did not always work when the database contains referential integrity constraints.
changelog_1072_li=Java 1.5 is now required to run H2. If required, Retrotranslator can be used to create a Java 1.4 version (http\://retrotranslator.sourceforge.net/).
changelog_1073_h2=Version 1.1.113 (2009-05-21)
changelog_1074_li=Shell tool\:the built-in commands EXIT, HELP, ?, LIST, and so on didn't work with a semicolon at the end.
changelog_1075_li=JDK 1.5 is now required to build the jar file. However it is still possible to create a jar file for Java 1.4. For details, see buildRelease.sh and buildRelease.bat. As an alternative, compile using JDK 1.5 or 1.6 and use Retrotranslator to create a Java 1.4 version (http\://retrotranslator.sourceforge.net/).
changelog_1076_li=When deleting or updating many rows in a table, the space in the index file was not re-used in the default mode (persistent database, b-tree index, LOG\=1). This caused the index file to grow over time. Workarounds were to delete and re-created the index file, alter the table (add a remove a column), or append ;LOG\=2 to the database URL. To disable the change, set the system property h2.reuseSpaceBtreeIndex to false.
changelog_1077_li=Identifiers with a digit and then a dollar sign didn't work. Example\:A1$B.
changelog_1078_li=MS SQL Server compatibility\:support for linked tables with NVARCHAR, NCHAR, NCLOB, and LONGNVARCHAR.
changelog_1079_li=Android\:workaround for a problem when using read-only databases in zip files (skip seems to be implemented incorrectly on the Android system).
changelog_1080_li=Calling execute() or prepareStatement() with null as the SQL statement now throws an exception.
changelog_1081_li=Benchmark\:the number of executed statements was incorrect. The H2 database was loaded at the beginning of the test to collect results, now it is loaded at the very end. Thanks to Fred Toussi from HSQLDB for reporting those problems. However the changed do not affect the relative performance.
changelog_1082_li=H2 Console\:command line settings are no longer stored in the properties file. They are now only used for the current process, except if they are explicitly saved.
changelog_1083_li=Cache\:support for a second level soft-references cache. To enable it, append ;CACHE_TYPE\=SOFT_LRU (or SOFT_TQ) to the database URL, or set the system property h2.cacheTypeDefault to "SOFT_LRU" / "SOFT_TQ". Enabling the second level cache reduces performance for small databases, but speeds up large databases. It makes sense to use it if the available memory size is unknown. Thanks a lot to Jan Kotek\!
changelog_1084_h2=Version 1.1.112 (2009-05-01)
changelog_1085_li=JdbcPreparedStatement.toString() could throw a NullPointerException.
changelog_1087_li=Connection pool\:the default login timeout is now 5 minutes.
changelog_1088_li=After truncating tables, opening large databases could become slow because indexes were always re-built unnecessarily when opening.
changelog_1089_li=More bugs in the server-less multi-connection mode have been fixed\:Sometimes parameters of prepared statements were lost when a reconnecting. Concurrent read operations were slow. To improve performance, executeQuery(..) must be used for queries (execute(..) switches to the write mode, which is slow).
changelog_1090_li=GROUP BY queries with a self-join (join to the same table) that were grouped by columns with indexes returned the wrong result in some cases.
changelog_1091_li=Improved error message when the .lock.db file modification time is in the future.
changelog_1092_li=The MERGE statement now returns 0 as the generated key if the row was updated.
changelog_1093_li=Running code coverage is now automated.
changelog_1094_li=A file system implementation can now be registered using FileSystem.register.
changelog_1095_li=The database file system is no longer included in the jar file, it moved to the test section.
changelog_1096_h2=Version 1.1.111 (2009-04-10)
changelog_1097_li=In-memory databases can now run inside the Google App Engine.
changelog_1098_li=Queries that are ordered by an indexed column returned no rows in certain cases (if all rows were deleted from the table previously, and there is a low number of rows in the table, and when not using other conditions, and when using the default b tree index).
changelog_1099_li=The wrong exception was thrown when using unquoted text for the SQL statements COMMENT, ALTER USER, and SET PASSWORD.
changelog_1100_li=The built-in connection pool did not roll back transactions and enable autocommit enabled after closing a connection.
changelog_1101_li=Sometimes a StackOverflow occurred when checking for deadlock. See also http\://code.google.com/p/h2database/issues/detail?id\=61
changelog_1102_li=The Shell tool no longer truncates results with only one column, and displays a message if data was truncated.
changelog_1103_h2=Version 1.1.110 (2009-04-03)
changelog_1104_li=Support for not persistent in-memory tables in regular (persistent) databases using CREATE MEMORY TABLE(..) NOT PERSISTENT. Thanks a lot to Sergi Vladykin for the patch\!
changelog_1105_li=The H2 Console trimmed the password (removed leading and trailing spaces). This is no longer the case, to support encrypted H2 database with an empty user password.
changelog_1106_li=The data type of a SUBSTRING method was wrong.
changelog_1107_li=ResultSet.findColumn and get methods with column label parameters now also check for matching column names (like most databases except MySQL).
changelog_1108_li=H2 Console\:the browser system property now supports a list of arguments. Example\:java -Dh2.browser\="open,-a,Safari,%url"...
changelog_1109_li=Improved Javadoc navigation (similar to Scaladoc).
changelog_1110_li=H2 Console\:auto-complete of identifiers did not work correctly for H2 databases in MySQL mode.
changelog_1111_li=DISTINCT and GROUP BY on a CLOB column was broken.
changelog_1112_li=The FTP server moved to the tools section and is no longer included in the h2*.jar file.
changelog_1113_li=Improved error message for unsupported features\:now the message says what exactly is not supported.
changelog_1114_li=Improved OSGi support.
changelog_1115_li=Some internal caches did not use the LRU mechanism. Fixed (LOB file list, optimizer cost cache, trace system, view indexes, collection keys, compressed in-memory file system).
changelog_1116_li=The API of the tools changed a bit (each tool now returns an exit code).
changelog_1117_li=Command line help of the tools now match the javadocs. The build converts the javadocs to a resource that is read by the tool at runtime. This should not have an effect on using the database, but it reduces duplicate and out-of-sync documentation.
changelog_1118_li=CREATE TABLE\:improved compatibility (support for UNIQUE NOT NULL).
changelog_1119_li=DatabaseMetaData.getSQLKeywords now returns the correct list.
changelog_1120_li=Deterministic user defined functions did not work when the parameter was a column. Fixed.
changelog_1121_li=JdbcConnectionPool.setLoginTimeout with 0 now uses the default timeout.
changelog_1122_li=Creating a JdbcConnectionPool has been simplified a bit.
changelog_1123_li=The built-in connection pool did not re-use connections. Getting a connection using the built-in JdbcConnectionPool is now about 70 times faster than opening connections using DriverManager.getConnection.
changelog_1124_li=More bugs in the server-less multi-connection mode have been fixed\:If a process terminated while writing, other open connections were blocked. If two processes were writing to the database, sometimes the database was corrupt after closing.
changelog_1125_li=Linked tables to SQLite database can now be created.
changelog_1126_li=Nested IN(IN(...)) didn't work.
changelog_1127_li=NIO storage\:the nio\:prefix was using memory mapped files instead of FileChannel.
changelog_1128_h2=Version 1.1.109 (2009-03-14)
changelog_1129_li=The optimization for IN(...) is now only used if comparing a column with an index.
changelog_1130_li=User defined functions can now be deterministic (see CREATE ALIAS documentation).
changelog_1131_li=Multiple nested queries in the FROM clause with parameters did not always work.
changelog_1132_li=When converting CLOB to BINARY, each character resulted in one byte. Now, the text is parsed as a hex as when converting VARCHAR.
changelog_1133_li=New experimental NIO storage mechanism with both FileChannel and memory mapped files. To use it, use the file name prefix nio\:or nioMapped\:as in jdbc\:h2\:nio\:~/test. So far it looks like NIO storage is faster on Mac OS but slower on some Windows systems. Thanks a lot to Jan Kotek for the patch\!
changelog_1134_li=The functions BITOR, BITAND, BITXOR, and MOD now accept and return BIGINT instead of INT.
changelog_1135_li=Could not use the same linked table multiple times in the same query.
changelog_1136_li=Bugs in the server-less multi-connection mode have been fixed.
changelog_1137_li=Column names could not be named "UNIQUE" (with the quotes).
changelog_1138_li=New system function TRANSACTION_ID() to get the current transaction identifier for a session.
changelog_1139_h2=Version 1.1.108 (2009-02-28)
changelog_1140_li=When the shutdown hook closed the database, the last log file was deleted too early. This could cause uncommitted changes to be persisted. In some cases, this could cause data corruption.
changelog_1141_li=JdbcConnectionPool\:it was possible to set a negative connection pool size.
changelog_1142_li=Fulltext search did not support table names with a backslash.
changelog_1143_li=The internal IntArray class did not work correctly when initialized with a zero length array.
changelog_1144_li=The H2 Console web application (war file) did only support ASCII characters. Now UTF-8 is supported.
changelog_1145_li=DATEADD does no longer require that the argument is a timestamp.
changelog_1146_li=The database file locking mechanism didn't work correctly on Mac OS.
changelog_1147_li=Some built-in functions reported the wrong precision, scale, and display size.
changelog_1148_li=MySQL compatibility for CREATE TABLE is improved (UNSIGNED, KEY).
changelog_1149_li=Recovery did not work if there were more than 255 lobs stored as files.
changelog_1150_li=New experimental mode to support multiple read-write connections without starting a server. To enable this mode, append ;FILE_LOCK\=SERIALIZED;OPEN_NEW\=TRUE to the database URL. Don't expect high performance when multiple concurrent writers.
changelog_1151_li=In a web application, the database classes are not unloaded if a connection is open. This may cause out of memory when re-deploying a web application. The DbStarter is changed to close all connections to the configured database (by executing SHUTDOWN).
changelog_1152_li=The WebServlet did not close the database when un-deploying the web application.
changelog_1153_li=The exception message of failed INSERT or MERGE statements now includes all values and the row number.
changelog_1154_li=If opening a database failed with an out of memory exception, some files were not closed.
changelog_1155_li=Optimizer\:the expected runtime calculation was incorrect. The fixed calculation should give slightly better query plans when using many joins.
changelog_1156_li=Improved exception message when connecting to a just started server fails.
changelog_1157_li=Connection.isValid is a bit faster.
changelog_1158_li=H2 Console\:the autocomplete feature has been improved a bit. It can now better parse conditions.
changelog_1159_li=When restarting a web application in Tomcat, an exception was thrown sometimes. In most cases this was a NullPointerException. A workaround in H2 has been implemented. The root cause of the problem is now documented in the FAQ\:Tomcat sets all static fields (final or non-final) to null when unloading a web application. A workaround is to put the h2.jar in the lib directory, or set the system property org.apache.catalina.loader.WebappClassLoader.ENABLE_CLEAR_REFERENCES to false.
changelog_1160_h2=Version 1.1.107 (2009-01-24)
changelog_1161_li=Some DatabaseMetaData operations did not work for non-admin users for versions 1.1.x.
changelog_1162_li=The MySQL compatibility extension fromUnixTime now used the English locale.
changelog_1163_li=When using LOG\=2 and repeatedly updating the last row rows of a table, the index file grew quickly.
changelog_1164_li=In versions 1.1.105 and 1.1.106, encrypted script files of earlier versions could not be processed. This is now again possible. The problem was that such script files were stored in a special format (STORAGE\=TEXT) but support for this format was removed in version 1.1.105.
changelog_1165_li=Enabling the trace mechanism by creating a specially named file is no longer supported.
changelog_1166_h2=Version 1.1.106 (2009-01-04)
changelog_1167_li=Statement.setQueryTimeout did not work correctly for some statements.
changelog_1168_li=CREATE DOMAIN\:built-in data types can now only be changed if no tables exist.
changelog_1169_li=Linked tables\:a workaround for Oracle DATE columns has been implemented.
changelog_1170_li=DatabaseMetaData.getPrimaryKeys\:the column PK_NAME now contains the constraint name instead of the index name (compatibility for PostgreSQL and Derby).
changelog_1171_li=Using IN(..) inside a IN(SELECT..) did not always work.
changelog_1172_li=Views with IN(..) that used a view itself did not work.
changelog_1173_li=Union queries with LIMIT or ORDER BY that are used in a view or subquery did not work.
changelog_1174_li=The license change a bit\:so far the license was modified to say 'Swiss law'. This is now changed back to the original 'US law'. This was requested by a user, and I don't see a problem.
changelog_1175_li=Constraints for local temporary tables now session scoped. So far they were global. Thanks a lot to Eric Faulhaber for finding and fixing this problem\!
changelog_1176_li=When using the auto-server mode, and if the lock file was modified in the future, the wrong exception was thrown ('Connection is broken' instead of 'Error opening database\:lock file modified in the future').
changelog_1177_h2=Version 1.1.105 (2008-12-19)
changelog_1178_li=The setting STORAGE\=TEXT is no longer supported.
changelog_1179_li=Deleting a database using the tool DeleteDbFiles deleted LOB files of other databases in the same directory.
changelog_1180_li=When used in a subquery, LIKE and IN(..) did not work correctly sometimes.
changelog_1181_li=The fulltext search documentation has been improved.
changelog_1182_li=ARRAY_GET returned the wrong data type (ARRAY). Now it returns VARCHAR.
changelog_1183_li=Natural join\:the joined columns are not repeated any more when using SELECT *.
changelog_1184_li=User defined aggregate functions\:the method getType expected internal data types instead of SQL types.
changelog_1185_li=User defined aggregate functions did not work if there was no group by expression.
changelog_1186_li=MySQL compatibility\:support for \:\=assignment as in @sum\:\=@sum+x
changelog_1187_li=INSERT INTO TEST(SELECT * FROM TEST) is now supported.
changelog_1188_li=Each session threw an invisible exception when garbage collected.
changelog_1189_li=Foreign key constraints that refer to a quoted column did not work.
changelog_1190_li=New meta data column INFORMATION_SCHEMA.TABLES.LAST_MODIFICATION to get the table modification counter.
changelog_1191_li=Shell\:line comments didn't work correctly.
changelog_1192_li=H2 Console\:columns are now listed for up to 500 tables instead of 100.
changelog_1193_li=H2 Console\:Cmd+Enter executes the current statement, Alt+Space for autocomplete.
changelog_1194_li=JaQu\:the maximum length of a column can now be defined using maxLength. For an example, see Product.java (maxLength(category, 255)).
changelog_1195_li=R&\\\#305;dvan A&\\\#287;ar has completed the Turkish translation of the H2 Console. Thanks a lot\!
changelog_1196_h2=Version 1.1.104 (2008-11-28)
changelog_1197_li=If a query that was used like a table contained group by and was ordered by an expression that is not in the column list, an exception was thrown.
changelog_1198_li=JaQu\:tables are now auto-created when running a query.
changelog_1199_li=The optimizer had problems with function tables (for example CSVREAD and FTL_SEARCH). A new system property h2.estimatedFunctionTableRows (default 1000) defines how many rows can be expected in the table.
changelog_1200_li=The function SUM could overflow when using large values. It returns now a data type that is safe.
changelog_1201_li=The function AVG could overflow when using large values. Fixed.
changelog_1202_li=The emergency reserve file has been removed. It didn't provide an appropriate solution for the problem. It is still possible for an application to detect and deal with the low disk space problem (deleting temporary files for example) using DatabaseEventListener.diskSpaceIsLow, but this method is now always called with stillAvailable\=0.
changelog_1203_li=Build\:JAVA_HOME is now automatically detected on Mac OS X.
changelog_1204_li=Testing for local connections was very slow on some systems.
changelog_1205_li=The cache memory usage calculation is more conservative.
changelog_1206_li=Allocating space got slower and slower the larger the database.
changelog_1207_li=ALTER TABLE ALTER COLUMN could throw the wrong exception in the last version (Table not found).
changelog_1208_li=Updatable result sets\:the key columns can now be updated.
changelog_1209_li=The H2DatabaseProvider for ActiveObjects is now included in the tools section.
changelog_1210_li=The H2Platform for Oracle Toplink Essential has been improved a bit.
changelog_1211_li=The Windows service to start H2 didn't work in version 1.1.
changelog_1212_li=File systems with a maximum file size (for example FAT) are now supported using the file prefix 'split\:'. In this case the files are split in parts of 1 GB. Example URL\:jdbc\:h2\:split\:~/db/test. If you want to split into parts of 1 MB, use jdbc\:h2\:split\:20\:~/db/test (the part size is 1 << x, the default is 30 meaning 1 GB).
changelog_1213_li=The database now tries to detect if the classloader or virtual machine has almost shut down by checking if static final variables are set to null. This should help reduce exceptions when stopping the web application.
changelog_1214_li=Compatibility for MS SQL Server DATEDIFF(YYYY, .., ..)
changelog_1215_li=ResultSet.getObject for CLOB or BLOB will return a java.sql.Clob / java.sql.Blob object instead of a java.io.Reader / java.io.InputStream as in version 1.0. This behavior can be changed using the system property h2.returnLobObjects (true by default for version 1.1).
changelog_1216_li=The interface CloseListener has a new method 'remove' that is called when the trigger is dropped.
changelog_1217_li=Fulltext search\:there was a memory leak when creating and dropping fulltext indexes in a loop.
changelog_1218_h2=Version 1.1.103 (2008-11-07)
changelog_1219_li=Could not order by a formula when the formula was in the group by list but not in the select list.
changelog_1220_li=Date values that match the daylight saving time end were not allowed in times zones were the daylight saving time ends at midnight, for years larger than 2037. Example\:timezone Brasilia, date 2042-10-12. This is a problem of Java, however a workaround is implemented in H2 that solves most problems (except the problems of java.util.Date itself).
changelog_1221_li=ALTER TABLE used a lot of memory when using multi-version concurrency.
changelog_1222_li=Referential integrity for in-memory databases didn't work in some cases in version 1.1.102.
changelog_1223_li=New column INFORMATION_SCHEMA.COLUMNS.SEQUENCE_NAME to get the name of the sequence for auto-increment columns.
changelog_1224_li=Aliases for built-in data types (such as MEDIUMBLOB which is an alias for BLOB) can now be re-mapped to another data type using CREATE DOMAIN. However main built-in data types (such as INTEGER) can not be re-mapped.
changelog_1225_li=The Japanese translation has been completed by Masahiro Ikemoto. Thanks a lot\!
changelog_1226_li=Improved PostgreSQL compatibility for NEXTVAL and CURRVAL.
changelog_1227_li=Less heap memory is needed when multiple databases are open at the same time\:the memory reserve (used to rollback after out of memory) is now global and no longer allocated for each database separately.
changelog_1228_li=New system property h2.browser to set the browser to use.
changelog_1229_li=To start the browser, java.awt.Desktop.browse is now used if available.
changelog_1230_h2=Version 1.1.102 (2008-10-24)
changelog_1231_li=The French translation of the H2 Console has been improved by Olivier Parent. Thanks a lot\!
changelog_1232_li=There was a memory leak when creating and dropping tables and indexes in a loop (persistent database only).
changelog_1233_li=SET LOG 2 was not effective if executed after opening the database.
changelog_1234_li=Translating the H2 Console is now simpler.
changelog_1235_li=Common exception (error code 23*) are no longer written to the .trace.db file by default.
changelog_1236_li=In-memory databases don't write LOBs to files any longer.
changelog_1237_li=Self referencing constraints didn't restrict deleting rows that reference itself if there is another row that references it.
changelog_1238_li=ResultSetMetaData.getColumnName now returns the alias name except for columns.
changelog_1239_li=Temporary files are now deleted when the database is closed, even if they were not garbage collected so far.
changelog_1240_h2=Version 1.1.101 (2008-10-17)
changelog_1241_li=Errors with code 42000 - 42999 are no longer written to the trace file by default.
changelog_1242_li=Queries with more than 10 tables are now faster.
changelog_1243_li=Opening a connection with AUTO_SERVER\=TRUE is now fast when the database is already open in another process (less than 0.01 seconds instead of 2 seconds).
changelog_1244_li=IF [NOT] EXISTS is supported for named constraints in ALTER TABLE ... ADD/DROP CONSTRAINT.
changelog_1245_li=The error messages have been translated to Spanish by Dario V. Fassi. Thanks a lot\!
changelog_1246_li=Linked tables\:the automatic connection sharing didn't work. Actually the system property h2.shareLinkedConnections was working in the opposite direction\:it was disabled when set to true. Now it works as expected.
changelog_1247_li=Opening large database is now faster.
changelog_1248_li=New system property h2.socketConnectTimeout, the timeout in milliseconds to connect to a server. The default is 2000 (2 seconds).
changelog_1249_li=The wrong parameters were bound to subqueries with parameters, specially when using IN(SELECT ...) and IN(...).
changelog_1250_li=Unset parameters were not detected when the query was re-compiled.
changelog_1251_li=New functions ISO_YEAR, ISO_WEEK, ISO_DAY_OF_WEEK. Thanks a lot to Robert Rathsack for implementing those\!
changelog_1252_li=The date functions DAYOFYEAR, DAYOFMONTH, DAYOFWEEK are now called DAY_OF_YEAR, DAY_OF_MONTH, DAY_OF_WEEK (the old names still work).
changelog_1253_li=An out of memory error while deleting or updating many rows could result in a strange exception.
changelog_1254_li=Linked tables\:compatibility with MS SQL Server has been improved.
changelog_1255_li=Renaming tables that have foreign keys with cascade didn't work correctly.
changelog_1256_li=The auto-reconnect feature didn't work when using the auto-server mode. Fixed.
changelog_1258_li=The optimization to group using an index didn't work in some cases in version 1.1 (see also system property h2.optimizeGroupSorted).
changelog_1259_li=OSGi meta data is included in the manifest file. An OSGi BundleActivator is included\:it loads the database driver when starting the bundle, and unloads it when stopping the bundle.
changelog_1260_li=The default value for MAX_MEMORY_UNDO is now 50000.
changelog_1261_li=For alias columns, ResultSetMetaData.getTableName() and getColumnName() now return the real table and column name in the default mode.
changelog_1262_li=In SQL scripts created with SCRIPT TO, schemas are now only created if they don't exist yet.
changelog_1263_li=After re-connecting to a database, the database event listener (if set) is informed about it.
changelog_1264_li=Local temporary tables now support indexes. Thanks a lot to Matt Roy\!
changelog_1265_li=RUNSCRIPT no longer uses a temporary file.
changelog_1266_li=New system table INFORMATION_SCHEMA.SESSION_STATE containing the SQL statements that make up the session state. The list currently contains variables (SET @..) and local temporary tables (without data).
changelog_1267_li=After an automatic re-connect, part of the session state stays (the part that is stored in the SESSION_STATE table).
changelog_1268_li=The build didn't work if the directory temp didn't exist before.
changelog_1269_li=New system property h2.maxReconnect (default 3) to limit the number of re-connects for the same SQL statement (this is usually only important for SHUTDOWN).
changelog_1270_li=WHERE .. IN (SELECT ...) could throw a NullPointerException.
changelog_1271_li=Improved Glassfish / Toplink support in H2Platform thanks to Marcio Borges from Brazil. Thanks a lot\!
changelog_1272_h2=Version 1.1.100 (2008-10-04)
changelog_1273_li=In version 1.1, the following system properties are now enabled by default\:h2.lobFilesInDirectories, h2.optimizeGroupSorted, h2.optimizeInJoin, h2.shareLinkedConnections
changelog_1274_li=The H2 Console tool now works with the JDBC-ODBC bridge.
changelog_1275_li=The H2 Console tool now supports command line options to start things separately.
changelog_1276_li=Large objects did not work for in-memory databases in server mode in Linux.
changelog_1277_li=Connections from a local address other than 'localhost' were not allowed if remote connections were disabled. This was always a problem, but only got visible in the last release because the server no longer connects to 'localhost' if networked.
changelog_1278_li=The h2console.war can now be built using the Java build.
changelog_1279_li=By default, databases are shared in the same process. For read-only databases this causes unnecessary synchronization, but safes memory. If you want that each connection opens its own database, append ;OPEN_NEW\=TRUE to the database URL.
changelog_1280_li=New auto-reconnect feature will cause the JDBC driver to reconnect to the database if the connection is lost. To enable, append ;AUTO_RECONNECT\=TRUE to the database URL. This is specially helpful when using AUTO_SERVER. AUTO_SERVER automatically uses auto-reconnect.
changelog_1281_li=CreateCluster\:the property 'serverlist' is now called 'serverList'.
changelog_1282_li=The ConvertTraceFile tool could not parse some files because the trace mechanism did not encode prepared statement parameters.
changelog_1283_li=Databases names can now be one character long (the minimum size used to be 2 characters).
changelog_1284_h2=Version 1.0.79 (2008-09-26)
changelog_1285_li=Linked tables that point to the same database can now share the connection within the same database. Access to the same connection is serialized. To enable this feature, set the system property h2.shareLinkedConnections to true.
changelog_1286_li=Multiple processes can now access the same database without having to explicitly start the server. To do that, append ;AUTO_SERVER\=TRUE to the database URL. In this case, the server is started automatically if the connection is in embedded mode, and the server mode is used if a server is running. If the process that opened the first connection is closed, the other client need to reconnect (there is no automatic re-connect so far). Remote connections are allowed, but only to this database.
changelog_1287_li=The server tool now displays the correct IP address if networked.
changelog_1288_li=Can now start a TCP server with port 0 (automatically select a port).
changelog_1289_li=Result sets with just a unique index can now be updated (previously a primary key was required).
changelog_1290_li=LINKED TABLE\:the schema name can now be set. When multiple tables exist in different schema, and the schema name is not set, an exception is thrown.
changelog_1291_li=LINKED TABLE\:worked around a bug in Oracle with the CHAR data type.
changelog_1292_li=Faster hash code calculation for large binary arrays.
changelog_1293_li=Faster storage re-use algorithm thanks to Greg Dhuse from cleversafe.com.
changelog_1294_li=The database supports the SHOW command for better MySQL and PostgreSQL compatibility.
changelog_1295_li=The H2 Console now abbreviates large texts in results.
changelog_1296_li=Multiple UNION queries could not be used in derived tables.
changelog_1297_li=Linked tables can now be read-only.
changelog_1298_li=Temporary linked tables are now supported.
changelog_1299_li=It was possible to create tables in read-only databases.
changelog_1300_li=SET SCHEMA_SEARCH_PATH is now documented.
changelog_1301_li=SET SCHEMA did not work for views.
changelog_1302_li=Row level locking for MVCC is now enabled. The exception 'Concurrent update in table ...' is still thrown, but only after the lock timeout.
changelog_1303_li=The maximum log file size setting was ignored for large databases.
changelog_1304_li=Multi-Version Concurrency (MVCC) may no longer be used when using the multi-threaded kernel feature (MULTI_THREADED). An exception is thrown when trying to connect with both settings. Additional synchronization is required before those features can be used together.
changelog_1305_li=The data type JAVA_OBJECT could not be used in updatable result sets.
changelog_1306_li=The system property h2.optimizeInJoin did not work correctly.
changelog_1307_li=Conditions such as ID\=? AND ID>? were slow.
changelog_1308_h2=Version 1.0.78 (2008-08-28)
changelog_1309_li=The documentation no longer uses a frameset (except the Javadocs).
changelog_1310_li=When using DB_CLOSE_DELAY, sometimes a NullPointerException is thrown when the database is opened almost at the same time as it is closed automatically. Thanks a lot to Dmitry Pekar for finding this\!
changelog_1311_li=Java methods with variable number of parameters can now be used (for Java 1.5 or newer).
changelog_1312_li=The Japanese translation has been improved by Masahiro Ikemoto. Thanks a lot\!
changelog_1313_li=The H2 Console replaced an empty user name with a single space.
changelog_1314_li=The build target 'build jarSmall' now includes the embedded database.
changelog_1315_li=JdbcDataSource now keeps the password in a char array where possible.
changelog_1316_li=ResultSet.absolute did not always work with large result sets.
changelog_1317_li=Column aliases can now be used in GROUP BY and HAVING.
changelog_1318_li=Jason Brittain has contributed MySQL date functions. Thanks a lot\!They are not in the h2.jar file currently, but in src/tools/org/h2/mode/FunctionsMySQL.java. To install, add this class to the classpath and call FunctionsMySQL.register(conn) in the Java code.
changelog_1319_h2=Version 1.0.77 (2008-08-16)
changelog_1320_li=JaQu is now using prepared statements and supports Date, Time, Timestamp.
changelog_1321_li=When using remote in-memory databases, large LOB objects did not work.
changelog_1322_li=Timestamp columns such as TIMESTAMP(6) were not compatible to other database.
changelog_1323_li=Opening a large database was slow if there was a problem opening the previous time.
changelog_1324_li=NOT IN(SELECT ...) was incorrect if the subquery returns no rows.
changelog_1325_li=CREATE TABLE AS SELECT did not work correctly in the multi-version concurrency mode.
changelog_1326_li=Support a comma before closing a list, as in\:create table test(id int,)
changelog_1327_li=MySQL compatibility\:linked tables had lower case column names on some systems.
changelog_1328_li=DB2 compatibility\:the DB2 fetch-first-clause is supported.
changelog_1329_li=Oracle compatibility\:old style outer join syntax using (+) did work correctly sometimes.
changelog_1330_li=ResultSet.setFetchSize is now supported.
changelog_1331_li=It has been reported that when using Install4j on some Linux systems and enabling the 'pack200' option, the h2.jar becomes corrupted by the install process, causing application failure. A workaround is to add an empty file h2.jar.nopack next to the h2.jar file. The reason for this problem is not known.
changelog_1332_h2=Version 1.0.76 (2008-07-27)
changelog_1333_li=The comment of a domain (user defined data type) is now used as the default column comment when creating a column with this domain.
changelog_1334_li=Invalid database names are now detected and a better error message is thrown.
changelog_1335_li=ResultSetMetaData.getColumnClassName now returns the correct class name for BLOB and CLOB.
changelog_1336_li=Fixed the Oracle mode\:Oracle allows multiple rows only where all columns of the unique index are NULL.
changelog_1337_li=There is a problem with Hibernate when using Boolean columns. A patch for Hibernate has been submitted at http\://opensource.atlassian.com/projects/hibernate/browse/HHH-3401
changelog_1338_li=ORDER BY on tableName.columnName didn't work correctly if the column name was also used as an alias.
changelog_1339_li=H2 Console\:the progress display when opening a database has been improved.
changelog_1340_li=The error message when the server doesn't start has been improved.
changelog_1341_li=Key values can now be changed in updatable result sets.
changelog_1342_li=Changes in updatable result sets are now visible even when resetting the result set.
changelog_1343_li=Temporary files were sometimes deleted too late when executing large insert, update, or delete operations.
changelog_1344_li=The database file was growing after deleting many rows, and after large update operations.
changelog_1002_li=Better support GaeVFS (Google App Engine Virtual File System).
changelog_1003_li=JaQu\:the plan is to support natural (pure Java) conditions such as (id \=\=1 && name.equals("Test")). A proof of concept decompiler is now included (it doesn't work yet).
changelog_1004_li=Various bugfixes and improvements in the page store mechanism (still experimental).
changelog_1005_li=PreparedStatement.setObject now converts a java.lang.Character to a string.
changelog_1006_li=H2 Console\:PierPaolo Ucchino has completed the Italian translation. Thanks a lot\!
changelog_1007_li=Various tools now use Java 5 var-args, such as main the methods and SimpleResultSet.addRow.
changelog_1008_li=H2 Console\:indexes of tables of non-default schemas are now also listed.
changelog_1009_li=Issue 111\:Multi-version concurrency / duplicate primary key after rollback.
changelog_1010_li=Issue 110\:Multi-version concurrency / wrong exception is thrown.
changelog_1011_li=Parser\:sequenceName.NEXTVAL and CURRVAL did not respect the schema search path.
changelog_1012_li=Issue 101\:The following sequence could throw the exception "Row not found when trying to delete"\:start a transaction, insert many rows, delete many rows, rollback. The number of rows depends on the cache size.
changelog_1013_li=The stack trace of very common exceptions is no longer written to the .trace.db file by default.
changelog_1014_li=An optimization for OR is implemented, but disabled by default. Expressions of the type X\=1 OR X\=2 are converted to X IN(1, 2). To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver.
changelog_1015_li=An optimization for IN(..) and IN(SELECT...) is implemented, but disabled by default. To enable, set the system property h2.optimizeInList to true before loading the H2 JDBC driver. If enabled, this overrides h2.optimizeIn and h2.optimizeInJoin. Unlike now, this optimization will also speed up updates and deletes.
changelog_1016_h2=Version 1.1.117 (2009-08-09)
changelog_1017_li=New committer\:Sam Van Oort has been contributing to H2 since quite some time in many ways (on the mailing list, documentation, and in the form of patches). He is now a committer.
changelog_1018_li=JaQu\:the order of the fields in the database no longer needs to match the order in the database.
changelog_1019_li=Issue 103\:MVCC\:the setting MAX_MEMORY_UNDO can currently not be supported when using multi-version concurrency, that means the complete undo log must fit in memory.
changelog_1020_li=LIKE\:the escape mechanism can now be disable using ESCAPE ''. The default escape character can be changed using the system property h2.defaultEscape. The default is still '\\' (as in MySQL and PostgreSQL).
changelog_1021_li=Views using functions were not re-evaluated when necessary.
changelog_1022_li=Improved MySQL compatibility for SHOW COLUMNS.
changelog_1023_li=Improved PostgreSQL compatibility for timestamp literals with timezone.
changelog_1024_li=Sergi Vladykin translated the error messages to Russian. Thanks a lot\!
changelog_1025_li=Support for Java 6 DatabaseMetaData.getTables, getColumns, getProcedures, and getProcedureColumns.
changelog_1026_li=Issue 101\:Rollback of a large transaction (more than 100000 rows) could fail.
changelog_1027_li=Various bugfixes and improvements in the page store mechanism (still experimental).
changelog_1028_li=The functions LENGTH, OCTET_LENGTH, and BIT_LENGTH now return BIGINT.
changelog_1029_li=Data types CLOB and BLOB\:the maximum precision was Integer.MAX_VALUE, it is now Long.MAX_VALUE.
changelog_1030_li=Multi-threaded kernel\:creating and dropping temporary database objects and the potentially free pages list was not correctly synchronized. Thanks a lot to Eric Faulhaber for the test case and patch\!
changelog_1031_li=Parsing SQL script files is now faster.
changelog_1032_li=CSV reading is now faster.
changelog_1033_li=SimpleResultSet.newInstance(SimpleRowSource rs) did not work.
changelog_1034_h2=Version 1.1.116 (2009-07-18)
changelog_1035_li=Server-less multi-connection mode\:more bugs are fixed.
changelog_1036_li=The built-in help (INFORMATION_SCHEMA.HELP) is smaller, shrinking the jar file size a bit.
changelog_1037_li=H2 Console\:column of tables of non-default schemas are now also listed, except for schemas starting with 'INFO'.
changelog_1038_li=ALTER TABLE\:removing an auto-increment or identity column didn't remove the sequence.
changelog_1039_li=Creating indexes is now a bit faster.
changelog_1040_li=PG Server\:new system property h2.pgClientEncoding to explicitly set the encoding for clients that don't send the encoding (the default encoding is UTF-8). Thanks a lot to Sergi Vladykin for the patch\!
changelog_1041_li=PG Server\:improved compatibility by using the type ids of the PostgreSQL driver. Thanks a lot to Sergi Vladykin for the patch\!
changelog_1042_li=H2 Console\:Oracle system tables are no longer listed, improving performance.
changelog_1043_li=Result sets are now read-only except if the statement or prepared statement was created with the concurrency ResultSet.CONCUR_UPDATABLE. This change is required because the old behavior (all result set are updatable) violated the JDBC spec. For backward compatibility, use the system property h2.defaultResultSetConcurrency.
changelog_1044_li=New system property h2.defaultResultSetConcurrency to change the default result set concurrency.
changelog_1045_li=JDBC\:using an invalid result set type or concurrency now throws an exception.
changelog_1046_li=If a pooled connection was not closed but garbage collected, a NullPointerException could occur.
changelog_1047_li=Fulltext search\:a NullPointerException was thrown when updating a value that was NULL previously.
changelog_1048_li=The Recover tool did not work with .data.db files of the wrong size.
changelog_1049_li=Triggers\:if there was an exception when initializing a trigger, this exception could be hidden, and in some cases (specially when using the Lucene fulltext index mechanism) a NullPointerException was thrown later on. Now the exception that occurred on init is thrown when changing data.
changelog_1050_li=The soft-references cache (CACHE_TYPE\=SOFT_LRU) could throw a NullPointerException.
changelog_1051_li=To enable the new page store mechanism, append ;PAGE_STORE\=TRUE to the database URL. or set the system property h2.pageStore to true. This mechanism is still experimental, and the file format will change, but it is quite stable now.
changelog_1052_h2=Version 1.1.115 (2009-06-21)
changelog_1053_li=The new storage mechanism is now alpha quality. To try it out, set the system property "h2.pageStore" to "true" (java -Dh2.pageStore\=true). There are still bugs to be found and fixed, for example inserting many rows references a lot of main memory. Performance is currently about the same as with the regular storage mechanism, but the database file size is smaller. The file format is not stable yet.
changelog_1054_li=ALTER TABLE could throw an exception "object already exists" in some cases.
changelog_1055_li=Views\:in some situations, an ArrayIndexOutOfBoundsException was thrown when using the same view concurrently.
changelog_1056_li=java.util.UUID is now supported in PreparedStatement.setObject and user defined Java functions. ResultSet.getObject() returns a java.util.UUID when using the UUID data type.
changelog_1057_li=H2 Console\:the language was reset to the browser language when disconnecting.
changelog_1059_li=Server-less multi-connection mode\:more bugs are fixed.
changelog_1060_li=The download page now included the SHA1 checksums.
changelog_1061_li=Shell tool\:the file encoding workaround is now documented if you run java org.h2.tools.Shell -?.
changelog_1062_li=The RunScript tool and SQL statement did not work with the compression method LZF.
changelog_1063_li=Fulltext search\:searching for NULL or an empty string threw an exception.
changelog_1064_li=Lucene fulltext search\:FTL_DROP_ALL did not drop the triggers.
changelog_1065_li=Backup\:if the database contained CLOB or BLOB data, the backup included a file entry for the LOB directory. This caused the restore to fail.
changelog_1066_li=Data types\:LONG is now an alias for BIGINT.
changelog_1067_h2=Version 1.1.114 (2009-06-01)
changelog_1068_li=ResultSetMetaData.getColumnClassName returned the wrong class for CLOB and BLOB columns.
changelog_1069_li=Fulltext search\:data is no longer deleted and re-inserted if the indexed columns didn't change.
changelog_1070_li=In some situations, an ArrayIndexOutOfBoundsException was thrown when adding rows. This was caused by a bug in the b-tree code.
changelog_1071_li=Microsoft Windows Vista\:when using the the installer, Vista wrote "This program may not have installed correctly." This message should no longer appear (in the h2.nsi file, the line 'RequestExecutionLevel highest' was added).
changelog_1072_li=The Recover tool did not always work when the database contains referential integrity constraints.
changelog_1073_li=Java 1.5 is now required to run H2. If required, Retrotranslator can be used to create a Java 1.4 version (http\://retrotranslator.sourceforge.net/).
changelog_1074_h2=Version 1.1.113 (2009-05-21)
changelog_1075_li=Shell tool\:the built-in commands EXIT, HELP, ?, LIST, and so on didn't work with a semicolon at the end.
changelog_1076_li=JDK 1.5 is now required to build the jar file. However it is still possible to create a jar file for Java 1.4. For details, see buildRelease.sh and buildRelease.bat. As an alternative, compile using JDK 1.5 or 1.6 and use Retrotranslator to create a Java 1.4 version (http\://retrotranslator.sourceforge.net/).
changelog_1077_li=When deleting or updating many rows in a table, the space in the index file was not re-used in the default mode (persistent database, b-tree index, LOG\=1). This caused the index file to grow over time. Workarounds were to delete and re-created the index file, alter the table (add a remove a column), or append ;LOG\=2 to the database URL. To disable the change, set the system property h2.reuseSpaceBtreeIndex to false.
changelog_1078_li=Identifiers with a digit and then a dollar sign didn't work. Example\:A1$B.
changelog_1079_li=MS SQL Server compatibility\:support for linked tables with NVARCHAR, NCHAR, NCLOB, and LONGNVARCHAR.
changelog_1080_li=Android\:workaround for a problem when using read-only databases in zip files (skip seems to be implemented incorrectly on the Android system).
changelog_1081_li=Calling execute() or prepareStatement() with null as the SQL statement now throws an exception.
changelog_1082_li=Benchmark\:the number of executed statements was incorrect. The H2 database was loaded at the beginning of the test to collect results, now it is loaded at the very end. Thanks to Fred Toussi from HSQLDB for reporting those problems. However the changed do not affect the relative performance.
changelog_1083_li=H2 Console\:command line settings are no longer stored in the properties file. They are now only used for the current process, except if they are explicitly saved.
changelog_1084_li=Cache\:support for a second level soft-references cache. To enable it, append ;CACHE_TYPE\=SOFT_LRU (or SOFT_TQ) to the database URL, or set the system property h2.cacheTypeDefault to "SOFT_LRU" / "SOFT_TQ". Enabling the second level cache reduces performance for small databases, but speeds up large databases. It makes sense to use it if the available memory size is unknown. Thanks a lot to Jan Kotek\!
changelog_1085_h2=Version 1.1.112 (2009-05-01)
changelog_1086_li=JdbcPreparedStatement.toString() could throw a NullPointerException.
changelog_1088_li=Connection pool\:the default login timeout is now 5 minutes.
changelog_1089_li=After truncating tables, opening large databases could become slow because indexes were always re-built unnecessarily when opening.
changelog_1090_li=More bugs in the server-less multi-connection mode have been fixed\:Sometimes parameters of prepared statements were lost when a reconnecting. Concurrent read operations were slow. To improve performance, executeQuery(..) must be used for queries (execute(..) switches to the write mode, which is slow).
changelog_1091_li=GROUP BY queries with a self-join (join to the same table) that were grouped by columns with indexes returned the wrong result in some cases.
changelog_1092_li=Improved error message when the .lock.db file modification time is in the future.
changelog_1093_li=The MERGE statement now returns 0 as the generated key if the row was updated.
changelog_1094_li=Running code coverage is now automated.
changelog_1095_li=A file system implementation can now be registered using FileSystem.register.
changelog_1096_li=The database file system is no longer included in the jar file, it moved to the test section.
changelog_1097_h2=Version 1.1.111 (2009-04-10)
changelog_1098_li=In-memory databases can now run inside the Google App Engine.
changelog_1099_li=Queries that are ordered by an indexed column returned no rows in certain cases (if all rows were deleted from the table previously, and there is a low number of rows in the table, and when not using other conditions, and when using the default b tree index).
changelog_1100_li=The wrong exception was thrown when using unquoted text for the SQL statements COMMENT, ALTER USER, and SET PASSWORD.
changelog_1101_li=The built-in connection pool did not roll back transactions and enable autocommit enabled after closing a connection.
changelog_1102_li=Sometimes a StackOverflow occurred when checking for deadlock. See also http\://code.google.com/p/h2database/issues/detail?id\=61
changelog_1103_li=The Shell tool no longer truncates results with only one column, and displays a message if data was truncated.
changelog_1104_h2=Version 1.1.110 (2009-04-03)
changelog_1105_li=Support for not persistent in-memory tables in regular (persistent) databases using CREATE MEMORY TABLE(..) NOT PERSISTENT. Thanks a lot to Sergi Vladykin for the patch\!
changelog_1106_li=The H2 Console trimmed the password (removed leading and trailing spaces). This is no longer the case, to support encrypted H2 database with an empty user password.
changelog_1107_li=The data type of a SUBSTRING method was wrong.
changelog_1108_li=ResultSet.findColumn and get methods with column label parameters now also check for matching column names (like most databases except MySQL).
changelog_1109_li=H2 Console\:the browser system property now supports a list of arguments. Example\:java -Dh2.browser\="open,-a,Safari,%url"...
changelog_1110_li=Improved Javadoc navigation (similar to Scaladoc).
changelog_1111_li=H2 Console\:auto-complete of identifiers did not work correctly for H2 databases in MySQL mode.
changelog_1112_li=DISTINCT and GROUP BY on a CLOB column was broken.
changelog_1113_li=The FTP server moved to the tools section and is no longer included in the h2*.jar file.
changelog_1114_li=Improved error message for unsupported features\:now the message says what exactly is not supported.
changelog_1115_li=Improved OSGi support.
changelog_1116_li=Some internal caches did not use the LRU mechanism. Fixed (LOB file list, optimizer cost cache, trace system, view indexes, collection keys, compressed in-memory file system).
changelog_1117_li=The API of the tools changed a bit (each tool now returns an exit code).
changelog_1118_li=Command line help of the tools now match the javadocs. The build converts the javadocs to a resource that is read by the tool at runtime. This should not have an effect on using the database, but it reduces duplicate and out-of-sync documentation.
changelog_1119_li=CREATE TABLE\:improved compatibility (support for UNIQUE NOT NULL).
changelog_1120_li=DatabaseMetaData.getSQLKeywords now returns the correct list.
changelog_1121_li=Deterministic user defined functions did not work when the parameter was a column. Fixed.
changelog_1122_li=JdbcConnectionPool.setLoginTimeout with 0 now uses the default timeout.
changelog_1123_li=Creating a JdbcConnectionPool has been simplified a bit.
changelog_1124_li=The built-in connection pool did not re-use connections. Getting a connection using the built-in JdbcConnectionPool is now about 70 times faster than opening connections using DriverManager.getConnection.
changelog_1125_li=More bugs in the server-less multi-connection mode have been fixed\:If a process terminated while writing, other open connections were blocked. If two processes were writing to the database, sometimes the database was corrupt after closing.
changelog_1126_li=Linked tables to SQLite database can now be created.
changelog_1127_li=Nested IN(IN(...)) didn't work.
changelog_1128_li=NIO storage\:the nio\:prefix was using memory mapped files instead of FileChannel.
changelog_1129_h2=Version 1.1.109 (2009-03-14)
changelog_1130_li=The optimization for IN(...) is now only used if comparing a column with an index.
changelog_1131_li=User defined functions can now be deterministic (see CREATE ALIAS documentation).
changelog_1132_li=Multiple nested queries in the FROM clause with parameters did not always work.
changelog_1133_li=When converting CLOB to BINARY, each character resulted in one byte. Now, the text is parsed as a hex as when converting VARCHAR.
changelog_1134_li=New experimental NIO storage mechanism with both FileChannel and memory mapped files. To use it, use the file name prefix nio\:or nioMapped\:as in jdbc\:h2\:nio\:~/test. So far it looks like NIO storage is faster on Mac OS but slower on some Windows systems. Thanks a lot to Jan Kotek for the patch\!
changelog_1135_li=The functions BITOR, BITAND, BITXOR, and MOD now accept and return BIGINT instead of INT.
changelog_1136_li=Could not use the same linked table multiple times in the same query.
changelog_1137_li=Bugs in the server-less multi-connection mode have been fixed.
changelog_1138_li=Column names could not be named "UNIQUE" (with the quotes).
changelog_1139_li=New system function TRANSACTION_ID() to get the current transaction identifier for a session.
changelog_1140_h2=Version 1.1.108 (2009-02-28)
changelog_1141_li=When the shutdown hook closed the database, the last log file was deleted too early. This could cause uncommitted changes to be persisted. In some cases, this could cause data corruption.
changelog_1142_li=JdbcConnectionPool\:it was possible to set a negative connection pool size.
changelog_1143_li=Fulltext search did not support table names with a backslash.
changelog_1144_li=The internal IntArray class did not work correctly when initialized with a zero length array.
changelog_1145_li=The H2 Console web application (war file) did only support ASCII characters. Now UTF-8 is supported.
changelog_1146_li=DATEADD does no longer require that the argument is a timestamp.
changelog_1147_li=The database file locking mechanism didn't work correctly on Mac OS.
changelog_1148_li=Some built-in functions reported the wrong precision, scale, and display size.
changelog_1149_li=MySQL compatibility for CREATE TABLE is improved (UNSIGNED, KEY).
changelog_1150_li=Recovery did not work if there were more than 255 lobs stored as files.
changelog_1151_li=New experimental mode to support multiple read-write connections without starting a server. To enable this mode, append ;FILE_LOCK\=SERIALIZED;OPEN_NEW\=TRUE to the database URL. Don't expect high performance when multiple concurrent writers.
changelog_1152_li=In a web application, the database classes are not unloaded if a connection is open. This may cause out of memory when re-deploying a web application. The DbStarter is changed to close all connections to the configured database (by executing SHUTDOWN).
changelog_1153_li=The WebServlet did not close the database when un-deploying the web application.
changelog_1154_li=The exception message of failed INSERT or MERGE statements now includes all values and the row number.
changelog_1155_li=If opening a database failed with an out of memory exception, some files were not closed.
changelog_1156_li=Optimizer\:the expected runtime calculation was incorrect. The fixed calculation should give slightly better query plans when using many joins.
changelog_1157_li=Improved exception message when connecting to a just started server fails.
changelog_1158_li=Connection.isValid is a bit faster.
changelog_1159_li=H2 Console\:the autocomplete feature has been improved a bit. It can now better parse conditions.
changelog_1160_li=When restarting a web application in Tomcat, an exception was thrown sometimes. In most cases this was a NullPointerException. A workaround in H2 has been implemented. The root cause of the problem is now documented in the FAQ\:Tomcat sets all static fields (final or non-final) to null when unloading a web application. A workaround is to put the h2.jar in the lib directory, or set the system property org.apache.catalina.loader.WebappClassLoader.ENABLE_CLEAR_REFERENCES to false.
changelog_1161_h2=Version 1.1.107 (2009-01-24)
changelog_1162_li=Some DatabaseMetaData operations did not work for non-admin users for versions 1.1.x.
changelog_1163_li=The MySQL compatibility extension fromUnixTime now used the English locale.
changelog_1164_li=When using LOG\=2 and repeatedly updating the last row rows of a table, the index file grew quickly.
changelog_1165_li=In versions 1.1.105 and 1.1.106, encrypted script files of earlier versions could not be processed. This is now again possible. The problem was that such script files were stored in a special format (STORAGE\=TEXT) but support for this format was removed in version 1.1.105.
changelog_1166_li=Enabling the trace mechanism by creating a specially named file is no longer supported.
changelog_1167_h2=Version 1.1.106 (2009-01-04)
changelog_1168_li=Statement.setQueryTimeout did not work correctly for some statements.
changelog_1169_li=CREATE DOMAIN\:built-in data types can now only be changed if no tables exist.
changelog_1170_li=Linked tables\:a workaround for Oracle DATE columns has been implemented.
changelog_1171_li=DatabaseMetaData.getPrimaryKeys\:the column PK_NAME now contains the constraint name instead of the index name (compatibility for PostgreSQL and Derby).
changelog_1172_li=Using IN(..) inside a IN(SELECT..) did not always work.
changelog_1173_li=Views with IN(..) that used a view itself did not work.
changelog_1174_li=Union queries with LIMIT or ORDER BY that are used in a view or subquery did not work.
changelog_1175_li=The license change a bit\:so far the license was modified to say 'Swiss law'. This is now changed back to the original 'US law'. This was requested by a user, and I don't see a problem.
changelog_1176_li=Constraints for local temporary tables now session scoped. So far they were global. Thanks a lot to Eric Faulhaber for finding and fixing this problem\!
changelog_1177_li=When using the auto-server mode, and if the lock file was modified in the future, the wrong exception was thrown ('Connection is broken' instead of 'Error opening database\:lock file modified in the future').
changelog_1178_h2=Version 1.1.105 (2008-12-19)
changelog_1179_li=The setting STORAGE\=TEXT is no longer supported.
changelog_1180_li=Deleting a database using the tool DeleteDbFiles deleted LOB files of other databases in the same directory.
changelog_1181_li=When used in a subquery, LIKE and IN(..) did not work correctly sometimes.
changelog_1182_li=The fulltext search documentation has been improved.
changelog_1183_li=ARRAY_GET returned the wrong data type (ARRAY). Now it returns VARCHAR.
changelog_1184_li=Natural join\:the joined columns are not repeated any more when using SELECT *.
changelog_1185_li=User defined aggregate functions\:the method getType expected internal data types instead of SQL types.
changelog_1186_li=User defined aggregate functions did not work if there was no group by expression.
changelog_1187_li=MySQL compatibility\:support for \:\=assignment as in @sum\:\=@sum+x
changelog_1188_li=INSERT INTO TEST(SELECT * FROM TEST) is now supported.
changelog_1189_li=Each session threw an invisible exception when garbage collected.
changelog_1190_li=Foreign key constraints that refer to a quoted column did not work.
changelog_1191_li=New meta data column INFORMATION_SCHEMA.TABLES.LAST_MODIFICATION to get the table modification counter.
changelog_1192_li=Shell\:line comments didn't work correctly.
changelog_1193_li=H2 Console\:columns are now listed for up to 500 tables instead of 100.
changelog_1194_li=H2 Console\:Cmd+Enter executes the current statement, Alt+Space for autocomplete.
changelog_1195_li=JaQu\:the maximum length of a column can now be defined using maxLength. For an example, see Product.java (maxLength(category, 255)).
changelog_1196_li=R&\\\#305;dvan A&\\\#287;ar has completed the Turkish translation of the H2 Console. Thanks a lot\!
changelog_1197_h2=Version 1.1.104 (2008-11-28)
changelog_1198_li=If a query that was used like a table contained group by and was ordered by an expression that is not in the column list, an exception was thrown.
changelog_1199_li=JaQu\:tables are now auto-created when running a query.
changelog_1200_li=The optimizer had problems with function tables (for example CSVREAD and FTL_SEARCH). A new system property h2.estimatedFunctionTableRows (default 1000) defines how many rows can be expected in the table.
changelog_1201_li=The function SUM could overflow when using large values. It returns now a data type that is safe.
changelog_1202_li=The function AVG could overflow when using large values. Fixed.
changelog_1203_li=The emergency reserve file has been removed. It didn't provide an appropriate solution for the problem. It is still possible for an application to detect and deal with the low disk space problem (deleting temporary files for example) using DatabaseEventListener.diskSpaceIsLow, but this method is now always called with stillAvailable\=0.
changelog_1204_li=Build\:JAVA_HOME is now automatically detected on Mac OS X.
changelog_1205_li=Testing for local connections was very slow on some systems.
changelog_1206_li=The cache memory usage calculation is more conservative.
changelog_1207_li=Allocating space got slower and slower the larger the database.
changelog_1208_li=ALTER TABLE ALTER COLUMN could throw the wrong exception in the last version (Table not found).
changelog_1209_li=Updatable result sets\:the key columns can now be updated.
changelog_1210_li=The H2DatabaseProvider for ActiveObjects is now included in the tools section.
changelog_1211_li=The H2Platform for Oracle Toplink Essential has been improved a bit.
changelog_1212_li=The Windows service to start H2 didn't work in version 1.1.
changelog_1213_li=File systems with a maximum file size (for example FAT) are now supported using the file prefix 'split\:'. In this case the files are split in parts of 1 GB. Example URL\:jdbc\:h2\:split\:~/db/test. If you want to split into parts of 1 MB, use jdbc\:h2\:split\:20\:~/db/test (the part size is 1 << x, the default is 30 meaning 1 GB).
changelog_1214_li=The database now tries to detect if the classloader or virtual machine has almost shut down by checking if static final variables are set to null. This should help reduce exceptions when stopping the web application.
changelog_1215_li=Compatibility for MS SQL Server DATEDIFF(YYYY, .., ..)
changelog_1216_li=ResultSet.getObject for CLOB or BLOB will return a java.sql.Clob / java.sql.Blob object instead of a java.io.Reader / java.io.InputStream as in version 1.0. This behavior can be changed using the system property h2.returnLobObjects (true by default for version 1.1).
changelog_1217_li=The interface CloseListener has a new method 'remove' that is called when the trigger is dropped.
changelog_1218_li=Fulltext search\:there was a memory leak when creating and dropping fulltext indexes in a loop.
changelog_1219_h2=Version 1.1.103 (2008-11-07)
changelog_1220_li=Could not order by a formula when the formula was in the group by list but not in the select list.
changelog_1221_li=Date values that match the daylight saving time end were not allowed in times zones were the daylight saving time ends at midnight, for years larger than 2037. Example\:timezone Brasilia, date 2042-10-12. This is a problem of Java, however a workaround is implemented in H2 that solves most problems (except the problems of java.util.Date itself).
changelog_1222_li=ALTER TABLE used a lot of memory when using multi-version concurrency.
changelog_1223_li=Referential integrity for in-memory databases didn't work in some cases in version 1.1.102.
changelog_1224_li=New column INFORMATION_SCHEMA.COLUMNS.SEQUENCE_NAME to get the name of the sequence for auto-increment columns.
changelog_1225_li=Aliases for built-in data types (such as MEDIUMBLOB which is an alias for BLOB) can now be re-mapped to another data type using CREATE DOMAIN. However main built-in data types (such as INTEGER) can not be re-mapped.
changelog_1226_li=The Japanese translation has been completed by Masahiro Ikemoto. Thanks a lot\!
changelog_1227_li=Improved PostgreSQL compatibility for NEXTVAL and CURRVAL.
changelog_1228_li=Less heap memory is needed when multiple databases are open at the same time\:the memory reserve (used to rollback after out of memory) is now global and no longer allocated for each database separately.
changelog_1229_li=New system property h2.browser to set the browser to use.
changelog_1230_li=To start the browser, java.awt.Desktop.browse is now used if available.
changelog_1231_h2=Version 1.1.102 (2008-10-24)
changelog_1232_li=The French translation of the H2 Console has been improved by Olivier Parent. Thanks a lot\!
changelog_1233_li=There was a memory leak when creating and dropping tables and indexes in a loop (persistent database only).
changelog_1234_li=SET LOG 2 was not effective if executed after opening the database.
changelog_1235_li=Translating the H2 Console is now simpler.
changelog_1236_li=Common exception (error code 23*) are no longer written to the .trace.db file by default.
changelog_1237_li=In-memory databases don't write LOBs to files any longer.
changelog_1238_li=Self referencing constraints didn't restrict deleting rows that reference itself if there is another row that references it.
changelog_1239_li=ResultSetMetaData.getColumnName now returns the alias name except for columns.
changelog_1240_li=Temporary files are now deleted when the database is closed, even if they were not garbage collected so far.
changelog_1241_h2=Version 1.1.101 (2008-10-17)
changelog_1242_li=Errors with code 42000 - 42999 are no longer written to the trace file by default.
changelog_1243_li=Queries with more than 10 tables are now faster.
changelog_1244_li=Opening a connection with AUTO_SERVER\=TRUE is now fast when the database is already open in another process (less than 0.01 seconds instead of 2 seconds).
changelog_1245_li=IF [NOT] EXISTS is supported for named constraints in ALTER TABLE ... ADD/DROP CONSTRAINT.
changelog_1246_li=The error messages have been translated to Spanish by Dario V. Fassi. Thanks a lot\!
changelog_1247_li=Linked tables\:the automatic connection sharing didn't work. Actually the system property h2.shareLinkedConnections was working in the opposite direction\:it was disabled when set to true. Now it works as expected.
changelog_1248_li=Opening large database is now faster.
changelog_1249_li=New system property h2.socketConnectTimeout, the timeout in milliseconds to connect to a server. The default is 2000 (2 seconds).
changelog_1250_li=The wrong parameters were bound to subqueries with parameters, specially when using IN(SELECT ...) and IN(...).
changelog_1251_li=Unset parameters were not detected when the query was re-compiled.
changelog_1252_li=New functions ISO_YEAR, ISO_WEEK, ISO_DAY_OF_WEEK. Thanks a lot to Robert Rathsack for implementing those\!
changelog_1253_li=The date functions DAYOFYEAR, DAYOFMONTH, DAYOFWEEK are now called DAY_OF_YEAR, DAY_OF_MONTH, DAY_OF_WEEK (the old names still work).
changelog_1254_li=An out of memory error while deleting or updating many rows could result in a strange exception.
changelog_1255_li=Linked tables\:compatibility with MS SQL Server has been improved.
changelog_1256_li=Renaming tables that have foreign keys with cascade didn't work correctly.
changelog_1257_li=The auto-reconnect feature didn't work when using the auto-server mode. Fixed.
changelog_1259_li=The optimization to group using an index didn't work in some cases in version 1.1 (see also system property h2.optimizeGroupSorted).
changelog_1260_li=OSGi meta data is included in the manifest file. An OSGi BundleActivator is included\:it loads the database driver when starting the bundle, and unloads it when stopping the bundle.
changelog_1261_li=The default value for MAX_MEMORY_UNDO is now 50000.
changelog_1262_li=For alias columns, ResultSetMetaData.getTableName() and getColumnName() now return the real table and column name in the default mode.
changelog_1263_li=In SQL scripts created with SCRIPT TO, schemas are now only created if they don't exist yet.
changelog_1264_li=After re-connecting to a database, the database event listener (if set) is informed about it.
changelog_1265_li=Local temporary tables now support indexes. Thanks a lot to Matt Roy\!
changelog_1266_li=RUNSCRIPT no longer uses a temporary file.
changelog_1267_li=New system table INFORMATION_SCHEMA.SESSION_STATE containing the SQL statements that make up the session state. The list currently contains variables (SET @..) and local temporary tables (without data).
changelog_1268_li=After an automatic re-connect, part of the session state stays (the part that is stored in the SESSION_STATE table).
changelog_1269_li=The build didn't work if the directory temp didn't exist before.
changelog_1270_li=New system property h2.maxReconnect (default 3) to limit the number of re-connects for the same SQL statement (this is usually only important for SHUTDOWN).
changelog_1271_li=WHERE .. IN (SELECT ...) could throw a NullPointerException.
changelog_1272_li=Improved Glassfish / Toplink support in H2Platform thanks to Marcio Borges from Brazil. Thanks a lot\!
changelog_1273_h2=Version 1.1.100 (2008-10-04)
changelog_1274_li=In version 1.1, the following system properties are now enabled by default\:h2.lobFilesInDirectories, h2.optimizeGroupSorted, h2.optimizeInJoin, h2.shareLinkedConnections
changelog_1275_li=The H2 Console tool now works with the JDBC-ODBC bridge.
changelog_1276_li=The H2 Console tool now supports command line options to start things separately.
changelog_1277_li=Large objects did not work for in-memory databases in server mode in Linux.
changelog_1278_li=Connections from a local address other than 'localhost' were not allowed if remote connections were disabled. This was always a problem, but only got visible in the last release because the server no longer connects to 'localhost' if networked.
changelog_1279_li=The h2console.war can now be built using the Java build.
changelog_1280_li=By default, databases are shared in the same process. For read-only databases this causes unnecessary synchronization, but safes memory. If you want that each connection opens its own database, append ;OPEN_NEW\=TRUE to the database URL.
changelog_1281_li=New auto-reconnect feature will cause the JDBC driver to reconnect to the database if the connection is lost. To enable, append ;AUTO_RECONNECT\=TRUE to the database URL. This is specially helpful when using AUTO_SERVER. AUTO_SERVER automatically uses auto-reconnect.
changelog_1282_li=CreateCluster\:the property 'serverlist' is now called 'serverList'.
changelog_1283_li=The ConvertTraceFile tool could not parse some files because the trace mechanism did not encode prepared statement parameters.
changelog_1284_li=Databases names can now be one character long (the minimum size used to be 2 characters).
changelog_1285_h2=Version 1.0.79 (2008-09-26)
changelog_1286_li=Linked tables that point to the same database can now share the connection within the same database. Access to the same connection is serialized. To enable this feature, set the system property h2.shareLinkedConnections to true.
changelog_1287_li=Multiple processes can now access the same database without having to explicitly start the server. To do that, append ;AUTO_SERVER\=TRUE to the database URL. In this case, the server is started automatically if the connection is in embedded mode, and the server mode is used if a server is running. If the process that opened the first connection is closed, the other client need to reconnect (there is no automatic re-connect so far). Remote connections are allowed, but only to this database.
changelog_1288_li=The server tool now displays the correct IP address if networked.
changelog_1289_li=Can now start a TCP server with port 0 (automatically select a port).
changelog_1290_li=Result sets with just a unique index can now be updated (previously a primary key was required).
changelog_1291_li=LINKED TABLE\:the schema name can now be set. When multiple tables exist in different schema, and the schema name is not set, an exception is thrown.
changelog_1292_li=LINKED TABLE\:worked around a bug in Oracle with the CHAR data type.
changelog_1293_li=Faster hash code calculation for large binary arrays.
changelog_1294_li=Faster storage re-use algorithm thanks to Greg Dhuse from cleversafe.com.
changelog_1295_li=The database supports the SHOW command for better MySQL and PostgreSQL compatibility.
changelog_1296_li=The H2 Console now abbreviates large texts in results.
changelog_1297_li=Multiple UNION queries could not be used in derived tables.
changelog_1298_li=Linked tables can now be read-only.
changelog_1299_li=Temporary linked tables are now supported.
changelog_1300_li=It was possible to create tables in read-only databases.
changelog_1301_li=SET SCHEMA_SEARCH_PATH is now documented.
changelog_1302_li=SET SCHEMA did not work for views.
changelog_1303_li=Row level locking for MVCC is now enabled. The exception 'Concurrent update in table ...' is still thrown, but only after the lock timeout.
changelog_1304_li=The maximum log file size setting was ignored for large databases.
changelog_1305_li=Multi-Version Concurrency (MVCC) may no longer be used when using the multi-threaded kernel feature (MULTI_THREADED). An exception is thrown when trying to connect with both settings. Additional synchronization is required before those features can be used together.
changelog_1306_li=The data type JAVA_OBJECT could not be used in updatable result sets.
changelog_1307_li=The system property h2.optimizeInJoin did not work correctly.
changelog_1308_li=Conditions such as ID\=? AND ID>? were slow.
changelog_1309_h2=Version 1.0.78 (2008-08-28)
changelog_1310_li=The documentation no longer uses a frameset (except the Javadocs).
changelog_1311_li=When using DB_CLOSE_DELAY, sometimes a NullPointerException is thrown when the database is opened almost at the same time as it is closed automatically. Thanks a lot to Dmitry Pekar for finding this\!
changelog_1312_li=Java methods with variable number of parameters can now be used (for Java 1.5 or newer).
changelog_1313_li=The Japanese translation has been improved by Masahiro Ikemoto. Thanks a lot\!
changelog_1314_li=The H2 Console replaced an empty user name with a single space.
changelog_1315_li=The build target 'build jarSmall' now includes the embedded database.
changelog_1316_li=JdbcDataSource now keeps the password in a char array where possible.
changelog_1317_li=ResultSet.absolute did not always work with large result sets.
changelog_1318_li=Column aliases can now be used in GROUP BY and HAVING.
changelog_1319_li=Jason Brittain has contributed MySQL date functions. Thanks a lot\!They are not in the h2.jar file currently, but in src/tools/org/h2/mode/FunctionsMySQL.java. To install, add this class to the classpath and call FunctionsMySQL.register(conn) in the Java code.
changelog_1320_h2=Version 1.0.77 (2008-08-16)
changelog_1321_li=JaQu is now using prepared statements and supports Date, Time, Timestamp.
changelog_1322_li=When using remote in-memory databases, large LOB objects did not work.
changelog_1323_li=Timestamp columns such as TIMESTAMP(6) were not compatible to other database.
changelog_1324_li=Opening a large database was slow if there was a problem opening the previous time.
changelog_1325_li=NOT IN(SELECT ...) was incorrect if the subquery returns no rows.
changelog_1326_li=CREATE TABLE AS SELECT did not work correctly in the multi-version concurrency mode.
changelog_1327_li=Support a comma before closing a list, as in\:create table test(id int,)
changelog_1328_li=MySQL compatibility\:linked tables had lower case column names on some systems.
changelog_1329_li=DB2 compatibility\:the DB2 fetch-first-clause is supported.
changelog_1330_li=Oracle compatibility\:old style outer join syntax using (+) did work correctly sometimes.
changelog_1331_li=ResultSet.setFetchSize is now supported.
changelog_1332_li=It has been reported that when using Install4j on some Linux systems and enabling the 'pack200' option, the h2.jar becomes corrupted by the install process, causing application failure. A workaround is to add an empty file h2.jar.nopack next to the h2.jar file. The reason for this problem is not known.
changelog_1333_h2=Version 1.0.76 (2008-07-27)
changelog_1334_li=The comment of a domain (user defined data type) is now used as the default column comment when creating a column with this domain.
changelog_1335_li=Invalid database names are now detected and a better error message is thrown.
changelog_1336_li=ResultSetMetaData.getColumnClassName now returns the correct class name for BLOB and CLOB.
changelog_1337_li=Fixed the Oracle mode\:Oracle allows multiple rows only where all columns of the unique index are NULL.
changelog_1338_li=There is a problem with Hibernate when using Boolean columns. A patch for Hibernate has been submitted at http\://opensource.atlassian.com/projects/hibernate/browse/HHH-3401
changelog_1339_li=ORDER BY on tableName.columnName didn't work correctly if the column name was also used as an alias.
changelog_1340_li=H2 Console\:the progress display when opening a database has been improved.
changelog_1341_li=The error message when the server doesn't start has been improved.
changelog_1342_li=Key values can now be changed in updatable result sets.
changelog_1343_li=Changes in updatable result sets are now visible even when resetting the result set.
changelog_1344_li=Temporary files were sometimes deleted too late when executing large insert, update, or delete operations.
changelog_1345_li=The database file was growing after deleting many rows, and after large update operations.
performance_1399_p=Now convert the .trace.db file using the ConvertTraceFile tool\:
performance_1400_p=The generated file <code>test.sql</code> will contain the SQL statements as well as the following profiling data (results vary)\:
performance_1401_h2=Database Performance Tuning
performance_1402_h3=Virus Scanners
performance_1403_p=Some virus scanners scan files every time they are accessed. It is very important for performance that database files are not scanned for viruses. The database engine does never interprets the data stored in the files as programs, that means even if somebody would store a virus in a database file, this would be harmless (when the virus does not run, it cannot spread). Some virus scanners allow to exclude files by suffix. Make sure files ending with .db are not scanned.
performance_1404_h3=Using the Trace Options
performance_1405_p=If the main performance hot spots are in the database engine, in many cases the performance can be optimized by creating additional indexes, or changing the schema. Sometimes the application does not directly generate the SQL statements, for example if an O/R mapping tool is used. To view the SQL statements and JDBC API calls, you can use the trace options. For more information, see <a href\="features.html\#trace_options">Using the Trace Options</a> .
performance_1406_h3=Index Usage
performance_1407_p=This database uses indexes to improve the performance of SELECT, UPDATE and DELETE statements. If a column is used in the WHERE clause of a query, and if an index exists on this column, then the index can be used. Multi-column indexes are used if all or the first columns of the index are used. Both equality lookup and range scans are supported. Indexes are used to order result sets, but only if the condition uses the same index or no index at all. The results are sorted in memory if required. Indexes are created automatically for primary key and unique constraints. Indexes are also created for foreign key constraints, if required. For other columns, indexes need to be created manually using the CREATE INDEX statement.
performance_1408_h3=Optimizer
performance_1409_p=This database uses a cost based optimizer. For simple and queries and queries with medium complexity (less than 7 tables in the join), the expected cost (running time) of all possible plans is calculated, and the plan with the lowest cost is used. For more complex queries, the algorithm first tries all possible combinations for the first few tables, and the remaining tables added using a greedy algorithm (this works well for most joins). Afterwards a genetic algorithm is used to test at most 2000 distinct plans. Only left-deep plans are evaluated.
performance_1410_h3=Expression Optimization
performance_1411_p=After the statement is parsed, all expressions are simplified automatically if possible. Operations are evaluated only once if all parameters are constant. Functions are also optimized, but only if the function is constant (always returns the same result for the same parameter values). If the WHERE clause is always false, then the table is not accessed at all.
performance_1412_h3=COUNT(*) Optimization
performance_1413_p=If the query only counts all rows of a table, then the data is not accessed. However, this is only possible if no WHERE clause is used, that means it only works for queries of the form SELECT COUNT(*) FROM table.
performance_1415_p=When executing a query, at most one index per joined table can be used. If the same table is joined multiple times, for each join only one index is used. Example\:for the query SELECT * FROM TEST T1, TEST T2 WHERE T1.NAME\='A'AND T2.ID\=T1.ID, two index can be used, in this case the index on NAME for T1 and the index on ID for T2.
performance_1416_p=If a table has multiple indexes, sometimes more than one index could be used. Example\:if there is a table TEST(ID, NAME, FIRSTNAME) and an index on each column, then two indexes could be used for the query SELECT * FROM TEST WHERE NAME\='A'AND FIRSTNAME\='B', the index on NAME or the index on FIRSTNAME. It is not possible to use both indexes at the same time. Which index is used depends on the selectivity of the column. The selectivity describes the 'uniqueness' of values in a column. A selectivity of 100 means each value appears only once, and a selectivity of 1 means the same value appears in many or most rows. For the query above, the index on NAME should be used if the table contains more distinct names than first names.
performance_1417_p=The SQL statement ANALYZE can be used to automatically estimate the selectivity of the columns in the tables. This command should be run from time to time to improve the query plans generated by the optimizer.
performance_1418_h3=In-Memory (Hash) Indexes
performance_1419_p=Using in-memory indexes, specially in-memory hash indexes, can speed up queries and data manipulation.
performance_1420_p=In-memory indexes are automatically used for in-memory databases, but can also be created for persistent databases using <code>CREATE MEMORY TABLE</code> . In many cases, the rows itself will also be kept in-memory. Please note this may cause memory problems for large tables.
performance_1421_p=In-memory hash indexes are backed by a hash table and are usually faster than regular indexes. However, hash indexes only supports direct lookup (WHERE ID \=?) but not range scan (WHERE ID < ?). To use hash indexes, use HASH as in\:<code>CREATE UNIQUE HASH INDEX</code> and <code>CREATE TABLE ...(ID INT PRIMARY KEY HASH,...)</code> .
performance_1422_h3=Optimization Examples
performance_1423_p=See <code>src/test/org/h2/samples/optimizations.sql</code> for a few examples of queries that benefit from special optimizations built into the database.
performance_1424_h3=Cache Size and Type
performance_1425_p=By default the cache size of H2 is quite small. Consider using a larger cache size, or enable the second level soft reference cache. See also <a href\="features.html\#cache_settings">Cache Settings</a> .
performance_1426_h2=Fast Database Import
performance_1427_p=To speed up large imports, consider using the following options temporarily\:
performance_1428_li=SET CACHE_SIZE (a large cache is faster)
performance_1430_li=SET LOG 0 (disable the transaction log)
performance_1431_li=SET UNDO_LOG 0 (disable the session undo log)
performance_1432_p=These options can be set in the database URL\:<code>jdbc\:h2\:~/test;CACHE_SIZE\=65536;LOCK_MODE\=0;LOG\=0;UNDO_LOG\=0</code> . Most of those options are not recommended for regular use, that means you need to reset them after use.
performance_1402_h3=Use a Modern JVM
performance_1403_p=Newer JVMs are faster. Upgrading to the latest version of your JVM can provide a "free" boost to performance. On the Windows platform, switching from the default Client JVM to the Server JVM using the <code>-server</code> command-line option improves performance at the cost of a slight increase in start-up time.
performance_1404_h3=Virus Scanners
performance_1405_p=Some virus scanners scan files every time they are accessed. It is very important for performance that database files are not scanned for viruses. The database engine does never interprets the data stored in the files as programs, that means even if somebody would store a virus in a database file, this would be harmless (when the virus does not run, it cannot spread). Some virus scanners allow to exclude files by suffix. Make sure files ending with .db are not scanned.
performance_1406_h3=Using the Trace Options
performance_1407_p=If the main performance hot spots are in the database engine, in many cases the performance can be optimized by creating additional indexes, or changing the schema. Sometimes the application does not directly generate the SQL statements, for example if an O/R mapping tool is used. To view the SQL statements and JDBC API calls, you can use the trace options. For more information, see <a href\="features.html\#trace_options">Using the Trace Options</a> .
performance_1408_h3=Index Usage
performance_1409_p=This database uses indexes to improve the performance of SELECT, UPDATE and DELETE statements. If a column is used in the WHERE clause of a query, and if an index exists on this column, then the index can be used. Multi-column indexes are used if all or the first columns of the index are used. Both equality lookup and range scans are supported. Indexes are used to order result sets, but only if the condition uses the same index or no index at all. The results are sorted in memory if required. Indexes are created automatically for primary key and unique constraints. Indexes are also created for foreign key constraints, if required. For other columns, indexes need to be created manually using the CREATE INDEX statement.
performance_1410_h3=Optimizer
performance_1411_p=This database uses a cost based optimizer. For simple and queries and queries with medium complexity (less than 7 tables in the join), the expected cost (running time) of all possible plans is calculated, and the plan with the lowest cost is used. For more complex queries, the algorithm first tries all possible combinations for the first few tables, and the remaining tables added using a greedy algorithm (this works well for most joins). Afterwards a genetic algorithm is used to test at most 2000 distinct plans. Only left-deep plans are evaluated.
performance_1412_h3=Expression Optimization
performance_1413_p=After the statement is parsed, all expressions are simplified automatically if possible. Operations are evaluated only once if all parameters are constant. Functions are also optimized, but only if the function is constant (always returns the same result for the same parameter values). If the WHERE clause is always false, then the table is not accessed at all.
performance_1414_h3=COUNT(*) Optimization
performance_1415_p=If the query only counts all rows of a table, then the data is not accessed. However, this is only possible if no WHERE clause is used, that means it only works for queries of the form SELECT COUNT(*) FROM table.
performance_1417_p=When executing a query, at most one index per joined table can be used. If the same table is joined multiple times, for each join only one index is used. Example\:for the query SELECT * FROM TEST T1, TEST T2 WHERE T1.NAME\='A'AND T2.ID\=T1.ID, two index can be used, in this case the index on NAME for T1 and the index on ID for T2.
performance_1418_p=If a table has multiple indexes, sometimes more than one index could be used. Example\:if there is a table TEST(ID, NAME, FIRSTNAME) and an index on each column, then two indexes could be used for the query SELECT * FROM TEST WHERE NAME\='A'AND FIRSTNAME\='B', the index on NAME or the index on FIRSTNAME. It is not possible to use both indexes at the same time. Which index is used depends on the selectivity of the column. The selectivity describes the 'uniqueness' of values in a column. A selectivity of 100 means each value appears only once, and a selectivity of 1 means the same value appears in many or most rows. For the query above, the index on NAME should be used if the table contains more distinct names than first names.
performance_1419_p=The SQL statement ANALYZE can be used to automatically estimate the selectivity of the columns in the tables. This command should be run from time to time to improve the query plans generated by the optimizer.
performance_1420_h3=In-Memory (Hash) Indexes
performance_1421_p=Using in-memory indexes, specially in-memory hash indexes, can speed up queries and data manipulation.
performance_1422_p=In-memory indexes are automatically used for in-memory databases, but can also be created for persistent databases using <code>CREATE MEMORY TABLE</code> . In many cases, the rows itself will also be kept in-memory. Please note this may cause memory problems for large tables.
performance_1423_p=In-memory hash indexes are backed by a hash table and are usually faster than regular indexes. However, hash indexes only supports direct lookup (WHERE ID \=?) but not range scan (WHERE ID < ?). To use hash indexes, use HASH as in\:<code>CREATE UNIQUE HASH INDEX</code> and <code>CREATE TABLE ...(ID INT PRIMARY KEY HASH,...)</code> .
performance_1424_h3=Optimization Examples
performance_1425_p=See <code>src/test/org/h2/samples/optimizations.sql</code> for a few examples of queries that benefit from special optimizations built into the database.
performance_1426_h3=Cache Size and Type
performance_1427_p=By default the cache size of H2 is quite small. Consider using a larger cache size, or enable the second level soft reference cache. See also <a href\="features.html\#cache_settings">Cache Settings</a> .
performance_1428_h3=Data Types
performance_1429_p=Each data type has different storage and performance characteristics\:
performance_1430_li=The DECIMAL/NUMERIC type is slower and requires more storage than the REAL and DOUBLE types.
performance_1431_li=Text types are slower to read, write, and compare than numeric types and generally require more storage.
performance_1432_li=See <a href\="advanced.html\#large_objects">Large Objects</a> for information on BINARY vs. BLOB and VARCHAR vs. CLOB performance.
performance_1433_li=Parsing and formatting takes longer for the TIME, DATE, and TIMESTAMP types than the numeric types.
performance_1434_li=SMALLINT/TINYINT/BOOLEAN are not significantly smaller or faster to work with than INTEGER in most modes.
performance_1435_h2=Fast Database Import
performance_1436_p=To speed up large imports, consider using the following options temporarily\:
performance_1437_li=SET CACHE_SIZE (a large cache is faster)
performance_1439_li=SET LOG 0 (disable the transaction log)
performance_1440_li=SET UNDO_LOG 0 (disable the session undo log)
performance_1441_p=These options can be set in the database URL\:<code>jdbc\:h2\:~/test;CACHE_SIZE\=65536;LOCK_MODE\=0;LOG\=0;UNDO_LOG\=0</code> . Most of those options are not recommended for regular use, that means you need to reset them after use.
