JaQu is now using prepared statements and supports Date, Time, Timestamp.
@changelog_1005_li
When using remote in-memory databases, large LOB objects did not work.
@changelog_1006_li
Timestamp columns such as TIMESTAMP(6) were not compatible to other database.
@changelog_1003_li
@changelog_1007_li
Opening a large database was slow if there was a problem opening the previous time.
@changelog_1004_li
@changelog_1008_li
NOT IN(SELECT ...) was incorrect if the subquery returns no rows.
@changelog_1005_li
@changelog_1009_li
CREATE TABLE AS SELECT did not work correctly in the multi-version concurrency mode.
@changelog_1006_li
@changelog_1010_li
Support a comma before closing a list, as in: create table test(id int,)
@changelog_1007_li
@changelog_1011_li
MySQL compatibility: linked tables had lower case column names on some systems.
@changelog_1008_li
@changelog_1012_li
DB2 compatibility: the DB2 fetch-first-clause is supported.
@changelog_1009_li
@changelog_1013_li
Oracle compatibility: old style outer join syntax using (+) did work correctly sometimes.
@changelog_1010_li
@changelog_1014_li
ResultSet.setFetchSize is now supported.
@changelog_1011_h2
@changelog_1015_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_1016_h2
Version 1.0.76 (2008-07-27)
@changelog_1012_li
@changelog_1017_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_1013_li
@changelog_1018_li
Invalid database names are now detected and a better error message is thrown.
@changelog_1014_li
@changelog_1019_li
ResultSetMetaData.getColumnClassName now returns the correct class name for BLOB and CLOB.
@changelog_1015_li
@changelog_1020_li
Fixed the Oracle mode: Oracle allows multiple rows only where all columns of the unique index are NULL.
@changelog_1016_li
@changelog_1021_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_1017_li
@changelog_1022_li
ORDER BY on tableName.columnName didn't work correctly if the column name was also used as an alias.
@changelog_1018_li
@changelog_1023_li
H2 Console: The progress display when opening a database has been improved.
@changelog_1019_li
@changelog_1024_li
The error message when the server doesn't start has been improved.
@changelog_1020_li
@changelog_1025_li
Key values can now be changed in updatable result sets.
@changelog_1021_li
@changelog_1026_li
Changes in updatable result sets are now visible even when resetting the result set.
@changelog_1022_li
@changelog_1027_li
Temporary files were sometimes deleted too late when executing large insert, update, or delete operations.
@changelog_1023_li
@changelog_1028_li
The database file was growing after deleting many rows, and after large update operations.
@changelog_1024_h2
@changelog_1029_h2
Version 1.0.75 (2008-07-14)
@changelog_1025_li
@changelog_1030_li
Multi version concurrency (MVCC): when a row was updated or deleted, but this change was rolled back, the row was not visible by other sessions if no index was used to access it. Fixed.
@changelog_1026_li
@changelog_1031_li
Views with multiple joined tables (where one was an outer join) couldn't be used in some cases. Fixed.
@changelog_1027_li
@changelog_1032_li
The CSVREAD method did not process NULL correctly when using a whitespace field separator.
@changelog_1028_li
@changelog_1033_li
Fixed the Oracle mode: Oracle allows multiple rows with NULL in a unique index.
@changelog_1029_li
@changelog_1034_li
Running out of memory could result in incomplete transactions or corrupted databases. Fixed.
@changelog_1030_li
@changelog_1035_li
When using order by in a query that uses the same table multiple times, the order could be incorrect. Fixed.
@changelog_1031_li
@changelog_1036_li
Referential constraint checking improvement: now the constraint is only checked if the key column values change.
@changelog_1032_li
@changelog_1037_li
Some database metadata calls returned the wrong data type for DATA_TYPE columns.
@changelog_1033_li
@changelog_1038_li
The Lucene fulltext index was empty when opening a database with fulltext index enabled, and re-indexing it didn't work. Fixed.
@changelog_1034_li
@changelog_1039_li
The character '$' could not be used in identifier names (table name, column names and so on). Fixed.
@changelog_1035_li
@changelog_1040_li
The new method org.h2.tools.Server.startWebServer(conn) starts the H2 Console to inspect a database while debugging.
@changelog_1036_li
@changelog_1041_li
Stopping a WebServer didn't always work. Fixed.
@changelog_1037_h2
@changelog_1042_h2
Version 1.0.74 (2008-06-21)
@changelog_1038_li
@changelog_1043_li
Work on row level locking has been started (but there is nothing usable yet).
@changelog_1039_li
@changelog_1044_li
JaQu (Java Query), a tool similar to LINQ (Language Integrated Query; from Microsoft) is now included under src/tools/org/h2/jaqu. A small sample application is included under src/test/org/h2/test/jaqu.
@changelog_1040_li
@changelog_1045_li
The source code is now switched to Java 1.6 by default. To switch back to Java 1.4, run 'build compile'. The h2.jar file is still Java 1.4.
@changelog_1041_li
@changelog_1046_li
The ChangePassword tool is now called ChangeFileEncryption.
@changelog_1042_li
@changelog_1047_li
It is no longer allowed to create columns with the data type NULL. Also, it is no longer allowed to convert a column to the data type NULL. This was possible before but caused data loss.
@changelog_1043_li
@changelog_1048_li
When using computed columns or default values with a different data type than the column data type, a class cast exception could occur. Fixed.
@changelog_1044_li
@changelog_1049_li
Opening databases larger than 1 GB was sometimes very slow if a lot of data was deleted previously. Fixed.
@changelog_1045_li
@changelog_1050_li
RUNSCRIPT could throw a NullPointerException if the script name was an expression.
@changelog_1046_li
@changelog_1051_li
Improved compatibility. New compatibility modes for Oracle and Derby. New compatibility flag uniqueIndexNullDistinct to only allow one row with 'NULL' in a unique index. This flag is enabled for Derby, Oracle, MSSQLServer, and HSQLDB.
@changelog_1047_li
@changelog_1052_li
Linked tables: To view the statements that are executed against the target table, set the trace level to 3.
@changelog_1048_li
@changelog_1053_li
RunScript tool: new options to show and check the results of queries.
@changelog_1049_li
@changelog_1054_li
Deadlocks are now detected. One transaction is rolled back automatically.
@changelog_1050_li
@changelog_1055_li
The Lucene fulltext index was always re-created when opening a database with fulltext index enabled.
@changelog_1051_li
@changelog_1056_li
Support for overloaded Java methods. A user defined function can now be bound to multiple Java methods, if the Java methods have the same name but a different number of parameters. Thanks to Gary Tong for providing a patch!
@changelog_1052_h2
@changelog_1057_h2
Version 1.0.73 (2008-05-31)
@changelog_1053_li
@changelog_1058_li
ParameterMetaData now returns the right data type for most conditions, as in WHERE ID=?.
@changelog_1054_li
@changelog_1059_li
The table SYSTEM_RANGE now supports expressions and parameters.
@changelog_1055_li
@changelog_1060_li
New column INFORMATION_SCHEMA.CONSTRAINTS.UNIQUE_INDEX_NAME that contains the name of the unique index used to enforce this constraint, if there is such an index.
@changelog_1056_li
@changelog_1061_li
SET QUERY_TIMEOUT and Statement.setQueryTimeout no longer commits a transaction. The same applies to SET @VARIABLE, SET LOCK_TIMEOUT, SET TRACE_LEVEL_*, SET THROTTLE, and SET PATH.
@changelog_1057_li
@changelog_1062_li
The SCRIPT command does now emit IF NOT EXISTS for CREATE ROLE.
@changelog_1058_li
@changelog_1063_li
MySQL compatibility: auto_increment column are no longer automatically converted to primary key columns.
@changelog_1059_li
@changelog_1064_li
PostgreSQL compatibility: support for BOOL_OR and BOOL_AND aggregate functions.
@changelog_1060_li
@changelog_1065_li
Negative scale values for DECIMAL or NUMBER columns are now supported in regular tables and in linked tables.
@changelog_1061_li
@changelog_1066_li
A role or right can now be granted or revoked multiple times without getting an exception.
@changelog_1062_li
@changelog_1067_li
Infinite numbers in SQL scripts are listed as POWER(0, -1)), negative infinite as (-POWER(0, -1)), and NaN (not a number) as SQRT(-1).
@changelog_1063_li
@changelog_1068_li
The special double and float values 'NaN' (not a number) did not work correctly when sorting or comparing.
@changelog_1064_li
@changelog_1069_li
The fulltext search did not support CLOB data types.
@changelog_1065_li
@changelog_1070_li
If the drive with the database files was disconnected or unmounted while writing, sometimes a stack overflow exception was thrown instead of a IO exception.
@changelog_1066_li
@changelog_1071_li
The H2 Console could not be shut down from within the tool if the browser supports keepAlive (most browsers do).
@changelog_1067_li
@changelog_1072_li
If the password was passed as a char array, it was kept in an internal buffer longer than required. Theoretically the password could have been stolen if the main memory was swapped to disk before the garbage collection was run.
@changelog_1068_h2
@changelog_1073_h2
Version 1.0.72 (2008-05-10)
@changelog_1069_li
@changelog_1074_li
Some databases could not be opened when appending ;RECOVER=1 to the database URL.
@changelog_1070_li
@changelog_1075_li
The Japanese translation of the error messages and the H2 Console has been completed by Masahiro Ikemoto (Arizona Design Inc.)
@changelog_1071_li
@changelog_1076_li
Updates made to updatable rows are now visible within the same result set. DatabaseMetaData.ownUpdatesAreVisible now returns true.
@changelog_1072_li
@changelog_1077_li
ParameterMetaData now returns the correct data for INSERT and UPDATE statements.
@changelog_1073_li
@changelog_1078_li
H2 Shell: DESCRIBE now supports an schema name.
@changelog_1074_li
@changelog_1079_li
A subset of the PostgreSQL 'dollar quoting' feature is now supported.
@changelog_1075_li
@changelog_1080_li
SLF4J is now supported by using adding TRACE_LEVEL_FILE=4 to the database URL.
@changelog_1076_li
@changelog_1081_li
The recovery tool did not work if the table name contained spaces or if there was a comment on the table.
@changelog_1077_li
@changelog_1082_li
Triggers are no longer executed when changing the table structure (ALTER TABLE).
@changelog_1078_li
@changelog_1083_li
When setting BLOB or CLOB values larger than 65 KB using a remote connection, temporary files were kept on the client longer than required (until the connection was closed or the object is garbage collected). Now they are removed as soon as the PreparedStatement is closed, or when the value is overwritten.
@changelog_1079_li
@changelog_1084_li
Statements can now be cancelled remotely (when using remote connections).
@changelog_1080_li
@changelog_1085_li
The Shell tool now uses java.io.Console to read the password when using JDK 1.6
@changelog_1081_li
@changelog_1086_li
When using read-only databases and setting LOG=2, an exception was written to the trace file when closing the database. Fixed.
@changelog_1082_h2
@changelog_1087_h2
Version 1.0.71 (2008-04-25)
@changelog_1083_li
@changelog_1088_li
H2 is now dual-licensed under the Eclipse Public License (EPL) and the old 'H2 License' (which is basically MPL).
@changelog_1084_li
@changelog_1089_li
Sometimes an exception 'File ID mismatch' or 'try to add a record twice' occurred after large records (8 KB or larger) are updated or deleted. See also http://code.google.com/p/h2database/issues/detail?id=22
@changelog_1085_li
@changelog_1090_li
H2 Console: The tools can now be translated (it didn't work in the last release).
@changelog_1086_li
@changelog_1091_li
New traditional Chinese translation. Thanks a lot to Derek Chao!
@changelog_1087_li
@changelog_1092_li
Indexes were not used when enabling the optimization for IN(SELECT...) (system property h2.optimizeInJoin).
@changelog_1088_h2
@changelog_1093_h2
Version 1.0.70 (2008-04-20)
@changelog_1089_li
@changelog_1094_li
The plan is to dual-license H2. The additional license is EPL (Eclipse Public License). The current license (MPL, Mozilla Public License) will stay. Current users are not affected because they can keep MPL. EPL is very similar to MPL, the only bigger difference is related to patents (EPL is a bit more business friendly in this regard). See also http://opensource.org/licenses/eclipse-1.0.php, http://www.eclipse.org/legal/eplfaq.php (FAQ), http://blogs.zdnet.com/Burnette/?p=131
@changelog_1090_li
@changelog_1095_li
Multi version concurrency (MVCC): when a row was updated, and the updated column was not indexed, this update was visible sometimes for other sessions even if it was not committed.
@changelog_1091_li
@changelog_1096_li
Calling SHUTDOWN on one connection and starting a query on another connection concurrently could result in a Java level deadlock.
@changelog_1092_li
@changelog_1097_li
New system property h2.enableAnonymousSSL (default: true) to enable anonymous SSL connections.
@changelog_1093_li
@changelog_1098_li
The precision if SUBSTR is now calculated if possible.
@changelog_1094_li
@changelog_1099_li
The autocomplete in the H2 Console has been improved a bit.
@changelog_1095_li
@changelog_1100_li
The tools in the H2 Console are now translatable.
@changelog_1096_li
@changelog_1101_li
The servlet and lucene jar files are now automatically downloaded when building.
@changelog_1097_li
@changelog_1102_li
The code switch tool has been replaced by a simpler tool called SwitchSource that just uses find and replace.
@changelog_1098_li
@changelog_1103_li
Started to write a Ant replacement ('JAnt') that uses pure Java build definitions. Advantages: ability to debug the build, extensible, flexible, no XML, a bit faster. Future plan: support creating custom h2 distributions (for embedded use). Maybe create a new project 'Jant' or 'Javen' if other people are interested.
@changelog_1099_li
@changelog_1104_li
The jar file is now about 10% smaller because the variable debugging info is no longer included. The source file and line number debugging info is still included. If required, the jar file size of the full version can be further reduced to about 720 KB using 'build jarSmall' or even more by removing unneeded components.
@changelog_1100_li
@changelog_1105_li
Added shell scripts run.sh and build.sh. chmod +x is required, but otherwise it should work. Feedback or improvements are welcome!
@changelog_1101_li
@changelog_1106_li
Databases in zip files: large queries are now supported. Temp files are created in the temp directory if required. The documentation how to create the zip file has been corrected.
The Japanese translation of the error messages and the H2 Console has been improved. Thanks a lot to Masahiro IKEMOTO.
@changelog_1104_li
@changelog_1109_li
Optimization for MIN() and MAX() when using MVCC.
@changelog_1105_li
@changelog_1110_li
To protect against remote brute force password attacks, the delay after each unsuccessful login now gets double as long. New system properties h2.delayWrongPasswordMin and h2.delayWrongPasswordMax.
@changelog_1106_li
@changelog_1111_li
After setting the query timeout and then resetting it, the next query would still timeout. Fixed.
@changelog_1107_li
@changelog_1112_li
Adding a IDENTITY column to a table with data threw a lock timeout.
@changelog_1108_li
@changelog_1113_li
OutOfMemoryError could occur when using EXISTS or IN(SELECT ..).
@changelog_1109_li
@changelog_1114_li
The built-in connection pool is not called JdbcConnectionPool. The API and documentation has been changed.
@changelog_1110_li
@changelog_1115_li
The ConvertTraceFile tool now generates SQL statement statistics at the end of the SQL script file (similar to the profiling data generated when using java -Xrunhprof).
@changelog_1111_li
@changelog_1116_li
Nested joins are now supported (A JOIN B JOIN C ON .. ON ..)
@changelog_1112_h2
@changelog_1117_h2
Version 1.0.69 (2008-03-29)
@changelog_1113_li
@changelog_1118_li
Most command line tools can now be called from within the H2 Console.
@changelog_1114_li
@changelog_1119_li
A new Shell tools is now included (org.h2.tools.Shell) to query a database from the command line.
@changelog_1115_li
@changelog_1120_li
The command line options in the tools have changed: instead of '-log true' now '-trace' is used. Also, '-ifExists', '-tcpSSL' and '-tcpAllowOthers' and so on have changed: now the 'true' is no longer needed. The old behavior is still supported.
@changelog_1116_li
@changelog_1121_li
New system property h2.sortNullsHigh to invert the default sorting behavior for NULL. The default didn't change.
@changelog_1117_li
@changelog_1122_li
Performance was very slow when using LOG=2 and deleting or updating all rows of a table in a loop. Fixed.
@changelog_1118_li
@changelog_1123_li
ALTER TABLE or CREATE TABLE now support parameters for the password field.
@changelog_1119_li
@changelog_1124_li
The linear hash has been removed. It was always slower than the b-tree index, and there were some bugs that would be hard to fix.
@changelog_1120_li
@changelog_1125_li
TRACE_LEVEL_ settings are no longer persistent. This was a problem when database initialization code caused a lot of trace output.
@changelog_1121_li
@changelog_1126_li
Fulltext search (native implementation): The words table is no longer an in-memory table because this caused memory problems in some cases.
@changelog_1122_li
@changelog_1127_li
It was possible to create a role with the name as an existing user (but not vice versa). This is not allowed any more.
@changelog_1123_li
@changelog_1128_li
The recovery tool didn't work correctly for tables without rows.
@changelog_1124_li
@changelog_1129_li
For years below 1, the YEAR method didn't return the correct value, and the conversion from date and timestamp to varchar was incorrect.
@changelog_1125_li
@changelog_1130_li
CSVWRITE caused a NullPointerException when not specifying a nullString.
@changelog_1126_li
@changelog_1131_li
When a log file switch occurred just after a truncate table or drop table statement, the database could not be started normally (RECOVER=1 was required). Fixed.
@changelog_1127_li
@changelog_1132_li
When a log file switch occurred in the middle of a sequence flush (sequences are only flushed every 32 values by default), the sequence value was lost. Fixed.
@changelog_1128_li
@changelog_1133_li
Altering a sequence didn't unlock the system table when autocommit switched off.
@changelog_1129_h2
@changelog_1134_h2
Version 1.0.68 (2008-03-18)
@changelog_1130_li
@changelog_1135_li
Very large SELECT DISTINCT and UNION EXCEPT queries are now supported, however this feature is disabled by default. To enable it, set the system property h2.maxMemoryRowsDistinct to a lower value, for example 10000.
@changelog_1131_li
@changelog_1136_li
A error is now thrown when trying to call a method inside a trigger that implicitly commits the current transaction, if an object is locked.
@changelog_1132_li
@changelog_1137_li
Unused LOB files were deleted much too late. Now they are deleted if no longer referenced in memory.
@changelog_1133_li
@changelog_1138_li
ALTER SEQUENCE and ALTER TABLE ALTER COLUMN RESTART can now be used inside a transaction.
@changelog_1134_li
@changelog_1139_li
New system property h2.aliasColumnName. When enabled, aliased columns (as in SELECT ID AS I FROM TEST) return the real table and column name in ResultSetMetaData.getTableName() and getColumnName(). This is disabled by default for compatibility with other databases (HSQLDB, Apache Derby, PostgreSQL, some version of MySQL). In version 1.1 this setting will be enabled.
@changelog_1135_li
@changelog_1140_li
When using encrypted databases, and using the wrong file password, the log file was renamed if the database was not already open. Fixed.
@changelog_1136_li
@changelog_1141_li
Improved performance when using lob files in directories (however this is still disabled by default)
@changelog_1137_li
@changelog_1142_li
H2 Console: autocomplete didn't work with very large scripts. Fixed.
@changelog_1138_li
@changelog_1143_li
Fulltext search: new method SEARCH_DATA that returns the column names and primary keys as arrays.
@changelog_1139_li
@changelog_1144_li
New experimental optimization for GROUP BY queries if an index can be used that matches the group by columns. To enable this optimization, set the system property h2.optimizeGroupSorted to true.
@changelog_1140_li
@changelog_1145_li
When using multi-version concurrency (MVCC=TRUE), duplicate rows could appear in the result set when running queries with uncommitted changes in the same session.
@changelog_1141_li
@changelog_1146_li
H2 Console: remote connections were very slow because getHostName/getRemoteHost was used. Fixed (now using getHostAddress/getRemoteAddr.
@changelog_1142_li
@changelog_1147_li
H2 Console: on Linux, Firefox, Konqueror, or Opera (in this order) are now started if available. This has been tested on Ubuntu.
@changelog_1143_li
@changelog_1148_li
H2 Console: the start window works better with IKVM
@changelog_1144_li
@changelog_1149_li
H2 Console: improved compatibility with Safari (Safari requires keep-alive)
@changelog_1145_li
@changelog_1150_li
Random: the process didn't stop if generating the random seed using the standard way (SecureRandom.generateSeed) was very slow. Now using a daemon thread to avoid this problem.
@changelog_1146_li
@changelog_1151_li
SELECT UNION with a different number of ORDER BY columns did throw an ArrayIndexOutOfBoundsException.
@changelog_1147_li
@changelog_1152_li
When using a view, the column precision was changed to the default scale for some data types.
@changelog_1148_li
@changelog_1153_li
CSVWRITE now supports a 'null string' that is used for parsing and writing NULL.
@changelog_1149_li
@changelog_1154_li
Some long running queries could not be cancelled.
@changelog_1150_li
@changelog_1155_li
Queries with many outer join tables were very slow. Fixed.
@changelog_1151_li
@changelog_1156_li
The performance of text comparison has been improved when using locale sensitive string comparison (SET COLLATOR). Now CollationKey is used with a LRU cache. The default cache size is 10000, and can be changed using the system property h2.collatorCacheSize. Use 0 to disable the cache.
@changelog_1152_li
@changelog_1157_li
UPDATE SET column=DEFAULT is now supported.
@changelog_1153_h2
@changelog_1158_h2
Version 1.0.67 (2008-02-22)
@changelog_1154_li
@changelog_1159_li
New function FILE_READ to read a file or from an URL. Both binary and text data is supported.
@changelog_1155_li
@changelog_1160_li
CREATE TABLE AS SELECT now supports specifying the column list and data types.
@changelog_1156_li
@changelog_1161_li
Connecting to a TCP server and at shutting it down at the same time could cause a Java level deadlock.
@changelog_1157_li
@changelog_1162_li
A user now has all rights on his own local temporary tables.
@changelog_1158_li
@changelog_1163_li
The CSV tool now supports a custom lineSeparator.
@changelog_1159_li
@changelog_1164_li
When using multiple connections, empty space was reused too early sometimes. This could corrupt the database when recovering.
@changelog_1160_li
@changelog_1165_li
The H2 Console has been translated to Dutch. Thanks a lot to Remco Schoen!
@changelog_1161_li
@changelog_1166_li
Databases can now be opened even if trigger classes are not in the classpath. The exception is thrown when trying to fire the trigger.
@changelog_1162_li
@changelog_1167_li
Opening databases with ACCESS_MODE_DATA=r is now supported. In this case the database is read-only, but the files don't not need to be read-only.
@changelog_1163_li
@changelog_1168_li
Security: The database now waits 200 ms before throwing an exception if the user name or password don't match, to slow down dictionary attacks.
@changelog_1164_li
@changelog_1169_li
The value cache is now a soft reference cache. This should help save memory.
@changelog_1165_li
@changelog_1170_li
CREATE INDEX on a table with many rows could run out of memory. Fixed.
@changelog_1166_li
@changelog_1171_li
Large result sets are now a bit faster.
@changelog_1167_li
@changelog_1172_li
ALTER TABLE ALTER COLUMN RESTART and ALTER SEQUENCE now support parameters (any expressions).
@changelog_1168_li
@changelog_1173_li
When setting the base directory on the command line, the user directory prefix ('~') was ignored.
@changelog_1169_li
@changelog_1174_li
The DbStarter servlet didn't start the TCP listener even if configured.
@changelog_1170_li
@changelog_1175_li
Statement.setQueryTimeout() is now supported.
@changelog_1171_li
@changelog_1176_li
New session setting QUERY_TIMEOUT, and new system property h2.maxQueryTimeout.
@changelog_1172_li
@changelog_1177_li
Changing the transaction log level (SET LOG) is now written to the trace file by default.
@changelog_1173_li
@changelog_1178_li
In a SQL script, primary key constraints are now ordered before foreign key constraints.
@changelog_1174_li
@changelog_1179_li
It was not possible to create a referential constraint to a table in a different schema in some situations.
@changelog_1175_li
@changelog_1180_li
The H2 Console was slow when the database contains many tables. Now the column names are not shown in this case.
@changelog_1176_h2
@changelog_1181_h2
Version 1.0.66 (2008-02-02)
@changelog_1177_li
@changelog_1182_li
There is a new online error analyzer tool.
@changelog_1178_li
@changelog_1183_li
H2 Console: stack traces are now links to the source code in the source repository (H2 database only).
@changelog_1179_li
@changelog_1184_li
CHAR data type equals comparison was case insensitive instead of case sensitive.
@changelog_1180_li
@changelog_1185_li
The exception 'Value too long for column' now includes the data.
@changelog_1181_li
@changelog_1186_li
The table name was missing in the documentation of CREATE INDEX.
@changelog_1182_li
@changelog_1187_li
Better support for IKVM (www.ikvm.net): the H2 Console now opens a browser window.
@changelog_1183_li
@changelog_1188_li
The cache size was not correctly calculated for tables with large objects (specially if compression is used). This could lead to out-of-memory exceptions.
@changelog_1184_li
@changelog_1189_li
The exception "Hexadecimal string contains non-hex character" was not always thrown when it should have been. Fixed.
@changelog_1185_li
@changelog_1190_li
The H2 Console now provides a link to the documentation when an error occurs (H2 databases only so far).
@changelog_1186_li
@changelog_1191_li
The acting as PostgreSQL server, when a base directory was set, and the H2 Console was started as well, the base directory was applied twice.
@changelog_1187_li
@changelog_1192_li
Calling EXTRACT(HOUR FROM ...) or EXTRACT(HH FROM ...) returned the wrong values (0 to 11 instead of 0 to 23). All other tested databases return values from 0 to 23. Please check if your application relies on the old behavior before upgrading.
@changelog_1188_li
@changelog_1193_li
For compatibility with other databases the column default (COLUMN_DEF) for columns without default is now null (it was an empty string).
@changelog_1189_li
@changelog_1194_li
Statements that contain very large subqueries (where the subquery result does not fit in memory) are now faster.
@changelog_1190_li
@changelog_1195_li
Variables: large objects (CLOB and BLOB) that don't fit in memory did not work correctly when used as variables.
@changelog_1191_li
@changelog_1196_li
Fulltext search is now supported in named in-memory databases.
@changelog_1192_li
@changelog_1197_li
H2 Console: multiple consecutive spaces in the setting name did not work. Fixed.
@changelog_1193_h2
@changelog_1198_h2
Version 1.0.65 (2008-01-18)
@changelog_1194_li
@changelog_1199_li
The build (ant) now automatically switches the source code to the correct version (JDK 1.4/1.5 or 1.6).
@changelog_1195_li
@changelog_1200_li
A recovery bug has been fixed. With older versions, it was necessary to add ;RECOVER=1 to the database URL in cases where it should not have been required.
@changelog_1196_li
@changelog_1201_li
The performance for DROP and DROP ALL OBJECTS has been improved.
@changelog_1197_li
@changelog_1202_li
The ChangePassword API has been improved.
@changelog_1198_li
@changelog_1203_li
User defined variables are now supported. Examples: SET @VAR=10;CALL @VAR. This can be used for running totals as in: select x, set(@t, ifnull(@t, 0) + x) from system_range(1, 10)
@changelog_1199_li
@changelog_1204_li
The Ukrainian translation has been improved.
@changelog_1200_li
@changelog_1205_li
CALL statements can now be used in batch updates and called using Statement.executeUpdate.
@changelog_1201_li
@changelog_1206_li
New read-only setting CREATE_BUILD (the build number of the database engine that created the database).
@changelog_1202_li
@changelog_1207_li
The optimizer did not use multi column indexes for range queries in some cases. Fixed.
@changelog_1203_li
@changelog_1208_li
The H2 Console now calls DataSource.getConnection() instead of DataSource.getConnection(user, password) when user name and password are not specified.
@changelog_1204_li
@changelog_1209_li
The bind IP address can now be set when using multi-homed host (if multiple network adapters are available) using the system property h2.bindAddress.
@changelog_1205_li
@changelog_1210_li
Batch update: Calling BatchUpdateException.printStackTrace() could result in out of memory. Fixed.
@changelog_1206_li
@changelog_1211_li
Indexes of unique or foreign constraints where not dropped when the constraint was dropped after altering the table (for example dropping a column). Fixed.
@changelog_1207_li
@changelog_1212_li
The performance for large result sets in the server mode has been improved.
@changelog_1208_li
@changelog_1213_li
The setting h2.serverSmallResultSetSize has been renamed to h2.serverResultSetFetchSize.
@changelog_1209_li
@changelog_1214_li
The SCRIPT command now uses multi-row insert statements to save space except if the option SIMPLE is used.
@changelog_1210_li
@changelog_1215_li
The SCRIPT command did not split up CLOB data correctly. Fixed.
@changelog_1211_li
@changelog_1216_li
Optimization for single column distinct queries with an index: select distinct name from test. Can be disabled by setting the system property h2.optimizeDistinct to false.
@changelog_1212_li
@changelog_1217_li
DROP ALL OBJECTS did not drop user defined aggregate functions and domains.
@changelog_1213_li
@changelog_1218_li
PostgreSQL compatibility: COUNT(T.*) is now supported.
@changelog_1214_li
@changelog_1219_li
LIKE comparisons are now faster.
@changelog_1215_li
@changelog_1220_li
Encrypted databases are now faster.
@changelog_1216_h2
@changelog_1221_h2
Version 1.0.64 (2007-12-27)
@changelog_1217_li
@changelog_1222_li
3-way union queries with prepared statement or views could return the wrong results. Fixed.
@changelog_1218_li
@changelog_1223_li
The PostgreSQL ODBC driver did not work in the last release due to a parser regression. Fixed.
@changelog_1219_li
@changelog_1224_li
CSV tool: some escape/separator character combinations did not work. Fixed.
@changelog_1220_li
@changelog_1225_li
CSV tool: the character # could not be used as a separator when reading.
@changelog_1221_li
@changelog_1226_li
Recovery: when the index file is corrupt, now the database deletes it and re-creates it automatically.
@changelog_1222_li
@changelog_1227_li
The MVCC mode did not work well with in-memory databases. Fixed.
@changelog_1223_li
@changelog_1228_li
The FTP server now supports a event listener. Thanks Fulvio Biondi for the help!
@changelog_1224_li
@changelog_1229_li
New system function CANCEL_SESSION to cancel the currently executing statement of another session.
@changelog_1225_li
@changelog_1230_li
The database now supports an exclusive mode. In exclusive mode, new connections are rejected.
@changelog_1226_li
@changelog_1231_li
H2 Console: when editing result sets, columns can now be set to null. The text 'null' must be escaped using '=null'.
@changelog_1227_li
@changelog_1232_li
New built-in functions RPAD and LPAD.
@changelog_1228_li
@changelog_1233_li
New meta data table INFORMATION_SCHEMA.SESSIONS and LOCKS to get information about active connections and locks. Admins will see all connections, non-admins only their own session.
@changelog_1229_li
@changelog_1234_li
The Ukrainian translation was not working in the last release. Fixed.
@changelog_1230_li
@changelog_1235_li
Creating many tables (many hundreds) was slow. Fixed.
@changelog_1231_li
@changelog_1236_li
Opening a database with many indexes (thousands) was slow. Fixed.
@changelog_1232_li
@changelog_1237_li
H2 Console / autocomplete: Ctrl+Space now shows the list in all modes.
@changelog_1233_li
@changelog_1238_li
The method Trigger.init has been changed: the parameters 'before' and 'type', have been added to the init method.
@changelog_1234_li
@changelog_1239_li
The performance has been improved for ResultSet methods with column name.
@changelog_1235_li
@changelog_1240_li
A stack trace was thrown if the system did not provide a quick secure random source and if there is no network or the network settings are not configured. Fixed.
@changelog_1236_li
@changelog_1241_li
The H2 Console has been translated to Turkish. Thanks a lot to Ridvan Agar!
@changelog_1237_li
@changelog_1242_li
Improved debugging support: toString methods of most object now return a meaningful text.
@changelog_1238_li
@changelog_1243_li
The classes DbStarter and WebServlet have been moved to src/main.
@changelog_1239_li
@changelog_1244_li
The column INFORMATION_SCHEMA.TRIGGERS.SQL now contains the CREATE TRIGGER statement.
@changelog_1240_li
@changelog_1245_li
Loading classes and calling methods can be restricted using the new system property h2.allowedClasses.
@changelog_1241_li
@changelog_1246_li
The database could not be used in Java applets due to security exceptions. Fixed.
@changelog_1242_h2
@changelog_1247_h2
Version 1.0.63 (2007-12-02)
@changelog_1243_li
@changelog_1248_li
The SecurePassword example has been improved.
@changelog_1244_li
@changelog_1249_li
In time zones where the summer time saving limit is at midnight, some dates do not work in some virtual machines, for example 2007-10-14 in Chile, using the Sun JVM 1.6.0_03-b05. Fixed.
@changelog_1245_li
@changelog_1250_li
The native fulltext search was not working properly after re-connecting.
@changelog_1246_li
@changelog_1251_li
Improved FTP server: now the PORT command is supported.
@changelog_1247_li
@changelog_1252_li
Temporary views (FROM(...)) with UNION didn't work if nested. Fixed.
@changelog_1248_li
@changelog_1253_li
Performance optimization for IN(...) and IN(SELECT...), currently disabled by default. To enable, use java -Dh2.optimizeInJoin=true
@changelog_1249_li
@changelog_1254_li
The H2 Console has been translated to Ukrainian by Igor Dobrovolskyi. Thanks a lot!
@changelog_1250_li
@changelog_1255_li
New function TABLE_DISTINCT.
@changelog_1251_li
@changelog_1256_li
Using LIMIT with values close to Integer.MAX_VALUE didn't work correctly.
@changelog_1252_li
@changelog_1257_li
Certain setting in the Server didn't work (http://code.google.com/p/h2database/issues/detail?id=7).
@changelog_1253_h2
@changelog_1258_h2
Version 1.0.62 (2007-11-25)
@changelog_1254_li
@changelog_1259_li
Large updates and deletes are now supported by buffering data to disk if required. The threshold is currently set to 100'000 bytes and can be changed using SET MAX_OPERATION_MEMORY or using by appending ;MAX_OPERATION_MEMORY=.. to the database URL. See also the docs.
@changelog_1255_li
@changelog_1260_li
MVCC: now an exception is thrown when an application tries to change the MVCC setting while the database is already open.
@changelog_1256_li
@changelog_1261_li
Referential integrity checks didn't lock the referenced table, and thus could read uncommitted rows of other connections. In that way the referential constraints could get violated (except when using MVCC).
@changelog_1257_li
@changelog_1262_li
Renaming or dropping a user with a schema, or removing the admin property of that user made the schema inaccessible after re-opening the database. Fixed.
@changelog_1258_li
@changelog_1263_li
The H2 Console now also support the command line option -ifExists when started from the Server tool, but only when connecting to H2 databases.
@changelog_1259_li
@changelog_1264_li
Duplicate column names were not detected when renaming columns. Fixed.
@changelog_1260_li
@changelog_1265_li
The console did not display multiple embedded spaces in text correctly. Fixed.
@changelog_1261_li
@changelog_1266_li
Google Android support: use 'ant codeswitchAndroid' to switch the source code to Android.
@changelog_1262_li
@changelog_1267_li
Values of type ARRAY are now sorted as in PostgreSQL.
@changelog_1263_li
@changelog_1268_li
In the cluster mode, could not connect if only one server was running (last release only). Fixed.
@changelog_1264_li
@changelog_1269_li
The performance of large CSV operations has been improved.
@changelog_1265_li
@changelog_1270_li
Now using custom toString() for most JDBC objects and commands.
@changelog_1266_li
@changelog_1271_li
Nested temporary views (SELECT * FROM (SELECT ...)) with parameters didn't work in some cases. Fixed.
@changelog_1267_li
@changelog_1272_li
CSV: Using an empty field delimiter didn't work (a workaround was using char(0)). Fixed.
@changelog_1268_li
@changelog_1273_li
A patch for Apache DDL Utils is available at https://issues.apache.org/jira/browse/DDLUTILS-185
@changelog_1269_li
@changelog_1274_li
The default value for h2.emergencySpaceInitial is now 256 KB (to speed up creating encrypted databases)
@changelog_1270_li
@changelog_1275_li
Eduardo Velasques has translated the H2 Console and the error messages to Brazilian Portuguese. Thanks a lot!
@changelog_1271_li
@changelog_1276_li
Creating a table from GROUP_CONCAT didn't work if the data was longer than 255 characters
@changelog_1272_h2
@changelog_1277_h2
Version 1.0.61 (2007-11-10)
@changelog_1273_li
@changelog_1278_li
The Lucene Fulltext implementation is now compiled and included in the h2.jar. Requires Lucene 2.2.
@changelog_1274_li
@changelog_1279_li
Added more tests. The code coverage is now at 83%.
@changelog_1275_li
@changelog_1280_li
ResultSetMetaData.getColumnDisplaySize was calculated as the longest display size for the given result set, but should be the maximum size that fits in the column. Fixed.
@changelog_1276_li
@changelog_1281_li
The MODE used to be a global setting, now it is a database level setting.
@changelog_1277_li
@changelog_1282_li
The database does now always round to the nearest number when converting a floating point to a integer: CAST(1.5 AS INT) will now result in 2, like in PostgreSQL and MySQL.
@changelog_1278_li
@changelog_1283_li
Math operations using unknown data types (for example -? and ?+?) are now interpreted as decimal.
@changelog_1279_li
@changelog_1284_li
INSTR, LOCATE: backward searching is not supported by using a negative start position.
@changelog_1280_li
@changelog_1285_li
Can now open a database stored in a jar or zip file (for example, jdbc:h2:zip:c:/temp/h2.zip!/test).
@changelog_1281_li
@changelog_1286_li
Files access now uses an API (FileSystem, FileObject), this will simplify adding other file systems and features (for example replication).
@changelog_1282_li
@changelog_1287_li
Vlad Alexahin has translated H2 Console to Russian. Thanks a lot!
@changelog_1283_li
@changelog_1288_li
Descending indexes are now supported. This is useful when sorting columns descending, for example by creation date.
@changelog_1284_li
@changelog_1289_li
Solved a Java level deadlock in the DatabaseCloser.
@changelog_1285_li
@changelog_1290_li
CREATE SEQUENCE: New option CACHE (number of pre-allocated numbers). New column CACHE in the sequence meta data table. The default cache size is still 32.
@changelog_1286_li
@changelog_1291_li
MVCC: The system property h2.mvcc has been removed. A few bugs have been fixed, and new tests have been added.
@changelog_1287_h2
@changelog_1292_h2
Version 1.0.60 (2007-10-20)
@changelog_1288_li
@changelog_1293_li
JdbcXAConnection: starting a transaction before getting the connection didn't switch off autocommit.
@changelog_1289_li
@changelog_1294_li
User defined aggregate functions are not supported.
@changelog_1290_li
@changelog_1295_li
Server.shutdownTcpServer was blocked when first called with force=false and then force=true. Now documentation is improved, and it is no longer blocked.
@changelog_1291_li
@changelog_1296_li
Stack traces did not include the SQL statement in all cases where they could have. Also, stack traces with SQL statement are now shorter.
@changelog_1292_li
@changelog_1297_li
Linked tables: now tables in non-default schemas are supported as well
@changelog_1293_li
@changelog_1298_li
New Italian translation from PierPaolo Ucchino. Thanks a lot!
@changelog_1294_li
@changelog_1299_li
CSV: New methods to set the escape character and field delimiter in the Csv tool and the CSVWRITE and CSVREAD methods.
@changelog_1295_li
@changelog_1300_li
Prepared statements could not be used after data definition statements (creating tables and so on). Fixed.
@changelog_1296_li
@changelog_1301_li
PreparedStatement.setMaxRows could not be changed to a higher value after the statement was executed.
@changelog_1297_li
@changelog_1302_li
The H2 Console could not connect twice to the same H2 embedded database at the same time. Fixed.
@changelog_1298_li
@changelog_1303_li
CSVREAD, RUNSCRIPT and so on now support URLs as well, using URL.openStream(). Example: select * from csvread('jar:file:///c:/temp/test.jar!/test.csv');
@changelog_1299_h2
@changelog_1304_h2
Version 1.0.59 (2007-10-03)
@changelog_1300_li
@changelog_1305_li
When the data type was unknown in a subquery, sometimes the wrong exception (ArrayIndexOutOfBounds) was thrown. Fixed.
@changelog_1301_li
@changelog_1306_li
If the process was killed while the database was running, sometimes the database could not be opened ('double allocation') except when the system property h2.check was set to false. Fixed.
@changelog_1302_li
@changelog_1307_li
Multi-threaded kernel (MULTI_THREADED=1): A synchronization problem has been fixed.
@changelog_1303_li
@changelog_1308_li
A PreparedStatement that was cancelled could not be reused. Fixed.
@changelog_1304_li
@changelog_1309_li
H2 Console: Progress information when logging into a H2 embedded database (useful when opening a database is slow).
@changelog_1305_li
@changelog_1310_li
When the database was closed while logging was disabled (LOG 0), re-opening the database was slow. Fixed.
@changelog_1306_li
@changelog_1311_li
Fulltext search is now documented (in the Tutorial).
@changelog_1307_li
@changelog_1312_li
The Console did not refresh the table list if the CREATE TABLE statement started with a comment. Fixed.
@changelog_1308_li
@changelog_1313_li
When creating a table using CREATE TABLE .. AS SELECT, the precision for some data types (for example VARCHAR) was set to the default precision. Fixed.
@changelog_1309_li
@changelog_1314_li
When using the (undocumented) in-memory file system (jdbc:h2:memFS:x or jdbc:h2:memLZF:x), and using multiple connections, a ConcurrentModificationException could occur. Fixed.
@changelog_1310_li
@changelog_1315_li
REGEXP compatibility: So far String.matches was used, but for compatibility with MySQL, now Matcher.find is used.
@changelog_1311_li
@changelog_1316_li
SCRIPT: the SQL statements in the result set now include the terminating semicolon as well. Simplifies copy and paste.
@changelog_1312_li
@changelog_1317_li
When using a subquery with group by as a table, some columns could not be used in the where condition in the outer query. Example: SELECT * FROM (SELECT ID, COUNT(*) C FROM TEST) WHERE C > 100. Fixed.
@changelog_1313_li
@changelog_1318_li
Views with subqueries as tables and queries with nested subqueries as tables did not always work. Fixed.
@changelog_1314_li
@changelog_1319_li
Compatibility: comparing columns with constants that are out of range does not throw an exception.
@changelog_1315_h2
@changelog_1320_h2
Version 1.0.58 (2007-09-15)
@changelog_1316_li
@changelog_1321_li
System.exit is no longer called by the WebServer, the Console and the Server tool (except to set the exit code if required). This is important when using OSGi.
@changelog_1317_li
@changelog_1322_li
Optimization for independent subqueries. For example, this query can now an index: SELECT * FROM TEST WHERE ID = (SELECT MAX(ID) FROM TEST) This can be disabled by setting the system property h2.optimizeSubqueryCache to false.
@changelog_1318_li
@changelog_1323_li
The explain plan now says: /* direct lookup query */ if the query can be processed directly without reading rows, for example when using MIN(indexed column), MAX(indexed column), or COUNT(*).
@changelog_1319_li
@changelog_1324_li
When using IFNULL, NULLIF, COALESCE, LEAST, or GREATEST, and the first parameter was ?, an exception was thrown. Now the highest data type of all parameters is used.
@changelog_1320_li
@changelog_1325_li
When comparing TINYINT or SMALLINT columns against constants, the index was not used. Fixed.
@changelog_1321_li
@changelog_1326_li
Maven 2: new version are now automatically synced with the central repositories.
@changelog_1322_li
@changelog_1327_li
The default value for MAX_MEMORY_UNDO is now 100000.
@changelog_1323_li
@changelog_1328_li
The documentation indexer does no longer index Japanese pages. If somebody knows how to split Japanese into words please post it.
@changelog_1324_li
@changelog_1329_li
Oracle compatibility: SYSDATE now returns a timestamp. CHR(..) is now an alias for CHAR(..).
@changelog_1325_li
@changelog_1330_li
After deleting data, empty space in the database files was not efficiently reused (but it was reused when opening the database). This has been fixed.
@changelog_1326_li
@changelog_1331_li
About 230 bytes per database was leaked. This is a problem for applications opening and closing many thousand databases. The main problem: a shutdown hook was added but never removed. Fixed. In JDK 1.4, there is <a href="http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=4197876">an additionally problem</a> . A workaround has been implemented.
@changelog_1327_li
@changelog_1332_li
Optimization for COLUMN IN(.., NULL) if the column does not allow NULL values.
@changelog_1328_li
@changelog_1333_li
Using spaces in column and table aliases was not supported when used inside a view or temporary view.
@changelog_1329_li
@changelog_1334_li
The version (build) number is now included in the manifest file.
@changelog_1330_li
@changelog_1335_li
In some systems, SecureRandom.generateSeed is very slow (taking one minute or more). For those cases, an alternative method is used that takes less than one second.
@changelog_1331_li
@changelog_1336_li
The database file sizes are now increased at most 32 MB at any time.
@changelog_1332_li
@changelog_1337_li
New method DatabaseEventListener.opened that is called just after opening a database.
@changelog_1333_li
@changelog_1338_li
When using the Console with Internet Explorer 6.0 or 7.0, a Javascript error was thrown after clearing the query.
@changelog_1334_li
@changelog_1339_li
A database can now be opened even if class of a user defined function is not in the classpath. Trying to call the function will throws an exception.
@changelog_1335_li
@changelog_1340_li
User defined functions and constants may not overload built-in functions and constants. This didn't work before, but now trying to create such an object will fail.
@changelog_1336_li
@changelog_1341_li
Improved MultiDimension tool (for spatial queries): in the last few releases the tool was actually slower than using a regular query (because index lookup got faster, and because the tool didn't support prepared statements) Now the tool generates prepared statements, and the performance is better again (about 5 times faster for a reasonable amount of data).
@changelog_1337_li
@changelog_1342_li
Adding a foreign key or when re-enabling referential integrity for a table failed when checking was enabled and the reference contained NULL.
@changelog_1338_li
@changelog_1343_li
For PgServer, character encoding other than UTF-8 did not work correctly. Fixed.
@changelog_1339_li
@changelog_1344_li
Using a function in a GROUP BY expression that is used in a view as a condition did not always work.
@download_1000_h1
Downloads
@download_1001_h3
Version 1.0.76 (2008-07-28, Current)
Version 1.0.77 (2008-08-16, Current)
@download_1002_a
Windows Installer
...
...
@@ -2135,7 +2150,7 @@ Windows Installer
Platform-Independent Zip
@download_1004_h3
Version 1.0.75 (2008-07-14, Last Stable)
Version 1.0.76 (2008-07-28, Last Stable)
@download_1005_a
Windows Installer
...
...
@@ -2203,154 +2218,157 @@ Usually, bugs get fixes as they are found. There is a release every few weeks. H
@faq_1014_li
Some problems have been found with right outer join. Internally, it is converted to left outer join, which does not always produce the same results as other databases when used in combination with other joins.
@faq_1015_h3
@faq_1015_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.
@faq_1016_h3
Is this Database Engine Open Source?
@faq_1016_p
@faq_1017_p
Yes. It is free to use and distribute, and the source code is included. See also under license.
@faq_1017_h3
@faq_1018_h3
My Query is Slow
@faq_1018_p
@faq_1019_p
Slow SELECT (or DELETE, UPDATE, MERGE) statement can have multiple reasons. Follow this checklist:
@faq_1019_li
@faq_1020_li
Run ANALYSE (see documentation for details).
@faq_1020_li
@faq_1021_li
Run the query with EXPLAIN and check if indexes are used (see documentation for details).
@faq_1021_li
@faq_1022_li
If required, create additional indexes and try again using ANALYZE and EXPLAIN.
@faq_1022_li
@faq_1023_li
If it doesn't help please report the problem.
@faq_1023_h3
@faq_1024_h3
How to Create a New Database?
@faq_1024_p
@faq_1025_p
By default, a new database is automatically created if it does not yet exist.
@faq_1025_h3
@faq_1026_h3
How to Connect to a Database?
@faq_1026_p
@faq_1027_p
The database driver is <code>org.h2.Driver</code> , and the database URL starts with <code>jdbc:h2:</code> . To connect to a database using JDBC, use the following code:
@faq_1027_h3
@faq_1028_h3
Where are the Database Files Stored?
@faq_1028_p
@faq_1029_p
When using database URLs like jdbc:h2:~/test, the database is stored in the user directory. For Windows, this is usually C:\Documents and Settings\<userName>. If the base directory is not set (as in jdbc:h2:test), the database files are stored in the directory where the application is started (the current working directory). When using the H2 Console application from the start menu, this is [Installation Directory]/bin. The base directory can be set in the database URL. A fixed or relative path can be used. When using the URL jdbc:h2:file:data/sample, the database is stored in the directory data (relative to the current working directory). The directory is created automatically if it does not yet exist. It is also possible to use the fully qualified directory (and for Windows, drive) name. Example: jdbc:h2:file:C:/data/test
@faq_1029_h3
@faq_1030_h3
What is the Size Limit (Maximum Size) of a Database?
@faq_1030_p
@faq_1031_p
The theoretical limit is currently 256 GB for the data. This number is excluding BLOB and CLOB data: Every CLOB or BLOB can be up to 256 GB as well. The size limit of the index data is 256 GB as well.
@faq_1031_p
@faq_1032_p
The maximum file size for FAT or FAT32 file systems is 4 GB. So if you use FAT or FAT32, the limit is 4 GB for the data.
@faq_1032_p
@faq_1033_p
The larger the database, the more main memory is required. Currently the minimum main memory required for a 12 GB database is around 240 MB.
@faq_1033_h3
@faq_1034_h3
Is it Reliable?
@faq_1034_p
@faq_1035_p
That is not easy to say. It is still a quite new product. A lot of tests have been written, and the code coverage of these tests is very high. Randomized stress tests are run regularly. But as this is a relatively new product, there are probably some problems that have not yet been found (as with most software). Some features are known to be dangerous by design, and some problems are hard to solve. Those are:
@faq_1035_li
@faq_1036_li
Using SET LOG 0 to disable the transaction log file.
@faq_1036_li
@faq_1037_li
Using the transaction isolation level READ_UNCOMMITTED (LOCK_MODE 0) while at the same time using multiple connections may result in inconsistent transactions.
@faq_1037_li
@faq_1038_li
Using FILE_LOCK=NO in the database URL.
@faq_1038_p
@faq_1039_p
In addition to that, running out of memory should be avoided. In some versions, OutOfMemory errors while using the database could corrupt a databases. Not all such problems may be fixed.
@faq_1039_p
@faq_1040_p
Areas that are not fully tested:
@faq_1040_li
@faq_1041_li
Platforms other than Windows XP and the Sun JVM 1.4 and 1.5
@faq_1041_li
@faq_1042_li
The MVCC (multi version concurrency) mode
@faq_1042_li
@faq_1043_li
Cluster mode, 2-phase commit, savepoints
@faq_1043_li
@faq_1044_li
24/7 operation
@faq_1044_li
@faq_1045_li
Some operations on databases larger than 500 MB may be slower than expected
@faq_1045_li
@faq_1046_li
Updatable result sets
@faq_1046_li
@faq_1047_li
Referential integrity and check constraints, triggers
@faq_1047_li
@faq_1048_li
ALTER TABLE statements, views, linked tables, schema, UNION
@faq_1048_li
@faq_1049_li
Not all built-in functions are completely tested
@faq_1049_li
@faq_1050_li
The optimizer may not always select the best plan
@faq_1050_li
@faq_1051_li
Data types BLOB, CLOB, VARCHAR_IGNORECASE, OTHER
@faq_1051_li
@faq_1052_li
Wide indexes with large VARCHAR or VARBINARY columns and / or with a lot of columns
@faq_1052_li
@faq_1053_li
Multi-threading and using multiple connections
@faq_1053_p
@faq_1054_p
Areas considered Experimental:
@faq_1054_li
@faq_1055_li
The PostgreSQL server
@faq_1055_li
@faq_1056_li
Compatibility modes for other databases (only some features are implemented)
@faq_1056_li
@faq_1057_li
The ARRAY data type and related functionality
@faq_1057_h3
@faq_1058_h3
Why is Opening my Database Slow?
@faq_1058_p
@faq_1059_p
If it takes a long time to open a database, in most cases it was not closed the last time. This is specially a problem for larger databases. To close a database, close all connections to it before the application ends, or execute the command SHUTDOWN. The database is also closed when the virtual machine exits normally by using a shutdown hook. However killing a Java process or calling Runtime.halt will prevent this.
@faq_1059_p
@faq_1060_p
To find out what the problem is, open the database in embedded mode using the H2 Console. This will print progress information. If you have many 'Creating index' lines it is an indication that the database was not closed the last time.
@faq_1060_p
@faq_1061_p
Other possible reasons are: the database is very big (many GB), or contains linked tables that are slow to open.
@faq_1061_h3
@faq_1062_h3
Is the GCJ Version Stable? Faster?
@faq_1062_p
@faq_1063_p
The GCJ version is not as stable as the Java version. When running the regression test with the GCJ version, sometimes the application just stops at what seems to be a random point without error message. Currently, the GCJ version is also slower than when using the Sun VM. However, the startup of the GCJ version is faster than when using a VM.
@faq_1063_h3
@faq_1064_h3
How to Translate this Project?
@faq_1064_p
@faq_1065_p
For more information, see <a href="build.html#translating">Build/Translating</a> .
@features_1000_h1
...
...
@@ -3170,13 +3188,13 @@ In embedded mode, an application opens a database from within the same JVM using
Remote Mode
@features_1272_p
When using the remote mode (sometimes called client/server mode), an application opens a database remotely using the JDBC or ODBC API. A server needs to be started within the same or another virtual machine (or on another computer). Many applications can connect to the same database at the same time. The remote mode is slower than the embedded mode, because all data is transferred over TCP/IP. As in all modes, both persistent and in-memory databases are supported. There is no limit on the number of database open concurrently, or on the number of open connections.
When using the remote mode (sometimes called server mode or client/server mode), an application opens a database remotely using the JDBC or ODBC API. A server needs to be started within the same or another virtual machine (or on another computer). Many applications can connect to the same database at the same time. The remote mode is slower than the embedded mode, because all data is transferred over TCP/IP. As in all modes, both persistent and in-memory databases are supported. There is no limit on the number of database open concurrently, or on the number of open connections.
@features_1273_h3
Mixed Mode
@features_1274_p
The mixed mode is a combination of the embedded and the remote mode. The main application connects to a database in embedded mode, but also starts a server so that other applications (running in different virtual machines) can concurrently access the same data.
The mixed mode is a combination of the embedded and the remote mode. The main application connects to a database in embedded mode, but also starts a server so that other applications (running in different virtual machines) can concurrently access the same data. The embedded connections are as fast as if the database is used in just the embedded mode, while the remote connections are a bit slower.
@features_1275_h2
Database URL Overview
...
...
@@ -5348,7 +5366,7 @@ Small footprint: around 1 MB
#On the command line, go to the directory h2 and execute the following command:
@build_1024_p
#You will get a list of targets. If you want to build the jar file, execute: #JDBC APIを実装し、サーバーにのみ接続するクラスを持つjarファイルをビルドするには、jarCliantターゲットを用います:
#You will get a list of targets. If you want to build the jar file, execute:
@build_1025_h2
#Build Targets
...
...
@@ -1111,1024 +1111,1039 @@ Centralリポジトリの利用
#Next Version (unreleased)
@changelog_1002_li
#-
@changelog_1003_h2
#Version 1.0.77 (2008-08-16)
@changelog_1004_li
#JaQu is now using prepared statements and supports Date, Time, Timestamp.
@changelog_1005_li
#When using remote in-memory databases, large LOB objects did not work.
@changelog_1006_li
#Timestamp columns such as TIMESTAMP(6) were not compatible to other database.
@changelog_1003_li
@changelog_1007_li
#Opening a large database was slow if there was a problem opening the previous time.
@changelog_1004_li
@changelog_1008_li
#NOT IN(SELECT ...) was incorrect if the subquery returns no rows.
@changelog_1005_li
@changelog_1009_li
#CREATE TABLE AS SELECT did not work correctly in the multi-version concurrency mode.
@changelog_1006_li
@changelog_1010_li
#Support a comma before closing a list, as in: create table test(id int,)
@changelog_1007_li
@changelog_1011_li
#MySQL compatibility: linked tables had lower case column names on some systems.
@changelog_1008_li
@changelog_1012_li
#DB2 compatibility: the DB2 fetch-first-clause is supported.
@changelog_1009_li
@changelog_1013_li
#Oracle compatibility: old style outer join syntax using (+) did work correctly sometimes.
@changelog_1010_li
@changelog_1014_li
#ResultSet.setFetchSize is now supported.
@changelog_1011_h2
@changelog_1015_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_1016_h2
#Version 1.0.76 (2008-07-27)
@changelog_1012_li
@changelog_1017_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_1013_li
@changelog_1018_li
#Invalid database names are now detected and a better error message is thrown.
@changelog_1014_li
@changelog_1019_li
#ResultSetMetaData.getColumnClassName now returns the correct class name for BLOB and CLOB.
@changelog_1015_li
@changelog_1020_li
#Fixed the Oracle mode: Oracle allows multiple rows only where all columns of the unique index are NULL.
@changelog_1016_li
@changelog_1021_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_1017_li
@changelog_1022_li
#ORDER BY on tableName.columnName didn't work correctly if the column name was also used as an alias.
@changelog_1018_li
@changelog_1023_li
#H2 Console: The progress display when opening a database has been improved.
@changelog_1019_li
@changelog_1024_li
#The error message when the server doesn't start has been improved.
@changelog_1020_li
@changelog_1025_li
#Key values can now be changed in updatable result sets.
@changelog_1021_li
@changelog_1026_li
#Changes in updatable result sets are now visible even when resetting the result set.
@changelog_1022_li
@changelog_1027_li
#Temporary files were sometimes deleted too late when executing large insert, update, or delete operations.
@changelog_1023_li
@changelog_1028_li
#The database file was growing after deleting many rows, and after large update operations.
@changelog_1024_h2
@changelog_1029_h2
#Version 1.0.75 (2008-07-14)
@changelog_1025_li
@changelog_1030_li
#Multi version concurrency (MVCC): when a row was updated or deleted, but this change was rolled back, the row was not visible by other sessions if no index was used to access it. Fixed.
@changelog_1026_li
@changelog_1031_li
#Views with multiple joined tables (where one was an outer join) couldn't be used in some cases. Fixed.
@changelog_1027_li
@changelog_1032_li
#The CSVREAD method did not process NULL correctly when using a whitespace field separator.
@changelog_1028_li
@changelog_1033_li
#Fixed the Oracle mode: Oracle allows multiple rows with NULL in a unique index.
@changelog_1029_li
@changelog_1034_li
#Running out of memory could result in incomplete transactions or corrupted databases. Fixed.
@changelog_1030_li
@changelog_1035_li
#When using order by in a query that uses the same table multiple times, the order could be incorrect. Fixed.
@changelog_1031_li
@changelog_1036_li
#Referential constraint checking improvement: now the constraint is only checked if the key column values change.
@changelog_1032_li
@changelog_1037_li
#Some database metadata calls returned the wrong data type for DATA_TYPE columns.
@changelog_1033_li
@changelog_1038_li
#The Lucene fulltext index was empty when opening a database with fulltext index enabled, and re-indexing it didn't work. Fixed.
@changelog_1034_li
@changelog_1039_li
#The character '$' could not be used in identifier names (table name, column names and so on). Fixed.
@changelog_1035_li
@changelog_1040_li
#The new method org.h2.tools.Server.startWebServer(conn) starts the H2 Console to inspect a database while debugging.
@changelog_1036_li
@changelog_1041_li
#Stopping a WebServer didn't always work. Fixed.
@changelog_1037_h2
@changelog_1042_h2
#Version 1.0.74 (2008-06-21)
@changelog_1038_li
@changelog_1043_li
#Work on row level locking has been started (but there is nothing usable yet).
@changelog_1039_li
@changelog_1044_li
#JaQu (Java Query), a tool similar to LINQ (Language Integrated Query; from Microsoft) is now included under src/tools/org/h2/jaqu. A small sample application is included under src/test/org/h2/test/jaqu.
@changelog_1040_li
@changelog_1045_li
#The source code is now switched to Java 1.6 by default. To switch back to Java 1.4, run 'build compile'. The h2.jar file is still Java 1.4.
@changelog_1041_li
@changelog_1046_li
#The ChangePassword tool is now called ChangeFileEncryption.
@changelog_1042_li
@changelog_1047_li
#It is no longer allowed to create columns with the data type NULL. Also, it is no longer allowed to convert a column to the data type NULL. This was possible before but caused data loss.
@changelog_1043_li
@changelog_1048_li
#When using computed columns or default values with a different data type than the column data type, a class cast exception could occur. Fixed.
@changelog_1044_li
@changelog_1049_li
#Opening databases larger than 1 GB was sometimes very slow if a lot of data was deleted previously. Fixed.
@changelog_1045_li
@changelog_1050_li
#RUNSCRIPT could throw a NullPointerException if the script name was an expression.
@changelog_1046_li
@changelog_1051_li
#Improved compatibility. New compatibility modes for Oracle and Derby. New compatibility flag uniqueIndexNullDistinct to only allow one row with 'NULL' in a unique index. This flag is enabled for Derby, Oracle, MSSQLServer, and HSQLDB.
@changelog_1047_li
@changelog_1052_li
#Linked tables: To view the statements that are executed against the target table, set the trace level to 3.
@changelog_1048_li
@changelog_1053_li
#RunScript tool: new options to show and check the results of queries.
@changelog_1049_li
@changelog_1054_li
#Deadlocks are now detected. One transaction is rolled back automatically.
@changelog_1050_li
@changelog_1055_li
#The Lucene fulltext index was always re-created when opening a database with fulltext index enabled.
@changelog_1051_li
@changelog_1056_li
#Support for overloaded Java methods. A user defined function can now be bound to multiple Java methods, if the Java methods have the same name but a different number of parameters. Thanks to Gary Tong for providing a patch!
@changelog_1052_h2
@changelog_1057_h2
#Version 1.0.73 (2008-05-31)
@changelog_1053_li
@changelog_1058_li
#ParameterMetaData now returns the right data type for most conditions, as in WHERE ID=?.
@changelog_1054_li
@changelog_1059_li
#The table SYSTEM_RANGE now supports expressions and parameters.
@changelog_1055_li
@changelog_1060_li
#New column INFORMATION_SCHEMA.CONSTRAINTS.UNIQUE_INDEX_NAME that contains the name of the unique index used to enforce this constraint, if there is such an index.
@changelog_1056_li
@changelog_1061_li
#SET QUERY_TIMEOUT and Statement.setQueryTimeout no longer commits a transaction. The same applies to SET @VARIABLE, SET LOCK_TIMEOUT, SET TRACE_LEVEL_*, SET THROTTLE, and SET PATH.
@changelog_1057_li
@changelog_1062_li
#The SCRIPT command does now emit IF NOT EXISTS for CREATE ROLE.
@changelog_1058_li
@changelog_1063_li
#MySQL compatibility: auto_increment column are no longer automatically converted to primary key columns.
@changelog_1059_li
@changelog_1064_li
#PostgreSQL compatibility: support for BOOL_OR and BOOL_AND aggregate functions.
@changelog_1060_li
@changelog_1065_li
#Negative scale values for DECIMAL or NUMBER columns are now supported in regular tables and in linked tables.
@changelog_1061_li
@changelog_1066_li
#A role or right can now be granted or revoked multiple times without getting an exception.
@changelog_1062_li
@changelog_1067_li
#Infinite numbers in SQL scripts are listed as POWER(0, -1)), negative infinite as (-POWER(0, -1)), and NaN (not a number) as SQRT(-1).
@changelog_1063_li
@changelog_1068_li
#The special double and float values 'NaN' (not a number) did not work correctly when sorting or comparing.
@changelog_1064_li
@changelog_1069_li
#The fulltext search did not support CLOB data types.
@changelog_1065_li
@changelog_1070_li
#If the drive with the database files was disconnected or unmounted while writing, sometimes a stack overflow exception was thrown instead of a IO exception.
@changelog_1066_li
@changelog_1071_li
#The H2 Console could not be shut down from within the tool if the browser supports keepAlive (most browsers do).
@changelog_1067_li
@changelog_1072_li
#If the password was passed as a char array, it was kept in an internal buffer longer than required. Theoretically the password could have been stolen if the main memory was swapped to disk before the garbage collection was run.
@changelog_1068_h2
@changelog_1073_h2
#Version 1.0.72 (2008-05-10)
@changelog_1069_li
@changelog_1074_li
#Some databases could not be opened when appending ;RECOVER=1 to the database URL.
@changelog_1070_li
@changelog_1075_li
#The Japanese translation of the error messages and the H2 Console has been completed by Masahiro Ikemoto (Arizona Design Inc.)
@changelog_1071_li
@changelog_1076_li
#Updates made to updatable rows are now visible within the same result set. DatabaseMetaData.ownUpdatesAreVisible now returns true.
@changelog_1072_li
@changelog_1077_li
#ParameterMetaData now returns the correct data for INSERT and UPDATE statements.
@changelog_1073_li
@changelog_1078_li
#H2 Shell: DESCRIBE now supports an schema name.
@changelog_1074_li
@changelog_1079_li
#A subset of the PostgreSQL 'dollar quoting' feature is now supported.
@changelog_1075_li
@changelog_1080_li
#SLF4J is now supported by using adding TRACE_LEVEL_FILE=4 to the database URL.
@changelog_1076_li
@changelog_1081_li
#The recovery tool did not work if the table name contained spaces or if there was a comment on the table.
@changelog_1077_li
@changelog_1082_li
#Triggers are no longer executed when changing the table structure (ALTER TABLE).
@changelog_1078_li
@changelog_1083_li
#When setting BLOB or CLOB values larger than 65 KB using a remote connection, temporary files were kept on the client longer than required (until the connection was closed or the object is garbage collected). Now they are removed as soon as the PreparedStatement is closed, or when the value is overwritten.
@changelog_1079_li
@changelog_1084_li
#Statements can now be cancelled remotely (when using remote connections).
@changelog_1080_li
@changelog_1085_li
#The Shell tool now uses java.io.Console to read the password when using JDK 1.6
@changelog_1081_li
@changelog_1086_li
#When using read-only databases and setting LOG=2, an exception was written to the trace file when closing the database. Fixed.
@changelog_1082_h2
@changelog_1087_h2
#Version 1.0.71 (2008-04-25)
@changelog_1083_li
@changelog_1088_li
#H2 is now dual-licensed under the Eclipse Public License (EPL) and the old 'H2 License' (which is basically MPL).
@changelog_1084_li
@changelog_1089_li
#Sometimes an exception 'File ID mismatch' or 'try to add a record twice' occurred after large records (8 KB or larger) are updated or deleted. See also http://code.google.com/p/h2database/issues/detail?id=22
@changelog_1085_li
@changelog_1090_li
#H2 Console: The tools can now be translated (it didn't work in the last release).
@changelog_1086_li
@changelog_1091_li
#New traditional Chinese translation. Thanks a lot to Derek Chao!
@changelog_1087_li
@changelog_1092_li
#Indexes were not used when enabling the optimization for IN(SELECT...) (system property h2.optimizeInJoin).
@changelog_1088_h2
@changelog_1093_h2
#Version 1.0.70 (2008-04-20)
@changelog_1089_li
@changelog_1094_li
#The plan is to dual-license H2. The additional license is EPL (Eclipse Public License). The current license (MPL, Mozilla Public License) will stay. Current users are not affected because they can keep MPL. EPL is very similar to MPL, the only bigger difference is related to patents (EPL is a bit more business friendly in this regard). See also http://opensource.org/licenses/eclipse-1.0.php, http://www.eclipse.org/legal/eplfaq.php (FAQ), http://blogs.zdnet.com/Burnette/?p=131
@changelog_1090_li
@changelog_1095_li
#Multi version concurrency (MVCC): when a row was updated, and the updated column was not indexed, this update was visible sometimes for other sessions even if it was not committed.
@changelog_1091_li
@changelog_1096_li
#Calling SHUTDOWN on one connection and starting a query on another connection concurrently could result in a Java level deadlock.
@changelog_1092_li
@changelog_1097_li
#New system property h2.enableAnonymousSSL (default: true) to enable anonymous SSL connections.
@changelog_1093_li
@changelog_1098_li
#The precision if SUBSTR is now calculated if possible.
@changelog_1094_li
@changelog_1099_li
#The autocomplete in the H2 Console has been improved a bit.
@changelog_1095_li
@changelog_1100_li
#The tools in the H2 Console are now translatable.
@changelog_1096_li
@changelog_1101_li
#The servlet and lucene jar files are now automatically downloaded when building.
@changelog_1097_li
@changelog_1102_li
#The code switch tool has been replaced by a simpler tool called SwitchSource that just uses find and replace.
@changelog_1098_li
@changelog_1103_li
#Started to write a Ant replacement ('JAnt') that uses pure Java build definitions. Advantages: ability to debug the build, extensible, flexible, no XML, a bit faster. Future plan: support creating custom h2 distributions (for embedded use). Maybe create a new project 'Jant' or 'Javen' if other people are interested.
@changelog_1099_li
@changelog_1104_li
#The jar file is now about 10% smaller because the variable debugging info is no longer included. The source file and line number debugging info is still included. If required, the jar file size of the full version can be further reduced to about 720 KB using 'build jarSmall' or even more by removing unneeded components.
@changelog_1100_li
@changelog_1105_li
#Added shell scripts run.sh and build.sh. chmod +x is required, but otherwise it should work. Feedback or improvements are welcome!
@changelog_1101_li
@changelog_1106_li
#Databases in zip files: large queries are now supported. Temp files are created in the temp directory if required. The documentation how to create the zip file has been corrected.
#The Japanese translation of the error messages and the H2 Console has been improved. Thanks a lot to Masahiro IKEMOTO.
@changelog_1104_li
@changelog_1109_li
#Optimization for MIN() and MAX() when using MVCC.
@changelog_1105_li
@changelog_1110_li
#To protect against remote brute force password attacks, the delay after each unsuccessful login now gets double as long. New system properties h2.delayWrongPasswordMin and h2.delayWrongPasswordMax.
@changelog_1106_li
@changelog_1111_li
#After setting the query timeout and then resetting it, the next query would still timeout. Fixed.
@changelog_1107_li
@changelog_1112_li
#Adding a IDENTITY column to a table with data threw a lock timeout.
@changelog_1108_li
@changelog_1113_li
#OutOfMemoryError could occur when using EXISTS or IN(SELECT ..).
@changelog_1109_li
@changelog_1114_li
#The built-in connection pool is not called JdbcConnectionPool. The API and documentation has been changed.
@changelog_1110_li
@changelog_1115_li
#The ConvertTraceFile tool now generates SQL statement statistics at the end of the SQL script file (similar to the profiling data generated when using java -Xrunhprof).
@changelog_1111_li
@changelog_1116_li
#Nested joins are now supported (A JOIN B JOIN C ON .. ON ..)
@changelog_1112_h2
@changelog_1117_h2
#Version 1.0.69 (2008-03-29)
@changelog_1113_li
@changelog_1118_li
#Most command line tools can now be called from within the H2 Console.
@changelog_1114_li
@changelog_1119_li
#A new Shell tools is now included (org.h2.tools.Shell) to query a database from the command line.
@changelog_1115_li
@changelog_1120_li
#The command line options in the tools have changed: instead of '-log true' now '-trace' is used. Also, '-ifExists', '-tcpSSL' and '-tcpAllowOthers' and so on have changed: now the 'true' is no longer needed. The old behavior is still supported.
@changelog_1116_li
@changelog_1121_li
#New system property h2.sortNullsHigh to invert the default sorting behavior for NULL. The default didn't change.
@changelog_1117_li
@changelog_1122_li
#Performance was very slow when using LOG=2 and deleting or updating all rows of a table in a loop. Fixed.
@changelog_1118_li
@changelog_1123_li
#ALTER TABLE or CREATE TABLE now support parameters for the password field.
@changelog_1119_li
@changelog_1124_li
#The linear hash has been removed. It was always slower than the b-tree index, and there were some bugs that would be hard to fix.
@changelog_1120_li
@changelog_1125_li
#TRACE_LEVEL_ settings are no longer persistent. This was a problem when database initialization code caused a lot of trace output.
@changelog_1121_li
@changelog_1126_li
#Fulltext search (native implementation): The words table is no longer an in-memory table because this caused memory problems in some cases.
@changelog_1122_li
@changelog_1127_li
#It was possible to create a role with the name as an existing user (but not vice versa). This is not allowed any more.
@changelog_1123_li
@changelog_1128_li
#The recovery tool didn't work correctly for tables without rows.
@changelog_1124_li
@changelog_1129_li
#For years below 1, the YEAR method didn't return the correct value, and the conversion from date and timestamp to varchar was incorrect.
@changelog_1125_li
@changelog_1130_li
#CSVWRITE caused a NullPointerException when not specifying a nullString.
@changelog_1126_li
@changelog_1131_li
#When a log file switch occurred just after a truncate table or drop table statement, the database could not be started normally (RECOVER=1 was required). Fixed.
@changelog_1127_li
@changelog_1132_li
#When a log file switch occurred in the middle of a sequence flush (sequences are only flushed every 32 values by default), the sequence value was lost. Fixed.
@changelog_1128_li
@changelog_1133_li
#Altering a sequence didn't unlock the system table when autocommit switched off.
@changelog_1129_h2
@changelog_1134_h2
#Version 1.0.68 (2008-03-18)
@changelog_1130_li
@changelog_1135_li
#Very large SELECT DISTINCT and UNION EXCEPT queries are now supported, however this feature is disabled by default. To enable it, set the system property h2.maxMemoryRowsDistinct to a lower value, for example 10000.
@changelog_1131_li
@changelog_1136_li
#A error is now thrown when trying to call a method inside a trigger that implicitly commits the current transaction, if an object is locked.
@changelog_1132_li
@changelog_1137_li
#Unused LOB files were deleted much too late. Now they are deleted if no longer referenced in memory.
@changelog_1133_li
@changelog_1138_li
#ALTER SEQUENCE and ALTER TABLE ALTER COLUMN RESTART can now be used inside a transaction.
@changelog_1134_li
@changelog_1139_li
#New system property h2.aliasColumnName. When enabled, aliased columns (as in SELECT ID AS I FROM TEST) return the real table and column name in ResultSetMetaData.getTableName() and getColumnName(). This is disabled by default for compatibility with other databases (HSQLDB, Apache Derby, PostgreSQL, some version of MySQL). In version 1.1 this setting will be enabled.
@changelog_1135_li
@changelog_1140_li
#When using encrypted databases, and using the wrong file password, the log file was renamed if the database was not already open. Fixed.
@changelog_1136_li
@changelog_1141_li
#Improved performance when using lob files in directories (however this is still disabled by default)
@changelog_1137_li
@changelog_1142_li
#H2 Console: autocomplete didn't work with very large scripts. Fixed.
@changelog_1138_li
@changelog_1143_li
#Fulltext search: new method SEARCH_DATA that returns the column names and primary keys as arrays.
@changelog_1139_li
@changelog_1144_li
#New experimental optimization for GROUP BY queries if an index can be used that matches the group by columns. To enable this optimization, set the system property h2.optimizeGroupSorted to true.
@changelog_1140_li
@changelog_1145_li
#When using multi-version concurrency (MVCC=TRUE), duplicate rows could appear in the result set when running queries with uncommitted changes in the same session.
@changelog_1141_li
@changelog_1146_li
#H2 Console: remote connections were very slow because getHostName/getRemoteHost was used. Fixed (now using getHostAddress/getRemoteAddr.
@changelog_1142_li
@changelog_1147_li
#H2 Console: on Linux, Firefox, Konqueror, or Opera (in this order) are now started if available. This has been tested on Ubuntu.
@changelog_1143_li
@changelog_1148_li
#H2 Console: the start window works better with IKVM
@changelog_1144_li
@changelog_1149_li
#H2 Console: improved compatibility with Safari (Safari requires keep-alive)
@changelog_1145_li
@changelog_1150_li
#Random: the process didn't stop if generating the random seed using the standard way (SecureRandom.generateSeed) was very slow. Now using a daemon thread to avoid this problem.
@changelog_1146_li
@changelog_1151_li
#SELECT UNION with a different number of ORDER BY columns did throw an ArrayIndexOutOfBoundsException.
@changelog_1147_li
@changelog_1152_li
#When using a view, the column precision was changed to the default scale for some data types.
@changelog_1148_li
@changelog_1153_li
#CSVWRITE now supports a 'null string' that is used for parsing and writing NULL.
@changelog_1149_li
@changelog_1154_li
#Some long running queries could not be cancelled.
@changelog_1150_li
@changelog_1155_li
#Queries with many outer join tables were very slow. Fixed.
@changelog_1151_li
@changelog_1156_li
#The performance of text comparison has been improved when using locale sensitive string comparison (SET COLLATOR). Now CollationKey is used with a LRU cache. The default cache size is 10000, and can be changed using the system property h2.collatorCacheSize. Use 0 to disable the cache.
@changelog_1152_li
@changelog_1157_li
#UPDATE SET column=DEFAULT is now supported.
@changelog_1153_h2
@changelog_1158_h2
#Version 1.0.67 (2008-02-22)
@changelog_1154_li
@changelog_1159_li
#New function FILE_READ to read a file or from an URL. Both binary and text data is supported.
@changelog_1155_li
@changelog_1160_li
#CREATE TABLE AS SELECT now supports specifying the column list and data types.
@changelog_1156_li
@changelog_1161_li
#Connecting to a TCP server and at shutting it down at the same time could cause a Java level deadlock.
@changelog_1157_li
@changelog_1162_li
#A user now has all rights on his own local temporary tables.
@changelog_1158_li
@changelog_1163_li
#The CSV tool now supports a custom lineSeparator.
@changelog_1159_li
@changelog_1164_li
#When using multiple connections, empty space was reused too early sometimes. This could corrupt the database when recovering.
@changelog_1160_li
@changelog_1165_li
#The H2 Console has been translated to Dutch. Thanks a lot to Remco Schoen!
@changelog_1161_li
@changelog_1166_li
#Databases can now be opened even if trigger classes are not in the classpath. The exception is thrown when trying to fire the trigger.
@changelog_1162_li
@changelog_1167_li
#Opening databases with ACCESS_MODE_DATA=r is now supported. In this case the database is read-only, but the files don't not need to be read-only.
@changelog_1163_li
@changelog_1168_li
#Security: The database now waits 200 ms before throwing an exception if the user name or password don't match, to slow down dictionary attacks.
@changelog_1164_li
@changelog_1169_li
#The value cache is now a soft reference cache. This should help save memory.
@changelog_1165_li
@changelog_1170_li
#CREATE INDEX on a table with many rows could run out of memory. Fixed.
@changelog_1166_li
@changelog_1171_li
#Large result sets are now a bit faster.
@changelog_1167_li
@changelog_1172_li
#ALTER TABLE ALTER COLUMN RESTART and ALTER SEQUENCE now support parameters (any expressions).
@changelog_1168_li
@changelog_1173_li
#When setting the base directory on the command line, the user directory prefix ('~') was ignored.
@changelog_1169_li
@changelog_1174_li
#The DbStarter servlet didn't start the TCP listener even if configured.
@changelog_1170_li
@changelog_1175_li
#Statement.setQueryTimeout() is now supported.
@changelog_1171_li
@changelog_1176_li
#New session setting QUERY_TIMEOUT, and new system property h2.maxQueryTimeout.
@changelog_1172_li
@changelog_1177_li
#Changing the transaction log level (SET LOG) is now written to the trace file by default.
@changelog_1173_li
@changelog_1178_li
#In a SQL script, primary key constraints are now ordered before foreign key constraints.
@changelog_1174_li
@changelog_1179_li
#It was not possible to create a referential constraint to a table in a different schema in some situations.
@changelog_1175_li
@changelog_1180_li
#The H2 Console was slow when the database contains many tables. Now the column names are not shown in this case.
@changelog_1176_h2
@changelog_1181_h2
#Version 1.0.66 (2008-02-02)
@changelog_1177_li
@changelog_1182_li
#There is a new online error analyzer tool.
@changelog_1178_li
@changelog_1183_li
#H2 Console: stack traces are now links to the source code in the source repository (H2 database only).
@changelog_1179_li
@changelog_1184_li
#CHAR data type equals comparison was case insensitive instead of case sensitive.
@changelog_1180_li
@changelog_1185_li
#The exception 'Value too long for column' now includes the data.
@changelog_1181_li
@changelog_1186_li
#The table name was missing in the documentation of CREATE INDEX.
@changelog_1182_li
@changelog_1187_li
#Better support for IKVM (www.ikvm.net): the H2 Console now opens a browser window.
@changelog_1183_li
@changelog_1188_li
#The cache size was not correctly calculated for tables with large objects (specially if compression is used). This could lead to out-of-memory exceptions.
@changelog_1184_li
@changelog_1189_li
#The exception "Hexadecimal string contains non-hex character" was not always thrown when it should have been. Fixed.
@changelog_1185_li
@changelog_1190_li
#The H2 Console now provides a link to the documentation when an error occurs (H2 databases only so far).
@changelog_1186_li
@changelog_1191_li
#The acting as PostgreSQL server, when a base directory was set, and the H2 Console was started as well, the base directory was applied twice.
@changelog_1187_li
@changelog_1192_li
#Calling EXTRACT(HOUR FROM ...) or EXTRACT(HH FROM ...) returned the wrong values (0 to 11 instead of 0 to 23). All other tested databases return values from 0 to 23. Please check if your application relies on the old behavior before upgrading.
@changelog_1188_li
@changelog_1193_li
#For compatibility with other databases the column default (COLUMN_DEF) for columns without default is now null (it was an empty string).
@changelog_1189_li
@changelog_1194_li
#Statements that contain very large subqueries (where the subquery result does not fit in memory) are now faster.
@changelog_1190_li
@changelog_1195_li
#Variables: large objects (CLOB and BLOB) that don't fit in memory did not work correctly when used as variables.
@changelog_1191_li
@changelog_1196_li
#Fulltext search is now supported in named in-memory databases.
@changelog_1192_li
@changelog_1197_li
#H2 Console: multiple consecutive spaces in the setting name did not work. Fixed.
@changelog_1193_h2
@changelog_1198_h2
#Version 1.0.65 (2008-01-18)
@changelog_1194_li
@changelog_1199_li
#The build (ant) now automatically switches the source code to the correct version (JDK 1.4/1.5 or 1.6).
@changelog_1195_li
@changelog_1200_li
#A recovery bug has been fixed. With older versions, it was necessary to add ;RECOVER=1 to the database URL in cases where it should not have been required.
@changelog_1196_li
@changelog_1201_li
#The performance for DROP and DROP ALL OBJECTS has been improved.
@changelog_1197_li
@changelog_1202_li
#The ChangePassword API has been improved.
@changelog_1198_li
@changelog_1203_li
#User defined variables are now supported. Examples: SET @VAR=10;CALL @VAR. This can be used for running totals as in: select x, set(@t, ifnull(@t, 0) + x) from system_range(1, 10)
@changelog_1199_li
@changelog_1204_li
#The Ukrainian translation has been improved.
@changelog_1200_li
@changelog_1205_li
#CALL statements can now be used in batch updates and called using Statement.executeUpdate.
@changelog_1201_li
@changelog_1206_li
#New read-only setting CREATE_BUILD (the build number of the database engine that created the database).
@changelog_1202_li
@changelog_1207_li
#The optimizer did not use multi column indexes for range queries in some cases. Fixed.
@changelog_1203_li
@changelog_1208_li
#The H2 Console now calls DataSource.getConnection() instead of DataSource.getConnection(user, password) when user name and password are not specified.
@changelog_1204_li
@changelog_1209_li
#The bind IP address can now be set when using multi-homed host (if multiple network adapters are available) using the system property h2.bindAddress.
@changelog_1205_li
@changelog_1210_li
#Batch update: Calling BatchUpdateException.printStackTrace() could result in out of memory. Fixed.
@changelog_1206_li
@changelog_1211_li
#Indexes of unique or foreign constraints where not dropped when the constraint was dropped after altering the table (for example dropping a column). Fixed.
@changelog_1207_li
@changelog_1212_li
#The performance for large result sets in the server mode has been improved.
@changelog_1208_li
@changelog_1213_li
#The setting h2.serverSmallResultSetSize has been renamed to h2.serverResultSetFetchSize.
@changelog_1209_li
@changelog_1214_li
#The SCRIPT command now uses multi-row insert statements to save space except if the option SIMPLE is used.
@changelog_1210_li
@changelog_1215_li
#The SCRIPT command did not split up CLOB data correctly. Fixed.
@changelog_1211_li
@changelog_1216_li
#Optimization for single column distinct queries with an index: select distinct name from test. Can be disabled by setting the system property h2.optimizeDistinct to false.
@changelog_1212_li
@changelog_1217_li
#DROP ALL OBJECTS did not drop user defined aggregate functions and domains.
@changelog_1213_li
@changelog_1218_li
#PostgreSQL compatibility: COUNT(T.*) is now supported.
@changelog_1214_li
@changelog_1219_li
#LIKE comparisons are now faster.
@changelog_1215_li
@changelog_1220_li
#Encrypted databases are now faster.
@changelog_1216_h2
@changelog_1221_h2
#Version 1.0.64 (2007-12-27)
@changelog_1217_li
@changelog_1222_li
#3-way union queries with prepared statement or views could return the wrong results. Fixed.
@changelog_1218_li
@changelog_1223_li
#The PostgreSQL ODBC driver did not work in the last release due to a parser regression. Fixed.
@changelog_1219_li
@changelog_1224_li
#CSV tool: some escape/separator character combinations did not work. Fixed.
@changelog_1220_li
@changelog_1225_li
#CSV tool: the character # could not be used as a separator when reading.
@changelog_1221_li
@changelog_1226_li
#Recovery: when the index file is corrupt, now the database deletes it and re-creates it automatically.
@changelog_1222_li
@changelog_1227_li
#The MVCC mode did not work well with in-memory databases. Fixed.
@changelog_1223_li
@changelog_1228_li
#The FTP server now supports a event listener. Thanks Fulvio Biondi for the help!
@changelog_1224_li
@changelog_1229_li
#New system function CANCEL_SESSION to cancel the currently executing statement of another session.
@changelog_1225_li
@changelog_1230_li
#The database now supports an exclusive mode. In exclusive mode, new connections are rejected.
@changelog_1226_li
@changelog_1231_li
#H2 Console: when editing result sets, columns can now be set to null. The text 'null' must be escaped using '=null'.
@changelog_1227_li
@changelog_1232_li
#New built-in functions RPAD and LPAD.
@changelog_1228_li
@changelog_1233_li
#New meta data table INFORMATION_SCHEMA.SESSIONS and LOCKS to get information about active connections and locks. Admins will see all connections, non-admins only their own session.
@changelog_1229_li
@changelog_1234_li
#The Ukrainian translation was not working in the last release. Fixed.
@changelog_1230_li
@changelog_1235_li
#Creating many tables (many hundreds) was slow. Fixed.
@changelog_1231_li
@changelog_1236_li
#Opening a database with many indexes (thousands) was slow. Fixed.
@changelog_1232_li
@changelog_1237_li
#H2 Console / autocomplete: Ctrl+Space now shows the list in all modes.
@changelog_1233_li
@changelog_1238_li
#The method Trigger.init has been changed: the parameters 'before' and 'type', have been added to the init method.
@changelog_1234_li
@changelog_1239_li
#The performance has been improved for ResultSet methods with column name.
@changelog_1235_li
@changelog_1240_li
#A stack trace was thrown if the system did not provide a quick secure random source and if there is no network or the network settings are not configured. Fixed.
@changelog_1236_li
@changelog_1241_li
#The H2 Console has been translated to Turkish. Thanks a lot to Ridvan Agar!
@changelog_1237_li
@changelog_1242_li
#Improved debugging support: toString methods of most object now return a meaningful text.
@changelog_1238_li
@changelog_1243_li
#The classes DbStarter and WebServlet have been moved to src/main.
@changelog_1239_li
@changelog_1244_li
#The column INFORMATION_SCHEMA.TRIGGERS.SQL now contains the CREATE TRIGGER statement.
@changelog_1240_li
@changelog_1245_li
#Loading classes and calling methods can be restricted using the new system property h2.allowedClasses.
@changelog_1241_li
@changelog_1246_li
#The database could not be used in Java applets due to security exceptions. Fixed.
@changelog_1242_h2
@changelog_1247_h2
#Version 1.0.63 (2007-12-02)
@changelog_1243_li
@changelog_1248_li
#The SecurePassword example has been improved.
@changelog_1244_li
@changelog_1249_li
#In time zones where the summer time saving limit is at midnight, some dates do not work in some virtual machines, for example 2007-10-14 in Chile, using the Sun JVM 1.6.0_03-b05. Fixed.
@changelog_1245_li
@changelog_1250_li
#The native fulltext search was not working properly after re-connecting.
@changelog_1246_li
@changelog_1251_li
#Improved FTP server: now the PORT command is supported.
@changelog_1247_li
@changelog_1252_li
#Temporary views (FROM(...)) with UNION didn't work if nested. Fixed.
@changelog_1248_li
@changelog_1253_li
#Performance optimization for IN(...) and IN(SELECT...), currently disabled by default. To enable, use java -Dh2.optimizeInJoin=true
@changelog_1249_li
@changelog_1254_li
#The H2 Console has been translated to Ukrainian by Igor Dobrovolskyi. Thanks a lot!
@changelog_1250_li
@changelog_1255_li
#New function TABLE_DISTINCT.
@changelog_1251_li
@changelog_1256_li
#Using LIMIT with values close to Integer.MAX_VALUE didn't work correctly.
@changelog_1252_li
@changelog_1257_li
#Certain setting in the Server didn't work (http://code.google.com/p/h2database/issues/detail?id=7).
@changelog_1253_h2
@changelog_1258_h2
#Version 1.0.62 (2007-11-25)
@changelog_1254_li
@changelog_1259_li
#Large updates and deletes are now supported by buffering data to disk if required. The threshold is currently set to 100'000 bytes and can be changed using SET MAX_OPERATION_MEMORY or using by appending ;MAX_OPERATION_MEMORY=.. to the database URL. See also the docs.
@changelog_1255_li
@changelog_1260_li
#MVCC: now an exception is thrown when an application tries to change the MVCC setting while the database is already open.
@changelog_1256_li
@changelog_1261_li
#Referential integrity checks didn't lock the referenced table, and thus could read uncommitted rows of other connections. In that way the referential constraints could get violated (except when using MVCC).
@changelog_1257_li
@changelog_1262_li
#Renaming or dropping a user with a schema, or removing the admin property of that user made the schema inaccessible after re-opening the database. Fixed.
@changelog_1258_li
@changelog_1263_li
#The H2 Console now also support the command line option -ifExists when started from the Server tool, but only when connecting to H2 databases.
@changelog_1259_li
@changelog_1264_li
#Duplicate column names were not detected when renaming columns. Fixed.
@changelog_1260_li
@changelog_1265_li
#The console did not display multiple embedded spaces in text correctly. Fixed.
@changelog_1261_li
@changelog_1266_li
#Google Android support: use 'ant codeswitchAndroid' to switch the source code to Android.
@changelog_1262_li
@changelog_1267_li
#Values of type ARRAY are now sorted as in PostgreSQL.
@changelog_1263_li
@changelog_1268_li
#In the cluster mode, could not connect if only one server was running (last release only). Fixed.
@changelog_1264_li
@changelog_1269_li
#The performance of large CSV operations has been improved.
@changelog_1265_li
@changelog_1270_li
#Now using custom toString() for most JDBC objects and commands.
@changelog_1266_li
@changelog_1271_li
#Nested temporary views (SELECT * FROM (SELECT ...)) with parameters didn't work in some cases. Fixed.
@changelog_1267_li
@changelog_1272_li
#CSV: Using an empty field delimiter didn't work (a workaround was using char(0)). Fixed.
@changelog_1268_li
@changelog_1273_li
#A patch for Apache DDL Utils is available at https://issues.apache.org/jira/browse/DDLUTILS-185
@changelog_1269_li
@changelog_1274_li
#The default value for h2.emergencySpaceInitial is now 256 KB (to speed up creating encrypted databases)
@changelog_1270_li
@changelog_1275_li
#Eduardo Velasques has translated the H2 Console and the error messages to Brazilian Portuguese. Thanks a lot!
@changelog_1271_li
@changelog_1276_li
#Creating a table from GROUP_CONCAT didn't work if the data was longer than 255 characters
@changelog_1272_h2
@changelog_1277_h2
#Version 1.0.61 (2007-11-10)
@changelog_1273_li
@changelog_1278_li
#The Lucene Fulltext implementation is now compiled and included in the h2.jar. Requires Lucene 2.2.
@changelog_1274_li
@changelog_1279_li
#Added more tests. The code coverage is now at 83%.
@changelog_1275_li
@changelog_1280_li
#ResultSetMetaData.getColumnDisplaySize was calculated as the longest display size for the given result set, but should be the maximum size that fits in the column. Fixed.
@changelog_1276_li
@changelog_1281_li
#The MODE used to be a global setting, now it is a database level setting.
@changelog_1277_li
@changelog_1282_li
#The database does now always round to the nearest number when converting a floating point to a integer: CAST(1.5 AS INT) will now result in 2, like in PostgreSQL and MySQL.
@changelog_1278_li
@changelog_1283_li
#Math operations using unknown data types (for example -? and ?+?) are now interpreted as decimal.
@changelog_1279_li
@changelog_1284_li
#INSTR, LOCATE: backward searching is not supported by using a negative start position.
@changelog_1280_li
@changelog_1285_li
#Can now open a database stored in a jar or zip file (for example, jdbc:h2:zip:c:/temp/h2.zip!/test).
@changelog_1281_li
@changelog_1286_li
#Files access now uses an API (FileSystem, FileObject), this will simplify adding other file systems and features (for example replication).
@changelog_1282_li
@changelog_1287_li
#Vlad Alexahin has translated H2 Console to Russian. Thanks a lot!
@changelog_1283_li
@changelog_1288_li
#Descending indexes are now supported. This is useful when sorting columns descending, for example by creation date.
@changelog_1284_li
@changelog_1289_li
#Solved a Java level deadlock in the DatabaseCloser.
@changelog_1285_li
@changelog_1290_li
#CREATE SEQUENCE: New option CACHE (number of pre-allocated numbers). New column CACHE in the sequence meta data table. The default cache size is still 32.
@changelog_1286_li
@changelog_1291_li
#MVCC: The system property h2.mvcc has been removed. A few bugs have been fixed, and new tests have been added.
@changelog_1287_h2
@changelog_1292_h2
#Version 1.0.60 (2007-10-20)
@changelog_1288_li
@changelog_1293_li
#JdbcXAConnection: starting a transaction before getting the connection didn't switch off autocommit.
@changelog_1289_li
@changelog_1294_li
#User defined aggregate functions are not supported.
@changelog_1290_li
@changelog_1295_li
#Server.shutdownTcpServer was blocked when first called with force=false and then force=true. Now documentation is improved, and it is no longer blocked.
@changelog_1291_li
@changelog_1296_li
#Stack traces did not include the SQL statement in all cases where they could have. Also, stack traces with SQL statement are now shorter.
@changelog_1292_li
@changelog_1297_li
#Linked tables: now tables in non-default schemas are supported as well
@changelog_1293_li
@changelog_1298_li
#New Italian translation from PierPaolo Ucchino. Thanks a lot!
@changelog_1294_li
@changelog_1299_li
#CSV: New methods to set the escape character and field delimiter in the Csv tool and the CSVWRITE and CSVREAD methods.
@changelog_1295_li
@changelog_1300_li
#Prepared statements could not be used after data definition statements (creating tables and so on). Fixed.
@changelog_1296_li
@changelog_1301_li
#PreparedStatement.setMaxRows could not be changed to a higher value after the statement was executed.
@changelog_1297_li
@changelog_1302_li
#The H2 Console could not connect twice to the same H2 embedded database at the same time. Fixed.
@changelog_1298_li
@changelog_1303_li
#CSVREAD, RUNSCRIPT and so on now support URLs as well, using URL.openStream(). Example: select * from csvread('jar:file:///c:/temp/test.jar!/test.csv');
@changelog_1299_h2
@changelog_1304_h2
#Version 1.0.59 (2007-10-03)
@changelog_1300_li
@changelog_1305_li
#When the data type was unknown in a subquery, sometimes the wrong exception (ArrayIndexOutOfBounds) was thrown. Fixed.
@changelog_1301_li
@changelog_1306_li
#If the process was killed while the database was running, sometimes the database could not be opened ('double allocation') except when the system property h2.check was set to false. Fixed.
@changelog_1302_li
@changelog_1307_li
#Multi-threaded kernel (MULTI_THREADED=1): A synchronization problem has been fixed.
@changelog_1303_li
@changelog_1308_li
#A PreparedStatement that was cancelled could not be reused. Fixed.
@changelog_1304_li
@changelog_1309_li
#H2 Console: Progress information when logging into a H2 embedded database (useful when opening a database is slow).
@changelog_1305_li
@changelog_1310_li
#When the database was closed while logging was disabled (LOG 0), re-opening the database was slow. Fixed.
@changelog_1306_li
@changelog_1311_li
#Fulltext search is now documented (in the Tutorial).
@changelog_1307_li
@changelog_1312_li
#The Console did not refresh the table list if the CREATE TABLE statement started with a comment. Fixed.
@changelog_1308_li
@changelog_1313_li
#When creating a table using CREATE TABLE .. AS SELECT, the precision for some data types (for example VARCHAR) was set to the default precision. Fixed.
@changelog_1309_li
@changelog_1314_li
#When using the (undocumented) in-memory file system (jdbc:h2:memFS:x or jdbc:h2:memLZF:x), and using multiple connections, a ConcurrentModificationException could occur. Fixed.
@changelog_1310_li
@changelog_1315_li
#REGEXP compatibility: So far String.matches was used, but for compatibility with MySQL, now Matcher.find is used.
@changelog_1311_li
@changelog_1316_li
#SCRIPT: the SQL statements in the result set now include the terminating semicolon as well. Simplifies copy and paste.
@changelog_1312_li
@changelog_1317_li
#When using a subquery with group by as a table, some columns could not be used in the where condition in the outer query. Example: SELECT * FROM (SELECT ID, COUNT(*) C FROM TEST) WHERE C > 100. Fixed.
@changelog_1313_li
@changelog_1318_li
#Views with subqueries as tables and queries with nested subqueries as tables did not always work. Fixed.
@changelog_1314_li
@changelog_1319_li
#Compatibility: comparing columns with constants that are out of range does not throw an exception.
@changelog_1315_h2
@changelog_1320_h2
#Version 1.0.58 (2007-09-15)
@changelog_1316_li
@changelog_1321_li
#System.exit is no longer called by the WebServer, the Console and the Server tool (except to set the exit code if required). This is important when using OSGi.
@changelog_1317_li
@changelog_1322_li
#Optimization for independent subqueries. For example, this query can now an index: SELECT * FROM TEST WHERE ID = (SELECT MAX(ID) FROM TEST) This can be disabled by setting the system property h2.optimizeSubqueryCache to false.
@changelog_1318_li
@changelog_1323_li
#The explain plan now says: /* direct lookup query */ if the query can be processed directly without reading rows, for example when using MIN(indexed column), MAX(indexed column), or COUNT(*).
@changelog_1319_li
@changelog_1324_li
#When using IFNULL, NULLIF, COALESCE, LEAST, or GREATEST, and the first parameter was ?, an exception was thrown. Now the highest data type of all parameters is used.
@changelog_1320_li
@changelog_1325_li
#When comparing TINYINT or SMALLINT columns against constants, the index was not used. Fixed.
@changelog_1321_li
@changelog_1326_li
#Maven 2: new version are now automatically synced with the central repositories.
@changelog_1322_li
@changelog_1327_li
#The default value for MAX_MEMORY_UNDO is now 100000.
@changelog_1323_li
@changelog_1328_li
#The documentation indexer does no longer index Japanese pages. If somebody knows how to split Japanese into words please post it.
@changelog_1324_li
@changelog_1329_li
#Oracle compatibility: SYSDATE now returns a timestamp. CHR(..) is now an alias for CHAR(..).
@changelog_1325_li
@changelog_1330_li
#After deleting data, empty space in the database files was not efficiently reused (but it was reused when opening the database). This has been fixed.
@changelog_1326_li
@changelog_1331_li
#About 230 bytes per database was leaked. This is a problem for applications opening and closing many thousand databases. The main problem: a shutdown hook was added but never removed. Fixed. In JDK 1.4, there is <a href="http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=4197876">an additionally problem</a> . A workaround has been implemented.
@changelog_1327_li
@changelog_1332_li
#Optimization for COLUMN IN(.., NULL) if the column does not allow NULL values.
@changelog_1328_li
@changelog_1333_li
#Using spaces in column and table aliases was not supported when used inside a view or temporary view.
@changelog_1329_li
@changelog_1334_li
#The version (build) number is now included in the manifest file.
@changelog_1330_li
@changelog_1335_li
#In some systems, SecureRandom.generateSeed is very slow (taking one minute or more). For those cases, an alternative method is used that takes less than one second.
@changelog_1331_li
@changelog_1336_li
#The database file sizes are now increased at most 32 MB at any time.
@changelog_1332_li
@changelog_1337_li
#New method DatabaseEventListener.opened that is called just after opening a database.
@changelog_1333_li
@changelog_1338_li
#When using the Console with Internet Explorer 6.0 or 7.0, a Javascript error was thrown after clearing the query.
@changelog_1334_li
@changelog_1339_li
#A database can now be opened even if class of a user defined function is not in the classpath. Trying to call the function will throws an exception.
@changelog_1335_li
@changelog_1340_li
#User defined functions and constants may not overload built-in functions and constants. This didn't work before, but now trying to create such an object will fail.
@changelog_1336_li
@changelog_1341_li
#Improved MultiDimension tool (for spatial queries): in the last few releases the tool was actually slower than using a regular query (because index lookup got faster, and because the tool didn't support prepared statements) Now the tool generates prepared statements, and the performance is better again (about 5 times faster for a reasonable amount of data).
@changelog_1337_li
@changelog_1342_li
#Adding a foreign key or when re-enabling referential integrity for a table failed when checking was enabled and the reference contained NULL.
@changelog_1338_li
@changelog_1343_li
#For PgServer, character encoding other than UTF-8 did not work correctly. Fixed.
@changelog_1339_li
@changelog_1344_li
#Using a function in a GROUP BY expression that is used in a view as a condition did not always work.
#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.
#When using database URLs like jdbc:h2:~/test, the database is stored in the user directory. For Windows, this is usually C:\Documents and Settings\<userName>. If the base directory is not set (as in jdbc:h2:test), the database files are stored in the directory where the application is started (the current working directory). When using the H2 Console application from the start menu, this is [Installation Directory]/bin. The base directory can be set in the database URL. A fixed or relative path can be used. When using the URL jdbc:h2:file:data/sample, the database is stored in the directory data (relative to the current working directory). The directory is created automatically if it does not yet exist. It is also possible to use the fully qualified directory (and for Windows, drive) name. Example: jdbc:h2:file:C:/data/test
@faq_1029_h3
@faq_1030_h3
#What is the Size Limit (Maximum Size) of a Database?
#The larger the database, the more main memory is required. Currently the minimum main memory required for a 12 GB database is around 240 MB.
@faq_1033_h3
@faq_1034_h3
これは信頼できるデータベースですか？
@faq_1034_p
@faq_1035_p
#That is not easy to say. It is still a quite new product. A lot of tests have been written, and the code coverage of these tests is very high. Randomized stress tests are run regularly. But as this is a relatively new product, there are probably some problems that have not yet been found (as with most software). Some features are known to be dangerous by design, and some problems are hard to solve. Those are:
@faq_1035_li
@faq_1036_li
#Using SET LOG 0 to disable the transaction log file.
@faq_1036_li
@faq_1037_li
#Using the transaction isolation level READ_UNCOMMITTED (LOCK_MODE 0) while at the same time using multiple connections may result in inconsistent transactions.
@faq_1037_li
@faq_1038_li
#Using FILE_LOCK=NO in the database URL.
@faq_1038_p
@faq_1039_p
#In addition to that, running out of memory should be avoided. In some versions, OutOfMemory errors while using the database could corrupt a databases. Not all such problems may be fixed.
@faq_1039_p
@faq_1040_p
#Areas that are not fully tested:
@faq_1040_li
WindowsXP以外のプラットフォーム、及びSUN JVM1.4、1.5での動作確認
@faq_1041_li
#The MVCC (multi version concurrency) mode
WindowsXP以外のプラットフォーム、及びSUN JVM1.4、1.5での動作確認
@faq_1042_li
#Cluster mode, 2-phase commit, savepoints
#The MVCC (multi version concurrency) mode
@faq_1043_li
#24/7 operation
#Cluster mode, 2-phase commit, savepoints
@faq_1044_li
#Some operations on databases larger than 500 MB may be slower than expected #Updatable result sets
#24/7 operation
@faq_1045_li
Updatable result sets
#Some operations on databases larger than 500 MB may be slower than expected
@faq_1046_li
#Referential integrity and check constraints, triggers
Updatable result sets
@faq_1047_li
#ALTER TABLE statements, views, linked tables, schema, UNION #すべての組み込み関数が完全にテストされたわけではありません
#Referential integrity and check constraints, triggers
@faq_1048_li
すべての組み込み関数が完全にテストされたわけではありません
#ALTER TABLE statements, views, linked tables, schema, UNION
@faq_1049_li
#The optimizer may not always select the best plan #データ型 BLOB、CLOB、VARCHAR_IGNORECASE、OTHER
すべての組み込み関数が完全にテストされたわけではありません
@faq_1050_li
データ型 BLOB、CLOB、VARCHAR_IGNORECASE、OTHER
#The optimizer may not always select the best plan
@faq_1051_li
大きなVARCHAR、VARBINARYカラム、または多数のカラムによる幅の広いインデックス
データ型 BLOB、CLOB、VARCHAR_IGNORECASE、OTHER
@faq_1052_li
大きなVARCHAR、VARBINARYカラム、または多数のカラムによる幅の広いインデックス
@faq_1053_li
#Multi-threading and using multiple connections
@faq_1053_p
@faq_1054_p
試験的に考慮された箇所は以下の通り:
@faq_1054_li
#The PostgreSQL server #他のデータベースとの互換モード (一部の特徴のみ提供される)
@faq_1055_li
他のデータベースとの互換モード (一部の特徴のみ提供される)
#The PostgreSQL server
@faq_1056_li
他のデータベースとの互換モード (一部の特徴のみ提供される)
@faq_1057_li
#The ARRAY data type and related functionality
@faq_1057_h3
@faq_1058_h3
#Why is Opening my Database Slow?
@faq_1058_p
@faq_1059_p
#If it takes a long time to open a database, in most cases it was not closed the last time. This is specially a problem for larger databases. To close a database, close all connections to it before the application ends, or execute the command SHUTDOWN. The database is also closed when the virtual machine exits normally by using a shutdown hook. However killing a Java process or calling Runtime.halt will prevent this.
@faq_1059_p
@faq_1060_p
#To find out what the problem is, open the database in embedded mode using the H2 Console. This will print progress information. If you have many 'Creating index' lines it is an indication that the database was not closed the last time.
@faq_1060_p
@faq_1061_p
#Other possible reasons are: the database is very big (many GB), or contains linked tables that are slow to open.
#For more information, see <a href="build.html#translating">Build/Translating</a> .
@features_1000_h1
...
...
@@ -3172,13 +3190,13 @@ McKoi
#Remote Mode
@features_1272_p
#When using the remote mode (sometimes called client/server mode), an application opens a database remotely using the JDBC or ODBC API. A server needs to be started within the same or another virtual machine (or on another computer). Many applications can connect to the same database at the same time. The remote mode is slower than the embedded mode, because all data is transferred over TCP/IP. As in all modes, both persistent and in-memory databases are supported. There is no limit on the number of database open concurrently, or on the number of open connections.
#When using the remote mode (sometimes called server mode or client/server mode), an application opens a database remotely using the JDBC or ODBC API. A server needs to be started within the same or another virtual machine (or on another computer). Many applications can connect to the same database at the same time. The remote mode is slower than the embedded mode, because all data is transferred over TCP/IP. As in all modes, both persistent and in-memory databases are supported. There is no limit on the number of database open concurrently, or on the number of open connections.
@features_1273_h3
#Mixed Mode
@features_1274_p
#The mixed mode is a combination of the embedded and the remote mode. The main application connects to a database in embedded mode, but also starts a server so that other applications (running in different virtual machines) can concurrently access the same data.
#The mixed mode is a combination of the embedded and the remote mode. The main application connects to a database in embedded mode, but also starts a server so that other applications (running in different virtual machines) can concurrently access the same data. The embedded connections are as fast as if the database is used in just the embedded mode, while the remote connections are a bit slower.
