shaofengshi closed pull request #411: KYLIN-3737 refactor cache part for RDBMS
URL: https://github.com/apache/kylin/pull/411
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git
a/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/AbstractJdbcAdaptor.java
b/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/AbstractJdbcAdaptor.java
index 3e36faedf3..3a66499b33 100644
---
a/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/AbstractJdbcAdaptor.java
+++
b/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/AbstractJdbcAdaptor.java
@@ -53,11 +53,11 @@
protected final DataSourceDef dataSourceDef;
protected SqlConverter.IConfigurer configurer;
protected final Cache<String, List<String>> columnsCache =
CacheBuilder.newBuilder()
- .expireAfterWrite(1, TimeUnit.DAYS).maximumSize(30).build();
+ .expireAfterWrite(1, TimeUnit.DAYS).maximumSize(4096).build();
protected final Cache<String, List<String>> databasesCache =
CacheBuilder.newBuilder()
- .expireAfterWrite(1, TimeUnit.DAYS).maximumSize(30).build();
+ .expireAfterWrite(1, TimeUnit.DAYS).maximumSize(4096).build();
protected final Cache<String, List<String>> tablesCache =
CacheBuilder.newBuilder()
- .expireAfterWrite(1, TimeUnit.DAYS).maximumSize(30).build();
+ .expireAfterWrite(1, TimeUnit.DAYS).maximumSize(4096).build();
private static Joiner joiner = Joiner.on("_");
@@ -308,7 +308,7 @@ public String getDataSourceId() {
*/
public List<String> listDatabasesWithCache(boolean init) throws
SQLException {
if (configurer.enableCache()) {
- String cacheKey = config.datasourceId + config.url + "_databases";
+ String cacheKey = joiner.join(config.datasourceId, config.url,
"databases");
List<String> cachedDatabases;
if (init || (cachedDatabases =
databasesCache.getIfPresent(cacheKey)) == null) {
cachedDatabases = listDatabases();
@@ -429,7 +429,7 @@ public String getDataSourceId() {
*/
public List<String> listColumnsWithCache(String database, String
tableName, boolean init) throws SQLException {
if (configurer.enableCache()) {
- String cacheKey = config.datasourceId + config.url + "_" +
tableName + "_columns";
+ String cacheKey = joiner.join(config.datasourceId, config.url,
database, tableName, "columns");
List<String> cachedColumns;
if (init || (cachedColumns = columnsCache.getIfPresent(cacheKey))
== null) {
cachedColumns = listColumns(database, tableName);
diff --git
a/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/DefaultAdaptor.java
b/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/DefaultAdaptor.java
index 66c45e1dcf..da24e9831b 100644
---
a/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/DefaultAdaptor.java
+++
b/datasource-sdk/src/main/java/org/apache/kylin/sdk/datasource/adaptor/DefaultAdaptor.java
@@ -28,6 +28,7 @@
import java.util.Map;
import javax.sql.rowset.CachedRowSet;
+import com.google.common.base.Joiner;
import org.apache.commons.lang.StringUtils;
/**
@@ -36,9 +37,7 @@
*/
public class DefaultAdaptor extends AbstractJdbcAdaptor {
- protected static final String QUOTE_REG_LFT = "[`\"\\[]*";
- protected static final String QUOTE_REG_RHT = "[`\"\\]]*";
- private final static String [] POSSIBLE_TALBE_END= {",", " ", ")", "\r",
"\n", "."};
+ private static Joiner joiner = Joiner.on('_');
public DefaultAdaptor(AdaptorConfig config) throws Exception {
super(config);
@@ -140,19 +139,6 @@ public String fixSql(String sql) {
return sql;
}
- private boolean checkSqlContainstable(String orig, String table) {
- // ensure table is single match(e.g match account but not match
accountant)
- if (orig.endsWith(table.toUpperCase(Locale.ROOT))) {
- return true;
- }
- for (String end:POSSIBLE_TALBE_END) {
- if (orig.contains(table.toUpperCase(Locale.ROOT) + end)){
- return true;
- }
- }
- return false;
- }
-
/**
* By default, use schema as database of kylin.
* @return
@@ -270,26 +256,100 @@ public CachedRowSet getTableColumns(String schema,
String table) throws SQLExcep
public String fixIdentifierCaseSensitve(String identifier) {
try {
List<String> databases = listDatabasesWithCache();
- for (String db : databases) {
- if (db.equalsIgnoreCase(identifier)) {
- return db;
+ for (String database : databases) {
+ if (identifier.equalsIgnoreCase(database)) {
+ return database;
}
- List<String> tables = listTablesWithCache(db);
- for (String table : tables) {
- if (table.equalsIgnoreCase(identifier)) {
- return table;
- }
- List<String> cols = listColumnsWithCache(db, table);
- for (String col : cols) {
- if (col.equalsIgnoreCase(identifier)) {
- return col;
- }
- }
+ }
+ List<String> tables = listTables();
+ for (String table : tables) {
+ if (identifier.equalsIgnoreCase(table)) {
+ return table;
+ }
+ }
+ List<String> columns = listColumns();
+ for (String column : columns) {
+ if (identifier.equalsIgnoreCase(column)) {
+ return column;
}
}
} catch (Exception e) {
- throw new RuntimeException(e);
+ throw new IllegalStateException(e);
}
return identifier;
}
+
+ /**
+ * Get All tables for sql case sensitive
+ * @return
+ * @throws SQLException
+ */
+ public List<String> listTables() throws SQLException {
+ List<String> ret = new ArrayList<>();
+ if (tablesCache == null || tablesCache.size() == 0) {
+ try (Connection conn = getConnection();
+ ResultSet rs = conn.getMetaData().getTables(null, null,
null, null)) {
+ while (rs.next()) {
+ String name = rs.getString("TABLE_NAME");
+ String database = rs.getString("TABLE_SCHEM") != null ?
rs.getString("TABLE_SCHEM")
+ : rs.getString("TABLE_CAT");
+ String cacheKey = joiner.join(config.datasourceId,
config.url, database, "tables");
+ List<String> cachedTables =
tablesCache.getIfPresent(cacheKey);
+ if (cachedTables == null) {
+ cachedTables = new ArrayList<>();
+ tablesCache.put(cacheKey, cachedTables);
+ logger.debug("Add table cache for database {}",
database);
+ }
+ if (!cachedTables.contains(name)) {
+ cachedTables.add(name);
+ }
+ ret.add(name);
+ }
+ }
+ } else {
+ for (Map.Entry<String, List<String>> entry :
tablesCache.asMap().entrySet()) {
+ ret.addAll(entry.getValue());
+ }
+ }
+
+ return ret;
+ }
+
+ /**
+ * Get All columns for sql case sensitive
+ * @return
+ * @throws SQLException
+ */
+ public List<String> listColumns() throws SQLException {
+ List<String> ret = new ArrayList<>();
+ if (columnsCache == null || columnsCache.size() == 0) {
+ CachedRowSet columnsRs = null;
+ try (Connection conn = getConnection();
+ ResultSet rs = conn.getMetaData().getColumns(null, null,
null, null)) {
+ columnsRs = cacheResultSet(rs);
+ }
+ while (columnsRs.next()) {
+ String database = columnsRs.getString("TABLE_SCHEM") != null ?
columnsRs.getString("TABLE_SCHEM")
+ : columnsRs.getString("TABLE_CAT");
+ String table = columnsRs.getString("TABLE_NAME");
+ String column = columnsRs.getString("COLUMN_NAME");
+ String cacheKey = joiner.join(config.datasourceId, config.url,
database, table, "columns");
+ List<String> cachedColumns =
columnsCache.getIfPresent(cacheKey);
+ if (cachedColumns == null) {
+ cachedColumns = new ArrayList<>();
+ columnsCache.put(cacheKey, cachedColumns);
+ logger.debug("Add column cache for table {}.{}", database,
table);
+ }
+ if (!cachedColumns.contains(column)) {
+ cachedColumns.add(column);
+ }
+ ret.add(column);
+ }
+ } else {
+ for (Map.Entry<String, List<String>> entry :
columnsCache.asMap().entrySet()) {
+ ret.addAll(entry.getValue());
+ }
+ }
+ return ret;
+ }
}
\ No newline at end of file
diff --git a/datasource-sdk/src/main/resources/datasource/mysql.xml
b/datasource-sdk/src/main/resources/datasource/mysql.xml
index d31c11e7b8..5e23cc3319 100644
--- a/datasource-sdk/src/main/resources/datasource/mysql.xml
+++ b/datasource-sdk/src/main/resources/datasource/mysql.xml
@@ -23,15 +23,8 @@
<PROPERTY NAME="sql.allow-no-orderby-with-fetch" VALUE="true"/>
<PROPERTY NAME="sql.keyword-default-escape" VALUE="true"/>
<PROPERTY NAME="sql.keyword-default-uppercase" VALUE="true"/>
- <PROPERTY NAME="table-sampling.template.max-or-min-value-default"
- VALUE="SELECT MAX({0}), MIN({0}) FROM {1} WHERE {0} IS NOT
NULL"/>
- <PROPERTY NAME="table-sampling.template.max-or-min-len-value-default"
- VALUE="SELECT {0} FROM {1} WHERE {0} IS NOT NULL ORDER BY
CHAR_LENGTH({0}){2} LIMIT 1"/>
- <PROPERTY NAME="table-sampling.template.exceed-precision-count-default"
- VALUE="SELECT COUNT({0}) FROM {1} WHERE CHAR_LENGTH({0}) > {2}"/>
- <PROPERTY
NAME="table-sampling.template.exceed-precision-max-length-value-default"
- VALUE="SELECT MAX(CHAR_LENGTH({0})) FROM {1} WHERE
CHAR_LENGTH({0}) > {2}"/>
<PROPERTY NAME="sql.case-sensitive" VALUE="true"/>
+ <PROPERTY NAME="metadata.enable-cache" VALUE="true"/>
<PROPERTY NAME="sql.paging-type" VALUE="LIMIT_OFFSET"/>
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
