Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Improve][JdbcSource] Optimize catalog-table metadata merge logic #5828

Merged
merged 1 commit into from
Nov 11, 2023
Merged

[Improve][JdbcSource] Optimize catalog-table metadata merge logic #5828

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
113 changes: 64 additions & 49 deletions .../src/main/java/org/apache/seatunnel/connectors/seatunnel/jdbc/utils/JdbcCatalogUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,64 +173,58 @@ private static CatalogTable getCatalogTable(
return jdbcCatalog.getTable(tableConfig.getQuery());
}

private static CatalogTable mergeCatalogTable(
CatalogTable tableOfPath, CatalogTable tableOfQuery) {
String catalogName =
tableOfQuery.getTableId() == null
? DEFAULT_CATALOG_NAME
: tableOfQuery.getTableId().getCatalogName();
TableIdentifier tableIdentifier =
TableIdentifier.of(
catalogName,
tableOfPath.getTableId().getDatabaseName(),
tableOfPath.getTableId().getSchemaName(),
tableOfPath.getTableId().getTableName());

static CatalogTable mergeCatalogTable(CatalogTable tableOfPath, CatalogTable tableOfQuery) {
hailin0 marked this conversation as resolved.
Show resolved Hide resolved
TableSchema tableSchemaOfPath = tableOfPath.getTableSchema();
Map<String, Column> columnsOfPath =
tableSchemaOfPath.getColumns().stream()
.collect(Collectors.toMap(Column::getName, Function.identity()));
Set<String> columnKeysOfPath = columnsOfPath.keySet();
.collect(
Collectors.toMap(
Column::getName,
Function.identity(),
(o1, o2) -> o1,
LinkedHashMap::new));
TableSchema tableSchemaOfQuery = tableOfQuery.getTableSchema();
Map<String, Column> columnsOfQuery =
tableSchemaOfQuery.getColumns().stream()
.collect(Collectors.toMap(Column::getName, Function.identity()));
.collect(
Collectors.toMap(
Column::getName,
Function.identity(),
(o1, o2) -> o1,
LinkedHashMap::new));
Set<String> columnKeysOfQuery = columnsOfQuery.keySet();

if (columnKeysOfPath.equals(columnKeysOfQuery)) {
boolean schemaEquals =
columnKeysOfPath.stream()
.allMatch(
key ->
columnsOfPath
.get(key)
.getDataType()
.equals(columnsOfQuery.get(key).getDataType()));
if (schemaEquals) {
return CatalogTable.of(
tableIdentifier,
TableSchema.builder()
.primaryKey(tableSchemaOfPath.getPrimaryKey())
.constraintKey(tableSchemaOfPath.getConstraintKeys())
.columns(tableSchemaOfQuery.getColumns())
.build(),
tableOfPath.getOptions(),
tableOfPath.getPartitionKeys(),
tableOfPath.getComment(),
tableIdentifier.getCatalogName());
}
List<Column> columnsOfMerge =
tableSchemaOfQuery.getColumns().stream()
.filter(
column ->
columnsOfPath.containsKey(column.getName())
&& columnsOfPath
.get(column.getName())
.getDataType()
.equals(
columnsOfQuery
.get(column.getName())
.getDataType()))
.map(column -> columnsOfPath.get(column.getName()))
.collect(Collectors.toList());
boolean schemaIncludeAllColumns = columnsOfMerge.size() == columnKeysOfQuery.size();
boolean schemaEquals =
schemaIncludeAllColumns && columnsOfMerge.size() == columnsOfPath.size();
if (schemaEquals) {
return tableOfPath;
}

PrimaryKey primaryKeyOfPath = tableSchemaOfPath.getPrimaryKey();
List<ConstraintKey> constraintKeysOfPath = tableSchemaOfPath.getConstraintKeys();
List<String> partitionKeysOfPath = tableOfPath.getPartitionKeys();
PrimaryKey primaryKeyOfQuery = null;
List<ConstraintKey> constraintKeysOfQuery = new ArrayList<>();
List<String> partitionKeysOfQuery = new ArrayList<>();
PrimaryKey primaryKeyOfMerge = null;
List<ConstraintKey> constraintKeysOfMerge = new ArrayList<>();
List<String> partitionKeysOfMerge = new ArrayList<>();

if (primaryKeyOfPath != null
&& columnKeysOfQuery.containsAll(primaryKeyOfPath.getColumnNames())) {
primaryKeyOfQuery = primaryKeyOfPath;
primaryKeyOfMerge = primaryKeyOfPath;
}
if (constraintKeysOfPath != null) {
for (ConstraintKey constraintKey : constraintKeysOfPath) {
Expand All @@ -239,26 +233,47 @@ private static CatalogTable mergeCatalogTable(
.map(e -> e.getColumnName())
.collect(Collectors.toSet());
if (columnKeysOfQuery.containsAll(constraintKeyFields)) {
constraintKeysOfQuery.add(constraintKey);
constraintKeysOfMerge.add(constraintKey);
}
}
}
if (partitionKeysOfPath != null && columnKeysOfQuery.containsAll(partitionKeysOfPath)) {
partitionKeysOfQuery = partitionKeysOfPath;
partitionKeysOfMerge = partitionKeysOfPath;
}
if (schemaIncludeAllColumns) {
return CatalogTable.of(
tableOfPath.getTableId(),
TableSchema.builder()
.primaryKey(primaryKeyOfMerge)
.constraintKey(constraintKeysOfMerge)
.columns(columnsOfMerge)
.build(),
tableOfPath.getOptions(),
partitionKeysOfMerge,
tableOfPath.getComment());
}

String catalogName =
tableOfQuery.getTableId() == null
? DEFAULT_CATALOG_NAME
: tableOfQuery.getTableId().getCatalogName();
TableIdentifier tableIdentifier =
TableIdentifier.of(
catalogName,
tableOfPath.getTableId().getDatabaseName(),
tableOfPath.getTableId().getSchemaName(),
tableOfPath.getTableId().getTableName());
CatalogTable mergedCatalogTable =
CatalogTable.of(
tableIdentifier,
TableSchema.builder()
.primaryKey(primaryKeyOfQuery)
.constraintKey(constraintKeysOfQuery)
.primaryKey(primaryKeyOfMerge)
.constraintKey(constraintKeysOfMerge)
.columns(tableSchemaOfQuery.getColumns())
.build(),
tableOfPath.getOptions(),
partitionKeysOfQuery,
tableOfPath.getComment(),
tableIdentifier.getCatalogName());
partitionKeysOfMerge,
tableOfPath.getComment());

log.info("Merged catalog table of path {}", tableOfPath.getTableId().toTablePath());
return mergedCatalogTable;
Expand Down
Loading