gudusoft.gsqlparser.dlineage

Class DataFlowAnalyzer

Object

gudusoft.gsqlparser.dlineage.DataFlowAnalyzer

All Implemented Interfaces:

IDataFlowAnalyzer

public class DataFlowAnalyzer
extends Object
implements IDataFlowAnalyzer

Constructor Summary

Constructors

Constructor and Description
DataFlowAnalyzer(File[] sqlFiles, EDbVendor dbVendor, boolean simpleOutput)
DataFlowAnalyzer(File[] sqlFiles, Option option)
DataFlowAnalyzer(File sqlFile, EDbVendor dbVendor, boolean simpleOutput)
DataFlowAnalyzer(File sqlFile, Option option)
DataFlowAnalyzer(SqlInfo[] sqlInfos, EDbVendor dbVendor, boolean simpleOutput)
DataFlowAnalyzer(SqlInfo[] sqlInfos, Option option)
DataFlowAnalyzer(String[] sqlContents, EDbVendor dbVendor, boolean simpleOutput)
DataFlowAnalyzer(String[] sqlContents, EDbVendor dbVendor, boolean simpleOutput, String defaultServer, String defaultDatabase, String defaltSchema)
DataFlowAnalyzer(String[] sqlContents, Option option)
DataFlowAnalyzer(String sqlContent, EDbVendor dbVendor, boolean simpleOutput)
DataFlowAnalyzer(String sqlContent, EDbVendor dbVendor, boolean simpleOutput, String defaultServer, String defaultDatabase, String defaltSchema)
DataFlowAnalyzer(String sqlContent, Option option)

Method Summary

Modifier and Type	Method and Description
protected void	analyzeResultColumnExpressionRelation(Object resultColumn, TExpression expression)
protected void	analyzeTableSubquery(TTable table)
String	chechSyntax()
protected List<SqlInfo>	convertSQL(EDbVendor vendor, String json)
void	dispose()
protected void	flattenStructColumns(boolean hasDefinition, Table tableModel, TColumnDefinition column, Stack<TColumnDefinition> columnPaths, int index)
String	generateDataFlow()
String	generateDataFlow(boolean withExtraInfo)
String	generateSqlInfos()
dataflow	getDataFlow()
Map	getDynamicSQLMap()
List<DynamicSqlSite>	getDynamicSqlSites() Every dynamic-SQL execution site (T-SQL EXEC(...) / sp_executesql) the analyzer encountered, with whether it was statically resolved.
List<ErrorInfo>	getErrorMessages()
Map	getHashSQLMap()
protected String	getIdentifiedFunctionName(Function function)
Option	getOption()
static String	getReleaseDate()
DbObjectPosition	getSelectedDbObjectInfo(Coordinate start, Coordinate end) Deprecated. please use SqlInfoHelper.getSelectedDbObjectInfo
dataflow	getSimpleDataflow(dataflow instance, boolean simpleOutput)
dataflow	getSimpleDataflow(dataflow instance, boolean simpleOutput, List<String> types)
static Dataflow	getSqlflowJSONModel(dataflow dataflow) Deprecated.
static Dataflow	getSqlflowJSONModel(dataflow dataflow, EDbVendor vendor)
static Dataflow	getSqlflowJSONModel(EDbVendor vendor, dataflow dataflow, boolean normalizeIdentifier)
Map<String,List<SqlInfo>>	getSqlInfos()
protected TObjectNameList	getTableLinkedColumns(TTable table)
static String	getVersion()
boolean	isAggregateFunction(TFunctionCall func)
boolean	isBuiltInFunctionName(String functionName)
boolean	isBuiltInFunctionName(TObjectName object)
boolean	isConstant(TObjectName object)
boolean	isIgnoreCoordinate()
boolean	isIgnoreRecordSet()
boolean	isIgnoreTemporaryTable()
boolean	isKeyword(String objectName)
boolean	isKeyword(TObjectName object)
boolean	isLinkOrphanColumnToFirstTable()
boolean	isShowCallRelation()
boolean	isShowConstantTable()
boolean	isShowCountTableColumn()
boolean	isShowImplicitSchema()
boolean	isShowJoin()
boolean	isSimpleShowFunction()
boolean	isSimpleShowTopSelectResultSet()
protected boolean	isStructColumn(TObjectName columnName)
protected boolean	isTopResultSet(TSelectSqlStatement stmt)
boolean	isTransform()
boolean	isTransformCoordinate()
static void	main(String[] args)
static dataflow	mergeTables(dataflow dataflow, Long startId)
static dataflow	mergeTables(dataflow dataflow, Long startId, Option option)
DynamicLineageResult	resolveDynamicSqlLineage(TCustomSqlStatement procAst, EDbVendor vendor, TSQLEnv sqlEnv, String currentDatabase, String defaultSchema, Map<String,SqlValue> bindings, DynamicLineageOptions options) Resolve dynamic-SQL object names by abstractly evaluating a stored procedure with a set of parameter bindings.
void	setHandleListener(DataFlowHandleListener listener)
void	setIgnoreCoordinate(boolean ignoreCoordinate)
void	setIgnoreRecordSet(boolean ignoreRecordSet)
void	setIgnoreTemporaryTable(boolean ignoreTemporaryTable)
void	setLinkOrphanColumnToFirstTable(boolean linkOrphanColumnToFirstTable)
void	setOption(Option option)
void	setShowCallRelation(boolean showCallRelation)
void	setShowConstantTable(boolean showConstantTable)
void	setShowCountTableColumn(boolean showCountTableColumn)
void	setShowImplicitSchema(boolean showImplicitSchema)
void	setShowJoin(boolean showJoin)
void	setSimpleShowFunction(boolean simpleShowFunction)
void	setSimpleShowTopSelectResultSet(boolean simpleShowTopSelectResultSet)
void	setSqlEnv(TSQLEnv sqlenv)
void	setTextFormat(boolean textFormat)
void	setTransform(boolean transform)
void	setTransformCoordinate(boolean transformCoordinate)
String	traceView()

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

DataFlowAnalyzer

public DataFlowAnalyzer(String sqlContent,
                        Option option)

DataFlowAnalyzer

public DataFlowAnalyzer(String sqlContent,
                        EDbVendor dbVendor,
                        boolean simpleOutput,
                        String defaultServer,
                        String defaultDatabase,
                        String defaltSchema)

DataFlowAnalyzer

public DataFlowAnalyzer(String sqlContent,
                        EDbVendor dbVendor,
                        boolean simpleOutput)

DataFlowAnalyzer

public DataFlowAnalyzer(String[] sqlContents,
                        Option option)

DataFlowAnalyzer

public DataFlowAnalyzer(String[] sqlContents,
                        EDbVendor dbVendor,
                        boolean simpleOutput,
                        String defaultServer,
                        String defaultDatabase,
                        String defaltSchema)

DataFlowAnalyzer

public DataFlowAnalyzer(String[] sqlContents,
                        EDbVendor dbVendor,
                        boolean simpleOutput)

DataFlowAnalyzer

public DataFlowAnalyzer(SqlInfo[] sqlInfos,
                        Option option)

DataFlowAnalyzer

public DataFlowAnalyzer(SqlInfo[] sqlInfos,
                        EDbVendor dbVendor,
                        boolean simpleOutput)

DataFlowAnalyzer

public DataFlowAnalyzer(File[] sqlFiles,
                        Option option)

DataFlowAnalyzer

public DataFlowAnalyzer(File[] sqlFiles,
                        EDbVendor dbVendor,
                        boolean simpleOutput)

DataFlowAnalyzer

public DataFlowAnalyzer(File sqlFile,
                        Option option)

DataFlowAnalyzer

public DataFlowAnalyzer(File sqlFile,
                        EDbVendor dbVendor,
                        boolean simpleOutput)

Method Detail

isIgnoreRecordSet

public boolean isIgnoreRecordSet()

Specified by:

isIgnoreRecordSet in interface IDataFlowAnalyzer

setIgnoreRecordSet

public void setIgnoreRecordSet(boolean ignoreRecordSet)

Specified by:

setIgnoreRecordSet in interface IDataFlowAnalyzer

isSimpleShowTopSelectResultSet

public boolean isSimpleShowTopSelectResultSet()

Specified by:

isSimpleShowTopSelectResultSet in interface IDataFlowAnalyzer

setSimpleShowTopSelectResultSet

public void setSimpleShowTopSelectResultSet(boolean simpleShowTopSelectResultSet)

Specified by:

setSimpleShowTopSelectResultSet in interface IDataFlowAnalyzer

isSimpleShowFunction

public boolean isSimpleShowFunction()

Specified by:

isSimpleShowFunction in interface IDataFlowAnalyzer

setSimpleShowFunction

public void setSimpleShowFunction(boolean simpleShowFunction)

Specified by:

setSimpleShowFunction in interface IDataFlowAnalyzer

isShowJoin

public boolean isShowJoin()

Specified by:

isShowJoin in interface IDataFlowAnalyzer

setShowJoin

public void setShowJoin(boolean showJoin)

Specified by:

setShowJoin in interface IDataFlowAnalyzer

setShowCallRelation

public void setShowCallRelation(boolean showCallRelation)

isShowCallRelation

public boolean isShowCallRelation()

isShowImplicitSchema

public boolean isShowImplicitSchema()

Specified by:

isShowImplicitSchema in interface IDataFlowAnalyzer

setShowImplicitSchema

public void setShowImplicitSchema(boolean showImplicitSchema)

Specified by:

setShowImplicitSchema in interface IDataFlowAnalyzer

isShowConstantTable

public boolean isShowConstantTable()

Specified by:

isShowConstantTable in interface IDataFlowAnalyzer

setShowConstantTable

public void setShowConstantTable(boolean showConstantTable)

Specified by:

setShowConstantTable in interface IDataFlowAnalyzer

isShowCountTableColumn

public boolean isShowCountTableColumn()

Specified by:

isShowCountTableColumn in interface IDataFlowAnalyzer

setShowCountTableColumn

public void setShowCountTableColumn(boolean showCountTableColumn)

Specified by:

setShowCountTableColumn in interface IDataFlowAnalyzer

isTransform

public boolean isTransform()

Specified by:

isTransform in interface IDataFlowAnalyzer

setTransform

public void setTransform(boolean transform)

Specified by:

setTransform in interface IDataFlowAnalyzer

isTransformCoordinate

public boolean isTransformCoordinate()

Specified by:

isTransformCoordinate in interface IDataFlowAnalyzer

setTransformCoordinate

public void setTransformCoordinate(boolean transformCoordinate)

Specified by:

setTransformCoordinate in interface IDataFlowAnalyzer

isLinkOrphanColumnToFirstTable

public boolean isLinkOrphanColumnToFirstTable()

Specified by:

isLinkOrphanColumnToFirstTable in interface IDataFlowAnalyzer

setLinkOrphanColumnToFirstTable

public void setLinkOrphanColumnToFirstTable(boolean linkOrphanColumnToFirstTable)

Specified by:

setLinkOrphanColumnToFirstTable in interface IDataFlowAnalyzer

isIgnoreTemporaryTable

public boolean isIgnoreTemporaryTable()

setIgnoreTemporaryTable

public void setIgnoreTemporaryTable(boolean ignoreTemporaryTable)

isIgnoreCoordinate

public boolean isIgnoreCoordinate()

Specified by:

isIgnoreCoordinate in interface IDataFlowAnalyzer

setIgnoreCoordinate

public void setIgnoreCoordinate(boolean ignoreCoordinate)

Specified by:

setIgnoreCoordinate in interface IDataFlowAnalyzer

setHandleListener

public void setHandleListener(DataFlowHandleListener listener)

Specified by:

setHandleListener in interface IDataFlowAnalyzer

setSqlEnv

public void setSqlEnv(TSQLEnv sqlenv)

Specified by:

setSqlEnv in interface IDataFlowAnalyzer

setOption

public void setOption(Option option)

Specified by:

setOption in interface IDataFlowAnalyzer

getOption

public Option getOption()

Specified by:

getOption in interface IDataFlowAnalyzer

chechSyntax

public String chechSyntax()

generateDataFlow

public String generateDataFlow(boolean withExtraInfo)

Specified by:

generateDataFlow in interface IDataFlowAnalyzer

generateDataFlow

public String generateDataFlow()

Specified by:

generateDataFlow in interface IDataFlowAnalyzer

generateSqlInfos

public String generateSqlInfos()

Specified by:

generateSqlInfos in interface IDataFlowAnalyzer

getSqlInfos

public Map<String,List<SqlInfo>> getSqlInfos()

Specified by:

getSqlInfos in interface IDataFlowAnalyzer

getHashSQLMap

public Map getHashSQLMap()

Specified by:

getHashSQLMap in interface IDataFlowAnalyzer

getDynamicSQLMap

public Map getDynamicSQLMap()

getSelectedDbObjectInfo

public DbObjectPosition getSelectedDbObjectInfo(Coordinate start,
                                                Coordinate end)

Deprecated. please use SqlInfoHelper.getSelectedDbObjectInfo

Specified by:

getSelectedDbObjectInfo in interface IDataFlowAnalyzer

mergeTables

public static dataflow mergeTables(dataflow dataflow,
                                   Long startId)

mergeTables

public static dataflow mergeTables(dataflow dataflow,
                                   Long startId,
                                   Option option)

getDataFlow

public dataflow getDataFlow()

Specified by:

getDataFlow in interface IDataFlowAnalyzer

getSimpleDataflow

public dataflow getSimpleDataflow(dataflow instance,
                                  boolean simpleOutput)
                           throws Exception

Throws:

Exception

getSimpleDataflow

public dataflow getSimpleDataflow(dataflow instance,
                                  boolean simpleOutput,
                                  List<String> types)
                           throws Exception

Throws:

Exception

analyzeResultColumnExpressionRelation

protected void analyzeResultColumnExpressionRelation(Object resultColumn,
                                                     TExpression expression)

flattenStructColumns

protected void flattenStructColumns(boolean hasDefinition,
                                    Table tableModel,
                                    TColumnDefinition column,
                                    Stack<TColumnDefinition> columnPaths,
                                    int index)

getTableLinkedColumns

protected TObjectNameList getTableLinkedColumns(TTable table)

isTopResultSet

protected boolean isTopResultSet(TSelectSqlStatement stmt)

analyzeTableSubquery

protected void analyzeTableSubquery(TTable table)

isStructColumn

protected boolean isStructColumn(TObjectName columnName)

getIdentifiedFunctionName

protected String getIdentifiedFunctionName(Function function)

dispose

public void dispose()

Specified by:

dispose in interface IDataFlowAnalyzer

getSqlflowJSONModel

@Deprecated
public static Dataflow getSqlflowJSONModel(dataflow dataflow)

Deprecated.

getSqlflowJSONModel

public static Dataflow getSqlflowJSONModel(dataflow dataflow,
                                           EDbVendor vendor)

getSqlflowJSONModel

public static Dataflow getSqlflowJSONModel(EDbVendor vendor,
                                           dataflow dataflow,
                                           boolean normalizeIdentifier)

getVersion

public static String getVersion()

getReleaseDate

public static String getReleaseDate()

main

public static void main(String[] args)

getErrorMessages

public List<ErrorInfo> getErrorMessages()

Specified by:

getErrorMessages in interface IDataFlowAnalyzer

getDynamicSqlSites

public List<DynamicSqlSite> getDynamicSqlSites()

Every dynamic-SQL execution site (T-SQL EXEC(...) / sp_executesql) the analyzer encountered, with whether it was statically resolved. Diagnostic only; not consumed by lineage. Read-only snapshot; see DynamicSqlSite.

resolveDynamicSqlLineage

public DynamicLineageResult resolveDynamicSqlLineage(TCustomSqlStatement procAst,
                                                     EDbVendor vendor,
                                                     TSQLEnv sqlEnv,
                                                     String currentDatabase,
                                                     String defaultSchema,
                                                     Map<String,SqlValue> bindings,
                                                     DynamicLineageOptions options)

Resolve dynamic-SQL object names by abstractly evaluating a stored procedure with a set of parameter bindings.

Given a T-SQL CREATE PROC parse tree and the values its parameters actually had at a call site (e.g. @SourceDB='QSP', @STG_AEG='STG_AEG'), this evaluates the procedure's dynamic-SQL string building (assignment + concatenation + name-building functions), materializes the concrete SQL each EXEC / sp_executesql site runs, analyzes it with ordinary dlineage, and returns the lineage edges tagged with dynamic provenance (origin=DYNAMIC_RESOLVED, source proc, stable dynamic-site id, binding hash). Sites that cannot be reduced are reported as honest UNRESOLVED diagnostics — never guessed.

This is abstract string evaluation, NOT execution: no table reads, no cursors, no data-dependent control flow. It is purely additive — it builds throwaway analyzers for the materialized strings and does not change the default dlineage output of this analyzer.

Parameters:

procAst - the CREATE PROC parse tree (currently T-SQL)

vendor - the SQL dialect (dbvmssql)

sqlEnv - catalog env for the resolved analysis (may be null)

currentDatabase - the proc's database (resolves unqualified names)

defaultSchema - the proc's default schema (e.g. dbo)

bindings - parameter name → concrete value

options - resource bounds (may be null for defaults)

traceView

public String traceView()

convertSQL

protected List<SqlInfo> convertSQL(EDbVendor vendor,
                                   String json)

setTextFormat

public void setTextFormat(boolean textFormat)

isBuiltInFunctionName

public boolean isBuiltInFunctionName(TObjectName object)

isBuiltInFunctionName

public boolean isBuiltInFunctionName(String functionName)

isKeyword

public boolean isKeyword(TObjectName object)

isKeyword

public boolean isKeyword(String objectName)

isAggregateFunction

public boolean isAggregateFunction(TFunctionCall func)

isConstant

public boolean isConstant(TObjectName object)