/** Check the 2 lists comparing the rows in order. If they are not the same fail the test. */
public void checkRows(List<RowMetaAndData> rows1, List<RowMetaAndData> rows2) {
int idx = 1;
if (rows1.size() != rows2.size()) {
fail("Number of rows is not the same: " + rows1.size() + " and " + rows2.size());
}
Iterator<RowMetaAndData> it1 = rows1.iterator();
Iterator<RowMetaAndData> it2 = rows2.iterator();
while (it1.hasNext() && it2.hasNext()) {
RowMetaAndData rm1 = it1.next();
RowMetaAndData rm2 = it2.next();
Object[] r1 = rm1.getData();
Object[] r2 = rm2.getData();
if (rm1.size() != rm2.size()) {
fail("row nr " + idx + " is not equal");
}
int fields[] = new int[rm1.size()];
for (int ydx = 0; ydx < rm1.size(); ydx++) {
fields[ydx] = ydx;
}
try {
if (rm1.getRowMeta().compare(r1, r2, fields) != 0) {
fail("row nr " + idx + " is not equal");
}
} catch (KettleValueException e) {
fail("row nr " + idx + " is not equal");
}
idx++;
}
}
public boolean init(StepMetaInterface smi, StepDataInterface sdi) {
meta = (RowGeneratorMeta) smi;
data = (RowGeneratorData) sdi;
if (super.init(smi, sdi)) {
// Determine the number of rows to generate...
data.rowLimit = Const.toLong(environmentSubstitute(meta.getRowLimit()), -1L);
data.rowsWritten = 0L;
if (data.rowLimit < 0L) // Unable to parse
{
logError(BaseMessages.getString(PKG, "RowGenerator.Wrong.RowLimit.Number"));
return false; // fail
}
// Create a row (constants) with all the values in it...
List<CheckResultInterface> remarks =
new ArrayList<CheckResultInterface>(); // stores the errors...
RowMetaAndData outputRow = buildRow(meta, remarks, getStepname());
if (!remarks.isEmpty()) {
for (int i = 0; i < remarks.size(); i++) {
CheckResult cr = (CheckResult) remarks.get(i);
logError(cr.getText());
}
return false;
}
data.outputRowData = outputRow.getData();
data.outputRowMeta = outputRow.getRowMeta();
return true;
}
return false;
}
/** Test case for injector step... also a show case on how to use injector. */
public void testInjector() throws Exception {
KettleEnvironment.init();
//
// Create a new transformation...
//
TransMeta transMeta = new TransMeta();
transMeta.setName("injectortest");
PluginRegistry registry = PluginRegistry.getInstance();
//
// create an injector step...
//
String injectorStepname = "injector step";
InjectorMeta im = new InjectorMeta();
// Set the information of the injector.
String injectorPid = registry.getPluginId(StepPluginType.class, im);
StepMeta injectorStep = new StepMeta(injectorPid, injectorStepname, (StepMetaInterface) im);
transMeta.addStep(injectorStep);
//
// Create a dummy step
//
String dummyStepname = "dummy step";
DummyTransMeta dm = new DummyTransMeta();
String dummyPid = registry.getPluginId(StepPluginType.class, dm);
StepMeta dummyStep = new StepMeta(dummyPid, dummyStepname, (StepMetaInterface) dm);
transMeta.addStep(dummyStep);
TransHopMeta hi = new TransHopMeta(injectorStep, dummyStep);
transMeta.addTransHop(hi);
// Now execute the transformation...
Trans trans = new Trans(transMeta);
trans.prepareExecution(null);
StepInterface si = trans.getStepInterface(dummyStepname, 0);
RowStepCollector rc = new RowStepCollector();
si.addRowListener(rc);
RowProducer rp = trans.addRowProducer(injectorStepname, 0);
trans.startThreads();
// add rows
List<RowMetaAndData> inputList = createData();
for (RowMetaAndData rm : inputList) {
rp.putRow(rm.getRowMeta(), rm.getData());
}
rp.finished();
trans.waitUntilFinished();
List<RowMetaAndData> resultRows = rc.getRowsWritten();
checkRows(resultRows, inputList);
}
/**
* Check the 2 lists comparing the rows in order. If they are not the same fail the test.
*
* @param rows1 set 1 of rows to compare
* @param rows2 set 2 of rows to compare
* @param fileNameColumn Number of the column containing the filename. This is only checked for
* being non-null (some systems maybe canonize names differently than we input).
*/
public static void checkRows(
List<RowMetaAndData> rows1, List<RowMetaAndData> rows2, int fileNameColumn)
throws TestFailedException {
int idx = 1;
if (rows1.size() != rows2.size()) {
throw new TestFailedException(
"Number of rows is not the same: " + rows1.size() + " and " + rows2.size());
}
Iterator<RowMetaAndData> itrRows1 = rows1.iterator();
Iterator<RowMetaAndData> itrRows2 = rows2.iterator();
while (itrRows1.hasNext() && itrRows2.hasNext()) {
RowMetaAndData rowMetaAndData1 = itrRows1.next();
RowMetaAndData rowMetaAndData2 = itrRows2.next();
RowMetaInterface rowMetaInterface1 = rowMetaAndData1.getRowMeta();
Object[] rowObject1 = rowMetaAndData1.getData();
Object[] rowObject2 = rowMetaAndData2.getData();
if (rowMetaAndData1.size() != rowMetaAndData2.size()) {
throw new TestFailedException("row number " + idx + " is not equal");
}
int[] fields = new int[rowMetaInterface1.size()];
for (int ydx = 0; ydx < rowMetaInterface1.size(); ydx++) {
fields[ydx] = ydx;
}
try {
if (fileNameColumn >= 0) {
rowObject1[fileNameColumn] = rowObject2[fileNameColumn];
}
if (rowMetaAndData1.getRowMeta().compare(rowObject1, rowObject2, fields) != 0) {
throw new ComparisonFailure(
"row nr " + idx + " is not equal",
rowMetaInterface1.getString(rowObject1),
rowMetaInterface1.getString(rowObject2));
}
} catch (KettleValueException e) {
throw new TestFailedException("row nr " + idx + " is not equal");
}
idx++;
}
}
public synchronized int getNrStepAttributes(ObjectId id_step) throws KettleException {
int retval = 0;
RowMetaAndData par = repository.connectionDelegate.getParameterMetaData(id_step);
String sql =
"SELECT COUNT(*) FROM "
+ quoteTable(KettleDatabaseRepository.TABLE_R_STEP_ATTRIBUTE)
+ " WHERE "
+ quote(KettleDatabaseRepository.FIELD_STEP_ATTRIBUTE_ID_STEP)
+ " = ? ";
RowMetaAndData r =
repository.connectionDelegate.getOneRow(sql, par.getRowMeta(), par.getData());
if (r != null) {
retval = (int) r.getInteger(0, 0L);
}
return retval;
}
public synchronized int getNrDatabases(ObjectId id_transformation) throws KettleException {
int retval = 0;
RowMetaAndData transIdRow =
repository.connectionDelegate.getParameterMetaData(id_transformation);
String sql =
"SELECT COUNT(*) FROM "
+ quoteTable(KettleDatabaseRepository.TABLE_R_STEP_DATABASE)
+ " WHERE "
+ quote(KettleDatabaseRepository.FIELD_STEP_DATABASE_ID_TRANSFORMATION)
+ " = ? ";
RowMetaAndData r =
repository.connectionDelegate.getOneRow(sql, transIdRow.getRowMeta(), transIdRow.getData());
if (r != null) {
retval = (int) r.getInteger(0, 0L);
}
return retval;
}
private Object[] getRowFromCache(RowMetaInterface lookupMeta, Object[] lookupRow)
throws KettleException {
if (data.allEquals) {
// only do the hashtable lookup when all equals otherwise conditions >, <, <> will give wrong
// results
TimedRow timedRow = data.look.get(new RowMetaAndData(data.lookupMeta, lookupRow));
if (timedRow != null) {
return timedRow.getRow();
}
} else { // special handling of conditions <,>, <> etc.
if (!data.hasDBCondition) { // e.g. LIKE not handled by this routine, yet
// TODO: find an alternative way to look up the data based on the condition.
// Not all conditions are "=" so we are going to have to evaluate row by row
// A sorted list or index might be a good solution here...
//
Enumeration<RowMetaAndData> keys = data.look.keys();
while (keys.hasMoreElements()) {
RowMetaAndData key = keys.nextElement();
// Now verify that the key is matching our conditions...
//
boolean match = true;
int lookupIndex = 0;
for (int i = 0; i < data.conditions.length && match; i++) {
ValueMetaInterface cmpMeta = lookupMeta.getValueMeta(lookupIndex);
Object cmpData = lookupRow[lookupIndex];
ValueMetaInterface keyMeta = key.getValueMeta(i);
Object keyData = key.getData()[i];
switch (data.conditions[i]) {
case DatabaseLookupMeta.CONDITION_EQ:
match = (cmpMeta.compare(cmpData, keyMeta, keyData) == 0);
break;
case DatabaseLookupMeta.CONDITION_NE:
match = (cmpMeta.compare(cmpData, keyMeta, keyData) != 0);
break;
case DatabaseLookupMeta.CONDITION_LT:
match = (cmpMeta.compare(cmpData, keyMeta, keyData) > 0);
break;
case DatabaseLookupMeta.CONDITION_LE:
match = (cmpMeta.compare(cmpData, keyMeta, keyData) >= 0);
break;
case DatabaseLookupMeta.CONDITION_GT:
match = (cmpMeta.compare(cmpData, keyMeta, keyData) < 0);
break;
case DatabaseLookupMeta.CONDITION_GE:
match = (cmpMeta.compare(cmpData, keyMeta, keyData) <= 0);
break;
case DatabaseLookupMeta.CONDITION_IS_NULL:
match = keyMeta.isNull(keyData);
break;
case DatabaseLookupMeta.CONDITION_IS_NOT_NULL:
match = !keyMeta.isNull(keyData);
break;
case DatabaseLookupMeta.CONDITION_BETWEEN:
// Between key >= cmp && key <= cmp2
ValueMetaInterface cmpMeta2 = lookupMeta.getValueMeta(lookupIndex + 1);
Object cmpData2 = lookupRow[lookupIndex + 1];
match = (keyMeta.compare(keyData, cmpMeta, cmpData) >= 0);
if (match) {
match = (keyMeta.compare(keyData, cmpMeta2, cmpData2) <= 0);
}
lookupIndex++;
break;
// TODO: add LIKE operator (think of changing the hasDBCondition logic then)
default:
match = false;
data.hasDBCondition =
true; // avoid looping in here the next time, also safety when a new condition
// will be introduced
break;
}
lookupIndex++;
}
if (match) {
TimedRow timedRow = data.look.get(key);
if (timedRow != null) {
return timedRow.getRow();
}
}
}
}
}
return null;
}
/** Test case for janino step. */
public void testJaninoStep() throws Exception {
KettleEnvironment.init();
//
// Create a new transformation...
//
TransMeta transMeta = new TransMeta();
transMeta.setName("janino test");
PluginRegistry registry = PluginRegistry.getInstance();
// create an injector step...
String injectorStepName = "injector step";
InjectorMeta im = new InjectorMeta();
// Set the information of the injector.
String injectorPid = registry.getPluginId(StepPluginType.class, im);
StepMeta injectorStep = new StepMeta(injectorPid, injectorStepName, im);
transMeta.addStep(injectorStep);
//
// create a janino step...
//
String stepname = "janino";
JaninoMeta jm = new JaninoMeta();
// Set the information of the step
String janinoPid = registry.getPluginId(StepPluginType.class, jm);
StepMeta janinoStep = new StepMeta(janinoPid, stepname, jm);
transMeta.addStep(janinoStep);
jm.setDefault();
JaninoMetaFunction[] formulas = {
new JaninoMetaFunction(
"string",
"(string==null)?null:\"string-value\"",
ValueMeta.TYPE_STRING,
-1,
-1,
"string"),
new JaninoMetaFunction(
"integer",
"(integer==null)?null:new Long(42L)",
ValueMeta.TYPE_INTEGER,
-1,
-1,
"integer"),
new JaninoMetaFunction(
"number",
"(number==null)?null:new Double(23.0)",
ValueMeta.TYPE_NUMBER,
-1,
-1,
"number"),
new JaninoMetaFunction(
"bigdecimal",
"(bigdecimal==null)?null:new java.math.BigDecimal(11.0)",
ValueMeta.TYPE_BIGNUMBER,
-1,
-1,
"bigdecimal"),
new JaninoMetaFunction(
"date",
"(date==null)?null:new java.util.Date(10000000)",
ValueMeta.TYPE_DATE,
-1,
-1,
"date"),
new JaninoMetaFunction(
"binary",
"(binary==null)?null:new byte[]{1,2,3,4,5}",
ValueMeta.TYPE_BINARY,
-1,
-1,
"binary"),
new JaninoMetaFunction(
"bool", "(bool==null)?null:Boolean.TRUE", ValueMeta.TYPE_BOOLEAN, -1, -1, "bool"),
};
jm.setFormula(formulas);
transMeta.addTransHop(new TransHopMeta(injectorStep, janinoStep));
//
// Create a dummy step
//
String dummyStepname = "dummy step";
DummyTransMeta dm = new DummyTransMeta();
String dummyPid = registry.getPluginId(StepPluginType.class, dm);
StepMeta dummyStep = new StepMeta(dummyPid, dummyStepname, dm);
transMeta.addStep(dummyStep);
TransHopMeta hi = new TransHopMeta(janinoStep, dummyStep);
transMeta.addTransHop(hi);
// Now execute the transformation...
Trans trans = new Trans(transMeta);
trans.prepareExecution(null);
StepInterface si = trans.getStepInterface(dummyStepname, 0);
RowStepCollector rc = new RowStepCollector();
si.addRowListener(rc);
RowProducer rp = trans.addRowProducer(injectorStepName, 0);
trans.startThreads();
for (RowMetaAndData rm : createInputList()) {
rp.putRow(rm.getRowMeta(), rm.getData());
}
rp.finished();
trans.waitUntilFinished();
List<RowMetaAndData> checkList = createExpectedList();
List<RowMetaAndData> resultRows = rc.getRowsWritten();
checkRows(resultRows, checkList);
}
protected Object[] writeToTable(RowMetaInterface rowMeta, Object[] r) throws KettleException {
if (r == null) { // Stop: last line or error encountered
if (log.isDetailed()) {
logDetailed("Last line inserted: stop");
}
return null;
}
PreparedStatement insertStatement = null;
Object[] insertRowData;
Object[] outputRowData = r;
String tableName = null;
boolean sendToErrorRow = false;
String errorMessage = null;
boolean rowIsSafe = false;
int[] updateCounts = null;
List<Exception> exceptionsList = null;
boolean batchProblem = false;
Object generatedKey = null;
if (meta.isTableNameInField()) {
// Cache the position of the table name field
if (data.indexOfTableNameField < 0) {
String realTablename = environmentSubstitute(meta.getTableNameField());
data.indexOfTableNameField = rowMeta.indexOfValue(realTablename);
if (data.indexOfTableNameField < 0) {
String message = "Unable to find table name field [" + realTablename + "] in input row";
logError(message);
throw new KettleStepException(message);
}
if (!meta.isTableNameInTable() && !meta.specifyFields()) {
data.insertRowMeta.removeValueMeta(data.indexOfTableNameField);
}
}
tableName = rowMeta.getString(r, data.indexOfTableNameField);
if (!meta.isTableNameInTable() && !meta.specifyFields()) {
// If the name of the table should not be inserted itself, remove the table name
// from the input row data as well. This forcibly creates a copy of r
//
insertRowData = RowDataUtil.removeItem(rowMeta.cloneRow(r), data.indexOfTableNameField);
} else {
insertRowData = r;
}
} else if (meta.isPartitioningEnabled()
&& (meta.isPartitioningDaily() || meta.isPartitioningMonthly())
&& (meta.getPartitioningField() != null && meta.getPartitioningField().length() > 0)) {
// Initialize some stuff!
if (data.indexOfPartitioningField < 0) {
data.indexOfPartitioningField =
rowMeta.indexOfValue(environmentSubstitute(meta.getPartitioningField()));
if (data.indexOfPartitioningField < 0) {
throw new KettleStepException(
"Unable to find field [" + meta.getPartitioningField() + "] in the input row!");
}
if (meta.isPartitioningDaily()) {
data.dateFormater = new SimpleDateFormat("yyyyMMdd");
} else {
data.dateFormater = new SimpleDateFormat("yyyyMM");
}
}
ValueMetaInterface partitioningValue = rowMeta.getValueMeta(data.indexOfPartitioningField);
if (!partitioningValue.isDate() || r[data.indexOfPartitioningField] == null) {
throw new KettleStepException(
"Sorry, the partitioning field needs to contain a data value and can't be empty!");
}
Object partitioningValueData = rowMeta.getDate(r, data.indexOfPartitioningField);
tableName =
environmentSubstitute(meta.getTableName())
+ "_"
+ data.dateFormater.format((Date) partitioningValueData);
insertRowData = r;
} else {
tableName = data.tableName;
insertRowData = r;
}
if (meta.specifyFields()) {
//
// The values to insert are those in the fields sections
//
insertRowData = new Object[data.valuenrs.length];
for (int idx = 0; idx < data.valuenrs.length; idx++) {
insertRowData[idx] = r[data.valuenrs[idx]];
}
}
if (Const.isEmpty(tableName)) {
throw new KettleStepException("The tablename is not defined (empty)");
}
insertStatement = data.preparedStatements.get(tableName);
if (insertStatement == null) {
String sql =
data.db.getInsertStatement(
environmentSubstitute(meta.getSchemaName()), tableName, data.insertRowMeta);
if (log.isDetailed()) {
logDetailed("Prepared statement : " + sql);
}
insertStatement = data.db.prepareSQL(sql, meta.isReturningGeneratedKeys());
data.preparedStatements.put(tableName, insertStatement);
}
try {
// For PG & GP, we add a savepoint before the row.
// Then revert to the savepoint afterwards... (not a transaction, so hopefully still fast)
//
if (data.useSafePoints) {
data.savepoint = data.db.setSavepoint();
}
data.db.setValues(data.insertRowMeta, insertRowData, insertStatement);
data.db.insertRow(
insertStatement, data.batchMode, false); // false: no commit, it is handled in this step
// different
if (isRowLevel()) {
logRowlevel("Written row: " + data.insertRowMeta.getString(insertRowData));
}
// Get a commit counter per prepared statement to keep track of separate tables, etc.
//
Integer commitCounter = data.commitCounterMap.get(tableName);
if (commitCounter == null) {
commitCounter = Integer.valueOf(1);
} else {
commitCounter++;
}
data.commitCounterMap.put(tableName, Integer.valueOf(commitCounter.intValue()));
// Release the savepoint if needed
//
if (data.useSafePoints) {
if (data.releaseSavepoint) {
data.db.releaseSavepoint(data.savepoint);
}
}
// Perform a commit if needed
//
if ((data.commitSize > 0) && ((commitCounter % data.commitSize) == 0)) {
if (data.db.getUseBatchInsert(data.batchMode)) {
try {
insertStatement.executeBatch();
data.db.commit();
insertStatement.clearBatch();
} catch (SQLException ex) {
throw Database.createKettleDatabaseBatchException("Error updating batch", ex);
} catch (Exception ex) {
throw new KettleDatabaseException("Unexpected error inserting row", ex);
}
} else {
// insertRow normal commit
data.db.commit();
}
// Clear the batch/commit counter...
//
data.commitCounterMap.put(tableName, Integer.valueOf(0));
rowIsSafe = true;
} else {
rowIsSafe = false;
}
// See if we need to get back the keys as well...
if (meta.isReturningGeneratedKeys()) {
RowMetaAndData extraKeys = data.db.getGeneratedKeys(insertStatement);
if (extraKeys.getRowMeta().size() > 0) {
// Send out the good word!
// Only 1 key at the moment. (should be enough for now :-)
generatedKey = extraKeys.getRowMeta().getInteger(extraKeys.getData(), 0);
} else {
// we have to throw something here, else we don't know what the
// type is of the returned key(s) and we would violate our own rule
// that a hop should always contain rows of the same type.
throw new KettleStepException(
"No generated keys while \"return generated keys\" is active!");
}
}
} catch (KettleDatabaseBatchException be) {
errorMessage = be.toString();
batchProblem = true;
sendToErrorRow = true;
updateCounts = be.getUpdateCounts();
exceptionsList = be.getExceptionsList();
if (getStepMeta().isDoingErrorHandling()) {
data.db.clearBatch(insertStatement);
data.db.commit(true);
} else {
data.db.clearBatch(insertStatement);
data.db.rollback();
StringBuilder msg =
new StringBuilder("Error batch inserting rows into table [" + tableName + "].");
msg.append(Const.CR);
msg.append("Errors encountered (first 10):").append(Const.CR);
for (int x = 0; x < be.getExceptionsList().size() && x < 10; x++) {
Exception exception = be.getExceptionsList().get(x);
if (exception.getMessage() != null) {
msg.append(exception.getMessage()).append(Const.CR);
}
}
throw new KettleException(msg.toString(), be);
}
} catch (KettleDatabaseException dbe) {
if (getStepMeta().isDoingErrorHandling()) {
if (isRowLevel()) {
logRowlevel("Written row to error handling : " + getInputRowMeta().getString(r));
}
if (data.useSafePoints) {
data.db.rollback(data.savepoint);
if (data.releaseSavepoint) {
data.db.releaseSavepoint(data.savepoint);
}
// data.db.commit(true); // force a commit on the connection too.
}
sendToErrorRow = true;
errorMessage = dbe.toString();
} else {
if (meta.ignoreErrors()) {
if (data.warnings < 20) {
if (log.isBasic()) {
logBasic(
"WARNING: Couldn't insert row into table: "
+ rowMeta.getString(r)
+ Const.CR
+ dbe.getMessage());
}
} else if (data.warnings == 20) {
if (log.isBasic()) {
logBasic(
"FINAL WARNING (no more then 20 displayed): Couldn't insert row into table: "
+ rowMeta.getString(r)
+ Const.CR
+ dbe.getMessage());
}
}
data.warnings++;
} else {
setErrors(getErrors() + 1);
data.db.rollback();
throw new KettleException(
"Error inserting row into table ["
+ tableName
+ "] with values: "
+ rowMeta.getString(r),
dbe);
}
}
}
// We need to add a key
if (generatedKey != null) {
outputRowData = RowDataUtil.addValueData(outputRowData, rowMeta.size(), generatedKey);
}
if (data.batchMode) {
if (sendToErrorRow) {
if (batchProblem) {
data.batchBuffer.add(outputRowData);
outputRowData = null;
processBatchException(errorMessage, updateCounts, exceptionsList);
} else {
// Simply add this row to the error row
putError(rowMeta, r, 1L, errorMessage, null, "TOP001");
outputRowData = null;
}
} else {
data.batchBuffer.add(outputRowData);
outputRowData = null;
if (rowIsSafe) { // A commit was done and the rows are all safe (no error)
for (int i = 0; i < data.batchBuffer.size(); i++) {
Object[] row = data.batchBuffer.get(i);
putRow(data.outputRowMeta, row);
incrementLinesOutput();
}
// Clear the buffer
data.batchBuffer.clear();
}
}
} else {
if (sendToErrorRow) {
putError(rowMeta, r, 1, errorMessage, null, "TOP001");
outputRowData = null;
}
}
return outputRowData;
}