use of org.pentaho.di.ui.trans.steps.textfileinput.TextFileCSVImportProgressDialog in project pentaho-kettle by pentaho.
the class S3CsvInputDialog method getCSV.
// Get the data layout
private void getCSV() {
InputStream inputStream = null;
try {
S3CsvInputMeta meta = new S3CsvInputMeta();
getInfo(meta);
String filename = transMeta.environmentSubstitute(meta.getFilename());
String bucketname = transMeta.environmentSubstitute(meta.getBucket());
int maxLineSize = Const.toInt(transMeta.environmentSubstitute(meta.getMaxLineSize()), 2000);
wFields.table.removeAll();
S3ObjectsProvider s3ObjProvider = new S3ObjectsProvider(meta.getS3Service(transMeta));
S3Bucket s3bucket = s3ObjProvider.getBucket(bucketname);
if (s3bucket == null) {
throw new Exception(Messages.getString("S3DefaultService.Exception.UnableToFindBucket.Message", bucketname));
}
// Now we can continue reading the rows of data and we can guess the
// Sample a few lines to determine the correct type of the fields...
//
String shellText = Messages.getString("S3CsvInputDialog.LinesToSample.DialogTitle");
String lineText = Messages.getString("S3CsvInputDialog.LinesToSample.DialogMessage");
EnterNumberDialog end = new EnterNumberDialog(shell, 100, shellText, lineText);
int samples = end.open();
if (samples < 0) {
return;
}
// Only get the first lines, not the complete file
// And grab an input stream to the data...
inputStream = s3ObjProvider.getS3Object(s3bucket, filename, 0L, (long) samples * (long) maxLineSize).getDataInputStream();
InputStreamReader reader = new InputStreamReader(inputStream);
// Read a line of data to determine the number of rows...
//
String line = TextFileInput.getLine(log, reader, TextFileInputMeta.FILE_FORMAT_MIXED, new StringBuilder(1000));
// Split the string, header or data into parts...
//
String[] fieldNames = Const.splitString(line, meta.getDelimiter());
if (!meta.isHeaderPresent()) {
// Don't use field names from the header...
// Generate field names F1 ... F10
//
// $NON-NLS-1$
DecimalFormat df = new DecimalFormat("000");
for (int i = 0; i < fieldNames.length; i++) {
// $NON-NLS-1$
fieldNames[i] = "Field_" + df.format(i);
}
} else {
if (!Utils.isEmpty(meta.getEnclosure())) {
for (int i = 0; i < fieldNames.length; i++) {
if (fieldNames[i].startsWith(meta.getEnclosure()) && fieldNames[i].endsWith(meta.getEnclosure()) && fieldNames[i].length() > 1) {
fieldNames[i] = fieldNames[i].substring(1, fieldNames[i].length() - 1);
}
}
}
}
//
for (int i = 0; i < fieldNames.length; i++) {
fieldNames[i] = Const.trim(fieldNames[i]);
}
//
for (int i = 0; i < fieldNames.length; i++) {
TableItem item = new TableItem(wFields.table, SWT.NONE);
item.setText(1, fieldNames[i]);
item.setText(2, ValueMeta.getTypeDesc(ValueMetaInterface.TYPE_STRING));
}
wFields.removeEmptyRows();
wFields.setRowNums();
wFields.optWidth(true);
getInfo(meta);
TextFileCSVImportProgressDialog pd = new TextFileCSVImportProgressDialog(shell, meta, transMeta, reader, samples, true);
String message = pd.open();
if (message != null) {
wFields.removeAll();
// OK, what's the result of our search?
getData(meta);
wFields.removeEmptyRows();
wFields.setRowNums();
wFields.optWidth(true);
EnterTextDialog etd = new EnterTextDialog(shell, Messages.getString("S3CsvInputDialog.ScanResults.DialogTitle"), Messages.getString("S3CsvInputDialog.ScanResults.DialogMessage"), message, true);
etd.setReadOnly();
etd.open();
}
} catch (IOException e) {
new ErrorDialog(shell, Messages.getString("S3CsvInputDialog.IOError.DialogTitle"), Messages.getString("S3CsvInputDialog.IOError.DialogMessage"), e);
} catch (Exception e) {
new ErrorDialog(shell, Messages.getString("System.Dialog.Error.Title"), Messages.getString("S3CsvInputDialog.ErrorGettingFileDesc.DialogMessage"), e);
} finally {
try {
if (inputStream != null) {
inputStream.close();
}
} catch (Exception e) {
log.logError(stepname, "Error closing s3 data input stream", e);
}
}
}
use of org.pentaho.di.ui.trans.steps.textfileinput.TextFileCSVImportProgressDialog in project pentaho-kettle by pentaho.
the class CsvInputDialog method getCSV.
// Get the data layout
private void getCSV() {
InputStream inputStream = null;
try {
CsvInputMeta meta = new CsvInputMeta();
getInfo(meta);
String filename = transMeta.environmentSubstitute(meta.getFilename());
String delimiter = transMeta.environmentSubstitute(meta.getDelimiter());
String enclosure = transMeta.environmentSubstitute(meta.getEnclosure());
FileObject fileObject = KettleVFS.getFileObject(filename);
if (!(fileObject instanceof LocalFile)) {
//
throw new KettleException(BaseMessages.getString(PKG, "CsvInput.Log.OnlyLocalFilesAreSupported"));
}
wFields.table.removeAll();
inputStream = KettleVFS.getInputStream(fileObject);
String realEncoding = transMeta.environmentSubstitute(meta.getEncoding());
InputStreamReader reader;
if (Utils.isEmpty(realEncoding)) {
reader = new InputStreamReader(inputStream);
} else {
reader = new InputStreamReader(inputStream, realEncoding);
}
EncodingType encodingType = EncodingType.guessEncodingType(reader.getEncoding());
// Read a line of data to determine the number of rows...
//
String line = TextFileInput.getLine(log, reader, encodingType, TextFileInputMeta.FILE_FORMAT_UNIX, new StringBuilder(1000));
// Split the string, header or data into parts...
//
String[] fieldNames = CsvInput.guessStringsFromLine(log, line, delimiter, enclosure, meta.getEscapeCharacter());
if (!meta.isHeaderPresent()) {
// Don't use field names from the header...
// Generate field names F1 ... F10
//
DecimalFormat df = new DecimalFormat("000");
for (int i = 0; i < fieldNames.length; i++) {
fieldNames[i] = "Field_" + df.format(i);
}
} else {
if (!Utils.isEmpty(meta.getEnclosure())) {
for (int i = 0; i < fieldNames.length; i++) {
if (fieldNames[i].startsWith(meta.getEnclosure()) && fieldNames[i].endsWith(meta.getEnclosure()) && fieldNames[i].length() > 1) {
fieldNames[i] = fieldNames[i].substring(1, fieldNames[i].length() - 1);
}
}
}
}
//
for (int i = 0; i < fieldNames.length; i++) {
fieldNames[i] = Const.trim(fieldNames[i]);
}
//
for (int i = 0; i < fieldNames.length; i++) {
TableItem item = new TableItem(wFields.table, SWT.NONE);
item.setText(1, fieldNames[i]);
item.setText(2, ValueMetaFactory.getValueMetaName(ValueMetaInterface.TYPE_STRING));
}
wFields.removeEmptyRows();
wFields.setRowNums();
wFields.optWidth(true);
// Now we can continue reading the rows of data and we can guess the
// Sample a few lines to determine the correct type of the fields...
//
String shellText = BaseMessages.getString(PKG, "CsvInputDialog.LinesToSample.DialogTitle");
String lineText = BaseMessages.getString(PKG, "CsvInputDialog.LinesToSample.DialogMessage");
EnterNumberDialog end = new EnterNumberDialog(shell, 100, shellText, lineText);
int samples = end.open();
if (samples >= 0) {
getInfo(meta);
TextFileCSVImportProgressDialog pd = new TextFileCSVImportProgressDialog(shell, meta, transMeta, reader, samples, true);
String message = pd.open();
if (message != null) {
wFields.removeAll();
// OK, what's the result of our search?
getData(meta, false);
wFields.removeEmptyRows();
wFields.setRowNums();
wFields.optWidth(true);
EnterTextDialog etd = new EnterTextDialog(shell, BaseMessages.getString(PKG, "CsvInputDialog.ScanResults.DialogTitle"), BaseMessages.getString(PKG, "CsvInputDialog.ScanResults.DialogMessage"), message, true);
etd.setReadOnly();
etd.open();
// asyncUpdatePreview();
}
}
} catch (IOException e) {
new ErrorDialog(shell, BaseMessages.getString(PKG, "CsvInputDialog.IOError.DialogTitle"), BaseMessages.getString(PKG, "CsvInputDialog.IOError.DialogMessage"), e);
} catch (KettleException e) {
new ErrorDialog(shell, BaseMessages.getString(PKG, "System.Dialog.Error.Title"), BaseMessages.getString(PKG, "CsvInputDialog.ErrorGettingFileDesc.DialogMessage"), e);
} finally {
try {
inputStream.close();
} catch (Exception e) {
// Ignore close errors
}
}
}
use of org.pentaho.di.ui.trans.steps.textfileinput.TextFileCSVImportProgressDialog in project pentaho-kettle by pentaho.
the class ParGzipCsvInputDialog method getCSV.
// Get the data layout
private void getCSV() {
InputStream inputStream = null;
try {
ParGzipCsvInputMeta meta = new ParGzipCsvInputMeta();
getInfo(meta);
String filename = transMeta.environmentSubstitute(meta.getFilename());
FileObject fileObject = KettleVFS.getFileObject(filename);
if (!(fileObject instanceof LocalFile)) {
//
throw new KettleException(BaseMessages.getString(PKG, "ParGzipCsvInput.Log.OnlyLocalFilesAreSupported"));
}
wFields.table.removeAll();
inputStream = new GZIPInputStream(KettleVFS.getInputStream(fileObject));
InputStreamReader reader = new InputStreamReader(inputStream);
EncodingType encodingType = EncodingType.guessEncodingType(reader.getEncoding());
// Read a line of data to determine the number of rows...
//
String line = TextFileInput.getLine(log, reader, encodingType, TextFileInputMeta.FILE_FORMAT_MIXED, new StringBuilder(1000));
// Split the string, header or data into parts...
//
String[] fieldNames = Const.splitString(line, meta.getDelimiter());
if (!meta.isHeaderPresent()) {
// Don't use field names from the header...
// Generate field names F1 ... F10
//
DecimalFormat df = new DecimalFormat("000");
for (int i = 0; i < fieldNames.length; i++) {
fieldNames[i] = "Field_" + df.format(i);
}
} else {
if (!Utils.isEmpty(meta.getEnclosure())) {
for (int i = 0; i < fieldNames.length; i++) {
if (fieldNames[i].startsWith(meta.getEnclosure()) && fieldNames[i].endsWith(meta.getEnclosure()) && fieldNames[i].length() > 1) {
fieldNames[i] = fieldNames[i].substring(1, fieldNames[i].length() - 1);
}
}
}
}
//
for (int i = 0; i < fieldNames.length; i++) {
fieldNames[i] = Const.trim(fieldNames[i]);
}
//
for (int i = 0; i < fieldNames.length; i++) {
TableItem item = new TableItem(wFields.table, SWT.NONE);
item.setText(1, fieldNames[i]);
item.setText(2, ValueMetaFactory.getValueMetaName(ValueMetaInterface.TYPE_STRING));
}
wFields.removeEmptyRows();
wFields.setRowNums();
wFields.optWidth(true);
// Now we can continue reading the rows of data and we can guess the
// Sample a few lines to determine the correct type of the fields...
//
String shellText = BaseMessages.getString(PKG, "ParGzipCsvInputDialog.LinesToSample.DialogTitle");
String lineText = BaseMessages.getString(PKG, "ParGzipCsvInputDialog.LinesToSample.DialogMessage");
EnterNumberDialog end = new EnterNumberDialog(shell, 100, shellText, lineText);
int samples = end.open();
if (samples >= 0) {
getInfo(meta);
TextFileCSVImportProgressDialog pd = new TextFileCSVImportProgressDialog(shell, meta, transMeta, reader, samples, true);
String message = pd.open();
if (message != null) {
wFields.removeAll();
// OK, what's the result of our search?
getData(meta);
wFields.removeEmptyRows();
wFields.setRowNums();
wFields.optWidth(true);
EnterTextDialog etd = new EnterTextDialog(shell, BaseMessages.getString(PKG, "ParGzipCsvInputDialog.ScanResults.DialogTitle"), BaseMessages.getString(PKG, "ParGzipCsvInputDialog.ScanResults.DialogMessage"), message, true);
etd.setReadOnly();
etd.open();
}
}
} catch (IOException e) {
new ErrorDialog(shell, BaseMessages.getString(PKG, "ParGzipCsvInputDialog.IOError.DialogTitle"), BaseMessages.getString(PKG, "ParGzipCsvInputDialog.IOError.DialogMessage"), e);
} catch (KettleException e) {
new ErrorDialog(shell, BaseMessages.getString(PKG, "System.Dialog.Error.Title"), BaseMessages.getString(PKG, "ParGzipCsvInputDialog.ErrorGettingFileDesc.DialogMessage"), e);
} finally {
try {
inputStream.close();
} catch (Exception e) {
// Ignore errors
}
}
}
Aggregations