Package org.pentaho.di.trans.steps.fileinput.text

Class TextFileInputUtils

java.lang.Object

org.pentaho.di.trans.steps.fileinput.text.TextFileInputUtils

public class TextFileInputUtils
extends Object

Some common methods for text file parsing.

Author:

Alexander Buloichik

Constructor Summary

Constructors

Constructor	Description
TextFileInputUtils()

Method Summary

Modifier and Type	Method	Description
static int	checkPattern(String text, String regexChar)	Finds a pattern within a String returning the occurrences number
static int	checkPattern(String text, String regexChar, String escapeCharacter)	Finds a pattern within a String returning the occurrences number
static final Object[]	convertLineToRow(org.pentaho.di.core.logging.LogChannelInterface log, TextFileLine textFileLine, TextFileInputMeta info, Object[] passThruFields, int nrPassThruFields, org.pentaho.di.core.row.RowMetaInterface outputRowMeta, org.pentaho.di.core.row.RowMetaInterface convertRowMeta, String fname, long rowNr, String delimiter, String enclosure, String escapeCharacter, FileErrorHandler errorHandler, BaseFileInputAdditionalField additionalOutputFields, String shortFilename, String path, boolean hidden, Date modificationDateTime, String uri, String rooturi, String extension, Long size)
static final Object[]	convertLineToRow(org.pentaho.di.core.logging.LogChannelInterface log, TextFileLine textFileLine, TextFileInputMeta info, Object[] passThruFields, int nrPassThruFields, org.pentaho.di.core.row.RowMetaInterface outputRowMeta, org.pentaho.di.core.row.RowMetaInterface convertRowMeta, String fname, long rowNr, String delimiter, String enclosure, String escapeCharacter, FileErrorHandler errorHandler, BaseFileInputAdditionalField additionalOutputFields, String shortFilename, String path, boolean hidden, Date modificationDateTime, String uri, String rooturi, String extension, Long size, boolean failOnParseError)
static final String[]	convertLineToStrings(org.pentaho.di.core.logging.LogChannelInterface log, String line, TextFileInputMeta inf, String delimiter, String enclosure, String escapeCharacters)
static final String	getLine(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, int formatNr, StringBuilder line)
static final String	getLine(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, EncodingType encodingType, int formatNr, StringBuilder line)
static final String	getLine(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, EncodingType encodingType, int fileFormatType, StringBuilder line, String regex)
static final TextFileLine	getLine(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, EncodingType encodingType, int fileFormatType, StringBuilder line, String regex, long lineNumberInFile)	Returns in the first position a line; ; on the second position how many lines from file were read to get a full line
static final String	getLine(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, EncodingType encodingType, int fileFormatType, StringBuilder line, String regex, String escapeChar)
static final TextFileLine	getLine(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, EncodingType encodingType, int fileFormatType, StringBuilder line, String regex, String escapeChar, long lineNumberInFile)
static final String[]	guessStringsFromLine(org.pentaho.di.core.variables.VariableSpace space, org.pentaho.di.core.logging.LogChannelInterface log, String line, TextFileInputMeta inf, String delimiter, String enclosure, String escapeCharacter)
static long	skipLines(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, EncodingType encodingType, int fileFormatType, StringBuilder line, int nrLinesToSkip, String regex, long lineNumberInFile)	Returns the line number in file
static long	skipLines(org.pentaho.di.core.logging.LogChannelInterface log, BufferedInputStreamReader reader, EncodingType encodingType, int fileFormatType, StringBuilder line, int nrLinesToSkip, String regex, String escapeChar, long lineNumberInFile)

Methods inherited from class java.lang.Object

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

Constructor Details

TextFileInputUtils

public TextFileInputUtils()

Method Details

guessStringsFromLine

public static final String[] guessStringsFromLine(org.pentaho.di.core.variables.VariableSpace space,
 org.pentaho.di.core.logging.LogChannelInterface log,
 String line,
 TextFileInputMeta inf,
 String delimiter,
 String enclosure,
 String escapeCharacter)
                                           throws org.pentaho.di.core.exception.KettleException

Throws:

org.pentaho.di.core.exception.KettleException

getLine

public static final String getLine(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 int formatNr,
 StringBuilder line)
                            throws org.pentaho.di.core.exception.KettleFileException

Throws:

org.pentaho.di.core.exception.KettleFileException

getLine

public static final String getLine(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 EncodingType encodingType,
 int fileFormatType,
 StringBuilder line,
 String regex)
                            throws org.pentaho.di.core.exception.KettleFileException

Throws:

org.pentaho.di.core.exception.KettleFileException

getLine

public static final String getLine(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 EncodingType encodingType,
 int fileFormatType,
 StringBuilder line,
 String regex,
 String escapeChar)
                            throws org.pentaho.di.core.exception.KettleFileException

Throws:

org.pentaho.di.core.exception.KettleFileException

getLine

public static final TextFileLine getLine(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 EncodingType encodingType,
 int fileFormatType,
 StringBuilder line,
 String regex,
 long lineNumberInFile)
                                  throws org.pentaho.di.core.exception.KettleFileException

Returns in the first position a line; ; on the second position how many lines from file were read to get a full line

Throws:

org.pentaho.di.core.exception.KettleFileException

getLine

public static final TextFileLine getLine(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 EncodingType encodingType,
 int fileFormatType,
 StringBuilder line,
 String regex,
 String escapeChar,
 long lineNumberInFile)
                                  throws org.pentaho.di.core.exception.KettleFileException

Throws:

org.pentaho.di.core.exception.KettleFileException

getLine

public static final String getLine(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 EncodingType encodingType,
 int formatNr,
 StringBuilder line)
                            throws org.pentaho.di.core.exception.KettleFileException

Throws:

org.pentaho.di.core.exception.KettleFileException

convertLineToRow

public static final Object[] convertLineToRow(org.pentaho.di.core.logging.LogChannelInterface log,
 TextFileLine textFileLine,
 TextFileInputMeta info,
 Object[] passThruFields,
 int nrPassThruFields,
 org.pentaho.di.core.row.RowMetaInterface outputRowMeta,
 org.pentaho.di.core.row.RowMetaInterface convertRowMeta,
 String fname,
 long rowNr,
 String delimiter,
 String enclosure,
 String escapeCharacter,
 FileErrorHandler errorHandler,
 BaseFileInputAdditionalField additionalOutputFields,
 String shortFilename,
 String path,
 boolean hidden,
 Date modificationDateTime,
 String uri,
 String rooturi,
 String extension,
 Long size)
                                       throws org.pentaho.di.core.exception.KettleException

Throws:

org.pentaho.di.core.exception.KettleException

convertLineToRow

public static final Object[] convertLineToRow(org.pentaho.di.core.logging.LogChannelInterface log,
 TextFileLine textFileLine,
 TextFileInputMeta info,
 Object[] passThruFields,
 int nrPassThruFields,
 org.pentaho.di.core.row.RowMetaInterface outputRowMeta,
 org.pentaho.di.core.row.RowMetaInterface convertRowMeta,
 String fname,
 long rowNr,
 String delimiter,
 String enclosure,
 String escapeCharacter,
 FileErrorHandler errorHandler,
 BaseFileInputAdditionalField additionalOutputFields,
 String shortFilename,
 String path,
 boolean hidden,
 Date modificationDateTime,
 String uri,
 String rooturi,
 String extension,
 Long size,
 boolean failOnParseError)
                                       throws org.pentaho.di.core.exception.KettleException

Parameters:

failOnParseError - if set to true, parsing failure on any line will cause parsing to be terminated; when set to false, parsing failure on a given line will not prevent remaining lines from being parsed - this allows us to analyze fields, even if some field is mis-configured and causes a parsing error for the values of that field.

Throws:

org.pentaho.di.core.exception.KettleException

convertLineToStrings

public static final String[] convertLineToStrings(org.pentaho.di.core.logging.LogChannelInterface log,
 String line,
 TextFileInputMeta inf,
 String delimiter,
 String enclosure,
 String escapeCharacters)
                                           throws org.pentaho.di.core.exception.KettleException

Throws:

org.pentaho.di.core.exception.KettleException

checkPattern

public static int checkPattern(String text,
 String regexChar)

Finds a pattern within a String returning the occurrences number

Parameters:

text - String to be evaluated

regexChar - String regexChar

Returns:

pattern occurrences number

checkPattern

public static int checkPattern(String text,
 String regexChar,
 String escapeCharacter)

Finds a pattern within a String returning the occurrences number

Parameters:

text - String to be evaluated

regexChar - String regexChar

escapeCharacter - String escapeCharacter, an empty string will be ignored

Returns:

pattern occurrences number

skipLines

public static long skipLines(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 EncodingType encodingType,
 int fileFormatType,
 StringBuilder line,
 int nrLinesToSkip,
 String regex,
 long lineNumberInFile)
                      throws org.pentaho.di.core.exception.KettleFileException

Returns the line number in file

Throws:

org.pentaho.di.core.exception.KettleFileException

skipLines

public static long skipLines(org.pentaho.di.core.logging.LogChannelInterface log,
 BufferedInputStreamReader reader,
 EncodingType encodingType,
 int fileFormatType,
 StringBuilder line,
 int nrLinesToSkip,
 String regex,
 String escapeChar,
 long lineNumberInFile)
                      throws org.pentaho.di.core.exception.KettleFileException

Throws:

org.pentaho.di.core.exception.KettleFileException