The Meta-Environment API

com.csvreader
Class CsvReader

java.lang.Object
  extended by com.csvreader.CsvReader

public class CsvReader
extends java.lang.Object

A stream based parser for parsing delimited text data from a file or a stream.


Nested Class Summary
private  class CsvReader.ColumnBuffer
           
private  class CsvReader.ComplexEscape
           
private  class CsvReader.DataBuffer
           
private  class CsvReader.HeadersHolder
           
private  class CsvReader.Letters
           
private  class CsvReader.RawRecordBuffer
           
private  class CsvReader.StaticSettings
           
private  class CsvReader.UserSettings
           
 
Field Summary
private  java.nio.charset.Charset charset
           
private  boolean closed
           
private  CsvReader.ColumnBuffer columnBuffer
           
private  int columnsCount
           
private  long currentRecord
           
private  CsvReader.DataBuffer dataBuffer
           
static int ESCAPE_MODE_BACKSLASH
          Use a backslash character before the text qualifier to represent an occurance of the text qualifier.
static int ESCAPE_MODE_DOUBLED
          Double up the text qualifier to represent an occurance of the text qualifier.
private  java.lang.String fileName
           
private  boolean hasMoreData
           
private  boolean hasReadNextLine
           
private  CsvReader.HeadersHolder headersHolder
           
private  boolean initialized
           
private  java.io.Reader inputStream
           
private  boolean[] isQualified
           
private  char lastLetter
           
private  CsvReader.RawRecordBuffer rawBuffer
           
private  java.lang.String rawRecord
           
private  boolean startedColumn
           
private  boolean startedWithQualifier
           
private  boolean useCustomRecordDelimiter
           
private  CsvReader.UserSettings userSettings
           
private  java.lang.String[] values
           
 
Constructor Summary
CsvReader(java.io.InputStream inputStream, char delimiter, java.nio.charset.Charset charset)
          Constructs a CsvReader object using an InputStream object as the data source.
CsvReader(java.io.InputStream inputStream, java.nio.charset.Charset charset)
          Constructs a CsvReader object using an InputStream object as the data source. Uses a comma as the column delimiter.
CsvReader(java.io.Reader inputStream)
          Constructs a CsvReader object using a Reader object as the data source. Uses a comma as the column delimiter.
CsvReader(java.io.Reader inputStream, char delimiter)
          Constructs a CsvReader object using a Reader object as the data source.
CsvReader(java.lang.String fileName)
          Creates a CsvReader object using a file as the data source. Uses a comma as the column delimiter and ISO-8859-1 as the Charset.
CsvReader(java.lang.String fileName, char delimiter)
          Creates a CsvReader object using a file as the data source. Uses ISO-8859-1 as the Charset.
CsvReader(java.lang.String fileName, char delimiter, java.nio.charset.Charset charset)
          Creates a CsvReader object using a file as the data source.
 
Method Summary
private  void appendLetter(char letter)
           
private  void checkClosed()
           
private  void checkDataLength()
           
 void close()
          Closes and releases all related resources.
private  void close(boolean closing)
           
private  void endColumn()
           
private  void endRecord()
           
protected  void finalize()
           
 java.lang.String get(int columnIndex)
          Returns the current column value for a given column index.
 java.lang.String get(java.lang.String headerName)
          Returns the current column value for a given column header name.
 boolean getCaptureRawRecord()
           
 int getColumnCount()
          Gets the count of columns found in this record.
 char getComment()
          Gets the character being used as a comment signal.
 long getCurrentRecord()
          Gets the index of the current record.
 char getDelimiter()
          Gets the character being used as the column delimiter.
 int getEscapeMode()
          Gets the current way to escape an occurance of the text qualifier inside qualified data.
 java.lang.String getHeader(int columnIndex)
          Returns the column header value for a given column index.
 int getHeaderCount()
          Gets the count of headers read in by a previous call to readHeaders().
 java.lang.String[] getHeaders()
          Returns the header values as a string array.
 int getIndex(java.lang.String headerName)
          Gets the corresponding column index for a given column header name.
 java.lang.String getRawRecord()
           
 char getRecordDelimiter()
           
 boolean getSafetySwitch()
          Safety caution to prevent the parser from using large amounts of memory in the case where parsing settings like file encodings don't end up matching the actual format of a file.
 boolean getSkipEmptyRecords()
           
 char getTextQualifier()
          Gets the character to use as a text qualifier in the data.
 boolean getTrimWhitespace()
          Gets whether leading and trailing whitespace characters are being trimmed from non-textqualified column data.
 boolean getUseComments()
          Gets whether comments are being looked for while parsing or not.
 boolean getUseTextQualifier()
          Whether text qualifiers will be used while parsing or not.
 java.lang.String[] getValues()
           
private static char hexToDec(char hex)
           
 boolean isQualified(int columnIndex)
           
static CsvReader parse(java.lang.String data)
          Creates a CsvReader object using a string of data as the source. Uses ISO-8859-1 as the Charset.
 boolean readHeaders()
          Read the first record of data as column headers.
 boolean readRecord()
          Reads another record.
 void setCaptureRawRecord(boolean captureRawRecord)
           
 void setComment(char comment)
          Sets the character to use as a comment signal.
 void setDelimiter(char delimiter)
          Sets the character to use as the column delimiter.
 void setEscapeMode(int escapeMode)
          Sets the current way to escape an occurance of the text qualifier inside qualified data.
 void setHeaders(java.lang.String[] headers)
           
 void setRecordDelimiter(char recordDelimiter)
          Sets the character to use as the record delimiter.
 void setSafetySwitch(boolean safetySwitch)
          Safety caution to prevent the parser from using large amounts of memory in the case where parsing settings like file encodings don't end up matching the actual format of a file.
 void setSkipEmptyRecords(boolean skipEmptyRecords)
           
 void setTextQualifier(char textQualifier)
          Sets the character to use as a text qualifier in the data.
 void setTrimWhitespace(boolean trimWhitespace)
          Sets whether leading and trailing whitespace characters should be trimmed from non-textqualified column data or not.
 void setUseComments(boolean useComments)
          Sets whether comments are being looked for while parsing or not.
 void setUseTextQualifier(boolean useTextQualifier)
          Sets whether text qualifiers will be used while parsing or not.
 boolean skipLine()
          Skips the next line of data using the standard end of line characters and does not do any column delimited parsing.
 boolean skipRecord()
          Skips the next record of data by parsing each column. Does not increment getCurrentRecord().
private  void updateCurrentValue()
           
 
Methods inherited from class java.lang.Object
clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

inputStream

private java.io.Reader inputStream

fileName

private java.lang.String fileName

userSettings

private CsvReader.UserSettings userSettings

charset

private java.nio.charset.Charset charset

useCustomRecordDelimiter

private boolean useCustomRecordDelimiter

dataBuffer

private CsvReader.DataBuffer dataBuffer

columnBuffer

private CsvReader.ColumnBuffer columnBuffer

rawBuffer

private CsvReader.RawRecordBuffer rawBuffer

isQualified

private boolean[] isQualified

rawRecord

private java.lang.String rawRecord

headersHolder

private CsvReader.HeadersHolder headersHolder

startedColumn

private boolean startedColumn

startedWithQualifier

private boolean startedWithQualifier

hasMoreData

private boolean hasMoreData

lastLetter

private char lastLetter

hasReadNextLine

private boolean hasReadNextLine

columnsCount

private int columnsCount

currentRecord

private long currentRecord

values

private java.lang.String[] values

initialized

private boolean initialized

closed

private boolean closed

ESCAPE_MODE_DOUBLED

public static final int ESCAPE_MODE_DOUBLED
Double up the text qualifier to represent an occurance of the text qualifier.

See Also:
Constant Field Values

ESCAPE_MODE_BACKSLASH

public static final int ESCAPE_MODE_BACKSLASH
Use a backslash character before the text qualifier to represent an occurance of the text qualifier.

See Also:
Constant Field Values
Constructor Detail

CsvReader

public CsvReader(java.lang.String fileName,
                 char delimiter,
                 java.nio.charset.Charset charset)
          throws java.io.FileNotFoundException
Creates a CsvReader object using a file as the data source.

Parameters:
fileName - The path to the file to use as the data source.
delimiter - The character to use as the column delimiter.
charset - The Charset to use while parsing the data.
Throws:
java.io.FileNotFoundException

CsvReader

public CsvReader(java.lang.String fileName,
                 char delimiter)
          throws java.io.FileNotFoundException
Creates a CsvReader object using a file as the data source. Uses ISO-8859-1 as the Charset.

Parameters:
fileName - The path to the file to use as the data source.
delimiter - The character to use as the column delimiter.
Throws:
java.io.FileNotFoundException

CsvReader

public CsvReader(java.lang.String fileName)
          throws java.io.FileNotFoundException
Creates a CsvReader object using a file as the data source. Uses a comma as the column delimiter and ISO-8859-1 as the Charset.

Parameters:
fileName - The path to the file to use as the data source.
Throws:
java.io.FileNotFoundException

CsvReader

public CsvReader(java.io.Reader inputStream,
                 char delimiter)
Constructs a CsvReader object using a Reader object as the data source.

Parameters:
inputStream - The stream to use as the data source.
delimiter - The character to use as the column delimiter.

CsvReader

public CsvReader(java.io.Reader inputStream)
Constructs a CsvReader object using a Reader object as the data source. Uses a comma as the column delimiter.

Parameters:
inputStream - The stream to use as the data source.

CsvReader

public CsvReader(java.io.InputStream inputStream,
                 char delimiter,
                 java.nio.charset.Charset charset)
Constructs a CsvReader object using an InputStream object as the data source.

Parameters:
inputStream - The stream to use as the data source.
delimiter - The character to use as the column delimiter.
charset - The Charset to use while parsing the data.

CsvReader

public CsvReader(java.io.InputStream inputStream,
                 java.nio.charset.Charset charset)
Constructs a CsvReader object using an InputStream object as the data source. Uses a comma as the column delimiter.

Parameters:
inputStream - The stream to use as the data source.
charset - The Charset to use while parsing the data.
Method Detail

getCaptureRawRecord

public boolean getCaptureRawRecord()

setCaptureRawRecord

public void setCaptureRawRecord(boolean captureRawRecord)

getRawRecord

public java.lang.String getRawRecord()

getTrimWhitespace

public boolean getTrimWhitespace()
Gets whether leading and trailing whitespace characters are being trimmed from non-textqualified column data. Default is true.

Returns:
Whether leading and trailing whitespace characters are being trimmed from non-textqualified column data.

setTrimWhitespace

public void setTrimWhitespace(boolean trimWhitespace)
Sets whether leading and trailing whitespace characters should be trimmed from non-textqualified column data or not. Default is true.

Parameters:
trimWhitespace - Whether leading and trailing whitespace characters should be trimmed from non-textqualified column data or not.

getDelimiter

public char getDelimiter()
Gets the character being used as the column delimiter. Default is comma, ','.

Returns:
The character being used as the column delimiter.

setDelimiter

public void setDelimiter(char delimiter)
Sets the character to use as the column delimiter. Default is comma, ','.

Parameters:
delimiter - The character to use as the column delimiter.

getRecordDelimiter

public char getRecordDelimiter()

setRecordDelimiter

public void setRecordDelimiter(char recordDelimiter)
Sets the character to use as the record delimiter.

Parameters:
recordDelimiter - The character to use as the record delimiter. Default is combination of standard end of line characters for Windows, Unix, or Mac.

getTextQualifier

public char getTextQualifier()
Gets the character to use as a text qualifier in the data.

Returns:
The character to use as a text qualifier in the data.

setTextQualifier

public void setTextQualifier(char textQualifier)
Sets the character to use as a text qualifier in the data.

Parameters:
textQualifier - The character to use as a text qualifier in the data.

getUseTextQualifier

public boolean getUseTextQualifier()
Whether text qualifiers will be used while parsing or not.

Returns:
Whether text qualifiers will be used while parsing or not.

setUseTextQualifier

public void setUseTextQualifier(boolean useTextQualifier)
Sets whether text qualifiers will be used while parsing or not.

Parameters:
useTextQualifier - Whether to use a text qualifier while parsing or not.

getComment

public char getComment()
Gets the character being used as a comment signal.

Returns:
The character being used as a comment signal.

setComment

public void setComment(char comment)
Sets the character to use as a comment signal.

Parameters:
comment - The character to use as a comment signal.

getUseComments

public boolean getUseComments()
Gets whether comments are being looked for while parsing or not.

Returns:
Whether comments are being looked for while parsing or not.

setUseComments

public void setUseComments(boolean useComments)
Sets whether comments are being looked for while parsing or not.

Parameters:
useComments - Whether comments are being looked for while parsing or not.

getEscapeMode

public int getEscapeMode()
Gets the current way to escape an occurance of the text qualifier inside qualified data.

Returns:
The current way to escape an occurance of the text qualifier inside qualified data.

setEscapeMode

public void setEscapeMode(int escapeMode)
                   throws java.lang.IllegalArgumentException
Sets the current way to escape an occurance of the text qualifier inside qualified data.

Parameters:
escapeMode - The way to escape an occurance of the text qualifier inside qualified data.
Throws:
java.lang.IllegalArgumentException - When an illegal value is specified for escapeMode.

getSkipEmptyRecords

public boolean getSkipEmptyRecords()

setSkipEmptyRecords

public void setSkipEmptyRecords(boolean skipEmptyRecords)

getSafetySwitch

public boolean getSafetySwitch()
Safety caution to prevent the parser from using large amounts of memory in the case where parsing settings like file encodings don't end up matching the actual format of a file. This switch can be turned off if the file format is known and tested. With the switch off, the max column lengths and max column count per record supported by the parser will greatly increase. Default is true.

Returns:
The current setting of the safety switch.

setSafetySwitch

public void setSafetySwitch(boolean safetySwitch)
Safety caution to prevent the parser from using large amounts of memory in the case where parsing settings like file encodings don't end up matching the actual format of a file. This switch can be turned off if the file format is known and tested. With the switch off, the max column lengths and max column count per record supported by the parser will greatly increase. Default is true.

Parameters:
safetySwitch -

getColumnCount

public int getColumnCount()
Gets the count of columns found in this record.

Returns:
The count of columns found in this record.

getCurrentRecord

public long getCurrentRecord()
Gets the index of the current record.

Returns:
The index of the current record.

getHeaderCount

public int getHeaderCount()
Gets the count of headers read in by a previous call to readHeaders().

Returns:
The count of headers read in by a previous call to readHeaders().

getHeaders

public java.lang.String[] getHeaders()
                              throws java.io.IOException
Returns the header values as a string array.

Returns:
The header values as a String array.
Throws:
java.io.IOException - Thrown if this object has already been closed.

setHeaders

public void setHeaders(java.lang.String[] headers)

getValues

public java.lang.String[] getValues()
                             throws java.io.IOException
Throws:
java.io.IOException

get

public java.lang.String get(int columnIndex)
                     throws java.io.IOException
Returns the current column value for a given column index.

Parameters:
columnIndex - The index of the column.
Returns:
The current column value.
Throws:
java.io.IOException - Thrown if this object has already been closed.

get

public java.lang.String get(java.lang.String headerName)
                     throws java.io.IOException
Returns the current column value for a given column header name.

Parameters:
headerName - The header name of the column.
Returns:
The current column value.
Throws:
java.io.IOException - Thrown if this object has already been closed.

parse

public static CsvReader parse(java.lang.String data)
Creates a CsvReader object using a string of data as the source. Uses ISO-8859-1 as the Charset.

Parameters:
data - The String of data to use as the source.
Returns:
A CsvReader object using the String of data as the source.

readRecord

public boolean readRecord()
                   throws java.io.IOException
Reads another record.

Returns:
Whether another record was successfully read or not.
Throws:
java.io.IOException - Thrown if an error occurs while reading data from the source stream.

checkDataLength

private void checkDataLength()
                      throws java.io.IOException
Throws:
java.io.IOException - Thrown if an error occurs while reading data from the source stream.

readHeaders

public boolean readHeaders()
                    throws java.io.IOException
Read the first record of data as column headers.

Returns:
Whether the header record was successfully read or not.
Throws:
java.io.IOException - Thrown if an error occurs while reading data from the source stream.

getHeader

public java.lang.String getHeader(int columnIndex)
                           throws java.io.IOException
Returns the column header value for a given column index.

Parameters:
columnIndex - The index of the header column being requested.
Returns:
The value of the column header at the given column index.
Throws:
java.io.IOException - Thrown if this object has already been closed.

isQualified

public boolean isQualified(int columnIndex)
                    throws java.io.IOException
Throws:
java.io.IOException

endColumn

private void endColumn()
                throws java.io.IOException
Throws:
java.io.IOException - Thrown if a very rare extreme exception occurs during parsing, normally resulting from improper data format.

appendLetter

private void appendLetter(char letter)

updateCurrentValue

private void updateCurrentValue()

endRecord

private void endRecord()

getIndex

public int getIndex(java.lang.String headerName)
             throws java.io.IOException
Gets the corresponding column index for a given column header name.

Parameters:
headerName - The header name of the column.
Returns:
The column index for the given column header name. Returns -1 if not found.
Throws:
java.io.IOException - Thrown if this object has already been closed.

skipRecord

public boolean skipRecord()
                   throws java.io.IOException
Skips the next record of data by parsing each column. Does not increment getCurrentRecord().

Returns:
Whether another record was successfully skipped or not.
Throws:
java.io.IOException - Thrown if an error occurs while reading data from the source stream.

skipLine

public boolean skipLine()
                 throws java.io.IOException
Skips the next line of data using the standard end of line characters and does not do any column delimited parsing.

Returns:
Whether a line was successfully skipped or not.
Throws:
java.io.IOException - Thrown if an error occurs while reading data from the source stream.

close

public void close()
Closes and releases all related resources.


close

private void close(boolean closing)

checkClosed

private void checkClosed()
                  throws java.io.IOException
Throws:
java.io.IOException - Thrown if this object has already been closed.

finalize

protected void finalize()
Overrides:
finalize in class java.lang.Object

hexToDec

private static char hexToDec(char hex)

The Meta-Environment API