org.apache.drill.exec.store.easy.text.compliant

Class TextParsingSettings

java.lang.Object

org.apache.drill.exec.store.easy.text.compliant.TextParsingSettings

public class TextParsingSettings
extends Object

Field Summary

Fields

Modifier and Type	Field and Description
static TextParsingSettings	DEFAULT

Constructor Summary

Constructors

Constructor and Description
TextParsingSettings()

Method Summary

Methods

Modifier and Type	Method and Description
byte	getComment()
byte	getDelimiter() Returns the field delimiter character.
String	getEmptyValue() Returns the String representation of an empty value (defaults to null)
String	getLineSeparatorString()
long	getMaxCharsPerColumn()
byte[]	getNewLineDelimiter()
byte	getNormalizedNewLine()
int	getNumberOfRecordsToRead() The number of valid records to be parsed before the process is stopped.
byte	getQuote() Returns the character used for escaping values where the field delimiter is part of the value.
byte	getQuoteEscape() Returns the character used for escaping quotes inside an already quoted value.
boolean	isDelimiter(byte ch) Identifies whether or not a given character represents a field delimiter
boolean	isHeaderExtractionEnabled() Indicates whether or not the first valid record parsed from the input should be considered as the row containing the names of each column
boolean	isIgnoreLeadingWhitespaces()
boolean	isIgnoreTrailingWhitespaces()
boolean	isParseUnescapedQuotes() Indicates whether the CSV parser should accept unescaped quotes inside quoted values and parse them normally.
boolean	isQuote(byte ch) Identifies whether or not a given character is used for escaping values where the field delimiter is part of the value
boolean	isQuoteEscape(byte ch) Identifies whether or not a given character is used for escaping quotes inside an already quoted value.
boolean	isSkipFirstLine()
boolean	isUseRepeatedVarChar()
void	set(TextFormatPlugin.TextFormatConfig config)
void	setComment(byte comment)
void	setDelimiter(byte delimiter) Defines the field delimiter character.
void	setEmptyValue(String emptyValue) Sets the String representation of an empty value (defaults to null)
void	setHeaderExtractionEnabled(boolean headerExtractionEnabled) Defines whether or not the first valid record parsed from the input should be considered as the row containing the names of each column
void	setIgnoreLeadingWhitespaces(boolean ignoreLeadingWhitespaces)
void	setIgnoreTrailingWhitespaces(boolean ignoreTrailingWhitespaces)
void	setMaxCharsPerColumn(long maxCharsPerColumn)
void	setNormalizedNewLine(byte normalizedNewLine)
void	setNumberOfRecordsToRead(int numberOfRecordsToRead) Defines the number of valid records to be parsed before the process is stopped.
void	setParseUnescapedQuotes(boolean parseUnescapedQuotes) Configures how to handle unescaped quotes inside quoted values.
void	setQuote(byte quote) Defines the character used for escaping values where the field delimiter is part of the value.
void	setQuoteEscape(byte quoteEscape) Defines the character used for escaping quotes inside an already quoted value.
void	setSkipFirstLine(boolean skipFirstLine)
void	setUseRepeatedVarChar(boolean useRepeatedVarChar)

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT

public static final TextParsingSettings DEFAULT

Constructor Detail

TextParsingSettings

public TextParsingSettings()

Method Detail

set

public void set(TextFormatPlugin.TextFormatConfig config)

getComment

public byte getComment()

isSkipFirstLine

public boolean isSkipFirstLine()

setSkipFirstLine

public void setSkipFirstLine(boolean skipFirstLine)

isUseRepeatedVarChar

public boolean isUseRepeatedVarChar()

setUseRepeatedVarChar

public void setUseRepeatedVarChar(boolean useRepeatedVarChar)

getNewLineDelimiter

public byte[] getNewLineDelimiter()

getQuote

public byte getQuote()

Returns the character used for escaping values where the field delimiter is part of the value. Defaults to '"'

Returns:

the quote character

setQuote

public void setQuote(byte quote)

Defines the character used for escaping values where the field delimiter is part of the value. Defaults to '"'

Parameters:

quote - the quote character

getLineSeparatorString

public String getLineSeparatorString()

isQuote

public boolean isQuote(byte ch)

Identifies whether or not a given character is used for escaping values where the field delimiter is part of the value

Parameters:

ch - the character to be verified

Returns:

true if the given character is the character used for escaping values, false otherwise

getQuoteEscape

public byte getQuoteEscape()

Returns the character used for escaping quotes inside an already quoted value. Defaults to '"'

Returns:

the quote escape character

setQuoteEscape

public void setQuoteEscape(byte quoteEscape)

Defines the character used for escaping quotes inside an already quoted value. Defaults to '"'

Parameters:

quoteEscape - the quote escape character

isQuoteEscape

public boolean isQuoteEscape(byte ch)

Identifies whether or not a given character is used for escaping quotes inside an already quoted value.

Parameters:

ch - the character to be verified

Returns:

true if the given character is the quote escape character, false otherwise

getDelimiter

public byte getDelimiter()

Returns the field delimiter character. Defaults to ','

Returns:

the field delimiter character

setDelimiter

public void setDelimiter(byte delimiter)

Defines the field delimiter character. Defaults to ','

Parameters:

delimiter - the field delimiter character

isDelimiter

public boolean isDelimiter(byte ch)

Identifies whether or not a given character represents a field delimiter

Parameters:

ch - the character to be verified

Returns:

true if the given character is the field delimiter character, false otherwise

getEmptyValue

public String getEmptyValue()

Returns the String representation of an empty value (defaults to null)

When reading, if the parser does not read any character from the input, and the input is within quotes, the empty is used instead of an empty string

Returns:

the String representation of an empty value

setEmptyValue

public void setEmptyValue(String emptyValue)

Sets the String representation of an empty value (defaults to null)

When reading, if the parser does not read any character from the input, and the input is within quotes, the empty is used instead of an empty string

Parameters:

emptyValue - the String representation of an empty value

isParseUnescapedQuotes

public boolean isParseUnescapedQuotes()

Indicates whether the CSV parser should accept unescaped quotes inside quoted values and parse them normally. Defaults to true.

Returns:

a flag indicating whether or not the CSV parser should accept unescaped quotes inside quoted values.

setParseUnescapedQuotes

public void setParseUnescapedQuotes(boolean parseUnescapedQuotes)

Configures how to handle unescaped quotes inside quoted values. If set to true, the parser will parse the quote normally as part of the value. If set the false, a TextParsingException will be thrown. Defaults to true.

Parameters:

parseUnescapedQuotes - indicates whether or not the CSV parser should accept unescaped quotes inside quoted values.

isHeaderExtractionEnabled

public boolean isHeaderExtractionEnabled()

Indicates whether or not the first valid record parsed from the input should be considered as the row containing the names of each column

Returns:

true if the first valid record parsed from the input should be considered as the row containing the names of each column, false otherwise

setHeaderExtractionEnabled

public void setHeaderExtractionEnabled(boolean headerExtractionEnabled)

Defines whether or not the first valid record parsed from the input should be considered as the row containing the names of each column

Parameters:

headerExtractionEnabled - a flag indicating whether the first valid record parsed from the input should be considered as the row containing the names of each column

getNumberOfRecordsToRead

public int getNumberOfRecordsToRead()

The number of valid records to be parsed before the process is stopped. A negative value indicates there's no limit (defaults to -1).

Returns:

the number of records to read before stopping the parsing process.

setNumberOfRecordsToRead

public void setNumberOfRecordsToRead(int numberOfRecordsToRead)

Defines the number of valid records to be parsed before the process is stopped. A negative value indicates there's no limit (defaults to -1).

Parameters:

numberOfRecordsToRead - the number of records to read before stopping the parsing process.

getMaxCharsPerColumn

public long getMaxCharsPerColumn()

setMaxCharsPerColumn

public void setMaxCharsPerColumn(long maxCharsPerColumn)

setComment

public void setComment(byte comment)

getNormalizedNewLine

public byte getNormalizedNewLine()

setNormalizedNewLine

public void setNormalizedNewLine(byte normalizedNewLine)

isIgnoreLeadingWhitespaces

public boolean isIgnoreLeadingWhitespaces()

setIgnoreLeadingWhitespaces

public void setIgnoreLeadingWhitespaces(boolean ignoreLeadingWhitespaces)

isIgnoreTrailingWhitespaces

public boolean isIgnoreTrailingWhitespaces()

setIgnoreTrailingWhitespaces

public void setIgnoreTrailingWhitespaces(boolean ignoreTrailingWhitespaces)