org.apache.nifi.processors.standard

Class ValidateCsv

java.lang.Object

org.apache.nifi.components.AbstractConfigurableComponent

org.apache.nifi.processor.AbstractSessionFactoryProcessor

org.apache.nifi.processor.AbstractProcessor

org.apache.nifi.processors.standard.ValidateCsv

All Implemented Interfaces:

ConfigurableComponent, Processor

@EventDriven
 @SideEffectFree
 @SupportsBatching
 @InputRequirement(value=INPUT_REQUIRED)
 @Tags(value={"csv","schema","validation"})
 @CapabilityDescription(value="Validates the contents of FlowFiles against a user-specified CSV schema. Take a look at the additional documentation of this processor for some schema examples.")
 @WritesAttribute(attribute="count.valid.lines",description="If line by line validation, number of valid lines extracted from the source data") @WritesAttribute(attribute="count.invalid.lines",description="If line by line validation, number of invalid lines extracted from the source data") @WritesAttribute(attribute="count.total.lines",description="If line by line validation, total number of lines in the source data") @WritesAttribute(attribute="validation.error.message",description="For flow files routed to invalid, message of the first validation error")
public class ValidateCsv
extends AbstractProcessor

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
private class	ValidateCsv.NifiCsvListReader This is required to avoid the side effect of Parse* cell processors.

Field Summary

Fields

Modifier and Type	Field and Description
private static List<String>	allowedOperators
static PropertyDescriptor	DELIMITER_CHARACTER
static PropertyDescriptor	END_OF_LINE_CHARACTER
static PropertyDescriptor	HEADER
private List<PropertyDescriptor>	properties
static PropertyDescriptor	QUOTE_CHARACTER
static Relationship	REL_INVALID
static Relationship	REL_VALID
private Set<Relationship>	relationships
private static String	routeLinesIndividually
private static String	routeWholeFlowFile
static PropertyDescriptor	SCHEMA
static AllowableValue	VALIDATE_LINES_INDIVIDUALLY
static AllowableValue	VALIDATE_WHOLE_FLOWFILE
static PropertyDescriptor	VALIDATION_STRATEGY

Constructor Summary

Constructors

Constructor and Description
ValidateCsv()

Method Summary

Modifier and Type	Method and Description
protected Collection<ValidationResult>	customValidate(ValidationContext context)
org.supercsv.prefs.CsvPreference	getPreference(ProcessContext context, FlowFile flowFile)
private org.supercsv.cellprocessor.ift.CellProcessor	getProcessor(String method, String argument)
Set<Relationship>	getRelationships()
protected List<PropertyDescriptor>	getSupportedPropertyDescriptors()
protected void	init(ProcessorInitializationContext context)
void	onTrigger(ProcessContext context, ProcessSession session)
private org.supercsv.cellprocessor.ift.CellProcessor[]	parseSchema(String schema) Method used to parse the string supplied by the user.
private byte[]	print(String row, org.supercsv.prefs.CsvPreference csvPref, boolean isFirstLine)
private String	setProcessor(String remaining, List<org.supercsv.cellprocessor.ift.CellProcessor> processorsList)

Methods inherited from class org.apache.nifi.processor.AbstractProcessor

onTrigger

Methods inherited from class org.apache.nifi.processor.AbstractSessionFactoryProcessor

getControllerServiceLookup, getIdentifier, getLogger, getNodeTypeProvider, initialize, isConfigurationRestored, isScheduled, toString, updateConfiguredRestoredTrue, updateScheduledFalse, updateScheduledTrue

Methods inherited from class org.apache.nifi.components.AbstractConfigurableComponent

equals, getPropertyDescriptor, getPropertyDescriptors, getSupportedDynamicPropertyDescriptor, hashCode, onPropertyModified, validate

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.nifi.processor.Processor

isStateful

Methods inherited from interface org.apache.nifi.components.ConfigurableComponent

getPropertyDescriptor, getPropertyDescriptors, onPropertyModified, validate

Field Detail

allowedOperators

private static final List<String> allowedOperators

routeWholeFlowFile

private static final String routeWholeFlowFile

See Also:

Constant Field Values

routeLinesIndividually

private static final String routeLinesIndividually

See Also:

Constant Field Values

VALIDATE_WHOLE_FLOWFILE

public static final AllowableValue VALIDATE_WHOLE_FLOWFILE

VALIDATE_LINES_INDIVIDUALLY

public static final AllowableValue VALIDATE_LINES_INDIVIDUALLY

SCHEMA

public static final PropertyDescriptor SCHEMA

HEADER

public static final PropertyDescriptor HEADER

QUOTE_CHARACTER

public static final PropertyDescriptor QUOTE_CHARACTER

DELIMITER_CHARACTER

public static final PropertyDescriptor DELIMITER_CHARACTER

END_OF_LINE_CHARACTER

public static final PropertyDescriptor END_OF_LINE_CHARACTER

VALIDATION_STRATEGY

public static final PropertyDescriptor VALIDATION_STRATEGY

REL_VALID

public static final Relationship REL_VALID

REL_INVALID

public static final Relationship REL_INVALID

properties

private List<PropertyDescriptor> properties

relationships

private Set<Relationship> relationships

Constructor Detail

ValidateCsv

public ValidateCsv()

Method Detail

init

protected void init(ProcessorInitializationContext context)

Overrides:

init in class AbstractSessionFactoryProcessor

getRelationships

public Set<Relationship> getRelationships()

Specified by:

getRelationships in interface Processor

Overrides:

getRelationships in class AbstractSessionFactoryProcessor

getSupportedPropertyDescriptors

protected List<PropertyDescriptor> getSupportedPropertyDescriptors()

Overrides:

getSupportedPropertyDescriptors in class AbstractConfigurableComponent

customValidate

protected Collection<ValidationResult> customValidate(ValidationContext context)

Overrides:

customValidate in class AbstractConfigurableComponent

getPreference

public org.supercsv.prefs.CsvPreference getPreference(ProcessContext context,
                                                      FlowFile flowFile)

parseSchema

private org.supercsv.cellprocessor.ift.CellProcessor[] parseSchema(String schema)

Method used to parse the string supplied by the user. The string is converted to a list of cell processors used to validate the CSV data.

Parameters:

schema - Schema to parse

setProcessor

private String setProcessor(String remaining,
                            List<org.supercsv.cellprocessor.ift.CellProcessor> processorsList)

getProcessor

private org.supercsv.cellprocessor.ift.CellProcessor getProcessor(String method,
                                                                  String argument)

onTrigger

public void onTrigger(ProcessContext context,
                      ProcessSession session)

Specified by:

onTrigger in class AbstractProcessor

print

private byte[] print(String row,
                     org.supercsv.prefs.CsvPreference csvPref,
                     boolean isFirstLine)