org.apache.nifi.processors.standard

Class ExtractText

java.lang.Object

org.apache.nifi.components.AbstractConfigurableComponent

org.apache.nifi.processor.AbstractSessionFactoryProcessor

org.apache.nifi.processor.AbstractProcessor

org.apache.nifi.processors.standard.ExtractText

All Implemented Interfaces:

ConfigurableComponent, Processor

@EventDriven
 @SideEffectFree
 @SupportsBatching
 @InputRequirement(value=INPUT_REQUIRED)
 @Tags(value={"evaluate","extract","Text","Regular Expression","regex"})
 @CapabilityDescription(value="Evaluates one or more Regular Expressions against the content of a FlowFile.  The results of those Regular Expressions are assigned to FlowFile Attributes.  Regular Expressions are entered by adding user-defined properties; the name of the property maps to the Attribute Name into which the result will be placed.  The attributes are generated differently based on the enabling of named capture groups.  If named capture groups are not enabled:  The first capture group, if any found, will be placed into that attribute name.But all capture groups, including the matching string sequence itself will also be provided at that attribute name with an index value provided, with the exception of a capturing group that is optional and does not match - for example, given the attribute name \"regex\" and expression \"abc(def)?(g)\" we would add an attribute \"regex.1\" with a value of \"def\" if the \"def\" matched. If the \"def\" did not match, no attribute named \"regex.1\" would be added but an attribute named \"regex.2\" with a value of \"g\" will be added regardless.If named capture groups are enabled:  Each named capture group, if found will be placed into the attributes name with the name provided.  If enabled the matching string sequence itself will be placed into the attribute name.  If multiple matches are enabled, and index will be applied after the first set of matches. The exception is a capturing group that is optional and does not match  For example, given the attribute name \"regex\" and expression \"abc(?<NAMED>def)?(?<NAMED-TWO>g)\"  we would add an attribute \"regex.NAMED\" with the value of \"def\" if the \"def\" matched.  We would   add an attribute \"regex.NAMED-TWO\" with the value of \"g\" if the \"g\" matched regardless.  The value of the property must be a valid Regular Expressions with one or more capturing groups. If named capture groups are enabled, all capture groups must be named.  If they are not, then the  processor configuration will fail validation.  If the Regular Expression matches more than once, only the first match will be used unless the property enabling repeating capture group is set to true. If any provided Regular Expression matches, the FlowFile(s) will be routed to \'matched\'. If no provided Regular Expression matches, the FlowFile will be routed to \'unmatched\' and no attributes will be applied to the FlowFile.")
 @DynamicProperty(name="A FlowFile attribute",
                 value="A Regular Expression with one or more capturing group",
                 description="The first capture group, if any found, will be placed into that attribute name.But all capture groups, including the matching string sequence itself will also be provided at that attribute name with an index value provided.")
public class ExtractText
extends AbstractProcessor

Field Summary

Fields

Modifier and Type	Field and Description
private BlockingQueue<byte[]>	bufferQueue
static PropertyDescriptor	CANON_EQ
static PropertyDescriptor	CASE_INSENSITIVE
static PropertyDescriptor	CHARACTER_SET
static PropertyDescriptor	COMMENTS
private AtomicReference<Map<String,Pattern>>	compiledPattersMapRef
static PropertyDescriptor	DOTALL
static PropertyDescriptor	ENABLE_NAMED_GROUPS
static PropertyDescriptor	ENABLE_REPEATING_CAPTURE_GROUP
static PropertyDescriptor	INCLUDE_CAPTURE_GROUP_ZERO
static PropertyDescriptor	LITERAL
static PropertyDescriptor	MAX_BUFFER_SIZE
static PropertyDescriptor	MAX_CAPTURE_GROUP_LENGTH
static PropertyDescriptor	MULTILINE
private List<PropertyDescriptor>	properties
static Relationship	REL_MATCH
static Relationship	REL_NO_MATCH
private Set<Relationship>	relationships
static PropertyDescriptor	UNICODE_CASE
static PropertyDescriptor	UNICODE_CHARACTER_CLASS
static PropertyDescriptor	UNIX_LINES

Constructor Summary

Constructors

Constructor and Description
ExtractText()

Method Summary

Modifier and Type	Method and Description
protected Collection<ValidationResult>	customValidate(ValidationContext validationContext)
(package private) int	getCompileFlags(ProcessContext context)
Set<Relationship>	getRelationships()
protected PropertyDescriptor	getSupportedDynamicPropertyDescriptor(String propertyDescriptorName)
protected List<PropertyDescriptor>	getSupportedPropertyDescriptors()
protected void	init(ProcessorInitializationContext context)
void	onScheduled(ProcessContext context)
void	onStopped()
void	onTrigger(ProcessContext context, ProcessSession session)

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, 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

CHARACTER_SET

public static final PropertyDescriptor CHARACTER_SET

MAX_BUFFER_SIZE

public static final PropertyDescriptor MAX_BUFFER_SIZE

MAX_CAPTURE_GROUP_LENGTH

public static final PropertyDescriptor MAX_CAPTURE_GROUP_LENGTH

CANON_EQ

public static final PropertyDescriptor CANON_EQ

CASE_INSENSITIVE

public static final PropertyDescriptor CASE_INSENSITIVE

COMMENTS

public static final PropertyDescriptor COMMENTS

DOTALL

public static final PropertyDescriptor DOTALL

LITERAL

public static final PropertyDescriptor LITERAL

MULTILINE

public static final PropertyDescriptor MULTILINE

UNICODE_CASE

public static final PropertyDescriptor UNICODE_CASE

UNICODE_CHARACTER_CLASS

public static final PropertyDescriptor UNICODE_CHARACTER_CLASS

UNIX_LINES

public static final PropertyDescriptor UNIX_LINES

INCLUDE_CAPTURE_GROUP_ZERO

public static final PropertyDescriptor INCLUDE_CAPTURE_GROUP_ZERO

ENABLE_REPEATING_CAPTURE_GROUP

public static final PropertyDescriptor ENABLE_REPEATING_CAPTURE_GROUP

ENABLE_NAMED_GROUPS

public static final PropertyDescriptor ENABLE_NAMED_GROUPS

REL_MATCH

public static final Relationship REL_MATCH

REL_NO_MATCH

public static final Relationship REL_NO_MATCH

relationships

private Set<Relationship> relationships

properties

private List<PropertyDescriptor> properties

bufferQueue

private final BlockingQueue<byte[]> bufferQueue

compiledPattersMapRef

private final AtomicReference<Map<String,Pattern>> compiledPattersMapRef

Constructor Detail

ExtractText

public ExtractText()

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

getSupportedDynamicPropertyDescriptor

protected PropertyDescriptor getSupportedDynamicPropertyDescriptor(String propertyDescriptorName)

Overrides:

getSupportedDynamicPropertyDescriptor in class AbstractConfigurableComponent

customValidate

protected Collection<ValidationResult> customValidate(ValidationContext validationContext)

Overrides:

customValidate in class AbstractConfigurableComponent

onScheduled

@OnScheduled
public final void onScheduled(ProcessContext context)
                                    throws IOException

Throws:

IOException

onStopped

@OnStopped
public void onStopped()

onTrigger

public void onTrigger(ProcessContext context,
                      ProcessSession session)

Specified by:

onTrigger in class AbstractProcessor

getCompileFlags

int getCompileFlags(ProcessContext context)