grammarscope.server.corenlp

Class Pipeline

java.lang.Object

grammarscope.server.corenlp.Pipeline

public class Pipeline
extends java.lang.Object

Pipeline

Author:

Bernard Bou

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
(package private) static interface	Pipeline.IProcessor<T> Processor interface

Field Summary

Fields

Modifier and Type	Field and Description
(package private) static java.lang.String	PIPELINE_ANNOTATORS
(package private) static java.lang.String	PIPELINE_DEPPARSER_MODEL
(package private) static java.lang.String	PIPELINE_DEPPARSER_OPTIONS
(package private) static java.lang.String	PIPELINE_LANGUAGE
(package private) static java.lang.String	PIPELINE_PARSER_MODEL
(package private) static java.lang.String	PIPELINE_PARSER_OPTIONS
(package private) static java.lang.String	PIPELINE_POSTAGGER_MODEL
(package private) static java.lang.String	PIPELINE_TOKENIZE_LANGUAGE
protected java.util.Properties	properties Properties (raw)
protected edu.stanford.nlp.pipeline.StanfordCoreNLP	stanfordPipeline Stanford Pipeline

Constructor Summary

Constructors

Constructor and Description
Pipeline() Default constructor
Pipeline(java.util.Properties properties0) Constructor

Method Summary

Modifier and Type	Method and Description
private static <T> java.util.List<T>	getAnnotations(edu.stanford.nlp.util.CoreMap map, java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.ling.CoreLabel>>> class1, java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<T>> class2) Get annotations
static java.util.List<BreadthAnalysis>	getBreadthAnalyses(edu.stanford.nlp.pipeline.Annotation document) Analysis
static long	getCapabilities() Capabilities
static java.util.List<java.util.List<java.lang.Integer>>	getCharBegins(edu.stanford.nlp.pipeline.Annotation document) Get character offset begins
static java.util.List<java.util.List<java.lang.Integer>>	getCharEnds(edu.stanford.nlp.pipeline.Annotation document) Get character offset ends
java.lang.String	getConstituencyParseModel()
static java.util.List<java.util.List<java.lang.Integer>>	getCoreferenceIndices(edu.stanford.nlp.pipeline.Annotation document) Get coreference cluster indices
static java.util.Map<java.lang.Integer,edu.stanford.nlp.coref.data.CorefChain>	getCoreferences(edu.stanford.nlp.pipeline.Annotation document) Get coreferences.
java.lang.String	getDependencyParseModel()
static java.util.List<DepthAnalysis>	getDepthAnalyses(edu.stanford.nlp.pipeline.Annotation document) Analysis
java.lang.String	getGrammaticalRelationModel()
static java.util.List<java.util.List<java.lang.String>>	getNamedEntities(edu.stanford.nlp.pipeline.Annotation document) Get named entities
static java.util.List<edu.stanford.nlp.trees.Tree>	getParseTrees(edu.stanford.nlp.pipeline.Annotation document) Parse
java.util.Properties	getPipelineProperties() Get pipeline properties
static java.util.List<java.util.List<java.lang.String>>	getPoses(edu.stanford.nlp.pipeline.Annotation document) Get parts-of-speech
java.lang.String	getPosTaggerModel()
static java.util.List<edu.stanford.nlp.semgraph.SemanticGraph>	getSemanticGraphs(edu.stanford.nlp.pipeline.Annotation document, TypedDependencyMode mode) Semantic graphs
static TextBreadthAnalysis	getTextBreadthAnalysis(edu.stanford.nlp.pipeline.Annotation document) Text Analysis
static TextDepthAnalysis	getTextDepthAnalysis(edu.stanford.nlp.pipeline.Annotation document) Text Analysis
private static <T> java.util.List<java.util.List<T>>	getTokenAnnotations(edu.stanford.nlp.util.CoreMap map, java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<T>> clazz) Get token annotations
java.lang.String	getTokenizeModel()
static java.util.List<java.util.Collection<edu.stanford.nlp.trees.TypedDependency>>	getTypedDependencies(edu.stanford.nlp.pipeline.Annotation document, TypedDependencyMode mode) Typed Dependencies
static java.util.List<java.util.List<java.lang.String>>	getWords(edu.stanford.nlp.pipeline.Annotation document) Get words
boolean	isValid() Whether pipeline is valid
static void	main(java.lang.String[] args) Main
static java.util.Properties	makeDefaultProperties() Make default pipeline properties
private static java.util.List<NamedEntity>	makeNamedEntities(edu.stanford.nlp.util.CoreMap map) Make named entities
static java.util.Properties	makePipelineProperties(java.util.Properties properties0) Make pipeline properties
static java.lang.String	makeText(java.util.List<java.lang.String> tokens, java.util.List<WordSegment> wordSegments) Make text from tokens and segments
(package private) static void	makeText(java.lang.String substring, Segment segment, int from0, java.lang.StringBuffer sb) Make text from string, its start and segment
(package private) static void	makeText(java.lang.String substring, Segment segment, java.lang.StringBuffer sb) Make text from string and its segment
private static java.util.List<WordSegment>	makeWordSegments(java.util.List<java.lang.Integer> begins, java.util.List<java.lang.Integer> ends) Make word segments from positions
void	print(edu.stanford.nlp.pipeline.Annotation document, java.io.PrintWriter out, boolean xMLFlag) Print document
edu.stanford.nlp.pipeline.Annotation	process(java.lang.String text) Pipeline-process text
edu.stanford.nlp.pipeline.Annotation	processFile(java.lang.String file) Pipeline-process file (path)
private static <T> java.util.List<T>	processLabels(edu.stanford.nlp.util.CoreMap map, java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.ling.CoreLabel>>> elementAnnotationClass, Pipeline.IProcessor<T> processor) Process this annotation map
private static <T> java.util.List<T>	processMaps(edu.stanford.nlp.util.CoreMap map, java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.util.CoreMap>>> elementAnnotationClass, Pipeline.IProcessor<T> processor) Process this annotation map
private static <T> java.util.List<java.util.List<T>>	processSub(edu.stanford.nlp.util.CoreMap map, java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.util.CoreMap>>> elementAnnotationClass, java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.ling.CoreLabel>>> subElementAnnotationClass, Pipeline.IProcessor<T> processor) Process this annotation map
edu.stanford.nlp.pipeline.Annotation	processURL(java.net.URL url) Pipeline-process file (url)
void	reset() Reset
private static java.lang.Class<? extends SemanticGraphAnnotator.SemanticGraphAnnotation>	semanticGraphModeToAnnotation2Class(TypedDependencyMode mode) Semantic graph mode to Annotation class
private static java.lang.Class<? extends SemanticGraphAnnotator.SemanticGraphAnnotation>	semanticGraphModeToAnnotationClass(TypedDependencyMode mode) Semantic graph mode to Annotation class
java.lang.String	toString(edu.stanford.nlp.pipeline.Annotation document) Document to string
java.lang.String	toString(edu.stanford.nlp.pipeline.Annotation document, boolean xMLFlag) Document to string
java.lang.String	toXMLString(edu.stanford.nlp.pipeline.Annotation document) Document to XML string
private static java.lang.Class<? extends TypedDependenciesAnnotator.TypedDependenciesAnnotation>	typedDependencyModeToAnnotation2Class(TypedDependencyMode mode)
private static java.lang.Class<? extends TypedDependenciesAnnotator.TypedDependenciesAnnotation>	typedDependencyModeToAnnotationClass(TypedDependencyMode mode) Typed dependencies mode to Annotation class

Methods inherited from class java.lang.Object

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

Field Detail

PIPELINE_ANNOTATORS

static final java.lang.String PIPELINE_ANNOTATORS

See Also:

Constant Field Values

PIPELINE_TOKENIZE_LANGUAGE

static final java.lang.String PIPELINE_TOKENIZE_LANGUAGE

See Also:

Constant Field Values

PIPELINE_POSTAGGER_MODEL

static final java.lang.String PIPELINE_POSTAGGER_MODEL

See Also:

Constant Field Values

PIPELINE_PARSER_MODEL

static final java.lang.String PIPELINE_PARSER_MODEL

See Also:

Constant Field Values

PIPELINE_PARSER_OPTIONS

static final java.lang.String PIPELINE_PARSER_OPTIONS

See Also:

Constant Field Values

PIPELINE_DEPPARSER_MODEL

static final java.lang.String PIPELINE_DEPPARSER_MODEL

See Also:

Constant Field Values

PIPELINE_DEPPARSER_OPTIONS

static final java.lang.String PIPELINE_DEPPARSER_OPTIONS

See Also:

Constant Field Values

PIPELINE_LANGUAGE

static final java.lang.String PIPELINE_LANGUAGE

See Also:

Constant Field Values

stanfordPipeline

protected edu.stanford.nlp.pipeline.StanfordCoreNLP stanfordPipeline

Stanford Pipeline

properties

protected final java.util.Properties properties

Properties (raw)

Constructor Detail

Pipeline

public Pipeline()

Default constructor

Pipeline

public Pipeline(java.util.Properties properties0)

Constructor

Parameters:

properties0 - pipeline properties

Method Detail

isValid

public boolean isValid()

Whether pipeline is valid

Returns:

whether pipeline is valid

getPipelineProperties

public java.util.Properties getPipelineProperties()

Get pipeline properties

Returns:

pipeline properties

reset

public void reset()

Reset

makePipelineProperties

public static java.util.Properties makePipelineProperties(java.util.Properties properties0)

Make pipeline properties

Parameters:

properties0 - properties to read values from

Returns:

pipeline properties

makeDefaultProperties

public static java.util.Properties makeDefaultProperties()

Make default pipeline properties

Returns:

default pipeline properties

toString

public java.lang.String toString(edu.stanford.nlp.pipeline.Annotation document)
                          throws java.io.IOException

Document to string

Parameters:

document - document

Returns:

string

Throws:

java.io.IOException - exception

toXMLString

public java.lang.String toXMLString(edu.stanford.nlp.pipeline.Annotation document)
                             throws java.io.IOException

Document to XML string

Parameters:

document - document

Returns:

string in XML format

Throws:

java.io.IOException - exception

toString

public java.lang.String toString(edu.stanford.nlp.pipeline.Annotation document,
                                 boolean xMLFlag)
                          throws java.io.IOException

Document to string

Parameters:

document - document

xMLFlag - whether output is in XML format

Returns:

document string

Throws:

java.io.IOException - exception

print

public void print(edu.stanford.nlp.pipeline.Annotation document,
                  java.io.PrintWriter out,
                  boolean xMLFlag)
           throws java.io.IOException

Print document

Parameters:

document - document

out - print writer

xMLFlag - whether to output in XML format

Throws:

java.io.IOException - exception

processFile

public edu.stanford.nlp.pipeline.Annotation processFile(java.lang.String file)

Pipeline-process file (path)

Parameters:

file - input file path

Returns:

document

processURL

public edu.stanford.nlp.pipeline.Annotation processURL(java.net.URL url)

Pipeline-process file (url)

Parameters:

url - url

Returns:

document

process

public edu.stanford.nlp.pipeline.Annotation process(java.lang.String text)

Pipeline-process text

Parameters:

text - text

Returns:

document

processMaps

private static <T> java.util.List<T> processMaps(edu.stanford.nlp.util.CoreMap map,
                                                 java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.util.CoreMap>>> elementAnnotationClass,
                                                 Pipeline.IProcessor<T> processor)

Process this annotation map

Type Parameters:

T - type of returned list element

Parameters:

map - annotation map

elementAnnotationClass - element selector class

processor - processor

Returns:

list of processed elements

processLabels

private static <T> java.util.List<T> processLabels(edu.stanford.nlp.util.CoreMap map,
                                                   java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.ling.CoreLabel>>> elementAnnotationClass,
                                                   Pipeline.IProcessor<T> processor)

Process this annotation map

Type Parameters:

T - type of returned list element

Parameters:

map - annotation map

elementAnnotationClass - element selector class

processor - processor

Returns:

list of processed elements

processSub

private static <T> java.util.List<java.util.List<T>> processSub(edu.stanford.nlp.util.CoreMap map,
                                                                java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.util.CoreMap>>> elementAnnotationClass,
                                                                java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.ling.CoreLabel>>> subElementAnnotationClass,
                                                                Pipeline.IProcessor<T> processor)

Process this annotation map

Type Parameters:

T - type of returned list element

Parameters:

map - annotation map

elementAnnotationClass - element selector class

subElementAnnotationClass - subelement selector class

processor - processor

Returns:

list of list processed sub elements

getAnnotations

private static <T> java.util.List<T> getAnnotations(edu.stanford.nlp.util.CoreMap map,
                                                    java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<java.util.List<edu.stanford.nlp.ling.CoreLabel>>> class1,
                                                    java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<T>> class2)

Get annotations

Type Parameters:

T - type of returned list element

Parameters:

map - annotation map

class1 - selector class at first level

class2 - selector class at second level

Returns:

list of annotation values

getTokenAnnotations

private static <T> java.util.List<java.util.List<T>> getTokenAnnotations(edu.stanford.nlp.util.CoreMap map,
                                                                         java.lang.Class<? extends edu.stanford.nlp.ling.CoreAnnotation<T>> clazz)

Get token annotations

Type Parameters:

T - type of returned list element

Parameters:

map - annotation map (document level)

clazz - selector class at Token level

Returns:

list of list of annotation values

typedDependencyModeToAnnotationClass

private static java.lang.Class<? extends TypedDependenciesAnnotator.TypedDependenciesAnnotation> typedDependencyModeToAnnotationClass(TypedDependencyMode mode)

Typed dependencies mode to Annotation class

Parameters:

mode - typed dependency mode

Returns:

matching annotation class

typedDependencyModeToAnnotation2Class

private static java.lang.Class<? extends TypedDependenciesAnnotator.TypedDependenciesAnnotation> typedDependencyModeToAnnotation2Class(TypedDependencyMode mode)

semanticGraphModeToAnnotationClass

private static java.lang.Class<? extends SemanticGraphAnnotator.SemanticGraphAnnotation> semanticGraphModeToAnnotationClass(TypedDependencyMode mode)

Semantic graph mode to Annotation class

Parameters:

mode - typed dependency mode

Returns:

matching annotation class

semanticGraphModeToAnnotation2Class

private static java.lang.Class<? extends SemanticGraphAnnotator.SemanticGraphAnnotation> semanticGraphModeToAnnotation2Class(TypedDependencyMode mode)

Semantic graph mode to Annotation class

Parameters:

mode - typed dependency mode

Returns:

matching annotation class

makeText

public static java.lang.String makeText(java.util.List<java.lang.String> tokens,
                                        java.util.List<WordSegment> wordSegments)

Make text from tokens and segments

Parameters:

tokens - tokens

wordSegments - word segments

Returns:

text

makeText

static void makeText(java.lang.String substring,
                     Segment segment,
                     int from0,
                     java.lang.StringBuffer sb)

Make text from string, its start and segment

Parameters:

substring - text fragment

segment - fragment's segment

from0 - fragment's start

sb - string sb

makeText

static void makeText(java.lang.String substring,
                     Segment segment,
                     java.lang.StringBuffer sb)

Make text from string and its segment

Parameters:

substring - substring

segment - its segment

sb - string sb

makeWordSegments

private static java.util.List<WordSegment> makeWordSegments(java.util.List<java.lang.Integer> begins,
                                                            java.util.List<java.lang.Integer> ends)

Make word segments from positions

Parameters:

begins - segment begins

ends - segment ends

Returns:

word segments

makeNamedEntities

private static java.util.List<NamedEntity> makeNamedEntities(edu.stanford.nlp.util.CoreMap map)

Make named entities

Parameters:

map - sentence annotation map

Returns:

named entities

getTextBreadthAnalysis

public static TextBreadthAnalysis getTextBreadthAnalysis(edu.stanford.nlp.pipeline.Annotation document)

Text Analysis

Parameters:

document - document

Returns:

text breadth analysis

getTextDepthAnalysis

public static TextDepthAnalysis getTextDepthAnalysis(edu.stanford.nlp.pipeline.Annotation document)

Text Analysis

Parameters:

document - document

Returns:

text depth analysis

getBreadthAnalyses

public static java.util.List<BreadthAnalysis> getBreadthAnalyses(edu.stanford.nlp.pipeline.Annotation document)

Analysis

Parameters:

document - document

Returns:

list of breadth analyses

getDepthAnalyses

public static java.util.List<DepthAnalysis> getDepthAnalyses(edu.stanford.nlp.pipeline.Annotation document)

Analysis

Parameters:

document - document

Returns:

list of depth analyses

getParseTrees

public static java.util.List<edu.stanford.nlp.trees.Tree> getParseTrees(edu.stanford.nlp.pipeline.Annotation document)

Parse

Parameters:

document - document

Returns:

list of parse trees

getTypedDependencies

public static java.util.List<java.util.Collection<edu.stanford.nlp.trees.TypedDependency>> getTypedDependencies(edu.stanford.nlp.pipeline.Annotation document,
                                                                                                                TypedDependencyMode mode)

Typed Dependencies

Parameters:

document - document

mode - typed dependency mode

Returns:

list of typed dependencies

getSemanticGraphs

public static java.util.List<edu.stanford.nlp.semgraph.SemanticGraph> getSemanticGraphs(edu.stanford.nlp.pipeline.Annotation document,
                                                                                        TypedDependencyMode mode)

Semantic graphs

Parameters:

document - document

mode - typed dependency mode

Returns:

list of semantic graphs

getWords

public static java.util.List<java.util.List<java.lang.String>> getWords(edu.stanford.nlp.pipeline.Annotation document)

Get words

Parameters:

document - document

Returns:

list of list of words

getPoses

public static java.util.List<java.util.List<java.lang.String>> getPoses(edu.stanford.nlp.pipeline.Annotation document)

Get parts-of-speech

Parameters:

document - document

Returns:

list of list of parts-of-speech

getNamedEntities

public static java.util.List<java.util.List<java.lang.String>> getNamedEntities(edu.stanford.nlp.pipeline.Annotation document)

Get named entities

Parameters:

document - document

Returns:

list of list of named entities

getCoreferenceIndices

public static java.util.List<java.util.List<java.lang.Integer>> getCoreferenceIndices(edu.stanford.nlp.pipeline.Annotation document)

Get coreference cluster indices

Parameters:

document - document

Returns:

list of list of coreference cluster indices

getCharBegins

public static java.util.List<java.util.List<java.lang.Integer>> getCharBegins(edu.stanford.nlp.pipeline.Annotation document)

Get character offset begins

Parameters:

document - document

Returns:

list of list of character offset begins

getCharEnds

public static java.util.List<java.util.List<java.lang.Integer>> getCharEnds(edu.stanford.nlp.pipeline.Annotation document)

Get character offset ends

Parameters:

document - document

Returns:

list of list of character offset begins

getCoreferences

public static java.util.Map<java.lang.Integer,edu.stanford.nlp.coref.data.CorefChain> getCoreferences(edu.stanford.nlp.pipeline.Annotation document)

Get coreferences. This is the coreference link graph. Each chain stores a set of mentions that link to each other, along with a method for getting the most representative mention. Both sentence and token offsets start at 1!

Parameters:

document - document

Returns:

indexed coreference chains

getCapabilities

public static long getCapabilities()

Capabilities

Returns:

capabilities

getTokenizeModel

public java.lang.String getTokenizeModel()

getPosTaggerModel

public java.lang.String getPosTaggerModel()

getConstituencyParseModel

public java.lang.String getConstituencyParseModel()

getDependencyParseModel

public java.lang.String getDependencyParseModel()

getGrammaticalRelationModel

public java.lang.String getGrammaticalRelationModel()

main

public static void main(java.lang.String[] args)
                 throws java.io.IOException

Main

Parameters:

args - arguments

Throws:

java.io.IOException - exception