org.carrot2.text.preprocessing.TokenizerDescriptor Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of carrot2-core Show documentation
Carrot2 search results clustering framework core, document sources and clustering algorithms.
There is a newer version: 4.6.0


// APT-generated file.

package org.carrot2.text.preprocessing;

//Imported for JavaDoc references mostly.
import org.carrot2.util.attribute.*;

import java.util.*;
import javax.annotation.*;

/**
 * Metadata and attributes of the {@link org.carrot2.text.preprocessing.Tokenizer} component. You can use 
 * this descriptor to obtain metadata, such as human readable name and description, about the component 
 * as a whole as well as about its attributes. Using the {@link #attributeBuilder(Map)}
 * you can obtain a builder for type-safe generation of the attribute maps. Please see the
 * main overview for a complete code example. 
 */
@Generated("Generated from org.carrot2.text.preprocessing.Tokenizer")
public final class TokenizerDescriptor implements IBindableDescriptor
{
    /**
     * The component class for which this descriptor was generated. 
     */
    public final String bindableClassName = "org.carrot2.text.preprocessing.Tokenizer";

    /**
     * Attribute prefix used by the component.
     */
    public final String prefix = "Tokenizer";

    /**
     * A one sentence summary of the component. It could be presented as a header of the tool
     * tip of the corresponding UI component.
     */
    public final String title = "Performs tokenization of documents";
    
    /**
     * A short label for the component. It can be presented as a label of the
     * corresponding UI component.
     */
    public final String label = "";

    /**
     * A longer, possibly multi sentence, description of the component. It could be presented
     * as a body of the tool tip of the corresponding UI component.
     */
    public final String description = " This class saves the following results to the PreprocessingContext: 
 AllTokens.image
 AllTokens.documentIndex
 AllTokens.fieldIndex
 AllTokens.type
 ";

    /**
     * Attributes of the component. Note that only statically reachable fields are included.
     * Additional attributes may be available at run time. 
     */
    public final static Attributes attributes; 

    /**
     * Attributes declared directly by the component.
     */
    private final static Set ownAttributes;

    /**
     * Attributes declared by the component or its superclasses.
     */
    private final static Set allAttributes;

    /**
     * Attributes declared by the component or its superclasses, lookup dictionary 
     * by attribute key.
     */
    private final static Map allAttributesByKey;

    /**
     * Attributes declared by the component or its superclasses, lookup dictionary by 
     * attribute's field name.
     */
    private final static Map allAttributesByFieldName;

    /**
     * Static initializer for internal collections.
     */
    static
    {
        attributes = new Attributes();

        final Set ownAttrs = new HashSet();
        ownAttrs.add(attributes.documentFields);

        final Set allAttrs = new HashSet();
        allAttrs.add(org.carrot2.text.preprocessing.TokenizerDescriptor.attributes.documentFields);

        allAttributes = Collections.unmodifiableSet(allAttrs);
        ownAttributes = Collections.unmodifiableSet(ownAttrs);
        
        final Map allAttrsByKey = new HashMap();
        final Map allAttrsByFieldName = new HashMap();
        for (AttributeInfo ai : allAttrs)
        {
            allAttrsByKey.put(ai.key, ai);
            allAttrsByFieldName.put(ai.fieldName, ai);
        }

        allAttributesByKey = Collections.unmodifiableMap(allAttrsByKey);
        allAttributesByFieldName = Collections.unmodifiableMap(allAttrsByFieldName);
    }

    
    /* Attribute keys. */

    /**
     * Constants for all attribute keys of the {@link org.carrot2.text.preprocessing.Tokenizer} component.
     */
    public static class Keys 
    {
        protected Keys() {} 

        /** Attribute key for: {@link org.carrot2.text.preprocessing.Tokenizer#documentFields}. */
        public static final String DOCUMENT_FIELDS = "Tokenizer.documentFields";
    }


    /* Attribute descriptors. */

    /**
     * All attributes of the {@link org.carrot2.text.preprocessing.Tokenizer} component.
     */
    public static final class Attributes
    {
        private Attributes() { /* No public instances. */ }

        /**
         *          */
        public final AttributeInfo documentFields = 
            new AttributeInfo(
                "Tokenizer.documentFields",
                "org.carrot2.text.preprocessing.Tokenizer",
                "documentFields",
                "Textual fields of documents that should be tokenized and parsed for clustering.",
                "Document fields",
                "Textual fields of documents that should be tokenized and parsed for clustering",
                null,
                "Preprocessing",
                org.carrot2.util.attribute.AttributeLevel.ADVANCED,
                null
            );


    }

    /**
     * Attribute map builder for the  {@link org.carrot2.text.preprocessing.Tokenizer} component. You can use this
     * builder as a type-safe alternative to populating the attribute map using attribute keys.
     */
    public static class AttributeBuilder 
    {
        /** The attribute map populated by this builder. */
        public final Map map;

        /**
         * Creates a builder backed by the provided map.
         */
        protected AttributeBuilder(Map map)
        {
            
            this.map = map;
        }


        
        
        /**
         * Textual fields of documents that should be tokenized and parsed for clustering.
         * 
         * @see org.carrot2.text.preprocessing.Tokenizer#documentFields 
         */
        public AttributeBuilder documentFields(java.util.Collection value)
        {
            map.put("Tokenizer.documentFields", value);
            return this;
        }
        
        
        
        
        
        /**
         * Textual fields of documents that should be tokenized and parsed for clustering.
         * 
         * @see org.carrot2.text.preprocessing.Tokenizer#documentFields 
         */
        public AttributeBuilder documentFields(IObjectFactory> value)
        {
            map.put("Tokenizer.documentFields", value);
            return this;
        }
        
        
        
    }

    /**
     * Creates an attribute map builder for the component. You can use this
     * builder as a type-safe alternative to populating the attribute map using attribute keys.
     * 
     * @param attributeValues An existing map which should be used to collect attribute values. 
     *        Attribute values set by this builder will be added to the provided map, overwriting
     *        previously defined mappings, if any.
     */
    public static AttributeBuilder attributeBuilder(Map attributeValues)
    {
        return new AttributeBuilder(attributeValues);
    }
    
    /* IBindableDescriptor */

    @Override 
    public String getPrefix()
    {
        return prefix;
    }

    @Override 
    public String getTitle()
    {
        return title;
    }
    
    @Override 
    public String getLabel()      
    { 
        return label;
    }
    
    @Override 
    public String getDescription() 
    { 
        return description; 
    }

    @Override 
    public Set getOwnAttributes()
    { 
        return ownAttributes;
    }

    @Override 
    public Set getAttributes()
    {
        return allAttributes;
    }

    @Override 
    public Map getAttributesByKey()
    {
        return allAttributesByKey;
    }

    @Override 
    public Map getAttributesByFieldName()
    {
        return allAttributesByFieldName;
    }
}