This is an automated email from the ASF dual-hosted git repository.
aradzinski pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/master by this push:
new 03626dd WIP
03626dd is described below
commit 03626dd56f81244c6702ea542162b40c351e4cf4
Author: Aaron Radzinski <[email protected]>
AuthorDate: Wed Oct 6 13:54:01 2021 -0700
WIP
---
nlpcraft/pom.xml | 5 +
.../org/apache/nlpcraft/common/util/NCUtils.scala | 14 +
.../org/apache/nlpcraft/model/NCMetadata.java | 120 +++++++++
.../scala/org/apache/nlpcraft/model/NCModel.java | 25 ++
.../org/apache/nlpcraft/model/NCRejection.java | 49 ++++
.../scala/org/apache/nlpcraft/model/NCResult.java | 257 ++++++++++++++++++
.../scala/org/apache/nlpcraft/model/NCToken.java | 294 +++++++++++++++++++++
.../nlpcraft/model/impl/NCMetadataAdapter.java | 50 ++++
pom.xml | 7 +
9 files changed, 821 insertions(+)
diff --git a/nlpcraft/pom.xml b/nlpcraft/pom.xml
index 94a9ea2..a01bc70 100644
--- a/nlpcraft/pom.xml
+++ b/nlpcraft/pom.xml
@@ -89,6 +89,11 @@
<artifactId>antlr4-runtime</artifactId>
</dependency>
+ <dependency>
+ <groupId>com.google.code.gson</groupId>
+ <artifactId>gson</artifactId>
+ </dependency>
+
<!--
JUnit & ScalaTest dependencies.
===============================
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/common/util/NCUtils.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/common/util/NCUtils.scala
index 4cc3469..5838a2d 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/common/util/NCUtils.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/common/util/NCUtils.scala
@@ -17,6 +17,7 @@
package org.apache.nlpcraft.common.util
+import com.google.gson.GsonBuilder
import com.typesafe.scalalogging.*
import org.apache.nlpcraft.common.NCException
import org.apache.nlpcraft.common.ansi.NCAnsi.*
@@ -36,6 +37,7 @@ object NCUtils extends LazyLogging:
final val NL = System getProperty "line.separator"
private val RND = new Random()
private val sysProps = new SystemProperties
+ private final lazy val GSON = new
GsonBuilder().setPrettyPrinting().disableHtmlEscaping().create()
private final val ANSI_SEQ = Pattern.compile("\u001B\\[[?;\\d]*[a-zA-Z]")
private val ANSI_FG_8BIT_COLORS = for (i <- 16 to 255) yield ansi256Fg(i)
private val ANSI_BG_8BIT_COLORS = for (i <- 16 to 255) yield ansi256Bg(i)
@@ -75,6 +77,18 @@ object NCUtils extends LazyLogging:
def isSysEnvSet(s: String): Boolean = sysProps.get(s).nonEmpty ||
sys.env.contains(s)
/**
+ * Creates object from JSON string.
+ *
+ * @param js JSON string.
+ */
+ @throws[NCException]
+ def jsonToObject(js: String): AnyRef =
+ try
+ GSON.fromJson(js, classOf[Object])
+ catch
+ case e: Exception => throw new NCException(s"Failed to convert
JSON string to map: $js", e)
+
+ /**
* Returns `true` if given system property, or environment variable is
provided and has value
* 'true'. In all other cases returns `false`.
*
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCMetadata.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCMetadata.java
new file mode 100644
index 0000000..91c10f4
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCMetadata.java
@@ -0,0 +1,120 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nlpcraft.model;
+
+import org.apache.nlpcraft.common.*;
+import java.util.*;
+
+/**
+ * Provides support for mutable runtime-only metadata.
+ * <p>
+ * Read full documentation in <a target=_
href="https://nlpcraft.apache.org/data-model.html";>Data Model</a> section and
review
+ * <a target=_
href="https://github.com/apache/incubator-nlpcraft/tree/master/nlpcraft-examples";>examples</a>.
+ */
+public interface NCMetadata {
+ /**
+ * Factory for creating metadata out of standard map.
+ *
+ * @param map Map to convert to metadata.
+ * @return Newly created metadata container.
+ */
+ static NCMetadata apply(Map<String, Object> map) {
+ return () -> map;
+ }
+
+ /**
+ * Gets mutable metadata underlying container.
+ * Returned map can be used to mutate the metadata or perform any other
operations.
+ *
+ * @return Mutable, underlying metadata container.
+ * @see #meta(String)
+ * @see #metaOpt(String)
+ * @see #meta(String, Object)
+ */
+ Map<String, Object> getMetadata();
+
+ /**
+ * Shortcut method to get given optional metadata property. Equivalent to:
+ * <pre class="brush: java">
+ * Optional.ofNullable((T)getMetadata().get(prop));
+ * </pre>
+ *
+ * @param prop Metadata property name.
+ * @param <T> Type of the metadata property.
+ * @return Metadata optional property value.
+ */
+ @SuppressWarnings("unchecked")
+ default <T> Optional<T> metaOpt(String prop) {
+ return Optional.ofNullable((T)getMetadata().get(prop));
+ }
+
+ /**
+ * Shortcut method to get given metadata property. Equivalent to:
+ * <pre class="brush: java">
+ * (T)getMetadata().get(prop);
+ * </pre>
+ *
+ * @param prop Metadata property name.
+ * @param <T> Type of the metadata property.
+ * @return Metadata property value or {@code null} if given metadata
property not found.
+ */
+ @SuppressWarnings("unchecked")
+ default <T> T meta(String prop) {
+ return (T)getMetadata().get(prop);
+ }
+
+ /**
+ * Shortcut method to get given mandatory metadata property. Equivalent to:
+ * <pre class="brush: java">
+ * T t = (T)getMetadata().get(prop);
+ * if (t == null)
+ * throw new NCException("Mandatory metadata property not found: "
+ prop);
+ * else
+ * return t;
+ * </pre>
+ *
+ * @param prop Metadata property name.
+ * @param <T> Type of the metadata property.
+ * @return Metadata property value or throws an exception if given
metadata property not found.
+ * @throws NCException Thrown if given metadata property not found.
+ */
+ default <T> T metax(String prop) throws NCException {
+ T t = meta(prop);
+
+ if (t == null)
+ throw new NCException("Mandatory metadata property not found: " +
prop);
+ else
+ return t;
+ }
+
+ /**
+ * Shortcut method to get given metadata property. Equivalent to:
+ * <pre class="brush: java">
+ * getMetadata().get(tokId, prop, dflt);
+ * </pre>
+ *
+ * @param prop Metadata property name.
+ * @param dflt Default value to return if specified one isn't set.
+ * @param <T> Type of the metadata property.
+ * @return Metadata property value or default value if one isn't set.
+ */
+ @SuppressWarnings("unchecked")
+ default <T> T meta(String prop, T dflt) {
+ return (T)getMetadata().getOrDefault(prop, dflt);
+ }
+}
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCModel.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCModel.java
new file mode 100644
index 0000000..45a0a06
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCModel.java
@@ -0,0 +1,25 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * https://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nlpcraft.model;
+
+/**
+ *
+ */
+public interface NCModel {
+ // TODO
+}
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCRejection.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCRejection.java
new file mode 100644
index 0000000..6ae83b3
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCRejection.java
@@ -0,0 +1,49 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nlpcraft.model;
+
+import org.apache.nlpcraft.common.*;
+
+/**
+ * Exception to indicate that user input cannot be processed as is. This
exception can be thrown from
+ * intent callbacks.
+ * <p>
+ * This exception typically indicates that user has not provided enough
information in the input string
+ * to have it processed automatically. In most cases this means that the
user's input is either too short
+ * or too simple, too long or too complex, missing required context, or
unrelated to requested data model.
+ */
+public class NCRejection extends NCException {
+ /**
+ * Creates new rejection exception with given message.
+ *
+ * @param msg Rejection message.
+ */
+ public NCRejection(String msg) {
+ super(msg);
+ }
+
+ /**
+ * Creates new rejection exception with given message and cause.
+ *
+ * @param msg Rejection message.
+ * @param cause Cause of this exception.
+ */
+ public NCRejection(String msg, Throwable cause) {
+ super(msg, cause);
+ }
+}
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCResult.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCResult.java
new file mode 100644
index 0000000..5ff6681
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCResult.java
@@ -0,0 +1,257 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nlpcraft.model;
+
+import org.apache.nlpcraft.common.NCException;
+import org.apache.nlpcraft.common.util.*;
+import org.apache.nlpcraft.model.impl.NCMetadataAdapter;
+
+import java.io.Serializable;
+import java.util.Collection;
+
+/**
+ * Data model result returned from model intent callbacks. Result consists of
the
+ * text body and the type. The type is similar in notion to MIME types.
+ * <table class="dl-table">
+ * <caption>Supported result types:</caption>
+ * <tr>
+ * <th>Result Type</th>
+ * <th>Factory Method</th>
+ * </tr>
+ * <tr>
+ * <td><code>text</code></td>
+ * <td>{@link #text(String)}</td>
+ * </tr>
+ * <tr>
+ * <td><code>html</code></td>
+ * <td>{@link #html(String)}</td>
+ * </tr>
+ * <tr>
+ * <td><code>json</code></td>
+ * <td>{@link #json(String)}</td>
+ * </tr>
+ * <tr>
+ * <td><code>yaml</code></td>
+ * <td>{@link #yaml(String)}</td>
+ * </tr>
+ * <tr>
+ * <td><code>confirm</code></td>
+ * <td>{@link #confirm(String)}</td>
+ * </tr>
+ * </table>
+ * Note that all of these types have specific meaning for client applications
that interpret them
+ * accordingly. For example, the REST client interfacing between NLPCraft and
Amazon Alexa or Apple HomeKit can only
+ * accept {@code text} result type and ignore everything else.
+ */
+public class NCResult extends NCMetadataAdapter implements Serializable,
NCMetadata {
+ /** Data Model result text. */
+ private String body;
+
+ /** Data Model result type. One of text, html, json or yaml. */
+ private String type;
+
+ /** Sequence of tokens represents a fully parsed (see {@link
NCContext#getVariants()} method) user input. */
+ private Collection<NCToken> tokens;
+
+ /** ID of the intent. */
+ private String intentId;
+
+ /**
+ * Creates new result with given body and type.
+ *
+ * @param body Result body.
+ * @param type Result type.
+ * @throws IllegalArgumentException Thrown if type is invalid.
+ */
+ public NCResult(String body, String type) {
+ assert body != null;
+ assert type != null;
+
+ this.body = body;
+ this.type = checkType(type);
+ }
+
+ /**
+ * No-arg constructor.
+ */
+ public NCResult() {
+ // No-op.
+ }
+
+ /**
+ * Creates {@code text} result.
+ *
+ * @param txt Textual result. Text interpretation will be defined by the
client receiving this result.
+ * @return Newly created query result.
+ */
+ public static NCResult text(String txt) {
+ return new NCResult(txt, "text");
+ }
+
+ /**
+ * Creates {@code html} result.
+ *
+ * @param html HTML markup.
+ * @return Newly created query result.
+ */
+ public static NCResult html(String html) {
+ return new NCResult(html, "html");
+ }
+
+ /**
+ * Creates {@code confirm} result.
+ *
+ * @param body Confirm result body.
+ * @return Newly created query result.
+ */
+ public static NCResult confirm(String body) {
+ return new NCResult(body, "confirm");
+ }
+
+ /**
+ * Creates {@code json} result. Note that this method will test given JSON
string
+ * for validness by using <code>com.google.gson.Gson</code> JSON utility.
If JSON string is invalid
+ * the {@link IllegalArgumentException} exception will be thrown.
+ *
+ * @param json Any JSON string to be rendered on the client.
+ * @return Newly created query result.
+ * @throws IllegalArgumentException Thrown if given JSON string is invalid.
+ */
+ public static NCResult json(String json) {
+ // Validation.
+ try {
+ NCUtils.jsonToObject(json);
+ }
+ catch (NCException e) {
+ throw new IllegalArgumentException(String.format("Invalid JSON
value: %s.", json), e.getCause());
+ }
+
+ return new NCResult(json, "json");
+ }
+
+ /**
+ * Creates {@code yaml} result.
+ *
+ * @param yaml Any YAML string to be rendered on the client.
+ * @return Newly created query result.
+ */
+ public static NCResult yaml(String yaml) {
+ return new NCResult(yaml, "yaml");
+ }
+
+ /**
+ *
+ * @param type Type to check.
+ * @throws IllegalArgumentException Thrown if type is invalid.
+ */
+ private String checkType(String type) {
+ String typeLc = type.toLowerCase();
+
+ if (!typeLc.equals("html") &&
+ !typeLc.equals("json") &&
+ !typeLc.equals("yaml") &&
+ !typeLc.equals("confirm") &&
+ !typeLc.equals("text"))
+ throw new IllegalArgumentException("Invalid result type: " + type);
+ else
+ return typeLc;
+ }
+
+ /**
+ * Sets result body.
+ *
+ * @param body Result body.
+ */
+ public void setBody(String body) {
+ this.body = body;
+ }
+
+ /**
+ * Set result type.
+ *
+ * @param type Result type.
+ * @throws IllegalArgumentException Thrown if type is invalid.
+ */
+ public void setType(String type) {
+ this.type = checkType(type);
+ }
+
+ /**
+ * Gets tokens that were used to produce this query result. Note that the
+ * returned tokens can come from the current request as well as from the
conversation (i.e. from
+ * previous requests). Order of tokens is not important.
+ *
+ * @return Gets tokens that were used to produce this query result.
+ * @see #setTokens(Collection)
+ */
+ public Collection<NCToken> getTokens() {
+ return tokens;
+ }
+
+ /**
+ * Sets a collection of tokens that was used to produce this query result.
Note that the
+ * returned tokens can come from the current request as well as from the
conversation (i.e. from
+ * previous requests). Order of tokens is not important.
+ * <p>
+ * Providing these tokens is necessary for proper STM operation. If
conversational support isn't used
+ * setting these tokens is not required. Note that built-in intent based
matched automatically sets
+ * these tokens.
+ *
+ * @param tokens Collection of tokens that was used to produce this query
result.
+ * @see #getTokens()
+ */
+ public void setTokens(Collection<NCToken> tokens) {
+ this.tokens = tokens;
+ }
+
+ /**
+ * Gets result type.
+ *
+ * @return Result type.
+ */
+ public String getType() {
+ return type;
+ }
+
+ /**
+ * Gets result body.
+ *
+ * @return Result body.
+ */
+ public String getBody() {
+ return body;
+ }
+
+ /**
+ * Get optional intent ID.
+ *
+ * @return Intent ID or {@code null} if intent ID was not available.
+ */
+ public String getIntentId() {
+ return intentId;
+ }
+
+ /**
+ * Sets optional intent ID.
+ *
+ * @param intentId Intent ID to set for this result.
+ */
+ public void setIntentId(String intentId) {
+ this.intentId = intentId;
+ }
+}
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCToken.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCToken.java
new file mode 100644
index 0000000..b815511
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/NCToken.java
@@ -0,0 +1,294 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * https://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nlpcraft.model;
+
+import java.util.List;
+
+/**
+ * Detected model element.
+ * <p>
+ * Read full documentation in <a target=_
href="https://nlpcraft.apache.org/data-model.html";>Data Model</a> section and
review
+ * <a target=_
href="https://github.com/apache/incubator-nlpcraft/tree/master/nlpcraft-examples";>examples</a>.
+ *
+ * @see NCElement
+ */
+public interface NCToken extends NCMetadata {
+ /**
+ * Gets reference to the model this token belongs to.
+ *
+ * @return Model reference.
+ */
+ NCModel getModel();
+
+ /**
+ * Gets ID of the server request this token is part of.
+ *
+ * @return ID of the server request this token is part of.
+ */
+ String getServerRequestId();
+
+ /**
+ * If this token represents user defined model element this method returns
+ * the ID of that element. Otherwise, it returns ID of the built-in system
token.
+ * Note that a sentence can have multiple tokens with the same element ID.
+ *
+ * @return ID of the element (system or user defined).
+ * @see NCElement#getId()
+ */
+ String getId();
+
+ /**
+ * Gets the optional parent ID of the model element this token represents.
This only available
+ * for user-defined model elements - built-in tokens do not have parents
and this will return {@code null}.
+ *
+ * @return ID of the token's element immediate parent or {@code null} if
not available.
+ * @see NCElement#getParentId()
+ * @see #getAncestors()
+ */
+ String getParentId();
+
+ /**
+ * Gets the list of all parent IDs from this token up to the root. This
only available
+ * for user-defined model elements = built-in tokens do not have parents
and will return an empty list.
+ *
+ * @return List, potentially empty but never {@code null}, of all parent
IDs from this token up to the root.
+ * @see #getParentId()
+ */
+ List<String> getAncestors();
+
+ /**
+ * Tests whether this token is a child of given token ID. It is equivalent
to:
+ * <pre class="brush: java">
+ * return getAncestors().contains(tokId);
+ * </pre>
+ *
+ * @param tokId Ancestor token ID.
+ * @return <code>true</code> this token is a child of given token ID,
<code>false</code> otherwise.
+ */
+ default boolean isChildOf(String tokId) {
+ return getAncestors().contains(tokId);
+ }
+
+ /**
+ * Gets the value if this token was detected via element's value (or its
synonyms). Otherwise,
+ * returns {@code null}. Only applicable for user-defined model elements -
built-in tokens
+ * do not have values, and it will return {@code null}.
+ *
+ * @return Value for the user-defined model element or {@code null}, if
not available.
+ * @see NCElement#getValues()
+ */
+ String getValue();
+
+ /**
+ * Gets the list of groups this token belongs to. Note that, by default,
if not specified explicitly,
+ * token always belongs to one group with ID equal to token ID.
+ *
+ * @return Token groups list. Never {@code null} - but can be empty.
+ * @see NCElement#getGroups()
+ */
+ List<String> getGroups();
+
+ /**
+ * Tests whether this token belongs to the given group. It is equivalent
to:
+ * <pre class="brush: java">
+ * return getGroups().contains(grp);
+ * </pre>
+ *
+ * @param grp Group to test.
+ * @return <code>True</code> if this token belongs to the group
<code>grp</code>, {@code false} otherwise.
+ */
+ default boolean isMemberOf(String grp) {
+ return getGroups().contains(grp);
+ }
+
+ /**
+ * Gets start character index of this token in the original text.
+ *
+ * @return Start character index of this token.
+ */
+ int getStartCharIndex();
+
+ /**
+ * Gets end character index of this token in the original text.
+ *
+ * @return End character index of this token.
+ */
+ int getEndCharIndex();
+
+ /**
+ * A shortcut method checking whether this token is a stopword. Stopwords
are some extremely common
+ * words which add little value in helping to understand user input and
are excluded from the
+ * processing entirely. For example, words like a, the, can, of, about,
over, etc. are
+ * typical stopwords in English. NLPCraft has built-in set of stopwords.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:stopword");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Whether this token is a stopword.
+ */
+ default boolean isStopWord() {
+ return meta("nlpcraft:nlp:stopword");
+ }
+
+ /**
+ * A shortcut method checking whether this token represents a free word. A
free word is a
+ * token that was detected neither as a part of user defined nor system
tokens.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:freeword");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Whether this token is a freeword.
+ */
+ default boolean isFreeWord() {
+ return meta("nlpcraft:nlp:freeword");
+ }
+
+ /**
+ * A shortcut method that gets original user input text for this token.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:origtext");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Original user input text for this token.
+ */
+ default String getOriginalText() {
+ return meta("nlpcraft:nlp:origtext");
+ }
+
+ /**
+ * A shortcut method that gets index of this token in the sentence.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:index");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Index of this token in the sentence.
+ */
+ default int getIndex() {
+ return meta("nlpcraft:nlp:index");
+ }
+
+ /**
+ * A shortcut method that gets normalized user input text for this token.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:normtext");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Normalized user input text for this token.
+ */
+ default String getNormalizedText() {
+ return meta("nlpcraft:nlp:normtext");
+ }
+
+ /**
+ * A shortcut method on whether this token is a swear word. NLPCraft has
built-in list of
+ * common English swear words.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:swear");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Whether this token is a swear word.
+ */
+ default boolean isSwear() {
+ return meta("nlpcraft:nlp:swear");
+ }
+
+ /**
+ * A shortcut method to get lemma of this token, i.e. a canonical form of
this word. Note that
+ * stemming and lemmatization allow reducing inflectional forms and
sometimes derivationally related
+ * forms of a word to a common base form. Lemmatization refers to the use
of a vocabulary and
+ * morphological analysis of words, normally aiming to remove inflectional
endings only and to
+ * return the base or dictionary form of a word, which is known as the
lemma.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:lemma");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Lemma of this token, i.e. a canonical form of this word.
+ */
+ default String getLemma() {
+ return meta("nlpcraft:nlp:lemma");
+ }
+
+ /**
+ * A shortcut method to get stem of this token. Note that stemming and
lemmatization allow to reduce
+ * inflectional forms and sometimes derivationally related forms of a word
to a common base form.
+ * Unlike lemma, stemming is a basic heuristic process that chops off the
ends of words in the
+ * hope of achieving this goal correctly most of the time, and often
includes the removal of derivational affixes.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:stem");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Stem of this token.
+ */
+ default String getStem() {
+ return meta("nlpcraft:nlp:stem");
+ }
+
+ /**
+ * A shortcut method to get Penn Treebank POS tag for this token. Note
that additionally to standard Penn
+ * Treebank POS tags NLPCraft introduced '---' synthetic tag to indicate a
POS tag for multiword tokens.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:pos");
+ * </pre>
+ * See more information on token metadata <a target=_
href="https://nlpcraft.apache.org/data-model.html";>here</a>.
+ *
+ * @return Penn Treebank POS tag for this token.
+ */
+ default String getPos() {
+ return meta("nlpcraft:nlp:pos");
+ }
+
+ /**
+ * A shortcut method that gets internal globally unique system ID of the
token.
+ * <p>
+ * This method is equivalent to:
+ * <pre class="brush: java">
+ * return meta("nlpcraft:nlp:unid");
+ * </pre>
+ *
+ * @return Internal globally unique system ID of the token.
+ */
+ default String getUnid() {
+ return meta("nlpcraft:nlp:unid");
+ }
+}
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/impl/NCMetadataAdapter.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/impl/NCMetadataAdapter.java
new file mode 100644
index 0000000..b3b9d09
--- /dev/null
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/impl/NCMetadataAdapter.java
@@ -0,0 +1,50 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nlpcraft.model.impl;
+
+import org.apache.nlpcraft.model.NCMetadata;
+
+import java.util.HashMap;
+import java.util.Map;
+
+/**
+ * Abstract adapter for metadata.
+ */
+public abstract class NCMetadataAdapter implements NCMetadata {
+ final private Map<String, Object> meta;
+
+ /**
+ *
+ */
+ protected NCMetadataAdapter() {
+ meta = new HashMap<>();
+ }
+
+ /**
+ *
+ * @param meta Metadata container to use.
+ */
+ protected NCMetadataAdapter(Map<String, Object> meta) {
+ this.meta = meta;
+ }
+
+ @Override
+ public Map<String, Object> getMetadata() {
+ return meta;
+ }
+}
diff --git a/pom.xml b/pom.xml
index 9f93030..6210045 100644
--- a/pom.xml
+++ b/pom.xml
@@ -102,6 +102,7 @@
<scala3.ref.ver>1.0.0</scala3.ref.ver>
<junit.ver>5.8.1</junit.ver>
<scalatest.ver>3.2.9</scalatest.ver>
+ <gson.ver>2.8.5</gson.ver>
<!-- Force specific encoding on text resources. -->
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
@@ -154,6 +155,12 @@
-->
<dependency>
+ <groupId>com.google.code.gson</groupId>
+ <artifactId>gson</artifactId>
+ <version>${gson.ver}</version>
+ </dependency>
+
+ <dependency>
<groupId>org.antlr</groupId>
<artifactId>antlr4-runtime</artifactId>
<version>${org.antlr4.ver}</version>
