Checkstyle fixes for lang ident model

Author: davidkyle

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/InferenceProcessor.java

@@ -11,7 +11,6 @@
 import org.elasticsearch.ingest.IngestDocument;
 import org.elasticsearch.ingest.Processor;
 
-import java.util.HashMap;
 import java.util.Map;
 import java.util.concurrent.ConcurrentHashMap;
 import java.util.function.BiConsumer;

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/EmbeddingNetwork.java

@@ -6,7 +6,9 @@
 
 package org.elasticsearch.xpack.ml.inference.langident;
 
-import java.util.*;
+
+import java.util.ArrayList;
+import java.util.Arrays;
 
 /**
  * Classifier using a hand-coded feed-forward neural network.

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/EmbeddingNetworkParams.java

@@ -6,9 +6,6 @@
 
 package org.elasticsearch.xpack.ml.inference.langident;
 
-/**
- *
- */
 public abstract class EmbeddingNetworkParams {
     public enum QuantizationType {
         NONE,

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/FeatureUtils.java

@@ -6,11 +6,7 @@
 
 package org.elasticsearch.xpack.ml.inference.langident;
 
-import org.apache.logging.log4j.message.ParameterizedMessage;
-import org.apache.logging.log4j.util.Supplier;
-
 import java.io.UnsupportedEncodingException;
-import java.nio.charset.StandardCharsets;
 import java.util.Locale;
 
 /**
@@ -195,7 +191,8 @@ public static String toUTF8ByteString(String text) {
             boolean isIdeographic = Character.isIdeographic(codepoint);
             Character.UnicodeBlock unicodeBlock = Character.UnicodeBlock.of(codepoint);
 
-            sb.append(String.format("%d|%b,%b,%b,%b,%s|", codepoint, isLetter, isSupplementaryCodePoint, isSpaceChar, isIdeographic, unicodeBlock.toString()));
+            sb.append(String.format("%d|%b,%b,%b,%b,%s|", codepoint, isLetter, isSupplementaryCodePoint,
+             isSpaceChar, isIdeographic, unicodeBlock.toString()));
 
             offset += Character.charCount(codepoint);
         }
@@ -204,11 +201,11 @@ public static String toUTF8ByteString(String text) {
             byte[] bytes = text.getBytes("UTF-8");
             StringBuilder sb = new StringBuilder();
             for (byte b : bytes) {
-                sb.append(String.format("%02X", b));
+                sb.append(String.format(Locale.ROOT, "%02X", b));
             }
             return sb.toString();
         } catch (UnsupportedEncodingException e) {
-            e.printStackTrace();
+//            e.printStackTrace();
         }
         return "";
     }

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/FeatureVector.java

@@ -54,16 +54,16 @@ private class Element {
         private final FeatureType featureType;
         private final long featureValue;
 
-        public Element(FeatureType featureType, long featureValue) {
+        Element(FeatureType featureType, long featureValue) {
             this.featureType = featureType;
             this.featureValue = featureValue;
         }
 
-        public FeatureType getFeatureType() {
+        FeatureType getFeatureType() {
             return featureType;
         }
 
-        public long getFeatureValue() {
+        long getFeatureValue() {
             return featureValue;
         }
     }

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/LangIdentModel.java

@@ -29,7 +29,7 @@ final class LangIdentModel implements Model {
     private final String targetIsReliableField;
     private final boolean ignoreMissing;
 
-    public LangIdentModel(String field,
+    LangIdentModel(String field,
                           String targetLanguageField, String targetProbabilityField,
                           String targetTopProbabilitiesField, String targetIsReliableField,
                           boolean ignoreMissing) {
@@ -71,7 +71,7 @@ public void infer(IngestDocument ingestDocument, BiConsumer<IngestDocument, Exce
             }
             if (targetTopProbabilitiesField != null) {
                 ingestDocument.setFieldValue(targetTopProbabilitiesField, result.getTopProbabilities().toString());
-            }+
+            }
             if (targetIsReliableField != null) {
                 ingestDocument.setFieldValue(targetIsReliableField, result.isReliable());
             }
@@ -82,23 +82,4 @@ public void infer(IngestDocument ingestDocument, BiConsumer<IngestDocument, Exce
 
         handler.accept(ingestDocument, null);
     }
-
-    public NNetLanguageIdentifier.Result identifyLanguage(String text) {
-        NNetLanguageIdentifier.Result result = null;
-
-        if (languageIdentifier == null) {
-            logger.error("Language identifier model not initialised - unknown language returned");
-            return new NNetLanguageIdentifier.Result();
-        }
-
-        try {
-            result = languageIdentifier.findLanguage(text);
-        } catch (Exception e) {
-            logger.error((Supplier<?>) () -> new ParameterizedMessage(
-                "Error identifjying language [{}]", text), e);
-            result = new NNetLanguageIdentifier.Result();
-        }
-
-        return result;
-    }
 }

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/LangIdentParams.java

@@ -7,7 +7,7 @@
 package org.elasticsearch.xpack.ml.inference.langident;
 
 public class LangIdentParams {
-    public final static String kLanguageNames[] = {
+    public static final String kLanguageNames[] = {
         "eo", "co", "eu", "ta", "de", "mt", "ps", "te", "su", "uz", "zh-Latn", "ne",
         "nl", "sw", "sq", "hmn", "ja", "no", "mn", "so", "ko", "kk", "sl", "ig",
         "mr", "th", "zu", "ml", "hr", "bs", "lo", "sd", "cy", "hy", "uk", "pt",

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/NNetLanguageIdentifier.java

@@ -7,7 +7,11 @@
 package org.elasticsearch.xpack.ml.inference.langident;
 
 import java.io.FileNotFoundException;
-import java.util.*;
+import java.util.AbstractMap;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+import java.util.Map;
 
 public class NNetLanguageIdentifier {
     public static final int kMaxNumInputBytesToConsider = 10000;
@@ -50,7 +54,7 @@ public ArrayList<FeatureVector> getFeatures(String text) throws Exception {
 
         return features;
     }
-
+/*
     private void dumpFeatures(String text, ArrayList<FeatureVector> featureVectors) {
         System.out.println("'" + text + "'" + text.length() + "{");
         System.out.println("features:" + featureVectors.size());
@@ -67,6 +71,7 @@ private void dumpFeatures(String text, ArrayList<FeatureVector> featureVectors)
         }
         System.out.println("}");
     }
+*/
 
     private Result findLanguageOfValidUTF8(String text) throws Exception {
         // Create the feature vector with it actually a list
@@ -123,7 +128,7 @@ boolean resultIsReliable(String language, float probability) {
     }
 
     public static class Result {
-        public final static int TOP_N = 5;
+        public static final int TOP_N = 5;
 
         private final String language;
         private final float probability;

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/inference/langident/NNetParams.java

@@ -6,15 +6,11 @@
 
 package org.elasticsearch.xpack.ml.inference.langident;
 
-import java.io.File;
+import org.apache.commons.codec.Charsets;
+
 import java.io.FileNotFoundException;
-import java.io.InputStream;
-import java.util.InputMismatchException;
 import java.util.Scanner;
 
-/**
- *
- */
 public class NNetParams extends EmbeddingNetworkParams {
     private static final int EMBEDDINGS_SIZE = 6;
     private static final int EMBEDDING_NUM_FEATURES_SIZE = 6;
@@ -111,7 +107,7 @@ public NNetParams() throws FileNotFoundException {
     }
 
     private static short[] readFileToShortArray(String path) throws FileNotFoundException {
-        Scanner s = new Scanner(NNetParams.class.getResourceAsStream(path));
+        Scanner s = new Scanner(NNetParams.class.getResourceAsStream(path), Charsets.UTF_8);
         // Read first entry (array size) as integer
         short[] array = new short[s.nextInt()];
         for (int i = 0; i < array.length; i++) {
@@ -121,7 +117,7 @@ private static short[] readFileToShortArray(String path) throws FileNotFoundExce
     }
 
     private static char[] readFileToCharArray(String path) throws FileNotFoundException {
-        Scanner s = new Scanner(NNetParams.class.getResourceAsStream(path));
+        Scanner s = new Scanner(NNetParams.class.getResourceAsStream(path), Charsets.UTF_8);
         // Read first entry (array size) as integer
         char[] array = new char[s.nextInt()];
         for (int i = 0; i < array.length; i++) {
@@ -132,7 +128,7 @@ private static char[] readFileToCharArray(String path) throws FileNotFoundExcept
     }
 
     private static float[] readFileToFloatArray(String path) throws FileNotFoundException {
-        Scanner s = new Scanner(NNetParams.class.getResourceAsStream(path));
+        Scanner s = new Scanner(NNetParams.class.getResourceAsStream(path), Charsets.UTF_8);
         // Read first entry (array size) as integer
         float[] array = new float[s.nextInt()];
         for (int i = 0; i < array.length; i++) {
@@ -143,7 +139,6 @@ private static float[] readFileToFloatArray(String path) throws FileNotFoundExce
                 array[i] = f;
             } catch (Exception e) {
                 // TODO resolve error
-                System.out.println("Can not parse to float '" + text + "'" + e.toString());
                 throw e;
             }
         }