Rename PathCache to Selector #129

pom.xml

@@ -64,7 +64,6 @@
     <project.region>US</project.region>
     <argLine>-Duser.timezone=${project.timezone} -Dfile.encoding=${project.build.sourceEncoding} -Duser.language=${project.language} -Duser.region=${project.region}</argLine>
     <skipUnitTests>false</skipUnitTests>
-    <testsToExclude>edu.harvard.iq.dataverse.NonEssentialTests</testsToExclude>
 
     <!-- sonarcloud properties -->
     <sonar.projectKey>pkiraly_metadata-qa-api</sonar.projectKey>

src/main/java/de/gwdg/metadataqa/api/calculator/AnnotationCalculator.java

@@ -3,7 +3,7 @@
 import de.gwdg.metadataqa.api.counter.FieldCounter;
 import de.gwdg.metadataqa.api.interfaces.Calculator;
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.problemcatalog.FieldCounterBasedResult;
 
 import java.io.Serializable;
@@ -24,7 +24,7 @@ public AnnotationCalculator(Map<String, Object> annotaionColumns) {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache) {
+  public List<MetricResult> measure(Selector cache) {
     if (results == null) {
       FieldCounter<Object> resultMap = new FieldCounter<>();
       for (Map.Entry<String, Object> entry : annotaionColumns.entrySet())

src/main/java/de/gwdg/metadataqa/api/calculator/CalculatorFacade.java

@@ -7,9 +7,9 @@
 import de.gwdg.metadataqa.api.interfaces.Calculator;
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
 import de.gwdg.metadataqa.api.interfaces.Shutdownable;
-import de.gwdg.metadataqa.api.model.pathcache.CsvPathCache;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
-import de.gwdg.metadataqa.api.model.PathCacheFactory;
+import de.gwdg.metadataqa.api.model.selector.CsvSelector;
+import de.gwdg.metadataqa.api.model.selector.Selector;
+import de.gwdg.metadataqa.api.model.selector.SelectorFactory;
 import de.gwdg.metadataqa.api.model.XmlFieldInstance;
 import de.gwdg.metadataqa.api.schema.Format;
 import de.gwdg.metadataqa.api.schema.Schema;
@@ -68,7 +68,7 @@ public class CalculatorFacade implements Serializable {
   protected TfIdfCalculator tfidfCalculator;
 
   // protected Format format = Format.JSON;
-  protected PathCache<? extends XmlFieldInstance> cache;
+  protected Selector<? extends XmlFieldInstance> cache;
   protected Schema schema;
   protected CsvReader csvReader;
 
@@ -184,7 +184,7 @@ protected <T extends XmlFieldInstance> Object measureWithGenerics(String content
     } else {
       var format = schema.getFormat();
       if (format != null && content != null) {
-        cache = PathCacheFactory.getInstance(schema.getFormat(), content);
+        cache = SelectorFactory.getInstance(schema.getFormat(), content);
         if (schema.getFormat().equals(Format.CSV))
           initializeCsvCache(content);
 
@@ -208,7 +208,7 @@ private void initializeCsvCache(String content) {
         LOGGER.log(Level.WARNING, "initializeCsvCache", e);
       }
 
-    ((CsvPathCache)cache).setCsvReader(csvReader);
+    ((CsvSelector)cache).setCsvReader(csvReader);
   }
 
   protected <T extends XmlFieldInstance> Object measureCsvWithGenerics(List<String> content,
@@ -226,7 +226,7 @@ protected <T extends XmlFieldInstance> Object measureCsvWithGenerics(List<String
     MetricCollector collector = new MetricCollector();
 
     if (content != null) {
-      cache = new CsvPathCache<>(csvReader, content);
+      cache = new CsvSelector<>(csvReader, content);
       runMeasurements(collector);
     }
 
@@ -314,7 +314,7 @@ public CalculatorFacade setCompressionLevel(CompressionLevel compressionLevel) {
     return this;
   }
 
-  public PathCache<? extends XmlFieldInstance> getCache() {
+  public Selector<? extends XmlFieldInstance> getCache() {
     return cache;
   }
 

src/main/java/de/gwdg/metadataqa/api/calculator/CompletenessCalculator.java

@@ -7,7 +7,7 @@
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
 import de.gwdg.metadataqa.api.json.FieldGroup;
 import de.gwdg.metadataqa.api.json.DataElement;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.model.XmlFieldInstance;
 import de.gwdg.metadataqa.api.problemcatalog.FieldCounterBasedResult;
 import de.gwdg.metadataqa.api.schema.Schema;
@@ -68,7 +68,7 @@ public String getCalculatorName() {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache)
+  public List<MetricResult> measure(Selector cache)
       throws InvalidJsonException {
     initializeCounters();
 
@@ -158,7 +158,7 @@ public void handleEmptyFragment(DataElement collection) {
   }
 
   public void evaluateDataElement(DataElement dataElement,
-                                  PathCache cache,
+                                  Selector cache,
                                   CompletenessCounter completenessCounter,
                                   String address,
                                   Object jsonFragment) {

src/main/java/de/gwdg/metadataqa/api/calculator/FieldExtractor.java

@@ -5,7 +5,7 @@
 import de.gwdg.metadataqa.api.interfaces.Calculator;
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
 import de.gwdg.metadataqa.api.model.EdmFieldInstance;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.model.XmlFieldInstance;
 import de.gwdg.metadataqa.api.problemcatalog.FieldCounterBasedResult;
 import de.gwdg.metadataqa.api.schema.Schema;
@@ -48,7 +48,7 @@ public String getCalculatorName() {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache)
+  public List<MetricResult> measure(Selector cache)
       throws InvalidJsonException {
     FieldCounter<String> resultMap = new FieldCounter<>();
     if (idPath != null)
@@ -66,7 +66,7 @@ public List<MetricResult> measure(PathCache cache)
     return List.of(new FieldCounterBasedResult<>(getCalculatorName(), resultMap).withNoCompression());
   }
 
-  private void extractSingleField(PathCache cache, FieldCounter<String> resultMap, String path, String fieldName) {
+  private void extractSingleField(Selector cache, FieldCounter<String> resultMap, String path, String fieldName) {
     List<XmlFieldInstance> values = cache.get(path);
     String value = null;
     if (values == null || values.isEmpty() || values.get(0) == null) {

src/main/java/de/gwdg/metadataqa/api/calculator/Indexer.java

@@ -5,7 +5,7 @@
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
 import de.gwdg.metadataqa.api.interfaces.Shutdownable;
 import de.gwdg.metadataqa.api.model.XmlFieldInstance;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.schema.Schema;
 import de.gwdg.metadataqa.api.uniqueness.SolrClient;
 import de.gwdg.metadataqa.api.uniqueness.UniquenessField;
@@ -31,7 +31,7 @@ public Indexer(SolrClient solrClient, Schema schema) {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache) {
+  public List<MetricResult> measure(Selector cache) {
     try {
       String recordId = extractValue(cache, schema.getRecordId().getPath()).get(0);
 
@@ -52,7 +52,7 @@ public List<MetricResult> measure(PathCache cache) {
     return null;
   }
 
-  private List<String> extractValue(PathCache cache, String path) {
+  private List<String> extractValue(Selector cache, String path) {
     List<String> values = new ArrayList<>();
     List<XmlFieldInstance> instances = cache.get(path);
     if (instances != null && !instances.isEmpty())

src/main/java/de/gwdg/metadataqa/api/calculator/LanguageCalculator.java

@@ -5,7 +5,7 @@
 import de.gwdg.metadataqa.api.counter.FieldCounter;
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
 import de.gwdg.metadataqa.api.json.DataElement;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.problemcatalog.FieldCounterBasedResult;
 import de.gwdg.metadataqa.api.schema.Schema;
 import java.util.ArrayList;
@@ -44,7 +44,7 @@ public List<String> getHeader() {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache)
+  public List<MetricResult> measure(Selector cache)
       throws InvalidJsonException {
 
     Language language = new Language(schema, cache);

src/main/java/de/gwdg/metadataqa/api/calculator/MultilingualitySaturationCalculator.java

@@ -5,7 +5,7 @@
 import de.gwdg.metadataqa.api.counter.FieldCounter;
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
 import de.gwdg.metadataqa.api.json.DataElement;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.problemcatalog.FieldCounterBasedResult;
 import de.gwdg.metadataqa.api.schema.Schema;
 import de.gwdg.metadataqa.api.util.SkippedEntitySelector;
@@ -89,7 +89,7 @@ public List<String> getHeader() {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache)
+  public List<MetricResult> measure(Selector cache)
       throws InvalidJsonException {
 
     Multilinguality multilinguality = new Multilinguality(schema, cache, resultType, skippedEntryChecker, skippedEntitySelector);

src/main/java/de/gwdg/metadataqa/api/calculator/SkippedEntryChecker.java

@@ -1,6 +1,6 @@
 package de.gwdg.metadataqa.api.calculator;
 
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.model.XmlFieldInstance;
 
 import java.io.Serializable;
@@ -12,6 +12,6 @@
  * @author Péter Király <peter.kiraly at gwdg.de>
  */
 public interface SkippedEntryChecker extends Serializable {
-  List<String> getSkippableCollectionIds(PathCache cache);
+  List<String> getSkippableCollectionIds(Selector cache);
   <T extends XmlFieldInstance> String extractId(T value);
 }

src/main/java/de/gwdg/metadataqa/api/calculator/TfIdfCalculator.java

@@ -4,7 +4,7 @@
 import de.gwdg.metadataqa.api.interfaces.Calculator;
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
 import de.gwdg.metadataqa.api.json.DataElement;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.problemcatalog.FieldCounterBasedResult;
 import de.gwdg.metadataqa.api.schema.Schema;
 import de.gwdg.metadataqa.api.uniqueness.SolrClient;
@@ -76,7 +76,7 @@ public String getCalculatorName() {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache) {
+  public List<MetricResult> measure(Selector cache) {
     String recordId = cache.getRecordId();
     if (recordId.startsWith("/")) {
       recordId = recordId.substring(1);

src/main/java/de/gwdg/metadataqa/api/calculator/UniquenessCalculator.java

@@ -2,7 +2,7 @@
 
 import de.gwdg.metadataqa.api.calculator.solr.QaSolrClient;
 import de.gwdg.metadataqa.api.interfaces.MetricResult;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.counter.FieldCounter;
 import de.gwdg.metadataqa.api.interfaces.Calculator;
 import de.gwdg.metadataqa.api.problemcatalog.FieldCounterBasedResult;
@@ -37,7 +37,7 @@ public String getCalculatorName() {
   }
 
   @Override
-  public List<MetricResult> measure(PathCache cache) {
+  public List<MetricResult> measure(Selector cache) {
     String recordId = cache.getRecordId();
     if (StringUtils.isNotBlank(recordId) && recordId.startsWith("/")) {
       recordId = recordId.substring(1);

src/main/java/de/gwdg/metadataqa/api/calculator/edm/EnhancementIdExtractor.java

@@ -3,7 +3,7 @@
 import de.gwdg.metadataqa.api.json.DataElement;
 import de.gwdg.metadataqa.api.json.JsonUtils;
 import de.gwdg.metadataqa.api.model.EdmFieldInstance;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.schema.Format;
 import de.gwdg.metadataqa.api.schema.Schema;
 import de.gwdg.metadataqa.api.util.Converter;
@@ -42,7 +42,7 @@ public final class EnhancementIdExtractor implements Serializable {
   private EnhancementIdExtractor() {
   }
 
-  public static List<String> extractIds(PathCache cache, Schema schema) {
+  public static List<String> extractIds(Selector cache, Schema schema) {
     List<String> enhancementIds = new ArrayList<>();
     String path = schema.getPathByLabel("Proxy").getPath().replace("false", "true");
     Object rawJsonFragment = cache.getFragment(path);
@@ -55,7 +55,7 @@ public static List<String> extractIds(PathCache cache, Schema schema) {
     return enhancementIds;
   }
 
-  public static void processXml(PathCache cache, Schema schema, List<String> enhancementIds, List<Object> jsonFragments) {
+  public static void processXml(Selector cache, Schema schema, List<String> enhancementIds, List<Object> jsonFragments) {
     DataElement parent = schema.getPathByLabel("Proxy");
     for (DataElement child : parent.getChildren()) {
       if (isEnrichmentField(child.getLabel())) {

src/main/java/de/gwdg/metadataqa/api/calculator/language/Language.java

@@ -4,7 +4,7 @@
 import de.gwdg.metadataqa.api.counter.FieldCounter;
 import de.gwdg.metadataqa.api.json.DataElement;
 import de.gwdg.metadataqa.api.model.EdmFieldInstance;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.schema.Schema;
 import de.gwdg.metadataqa.api.util.Converter;
 
@@ -15,12 +15,12 @@
 import java.util.TreeMap;
 
 public class Language {
-  private final PathCache cache;
+  private final Selector cache;
   private final Schema schema;
   FieldCounter<String> languageMap;
   Map<String, SortedMap<String, Integer>> rawLanguageMap;
 
-  public Language(Schema schema, PathCache cache) {
+  public Language(Schema schema, Selector cache) {
     this.schema = schema;
     this.cache = cache;
   }

src/main/java/de/gwdg/metadataqa/api/calculator/language/Multilinguality.java

@@ -7,7 +7,7 @@
 import de.gwdg.metadataqa.api.json.DataElement;
 import de.gwdg.metadataqa.api.model.EdmFieldInstance;
 import de.gwdg.metadataqa.api.model.LanguageSaturationType;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 import de.gwdg.metadataqa.api.schema.Schema;
 import de.gwdg.metadataqa.api.util.Converter;
 import de.gwdg.metadataqa.api.util.SkippedEntitySelector;
@@ -36,7 +36,7 @@ public class Multilinguality {
   public static final String NORMALIZED = MultilingualitySaturationCalculator.CALCULATOR_NAME + ":normalized";
 
   private Schema schema;
-  private PathCache cache;
+  private Selector cache;
   private MultilingualitySaturationCalculator.ResultTypes resultType;
   private SkippedEntryChecker skippedEntryChecker;
   private SkippedEntitySelector skippedEntitySelector;
@@ -45,7 +45,7 @@ public class Multilinguality {
   Map<String, Map<String, Double>> rawScoreMap = new LinkedHashMap<>();
 
   public Multilinguality(Schema schema,
-                         PathCache cache,
+                         Selector cache,
                          MultilingualitySaturationCalculator.ResultTypes resultType,
                          SkippedEntryChecker skippedEntryChecker,
                          SkippedEntitySelector skippedEntitySelector) {

src/main/java/de/gwdg/metadataqa/api/interfaces/Calculator.java

@@ -1,6 +1,6 @@
 package de.gwdg.metadataqa.api.interfaces;
 
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 
 import java.io.Serializable;
 import java.util.List;
@@ -16,7 +16,7 @@ public interface Calculator extends Serializable {
    * @param cache
    *   The JSON cache object
    */
-  List<MetricResult> measure(PathCache cache);
+  List<MetricResult> measure(Selector cache);
 
   /**
    * Get header (the name of metrics) as a list.

src/main/java/de/gwdg/metadataqa/api/interfaces/Observer.java

@@ -1,7 +1,7 @@
 package de.gwdg.metadataqa.api.interfaces;
 
 import de.gwdg.metadataqa.api.counter.FieldCounter;
-import de.gwdg.metadataqa.api.model.pathcache.PathCache;
+import de.gwdg.metadataqa.api.model.selector.Selector;
 
 /**
  * Implementation of the Observer design pattern
@@ -21,7 +21,7 @@ public interface Observer {
    * @param results
    *   The result map
    */
-  void update(PathCache cache, FieldCounter<Double> results);
+  void update(Selector cache, FieldCounter<Double> results);
 
   /**
    * Get a header, which is the name of metric, the observer measures.