Refactoring TimeSeriesTypeSource and cleaning up CsvFileConnector

CHANGELOG.md

@@ -10,7 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - SQL time series sources (`SqlTimeSeriesSource` and `SqlTimeSeriesMappingSource`) [#467](https://github.com/ie3-institute/PowerSystemDataModel/issues/467)
 - SQL time series have a different structure than CSV counterparts [#545](https://github.com/ie3-institute/PowerSystemDataModel/issues/545)
 - Graph with impedance weighted edges including facilities to create it [#440](https://github.com/ie3-institute/PowerSystemDataModel/issues/440)
-- `TimeSeriesTypeSource` providing a source for the mapping of time series uuids to column schemes (previously provided by `TimeSeriesMappingSource`) [#515](https://github.com/ie3-institute/PowerSystemDataModel/issues/515)
+- `TimeSeriesMetaInformationSource` providing a source for the mapping of time series uuids to column schemes (previously provided by `TimeSeriesMappingSource`) [#515](https://github.com/ie3-institute/PowerSystemDataModel/issues/515)
 - `TemperatureDependantLoadProfile`s for depiction of profile behavior of night storage heating and heat pumps [#601](https://github.com/ie3-institute/PowerSystemDataModel/issues/601)
 - `ThermalUnits` as a container to hold all thermal units [#134](https://github.com/ie3-institute/PowerSystemDataModel/issues/134)
 - `ThermalInput` as a distinct abstract class for all thermal models
@@ -29,6 +29,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
     - Create JavaDoc with java 17 instead of java 8
     - Let JavDoc pass, if there are warnings **ATTENTION:** Should be removed, when JavaDoc is fixed! (cf. Issue [#494](https://github.com/ie3-institute/PowerSystemDataModel/issues/494))
 - `BufferedCsvWriter` writes columns in the order, that the headline elements are defined [#434](https://github.com/ie3-institute/PowerSystemDataModel/issues/393)
+-  Cleaned up `IndividualTimeSeriesMetaInformation`-related methods in `CsvFileConnector` [#544](https://github.com/ie3-institute/PowerSystemDataModel/issues/544)
 
 ### Changed
 - BREAKING: PvInput Model parameter name height changed to elevationAngle [#393](https://github.com/ie3-institute/PowerSystemDataModel/issues/393) :warning:

src/main/java/edu/ie3/datamodel/io/connectors/CsvFileConnector.java

@@ -22,6 +22,7 @@
 import java.nio.file.Path;
 import java.nio.file.Paths;
 import java.util.*;
+import java.util.function.Function;
 import java.util.stream.Collectors;
 import java.util.stream.Stream;
 import org.apache.commons.io.FilenameUtils;
@@ -42,8 +43,10 @@ public class CsvFileConnector implements DataConnector {
       new HashMap<>();
   private final Map<UUID, BufferedCsvWriter> timeSeriesWriters = new HashMap<>();
   // ATTENTION: Do not finalize. It's meant for lazy evaluation.
+  @Deprecated(since = "3.0", forRemoval = true)
   private Map<UUID, edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation>
       individualTimeSeriesMetaInformation;
+
   private final FileNamingStrategy fileNamingStrategy;
   private final String baseDirectoryName;
 
@@ -221,87 +224,45 @@ public BufferedReader initReader(String filePath) throws FileNotFoundException {
    *
    * @param timeSeriesUuid The time series in question
    * @return An option on the queried information
-   * @deprecated since 3.0. Use {@link #getIndividualTimeSeriesMetaInformation()} instead
+   * @deprecated since 3.0. Use {@link #getCsvIndividualTimeSeriesMetaInformation(ColumnScheme...)}
+   *     instead
    */
   @Deprecated(since = "3.0", forRemoval = true)
   public Optional<edu.ie3.datamodel.io.csv.timeseries.IndividualTimeSeriesMetaInformation>
       getIndividualTimeSeriesMetaInformation(UUID timeSeriesUuid) {
     if (Objects.isNull(individualTimeSeriesMetaInformation))
-      individualTimeSeriesMetaInformation = buildIndividualTimeSeriesMetaInformation();
+      individualTimeSeriesMetaInformation = getCsvIndividualTimeSeriesMetaInformation();
 
     return Optional.ofNullable(individualTimeSeriesMetaInformation.get(timeSeriesUuid))
         .map(edu.ie3.datamodel.io.csv.timeseries.IndividualTimeSeriesMetaInformation::new);
   }
 
   /**
-   * Get time series meta information
-   *
-   * <p>This method lazily evaluates the mapping from <i>all</i> time series files to their meta
-   * information.
+   * Receive the information for specific time series. They are given back filtered by the column
+   * scheme in order to allow for accounting the different content types.
    *
-   * @return All time series meta information
+   * @param columnSchemes the column schemes to initialize readers for. If no scheme is given, all
+   *     possible readers will be initialized.
+   * @return A mapping from column scheme to the individual time series meta information
    */
   public Map<UUID, edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation>
-      getIndividualTimeSeriesMetaInformation() {
-    if (Objects.isNull(individualTimeSeriesMetaInformation))
-      individualTimeSeriesMetaInformation = buildIndividualTimeSeriesMetaInformation();
-
-    return individualTimeSeriesMetaInformation;
-  }
-
-  /**
-   * This method creates a map from time series uuid to it's meta information.
-   *
-   * @return Mapping from time series uuid to it's meta information.
-   */
-  private Map<UUID, edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation>
-      buildIndividualTimeSeriesMetaInformation() {
+      getCsvIndividualTimeSeriesMetaInformation(final ColumnScheme... columnSchemes) {
     return getIndividualTimeSeriesFilePaths().parallelStream()
         .map(
             filePath -> {
               /* Extract meta information from file path and enhance it with the file path itself */
-              String filePathWithoutEnding = removeFileEnding(filePath);
               IndividualTimeSeriesMetaInformation metaInformation =
-                  (IndividualTimeSeriesMetaInformation)
-                      fileNamingStrategy.timeSeriesMetaInformation(filePathWithoutEnding);
+                  fileNamingStrategy.individualTimeSeriesMetaInformation(filePath);
               return new edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation(
-                  metaInformation, filePathWithoutEnding);
-            })
-        .collect(Collectors.toMap(TimeSeriesMetaInformation::getUuid, v -> v));
-  }
-
-  /**
-   * Receive the information for specific time series. They are given back grouped by the column
-   * scheme in order to allow for accounting the different content types.
-   *
-   * @param columnSchemes the column schemes to initialize readers for. If no scheme is given, all
-   *     possible readers will be initialized.
-   * @return A mapping from column scheme to the individual time series meta information
-   */
-  public Map<ColumnScheme, Set<edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation>>
-      getCsvIndividualTimeSeriesMetaInformation(ColumnScheme... columnSchemes) {
-    return getIndividualTimeSeriesFilePaths().parallelStream()
-        .map(
-            pathString -> {
-              String filePathWithoutEnding = removeFileEnding(pathString);
-              return buildCsvTimeSeriesMetaInformation(filePathWithoutEnding, columnSchemes);
+                  metaInformation, FileNamingStrategy.removeFileNameEnding(filePath));
             })
-        .filter(Optional::isPresent)
-        .map(Optional::get)
-        .collect(
-            Collectors.groupingBy(
-                edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation::getColumnScheme,
-                Collectors.toSet()));
-  }
-
-  /**
-   * Removes the file ending from input string
-   *
-   * @param input String to manipulate
-   * @return input without possible ending
-   */
-  private String removeFileEnding(String input) {
-    return input.replaceAll(FILE_ENDING + "$", "");
+        .filter(
+            metaInformation ->
+                columnSchemes == null
+                    || columnSchemes.length == 0
+                    || Stream.of(columnSchemes)
+                        .anyMatch(scheme -> scheme.equals(metaInformation.getColumnScheme())))
+        .collect(Collectors.toMap(TimeSeriesMetaInformation::getUuid, Function.identity()));
   }
 
   /**
@@ -320,7 +281,7 @@ private Set<String> getIndividualTimeSeriesFilePaths() {
           .map(baseDirectoryPath::relativize)
           .filter(
               path -> {
-                String withoutEnding = removeFileEnding(path.toString());
+                String withoutEnding = FileNamingStrategy.removeFileNameEnding(path.toString());
                 return fileNamingStrategy
                     .getIndividualTimeSeriesPattern()
                     .matcher(withoutEnding)
@@ -334,55 +295,6 @@ private Set<String> getIndividualTimeSeriesFilePaths() {
     }
   }
 
-  /**
-   * Compose the needed information for reading in a single time series. If the file points to a
-   * non-individual time series or a time series of a column scheme other than the specified ones,
-   * or the initialisation of the reader does not work, an empty {@link Optional} is given back
-   *
-   * @param filePathString String describing the path to the time series file
-   * @param columnSchemes the allowed column schemes. If no scheme is specified, all schemes are
-   *     allowed.
-   * @return An {@link Optional} to {@link IndividualTimeSeriesMetaInformation}
-   */
-  private Optional<edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation>
-      buildCsvTimeSeriesMetaInformation(String filePathString, ColumnScheme... columnSchemes) {
-    try {
-      TimeSeriesMetaInformation metaInformation =
-          fileNamingStrategy.timeSeriesMetaInformation(filePathString);
-      if (!IndividualTimeSeriesMetaInformation.class.isAssignableFrom(metaInformation.getClass())) {
-        log.error(
-            "The time series file '{}' does not represent an individual time series.",
-            filePathString);
-        return Optional.empty();
-      }
-
-      IndividualTimeSeriesMetaInformation individualMetaInformation =
-          (IndividualTimeSeriesMetaInformation) metaInformation;
-
-      // If no column schemes are specified, we will include all. If there a specified schemes, we
-      // check if the file's column scheme matches any of them
-      if (columnSchemes != null
-          && columnSchemes.length > 0
-          && Stream.of(columnSchemes)
-              .noneMatch(scheme -> scheme.equals(individualMetaInformation.getColumnScheme()))) {
-        log.warn(
-            "The column scheme of the time series file {} does not match any of the specified column schemes ({}), so it will not be processed.",
-            filePathString,
-            columnSchemes);
-        return Optional.empty();
-      }
-      return Optional.of(
-          new edu.ie3.datamodel.io.csv.CsvIndividualTimeSeriesMetaInformation(
-              individualMetaInformation.getUuid(),
-              individualMetaInformation.getColumnScheme(),
-              filePathString));
-    } catch (IllegalArgumentException e) {
-      log.error(
-          "Error during extraction of meta information from file name '{}'.", filePathString, e);
-      return Optional.empty();
-    }
-  }
-
   /**
    * Initialises a reader to get grip on the file that contains mapping information between
    * coordinate id and actual coordinate

src/main/java/edu/ie3/datamodel/io/factory/timeseries/TimeSeriesTypeFactory.java → src/main/java/edu/ie3/datamodel/io/factory/timeseries/TimeSeriesMetaInformationFactory.java

@@ -8,7 +8,7 @@
 import edu.ie3.datamodel.io.factory.EntityFactory;
 import edu.ie3.datamodel.io.factory.SimpleEntityData;
 import edu.ie3.datamodel.io.naming.timeseries.ColumnScheme;
-import edu.ie3.datamodel.io.source.TimeSeriesTypeSource;
+import edu.ie3.datamodel.io.naming.timeseries.IndividualTimeSeriesMetaInformation;
 import java.util.Collections;
 import java.util.List;
 import java.util.Set;
@@ -17,15 +17,16 @@
 import java.util.stream.Stream;
 
 /**
- * Factory that creates {@link TimeSeriesTypeSource.TypeEntry} entities from source field mappings
+ * Factory that creates {@link IndividualTimeSeriesMetaInformation} entities from source field
+ * mappings
  */
-public class TimeSeriesTypeFactory
-    extends EntityFactory<TimeSeriesTypeSource.TypeEntry, SimpleEntityData> {
+public class TimeSeriesMetaInformationFactory
+    extends EntityFactory<IndividualTimeSeriesMetaInformation, SimpleEntityData> {
   private static final String TIME_SERIES = "timeSeries";
   private static final String COLUMN_SCHEME = "columnScheme";
 
-  public TimeSeriesTypeFactory() {
-    super(TimeSeriesTypeSource.TypeEntry.class);
+  public TimeSeriesMetaInformationFactory() {
+    super(IndividualTimeSeriesMetaInformation.class);
   }
 
   @Override
@@ -35,9 +36,9 @@ protected List<Set<String>> getFields(SimpleEntityData data) {
   }
 
   @Override
-  protected TimeSeriesTypeSource.TypeEntry buildModel(SimpleEntityData data) {
+  protected IndividualTimeSeriesMetaInformation buildModel(SimpleEntityData data) {
     UUID timeSeries = data.getUUID(TIME_SERIES);
     ColumnScheme columnScheme = ColumnScheme.parse(data.getField(COLUMN_SCHEME)).orElseThrow();
-    return new TimeSeriesTypeSource.TypeEntry(timeSeries, columnScheme);
+    return new IndividualTimeSeriesMetaInformation(timeSeries, columnScheme);
   }
 }

src/main/java/edu/ie3/datamodel/io/naming/FileNamingStrategy.java

@@ -274,7 +274,7 @@ public FileNameMetaInformation extractTimeSeriesMetaInformation(String fileName)
    */
   public TimeSeriesMetaInformation timeSeriesMetaInformation(String fileName) {
     /* Remove the file ending (ending limited to 255 chars, which is the max file name allowed in NTFS and ext4) */
-    String withoutEnding = fileName.replaceAll("(?:\\.[^\\\\/\\s]{1,255}){1,2}$", "");
+    String withoutEnding = removeFileNameEnding(fileName);
 
     if (getIndividualTimeSeriesPattern().matcher(withoutEnding).matches())
       return entityPersistenceNamingStrategy.individualTimesSeriesMetaInformation(withoutEnding);
@@ -285,6 +285,15 @@ else if (getLoadProfileTimeSeriesPattern().matcher(withoutEnding).matches())
           "Unknown format of '" + fileName + "'. Cannot extract meta information.");
   }
 
+  public IndividualTimeSeriesMetaInformation individualTimeSeriesMetaInformation(String fileName) {
+    return entityPersistenceNamingStrategy.individualTimesSeriesMetaInformation(
+        removeFileNameEnding(fileName));
+  }
+
+  public static String removeFileNameEnding(String fileName) {
+    return fileName.replaceAll("(?:\\.[^.\\\\/\\s]{1,255}){1,2}$", "");
+  }
+
   /**
    * Get the entity name for coordinates
    *

src/main/java/edu/ie3/datamodel/io/naming/TimeSeriesMetaInformation.java

@@ -5,35 +5,13 @@
 */
 package edu.ie3.datamodel.io.naming;
 
-import java.util.Objects;
+import edu.ie3.datamodel.models.input.InputEntity;
 import java.util.UUID;
 
 /** Meta information, that describe a certain data source */
-public abstract class TimeSeriesMetaInformation {
-  private final UUID uuid;
+public abstract class TimeSeriesMetaInformation extends InputEntity {
 
   protected TimeSeriesMetaInformation(UUID uuid) {
-    this.uuid = uuid;
-  }
-
-  public UUID getUuid() {
-    return uuid;
-  }
-
-  @Override
-  public boolean equals(Object o) {
-    if (this == o) return true;
-    if (!(o instanceof TimeSeriesMetaInformation that)) return false;
-    return uuid.equals(that.uuid);
-  }
-
-  @Override
-  public int hashCode() {
-    return Objects.hash(uuid);
-  }
-
-  @Override
-  public String toString() {
-    return "TimeSeriesMetaInformation{" + "uuid=" + uuid + '}';
+    super(uuid);
   }
 }

src/main/java/edu/ie3/datamodel/io/source/TimeSeriesMappingSource.java

@@ -38,7 +38,8 @@ default Optional<UUID> getTimeSeriesUuid(UUID modelIdentifier) {
    *
    * @param timeSeriesUuid Unique identifier of the time series in question
    * @return An Option onto the meta information
-   * @deprecated since 3.0. Use {@link TimeSeriesTypeSource#getTimeSeriesMetaInformation()} instead
+   * @deprecated since 3.0. Use {@link
+   *     TimeSeriesMetaInformationSource#getTimeSeriesMetaInformation()} instead
    */
   @Deprecated(since = "3.0", forRemoval = true)
   Optional<edu.ie3.datamodel.io.csv.timeseries.IndividualTimeSeriesMetaInformation>

src/main/java/edu/ie3/datamodel/io/source/TimeSeriesMetaInformationSource.java

@@ -0,0 +1,32 @@
+/*
+ * © 2022. TU Dortmund University,
+ * Institute of Energy Systems, Energy Efficiency and Energy Economics,
+ * Research group Distribution grid planning and operation
+*/
+package edu.ie3.datamodel.io.source;
+
+import edu.ie3.datamodel.io.naming.timeseries.ColumnScheme;
+import edu.ie3.datamodel.io.naming.timeseries.IndividualTimeSeriesMetaInformation;
+import java.util.Map;
+import java.util.Optional;
+import java.util.UUID;
+
+/** Source for all available time series with their {@link UUID} and {@link ColumnScheme} */
+public interface TimeSeriesMetaInformationSource extends DataSource {
+
+  /**
+   * Get a mapping from time series {@link UUID} to its meta information {@link
+   * IndividualTimeSeriesMetaInformation}
+   *
+   * @return that mapping
+   */
+  Map<UUID, IndividualTimeSeriesMetaInformation> getTimeSeriesMetaInformation();
+
+  /**
+   * Get an option on the given time series meta information
+   *
+   * @param timeSeriesUuid Unique identifier of the time series in question
+   * @return An Option on the meta information
+   */
+  Optional<IndividualTimeSeriesMetaInformation> getTimeSeriesMetaInformation(UUID timeSeriesUuid);
+}