Formatter: enable to select multiple identifiers and save records as …

…MARCXML #558

README.md

@@ -1100,7 +1100,10 @@ or with a bash script
 
 options:
 * [general parameters](#general-parameters)
-* `-f`, `--format`: the name of the format (at time of writing there is no any)
+* `-f`, `--format`: the MARC output format
+  * if not set, the output format follows the examples in the MARC21 
+    documentation (see the example below)
+  * `xml`: the output will be MARCXML
 * `-c <number>`, `-countNr <number>`: count number of the record (e.g. 1 means
   the first record)
 * `-s [path=query]`, `-search [path=query]`: print records matching the query.
@@ -1118,6 +1121,8 @@ options:
   (default: TAB)
 * `-e <file>`, `--fileName <file>`: the name of report the program produces
   (default: `extracted.csv`)
+* `-A <identifiers>`, `--ids <identifiers>`: a comma separated list of record 
+  identifiers 
 
 The output of displaying a single MARC record is something like this one:
 
@@ -1823,6 +1828,7 @@ options:
   with `_txt`). \[This parameter is available from v0.8.0\]
 * `-D <int>`, `--commitAt <int>`: commit index after this number of records \[This parameter is available from v0.8.0\]
 * `-E`, `--indexFieldCounts`: index the count of field instances \[This parameter is available from v0.8.0\]
+* `-G`, `--indexSubfieldCounts`: index the count of subfield instances \[This parameter is available from v0.8.0\]
 * `-F`, `--fieldPrefix <arg>`: field prefix
 
 The `./index` file (which is used by `catalogues/[catalogue].sh` and `./qa-catalogue` scripts) has additional parameters:

src/main/java/de/gwdg/metadataqa/marc/cli/Formatter.java

@@ -15,10 +15,15 @@
 import org.apache.commons.cli.Options;
 import org.apache.commons.cli.ParseException;
 import org.apache.commons.lang3.StringUtils;
+import org.marc4j.MarcException;
+import org.marc4j.MarcXmlWriter;
 import org.marc4j.marc.Record;
 
 import java.io.BufferedWriter;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
 import java.io.IOException;
+import java.io.OutputStream;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.nio.file.Paths;
@@ -40,6 +45,7 @@ public class Formatter implements BibliographicInputProcessor {
   private final FormatterParameters parameters;
   private final boolean readyToProcess;
   private BufferedWriter writer;
+  private MarcXmlWriter marcXmlWriter;
 
   public Formatter(String[] args) throws ParseException {
     parameters = new FormatterParameters(args);
@@ -103,6 +109,18 @@ public void beforeIteration() {
         logger.log(Level.WARNING, "beforeIteration", e);
       }
     }
+    if (parameters.getIds() != null && !parameters.getIds().isEmpty()
+        && parameters.getFormat().equals("xml")) {
+      var path = Paths.get(parameters.getOutputDir(), parameters.getFileName());
+      logger.info("path: " + path.toAbsolutePath());
+      try {
+        // outputStream = new FileOutputStream(path.toFile());
+        marcXmlWriter = new MarcXmlWriter(new FileOutputStream(path.toFile()));
+        marcXmlWriter.setIndent(true);
+      } catch (FileNotFoundException e) {
+        logger.log(Level.WARNING, "beforeIteration", e);
+      }
+    }
   }
 
   @Override
@@ -112,15 +130,28 @@ public void fileOpened(Path file) {
 
   @Override
   public void processRecord(Record marc4jRecord, int recordNumber) throws IOException {
-    boolean hasSpecifiedId = parameters.hasId() &&
-      marc4jRecord.getControlNumber() != null &&
-      marc4jRecord.getControlNumber().trim().equals(parameters.getId());
+    String id = marc4jRecord.getControlNumber() != null ?
+      marc4jRecord.getControlNumber().trim() : null;
+
+    boolean hasSpecifiedId = parameters.hasId() && id != null && id.equals(parameters.getId());
+
+    if (!hasSpecifiedId)
+      hasSpecifiedId = id != null
+                       && parameters.getIds() != null
+                       && !parameters.getIds().isEmpty()
+                       && parameters.getIds().contains(id);
 
     boolean hasSpecifiedRecordNumber = parameters.getCountNr() > -1
       && parameters.getCountNr() == recordNumber;
 
     if (hasSpecifiedId || hasSpecifiedRecordNumber) {
-      logger.info(marc4jRecord::toString);
+      if (parameters.getFormat().equals("xml")) {
+        marcXmlWriter.write(marc4jRecord);
+        // MarcXmlWriter.writeSingleRecord(marc4jRecord, System.out, true);
+        // MarcXmlWriter.writeSingleRecord(marc4jRecord, outputStream, true);
+      } else {
+        logger.info(marc4jRecord::toString);
+      }
     }
   }
 
@@ -135,7 +166,6 @@ public void processRecord(BibliographicRecord marcRecord, int recordNumber) thro
       for (DataField field : marcRecord.getDatafields()) {
        logger.info(field.getTag());
       }
-      logger.info(() -> "has STA: " + marcRecord.hasDatafield("STA"));
     }
 
     if (parameters.hasSearch()) {
@@ -174,15 +204,20 @@ public void fileProcessed() {
 
   @Override
   public void afterIteration(int numberOfprocessedRecords, long duration) {
-    if (writer == null) {
-      return;
-    }
 
-    try {
-      writer.close();
-    } catch (IOException e) {
-      logger.log(Level.SEVERE, "afterIteration", e);
-    }
+    if (writer != null)
+      try {
+        writer.close();
+      } catch (IOException e) {
+        logger.log(Level.SEVERE, "afterIteration", e);
+      }
+
+    if (marcXmlWriter != null)
+      try {
+        marcXmlWriter.close();
+      } catch (MarcException e) {
+        logger.log(Level.SEVERE, "afterIteration", e);
+      }
   }
 
   private List<String> selectPicaResults(PicaRecord picaRecord) {

src/main/java/de/gwdg/metadataqa/marc/cli/parameters/FormatterParameters.java

@@ -22,6 +22,7 @@ public class FormatterParameters extends CommonParameters {
   private boolean withId = false;
   private String separator = "\t";
   private String fileName = DEFAULT_FILE_NAME;
+  private List<String> ids;
 
   private boolean isOptionSet = false;
 
@@ -35,6 +36,7 @@ protected void setOptions() {
       options.addOption("l", "selector", true, "selectors");
       options.addOption("w", "withId", false, "the generated CSV should contain record ID as first field");
       options.addOption("p", "separator", true, "separator between the parts (default: TAB)");
+      options.addOption("A", "ids", true, "list of identifiers separated by comma");
       options.addOption("e", "fileName", true, String.format("output file (default: %s)", DEFAULT_FILE_NAME));
       isOptionSet = true;
     }
@@ -80,6 +82,10 @@ public FormatterParameters(String[] arguments) throws ParseException {
 
     if (cmd.hasOption("fileName"))
       fileName = cmd.getOptionValue("fileName");
+
+    if (cmd.hasOption("ids")) {
+      ids = List.of(cmd.getOptionValue("ids").split(","));
+    }
   }
 
   public String getFormat() {
@@ -126,6 +132,10 @@ public String getFileName() {
     return fileName;
   }
 
+  public List<String> getIds() {
+    return ids;
+  }
+
   @Override
   public String formatParameters() {
     String text = super.formatParameters();
@@ -135,6 +145,7 @@ public String formatParameters() {
     text += String.format("withId: %s%n", withId);
     text += String.format("separator: %s%n", separator);
     text += String.format("outputFile: %s%n", fileName);
+    text += String.format("ids: %s%n", StringUtils.join(ids, ", "));
     return text;
   }