-
Notifications
You must be signed in to change notification settings - Fork 18
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
issue #142: calculating PICA completeness
- Loading branch information
Showing
9 changed files
with
126 additions
and
24 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
2 changes: 2 additions & 0 deletions
2
src/main/java/de/gwdg/metadataqa/marc/cli/plugin/CompletenessPlugin.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,7 +1,9 @@ | ||
| package de.gwdg.metadataqa.marc.cli.plugin; | ||
|
|
||
| import de.gwdg.metadataqa.marc.dao.MarcRecord; | ||
| import de.gwdg.metadataqa.marc.utils.TagHierarchy; | ||
|
|
||
| public interface CompletenessPlugin { | ||
| String getDocumentType(MarcRecord marcRecord); | ||
| TagHierarchy getTagHierarchy(String path); | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
69 changes: 65 additions & 4 deletions
69
src/main/java/de/gwdg/metadataqa/marc/cli/plugin/PicaCompletenessPlugin.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,24 +1,85 @@ | ||
| package de.gwdg.metadataqa.marc.cli.plugin; | ||
|
|
||
| import de.gwdg.metadataqa.marc.Utils; | ||
| import de.gwdg.metadataqa.marc.cli.parameters.CompletenessParameters; | ||
| import de.gwdg.metadataqa.marc.dao.MarcRecord; | ||
| import de.gwdg.metadataqa.marc.definition.structure.SubfieldDefinition; | ||
| import de.gwdg.metadataqa.marc.definition.tags.TagCategory; | ||
| import de.gwdg.metadataqa.marc.utils.TagHierarchy; | ||
| import de.gwdg.metadataqa.marc.utils.pica.FieldPath; | ||
| import de.gwdg.metadataqa.marc.utils.pica.PicaFieldDefinition; | ||
| import de.gwdg.metadataqa.marc.utils.pica.PicaSchemaReader; | ||
| import org.apache.commons.lang3.StringUtils; | ||
|
|
||
| import java.nio.file.Paths; | ||
| import java.util.Map; | ||
| import java.util.regex.Pattern; | ||
|
|
||
| public class PicaCompletenessPlugin implements CompletenessPlugin { | ||
| private final CompletenessParameters parameters; | ||
| private final String field; | ||
| private final String subfield; | ||
| private final String separator; | ||
| private final Map<String, PicaFieldDefinition> picaSchema; | ||
| private final static Map<String, String> types = Map.ofEntries( | ||
| Map.entry("A", "Druckschriften (einschließlich Bildbänden)"), | ||
| Map.entry("B", "Tonträger, Videodatenträger, Bildliche Darstellungen"), | ||
| Map.entry("C", "Blindenschriftträger und andere taktile Materialien"), | ||
| Map.entry("E", "Mikroform"), | ||
| Map.entry("H", "Handschriftliches Material"), | ||
| Map.entry("L", "Lokales Katalogisat (nur GBV)"), | ||
| Map.entry("O", "Elektronische Ressource im Fernzugriff"), | ||
| Map.entry("S", "Elektronische Ressource auf Datenträger"), | ||
| Map.entry("V", "Objekt"), | ||
| Map.entry("Z", "Medienkombination"), | ||
| Map.entry("a", "Mailboxsatz") | ||
| ); | ||
|
|
||
| public PicaCompletenessPlugin(CompletenessParameters parameters) { | ||
| this.parameters = parameters; | ||
| String[] parts = parameters.getPicaRecordTypeField().split(Pattern.quote(parameters.getPicaSubfieldSeparator())); | ||
| field = parts[0]; | ||
| subfield = parts[1]; | ||
| separator = Pattern.quote(parameters.getPicaSubfieldSeparator()); | ||
| FieldPath path = parse(parameters.getPicaRecordTypeField()); | ||
| // String[] parts = parameters.getPicaRecordTypeField().split(Pattern.quote(parameters.getPicaSubfieldSeparator())); | ||
| field = path.getField(); | ||
| subfield = path.getSubfield(); | ||
| String schemaFile = StringUtils.isNotEmpty(parameters.getPicaSchemaFile()) | ||
| ? parameters.getPicaSchemaFile() | ||
| : Paths.get("src/main/resources/pica/avram-k10plus.json").toAbsolutePath().toString(); | ||
| picaSchema = PicaSchemaReader.create(schemaFile); | ||
|
|
||
| } | ||
|
|
||
| @Override | ||
| public String getDocumentType(MarcRecord marcRecord) { | ||
| return marcRecord.getDatafield(field).get(0).getSubfield(subfield).get(0).getValue(); | ||
| String code = marcRecord.getDatafield(field).get(0).getSubfield(subfield).get(0).getValue().substring(0, 1); | ||
| return types.getOrDefault(code, "invalid"); | ||
| } | ||
|
|
||
| @Override | ||
| public TagHierarchy getTagHierarchy(String rawpath) { | ||
| FieldPath path = parse(rawpath); | ||
| String fieldLabel = ""; | ||
| String subfieldLabel = ""; | ||
| PicaFieldDefinition field = picaSchema.get(path.getField()); | ||
| TagCategory category = TagCategory.other; | ||
| if (field != null) { | ||
| category = TagCategory.pica; | ||
| fieldLabel = field.getLabel(); | ||
| if (!path.getSubfield().equals("")){ | ||
| SubfieldDefinition subfield = field.getSubfield(path.getSubfield()); | ||
| subfieldLabel = subfield != null ? subfield.getLabel() : ""; | ||
| } | ||
| } | ||
|
|
||
| return new TagHierarchy(category, fieldLabel, subfieldLabel); | ||
| } | ||
|
|
||
| private FieldPath parse(String path) { | ||
| String[] parts = path.split(separator); | ||
| if (parts.length == 1) { | ||
| System.err.println("problem with path: " + path); | ||
| return new FieldPath(parts[0], ""); | ||
| } | ||
| return new FieldPath(parts[0], parts[1]); | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
19 changes: 19 additions & 0 deletions
19
src/main/java/de/gwdg/metadataqa/marc/utils/pica/FieldPath.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,19 @@ | ||
| package de.gwdg.metadataqa.marc.utils.pica; | ||
|
|
||
| public class FieldPath { | ||
| String field; | ||
| String subfield; | ||
|
|
||
| public FieldPath(String field, String subfield) { | ||
| this.field = field; | ||
| this.subfield = subfield; | ||
| } | ||
|
|
||
| public String getField() { | ||
| return field; | ||
| } | ||
|
|
||
| public String getSubfield() { | ||
| return subfield; | ||
| } | ||
| } |