I am refactoring a legacy codebase to use spring. I am newish to spring and was wondering if you have any suggestions for the following code I refactored. Specifically about providing the ExpeditionEntitiesService.
Here is a REST service which uploads a file:
public class myRestService {
@POST
public Response upload(//params) {
// do work
ExpeditionEntities expeditionEntities = expeditionService.getExpeditionEntities(processController.getExpeditionId());
ExpeditionEntitiesService expeditionEntitiesService = new ExpeditionEntitiesService(expeditionEntities, processController, bcidService, expeditionService);
// run the triplifier
Triplifier triplifier = new Triplifier(outputPrefix, uploadPath(), processController, expeditionEntitiesService);
boolean runDeepRoots = Boolean.valueOf(settingsManager.retrieveValue("deepRoots"));
triplifier.run(processController.getValidation().getSqliteFile());
// more work
}
}
The next class is used to convert the file to triples to be stored in Apache fuseki TBD:
public class Triplifier {
public Connection connection;
private String outputFolder;
private Model model;
private String tripleOutputFile;
private String filenamePrefix;
private ProcessController processController;
private final ExpeditionEntitiesService expeditionEntitiesService;
private static Logger logger = LoggerFactory.getLogger(Triplifier.class);
/**
* triplify dataset on the tabularDataReader, writing output to the specified outputFolder and filenamePrefix
*
* @param filenamePrefix
* @param outputFolder
*/
public Triplifier(String filenamePrefix, String outputFolder,
ProcessController processController, ExpeditionEntitiesService expeditionEntitiesService) {
this.outputFolder = outputFolder;
this.filenamePrefix = filenamePrefix;
this.processController = processController;
this.expeditionEntitiesService = expeditionEntitiesService;
}
public String getOutputFolder() {return outputFolder;}
public String getFilenamePrefix() {return filenamePrefix;}
public Model getModel() {return model;}
public String getTripleOutputFile() {return tripleOutputFile;}
/**
* Return triples
*
* @return
*/
private void getTriples() {
System.gc();
String status = "\tWriting Temporary Output ...";
processController.appendStatus(status + "<br>");
// Write the model
model = new ModelD2RQ(FileUtils.toURL(getMapping()),
FileUtils.langN3, "urn:x-biscicol:");
model.setNsPrefix("ark", "http://ezid.cdlib.org/id/ark");
// Write the model as simply a Turtle file
File tripleFile = PathManager.createUniqueFile(filenamePrefix + ".n3", outputFolder);
try {
FileOutputStream fos = new FileOutputStream(tripleFile);
model.write(fos, FileUtils.langNTriple, null);
fos.close();
} catch (FileNotFoundException e) {
throw new FimsRuntimeException(500, e);
} catch (IOException e) {
logger.warn("IOException thrown trying to close FileOutputStream object.", e);
}
tripleOutputFile = outputFolder + File.separator + tripleFile.getName();
if (tripleFile.length() < 1)
throw new FimsRuntimeException("No triples to write!", 500);
}
/**
* Construct the mapping file for D2RQ to read
*
* @return
*/
private String getMapping() {
connection.verifyFile();
File mapFile = PathManager.createUniqueFile(filenamePrefix + ".mapping.n3", outputFolder);
try {
PrintWriter pw = new PrintWriter(mapFile);
TabularDataReader tdr = processController.getValidation().getTabularDataReader();
Mapping mapping = processController.getMapping();
new D2RQPrinter(pw, connection, expeditionEntitiesService).printD2RQ(tdr.getColNames(), mapping);
pw.close();
} catch (FileNotFoundException e) {
throw new FimsRuntimeException(500, e);
}
return outputFolder + File.separator + mapFile.getName();
}
/**
* Run the triplifier using this class
*/
public boolean run(File sqlLiteFile) {
String status = "Converting Data Format ...";
processController.appendStatus(status + "<br>");
this.connection = new Connection(sqlLiteFile);
getTriples();
return true;
}
}
The next class is used by the Triplifier to generate the mapping file used to create the triples:
public class D2RQPrinter {
private PrintWriter pw;
private Connection connection;
private final ExpeditionEntitiesService expeditionEntitiesService;
public D2RQPrinter(PrintWriter pw, Connection connection, ExpeditionEntitiesService expeditionEntitiesService) {
this.pw = pw;
this.connection = connection;
this.expeditionEntitiesService = expeditionEntitiesService;
}
/**
* Generate D2RQ Mapping Language representation of this Mapping's connection, entities and relations.
*/
public void printD2RQ(List<String> colNames, Mapping mapping) {
printPrefixes();
printConnectionD2RQ();
for (Entity entity : mapping.getEntities())
printEntityD2RQ(entity, colNames);
for (Relation relation : mapping.getRelations()) {
printRelationD2RQ(relation, mapping);
}
}
/**
* Generate D2RQ Mapping Language representation of this Relation.
*
*/
public void printRelationD2RQ(Relation relation, Mapping mapping) {
Entity subjEntity = mapping.findEntity(relation.getSubject());
Entity objEntity = mapping.findEntity(relation.getObject());
if (subjEntity == null || objEntity == null)
return;
String subjClassMap = getClassMap(subjEntity);
String objClassMap = getClassMap(objEntity);
pw.println("map:" + subjClassMap + "_" + objClassMap + "_rel" + " a d2rq:PropertyBridge;");
pw.println("\td2rq:belongsToClassMap " + "map:" + subjClassMap + ";");
pw.println("\td2rq:property <" + relation.getPredicate() + ">;");
pw.println(getPersistentIdentifierMapping(objEntity));
pw.println("\td2rq:condition \"" + objEntity.getWorksheetUniqueKey() + " <> ''\";");
pw.println("\t.");
}
/**
* Generate D2RQ Mapping Language ClassMap name for a given Entity.
*
* @return D2RQ Mapping ClassMap name.
*/
private String getClassMap(Entity entity) {
return entity.getWorksheet() + "_" + entity.getWorksheetUniqueKey() + "_" + entity.getConceptAlias();
}
/**
* Generate D2RQ Mapping Language representation of this Entity with Attributes.
*/
private void printEntityD2RQ(Entity entity, List<String> colNames) {
pw.println("map:" + getClassMap(entity) + " a d2rq:ClassMap;");
pw.println("\td2rq:dataStorage " + "map:database;");
pw.println(getPersistentIdentifierMapping(entity));
pw.println("\td2rq:class <" + entity.getConceptURI() + ">;");
// ensures non-null values ... don't apply if this is a hash
if (!entity.getColumn().contains("hash"))
pw.println("\td2rq:condition \"" + entity.getColumn() + " <> ''\";");
// TODO: add in extra conditions (May not be necessary)
//pw.println(getExtraConditions());
pw.println("\t.");
// Get a list of colNames that we know are good from the spreadsheet
// Normalize the column names so they can be mapped according to how they appear in SQLite
ArrayList<String> normalizedColNames = new ArrayList<String>();
Iterator it = colNames.iterator();
while (it.hasNext()) {
String colName = (String) it.next();
normalizedColNames.add(colName.replace(" ", "_").replace("/", ""));
}
// Loop through attributes associated with this Entity
if (entity.getAttributes().size() > 0) {
for (Attribute attribute : entity.getAttributes())
printAttributeD2RQ(attribute, entity, normalizedColNames);
}
}
/**
* * Generate D2RQ Mapping Language representation of this Attribute.
*
* @param parent
* @param colNames
*/
private void printAttributeD2RQ(Attribute attribute, Entity parent, List<String> colNames) {
String classMap = getClassMap(parent);
String table = parent.getWorksheet();
String classMapStringEquivalence = "";
Boolean runColumn = false;
if (colNames.contains(attribute.getColumn())) {
runColumn = true;
}
// Only print this column if it is in a list of colNames
if (runColumn) {
String classMapString = "map:" + classMap + "_" + attribute.getColumn();
pw.println(classMapString + " a d2rq:PropertyBridge;");
pw.println("\td2rq:belongsToClassMap " + "map:" + classMap + ";");
pw.println("\td2rq:property <" + attribute.getUri() + ">;");
pw.println("\td2rq:column \"" + table + "." + attribute.getColumn() + "\";");
pw.println("\td2rq:condition \"" + table + "." + attribute.getColumn() + " <> ''\";");
// Specify an equivalence, which is isDefinedBy
classMapStringEquivalence = classMapString + "_Equivalence";
pw.println("\td2rq:additionalPropertyDefinitionProperty " + classMapStringEquivalence + ";");
pw.println("\t.");
// Always use isDefinedBy, even if the user has not expressed it explicitly. We do this by
// using the uri value if NO isDefinedBy is expressed.
pw.println(classMapStringEquivalence + " a d2rq:AdditionalProperty;");
pw.println("\td2rq:propertyName <" + attribute.getIsDefinedByURIString() + ">;");
if (attribute.getDefined_by()!= null) {
pw.println("\td2rq:propertyValue <" + attribute.getDefined_by() + ">;");
} else {
pw.println("\td2rq:propertyValue <" + attribute.getUri() + ">;");
}
pw.println("\t.");
/*
Loop multi-value columns
This is used when the Configuration file indicates an attribute that should be composed of more than one column
*/
} else if (attribute.getColumn().contains(",")) {
// TODO: clean this up and integrate with above code.
String tempColumnName = attribute.getColumn().replace(",", "");
String[] columns = attribute.getColumn().split(",");
// Check if we should run this -- all columns need to be present in colNames list
Boolean runMultiValueColumn = true;
for (int i = 0; i < columns.length; i++) {
if (!colNames.contains(columns[i])) {
runMultiValueColumn = false;
}
}
// Only run this portion if the tempColumnName appears
if (runMultiValueColumn) {
String classMapString = "map:" + classMap + "_" + tempColumnName;
pw.println(classMapString + " a d2rq:PropertyBridge;");
pw.println("\td2rq:belongsToClassMap " + "map:" + classMap + ";");
pw.println("\td2rq:property <" + attribute.getUri() + ">;");
// Construct SQL Expression
StringBuilder result = new StringBuilder();
// Call this a sqlExpression
result.append("\td2rq:sqlExpression \"");
// Append ALL columns together using the delimiter... ALL are required
if (attribute.getType().equals("all")) {
for (int i = 0; i < columns.length; i++) {
if (i != 0)
result.append(" || '" + attribute.getDelimited_by() + "' || ");
// Set required function parameters
if (attribute.getType().equals("all"))
pw.println("\td2rq:condition \"" + table + "." + columns[i] + " <> ''\";");
result.append(columns[i]);
}
result.append("\";");
}
// This is the YMD case using a very special SQLIte function to format data
// Assume that columns are Year, Month, and Day EXACTLY
else if (attribute.getType().equals("ymd")) {
// Require Year
pw.println("\td2rq:condition \"" + table + "." + columns[0] + " <> ''\";");
result.append("yearCollected || ifnull(nullif('-'||substr('0'||monthCollected,-2,2),'-0') || " +
"ifnull(nullif('-'||substr('0'||dayCollected,-2,2),'-0'),'')" +
",'') ");
result.append("\";");
}
pw.println(result.toString());
//pw.println("\td2rq:column \"" + table + "." + column + "\";");
//pw.println("\td2rq:condition \"" + table + "." + column + " <> ''\";");
// Specify an equivalence, which is isDefinedBy
classMapStringEquivalence = classMapString + "_Equivalence";
pw.println("\td2rq:additionalPropertyDefinitionProperty " + classMapStringEquivalence + ";");
pw.println("\t.");
// Always use isDefinedBy, even if the user has not expressed it explicitly. We do this by
// using the uri value if NO isDefinedBy is expressed.
pw.println(classMapStringEquivalence + " a d2rq:AdditionalProperty;");
pw.println("\td2rq:propertyName <" + attribute.getIsDefinedByURIString() + ">;");
if (attribute.getDefined_by() != null) {
pw.println("\td2rq:propertyValue <" + attribute.getDefined_by() + ">;");
} else {
pw.println("\td2rq:propertyValue <" + attribute.getUri() + ">;");
}
pw.println("\t.");
}
}
}
/**
* Generate D2RQ Mapping Language representation of this Connection.
*/
private void printConnectionD2RQ() {
pw.println("map:database a d2rq:Database;");
pw.println("\td2rq:jdbcDriver \"" + connection.system.driver + "\";");
pw.println("\td2rq:jdbcDSN \"" + connection.getJdbcUrl() + "\";");
if (connection.username != null && !connection.username.isEmpty())
pw.println("\td2rq:username \"" + connection.username + "\";");
if (connection.password != null && !connection.password.isEmpty())
pw.println("\td2rq:password \"" + connection.password + "\";");
pw.println("\td2rq:fetchSize \"" + (connection.system == DBsystem.mysql ? Integer.MIN_VALUE : 500) + "\";");
pw.println("\t.");
}
/**
* Generate all possible RDF prefixes.
*/
private void printPrefixes() {
// TODO: Allow configuration files to specify namespace prefixes!
pw.println("@prefix map: <" + "" + "> .");
pw.println("@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .");
pw.println("@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .");
pw.println("@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .");
pw.println("@prefix d2rq: <http://www.wiwiss.fu-berlin.de/suhl/bizer/D2RQ/0.1#> .");
pw.println("@prefix jdbc: <http://d2rq.org/terms/jdbc/> .");
pw.println("@prefix ro: <http://www.obofoundry.org/ro/ro.owl#> .");
pw.println("@prefix bsc: <http://biscicol.org/terms/index.html#> .");
pw.println("@prefix urn: <http://biscicol.org/terms/index.html#> .");
// TODO: update this prefix to EZID location when suffixPassthrough is ready
pw.println("@prefix ark: <http://biscicol.org/id/ark:> .");
pw.println();
}
/**
* Sets the URI as a identifier to a column, or not, according to D2RQ conventions
*
* @param entity
* @return
*/
private String getPersistentIdentifierMapping(Entity entity) {
String identifier = expeditionEntitiesService.getEntityIdentifier(entity);
return "\td2rq:uriPattern \"" + identifier + "@@" + entity.getColumn() + "@@\";";
}
}
The next class is used to get the unique persistent identifier for the triples:
public class ExpeditionEntitiesService {
private static String DEFAULT_IDENTIFIER_PREFIX = "urn:x-biscicol:";
private final ExpeditionEntities expeditionEntities;
private final ProcessController processController;
private final BcidService bcidService;
private final ExpeditionService expeditionService;
public ExpeditionEntitiesService(ExpeditionEntities expeditionEntities, ProcessController processController,
BcidService bcidService, ExpeditionService expeditionService) {
this.expeditionEntities = expeditionEntities;
this.processController = processController;
this.bcidService = bcidService;
this.expeditionService = expeditionService;
}
public String getEntityIdentifier(Entity entity) {
// Use the DeepRoots System to lookup Key
String identifier = null;
if (expeditionEntities != null) {
identifier = lookupPrefix(entity);
}
// Use the default namespace value if dRoots is unsuccessful...
if (identifier == null) {
identifier = DEFAULT_IDENTIFIER_PREFIX + entity.getConceptAlias() + ":";
}
return identifier;
}
/**
* Find the appropriate identifier for a concept contained in this file
*
* @return returns the Bcid for Entity resourceType in this DeepRoots file
*/
public String lookupPrefix(Entity entity) {
HashMap<String, String> entities = expeditionEntities.getEntities();
Iterator it = entities.entrySet().iterator();
while (it.hasNext()) {
Map.Entry pairs = (Map.Entry) it.next();
if (pairs.getKey().toString().trim().equals(entity.getConceptAlias().trim())) {
String postfix = (String) pairs.getValue();
return postfix;
}
}
FimsPrinter.out.println("\tWarning: " + entity.getConceptAlias() + " cannot be mapped in Deep Roots, attempting to create mapping");
// Create a mapping in the deeproots system for this URI
FimsPrinter.out.println("\tCreating bcid root for " + entity.getConceptAlias() + " with resource type = " + entity.getConceptURI());
Bcid bcid = new Bcid.BcidBuilder(entity.getConceptAlias())
.title(entity.getConceptAlias())
.build();
bcidService.create(bcid, processController.getUserId());
Expedition expedition = expeditionService.getExpedition(processController.getExpeditionCode(), processController.getProjectId());
bcidService.attachBcidToExpedition(bcid, expedition.getExpeditionId());
// Add this element to the entities string so we don't keep trying to add it in the loop above
entities.put(entity.getConceptAlias(), String.valueOf(bcid.getIdentifier()));
System.out.println("\tNew identifier = " + bcid.getIdentifier());
return String.valueOf(bcid.getIdentifier());
}
}
