honeymoose
/
org.hl7.fhir.core
mirror of https://github.com/hapifhir/org.hl7.fhir.core.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add PhinVads Importer

This commit is contained in:
Grahame Grieve 2020-08-20 20:37:30 +10:00
parent 5fc297b3b5
commit 9a51722ee0
3 changed files with 160 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

116
org.hl7.fhir.convertors/src/main/java/org/hl7/fhir/convertors/misc/PhinVadsImporter.java Normal file
View File

@ -0,0 +1,116 @@
package org.hl7.fhir.convertors.misc;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.List;
import org.hl7.fhir.exceptions.FHIRException;
import org.hl7.fhir.r5.context.IWorkerContext;
import org.hl7.fhir.r5.context.SimpleWorkerContext;
import org.hl7.fhir.r5.formats.JsonParser;
import org.hl7.fhir.r5.model.Enumerations.PublicationStatus;
import org.hl7.fhir.r5.model.ValueSet;
import org.hl7.fhir.r5.model.ValueSet.ConceptSetComponent;
import org.hl7.fhir.utilities.CSVReader;
import org.hl7.fhir.utilities.TextFile;
import org.hl7.fhir.utilities.Utilities;
import org.hl7.fhir.utilities.cache.FilesystemPackageCacheManager;
import org.hl7.fhir.utilities.cache.NpmPackage;
import org.hl7.fhir.utilities.cache.ToolsVersion;
public class PhinVadsImporter {
public static void main(String[] args) throws FileNotFoundException, FHIRException, IOException, ParseException {
PhinVadsImporter self = new PhinVadsImporter();
self.init();
self.process(args[0], args[1]);
}
private IWorkerContext context;
public PhinVadsImporter() {
super();
}
private void init() throws FileNotFoundException, FHIRException, IOException {
FilesystemPackageCacheManager pcm = new FilesystemPackageCacheManager(true, ToolsVersion.TOOLS_VERSION);
NpmPackage npm = pcm.loadPackage("hl7.fhir.r5.core", "current");
SimpleWorkerContext ctxt = SimpleWorkerContext.fromPackage(npm);
ctxt.setAllowLoadingDuplicates(true);
ctxt.loadFromPackage(pcm.loadPackage("hl7.terminology"), null);
context = ctxt;
}
private void process(String source, String dest) {
for (File f : new File(source).listFiles()) {
try {
System.out.println("Process "+f.getName());
ValueSet vs = importValueSet(TextFile.fileToBytes(f));
new JsonParser().compose(new FileOutputStream(Utilities.path(dest, "ValueSet-"+vs.getId()+".json")), vs);
} catch (Exception e) {
e.printStackTrace();
}
}
}
private ValueSet importValueSet(byte[] source) throws FHIRException, IOException, ParseException {
// first thing do is split into 2
List<byte[]> parts = Utilities.splitBytes(source, "\r\n\r\n".getBytes());
if (parts.size() != 2) {
throw new FHIRException("Unable to parse phinvads value set: "+parts.size()+" parts found");
}
CSVReader rdr = new CSVReader(new ByteArrayInputStream(parts.get(0)));
rdr.setDelimiter('\t');
rdr.readHeaders();
rdr.line();
ValueSet vs = new ValueSet();
vs.setId(rdr.cell("Value Set OID"));
vs.setUrl("https://phinvads.cdc.gov/fhir/ValueSet/"+vs.getId());
vs.setVersion(rdr.cell("Value Set Version"));
vs.setTitle(rdr.cell("Value Set Name"));
vs.setName(rdr.cell("Value Set Code"));
vs.setDescription(rdr.cell("Value Set Definition"));
if ("Published".equals(rdr.cell("Value Set Status"))) {
vs.setStatus(PublicationStatus.ACTIVE);
}
if (rdr.has("VS Last Updated Date")) {
vs.setDate(new SimpleDateFormat("mm/dd/yyyy").parse(rdr.cell("VS Last Updated Date")));
}
rdr = new CSVReader(new ByteArrayInputStream(parts.get(1)));
rdr.setDelimiter('\t');
rdr.readHeaders();
while (rdr.line()) {
String code = rdr.cell("Concept Code");
String display = rdr.cell("Preferred Concept Name");
String csoid = rdr.cell("Code System OID");
String csver = rdr.cell("Code System Version");
String url = context.oid2Uri(csoid);
if (url == null) {
url = "urn:oid:"+csoid;
}
ConceptSetComponent inc = getInclude(vs, url, csver);
inc.addConcept().setCode(code).setDisplay(display);
}
return vs;
}
private ConceptSetComponent getInclude(ValueSet vs, String url, String csver) {
for (ConceptSetComponent t : vs.getCompose().getInclude()) {
if (t.getSystem().equals(url) && t.getVersion().equals(csver)) {
return t;
}
}
ConceptSetComponent c = vs.getCompose().addInclude();
c.setSystem(url);
c.setVersion(csver);
return c;
}
}

13
org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/CSVReader.java
View File

@ -60,6 +60,7 @@ public class CSVReader extends InputStreamReader {
private String[] cols;
private String[] cells;
private char delimiter = ',';
public void readHeaders() throws IOException, FHIRException {
cols = parseLine();
@ -90,7 +91,7 @@ public class CSVReader extends InputStreamReader {
}
if (index == -1)
throw new FHIRException("no cell "+name);
String s = cells.length >= index ? cells[index] : null;
String s = cells.length > index ? cells[index] : null;
if (Utilities.noString(s))
return null;
if (s.startsWith("\"") && s.endsWith("\"")) {
@ -150,7 +151,7 @@ public class CSVReader extends InputStreamReader {
inQuote = !inQuote;
}
}
else if (!inQuote && c == ',') {
else if (!inQuote && c == delimiter ) {
res.add(b.toString().trim());
b = new StringBuilder();
}
@ -210,5 +211,13 @@ public class CSVReader extends InputStreamReader {
return cells[i-1];
}
public char getDelimiter() {
return delimiter;
}
public void setDelimiter(char delimiter) {
this.delimiter = delimiter;
}
}

33
org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/Utilities.java
View File

@ -48,8 +48,10 @@ import java.nio.channels.FileChannel;
import java.nio.file.Paths;
import java.time.Duration;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collection;
import java.util.Collections;
import java.util.LinkedList;
import java.util.List;
import java.util.Set;
import java.util.UUID;
@ -1328,4 +1330,35 @@ public class Utilities {
}
return length + BT;
}
public static List<byte[]> splitBytes(byte[] array, byte[] delimiter) {
List<byte[]> byteArrays = new LinkedList<byte[]>();
if (delimiter.length == 0)
{
return byteArrays;
}
int begin = 0;
outer: for (int i = 0; i < array.length - delimiter.length + 1; i++)
{
for (int j = 0; j < delimiter.length; j++)
{
if (array[i + j] != delimiter[j])
{
continue outer;
}
}
// If delimiter is at the beginning then there will not be any data.
if (begin < i)
byteArrays.add(Arrays.copyOfRange(array, begin, i));
begin = i + delimiter.length;
}
// delimiter at the very end with no data following?
if (begin != array.length)
byteArrays.add(Arrays.copyOfRange(array, begin, array.length));
return byteArrays;
}
}