Join active snomed concept FSNs to a TSV list of codes.

FSNJoiner.java

import it.unimi.dsi.fastutil.longs.Long2ObjectOpenHashMap;
import java.io.*;
import java.util.Map;

public class Temp {

	public static void main(String[] args) throws IOException {
		run();
	}

	private static void run() throws IOException {
		Map<Long, String> conceptFsn = new Long2ObjectOpenHashMap<>();
		try (BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream("SnomedCT_USEditionRF2_PRODUCTION_20200301T120000Z/Snapshot/Terminology/sct2_Description_Snapshot-en_US1000124_20200301.txt")))) {
			String line;
			while ((line = reader.readLine()) != null) {
				// id	effectiveTime	active	moduleId	conceptId	languageCode	typeId	term	caseSignificanceId
				// 0	1				2		3			4			5				6		7		8
				String[] split = line.split("\t");
				if (split[2].equals("1") && split[6].equals("900000000000003001")) {
					conceptFsn.put(Long.parseLong(split[4]), split[7]);
				}
			}
		}
		System.out.println(conceptFsn.size() + " terms read");

		try (BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream("frequencies-of-sct-codes.tsv")));
			 BufferedWriter writer = new BufferedWriter(new FileWriter("out.txt"))) {
			String line;
			writer.write(reader.readLine());
			writer.newLine();
			while ((line = reader.readLine()) != null) {
				// concept_code	group
				// 0			1
				String[] split = line.split("\t");
				Long conceptId = Long.parseLong(split[0]);
				String term = conceptFsn.get(conceptId);
				if (term == null) {
					term = "";
				}
				writer.write(String.join("\t", split[0], term, split[1]));
				writer.newLine();
			}
		}
	}

}