You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
336 lines
11 KiB
336 lines
11 KiB
package util;
|
|
|
|
import static util.Util.*;
|
|
|
|
import java.io.*;
|
|
import java.nio.charset.StandardCharsets;
|
|
import java.util.*;
|
|
import java.util.concurrent.ConcurrentHashMap;
|
|
import java.util.concurrent.ConcurrentMap;
|
|
import java.util.concurrent.atomic.AtomicLong;
|
|
|
|
import data.Filter;
|
|
import org.apache.commons.csv.CSVFormat;
|
|
import org.apache.commons.csv.CSVPrinter;
|
|
import org.apache.commons.lang3.tuple.Pair;
|
|
import org.json.simple.JSONArray;
|
|
import org.json.simple.JSONObject;
|
|
|
|
import data.Enums.WordLevelType;
|
|
|
|
@SuppressWarnings("unchecked")
|
|
public class Export {
|
|
public static void SetToJSON(Set<Pair<String, Map<String, Long>>> set) {
|
|
JSONArray wrapper = new JSONArray();
|
|
|
|
for (Pair<String, Map<String, Long>> p : set) {
|
|
JSONArray data_wrapper = new JSONArray();
|
|
JSONObject metric = new JSONObject();
|
|
|
|
String title = p.getLeft();
|
|
Map<String, Long> map = p.getRight();
|
|
|
|
if (map.isEmpty())
|
|
continue;
|
|
|
|
long total = Util.mapSumFrequencies(map);
|
|
|
|
for (Map.Entry<String, Long> e : map.entrySet()) {
|
|
JSONObject data_entry = new JSONObject();
|
|
data_entry.put("word", e.getKey());
|
|
data_entry.put("frequency", e.getValue());
|
|
data_entry.put("percent", formatNumberAsPercent((double) e.getValue() / total));
|
|
|
|
data_wrapper.add(data_entry);
|
|
}
|
|
|
|
metric.put("Title", title);
|
|
metric.put("data", data_wrapper);
|
|
wrapper.add(metric);
|
|
}
|
|
|
|
try (FileWriter file = new FileWriter("statistics.json")) {
|
|
file.write(wrapper.toJSONString());
|
|
} catch (IOException e) {
|
|
e.printStackTrace();
|
|
}
|
|
}
|
|
|
|
public static String SetToCSV(Set<Pair<String, Map<String, Long>>> set, File resultsPath, LinkedHashMap<String, String> headerInfoBlock,
|
|
Map<String, Map<String, AtomicLong>> taxonomyResults) {
|
|
//Delimiter used in CSV file
|
|
String NEW_LINE_SEPARATOR = "\n";
|
|
List<Object> FILE_HEADER_AL = new ArrayList<Object>();
|
|
Object[] FILE_HEADER;
|
|
|
|
//Count frequencies
|
|
long num_frequencies = 0;
|
|
for (Pair<String, Map<String, Long>> p : set) {
|
|
Map<String, Long> map = p.getRight();
|
|
if (map.isEmpty())
|
|
continue;
|
|
num_frequencies = Util.mapSumFrequencies(map);
|
|
}
|
|
|
|
Map<String, Long> num_taxonomy_frequencies = new ConcurrentHashMap<>();
|
|
for (String taxonomyKey : taxonomyResults.keySet()) {
|
|
num_taxonomy_frequencies.put(taxonomyKey, (long) 0);
|
|
for (AtomicLong value : taxonomyResults.get(taxonomyKey).values()){
|
|
long val = num_taxonomy_frequencies.get(taxonomyKey);
|
|
val += value.get();
|
|
num_taxonomy_frequencies.put(taxonomyKey, val);
|
|
}
|
|
}
|
|
|
|
|
|
//CSV file header
|
|
if (headerInfoBlock.containsKey("Analiza") && headerInfoBlock.get("Analiza").equals("Besede")) {
|
|
if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("različnica")) {
|
|
headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
|
|
FILE_HEADER_AL.add("Različnica");
|
|
FILE_HEADER_AL.add("Skupna absolutna pogostost");
|
|
FILE_HEADER_AL.add("Delež glede na vse različnice");
|
|
} else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("lema")) {
|
|
headerInfoBlock.put("Skupna vsota vseh lem:", String.valueOf(num_frequencies));
|
|
FILE_HEADER_AL.add("Lema");
|
|
FILE_HEADER_AL.add("Skupna absolutna pogostost");
|
|
FILE_HEADER_AL.add("Delež glede na vse leme");
|
|
} else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("oblikoskladenjska oznaka")) {
|
|
headerInfoBlock.put("Skupna vsota vseh oblikoskladenjskih oznak:", String.valueOf(num_frequencies));
|
|
FILE_HEADER_AL.add("Oblikoskladenjska oznaka");
|
|
FILE_HEADER_AL.add("Skupna absolutna pogostost");
|
|
FILE_HEADER_AL.add("Delež glede na vse oblikoskladenjske oznake");
|
|
} else {
|
|
headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
|
|
FILE_HEADER_AL.add("Lema");
|
|
FILE_HEADER_AL.add("Skupna absolutna pogostost");
|
|
FILE_HEADER_AL.add("Delež glede na vse leme");
|
|
}
|
|
FILE_HEADER_AL.add("Skupna relativna pogostost");
|
|
for (String key : taxonomyResults.keySet()) {
|
|
FILE_HEADER_AL.add("Absolutna pogostost [" + key + "]");
|
|
FILE_HEADER_AL.add("Delež [" + key + "]");
|
|
FILE_HEADER_AL.add("Relativna pogostost [" + key + "]");
|
|
}
|
|
FILE_HEADER = new String[ FILE_HEADER_AL.size() ];
|
|
FILE_HEADER_AL.toArray(FILE_HEADER);
|
|
} else {
|
|
FILE_HEADER = new Object[]{"word", "frequency", "percent"};
|
|
}
|
|
|
|
String fileName = "";
|
|
|
|
for (Pair<String, Map<String, Long>> p : set) {
|
|
String title = p.getLeft();
|
|
fileName = title.replace(": ", "-");
|
|
fileName = fileName.replace(" ", "_").concat(".csv");
|
|
|
|
fileName = resultsPath.toString().concat(File.separator).concat(fileName);
|
|
|
|
Map<String, Long> map = p.getRight();
|
|
|
|
if (map.isEmpty())
|
|
continue;
|
|
|
|
// long total = Util.mapSumFrequencies(map);
|
|
|
|
OutputStreamWriter fileWriter = null;
|
|
CSVPrinter csvFilePrinter = null;
|
|
|
|
//Create the CSVFormat object with "\n" as a record delimiter
|
|
CSVFormat csvFileFormat = CSVFormat.DEFAULT.withRecordSeparator(NEW_LINE_SEPARATOR).withDelimiter(';');
|
|
|
|
try {
|
|
//initialize FileWriter object
|
|
fileWriter = new OutputStreamWriter(new FileOutputStream(fileName), StandardCharsets.UTF_8);
|
|
|
|
//initialize CSVPrinter object
|
|
csvFilePrinter = new CSVPrinter(fileWriter, csvFileFormat);
|
|
|
|
// write info block
|
|
printHeaderInfo(csvFilePrinter, headerInfoBlock);
|
|
|
|
//Create CSV file header
|
|
csvFilePrinter.printRecord(FILE_HEADER);
|
|
|
|
for (Map.Entry<String, Long> e : map.entrySet()) {
|
|
List dataEntry = new ArrayList<>();
|
|
dataEntry.add(e.getKey());
|
|
dataEntry.add(e.getValue().toString());
|
|
dataEntry.add(formatNumberAsPercent((double) e.getValue() / num_frequencies));
|
|
dataEntry.add(String.format("%.2f", ((double) e.getValue() * 10000)/num_frequencies));
|
|
for (String key : taxonomyResults.keySet()){
|
|
AtomicLong frequency = taxonomyResults.get(key).get(e.getKey());
|
|
dataEntry.add(frequency.toString());
|
|
dataEntry.add(formatNumberAsPercent((double) frequency.get() / num_taxonomy_frequencies.get(key)));
|
|
dataEntry.add(String.format("%.2f", ((double) frequency.get() * 10000) / num_taxonomy_frequencies.get(key)));
|
|
|
|
}
|
|
|
|
csvFilePrinter.printRecord(dataEntry);
|
|
}
|
|
} catch (Exception e) {
|
|
System.out.println("Error in CsvFileWriter!");
|
|
e.printStackTrace();
|
|
} finally {
|
|
try {
|
|
if (fileWriter != null) {
|
|
fileWriter.flush();
|
|
fileWriter.close();
|
|
}
|
|
if (csvFilePrinter != null) {
|
|
csvFilePrinter.close();
|
|
}
|
|
} catch (IOException e) {
|
|
System.out.println("Error while flushing/closing fileWriter/csvPrinter!");
|
|
e.printStackTrace();
|
|
}
|
|
}
|
|
}
|
|
|
|
return fileName;
|
|
}
|
|
|
|
public static String SetToCSV(String title, Object[][] result, File resultsPath, LinkedHashMap<String, String> headerInfoBlock) {
|
|
//Delimiter used in CSV file
|
|
String NEW_LINE_SEPARATOR = "\n";
|
|
|
|
//CSV file header
|
|
Object[] FILE_HEADER = {"word", "frequency", "percent"};
|
|
|
|
String fileName = "";
|
|
|
|
fileName = title.replace(": ", "-");
|
|
fileName = fileName.replace(" ", "_").concat(".csv");
|
|
|
|
fileName = resultsPath.toString().concat(File.separator).concat(fileName);
|
|
|
|
OutputStreamWriter fileWriter = null;
|
|
CSVPrinter csvFilePrinter = null;
|
|
|
|
//Create the CSVFormat object with "\n" as a record delimiter
|
|
CSVFormat csvFileFormat = CSVFormat.DEFAULT.withRecordSeparator(NEW_LINE_SEPARATOR).withDelimiter(';');
|
|
|
|
try {
|
|
//initialize FileWriter object
|
|
fileWriter = new OutputStreamWriter(new FileOutputStream(fileName), StandardCharsets.UTF_8);
|
|
|
|
//initialize CSVPrinter object
|
|
csvFilePrinter = new CSVPrinter(fileWriter, csvFileFormat);
|
|
|
|
// write info block
|
|
printHeaderInfo(csvFilePrinter, headerInfoBlock);
|
|
|
|
//Create CSV file header
|
|
csvFilePrinter.printRecord(FILE_HEADER);
|
|
|
|
for (Object[] resultEntry : result) {
|
|
List dataEntry = new ArrayList<>();
|
|
dataEntry.add(resultEntry[0]);
|
|
dataEntry.add(resultEntry[1]);
|
|
dataEntry.add(formatNumberAsPercent(resultEntry[2]));
|
|
csvFilePrinter.printRecord(dataEntry);
|
|
}
|
|
} catch (Exception e) {
|
|
System.out.println("Error in CsvFileWriter!");
|
|
e.printStackTrace();
|
|
} finally {
|
|
try {
|
|
if (fileWriter != null) {
|
|
fileWriter.flush();
|
|
fileWriter.close();
|
|
}
|
|
if (csvFilePrinter != null) {
|
|
csvFilePrinter.close();
|
|
}
|
|
} catch (IOException e) {
|
|
System.out.println("Error while flushing/closing fileWriter/csvPrinter!");
|
|
e.printStackTrace();
|
|
}
|
|
}
|
|
|
|
return fileName;
|
|
}
|
|
|
|
public static String nestedMapToCSV(String title, Map<WordLevelType, Map<String, Map<String, Long>>> result, File resultsPath, LinkedHashMap<String, String> headerInfoBlock) {
|
|
//Delimiter used in CSV file
|
|
String NEW_LINE_SEPARATOR = "\n";
|
|
|
|
//CSV file header
|
|
Object[] FILE_HEADER = {"type", "key", "word", "frequency"};
|
|
|
|
String fileName = "";
|
|
|
|
fileName = title.replace(": ", "-");
|
|
fileName = fileName.replace(" ", "_").concat(".csv");
|
|
|
|
fileName = resultsPath.toString().concat(File.separator).concat(fileName);
|
|
|
|
OutputStreamWriter fileWriter = null;
|
|
CSVPrinter csvFilePrinter = null;
|
|
|
|
//Create the CSVFormat object with "\n" as a record delimiter
|
|
CSVFormat csvFileFormat = CSVFormat.DEFAULT.withRecordSeparator(NEW_LINE_SEPARATOR).withDelimiter(';');
|
|
|
|
try {
|
|
//initialize FileWriter object
|
|
fileWriter = new OutputStreamWriter(new FileOutputStream(fileName), StandardCharsets.UTF_8);
|
|
|
|
//initialize CSVPrinter object
|
|
csvFilePrinter = new CSVPrinter(fileWriter, csvFileFormat);
|
|
|
|
// write info block
|
|
printHeaderInfo(csvFilePrinter, headerInfoBlock);
|
|
|
|
//Create CSV file header
|
|
csvFilePrinter.printRecord(FILE_HEADER);
|
|
|
|
for (Map.Entry<WordLevelType, Map<String, Map<String, Long>>> typeEntry : result.entrySet()) {
|
|
for (Map.Entry<String, Map<String, Long>> keyWordEntry : typeEntry.getValue().entrySet()) {
|
|
for (Map.Entry<String, Long> calculationResults : keyWordEntry.getValue().entrySet()) {
|
|
List values = new ArrayList();
|
|
values.add(typeEntry.getKey().getName());
|
|
values.add(keyWordEntry.getKey());
|
|
values.add(calculationResults.getKey());
|
|
values.add(calculationResults.getValue());
|
|
csvFilePrinter.printRecord(values);
|
|
}
|
|
}
|
|
}
|
|
} catch (Exception e) {
|
|
System.out.println("Error in CsvFileWriter!");
|
|
e.printStackTrace();
|
|
} finally {
|
|
try {
|
|
if (fileWriter != null) {
|
|
fileWriter.flush();
|
|
fileWriter.close();
|
|
}
|
|
if (csvFilePrinter != null) {
|
|
csvFilePrinter.close();
|
|
}
|
|
} catch (IOException e) {
|
|
System.out.println("Error while flushing/closing fileWriter/csvPrinter!");
|
|
e.printStackTrace();
|
|
}
|
|
}
|
|
|
|
return fileName;
|
|
}
|
|
|
|
private static void printHeaderInfo(CSVPrinter csvFilePrinter, LinkedHashMap<String, String> headerInfoBlock) throws IOException {
|
|
for (Map.Entry<String, String> entry : headerInfoBlock.entrySet()) {
|
|
List values = new ArrayList();
|
|
values.add(entry.getKey());
|
|
values.add(entry.getValue());
|
|
csvFilePrinter.printRecord(values);
|
|
}
|
|
|
|
// 2 empty lines
|
|
List values = new ArrayList();
|
|
csvFilePrinter.printRecord(values);
|
|
csvFilePrinter.printRecord(values);
|
|
|
|
}
|
|
}
|