Reimplementation of other signs (,/*() etc.) in ngrams.
This commit is contained in:
@@ -90,6 +90,7 @@ public class Export {
|
||||
FILE_HEADER_AL.add(filter.getCalculateFor().toHeaderString());
|
||||
if (filter.getCalculateFor().equals(CalculateFor.LEMMA))
|
||||
FILE_HEADER_AL.add("Lema male črke");
|
||||
headerInfoBlock.put(filter.getCalculateFor().toMetadataString(), String.valueOf(num_frequencies));
|
||||
|
||||
// if (headerInfoBlock.containsKey("Analiza") && (headerInfoBlock.get("Analiza").equals("Besede") || headerInfoBlock.get("Analiza").equals("Besedni nizi"))) {
|
||||
// if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("različnica")) {
|
||||
@@ -161,7 +162,7 @@ public class Export {
|
||||
// } else {
|
||||
// FILE_HEADER_AL.add("Delež glede na vse leme");
|
||||
// }
|
||||
FILE_HEADER_AL.add("Skupna relativna pogostost");
|
||||
FILE_HEADER_AL.add("Skupna relativna pogostost (na milijon pojavitev)");
|
||||
for (String key : taxonomyResults.keySet()) {
|
||||
if(!key.equals("Total")) {
|
||||
FILE_HEADER_AL.add("Absolutna pogostost [" + key + "]");
|
||||
@@ -213,8 +214,7 @@ public class Export {
|
||||
for (Map.Entry<MultipleHMKeys, Long> e : map.entrySet()) {
|
||||
List dataEntry = new ArrayList<>();
|
||||
dataEntry.add(e.getKey().getK1());
|
||||
if (headerInfoBlock.containsKey("Analiza") && (headerInfoBlock.get("Analiza").equals("Besede") || headerInfoBlock.get("Analiza").equals("Besedni nizi")) &&
|
||||
headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("lema")){
|
||||
if (filter.getCalculateFor().equals(CalculateFor.LEMMA)){
|
||||
dataEntry.add(e.getKey().getK1().toLowerCase());
|
||||
}
|
||||
|
||||
@@ -255,16 +255,55 @@ public class Export {
|
||||
// }
|
||||
dataEntry.add(e.getValue().toString());
|
||||
dataEntry.add(formatNumberAsPercent((double) e.getValue() / num_frequencies));
|
||||
dataEntry.add(String.format("%.2f", ((double) e.getValue() * 10000)/num_frequencies));
|
||||
dataEntry.add(String.format("%.2f", ((double) e.getValue() * 1000000)/num_frequencies));
|
||||
for (String key : taxonomyResults.keySet()){
|
||||
if(!key.equals("Total")) {
|
||||
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)));
|
||||
dataEntry.add(String.format("%.2f", ((double) frequency.get() * 1000000) / num_taxonomy_frequencies.get(key)));
|
||||
}
|
||||
}
|
||||
|
||||
// Write msd separated per letters at the end of each line in csv
|
||||
if (filter.getWriteMsdAtTheEnd()) {
|
||||
String msd = "";
|
||||
if (filter.getCalculateFor().equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
|
||||
msd = e.getKey().getK1();
|
||||
} else if (filter.getMultipleKeys().contains(CalculateFor.MORPHOSYNTACTIC_SPECS)) {
|
||||
i = 0;
|
||||
for (CalculateFor otherKey : filter.getMultipleKeys()){
|
||||
switch(i){
|
||||
case 0:
|
||||
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
|
||||
msd = e.getKey().getK2();
|
||||
}
|
||||
break;
|
||||
case 1:
|
||||
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
|
||||
msd = e.getKey().getK3();
|
||||
}
|
||||
break;
|
||||
case 2:
|
||||
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
|
||||
msd = e.getKey().getK4();
|
||||
}
|
||||
break;
|
||||
case 3:
|
||||
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
|
||||
msd = e.getKey().getK5();
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
i++;
|
||||
}
|
||||
}
|
||||
String [] charArray = msd.split("(?!^)");
|
||||
dataEntry.addAll(Arrays.asList(charArray));
|
||||
|
||||
}
|
||||
|
||||
csvFilePrinter.printRecord(dataEntry);
|
||||
}
|
||||
} catch (Exception e) {
|
||||
|
||||
Reference in New Issue
Block a user