lkrsnik/list
1
0
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

Added functional additional combinational filters for words

Browse Source
This commit is contained in:
Luka
2018-07-16 10:14:21 +02:00
parent e2ce656fc5
commit c073e12f55
8 changed files with 192 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/main/java/data/Filter.java
View File

@@ -24,7 +24,8 @@ public class Filter {
TAXONOMY,
MSD,
HAS_MSD,
SOLAR_FILTERS
SOLAR_FILTERS,
MULTIPLE_KEYS
}
public Filter() {
@@ -141,4 +142,23 @@ public class Filter {
public HashMap<String, HashSet<String>> getSolarFilters() {
return (HashMap<String, HashSet<String>>) filter.get(SOLAR_FILTERS);
}
public void setMultipleKeys(ArrayList<String> keys) {
ArrayList<CalculateFor> newKeys = new ArrayList<>();
if (keys != null) {
for (String key : keys) {
newKeys.add(CalculateFor.factory(key));
}
}
filter.put(MULTIPLE_KEYS, newKeys);
}
public ArrayList<CalculateFor> getMultipleKeys() {
if (filter.containsKey(MULTIPLE_KEYS) && filter.get(MULTIPLE_KEYS) != null) {
return (ArrayList<CalculateFor>) filter.get(MULTIPLE_KEYS);
} else {
return new ArrayList<>();
}
}
}

54
src/main/java/data/MultipleHMKeys.java
View File

@@ -2,48 +2,54 @@ package data;
/*
Created for when words are sorted by multiple keys, i.e. not just lemmas but lemmas and msd simultaneously.
*/
final class MultipleHMKeys {
private final String key1, key2, key3;
public final class MultipleHMKeys {
private final String key, lemma, wordType, msd;
public MultipleHMKeys(String key1) {
this.key1 = key1;
this.key2 = null;
this.key3 = null;
public MultipleHMKeys(String key) {
this.key = key;
this.lemma = "";
this.wordType = "";
this.msd = "";
}
public MultipleHMKeys(String key1, String key2) {
this.key1 = key1;
this.key2 = key2;
this.key3 = null;
public MultipleHMKeys(String key, String lemma, String wordType, String msd) {
this.key = key;
this.lemma = lemma;
this.wordType = wordType;
this.msd = msd;
}
public MultipleHMKeys(String key1, String key2, String key3) {
this.key1 = key1;
this.key2 = key2;
this.key3 = key3;
public String getKey() {
return key;
}
public String getKey1() {
return key1;
public String getLemma() {
return lemma;
}
public String getKey2() {
return key2;
public String getWordType() {
return wordType;
}
public String getKey3() {
return key3;
public String getMsd() {
return msd;
}
@Override
public int hashCode() {
return key1.hashCode() ^ key2.hashCode() ^ key3.hashCode();
// if(key2 == null){
// return key1.hashCode();
// } else if (key3 == null){
// return key1.hashCode() ^ key2.hashCode();
// }
return key.hashCode() ^ lemma.hashCode() ^ wordType.hashCode() ^ msd.hashCode();
}
@Override
public boolean equals(Object obj) {
return (obj instanceof MultipleHMKeys) && ((MultipleHMKeys) obj).key1.equals(key1)
&& ((MultipleHMKeys) obj).key2.equals(key2)
&& ((MultipleHMKeys) obj).key3.equals(key3);
return (obj instanceof MultipleHMKeys) && ((MultipleHMKeys) obj).key.equals(key)
&& ((MultipleHMKeys) obj).lemma.equals(lemma)
&& ((MultipleHMKeys) obj).wordType.equals(wordType)
&& ((MultipleHMKeys) obj).msd.equals(msd);
}
}

2
src/main/java/data/Statistics.java
View File

@@ -222,7 +222,7 @@ public class Statistics {
// return sortedM;
// }
private Map<String, Long> getSortedResult(Map<String, AtomicLong> map, int limit) {
private Map<MultipleHMKeys, Long> getSortedResult(Map<MultipleHMKeys, AtomicLong> map, int limit) {
return Util.sortByValue(Util.atomicInt2StringAndInt(map), limit);
}

43
src/main/java/data/StatisticsNew.java
View File

@@ -32,10 +32,10 @@ public class StatisticsNew {
private String resultTitle;
private Map<String, AtomicLong> result;
private Map<String, Map<String, AtomicLong>> taxonomyResult;
private Map<String, Map<MultipleHMKeys, AtomicLong>> taxonomyResult;
private Object[][] resultCustom; // for when calculating percentages that don't add up to 100%
private Map<String, ConcurrentHashMap<String, AtomicLong>> resultNestedSuffix;
private Map<String, ConcurrentHashMap<String, AtomicLong>> resultNestedPrefix;
private Map<String, ConcurrentHashMap<MultipleHMKeys, AtomicLong>> resultNestedSuffix;
private Map<String, ConcurrentHashMap<MultipleHMKeys, AtomicLong>> resultNestedPrefix;
private boolean useDB;
private RDB db;
private boolean analysisProducedResults;
@@ -194,7 +194,7 @@ public class StatisticsNew {
}
public boolean saveResultToDisk(int... limit) throws UnsupportedEncodingException {
Set<Pair<String, Map<String, Long>>> stats = new HashSet<>();
Set<Pair<String, Map<MultipleHMKeys, Long>>> stats = new HashSet<>();
if (useDB) {
result = db.getDump();
@@ -223,13 +223,14 @@ public class StatisticsNew {
}
Map<WordLevelType, Map<String, Map<String, Long>>> results = new HashMap<>();
if (!isEmpty(resultNestedSuffix)) {
results.put(WordLevelType.SUFFIX, sortNestedMap(resultNestedSuffix, Util.getValidInt(limit)));
}
if (!isEmpty(resultNestedPrefix)) {
results.put(WordLevelType.PREFIX, sortNestedMap(resultNestedPrefix, Util.getValidInt(limit)));
}
// UNCOMMENT!!!!!!
// if (!isEmpty(resultNestedSuffix)) {
// results.put(WordLevelType.SUFFIX, sortNestedMap(resultNestedSuffix, Util.getValidInt(limit)));
// }
//
// if (!isEmpty(resultNestedPrefix)) {
// results.put(WordLevelType.PREFIX, sortNestedMap(resultNestedPrefix, Util.getValidInt(limit)));
// }
// if no results and nothing to save, return false
if (!(results.size() > 0)) {
@@ -266,8 +267,8 @@ public class StatisticsNew {
return true;
}
private Map<String, Map<String, Long>> sortNestedMap(Map<String, ConcurrentHashMap<String, AtomicLong>> nestedMap, int limit) {
Map<String, Map<String, Long>> sorted = new HashMap<>();
private Map<String, Map<MultipleHMKeys, Long>> sortNestedMap(Map<String, ConcurrentHashMap<MultipleHMKeys, AtomicLong>> nestedMap, int limit) {
Map<String, Map<MultipleHMKeys, Long>> sorted = new HashMap<>();
for (String s : nestedMap.keySet()) {
sorted.put(s, getSortedResult(nestedMap.get(s), Util.getValidInt(limit)));
@@ -277,11 +278,11 @@ public class StatisticsNew {
}
private Map<String, Long> getSortedResult(Map<String, AtomicLong> map, int limit) {
private Map<MultipleHMKeys, Long> getSortedResult(Map<MultipleHMKeys, AtomicLong> map, int limit) {
return Util.sortByValue(Util.atomicInt2StringAndInt(map), limit);
}
public void updateTaxonomyResults(String o, List<String> taxonomy) {
public void updateTaxonomyResults(MultipleHMKeys o, List<String> taxonomy) {
for (String key : taxonomyResult.keySet()) {
// first word should have the same taxonomy as others
if (taxonomy.contains(key) || key.equals("Total")) {
@@ -335,9 +336,11 @@ public class StatisticsNew {
}
public void updateResultsNestedSuffix(String key, String stringValue) {
MultipleHMKeys mkStringValue = new MultipleHMKeys(stringValue);
if (resultNestedSuffix.containsKey(key)) {
// if not in map
AtomicLong r = resultNestedSuffix.get(key).putIfAbsent(stringValue, new AtomicLong(1));
AtomicLong r = resultNestedSuffix.get(key).putIfAbsent(mkStringValue, new AtomicLong(1));
// else
if (r != null) {
@@ -345,7 +348,7 @@ public class StatisticsNew {
}
} else {
resultNestedSuffix.putIfAbsent(key, new ConcurrentHashMap<>());
AtomicLong r = resultNestedSuffix.get(key).putIfAbsent(stringValue, new AtomicLong(1));
AtomicLong r = resultNestedSuffix.get(key).putIfAbsent(mkStringValue, new AtomicLong(1));
if (r != null) {
resultNestedSuffix.get(key).get(stringValue).incrementAndGet();
@@ -354,9 +357,11 @@ public class StatisticsNew {
}
public void updateResultsNestedPrefix(String key, String stringValue) {
MultipleHMKeys mkStringValue = new MultipleHMKeys(stringValue);
if (resultNestedPrefix.containsKey(key)) {
// if not in map
AtomicLong r = resultNestedPrefix.get(key).putIfAbsent(stringValue, new AtomicLong(1));
AtomicLong r = resultNestedPrefix.get(key).putIfAbsent(mkStringValue, new AtomicLong(1));
// else
if (r != null) {
@@ -364,7 +369,7 @@ public class StatisticsNew {
}
} else {
resultNestedPrefix.putIfAbsent(key, new ConcurrentHashMap<>());
AtomicLong r = resultNestedPrefix.get(key).putIfAbsent(stringValue, new AtomicLong(1));
AtomicLong r = resultNestedPrefix.get(key).putIfAbsent(mkStringValue, new AtomicLong(1));
if (r != null) {
resultNestedPrefix.get(key).get(stringValue).incrementAndGet();