07_STD: Änderungen an string_similarity
This commit is contained in:
parent
789099fbde
commit
6ef408d6db
|
|
@ -6,25 +6,27 @@
|
|||
#include <list>
|
||||
#include <algorithm>
|
||||
#include <unordered_map>
|
||||
#include <set>
|
||||
#include <map>
|
||||
#include "grundgeruest.hpp"
|
||||
|
||||
struct BinaryOctet {
|
||||
bool evenParity;
|
||||
char bitsAsDigits[8];
|
||||
bool evenParity;
|
||||
char bitsAsDigits[8];
|
||||
|
||||
BinaryOctet(int i) {
|
||||
BinaryOctet(int i) {
|
||||
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
int main() {
|
||||
std::srand(static_cast<unsigned int>(std::time(0)));
|
||||
std::srand(static_cast<unsigned int>(std::time(nullptr)));
|
||||
int array[41];
|
||||
|
||||
std::default_random_engine generator;
|
||||
std::uniform_int_distribution<int> distribution(0, 23);
|
||||
|
||||
for(int i = 0; i <= 41; i++) {
|
||||
for (int i = 0; i <= 41; i++) {
|
||||
int rnd = distribution(generator);
|
||||
array[i] = rnd;
|
||||
}
|
||||
|
|
@ -35,24 +37,103 @@ int main() {
|
|||
|
||||
//TODO: Punkte gleichmässig verteilen
|
||||
int stringSimilarity(std::string string1, std::string string2) {
|
||||
std::string alphabet = "abcdefghijklmnopqrstuvwxyzäöü";
|
||||
//wenn gleicher String, gleich 100 Punkte geben, spart den Rest
|
||||
if(string1 == string2) return 100;
|
||||
if (string1 == string2) return 100;
|
||||
int points = 0;
|
||||
|
||||
//gleiche Länge +10 Punkte
|
||||
if(string1.length() == string2.length()) points += 10;
|
||||
if (string1.length() == string2.length()) points += 10;
|
||||
|
||||
//Anzahl der verschiedenen Zeichen zählen
|
||||
std::map<char, int> charCount;
|
||||
std::map<char, int> charCountString1;
|
||||
std::map<char, int> charCountString2;
|
||||
for (char c : string1) {
|
||||
charCount[c]++;
|
||||
charCountString1[c]++;
|
||||
}
|
||||
for (char c : string2) {
|
||||
charCount[c]++;
|
||||
charCountString2[c]++;
|
||||
}
|
||||
std::cout << charCount.size() << " : " << charCountString1.size() << " : " << charCountString2.size() << std::endl;
|
||||
int equalCharsPercentage = static_cast<int>((double(charCountString1.size()) / double(charCount.size())) * 100);
|
||||
|
||||
points += equalCharsPercentage / 10;
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
/*//Anzahl der verschiedenen Zeichen zählen
|
||||
std::unordered_map<char, int> string1map;
|
||||
std::unordered_map<char, int> string2map;
|
||||
std::unordered_map<char, int> characterCount;
|
||||
std::set<char> characters;
|
||||
|
||||
for(char c : string1) {
|
||||
characters.insert(c);
|
||||
string1map[c]++;
|
||||
characterCount[c]++;
|
||||
}
|
||||
for(char c : string2) {
|
||||
characters.insert(c);
|
||||
string2map[c]++;
|
||||
characterCount[c]++;
|
||||
}
|
||||
|
|
@ -60,26 +141,30 @@ int stringSimilarity(std::string string1, std::string string2) {
|
|||
//gleiche Anzahl an verschiedenen Zeichen +10 Punkte
|
||||
if(string1map.size() == string2map.size()) points += 10;
|
||||
|
||||
int equalCharCount = 0;
|
||||
int caseSensitiveCount = 0;
|
||||
for(std::pair<char, int> c : characterCount) {
|
||||
//gleiche Anzahl an gleichen Zeichen in beiden überprüfen
|
||||
int charCount = c.second / 2;
|
||||
if(charCount == string1map[c.first] && charCount == string2map[c.first]) {
|
||||
equalCharCount++;
|
||||
caseSensitiveCount++;
|
||||
}
|
||||
if(islower(c.first)) {
|
||||
c.first = static_cast<char>(toupper(c.first));
|
||||
}
|
||||
|
||||
if(isupper(c.first)) c.first = tolower(c.first);
|
||||
}
|
||||
|
||||
|
||||
|
||||
//gleiche Anzahl an gleichen Zeichen +10 Punkte
|
||||
if(equalCharCount == characterCount.size()) points += 10;
|
||||
if(caseSensitiveCount == characterCount.size()) points += 10;
|
||||
|
||||
int caseInsensitiveCount = 0;
|
||||
for(std::pair<char, int> c : characterCount) {
|
||||
int charCount = c.second / 2;
|
||||
if(charCount == string1map[c.first] && charCount == string2map[c.first]) {
|
||||
caseInsensitiveCount++;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
//TODO: Punkte für gleiche Buchstaben und gleiche Buchstaben Anzahl vergeben
|
||||
|
||||
if(caseInsensitiveCount == characterCount.size()) points += 10;*/
|
||||
|
||||
|
||||
return points;
|
||||
|
|
@ -91,21 +176,22 @@ void unittest_stringSimilarity() {
|
|||
std::cout << "Hello World | Hallo Welt ---> " << stringSimilarity("Hello World", "Hallo Welt") << std::endl;
|
||||
std::cout << "bla | ping ---> " << stringSimilarity("bla", "ping") << std::endl;
|
||||
std::cout << "Lorem ipsum..... | Lorem ipsum ---> " << stringSimilarity("Lorem ipsum dolor sit amet, "
|
||||
"consetetur sadipscing elitr, "
|
||||
"sed diam nonumy eirmod tempor"
|
||||
"invidunt ut labore et dolore "
|
||||
"magna aliquyam erat, sed diam voluptua. "
|
||||
"At vero eos et accusam et justo duo dolores "
|
||||
"et ea rebum. Stet clita kasd gubergren, "
|
||||
"no sea takimata sanctus est Lorem "
|
||||
"ipsum dolor sit amet. "
|
||||
"Lorem ipsum dolor sit amet, "
|
||||
"consetetur sadipscing elitr, "
|
||||
"sed diam nonumy eirmod tempor "
|
||||
"invidunt ut labore et dolore magna "
|
||||
"aliquyam erat, sed diam voluptua. "
|
||||
"At vero eos et accusam et justo duo dolores "
|
||||
"et ea rebum. Stet clita kasd gubergren, "
|
||||
"no sea takimata sanctus est Lorem ipsum "
|
||||
"dolor sit amet.", "Lorem ipsum") << std::endl;
|
||||
"consetetur sadipscing elitr, "
|
||||
"sed diam nonumy eirmod tempor"
|
||||
"invidunt ut labore et dolore "
|
||||
"magna aliquyam erat, sed diam voluptua. "
|
||||
"At vero eos et accusam et justo duo dolores "
|
||||
"et ea rebum. Stet clita kasd gubergren, "
|
||||
"no sea takimata sanctus est Lorem "
|
||||
"ipsum dolor sit amet. "
|
||||
"Lorem ipsum dolor sit amet, "
|
||||
"consetetur sadipscing elitr, "
|
||||
"sed diam nonumy eirmod tempor "
|
||||
"invidunt ut labore et dolore magna "
|
||||
"aliquyam erat, sed diam voluptua. "
|
||||
"At vero eos et accusam et justo duo dolores "
|
||||
"et ea rebum. Stet clita kasd gubergren, "
|
||||
"no sea takimata sanctus est Lorem ipsum "
|
||||
"dolor sit amet.", "Lorem ipsum")
|
||||
<< std::endl;
|
||||
}
|
||||
Loading…
Reference in New Issue