46 lines
1.3 KiB
C++
46 lines
1.3 KiB
C++
#include "token.h"
|
|
#include <algorithm>
|
|
#include <random>
|
|
|
|
void Tokenizer::add(std::string word) {
|
|
int id = wordToId.size();
|
|
wordToId[word] = id;
|
|
idToWord[id] = word;
|
|
}
|
|
|
|
std::string Tokenizer::getWord(int id) {
|
|
return idToWord.count(id) ? idToWord[id] : "";
|
|
}
|
|
|
|
std::vector<int> Tokenizer::textToTokens(const std::string& text) {
|
|
std::vector<int> tokens;
|
|
size_t pos = 0;
|
|
while (pos < text.length()) {
|
|
int longestId = -1; size_t longestLen = 0;
|
|
for (auto const& [word, id] : wordToId) {
|
|
if (text.compare(pos, word.length(), word) == 0) {
|
|
if (word.length() > longestLen) {
|
|
longestLen = word.length(); longestId = id;
|
|
}
|
|
}
|
|
}
|
|
if (longestId != -1) {
|
|
tokens.push_back(longestId);
|
|
pos += longestLen;
|
|
} else pos++;
|
|
}
|
|
return tokens;
|
|
}
|
|
|
|
Embedder::Embedder(int vSize, int dim) {
|
|
std::mt19937 gen(42);
|
|
std::uniform_real_distribution<double> dist(-1.0, 1.0);
|
|
matrix.resize(vSize, std::vector<double>(dim));
|
|
for(int i=0; i<vSize; i++)
|
|
for(int j=0; j<dim; j++) matrix[i][j] = dist(gen);
|
|
}
|
|
|
|
std::vector<double> Embedder::get(int id) {
|
|
if (id >= 0 && id < (int)matrix.size()) return matrix[id];
|
|
return std::vector<double>(matrix[0].size(), 0.0);
|
|
} |