Fuzzy matching of an OCR output in text file - ocr

Question

I have a question regarding partial match of two strings.
I have a string and I need to validate it. To be more specific, I have an output from OCR reading and it contains some mistakes, of course. I need to check if the string is really there but as it can be written incorrectly I need only 70% match.
Is it possible to do that in UiPath? The string is in notepad (.txt) so any idead would be helpful.

Answer 1

Try passing OCR output/words_detected against a base word.(double fuzzyness is 0-1)
list<string> Search(string word, list<string> wordList, double fuzzyness) {
list<string> foundWords;
for (string s : wordList) {
int levenshteinDistance = LevenshteinDistance(word, s);
int length = max(word.length(), s.length());
double score = 1.0 - (double)levenshteinDistance / length;
if (score > fuzzyness) foundWords.push_back(s);
}
if (foundWords.size() > 1) {
for (double d = fuzzyness; ; d++) {
foundWords = Search(word, wordList, d);
if (foundWords.size() == 1) break;
}
}
return foundWords;}
int LevenshteinDistance(string src, string dest) {
std::vector<vector<int>> d;
d.resize((int)src.size() + 1, std::vector<int>((int)dest.size() + 1, 0));
int i, j, cost;
std::vector<char> str1(src.begin(), src.end());
std::vector<char> str2(dest.begin(), dest.end());
for (i = 0; i <= str1.size(); i++) d[i][0] = i;
for (j = 0; j <= str2.size(); j++) d[0][j] = j;
for (i = 1; i <= str1.size(); i++) {
for (j = 1; j <= str2.size(); j++) {
if (str1[i - 1] == str2[j - 1]) cost = 0;
else cost = 1;
d[i][j] = min(d[i - 1][j] + 1, min(d[i][j - 1] + 1, d[i - 1][j - 1] + cost));
if ((i > 1) && (j > 1) && (str1[i - 1] == str2[j - 2]) && (str1[i - 2] == str2[j - 1])) d[i][j] = min(d[i][j], d[i - 2][j - 2] + cost);
}
}
return d[str1.size()][str2.size()];}