Created
August 10, 2011 10:41
-
-
Save snapbug/1136534 to your computer and use it in GitHub Desktop.
43 Line C++ Index and Search
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <algorithm> | |
| #include <cmath> | |
| #include <fstream> | |
| #include <iostream> | |
| #include <map> | |
| #include <sstream> | |
| #include <vector> | |
| using namespace std; | |
| int main(int argc, char **argv) { | |
| string line, term; | |
| ifstream file(argv[1]); | |
| map<string, map<long, long> > index; | |
| map<long, long>::iterator iter; | |
| vector<string> documents; | |
| while (file) { | |
| getline(file, line); | |
| stringstream ss(line); | |
| long document_length = 0; | |
| while (ss >> term && ++document_length) | |
| index[term][documents.size()] = (iter = index[term].find(documents.size())) != index[term].end() ? iter->second + 1 : 1; | |
| index[" length"][documents.size()] = document_length; | |
| documents.push_back(line); | |
| } | |
| vector<pair<double, long> > results(documents.size()); | |
| while (cin) { | |
| for (long i = 0; i < results.size(); i++) | |
| results[i] = make_pair(0, i); | |
| getline(cin, line); | |
| stringstream ss(line); | |
| while (ss >> term) | |
| if (index.find(term) != index.end()) | |
| for (iter = index[term].begin(); iter != index[term].end(); ++iter) | |
| results[iter->first].first += log(1.0 * documents.size() / index[term].size()) * iter->second / index[" length"][iter->first]; | |
| sort(results.rbegin(), results.rend()); | |
| for (vector<pair<double, long> >::iterator result_iter = results.begin(); result_iter != results.end() && result_iter->first; ++result_iter) | |
| cout << result_iter->first << ": " << documents[result_iter->second] << endl; | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment