1
0
Fork 0
forked from hashirama/Hakurei

add option to select the dictionary path

This commit is contained in:
千住柱間 2024-05-11 16:35:34 -04:00
parent 8b791f04bc
commit 6d43fe4a24
Signed by: hashirama
GPG key ID: 53E62470A86BC185
2 changed files with 33 additions and 23 deletions

BIN
a.out Executable file

Binary file not shown.

View file

@ -2,8 +2,12 @@
#include <vector> #include <vector>
#include <algorithm> #include <algorithm>
#include <limits> #include <limits>
#include <cstring>
#include <cctype>
#include <xcdat.hpp> #include <xcdat.hpp>
// as this is in test phase, i recommend testing with the input being "特別協力組合理事"
struct Entry { struct Entry {
std::string_view decoded_view; std::string_view decoded_view;
uint64_t id; uint64_t id;
@ -12,42 +16,47 @@ struct Entry {
int main(int argc, char* argv[]) { int main(int argc, char* argv[]) {
if (argc < 2) { if (argc < 2) {
std::cerr << "Usage: " << argv[0] << " <search_string> [--debug]" << std::endl; std::cerr << "Usage: " << argv[0] << " <search_string> [--debug] [--dict <path_to_dictionary>]" << std::endl;
return 1; return 1;
} }
const char* filename = "dict.bin"; std::string search_string;
std::string search_string = argv[1]; bool debug_mode = false;
bool debug_mode = false; // Debug mode flag std::string dict_file = "dict.bin"; // Default dictionary file path
// Check if --debug is passed // Parse command line arguments
if (argc == 3 && std::string(argv[2]) == "--debug") { for (int i = 1; i < argc; ++i) {
if (std::strcmp(argv[i], "--debug") == 0) {
debug_mode = true; debug_mode = true;
} else if (std::strcmp(argv[i], "--dict") == 0 && i + 1 < argc) {
dict_file = argv[i + 1];
i++; // Skip the next argument as it's the dictionary file path
} else {
search_string = argv[i];
}
} }
std::string raw_output; // To store raw output if (search_string.empty()) {
std::cerr << "Search string not provided." << std::endl;
return 1;
}
// The trie dictionary type from the four types std::string raw_output;
using trie_type = xcdat::trie_15_type; const auto trie = xcdat::load<xcdat::trie_15_type>(dict_file);
// Load the trie dictionary from the hardcoded file.
const auto trie = xcdat::load<trie_type>(filename);
std::vector<std::string> substrings; std::vector<std::string> substrings;
// Process the input string iteratively
while (!search_string.empty()) { while (!search_string.empty()) {
std::vector<Entry> results; std::vector<Entry> results;
// Common prefix search
auto itr = trie.make_prefix_iterator(search_string); auto itr = trie.make_prefix_iterator(search_string);
while (itr.next()) { while (itr.next()) {
results.emplace_back(itr.decoded_view(), itr.id()); results.emplace_back(itr.decoded_view(), itr.id());
} }
// Find the smallest common prefix
size_t min_length = std::numeric_limits<size_t>::max(); size_t min_length = std::numeric_limits<size_t>::max();
std::string_view smallest_prefix; std::string_view smallest_prefix;
for (const auto& entry : results) { for (const auto& entry : results) {
if (entry.decoded_view.size() < min_length) { if (entry.decoded_view.size() < min_length) {
min_length = entry.decoded_view.size(); min_length = entry.decoded_view.size();
@ -55,35 +64,36 @@ int main(int argc, char* argv[]) {
} }
} }
// Subtract the smallest common prefix from the input string
if (min_length > 0) { if (min_length > 0) {
std::string substring = search_string.substr(0, search_string.find(smallest_prefix)); std::string substring = search_string.substr(0, search_string.find(smallest_prefix));
if (!substring.empty()) { if (!substring.empty()) {
substrings.push_back(substring); substrings.push_back(substring);
} }
std::cout << search_string << " - " << smallest_prefix << " = "; std::cout << search_string << " - " << smallest_prefix << " = ";
if (debug_mode) { if (debug_mode) {
raw_output += search_string + " - " + smallest_prefix.data() + " = "; // Accumulate raw output raw_output += search_string + " - " + std::string(smallest_prefix) + " = ";
} }
size_t pos = search_string.find(smallest_prefix); size_t pos = search_string.find(smallest_prefix);
if (pos != std::string::npos) { if (pos != std::string::npos) {
search_string.erase(0, pos + smallest_prefix.length()); search_string.erase(0, pos + smallest_prefix.length());
} }
std::cout << search_string << std::endl; std::cout << search_string << std::endl;
if (debug_mode) { if (debug_mode) {
raw_output += search_string + '\n'; // Add the result to raw output raw_output += search_string + '\n';
} }
// Remove leading whitespace, if any
while (!search_string.empty() && std::isspace(search_string.front())) { while (!search_string.empty() && std::isspace(search_string.front())) {
search_string.erase(0, 1); search_string.erase(0, 1);
} }
} else { } else {
// If no common prefix found, break the loop
break; break;
} }
} }
// Print the stored raw output if debug mode is active
if (debug_mode) { if (debug_mode) {
std::cout << "Stored raw output:" << std::endl << raw_output << std::endl; std::cout << "Stored raw output:" << std::endl << raw_output << std::endl;
} }