#include "../src/unicode.h"

#include <cstdio>
#include <string>
#include <utility>
#include <vector>

int main() {
    const std::vector<std::pair<std::vector<uint32_t>, std::vector<uint32_t>>> normalization = {
        {{}, {}},
        {{0x65, 0x301}, {0xE9}},
        {{0xE9}, {0xE9}},
        {{0x212B}, {0xC5}},
        {{0x61, 0x315, 0x300}, {0xE0, 0x315}},
        {{0x61, 0x305, 0x301}, {0x61, 0x305, 0x301}},
        {{0x301, 0x327}, {0x327, 0x301}},
        {{0x1100, 0x1161, 0x11A8}, {0xAC01}},
        {{0xAC01}, {0xAC01}},
        {{0xFB01, 0xFF21}, {0xFB01, 0xFF21}},
        {{0x958}, {0x915, 0x93C}},
        {{0x1D15E}, {0x1D157, 0x1D165}},
    };
    for (const auto & test : normalization) {
        if (unicode_cpts_normalize_nfc(test.first) != test.second || unicode_cpts_normalize_nfc(test.second) != test.second) {
            fprintf(stderr, "unexpected NFC normalization\n");
            return 1;
        }
    }

    const std::vector<std::string> regex_exprs = {
        "[~][A-Za-z]+| ?[\\p{S}]+|\\s+",
    };
    const std::vector<std::string> expected = { " ~", "foo" };
    const auto actual = unicode_regex_split(" ~foo", regex_exprs, false);

    if (actual != expected) {
        fprintf(stderr, "unexpected split:");
        for (const auto & piece : actual) {
            fprintf(stderr, " [%s]", piece.c_str());
        }
        fprintf(stderr, "\n");
        return 1;
    }

    return 0;
}