void cut_input (char *DICT_PATH, char *HMM_PATH, char *USER_DICT) {
char *s;
Jieba handle = NewJieba (DICT_PATH, HMM_PATH, USER_DICT);
setlocale (LC_ALL, "");
printf ("Chinese word segmentation\n=========================\n\n");
while (s = getstr ()) {
if (strcmp (s, "EOF") == 0) {
free (s);
printf ("bye\n");
break;
} else {
size_t len = strlen (s);
CJiebaWord* words = Cut (handle, s, len);
CJiebaWord* x;
for (x = words; x && x->word; x++) {
/* printf ("%*.*s/", x->len, x->len, x->word); */
printf ("%d ", x->len / CJIEBA_WCHAR_SIZE);
}
printf ("\n");
free (s);
FreeWords (words);
}
}
FreeJieba (handle);
}
int main() {
LoadDictionary("dictionary.txt");
const char * test1results[] = { "ait", "qat", "dae", "quiz", "zed", "zax", "zit", "zea", "aue", "eau", "eat", "adz", "tuque", "ita", "quat", "qua", "uta", "tui", "tix", "tai", "tae", "taxi", "tau", "tax", "tad", "daut", "daze", "zati", "aitu", "adze", "quai", "quad", "quit", "taed" };
const int test1count = 34;
const int test1score = 35;
Results results1 = FindWords("dzxeaiqut", 3, 3);
checkEquals(results1, test1results, test1count, test1score, "test1");
FreeWords(results1);
const char * test2results[] = { "ply", "flir", "eik", "oye", "yuk", "wye", "reik", "wey", "rei", "plue", "ewt", "euk", "ire", "rew", "rue", "tye", "kir", "top", "toph", "lure", "ruly", "toy", "ure", "puer", "tyer", "lie", "yup", "pot", "yew", "fly", "uey", "puli", "upo", "lye", "ilk", "opt", "plu", "lur", "eyot", "kue", "poh", "phot", "pho", "pye", "flukier", "puy", "pul", "hot", "pur", "jot", "joy", "hop", "hoy", "flu", "weir", "oyer", "weil", "plie", "typo", "yeuk", "iure", "pyot", "puir", "pulk", "puly", "pure", "puri", "lire", "lier", "lieu", "erupt", "kilp", "kier", "kuri", "toyer", "glue", "flue", "twyer", "plier", "plyer", "pulik", "gluer", "gluey", "glyph", "fluyt", "fluey", "flier", "flyer", "yukier", "pulier", "gluier", "fluier" };
const int test2count = 92;
const int test2score = 117;
Results results2 = FindWords("qwertyuioplkjhgf", 4, 4);
checkEquals(results2, test2results, test2count, test2score, "test2");
FreeWords(results2);
const char * test3results[] = { "lou", "mol", "cert", "wex", "holk", "rew", "jupon", "mon", "upon", "rec", "rev", "crew", "poh", "rex", "vex", "hom", "mop", "mou", "til", "noh", "nom", "jol", "only", "kit", "lit", "once", "pol", "noup", "pom", "oup", "lop", "ilk", "upo", "hop", "hon", "holy", "wert", "moly", "reck", "trew", "oncer", "vert", "verb", "brew", "moup", "klik", "polk", "poly", "loup", "treck", "ponce" };
const int test3count = 51;
const int test3score = 55;
Results results3 = FindWords("qwertzxcvbmnjklpolkiujhyt", 5, 5);
checkEquals(results3, test3results, test3count, test3score, "test3");
FreeWords(results3);
const char * test4results[] = { "dad", "add", "dada" };
const int test4count = 3;
const int test4score = 3;
Results results4 = FindWords("dadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadadada", 10, 10);
checkEquals(results4, test4results, test4count, test4score, "test4");
FreeWords(results4);
const char * test5results[] = { "not", "bos", "oon", "bone", "tote", "noo", "non", "nebs", "nos", "bosket", "tete", "nek", "tee", "oot", "nonettos", "keb", "ono", "kons", "tot", "bon", "oos", "sot", "ons", "ten", "snoeks", "tet", "ketones", "oke", "sooks", "ton", "bot", "sen", "books", "too", "tene", "otto", "een", "kon", "note", "ene", "obe", "set", "sneb", "boo", "eek", "bet", "toot", "bee", "ben", "tone", "teen", "toetoe", "obo", "bootee", "sob", "one", "skeet", "ket", "tes", "tokens", "toe", "bes", "skeen", "nene", "eon", "ken", "nob", "net", "knees", "nee", "onos", "neb", "betook", "ens", "bonnet", "bete", "son", "neon", "obs", "oes", "bonks", "ose", "see", "nott", "besee", "noon", "nook", "oons", "ketone", "oont", "toes", "tent", "toon", "tons", "beento", "nenes", "kens", "eons", "took", "ebon", "boose", "eten", "book", "boot", "knot", "boon", "bott", "been", "nonbook", "beet", "bene", "koto", "bent", "bonk", "onto", "keto", "seen", "kete", "ones", "keet", "botone", "toko", "toke", "none", "nett", "nete", "tonk", "sone", "teek", "snot", "snob", "sook", "etens", "soot", "neks", "soon", "nobs", "noes", "okes", "nose", "oose", "tose", "beset", "boos", "tenons", "knee", "keen", "sket", "kebs", "besot", "keno", "kent", "knob", "toetoes", "obos", "tees", "ebook", "tens", "sett", "sekt", "sent", "snee", "seek", "sene", "tenon", "skee", "sken", "skeo", "notebook", "esne", "bosk", "bees", "bens", "obes", "enes", "noons", "nooks", "ottos", "tenet", "tenno", "tenne", "toons", "botte", "bonne", "beton", "benet", "benne", "bento", "boons", "tokes", "token", "nonet", "obento", "neons", "snook", "noose", "nones", "tonne", "tonks", "beknot", "teens", "tones", "snoot", "snoke", "snoek", "soote", "nonette", "notes", "bones", "totes", "onset", "boson", "kotos", "keeno", "kenos", "kente", "netes", "teene", "tense", "tetes", "ebons", "sonne", "seton", "sente", "tenes", "betes", "benes", "obese", "nektons", "neese", "betokens", "nebek", "knobs", "tennos", "tennes", "betons", "entetee", "bennet", "bonnes", "bennes", "ketose", "tonnes", "snooks", "snokes", "sootes", "bookoo", "bottes", "ketene", "keenos", "kennet", "nekton", "tenson", "entete", "settee", "sonnes", "setons", "sennet", "sonnet", "beseen", "nebeks", "botonee", "boneset", "betoken", "nonetto", "tonette", "bookoos", "bootees", "kennett", "ketenes", "nonbooks", "botonnee", "nonettes", "tonettes", "nonobese" };
const int test5count = 274;
const int test5score = 559;
Results results5 = FindWords("notebooknotenotesnotnotebooknotenotesnotnotebooknotenotesnotnotebooknotenotesnotnotebooknotenotesnotnotebooknotenotesnotnotebooknotenotesnotnotebooknotenotesnot", 8, 20);
checkEquals(results5, test5results, test5count, test5score, "test5");
FreeWords(results5);
FreeDictionary();
std::cout << "Done!" << std::endl;
return 0;
}
void CutDemo() {
printf("CutDemo:\n");
static const char* DICT_PATH = "./dict/jieba.dict.utf8";
static const char* HMM_PATH = "./dict/hmm_model.utf8";
static const char* USER_DICT = "./dict/user.dict.utf8";
// init will take a few seconds to load dicts.
Jieba handle = NewJieba(DICT_PATH, HMM_PATH, USER_DICT);
char** words = Cut(handle, "南京市长江大桥");
char** x = words;
while (x && *x) {
printf("%s\n", *x);
x++;
}
FreeWords(words);
FreeJieba(handle);
}
void ExtractDemo() {
printf("ExtractDemo:\n");
static const char* DICT_PATH = "./dict/jieba.dict.utf8";
static const char* HMM_PATH = "./dict/hmm_model.utf8";
static const char* IDF_PATH = "./dict/idf.utf8";
static const char* STOP_WORDS_PATH = "./dict/stop_words.utf8";
static const char* USER_DICT = "./dict/user.dict.utf8";
// init will take a few seconds to load dicts.
Extractor handle = NewExtractor(DICT_PATH,
HMM_PATH,
IDF_PATH,
STOP_WORDS_PATH,
USER_DICT);
char** words = Extract(handle, "我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。", 5);
char** x = words;
while (x && *x) {
printf("%s\n", *x);
x++;
}
FreeWords(words);
FreeExtractor(handle);
}
