int nmatch(char *s1, char *s2)
{
if (*s1 != '\0' && *s2 == '*')
return (nmatch(s1 + 1, s2) + nmatch(s1, s2 + 1));
else if (*s1 == '\0' && *s2 == '*')
return (nmatch(s1, s2 + 1));
else if (*s1 == *s2 && *s1 != '\0' && *s2 != '\0')
return (nmatch(s1 + 1, s2 + 1));
else if (*s1 == '\0' && *s2 == '\0')
return (1);
return (0);
}
int nmatch(char *s1, char *s2)
{
if (!*s1 && !*s2)
return (1);
else if (*s1 == *s2)
return (nmatch(s1 + 1, s2 + 1));
else if (*s2 == '*' && !*s1)
return (nmatch(s1, s2 + 1));
else if (*s2 == '*' && *s1)
return (nmatch(s1 + 1, s2) + nmatch(s1, s2 + 1));
return (0);
}
int main (int ac, char **av)
{
if (ac > 1)
{
printf("%d", nmatch(av[1], av[2]));
}
}
int nmatch(char *s1, char *s2)
{
static int i = 0;
if (*s2)
if (*s2 == '*' && *(s2 + 1) == '\0')
return (i+1);
if (*s2 == '*' && *s1)
{
if (nmatch(s1, s2 + 1))
return (i+1);
else
return (nmatch(s1 + 1, s2));
}
if (*s2 == '\0' && *s1 == '\0')
return (i+1);
if (*s1 == *s2)
return(nmatch(s1 + 1, s2 + 1));
else
return (i);
}
unsigned rtps_def_trace (unsigned handle, const char *name)
{
unsigned i;
for (i = 0; i < MAX_HANDLE_TRACES && rtps_handle_traces [i].handle; i++)
if (rtps_handle_traces [i].handle == handle)
return (rtps_handle_traces [i].mode);
for (i = 0; i < MAX_NAME_TRACES && rtps_name_traces [i].name [0]; i++)
if (!nmatch (rtps_name_traces [i].name, name, NM_NOESCAPE))
return (rtps_name_traces [i].mode);
return (dds_dtrace);
}
void t_ignore (const char *cmd, DDS_DomainParticipant part)
{
Topic *tp;
char spec [192];
skip_blanks (&cmd);
skip_string (&cmd, spec);
if (spec [0]) {
lock_take (topic_lock);
LIST_FOREACH (topics, tp)
if (tp->active &&
!nmatch (spec, tp->topic_name, NM_CASEFOLD))
stop_reader (part, tp);
lock_release (topic_lock);
}
}
int main (int argc, const char *argv[])
{
const char *name, *pattern, *s;
unsigned i;
int flags = 0, r;
if (argc == 4)
if (argv [1][0] == '-') {
pattern = argv [2];
name = argv [3];
s = argv [1];
while (*++s != '\0')
if (*s == 'e')
flags |= NM_NOESCAPE;
else if (*s == 'c')
flags |= NM_CASEFOLD;
else if (*s == 's')
flags |= NM_SQL;
else
usage ();
}
else
usage ();
else if (argc == 3) {
pattern = argv [1];
name = argv [2];
}
else
usage ();
printf ("NoEscape:%u, CaseFold:%u, SQL:%u, Pattern:'%s', Name:'%s' -> ",
(flags & NM_NOESCAPE) != 0,
(flags & NM_CASEFOLD) != 0,
(flags & NM_SQL) != 0,
pattern,
name);
r = nmatch (pattern, name, flags);
if (r == NM_MATCH)
printf ("Match!\r\n");
else
printf ("No match\n");
}
void train_once_KernelPerceptronModel(KernelPerceptron mdl, const CoNLLCorpus corpus, int max_rec) {
long match = 0, total = 0;
//size_t slen=0;
double s_initial = dsecnd();
int max_sv = 0;
log_info("Total number of training instances %d", (max_rec == -1) ? DArray_count(corpus->sentences) : max_rec);
for (int si = 0; si < ((max_rec == -1) ? DArray_count(corpus->sentences) : max_rec); si++) {
FeaturedSentence sent = (FeaturedSentence) DArray_get(corpus->sentences, si);
debug("Building feature matrix for sentence %d", si);
set_FeatureMatrix(NULL, corpus, si);
set_adjacency_matrix_fast(corpus, si, mdl, false);
max_sv += (sent->length + 1) * sent->length - sent->length;
int *model = parse(sent);
//printfarch(model, sent->length);
debug("Parsing sentence %d of length %d is done", si, sent->length);
int *empirical = get_parents(sent);
//printfarch(empirical, sent->length);
int nm = nmatch(model, empirical, sent->length);
debug("Model matches %d arcs out of %d arcs", nm, sent->length);
if (nm != sent->length) { // root has no valid parent.
log_info("Sentence %d (section %d) of length %d (%d arcs out of %d arcs are correct)", si, sent->section, sent->length, nm, sent->length);
int sentence_length = sent->length;
for (int to = 1; to <= sentence_length; to++) {
if (model[to] != empirical[to]) {
update_alpha(mdl, si, model[to], to, sent, -1);
update_alpha(mdl, si, empirical[to], to, sent, +1);
}
}
} else {
log_info("Sentence %d (section %d) of length %d (Perfect parse)", si, sent->section, sent->length);
}
size_t nsuccess;
if (budget_method == RANDOMIZED) {
if (mdl->M > budget_target) {
size_t nbefore = mdl->M;
size_t nasked = nbefore - budget_target;
nsuccess = delete_n_random_hypothesis(mdl, nasked);
log_info("%lu vectors deleted (%lu asked). Current hypothesis set size reduced from %lu to %lu", nsuccess, nasked, nbefore, mdl->M);
}
}
mdl->c++;
free_feature_matrix(corpus, si);
match += nm;
total += (sent->length);
if ((si + 1) % 1000 == 0 && si != 0) {
log_info("Running training accuracy %lf after %d sentence.", (match * 1.) / total, si + 1);
unsigned nsv = mdl->M;
log_info("%u (%f of total %d) support vectors", nsv, (nsv * 1.) / max_sv, max_sv);
}
free(model);
free(empirical);
}
unsigned nsv = mdl->M;
log_info("Running training accuracy %lf", (match * 1.) / total);
log_info("%u (%f of total %d) support vectors", nsv, (nsv * 1.) / max_sv, max_sv);
if (verbosity > 0) {
dump_support_vectors(mdl);
}
update_average_alpha(mdl);
return;
}
Endpoint *ep_create (DDS_DomainParticipant part,
DDS_BuiltinTopicKey_t *key,
const char *topic_name,
const char *type_name,
DDS_PublicationBuiltinTopicData *data,
int writer)
{
Topic *tp;
Endpoint *ep;
printf ("* New %s (%s/%s)\r\n", (writer) ? "writer" : "reader",
topic_name, type_name);
ep = ep_lookup (key);
if (ep) {
if (writer) {
ep->data = *data;
tp = ep->topic;
ep->data.topic_name = tp->topic_name;
ep->data.type_name = tp->type_name;
}
return (ep);
}
ep = malloc (sizeof (Endpoint));
if (!ep) {
fprintf (stderr, "Not enough memory to create endpoint!\r\n");
return (NULL);
}
ep->topic = tp = t_lookup (topic_name);
if (!tp) {
ep->link = NULL;
tp = malloc (sizeof (Topic));
if (!tp) {
fprintf (stderr, "Not enough memory to create topic!\r\n");
free (ep);
return (NULL);
}
if (writer) {
tp->writers = ep;
tp->readers = NULL;
}
else {
tp->readers = ep;
tp->writers = NULL;
}
tp->topic_name = strdup (topic_name);
tp->type_name = strdup (type_name);
tp->active = 0;
tp->topic = NULL;
tp->dtype = NULL;
tp->sub = NULL;
tp->ts = NULL;
tp->ndata = tp->ndispose = tp->nnowriter = 0;
ep->topic = tp;
LIST_ADD_TAIL (topics, *tp);
}
else if (writer) {
ep->link = tp->writers;
tp->writers = ep;
}
else {
ep->link = tp->readers;
tp->readers = ep;
}
ep->writer = writer;
ep->key = *key;
if (ep->writer) {
ep->data = *data;
ep->data.topic_name = tp->topic_name;
ep->data.type_name = tp->type_name;
}
LIST_ADD_TAIL (endpoints, *ep);
/* Endpoint successfully added -- check if we need a reader. */
if (writer &&
!ep->link &&
auto_filter [0] &&
!nmatch (auto_filter, tp->topic_name, NM_CASEFOLD))
start_reader (part, tp);
return (ep);
}
void train_once_PerceptronModel(PerceptronModel mdl, const CoNLLCorpus corpus, int max_rec) {
long match = 0, total = 0;
//size_t slen=0;
log_info("Total number of training instances %d", (max_rec == -1) ? DArray_count(corpus->sentences) : max_rec);
for (int si = 0; si < ((max_rec == -1) ? DArray_count(corpus->sentences) : max_rec); si++) {
//log_info("Parsing sentence %d/%d", si+1, DArray_count(corpus));
FeaturedSentence sent = (FeaturedSentence) DArray_get(corpus->sentences, si);
start(&parser_rate);
//debug("Building feature matrix for sentence %d of length %d", si, sent->length);
//set_FeatureMatrix(NULL, corpus, si);
//printfembedding(sent->feature_matrix, sent->length);
debug("Building adjacency matrix for sentence %d of length %d", si, sent->length);
build_adjacency_matrix(corpus, si, mdl->embedding_w, NULL);
//printfmatrix(sent->adjacency_matrix, sent->length);
//log_info("Adjacency matrix construction is done");
int *model = parse(sent);
stop(&parser_rate);
debug("Parsing sentence %d is done", si);
int *empirical = get_parents(sent);
/*
log_info("Model:");
printfarch(model, sent->length);
log_info("Empirical:");
printfarch(empirical, sent->length);
*/
int nm = nmatch(model, empirical, sent->length);
debug("Model matches %d arcs out of %d arcs", nm, sent->length);
if (nm != sent->length) { // root has no valid parent.
if (corpus->disrete_patterns_parts) {
log_info("I have discrete features");
DArray* model_features = DArray_create(sizeof (uint32_t), 16);
DArray* empirical_features = DArray_create(sizeof (uint32_t), 16);
for (int fi = 1; fi < sent->length; fi++) {
fill_features(mdl->features->map, model_features, model[fi], fi, sent);
fill_features(mdl->features->map, empirical_features, empirical[fi], fi, sent);
}
for (int i = 0; i < DArray_count(model_features); i++) {
uint32_t *fidx = (uint32_t *) DArray_get(model_features, i);
mdl->discrete_w->data[*fidx] -= 1.0;
mdl->discrete_w_avg->data[*fidx] -= (mdl->c) * 1.0;
mdl->discrete_w_temp->data[*fidx] -= 1.0;
}
for (int i = 0; i < DArray_count(empirical_features); i++) {
uint32_t *fidx = (uint32_t *) DArray_get(empirical_features, i);
mdl->discrete_w->data[*fidx] += 1.0;
mdl->discrete_w_avg->data[*fidx] += (mdl->c) * 1.0;
mdl->discrete_w_temp->data[*fidx] += 1.0;
}
DArray_destroy(model_features);
DArray_destroy(empirical_features);
}
for (int i = 1; i <= sent->length; i++) {
if (model[i] != empirical[i]){
// -1 for Model arch
embedding_feature(sent, model[i], i, xformed_v);
vadd(mdl->embedding_w, xformed_v, -1.0);
vadd(mdl->embedding_w_temp, xformed_v, -1.0);
vadd(mdl->embedding_w_avg, xformed_v, -(mdl->c));
// +1 for Gold arc
embedding_feature(sent, empirical[i], i, xformed_v);
vadd(mdl->embedding_w, xformed_v, 1.0);
vadd(mdl->embedding_w_temp, xformed_v, 1.0);
vadd(mdl->embedding_w_avg, xformed_v, (mdl->c));
}
//free(real_embedding);
//free(model_embedding);
}
}
free_feature_matrix(corpus, si);
mdl->c++;
match += nm;
total += (sent->length);
if (si % 1000 == 0 && si > 0) {
log_info("Running training accuracy %lf", (match * 1.) / total);
}
free(model);
free(empirical);
//free_sentence_structures(sent);
}
log_info("Running training accuracy %lf", (match * 1.) / total);
if (corpus->disrete_patterns_parts) {
for (int i = 0; i < mdl->n; i++) {
// mdl->w_avg[i] /= (numit * DArray_count(corpus));
//mdl->w[i] -=(mdl->w_avg[i])/(mdl->c);
mdl->discrete_w_temp->data[i] = mdl->discrete_w->data[i] - (mdl->discrete_w_avg->data[i]) / (mdl->c);
}
}
//vadd(mdl->w_cont, mdl->w_cont_avg, -1./(mdl->c), SCODE_FEATURE_VECTOR_LENGTH);
memcpy(mdl->embedding_w_temp->data, mdl->embedding_w->data, mdl->embedding_w->n * sizeof (float));
vadd(mdl->embedding_w_temp, mdl->embedding_w_avg, -1. / (mdl->c));
// free(mdl->w);
// mdl->w = mdl->w_avg;
//free_feature_matrix(sent);
}
int main(void)
{
printf("%d\n", nmatch("bonjour", "**j**"));
return (0);
}
/* Return a pointer to the interface struct for the passed address. */
struct ifreq *
getif(int s, struct in_addr *addrp)
/* socket file descriptor */
/* destination address on interface */
{
int maxmatch;
int len, m, incr;
struct ifreq *ifrq, *ifrmax;
struct sockaddr_in *sip;
char *p;
/* If no address was supplied, just return NULL. */
if (!addrp)
return (struct ifreq *) 0;
/* Get the interface config if not done already. */
if (ifconf.ifc_len == 0) {
#ifdef SVR4
/*
* SysVr4 returns garbage if you do this the obvious way!
* This one took a while to figure out... -gwr
*/
struct strioctl ioc;
ioc.ic_cmd = SIOCGIFCONF;
ioc.ic_timout = 0;
ioc.ic_len = sizeof(ifreq);
ioc.ic_dp = (char *) ifreq;
m = ioctl(s, I_STR, (char *) &ioc);
ifconf.ifc_len = ioc.ic_len;
ifconf.ifc_req = ifreq;
#else /* SVR4 */
ifconf.ifc_len = sizeof(ifreq);
ifconf.ifc_req = ifreq;
m = ioctl(s, SIOCGIFCONF, (caddr_t) & ifconf);
#endif /* SVR4 */
if ((m < 0) || (ifconf.ifc_len <= 0)) {
report(LOG_ERR, "ioctl SIOCGIFCONF");
return (struct ifreq *) 0;
}
}
maxmatch = 7; /* this many bits or less... */
ifrmax = (struct ifreq *) 0;/* ... is not a valid match */
p = (char *) ifreq;
len = ifconf.ifc_len;
while (len > 0) {
ifrq = (struct ifreq *) p;
if (ifrq->ifr_addr.sa_family == AF_INET) {
sip = (struct sockaddr_in *) &ifrq->ifr_addr;
m = nmatch((u_char *)addrp, (u_char *)&(sip->sin_addr));
if (m > maxmatch) {
maxmatch = m;
ifrmax = ifrq;
}
}
/* XXX - Could this be just #ifndef IFNAMSIZ instead? -gwr */
#if (BSD - 0) < 43
/* BSD not defined or earlier than 4.3 */
incr = sizeof(*ifrq);
#else /* NetBSD */
incr = ifrq->ifr_addr.sa_len + IFNAMSIZ;
#endif /* NetBSD */
p += incr;
len -= incr;
}
return ifrmax;
}
int *parsing_file(char *file_name, int *counter, llist l_args)
{
FILE *fp;
FILE *np;
char *line = NULL;
size_t len = 0;
ssize_t read;
int i = 1;
int comment_count = 0;
DIR *d;
char *directory = make_directory(l_args->directory, file_name);
int sub_dir = l_args->pr_s;
char *org_dir = l_args->directory;
struct dirent *dir;
if (nmatch(file_name, "*/..") == 1 || nmatch(file_name, "*/.") == 1 ||
nmatch(file_name, ".") == 1 || nmatch(file_name, "..") == 1 ||
nmatch(file_name, "no_comment") == 1)
return (counter);
counter[3] = counter[3] + 1;
if (is_directory(file_name) == 1 && nmatch(file_name, org_dir) == 0)
{
d = opendir(file_name);
if (d && sub_dir == 1)
{
printf(ANSI_COLOR_BLUE"!---> Reading directory '%s':\n"ANSI_COLOR_RESET,
file_name);
while ((dir = readdir(d)) != NULL)
{
check_directory(directory, 1);
counter = parsing_file(make_directory(file_name, dir->d_name),
counter, l_args);
}
printf(ANSI_COLOR_BLUE"End of directory '%s' <---!\n"ANSI_COLOR_RESET,
file_name);
return (counter);
closedir(d);
}
return (counter);
}
printf("\n> Reading file: '%s'\n", file_name);
printf("Destination: '%s'\n", directory);
if ((fp = fopen(file_name, "r")) == NULL)
{
printf(ANSI_COLOR_RED"! Error while reading file '%s'\n" ANSI_COLOR_RESET
, (file_name ? file_name : " "));
counter[1] = counter[1] + 1;
return (counter);
}
if ((np = fopen(directory, "w+")) == NULL)
{
printf(ANSI_COLOR_RED"! Error while creating file '%s'\n"ANSI_COLOR_RESET
, (file_name ? file_name : " "));
counter[1] = counter[1] + 1;
return (counter);
}
counter[0] = counter[0] + 1;
while ((read = getline(&line, &len, fp)) != -1)
comment_count = write_file(np, line, comment_count);
printf("Total of comments deleted: %d\n", comment_count);
printf(ANSI_COLOR_GREEN "--> Done for %s\n\n"ANSI_COLOR_RESET, file_name);
counter[2] = counter[2] + comment_count;
return (counter);
fclose(fp);
fclose (np);
}
