int parse_opts(int argc, char * const *argv, char const **ttyfile,
char const **conffile, int *verify, int *usertscts,
struct sdp_work **cmd_head)
{
char c;
*conffile = NULL;
*ttyfile = NULL;
static struct option long_options[] = {
{"help", no_argument, 0, 'h' },
{"verify", no_argument, 0, 'v' },
{"no-rtscts", no_argument, 0, 'n' },
{0, 0, 0, 0 },
};
while ((c = getopt_long(argc, argv, "+hvn", long_options, NULL)) != -1) {
switch (c)
{
case 'h':
case '?':
print_usage();
return -1;
case 'n':
*usertscts = 0;
break;
case 'v':
*verify = 1;
break;
}
}
// Options parsed, get mandatory arguments...
if (optind >= argc) {
fprintf(stderr, "non optional argument UART is missing\n");
return -1;
}
*ttyfile = argv[optind];
optind++;
if (optind >= argc) {
fprintf(stderr, "non optional argument CONFIG is missing\n");
return -1;
}
*conffile = argv[optind];
optind++;
if (optind < argc) {
// Parse optional job arguments...
*cmd_head = parse_cmd_args(argc - optind, &argv[optind]);
}
return 0;
}
boost::optional<Config> create_config(int argc, char const* argv[]) {
opts::variables_map vmap = parse_cmd_args(argc, argv);
if (vmap.count("help")) {
std::cout << create_parse_format() << std::endl;
return boost::optional<Config>();
}
Config config;
config.image_path = vmap.count("image_path")
? vmap["image_path"].as<std::string>()
: "";
return boost::optional<Config>(config);
}
int parse_opts(int argc, char * const *argv, char const **configdir,
int *verify, struct sdp_work **cmd_head)
{
int c;
static struct option long_options[] = {
{"help", no_argument, 0, 'h' },
{"debugmode", no_argument, 0, 'd' },
{"verify", no_argument, 0, 'v' },
{"configdir", required_argument, 0, 'c' },
{0, 0, 0, 0 },
};
while ((c = getopt_long(argc, argv, "+hdvc:", long_options, NULL)) != -1) {
switch (c)
{
case 'h':
case '?':
print_usage();
return 1;
case 'd':
debugmode = 1; /* global extern */
break;
case 'v':
*verify = 1;
break;
case 'c':
*configdir = optarg;
break;
}
}
if (optind < argc) {
// Parse optional job arguments...
*cmd_head = parse_cmd_args(argc - optind, &argv[optind]);
}
else
{
*cmd_head = NULL;
}
return 0;
}
int
main(int argc, char *argv[])
{
pid_t pid;
mpssenv_init(&mpssenv);
parse_cmd_args(argc, argv);
setsighandlers();
if (logfp != stderr) {
if ((logfp = fopen(LOGFILE_NAME, "a+")) == NULL) {
fprintf(stderr, "cannot open logfile '%s'\n", LOGFILE_NAME);
exit(EBADF);
}
}
mpsslog(PINFO, "MPSS Daemon start\n");
if ((miclist = mpss_get_miclist(&mpssenv, NULL)) == NULL) {
mpsslog(PINFO, "MIC module not loaded\n");
exit(2);
}
if (logfp == stderr) {
start_daemon();
} else {
start_pid = getpid();
switch ((pid = fork())) {
case -1:
fprintf(stderr, "cannot fork: %s\n", strerror(errno));
exit(ENOEXEC);
case 0:
start_daemon();
default:
pause();
}
}
exit(0);
}
/* Initialise the game and return the state structure or NULL on failure: */
nbstate *init(int argc, char *argv[])
{
GR_PROP *prop;
nbstate *state;
GR_SCREEN_INFO si;
GR_BITMAP cursor = 0;
GR_WM_PROPERTIES props;
/* Try to connect to the Nano-X server: */
if(GrOpen() < 1) {
fprintf(stderr, "Couldn't connect to Nano-X server\n");
return NULL;
}
/* Check that the server was built with alpha blending support
* (necessary for the alpha blended sprites and special effects): */
GrGetScreenInfo(&si);
if(!si.alphablend) {
fprintf(stderr, "Error: Nano-X server was built without alpha "
"blending support\nSet ALPHABLENDING = 1 in "
"include/device.h, rebuild, and try again.\n");
return NULL;
}
/* Allocate the state structure and initialise it with defaults: */
if(!(state = malloc(sizeof(nbstate)))) return NULL;
setup_default_state(state);
/* Try to parse the command line arguments: */
if(parse_cmd_args(state, argc, argv)) {
free(state);
return NULL;
}
/* Try to load the game file: */
if(load_game_file(state)) {
free(state);
return NULL;
}
/* Load the high score file: */
load_hiscore(state);
/* Calculate the canvas size: */
state->canvaswidth = state->width * state->brickwidth;
state->canvasheight = state->scores.h + state->ball.s->h +
(2 * BALLS_BORDER) +
(state->height * state->brickheight) +
3 * state->brickheight + state->batheight;
/* Place the bat in the centre of the window: */
state->batx = state->canvaswidth / 2;
/* Create various pixmaps and alpha channels: */
state->scores.p = GrNewPixmap(state->canvaswidth, state->scores.h,
NULL);
state->scores.a = GrNewAlpha(state->canvaswidth, state->scores.h);
state->canvas = GrNewPixmap(state->canvaswidth, state->canvasheight,
NULL);
/* The new and old canvasses are only used when screen fading is
* enabled: */
if(state->faderate) {
state->newcanvas = GrNewPixmap(state->canvaswidth,
state->canvasheight, NULL);
state->oldcanvas = GrNewPixmap(state->canvaswidth,
state->canvasheight, NULL);
}
state->brickalpha = GrNewAlpha(state->brickwidth, state->brickheight);
/* Start off with the canvas completely black: */
GrSetGCForeground(state->gc, GR_COLOR_BLACK);
GrFillRect(state->canvas, state->gc, 0, 0, state->canvaswidth,
state->canvasheight);
/* If there is a window manager running, place the window off the
* screen and let the window manager move it where it wants (avoids
* flicker if we were to draw the window on screen before the window
* manager moved it somewhere else): */
if(GrGetWindowProperty(GR_ROOT_WINDOW_ID, "WINDOW_MANAGER", &prop)) {
free(prop);
state->winx = GR_OFF_SCREEN;
}
/* Create the output window: */
state->wid = GrNewWindow(GR_ROOT_WINDOW_ID, state->winx, 0,
state->canvaswidth, state->canvasheight, 0, 0, 0);
/* Set the window title: */
props.flags = GR_WM_FLAGS_TITLE;
props.title = "NanoBreaker";
GrSetWMProperties(state->wid, &props);
/* Make the cursor over the output window be invisible: */
GrSetCursor(state->wid, 1, 1, 1, 1, 0, 0, &cursor, &cursor);
/* Select the events we want to receive for the output window: */
GrSelectEvents(state->wid, GR_EVENT_MASK_CLOSE_REQ |
GR_EVENT_MASK_EXPOSURE |
GR_EVENT_MASK_BUTTON_DOWN |
GR_EVENT_MASK_KEY_DOWN |
GR_EVENT_MASK_KEY_UP |
GR_EVENT_MASK_UPDATE |
GR_EVENT_MASK_TIMER);
/* Select for mouse position events on the root window so we can move
* the bat even when the pointer strays outside the window (which it
* often does because the cursor is invisible you don't know exactly
* where it is): */
GrSelectEvents(GR_ROOT_WINDOW_ID, GR_EVENT_MASK_MOUSE_POSITION);
/* Map the output window (make it visible): */
GrMapWindow(state->wid);
/* Create the one second periodic timer that is used to decrement the
* power-up and power-down timers: */
state->tid = GrCreateTimer(state->wid, 1000, GR_TRUE);
/* Reset the game: */
reset_game(state);
return state; /* Return the newly allocated state structure. */
}
static void add_cmd(const char *cmdstr)
{
sed_cmd_t *sed_cmd;
unsigned len, n;
/* Append this line to any unfinished line from last time. */
if (G.add_cmd_line) {
char *tp = xasprintf("%s\n%s", G.add_cmd_line, cmdstr);
free(G.add_cmd_line);
cmdstr = G.add_cmd_line = tp;
}
/* If this line ends with unescaped backslash, request next line. */
n = len = strlen(cmdstr);
while (n && cmdstr[n-1] == '\\')
n--;
if ((len - n) & 1) { /* if odd number of trailing backslashes */
if (!G.add_cmd_line)
G.add_cmd_line = xstrdup(cmdstr);
G.add_cmd_line[len-1] = '\0';
return;
}
/* Loop parsing all commands in this line. */
while (*cmdstr) {
/* Skip leading whitespace and semicolons */
cmdstr += strspn(cmdstr, semicolon_whitespace);
/* If no more commands, exit. */
if (!*cmdstr) break;
/* if this is a comment, jump past it and keep going */
if (*cmdstr == '#') {
/* "#n" is the same as using -n on the command line */
if (cmdstr[1] == 'n')
G.be_quiet++;
cmdstr = strpbrk(cmdstr, "\n\r");
if (!cmdstr) break;
continue;
}
/* parse the command
* format is: [addr][,addr][!]cmd
* |----||-----||-|
* part1 part2 part3
*/
sed_cmd = xzalloc(sizeof(sed_cmd_t));
/* first part (if present) is an address: either a '$', a number or a /regex/ */
cmdstr += get_address(cmdstr, &sed_cmd->beg_line, &sed_cmd->beg_match);
sed_cmd->beg_line_orig = sed_cmd->beg_line;
/* second part (if present) will begin with a comma */
if (*cmdstr == ',') {
int idx;
cmdstr++;
if (*cmdstr == '+' && isdigit(cmdstr[1])) {
/* http://sed.sourceforge.net/sedfaq3.html#s3.3
* Under GNU sed 3.02+, ssed, and sed15+, <address2>
* may also be a notation of the form +num,
* indicating the next num lines after <address1> is
* matched.
* GNU sed 4.2.1 accepts even "+" (meaning "+0").
* We don't (we check for isdigit, see above), think
* about the "+-3" case.
*/
char *end;
/* code is smaller compared to using &cmdstr here: */
idx = strtol(cmdstr+1, &end, 10);
sed_cmd->end_line = -2 - idx;
cmdstr = end;
} else {
idx = get_address(cmdstr, &sed_cmd->end_line, &sed_cmd->end_match);
cmdstr += idx;
idx--; /* if 0, trigger error check below */
}
if (idx < 0)
bb_error_msg_and_die("no address after comma");
sed_cmd->end_line_orig = sed_cmd->end_line;
}
/* skip whitespace before the command */
cmdstr = skip_whitespace(cmdstr);
/* Check for inversion flag */
if (*cmdstr == '!') {
sed_cmd->invert = 1;
cmdstr++;
/* skip whitespace before the command */
cmdstr = skip_whitespace(cmdstr);
}
/* last part (mandatory) will be a command */
if (!*cmdstr)
bb_error_msg_and_die("missing command");
sed_cmd->cmd = *cmdstr++;
cmdstr = parse_cmd_args(sed_cmd, cmdstr);
/* cmdstr now points past args.
* GNU sed requires a separator, if there are more commands,
* else it complains "char N: extra characters after command".
* Example: "sed 'p;d'". We also allow "sed 'pd'".
*/
/* Add the command to the command array */
*G.sed_cmd_tail = sed_cmd;
G.sed_cmd_tail = &sed_cmd->next;
}
/* If we glued multiple lines together, free the memory. */
free(G.add_cmd_line);
G.add_cmd_line = NULL;
}
int main(int argc,char *argv[])
{
int i,filecount;
static K2PDFOPT_SETTINGS _k2settings;
K2PDFOPT_SETTINGS *k2settings;
static STRBUF _cmdline,_env,_usermenu;
STRBUF *cmdline,*env,*usermenu;
k2settings=&_k2settings;
cmdline=&_cmdline;
env=&_env;
usermenu=&_usermenu;
strbuf_init(cmdline);
strbuf_init(env);
strbuf_init(usermenu);
strbuf_cpy(env,getenv("K2PDFOPT"));
for (i=1;i<argc;i++)
strbuf_cat_with_quotes(cmdline,argv[i]);
k2sys_init();
k2pdfopt_settings_init(k2settings);
/* Only set ansi and user interface */
filecount=parse_cmd_args(k2settings,env,cmdline,usermenu,2,0);
if (k2settings->show_usage)
{
k2sys_header();
if (k2settings->query_user==0
#if (defined(WIN32) || defined(WIN64))
|| !win_has_own_window()
#endif
)
k2usage_show_all(stdout);
else
{
if (!k2pdfopt_usage())
{
k2sys_close(k2settings);
strbuf_free(usermenu);
strbuf_free(env);
strbuf_free(cmdline);
return(0);
}
}
if (k2settings->query_user!=0)
k2sys_enter_to_exit(k2settings);
k2sys_close(k2settings);
strbuf_free(usermenu);
strbuf_free(env);
strbuf_free(cmdline);
return(0);
}
if (k2settings->query_user<0)
#if (defined(WIN32) || defined(WIN64))
{
if (win_has_own_window())
k2settings->query_user=1;
else
k2settings->query_user=(filecount==0);
}
#else
k2settings->query_user=1;
#endif
#if (!defined(WIN32) && !defined(WIN64))
if (k2settings->query_user)
{
int tty_rows;
tty_rows = get_ttyrows();
for (i=0;i<tty_rows-16;i++)
aprintf("\n");
}
#endif
k2sys_header();
/*
** Set all options from command-line arguments
*/
parse_cmd_args(k2settings,env,cmdline,usermenu,1,0);
/*
** Get user input
*/
if (k2pdfopt_menu(k2settings,filecount,env,cmdline,usermenu)==-1)
{
strbuf_free(usermenu);
strbuf_free(env);
strbuf_free(cmdline);
k2sys_close(k2settings);
return(0);
}
/*
** Re-init and then re-parse after all user menu entries applied.
*/
k2pdfopt_settings_init(k2settings);
parse_cmd_args(k2settings,env,cmdline,usermenu,1,0);
/*
** Sanity check / adjust user inputs
*/
k2pdfopt_settings_sanity_check(k2settings);
/*
** Process files
*/
parse_cmd_args(k2settings,env,cmdline,usermenu,0,1);
/*
** All done.
*/
strbuf_free(usermenu);
strbuf_free(env);
strbuf_free(cmdline);
k2sys_enter_to_exit(k2settings);
k2sys_close(k2settings);
return(0);
}
static void add_cmd(const char *cmdstr)
{
sed_cmd_t *sed_cmd;
unsigned len, n;
/* Append this line to any unfinished line from last time. */
if (G.add_cmd_line) {
char *tp = xasprintf("%s\n%s", G.add_cmd_line, cmdstr);
free(G.add_cmd_line);
cmdstr = G.add_cmd_line = tp;
}
/* If this line ends with unescaped backslash, request next line. */
n = len = strlen(cmdstr);
while (n && cmdstr[n-1] == '\\')
n--;
if ((len - n) & 1) { /* if odd number of trailing backslashes */
if (!G.add_cmd_line)
G.add_cmd_line = xstrdup(cmdstr);
G.add_cmd_line[len-1] = '\0';
return;
}
/* Loop parsing all commands in this line. */
while (*cmdstr) {
/* Skip leading whitespace and semicolons */
cmdstr += strspn(cmdstr, semicolon_whitespace);
/* If no more commands, exit. */
if (!*cmdstr) break;
/* if this is a comment, jump past it and keep going */
if (*cmdstr == '#') {
/* "#n" is the same as using -n on the command line */
if (cmdstr[1] == 'n')
G.be_quiet++;
cmdstr = strpbrk(cmdstr, "\n\r");
if (!cmdstr) break;
continue;
}
/* parse the command
* format is: [addr][,addr][!]cmd
* |----||-----||-|
* part1 part2 part3
*/
sed_cmd = xzalloc(sizeof(sed_cmd_t));
/* first part (if present) is an address: either a '$', a number or a /regex/ */
cmdstr += get_address(cmdstr, &sed_cmd->beg_line, &sed_cmd->beg_match);
sed_cmd->beg_line_orig = sed_cmd->beg_line;
/* second part (if present) will begin with a comma */
if (*cmdstr == ',') {
int idx;
cmdstr++;
idx = get_address(cmdstr, &sed_cmd->end_line, &sed_cmd->end_match);
if (!idx)
bb_error_msg_and_die("no address after comma");
cmdstr += idx;
}
/* skip whitespace before the command */
cmdstr = skip_whitespace(cmdstr);
/* Check for inversion flag */
if (*cmdstr == '!') {
sed_cmd->invert = 1;
cmdstr++;
/* skip whitespace before the command */
cmdstr = skip_whitespace(cmdstr);
}
/* last part (mandatory) will be a command */
if (!*cmdstr)
bb_error_msg_and_die("missing command");
sed_cmd->cmd = *cmdstr++;
cmdstr = parse_cmd_args(sed_cmd, cmdstr);
/* Add the command to the command array */
*G.sed_cmd_tail = sed_cmd;
G.sed_cmd_tail = &sed_cmd->next;
}
/* If we glued multiple lines together, free the memory. */
free(G.add_cmd_line);
G.add_cmd_line = NULL;
}
/*
* Main program
*/
int main(int argc, char *argv[])
{
int i = 0;
int ret = 0;
struct sockaddr_in client_address;
int client_sockfd = 0;
pthread_t threads[MAX_THREADS];
/* Parse commandline args */
params = malloc(sizeof(cmd_params));
ret = parse_cmd_args(&argc, argv);
if (params->help)
{
display_help_page();
exit(0);
}
if (params->version)
{
display_version_info();
exit(0);
}
if (ret < 0)
{
if (ret == -2)
logline(LOG_ERROR, "Error: Invalid port range specified (-p)");
if (ret == -6)
logline(LOG_ERROR, "Error: Invalid log level option specified (-l).");
logline(LOG_ERROR, "Use the -h option if you need help.");
exit(ret);
}
/* Set log level */
switch (params->loglevel)
{
case 1: set_loglevel(LOG_ERROR); break;
case 2: set_loglevel(LOG_INFO); break;
case 3: set_loglevel(LOG_DEBUG); break;
default: set_loglevel(LOG_ERROR);
}
/* Setup signal handler */
signal(SIGINT, shutdown_server);
signal(SIGTERM, shutdown_server);
/* Show banner and stuff */
show_gnu_banner();
/* Startup the server listener */
if (startup_server() < 0)
{
logline(LOG_ERROR, "Error during server startup. Please consult debug log for details.");
exit(-1);
}
/* Post ready message */
logline(LOG_INFO, "Server listening on %s, port %d", params->ip, params->port);
switch (params->loglevel)
{
case LOG_ERROR: logline(LOG_INFO, "Log level set to ERROR"); break;
case LOG_INFO: logline(LOG_INFO, "Log level set to INFO"); break;
case LOG_DEBUG: logline(LOG_INFO, "Log level set to DEBUG"); break;
default: logline(LOG_INFO, "Unknown log level specified"); break;
}
/* Handle connections */
while (1)
{
logline(LOG_INFO, "Waiting for incoming connection...");
/* Accept a client connection */
client_len = sizeof(client_address);
client_sockfd = accept(server_sockfd, (struct sockaddr *)&client_address, (socklen_t *)&client_len);
if (client_sockfd > 0)
{
logline(LOG_INFO, "Server accepted new connection on socket id %d", client_sockfd);
/* A connection between a client and the server has been established.
* Now create a new thread and handover the client_sockfd
*/
pthread_mutex_lock(&curr_thread_count_mutex);
if (curr_thread_count < MAX_THREADS)
{
/* Prepare client infos in handy structure */
client_info *ci = (client_info *)malloc(sizeof(client_info));
ci->sockfd = client_sockfd;
ci->address = client_address;
sprintf(ci->nickname, "anonymous_%d", client_sockfd);
/* Add client info to linked list */
llist_insert(&list_start, ci);
llist_show(&list_start);
/* Pass client info and invoke new thread */
ret = pthread_create(&threads[curr_thread_count],
NULL,
(void *)&proc_client,
(void *)&client_sockfd); /* only pass socket id ? */
if (ret == 0)
{
pthread_detach(threads[curr_thread_count]);
curr_thread_count++;
/* Notify server and clients */
logline(LOG_INFO, "User %s joined the chat.", ci->nickname);
logline(LOG_DEBUG, "main(): Connections used: %d of %d", curr_thread_count, MAX_THREADS);
}
else
{
free(ci);
close(client_sockfd);
}
}
else
{
logline(LOG_ERROR, "Max. connections reached. Connection limit is %d. Connection dropped.", MAX_THREADS);
close(client_sockfd);
}
pthread_mutex_unlock(&curr_thread_count_mutex);
}
else
{
/* Connection could not be established. Post error and exit. */
perror(strerror(errno));
exit(-3);
}
}
free(params);
return 0;
}
int main(int argc, char **argv) {
setlocale(LC_ALL, ""); // Comment-out on non-Posix systems
clock_t time_start = clock();
time_t time_t_start;
time(&time_t_start);
argv_0_basename = basename(argv[0]);
get_usage_string(usage, USAGE_LEN); // This is a big scary string, so build it elsewhere
//printf("sizeof(cmd_args)=%zd\n", sizeof(cmd_args));
parse_cmd_args(argc, argv, usage, &cmd_args);
if (cmd_args.class_algo == EXCHANGE || cmd_args.class_algo == EXCHANGE_BROWN)
memusage += sizeof(float) * ENTROPY_TERMS_MAX; // We'll build the precomputed entropy terms after reporting memusage
struct_model_metadata global_metadata;
// The list of unique words should always include <s>, unknown word, and </s>
map_update_count(&word_map, UNKNOWN_WORD, 0, 0); // Should always be first
map_update_count(&word_map, "<s>", 0, 1);
map_update_count(&word_map, "</s>", 0, 2);
// Open input
FILE *in_train_file = stdin;
if (in_train_file_string)
in_train_file = fopen(in_train_file_string, "r");
if (in_train_file == NULL) {
fprintf(stderr, "%s: Error: Unable to open input file %s\n", argv_0_basename, in_train_file_string); fflush(stderr);
exit(15);
}
// Process input sentences
size_t input_memusage = 0;
const struct_model_metadata input_model_metadata = process_input(cmd_args, in_train_file, &word_map, &initial_bigram_map, &input_memusage);
memusage += input_memusage;
fclose(in_train_file);
clock_t time_input_processed = clock();
if (cmd_args.verbose >= -1)
fprintf(stderr, "%s: Corpus processed in %'.2f CPU secs. %'lu lines, %'u types, %'lu tokens, current memusage: %'.1fMB\n", argv_0_basename, (double)(time_input_processed - time_start)/CLOCKS_PER_SEC, input_model_metadata.line_count, input_model_metadata.type_count, input_model_metadata.token_count, (double)memusage / 1048576); fflush(stderr);
global_metadata.token_count = input_model_metadata.token_count;
global_metadata.type_count = map_count(&word_map);
// Filter out infrequent words, reassign word_id's, and build a mapping from old word_id's to new word_id's
sort_by_count(&word_map);
word_id_t * restrict word_id_remap = calloc(sizeof(word_id_t), input_model_metadata.type_count);
get_ids(&word_map, word_id_remap);
word_id_t number_of_deleted_words = filter_infrequent_words(cmd_args, &global_metadata, &word_map, word_id_remap);
// Get list of unique words
char * * restrict word_list = (char **)malloc(sizeof(char*) * global_metadata.type_count);
memusage += sizeof(char*) * global_metadata.type_count;
reassign_word_ids(&word_map, word_list, word_id_remap);
get_keys(&word_map, word_list);
sort_by_id(&word_map);
// Check or set number of classes
if (cmd_args.num_classes >= global_metadata.type_count) { // User manually set number of classes is too low
fprintf(stderr, "%s: Error: Number of classes (%u) is not less than vocabulary size (%u). Decrease the value of --classes\n", argv_0_basename, cmd_args.num_classes, global_metadata.type_count); fflush(stderr);
exit(3);
} else if (cmd_args.num_classes == 0) { // User did not manually set number of classes at all
cmd_args.num_classes = (wclass_t) (sqrt(global_metadata.type_count) * 1.2);
}
// Build array of word_counts
word_count_t * restrict word_counts = malloc(sizeof(word_count_t) * global_metadata.type_count);
memusage += sizeof(word_count_t) * global_metadata.type_count;
build_word_count_array(&word_map, word_list, word_counts, global_metadata.type_count);
// Initialize clusters, and possibly read-in external class file
wclass_t * restrict word2class = malloc(sizeof(wclass_t) * global_metadata.type_count);
memusage += sizeof(wclass_t) * global_metadata.type_count;
init_clusters(cmd_args, global_metadata.type_count, word2class, word_counts, word_list);
if (initial_class_file != NULL)
import_class_file(&word_map, word2class, initial_class_file, cmd_args.num_classes); // Overwrite subset of word mappings, from user-provided initial_class_file
// Remap word_id's in initial_bigram_map
remap_and_rev_bigram_map(&initial_bigram_map, &new_bigram_map, &new_bigram_map_rev, word_id_remap, map_find_id(&word_map, UNKNOWN_WORD, -1));
global_metadata.start_sent_id = map_find_id(&word_map, "<s>", -1);; // need this for tallying emission probs
global_metadata.end_sent_id = map_find_id(&word_map, "</s>", -1);; // need this for tallying emission probs
global_metadata.line_count = map_find_count(&word_map, "</s>"); // Used for calculating perplexity
if (global_metadata.line_count == 0) {
fprintf(stderr, "%s: Warning: Number of lines is 0. Include <s> and </s> in your ngram counts, or perplexity values will be unreliable.\n", argv_0_basename); fflush(stderr);
}
//printf("init_bigram_map hash_count=%u\n", HASH_COUNT(initial_bigram_map)); fflush(stdout);
//printf("new_bigram_map hash_count=%u\n", HASH_COUNT(new_bigram_map)); fflush(stdout);
free(word_id_remap);
memusage -= sizeof(word_id_t) * input_model_metadata.type_count;
delete_all(&word_map); // static
delete_all_bigram(&initial_bigram_map); // static
memusage -= input_memusage;
// Initialize and set word bigram listing
clock_t time_bigram_start = clock();
size_t bigram_memusage = 0; size_t bigram_rev_memusage = 0;
struct_word_bigram_entry * restrict word_bigrams = NULL;
struct_word_bigram_entry * restrict word_bigrams_rev = NULL;
if (cmd_args.verbose >= -1)
fprintf(stderr, "%s: Word bigram listing ... ", argv_0_basename); fflush(stderr);
#pragma omp parallel sections // Both bigram listing and reverse bigram listing can be done in parallel
{
#pragma omp section
{
//sort_bigrams(&new_bigram_map); // speeds things up later
word_bigrams = calloc(global_metadata.type_count, sizeof(struct_word_bigram_entry));
memusage += sizeof(struct_word_bigram_entry) * global_metadata.type_count;
bigram_memusage = set_bigram_counts(word_bigrams, new_bigram_map);
// Copy entries in word_counts to struct_word_bigram_entry.headword_count since that struct entry is already loaded when clustering
for (word_id_t word = 0; word < global_metadata.type_count; word++)
word_bigrams[word].headword_count = word_counts[word];
}
// Initialize and set *reverse* word bigram listing
#pragma omp section
{
if (cmd_args.rev_alternate) { // Don't bother building this if it won't be used
//sort_bigrams(&new_bigram_map_rev); // speeds things up later
word_bigrams_rev = calloc(global_metadata.type_count, sizeof(struct_word_bigram_entry));
memusage += sizeof(struct_word_bigram_entry) * global_metadata.type_count;
bigram_rev_memusage = set_bigram_counts(word_bigrams_rev, new_bigram_map_rev);
// Copy entries in word_counts to struct_word_bigram_entry.headword_count since that struct entry is already loaded when clustering
for (word_id_t word = 0; word < global_metadata.type_count; word++)
word_bigrams_rev[word].headword_count = word_counts[word];
}
}
}
delete_all_bigram(&new_bigram_map);
delete_all_bigram(&new_bigram_map_rev);
memusage += bigram_memusage + bigram_rev_memusage;
clock_t time_bigram_end = clock();
if (cmd_args.verbose >= -1)
fprintf(stderr, "in %'.2f CPU secs. Bigram memusage: %'.1f MB\n", (double)(time_bigram_end - time_bigram_start)/CLOCKS_PER_SEC, (bigram_memusage + bigram_rev_memusage)/(double)1048576); fflush(stderr);
//print_word_bigrams(global_metadata, word_bigrams, word_list);
// Build <v,c> counts, which consists of a word followed by a given class
word_class_count_t * restrict word_class_counts = calloc(1 + cmd_args.num_classes * global_metadata.type_count , sizeof(word_class_count_t));
if (word_class_counts == NULL) {
fprintf(stderr, "%s: Error: Unable to allocate enough memory for <v,c>. %'.1f MB needed. Maybe increase --min-count\n", argv_0_basename, ((cmd_args.num_classes * global_metadata.type_count * sizeof(word_class_count_t)) / (double)1048576 )); fflush(stderr);
exit(13);
}
memusage += cmd_args.num_classes * global_metadata.type_count * sizeof(word_class_count_t);
fprintf(stderr, "%s: Allocating %'.1f MB for word_class_counts: num_classes=%u x type_count=%u x sizeof(w-cl-count_t)=%zu\n", argv_0_basename, (double)(cmd_args.num_classes * global_metadata.type_count * sizeof(word_class_count_t)) / 1048576 , cmd_args.num_classes, global_metadata.type_count, sizeof(word_class_count_t)); fflush(stderr);
build_word_class_counts(cmd_args, word_class_counts, word2class, word_bigrams, global_metadata.type_count/*, word_list*/);
//print_word_class_counts(cmd_args, global_metadata, word_class_counts);
// Build reverse: <c,v> counts: class followed by word. This and the normal one are both pretty fast, so no need to parallelize this
word_class_count_t * restrict word_class_rev_counts = NULL;
if (cmd_args.rev_alternate) { // Don't bother building this if it won't be used
word_class_rev_counts = calloc(1 + cmd_args.num_classes * global_metadata.type_count , sizeof(word_class_count_t));
if (word_class_rev_counts == NULL) {
fprintf(stderr, "%s: Warning: Unable to allocate enough memory for <v,c>. %'.1f MB needed. Falling back to --rev-alternate 0\n", argv_0_basename, ((cmd_args.num_classes * global_metadata.type_count * sizeof(word_class_count_t)) / (double)1048576 )); fflush(stderr);
cmd_args.rev_alternate = 0;
} else {
memusage += cmd_args.num_classes * global_metadata.type_count * sizeof(word_class_count_t);
fprintf(stderr, "%s: Allocating %'.1f MB for word_class_rev_counts: num_classes=%u x type_count=%u x sizeof(w-cl-count_t)=%zu\n", argv_0_basename, (double)(cmd_args.num_classes * global_metadata.type_count * sizeof(word_class_count_t)) / 1048576 , cmd_args.num_classes, global_metadata.type_count, sizeof(word_class_count_t)); fflush(stderr);
build_word_class_counts(cmd_args, word_class_rev_counts, word2class, word_bigrams_rev, global_metadata.type_count/*, word_list*/);
}
}
// Calculate memusage for count_arrays
for (unsigned char i = 1; i <= cmd_args.max_array; i++) {
memusage += 2 * (powi(cmd_args.num_classes, i) * sizeof(wclass_count_t));
//printf("11 memusage += %zu (now=%zu) count_arrays\n", 2 * (powi(cmd_args.num_classes, i) * sizeof(wclass_count_t)), memusage); fflush(stdout);
}
clock_t time_model_built = clock();
if (cmd_args.verbose >= -1)
fprintf(stderr, "%s: Finished loading %'lu tokens and %'u types (%'u filtered) from %'lu lines in %'.2f CPU secs\n", argv_0_basename, global_metadata.token_count, global_metadata.type_count, number_of_deleted_words, global_metadata.line_count, (double)(time_model_built - time_start)/CLOCKS_PER_SEC); fflush(stderr);
if (cmd_args.verbose >= -1)
fprintf(stderr, "%s: Approximate memory usage at clustering: %'.1fMB\n", argv_0_basename, (double)memusage / 1048576); fflush(stderr);
cluster(cmd_args, global_metadata, word_counts, word_list, word2class, word_bigrams, word_bigrams_rev, word_class_counts, word_class_rev_counts);
// Now print the final word2class mapping
if (cmd_args.verbose >= 0) {
FILE *out_file = stdout;
if (out_file_string)
out_file = fopen(out_file_string, "w");
if (out_file == NULL) {
fprintf(stderr, "%s: Error: Unable to open output file %s\n", argv_0_basename, out_file_string); fflush(stderr);
exit(16);
}
if (cmd_args.class_algo == EXCHANGE && (!cmd_args.print_word_vectors)) {
print_words_and_classes(out_file, global_metadata.type_count, word_list, word_counts, word2class, (int)cmd_args.class_offset, cmd_args.print_freqs);
} else if (cmd_args.class_algo == EXCHANGE && cmd_args.print_word_vectors) {
print_words_and_vectors(out_file, cmd_args, global_metadata, word_list, word2class, word_bigrams, word_bigrams_rev, word_class_counts, word_class_rev_counts);
}
fclose(out_file);
}
clock_t time_clustered = clock();
time_t time_t_end;
time(&time_t_end);
double time_secs_total = difftime(time_t_end, time_t_start);
if (cmd_args.verbose >= -1)
fprintf(stderr, "%s: Finished clustering in %'.2f CPU seconds. Total wall clock time was about %lim %lis\n", argv_0_basename, (double)(time_clustered - time_model_built)/CLOCKS_PER_SEC, (long)time_secs_total/60, ((long)time_secs_total % 60) );
free(word2class);
free(word_bigrams);
free(word_list);
free(word_counts);
exit(0);
}
static void parse_argv(ChildProcs *child_procs, Opts *opts, int argc, char *argv[]) {
child_procs->n_cmds = 1;
char **args_end = argv + argc;
for (char **i = argv + 1; i < args_end; ++i) {
if (! strcmp(*i, SEP))
++child_procs->n_cmds;
}
child_procs->cmds = calloc(child_procs->n_cmds, sizeof(Cmd));
*opts = (Opts) { .signal_everything = false };
parse_cmd_args(opts, child_procs->cmds, argv + 1, args_end);
char **arg_it = child_procs->cmds->args;
int cmd_idx = 0;
for (; arg_it < args_end; ++arg_it) {
if (! strcmp(*arg_it, SEP)) {
*arg_it = 0; // replace with null to terminate when passed to execvp
if (arg_it + 1 == args_end) {
fprintf(stderr, "command must follow `---'\n");
exit(1);
}
parse_cmd_args(opts, child_procs->cmds + (++cmd_idx), arg_it + 1, args_end);
Cmd *cmd = child_procs->cmds + cmd_idx;
arg_it = cmd->args - 1;
}
}
}
int main(int argc, char *argv[]) {
if (argc == 1) {
fprintf(stderr, "please supply at least one command to run\n");
return 1;
}
ChildProcs child_procs;
Opts opts;
parse_argv(&child_procs, &opts, argc, argv);
int n_watch_cmds = 0;
for (int i = 0; i < child_procs.n_cmds; ++i) {
if (child_procs.cmds[i].watch)
++n_watch_cmds;
}
// if -f hasn't been used then watch every command
if (0 == n_watch_cmds) {
for (int i = 0; i < child_procs.n_cmds; ++i) {
if (! child_procs.cmds[i].configuring) {
++n_watch_cmds;
child_procs.cmds[i].watch = true;
}
}
}
Cmd **watch_cmds = calloc(n_watch_cmds, sizeof(Cmd *));
{
int watch_cmd_end = 0;
for (int i = 0; i < child_procs.n_cmds; ++i) {
if (child_procs.cmds[i].watch)
watch_cmds[watch_cmd_end++] = child_procs.cmds + i;
}
}
install_term_and_int_handlers();
int error_code;
run_configure_cmds(child_procs.n_cmds, child_procs.cmds);
if (running) {
run_cmds(child_procs.n_cmds, child_procs.cmds);
error_code = wait_for_requested_commands_to_exit(n_watch_cmds, watch_cmds);
remove_term_and_int_handlers();
alarm(WAIT_FOR_PROC_DEATH_TIMEOUT);
kill(opts.signal_everything ? -1 : 0, SIGTERM);
wait_for_all_processes_to_exit(error_code);
DPRINTF("all processes exited cleanly");
}
free(watch_cmds);
free(child_procs.cmds);
return error_code;
}
int main (int argc, char *argv[]) {
int res = 0;
struct arguments opts = parse_cmd_args(argc, argv);
if ((opts.flags & Optionvalue_ts::ERROR) != 0) {
std::cerr << "There has been an error" << std::endl;
return EXIT_FAILURE;
}
if (opts.flags == Optionvalue_ts::HELP) {
print_help();
return EXIT_SUCCESS;
}
if (opts.filename.size() == 0) {
std::cerr << "No filename provided" << std::endl;
return EXIT_FAILURE;
}
//
// Setup the driver
Driver driver;
global_driver = &driver;
if ((opts.flags & Optionvalue_ts::PARSE_ONLY) != 0) {
if (driver.parse(opts.filename) == nullptr) {
std::cerr << "Error parsing file" << std::endl;
res = EXIT_FAILURE;
} else {
res = EXIT_SUCCESS;
}
} else if ((opts.flags & Optionvalue_ts::DUMP_AST) != 0) {
if (driver.parse(opts.filename) == nullptr) {
std::cerr << "Error parsing file" << std::endl;
return EXIT_FAILURE;
}
try {
AstDumpVisitor dump_visitor;
AstWalker<AstDumpVisitor, bool> dump_walker(dump_visitor);
dump_walker.walk_specification(driver.result);
std::cout << dump_visitor.get_dump();
res = EXIT_SUCCESS;
} catch (char const *e) {
std::cerr << "Abort after catching a string: "<< e;
res = EXIT_FAILURE;
}
} else {
if (driver.parse(opts.filename) == nullptr) {
std::cerr << "Error parsing file " << driver.result << std::endl;
return EXIT_FAILURE;
}
TypecheckVisitor typecheck_visitor(driver);
AstWalker<TypecheckVisitor, Type*> typecheck_walker(typecheck_visitor);
typecheck_walker.walk_specification(driver.result);
if (!driver.ok()) {
res = EXIT_FAILURE;
} else {
ExecutionContext ctx(driver.function_table, driver.get_init_rule(),
(opts.flags & Optionvalue_ts::SYMBOLIC) != 0,
(opts.flags & Optionvalue_ts::FILEOUT) != 0,
(opts.flags & Optionvalue_ts::DUMP_UPDATES) != 0);
if ((opts.flags & Optionvalue_ts::DEBUGINFO_FILTER) != 0) {
ctx.set_debuginfo_filter(opts.debuginfo_filter);
}
ExecutionVisitor visitor(ctx, driver);
ExecutionWalker walker(visitor);
try {
walker.run();
res = EXIT_SUCCESS;
} catch (const RuntimeException& ex) {
std::cerr << "Abort after runtime exception: "<< ex.what() << std::endl;;
res = EXIT_FAILURE;
} catch (const ImpossibleException& ex) {
res = EXIT_SUCCESS;
} catch (char * e) {
std::cerr << "Abort after catching a string: "<< e << std::endl;
res = EXIT_FAILURE;
}
}
}
if (driver.result) {
delete driver.result;
}
return res;
}
void add_cmd(char *cmdstr)
{
static char *add_cmd_line=NULL;
sed_cmd_t *sed_cmd;
int temp;
/* Append this line to any unfinished line from last time. */
if(add_cmd_line) {
int lastlen=strlen(add_cmd_line);
char *tmp=xmalloc(lastlen+strlen(cmdstr)+2);
memcpy(tmp,add_cmd_line,lastlen);
tmp[lastlen]='\n';
strcpy(tmp+lastlen+1,cmdstr);
free(add_cmd_line);
cmdstr=add_cmd_line=tmp;
} else add_cmd_line=NULL;
/* If this line ends with backslash, request next line. */
temp=strlen(cmdstr);
if(temp && cmdstr[temp-1]=='\\') {
if(!add_cmd_line) add_cmd_line=strdup(cmdstr);
add_cmd_line[temp-1]=0;
return;
}
/* Loop parsing all commands in this line. */
while(*cmdstr) {
/* Skip leading whitespace and semicolons */
cmdstr += strspn(cmdstr, semicolon_whitespace);
/* If no more commands, exit. */
if(!*cmdstr) break;
/* if this is a comment, jump past it and keep going */
if (*cmdstr == '#') {
/* "#n" is the same as using -n on the command line */
if (cmdstr[1] == 'n') be_quiet++;
if(!(cmdstr=strpbrk(cmdstr, "\n\r"))) break;
continue;
}
/* parse the command
* format is: [addr][,addr][!]cmd
* |----||-----||-|
* part1 part2 part3
*/
sed_cmd = xcalloc(1, sizeof(sed_cmd_t));
/* first part (if present) is an address: either a '$', a number or a /regex/ */
cmdstr += get_address(cmdstr, &sed_cmd->beg_line, &sed_cmd->beg_match);
/* second part (if present) will begin with a comma */
if (*cmdstr == ',') {
int idx;
cmdstr++;
idx = get_address(cmdstr, &sed_cmd->end_line, &sed_cmd->end_match);
if (!idx) bb_error_msg_and_die("get_address: no address found in string\n");
cmdstr += idx;
}
/* skip whitespace before the command */
while (isspace(*cmdstr)) cmdstr++;
/* Check for inversion flag */
if (*cmdstr == '!') {
sed_cmd->invert = 1;
cmdstr++;
/* skip whitespace before the command */
while (isspace(*cmdstr)) cmdstr++;
}
/* last part (mandatory) will be a command */
if (!*cmdstr) bb_error_msg_and_die("missing command");
sed_cmd->cmd = *(cmdstr++);
cmdstr = parse_cmd_args(sed_cmd, cmdstr);
/* Add the command to the command array */
sed_cmd_tail->next = sed_cmd;
sed_cmd_tail = sed_cmd_tail->next;
}
/* If we glued multiple lines together, free the memory. */
if(add_cmd_line) {
free(add_cmd_line);
add_cmd_line=NULL;
}
}
/*
** Conversion thread. This is launched as a separate thread to do the
** conversions while the dialog box displays the progress.
*/
static void k2gui_cbox_start_conversion(void *data)
{
void **ptrs;
int i;
K2PDFOPT_CONVERSION *k2conv;
K2PDFOPT_SETTINGS *k2settings;
K2PDFOPT_FILELIST_PROCESS k2listproc;
static char *funcname="k2gui_cbox_start_conversion";
ptrs=(void **)data;
k2conv=(K2PDFOPT_CONVERSION *)ptrs[0];
k2settings=&k2conv->k2settings;
/*
** Count files
*/
k2gui_cbox_set_num_files(1);
k2gui_cbox_set_files_completed(0,"Counting files...");
overwrite_set(1);
for (i=k2listproc.filecount=0;i<k2conv->k2files.n;i++)
{
k2listproc.bmp=NULL;
k2listproc.outname=NULL;
k2listproc.mode=K2PDFOPT_FILELIST_PROCESS_MODE_GET_FILECOUNT;
k2pdfopt_proc_wildarg(k2settings,k2conv->k2files.file[i],&k2listproc);
willus_mem_free((double **)&k2listproc.outname,funcname);
}
if (k2listproc.filecount==0)
{
k2gui_cbox_set_files_completed(0,"No files");
k2gui_alertbox(0,"No files","No files can be opened for conversion.");
k2gui_cbox_conversion_thread_cleanup();
return;
}
k2gui_cbox_set_num_files(k2listproc.filecount);
k2gui_cbox_set_files_completed(0,NULL);
/*
** Process files
*/
k2gui_cbox_set_error_count(0);
k2gui_cbox_freelist();
overwrite_set(0);
for (i=k2listproc.filecount=0;i<k2conv->k2files.n;i++)
{
char *buf;
K2PDFOPT_CONVERSION *k2c;
STRBUF *cmdline,_cmdline;
willus_mem_alloc_warn((void **)&buf,1024,funcname,10);
k2gui_cbox_set_num_pages(1);
sprintf(buf,"Starting conversion of %s...",k2gui_short_name(k2conv->k2files.file[i]));
k2gui_cbox_set_pages_completed(0,buf);
willus_mem_alloc_warn((void **)&k2c,sizeof(K2PDFOPT_CONVERSION),funcname,10);
k2pdfopt_conversion_init(k2c);
cmdline=&_cmdline;
strbuf_init(cmdline);
k2gui_settings_to_cmdline(cmdline,&k2conv->k2settings);
parse_cmd_args(k2c,k2gui->env,cmdline,&k2gui->cmdxtra,1,1);
k2listproc.outname=NULL;
k2listproc.bmp=NULL;
k2listproc.mode=K2PDFOPT_FILELIST_PROCESS_MODE_CONVERT_FILES;
k2pdfopt_proc_wildarg(&k2c->k2settings,k2conv->k2files.file[i],&k2listproc);
#if (WILLUSDEBUGX & 0x2000)
printf("\n\nDone conversion...\n\n");
#endif
str0_addstring(&k2gui_cbox->filelist,&k2gui_cbox->filelist_na,k2listproc.outname);
willus_mem_free((double **)&k2listproc.outname,funcname);
k2pdfopt_conversion_close(k2c);
willus_mem_free((double **)&k2c,funcname);
willus_mem_free((double **)&buf,funcname);
}
k2gui_cbox_set_files_completed(k2listproc.filecount,NULL);
if (k2listproc.filecount==k2conv->k2files.n && k2gui_cbox->error_count==0)
k2gui_cbox->successful=1;
k2gui_cbox_conversion_thread_cleanup();
}
int
main(int argc, char **argv)
{
char errbuf[_POSIX2_LINE_MAX], dummy;
size_t size;
struct cmdentry *cmd = NULL;
(void) setlocale(LC_ALL, "");
SLIST_INIT(&commands);
argc--, argv++;
if (argc > 0) {
if (argv[0][0] == '-') {
struct cmdtab *p;
p = lookup(&argv[0][1]);
if (p == (struct cmdtab *)-1)
errx(1, "%s: ambiguous request", &argv[0][1]);
if (p == (struct cmdtab *)0)
errx(1, "%s: unknown request", &argv[0][1]);
curcmd = p;
argc--, argv++;
}
parse_cmd_args (argc, argv);
}
kd = kvm_openfiles(NULL, NULL, NULL, O_RDONLY, errbuf);
if (kd != NULL) {
/*
* Try to actually read something, we may be in a jail, and
* have /dev/null opened as /dev/mem.
*/
if (kvm_nlist(kd, namelist) != 0 || namelist[0].n_value == 0 ||
kvm_read(kd, namelist[0].n_value, &dummy, sizeof(dummy)) !=
sizeof(dummy)) {
kvm_close(kd);
kd = NULL;
}
}
if (kd == NULL) {
/*
* Maybe we are lacking permissions? Retry, this time with bogus
* devices. We can now use sysctl only.
*/
use_kvm = 0;
kd = kvm_openfiles(_PATH_DEVNULL, _PATH_DEVNULL, _PATH_DEVNULL,
O_RDONLY, errbuf);
if (kd == NULL) {
error("%s", errbuf);
exit(1);
}
}
signal(SIGHUP, die);
signal(SIGINT, die);
signal(SIGQUIT, die);
signal(SIGTERM, die);
/*
* Initialize display. Load average appears in a one line
* window of its own. Current command's display appears in
* an overlapping sub-window of stdscr configured by the display
* routines to minimize update work by curses.
*/
initscr();
CMDLINE = LINES - 1;
wnd = (*curcmd->c_open)();
if (wnd == NULL) {
warnx("couldn't initialize display");
die(0);
}
wload = newwin(1, 0, 1, 20);
if (wload == NULL) {
warnx("couldn't set up load average window");
die(0);
}
gethostname(hostname, sizeof (hostname));
size = sizeof(clkinfo);
if (sysctlbyname("kern.clockrate", &clkinfo, &size, NULL, 0)
|| size != sizeof(clkinfo)) {
error("kern.clockrate");
die(0);
}
hertz = clkinfo.stathz;
(*curcmd->c_init)();
curcmd->c_flags |= CF_INIT;
labels();
if (curcmd->c_cmd != NULL)
SLIST_FOREACH (cmd, &commands, link)
if (!curcmd->c_cmd(cmd->cmd, cmd->argv))
warnx("command is not understood");
dellave = 0.0;
display();
noecho();
crmode();
keyboard();
/*NOTREACHED*/
return EXIT_SUCCESS;
}
int main (int argc, char **argv) {
/////////////////////
// Parse Arguments //
/////////////////////
params *pars = new params;
init_pars(pars);
parse_cmd_args(argc, argv, pars);
if( pars->version ) {
printf("ngsF v%s\nCompiled on %s @ %s", version, __DATE__, __TIME__);
#ifdef _USE_BGZF
printf(" (BGZF library)\n");
#else
printf(" (STD library)\n");
#endif
exit(0);
}
if( pars->verbose >= 1 ) {
printf("==> Input Arguments:\n");
printf("\tglf file: %s\n\tinit_values: %s\n\tfreq_fixed: %s\n\tout file: %s\n\tn_ind: %d\n\tn_sites: %lu\n\tchunk_size: %lu\n\tfast_lkl: %s\n\tapprox_EM: %s\n\tcall_geno: %s\n\tmax_iters: %d\n\tmin_epsilon: %.10f\n\tn_threads: %d\n\tseed: %lu\n\tquick: %s\n\tversion: %s\n\tverbose: %d\n\n",
pars->in_glf, pars->init_values, pars->freq_fixed ? "true":"false", pars->out_file, pars->n_ind, pars->n_sites, pars->max_chunk_size, pars->fast_lkl ? "true":"false", pars->approx_EM ? "true":"false", pars->call_geno ? "true":"false", pars->max_iters, pars->min_epsilon, pars->n_threads, pars->seed, pars->quick ? "true":"false", version, pars->verbose);
}
if( pars->verbose > 4 ) printf("==> Verbose values greater than 4 for debugging purpose only. Expect large amounts of info on screen\n");
/////////////////////
// Check Arguments //
/////////////////////
if(pars->in_glf == NULL)
error(__FUNCTION__,"GL input file (-glf) missing!");
else if( strcmp(pars->in_glf, "-") == 0 ) {
pars->in_glf_type = new char[6];
pars->in_glf_type = strcat(pars->in_glf_type, "STDIN");
} else {
pars->in_glf_type = strrchr(pars->in_glf, '.');
if(pars->in_glf_type == NULL)
error(__FUNCTION__,"invalid file type!");
}
if(pars->out_file == NULL)
error(__FUNCTION__,"output file (-out) missing!");
if(pars->n_ind == 0)
error(__FUNCTION__,"number of individuals (-n_ind) missing!");
if(pars->n_sites == 0)
error(__FUNCTION__,"number of sites (-n_sites) missing!");
///////////////////////
// Check input files //
///////////////////////
// Get file total size
struct stat st;
stat(pars->in_glf, &st);
if( strcmp(pars->in_glf_type, "STDIN") != 0 ) {
if( pars->n_sites == st.st_size/sizeof(double)/pars->n_ind/3 && strcmp(pars->in_glf_type, ".glf") == 0 ) {
if(pars->verbose >= 1)
printf("==> UNCOMP input file (\"%s\"): number of sites (%lu) match expected file size\n", pars->in_glf_type, pars->n_sites);
} else if( strcmp(pars->in_glf_type, ".glf") != 0 ) {
if( pars->verbose >= 1)
printf("==> COMPRESSED input file (\"%s\"): number of sites (%lu) do NOT match expected file size\n", pars->in_glf_type, pars->n_sites);
} else
error(__FUNCTION__,"wrong number of sites or invalid/corrupt file!");
}
// Adjust max_chunk_size in case of fewer sites
if(pars->max_chunk_size > pars->n_sites) {
if( pars->verbose >= 1 ) printf("==> Fewer sites (%lu) than chunk_size (%lu). Reducing chunk size to match number of sites\n", pars->n_sites, pars->max_chunk_size);
pars->max_chunk_size = pars->n_sites;
}
// Calculate total number of chunks
pars->n_chunks = ceil( (double) pars->n_sites/ (double) pars->max_chunk_size );
if( pars->verbose >= 1 ) printf("==> Analysis will be run in %ld chunk(s)\n", pars->n_chunks);
// Alocate memory for the chunk index
pars->chunks_voffset = new int64_t[pars->n_chunks];
memset(pars->chunks_voffset, 0, pars->n_chunks*sizeof(int64_t));
// Adjust thread number to chunks
if(pars->n_chunks < pars->n_threads) {
if( pars->verbose >= 1 ) printf("==> Fewer chunks (%ld) than threads (%d). Reducing the number of threads to match number of chunks\n", pars->n_chunks, pars->n_threads);
pars->n_threads = pars->n_chunks;
}
// Open input file
#ifdef _USE_BGZF
if( pars->verbose >= 1 ) printf("==> Using BGZF I/O library\n");
// Open BGZIP file
if( strcmp(pars->in_glf_type, ".bgz") == 0 ) {
if( (pars->in_glf_fh = bgzf_open(pars->in_glf, "rb")) < 0 )
error(__FUNCTION__,"Cannot open BGZIP file!");
} else
error(__FUNCTION__,"BGZF library only supports BGZIP files!");
bgzf_set_cache_size(pars->in_glf_fh, CACHE_SIZE * 1024uL * 1024uL * 1024uL);
#else
if( pars->verbose >= 1 ) printf("==> Using native I/O library\n");
// Open GLF file
if( strcmp(pars->in_glf_type, "STDIN") == 0 )
pars->in_glf_fh = stdin;
else if( strcmp(pars->in_glf_type, ".glf") == 0 ) {
if( (pars->in_glf_fh = fopen(pars->in_glf, "rb")) == NULL )
error(__FUNCTION__,"Cannot open GLF file!");
} else
error(__FUNCTION__,"Standard library only supports UNCOMPRESSED GLF files!");
// Allocate memory and read from the file
pars->data = new double* [pars->n_sites];
for(uint64_t s = 0; s < pars->n_sites; s++) {
pars->data[s] = new double[pars->n_ind * 3];
if( fread (pars->data[s], sizeof(double), pars->n_ind * 3, pars->in_glf_fh) != pars->n_ind * 3)
error(__FUNCTION__,"cannot read GLF file!");
if(pars->call_geno)
call_geno(pars->data[s], pars->n_ind, 3);
}
#endif
if( pars->in_glf_fh == NULL )
error(__FUNCTION__,"cannot open GLF file!");
///////////////////////////////////
// Declare variables for results //
///////////////////////////////////
out_data *output = new out_data;
output->site_freq = new double[pars->n_sites];
output->site_freq_num = new double[pars->n_sites];
output->site_freq_den = new double[pars->n_sites];
output->site_prob_var = new double[pars->n_sites];
output->site_tmpprob_var = new double[pars->n_sites];
output->indF = new double[pars->n_ind];
output->indF_num = new double[pars->n_ind];
output->indF_den = new double[pars->n_ind];
output->ind_lkl = new double[pars->n_ind];
// Initialize output
init_output(pars, output);
//////////////////
// Analyze Data //
//////////////////
if( pars->verbose >= 1 && !pars->fast_lkl && strcmp("e", pars->init_values) != 0 ) {
printf("==> Initial LogLkl: %.15f\n", full_HWE_like(pars, output->site_freq, output->indF, 0, pars->n_ind));
fflush(stdout);
}
do_EM(pars, output);
if( pars->verbose >= 1 ) printf("\nFinal logLkl: %f\n", output->global_lkl);
//////////////////
// Print Output //
//////////////////
FILE *out_file;
if( pars->verbose >= 1 ) printf("Printing Output...\n");
out_file = fopen(pars->out_file, "w");
if(out_file == NULL)
error(__FUNCTION__,"Cannot open OUTPUT file!");
for(uint16_t i = 0; i < pars->n_ind; i++)
fprintf(out_file,"%f\n", output->indF[i]);
fclose(out_file);
//////////////////////
// Close Input File //
//////////////////////
if( pars->verbose >= 1 ) printf("Exiting...\n");
#ifdef _USE_BGZF
bgzf_close(pars->in_glf_fh);
#else
for(uint64_t s = 0; s < pars->n_sites; s++)
delete [] pars->data[s];
delete [] pars->data;
fclose(pars->in_glf_fh);
#endif
/////////////////
// Free Memory //
/////////////////
delete [] output->site_freq;
delete [] output->site_freq_num;
delete [] output->site_freq_den;
delete [] output->site_prob_var;
delete [] output->indF;
delete [] output->indF_num;
delete [] output->indF_den;
delete [] output->ind_lkl;
delete output;
//if( strcmp("e", pars->init_values) == 0 )
//delete [] pars->init_values;
delete [] pars->chunks_voffset;
delete pars;
return 0;
}
/*
* App entry point. The place where everything starts...
*/
int main(int argc, char *argv[])
{
int ret = 0;
/* Initialize pseudo-random number generator */
srand((unsigned)time(NULL));
/* Allocate structures on heap */
params = malloc(sizeof(cmd_params));
/* Parse commandline args */
ret = parse_cmd_args(&argc, argv);
if (params->help)
{
display_help_page();
return 0;
}
if (params->version)
{
display_version_info();
return 0;
}
if (ret < 0)
{
switch (ret)
{
case -1:
logline(LOG_ERROR, "Error: No server specified (use option -s)");
break;
case -2:
logline(LOG_ERROR, "Error: Input file must be specified (use option -i)");
break;
case -3:
logline(LOG_ERROR, "Error: Servers could not be interpreted (use option -s)");
break;
case -4:
logline(LOG_ERROR, "Error: Invalid log level option specified (use option -l).");
break;
case -5:
logline(LOG_ERROR, "Error: No domain specified (use -d option).");
break;
default:
logline(LOG_ERROR, "Error: An unknown error occurred during parsing of command line args.");
}
logline(LOG_ERROR, "Use the -h option if you need help.");
return ret;
}
/* Set log level */
switch (params->loglevel)
{
case 1:
set_loglevel(LOG_ERROR);
break;
case 2:
set_loglevel(LOG_INFO);
break;
case 3:
set_loglevel(LOG_DEBUG);
break;
default:
set_loglevel(LOG_ERROR);
}
show_gnu_banner();
printf("Executing %s Version %s\n", APP_NAME, APP_VERSION);
printf("\n");
/* Display help page if desired. Otherwise, do DNS lookups */
ret = do_dns_lookups();
if (ret < 0)
{
logline(LOG_ERROR, "Error: Could not perform DNS lookups. Errorcode: %d", ret);
}
/* Free memory on heap */
free(params);
return ret;
}
