num_ty bi_sim(const string_impl& w1, const string_impl& w2) {
uint m = w1.length(),
n = w2.length();
string_impl x = w1,
y = w2;
lower_case(&x);
lower_case(&y);
char_impl x1 = x[0],
y1 = y[0];
upper_case(&x1);
upper_case(&y1);
x = x1 + x;
y = y1 + y;
// initialize and fill matrix
vector<vector<num_ty>> f;
f.resize(m+1);
for (uint i = 0; i <= m; ++i) {
f[i].resize(n+1);
f[i][0] = 0.0;
}
for (uint i = 0; i <= n; ++i)
f[0][i] = 0.0;
// calculate bi_sim
for (uint i = 1; i <= m; ++i)
for (uint j = 1; j <= n; ++j)
f[i][j] = max(max(f[i-1][j], f[i][j-1]),
f[i-1][j-1]
+ id(x[i-1], y[j-1])
+ id(x[i], y[j]));
return f[m][n] / (2 * max(m, n));
}
char* encipher(const char *src, char *key, int is_encode)
{
int i, klen, slen;
char *dest;
dest = strdup(src);
upper_case(dest);
upper_case(key);
/* strip out non-letters */
for (i = 0, slen = 0; dest[slen] != '\0'; slen++)
if (isupper(dest[slen]))
dest[i++] = dest[slen];
dest[slen = i] = '\0'; /* null pad it, make it safe to use */
klen = strlen(key);
for (i = 0; i < slen; i++) {
if (!isupper(dest[i])) continue;
dest[i] = 'A' + (is_encode
? dest[i] - 'A' + key[i % klen] - 'A'
: dest[i] - key[i % klen] + 26) % 26;
}
return dest;
}
/* 2010-10-22 : new routine */
int upper_case_compare( char *str1 , char* str2 ) {
char upper_buf1[ MAXSTRLEN ] ;
char upper_buf2[ MAXSTRLEN ] ;
upper_case( upper_buf1 , str1 ) ;
upper_case( upper_buf2 , str2 ) ;
return ( strcmp( upper_buf1 , upper_buf2 ) ) ;
}
string remote_tell(string cname, string from, string mud, string to, string msg, int wiz_level)
{
object ob;
string fromid;
string no_tell;
string can_tell;
// mapping conn;
//string reject;
string tell_out;
if (ob = MESSAGE_D->find_user(to))
{
if (ob->query("env/invisible"))
return "这个人现在不在线上。";
fromid = lower_case(from + "@" + mud);
no_tell = ob->query("env/no_tell");
if ((! intp(wiz_level) || wiz_level < 3) &&
(no_tell == "all" || no_tell == "ALL" ||
is_sub(fromid, no_tell)))
{
can_tell = ob->query("env/can_tell");
if (! is_sub(fromid, can_tell))
return "这个人不想听你罗嗦啦。";
}
fromid = capitalize(from) + "@" + upper_case(mud);
msg = replace_string(msg, "\n", "");
if (cname)
tell_out = sprintf(HIG "%s(%s)告诉你：%s\n" NOR,
cname, fromid, msg);
else
{
cname = "未知";
tell_out = sprintf(HIG "%s 告诉你：%s\n" NOR,
fromid, msg);
}
to = capitalize(to);
if (! notice_user(cname, fromid, ob, tell_out))
msg = sprintf(HIG "你的话没有送到%s(%s@%s)的耳边。\n" NOR,
ob->name(1), to, upper_case(INTERMUD_MUD_NAME));
else
msg = sprintf(HIG "你告诉%s(%s@%s)：%s" NOR, ob->name(1), to,
upper_case(INTERMUD_MUD_NAME), msg);
return msg;
} else
return "这个人现在不在线上。";
}
void do_index( string *skills ) {
string buf;
int x;
buf = "SKILLS\nINDEX\nThere are currently aproximately half a quintrillion different skills available to players in the game. This file is an index of the entire tree. Enjoy.\n\n";
for( x = 0; x < sizeof(skills); x++ ) {
string skill = skills[x];
int dot = member( skill, '.' );
if( dot == -1 ) {
// no dot means root skill
buf += " ~CBRT+ ~CTIT"+upper_case(skill)+"\n";
} else {
while( (dot = member(skill,'.')) != -1 ) {
buf += " ";
skill = skill[dot+1..];
}
buf += " ~CDEF- ~CBRT"+skill+"\n";
}
}
buf += "\n~CLABSee also: ~CREFskills, stats, spells";
do_write( "index", buf );
}
QString compute_oiio_files_filter()
{
stringstream sstr;
string extensions;
OIIO::getattribute("extension_list", extensions);
vector<string> formats;
split(extensions, ";", formats);
for (const_each<vector<string> > i = formats; i; ++i)
{
const string::size_type sep = i->find_first_of(':');
const string format = i->substr(0, sep);
const string extlist = i->substr(sep + 1);
vector<string> exts;
split(extlist, ",", exts);
sstr << upper_case(format) << " Files (";
for (const_each<vector<string> > e = exts; e; ++e)
{
if (e.it() != exts.begin())
sstr << ";";
sstr << "*." << *e;
}
sstr << ");;";
}
sstr << "All Files (*.*)";
return QString::fromStdString(sstr.str());
}
string from6to8(string text) {
text = upper_case(text);
bool found = true;
while( found ) {
found = false;
if( text.find("~[0X2B]") < text.length()) {
found = true;
text = text.replace(text.find("~[0X2B]"),7,"~[0X02]");
}
if( text.find("~[0X2C]") < text.length() ) {
found = true;
text = text.replace(text.find("~[0X2C]"),7,"~[0X03]");
}
if( text.find("~[0X2D]")< text.length()) {
found = true;
text = text.replace(text.find("~[0X2D]"),7,"~[0X04]");
}
if( text.find("~[0X2E]") < text.length()) {
found = true;
text = text.replace(text.find("~[0X2E]"),7,"~[0X05]");
}
if( text.find("~[0X2F]") < text.length() ) {
found = true;
text = text.replace(text.find("~[0X2F]"),7,"~[0X06]");
}
}
return text;
}
static bool test_upper_case_non_empty() {
emit_test("Test upper_case() on a non-empty std::string.");
std::string a("lower UPPER");
upper_case(a);
emit_output_expected_header();
emit_retval("%s", "LOWER UPPER");
emit_output_actual_header();
emit_retval("%s", a.c_str());
if(strcmp(a.c_str(), "LOWER UPPER") != MATCH) {
FAIL;
}
PASS;
}
void echo(int connfd, char *prefix)
{
size_t n;
char buf[MAXLINE];
rio_t rio;
Rio_readinitb(&rio, connfd);
while((n = Rio_readlineb(&rio, buf, MAXLINE)) != 0) {
bytecnt += n;
printf("%sreceived %d bytes (%d total)\n", prefix, (int) n, bytecnt);
upper_case(buf);
Rio_writen(connfd, buf, n);
}
}
void incoming_request(mapping info)
{
mapping minfo;
string tmsg;
#ifdef DEBUG
CHANNEL_D->do_channel(this_object(), DEBUG,
sprintf("gchannel message get from %s:%s.", info["HOSTADDRESS"],info["PORTUDP"]));
#endif
if(!ACCESS_CHECK(previous_object())) return;
if (info["NAME"]) {
if (info["NAME"] == Mud_name()) return ;
minfo = DNS_MASTER->query_mud_info(info["NAME"]);
if (!minfo || !strlen(info["USRNAME"])
|| !DNS_MASTER->dns_mudp(info["NAME"])) {
// We don't accept the message. But ping them anyway.
PING_Q->send_ping_q(info["HOSTADDRESS"], info["PORTUDP"]);
return ;
}
if ( (info["HOSTADDRESS"] != minfo["HOSTADDRESS"]) ) {
if (info["EMOTE"])
tmsg = info["USRNAME"]+"@"+upper_case(info["NAME"])+" "+info["MSG"];
else
tmsg = info["USRNAME"]+"@"+info["NAME"]+": "+info["MSG"];
// Faked. sheeze...
dns_log("dns_fake",sprintf( "Gchannel: %s %s\n%s", ctime(time()),
info["HOSTADDRESS"],tmsg));
DNS_MASTER->send_udp(info["HOSTADDRESS"], info["PORTUDP"],
"@@@"+DNS_WARNING+
"||NAME:"+Mud_name()+
"||MSG: Fake gchannel msg: "+tmsg+
"||FAKEHOST:"+info["HOSTADDRESS"]+
"@@@\n");
return;
}
if( undefinedp(info["CNAME"]) )
set("channel_id", sprintf("%s@%s", info["USRNAME"], info["NAME"]) );
else
set("channel_id", sprintf("%s(%s@%s)",info["CNAME"], info["USRNAME"], info["NAME"]) );
CHANNEL_D->do_channel(this_object(), lower_case(info["CHANNEL"]), info["MSG"], info["EMOTE"], 1);
} //if (info["NAME"])
}
int ident_zip(char *fn)
{
ZIP* zip;
struct zipent* zipf;
printf("Zip file to ident = '%s'\n", fn);
if ((zip = openzip(fn)) == 0) {
printf("Error, cannot open zip file '%s' !\n", fn);
return 1;
};
while (zipf = readzip(zip)) {
upper_case(zipf->name);
romident(zipf->name, zipf->crc32, zipf->uncompressed_size);
};
closezip(zip);
return 0;
}
QString get_oiio_image_files_filter()
{
static QString filter;
static QMutex mutex;
QMutexLocker locker(&mutex);
if (filter.isEmpty())
{
stringstream sstr;
string extensions;
OIIO::getattribute("extension_list", extensions);
vector<string> formats;
split(extensions, ";", formats);
for (const_each<vector<string> > i = formats; i; ++i)
{
const string::size_type sep = i->find_first_of(':');
const string format = i->substr(0, sep);
const string extlist = i->substr(sep + 1);
vector<string> exts;
split(extlist, ",", exts);
sstr << upper_case(format) << " Files (";
for (const_each<vector<string> > e = exts; e; ++e)
{
if (e.it() != exts.begin())
sstr << " ";
sstr << "*." << *e;
}
sstr << ");;";
}
sstr << "All Files (*.*)";
filter = QString::fromStdString(sstr.str());
}
return filter;
}
string timestamp(){
string rawtz;
int *t, gmtoff, offset;
gmtoff = localtime(time())[LT_GMTOFF];
// if the gmtoffset is set to zero by the driver, then we need to
// calculate an offset
if (gmtoff == 0){
// if the timezone.cfg file exists, use it else default to GMT
rawtz = query_tz();
offset = TIME_D->GetOffset(rawtz);
offset += EXTRA_TIME_OFFSET;
}
else {
rawtz = upper_case(localtime(time())[LT_ZONE]);
offset = 0;
}
t = localtime(time()+(offset*3600));
return sprintf("%04d.%02d.%02d-%02d.%02d", t[LT_YEAR], (t[LT_MON])+1, t[LT_MDAY], t[LT_HOUR], t[LT_MIN]);
}
int settings_set_variable(const char* key, const char* val, settings_t* sttngs)
{
char* _key = str_strip(key);
upper_case(_key);
char* _val = str_strip(val);
int rv = 0;
if (strcmp(_key, "START_OBSERVATION")==0)
{
sttngs->start += _atotime(_val, &rv);
if (rv==-1)
rv=0;
} else if (strcmp(_key, "END_OBSERVATION")==0)
{
sttngs->stop += _atotime(_val, &rv);
if (rv==-1)
rv=0;
} else if (strcmp(_key, "MAG")==0)
{
sttngs->mag_min = _atof(_val, &rv);
} else if (strcmp(_key, "UM")==0)
{
sttngs->um_min = _atof(_val, &rv);
} else if (strcmp(_key, "RA_RATE_MIN")==0)
{
sttngs->ra_rate_min = _atof(_val, &rv);
} else if (strcmp(_key, "RA_RATE_MAX")==0)
{
sttngs->ra_rate_max = _atof(_val, &rv);
} else if (strcmp(_key, "DECL_RATE_MIN")==0)
{
sttngs->decl_rate_min = _atof(_val, &rv);
} else if (strcmp(_key, "DECL_RATE_MAX")==0)
{
sttngs->decl_rate_max = _atof(_val, &rv);
} else if (strcmp(_key, "DAY")==0)
{
sttngs->start += _atodate(_val, &rv);
sttngs->stop += _atodate(_val, &rv);
} else if (strcmp(_key, "EFEM_DIR")==0)
{
sttngs->dir = strdup(_val);
} else if (strcmp(_key, "BLACK_LIST")==0)
{
int i=0;
char* str = _val;
char* tmp;
int len = strlen(_val);
int flag=1;
while (++i<len)
{
if (_val[i]==' ' || _val[i]=='\t' || _val[i]=='\n')
{
if (flag)
{
_val[i]='\0';
tmp = str_strip(str);
if (strlen(tmp))
{
vec_add((void **)&sttngs->black_list, (void *)&tmp);
str = &(_val[i])+1;
flag=0;
}
else
{
free(tmp);
}
}
}
else
{
flag=1;
}
}
tmp = str_strip(str);
if (strlen(tmp))
{
vec_add((void **)&sttngs->black_list, (void *)&tmp);
}
else
{
free(tmp);
}
} else if (strcmp(_key, "RA_POSITION_MIN")==0)
{
sttngs->ra_position_min = _ra(_val, &rv);
} else if (strcmp(_key, "RA_POSITION_MAX")==0)
{
sttngs->ra_position_max = _ra(_val, &rv);
} else if (strcmp(_key, "REPORT_TYPE")==0)
{
if (strcmp(_val, "HTML")==0)
{
sttngs->report_type = report_type_html;
}
} else if (strcmp(_key, "REPORT_HTML_FONT_SIZE")==0)
{
sttngs->report_html_font_size = strdup(_val);
} else if (strcmp(_key, "USE_ORB_FILE")==0)
{
sttngs->use_orb_file = (strcmp(_val, "NO")!=0);
} else if (strcmp(_key, "ORB_FILE")==0)
{
sttngs->orb_file = strdup(_val);
}
sfree(_val);
sfree(_key);
return rv;
}
int main(int argc, char *argv[])
{
int sockfd, newsockfd, portno, clilen;
char buffer[256];
struct sockaddr_in serv_addr, cli_addr;
int n;
FILE *fp;
char line[256];
char *line_cap;
bool flag_eof = false;
printf("Inside Server Code\n");
if (argc < 3) {
fprintf(stderr, "Usage: %s <filename> <port no>\n", argv[0]);
exit(1);
}
/* Socket to Send Capitalized Words to Client*/
sockfd = socket(AF_INET, SOCK_STREAM, 0);
if (sockfd < 0)
error("ERROR opening socket");
memset((char *) &serv_addr, 0, sizeof(serv_addr));
/* Populating Server Information */
portno = atoi(argv[2]);
serv_addr.sin_family = AF_INET;
serv_addr.sin_addr.s_addr = INADDR_ANY;
serv_addr.sin_port = htons(portno);
/*Server Binds and Listens */
if (bind(sockfd, (struct sockaddr *) &serv_addr,
sizeof(serv_addr)) < 0)
error("ERROR on binding");
listen(sockfd,5);
/* Accepting Connections*/
clilen = sizeof(cli_addr);
newsockfd = accept(sockfd, (struct sockaddr *) &cli_addr, &clilen);
if (newsockfd < 0)
error("ERROR on accept");
/*Open the File for reading*/
fp = fopen(argv[1], "r");
if (fp == NULL)
exit(EXIT_FAILURE);
while(1){
bzero(buffer,256);
n = read(newsockfd,buffer,256);
if (n < 0)
error("ERROR reading from socket");
printf("Here is the message: %s",buffer);
if(!strcmp(buffer, "LINE\n")){
if(fgets (line, 256, fp) == NULL){
printf("eof");
flag_eof = true;
fseek(fp, 0L, SEEK_SET);
}
if (flag_eof == true){
fgets(line, 256, fp);
flag_eof=false;
}
printf("Server Read = %s", line);
line_cap = upper_case(line);
printf("Server Processed = %s", line_cap);
if (feof(fp))
fseek(fp, 0L, SEEK_SET);
/* Send that Capitalized Line to the Client */
n = write(newsockfd, line, sizeof(line));
if (n < 0)
error("ERROR writing to socket");
}
else
exit(1);
} /*Close after while loops is over i.e., after the client has sent 10 things */
fclose(fp);
return 0;
}
//--------- Begin of function Font::text_width ----//
//
// Given the textPtr string, then calculate the width (unit:pixel).
//
// char* textPtr = the textPtr to be put on screen
// [int] textPtrLen = the length of the textPtr to be put
// (default : -1, until NULL character)
// [int] maxDispWidth = the maximum width can be displayed
// the textPtr width cannot > maxDispWidth
// [cap] set all letter to Cap letter (default : 0)
//
// Note : static var text_line_count is used to pass value to text_height()
//
// Return : <int> the screen width of the textPtr display using this font
//
int Font::text_width(const char* textPtr, int textPtrLen, int maxDispWidth, int cap)
{
int charWidth, x=0, lenCount, maxLen=0, wordWidth=0;
short textChar;
if( !init_flag )
return x;
textPtr = translate.process(textPtr);
if( textPtrLen < 0 )
textPtrLen = strlen(textPtr);
text_line_count=1;
//-------------------------------------//
for( lenCount=1 ; *textPtr && lenCount<=textPtrLen ; textPtr++, lenCount++, x+=inter_char_space )
{
textChar = *((unsigned char*)textPtr);
// ###### begin Ban 18/1 ######//
if( cap==1 )
{
textChar = upper_case(textChar);
}
// ###### end Ban 18/1 ######//
//-- if the line exceed the given max width, advance to next line --//
if( maxDispWidth && x > maxDispWidth )
{
maxLen = maxDispWidth;
x = wordWidth; // the last word of the prev line wraps to next line
text_line_count++;
}
//--- if the textPtr has more than 1 line, get the longest line ---//
if( textChar == '\n' )
{
if( x>maxLen )
maxLen=x;
x=0;
wordWidth=0;
text_line_count++;
continue; // next character
}
//-------- control char: FIRST_NATION_COLOR_CODE_IN_TEXT -----------//
else if( textChar >= FIRST_NATION_COLOR_CODE_IN_TEXT && textChar <= LAST_NATION_COLOR_CODE_IN_TEXT ) // display nation color bar in text
{
x += NATION_COLOR_BAR_WIDTH;
wordWidth = 0;
}
//--- add the width of the character to the total line width ---//
else if( textChar == ' ' )
{
x += space_width;
wordWidth = 0;
}
else if( textChar >= first_char && textChar <= last_char )
{
charWidth = font_info_array[textChar-first_char].width;
x += charWidth;
wordWidth += charWidth;
}
else
{
x += space_width;
wordWidth += space_width;
}
if( maxDispWidth && wordWidth > maxDispWidth )
{
x -= wordWidth - maxDispWidth;
wordWidth = maxDispWidth;
}
}
//-------------------------------------------//
if( maxDispWidth && x > maxDispWidth )
text_line_count++;
if( textPtr[-1] == '\n' ) // if last character is line feed, don't count double
text_line_count--;
return max(maxLen,x);
}
//--------- Start of function Font::put ---------//
//
// write text with pre-inited fonts
//
// int x,y = location of the font
// char* text = the text to be put on screen
// [int] clearBack = clear background with back_color or not
// (default : 0)
// [int] x2 = display font up to the right border x2 and also
// clear the area between the last character and right border
// [int] cap = set all letter to Cap letter (default : 0)
//
// Return : <int> lastX, the x coordination of the last pixel of last font
//
int Font::put(int x,int y,const char* textPtr, char clearBack, int x2, int cap )
{
err_when( x<0 || y<0 );
if( !init_flag )
return x;
//-------- process translation ---------//
short textChar;
textPtr = translate.process(textPtr);
//-------------------------------------//
int textPtrLen = strlen(textPtr);
if( x2 < 0 ) // default
x2 = x+max_font_width*textPtrLen;
x2 = min( x2, VGA_WIDTH-1 );
int y2 = y+font_height-1;
//-------------------------------------//
FontInfo* fontInfo;
for( int lenCount=1 ; *textPtr && lenCount<=textPtrLen ; textPtr++, lenCount++ )
{
textChar = *((unsigned char*)textPtr); // textChar is <unsiged char>
// ###### begin Ban 18/1 ######//
if( cap==1 )
{
textChar = upper_case(textChar);
}
// ###### end Ban 18/1 ######//
//--------------- space character ------------------//
if( textChar == ' ' )
{
if( x+space_width > x2 )
break;
x += space_width;
}
//####### patch begin Gilbert 28/2 ########//
// --------- control char: FIRST_NATION_COLOR_CODE_IN_TEXT -----------//
else if( textChar >= FIRST_NATION_COLOR_CODE_IN_TEXT && textChar <= LAST_NATION_COLOR_CODE_IN_TEXT ) // display nation color bar in text
{
if( x2 >= 0 && x+NATION_COLOR_BAR_WIDTH-1 > x2 ) // exceed right border x2
break;
char colorCode = game.color_remap_array[textChar-FIRST_NATION_COLOR_CODE_IN_TEXT].main_color;
nation_array.disp_nation_color(x, y+2, colorCode);
x += NATION_COLOR_BAR_WIDTH;
}
//####### end begin Gilbert 28/2 ########//
//------------- normal character ----------------//
else if( textChar >= first_char && textChar <= last_char )
{
fontInfo = font_info_array+textChar-first_char;
if( x+fontInfo->width > x2 )
break;
if( fontInfo->width > 0 )
{
Vga::active_buf->put_bitmap_trans(x, y+fontInfo->offset_y, font_bitmap_buf + fontInfo->bitmap_offset);
x += fontInfo->width; // inter-character space
}
}
else
{
//------ tab or unknown character -------//
if( textChar == '\t' ) // Tab
x += space_width*8; // one tab = 8 space chars
else
x += space_width;
}
//--------- inter-character space ---------//
x+=inter_char_space;
}
return x-1;
}
lexeme lexer::get_lexeme(void){
do{ /* we will roatate here till CIN isn't over */
if(_i == _read_chars_num){
_pconf._source_stream->read(_buffer, static_cast<streamsize>(_pconf._read_buffer_size));
_read_chars_num = static_cast<size_t>(_pconf._source_stream->gcount());
if(!_read_chars_num){
if(_current_state == C2){
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
_i = 0; //in case we have just one word, and there is nothing more, we return word and preparing for the next TERM
return WORD;
}
return TERM; /* end of stream reached*/
}
//if(_tot_characters_read + _read_chars_num > _pconf._max_content_length) /* we have reached max_content_length limitation */
// throw out_of_range(get_module_msg("max content length reached (") + stream_cast<string>(_pconf._max_content_length) + ")");
_tot_characters_read += _read_chars_num; /* increment read character counter */
_i = 0;
}
for(; _i < _read_chars_num; _i++){
//_strbuf.push_back(_buffer[_i]);
_strbuf.append(1, _buffer[_i]);
switch(_buffer[_i]){
case COLON :
_current_state = Lexer[_current_state][3];
break;
//case SEMICOLON :
// _current_state = Lexer[_current_state][4];
// break;
case QUOTE :
_current_state = Lexer[_current_state][5];
break;
case ENTER :
_current_state = Lexer[_current_state][1];
break;
case CR_RETURN :
_current_state = Lexer[_current_state][2];
break;
case SPACEBAR :
_current_state = Lexer[_current_state][6];
break;
case EQUALITY :
_current_state = Lexer[_current_state][10];
break;
case LEFT_SQUARE_BRACKET:
_current_state = Lexer[_current_state][11];
break;
case RIGHT_SQUARE_BRACKET:
_current_state = Lexer[_current_state][12];
break;
case SLASH:
_current_state = Lexer[_current_state][13];
break;
case MULT:
_current_state = Lexer[_current_state][14];
break;
default:
_current_state = Lexer[_current_state][0];
break;
}
bool _was_erased = false;
/* now, check out if we're in Terminate state */
if(Lexer[_current_state][8] == T && Lexer[_current_state][9] == YES){
//pushing back one symbol
//take you attention that we just not have to decrese _i, (due to implementation)
if(int(_strbuf.length()-1) >= 0){
_strbuf.erase(_strbuf.length()-1);
_was_erased = true;
}
}
if(Lexer[_current_state][8] == T && Lexer[_current_state][9] == NO && _i + 1 <= _read_chars_num){
_i++;
}
switch(_current_state){
case C3: /* we found WORD */
// That it is not the proper place for this hack
// but it make parser simplier
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
switch(_strbuf_copy.length()){
case 1:
_upper_str = upper_case(_strbuf_copy);
if(_upper_str == _BOLD)
return BOLD;
if(_upper_str == _ITALIC)
return ITALIC;
if(_upper_str == _UNDERLINE)
return UNDERLINE;
if(_upper_str == _HEADER)
return HEADER;
if(_upper_str == _SMALL)
return SMALL;
if(_upper_str == _OFFTOPIC)
return OFFTOPIC;
if(_upper_str == _Q)
return QQUOTE;
if(_upper_str == _MULT)
return MULT;
break;
case 2:
_upper_str = upper_case(_strbuf_copy);
if(_upper_str == _HR)
return HR;
break;
case 3:
_upper_str = upper_case(_strbuf_copy);
if(_upper_str == _SUP)
return SUP;
if(_upper_str == _SUB)
return SUB;
if(_upper_str == _RED)
return RED;
if(_upper_str == _URL)
return URL;
if(_upper_str == _IMG)
return IMG;
if(_upper_str == _PRE)
return PRE;
if(_upper_str == _RED)
return RED;
break;
case 4:
_upper_str = upper_case(_strbuf_copy);
if(_upper_str == _SIZE)
return SIZE;
if(_upper_str == _FACE)
return FACE;
if(_upper_str == _LIST)
return LIST;
if(_upper_str == _CODE)
return CODE;
if(_upper_str == _QUOTE)
return QQUOTE;
if(_upper_str == _BLUE)
return BLUE;
break;
case 5:
_upper_str = upper_case(_strbuf_copy);
if(_upper_str == _EMAIL)
return EMAIL;
if(_upper_str == _QUOTE)
return QQUOTE;
if(_upper_str == _COLOR)
return COLOR;
if(_upper_str == _GREEN)
return GREEN;
if(_upper_str == _WHITE)
return WHITE;
if(_upper_str == _BLACK)
return BLACK;
if(_upper_str == _OLIST)
return OLIST;
case 6:
_upper_str = upper_case(_strbuf_copy);
if(_upper_str == _ORANGE)
return ORANGE;
if(_upper_str == _PURPLE)
return PURPLE;
if(_upper_str == _YELLOW)
return YELLOW;
};
return WORD;
case C6: /* we found COLON */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return COLON;
case C7: /* we found SEMICOLON */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return SEMICOLON;
case C8: /* we found QUOTE */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return QUOTE;
case C11: /* we found SPACE */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return SPACE;
case C12: /* we found EQUALITY */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return EQUALITY;
case C13: /* we found LEFT_SQUARE_BRACKET */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return LEFT_SQUARE_BRACKET;
case C14: /* we found RIGHT_SQUARE_BRACKET */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return RIGHT_SQUARE_BRACKET;
case C15: /* we found SLASH */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return SLASH;
case C16: /* we found MULT */
_strbuf_copy = _strbuf;
_strbuf.clear();
_current_state = C1;
return MULT;
default :
break;
}
}
}while(_read_chars_num <= _pconf._read_buffer_size);
return TERM;
}
void align_reads(meta_data& meta_details, vector<reference_index>& refindex)
//void align_reads(string& first_read_file, string& second_read_file, string& sam_file, vector<reference_index>& refindex)
{
unordered_map<string, int> umap;
ofstream fp_detail, fp_fastq;
ifstream fp_read_first, fp_read_second;
ofstream fp_sam;//, fp_sam_first, fp_sam_second;
string detail_file = meta_details.output_path + meta_details.index + "_Details.txt";
string sam_output_file = meta_details.output_path + meta_details.index + "_All.sam";
string sam_fread_file = meta_details.output_path + meta_details.index + "_R1.sam";
string sam_sread_file = meta_details.output_path + meta_details.index + "_R2.sam";
string fastq_output_file = meta_details.output_path + meta_details.index + "_All.detail";
fp_detail.open(detail_file.c_str(), ofstream::out);
fp_read_first.open(meta_details.first_read.c_str(), ifstream::in);
fp_read_second.open(meta_details.second_read.c_str(), ifstream::in);
fp_sam.open(sam_output_file.c_str(), ofstream::out | ofstream::app);
//fp_sam_first.open(sam_fread_file.c_str(), ofstream::out);
//fp_sam_second.open(sam_sread_file.c_str(), ofstream::out);
fp_fastq.open(fastq_output_file.c_str(), ofstream::out);
string input_first, read_name_first;
string readseq_first, refgenome_first;
string input_second, read_name_second;
string readseq_second, refgenome_second;
string quality_first, quality_second;
string sam_output_name;
string readsequence, readquality;
fragment_alignment fragment_alignment_first;
fragment_alignment fragment_alignment_second;
vector<string> sam_output_first;
vector<string> sam_output_second;
/*
for(int i = 0; i < refindex.size(); i++)
{
fp_fastq << "> CONSENSUS" << endl;
fp_fastq << refindex[i].ref << endl;
}
*/
int map = 0, count = 0, cant_map = 0, name_length;
cell **matrix = NULL;
//init_matrix(matrix);//does not work
matrix = new cell *[2 * FRAGMENT_SIZE + 5];
for(int i = 0; i < 2 * FRAGMENT_SIZE + 5; i++)
{
matrix[i] = new cell[FRAGMENT_SIZE + 5];
}
if(DEBUG == 99)
fp_detail << "size of matrix = " << sizeof(matrix) << endl;
while(getline(fp_read_first, read_name_first) && getline(fp_read_second, read_name_second))
{
getline(fp_read_first, readseq_first);
getline(fp_read_first, input_first);
getline(fp_read_first, quality_first);
getline(fp_read_second, readseq_second);
getline(fp_read_second, input_second);
getline(fp_read_second, quality_second);
for(int i = 0; i < read_name_first.length(); i++)
{
if(read_name_first.at(i) == read_name_second.at(i))
name_length = i;
else
break;
}
sam_output_name = meta_details.index + "_" + read_name_first.substr(0, name_length);
/*
if(read_name_first.compare(read_name_second) != 0)
{
exit(0);
continue;
}
*/
//cout << "Input = " << readseq_first << endl;
if(count >= MAXREAD && MAXREAD != 0) break;
count += 1;
if(count <= MINREAD) continue;
if(count % 100000 == 0)
{
cout << endl << "Total " << count << " Reads Aligned for " << meta_details.index << endl << endl;
}
fp_detail << "####################################################################################################################" << endl;
fp_detail << count << ") " << sam_output_name << endl << endl;
fp_detail << "####################################################################################################################" << endl;
if(DEBUG == 99)
{
fp_detail << "First ) " << read_name_first << endl;
fp_detail << "Read String = " << readseq_first << endl;//.substr(0, 80) << endl;
fp_detail << "Quality = " << input_first << ": " << quality_first << endl << endl;
fp_detail << "Second) " << read_name_second << endl;
fp_detail << "Read String = " << readseq_second << endl;//.substr(0, 80) << endl;
fp_detail << "Quality = " << input_second << ": " << quality_second << endl << endl;
//referenceless_alignment(readseq_first, readseq_second, quality_first,
// quality_second, matrix, fp_detail);
}
upper_case(readseq_first);
upper_case(readseq_second);
referenceless_alignment(readseq_first, readseq_second, quality_first, quality_second,
readsequence, readquality, matrix, fp_detail);
/*
//////////////////////////////////////////////////////////////////////////////////////////
align_read_to_reference(readseq_first, read_name_first, fragment_alignment_first, quality_first,
sam_output_first, refindex, matrix, fp_sam_first, fp_detail);
align_read_to_reference(readseq_second, read_name_second, fragment_alignment_second, quality_second,
sam_output_second, refindex, matrix, fp_sam_second, fp_detail);
merge_both_alignments(refindex, sam_output_name, fragment_alignment_first, fragment_alignment_second,
fp_sam, fp_detail, fp_fastq, umap);
sam_output_first.clear();
fragment_alignment_first.alignment.clear();
sam_output_second.clear();
fragment_alignment_second.alignment.clear();
/////////////////////////////////////////////////////////////////////////////////////////
*/
fragment_alignment final_alignment_info;
vector<string> final_result;
align_read_to_reference(readsequence, sam_output_name, final_alignment_info, readquality,
final_result, refindex, meta_details, matrix, fp_sam, fp_detail);
if(umap.find(final_result[5]) == umap.end())
{
umap[final_result[5]] = 1;
fp_fastq << final_result[0] << endl;
fp_fastq << final_result[5] << endl;
fp_fastq << final_result[9] << endl;
}
else
{
umap[final_result[5]] += 1;
}
final_result.clear();
final_alignment_info.alignment.clear();
//break;
}
if(DEBUG == 99)
{
fp_detail << endl << "Overall Statistics - " << endl;
fp_detail << "Total read = " << count << endl;
}
//remove_matrix(matrix);
for(int i = 0; i < 2 * FRAGMENT_SIZE + 5; i++)
{
delete [] matrix[i];
matrix[i] = NULL;
}
delete [] matrix;
matrix = NULL;
fp_detail.close();
fp_read_first.close();
fp_read_second.close();
fp_sam.close();
//fp_sam_first.close();
//fp_sam_second.close();
fp_fastq.close();
ifstream fp_input;
fp_input.open(fastq_output_file.c_str(), ifstream::in);
ofstream fp_fasta;
string fastq_fasta_file = meta_details.output_path + meta_details.index + "_All.fasta";
fp_fasta.open(fastq_fasta_file.c_str(), ofstream::out);
string read_name, cigar, alignment_string;
for(int i = 0; i < refindex.size(); i++)
{
fp_fasta << ">CONSENSUS" << endl;
fp_fasta << refindex[i].ref << endl;
}
while(getline(fp_input, read_name))
{
getline(fp_input, cigar);
getline(fp_input, alignment_string);
fp_fasta << ">" << read_name;
fp_fasta << "|DUPCOUNT=" << umap[cigar];
fp_fasta << "|CIGAR=" << cigar << endl;
fp_fasta << alignment_string << endl;
}
}
int compare(void* empty,int x_len,const void* x_c,int y_len,const void* y_c) {
std::string::size_type t_pozX = 0;
std::string::size_type t_pozY = 0;
size_t tmp;
std::string stringX,stringY;
std::string x,y;
bool overwrite;
char t_result,n_result;
bool national_char;
n_result = 0;
t_result = 0;
x = std::string((const char*)x_c,x_len);
y = std::string((const char*)y_c,y_len);
// pomijanie kodow specjalnych....
// zmiana kolejnosci dla kodow 1e i 1f
/*
if( x.find(0x1d) != x.npos) {
t_pozX = x.find(0x1d);
//stringX = x.substr(t_pozX+7);
x = x.substr(0,t_pozX);
}
if( y.find(0x1d) != x.npos) {
t_pozY = y.find(0x1d);
//stringX = x.substr(t_pozX+7);
y = y.substr(0,t_pozY);
}
*/
if( code_page != 1252 ) {
for(size_t i = 0; i<x.size(); ++i) {
if( ((unsigned char)x[i]) < 32 )
x.erase(i,1);
}
for(size_t i = 0; i<y.size(); ++i) {
if( ((unsigned char)y[i]) < 32 )
y.erase(i,1);
}
}
overwrite = true;
stringX = upper_case(x);
if( stringX.find(0x1e) != stringX.npos) {
t_pozX = stringX.find(0x1e);
stringX = x.substr(t_pozX+1);
//stringX += x.substr(0,t_pozX);
overwrite = false;
}
if( stringX.find(0x1f) != stringX.npos) {
t_pozX = stringX.find(0x1f);
//stringX = x.substr(t_pozX+1);
stringX += x.substr(0,t_pozX);
overwrite = false;
}
if( overwrite )
stringX = x;
overwrite = true;
stringY = upper_case(y);
if( stringY.find(0x1e) != stringY.npos) {
t_pozY = stringY.find(0x1e);
stringY = y.substr(t_pozY+1);
//stringY += y.substr(0,t_pozY);
overwrite = false;
}
if( stringY.find(0x1f) != stringY.npos) {
t_pozY = stringY.find(0x1f);
//stringY = y.substr(t_pozY+7);
stringY += y.substr(0,t_pozY);
overwrite = false;
}
if( overwrite )
stringY = y;
/*
overwrite = true;
stringY = upper_case(y);
if( stringY.find("~[0X1E]") != stringY.npos) {
t_pozY = stringY.find("~[0X1E]");
stringY = y.substr(t_pozY+7);
stringY += y.substr(0,t_pozY);
overwrite = false;
}
if( stringY.find("~[0X1F]") != stringY.npos) {
t_pozY = stringY.find("~[0X1F]");
stringY = y.substr(t_pozY+7);
stringY += y.substr(0,t_pozY);
overwrite = false;
}
if( overwrite )
stringY = y;
*/
t_pozY = 0;
t_pozX=0;
while( stringX.find("~") != stringX.npos ) {
tmp = stringX.find("~");
if( tmp != stringX.find("[")-1 ) {
stringX = stringX.substr(0,tmp) + stringX.substr(tmp+1);
}
if( tmp == 0 )
stringX = stringX.substr(stringX.find("]")+1);
else
stringX = stringX.substr(0,tmp) + stringX.substr(stringX.find("]")+1);
}
while( stringY.find("~") != stringY.npos ) {
tmp = stringY.find("~");
if( tmp != stringY.find("[")-1 ) {
stringY = stringY.substr(0,tmp) + stringY.substr(tmp+1);
}
if( tmp == 0 )
stringY = stringY.substr(stringY.find("]")+1);
else
stringY = stringY.substr(0,tmp) + stringY.substr(stringY.find("]")+1);
}
national_char = false;
while(stringX.length() > t_pozX && stringY.length() > t_pozY) {
//
// ~[0x1b2b] - od tego ~[0x1e] - od tego symbolu sortowanie �
// ~[0x1b2c] - do tego ~[0x1f]- do tego symbolu
//
t_result = c_compare(stringX[t_pozX],stringY[t_pozY]);
if( t_result == -1 ) return -1;
if( t_result == 1 ) return 1;
if( t_result == -2 ) {
national_char = true;
n_result = -1;
}
if( t_result == 2 ) {
national_char = true;
n_result = 1;
}
t_pozX++;
t_pozY++;
}
if( national_char && stringX.length() == stringY.length() ) {
return n_result;
}
if(stringX.length() > stringY.length())
return 1;
if(stringX.length() < stringY.length())
return -1;
return 0;
}
void
get_current_configuration(struct supported_gdb_version *sp)
{
FILE *fp;
static char buf[512];
char *p;
#ifdef __alpha__
target_data.target = ALPHA;
#endif
#ifdef __i386__
target_data.target = X86;
#endif
#ifdef __powerpc__
target_data.target = PPC;
#endif
#ifdef __ia64__
target_data.target = IA64;
#endif
#ifdef __s390__
target_data.target = S390;
#endif
#ifdef __s390x__
target_data.target = S390X;
#endif
#ifdef __powerpc64__
target_data.target = PPC64;
#endif
#ifdef __x86_64__
target_data.target = X86_64;
#endif
#ifdef __arm__
target_data.target = ARM;
#endif
#ifdef __aarch64__
target_data.target = ARM64;
#endif
#ifdef __mips__
target_data.target = MIPS;
#endif
set_initial_target(sp);
/*
* Override target if specified on command line.
*/
target_data.host = target_data.target;
if (target_data.target_as_param) {
if ((target_data.target == X86 || target_data.target == X86_64) &&
(name_to_target((char *)target_data.target_as_param) == ARM)) {
/*
* Debugging of ARM core files supported on X86, and on
* X86_64 when built as a 32-bit executable.
*/
target_data.target = ARM;
} else if ((target_data.target == X86 || target_data.target == X86_64) &&
(name_to_target((char *)target_data.target_as_param) == MIPS)) {
/*
* Debugging of MIPS little-endian core files
* supported on X86, and on X86_64 when built as a
* 32-bit executable.
*/
target_data.target = MIPS;
} else if ((target_data.target == X86_64) &&
(name_to_target((char *)target_data.target_as_param) == X86)) {
/*
* Build an X86 crash binary on an X86_64 host.
*/
target_data.target = X86;
} else if ((target_data.target == X86_64) &&
(name_to_target((char *)target_data.target_as_param) == ARM64)) {
/*
* Build an ARM64 crash binary on an X86_64 host.
*/
target_data.target = ARM64;
} else if ((target_data.target == X86_64) &&
(name_to_target((char *)target_data.target_as_param) == PPC64)) {
/*
* Build a PPC64 little-endian crash binary on an X86_64 host.
*/
target_data.target = PPC64;
} else if ((target_data.target == PPC64) &&
(name_to_target((char *)target_data.target_as_param) == PPC)) {
/*
* Build an PPC crash binary on an PPC64 host.
*/
target_data.target = PPC;
} else if (name_to_target((char *)target_data.target_as_param) ==
target_data.host) {
if ((target_data.initial_gdb_target != UNKNOWN) &&
(target_data.host != target_data.initial_gdb_target))
arch_mismatch(sp);
} else {
fprintf(stderr,
"\ntarget=%s is not supported on the %s host architecture\n\n",
target_data.target_as_param,
target_to_name(target_data.host));
exit(1);
}
}
/*
* Impose implied (sticky) target if an initial build has been
* done in the source tree.
*/
if (target_data.initial_gdb_target &&
(target_data.target != target_data.initial_gdb_target)) {
if ((target_data.initial_gdb_target == ARM) &&
(target_data.target != ARM)) {
if ((target_data.target == X86) ||
(target_data.target == X86_64))
target_data.target = ARM;
else
arch_mismatch(sp);
}
if ((target_data.target == ARM) &&
(target_data.initial_gdb_target != ARM))
arch_mismatch(sp);
if ((target_data.initial_gdb_target == MIPS) &&
(target_data.target != MIPS)) {
if ((target_data.target == X86) ||
(target_data.target == X86_64))
target_data.target = MIPS;
else
arch_mismatch(sp);
}
if ((target_data.initial_gdb_target == X86) &&
(target_data.target != X86)) {
if (target_data.target == X86_64)
target_data.target = X86;
else
arch_mismatch(sp);
}
if ((target_data.target == X86) &&
(target_data.initial_gdb_target != X86))
arch_mismatch(sp);
if ((target_data.initial_gdb_target == ARM64) &&
(target_data.target != ARM64)) {
if (target_data.target == X86_64)
target_data.target = ARM64;
else
arch_mismatch(sp);
}
if ((target_data.target == ARM64) &&
(target_data.initial_gdb_target != ARM64))
arch_mismatch(sp);
if ((target_data.initial_gdb_target == PPC64) &&
(target_data.target != PPC64)) {
if (target_data.target == X86_64)
target_data.target = PPC64;
else
arch_mismatch(sp);
}
if ((target_data.target == PPC64) &&
(target_data.initial_gdb_target != PPC64))
arch_mismatch(sp);
if ((target_data.initial_gdb_target == PPC) &&
(target_data.target != PPC)) {
if (target_data.target == PPC64)
target_data.target = PPC;
else
arch_mismatch(sp);
}
if ((target_data.target == PPC) &&
(target_data.initial_gdb_target != PPC))
arch_mismatch(sp);
}
if ((fp = fopen("Makefile", "r")) == NULL) {
perror("Makefile");
goto get_release;
}
while (fgets(buf, 512, fp)) {
if (strncmp(buf, "PROGRAM=", strlen("PROGRAM=")) == 0) {
p = strstr(buf, "=") + 1;
strip_linefeeds(p);
upper_case(p, target_data.program);
if (target_data.flags & DAEMON)
strcat(target_data.program, "D");
continue;
}
}
fclose(fp);
get_release:
target_data.release[0] = '\0';
if (file_exists(".rh_rpm_package")) {
if ((fp = fopen(".rh_rpm_package", "r")) == NULL) {
perror(".rh_rpm_package");
} else {
if (fgets(buf, 512, fp)) {
strip_linefeeds(buf);
if (strlen(buf)) {
buf[MAXSTRLEN-1] = '\0';
strcpy(target_data.release, buf);
} else
fprintf(stderr,
"WARNING: .rh_rpm_package file is empty!\n");
} else
fprintf(stderr,
"WARNING: .rh_rpm_package file is empty!\n");
fclose(fp);
if (strlen(target_data.release))
return;
}
} else
fprintf(stderr,
"WARNING: .rh_rpm_package file does not exist!\n");
if ((fp = fopen("defs.h", "r")) == NULL) {
perror("defs.h");
return;
}
while (fgets(buf, 512, fp)) {
if (strncmp(buf, "#define BASELEVEL_REVISION",
strlen("#define BASELEVEL_REVISION")) == 0) {
p = strstr(buf, "\"") + 1;
strip_linefeeds(p);
p[strlen(p)-1] = '\0';
strcpy(target_data.release, p);
break;
}
}
fclose(fp);
}
void align_reads(vector<pair<string, string> >& reference, string& read_file, string& sam_file, vector<reference_index>& refindex)
{
time_t tstrt, tbgn, tnd;
time(&tstrt);
/////////////////////////////////////////////////
ifstream fp_nano;
string nano_input;
string nano_file = "last_but_not_nano.txt";
char *nano = new char[nano_file.length() + 1];
strcpy(nano, nano_file.c_str());
fp_nano.open(nano, ifstream::in);
unordered_map<string, int> nano_read;
while(getline(fp_nano, nano_input))
{
//cout << "" << nano_input << endl;
nano_read[nano_input] = 1;
//continue;
}
cout << "Total Size of Nano Read = " << nano_read.size() << endl << endl;
fp_nano.close();
delete [] nano;
////////////////////////////////////////////////
ifstream fp_read;
ofstream fp_sam;
ofstream fp_2D;
//vector<string> output;
char *read = new char[read_file.length() + 1];
strcpy(read, read_file.c_str());
char *sam = new char[sam_file.length() + 1];
strcpy(sam, sam_file.c_str());
//string file_2D_str = logstr.str() + "reverse.fa";
//string file_2D_str = "2D_file_1K";
fp_read.open(read, ifstream::in);
fp_sam.open(sam, ofstream::out | ofstream::app);
//fp_2D.open(file_2D_str.c_str(), ofstream::out);
string input, read_name, ref_name;
string readseq, refgenome;
string slash = "/";
int map = 0;
int count = 0;
int cant_map = 0;
int invalid_count = 0;
fp_csv << "cnt, red_nam, red_len, red_dir, ref_nam, ref_len, ref_pos, score, span, " <<
"percent, aln_len, spn_rat, aln_tim, tot_tim" << endl;
while(getline(fp_read, input))
{
int find = input.find(slash);
if(find != string::npos)
read_name = input.substr(1, find - 1);
else
read_name = input.substr(1);
getline(fp_read, readseq);
//getline(fp_read, input);
//getline(fp_read, input);
//ratio problem with channel_46_read_98_1406145606_2D
//if(read_name.find("channel_407_read_0_1405093831_2D") == std::string::npos)//to optimize the output
//if(read_name.find("channel_17_read_24_1405524767_2D") == std::string::npos)//small read to optimize
//if(read_name.find("channel_201_read_10_1405541481_2D") == std::string::npos)//to compare version 1 and 2
//if(read_name.find("channel_64_read_7_1403826200_template") == std::string::npos)//max length reads analysis
//if(read_name.find("channel_424_read_1_1403566249_template") == std::string::npos)//found in last but not in nano
//if(read_name.find("2D") == std::string::npos)//03-09-2015
// continue;//2D== 1D !=
//if(read_name.find("channel_237_read_42_1406145606_2D") == std::string::npos)
//if(read_name.find("channel_322_read_11_1405524767_template") == std::string::npos)
//if(readseq.length() > 100)
// continue;
//if(read_name.find("channel_171_read_2_1403855963_2D") == std::string::npos)//20 times higher than last
//if(read_name.find("channel_82_read_0_1403855963_2D") == std::string::npos)//20 times higher than last
//if(read_name.find("channel_221_read_19_1406145606_2D") == std::string::npos)//has maximul length of deletion
//if(read_name.find("channel_415_read_6_1406242409_template") == std::string::npos)//has 5 times less length than last
// continue;
//if(read_name.find("channel_167_read_19_1403811400_2D") == std::string::npos)//analyze output validity
// continue;
//if(nano_read.find(read_name) == nano_read.end())
// continue;
//if(read_name.find("channel_352_read_34_1405541481_template") == std::string::npos)//Why there are multiple results
//if(read_name.find("channel_68_read_22_1405541481_template") == std::string::npos)//multiple results, boundary problem
//if(read_name.find("channel_261_read_39_1405541481_template") == std::string::npos)//multiple result indexing
// continue;
//if(read_name.find("channel_302_read_2_1403855963_2D") == std::string::npos)//found in mms not in ssg = align length
// continue;
//readseq = readseq.substr(readseq.length() / 2, readseq.length() - readseq.length() / 2);
if(count >= MAXREAD && MAXREAD != 0) break;
count += 1;
//if(count < 65433) continue;
cout << count << ") " << read_name << endl;
if(readseq.length() < MINREADLEN || readseq.length() > MAXREADLEN)//03-09-2015
{
cout << "Invalid String Found" << endl;
invalid_count += 1;
count -= 1;
time(&tnd);
//fp_csv << count << ", " << readseq.length() << ", 0, 0, 0, " <<
// "0, 0, 0, 0, 0, 0, 0, " << difftime(tnd, tstrt) << endl;
continue;
}
if(count <= MINREAD) continue;
//if(count < 318) continue;
time(&tbgn);
fp_csv << count << ", " << read_name << ", " << readseq.length() << ", ";
upper_case(readseq);
//reverse_str(readseq);
//readseq = reverse_complement(readseq);
//fp_2D << input << endl;
//fp_2D << readseq << endl;
//continue;
int match_info, global_match = -1, indpos;
int match, max_match = 0, match_index, dir;
vector<string> final_result;
time_t start, end;
clock_t t_start, t_end;
//for(int i = 0; i < reference.size(); i++)
{
//vector<pair<int, pair<int, int> > > kmer_ref;
vector<pair<int, vector<pair<int, int> > > > kmer_ref;
cout << "Analysis for forward:" << endl;
time(&start);
t_start = clock();
read_vs_reference(readseq, read_name, FF, refindex, kmer_ref);
t_end = clock();
time(&end);
cout << "Total time taken for calling forward read_vs_ref = " << difftime(end, start) << endl;
//cout << "Total time for Hash_Lookup = " << (float(t_end - t_start) / CLOCKS_PER_SEC) << endl;
t_lookup += t_end - t_start;
//align(readseq, read_name, FF, refindex, kmer_ref, final_result);
//if(final_result.size() == 0)
//{
//kmer_ref.clear();
cout << "Data for reverse:" << endl;
time(&start);
t_start = clock();
string reverse = reverse_complement(readseq);
read_vs_reference(reverse, read_name, FR, refindex, kmer_ref);
t_end = clock();
time(&end);
cout << "Total time taken for calling reverse read_vs_ref = " << difftime(end, start) << endl;
//cout << "Total time for Hash_Lookup = " << (float(t_end - t_start) / CLOCKS_PER_SEC) << endl;
t_lookup += t_end - t_start;
cout << endl <<endl;
//uncomment here
align(readseq, read_name, FR, refindex, kmer_ref, final_result);
//}
if(final_result.size() == 0)
{
cant_map += 1;
kmer_ref.clear();
time(&tnd);
//fp_csv << "0, 0, ";
fp_csv << difftime(tnd, tbgn) << ", " << difftime(tnd, tstrt) << endl;
//fp_csv << endl;
continue;
}
assert(final_result.size() == 11);
cout << "No Assertion Occurred for ReferenceIndex = " << read_name << endl;
cout << endl << endl;
kmer_ref.clear();
}
//cout << "reference_index = " << indpos << ", and match_index = " << match_index <<
// ", and direction = " << dir << ", with matching = " << max_match << endl;
//break;
//global_match = read_vs_reference(reference, readseq, read_name, final_result);
fp_sam << final_result[0];
for(int k = 1; k < final_result.size(); k++)
{
fp_sam << "\t" << final_result[k];
//cout << i << ": " << output[k] << endl;
}
fp_sam << endl;
map += 1;
final_result.clear();
//if(count >10000)
// break;
time(&tnd);
fp_csv << difftime(tnd, tbgn) << ", " << difftime(tnd, tstrt) << endl;
cout << "\nTime taken to process " << count << "th read = " << difftime(tnd, tstrt) << "\n" << endl;
//break;
}
cout << endl;
cout << "Overall Statistics - " << endl;
cout << "total reference size = " << reference.size() << endl << endl;
cout << "Total read = " << count << endl << endl;
cout << "Total read mapped = " << map << endl << endl;
cout << "Total unmapped read = " << cant_map << endl << endl;
cout << "Out of range read (< 100 or > 15000) = " << invalid_count << endl << endl;
//cout << "Total MAX_MATCHED (= " << MAX_MATCHED << ") Reads = " << MAX_SCORED << endl << endl;
fp_read.close();
fp_sam.close();
fp_2D.close();
delete [] read;
delete [] sam;
}
void input_reference(vector<pair<string, string> >& reference, string& ref_file, string& sam_file)
{
ifstream fp_ref;
ofstream fp_sam;
char *ref = new char[ref_file.length() + 1];
strcpy(ref, ref_file.c_str());
char *sam = new char[sam_file.length() + 1];
strcpy(sam, sam_file.c_str());
fp_ref.open(ref, ifstream::in);
fp_sam.open(sam, ofstream::out);
string space = " ";
string input, output;
string ref_name;
string sequence;
getline(fp_ref, input);
while(!fp_ref.eof())
{
//getline(fp_ref, input);
size_t find = input.find(space);
if(find != string::npos)
ref_name = input.substr(1, find);
else
ref_name = input.substr(1);
sequence = "";
//cout << ref_name << endl;
while(getline(fp_ref, input))
{
if(input.length() < 1)
break;
if(input.at(0) == '>')
{
break;
}
sequence += input;
}
//if(ref_name.find("chr13") == string::npos)
// continue;//added on 03-13-15
upper_case(sequence);
//cout << sequence << endl;
reference.push_back(make_pair(ref_name, sequence));
output = "@SQ\tSN:" + ref_name + "\tLN:";
fp_sam << output << sequence.length() << endl;
if(input.length() < 1)
break; //added on 03-11-15
}
fp_ref.close();
fp_sam.close();
delete [] ref;
delete [] sam;
}
void align_reads(vector<pair<string, string> >& reference, string& read_file, string& sam_file, vector<reference_index>& refindex)
{
time_t tstrt, tbgn, tnd;
time(&tstrt);
/*//Can be used for analyzing the difference between LAST and NanoBLASTer
ifstream fp_nano;
string nano_input;
string nano_file = "last_but_not_nano.txt";
char *nano = new char[nano_file.length() + 1];
strcpy(nano, nano_file.c_str());
fp_nano.open(nano, ifstream::in);
unordered_map<string, int> nano_read;
while(getline(fp_nano, nano_input))
{
//cout << "" << nano_input << endl;
nano_read[nano_input] = 1;
//continue;
}
cout << "Total Size of Nano Read = " << nano_read.size() << endl << endl;
fp_nano.close();
delete [] nano;
*/
ifstream fp_read;
ofstream fp_sam;
char *read = new char[read_file.length() + 1];
strcpy(read, read_file.c_str());
char *sam = new char[sam_file.length() + 1];
strcpy(sam, sam_file.c_str());
fp_read.open(read, ifstream::in);
fp_sam.open(sam, ofstream::out | ofstream::app);
string input, read_name, ref_name;
string readseq, refgenome;
string slash = "/";
int map = 0;
int count = 0;
int cant_map = 0;
int invalid_count = 0;
fp_csv << "cnt, red_nam, red_len, red_dir, ref_nam, ref_len, ref_pos, score, span, " <<
"percent, aln_len, spn_rat, aln_tim, tot_tim" << endl;
getline(fp_read, input);
while(!fp_read.eof())
{
//int find = input.find(slash);
//if(find != string::npos)
// read_name = input.substr(1, find - 1);
//else
// read_name = input.substr(1);
read_name = input.substr(1);
readseq = "";
while(getline(fp_read, input))
{
if(input.length() == 0)
continue;
if(input.at(0) == '>')
break;
readseq += input;
}
//getline(fp_read, input);
//getline(fp_read, input);
//ratio problem with channel_46_read_98_1406145606_2D
//if(read_name.find("channel_407_read_0_1405093831_2D") == std::string::npos)//to optimize the output
//if(read_name.find("channel_17_read_24_1405524767_2D") == std::string::npos)//small read to optimize
//if(read_name.find("channel_201_read_10_1405541481_2D") == std::string::npos)//to compare version 1 and 2
//if(read_name.find("channel_64_read_7_1403826200_template") == std::string::npos)//max length reads analysis
//if(read_name.find("channel_424_read_1_1403566249_template") == std::string::npos)//found in last but not in nano
//if(read_name.find("2D") == std::string::npos)//03-09-2015
//if(read_name.find("channel_237_read_42_1406145606_2D") == std::string::npos)
//if(read_name.find("channel_322_read_11_1405524767_template") == std::string::npos)
//if(read_name.find("channel_171_read_2_1403855963_2D") == std::string::npos)//20 times higher than last
//if(read_name.find("channel_82_read_0_1403855963_2D") == std::string::npos)//20 times higher than last
//if(read_name.find("channel_221_read_19_1406145606_2D") == std::string::npos)//has maximul length of deletion
//if(read_name.find("channel_415_read_6_1406242409_template") == std::string::npos)//has 5 times less length than last
//if(read_name.find("channel_167_read_19_1403811400_2D") == std::string::npos)//analyze output validity
//if(read_name.find("channel_474_read_32_1405524767_template") == std::string::npos)//found in last and nano repeat
//if(read_name.find("channel_468_read_12_1403811400_complement") == std::string::npos)//cause exception in nano repeat
//if(read_name.find("channel_345_read_7_1403811400_2D") == std::string::npos)//max length increased
//if(read_name.find("channel_104_read_1_1403551548_template") == std::string::npos)//different in edit not lis
//if(read_name.find("channel_216_read_0_1403551548_template") == std::string::npos)//different in lis not edit
//if(read_name.find("channel_118_read_6_1403551548_template") == std::string::npos)//different in lis and edit
//if(read_name.find("channel_486_read_0_1403566249_template") == std::string::npos)//reverse problem
//if(nano_read.find(read_name) == nano_read.end())
//if(read_name.find("channel_352_read_34_1405541481_template") == std::string::npos)//Why there are multiple results
//if(read_name.find("channel_68_read_22_1405541481_template") == std::string::npos)//multiple results, boundary problem
//if(read_name.find("channel_261_read_39_1405541481_template") == std::string::npos)//multiple result indexing
//if(read_name.find("channel_302_read_2_1403855963_2D") == std::string::npos)//found in mms not in ssg = align length
//if(read_name.find("channel_243_read_0_1403595798_template") == std::string::npos)//found in 40655 not in lis+edit
//if(read_name.find("channel_452_read_46_1405541481_template") == std::string::npos)//same problem as above
//if(read_name.find("channel_431_read_2_1403915857_template") == std::string::npos)//require top 40 tuple list to solve
//readseq = readseq.substr(readseq.length() / 2, readseq.length() - readseq.length() / 2);
//if(read_name.find("channel_199_read_0_1403841073_template") == std::string::npos)//solved
//if(read_name.find("channel_480_read_91_1406242409_template") == std::string::npos)//in last and not in nano
//if(read_name.find("channel_389_read_57_1406242409_template") == std::string::npos)//solved
//if(read_name.find("channel_56_read_1_1403826200_template") == std::string::npos)
//if(read_name.find("channel_356_read_29_1406242409_template") == std::string::npos)// < 40 in nano very weird
//if(read_name.find("channel_131_read_5_1403826200_template") == string::npos)// < 100 in nano seems weird
//if(read_name.find("channel_75_read_80_1406145606_template") == std::string::npos)//80% last not found now solved
// continue;
if(count >= MAXREAD && MAXREAD != 0) break;
count += 1;
//if(count < 11762) continue;
cout << count << ") " << read_name << endl;
if(readseq.length() < MINREADLEN || readseq.length() > MAXREADLEN)//03-09-2015
{
cout << "Invalid String Found" << endl;
invalid_count += 1;
count -= 1;
fp_sam << read_name << "\t4\t*\t0\t0\t*\t*\t0\t0\t" << readseq << "\t*" << endl;
time(&tnd);
//fp_csv << count << ", " << readseq.length() << ", 0, 0, 0, " <<
// "0, 0, 0, 0, 0, 0, 0, " << difftime(tnd, tstrt) << endl;
continue;
}
if(count <= MINREAD) continue;
//if(count < 318) continue;
time(&tbgn);
if(DEBUG == 99)
fp_csv << count << ", " << read_name << ", " << readseq.length() << ", ";
upper_case(readseq);
//reverse_str(readseq);
//readseq = reverse_complement(readseq);
int match_info, global_match = -1, indpos;
int match, max_match = 0, match_index, dir;
vector<vector<string> > list_final_result;
//time_t start, end;
//clock_t t_start, t_end;
//for(int i = 0; i < reference.size(); i++)
{
//vector<pair<int, pair<int, int> > > kmer_ref;
vector<pair<int, vector<pair<int, int> > > > kmer_ref;
//cout << "Analysis for forward:" << endl;
//
//time(&start);
//t_start = clock();
read_vs_reference(readseq, read_name, FF, refindex, kmer_ref);
//t_end = clock();
//time(&end);
//cout << "Total time taken for calling forward read_vs_ref = " << difftime(end, start) << endl;
//t_lookup += t_end - t_start;
//align(readseq, read_name, FF, refindex, kmer_ref, final_result);
//cout << "Data for reverse:" << endl;
//time(&start);
//t_start = clock();
if(SINGLE == 1)
{
string reverse = reverse_complement(readseq);
read_vs_reference(reverse, read_name, FR, refindex, kmer_ref);
}
//t_end = clock();
//time(&end);
//cout << "Total time taken for calling reverse read_vs_ref = " << difftime(end, start) << endl;
//t_lookup += t_end - t_start;
//cout << endl <<endl;
//uncomment here for aligninng read
list_final_result.clear();
align(readseq, read_name, FR, refindex, kmer_ref, list_final_result);
if(list_final_result.size() == 0)
{
cant_map += 1;
kmer_ref.clear();
//time(&tnd);
//fp_csv << difftime(tnd, tbgn) << ", " << difftime(tnd, tstrt) << endl;
fp_sam << read_name << "\t4\t*\t0\t0\t*\t*\t0\t0\t" << readseq << "\t*" << endl;
continue;
}
kmer_ref.clear();
}
for(int i = 0; i < list_final_result.size(); i++)
{
vector<string>& final_result = list_final_result[i];
fp_sam << final_result[0];
for(int k = 1; k < final_result.size(); k++)
{
fp_sam << "\t" << final_result[k];
//cout << i << ": " << output[k] << endl;
}
fp_sam << endl;
map += 1;
final_result.clear();
}
/*
if(list_final_result.size() == 0 && SAM_FORMAT == 1)
{
fp_sam << read_name << "\t4\t*\t0\t0\t*\t*\t0\t0\t" << readseq << "\t*" << endl;
}
*/
//time(&tnd);
list_final_result.clear();
if(DEBUG == 99)
fp_csv << endl;//difftime(tnd, tbgn) << ", " << difftime(tnd, tstrt) << endl;
//cout << "\nTime taken to process " << count << "th read = " << difftime(tnd, tstrt) << "\n" << endl;
//break;
}
cout << endl;
cout << "Overall Statistics - " << endl;
cout << "total reference size = " << reference.size() << endl << endl;
cout << "Total read = " << count << endl << endl;
cout << "Total read mapped = " << map << endl << endl;
cout << "Total unmapped read = " << cant_map << endl << endl;
cout << "Out of range read (< 100 or > 15000) = " << invalid_count << endl << endl;
//cout << "Total MAX_MATCHED (= " << MAX_MATCHED << ") Reads = " << MAX_SCORED << endl << endl;
fp_read.close();
fp_sam.close();
delete [] read;
delete [] sam;
}
