RetroSearch Browse

)) {

294 return

GetDateFromISODate(

);

307

month =

.substr(0, pos);

308

year =

.substr(pos + 1);

311 "collection-date string is improperly formatted"

);

314

day =

.substr(0, pos);

315

month =

.substr(pos + 1, pos2 - pos - 1);

316

year =

.substr(pos2 + 1);

319 "collection-date string is improperly formatted"

);

330 "collection-date string has invalid month"

);

340 "collection-date string has invalid day value"

);

342

}

catch

(

const

exception& ) {

345 "collection-date string is improperly formatted"

);

351 "collection-date string is improperly formatted"

);

357

}

catch

(

const

exception& ) {

360 "collection-date string is improperly formatted"

);

370 if

(year_val < 1000) {

372 "collection-date year is out of range"

);

375 if

(year_val >= 2100) {

377 "collection-date year is out of range"

);

380 if

(day_val > 0 && month_val > 0 && !IsDayValueOkForMonth(day_val, month_val, year_val)) {

382 "collection-date day is greater than monthly maximum"

);

415 bool

in_future =

false

;

417

vector<string> pieces;

419 if

(pieces.size() > 2) {

422 ITERATE

(vector<string>, it, pieces) {

458

vector<string> pieces;

460 if

(pieces.size() > 2) {

463

}

else if

(pieces.size() == 2) {

464 bool

first_bad =

false

;

465 bool

first_future =

false

;

466 bool

second_bad =

false

;

467 bool

second_future =

false

;

470

bad_format = first_bad || second_bad;

472

in_future = first_future || second_future;

485 size_t

pos2 =

NStr::Find

(date_string,

"-"

, pos + 1);

486 if

(pos2 !=

&& pos != 2) {

507

vector<string> pieces;

509 if

(pieces.size() > 2) {

511

}

else if

(pieces.size() == 2) {

536 size_t

pos2 =

NStr::Find

(date_string,

"-"

, pos + 1);

537 if

(pos2 !=

&& pos != 2) {

563 "missing: control sample"

564 "missing: data agreement established pre-2023"

565 "missing: endangered species"

566 "missing: human-identifiable"

567 "missing: lab stock"

568 "missing: sample group"

569 "missing: synthetic construct"

570 "missing: third party data"

574 "restricted access"

580 if

(s_Null_CollectionDatesSet.find(date_string.c_str()) != s_Null_CollectionDatesSet.end()) {

581 if

(is_influenza_or_Sars2) {

582

is_null_and_virus =

true

;

583

problem = date_string;

587 size_t

rval = CheckDateFormat(date_string);

588 if

(rval & eDateFormatFlag_bad_format) {

589

problem =

"Collection_date format is not in DD-Mmm-YYYY format"

;

590

}

else if

(rval & eDateFormatFlag_in_future) {

591

problem =

"Collection_date is in the future"

;

592

}

else if

(rval & eDateFormatFlag_out_of_order) {

593

problem =

"Collection_dates are out of order"

;

601 bool

is_null_and_virus =

false

;

613 if

(second_pos !=

) {

616 bool

month_ambig =

false

;

617 string

first_date =

FixDateFormat

(orig_date.substr(0, pos),

true

, month_ambig);

621 string

second_date =

FixDateFormat

(orig_date.substr(pos + delim.

length

()),

true

, month_ambig);

625 string

fix = first_date +

"/"

+ second_date;

632 bool

month_ambiguous =

false

;

634 string

fix =

FixDateFormat

(orig_date,

true

, month_ambiguous);

635 if

(month_ambiguous) {

638 static const char

* delimiters[] = {

"/"

" to "

" and "

"-"

"_"

};

659 if

(suffix ==

) {

661 if

(suffix ==

) {

662 if

(require_time_zone) {

665

suffix = orig_time.length();

668 if

(orig_time.substr(suffix).length() != 6 ||

669

((

unsigned char

)orig_time[suffix + 1]) ||

670

((

unsigned char

)orig_time[suffix + 2]) ||

671

orig_time[suffix + 3] !=

':'

672

((

unsigned char

)orig_time[suffix + 4]) ||

673

((

unsigned char

)orig_time[suffix + 5])) {

684 if

(suffix != 2 && suffix != 5 && suffix != 8) {

688 if

((

unsigned char

)orig_time[0]) || !

((

unsigned char

)orig_time[1])) {

696 if

(hour < 0 || hour > 23) {

704 if

((

unsigned char

)orig_time[3]) || !

((

unsigned char

)orig_time[4])) {

709 if

(min < 0 || min > 59) {

718 if

((

unsigned char

)orig_time[6]) || !

((

unsigned char

)orig_time[7])) {

726

}

else if

(sec > 59) {

751 if

(cpy.length() != 10 && cpy.length() != 7) {

756

string::const_iterator it = cpy.begin();

757 while

(it != cpy.end() && rval) {

758 if

(pos == 4 || pos == 7) {

772 if

(month < 1 || month > 12) {

775 if

(cpy.length() == 10) {

791 string

cpy = orig_date;

795 if

(time_pos ==

) {

816 string

cpy = orig_date;

819 if

(time_pos !=

) {

820

cpy = cpy.substr(0, time_pos);

828 string

cpy = orig_date;

831 if

(time_pos ==

) {

844 string

cpy = orig_date;

851 if

(cpy.length() > 7) {

864

vector<string> tokens;

865 string

token_delimiters =

" ,-/=_."

;

867 string

cpy = orig_date;

871 bool

is_chars =

false

;

873 if

(token_delimiters.find(*s) !=

) {

875

tokens.push_back(curr_token);

879

}

else if

(is_chars && !

((

unsigned char

)(*s))) {

882

tokens.push_back(curr_token);

888

tokens.push_back(curr_token);

899

tokens.push_back(curr_token);

903 if

(tokens.size() > 3) {

904

vector<string>::iterator p = tokens.begin();

905 bool

prev_is_number =

((

unsigned char

)(*p)[0]);

906

vector<string>::iterator s = p;

908 while

(s != tokens.end()) {

909 if

(prev_is_number &&

916

prev_is_number =

false

;

920

prev_is_number =

((

unsigned char

)(*p)[0]);

929 bool s_ChooseMonthAndDay

(

const string

& token1,

const string

& token2,

bool

month_first,

string

& month,

int

& day,

bool

& month_ambiguous)

931

month_ambiguous =

false

;

936 if

(val1 > 12 && val2 > 12) {

939

}

else if

(val1 < 13 && val2 < 13) {

946

month_ambiguous =

true

;

955

}

else if

(val1 < 13) {

972 if

(orig_date.find_first_not_of(

" ,-/=_.0123456789"

) !=

) {

979 string

delims =

" ,-/=_."

;

981 size_t next

= orig_date.find_first_of(delims,

);

982

vector<string> tokens;

984 while

(

!= string::npos) {

987 if

(

.length() == 1) {

991

tokens.push_back(

);

994 next

= orig_date.find_first_of(delims,

);

997 if

(

< orig_date.length()) {

998 string str

= orig_date.substr(

, string::npos);

999 if

(

.length() == 1) {

1003

tokens.push_back(

);

1014

month_ambiguous =

false

;

1016 string

orig_date =

;

1027 string

reformatted_date;

1029 int

year = 0, day = 0;

1031 size_t

num_original_tokens = 0;

1035

num_original_tokens = tokens.size();

1036 if

(tokens.size() < 1 || tokens.size() > 3) {

1042

vector<string>::iterator it = tokens.begin();

1043 while

(it != tokens.end()) {

1045 bool

found =

false

;

1055

}

else if

(one_token.length() > 0

1056

((

unsigned char

)one_token[0])

1065

}

else if

(

((

unsigned char

)one_token[0])) {

1070 if

(one_token.length() > 3) {

1071

one_token = one_token.substr(0, 3);

1084 if

(this_val <

min

) {

1086

}

else if

(this_val >

max

) {

1100

it = tokens.erase(it);

1106 if

(tokens.size() == 0) {

1108

}

else if

(tokens.size() > 2) {

1115 if

s_ChooseMonthAndDay

(tokens[0], tokens[1], month_first, month, day, month_ambiguous)) {

1119

month_ambiguous =

true

;

1124

}

else if

(tokens.size() == 1) {

1131 if

(

> 0 &&

< 13) {

1146 if

(tokens.size() == 2) {

1159 if

(val1 < 10 && !zero_pad_1 && (val2 > 10 || zero_pad_2)) {

1165

}

else if

(val2 < 10 && !zero_pad_2 && (val1 > 10 || zero_pad_1)) {

1185 if

s_ChooseMonthAndDay

(tokens[0], tokens[1], month_first, month, day, month_ambiguous)) {

1202 if

(year > 0 && year < 100 && num_original_tokens > 1) {

1207 bool

format_bad =

false

;

1208 bool

in_future =

false

;

1216 if

(year >= 1000 && year < 2100) {

1219

reformatted_date = month +

"-"

+ reformatted_date;

1222 if

(day_str.length() < 2) {

1223

day_str =

"0"

+ day_str;

1225

reformatted_date = day_str +

"-"

+ reformatted_date;

1230 return

reformatted_date;

1240 if

(tokens.size() != 3) {

1249 ITERATE

(vector<string>, it, tokens) {

1258

vector<int> positions;

1259

positions.push_back(0);

1260

positions.push_back(0);

1261

positions.push_back(0);

1264 ITERATE

(vector<int>, it, nums) {

1266 if

(positions[

eYear

] > 0) {

1271

positions[

eYear

] = token_pos;

1272

}

else if

(*it > 12) {

1273 if

(positions[

eDay

] > 0) {

1278

positions[

eDay

] = token_pos;

1279

}

else if

(positions[

eMonth

] > 0) {

1284

positions[

eMonth

] = token_pos;

1288 if

(positions[

eDay

] < positions[

eMonth

]) {

1297 bool

& lat_in_range,

bool

& lon_in_range,

1298 double

& lat_value,

double

& lon_value)

1300

format_correct =

false

;

1301

lat_in_range =

false

;

1302

lon_in_range =

false

;

1303

precision_correct =

false

;

1313

}

else if

(sscanf (lat_lon.c_str(),

"%lf %c %lf %c%n"

, &ns, &lat, &ew, &lon, &processed) != 4

1314

size_t

(processed) != lat_lon.length()) {

1316

}

else if

((lat !=

'N'

&& lat !=

'S'

) || (lon !=

'E'

&& lon !=

'W'

)) {

1323

lat_value = 0.0 - ns;

1328

lon_value = 0.0 - ew;

1332

vector<string> pieces;

1334 if

(pieces.size() > 3) {

1338 char

reformatted[1000];

1339

sprintf (reformatted,

"%.*lf %c %.*lf %c"

, precision_lat, ns, lat,

1340

precision_lon, ew, lon);

1342 size_t len

= strlen (reformatted);

1344

&& (

== lat_lon.length()

1345

|| (

< lat_lon.length()

1346

&& lat_lon[

] ==

';'

))) {

1347

format_correct =

true

;

1348 if

(ns <= 90 && ns >= 0) {

1349

lat_in_range =

true

;

1351 if

(ew <= 180 && ew >= 0) {

1352

lon_in_range =

true

;

1354 if

(precision_lat < 3 && precision_lon < 3) {

1355

precision_correct =

true

;

1365 bool

format_correct =

false

;

1366 bool

precision_correct =

false

;

1367 bool

lat_in_range =

false

;

1368 bool

lon_in_range =

false

;

1369 double

lat_value = 0.0;

1370 double

lon_value = 0.0;

1372

lat_in_range, lon_in_range,

1373

lat_value, lon_value);

1374 if

(!format_correct || !lat_in_range || !lon_in_range || precision_correct) {

1377

vector<string> pieces;

1379 if

(pieces.size() > 3) {

1382 if

(precision_lat > 4) {

1385 if

(precision_lon > 4) {

1389 char

reformatted[1000];

1390

sprintf(reformatted,

"%.*lf %c %.*lf %c"

, precision_lat,

(lat_value), pieces[1].c_str()[0],

1391

precision_lon,

(lon_value), pieces[3].c_str()[0]);

1392 string

new_val = reformatted;

1412 for

(string::const_iterator

= old_str.begin();

!= old_str.end(); ++

)

1417 char

c =

static_cast<char>

(sym);

1418 if

'.'

&& c !=

'-'

&& c !=

'+'

)

1422 else if

(!new_str.empty() &&

1429 if

'.'

&& c !=

'-'

&& c !=

'+'

)

1445 bool

is_number =

true

;

1446 for

(string::const_iterator

= old_str.begin();

!= old_str.end(); ++

)

1451 char

c =

static_cast<char>

(sym);

1452 size_t

j = new_str.size();

1453 if

(j >= 4 && new_str[j-1] ==

' '

&& new_str[j-2] ==

'.'

&& new_str[j-3] ==

' '

(new_str[j-4]) &&

(c))

1461 if

'+'

&& c !=

'-'

&& c !=

'.'

&& !

isspace

(c)) {

1492 static string s_NormalizeTokens

(vector<string> &tokens, vector<double> &numbers, vector<string> &anum, vector<int> &

precision

, vector<string> &lat_long, vector<string> &nsew)

1494

vector<string> pattern;

1495 for

(

size_t i

= 0;

< tokens.size();

++)

1497 string

&token = tokens[

];

1502

numbers.push_back(num);

1503

anum.push_back(token);

1504

pattern.push_back(

"1"

);

1509

static_cast<int>

(token.length() - token.find(

'.'

) - 1);

1515

vector<string>

;

1517 double

num0, num1, num2;

1520

numbers.push_back(num0);

1521

anum.push_back(

[0]);

1522

pattern.push_back(

"1"

);

1524

numbers.push_back(num1);

1525

anum.push_back(

[1]);

1526

pattern.push_back(

"1"

);

1528

numbers.push_back(num2);

1529

anum.push_back(

[2]);

1530

pattern.push_back(

"1"

);

1536 if

(token ==

"\'"

>= 3 &&

s_IsNumber

(tokens[

- 1]) && tokens[

- 2] ==

"\'"

s_IsNumber

(tokens[

- 3]))

1544

pattern.push_back(

"degrees"

);

1549

pattern.push_back(

"\'"

);

1554

pattern.push_back(

"\""

);

1556 else if

(token ==

","

|| token ==

":"

|| token ==

"_"

|| token ==

"&"

|| token ==

"."

|| token ==

";"

|| token ==

"#"

NStr::EqualNocase

(token,

"and"

))

1561

pattern.push_back(

"lat"

);

1562

lat_long.push_back(

"lat"

);

1567

pattern.push_back(

"lat"

);

1568

lat_long.push_back(

"long"

);

1572

pattern.push_back(

"N"

);

1573

nsew.push_back(

"N"

);

1577

pattern.push_back(

"N"

);

1578

nsew.push_back(

"S"

);

1582

pattern.push_back(

"N"

);

1583

nsew.push_back(

"E"

);

1585 else if

(token ==

"W"

NStr::EqualNocase

(token,

"west"

) || token ==

"Wdeg"

)

1587

pattern.push_back(

"N"

);

1588

nsew.push_back(

"W"

);

1590 else if

(token ==

"NW"

)

1592

nsew.push_back(

"N"

);

1593

nsew.push_back(

"W"

);

1595 else if

(token ==

"NE"

)

1597

nsew.push_back(

"N"

);

1598

nsew.push_back(

"E"

);

1600 else if

(token ==

"SW"

)

1602

nsew.push_back(

"S"

);

1603

nsew.push_back(

"W"

);

1605 else if

(token ==

"SE"

)

1607

nsew.push_back(

"S"

);

1608

nsew.push_back(

"E"

);

1623 if

(numbers.size() != 2)

1628 if

(lat_long.size() == 2)

1630 if

(lat_long.front() ==

"long"

)

1632 swap

(numbers[0], numbers[1]);

1634 if

(nsew.size() == 2) {

1635 swap

(nsew[0], nsew[1]);

1639 else if

(!lat_long.empty())

1644 if

(nsew.size() == 2)

1646 if

((nsew[0] ==

"E"

|| nsew[0] ==

"W"

) &&

1647

(nsew[1] ==

"N"

|| nsew[1] ==

"S"

))

1649 swap

(numbers[0], numbers[1]);

1651 swap

(nsew[0], nsew[1]);

1653 if

(nsew[0] ==

"N"

)

1655

numbers[0] =

(numbers[0]);

1657 else if

(nsew[0] ==

"S"

)

1659 if

(numbers[0] != 0)

1660

numbers[0] = -

(numbers[0]);

1667 if

(nsew[1] ==

"E"

)

1669

numbers[1] =

(numbers[1]);

1671 else if

(nsew[1] ==

"W"

)

1673 if

(numbers[1] != 0)

1674

numbers[1] = -

(numbers[1]);

1683 else if

(!nsew.empty())

1688 if

(lat_long.empty() && nsew.empty() &&

(numbers[0]) > 90 &&

(numbers[1]) < 90)

1690 swap

(numbers[0], numbers[1]);

1693 if

(

(numbers[0]) > 90 ||

(numbers[1]) > 180)

1702

vector<string> tokens;

1704

vector<string> lat_long;

1705

vector<string> nsew;

1706

vector<string> anum;

1708 if

(pattern.empty())

1713

vector<double> degrees(2, 0);

1714

vector<int> prec(2, 0);

1717 if

( pattern ==

"1 1"

1718

pattern ==

"1 N 1 N"

1719

pattern ==

"N 1 N 1"

1720

pattern ==

"1 degrees N 1 degrees N"

1721

pattern ==

"lat 1 lat 1"

1722

pattern ==

"1 N lat 1 N lat"

1723

pattern ==

"1 degrees N lat 1 degrees N lat"

)

1725

degrees[0] = numbers[0];

1726

degrees[1] = numbers[1];

1730 else if

((pattern ==

"1 1 \" 1 1 '"

1731

pattern ==

"1 degrees 1 \" N 1 degrees 1 ' N"

)

1732

&& numbers[1] < 60 && numbers[3] < 60

1733

&& numbers[1] >= 0 && numbers[3] >= 0)

1735

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1736

sign2 = anum[2][0] ==

'-'

? -1 : 1;

1737

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 3600);

1738

degrees[1] = sign2*(

(numbers[2]) + numbers[3] / 60);

1742 else if

( (pattern ==

"1 1 ' 1"

1743

pattern ==

"1 degrees 1 ' N 1 degrees N"

)

1747

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1748

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 60);

1749

degrees[1] = numbers[2];

1753 else if

(pattern ==

"1 1 ' 1 \" 1" 1754

&& numbers[1] < 60 && numbers[2] < 60

1755

&& numbers[1] >= 0 && numbers[2] >= 0)

1757

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1758

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 60 + numbers[2] / 3600);

1759

degrees[1] = numbers[3];

1763 else if

((pattern ==

"1 1 ' 1 \" 1 1 '"

1764

pattern ==

"1 1 1 N 1 1 N"

1765

pattern ==

"1 degrees 1 ' 1 \" N 1 degrees 1 ' N"

)

1766

&& numbers[1] < 60 && numbers[2] < 60 && numbers[4] < 60

1767

&& numbers[1] >= 0 && numbers[2] >= 0 && numbers[4] >= 0)

1769

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1770

sign2 = anum[3][0] ==

'-'

? -1 : 1;

1771

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 60 + numbers[2] / 3600);

1772

degrees[1] = sign2*(

(numbers[3]) + numbers[4] / 60);

1776 else if

(( pattern ==

"1 1 ' 1 \" 1 1 ' 1 \""

1777

pattern ==

"1 1 ' 1 \" N 1 1 ' 1 \" N"

1778

pattern ==

"1 degrees 1 ' 1 \" 1 degrees 1 ' 1 \""

1779

pattern ==

"1 degrees 1 ' 1 \" N 1 degrees 1 ' 1 \" N"

1780

pattern ==

"N 1 degrees 1 ' 1 \" N 1 degrees 1 ' 1 \""

1781

pattern ==

"1 degrees 1 ' 1 N 1 degrees 1 ' 1 N"

1782

pattern ==

"1 degrees 1 1 N 1 degrees 1 1 N"

1783

pattern ==

"1 1 1 N 1 1 1 N"

)

1784

&& numbers[1] < 60 && numbers[2] < 60 && numbers[4] < 60 && numbers[5] < 60

1785

&& numbers[1] >= 0 && numbers[2] >= 0 && numbers[4] >= 0 && numbers[5] >= 0)

1787

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1788

sign2 = anum[3][0] ==

'-'

? -1 : 1;

1789

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 60 + numbers[2] / 3600);

1790

degrees[1] = sign2*(

(numbers[3]) + numbers[4] / 60 + numbers[5] / 3600);

1794 else if

(( pattern ==

"1 1 ' 1 1 '"

1795

pattern ==

"1 1 N 1 1 N"

1796

pattern ==

"1 1 ' N 1 1 ' N"

1797

pattern ==

"1 degrees 1 ' N 1 degrees 1 ' N"

1798

pattern ==

"lat 1 degrees 1 ' N lat 1 degrees 1 ' N"

1799

pattern ==

"1 degrees 1 N 1 degrees 1 N"

1800

pattern ==

"1 degrees 1 N 1 degrees 1 ' N"

1801

pattern ==

"1 degrees 1 ' N 1 degrees 1 N"

1802

pattern ==

"N 1 degrees 1 ' N 1 degrees 1"

1803

pattern ==

"N 1 degrees 1 ' N 1 degrees 1 '"

1804

pattern ==

"N 1 degrees 1 ' N 1 1 '"

)

1805

&& numbers[1] < 60 && numbers[3] < 60

1806

&& numbers[1] >= 0 && numbers[3] >= 0)

1808

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1809

sign2 = anum[2][0] ==

'-'

? -1 : 1;

1810

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 60);

1811

degrees[1] = sign2*(

(numbers[2]) + numbers[3] / 60);

1815 else if

((pattern ==

"1 N 1 1 N"

1816

pattern ==

"1 degrees N 1 degrees 1 ' N"

)

1820

sign2 = anum[1][0] ==

'-'

? -1 : 1;

1821

degrees[0] = numbers[0];

1822

degrees[1] = sign2*(

(numbers[1]) + numbers[2] / 60);

1826 else if

((pattern ==

"1 degrees 1 ' 1 degrees 1 ' 1 \""

1827

pattern ==

"N 1 1 N 1 1 1"

)

1828

&& numbers[1] < 60 && numbers[3] < 60 && numbers[4] < 60

1829

&& numbers[1] >= 0 && numbers[3] >= 0 && numbers[4] >= 0)

1831

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1832

sign2 = anum[2][0] ==

'-'

? -1 : 1;

1833

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 60);

1834

degrees[1] = sign2*(

(numbers[2]) + numbers[3] / 60 + numbers[4] / 3600);

1838 else if

(pattern ==

"1 degrees 1 degrees 1 ' 1 \"" 1839

&& numbers[2] < 60 && numbers[3] < 60

1840

&& numbers[2] >= 0 && numbers[3] >= 0)

1842

sign2 = anum[1][0] ==

'-'

? -1 : 1;

1843

degrees[0] = numbers[0];

1844

degrees[1] = sign2*(

(numbers[1]) + numbers[2] / 60 + numbers[3] / 3600);

1848 else if

(pattern ==

"1 degrees 1 ' 1 \" N 1 degrees 1 \" N" 1849

&& numbers[1] < 60 && numbers[2] < 60 && numbers[4] < 60

1850

&& numbers[1] >= 0 && numbers[2] >= 0 && numbers[4] >= 0)

1852

sign1 = anum[0][0] ==

'-'

? -1 : 1;

1853

sign2 = anum[3][0] ==

'-'

? -1 : 1;

1854

degrees[0] = sign1*(

(numbers[0]) + numbers[1] / 60 + numbers[2] / 3600);

1855

degrees[1] = sign2*(

(numbers[3]) + numbers[4] / 3600);

1864 swap

(degrees, numbers);

1872 string

north_or_south;

1874 string

east_or_west;

1880 if

(ch < '0' || ch >

'9'

) {

1886

lat_lon_stream >> lat;

1887

lat_lon_stream >> north_or_south;

1888

lat_lon_stream >> lon;

1889

lat_lon_stream >> east_or_west;

1890 if

( lat_lon_stream.bad() ) {

1894 if

( north_or_south !=

"N"

&& north_or_south !=

"S"

) {

1898 if

( east_or_west !=

"E"

&& east_or_west !=

"W"

) {

1904 size_t len

= lat.length();

1905 if

(pos + 9 <

) {

1912 size_t len

= lon.length();

1913 if

(pos + 9 <

) {

1918 return

lat +

" "

+ north_or_south +

" "

+ lon +

" "

+ east_or_west;

1935

vector<double> numbers;

1939 if

(!numbers.empty())

1952 if

(lat_value < 0) {

1954

lat_value = -lat_value;

1957 if

(lon_value < 0) {

1959

lon_value = -lon_value;

1966 string

res = lat +

" "

+ ns +

" "

+ lon +

" "

+ ew;

1975 bool

goodmatch =

false

;

1981 id

->SetGuessCountry(guess->

());

1982 id

->SetGuessProvince(guess->

GetLevel1

());

1999 double

landdistance = 0.0;

2003 id

->SetClosestCountry(guess->

());

2004 id

->SetClosestProvince(guess->

GetLevel1

());

2013 double

landdistance = 0.0;

2017 id

->SetClosestCountry(guess->

());

2018 id

->SetClosestProvince(guess->

GetLevel1

());

2026 double

waterdistance = 0.0;

2029 id

->SetClosestWater(guess->

());

2040 double

distance = 0.0;

2045 id

->SetGuessCountry(country);

2046 id

->SetGuessProvince(province);

2068

{

"Adriatic Sea"

"Mediterranean Sea"

2069

{

"Aegean Sea"

"Mediterranean Sea"

2070

{

"Alboran Sea"

"Mediterranean Sea"

2071

{

"Andaman Sea"

"Indian Ocean"

2072

{

"Arabian Sea"

"Indian Ocean"

2073

{

"Argentine Sea"

"Atlantic Ocean"

2074

{

"Ariake Sea"

"Pacific Ocean"

2075

{

"Baffin Bay"

"Atlantic Ocean"

2076

{

"Balearic Sea"

"Mediterranean Sea"

2077

{

"Baltic Sea"

"Atlantic Ocean"

2078

{

"Barents Sea"

"Arctic Ocean"

2079

{

"Bay of Bengal"

"Indian Ocean"

2080

{

"Beaufort Sea"

"Arctic Ocean"

2081

{

"Bering Sea"

"Pacific Ocean"

2082

{

"Bismarck Sea"

"Pacific Ocean"

2083

{

"Black Sea"

"Mediterranean Sea"

2084

{

"Bohai Sea"

"Pacific Ocean"

2085

{

"Caribbean Sea"

"Atlantic Ocean"

2086

{

"Celebes Sea"

"Pacific Ocean"

2087

{

"Champlain Sea"

"Atlantic Ocean"

2088

{

"Chilean Sea"

"Pacific Ocean"

2089

{

"China Seas"

"Pacific Ocean"

2090

{

"Chukchi Sea"

"Arctic Ocean"

2091

{

"Coral Sea"

"Pacific Ocean"

2092

{

"Davis Strait"

"Atlantic Ocean"

2093

{

"East China Sea"

"Pacific Ocean"

2094

{

"East Siberian Sea"

"Arctic Ocean"

2095

{

"English Channel"

"Atlantic Ocean"

2096

{

"Erythraean Sea"

"Indian Ocean"

2097

{

"Golfo de California"

"Pacific Ocean"

2098

{

"Greenland Sea"

"Arctic Ocean"

2099

{

"Gulf of Mexico"

"Atlantic Ocean"

2100

{

"Gulf of Thailand"

"Pacific Ocean"

2101

{

"Gulf of Tonkin"

"Pacific Ocean"

2102

{

"Hudson Bay"

"Arctic Ocean"

2103

{

"Ionian Sea"

"Mediterranean Sea"

2104

{

"Irish Sea"

"Atlantic Ocean"

2105

{

"Irminger Sea"

"Atlantic Ocean"

2106

{

"James Bay"

"Atlantic Ocean"

2107

{

"Java Sea"

"Indian Ocean"

2108

{

"Kara Sea"

"Arctic Ocean"

2109

{

"Koro Sea"

"Pacific Ocean"

2110

{

"Labrador Sea"

"Atlantic Ocean"

2111

{

"Laccadive Sea"

"Indian Ocean"

2112

{

"Laptev Sea"

"Arctic Ocean"

2113

{

"Ligurian Sea"

"Mediterranean Sea"

2114

{

"Lincoln Sea"

"Arctic Ocean"

2115

{

"Myrtoan Sea"

"Mediterranean Sea"

2116

{

"North Sea"

"Atlantic Ocean"

2117

{

"Norwegian Sea"

"Atlantic Ocean"

2118

{

"Pechora Sea"

"Arctic Ocean"

2119

{

"Persian Gulf"

"Indian Ocean"

2120

{

"Philippine Sea"

"Pacific Ocean"

2121

{

"Red Sea"

"Indian Ocean"

2122

{

"Salish Sea"

"Pacific Ocean"

2123

{

"Sargasso Sea"

"Atlantic Ocean"

2124

{

"Scotia Sea"

"Southern Ocean"

2125

{

"Sea of Azov"

"Black Sea"

2126

{

"Sea of Chiloe"

"Pacific Ocean"

2127

{

"Sea of Crete"

"Mediterranean Sea"

2128

{

"Sea of Japan"

"Pacific Ocean"

2129

{

"Sea of Okhotsk"

"Pacific Ocean"

2130

{

"Sea of the Hebrides"

"Atlantic Ocean"

2131

{

"Sea of Zanj"

"Indian Ocean"

2132

{

"Seas of Greenland"

"Atlantic Ocean"

2133

{

"Sethusamudram"

"Indian Ocean"

2134

{

"Sibutu Passage"

"Pacific Ocean"

2135

{

"Solomon Sea"

"Pacific Ocean"

2136

{

"South China Sea"

"Pacific Ocean"

2137

{

"Sulu Sea"

"Pacific Ocean"

2138

{

"Tasman Sea"

"Pacific Ocean"

2139

{

"Thracian Sea"

"Mediterranean Sea"

2140

{

"Timor Sea"

"Indian Ocean"

2141

{

"Tyrrhenian Sea"

"Mediterranean Sea"

2142

{

"Wandel Sea"

"Arctic Ocean"

2143

{

"White Sea"

"Arctic Ocean"

2144

{

"Yellow Sea"

"Pacific Ocean"

}

2153 if

( new_water_pair_iter != sc_WaterPairMap.end() ) {

2154 return

new_water_pair_iter->second;

2163 string

countryname = input_countryname;

2168 bool

format_correct, lat_in_range, lon_in_range, precision_correct;

2169 double

lat_value = 0.0, lon_value = 0.0;

2171

lat_in_range, lon_in_range,

2172

lat_value, lon_value);

2173 if

(!format_correct) {

2177

lat_lon = lat_lon.substr(0, pos);

2179

lat_in_range, lon_in_range,

2180

lat_value, lon_value);

2185 if

(!format_correct || !lat_in_range || !lon_in_range) {

2195

countryname = countryname.substr(0, pos);

2199

countryname = countryname.substr(0, pos);

2204

countryname =

"Svalbard"

;

2207 string

country = countryname;

2213

province = country.substr(pos + 1);

2216

country = country.substr(0, pos);

2247 string

wguess =

id

->GetGuessWater();

2248 string

cguess =

id

->GetGuessCountry();

2252 if

(province.empty() &&

NStr::Equal

(cguess, country)) {

2272 double

neardist = 0.0;

2277 id

->SetGuessCountry (country);

2279 flags

id

->Classify(country, province);

2283

&& !

x_GetLatLonWaterMap

().IsNearLatLon(lat_value, lon_value, 20.0, neardist, country)) {

2286

adjusted_flags = adjust_id ==

? 0 : adjust_id->

Classify

(country, province);

2287 if

(adjusted_flags) {

2293 flags

= adjusted_flags;

2301

adjusted_flags = adjust_id ==

? 0 : adjust_id->

Classify

(country, province);

2302 if

(adjusted_flags) {

2308 flags

= adjusted_flags;

2316

adjusted_flags = adjust_id ==

? 0 : adjust_id->

Classify

(country, province);

2317 if

(adjusted_flags) {

2323 flags

= adjusted_flags;

2340 error

"Latitude and longitude values appear to be exchanged"

;

2344 if

(lat_value < 0.0) {

2345 error

"Latitude should be set to N (northern hemisphere)"

;

2347 error

"Latitude should be set to S (southern hemisphere)"

;

2349

lat_lon =

MakeLatLon

(-lat_value, lon_value);

2352 if

(lon_value < 0.0) {

2353 error

"Longitude should be set to E (eastern hemisphere)"

;

2355 error

"Longitude should be set to W (western hemisphere)"

;

2357

lat_lon =

MakeLatLon

(lat_value, -lon_value);

2365 string

full_guess =

id

->GetFullGuess();

2368 error

"Lat_lon "

+ lat_lon +

" is in "

id

->GetFullGuess()

2369

" (more specific than "

+ country +

")"

;

2374 bool

suppress =

false

;

2375 string

reportregion;

2377 string

desphrase =

"designated subregion "

;

2378 string

subphrase =

"another subregion "

;

2379 string

phrase = nosubphrase;

2380 bool

show_claimed =

false

;

2392

reportregion = countryname;

2398

reportregion =

id

->GetClosestFull();

2400

reportregion =

id

->GetClosestCountry();

2403

show_claimed =

true

;

2406 string

water =

id

->GetGuessWater();

2419

}

else if

(!suppress) {

2422 error

"Lat_lon '"

+ lat_lon +

"' is closest to "

+ phrase +

"'"

+ reportregion +

"' at distance " 2424

" km, but in water '"

id

->GetGuessWater()

2425

"' - claimed region '"

id

->GetClaimedFull()

2428 error

"Lat_lon '"

+ lat_lon +

"' is closest to "

+ phrase +

"'"

+ reportregion

2430

id

->GetGuessWater() +

"'"

;

2433

}

else if

(neardist > 0.0) {

2435 error

"Lat_lon '"

+ lat_lon +

"' is in water '"

id

->GetGuessWater() +

"', '" 2439 error

"Lat_lon '"

+ lat_lon +

"' is in water '"

id

->GetGuessWater() +

"'"

;

2442 string

full_guess =

id

->GetFullGuess();

2451 error

"Lat_lon '"

+ lat_lon +

"' maps to '"

id

->GetFullGuess() +

"' instead of '" 2452

+ countryname +

"'"

;

2456 error

"Lat_lon '"

+ lat_lon +

"' maps to '"

id

->GetFullGuess() +

"' instead of '" 2457

+ country +

"' - claimed region '"

id

->GetClaimedFull()

2465 error

"Lat_lon '"

+ lat_lon +

"' maps to '"

id

->GetFullGuess() +

"' instead of '" 2466

+ countryname +

"' - claimed region '"

id

->GetClaimedFull()

2475 error

"Lat_lon '"

+ lat_lon +

"' is closest to '"

id

->GetClosestCountry() +

"' instead of '" 2476

+ countryname +

"'"

;

2479 error

"Lat_lon '"

+ lat_lon +

"' is closest to '"

id

->GetClosestWater() +

"' instead of '" 2480

+ countryname +

"'"

;

2483 error

"Unable to determine mapping for lat_lon '"

+ lat_lon +

"' and country '"

+ countryname +

"'"

;

2513 "pooled males and females"

2514 "pooled male and female"

2525 if

(find(begin, end,

) != end) {

2543

vector<string> words;

2545 if

(words.size() == 0) {

2554 bool

is_good =

false

;

2556 ITERATE

(vector<string>, w, words) {

2560 if

(find(begin, end, *w) != end) {

2581

vector<string> words;

2584 if

(words.size() == 0) {

2592

vector<string> good_values;

2593 bool

pooled =

false

;

2595 ITERATE

(vector<string>, w, words) {

2602 if

(find(begin, end, *w) != end) {

2604

good_values.push_back(

"male"

);

2606

good_values.push_back(

"female"

);

2608

good_values.push_back(*w);

2616 if

(good_values.size() == 0) {

2621 string

fixed = good_values[0];

2622 for

(

size_t i

= 1;

< good_values.size();

++) {

2623 if

(good_values.size() > 2) {

2626 if

(

== good_values.size() - 1) {

2629

fixed +=

" "

+ good_values[

];

2632

fixed =

"pooled "

+ fixed;

2647

string::const_iterator it =

.begin();

2648 if

(*it ==

'+'

|| *it ==

'-'

) {

2653 bool

any_digit =

false

;

2654 bool

skip_comma =

true

;

2655 while

(it !=

.end() && (

(*it) || *it ==

','

)) {

2659

skip_comma =

false

;

2670 if

(it ==

.end()) {

2685 if

(it ==

.end() || *it !=

' '

|| !any_digit) {

2691 while

(it !=

.end()) {

2729 char

reformatted[1000];

2731 string

rval = reformatted;

2760

rval =

number

" "

"m"

;

2778

}

else if

(

.length() > 240) {

2782 for

(

auto

it :

) {

2831 string

genus = taxname.substr(0, pos);

2836 string

species = taxname.substr(pos + 1);

2840 if

(pos != 1 ||

[0] !=

'p'

) {

2861

}

else if

(

.length() > 32) {

2870 static const char

* s_ForbiddenPhrases[] = {

2882 for

(

auto

it : s_ForbiddenPhrases) {

2945 if

(s_PlasmidNameExceptions.find(

) != end(s_PlasmidNameExceptions)) {

2962 #include "cell_line.inc" 2966

vector<string> tokens;

2968 if

(tokens.size() < 4) {

2970

"; disregarding"

);

2987 size_t count

sizeof

(kCellLine) /

sizeof

(*kCellLine);

2988 const char

const

* start = kCellLine;

3003 string

cell_line_search = cell_line;

3007

rval =

"The International Cell Line Authentication Committee database indicates that "

3008

cell_line +

" from "

+ organism +

" is known to be contaminated by "

3011 ". Please see http://iclac.org/databases/cross-contaminations/ for more information and references."

;

3032 "Antigua and Barbuda"

3037 "Ashmore and Cartier Islands"

3057 "Bosnia and Herzegovina"

3061 "British Virgin Islands"

3071 "Central African Republic"

3075 "Christmas Island"

3076 "Clipperton Island"

3081 "Coral Sea Islands"

3089 "Democratic Republic of the Congo"

3093 "Dominican Republic"

3097 "Equatorial Guinea"

3103 "Falkland Islands (Islas Malvinas)"

3109 "French Polynesia"

3110 "French Southern and Antarctic Lands"

3118 "Glorioso Islands"

3130 "Heard Island and McDonald Islands"

3152 "Juan de Nova Island"

3155 "Kerguelen Archipelago"

3178 "Marshall Islands"

3183 "Mediterranean Sea"

3185 "Micronesia, Federated States of"

3210 "Northern Mariana Islands"

3218 "Papua New Guinea"

3223 "Pitcairn Islands"

3228 "Republic of the Congo"

3234 "Saint Barthelemy"

3236 "Saint Kitts and Nevis"

3239 "Saint Pierre and Miquelon"

3240 "Saint Vincent and the Grenadines"

3243 "Sao Tome and Principe"

3256 "South Georgia and the South Sandwich Islands"

3263 "State of Palestine"

3279 "Trinidad and Tobago"

3284 "Turks and Caicos Islands"

3289 "United Arab Emirates"

3298 "Wallis and Futuna"

3318 "Netherlands Antilles"

3319 "Serbia and Montenegro"

3322 "The former Yugoslav Republic of Macedonia"

3332 "missing: control sample"

3333 "missing: data agreement established pre-2023"

3334 "missing: endangered species"

3335 "missing: human-identifiable"

3336 "missing: lab stock"

3337 "missing: sample group"

3338 "missing: synthetic construct"

3339 "missing: third party data"

3349 string

name = country;

3350 size_t

pos = country.find(

':'

);

3352 if

( pos !=

) {

3353 if

(pos == country.length() - 1) {

3356

name = country.substr(0, pos);

3372 bool CCountries::IsValid

(

const string

& country,

bool

& is_miscapitalized,

bool

& is_null_and_virus,

bool

is_influenza_or_Sars2)

3374

is_miscapitalized =

false

;

3376 string

name = country;

3377 size_t

pos = country.find(

':'

);

3379 if

( pos !=

) {

3380

name = country.substr(0, pos);

3381 if

(pos == country.length() - 1) {

3395 if

(is_influenza_or_Sars2) {

3396

is_null_and_virus =

true

;

3403

is_miscapitalized =

true

;

3409

is_miscapitalized =

true

;

3415

is_miscapitalized =

true

;

3426 bool

is_null_and_virus =

false

;

3427 return IsValid

(country, is_miscapitalized, is_null_and_virus,

false

);

3433 string

name = country;

3434 size_t

pos = country.find(

':'

);

3436 if

( pos !=

) {

3437

name = country.substr(0, pos);

3447

is_miscapitalized =

false

;

3449 string

name = country;

3450 size_t

pos = country.find(

':'

);

3452 if

( pos !=

) {

3453

name = country.substr(0, pos);

3464

is_miscapitalized =

true

;

3476

{

"england"

"United Kingdom: England"

3477

{

"great britain"

"United Kingdom: Great Britain"

3478

{

"new jersey, usa"

"USA: New Jersey"

}

3484

{

"ABW"

"Aruba"

3485

{

"AFG"

"Afghanistan"

3486

{

"AGO"

"Angola"

3487

{

"AIA"

"Anguilla"

3488

{

"ALA"

"Aland Islands"

3489

{

"ALB"

"Albania"

3490

{

"AND"

"Andorra"

3491

{

"ARE"

"United Arab Emirates"

3492

{

"ARG"

"Argentina"

3493

{

"ARM"

"Armenia"

3494

{

"ASM"

"American Samoa"

3495

{

"ATA"

"Antarctica"

3496

{

"ATF"

"French Southern Territories"

3497

{

"ATG"

"Antigua and Barbuda"

3498

{

"AUS"

"Australia"

3499

{

"AUT"

"Austria"

3500

{

"AZE"

"Azerbaijan"

3501

{

"Antigua & Barbuda"

"Antigua and Barbuda"

3502

{

"Ashmore & Cartier Islands"

"Ashmore and Cartier Islands"

3503

{

"BDI"

"Burundi"

3504

{

"BEL"

"Belgium"

3505

{

"BEN"

"Benin"

3506

{

"BES"

"Bonaire, Sint Eustatius and Saba"

3507

{

"BFA"

"Burkina Faso"

3508

{

"BGD"

"Bangladesh"

3509

{

"BGR"

"Bulgaria"

3510

{

"BHR"

"Bahrain"

3511

{

"BHS"

"Bahamas"

3512

{

"BIH"

"Bosnia and Herzegovina"

3513

{

"BLM"

"Saint Barthelemy"

3514

{

"BLR"

"Belarus"

3515

{

"BLZ"

"Belize"

3516

{

"BMU"

"Bermuda"

3517

{

"BOL"

"Bolivia"

3518

{

"BRA"

"Brazil"

3519

{

"BRB"

"Barbados"

3520

{

"BRN"

"Brunei"

3521

{

"BTN"

"Bhutan"

3522

{

"BVT"

"Bouvet Island"

3523

{

"BWA"

"Botswana"

3524

{

"Brasil"

"Brazil"

3525

{

"CAF"

"Central African Republic"

3526

{

"CAN"

"Canada"

3527

{

"CCK"

"Cocos Islands"

3528

{

"CHE"

"Switzerland"

3529

{

"CHL"

"Chile"

3530

{

"CHN"

"China"

3531

{

"CIV"

"Cote d'Ivoire"

3532

{

"CMR"

"Cameroon"

3533

{

"COD"

"Democratic Republic of the Congo"

3534

{

"COG"

"Republic of the Congo"

3535

{

"COK"

"Cook Islands"

3536

{

"COL"

"Colombia"

3537

{

"COM"

"Comoros"

3538

{

"CPV"

"Cape Verde"

3539

{

"CRI"

"Costa Rica"

3541

{

"CUW"

"Curacao"

3542

{

"CXR"

"Christmas Island"

3543

{

"CYM"

"Cayman Islands"

3544

{

"CYP"

"Cyprus"

3545

{

"CZE"

"Czechia"

3546

{

"Cape Verde Islands"

"Cape Verde"

3547

{

"DEU"

"Germany"

3548

{

"DJI"

"Djibouti"

3549

{

"DMA"

"Dominica"

3550

{

"DNK"

"Denmark"

3551

{

"DOM"

"Dominican Republic"

3552

{

"DZA"

"Algeria"

3553

{

"Democratic Republic of Congo"

"Democratic Republic of the Congo"

3554

{

"ECU"

"Ecuador"

3555

{

"EGY"

"Egypt"

3556

{

"ERI"

"Eritrea"

3557

{

"ESH"

"Western Sahara"

3558

{

"ESP"

"Spain"

3559

{

"EST"

"Estonia"

3560

{

"ETH"

"Ethiopia"

3561

{

"FIN"

"Finland"

3563

{

"FLK"

"Falkland Islands (Islas Malvinas)"

3564

{

"FRA"

"France"

3565

{

"FRO"

"Faroe Islands"

3566

{

"FSM"

"Micronesia, Federated States of"

3567

{

"Falkland Islands"

"Falkland Islands (Islas Malvinas)"

3568

{

"French Southern & Antarctic Lands"

"French Southern and Antarctic Lands"

3569

{

"GAB"

"Gabon"

3570

{

"GBR"

"United Kingdom"

3571

{

"GEO"

"Georgia"

3572

{

"GGY"

"Guernsey"

3573

{

"GHA"

"Ghana"

3574

{

"GIB"

"Gibraltar"

3575

{

"GIN"

"Guinea"

3576

{

"GLP"

"Guadeloupe"

3577

{

"GMB"

"Gambia"

3578

{

"GNB"

"Guinea-Bissau"

3579

{

"GNQ"

"Equatorial Guinea"

3580

{

"GRC"

"Greece"

3581

{

"GRD"

"Grenada"

3582

{

"GRL"

"Greenland"

3583

{

"GTM"

"Guatemala"

3584

{

"GUF"

"French Guiana"

3586

{

"GUY"

"Guyana"

3587

{

"HKG"

"Hong Kong"

3588

{

"HMD"

"Heard Island and McDonald Islands"

3589

{

"HND"

"Honduras"

3590

{

"HRV"

"Croatia"

3591

{

"HTI"

"Haiti"

3592

{

"HUN"

"Hungary"

3593

{

"Heard Island & McDonald Islands"

"Heard Island and McDonald Islands"

3594

{

"IDN"

"Indonesia"

3595

{

"IMN"

"Isle of Man"

3596

{

"IND"

"India"

3597

{

"IOT"

"British Indian Ocean Territory"

3598

{

"IRL"

"Ireland"

3601

{

"ISL"

"Iceland"

3602

{

"ISR"

"Israel"

3603

{

"ITA"

"Italy"

3604

{

"Ivory Coast"

"Cote d'Ivoire"

3605

{

"JAM"

"Jamaica"

3606

{

"JEY"

"Jersey"

3607

{

"JOR"

"Jordan"

3608

{

"JPN"

"Japan"

3609

{

"KAZ"

"Kazakhstan"

3610

{

"KEN"

"Kenya"

3611

{

"KGZ"

"Kyrgyzstan"

3612

{

"KHM"

"Cambodia"

3613

{

"KIR"

"Kiribati"

3614

{

"KNA"

"Saint Kitts and Nevis"

3615

{

"KOR"

"South Korea"

3616

{

"KWT"

"Kuwait"

3617

{

"LAO"

"Lao People's Democratic Republic"

3618

{

"LBN"

"Lebanon"

3619

{

"LBR"

"Liberia"

3620

{

"LBY"

"Libyan Arab Jamahiriya"

3621

{

"LCA"

"Saint Lucia"

3622

{

"LIE"

"Liechtenstein"

3623

{

"LKA"

"Sri Lanka"

3624

{

"LSO"

"Lesotho"

3625

{

"LTU"

"Lithuania"

3626

{

"LUX"

"Luxembourg"

3627

{

"LVA"

"Latvia"

3628

{

"La Reunion Island"

"Reunion"

3629

{

"Luxemburg"

"Luxembourg"

3630

{

"MAC"

"Macao"

3631

{

"MAF"

"Saint Martin (French part)"

3632

{

"MAR"

"Morocco"

3633

{

"MCO"

"Monaco"

3634

{

"MDA"

"Moldova"

3635

{

"MDG"

"Madagascar"

3636

{

"MDV"

"Maldives"

3637

{

"MEX"

"Mexico"

3638

{

"MHL"

"Marshall Islands"

3639

{

"MKD"

"North Macedonia"

3641

{

"MLT"

"Malta"

3642

{

"MMR"

"Myanmar"

3643

{

"MNE"

"Montenegro"

3644

{

"MNG"

"Mongolia"

3645

{

"MNP"

"Northern Mariana Islands"

3646

{

"MOZ"

"Mozambique"

3647

{

"MRT"

"Mauritania"

3648

{

"MSR"

"Montserrat"

3649

{

"MTQ"

"Martinique"

3650

{

"MUS"

"Mauritius"

3651

{

"MWI"

"Malawi"

3652

{

"MYS"

"Malaysia"

3653

{

"MYT"

"Mayotte"

3654

{

"Macedonia"

"North Macedonia"

3655

{

"NAM"

"Namibia"

3656

{

"NCL"

"New Caledonia"

3657

{

"NER"

"Niger"

3658

{

"NFK"

"Norfolk Island"

3659

{

"NGA"

"Nigeria"

3660

{

"NIC"

"Nicaragua"

3662

{

"NLD"

"Netherlands"

3663

{

"NOR"

"Norway"

3664

{

"NPL"

"Nepal"

3665

{

"NRU"

"Nauru"

3666

{

"NZL"

"New Zealand"

3667

{

"Netherland"

"Netherlands"

3668

{

"New Guinea"

"Papua New Guinea"

3670

{

"P, R, China"

"China"

3671

{

"P.R. China"

"China"

3672

{

"P.R.China"

"China"

3673

{

"PAK"

"Pakistan"

3674

{

"PAN"

"Panama"

3675

{

"PCN"

"Pitcairn"

3677

{

"PHL"

"Philippines"

3678

{

"PLW"

"Palau"

3679

{

"PNG"

"Papua New Guinea"

3680

{

"POL"

"Poland"

3681

{

"PRI"

"Puerto Rico"

3682

{

"PRK"

"North Korea"

3683

{

"PRT"

"Portugal"

3684

{

"PRY"

"Paraguay"

3685

{

"PSE"

"Palestinian Territory"

3686

{

"PYF"

"French Polynesia"

3687

{

"People's Republic of China"

"China"

3688

{

"Pr China"

"China"

3689

{

"Prchina"

"China"

3690

{

"QAT"

"Qatar"

3691

{

"REU"

"Reunion"

3692

{

"ROU"

"Romania"

3693

{

"RUS"

"Russia"

3694

{

"RWA"

"Rwanda"

3695

{

"Republic of Congo"

"Republic of the Congo"

3696

{

"SAU"

"Saudi Arabia"

3697

{

"SDN"

"Sudan"

3698

{

"SEN"

"Senegal"

3699

{

"SGP"

"Singapore"

3700

{

"SGS"

"South Georgia and the South Sandwich Islands"

3701

{

"SHN"

"Saint Helena"

3702

{

"SJM"

"Svalbard and Jan Mayen"

3703

{

"SLB"

"Solomon Islands"

3704

{

"SLE"

"Sierra Leone"

3705

{

"SLV"

"El Salvador"

3706

{

"SMR"

"San Marino"

3707

{

"SOM"

"Somalia"

3708

{

"SPM"

"Saint Pierre and Miquelon"

3709

{

"SRB"

"Serbia"

3710

{

"SSD"

"South Sudan"

3711

{

"STP"

"Sao Tome and Principe"

3712

{

"SUR"

"Suriname"

3713

{

"SVK"

"Slovakia"

3714

{

"SVN"

"Slovenia"

3715

{

"SWE"

"Sweden"

3716

{

"SWZ"

"Eswatini"

3717

{

"SXM"

"Sint Maarten (Dutch part)"

3718

{

"SYC"

"Seychelles"

3719

{

"SYR"

"Syrian Arab Republic"

3720

{

"Saint Kitts & Nevis"

"Saint Kitts and Nevis"

3721

{

"Saint Pierre & Miquelon"

"Saint Pierre and Miquelon"

3722

{

"Saint Vincent & Grenadines"

"Saint Vincent and the Grenadines"

3723

{

"Saint Vincent & the Grenadines"

"Saint Vincent and the Grenadines"

3724

{

"Saint Vincent and Grenadines"

"Saint Vincent and the Grenadines"

3725

{

"San Tome and Principe Island"

"Sao Tome and Principe"

3726

{

"Sao Tome & Principe"

"Sao Tome and Principe"

3727

{

"South Georgia & South Sandwich Islands"

"South Georgia and the South Sandwich Islands"

3728

{

"South Georgia & the South Sandwich Islands"

"South Georgia and the South Sandwich Islands"

3729

{

"St Helena"

"Saint Helena"

3730

{

"St Lucia"

"Saint Lucia"

3731

{

"St Pierre and Miquelon"

"Saint Pierre and Miquelon"

3732

{

"St Vincent and the Grenadines"

"Saint Vincent and the Grenadines"

3733

{

"St. Helena"

"Saint Helena"

3734

{

"St. Lucia"

"Saint Lucia"

3735

{

"St. Pierre and Miquelon"

"Saint Pierre and Miquelon"

3736

{

"St. Vincent and the Grenadines"

"Saint Vincent and the Grenadines"

3737

{

"TCA"

"Turks and Caicos Islands"

3740

{

"THA"

"Thailand"

3741

{

"TJK"

"Tajikistan"

3742

{

"TKL"

"Tokelau"

3743

{

"TKM"

"Turkmenistan"

3744

{

"TLS"

"Timor-Leste"

3745

{

"TON"

"Tonga"

3746

{

"TTO"

"Trinidad and Tobago"

3747

{

"TUN"

"Tunisia"

3748

{

"TUR"

"Turkey"

3749

{

"TUV"

"Tuvalu"

3750

{

"TWN"

"Taiwan"

3751

{

"TZA"

"Tanzania"

3752

{

"The Netherlands"

"Netherlands"

3753

{

"Trinidad & Tobago"

"Trinidad and Tobago"

3754

{

"Turks & Caicos"

"Turks and Caicos Islands"

3755

{

"Turks & Caicos Islands"

"Turks and Caicos Islands"

3756

{

"Turks and Caicos"

"Turks and Caicos Islands"

3757

{

"U.S.A."

"USA"

3758

{

"UGA"

"Uganda"

3759

{

"UK"

"United Kingdom"

3760

{

"UKR"

"Ukraine"

3761

{

"UMI"

"United States Minor Outlying Islands"

3762

{

"URY"

"Uruguay"

3763

{

"UZB"

"Uzbekistan"

3764

{

"United States"

"USA"

3765

{

"United States of America"

"USA"

3766

{

"VAT"

"Holy See (Vatican City State)"

3767

{

"VCT"

"Saint Vincent and the Grenadines"

3768

{

"VEN"

"Venezuela"

3769

{

"VGB"

"British Virgin Islands"

3770

{

"VIR"

"Virgin Islands"

3771

{

"VNM"

"Viet Nam"

3772

{

"VUT"

"Vanuatu"

3773

{

"Vietnam"

"Viet Nam"

3774

{

"WLF"

"Wallis and Futuna"

3775

{

"WSM"

"Samoa"

3776

{

"YEM"

"Yemen"

3777

{

"ZAF"

"South Africa"

3778

{

"ZMB"

"Zambia"

3779

{

"ZWE"

"Zimbabwe"

3780

{

"the Netherlands"

"Netherlands"

}

3787

{

"Burma"

"Myanmar"

3788

{

"Siam"

"Thailand"

}

3794

{

"Antigua"

"Antigua and Barbuda: Antigua"

3795

{

"Ashmore Island"

"Ashmore and Cartier Islands: Ashmore Island"

3796

{

"Autonomous Region of the Azores"

"Portugal: Azores"

3797

{

"Azores"

"Portugal: Azores"

3798

{

"Barbuda"

"Antigua and Barbuda: Barbuda"

3799

{

"Bassas da India"

"French Southern and Antarctic Lands: Bassas da India"

3800

{

"Caicos Islands"

"Turks and Caicos Islands: Caicos Islands"

3801

{

"Canary Islands"

"Spain: Canary Islands"

3802

{

"Cartier Island"

"Ashmore and Cartier Islands: Cartier Island"

3803

{

"East Germany"

"Germany: East Germany"

3804

{

"El Hierro"

"Spain: El Hierro"

3805

{

"Europa Island"

"French Southern and Antarctic Lands: Europa Island"

3806

{

"Fuerteventura"

"Spain: Fuerteventura"

3807

{

"Glorioso Islands"

"French Southern and Antarctic Lands: Glorioso Islands"

3808

{

"Gran Canaria"

"Spain: Gran Canaria"

3809

{

"Grenadines"

"Saint Vincent and the Grenadines: Grenadines"

3810

{

"Heard Island"

"Heard Island and McDonald Islands: Heard Island"

3811

{

"Ile Amsterdam"

"French Southern and Antarctic Lands: Ile Amsterdam"

3812

{

"Ile Saint-Paul"

"French Southern and Antarctic Lands: Ile Saint-Paul"

3813

{

"Iles Crozet"

"French Southern and Antarctic Lands: Iles Crozet"

3814

{

"Iles Kerguelen"

"French Southern and Antarctic Lands: Iles Kerguelen"

3815

{

"Juan de Nova Island"

"French Southern and Antarctic Lands: Juan de Nova Island"

3816

{

"La Gomera"

"Spain: La Gomera"

3817

{

"La Graciosa"

"Spain: La Graciosa"

3818

{

"La Palma"

"Spain: La Palma"

3819

{

"Lanzarote"

"Spain: Lanzarote"

3820

{

"Madeira"

"Portugal: Madeira"

3821

{

"McDonald Island"

"Heard Island and McDonald Islands: McDonald Island"

3822

{

"McDonald Islands"

"Heard Island and McDonald Islands: McDonald Islands"

3823

{

"Miquelon"

"Saint Pierre and Miquelon: Miquelon"

3824

{

"Nevis"

"Saint Kitts and Nevis: Nevis"

3825

{

"Principe"

"Sao Tome and Principe: Principe"

3826

{

"Saint Kitts"

"Saint Kitts and Nevis: Saint Kitts"

3827

{

"Saint Pierre"

"Saint Pierre and Miquelon: Saint Pierre"

3828

{

"Saint Vincent"

"Saint Vincent and the Grenadines: Saint Vincent"

3829

{

"Sao Tome"

"Sao Tome and Principe: Sao Tome"

3830

{

"Scotland"

"United Kingdom: Scotland"

3831

{

"South Sandwich Islands"

"South Georgia and the South Sandwich Islands: South Sandwich Islands"

3832

{

"St Kitts"

"Saint Kitts and Nevis: Saint Kitts"

3833

{

"St Pierre"

"Saint Pierre and Miquelon: Saint Pierre"

3834

{

"St Thomas"

"USA: Saint Thomas"

3835

{

"St Vincent"

"Saint Vincent and the Grenadines: Saint Vincent"

3836

{

"St. Kitts"

"Saint Kitts and Nevis: Saint Kitts"

3837

{

"St. Pierre"

"Saint Pierre and Miquelon: Saint Pierre"

3838

{

"St. Thomas"

"USA: Saint Thomas"

3839

{

"St. Vincent"

"Saint Vincent and the Grenadines: Saint Vincent"

3840

{

"Tenerife"

"Spain: Tenerife"

3841

{

"Tobago"

"Trinidad and Tobago: Tobago"

3842

{

"Trinidad"

"Trinidad and Tobago: Trinidad"

3843

{

"Tromelin Island"

"French Southern and Antarctic Lands: Tromelin Island"

3844

{

"Turks Islands"

"Turks and Caicos Islands: Turks Islands"

3845

{

"Wales"

"United Kingdom: Wales"

3846

{

"West Germany"

"Germany: West Germany"

3861 "District of Columbia"

3908

vector<string> words;

3910 for

(vector<string>::iterator word = words.begin(); word != words.end(); ++word)

3911 if

(!word->empty() &&

(word->at(0)))

3912

word->at(0) = (

unsigned

char)

toupper

(word->at(0));

3920 if

(found != k_whole_country_fixes.end()) {

3921

new_country = found->second;

3926 for

(

size_t i

= 0;

< num_states; ++

) {

3941 string

country2(*c);

3945 while

(pos2 !=

)

3947 if

(pos2 <= pos1 && pos2+country2.length() >= pos1+country1.length())

3958 int

num_matches = 0;

3963 while

(pos !=

)

3965 if

(!((pos+country.length()<phrase.length() &&

(phrase[pos+country.length()]))

3966

|| (pos > 0 &&

(phrase[pos-1]))

3973 return

(num_matches > 1);

3991 bool

any_found =

true

;

3992 while

.empty() && any_found) {

4004 val

.substr(0,

.length() - 1);

4008 val

.substr(0,

.length() - 4);

4011 size_t len

.length();

4013 val

.substr(0,

.length() - 1);

4016

}

else if

(

> 5) {

4018 bool

do_remove =

true

;

4019 size_t

pos =

.length() - 2;

4021 while

(dist < 4 && do_remove) {

4029 val

.substr(0,

.length() - 1);

4040

vector<string> tokens;

4043

vector<string>::iterator it = tokens.begin();

4044 while

(it != tokens.end()) {

4046 if

(pos !=

&& pos > 3 && (*it).length() - pos > 4) {

4047 string first

= (*it).substr(0, pos);

4048 string

remainder = (*it).substr(pos + 1);

4050 size_t

len_to_space =

first

.length();

4051 while

(space_pos !=

) {

4053

len_to_space =

first

.length();

4056 if

(len_to_space > 4) {

4057

(*it) = (*it).substr(0, pos);

4058

it = tokens.insert(it, remainder);

4073 size_t

tlen =

.length();

4074 size_t

wlen = word.

length

();

4077 while

(pos !=

) {

4078 size_t

p = start + pos;

4079 if

( (p == 0 || !

((

unsigned char

)

[p - 1])) &&

4080

(p + wlen >= tlen || !

((

unsigned char

)

[p + wlen])) ) {

4103 const

vector<string>& countries,

4104 string

& valid_country,

4105 string

& orig_valid_country,

4106 bool

& too_many_countries,

4109 for

(

auto

country : countries) {

4110 if

(!country.empty() && !too_many_countries)

4112 string check

= country;

4116 bool

check_has_bad_cap =

false

;

4119 if

(valid_country.empty())

4121

valid_country =

check

;

4122

orig_valid_country =

check

;

4123

bad_cap = check_has_bad_cap;

4127

too_many_countries =

true

;

4133 if

(found != fix_map.

end

())

4135 if

(valid_country.empty())

4137

valid_country = found->second;

4138

orig_valid_country =

check

;

4142

too_many_countries =

true

;

4154 if

(

.length() == 0)

return false

;

4156 char

new char

[

sizeof

(char) * (

.length() + 1)];

4157

strcpy(

.c_str());

4168 while

(ch !=

'\0'

) {

4175 while

(ch ==

' '

) {

4201

{

"Acadia Parish"

4202

{

"AcadiaParish"

"Acadia Parish"

4203

{

"Allen Parish"

4204

{

"AllenParish"

"Allen Parish"

4205

{

"Ascension Parish"

4206

{

"AscensionParish"

"Ascension Parish"

4207

{

"Assumption Parish"

4208

{

"AssumptionParish"

"Assumption Parish"

4209

{

"Avoyelles Parish"

4210

{

"AvoyellesParish"

"Avoyelles Parish"

4211

{

"Beauregard Parish"

4212

{

"BeauregardParish"

"Beauregard Parish"

4213

{

"Bienville Parish"

4214

{

"BienvilleParish"

"Bienville Parish"

4215

{

"Bossier Parish"

4216

{

"BossierParish"

"Bossier Parish"

4217

{

"Caddo Parish"

4218

{

"CaddoParish"

"Caddo Parish"

4219

{

"Calcasieu Parish"

4220

{

"CalcasieuParish"

"Calcasieu Parish"

4221

{

"Caldwell Parish"

4222

{

"CaldwellParish"

"Caldwell Parish"

4223

{

"Cameron Parish"

4224

{

"CameronParish"

"Cameron Parish"

4225

{

"Catahoula Parish"

4226

{

"CatahoulaParish"

"Catahoula Parish"

4227

{

"Claiborne Parish"

4228

{

"ClaiborneParish"

"Claiborne Parish"

4229

{

"Concordia Parish"

4230

{

"ConcordiaParish"

"Concordia Parish"

4231

{

"DeSoto Parish"

4232

{

"DeSotoParish"

"DeSoto Parish"

4233

{

"East Baton Rouge Parish"

4234

{

"East Carroll Parish"

4235

{

"East Feliciana Parish"

4236

{

"EastBatonRougeParish"

"East Baton Rouge Parish"

4237

{

"EastCarrollParish"

"East Carroll Parish"

4238

{

"EastFelicianaParish"

"East Feliciana Parish"

4239

{

"Evangeline Parish"

4240

{

"EvangelineParish"

"Evangeline Parish"

4241

{

"Franklin Parish"

4242

{

"FranklinParish"

"Franklin Parish"

4243

{

"Grant Parish"

4244

{

"GrantParish"

"Grant Parish"

4245

{

"Iberia Parish"

4246

{

"IberiaParish"

"Iberia Parish"

4247

{

"Iberville Parish"

4248

{

"IbervilleParish"

"Iberville Parish"

4249

{

"Jackson Parish"

4250

{

"JacksonParish"

"Jackson Parish"

4251

{

"Jefferson Davis Parish"

4252

{

"Jefferson Parish"

4253

{

"JeffersonDavisParish"

"Jefferson Davis Parish"

4254

{

"JeffersonParish"

"Jefferson Parish"

4255

{

"Lafayette Parish"

4256

{

"LafayetteParish"

"Lafayette Parish"

4257

{

"Lafourche Parish"

4258

{

"LafourcheParish"

"Lafourche Parish"

4259

{

"LaSalle Parish"

4260

{

"LaSalleParish"

"LaSalle Parish"

4261

{

"Lincoln Parish"

4262

{

"LincolnParish"

"Lincoln Parish"

4263

{

"Livingston Parish"

4264

{

"LivingstonParish"

"Livingston Parish"

4265

{

"Madison Parish"

4266

{

"MadisonParish"

"Madison Parish"

4267

{

"Morehouse Parish"

4268

{

"MorehouseParish"

"Morehouse Parish"

4269

{

"Natchitoches Parish"

4270

{

"NatchitochesParish"

"Natchitoches Parish"

4271

{

"Orleans Parish"

4272

{

"OrleansParish"

"Orleans Parish"

4273

{

"Ouachita Parish"

4274

{

"OuachitaParish"

"Ouachita Parish"

4275

{

"Plaquemines Parish"

4276

{

"PlaqueminesParish"

"Plaquemines Parish"

4277

{

"Pointe Coupee Parish"

4278

{

"PointeCoupeeParish"

"Pointe Coupee Parish"

4279

{

"Rapides Parish"

4280

{

"RapidesParish"

"Rapides Parish"

4281

{

"Red River Parish"

4282

{

"RedRiverParish"

"Red River Parish"

4283

{

"Richland Parish"

4284

{

"RichlandParish"

"Richland Parish"

4285

{

"Sabine Parish"

4286

{

"SabineParish"

"Sabine Parish"

4287

{

"St. Bernard Parish"

4288

{

"St. Charles Parish"

4289

{

"St. Helena Parish"

4290

{

"St. James Parish"

4291

{

"St. John the Baptist Parish"

4292

{

"St. Landry Parish"

4293

{

"St. Martin Parish"

4294

{

"St. Mary Parish"

4295

{

"St. Tammany Parish"

4296

{

"St.BernardParish"

"St. Bernard Parish"

4297

{

"St.CharlesParish"

"St. Charles Parish"

4298

{

"St.HelenaParish"

"St. Helena Parish"

4299

{

"St.JamesParish"

"St. James Parish"

4300

{

"St.JohntheBaptistParish"

"St. John the Baptist Parish"

4301

{

"St.LandryParish"

"St. Landry Parish"

4302

{

"St.MartinParish"

"St. Martin Parish"

4303

{

"St.MaryParish"

"St. Mary Parish"

4304

{

"St.TammanyParish"

"St. Tammany Parish"

4305

{

"Tangipahoa Parish"

4306

{

"TangipahoaParish"

"Tangipahoa Parish"

4307

{

"Tensas Parish"

4308

{

"TensasParish"

"Tensas Parish"

4309

{

"Terrebonne Parish"

4310

{

"TerrebonneParish"

"Terrebonne Parish"

4311

{

"Union Parish"

4312

{

"UnionParish"

"Union Parish"

4313

{

"Vermilion Parish"

4314

{

"VermilionParish"

"Vermilion Parish"

4315

{

"Vernon Parish"

4316

{

"VernonParish"

"Vernon Parish"

4317

{

"Washington Parish"

4318

{

"WashingtonParish"

"Washington Parish"

4319

{

"Webster Parish"

4320

{

"WebsterParish"

"Webster Parish"

4321

{

"West Baton Rouge Parish"

4322

{

"West Carroll Parish"

4323

{

"West Feliciana Parish"

4324

{

"WestBatonRougeParish"

"West Baton Rouge Parish"

4325

{

"WestCarrollParish"

"West Carroll Parish"

4326

{

"WestFelicianaParish"

"West Feliciana Parish"

4327

{

"Winn Parish"

4328

{

"WinnParish"

"Winn Parish"

}

4336 if

( parish.empty() ) {

4341 if

( parish_find_iter != parishAbbrevMap.end() ) {

4343

parish = parish_find_iter->second;

4352

{

"AK"

"Alaska"

4353

{

"AL"

"Alabama"

4354

{

"Alabama"

4355

{

"Alaska"

4356

{

"American Samoa"

4357

{

"AR"

"Arkansas"

4358

{

"Arizona"

4359

{

"Arkansas"

4360

{

"AS"

"American Samoa"

4361

{

"AZ"

"Arizona"

4362

{

"CA"

"California"

4363

{

"California"

4364

{

"CO"

"Colorado"

4365

{

"Colorado"

4366

{

"Connecticut"

4367

{

"CT"

"Connecticut"

4368

{

"DC"

"District of Columbia"

4369

{

"DE"

"Delaware"

4370

{

"Delaware"

4371

{

"District of Columbia"

4372

{

"FL"

"Florida"

4373

{

"Florida"

4374

{

"GA"

"Georgia"

4375

{

"Georgia"

4377

{

"Guam"

4378

{

"Hawaii"

4379

{

"HI"

"Hawaii"

4382

{

"Idaho"

4383

{

"IL"

"Illinois"

4384

{

"Illinois"

4385

{

"IN"

"Indiana"

4386

{

"Indiana"

4387

{

"Iowa"

4388

{

"Kansas"

4389

{

"Kentucky"

4390

{

"KS"

"Kansas"

4391

{

"KY"

"Kentucky"

4392

{

"LA"

"Louisiana"

4393

{

"Louisiana"

4394

{

"MA"

"Massachusetts"

4395

{

"Maine"

4396

{

"Maryland"

4397

{

"Massachusetts"

4398

{

"MD"

"Maryland"

4400

{

"MI"

"Michigan"

4401

{

"Michigan"

4402

{

"Minnesota"

4403

{

"Mississippi"

4404

{

"Missouri"

4405

{

"MN"

"Minnesota"

4406

{

"MO"

"Missouri"

4407

{

"Montana"

4408

{

"MS"

"Mississippi"

4409

{

"MT"

"Montana"

4410

{

"NC"

"North Carolina"

4411

{

"ND"

"North Dakota"

4412

{

"NE"

"Nebraska"

4413

{

"Nebraska"

4414

{

"Nevada"

4415

{

"New Hampshire"

4416

{

"New Jersey"

4417

{

"New Mexico"

4418

{

"New York"

4419

{

"NH"

"New Hampshire"

4420

{

"NJ"

"New Jersey"

4421

{

"NM"

"New Mexico"

4422

{

"North Carolina"

4423

{

"North Dakota"

4424

{

"NV"

"Nevada"

4425

{

"NY"

"New York"

4427

{

"Ohio"

4428

{

"OK"

"Oklahoma"

4429

{

"Oklahoma"

4430

{

"OR"

"Oregon"

4431

{

"Oregon"

4432

{

"PA"

"Pennsylvania"

4433

{

"Pennsylvania"

4434

{

"PR"

"Puerto Rico"

4435

{

"Puerto Rico"

4436

{

"Rhode Island"

4437

{

"RI"

"Rhode Island"

4438

{

"SC"

"South Carolina"

4439

{

"SD"

"South Dakota"

4440

{

"South Carolina"

4441

{

"South Dakota"

4442

{

"Tennessee"

4443

{

"Texas"

4444

{

"TN"

"Tennessee"

4446

{

"US Virgin Islands"

4448

{

"Utah"

4449

{

"VA"

"Virginia"

4450

{

"Vermont"

4451

{

"VI"

"US Virgin Islands"

4452

{

"Virgin Islands"

"US Virgin Islands"

4453

{

"Virginia"

4454

{

"VT"

"Vermont"

4455

{

"WA"

"Washington"

4456

{

"Washington"

4457

{

"West Virginia"

4458

{

"WI"

"Wisconsin"

4459

{

"Wisconsin"

4460

{

"WV"

"West Virginia"

4461

{

"WY"

"Wyoming"

4462

{

"Wyoming"

}

4472 if

(

state

.empty() ) {

4476 string

original =

state

;

4477 string

working =

state

;

4494 if

( state_find_iter != stateAbbrevMap.end() ) {

4496 state

= state_find_iter->second;

4509 if

( country.empty() ) {

4514 string

original = country;

4515 string

working = country;

4519

working = working.substr ( 1, working.length() - 2 );

4545

vector<string> components;

4549 if

( components.size() < 1 ) {

4554 for

(

size_t

j = 0; j < components.size(); j++ ) {

4573 for

(

size_t

j = 0; j < components.size(); j++ ) {

4574 bool

modified =

false

;

4575 if

(

s_IsState

( components[j], modified )) {

4600

res.append (

"USA: "

);

4605

res.append ( components[

match

] );

4609 for

(

size_t

j = 0; j < components.size(); j++ ) {

4610 if

( j ==

match

)

continue

;

4612

res.append ( components[j] );

4620

}

else if

( num_states > 1 ) {

4636 if

( ! exception_file.empty()) {

4639 for

(

const auto

: my_stream ) {

4640 TFieldNo

number_of_fields =

. GetNumberOfFields();

4641 if

( number_of_fields != 2 )

continue

;

4642 string

fr =

[0].Get<

string

>();

4643 string

to =

[1].Get<

string

>();

4644

exceptions [fr] = to;

4655 for

(

const auto

& itm : exceptions ) {

4656 string

fr = itm.first;

4657 string

to = itm.second;

4664 if

( ! f1.empty() && ! f2.empty()) {

4665

fr = f1 +

": "

+ f2;

4668

(*exception_map)[fr] = to;

4676 if

( ! exception_file.empty()) {

4687 string

working = country;

4692 string

corrected = (*exception_map) [working];

4693 if

( ! corrected.empty()) {

4733 string

micronesia =

"Micronesia, Federated States of"

;

4757 if

(!usa1.empty() && !usa2.empty()) {

4761 input

"USA: "

+ usa2;

4765 auto

old_name_fix = k_old_country_name_fixes.find(

.c_str());

4766 if

(old_name_fix != k_old_country_name_fixes.end()) {

4767 input

= old_name_fix->second;

4771 if

(us_territories) {

4790 if

(!new_country.empty())

4793 bool

too_many_countries =

false

;

4794 bool

bad_cap =

false

;

4796 string

valid_country;

4797 string

orig_valid_country;

4799 x_FindCountryName

(k_country_name_fixes, countries, valid_country, orig_valid_country, too_many_countries, bad_cap);

4800 if

(valid_country.empty()) {

4801 x_FindCountryName

(k_subregion_fixes, countries, valid_country, orig_valid_country, too_many_countries, bad_cap);

4804 if

(!valid_country.empty() && !too_many_countries)

4807 if

(!valid_country.empty() && too_many_countries && valid_country ==

)

4812

new_country = str1+

": "

+str2;

4816 else if

(!valid_country.empty() && !too_many_countries)

4821 string

before =

.substr(0,pos);

4826 string

after =

.substr(pos+orig_valid_country.length());

4830 else

new_country = valid_country;

4831 if

(!before.empty() || !after.empty()) {

4833

new_country +=

": "

;

4835

new_country +=

", "

;

4838 if

(!before.empty())

4839

new_country += before;

4840 if

(!before.empty() && !after.empty() && !

NStr::Equal

(after,

")"

))

4841

new_country +=

", "

;

4843

new_country += after;

4856 for

(

size_t i

= 0;

< country.length();

++) {

4857 if

(country[

] ==

':'

) {

4860

country[

] =

','

;

4872 string

new_country = country;

4874 if

(country_end_pos !=

)

4877 while

(country[pos] ==

','

|| country[pos] ==

':'

isspace

((

unsigned char

)country[pos]))

4881 string

after = country.substr(pos);

4882 if

(after.empty()) {

4883 if

(pos > country_end_pos) {

4884

new_country = country.substr(0, country_end_pos);

4888 if

(capitalize_after_colon)

4890

new_country = country.substr(0,country_end_pos);

4891

new_country +=

": "

+ after;

4903

{

"adult"

4905

{

"juvenile"

4906

{

"larva"

}

4913 string

fix =

;

4916 if

(it != sc_DevStagePairs.end()) {

4924

{

"hemocyte"

4925

{

"hepatocyte"

4926

{

"lymphocyte"

4927

{

"neuroblast"

}

4933 string

fix =

;

4936 if

(it != sc_CellTypePairs.end()) {

4951

vector<CTempString> tokens;

4953 if

(tokens.size() > 1) {

4954

qual_map[tokens[0]] = tokens[1];

4960 const char

**built_in,

size_t

num_built_in,

4965 if

file

.empty()) {

4972 if

(built_in ==

) {

4975 if

(getenv(

"NCBI_DEBUG"

)) {

4976 ERR_POST

(

Note

"Falling back on built-in data for "

+ data_name);

4978 for

(

size_t i

= 0;

< num_built_in;

++) {

4979 const char

*p = built_in[

];

4984 if

(getenv(

"NCBI_DEBUG"

)) {

4989

}

while

->AtEOF());

4993 #include "isolation_sources.inc" 5003 s_AddOneDataFile

(

"isolation_sources.txt"

"isolation sources"

, (

const char

**)k_isolation_sources,

sizeof

(k_isolation_sources) /

sizeof

(

char

*),

s_IsolationSourceMap

.Get());

5013 string

fix =

;

5023 for

(

size_t i

= 0;

max

;

++) {

5040 string

fix =

;

5050 for

(

size_t i

= 0;

max

;

++) {

5073 string

new_val =

;

5121 const string

& name =

GetName

();

5194 return

deprecate_subsources.test((

ESubtype

)subtype);

5224 "[BankIt_uncultured16S_wizard]; [universal primers]; [tgge]"

5225 "[BankIt_uncultured16S_wizard]; [universal primers]; [dgge]"

5226 "[BankIt_uncultured16S_wizard]; [universal primers]"

5227 "[BankIt_cultured16S_wizard]"

5228 "[BankIt_organellerRNA_wizard]"

5229 "[BankIt_ITS_wizard]; [rRNAITS_notfound]"

5230 "[BankIt_ITS_wizard]"

5231 "[uncultured (using universal primers)]"

5232 "[uncultured (using universal primers) bacterial source]"

5233 "[cultured bacterial source]"

5234 "[enrichment culture bacterial source]"

5235 "[mixed bacterial source (cultured and uncultured)]"

5236 "[uncultured]; [universal primers]"

5237 "[mixed bacterial source]"

5239 "[cDNA derived from mRNA, purified viral particles]"

5240 "[cDNA derived from mRNA, whole cell/tissue lysate]"

5241 "[cDNA derived from genomic RNA, whole cell/tissue lysate]"

5242 "[cDNA derived from genomic RNA, purified viral particles]"

5243 "[universal primers]"

5244 "[uncultured; wizard]"

5245 "[uncultured; wizard; spans unknown]"

5246 "[cultured; wizard]"

5247 "[cultured; wizard; spans unknown]"

5248 "[intergenic wizard]"

5249 "[intergenic wizard; spans unknown]"

5250 "[Microsatellite wizard]"

5251 "[Microsatellite wizard; multiple repeats]"

5253 "[D-loop wizard; spans unknown]"

5254 "[D-loop wizard; spans known]"

5259 "[BankIt_uncultured16S_wizard]; [species_specific primers]; [tgge]"

5260 "[BankIt_uncultured16S_wizard]; [species_specific primers]; [dgge]"

5261 "[BankIt_uncultured16S_wizard]; [species_specific primers]"

5262 "[uncultured (with species-specific primers)]"

5263 "[uncultured]; [amplified with species-specific primers]"

5264 "[uncultured (using species-specific primers) bacterial source]"

5265 "[amplified with species-specific primers]"

5274 if

(pos != string::npos) {

5295 size_t

remove_len = to_remove.length();

5297 while

(pos !=

) {

5298 size_t

extra_len = strspn (

.c_str() + pos + remove_len,

" ;"

);

5299 value

.substr(0, pos) +

.substr(pos + remove_len + extra_len);

5311 if

(is_species_level) {

5314 value

"amplified with species-specific primers"

;

5335

(

const string

& country_name,

double

min_x,

double

max_x,

double

scale)

5336

: m_CountryName(country_name) ,

5351 #define EPSILON 0.001 5409

: m_CountryName(country_name) , m_MinX (min_x), m_MinY (min_y), m_MaxX(max_x), m_MaxY (max_y)

5412 size_t

pos =

NStr::Find

(country_name,

":"

);

5417 m_Level0

= country_name.substr(0, pos);

5419 m_Level1

= country_name.substr(pos + 1);

5493

&& m_MaxX <= other_block->

GetMaxX

()

5495

&& m_MinY <= other_block->

GetMaxY

()) {

5551

m_WaterDistance(-1),

5552

m_ClaimedDistance(-1)

5620 #include "lat_lon_country.inc" 5623 #include "lat_lon_water.inc" 5628 if

(getenv(

"NCBI_DEBUG"

)) {

5629 ERR_POST

(

Note

"Falling back on built-in data for latlon / water data."

);

5634 string

current_country;

5636 for

(

int i

= 0;

< num;

++) {

5638 if

(line[0] ==

'-'

) {

5640

}

else if

(

((

unsigned char

)line[0])) {

5641

current_country = line;

5642

}

else if

(

((

unsigned char

)line[0])) {

5645

vector<string> tokens;

5647 if

(tokens.size() > 3) {

5649 for

(

size_t

j = 2; j < tokens.size() - 1; j+=2) {

5666 if

(getenv(

"NCBI_DEBUG"

)) {

5667 ERR_POST

(

Note

"Reading from "

+ filename +

" for latlon/water data."

);

5674 string

current_country;

5679

vector<SIZE_TYPE> tab_positions;

5684 if

(line[0] ==

'-'

) {

5686

}

else if

(

((

unsigned char

)line[0])) {

5687

current_country = line;

5688

}

else if

(

((

unsigned char

)line[0])) {

5701

tab_positions.clear();

5703 while

( tab_pos !=

) {

5704

tab_positions.push_back(tab_pos);

5705

tab_pos = line.

find

(

'\t'

, tab_pos+1);

5708

tab_positions.push_back(line.

length

());

5710 const char

* line_start = line.

data

();

5711 if

( tab_positions.size() >= 4 ) {

5712 CTempString

y_str( line_start + tab_positions[0]+1, tab_positions[1] - tab_positions[0] - 1 );

5716 for

(

size_t

j = 1; j < tab_positions.size() - 2; j+=2) {

5717 const SIZE_TYPE

pos1 = tab_positions[j];

5718 const SIZE_TYPE

pos2 = tab_positions[j+1];

5719 const SIZE_TYPE

pos3 = tab_positions[j+2];

5720 CTempString

first_num( line_start + pos1 + 1, pos2 - pos1 - 1 );

5721 CTempString

second_num( line_start + pos2 + 1, pos3 - pos2 - 1 );

5726

}

while

( !

->AtEOF() );

5739

}

else if

(

->GetY() >

->GetY()) {

5742 if

(

->GetMinX() <

->GetMinX()) {

5757

}

else if

(

cmp

< 0) {

5771

}

else if

(

->GetY() >

->GetY()) {

5773

}

if

(

->GetMinX() <

->GetMinX()) {

5775

}

else if

(

->GetMinX() >

->GetMinX()) {

5777

}

else if

(

->GetMaxX() <

->GetMaxX()) {

5779

}

else if

(

->GetMaxX() >

->GetMaxX()) {

5797 const char

* env_val = getenv(

"NCBI_LAT_LON_DATA_PATH"

);

5800

data_path = (

string

) env_val;

5802

data_path = data_path +

"/"

;

5808 if

(data_path.empty() || !

x_InitFromFile

(data_path +

"lat_lon_water.txt"

)) {

5814 if

(data_path.empty() || !

x_InitFromFile

(data_path +

"lat_lon_country.txt"

)) {

5826

TCountryToLinesMap countryToLinesMap;

5828

countryToLinesMap[(*line_it)->GetCountry()].push_back(*line_it);

5838

country_lines_it->second;

5843

back_inserter(new_country_line_list));

5907

}

else if

(

cmp

> 0) {

6008 const string

& country,

6009 const string

& province)

const 6022 if

(best ==

) {

6024

}

else if

(!best->

PreferTo

(other, country, province, (

bool

)(best->

() <= other->

()))) {

6038 #define EARTH_RADIUS 6371.0 6039 #define CONST_PI 3.14159265359 6046 return

(degrees * (

CONST_PI

/ 180.0));

6057 double

lat1, lon1, lat2, lon2;

6058 double

dLat, dLon,

, c;

6068 a

= sin (dLat / 2) * sin (dLat / 2) +

6069

cos (lat1) * cos (lat2) * sin (dLon / 2) * sin (dLon / 2);

6070

c = 2 * atan2 (sqrt (

), sqrt (1 -

));

6081 double

lat1, lon1, lat2, lon2;

6082 double

dLat, dLon,

, c;

6092 a

= sin (dLat / 2) * sin (dLat / 2) +

6093

cos (lat1) * cos (lat2) * sin (dLon / 2) * sin (dLon / 2);

6094

c = 2 * atan2 (sqrt (

), sqrt (1 -

));

6110 int

min_y = y - maxDelta;

6111 int

max_y = y + maxDelta;

6112 int

min_x = x - maxDelta;

6113 int

max_x = x + maxDelta;

6118 double

closest = 0.0;

6134 if

(rval ==

|| closest > dist

6152 double

lat,

double

lon,

6153 double

range,

double

&distance)

const 6159 int

min_y = y - maxDelta;

6160 int

max_y = y + maxDelta;

6161 int

min_x = x - maxDelta;

6162 int

max_x = x + maxDelta;

6168 double

closest = 0.0;

6169 int

smallest_area = -1;

6187

smallest_area = ext->

();

6189

}

else if

(closest == dist) {

6196

&& (ext->

() < smallest_area

6199

smallest_area = ext->