A RetroSearch Logo

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Search Query:

Showing content from http://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/doxyhtml/unicode_8cpp_source.html below:

NCBI C++ ToolKit: src/util/unicode.cpp Source File

41 #define NCBI_USE_ERRCODE_X Util_Unicode 46 #include "unicode_plans.inl" 52

0, 0, 0, 0, 0, 0, 0, 0,

54

0, 0, 0, 0, 0, 0, 0, 0,

58

0, 0, 0, 0, 0, 0, 0, 0,

61

0, 0, 0, 0, 0, 0, 0, 0,

63

0, 0, 0, 0, 0, 0, 0, 0,

64

0, 0, 0, 0, 0, 0, 0, 0,

66

0, 0, 0, 0, 0, 0, 0, 0,

67

0, 0, 0, 0, 0, 0, 0, 0,

69

0, 0, 0, 0, 0, 0, 0, 0,

70

0, 0, 0, 0, 0, 0, 0, 0,

72

0, 0, 0, 0, 0, 0, 0, 0,

73

0, 0, 0, 0, 0, 0, 0, 0,

75

0, 0, 0, 0, 0, 0, 0, 0,

76

0, 0, 0, 0, 0, 0, 0, 0,

78

0, 0, 0, 0, 0, 0, 0, 0,

79

0, 0, 0, 0, 0, 0, 0, 0,

81

0, 0, 0, 0, 0, 0, 0, 0,

82

0, 0, 0, 0, 0, 0, 0, 0,

84

0, 0, 0, 0, 0, 0, 0, 0,

85

0, 0, 0, 0, 0, 0, 0, 0,

87

0, 0, 0, 0, 0, 0, 0, 0,

88

0, 0, 0, 0, 0, 0, 0, 0,

90

0, 0, 0, 0, 0, 0, 0, 0,

91

0, 0, 0, 0, 0, 0, 0, 0,

96

0, 0, 0, 0, 0, 0, 0, 0,

138

: m_initialized(

false

), m_pool(0)

164  if

(!ifs.is_open()) {

165  ERR_POST_X

(1,

"UnicodeToAscii table not found: "

<< name);

168  LOG_POST_X

(2,

Info

<<

"Loading UnicodeToAscii table at: "

<< name);

172  size_t

poolsize = filelen/2;

175  ERR_POST_X

(3,

"UnicodeToAscii table failed to load: not enough memory"

);

187  if

(

x_ParseLine

(line, symbol, translation) > 1) {

189  if

(poolpos + translation.size() + 1 > poolsize) {

190  m_pool

= (

char

*)realloc(

m_pool

, poolsize += filelen/4);

192  ERR_POST_X

(3,

"UnicodeToAscii table failed to load: not enough memory"

);

197

symbolToOffset[symbol] = poolpos;

198

memcpy(

m_pool

+poolpos, translation.data(), translation.size());

199

poolpos += translation.size();

200

*(

m_pool

+poolpos) =

'\0'

;

205  ERR_POST_X

(1,

"UnicodeToAscii table is empty: "

<< name);

216

sym != symend; ++sym) {

227  string

& line,

TUnicode

& symbol,

string

& translation)

234

string::size_type begin = line.find_first_not_of(

" \t"

, 0);

235  if

(begin == string::npos) {

238

string::size_type end = line.find_first_of(

" \t,#"

,begin);

242  if

(end == string::npos) {

250  if

( end == line.size() || line[end] ==

'#'

) {

254

end = line.find(

','

,end);

255  if

(end == string::npos) {

258

begin = line.find_first_not_of(

" \t"

, ++end);

259  if

(begin == string::npos) {

262  if

(*(line.data()+begin) !=

'\"'

) {

265  const char

*

data

= line.data()+begin;

266  const char

* dataend = line.data()+line.size();

274  if

(

data

< dataend) {

278  case 'a'

: c = 0x7;

break

;

279  case 'b'

: c = 0x8;

break

;

280  case 't'

: c = 0x9;

break

;

281  case 'n'

: c = 0xA;

break

;

282  case 'v'

: c = 0xB;

break

;

283  case 'f'

: c = 0xC;

break

;

284  case 'r'

: c = 0xD;

break

;

285  case '0'

: c = 0x0;

break

;

287  if

(

data

+ 1 < dataend) {

288

begin =

data

+ 1 - line.data();

289

end = line.find_first_not_of(

"0123456789abcdefABCDEF"

, begin);

290  if

(end == string::npos) {

294  data

= line.data() + end;

299  if

(

data

== dataend) {

303

translation.append(1,c);

317  return

&(

i

->second);

329  if

(

t

.IsInitialized()) {

330  return t

.GetTranslation(character);

335  if

((character & (~0xFFFF)) == 0) {

336  unsigned int

thePlanNo = (character & 0xFF00) >> 8;

337  unsigned int

theOffset = character & 0xFF;

340

translation = &((*thePlan)[theOffset]);

344  if

(!default_translation) {

349  "UnicodeToAscii: unknown Unicode symbol"

);

351

translation = default_translation;

359  const char

*p = theUTF;

362  if

( ((*theUTF) & 0xC0) != 0xC0 ) {

364  RC

|= (

unsigned

char)theUTF[0];

370  while

((counter =

Int1

(counter << 1)) < 0) {

371  unsigned char

c = *p++;

372  if

((c & ~077) != 0200) {

375

acc = (acc << 6) | (c & 077);

384  const char

*p = theUTF;

387  if

( (

unsigned char

)theUTF[0] < 0x80 ) {

389

*theUnicode = *theUTF;

393  if

( ((*theUTF) & 0xC0) != 0xC0 || ((*theUTF) & 0xFE) == 0xC0) {

399  if

( ((*theUTF) & 0xF8) == 0xF0 ) {

403  while

((counter =

Int1

(counter << 1)) < 0) {

404  unsigned char

c = *p++;

405  if

((c & ~077) != 0200) {

408

acc = (acc << 6) | (c & 077);

412  return

(

size_t

)(p - theUTF);

419  size_t

theLength =

UnicodeToUTF8

( theUnicode, theBuffer, 10 );

420  return string

( theBuffer, theLength );

425  size_t

theBufLength )

429  if

(theUnicode < 0x80) {

431  if

( Length > theBufLength )

return

0;

432

theBuffer[0] = char(theUnicode);

434  else if

(theUnicode < 0x800) {

436  if

( Length > theBufLength )

return

0;

437

theBuffer[0] = char( 0xC0 | (theUnicode>>6));

438

theBuffer[1] = char( 0x80 | (theUnicode & 0x3F));

440  else if

(theUnicode < 0x10000) {

442  if

( Length > theBufLength )

return

0;

443

theBuffer[0] = char( 0xE0 | (theUnicode>>12));

444

theBuffer[1] = char( 0x80 | ((theUnicode>>6) & 0x3F));

445

theBuffer[2] = char( 0x80 | (theUnicode & 0x3F));

447  else if

(theUnicode < 0x200000) {

449  if

( Length > theBufLength )

return

0;

450

theBuffer[0] = char( 0xF0 | (theUnicode>>18));

451

theBuffer[1] = char( 0x80 | ((theUnicode>>12) & 0x3F));

452

theBuffer[2] = char( 0x80 | ((theUnicode>>6) & 0x3F));

453

theBuffer[3] = char( 0x80 | (theUnicode & 0x3F));

466  if

( !src || !dst || dstLen == 0 )

return

0;

469  size_t

srcLen = strlen( src );

471  for

( srcPos = 0; srcPos < srcLen; ) {

473  char

* pDst = &(dst[dstPos]);

474  const char

* pSrc = &(src[srcPos]);

490  if

(

result

&& pSubst == default_translation) {

501

!(pSubst->

Subst

) ) {

508

memcpy( pDst, pSrc, utfLen );

514  size_t

substLen = strlen( pSubst->

Subst

);

515  if

( (dstPos + substLen) > dstLen ) {

520

memcpy( pDst, pSubst->

Subst

, substLen );

537  size_t

srcLen = strlen( src );

539  for

( srcPos = 0; srcPos < srcLen; ) {

541  const char

* pSrc = &(src[srcPos]);

557  if

(

result

&& pSubst == default_translation) {

569

!(pSubst->

Subst

) ) {

577

dst +=

string

( pSrc, utfLen );

583

dst += pSubst->

Subst

;

CTempString implements a light-weight string on top of a storage buffer whose lifetime management is ...

CUnicodeToAsciiTranslation(void)

void x_Initialize(const string &name)

bool IsInitialized(void) const

static int x_ParseLine(string &line, TUnicode &symbol, string &translation)

virtual ~CUnicodeToAsciiTranslation(void)

map< TUnicode, SUnicodeTranslation > m_SymbolToTranslation

const SUnicodeTranslation * GetTranslation(TUnicode symbol) const

container_type::const_iterator const_iterator

const_iterator begin() const

const_iterator end() const

const_iterator find(const key_type &key) const

#define LOG_POST_X(err_subcode, message)

#define ERR_POST_X(err_subcode, message)

Error posting with default error code and given error subcode.

#define NCBI_THROW(exception_class, err_code, message)

Generic macro to throw an exception, given the exception class, error code and message string.

void Info(CExceptionArgs_Base &args)

Int8 GetLength(void) const

Get size of file.

#define NCBI_PARAM_TYPE(section, name)

Generate typename for a parameter from its {section, name} attributes.

int8_t Int1

1-byte (8-bit) signed integer

#define END_NCBI_SCOPE

End previously defined NCBI scope.

#define END_SCOPE(ns)

End the previously defined scope.

#define BEGIN_NCBI_SCOPE

Define ncbi namespace.

#define BEGIN_SCOPE(ns)

Define a new scope.

CNcbiIstream & NcbiGetlineEOL(CNcbiIstream &is, string &str, string::size_type *count=NULL)

Read from "is" to "str" the next line (taking into account platform specifics of End-of-Line)

IO_PREFIX::ifstream CNcbiIfstream

Portable alias for ifstream.

static bool StartsWith(const CTempString str, const CTempString start, ECase use_case=eCase)

Check if a string starts with a specified prefix value.

static unsigned int StringToUInt(const CTempString str, TStringToNumFlags flags=0, int base=10)

Convert string to unsigned int.

ESubstType Type

Type of the substitutor.

string UTF8ToAsciiString(const char *src, const SUnicodeTranslation *default_translation, const TUnicodeTable *table, EConversionResult *result)

Convert UTF8 into ASCII string.

SUnicodeTranslation TUnicodePlan[256]

string UnicodeToUTF8(TUnicode theUnicode)

Convert Unicode character into UTF8.

const SUnicodeTranslation * UnicodeToAscii(TUnicode character, const TUnicodeTable *table, const SUnicodeTranslation *default_translation)

Convert Unicode character into ASCII string.

const char * Subst

Substitutor for unicode.

TUnicodePlan * TUnicodeTable[256]

ssize_t UTF8ToAscii(const char *src, char *dst, size_t dstLen, const SUnicodeTranslation *default_translation, const TUnicodeTable *table, EConversionResult *result)

Convert UTF8 into ASCII character buffer.

@ eSkip

Unicode to be skipped in translation. Usually it is combined mark.

@ eException

Throw exception (CUtilException, with type eWrongData)

@ eAsIs

Unicodes which should go into the text as is.

@ eDefaultTranslationUsed

Definition of all error codes used in util (xutil.lib).

<!DOCTYPE HTML >< html > n< header > n< title > PubSeq Gateway Help Page</title > n< style > n table

Static variables safety - create on demand, destroy on application termination.

Defines classes: CDirEntry, CFile, CDir, CSymLink, CMemoryFile, CFileUtil, CFileLock,...

std::istream & in(std::istream &in_, double &x_)

Structure to keep substititutions for the particular unicode character.

CSafeStatic< CUnicodeToAsciiTranslation > g_UnicodeTranslation

NCBI_PARAM_DECL(string, NCBI, UnicodeToAscii)

static string s_FindUnicodeToAscii(void)

static TUnicodeTable g_DefaultUnicodeTable

TUnicode UTF8ToUnicode(const char *theUTF)

NCBI_PARAM_DEF_WITH_INIT(string, NCBI, UnicodeToAscii, "", s_FindUnicodeToAscii)

static TUnicodePlan s_Plan_26h

static TUnicodePlan s_Plan_E4h

static TUnicodePlan s_Plan_30h

static TUnicodePlan s_Plan_04h

static TUnicodePlan s_Plan_FEh

static TUnicodePlan s_Plan_E2h

static TUnicodePlan s_Plan_27h

static TUnicodePlan s_Plan_21h

static TUnicodePlan s_Plan_E5h

static TUnicodePlan s_Plan_E8h

static TUnicodePlan s_Plan_00h

static TUnicodePlan s_Plan_E6h

static TUnicodePlan s_Plan_22h

static TUnicodePlan s_Plan_20h

static TUnicodePlan s_Plan_24h

static TUnicodePlan s_Plan_25h

static TUnicodePlan s_Plan_01h

static TUnicodePlan s_Plan_EAh

static TUnicodePlan s_Plan_EBh

static TUnicodePlan s_Plan_FBh

static TUnicodePlan s_Plan_23h

static TUnicodePlan s_Plan_E0h

static TUnicodePlan s_Plan_E3h

static TUnicodePlan s_Plan_1Eh

static TUnicodePlan s_Plan_02h

static TUnicodePlan s_Plan_03h

static TUnicodePlan s_Plan_E7h

string g_FindDataFile(const CTempString &name, CDirEntry::EType type=CDirEntry::eFile)

Look for an NCBI application data file or directory of the given name and type; in general,...

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4