[フレーム]

Macros | Functions

unicode_category.c File Reference

#include "postgres.h"
#include "common/unicode_category.h"
#include "common/unicode_category_table.h"

Include dependency graph for unicode_category.c:

Go to the source code of this file.

Macros

#define PG_U_CATEGORY_MASK(X) ((uint32)(1 << (X)))

#define PG_U_LU_MASK PG_U_CATEGORY_MASK(PG_U_UPPERCASE_LETTER)

#define PG_U_LL_MASK PG_U_CATEGORY_MASK(PG_U_LOWERCASE_LETTER)

#define PG_U_LT_MASK PG_U_CATEGORY_MASK(PG_U_TITLECASE_LETTER)

#define PG_U_LC_MASK (PG_U_LU_MASK|PG_U_LL_MASK|PG_U_LT_MASK)

#define PG_U_LM_MASK PG_U_CATEGORY_MASK(PG_U_MODIFIER_LETTER)

#define PG_U_LO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_LETTER)

#define PG_U_L_MASK

#define PG_U_MN_MASK PG_U_CATEGORY_MASK(PG_U_NONSPACING_MARK)

#define PG_U_ME_MASK PG_U_CATEGORY_MASK(PG_U_ENCLOSING_MARK)

#define PG_U_MC_MASK PG_U_CATEGORY_MASK(PG_U_SPACING_MARK)

#define PG_U_M_MASK (PG_U_MN_MASK|PG_U_MC_MASK|PG_U_ME_MASK)

#define PG_U_ND_MASK PG_U_CATEGORY_MASK(PG_U_DECIMAL_NUMBER)

#define PG_U_NL_MASK PG_U_CATEGORY_MASK(PG_U_LETTER_NUMBER)

#define PG_U_NO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_NUMBER)

#define PG_U_N_MASK (PG_U_ND_MASK|PG_U_NL_MASK|PG_U_NO_MASK)

#define PG_U_PC_MASK PG_U_CATEGORY_MASK(PG_U_CONNECTOR_PUNCTUATION)

#define PG_U_PD_MASK PG_U_CATEGORY_MASK(PG_U_DASH_PUNCTUATION)

#define PG_U_PS_MASK PG_U_CATEGORY_MASK(PG_U_OPEN_PUNCTUATION)

#define PG_U_PE_MASK PG_U_CATEGORY_MASK(PG_U_CLOSE_PUNCTUATION)

#define PG_U_PI_MASK PG_U_CATEGORY_MASK(PG_U_INITIAL_PUNCTUATION)

#define PG_U_PF_MASK PG_U_CATEGORY_MASK(PG_U_FINAL_PUNCTUATION)

#define PG_U_PO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_PUNCTUATION)

#define PG_U_P_MASK

#define PG_U_SM_MASK PG_U_CATEGORY_MASK(PG_U_MATH_SYMBOL)

#define PG_U_SC_MASK PG_U_CATEGORY_MASK(PG_U_CURRENCY_SYMBOL)

#define PG_U_SK_MASK PG_U_CATEGORY_MASK(PG_U_MODIFIER_SYMBOL)

#define PG_U_SO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_SYMBOL)

#define PG_U_S_MASK (PG_U_SM_MASK|PG_U_SC_MASK|PG_U_SK_MASK|PG_U_SO_MASK)

#define PG_U_ZS_MASK PG_U_CATEGORY_MASK(PG_U_SPACE_SEPARATOR)

#define PG_U_ZL_MASK PG_U_CATEGORY_MASK(PG_U_LINE_SEPARATOR)

#define PG_U_ZP_MASK PG_U_CATEGORY_MASK(PG_U_PARAGRAPH_SEPARATOR)

#define PG_U_Z_MASK (PG_U_ZS_MASK|PG_U_ZL_MASK|PG_U_ZP_MASK)

#define PG_U_CC_MASK PG_U_CATEGORY_MASK(PG_U_CONTROL)

#define PG_U_CF_MASK PG_U_CATEGORY_MASK(PG_U_FORMAT)

#define PG_U_CS_MASK PG_U_CATEGORY_MASK(PG_U_SURROGATE)

#define PG_U_CO_MASK PG_U_CATEGORY_MASK(PG_U_PRIVATE_USE)

#define PG_U_CN_MASK PG_U_CATEGORY_MASK(PG_U_UNASSIGNED)

#define PG_U_C_MASK

#define PG_U_CHARACTER_TAB 0x09

Functions

static bool range_search (const pg_unicode_range *tbl, size_t size, pg_wchar code)

pg_unicode_category unicode_category (pg_wchar code)

bool pg_u_prop_alphabetic (pg_wchar code)

bool pg_u_prop_lowercase (pg_wchar code)

bool pg_u_prop_uppercase (pg_wchar code)

bool pg_u_prop_cased (pg_wchar code)

bool pg_u_prop_case_ignorable (pg_wchar code)

bool pg_u_prop_white_space (pg_wchar code)

bool pg_u_prop_hex_digit (pg_wchar code)

bool pg_u_prop_join_control (pg_wchar code)

bool pg_u_isdigit (pg_wchar code, bool posix)

bool pg_u_isalpha (pg_wchar code)

bool pg_u_isalnum (pg_wchar code, bool posix)

bool pg_u_isword (pg_wchar code)

bool pg_u_isupper (pg_wchar code)

bool pg_u_islower (pg_wchar code)

bool pg_u_isblank (pg_wchar code)

bool pg_u_iscntrl (pg_wchar code)

bool pg_u_isgraph (pg_wchar code)

bool pg_u_isprint (pg_wchar code)

bool pg_u_ispunct (pg_wchar code, bool posix)

bool pg_u_isspace (pg_wchar code)

bool pg_u_isxdigit (pg_wchar code, bool posix)

const char * unicode_category_string (pg_unicode_category category)

const char * unicode_category_abbrev (pg_unicode_category category)

Macro Definition Documentation

◆ PG_U_C_MASK

#define PG_U_C_MASK

Value:

(PG_U_CC_MASK|PG_U_CF_MASK|PG_U_CS_MASK|PG_U_CO_MASK|\

PG_U_CN_MASK)

PG_U_CC_MASK

#define PG_U_CC_MASK

Definition: unicode_category.c:68

PG_U_CO_MASK

#define PG_U_CO_MASK

Definition: unicode_category.c:71

PG_U_CS_MASK

#define PG_U_CS_MASK

Definition: unicode_category.c:70

PG_U_CF_MASK

#define PG_U_CF_MASK

Definition: unicode_category.c:69

Definition at line 73 of file unicode_category.c.

◆ PG_U_CATEGORY_MASK

#define PG_U_CATEGORY_MASK ( X ) ((uint32)(1 << (X)))

Definition at line 32 of file unicode_category.c.

◆ PG_U_CC_MASK

#define PG_U_CC_MASK PG_U_CATEGORY_MASK(PG_U_CONTROL)

Definition at line 68 of file unicode_category.c.

◆ PG_U_CF_MASK

#define PG_U_CF_MASK PG_U_CATEGORY_MASK(PG_U_FORMAT)

Definition at line 69 of file unicode_category.c.

◆ PG_U_CHARACTER_TAB

#define PG_U_CHARACTER_TAB 0x09

Definition at line 76 of file unicode_category.c.

◆ PG_U_CN_MASK

#define PG_U_CN_MASK PG_U_CATEGORY_MASK(PG_U_UNASSIGNED)

Definition at line 72 of file unicode_category.c.

◆ PG_U_CO_MASK

#define PG_U_CO_MASK PG_U_CATEGORY_MASK(PG_U_PRIVATE_USE)

Definition at line 71 of file unicode_category.c.

◆ PG_U_CS_MASK

#define PG_U_CS_MASK PG_U_CATEGORY_MASK(PG_U_SURROGATE)

Definition at line 70 of file unicode_category.c.

◆ PG_U_L_MASK

#define PG_U_L_MASK

Value:

(PG_U_LU_MASK|PG_U_LL_MASK|PG_U_LT_MASK|PG_U_LM_MASK|\

PG_U_LO_MASK)

PG_U_LL_MASK

#define PG_U_LL_MASK

Definition: unicode_category.c:35

PG_U_LT_MASK

#define PG_U_LT_MASK

Definition: unicode_category.c:36

PG_U_LM_MASK

#define PG_U_LM_MASK

Definition: unicode_category.c:38

PG_U_LU_MASK

#define PG_U_LU_MASK

Definition: unicode_category.c:34

Definition at line 40 of file unicode_category.c.

◆ PG_U_LC_MASK

#define PG_U_LC_MASK (PG_U_LU_MASK|PG_U_LL_MASK|PG_U_LT_MASK)

Definition at line 37 of file unicode_category.c.

◆ PG_U_LL_MASK

#define PG_U_LL_MASK PG_U_CATEGORY_MASK(PG_U_LOWERCASE_LETTER)

Definition at line 35 of file unicode_category.c.

◆ PG_U_LM_MASK

#define PG_U_LM_MASK PG_U_CATEGORY_MASK(PG_U_MODIFIER_LETTER)

Definition at line 38 of file unicode_category.c.

◆ PG_U_LO_MASK

#define PG_U_LO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_LETTER)

Definition at line 39 of file unicode_category.c.

◆ PG_U_LT_MASK

#define PG_U_LT_MASK PG_U_CATEGORY_MASK(PG_U_TITLECASE_LETTER)

Definition at line 36 of file unicode_category.c.

◆ PG_U_LU_MASK

#define PG_U_LU_MASK PG_U_CATEGORY_MASK(PG_U_UPPERCASE_LETTER)

Definition at line 34 of file unicode_category.c.

◆ PG_U_M_MASK

#define PG_U_M_MASK (PG_U_MN_MASK|PG_U_MC_MASK|PG_U_ME_MASK)

Definition at line 45 of file unicode_category.c.

◆ PG_U_MC_MASK

#define PG_U_MC_MASK PG_U_CATEGORY_MASK(PG_U_SPACING_MARK)

Definition at line 44 of file unicode_category.c.

◆ PG_U_ME_MASK

#define PG_U_ME_MASK PG_U_CATEGORY_MASK(PG_U_ENCLOSING_MARK)

Definition at line 43 of file unicode_category.c.

◆ PG_U_MN_MASK

#define PG_U_MN_MASK PG_U_CATEGORY_MASK(PG_U_NONSPACING_MARK)

Definition at line 42 of file unicode_category.c.

◆ PG_U_N_MASK

#define PG_U_N_MASK (PG_U_ND_MASK|PG_U_NL_MASK|PG_U_NO_MASK)

Definition at line 49 of file unicode_category.c.

◆ PG_U_ND_MASK

#define PG_U_ND_MASK PG_U_CATEGORY_MASK(PG_U_DECIMAL_NUMBER)

Definition at line 46 of file unicode_category.c.

◆ PG_U_NL_MASK

#define PG_U_NL_MASK PG_U_CATEGORY_MASK(PG_U_LETTER_NUMBER)

Definition at line 47 of file unicode_category.c.

◆ PG_U_NO_MASK

#define PG_U_NO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_NUMBER)

Definition at line 48 of file unicode_category.c.

◆ PG_U_P_MASK

#define PG_U_P_MASK

Value:

(PG_U_PC_MASK|PG_U_PD_MASK|PG_U_PS_MASK|PG_U_PE_MASK|\

PG_U_PI_MASK|PG_U_PF_MASK|PG_U_PO_MASK)

PG_U_PO_MASK

#define PG_U_PO_MASK

Definition: unicode_category.c:56

PG_U_PS_MASK

#define PG_U_PS_MASK

Definition: unicode_category.c:52

PG_U_PC_MASK

#define PG_U_PC_MASK

Definition: unicode_category.c:50

PG_U_PD_MASK

#define PG_U_PD_MASK

Definition: unicode_category.c:51

PG_U_PF_MASK

#define PG_U_PF_MASK

Definition: unicode_category.c:55

PG_U_PE_MASK

#define PG_U_PE_MASK

Definition: unicode_category.c:53

Definition at line 57 of file unicode_category.c.

◆ PG_U_PC_MASK

#define PG_U_PC_MASK PG_U_CATEGORY_MASK(PG_U_CONNECTOR_PUNCTUATION)

Definition at line 50 of file unicode_category.c.

◆ PG_U_PD_MASK

#define PG_U_PD_MASK PG_U_CATEGORY_MASK(PG_U_DASH_PUNCTUATION)

Definition at line 51 of file unicode_category.c.

◆ PG_U_PE_MASK

#define PG_U_PE_MASK PG_U_CATEGORY_MASK(PG_U_CLOSE_PUNCTUATION)

Definition at line 53 of file unicode_category.c.

◆ PG_U_PF_MASK

#define PG_U_PF_MASK PG_U_CATEGORY_MASK(PG_U_FINAL_PUNCTUATION)

Definition at line 55 of file unicode_category.c.

◆ PG_U_PI_MASK

#define PG_U_PI_MASK PG_U_CATEGORY_MASK(PG_U_INITIAL_PUNCTUATION)

Definition at line 54 of file unicode_category.c.

◆ PG_U_PO_MASK

#define PG_U_PO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_PUNCTUATION)

Definition at line 56 of file unicode_category.c.

◆ PG_U_PS_MASK

#define PG_U_PS_MASK PG_U_CATEGORY_MASK(PG_U_OPEN_PUNCTUATION)

Definition at line 52 of file unicode_category.c.

◆ PG_U_S_MASK

#define PG_U_S_MASK (PG_U_SM_MASK|PG_U_SC_MASK|PG_U_SK_MASK|PG_U_SO_MASK)

Definition at line 63 of file unicode_category.c.

◆ PG_U_SC_MASK

#define PG_U_SC_MASK PG_U_CATEGORY_MASK(PG_U_CURRENCY_SYMBOL)

Definition at line 60 of file unicode_category.c.

◆ PG_U_SK_MASK

#define PG_U_SK_MASK PG_U_CATEGORY_MASK(PG_U_MODIFIER_SYMBOL)

Definition at line 61 of file unicode_category.c.

◆ PG_U_SM_MASK

#define PG_U_SM_MASK PG_U_CATEGORY_MASK(PG_U_MATH_SYMBOL)

Definition at line 59 of file unicode_category.c.

◆ PG_U_SO_MASK

#define PG_U_SO_MASK PG_U_CATEGORY_MASK(PG_U_OTHER_SYMBOL)

Definition at line 62 of file unicode_category.c.

◆ PG_U_Z_MASK

#define PG_U_Z_MASK (PG_U_ZS_MASK|PG_U_ZL_MASK|PG_U_ZP_MASK)

Definition at line 67 of file unicode_category.c.

◆ PG_U_ZL_MASK

#define PG_U_ZL_MASK PG_U_CATEGORY_MASK(PG_U_LINE_SEPARATOR)

Definition at line 65 of file unicode_category.c.

◆ PG_U_ZP_MASK

#define PG_U_ZP_MASK PG_U_CATEGORY_MASK(PG_U_PARAGRAPH_SEPARATOR)

Definition at line 66 of file unicode_category.c.

◆ PG_U_ZS_MASK

#define PG_U_ZS_MASK PG_U_CATEGORY_MASK(PG_U_SPACE_SEPARATOR)

Definition at line 64 of file unicode_category.c.

Function Documentation

◆ pg_u_isalnum()

bool pg_u_isalnum ( pg_wchar code,

bool posix

)

Definition at line 226 of file unicode_category.c.

227{

228 return pg_u_isalpha(code) || pg_u_isdigit(code, posix);

229}

pg_u_isalpha

bool pg_u_isalpha(pg_wchar code)

Definition: unicode_category.c:220

pg_u_isdigit

bool pg_u_isdigit(pg_wchar code, bool posix)

Definition: unicode_category.c:211

References pg_u_isalpha(), and pg_u_isdigit().

Referenced by initcap_wbnext(), and wc_isalnum_builtin().

◆ pg_u_isalpha()

bool pg_u_isalpha ( pg_wchar code )

Definition at line 220 of file unicode_category.c.

221{

222 return pg_u_prop_alphabetic(code);

223}

pg_u_prop_alphabetic

bool pg_u_prop_alphabetic(pg_wchar code)

Definition: unicode_category.c:111

References pg_u_prop_alphabetic().

Referenced by pg_u_isalnum(), pg_u_ispunct(), pg_u_isword(), and wc_isalpha_builtin().

◆ pg_u_isblank()

bool pg_u_isblank ( pg_wchar code )

Definition at line 255 of file unicode_category.c.

256{

257 return code == PG_U_CHARACTER_TAB ||

258 unicode_category(code) == PG_U_SPACE_SEPARATOR;

259}

PG_U_CHARACTER_TAB

#define PG_U_CHARACTER_TAB

Definition: unicode_category.c:76

unicode_category

pg_unicode_category unicode_category(pg_wchar code)

Definition: unicode_category.c:85

PG_U_SPACE_SEPARATOR

@ PG_U_SPACE_SEPARATOR

Definition: unicode_category.h:44

References PG_U_CHARACTER_TAB, PG_U_SPACE_SEPARATOR, and unicode_category().

Referenced by pg_u_isprint().

◆ pg_u_iscntrl()

bool pg_u_iscntrl ( pg_wchar code )

Definition at line 262 of file unicode_category.c.

263{

264 return unicode_category(code) == PG_U_CONTROL;

265}

PG_U_CONTROL

@ PG_U_CONTROL

Definition: unicode_category.h:47

References PG_U_CONTROL, and unicode_category().

◆ pg_u_isdigit()

bool pg_u_isdigit ( pg_wchar code,

bool posix

)

Definition at line 211 of file unicode_category.c.

212{

213 if (posix)

214 return ('0' <= code && code <= '9');

215 else

216 return unicode_category(code) == PG_U_DECIMAL_NUMBER;

217}

PG_U_DECIMAL_NUMBER

@ PG_U_DECIMAL_NUMBER

Definition: unicode_category.h:41

References PG_U_DECIMAL_NUMBER, and unicode_category().

Referenced by pg_u_isalnum(), and wc_isdigit_builtin().

◆ pg_u_isgraph()

bool pg_u_isgraph ( pg_wchar code )

Definition at line 268 of file unicode_category.c.

269{

270 uint32 category_mask = PG_U_CATEGORY_MASK(unicode_category(code));

271

272 if (category_mask & (PG_U_CC_MASK | PG_U_CS_MASK | PG_U_CN_MASK) ||

273 pg_u_isspace(code))

274 return false;

275 return true;

276}

uint32

uint32_t uint32

Definition: c.h:538

pg_u_isspace

bool pg_u_isspace(pg_wchar code)

Definition: unicode_category.c:311

PG_U_CATEGORY_MASK

#define PG_U_CATEGORY_MASK(X)

Definition: unicode_category.c:32

PG_U_CN_MASK

#define PG_U_CN_MASK

Definition: unicode_category.c:72

References PG_U_CATEGORY_MASK, PG_U_CC_MASK, PG_U_CN_MASK, PG_U_CS_MASK, pg_u_isspace(), and unicode_category().

Referenced by pg_u_isprint(), and wc_isgraph_builtin().

◆ pg_u_islower()

bool pg_u_islower ( pg_wchar code )

Definition at line 249 of file unicode_category.c.

250{

251 return pg_u_prop_lowercase(code);

252}

pg_u_prop_lowercase

bool pg_u_prop_lowercase(pg_wchar code)

Definition: unicode_category.c:122

References pg_u_prop_lowercase().

Referenced by wc_islower_builtin().

◆ pg_u_isprint()

bool pg_u_isprint ( pg_wchar code )

Definition at line 279 of file unicode_category.c.

280{

281 pg_unicode_category category = unicode_category(code);

282

283 if (category == PG_U_CONTROL)

284 return false;

285

286 return pg_u_isgraph(code) || pg_u_isblank(code);

287}

pg_u_isblank

bool pg_u_isblank(pg_wchar code)

Definition: unicode_category.c:255

pg_u_isgraph

bool pg_u_isgraph(pg_wchar code)

Definition: unicode_category.c:268

pg_unicode_category

Definition: unicode_category.h:31

References PG_U_CONTROL, pg_u_isblank(), pg_u_isgraph(), and unicode_category().

Referenced by wc_isprint_builtin().

◆ pg_u_ispunct()

bool pg_u_ispunct ( pg_wchar code,

bool posix

)

Definition at line 290 of file unicode_category.c.

291{

292 uint32 category_mask;

293

294 if (posix)

295 {

296 if (pg_u_isalpha(code))

297 return false;

298

299 category_mask = PG_U_CATEGORY_MASK(unicode_category(code));

300 return category_mask & (PG_U_P_MASK | PG_U_S_MASK);

301 }

302 else

303 {

304 category_mask = PG_U_CATEGORY_MASK(unicode_category(code));

305

306 return category_mask & PG_U_P_MASK;

307 }

308}

PG_U_P_MASK

#define PG_U_P_MASK

Definition: unicode_category.c:57

PG_U_S_MASK

#define PG_U_S_MASK

Definition: unicode_category.c:63

References PG_U_CATEGORY_MASK, pg_u_isalpha(), PG_U_P_MASK, PG_U_S_MASK, and unicode_category().

Referenced by wc_ispunct_builtin().

◆ pg_u_isspace()

bool pg_u_isspace ( pg_wchar code )

Definition at line 311 of file unicode_category.c.

312{

313 return pg_u_prop_white_space(code);

314}

pg_u_prop_white_space

bool pg_u_prop_white_space(pg_wchar code)

Definition: unicode_category.c:170

References pg_u_prop_white_space().

Referenced by pg_u_isgraph(), and wc_isspace_builtin().

◆ pg_u_isupper()

bool pg_u_isupper ( pg_wchar code )

Definition at line 243 of file unicode_category.c.

244{

245 return pg_u_prop_uppercase(code);

246}

pg_u_prop_uppercase

bool pg_u_prop_uppercase(pg_wchar code)

Definition: unicode_category.c:133

References pg_u_prop_uppercase().

Referenced by wc_isupper_builtin().

◆ pg_u_isword()

bool pg_u_isword ( pg_wchar code )

Definition at line 232 of file unicode_category.c.

233{

234 uint32 category_mask = PG_U_CATEGORY_MASK(unicode_category(code));

235

236 return

237 category_mask & (PG_U_M_MASK | PG_U_ND_MASK | PG_U_PC_MASK) ||

238 pg_u_isalpha(code) ||

239 pg_u_prop_join_control(code);

240}

PG_U_ND_MASK

#define PG_U_ND_MASK

Definition: unicode_category.c:46

PG_U_M_MASK

#define PG_U_M_MASK

Definition: unicode_category.c:45

pg_u_prop_join_control

bool pg_u_prop_join_control(pg_wchar code)

Definition: unicode_category.c:192

References PG_U_CATEGORY_MASK, pg_u_isalpha(), PG_U_M_MASK, PG_U_ND_MASK, PG_U_PC_MASK, pg_u_prop_join_control(), and unicode_category().

◆ pg_u_isxdigit()

bool pg_u_isxdigit ( pg_wchar code,

bool posix

)

Definition at line 317 of file unicode_category.c.

318{

319 if (posix)

320 return (('0' <= code && code <= '9') ||

321 ('A' <= code && code <= 'F') ||

322 ('a' <= code && code <= 'f'));

323 else

324 return unicode_category(code) == PG_U_DECIMAL_NUMBER ||

325 pg_u_prop_hex_digit(code);

326}

pg_u_prop_hex_digit

bool pg_u_prop_hex_digit(pg_wchar code)

Definition: unicode_category.c:181

References PG_U_DECIMAL_NUMBER, pg_u_prop_hex_digit(), and unicode_category().

◆ pg_u_prop_alphabetic()

bool pg_u_prop_alphabetic ( pg_wchar code )

Definition at line 111 of file unicode_category.c.

112{

113 if (code < 0x80)

114 return unicode_opt_ascii[code].properties & PG_U_PROP_ALPHABETIC;

115

116 return range_search(unicode_alphabetic,

117 lengthof(unicode_alphabetic),

118 code);

119}

lengthof

#define lengthof(array)

Definition: c.h:787

pg_unicode_properties::properties

uint8 properties

Definition: unicode_category_table.h:37

range_search

static bool range_search(const pg_unicode_range *tbl, size_t size, pg_wchar code)

Definition: unicode_category.c:481

PG_U_PROP_ALPHABETIC

#define PG_U_PROP_ALPHABETIC

Definition: unicode_category_table.h:44

unicode_alphabetic

static const pg_unicode_range unicode_alphabetic[1179]

Definition: unicode_category_table.h:4072

unicode_opt_ascii

static const pg_unicode_properties unicode_opt_ascii[128]

Definition: unicode_category_table.h:54

References lengthof, PG_U_PROP_ALPHABETIC, pg_unicode_properties::properties, range_search(), unicode_alphabetic, and unicode_opt_ascii.

Referenced by pg_u_isalpha().

◆ pg_u_prop_case_ignorable()

bool pg_u_prop_case_ignorable ( pg_wchar code )

Definition at line 159 of file unicode_category.c.

160{

161 if (code < 0x80)

162 return unicode_opt_ascii[code].properties & PG_U_PROP_CASE_IGNORABLE;

163

164 return range_search(unicode_case_ignorable,

165 lengthof(unicode_case_ignorable),

166 code);

167}

unicode_case_ignorable

static const pg_unicode_range unicode_case_ignorable[506]

Definition: unicode_category_table.h:6612

PG_U_PROP_CASE_IGNORABLE

#define PG_U_PROP_CASE_IGNORABLE

Definition: unicode_category_table.h:48

References lengthof, PG_U_PROP_CASE_IGNORABLE, pg_unicode_properties::properties, range_search(), unicode_case_ignorable, and unicode_opt_ascii.

Referenced by check_final_sigma().

◆ pg_u_prop_cased()

bool pg_u_prop_cased ( pg_wchar code )

Definition at line 144 of file unicode_category.c.

145{

146 uint32 category_mask;

147

148 if (code < 0x80)

149 return unicode_opt_ascii[code].properties & PG_U_PROP_CASED;

150

151 category_mask = PG_U_CATEGORY_MASK(unicode_category(code));

152

153 return category_mask & PG_U_LT_MASK ||

154 pg_u_prop_lowercase(code) ||

155 pg_u_prop_uppercase(code);

156}

PG_U_PROP_CASED

#define PG_U_PROP_CASED

Definition: unicode_category_table.h:47

References PG_U_CATEGORY_MASK, PG_U_LT_MASK, PG_U_PROP_CASED, pg_u_prop_lowercase(), pg_u_prop_uppercase(), pg_unicode_properties::properties, unicode_category(), and unicode_opt_ascii.

Referenced by check_final_sigma().

◆ pg_u_prop_hex_digit()

bool pg_u_prop_hex_digit ( pg_wchar code )

Definition at line 181 of file unicode_category.c.

182{

183 if (code < 0x80)

184 return unicode_opt_ascii[code].properties & PG_U_PROP_HEX_DIGIT;

185

186 return range_search(unicode_hex_digit,

187 lengthof(unicode_hex_digit),

188 code);

189}

PG_U_PROP_HEX_DIGIT

#define PG_U_PROP_HEX_DIGIT

Definition: unicode_category_table.h:51

unicode_hex_digit

static const pg_unicode_range unicode_hex_digit[6]

Definition: unicode_category_table.h:7139

References lengthof, PG_U_PROP_HEX_DIGIT, pg_unicode_properties::properties, range_search(), unicode_hex_digit, and unicode_opt_ascii.

Referenced by pg_u_isxdigit().

◆ pg_u_prop_join_control()

bool pg_u_prop_join_control ( pg_wchar code )

Definition at line 192 of file unicode_category.c.

193{

194 if (code < 0x80)

195 return unicode_opt_ascii[code].properties & PG_U_PROP_JOIN_CONTROL;

196

197 return range_search(unicode_join_control,

198 lengthof(unicode_join_control),

199 code);

200}

PG_U_PROP_JOIN_CONTROL

#define PG_U_PROP_JOIN_CONTROL

Definition: unicode_category_table.h:50

unicode_join_control

static const pg_unicode_range unicode_join_control[1]

Definition: unicode_category_table.h:7150

References lengthof, PG_U_PROP_JOIN_CONTROL, pg_unicode_properties::properties, range_search(), unicode_join_control, and unicode_opt_ascii.

Referenced by pg_u_isword().

◆ pg_u_prop_lowercase()

bool pg_u_prop_lowercase ( pg_wchar code )

Definition at line 122 of file unicode_category.c.

123{

124 if (code < 0x80)

125 return unicode_opt_ascii[code].properties & PG_U_PROP_LOWERCASE;

126

127 return range_search(unicode_lowercase,

128 lengthof(unicode_lowercase),

129 code);

130}

PG_U_PROP_LOWERCASE

#define PG_U_PROP_LOWERCASE

Definition: unicode_category_table.h:45

unicode_lowercase

static const pg_unicode_range unicode_lowercase[690]

Definition: unicode_category_table.h:5256

References lengthof, PG_U_PROP_LOWERCASE, pg_unicode_properties::properties, range_search(), unicode_lowercase, and unicode_opt_ascii.

Referenced by pg_u_islower(), and pg_u_prop_cased().

◆ pg_u_prop_uppercase()

bool pg_u_prop_uppercase ( pg_wchar code )

Definition at line 133 of file unicode_category.c.

134{

135 if (code < 0x80)

136 return unicode_opt_ascii[code].properties & PG_U_PROP_UPPERCASE;

137

138 return range_search(unicode_uppercase,

139 lengthof(unicode_uppercase),

140 code);

141}

PG_U_PROP_UPPERCASE

#define PG_U_PROP_UPPERCASE

Definition: unicode_category_table.h:46

unicode_uppercase

static const pg_unicode_range unicode_uppercase[656]

Definition: unicode_category_table.h:5951

References lengthof, PG_U_PROP_UPPERCASE, pg_unicode_properties::properties, range_search(), unicode_opt_ascii, and unicode_uppercase.

Referenced by pg_u_isupper(), and pg_u_prop_cased().

◆ pg_u_prop_white_space()

bool pg_u_prop_white_space ( pg_wchar code )

Definition at line 170 of file unicode_category.c.

171{

172 if (code < 0x80)

173 return unicode_opt_ascii[code].properties & PG_U_PROP_WHITE_SPACE;

174

175 return range_search(unicode_white_space,

176 lengthof(unicode_white_space),

177 code);

178}

unicode_white_space

static const pg_unicode_range unicode_white_space[11]

Definition: unicode_category_table.h:7123

PG_U_PROP_WHITE_SPACE

#define PG_U_PROP_WHITE_SPACE

Definition: unicode_category_table.h:49

References lengthof, PG_U_PROP_WHITE_SPACE, pg_unicode_properties::properties, range_search(), unicode_opt_ascii, and unicode_white_space.

Referenced by pg_u_isspace().

◆ range_search()

static bool range_search ( const pg_unicode_range * tbl,

size_t size,

pg_wchar code

)

static

Definition at line 481 of file unicode_category.c.

482{

483 int min = 0;

484 int mid;

485 int max = size - 1;

486

487 Assert(code <= 0x10ffff);

488

489 while (max >= min)

490 {

491 mid = (min + max) / 2;

492 if (code > tbl[mid].last)

493 min = mid + 1;

494 else if (code < tbl[mid].first)

495 max = mid - 1;

496 else

497 return true;

498 }

499

500 return false;

501}

Assert

Assert(PointerIsAligned(start, uint64))

References Assert().

Referenced by pg_u_prop_alphabetic(), pg_u_prop_case_ignorable(), pg_u_prop_hex_digit(), pg_u_prop_join_control(), pg_u_prop_lowercase(), pg_u_prop_uppercase(), and pg_u_prop_white_space().

◆ unicode_category()

pg_unicode_category unicode_category ( pg_wchar code )

Definition at line 85 of file unicode_category.c.

86{

87 int min = 0;

88 int mid;

89 int max = lengthof(unicode_categories) - 1;

90

91 Assert(code <= 0x10ffff);

92

93 if (code < 0x80)

94 return unicode_opt_ascii[code].category;

95

96 while (max >= min)

97 {

98 mid = (min + max) / 2;

99 if (code > unicode_categories[mid].last)

100 min = mid + 1;

101 else if (code < unicode_categories[mid].first)

102 max = mid - 1;

103 else

104 return unicode_categories[mid].category;

105 }

106

107 return PG_U_UNASSIGNED;

108}

pg_category_range::category

uint8 category

Definition: unicode_category_table.h:25

pg_unicode_properties::category

uint8 category

Definition: unicode_category_table.h:36

PG_U_UNASSIGNED

@ PG_U_UNASSIGNED

Definition: unicode_category.h:32

unicode_categories

static const pg_category_range unicode_categories[3368]

Definition: unicode_category_table.h:699

References Assert(), pg_category_range::category, pg_unicode_properties::category, lengthof, PG_U_UNASSIGNED, unicode_categories, and unicode_opt_ascii.

Referenced by pg_u_isblank(), pg_u_iscntrl(), pg_u_isdigit(), pg_u_isgraph(), pg_u_isprint(), pg_u_ispunct(), pg_u_isword(), pg_u_isxdigit(), pg_u_prop_cased(), and unicode_assigned().

◆ unicode_category_abbrev()

const char * unicode_category_abbrev ( pg_unicode_category category )

Definition at line 406 of file unicode_category.c.

407{

408 switch (category)

409 {

410 case PG_U_UNASSIGNED:

411 return "Cn";

412 case PG_U_UPPERCASE_LETTER:

413 return "Lu";

414 case PG_U_LOWERCASE_LETTER:

415 return "Ll";

416 case PG_U_TITLECASE_LETTER:

417 return "Lt";

418 case PG_U_MODIFIER_LETTER:

419 return "Lm";

420 case PG_U_OTHER_LETTER:

421 return "Lo";

422 case PG_U_NONSPACING_MARK:

423 return "Mn";

424 case PG_U_ENCLOSING_MARK:

425 return "Me";

426 case PG_U_SPACING_MARK:

427 return "Mc";

428 case PG_U_DECIMAL_NUMBER:

429 return "Nd";

430 case PG_U_LETTER_NUMBER:

431 return "Nl";

432 case PG_U_OTHER_NUMBER:

433 return "No";

434 case PG_U_SPACE_SEPARATOR:

435 return "Zs";

436 case PG_U_LINE_SEPARATOR:

437 return "Zl";

438 case PG_U_PARAGRAPH_SEPARATOR:

439 return "Zp";

440 case PG_U_CONTROL:

441 return "Cc";

442 case PG_U_FORMAT:

443 return "Cf";

444 case PG_U_PRIVATE_USE:

445 return "Co";

446 case PG_U_SURROGATE:

447 return "Cs";

448 case PG_U_DASH_PUNCTUATION:

449 return "Pd";

450 case PG_U_OPEN_PUNCTUATION:

451 return "Ps";

452 case PG_U_CLOSE_PUNCTUATION:

453 return "Pe";

454 case PG_U_CONNECTOR_PUNCTUATION:

455 return "Pc";

456 case PG_U_OTHER_PUNCTUATION:

457 return "Po";

458 case PG_U_MATH_SYMBOL:

459 return "Sm";

460 case PG_U_CURRENCY_SYMBOL:

461 return "Sc";

462 case PG_U_MODIFIER_SYMBOL:

463 return "Sk";

464 case PG_U_OTHER_SYMBOL:

465 return "So";

466 case PG_U_INITIAL_PUNCTUATION:

467 return "Pi";

468 case PG_U_FINAL_PUNCTUATION:

469 return "Pf";

470 }

471

472 Assert(false);

473 return "??"; /* keep compiler quiet */

474}

PG_U_CONNECTOR_PUNCTUATION

@ PG_U_CONNECTOR_PUNCTUATION

Definition: unicode_category.h:54

PG_U_OTHER_SYMBOL

@ PG_U_OTHER_SYMBOL

Definition: unicode_category.h:59

PG_U_DASH_PUNCTUATION

@ PG_U_DASH_PUNCTUATION

Definition: unicode_category.h:51

PG_U_UPPERCASE_LETTER

@ PG_U_UPPERCASE_LETTER

Definition: unicode_category.h:33

PG_U_CLOSE_PUNCTUATION

@ PG_U_CLOSE_PUNCTUATION

Definition: unicode_category.h:53

PG_U_NONSPACING_MARK

@ PG_U_NONSPACING_MARK

Definition: unicode_category.h:38

PG_U_INITIAL_PUNCTUATION

@ PG_U_INITIAL_PUNCTUATION

Definition: unicode_category.h:60

PG_U_CURRENCY_SYMBOL

@ PG_U_CURRENCY_SYMBOL

Definition: unicode_category.h:57

PG_U_LETTER_NUMBER

@ PG_U_LETTER_NUMBER

Definition: unicode_category.h:42

PG_U_MODIFIER_SYMBOL

@ PG_U_MODIFIER_SYMBOL

Definition: unicode_category.h:58

PG_U_OPEN_PUNCTUATION

@ PG_U_OPEN_PUNCTUATION

Definition: unicode_category.h:52

PG_U_FORMAT

@ PG_U_FORMAT

Definition: unicode_category.h:48

PG_U_PRIVATE_USE

@ PG_U_PRIVATE_USE

Definition: unicode_category.h:49

PG_U_OTHER_LETTER

@ PG_U_OTHER_LETTER

Definition: unicode_category.h:37

PG_U_PARAGRAPH_SEPARATOR

@ PG_U_PARAGRAPH_SEPARATOR

Definition: unicode_category.h:46

PG_U_SPACING_MARK

@ PG_U_SPACING_MARK

Definition: unicode_category.h:40

PG_U_TITLECASE_LETTER

@ PG_U_TITLECASE_LETTER

Definition: unicode_category.h:35

PG_U_OTHER_NUMBER

@ PG_U_OTHER_NUMBER

Definition: unicode_category.h:43

PG_U_MATH_SYMBOL

@ PG_U_MATH_SYMBOL

Definition: unicode_category.h:56

PG_U_LOWERCASE_LETTER

@ PG_U_LOWERCASE_LETTER

Definition: unicode_category.h:34

PG_U_LINE_SEPARATOR

@ PG_U_LINE_SEPARATOR

Definition: unicode_category.h:45

PG_U_SURROGATE

@ PG_U_SURROGATE

Definition: unicode_category.h:50

PG_U_FINAL_PUNCTUATION

@ PG_U_FINAL_PUNCTUATION

Definition: unicode_category.h:61

PG_U_MODIFIER_LETTER

@ PG_U_MODIFIER_LETTER

Definition: unicode_category.h:36

PG_U_OTHER_PUNCTUATION

@ PG_U_OTHER_PUNCTUATION

Definition: unicode_category.h:55

PG_U_ENCLOSING_MARK

@ PG_U_ENCLOSING_MARK

Definition: unicode_category.h:39

References Assert(), PG_U_CLOSE_PUNCTUATION, PG_U_CONNECTOR_PUNCTUATION, PG_U_CONTROL, PG_U_CURRENCY_SYMBOL, PG_U_DASH_PUNCTUATION, PG_U_DECIMAL_NUMBER, PG_U_ENCLOSING_MARK, PG_U_FINAL_PUNCTUATION, PG_U_FORMAT, PG_U_INITIAL_PUNCTUATION, PG_U_LETTER_NUMBER, PG_U_LINE_SEPARATOR, PG_U_LOWERCASE_LETTER, PG_U_MATH_SYMBOL, PG_U_MODIFIER_LETTER, PG_U_MODIFIER_SYMBOL, PG_U_NONSPACING_MARK, PG_U_OPEN_PUNCTUATION, PG_U_OTHER_LETTER, PG_U_OTHER_NUMBER, PG_U_OTHER_PUNCTUATION, PG_U_OTHER_SYMBOL, PG_U_PARAGRAPH_SEPARATOR, PG_U_PRIVATE_USE, PG_U_SPACE_SEPARATOR, PG_U_SPACING_MARK, PG_U_SURROGATE, PG_U_TITLECASE_LETTER, PG_U_UNASSIGNED, and PG_U_UPPERCASE_LETTER.

◆ unicode_category_string()

const char * unicode_category_string ( pg_unicode_category category )

Definition at line 332 of file unicode_category.c.

333{

334 switch (category)

335 {

336 case PG_U_UNASSIGNED:

337 return "Unassigned";

338 case PG_U_UPPERCASE_LETTER:

339 return "Uppercase_Letter";

340 case PG_U_LOWERCASE_LETTER:

341 return "Lowercase_Letter";

342 case PG_U_TITLECASE_LETTER:

343 return "Titlecase_Letter";

344 case PG_U_MODIFIER_LETTER:

345 return "Modifier_Letter";

346 case PG_U_OTHER_LETTER:

347 return "Other_Letter";

348 case PG_U_NONSPACING_MARK:

349 return "Nonspacing_Mark";

350 case PG_U_ENCLOSING_MARK:

351 return "Enclosing_Mark";

352 case PG_U_SPACING_MARK:

353 return "Spacing_Mark";

354 case PG_U_DECIMAL_NUMBER:

355 return "Decimal_Number";

356 case PG_U_LETTER_NUMBER:

357 return "Letter_Number";

358 case PG_U_OTHER_NUMBER:

359 return "Other_Number";

360 case PG_U_SPACE_SEPARATOR:

361 return "Space_Separator";

362 case PG_U_LINE_SEPARATOR:

363 return "Line_Separator";

364 case PG_U_PARAGRAPH_SEPARATOR:

365 return "Paragraph_Separator";

366 case PG_U_CONTROL:

367 return "Control";

368 case PG_U_FORMAT:

369 return "Format";

370 case PG_U_PRIVATE_USE:

371 return "Private_Use";

372 case PG_U_SURROGATE:

373 return "Surrogate";

374 case PG_U_DASH_PUNCTUATION:

375 return "Dash_Punctuation";

376 case PG_U_OPEN_PUNCTUATION:

377 return "Open_Punctuation";

378 case PG_U_CLOSE_PUNCTUATION:

379 return "Close_Punctuation";

380 case PG_U_CONNECTOR_PUNCTUATION:

381 return "Connector_Punctuation";

382 case PG_U_OTHER_PUNCTUATION:

383 return "Other_Punctuation";

384 case PG_U_MATH_SYMBOL:

385 return "Math_Symbol";

386 case PG_U_CURRENCY_SYMBOL:

387 return "Currency_Symbol";

388 case PG_U_MODIFIER_SYMBOL:

389 return "Modifier_Symbol";

390 case PG_U_OTHER_SYMBOL:

391 return "Other_Symbol";

392 case PG_U_INITIAL_PUNCTUATION:

393 return "Initial_Punctuation";

394 case PG_U_FINAL_PUNCTUATION:

395 return "Final_Punctuation";

396 }

397

398 Assert(false);

399 return "Unrecognized"; /* keep compiler quiet */

400}

References Assert(), PG_U_CLOSE_PUNCTUATION, PG_U_CONNECTOR_PUNCTUATION, PG_U_CONTROL, PG_U_CURRENCY_SYMBOL, PG_U_DASH_PUNCTUATION, PG_U_DECIMAL_NUMBER, PG_U_ENCLOSING_MARK, PG_U_FINAL_PUNCTUATION, PG_U_FORMAT, PG_U_INITIAL_PUNCTUATION, PG_U_LETTER_NUMBER, PG_U_LINE_SEPARATOR, PG_U_LOWERCASE_LETTER, PG_U_MATH_SYMBOL, PG_U_MODIFIER_LETTER, PG_U_MODIFIER_SYMBOL, PG_U_NONSPACING_MARK, PG_U_OPEN_PUNCTUATION, PG_U_OTHER_LETTER, PG_U_OTHER_NUMBER, PG_U_OTHER_PUNCTUATION, PG_U_OTHER_SYMBOL, PG_U_PARAGRAPH_SEPARATOR, PG_U_PRIVATE_USE, PG_U_SPACE_SEPARATOR, PG_U_SPACING_MARK, PG_U_SURROGATE, PG_U_TITLECASE_LETTER, PG_U_UNASSIGNED, and PG_U_UPPERCASE_LETTER.