FilesExpand file tree

 master

/

unicodectype.c

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

297 lines (234 loc) · 7.49 KB

 master

/

unicodectype.c

Copy path

Top

File metadata and controls

• Code
• Blame

297 lines (234 loc) · 7.49 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

/*

Unicode character type helpers.

Written by Marc-Andre Lemburg (mal@lemburg.com).

Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com)

Copyright (c) Corporation for National Research Initiatives.

*/

#include "Python.h"

#define ALPHA_MASK 0x01

#define DECIMAL_MASK 0x02

#define DIGIT_MASK 0x04

#define LOWER_MASK 0x08

#define LINEBREAK_MASK 0x10

#define SPACE_MASK 0x20

#define TITLE_MASK 0x40

#define UPPER_MASK 0x80

#define XID_START_MASK 0x100

#define XID_CONTINUE_MASK 0x200

#define PRINTABLE_MASK 0x400

#define NUMERIC_MASK 0x800

#define CASE_IGNORABLE_MASK 0x1000

#define CASED_MASK 0x2000

#define EXTENDED_CASE_MASK 0x4000

typedef struct {

/*

These are either deltas to the character or offsets in

_PyUnicode_ExtendedCase.

*/

const int upper;

const int lower;

const int title;

/* Note if more flag space is needed, decimal and digit could be unified. */

const unsigned char decimal;

const unsigned char digit;

const unsigned short flags;

} _PyUnicode_TypeRecord;

#include "unicodetype_db.h"

static const _PyUnicode_TypeRecord *

gettyperecord(Py_UCS4 code)

{

int index;

if (code >= 0x110000)

index = 0;

else

{

index = index1[(code>>SHIFT)];

index = index2[(index<<SHIFT)+(code&((1<<SHIFT)-1))];

}

return &_PyUnicode_TypeRecords[index];

}

/* Returns the titlecase Unicode characters corresponding to ch or just

ch if no titlecase mapping is known. */

Py_UCS4 _PyUnicode_ToTitlecase(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

if (ctype->flags & EXTENDED_CASE_MASK)

return _PyUnicode_ExtendedCase[ctype->title & 0xFFFF];

return ch + ctype->title;

}

/* Returns 1 for Unicode characters having the category 'Lt', 0

otherwise. */

int _PyUnicode_IsTitlecase(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & TITLE_MASK) != 0;

}

/* Returns 1 for Unicode characters having the XID_Start property, 0

otherwise. */

int _PyUnicode_IsXidStart(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & XID_START_MASK) != 0;

}

/* Returns 1 for Unicode characters having the XID_Continue property,

0 otherwise. */

int _PyUnicode_IsXidContinue(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & XID_CONTINUE_MASK) != 0;

}

/* Returns the integer decimal (0-9) for Unicode characters having

this property, -1 otherwise. */

int _PyUnicode_ToDecimalDigit(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & DECIMAL_MASK) ? ctype->decimal : -1;

}

int _PyUnicode_IsDecimalDigit(Py_UCS4 ch)

{

if (_PyUnicode_ToDecimalDigit(ch) < 0)

return 0;

return 1;

}

/* Returns the integer digit (0-9) for Unicode characters having

this property, -1 otherwise. */

int _PyUnicode_ToDigit(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & DIGIT_MASK) ? ctype->digit : -1;

}

int _PyUnicode_IsDigit(Py_UCS4 ch)

{

if (_PyUnicode_ToDigit(ch) < 0)

return 0;

return 1;

}

/* Returns the numeric value as double for Unicode characters having

this property, -1.0 otherwise. */

int _PyUnicode_IsNumeric(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & NUMERIC_MASK) != 0;

}

/* Returns 1 for Unicode characters to be hex-escaped when repr()ed,

0 otherwise.

All characters except those characters defined in the Unicode character

database as following categories are considered printable.

* Cc (Other, Control)

* Cf (Other, Format)

* Cs (Other, Surrogate)

* Co (Other, Private Use)

* Cn (Other, Not Assigned)

* Zl Separator, Line ('\u2028', LINE SEPARATOR)

* Zp Separator, Paragraph ('\u2029', PARAGRAPH SEPARATOR)

* Zs (Separator, Space) other than ASCII space('\x20').

*/

int _PyUnicode_IsPrintable(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & PRINTABLE_MASK) != 0;

}

/* Returns 1 for Unicode characters having the category 'Ll', 0

otherwise. */

int _PyUnicode_IsLowercase(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & LOWER_MASK) != 0;

}

/* Returns 1 for Unicode characters having the category 'Lu', 0

otherwise. */

int _PyUnicode_IsUppercase(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & UPPER_MASK) != 0;

}

/* Returns the uppercase Unicode characters corresponding to ch or just

ch if no uppercase mapping is known. */

Py_UCS4 _PyUnicode_ToUppercase(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

if (ctype->flags & EXTENDED_CASE_MASK)

return _PyUnicode_ExtendedCase[ctype->upper & 0xFFFF];

return ch + ctype->upper;

}

/* Returns the lowercase Unicode characters corresponding to ch or just

ch if no lowercase mapping is known. */

Py_UCS4 _PyUnicode_ToLowercase(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

if (ctype->flags & EXTENDED_CASE_MASK)

return _PyUnicode_ExtendedCase[ctype->lower & 0xFFFF];

return ch + ctype->lower;

}

int _PyUnicode_ToLowerFull(Py_UCS4 ch, Py_UCS4 *res)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

if (ctype->flags & EXTENDED_CASE_MASK) {

int index = ctype->lower & 0xFFFF;

int n = ctype->lower >> 24;

int i;

for (i = 0; i < n; i++)

res[i] = _PyUnicode_ExtendedCase[index + i];

return n;

}

res[0] = ch + ctype->lower;

return 1;

}

int _PyUnicode_ToTitleFull(Py_UCS4 ch, Py_UCS4 *res)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

if (ctype->flags & EXTENDED_CASE_MASK) {

int index = ctype->title & 0xFFFF;

int n = ctype->title >> 24;

int i;

for (i = 0; i < n; i++)

res[i] = _PyUnicode_ExtendedCase[index + i];

return n;

}

res[0] = ch + ctype->title;

return 1;

}

int _PyUnicode_ToUpperFull(Py_UCS4 ch, Py_UCS4 *res)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

if (ctype->flags & EXTENDED_CASE_MASK) {

int index = ctype->upper & 0xFFFF;

int n = ctype->upper >> 24;

int i;

for (i = 0; i < n; i++)

res[i] = _PyUnicode_ExtendedCase[index + i];

return n;

}

res[0] = ch + ctype->upper;

return 1;

}

int _PyUnicode_ToFoldedFull(Py_UCS4 ch, Py_UCS4 *res)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

if (ctype->flags & EXTENDED_CASE_MASK && (ctype->lower >> 20) & 7) {

int index = (ctype->lower & 0xFFFF) + (ctype->lower >> 24);

int n = (ctype->lower >> 20) & 7;

int i;

for (i = 0; i < n; i++)

res[i] = _PyUnicode_ExtendedCase[index + i];

return n;

}

return _PyUnicode_ToLowerFull(ch, res);

}

int _PyUnicode_IsCased(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & CASED_MASK) != 0;

}

int _PyUnicode_IsCaseIgnorable(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & CASE_IGNORABLE_MASK) != 0;

}

/* Returns 1 for Unicode characters having the category 'Ll', 'Lu', 'Lt',

'Lo' or 'Lm', 0 otherwise. */

int _PyUnicode_IsAlpha(Py_UCS4 ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

return (ctype->flags & ALPHA_MASK) != 0;

}