FilesExpand file tree

master

/

unicodectype.c

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

executable file

·

215 lines (164 loc) · 4.64 KB

master

/

unicodectype.c

Copy path

Top

File metadata and controls

• Code
• Blame

executable file

·

215 lines (164 loc) · 4.64 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

/*

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"

#include "unicodeobject.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 NODELTA_MASK 0x100

#define NUMERIC_MASK 0x200

typedef struct {

const Py_UNICODE upper;

const Py_UNICODE lower;

const Py_UNICODE title;

const unsigned char decimal;

const unsigned char digit;

const unsigned short flags;

} _PyUnicode_TypeRecord;

#include "unicodetype_db.h"

static const _PyUnicode_TypeRecord *

gettyperecord(Py_UNICODE code)

{

int index;

#ifdef Py_UNICODE_WIDE

if (code >= 0x110000)

index = 0;

else

#endif

{

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_UNICODE _PyUnicode_ToTitlecase(register Py_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

int delta = ctype->title;

if (ctype->flags & NODELTA_MASK)

return delta;

if (delta >= 32768)

delta -= 65536;

return ch + delta;

}

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

otherwise. */

int _PyUnicode_IsTitlecase(Py_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

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

}

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

this property, -1 otherwise. */

int _PyUnicode_ToDecimalDigit(Py_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

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

}

int _PyUnicode_IsDecimalDigit(Py_UNICODE 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_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

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

}

int _PyUnicode_IsDigit(Py_UNICODE 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_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

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

}

#ifndef WANT_WCTYPE_FUNCTIONS

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

otherwise. */

int _PyUnicode_IsLowercase(Py_UNICODE 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_UNICODE 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_UNICODE _PyUnicode_ToUppercase(Py_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

int delta = ctype->upper;

if (ctype->flags & NODELTA_MASK)

return delta;

if (delta >= 32768)

delta -= 65536;

return ch + delta;

}

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

ch if no lowercase mapping is known. */

Py_UNICODE _PyUnicode_ToLowercase(Py_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

int delta = ctype->lower;

if (ctype->flags & NODELTA_MASK)

return delta;

if (delta >= 32768)

delta -= 65536;

return ch + delta;

}

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

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

int _PyUnicode_IsAlpha(Py_UNICODE ch)

{

const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);

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

}

#else

/* Export the interfaces using the wchar_t type for portability

reasons: */

int _PyUnicode_IsLowercase(Py_UNICODE ch)

{

return iswlower(ch);

}

int _PyUnicode_IsUppercase(Py_UNICODE ch)

{

return iswupper(ch);

}

Py_UNICODE _PyUnicode_ToLowercase(Py_UNICODE ch)

{

return towlower(ch);

}

Py_UNICODE _PyUnicode_ToUppercase(Py_UNICODE ch)

{

return towupper(ch);

}

int _PyUnicode_IsAlpha(Py_UNICODE ch)

{

return iswalpha(ch);

}

#endif