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
|
/* --- Internal Unicode Format -------------------------------------------- */
/* Py_UNICODE was the native Unicode storage format (code unit) used by
Python and represents a single Unicode element in the Unicode type.
With PEP 393, Py_UNICODE is deprecated and replaced with a
typedef to wchar_t. */
#define PY_UNICODE_TYPE wchar_t
typedef wchar_t Py_UNICODE;
/* Py_UCS4 and Py_UCS2 are typedefs for the respective
unicode representations. */
/* PyPy: the cpyext parser does not understand uint32_t, uint16_t, uint8_t */
typedef unsigned int Py_UCS4;
typedef unsigned short Py_UCS2;
typedef unsigned char Py_UCS1;
/* --- Unicode Type ------------------------------------------------------- */
typedef struct {
/*
SSTATE_NOT_INTERNED (0)
SSTATE_INTERNED_MORTAL (1)
SSTATE_INTERNED_IMMORTAL (2)
If interned != SSTATE_NOT_INTERNED, the two references from the
dictionary to this object are *not* counted in ob_refcnt.
*/
/* no bit fields on PyPy
unsigned int interned:2; */
unsigned char interned;
/* Character size:
- PyUnicode_WCHAR_KIND (0):
* character type = wchar_t (16 or 32 bits, depending on the
platform)
- PyUnicode_1BYTE_KIND (1):
* character type = Py_UCS1 (8 bits, unsigned)
* all characters are in the range U+0000-U+00FF (latin1)
* if ascii is set, all characters are in the range U+0000-U+007F
(ASCII), otherwise at least one character is in the range
U+0080-U+00FF
- PyUnicode_2BYTE_KIND (2):
* character type = Py_UCS2 (16 bits, unsigned)
* all characters are in the range U+0000-U+FFFF (BMP)
* at least one character is in the range U+0100-U+FFFF
- PyUnicode_4BYTE_KIND (4):
* character type = Py_UCS4 (32 bits, unsigned)
* all characters are in the range U+0000-U+10FFFF
* at least one character is in the range U+10000-U+10FFFF
*/
/* no bit fields on PyPy
unsigned int kind:3; */
unsigned char kind;
/* Compact is with respect to the allocation scheme. Compact unicode
objects only require one memory block while non-compact objects use
one block for the PyUnicodeObject struct and another for its data
buffer. */
/* no bit fields on PyPy
unsigned int compact:1; */
unsigned char compact;
/* The string only contains characters in the range U+0000-U+007F (ASCII)
and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
set, use the PyASCIIObject structure. */
/* no bit fields on PyPy
unsigned int ascii:1; */
unsigned char ascii;
/* The ready flag indicates whether the object layout is initialized
completely. This means that this is either a compact object, or
the data pointer is filled out. The bit is redundant, and helps
to minimize the test in PyUnicode_IS_READY(). */
/* no bit fields on PyPy
unsigned int ready:1; */
unsigned char ready;
/* Padding to ensure that PyUnicode_DATA() is always aligned to
4 bytes (see issue #19537 on m68k). */
/* Not on PyPy, since not using bit fields */
/*unsigned int padding:24; */
} _PyASCIIObject_state_t;
/* ASCII-only strings created through PyUnicode_New use the PyASCIIObject
structure. state.ascii and state.compact are set, and the data
immediately follow the structure. utf8_length and wstr_length can be found
in the length field; the utf8 pointer is equal to the data pointer. */
typedef struct {
/* There are 4 forms of Unicode strings:
- compact ascii:
* structure = PyASCIIObject
* test: PyUnicode_IS_COMPACT_ASCII(op)
* kind = PyUnicode_1BYTE_KIND
* compact = 1
* ascii = 1
* ready = 1
* (length is the length of the utf8 and wstr strings)
* (data starts just after the structure)
* (since ASCII is decoded from UTF-8, the utf8 string are the data)
- compact:
* structure = PyCompactUnicodeObject
* test: PyUnicode_IS_COMPACT(op) && !PyUnicode_IS_ASCII(op)
* kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
PyUnicode_4BYTE_KIND
* compact = 1
* ready = 1
* ascii = 0
* utf8 is not shared with data
* utf8_length = 0 if utf8 is NULL
* wstr is shared with data and wstr_length=length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
* wstr_length = 0 if wstr is NULL
* (data starts just after the structure)
- legacy string, not ready:
* structure = PyUnicodeObject
* test: kind == PyUnicode_WCHAR_KIND
* length = 0 (use wstr_length)
* hash = -1
* kind = PyUnicode_WCHAR_KIND
* compact = 0
* ascii = 0
* ready = 0
* interned = SSTATE_NOT_INTERNED
* wstr is not NULL
* data.any is NULL
* utf8 is NULL
* utf8_length = 0
- legacy string, ready:
* structure = PyUnicodeObject structure
* test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
* kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
PyUnicode_4BYTE_KIND
* compact = 0
* ready = 1
* data.any is not NULL
* utf8 is shared and utf8_length = length with data.any if ascii = 1
* utf8_length = 0 if utf8 is NULL
* wstr is shared with data.any and wstr_length = length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
* wstr_length = 0 if wstr is NULL
Compact strings use only one memory block (structure + characters),
whereas legacy strings use one block for the structure and one block
for characters.
Legacy strings are created by PyUnicode_FromUnicode() and
PyUnicode_FromStringAndSize(NULL, size) functions. They become ready
when PyUnicode_READY() is called.
See also _PyUnicode_CheckConsistency().
*/
PyObject_HEAD
Py_ssize_t length; /* Number of code points in the string */
Py_hash_t hash; /* Hash value; -1 if not set */
_PyASCIIObject_state_t state;
wchar_t *wstr; /* wchar_t representation (null-terminated) */
} PyASCIIObject;
/* Non-ASCII strings allocated through PyUnicode_New use the
PyCompactUnicodeObject structure. state.compact is set, and the data
immediately follow the structure. */
typedef struct {
PyASCIIObject _base;
Py_ssize_t utf8_length; /* Number of bytes in utf8, excluding the
* terminating \0. */
char *utf8; /* UTF-8 representation (null-terminated) */
Py_ssize_t wstr_length; /* Number of code points in wstr, possible
* surrogates count as two code points. */
} PyCompactUnicodeObject;
/* Strings allocated through PyUnicode_FromUnicode(NULL, len) use the
PyUnicodeObject structure. The actual string data is initially in the wstr
block, and copied into the data block using _PyUnicode_Ready. */
typedef struct {
PyCompactUnicodeObject _base;
/*
union {
void *any;
Py_UCS1 *latin1;
Py_UCS2 *ucs2;
Py_UCS4 *ucs4;
} */ void * data; /* Canonical, smallest-form Unicode buffer */
} PyUnicodeObject;
/* --- Flexible String Representation Helper Macros (PEP 393) -------------- */
/* Values for PyASCIIObject.state: */
/* Interning state. */
#define SSTATE_NOT_INTERNED 0
#define SSTATE_INTERNED_MORTAL 1
#define SSTATE_INTERNED_IMMORTAL 2
/* --- Constants ---------------------------------------------------------- */
/* This Unicode character will be used as replacement character during
decoding if the errors argument is set to "replace". Note: the
Unicode character U+FFFD is the official REPLACEMENT CHARACTER in
Unicode 3.0. */
#define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UCS4) 0xFFFD)
|
