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 name tables */
/* rewritten for Python 2.1 by Fredrik Lundh (fredrik@pythonware.com) */
#include "Python.h"
#include "ucnhash.h"
/* data file generated by Tools/unicode/makeunicodedata.py */
#include "unicodename_db.h"
/* -------------------------------------------------------------------- */
/* database code (cut and pasted from the unidb package) */
static unsigned long
gethash(const char *s, int len)
{
int i;
unsigned long h = 0;
unsigned long ix;
for (i = 0; i < len; i++) {
/* magic value 47 was chosen to minimize the number
of collisions for the uninames dataset. see the
makeunicodedata script for more background */
h = (h * 47) + (unsigned char) toupper(s[i]);
ix = h & 0xff000000;
if (ix)
h = (h ^ ((ix>>24) & 0xff)) & 0x00ffffff;
}
return h;
}
static int
getname(Py_UCS4 code, char* buffer, int buflen)
{
int offset;
int i;
int word;
unsigned char* w;
if (code < 0 || code >= 65536)
return 0;
/* get offset into phrasebook */
offset = phrasebook_offset1[(code>>SHIFT)];
offset = phrasebook_offset2[(offset<<SHIFT)+(code&((1<<SHIFT)-1))];
if (!offset)
return 0;
i = 0;
for (;;) {
/* get word index */
if (phrasebook[offset] & 128) {
word = phrasebook[offset] & 127;
offset++;
} else {
word = (phrasebook[offset]<<8) + phrasebook[offset+1];
offset+=2;
}
if (i) {
if (i > buflen)
return 0; /* buffer overflow */
buffer[i++] = ' ';
}
/* copy word string from lexicon. the last character in the
word has bit 7 set. the last word in a string ends with
0x80 */
w = lexicon + lexicon_offset[word];
while (*w < 128) {
if (i >= buflen)
return 0; /* buffer overflow */
buffer[i++] = *w++;
}
if (i >= buflen)
return 0; /* buffer overflow */
buffer[i++] = *w & 127;
if (*w == 128)
break; /* end of word */
}
return 1;
}
static int
cmpname(int code, const char* name, int namelen)
{
/* check if code corresponds to the given name */
int i;
char buffer[NAME_MAXLEN];
if (!getname(code, buffer, sizeof(buffer)))
return 0;
for (i = 0; i < namelen; i++) {
if (toupper(name[i]) != buffer[i])
return 0;
}
return buffer[namelen] == '\0';
}
static int
getcode(const char* name, int namelen, Py_UCS4* code)
{
unsigned int h, v;
unsigned int mask = CODE_SIZE-1;
unsigned int i, incr;
/* the following is the same as python's dictionary lookup, with
only minor changes. see the makeunicodedata script for more
details */
h = (unsigned int) gethash(name, namelen);
i = (~h) & mask;
v = code_hash[i];
if (!v)
return 0;
if (cmpname(v, name, namelen)) {
*code = v;
return 1;
}
incr = (h ^ (h >> 3)) & mask;
if (!incr)
incr = mask;
for (;;) {
i = (i + incr) & mask;
v = code_hash[i];
if (!v)
return -1;
if (cmpname(v, name, namelen)) {
*code = v;
return 1;
}
incr = incr << 1;
if (incr > mask)
incr = incr ^ CODE_POLY;
}
}
static const _PyUnicode_Name_CAPI hashAPI =
{
sizeof(_PyUnicode_Name_CAPI),
getname,
getcode
};
/* -------------------------------------------------------------------- */
/* Python bindings */
static PyObject *
ucnhash_getname(PyObject* self, PyObject* args)
{
char name[NAME_MAXLEN];
int code;
if (!PyArg_ParseTuple(args, "i", &code))
return NULL;
if (!getname((Py_UCS4) code, name, sizeof(name))) {
PyErr_SetString(PyExc_ValueError, "undefined character code");
return NULL;
}
return Py_BuildValue("s", name);
}
static PyObject *
ucnhash_getcode(PyObject* self, PyObject* args)
{
Py_UCS4 code;
char* name;
int namelen;
if (!PyArg_ParseTuple(args, "s#", &name, &namelen))
return NULL;
if (!getcode(name, namelen, &code)) {
PyErr_SetString(PyExc_ValueError, "undefined character name");
return NULL;
}
return Py_BuildValue("i", code);
}
static
PyMethodDef ucnhash_methods[] =
{
{"getname", ucnhash_getname, 1},
{"getcode", ucnhash_getcode, 1},
{NULL, NULL},
};
static char *ucnhash_docstring = "ucnhash hash function module";
/* Create PyMethodObjects and register them in the module's dict */
DL_EXPORT(void)
initucnhash(void)
{
PyObject *m, *d, *v;
m = Py_InitModule4(
"ucnhash", /* Module name */
ucnhash_methods, /* Method list */
ucnhash_docstring, /* Module doc-string */
(PyObject *)NULL, /* always pass this as *self */
PYTHON_API_VERSION); /* API Version */
if (!m)
return;
d = PyModule_GetDict(m);
if (!d)
return;
/* Export C API */
v = PyCObject_FromVoidPtr((void *) &hashAPI, NULL);
PyDict_SetItemString(d, "Unicode_Names_CAPI", v);
Py_XDECREF(v);
}
|
