Mercurial > cpython-lru_cache-weakref

annotate Modules/unicodedata.c @ 16798:258dcafe2d0b legacy-trunk

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Gustavo Niemeyer <niemeyer@conectiva.com>: Fixed recno support (keys are integers rather than strings). Work around DB bug that cause stdin to be closed by rnopen() when the DB file needed to exist but did not (no longer segfaults). This closes SF tracker patch #403445. Also wrapped some long lines and added whitespace around operators -- FLD.
author Fred Drake <fdrake@acm.org>
date Tue, 27 Feb 2001 18:56:46 +0000
parents e9fcb46c1f2c
children 0b4c57a25977
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
1 /* ------------------------------------------------------------------------
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
2
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
3 unicodedata -- Provides access to the Unicode 3.0 data base.
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
4
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
5 Data was extracted from the Unicode 3.0 UnicodeData.txt file.
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
6
14835
96d31a143857 unicode database compression, step 2:
Fredrik Lundh <fredrik@pythonware.com>
parents: 14818
diff changeset
7 Written by Marc-Andre Lemburg (mal@lemburg.com).
96d31a143857 unicode database compression, step 2:
Fredrik Lundh <fredrik@pythonware.com>
parents: 14818
diff changeset
8 Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
9
14835
96d31a143857 unicode database compression, step 2:
Fredrik Lundh <fredrik@pythonware.com>
parents: 14818
diff changeset
10 Copyright (c) Corporation for National Research Initiatives.
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
11
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
12 ------------------------------------------------------------------------ */
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
13
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
14 #include "Python.h"
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
15 #include "ucnhash.h"
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
16
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
17 /* character properties */
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
18
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
19 typedef struct {
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
20 const unsigned char category; /* index into
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
21 _PyUnicode_CategoryNames */
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
22 const unsigned char combining; /* combining class value 0 - 255 */
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
23 const unsigned char bidirectional; /* index into
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
24 _PyUnicode_BidirectionalNames */
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
25 const unsigned char mirrored; /* true if mirrored in bidir mode */
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
26 } _PyUnicode_DatabaseRecord;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
27
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
28 /* data file generated by Tools/unicode/makeunicodedata.py */
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
29 #include "unicodedata_db.h"
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
30
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
31 static const _PyUnicode_DatabaseRecord*
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
32 _getrecord(PyUnicodeObject* v)
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
33 {
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
34 int code;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
35 int index;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
36
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
37 code = (int) *PyUnicode_AS_UNICODE(v);
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
38
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
39 if (code < 0 || code >= 65536)
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
40 index = 0;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
41 else {
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
42 index = index1[(code>>SHIFT)];
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
43 index = index2[(index<<SHIFT)+(code&((1<<SHIFT)-1))];
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
44 }
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
45
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
46 return &_PyUnicode_Database_Records[index];
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
47 }
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
48
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
49 /* --- Module API --------------------------------------------------------- */
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
50
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
51 static PyObject *
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
52 unicodedata_decimal(PyObject *self, PyObject *args)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
53 {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
54 PyUnicodeObject *v;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
55 PyObject *defobj = NULL;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
56 long rc;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
57
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
58 if (!PyArg_ParseTuple(args, "O!|O:decimal", &PyUnicode_Type, &v, &defobj))
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
59 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
60 if (PyUnicode_GET_SIZE(v) != 1) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
61 PyErr_SetString(PyExc_TypeError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
62 "need a single Unicode character as parameter");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
63 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
64 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
65 rc = Py_UNICODE_TODECIMAL(*PyUnicode_AS_UNICODE(v));
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
66 if (rc < 0) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
67 if (defobj == NULL) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
68 PyErr_SetString(PyExc_ValueError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
69 "not a decimal");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
70 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
71 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
72 else {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
73 Py_INCREF(defobj);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
74 return defobj;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
75 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
76 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
77 return PyInt_FromLong(rc);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
78 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
79
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
80 static PyObject *
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
81 unicodedata_digit(PyObject *self, PyObject *args)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
82 {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
83 PyUnicodeObject *v;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
84 PyObject *defobj = NULL;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
85 long rc;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
86
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
87 if (!PyArg_ParseTuple(args, "O!|O:digit", &PyUnicode_Type, &v, &defobj))
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
88 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
89 if (PyUnicode_GET_SIZE(v) != 1) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
90 PyErr_SetString(PyExc_TypeError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
91 "need a single Unicode character as parameter");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
92 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
93 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
94 rc = Py_UNICODE_TODIGIT(*PyUnicode_AS_UNICODE(v));
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
95 if (rc < 0) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
96 if (defobj == NULL) {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
97 PyErr_SetString(PyExc_ValueError, "not a digit");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
98 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
99 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
100 else {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
101 Py_INCREF(defobj);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
102 return defobj;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
103 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
104 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
105 return PyInt_FromLong(rc);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
106 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
107
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
108 static PyObject *
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
109 unicodedata_numeric(PyObject *self, PyObject *args)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
110 {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
111 PyUnicodeObject *v;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
112 PyObject *defobj = NULL;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
113 double rc;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
114
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
115 if (!PyArg_ParseTuple(args, "O!|O:numeric", &PyUnicode_Type, &v, &defobj))
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
116 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
117 if (PyUnicode_GET_SIZE(v) != 1) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
118 PyErr_SetString(PyExc_TypeError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
119 "need a single Unicode character as parameter");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
120 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
121 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
122 rc = Py_UNICODE_TONUMERIC(*PyUnicode_AS_UNICODE(v));
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
123 if (rc < 0) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
124 if (defobj == NULL) {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
125 PyErr_SetString(PyExc_ValueError, "not a numeric character");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
126 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
127 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
128 else {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
129 Py_INCREF(defobj);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
130 return defobj;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
131 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
132 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
133 return PyFloat_FromDouble(rc);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
134 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
135
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
136 static PyObject *
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
137 unicodedata_category(PyObject *self, PyObject *args)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
138 {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
139 PyUnicodeObject *v;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
140 int index;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
141
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
142 if (!PyArg_ParseTuple(args, "O!:category",
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
143 &PyUnicode_Type, &v))
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
144 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
145 if (PyUnicode_GET_SIZE(v) != 1) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
146 PyErr_SetString(PyExc_TypeError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
147 "need a single Unicode character as parameter");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
148 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
149 }
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
150 index = (int) _getrecord(v)->category;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
151 return PyString_FromString(_PyUnicode_CategoryNames[index]);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
152 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
153
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
154 static PyObject *
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
155 unicodedata_bidirectional(PyObject *self, PyObject *args)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
156 {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
157 PyUnicodeObject *v;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
158 int index;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
159
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
160 if (!PyArg_ParseTuple(args, "O!:bidirectional",
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
161 &PyUnicode_Type, &v))
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
162 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
163 if (PyUnicode_GET_SIZE(v) != 1) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
164 PyErr_SetString(PyExc_TypeError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
165 "need a single Unicode character as parameter");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
166 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
167 }
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
168 index = (int) _getrecord(v)->bidirectional;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
169 return PyString_FromString(_PyUnicode_BidirectionalNames[index]);
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
170 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
171
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
172 static PyObject *
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
173 unicodedata_combining(PyObject *self, PyObject *args)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
174 {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
175 PyUnicodeObject *v;
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
176
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
177 if (!PyArg_ParseTuple(args, "O!:combining",
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
178 &PyUnicode_Type, &v))
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
179 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
180 if (PyUnicode_GET_SIZE(v) != 1) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
181 PyErr_SetString(PyExc_TypeError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
182 "need a single Unicode character as parameter");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
183 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
184 }
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
185 return PyInt_FromLong((int) _getrecord(v)->combining);
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
186 }
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
187
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
188 static PyObject *
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
189 unicodedata_mirrored(PyObject *self, PyObject *args)
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
190 {
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
191 PyUnicodeObject *v;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
192
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
193 if (!PyArg_ParseTuple(args, "O!:mirrored",
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
194 &PyUnicode_Type, &v))
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
195 return NULL;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
196 if (PyUnicode_GET_SIZE(v) != 1) {
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
197 PyErr_SetString(PyExc_TypeError,
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
198 "need a single Unicode character as parameter");
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
199 return NULL;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
200 }
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
201 return PyInt_FromLong((int) _getrecord(v)->mirrored);
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
202 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
203
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
204 static PyObject *
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
205 unicodedata_decomposition(PyObject *self, PyObject *args)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
206 {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
207 PyUnicodeObject *v;
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
208 char decomp[256];
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
209 int code, index, count, i;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
210
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
211 if (!PyArg_ParseTuple(args, "O!:decomposition",
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
212 &PyUnicode_Type, &v))
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
213 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
214 if (PyUnicode_GET_SIZE(v) != 1) {
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
215 PyErr_SetString(PyExc_TypeError,
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
216 "need a single Unicode character as parameter");
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
217 return NULL;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
218 }
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
219
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
220 code = (int) *PyUnicode_AS_UNICODE(v);
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
221
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
222 if (code < 0 || code >= 65536)
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
223 index = 0;
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
224 else {
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
225 index = decomp_index1[(code>>DECOMP_SHIFT)];
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
226 index = decomp_index2[(index<<DECOMP_SHIFT)+
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
227 (code&((1<<DECOMP_SHIFT)-1))];
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
228 }
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
229
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
230 /* high byte is of hex bytes (usually one or two), low byte
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
231 is prefix code (from*/
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
232 count = decomp_data[index] >> 8;
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
233
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
234 /* XXX: could allocate the PyString up front instead
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
235 (strlen(prefix) + 5 * count + 1 bytes) */
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
236
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
237 /* copy prefix */
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
238 i = strlen(decomp_prefix[decomp_data[index] & 255]);
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
239 memcpy(decomp, decomp_prefix[decomp_data[index] & 255], i);
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
240
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
241 while (count-- > 0) {
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
242 if (i)
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
243 decomp[i++] = ' ';
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
244 sprintf(decomp + i, "%04X", decomp_data[++index]);
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
245 i += strlen(decomp + i);
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
246 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
247
16090
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
248 decomp[i] = '\0';
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
249
8ac40d48a581 compress unicode decomposition tables (this saves another 55k)
Fredrik Lundh <fredrik@pythonware.com>
parents: 14835
diff changeset
250 return PyString_FromString(decomp);
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
251 }
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
252
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
253 /* -------------------------------------------------------------------- */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
254 /* unicode character name tables */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
255
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
256 /* data file generated by Tools/unicode/makeunicodedata.py */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
257 #include "unicodename_db.h"
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
258
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
259 /* -------------------------------------------------------------------- */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
260 /* database code (cut and pasted from the unidb package) */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
261
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
262 static unsigned long
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
263 _gethash(const char *s, int len, int scale)
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
264 {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
265 int i;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
266 unsigned long h = 0;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
267 unsigned long ix;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
268 for (i = 0; i < len; i++) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
269 h = (h * scale) + (unsigned char) toupper(s[i]);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
270 ix = h & 0xff000000;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
271 if (ix)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
272 h = (h ^ ((ix>>24) & 0xff)) & 0x00ffffff;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
273 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
274 return h;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
275 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
276
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
277 static int
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
278 _getname(Py_UCS4 code, char* buffer, int buflen)
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
279 {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
280 int offset;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
281 int i;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
282 int word;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
283 unsigned char* w;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
284
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
285 if (code < 0 || code >= 65536)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
286 return 0;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
287
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
288 /* get offset into phrasebook */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
289 offset = phrasebook_offset1[(code>>phrasebook_shift)];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
290 offset = phrasebook_offset2[(offset<<phrasebook_shift) +
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
291 (code&((1<<phrasebook_shift)-1))];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
292 if (!offset)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
293 return 0;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
294
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
295 i = 0;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
296
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
297 for (;;) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
298 /* get word index */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
299 word = phrasebook[offset] - phrasebook_short;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
300 if (word >= 0) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
301 word = (word << 8) + phrasebook[offset+1];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
302 offset += 2;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
303 } else
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
304 word = phrasebook[offset++];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
305 if (i) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
306 if (i > buflen)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
307 return 0; /* buffer overflow */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
308 buffer[i++] = ' ';
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
309 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
310 /* copy word string from lexicon. the last character in the
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
311 word has bit 7 set. the last word in a string ends with
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
312 0x80 */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
313 w = lexicon + lexicon_offset[word];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
314 while (*w < 128) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
315 if (i >= buflen)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
316 return 0; /* buffer overflow */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
317 buffer[i++] = *w++;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
318 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
319 if (i >= buflen)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
320 return 0; /* buffer overflow */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
321 buffer[i++] = *w & 127;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
322 if (*w == 128)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
323 break; /* end of word */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
324 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
325
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
326 return 1;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
327 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
328
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
329 static int
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
330 _cmpname(int code, const char* name, int namelen)
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
331 {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
332 /* check if code corresponds to the given name */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
333 int i;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
334 char buffer[NAME_MAXLEN];
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
335 if (!_getname(code, buffer, sizeof(buffer)))
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
336 return 0;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
337 for (i = 0; i < namelen; i++) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
338 if (toupper(name[i]) != buffer[i])
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
339 return 0;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
340 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
341 return buffer[namelen] == '\0';
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
342 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
343
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
344 static int
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
345 _getcode(const char* name, int namelen, Py_UCS4* code)
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
346 {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
347 unsigned int h, v;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
348 unsigned int mask = code_size-1;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
349 unsigned int i, incr;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
350
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
351 /* the following is the same as python's dictionary lookup, with
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
352 only minor changes. see the makeunicodedata script for more
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
353 details */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
354
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
355 h = (unsigned int) _gethash(name, namelen, code_magic);
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
356 i = (~h) & mask;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
357 v = code_hash[i];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
358 if (!v)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
359 return 0;
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
360 if (_cmpname(v, name, namelen)) {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
361 *code = v;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
362 return 1;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
363 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
364 incr = (h ^ (h >> 3)) & mask;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
365 if (!incr)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
366 incr = mask;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
367 for (;;) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
368 i = (i + incr) & mask;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
369 v = code_hash[i];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
370 if (!v)
16662
89c1ccef5ce8 stupid typo (for some reason, this only caused problems on OpenVMS).
Fredrik Lundh <fredrik@pythonware.com>
parents: 16200
diff changeset
371 return 0;
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
372 if (_cmpname(v, name, namelen)) {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
373 *code = v;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
374 return 1;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
375 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
376 incr = incr << 1;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
377 if (incr > mask)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
378 incr = incr ^ code_poly;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
379 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
380 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
381
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
382 static const _PyUnicode_Name_CAPI hashAPI =
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
383 {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
384 sizeof(_PyUnicode_Name_CAPI),
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
385 _getname,
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
386 _getcode
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
387 };
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
388
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
389 /* -------------------------------------------------------------------- */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
390 /* Python bindings */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
391
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
392 static PyObject *
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
393 unicodedata_name(PyObject* self, PyObject* args)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
394 {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
395 char name[NAME_MAXLEN];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
396
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
397 PyUnicodeObject* v;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
398 PyObject* defobj = NULL;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
399 if (!PyArg_ParseTuple(args, "O!|O:name", &PyUnicode_Type, &v, &defobj))
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
400 return NULL;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
401
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
402 if (PyUnicode_GET_SIZE(v) != 1) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
403 PyErr_SetString(PyExc_TypeError,
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
404 "need a single Unicode character as parameter");
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
405 return NULL;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
406 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
407
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
408 if (!_getname((Py_UCS4) *PyUnicode_AS_UNICODE(v),
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
409 name, sizeof(name))) {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
410 if (defobj == NULL) {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
411 PyErr_SetString(PyExc_ValueError, "no such name");
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
412 return NULL;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
413 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
414 else {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
415 Py_INCREF(defobj);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
416 return defobj;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
417 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
418 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
419
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
420 return Py_BuildValue("s", name);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
421 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
422
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
423 static PyObject *
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
424 unicodedata_lookup(PyObject* self, PyObject* args)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
425 {
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
426 Py_UCS4 code;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
427 Py_UNICODE str[1];
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
428
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
429 char* name;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
430 int namelen;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
431 if (!PyArg_ParseTuple(args, "s#:lookup", &name, &namelen))
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
432 return NULL;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
433
16666
e9fcb46c1f2c renamed internal functions to avoid name clashes under OpenVMS
Fredrik Lundh <fredrik@pythonware.com>
parents: 16662
diff changeset
434 if (!_getcode(name, namelen, &code)) {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
435 PyErr_SetString(PyExc_KeyError, "undefined character name");
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
436 return NULL;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
437 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
438
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
439 str[0] = (Py_UNICODE) code;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
440 return PyUnicode_FromUnicode(str, 1);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
441 }
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
442
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
443 /* XXX Add doc strings. */
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
444
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
445 static PyMethodDef unicodedata_functions[] = {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
446 {"decimal", unicodedata_decimal, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
447 {"digit", unicodedata_digit, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
448 {"numeric", unicodedata_numeric, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
449 {"category", unicodedata_category, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
450 {"bidirectional", unicodedata_bidirectional, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
451 {"combining", unicodedata_combining, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
452 {"mirrored", unicodedata_mirrored, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
453 {"decomposition",unicodedata_decomposition, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
454 {"name", unicodedata_name, METH_VARARGS},
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
455 {"lookup", unicodedata_lookup, METH_VARARGS},
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
456 {NULL, NULL} /* sentinel */
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
457 };
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
458
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
459 static char *unicodedata_docstring = "unicode character database";
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
460
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
461 DL_EXPORT(void)
13651
8a063423e0b7 Bunch of minor ANSIfications: 'void initfunc()' -> 'void initfunc(void)',
Thomas Wouters <thomas@python.org>
parents: 12196
diff changeset
462 initunicodedata(void)
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
463 {
16200
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
464 PyObject *m, *d, *v;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
465
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
466 m = Py_InitModule4(
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
467 "unicodedata", unicodedata_functions,
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
468 unicodedata_docstring, NULL, PYTHON_API_VERSION);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
469 if (!m)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
470 return;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
471
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
472 d = PyModule_GetDict(m);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
473 if (!d)
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
474 return;
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
475
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
476 /* Export C API */
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
477 v = PyCObject_FromVoidPtr((void *) &hashAPI, NULL);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
478 PyDict_SetItemString(d, "ucnhash_CAPI", v);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
479 Py_XDECREF(v);
3484670c37f2 Move uchhash functionality into unicodedata (after the recent
Fredrik Lundh <fredrik@pythonware.com>
parents: 16091
diff changeset
480
11981
d7a4a5ae2dae Module unicodedata -- Provides access to the Unicode 3.0 data base.
Guido van Rossum <guido@python.org>
parents:
diff changeset
481 }