summaryrefslogtreecommitdiffstats
path: root/Python/codecs.c
blob: 27331ab66b171df122c25901708c19aeb8411fcd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
/* ------------------------------------------------------------------------

   Python Codec Registry and support functions

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

(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.

   ------------------------------------------------------------------------ */

#include "Python.h"
#include <ctype.h>
#ifdef HAVE_LIMITS_H
#include <limits.h>
#endif

/* --- Globals ------------------------------------------------------------ */

static PyObject *_PyCodec_SearchPath;
static PyObject *_PyCodec_SearchCache;

/* Flag used for lazy import of the standard encodings package */
static int import_encodings_called = 0;

/* --- Codec Registry ----------------------------------------------------- */

/* Import the standard encodings package which will register the first
   codec search function. 

   This is done in a lazy way so that the Unicode implementation does
   not downgrade startup time of scripts not needing it.

   ImportErrors are silently ignored by this function. Only one try is
   made.

*/

static
int import_encodings() 
{
    PyObject *mod;
    
    import_encodings_called = 1;
    mod = PyImport_ImportModule("encodings");
    if (mod == NULL) {
	if (PyErr_ExceptionMatches(PyExc_ImportError)) {
	    /* Ignore ImportErrors... this is done so that
	       distributions can disable the encodings package. Note
	       that other errors are not masked, e.g. SystemErrors
	       raised to inform the user of an error in the Python
	       configuration are still reported back to the user. */
	    PyErr_Clear();
	    return 0;
	}
	return -1;
    }
    Py_DECREF(mod);
    return 0;
}

int PyCodec_Register(PyObject *search_function)
{
    if (!import_encodings_called) {
	if (import_encodings())
	    goto onError;
    }
    if (search_function == NULL) {
	PyErr_BadArgument();
	goto onError;
    }
    if (!PyCallable_Check(search_function)) {
	PyErr_SetString(PyExc_TypeError,
			"argument must be callable");
	goto onError;
    }
    return PyList_Append(_PyCodec_SearchPath, search_function);

 onError:
    return -1;
}

/* Convert a string to a normalized Python string: all characters are
   converted to lower case, spaces are replaced with underscores. */

static
PyObject *normalizestring(const char *string)
{
    register size_t i;
    size_t len = strlen(string);
    char *p;
    PyObject *v;
    
	if (len > INT_MAX) {
		PyErr_SetString(PyExc_OverflowError, "string is too large");
		return NULL;
	}
	
    v = PyString_FromStringAndSize(NULL, (int)len);
    if (v == NULL)
	return NULL;
    p = PyString_AS_STRING(v);
    for (i = 0; i < len; i++) {
        register char ch = string[i];
        if (ch == ' ')
            ch = '-';
        else
            ch = tolower(ch);
	p[i] = ch;
    }
    return v;
}

/* Lookup the given encoding and return a tuple providing the codec
   facilities.

   The encoding string is looked up converted to all lower-case
   characters. This makes encodings looked up through this mechanism
   effectively case-insensitive.

   If no codec is found, a LookupError is set and NULL returned. 

   As side effect, this tries to load the encodings package, if not
   yet done. This is part of the lazy load strategy for the encodings
   package.

*/

PyObject *_PyCodec_Lookup(const char *encoding)
{
    PyObject *result, *args = NULL, *v;
    int i, len;

    if (encoding == NULL) {
	PyErr_BadArgument();
	goto onError;
    }
    if (_PyCodec_SearchCache == NULL || 
	_PyCodec_SearchPath == NULL) {
	PyErr_SetString(PyExc_SystemError,
			"codec module not properly initialized");
	goto onError;
    }
    if (!import_encodings_called) {
	if (import_encodings())
	    goto onError;
    }

    /* Convert the encoding to a normalized Python string: all
       characters are converted to lower case, spaces and hypens are
       replaced with underscores. */
    v = normalizestring(encoding);
    if (v == NULL)
	goto onError;
    PyString_InternInPlace(&v);

    /* First, try to lookup the name in the registry dictionary */
    result = PyDict_GetItem(_PyCodec_SearchCache, v);
    if (result != NULL) {
	Py_INCREF(result);
	Py_DECREF(v);
	return result;
    }
    
    /* Next, scan the search functions in order of registration */
    args = PyTuple_New(1);
    if (args == NULL)
	goto onError;
    PyTuple_SET_ITEM(args,0,v);

    len = PyList_Size(_PyCodec_SearchPath);
    if (len < 0)
	goto onError;
    if (len == 0) {
	PyErr_SetString(PyExc_LookupError,
			"no codec search functions registered: "
			"can't find encoding");
	goto onError;
    }

    for (i = 0; i < len; i++) {
	PyObject *func;
	
	func = PyList_GetItem(_PyCodec_SearchPath, i);
	if (func == NULL)
	    goto onError;
	result = PyEval_CallObject(func, args);
	if (result == NULL)
	    goto onError;
	if (result == Py_None) {
	    Py_DECREF(result);
	    continue;
	}
	if (!PyTuple_Check(result) || PyTuple_GET_SIZE(result) != 4) {
	    PyErr_SetString(PyExc_TypeError,
			    "codec search functions must return 4-tuples");
	    Py_DECREF(result);
	    goto onError;
	}
	break;
    }
    if (i == len) {
	/* XXX Perhaps we should cache misses too ? */
	PyErr_SetString(PyExc_LookupError,
			"unknown encoding");
	goto onError;
    }

    /* Cache and return the result */
    PyDict_SetItem(_PyCodec_SearchCache, v, result);
    Py_DECREF(args);
    return result;

 onError:
    Py_XDECREF(args);
    return NULL;
}

static
PyObject *args_tuple(PyObject *object,
		     const char *errors)
{
    PyObject *args;
    
    args = PyTuple_New(1 + (errors != NULL));
    if (args == NULL)
	return NULL;
    Py_INCREF(object);
    PyTuple_SET_ITEM(args,0,object);
    if (errors) {
	PyObject *v;
	
	v = PyString_FromString(errors);
	if (v == NULL) {
	    Py_DECREF(args);
	    return NULL;
	}
	PyTuple_SET_ITEM(args, 1, v);
    }
    return args;
}

/* Build a codec by calling factory(stream[,errors]) or just
   factory(errors) depending on whether the given parameters are
   non-NULL. */

static
PyObject *build_stream_codec(PyObject *factory,
			     PyObject *stream,
			     const char *errors)
{
    PyObject *args, *codec;

    args = args_tuple(stream, errors);
    if (args == NULL)
	return NULL;
    
    codec = PyEval_CallObject(factory, args);
    Py_DECREF(args);
    return codec;
}

/* Convenience APIs to query the Codec registry. 
   
   All APIs return a codec object with incremented refcount.
   
 */

PyObject *PyCodec_Encoder(const char *encoding)
{
    PyObject *codecs;
    PyObject *v;

    codecs = _PyCodec_Lookup(encoding);
    if (codecs == NULL)
	goto onError;
    v = PyTuple_GET_ITEM(codecs,0);
    Py_INCREF(v);
    return v;

 onError:
    return NULL;
}

PyObject *PyCodec_Decoder(const char *encoding)
{
    PyObject *codecs;
    PyObject *v;

    codecs = _PyCodec_Lookup(encoding);
    if (codecs == NULL)
	goto onError;
    v = PyTuple_GET_ITEM(codecs,1);
    Py_INCREF(v);
    return v;

 onError:
    return NULL;
}

PyObject *PyCodec_StreamReader(const char *encoding,
			       PyObject *stream,
			       const char *errors)
{
    PyObject *codecs;

    codecs = _PyCodec_Lookup(encoding);
    if (codecs == NULL)
	goto onError;
    return build_stream_codec(PyTuple_GET_ITEM(codecs,2),stream,errors);

 onError:
    return NULL;
}

PyObject *PyCodec_StreamWriter(const char *encoding,
			       PyObject *stream,
			       const char *errors)
{
    PyObject *codecs;

    codecs = _PyCodec_Lookup(encoding);
    if (codecs == NULL)
	goto onError;
    return build_stream_codec(PyTuple_GET_ITEM(codecs,3),stream,errors);

 onError:
    return NULL;
}

/* Encode an object (e.g. an Unicode object) using the given encoding
   and return the resulting encoded object (usually a Python string).

   errors is passed to the encoder factory as argument if non-NULL. */

PyObject *PyCodec_Encode(PyObject *object,
			 const char *encoding,
			 const char *errors)
{
    PyObject *encoder = NULL;
    PyObject *args = NULL, *result;
    PyObject *v;

    encoder = PyCodec_Encoder(encoding);
    if (encoder == NULL)
	goto onError;

    args = args_tuple(object, errors);
    if (args == NULL)
	goto onError;
    
    result = PyEval_CallObject(encoder,args);
    if (result == NULL)
	goto onError;

    if (!PyTuple_Check(result) || 
	PyTuple_GET_SIZE(result) != 2) {
	PyErr_SetString(PyExc_TypeError,
			"encoder must return a tuple (object,integer)");
	goto onError;
    }
    v = PyTuple_GET_ITEM(result,0);
    Py_INCREF(v);
    /* We don't check or use the second (integer) entry. */

    Py_DECREF(args);
    Py_DECREF(encoder);
    Py_DECREF(result);
    return v;
	
 onError:
    Py_XDECREF(args);
    Py_XDECREF(encoder);
    return NULL;
}

/* Decode an object (usually a Python string) using the given encoding
   and return an equivalent object (e.g. an Unicode object).

   errors is passed to the decoder factory as argument if non-NULL. */

PyObject *PyCodec_Decode(PyObject *object,
			 const char *encoding,
			 const char *errors)
{
    PyObject *decoder = NULL;
    PyObject *args = NULL, *result = NULL;
    PyObject *v;

    decoder = PyCodec_Decoder(encoding);
    if (decoder == NULL)
	goto onError;

    args = args_tuple(object, errors);
    if (args == NULL)
	goto onError;
    
    result = PyEval_CallObject(decoder,args);
    if (result == NULL)
	goto onError;
    if (!PyTuple_Check(result) || 
	PyTuple_GET_SIZE(result) != 2) {
	PyErr_SetString(PyExc_TypeError,
			"decoder must return a tuple (object,integer)");
	goto onError;
    }
    v = PyTuple_GET_ITEM(result,0);
    Py_INCREF(v);
    /* We don't check or use the second (integer) entry. */

    Py_DECREF(args);
    Py_DECREF(decoder);
    Py_DECREF(result);
    return v;
	
 onError:
    Py_XDECREF(args);
    Py_XDECREF(decoder);
    Py_XDECREF(result);
    return NULL;
}

void _PyCodecRegistry_Init()
{
    if (_PyCodec_SearchPath == NULL)
	_PyCodec_SearchPath = PyList_New(0);
    if (_PyCodec_SearchCache == NULL)
	_PyCodec_SearchCache = PyDict_New();
    if (_PyCodec_SearchPath == NULL || 
	_PyCodec_SearchCache == NULL)
	Py_FatalError("can't intialize codec registry");
}

void _PyCodecRegistry_Fini()
{
    Py_XDECREF(_PyCodec_SearchPath);
    _PyCodec_SearchPath = NULL;
    Py_XDECREF(_PyCodec_SearchCache);
    _PyCodec_SearchCache = NULL;
}