codecs.py 18 KB
Newer Older
1 2 3 4 5 6 7 8 9
""" codecs -- Python Codec Registry, API and helpers.


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

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

"""#"

10
import struct, types, __builtin__
11 12 13

### Registry and builtin stateless codec functions

14 15
try:
    from _codecs import *
16
except ImportError, why:
17 18
    raise SystemError,\
          'Failed to load the builtin codecs: %s' % why
19

20 21
__all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE",
           "BOM_LE", "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE"]
22

23 24 25 26 27
### Constants

#
# Byte Order Mark (BOM) and its possible values (BOM_BE, BOM_LE)
#
28
BOM = struct.pack('=H', 0xFEFF)
29 30
#
BOM_BE = BOM32_BE = '\376\377'
Tim Peters's avatar
Tim Peters committed
31 32
#       corresponds to Unicode U+FEFF in UTF-16 on big endian
#       platforms == ZERO WIDTH NO-BREAK SPACE
33
BOM_LE = BOM32_LE = '\377\376'
Tim Peters's avatar
Tim Peters committed
34 35
#       corresponds to Unicode U+FFFE in UTF-16 on little endian
#       platforms == defined as being an illegal Unicode character
36 37 38 39 40

#
# 64-bit Byte Order Marks
#
BOM64_BE = '\000\000\376\377'
Tim Peters's avatar
Tim Peters committed
41
#       corresponds to Unicode U+0000FEFF in UCS-4
42
BOM64_LE = '\377\376\000\000'
Tim Peters's avatar
Tim Peters committed
43
#       corresponds to Unicode U+0000FFFE in UCS-4
44 45 46 47 48 49 50 51 52 53 54 55


### Codec base classes (defining the API)

class Codec:

    """ Defines the interface for stateless encoders/decoders.

        The .encode()/.decode() methods may implement different error
        handling schemes by providing the errors argument. These
        string values are defined:

Guido van Rossum's avatar
Guido van Rossum committed
56
         'strict' - raise a ValueError error (or a subclass)
57 58 59 60 61 62
         'ignore' - ignore the character and continue with the next
         'replace' - replace with a suitable replacement character;
                    Python will use the official U+FFFD REPLACEMENT
                    CHARACTER for the builtin Unicode codecs.

    """
63
    def encode(self, input, errors='strict'):
64

65
        """ Encodes the object input and returns a tuple (output
66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
            object, length consumed).

            errors defines the error handling to apply. It defaults to
            'strict' handling.

            The method may not store state in the Codec instance. Use
            StreamCodec for codecs which have to keep state in order to
            make encoding/decoding efficient.

            The encoder must be able to handle zero length input and
            return an empty object of the output object type in this
            situation.

        """
        raise NotImplementedError

82
    def decode(self, input, errors='strict'):
83 84 85 86 87 88 89

        """ Decodes the object input and returns a tuple (output
            object, length consumed).

            input must be an object which provides the bf_getreadbuf
            buffer slot. Python strings, buffer objects and memory
            mapped files are examples of objects providing this slot.
90

91 92 93 94 95 96 97 98 99 100 101
            errors defines the error handling to apply. It defaults to
            'strict' handling.

            The method may not store state in the Codec instance. Use
            StreamCodec for codecs which have to keep state in order to
            make encoding/decoding efficient.

            The decoder must be able to handle zero length input and
            return an empty object of the output object type in this
            situation.

102
        """
103 104 105 106 107 108 109
        raise NotImplementedError

#
# The StreamWriter and StreamReader class provide generic working
# interfaces which can be used to implement new encodings submodules
# very easily. See encodings/utf_8.py for an example on how this is
# done.
110
#
111 112 113

class StreamWriter(Codec):

114
    def __init__(self, stream, errors='strict'):
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132

        """ Creates a StreamWriter instance.

            stream must be a file-like object open for writing
            (binary) data.

            The StreamWriter may implement different error handling
            schemes by providing the errors keyword argument. These
            parameters are defined:

             'strict' - raise a ValueError (or a subclass)
             'ignore' - ignore the character and continue with the next
             'replace'- replace with a suitable replacement character

        """
        self.stream = stream
        self.errors = errors

Guido van Rossum's avatar
Guido van Rossum committed
133
    def write(self, object):
134 135 136

        """ Writes the object's contents encoded to self.stream.
        """
137
        data, consumed = self.encode(object, self.errors)
138 139
        self.stream.write(data)

Guido van Rossum's avatar
Guido van Rossum committed
140 141 142 143 144 145
    def writelines(self, list):

        """ Writes the concatenated list of strings to the stream
            using .write().
        """
        self.write(''.join(list))
146

147 148 149 150 151 152 153 154 155 156 157 158
    def reset(self):

        """ Flushes and resets the codec buffers used for keeping state.

            Calling this method should ensure that the data on the
            output is put into a clean state, that allows appending
            of new fresh data without having to rescan the whole
            stream to recover state.

        """
        pass

159
    def __getattr__(self, name,
160 161 162 163
                    getattr=getattr):

        """ Inherit all other methods from the underlying stream.
        """
164
        return getattr(self.stream, name)
165 166 167 168 169

###

class StreamReader(Codec):

170
    def __init__(self, stream, errors='strict'):
171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188

        """ Creates a StreamReader instance.

            stream must be a file-like object open for reading
            (binary) data.

            The StreamReader may implement different error handling
            schemes by providing the errors keyword argument. These
            parameters are defined:

             'strict' - raise a ValueError (or a subclass)
             'ignore' - ignore the character and continue with the next
             'replace'- replace with a suitable replacement character;

        """
        self.stream = stream
        self.errors = errors

Guido van Rossum's avatar
Guido van Rossum committed
189
    def read(self, size=-1):
190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209

        """ Decodes data from the stream self.stream and returns the
            resulting object.

            size indicates the approximate maximum number of bytes to
            read from the stream for decoding purposes. The decoder
            can modify this setting as appropriate. The default value
            -1 indicates to read and decode as much as possible.  size
            is intended to prevent having to decode huge files in one
            step.

            The method should use a greedy read strategy meaning that
            it should read as much data as is allowed within the
            definition of the encoding and the given size, e.g.  if
            optional encoding endings or state markers are available
            on the stream, these should be read too.

        """
        # Unsliced reading:
        if size < 0:
210
            return self.decode(self.stream.read(), self.errors)[0]
211

212 213 214 215 216 217 218
        # Sliced reading:
        read = self.stream.read
        decode = self.decode
        data = read(size)
        i = 0
        while 1:
            try:
219
                object, decodedbytes = decode(data, self.errors)
220
            except ValueError, why:
221 222 223 224 225 226 227 228 229 230
                # This method is slow but should work under pretty much
                # all conditions; at most 10 tries are made
                i = i + 1
                newdata = read(1)
                if not newdata or i > 10:
                    raise
                data = data + newdata
            else:
                return object

Guido van Rossum's avatar
Guido van Rossum committed
231 232 233 234 235
    def readline(self, size=None):

        """ Read one line from the input stream and return the
            decoded data.

236 237 238 239 240 241 242
            Note: Unlike the .readlines() method, this method inherits
            the line breaking knowledge from the underlying stream's
            .readline() method -- there is currently no support for
            line breaking using the codec decoder due to lack of line
            buffering. Sublcasses should however, if possible, try to
            implement this method using their own knowledge of line
            breaking.
Guido van Rossum's avatar
Guido van Rossum committed
243 244 245

            size, if given, is passed as size argument to the stream's
            .readline() method.
246

Guido van Rossum's avatar
Guido van Rossum committed
247 248 249 250 251
        """
        if size is None:
            line = self.stream.readline()
        else:
            line = self.stream.readline(size)
252
        return self.decode(line, self.errors)[0]
253

Guido van Rossum's avatar
Guido van Rossum committed
254 255 256 257 258 259 260 261

    def readlines(self, sizehint=0):

        """ Read all lines available on the input stream
            and return them as list of lines.

            Line breaks are implemented using the codec's decoder
            method and are included in the list entries.
262

Guido van Rossum's avatar
Guido van Rossum committed
263 264 265 266 267 268 269 270
            sizehint, if given, is passed as size argument to the
            stream's .read() method.

        """
        if sizehint is None:
            data = self.stream.read()
        else:
            data = self.stream.read(sizehint)
271
        return self.decode(data, self.errors)[0].splitlines(1)
272 273 274 275 276 277

    def reset(self):

        """ Resets the codec buffers used for keeping state.

            Note that no stream repositioning should take place.
278
            This method is primarily intended to be able to recover
279 280 281 282 283
            from decoding errors.

        """
        pass

284
    def __getattr__(self, name,
285 286 287 288
                    getattr=getattr):

        """ Inherit all other methods from the underlying stream.
        """
289
        return getattr(self.stream, name)
290 291 292 293 294

###

class StreamReaderWriter:

295 296 297 298
    """ StreamReaderWriter instances allow wrapping streams which
        work in both read and write modes.

        The design is such that one can use the factory functions
299
        returned by the codec.lookup() function to construct the
300 301 302
        instance.

    """
Guido van Rossum's avatar
Guido van Rossum committed
303 304 305
    # Optional attributes set by the file wrappers below
    encoding = 'unknown'

306
    def __init__(self, stream, Reader, Writer, errors='strict'):
307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323

        """ Creates a StreamReaderWriter instance.

            stream must be a Stream-like object.

            Reader, Writer must be factory functions or classes
            providing the StreamReader, StreamWriter interface resp.

            Error handling is done in the same way as defined for the
            StreamWriter/Readers.

        """
        self.stream = stream
        self.reader = Reader(stream, errors)
        self.writer = Writer(stream, errors)
        self.errors = errors

324
    def read(self, size=-1):
325 326 327

        return self.reader.read(size)

Guido van Rossum's avatar
Guido van Rossum committed
328
    def readline(self, size=None):
Guido van Rossum's avatar
Guido van Rossum committed
329 330 331

        return self.reader.readline(size)

Guido van Rossum's avatar
Guido van Rossum committed
332
    def readlines(self, sizehint=None):
Guido van Rossum's avatar
Guido van Rossum committed
333 334 335

        return self.reader.readlines(sizehint)

336
    def write(self, data):
337 338 339

        return self.writer.write(data)

340
    def writelines(self, list):
Guido van Rossum's avatar
Guido van Rossum committed
341 342 343

        return self.writer.writelines(list)

344 345 346 347 348
    def reset(self):

        self.reader.reset()
        self.writer.reset()

349
    def __getattr__(self, name,
350 351 352 353
                    getattr=getattr):

        """ Inherit all other methods from the underlying stream.
        """
354
        return getattr(self.stream, name)
355 356 357 358 359

###

class StreamRecoder:

360 361 362 363 364 365 366 367 368 369 370 371 372 373 374
    """ StreamRecoder instances provide a frontend - backend
        view of encoding data.

        They use the complete set of APIs returned by the
        codecs.lookup() function to implement their task.

        Data written to the stream is first decoded into an
        intermediate format (which is dependent on the given codec
        combination) and then written to the stream using an instance
        of the provided Writer class.

        In the other direction, data is read from the stream using a
        Reader instance and then return encoded data to the caller.

    """
Guido van Rossum's avatar
Guido van Rossum committed
375 376 377 378
    # Optional attributes set by the file wrappers below
    data_encoding = 'unknown'
    file_encoding = 'unknown'

379 380
    def __init__(self, stream, encode, decode, Reader, Writer,
                 errors='strict'):
381 382 383

        """ Creates a StreamRecoder instance which implements a two-way
            conversion: encode and decode work on the frontend (the
384
            input to .read() and output of .write()) while
385
            Reader and Writer work on the backend (reading and
386
            writing to the stream).
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

            You can use these objects to do transparent direct
            recodings from e.g. latin-1 to utf-8 and back.

            stream must be a file-like object.

            encode, decode must adhere to the Codec interface, Reader,
            Writer must be factory functions or classes providing the
            StreamReader, StreamWriter interface resp.

            encode and decode are needed for the frontend translation,
            Reader and Writer for the backend translation. Unicode is
            used as intermediate encoding.

            Error handling is done in the same way as defined for the
            StreamWriter/Readers.

        """
        self.stream = stream
        self.encode = encode
        self.decode = decode
        self.reader = Reader(stream, errors)
        self.writer = Writer(stream, errors)
        self.errors = errors

412
    def read(self, size=-1):
413 414 415 416 417

        data = self.reader.read(size)
        data, bytesencoded = self.encode(data, self.errors)
        return data

418
    def readline(self, size=None):
Guido van Rossum's avatar
Guido van Rossum committed
419 420 421 422 423 424 425 426

        if size is None:
            data = self.reader.readline()
        else:
            data = self.reader.readline(size)
        data, bytesencoded = self.encode(data, self.errors)
        return data

427
    def readlines(self, sizehint=None):
Guido van Rossum's avatar
Guido van Rossum committed
428 429 430 431 432 433 434 435

        if sizehint is None:
            data = self.reader.read()
        else:
            data = self.reader.read(sizehint)
        data, bytesencoded = self.encode(data, self.errors)
        return data.splitlines(1)

436
    def write(self, data):
437 438 439 440

        data, bytesdecoded = self.decode(data, self.errors)
        return self.writer.write(data)

441
    def writelines(self, list):
Guido van Rossum's avatar
Guido van Rossum committed
442 443 444 445

        data = ''.join(list)
        data, bytesdecoded = self.decode(data, self.errors)
        return self.writer.write(data)
446 447 448 449 450 451

    def reset(self):

        self.reader.reset()
        self.writer.reset()

452
    def __getattr__(self, name,
453 454 455 456
                    getattr=getattr):

        """ Inherit all other methods from the underlying stream.
        """
457
        return getattr(self.stream, name)
458 459 460

### Shortcuts

461
def open(filename, mode='rb', encoding=None, errors='strict', buffering=1):
462 463 464 465 466 467 468 469 470

    """ Open an encoded file using the given mode and return
        a wrapped version providing transparent encoding/decoding.

        Note: The wrapped version will only accept the object format
        defined by the codecs, i.e. Unicode objects for most builtin
        codecs. Output is also codec dependent and will usually by
        Unicode as well.

471 472 473 474 475
        Files are always opened in binary mode, even if no binary mode
        was specified. Thisis done to avoid data loss due to encodings
        using 8-bit values. The default file mode is 'rb' meaning to
        open the file in binary read mode.

476 477 478 479 480 481 482 483 484 485
        encoding specifies the encoding which is to be used for the
        the file.

        errors may be given to define the error handling. It defaults
        to 'strict' which causes ValueErrors to be raised in case an
        encoding error occurs.

        buffering has the same meaning as for the builtin open() API.
        It defaults to line buffered.

486 487 488 489 490
        The returned wrapped file object provides an extra attribute
        .encoding which allows querying the used encoding. This
        attribute is only available if an encoding was specified as
        parameter.

491 492 493 494 495 496 497 498
    """
    if encoding is not None and \
       'b' not in mode:
        # Force opening of the file in binary mode
        mode = mode + 'b'
    file = __builtin__.open(filename, mode, buffering)
    if encoding is None:
        return file
499
    (e, d, sr, sw) = lookup(encoding)
Guido van Rossum's avatar
Guido van Rossum committed
500 501 502 503
    srw = StreamReaderWriter(file, sr, sw, errors)
    # Add attributes to simplify introspection
    srw.encoding = encoding
    return srw
504

Guido van Rossum's avatar
Guido van Rossum committed
505
def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'):
506 507 508 509 510

    """ Return a wrapped version of file which provides transparent
        encoding translation.

        Strings written to the wrapped file are interpreted according
Guido van Rossum's avatar
Guido van Rossum committed
511 512 513 514 515 516
        to the given data_encoding and then written to the original
        file as string using file_encoding. The intermediate encoding
        will usually be Unicode but depends on the specified codecs.

        Strings are read from the file using file_encoding and then
        passed back to the caller as string using data_encoding.
517

Guido van Rossum's avatar
Guido van Rossum committed
518
        If file_encoding is not given, it defaults to data_encoding.
519 520 521 522 523

        errors may be given to define the error handling. It defaults
        to 'strict' which causes ValueErrors to be raised in case an
        encoding error occurs.

524 525 526 527 528
        The returned wrapped file object provides two extra attributes
        .data_encoding and .file_encoding which reflect the given
        parameters of the same name. The attributes can be used for
        introspection by Python programs.

529
    """
Guido van Rossum's avatar
Guido van Rossum committed
530 531 532 533 534
    if file_encoding is None:
        file_encoding = data_encoding
    encode, decode = lookup(data_encoding)[:2]
    Reader, Writer = lookup(file_encoding)[2:]
    sr = StreamRecoder(file,
535
                       encode, decode, Reader, Writer,
Guido van Rossum's avatar
Guido van Rossum committed
536 537 538 539 540
                       errors)
    # Add attributes to simplify introspection
    sr.data_encoding = data_encoding
    sr.file_encoding = file_encoding
    return sr
541

542 543 544 545 546 547 548 549
### Helpers for charmap-based codecs

def make_identity_dict(rng):

    """ make_identity_dict(rng) -> dict

        Return a dictionary where elements of the rng sequence are
        mapped to themselves.
Tim Peters's avatar
Tim Peters committed
550

551 552 553 554 555 556
    """
    res = {}
    for i in rng:
        res[i]=i
    return res

557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
def make_encoding_map(decoding_map):

    """ Creates an encoding map from a decoding map.

        If a target mapping in the decoding map occurrs multiple
        times, then that target is mapped to None (undefined mapping),
        causing an exception when encountered by the charmap codec
        during translation.

        One example where this happens is cp875.py which decodes
        multiple character to \u001a.

    """
    m = {}
    for k,v in decoding_map.items():
        if not m.has_key(v):
            m[v] = k
        else:
            m[v] = None
    return m
Tim Peters's avatar
Tim Peters committed
577

578
### Tests
579

580 581 582
if __name__ == '__main__':

    import sys
583

Guido van Rossum's avatar
Guido van Rossum committed
584 585
    # Make stdout translate Latin-1 output into UTF-8 output
    sys.stdout = EncodedFile(sys.stdout, 'latin-1', 'utf-8')
586

Guido van Rossum's avatar
Guido van Rossum committed
587 588
    # Have stdin translate Latin-1 input into UTF-8 input
    sys.stdin = EncodedFile(sys.stdin, 'utf-8', 'latin-1')